2013-11-01: 00:00:38 contrapumpkin 00:00:45 Or perhaps just ntrapumpkin 00:01:36 oerjan: I think bignums would be easier if you don't use any fyte beginning with 1. You'd just do stuff in base 376 or whatever. 00:04:30 -!- Phantom_Hoover has joined. 00:05:21 Argh! PDFs that are only viewable online :-( No way to download. 00:05:24 Here: http://issuu.com/adpware/docs/mc069/MC069.pdf 00:06:02 -!- shikhin_ has joined. 00:08:42 -!- Taneb has quit (Read error: Operation timed out). 00:08:59 -!- Taneb has joined. 00:09:31 -!- shikhin has quit (Ping timeout: 272 seconds). 00:11:44 Hmm 00:12:09 I'm not sure how Rel forms a category 00:12:50 -!- Phantom__Hoover has joined. 00:12:51 With relation composition. 00:12:56 -!- Phantom__Hoover has quit (Changing host). 00:12:56 -!- Phantom__Hoover has joined. 00:13:28 -!- Phantom_Hoover has quit (Ping timeout: 268 seconds). 00:13:33 I like how they call the category where the objects are sets and the arrows are relations Rel, but for some reason the category where the objects are sets and the arrows are functions is called Set. 00:14:06 Oooh 00:14:19 shachaf, would you rather they called it Fun? 00:14:28 is there any actual reason for category names to be truncated to three characters. 00:14:29 That name would be more fun. 00:14:49 Bike, because mathematical notation is traditionally terse? 00:14:49 better than the one character the rest of math uses, i guess 00:14:49 Bike: yes, there's a deep categorical reason but you just don't know enough to understand it 00:15:12 aw :( 00:16:09 i don't either :'( 00:16:14 Also, do any of you have a particularly compelling reason I should not read "Categories, Types and Structures: An Introduction to Category Theory for the Working Computer Scientist" by Andrea Asperti and Giuseppe Longo 00:16:40 -!- Sgeo has joined. 00:16:48 i seriously don't get why people complain about this, mathematical variable names are symbolic shorthands 00:16:53 CTaSaItCTftWCS is kind of a shitty initialism? 00:17:09 Phantom__Hoover: same reason i complain about one letter variable names in a program? 00:17:31 Taneb: why that book 00:17:37 writing out full words makes expressions significantly harder to read 00:17:43 shachaf, because it had a nice blue cover 00:17:51 Bike, it's almost like they're different fields with different needs or something 00:18:17 sounds like you haven't been paying attention to the univalent revoluuuuuution 00:21:01 i suspect you just made that up 00:21:12 no some other people made it up 00:21:16 Bike is just playing along 00:24:06 Taneb: did you purchase it or something 00:24:44 shachaf, no, I took it out from the library 00:24:45 * oerjan has this extremely vague memory of going to seminars mentioning univalent functions. 00:26:31 and quasiconformal mappings. 00:26:41 -!- Lymia has joined. 00:32:25 -!- Sprocklem has quit (Ping timeout: 272 seconds). 00:32:37 It is kind of interesting how variables in math usually have short names and variables in programming usually have long names. 00:33:12 -!- Phantom__Hoover has quit (Ping timeout: 268 seconds). 00:33:19 It's explained by some degree, I think, by the fact that mathematical expressions are almost always embedded in prose, whereas programming statements usually are not. 00:35:11 There are exceptions, of course. "(a -> b -> c) -> (a -> b) -> a -> c" is probably easier to read than "(sharedArgumentType -> intermediateResultType -> finalResultType) -> (sharedArgumentType -> intermediateResultType) -> sharedArgumentType -> finalResultType". 00:35:12 also when you do math with your hand and a pen you want the variable names to be as short as possible 00:35:37 and you want "xy" to mean "x times y" or something, not "one identifier named with two letters" 00:35:51 whereas when you program you want people to understand what you're doing 00:36:08 * Taneb --> bed 00:36:11 -!- Taneb has quit (Quit: Leaving). 00:36:27 I also think lambda-calculus uses a lot more short variable names than imperative programming 00:36:42 which might be a consequence of variables being bounds or free etc. 00:36:58 that is, you know what a variable stands for because you know where it was defined 00:37:41 when you write int(f(x)dx) you don't need anyone to explain to you what x stands for, because it's bound to the integral 00:38:09 whereas in imperative programming if your program starts with "int x;" it's kinda hard to know what it is 00:39:10 nice "int" pun 00:39:22 UNINTENDED 00:41:31 UNINDENTED 00:41:59 balls 00:42:08 NINTENDUD 00:42:24 Oh no, dropped an E. 00:48:18 -!- Phantom__Hoover has joined. 00:51:23 yeah, short arbitrary names are good when they are so general that nothing concrete can apply 00:51:45 and a lot of the intro Haskell stuff is like that 00:51:50 -!- tswett_ has quit (Quit: Page closed). 00:52:08 which probably sets up an unreasonable bias towards short names 00:53:20 -!- yorick has quit (Remote host closed the connection). 01:05:21 -!- KingOfKarlsruhe has quit (Quit: ChatZilla 0.9.90.1 [Firefox 24.0/20130910160258]). 01:35:41 -!- Phantom__Hoover has quit (Ping timeout: 265 seconds). 01:41:01 -!- augur has quit (Remote host closed the connection). 01:41:37 -!- augur has joined. 01:42:14 -!- Koen_ has quit (Quit: The struct held his beloved integer in his strong, protecting arms, his eyes like sapphire orbs staring into her own. "W-will you... Will you union me?"). 01:46:25 -!- augur has quit (Ping timeout: 272 seconds). 01:51:05 -!- Sprocklem has joined. 02:08:14 -!- ^v has joined. 02:10:57 * Sgeo suddenly wants to try Microsoft Bob 02:11:33 I think I used software that used a Bob-like interface 02:11:38 Greeting Workshop 02:11:40 I miss it 02:12:18 http://www.danielsays.com/daniel-says-images/dlcc/microsoft-bob/bob-lives/bob-in-ms-greetings-workshop-10.gif 02:12:22 http://www.danielsays.com/ms-bob-16-bob-lives.html 02:13:46 -!- conehead has quit (Quit: Computer has gone to sleep.). 02:14:52 -!- ^v has quit (Read error: Connection reset by peer). 02:15:16 -!- ^v has joined. 02:18:20 -!- augur has joined. 02:21:30 I used Bob!!! 02:21:31 bitd 02:24:36 we had... hm, not Microsoft Plus!, but some other thing 02:25:32 i guess it was just one of the things you get with a Gateway 2000 computer 02:25:40 I also borrowed a bunch of these from the library: http://en.wikipedia.org/wiki/List_of_video_games_from_The_Magic_School_Bus 02:36:46 -!- FreeFull_ has joined. 02:38:52 -!- FreeFull has quit (Ping timeout: 264 seconds). 02:46:39 -!- shikhin_ has quit (Ping timeout: 246 seconds). 02:54:40 -!- Uguubee111119 has quit (Quit: Uguubee111119). 02:59:46 -!- Uguubee111119 has joined. 03:29:20 Sgeo: oh yeah those animated characters were built into the operating system and there was an API for them 03:29:26 I used them a bit from Visual Basic 03:30:11 `addquote Sgeo: oh yeah those animated characters were built into the operating system and there was an API for them 03:30:15 1125) Sgeo: oh yeah those animated characters were built into the operating system and there was an API for them 03:30:18 this is so Windows it hurts 03:30:35 Microsoft Agent is how I got into Creatures 03:31:01 (I was interested in 'agent', stumbled upon some site that collected... stuff that just happened to use the word, and C3/DS uses the term 'agent') 03:31:15 and ofc it makes Wine harder to write because now it has to provide animated paperclip APIs, just in case 03:31:37 Also, there was some chat program where you'd chat via Microsoft Agent. You'd download people's friends list to chat with them 03:31:55 I would send a command that put the agents to sleep, which stopped them from talking 03:31:58 Kind of trollish really 03:33:18 well I mean "operating system" here in a sense that maps to "Debian" or "GNOME" and not like "Linux kernel" 03:33:31 probably it's a DLL and that DLL might work unmodified in WINE 03:33:50 kmc: Windows devs use the term "kernel" to include many of the important libraries too 03:33:58 Sgeo: wow that's even weirder than Comic Chat 03:34:00 at least the libc equivalents 03:35:55 I FOUND IT 03:35:56 I think 03:35:57 http://thecyberbuddy.com/ 03:36:04 The FAQ certainly sounds like the chat system I remember 03:36:12 http://thecyberbuddy.com/Page7.html#QQ19 03:36:31 ais523\unfoog: That's courtesy of a pair of legacy issues. 03:36:43 First, kernel.dll was the closest to the kernel on Win16 there was. 03:36:49 I think I was banned from one of the main chatbots on there 03:36:51 A long time ago 03:36:58 Second, kernel32.dll is the only documented kernel entry point. 03:37:40 i will not be your "cyber buddy" 03:38:08 i will. ;) 03:38:18 i like how late 90s / early 00s Microsoft just did not give a fuck about using the correct names for anything 03:38:29 or actually implementing the standards they claimed to implement, etc 03:38:31 Bike: hot 03:40:20 @ask mnoqy i think this calls for a self portrait of Sgeo 03:40:21 Consider it noted. 03:40:26 pikhq: pretty much everything in Windows is somehow caused by legacy issues 03:40:35 except the frequent changes to their recommendations for UI toolkits 03:40:40 which are mostly just inexplicable 03:45:31 kmc: should i see Carrie (musical) this weekend 03:46:38 don't know anything about that 03:48:06 isn't that what i pay you for :'( 03:49:12 is it 03:49:24 http://wereverinmylaptop.tumblr.com/post/56728391141/snakes-guido-mocafico 03:49:25 snakes 03:50:54 are you a snake 03:51:22 don't think so 03:56:43 hard to know for sure 03:57:02 listen to snake hisses and check if you're turned on 03:57:08 of course, you may just be an asexual snake 03:57:14 or i could be a human with a snake fetish 03:57:17 that doesn't work in our furry age 03:57:23 more like scaly 03:57:26 webscale? 03:57:32 i'm not saying there aren't false positives or negatives here!! 03:57:33 spider / snake slash fiction 03:57:44 Bike: please rephrase in terms of "Type I" and "Type II" errors 03:57:58 that terminology is no better 03:58:09 webscale porn, sounds darnmyinnerdictionaryturnedoffagai 03:58:10 n 03:58:53 are off-by-one errors type I or type II 03:59:08 kmc: you were kind of snaky last time i saw 03:59:19 o 03:59:37 you had things snakes have like eyes and a tongue 03:59:39 'COMBINING SNAKE BELOW' (U+1DC2) what 03:59:41 what else do snakes have 03:59:56 `unicode 'COMBINING SNAKE BELOW' 03:59:58 Unknown character. 03:59:59 k᷂m᷂c᷂ 04:00:09 i may have already forgotten how this program works :( 04:00:32 Bike: rule (1): if you want _any_ kind of quoting, use `run. 04:00:33 did you know chrome has an ed emulation mode 04:00:40 type a command in the address bar and press ^E 04:00:44 `run python -c 'print u"hi\u1dc2".encode("utf-8")' 04:00:46 hi᷂ 04:00:53 very hi 04:00:56 so snake 04:00:58 wow 04:01:29 `run unicode 'COMBINING SNAKE BELOW' 04:01:30 ​᷂ 04:01:33 cool this program from 1987 is called "PATH" so i will never find it, ever 04:01:49 `man 1 rule 04:01:51 man: can't open the manpath configuration file /etc/manpath.config 04:02:03 I'm not sure what I expected 04:02:08 but that is more sensible than what I expected 04:02:36 this is silly 04:02:42 i have two cell phones next to each other 04:02:50 one of them vibrated, which turned the screen on in the other one 04:02:56 hot 04:03:18 I'm saddened by the sudden realisation that cellphone slash fiction almost certainly already exists :( 04:03:20 shachaf: Please go on. I’m interested to hear about the whole Rube Goldberg device. 04:03:48 ion: insert coin 04:04:59 ion: did you learn any exciting category things since last time 04:05:00 forbidden love between an iphone and an htc one 04:05:59 forbidden love is allowed in here 04:07:28 good to know 04:07:39 kmc: ok do you think Distributive and Representable should both exist "hard to decide" 04:07:50 shachaf: Not yet. I haven’t been very productive for a while. 04:08:20 class Distributive g where distribute :: Functor f => f (g a) -> g (f a) 04:08:30 cool, this chaos paper uses the unit bits/week 04:09:20 er, Functor g => Distributive g 04:09:24 IO String -> [IO Char] 04:09:53 class Distributive g => g where type Key g :: *; to :: (Key g -> a) -> g a; from :: g a -> Key g -> a 04:10:12 er, Distributive g => Representable g 04:10:46 Representable is for a functor G where G a ~~ T -> a for some T 04:11:00 e.g. Pair a ~~ Bool -> a 04:11:23 Distributive ends up having instances for all the same types but it has less power 04:11:28 so does it deserve to exist 04:11:46 i gotta know 04:11:55 Are there useful Distributive instances without useful Representable instances? 04:12:22 is there a kind-level Representable instance between Distributive and Representable 04:12:56 Bike: is that supposed to make sense or should i just stop trying to figure it out 04:13:14 ion: I think every type which is an instance of Distributive is also an instance of Representable. 04:13:34 Doesn’t sound like a too useful separation then. 04:13:46 I'm not sure. 04:14:05 Does it give you less power in a useful way? If you make a function which is generic over Distributive or something? 04:17:01 If there’s a combined instance, can you not still write that function? 04:19:01 copumpkin: is this you a billion years in the future?? http://mathoverflow.net/users/342/sixwingedseraph 04:19:16 ion: Combined instance? 04:20:02 Like Applicative combines Apply and Pointed? Or what would the alternative have been? 04:20:23 I'm not sure what you mean. 04:20:30 Me neither. 04:21:44 From what i understood, you pointed out two classes with a dependency between them and said every instance of either one is an instance of another. So i thought you were thinking of combining the classes. 04:22:20 Oh. Yes. Combining them into Representable. 04:22:41 Since you can write Distributive easily with to and from. 04:29:39 -!- Sprocklem has quit (Ping timeout: 253 seconds). 04:46:00 -!- Uguubee111119 has quit (Quit: Uguubee111119). 04:49:02 -!- Uguubee111119 has joined. 04:53:24 -!- nooodl has quit (Quit: Ik ga weg). 05:07:00 -!- Bike has quit (Ping timeout: 268 seconds). 05:10:26 -!- Bike has joined. 05:11:04 " writing out full words makes expressions significantly harder to read" but category names are not used in expressions much 05:11:26 that's probably why they are truncated _so little_ 05:11:49 but still truncated? 05:14:48 " It is kind of interesting how variables in math usually have short names and variables in programming usually have long names." <<< i've always figured this is because you need so many names in programming, while in math you often need just a few vectors. the things that are nonstandard but you need to remember for the whole of the article are usually definitions 05:14:55 and definitions are often just an english word 05:15:12 "We call such a sequence \emph{asstastic}." 05:15:38 hi oklofok 05:16:04 what was that question about homotopy or something 05:16:09 i don't remember 05:17:42 asstastic prime 05:19:22 shachaf: um i don't recall there being a question 05:19:36 i don't know why i said "vectors" 05:20:31 «The noun ‘Pegasus’ itself could then be treated as derivative, and identified after all with a description: ‘the thing that is-Pegasus’, ‘the thing that pegasizes’.» 05:21:42 i personally find one symbol variables annoying, because they are so annoying to look up when you don't remember what they mean (sometimes you basically have to start over). 05:22:03 a longer word you could just search for 05:22:43 if i had a working symbol search that could separate mathmode from textmode, i don't think there would be any problem 05:22:44 i guess that ties into the whole 'predates computers' thing. 05:25:47 lol some guy from the czech republic solved my geocaching mystery (which is in finnish) 05:27:31 nice 05:31:24 oklofok: relatedly, there's the rule in programming that a variable's name length should be proportional to its scope 05:34:51 -!- augur has quit (Remote host closed the connection). 05:36:57 and that's why JavaBeanFactoryVisitorFactory is global 05:37:37 now I want more universal scope variables 05:37:41 like in Network Headache 05:38:10 (CLC-INTERCAL's implementation of something similar is more interesting; each process has its own set of variables, but you can steal variables from other processes) 05:38:23 (stealing filehandles is a particularly nice simple way to set up a simple telnet-a-like) 05:38:46 kmc: i think that would be a good rule for math too 05:38:50 also for everything 05:39:17 trees would have magnificent names 05:39:54 we can rename "Cyprinodon salinus salinus" to "i jy" 05:40:04 what about for people 05:41:09 -!- Uguubee111119 has quit (Read error: Connection reset by peer). 05:41:28 you get a long name when you're born, and a letter drops each year 05:41:38 when you run out of name, you are murdered. 05:41:41 lol. 05:42:11 I thought it'd be based on scope 05:42:15 actually, it is to some extent 05:42:23 close family and the like refer to you with shorter names 05:42:25 what's the scope of a man 05:42:39 and you can use shorter nicks in smaller communities 05:42:56 counterpoint, i am known by all and sundry as "bike" 05:43:05 that's another way to think about it, but it's not what i'd consider the direct analog of scope 05:43:07 countercounterpoint, i don't know what 'sundry' means 05:43:41 says something intelligent about minimum description length 05:43:45 oklofok: well, the scope of a variable is the region of the program from which it's accessible/mentionable/nameable 05:43:45 but there are some languages/cultures where more familiar names are diminutives with extra letters 05:44:02 "Consisting of a haphazard assortment of different kinds; miscellaneous." what a weird word 05:44:31 so I guess the scope of a person is either the number of people who have heard of them, the number of people who can describe them, or the number of people who could reasonably expect to be able to just look up their number, phone them up, and talk to them 05:45:45 i think a kid's voice is described as "sundry" in south park in the episode where cartman wants to become the... something of the school in place of wendy 05:46:28 and i didn't know what it means back then, and i just always remember that episode when i hear it, but not the actual meaning 05:46:41 maybe i've always heard wrong 05:46:49 but yeah they ruined my life 05:46:50 i've only seen it in the dead phrase 'various and sundry'. 05:47:32 which is apparently a hella pleonasm 05:47:38 i seemed to recall you're from the us, and tried to whois you 05:47:43 but i accidentally joined you. 05:47:50 ##bike used to exist 05:47:57 somebody joined it to ask about bikes once 05:48:03 :D 05:48:12 makes sense i guess 05:48:17 i of course do not endorse ##bike, as indicated by the name 05:48:21 i've been on #unicycling so why not 05:48:33 (i have a unicycle) 05:48:39 i am a unicycle 05:48:42 i tried to link them to a channel about biking but i couldn't find one. 05:48:52 sundried raisins 05:48:59 yeah 05:49:12 sundry sundried raisins 05:49:17 kind of niche compared to php i guess 05:49:32 wait you were already talking about that word 05:49:39 what a waste 05:49:54 okay gtg byes 05:50:08 kmc: 22:11 http://www.jwz.org/images/lzamexm.gif -- mri of a banana. That's trippy. 05:51:04 now i can never eat bananas again. 05:51:06 -!- ^v has quit (Quit: Ping timeout: 1337 seconds). 05:51:18 great, i don't remember if bananas are fruits or what. 05:51:41 i mean, have you seen a banana tree? that shit is weird. 05:51:54 22:47 nwf: banana flower, not banana fruit 05:52:00 Bike: p. sure bananas don't grow on trees 05:52:11 of course they're not fruits, why would fruit wear pajamas 05:52:22 i have seen many banana trees in my time 05:52:33 oerjan: sounds pretty fruity to me 05:52:37 they grow on things that are like trees but not but also are because 'tree' isn't a real category anyway 05:52:59 have a music http://www.youtube.com/watch?v=cnai_KrK4Ko 05:53:04 well they don't have a trunk 05:53:11 which is the main requirement to be a tree 05:53:16 for example elephants and cars are trees 05:53:22 yeah 05:53:25 but not banana plants 05:53:36 anyway mainly i was wondering if the banana had xylem and shit in it. 05:54:45 shachaf: omg 05:55:06 help 05:55:09 MRI of a sharkbanana 05:56:22 -!- Uguubee111119 has joined. 05:56:54 `welcome Uguubee111119 05:56:56 Uguubee111119: Welcome to the international hub for esoteric programming language design and deployment! For more information, check out our wiki: http://esolangs.org/wiki/Main_Page. (For the other kind of esoterica, try #esoteric on irc.dal.net.) 05:57:44 `run sed -i 's#http://esolangs.org/wiki/Main_Page##' wisdom/welcome 05:57:48 No output. 05:58:29 `relcome Uguubee111119 05:58:32 ​Uguubee111119: Welcome to the international hub for esoteric programming language design and deployment! For more information, check out our wiki: . (For the other kind of esoterica, try #esoteric on irc.dal.net.) 05:58:44 http://1.bp.blogspot.com/-e3MjWHdNTkE/UlKV0MgMDEI/AAAAAAAABiQ/Z7CxO0-Q3dE/s1600/Charleysayswww-scarfolk-blogspot-com.jpg some good stuff on jwz today 05:59:50 http://3.bp.blogspot.com/-dq27_3O7T38/UkgoTj0YEfI/AAAAAAAABh0/3i25ms1TQrU/s1600/porn3www-scarfolk-blogspot-com.jpg long lost educational porn films 06:31:59 -!- oerjan has quit (Quit: Nite). 06:48:38 -!- augur has joined. 06:48:49 -!- Uguubee111119 has quit (Quit: Uguubee111119). 06:49:04 -!- augur has quit (Read error: Connection reset by peer). 06:49:13 -!- augur has joined. 06:51:06 -!- Uguubee111119 has joined. 07:02:29 also i lost 07:03:40 lost sharkbananas? 07:04:58 lost enthusiasm? 07:06:44 no- 07:07:05 @google what did kmc lose 07:07:09 http://www.hindustantimes.com/india-news/kolkata/kmc-set-to-lose-crores-on-puja-ad-tax/article1-1131980.aspx 07:07:09 Title: KMC set to lose crores on Puja ad tax - Hindustan Times 07:10:16 -!- asie has joined. 07:10:31 you know what's a weird looking function? the half iterate of sine. 07:10:55 What's that? 07:11:04 what about the half iteratee 07:11:05 the function f such that f.f = sine. 07:11:43 Oh. 07:12:15 well, i guess the weird part is mostly that as you keep taking half iterates it looks more and more like a triangle wave. 07:13:00 Can you generalize this to real numbers? 07:14:19 yeah. here, there's an exact solution for an easier one. the t-th iterate of \x -> x/(1-x) is just \x -> x/(1-x*t). 07:18:34 :t (*) 07:18:35 Ambiguous occurrence `*' 07:18:35 It could refer to either `L.*', 07:18:35 defined at /home/lambdabot/.lambdabot/State/L.hs:149:4 07:18:43 > 4 * 5 07:18:44 Ambiguous occurrence `*' 07:18:44 It could refer to either `L.*', defined at L.hs:1... 07:18:48 cool 07:18:50 -!- ais523\unfoog has quit. 07:20:22 Bike what did you do 07:20:28 > 4 L.* 5 07:20:32 *Exception: L.hs:150:1-11: Non-exhaustive patterns in function * 07:20:35 Bike...... 07:20:43 i didn't do it, honest! 07:21:00 i did " @let boring t x = x/(1-x*t)" in privmsg and it said the ambiguous occurence thing. 07:22:10 wow, i was going to try to mess with it but like... 07:22:12 > boring 1 10 07:22:16 -1.1111111111111112 07:22:19 > boring 1/2 10 07:22:20 Could not deduce (GHC.Num.Num (GHC.Integer.Type.Integer -> a -> a)) 07:22:20 aris... 07:22:23 thambdabot?? 07:23:11 @undefine 07:23:12 Undefined. 07:23:13 hth 07:23:38 rip :( 07:24:06 rip L.* 07:24:20 > 4 * 5 07:24:22 20 07:24:30 wait, so i did that somehow? 07:24:33 what happen. 07:25:43 ...does "boring 1/2 10" parse as "(boring 1)/(2 10)"? or something? 07:25:53 > (*) 1/2 10 07:25:55 Could not deduce (GHC.Num.Num (GHC.Integer.Type.Integer -> a -> a)) 07:25:55 aris... 07:26:01 > (*) (1/2) 10 07:26:02 5.0 07:28:13 Yes. 07:28:28 Function application is sticker than any operator. 07:32:17 stickier 07:33:49 so how'd the L.* thing happen. 07:35:39 Someone did @let x * y = ...? 07:35:46 00:20 :t (L.*) 07:35:46 00:20 (Eq a, Eq a1, Num a, Num a1, Num a2) => a -> a1 -> a2 07:36:06 Sounds like some 2*2=5 prank or something. 07:37:11 go and tell the king that the sky is falling in but it's not 08:24:07 -!- Uguubee111119 has quit (Read error: Connection reset by peer). 08:35:09 -!- carado has joined. 08:38:28 -!- sebbu has quit (Ping timeout: 240 seconds). 08:39:07 -!- Uguubee111119 has joined. 08:46:56 -!- sebbu has joined. 08:47:35 -!- sebbu has quit (Changing host). 08:47:36 -!- sebbu has joined. 08:50:43 -!- esowiki has joined. 08:50:47 -!- esowiki has joined. 08:50:48 -!- esowiki has joined. 08:51:20 -!- esowiki has joined. 08:51:24 -!- esowiki has joined. 08:51:25 -!- esowiki has joined. 08:51:54 -!- esowiki has joined. 08:51:58 -!- esowiki has joined. 08:51:59 -!- esowiki has joined. 08:52:34 -!- esowiki has joined. 08:52:38 -!- esowiki has joined. 08:52:39 -!- esowiki has joined. 08:53:13 -!- esowiki has joined. 08:53:18 -!- esowiki has joined. 08:53:18 -!- esowiki has joined. 08:53:54 -!- esowiki has joined. 08:53:58 -!- esowiki has joined. 08:53:59 -!- esowiki has joined. 08:54:40 -!- esowiki has joined. 08:54:44 -!- esowiki has joined. 08:54:44 -!- esowiki has joined. 08:55:23 -!- esowiki has joined. 08:55:27 -!- esowiki has joined. 08:55:27 -!- esowiki has joined. 08:56:01 -!- esowiki has joined. 08:56:05 -!- esowiki has joined. 08:56:05 -!- esowiki has joined. 08:56:57 -!- esowiki has joined. 08:57:02 -!- esowiki has joined. 08:57:02 -!- esowiki has joined. 08:57:34 -!- esowiki has joined. 08:57:38 -!- esowiki has joined. 08:57:38 -!- esowiki has joined. 08:58:21 -!- esowiki has joined. 08:58:25 -!- esowiki has joined. 08:58:25 -!- esowiki has joined. 08:58:58 -!- esowiki has joined. 08:58:59 -!- glogbot has joined. 08:59:02 -!- esowiki has joined. 08:59:02 -!- esowiki has joined. 08:59:09 -!- ais523_ has joined. 08:59:33 -!- ais523_ has changed nick to ais523_\unfoog. 09:09:54 -!- Koen_ has joined. 09:10:42 -!- Koen_ has quit (Read error: Connection reset by peer). 09:10:56 -!- Koen_ has joined. 09:11:16 http://sprunge.us/VGTK that's just ridiculous. 09:15:39 -!- carado has quit (Ping timeout: 252 seconds). 09:26:22 -!- shikhin has joined. 09:29:11 -!- FreeFull_ has changed nick to FreeFull. 09:29:35 -!- ais523_\unfoog has quit (Ping timeout: 250 seconds). 09:31:46 -!- ais523_\unfoog has joined. 09:53:15 -!- Slereahphone has joined. 09:56:14 -!- asie has quit (Quit: My MacBook Pro has gone to sleep. ZZZzzz...). 09:59:25 -!- ais523_\unfoog has quit. 10:05:16 -!- MindlessDrone has joined. 10:05:18 Is a butt Turingcomplete 10:11:35 -!- asie has joined. 10:20:01 -!- Phantom_Hoover has joined. 10:23:04 -!- atslash has joined. 10:28:27 -!- KingOfKarlsruhe has joined. 10:42:52 -!- Koen_ has quit (Quit: Koen_). 10:43:55 -!- shikhin_ has joined. 10:46:24 -!- shikhin has quit (Ping timeout: 252 seconds). 10:49:49 -!- MindlessDrone has quit (Ping timeout: 272 seconds). 10:59:19 -!- Taneb has joined. 11:03:17 -!- ski_ has changed nick to ski. 11:03:34 -!- MindlessDrone has joined. 11:29:33 -!- Phantom_Hoover has quit (Ping timeout: 246 seconds). 11:33:00 -!- Sgeo has quit (Read error: Connection reset by peer). 11:40:36 -!- shikhin__ has joined. 11:41:01 -!- shikhin_ has quit (Read error: Operation timed out). 11:42:28 -!- shikhin_ has joined. 11:42:57 -!- shikhin_ has changed nick to shikhin. 11:43:28 -!- nooodl has joined. 11:45:34 -!- shikhin__ has quit (Ping timeout: 273 seconds). 11:46:14 -!- Phantom_Hoover has joined. 12:04:37 -!- boily has joined. 12:08:38 -!- metasepia has joined. 12:09:53 -!- yorick has joined. 12:15:40 -!- Slereahphone has quit (Quit: Colloquy for iPhone - http://colloquy.mobi). 12:17:35 -!- Phantom_Hoover has quit (Ping timeout: 260 seconds). 12:38:51 good étuve morning! 12:39:33 wisdom question: since when are we angle-quoting the URL to the Main Page in the welcomes? 12:40:03 `relcome nooodl 12:40:07 ​nooodl: Welcome to the international hub for esoteric programming language design and deployment! For more information, check out our wiki: . (For the other kind of esoterica, try #esoteric on irc.dal.net.) 12:40:19 huh 12:40:46 shachaf: why did you anglify the URL? 12:41:20 Anglifying URLs.. does that make shachaf an angler? 12:42:07 angler, as in https://en.wikipedia.org/wiki/Lophius_piscatorius? 12:50:59 boily: I assume because some clients/terminals/etc. otherwise interpret the trailing '.' as part of the URL. 12:51:42 logical. 12:52:53 http://esolangs.org/wiki/Main_Page%2E works for me 12:56:01 I guess that's a workaround. 12:58:38 well what i'm saying is the extra . doesn't seem to matter either way 13:00:43 welcome to #esoteric, where everything is off-topic and the points don't matter! 13:02:14 the points are... pointless 13:07:10 -!- asie has quit (Quit: My MacBook Pro has gone to sleep. ZZZzzz...). 13:07:32 -!- asie has joined. 13:13:03 -!- carado has joined. 13:30:57 -!- Uguubee111119 has quit (Quit: Uguubee111119). 13:33:23 -!- Uguubee111119 has joined. 13:36:00 -!- mrhmouse has joined. 13:44:48 -!- nisstyre has quit (Ping timeout: 240 seconds). 13:48:03 `unidecode ÐĐ 13:48:05 ​[U+00D0 LATIN CAPITAL LETTER ETH] [U+0110 LATIN CAPITAL LETTER D WITH STROKE] 13:48:19 Are we still doing this? :P 13:48:39 `unicode MULTIOCULAR O 13:48:41 Unknown character. 13:48:46 we're always doing this. 13:48:56 `unicode CYRILLIC LETTER MULTIOCULAR O 13:48:57 ​ꙮ 13:49:37 mrhmouse: I was wikiwalking, and they mentioned capital eth and stroken-d being very similar. I had to verify their claim. 13:49:51 (you know, when you really have to know a useless fact.) 13:51:11 I can relate. 14:05:34 -!- nisstyre has joined. 14:26:19 I've just installed the SainT Atari ST emulator. It even simulates the noise of the disk drive! 14:32:04 -!- conehead has joined. 14:43:09 -!- atslash has quit (Quit: This computer has gone to sleep). 14:54:21 quinthellopia! 14:54:33 quintopia: you may receive the cookies today and/or Monday. 14:59:13 (meanwhile Up North, it's raining sideways.) 15:22:13 -!- smilerext has joined. 15:22:17 -!- smilerext has quit (Read error: Connection reset by peer). 15:40:52 -!- Sprocklem has joined. 15:51:45 -!- asie has quit (Quit: My MacBook Pro has gone to sleep. ZZZzzz...). 15:56:45 -!- tertu has joined. 16:02:06 -!- ^v has joined. 16:03:41 -!- Sprocklem has quit (Ping timeout: 272 seconds). 16:04:37 -!- carado has quit (Read error: No route to host). 16:05:08 -!- carado has joined. 16:06:21 -!- asie has joined. 16:08:24 -!- ter2 has joined. 16:09:28 -!- tertu3 has joined. 16:10:01 -!- tertu has quit (Ping timeout: 272 seconds). 16:13:26 -!- ter2 has quit (Ping timeout: 240 seconds). 16:19:27 It's raining man... 16:20:21 and I might have a heart attack 16:25:55 -!- oerjan has joined. 16:29:36 :t (*) 16:29:38 Num a => a -> a -> a 16:30:43 you know what's a weird looking function? the half iterate of sine. <-- i am not sure that half iterates are particularly uniquely defined. 16:31:09 when they exist at all. 16:31:53 i suppose having a continuous one at all is an accomplishment, which a triangle wave certainly is. 16:34:53 -!- augur has quit (Read error: Connection reset by peer). 16:36:18 -!- augur has joined. 16:36:49 :t let 2*2=5 in (*) 16:36:50 (Eq a, Eq a1, Num a, Num a1, Num a2) => a -> a1 -> a2 16:37:14 shachaf: perfect type match! 16:43:23 I have seen * be redefined locally to be some arbitrary operator 16:43:35 (meanwhile Up North, it's raining sideways.) <-- have you checked that the landscape hasn't just tilted? 16:43:54 FreeFull: completely legal 16:44:17 Yeah 16:44:31 Just a bit weird to see * not be multiplication 16:44:33 @src on 16:44:33 (*) `on` f = \x y -> f x * f y 16:44:42 -!- tertu3 has quit (Ping timeout: 240 seconds). 16:44:57 I think this is where I saw it 16:46:12 @ask boily (meanwhile Up North, it's raining sideways.) <-- have you checked that the landscape hasn't just tilted? 16:46:12 Consider it noted. 16:50:55 oerjan: in general they're not. half-iterates of identity are a pretty good example 16:51:08 -!- tertu3 has joined. 16:52:49 oerjan: strong gusts around 40 kt. 16:52:57 > [sin x | x <- [-1,-0.8 .. 1::Float]] 16:52:59 [-0.84147096,-0.7173561,-0.5646425,-0.38941836,-0.19866937,-5.9604645e-8,0.... 16:53:22 > [sin x | x <- [-0.2,0 .. 1::Float]] 16:53:23 too good for map, huh 16:53:23 [-0.19866933,0.0,0.19866933,0.38941833,0.5646425,0.71735615,0.8414711] 16:53:25 hu 16:53:32 > [0..1::Float] 16:53:33 [0.0,1.0] 16:53:44 it doesn't always go well. 16:53:46 > [0.5 .. 1::Float] 16:53:48 [0.5,1.5] 16:53:51 hm :( 16:53:53 i suppose having a constantly shrinking range might force things? 16:53:55 ~eval map sin [-1,-0.8..1 :: Float] 16:53:55 > [0..0.1..1.0] 16:53:56 [-0.84147096,-0.7173561,-0.5646425,-0.38941836,-0.19866937,-5.9604645e-8,0.19866925,0.38941827,0.56464237,0.717356,0.8414709] 16:53:57 :1:8: parse error on input `..' 16:54:01 ugh. 16:54:05 > [0,0.1..1.0] 16:54:06 > [0.1,0.5 .. 1::Float] 16:54:06 [0.0,0.1,0.2,0.30000000000000004,0.4000000000000001,0.5000000000000001,0.60... 16:54:07 [0.1,0.5,0.9] 16:54:09 I wonder if people would get mad if the powers that be just removed Enum from floats? 16:54:25 > succ (1:: Float) 16:54:27 2.0 16:54:30 ha 16:54:43 oerjan: strong gusts around 40 kt. <-- kilotons? are you sure this is normal wind? 16:54:48 I wonder if that would involve fixing more code than, say, the Num/Eq/Ord change that happened before, or the Functor/Applicative/Monad change that will happen? 16:54:57 the powers that be achieved enough positive karma by constraining Monads to Applicatives, so I feel they can do whatever they want with Enums. 16:55:08 ion: ↑ 16:55:32 boily: That would also be positive karma as far as i’m concerned. 16:55:43 ion: indeed. 16:55:45 -!- tertu3 has quit (Ping timeout: 246 seconds). 16:56:00 I wonder if people would get mad if the powers that be just removed 16:56:06 oerjan: apparently kn is the preferable abbreviation to “knots”, but kt is accepted. 16:56:08 argh 16:56:17 boily: ic 16:56:18 (insofar knots are socially correct.) 16:56:33 boily: depends, are you at sea? 16:56:33 kt is kilotonne. :-P 16:56:46 kt is what killed the dinosaurs. 16:57:06 kt is a telecom in South Korea. 16:58:26 I wonder if people would get mad if the powers that be just removed Enum from floats? <-- well it _might_ be nice if they actually supported the standard(s) backwards compatibly as written, which they already don't do and are planning to do even less. 16:59:22 Microsoft started using kt instead of kB in Finnish (because byte is “tavu” – the Finnish grammar doesn’t let allow doing that, though, it would need to be “kt.” to be grammatically correct because it’s an abbreviation and not an official unit symbol) and the whole IT media followed. 16:59:59 Also, kt is already a SI derived unit symbol. 17:00:20 um tonne isn't official is it? 17:01:24 Bike: thus the kt boundary? 17:01:25 I actually don’t know for sure, but it’s a hell of a lot more “official” than kilotavu. 17:01:52 oerjan: “It is a non-SI unit accepted for use with SI.” 17:02:07 -!- tertu3 has joined. 17:02:19 `relcome tertu3 17:02:20 -!- Bike has quit (Ping timeout: 268 seconds). 17:02:22 ​tertu3: Welcome to the international hub for esoteric programming language design and deployment! For more information, check out our wiki: . (For the other kind of esoterica, try #esoteric on irc.dal.net.) 17:02:26 boily: was just about to paste that 17:04:27 -!- shikhin has quit (Read error: Connection reset by peer). 17:05:58 -!- Phantom_Hoover has joined. 17:06:14 -!- tertu3 has quit (Ping timeout: 240 seconds). 17:07:38 -!- shikhin has joined. 17:09:30 -!- Bike has joined. 17:10:02 Bike: maybe you can tell me whether naturality and continuity are related somehow 17:10:34 naturality sounds like some kind of hippie food brand. 17:11:43 continuity doesn't, so probably they're totally unrelated. 17:12:11 continuity could totally be "some kind of hippie food brand" imo 17:12:16 continuity is like the opposite, they want you to keep buying the old poisonous food 17:12:50 oerjan: well "KT" just stands for "Cretaceous-Tertiary". presumably German is involved here. 17:14:31 i'm sure we discussed that not many weeks ago. 17:14:54 does 'we' include me 17:14:57 also discovered it's now officially changed to cretaceous-paleogene. 17:15:04 Bike: that i don't know. 17:15:23 paleogene also sounds like hippie food. category theorists, get on this. 17:16:52 well they cannot change it to c now that it is paleogene. 17:17:44 wp says K-Pg 17:18:43 * oerjan thinks he should drop the next pun he's thinking of. 17:20:51 -!- pong has joined. 17:21:05 I fail to understand the link between hippie brands and categories. 17:21:15 -!- pong has changed nick to Guest90179. 17:21:43 boily: it's a natural transformation 17:21:55 -!- ^v has quit (Disconnected by services). 17:21:57 -!- Guest90179 has changed nick to ^v. 17:22:58 * boily facepalms... “hook, line, sinker...” 17:26:35 -!- derpherp has joined. 17:27:04 `seen mnoqy 17:27:08 2013-10-29 00:06:06: i don't think i'd be able to explain it though 17:28:42 `seen HackEgo 17:28:47 2013-11-01 17:27:08: 2013-10-29 00:06:06: i don't think i'd be able to explain it though 17:28:49 `seen HackEgo 17:28:53 2013-11-01 17:28:47: 2013-11-01 17:27:08: 2013-10-29 00:06:06: i don't think i'd be able to explain it though 17:29:06 `seen HackEgo 17:29:11 2013-11-01 17:28:53: 2013-11-01 17:28:47: 2013-11-01 17:27:08: 2013-10-29 00:06:06: i don't think i'd be able to explain it though 17:29:30 I need to find a way to include django in that... 17:30:15 well, that's easy. 17:30:18 `quote django 17:30:20 265) django is named after a person? thought it would be a giraffe or something \ 310) `quote django ​352) django is named after a person? thought it would be a giraffe or something thankfully only one \ 311) `quote django ​352) django is named a 17:30:25 `seen HackEgo 17:30:29 2013-11-01 17:30:20: 265) django is named after a person? thought it would be a giraffe or something \ 310) `quote django ​352) django is named after a person? thought it would be a giraffe or something thankfully only one \ 311) `quote django ​ 17:30:32 `seen HackEgo 17:30:34 etc. 17:30:36 2013-11-01 17:30:29: 2013-11-01 17:30:20: 265) django is named after a person? thought it would be a giraffe or something \ 310) `quote django ​352) django is named after a person? thought it would be a giraffe or something thankfully only one \ 311) sadly, it doesn't make for a good quote :( 17:31:28 most things don't 17:33:22 -!- augur has quit (Remote host closed the connection). 17:33:55 -!- derpherp has quit (Quit: Ping timeout: 1337 seconds). 17:33:57 -!- augur has joined. 17:38:57 -!- augur has quit (Ping timeout: 272 seconds). 17:40:02 -!- Sprocklem has joined. 17:40:35 -!- Taneb has quit (Quit: Leaving). 17:44:33 -!- shikhin has quit (Read error: Operation timed out). 17:49:59 -!- oerjan has quit (Quit: leaving). 17:50:00 -!- metasepia has quit (Read error: Connection reset by peer). 17:50:05 -!- boily has quit (Read error: Connection reset by peer). 17:50:32 -!- Phantom__Hoover has joined. 17:50:45 -!- boily has joined. 17:51:45 -!- metasepia has joined. 17:52:15 -!- Phantom_Hoover has quit (Ping timeout: 272 seconds). 17:58:19 -!- shikhin has joined. 17:59:28 -!- shikhin has quit (Read error: Connection reset by peer). 18:00:53 -!- Bike has quit (Quit: Reconnecting). 18:01:08 -!- Bike has joined. 18:03:20 -!- shikhin has joined. 18:04:03 -!- lmt has joined. 18:04:48 xD 18:07:06 /\\\\//\\\\\\///\\\\/\\\\\\\\//\\/\\/\\\\//\\/\\\\//\\/\\\\\\/\\\\\\///\\//\\\\/\\//\\/\\//////\\/\\\\\\/\\\\\\//\\//\\\\/\\//\\\\\\///\\\\//\\//\\/\\/\\\\//\\\\\\///\\\\/\\\\\\\\//\\/\\/\\\\//\\/\\\\//\\/\\\\\\/\\\\\\///\\//\\\\/\\//\\/\\//////\\/\\\\\\/\\\\\\//\\//\\\\/\\//\\\\\\///\\\\//\\//\\/\\/\\\\//\\\\\\///\\\\/\\\\\\\\//\\/\\/\\\\//\\/\\\\//\\/\\\\\\/\\\\\\///\\//\\\\/\\//\\/\\//////\\/\\\\\\/\\\\\\//\\//\\\\/\\//\\\\\\///\\\\//\\//\\/\\/\\\\//\\\ 18:07:58 //\\\\//\\\\\\? 18:08:33 -!- augur has joined. 18:08:42 boily: // \ \\/ \\/ // 18:09:50 lmt: /. 18:10:04 \\?? 18:10:26 * lmt \/\/\/\/\/\/\/\/\ 18:12:06 * boily ////es lmt with a \\//\//\\\ 18:12:22 * lmt \\\\\\\ 18:12:28 :\ 18:15:39 it only was a small \\//\//\\\. it won't leave no bruise (well, after a week at least) 18:17:26 I wasn't interested at all in the conversation until that comment. 18:18:07 vice versa for me 18:18:11 i lost all interest 18:20:00 -!- JesseH has quit (Quit: Leaving). 18:20:51 Are we making labyrinths on the C64 again? 18:23:43 -!- tertu3 has joined. 18:26:11 -!- ^v has quit (Read error: Connection reset by peer). 18:26:35 -!- ^v has joined. 18:30:01 -!- atslash has joined. 18:30:21 -!- tertu3 has changed nick to tertu. 18:31:13 -!- shikhin has changed nick to hikhin. 18:32:17 -!- hikhin has changed nick to shikhin. 18:33:57 -!- conehead has quit (Quit: Computer has gone to sleep.). 18:36:57 -!- Phantom__Hoover has quit (Ping timeout: 272 seconds). 18:39:42 -!- shikhin has changed nick to hvidhin. 18:40:29 -!- hvidhin has changed nick to kickhin. 18:46:17 -!- kickhin has changed nick to shikhin. 18:47:15 FreeFull: like http://10print.org/ ? 18:47:30 "labyrinth" is a much cooler word than "maze", it's true 18:48:17 This book takes a single line of code—the extremely concise BASIC program for the Commodore 64 inscribed in the title 18:48:20 wow 18:48:28 these guys clearly haven't heard of golfscript 18:49:54 ah 50MB PDF? 18:49:57 are you serious 18:50:05 that almost certainly will crash adobe pdf reader 18:50:17 you've never seen a pdf that big before? 18:50:23 i mean, it's shit, but not uncommon. 18:52:14 aren't there alternatives to the Adobe on Windows? 18:54:05 pdf.js! 18:54:47 i guess it's not actually that much shorter in golfscript? 18:55:11 my naive approach is 1{2 rand"/""\\"if.print}do 18:55:11 -!- Phantom__Hoover has joined. 18:55:23 -1 18:56:31 not much of a maze without branches 18:57:26 tromp_: the characters themselves form a branched maze though 18:57:41 if you print them nicely like on 10print.org 19:04:31 -!- Bike has quit (Ping timeout: 260 seconds). 19:08:31 seriously though 19:08:42 can someone tell me the right golfscript program to do that? 19:09:01 i'm missing something with golfscript's conversion between strings and integers 19:18:04 golfscript looks strangely J-like... 19:19:28 kmc: More accurate than maze too for this 19:19:37 Since you don't get any branching paths 19:19:53 You don't get dead-ends either 19:21:23 -!- Bike has joined. 19:27:56 -!- boily has quit (Quit: Poulet!). 19:28:01 -!- metasepia has quit (Remote host closed the connection). 19:42:57 -!- ^v has quit (Quit: Ping timeout: 1337 seconds). 19:44:27 -!- Bike has quit (Ping timeout: 272 seconds). 19:47:04 -!- Bike has joined. 19:47:41 -!- Sprocklem has quit (Ping timeout: 245 seconds). 19:51:10 Has anyone here got access to the McCarthy files at Stanford? 19:55:29 -!- MindlessDrone has quit (Quit: MindlessDrone). 19:58:04 -!- augur has quit (Remote host closed the connection). 19:58:37 -!- augur has joined. 20:02:27 -!- carado has quit (Ping timeout: 252 seconds). 20:03:05 -!- augur has quit (Ping timeout: 272 seconds). 20:06:29 -!- Sprocklem has joined. 20:12:12 golfscript is J on speed 20:13:41 J on E 20:13:56 which reminds me to continue working on my Mahou project 20:15:12 Why is there no webprogramming language 20:15:14 I mean 20:15:21 It would be about time for one 20:15:26 what? 20:15:30 webprogramming? 20:15:34 yeah 20:15:39 websites'n'stuff 20:15:43 You mean like JavaScript, or am I missing something? 20:15:48 Or like to generate HTML? 20:15:51 server side 20:15:58 You can do JavaScript server side. 20:16:55 I'm looking for a language really made for that purpose 20:16:57 no like PHP 20:17:01 *not like PHP 20:17:09 PHP is merely a C-Api embedded in Apache 20:17:10 You're talking about generating pages? 20:17:14 Yes 20:17:17 and Database 20:17:25 something like haskell's route 20:17:27 JavaScript is a good candidate, actually >> 20:17:28 Oh 20:17:29 Haha. 20:17:30 url dispatching 20:17:31 Templates 20:17:34 and stuff 20:17:47 JavaScript still winning here. 20:17:53 Or Elm, for view code. 20:17:58 If you like Haskell. 20:18:16 i'm confused, you are just looking for a server side web language in general? cause uh a lot of those exist 20:18:27 what is the context of "Why is there no webprogramming language" 20:18:29 Yeah, there are tons.. 20:18:38 every major language has a web framework or six 20:18:46 I don't want a web framework 20:18:47 Python has like two dozen 20:18:51 Web frameworks do exists 20:18:53 in dozens 20:19:13 So.. you want a language that does nothing but web? 20:19:35 ideally some kind of language with very neat modelling support 20:20:08 what would be the point of that? the things you need to do to build websites fit well into most general purpose languages 20:20:57 they fit well 20:21:00 but not perfectly neat 20:21:02 As I'm understanding it, you want: view generation (templates), data storage and access, URL routing, and "neat modelling support" (whatever that is)...? 20:21:19 mroman: that should be fixed with better libraries rather than fundamentally new languages 20:21:22 imo 20:21:26 but also, there are web specific languages e.g. http://opalang.org/ 20:21:26 ^ 20:21:47 Django is really close to what I'd expect 20:21:51 Interesting link kmc! 20:22:02 it essentially generates the whole database etc from python classes 20:22:07 which is pretty neat 20:22:27 So you want a code-first approach - plenty of frameworks offer that :P 20:23:37 well 20:23:37 Really, it sounds like you can get what you want by combining several existing libraries.. 20:23:43 I actually want modell first :) 20:24:01 python 20:24:04 pythonpython 20:24:06 pythonpythonpython 20:24:07 pythonpythonpythonpython 20:24:37 I don't want to write
  • {{foo.title}} etc 20:24:40 say python again, say python again, i dare you, i double dare you motherfucker, say python one more goddamn time 20:24:42 that's already too low-level 20:25:18 esentially 20:25:23 oh no you didn't 20:25:28 I want a WYSIWYG editor to create Websitse 20:25:30 just say "too low-level" in #esoteric 20:25:37 webshits 20:25:54 webscheiße 20:25:58 ++ 20:26:05 fun fact: the swedish word for python means disgusting 20:26:07 or a lanugage that suitable is close enough to wysiwy 20:26:16 (and a kind of snake) 20:26:18 what you see is what you 20:26:22 well 20:26:26 y brain just has shutten down 20:26:35 all you touch and all you see is all your life will ever be 20:26:41 -!- augur has joined. 20:26:43 and strangely my shoulder still hurts when I breathe 20:26:58 try breathing with your lungs instead 20:27:04 wise guy. 20:27:07 :D 20:27:11 :D D: 20:27:18 or try not breathing, if it hurts it must be bad for you 20:27:42 YEah... 20:27:55 I'm gonna go back to watching some Jason Bourne Movie 20:28:37 -!- augur_ has joined. 20:28:38 -!- augur has quit (Read error: Connection reset by peer). 20:29:11 mroman: How's li a href: foo.d, foo.title 20:29:35 or if you write a helper method, just listAnchorFor foo 20:35:18 mroman: you're right that there are improvements to be made in HTML template languages 20:35:24 and those languages can be embedded within programming languages 20:35:36 but there's no reason the encompassing programming language needs to be redesigned from scratch 20:35:48 e.g. Yesod has some fancy template languages for HTML and CSS and JS, but it's embedded within Haskell 20:35:55 html embedded in javascript embedded in javascript 20:36:07 07:19:56 fucking art imo 07:24:10 -!- carado has joined. 07:24:11 shachaf: what do you think about making out 07:25:31 "JavaScript event handling is single-threaded, so handlers are executed sequentially." is this like, actually true 07:25:35 yes 07:25:52 -!- Sprocklem has quit (Ping timeout: 240 seconds). 07:26:04 in existing browser engines all JavaScript (including iframes) runs in a single thread and alternates with layout work on the same thread 07:26:11 (all for a single tab, I mean) 07:26:12 which is terrible 07:26:16 well i mean, is it required 07:26:20 and that's something we're trying to fix with Servo 07:26:29 but there are limits to what we can do because it's part of the platform spec 07:26:30 Bike: yes 07:26:36 huh. why? 07:26:55 Bike: JS doesn't have any kind of thread synchronization primitives built in, so if you allowed concurrent event handlers, there would be no way to make them race-free 07:27:22 but anyway there's 15 years worth of legacy javascript code which assumes no concurrency 07:27:25 ah, hm... still that seems like a limitation to me. maybe i'm being naive 07:27:44 you can now do concurrency in a limited sense, with web workers, but they can't touch the DOM or handle events 07:28:09 "Please recall that HTML-tag attribute names are case-insensitive, so oNcLiCk will work same as onClick or onclick" a lot of this advice seems like stuff i should be pretty skeptical of. just like every other time i've learned a programming language :/ 07:30:41 kmc: no particular opinions 07:31:30 ok 07:38:24 * kmc usually doesn't have musical accompanyment, though 07:38:55 -!- oerjan has quit (Quit: Adagio). 07:44:40 browsers are so amazing. it almost seems like a shame to have them so internet-oriented 07:45:30 imo browsers should be oriented to writing browsers 07:45:41 "the primary activity browser writers care about" 07:45:50 imo write your own browser in HTML/CSS/JS 07:46:03 market it as 'web compatible' 07:46:18 also really? 07:46:31 yeah. (as an example of what not to do) 07:46:36 my six language polyglot is more reasonable than that 07:46:36 oh 07:46:43 well, ok 07:46:50 of course as soon as i looked at a less reputable tutorial's source it had exactly that -_- 07:48:21 Bike: wasn't that the only backwards compatible way of doing it 07:48:38 (i think maybe it needs to be on three lines or something, i don't know 07:48:52 yeah i didn't feel like doing that. 07:52:12 -!- Uguubee1111110 has quit (Quit: Uguubee1111110). 07:54:37 -!- Uguubee1111110 has joined. 08:13:51 Bike: isn't it case insensitive in HTML4 08:13:57 but not in HTML5? 08:14:11 or it's case insensitive in some browsers but not in others 08:15:12 i'd liketo say it's the former but it's probably the latter too somehow 08:15:37 hm 08:15:41 google research is useless 08:15:45 looks like html is case insensitive but xml is not. 08:15:54 everyone seems to have a different opinion about the case sensitivity of attributes 08:16:01 Bike: Ah. Yes 08:16:05 well i was looking at w3, so. 08:16:07 XHtml 08:16:10 ok 08:16:18 anyway i was starting from 'oNcLiCk is a really shitty name' 08:16:22 onClick works in HTML4 but not in XHtml 08:17:06 ONcLICK 08:17:23 is called when the user licks the touchscreen 08:17:35 (if any) 08:30:43 Is there some simple way to wire something to composite video signals to make them appear in grayscale? 08:42:45 -!- zzo38 has quit (Remote host closed the connection). 09:19:34 Web Workers and Canvas Proxies. 09:26:47 are there approaches on how to compile low-level language to CIL/CLR? 09:26:51 or Java Byte Code 09:27:08 specifically the whole pointery stuff 09:28:51 One honking byte[] and pointers as indices to that. 09:29:06 (That's what Emscripten does, to compile C to JS.) 09:29:32 yeah 09:29:41 but that probably does not work for function pointers? 09:30:53 although 09:31:00 you can probably special treat function pointers 09:31:18 unless you use (void*) 09:31:29 which would loose the information that it was a function pointer 09:31:48 Speaking from a C perspective, if they're still indices to something, it wouldn't really matter. 09:32:05 You'd need to convert it back to a function pointer for calling, at which point it'd get back that information. 09:33:22 well yes 09:33:34 but you can't call javascript functions through an adress? 09:33:54 You'd have a table of functions. Function pointers would be indices to that. 09:34:08 ah 09:34:11 ok 09:34:12 I see 09:35:11 same for variables probably 09:35:24 i.e the address of a local variable 09:35:25 like 09:35:33 Anyway, if you compiled to a single Java bytecode method, you could use actual opcode offsets -- but that approach has at least two major problems: there's a 64k size limit for a function, and the bytecode verifier is going to insist on all kinds of things hard to satisfy. (I looked at this a bit for a Befunge-to-JVM thing where I wanted to use the native JVM stack as the Befunge stack.) 09:36:17 yeah 09:36:32 my source language requires you to be able to goto from one function in another 09:36:35 and stuff like that 09:36:43 which is not really easy to translate to other languages :) 09:36:51 because most don't allow that. 09:36:56 not even C 09:37:51 inline asm? 09:39:15 It might "work" for the single-JVM-method case (since you can do local jumps there), assuming you can satisfy the verifier, which might be tricky. (It e.g. insists that all possible paths to reach a particular instruction must provably have the same stack effect in terms of number of pushes and pops, which really didn't work for the Befunge case.) 09:40:01 (And then there's that size limit.) 09:40:49 befunge to jvm sounds like an awesome idea 09:41:30 I kind of abandoned the idea when it turned out the native stack wouldn't work, because using a separate object for the stack sounded so lame. 09:46:35 well 09:46:45 I could disect stuff into functions 09:46:54 i.e a label would be another function 09:47:08 like int main() { .... foo: ... } would split into 09:47:15 two functions 09:55:07 Assuming arbitrary jumps, then you'll need some kind of a thing to handle the otherwise-growing stack. 09:55:17 (There's no tail calls in the JVM.) 09:56:41 There's always trampolining, of course. 10:07:53 -!- MindlessDrone has joined. 10:20:33 well 10:20:43 jumping to another function is a really bad idea anyway 10:21:18 the only reason it is even possible is because I did not want to introduce scoping rules 10:21:23 so labels are globally visible 10:21:43 but I just might say jumping into another function is copmiler dependant behaviour 10:23:16 because that's what it actually is anyway 10:27:59 -!- Frooxius has quit (Read error: Connection reset by peer). 10:31:36 -!- Frooxius has joined. 10:34:52 -!- Taneb has joined. 10:45:34 -!- Taneb has quit (Quit: Page closed). 11:10:45 -!- Froox has joined. 11:13:18 -!- Froox has quit (Client Quit). 11:13:24 -!- Frooxius has quit (Quit: ChatZilla 0.9.90-rdmsoft [XULRunner 1.9.0.17/2009122204]). 11:13:40 -!- Frooxius has joined. 11:20:27 -!- Koen_ has joined. 11:24:59 -!- Frooxius has quit (Quit: Leaving). 11:25:15 -!- Frooxius has joined. 11:29:58 -!- Frooxius has quit (Client Quit). 11:30:10 -!- Frooxius has joined. 11:33:57 -!- Jafet has joined. 11:37:11 -!- Jafet has quit (Changing host). 11:37:11 -!- Jafet has joined. 11:39:57 -!- yorick has joined. 11:41:16 -!- shikhin has joined. 11:45:41 -!- shikhin has quit (Ping timeout: 248 seconds). 12:04:14 hm 12:04:20 when exactly is extern needed for C functions 12:04:35 you can refer to C functions in other compilation units without extern 12:04:53 i.e -c foo.o ... -c foo1.o and just link it together 12:04:55 without using extern 12:11:45 It's the default for functions. 12:12:10 "If a declaration of an identifier for a function has no storage-class specifier, its linkage is determined exactly as if it were declared with the storage-class specifier extern." 12:12:39 You do need it for declarations of objects in header files, because otherwise those turn into definitions for each translation unit, and then you've got multiple copies and the linker will complain. 12:16:25 -!- nooodl has joined. 12:19:40 Oh, I didn't notice the question was specifically for functions. I guess "never", then, since having no storage class specifiers is entirely equivalent. 12:29:51 -!- Phantom_Hoover has joined. 12:40:08 fizzie: I'm also guessing "never" 12:40:25 but I'm not 100% sure there is an edgecase where extern is needed for functions too 12:40:29 *if 12:41:30 I don't think there were any qualifiers for the statement I quoted. 12:43:12 maybe shared objects? 12:45:14 ok 12:46:53 fizzie: wouldn't modifiability of fungespace be a bigger problem for a befunge-to-JVM compiler? 12:48:56 FireFly: Maybe, but that's a problem for a befunge-to-anything compiler and not for a befunge-to-JVM compiler in particular. 12:49:10 what's fungespace? 12:49:14 is that the code? 12:49:17 Yes. 12:49:17 Yes 12:49:18 or where the code is located 12:49:19 ah 12:49:20 ok 12:49:44 (It's possible I was thinking of writing an interpreter, anyway. I don't remember the details, just that I wanted JVM stack == befunge stack.) 12:50:10 can't you compile each instruction as a fixed block of code 12:50:14 and then replace those blocks 12:50:36 That's essentially a threaded-code interpreter. 12:50:39 i.e transfroming the 2D space into a 1D space 12:51:02 should be fairly possible 12:51:08 maybe a bit inefficient 12:51:17 mroman: and if you put after the end of a line? 12:51:52 h 12:52:53 Anyway, you can certainly JIT befunge. 12:53:20 It's just slightly tricky tracking what all needs to be invalidated when the fungespace changes. 12:54:05 (If you treat each instruction as a single block, so that they're easy to replace, you can't e.g. constant-fold across the blocks, which makes the whole act of "compiling" it a bit pointless.) 12:55:52 fungot: Do you have any self-modifying code in you at all, anyway? 12:55:52 fizzie: sarahbot, yow")" to make writing a bf interp 12:56:05 (Spoiler: not really, discounting things like ^reload.) 12:56:39 I have somewhere an ahead-of-time Befunge(-to-LLVM, I think) compiler that's complete enough to compile and run fungot. 12:56:39 fizzie: if they meant it seriously, though. ( foo 1) to have x in the second 12:57:13 (Doesn't do any tracking of fungespace modification.) 12:58:41 Though self-modification is not the only problem for static compilation. You can't necessarily tell the code flow in advance, either, if there's something like &&x in the code. 12:59:02 (That's "read two integers from standard input and set the IP delta to that vector".) 13:01:54 -!- shikhin has joined. 13:31:50 -!- ais523 has joined. 14:02:09 -!- tertu has joined. 14:09:49 so I'm trying to compile Chris Pressey's mascarpone interpreter in haskell, using ghc. the error message is " Could not find module `System' It is a member of the hidden package `haskell98-2.0.0.2'.". should I explicitely tell ghc how to include this System module? 14:10:14 -XHaskell98? 14:11:13 nope, doesn't work either 14:18:51 -!- tertu has quit (Read error: Connection reset by peer). 14:19:08 -!- tertu has joined. 14:28:51 -!- asie has quit (Quit: My MacBook Pro has gone to sleep. ZZZzzz...). 14:39:41 -!- Phantom__Hoover has joined. 14:43:03 -!- Phantom_Hoover has quit (Ping timeout: 245 seconds). 14:55:38 -!- Uguubee1111110 has quit (Read error: Connection reset by peer). 14:58:34 -!- Uguubee1111110 has joined. 14:59:24 -!- tertu has quit (Read error: Connection reset by peer). 14:59:42 -!- tertu has joined. 15:08:13 -!- Uguubee1111110 has quit (Quit: Uguubee1111110). 15:10:45 -!- Uguubee1111110 has joined. 15:33:51 -!- tertu has quit (Ping timeout: 260 seconds). 15:35:16 -!- zzo38 has joined. 15:43:36 -!- yorick has quit (Remote host closed the connection). 15:51:12 -!- Uguubee1111110 has quit (Read error: Connection reset by peer). 15:53:42 -!- Uguubee1111110 has joined. 15:59:23 -!- conehead has joined. 16:05:15 -!- KingOfKarlsruhe has joined. 16:09:06 elliott: the only common thread I can see in our latest spambot rash, apart from the content of their posts (which I can't block unless abusefilter starts working again), is that they all claim to be using IE6 16:09:09 can we just block IE6? :) 16:09:48 jesus, do people still use ie6 16:09:56 we'll lose the east asian market 16:09:59 -!- Yonkie has quit. 16:10:40 fizzie: who needs constant folding anyway 16:10:47 my compiler produces for 3 + 5 16:11:10 load32 r0, 3; push r0; load32 r0, 5; push r0; pop r1; pop r0; add r0, r0, r1; push r0; 16:11:13 :) 16:11:15 Bike: I don't know if the spambots are actually using IE6, or just pretending 16:11:23 based on the homogeneity of the user agent, I'd say it's faked 16:12:04 ais523: Then perhaps program it so that if the user agent string specifies IE6, it enables things that won't work if it isn't really IE6 16:12:31 zzo38: hmm, interesting, but also probably quite timeconsuming 16:12:59 mroman: What compiler is that? What programming language? 16:15:28 jesus, when did chrome become the top browser 16:17:49 zzo38: My pre-bachelor thesis is an developping an imaginary computer architecture 16:17:54 -an 16:18:00 and an emulator for that architecture 16:18:26 but I came to the point where I did not want to write a line of assembler code anymore 16:18:32 so I started writing a complire 16:18:39 for my simple language :) 16:18:49 http://mroman.ch/va/rlmmu_simple.html <- that language 16:18:51 And it looks like not a very good compiler 16:19:24 indeed 16:19:30 it's a working compiler 16:19:40 it produces code for a stack machine with two registers 16:19:48 which my architecture is totally not 16:19:55 my arch has 16 registers :) 16:20:07 -!- Slereahphone has joined. 16:20:39 Even for a machine with only two registers it looks like a bad code. 16:20:43 zzo38: Yes 16:20:54 But I don't have the time to write a sophisticated compiler and emulator 16:21:02 so one of them is just quick'n'dirty 16:21:06 Not having constant folding isn't the only problem. 16:21:07 it produces working code 16:21:11 that's good enough for me 16:21:14 zzo38: I know 16:21:21 it even produces push r0; pop r0; blocks 16:21:23 etc. 16:21:32 and push r0; pop r1; can be optimizied to mov r1, r0; 16:21:33 etc. 16:21:55 -!- ^v has joined. 16:22:06 zzo38: You are very welcome to write a better compiler 16:22:09 you can even target x86 16:22:10 :) 16:22:18 That's what I plan to do anyway 16:22:24 if semester's over 16:22:29 write an x86 codegen for it 16:37:55 -!- Phantom__Hoover has quit (Ping timeout: 272 seconds). 16:53:27 -!- Phantom__Hoover has joined. 16:53:29 -!- Phantom__Hoover has quit (Changing host). 16:53:29 -!- Phantom__Hoover has joined. 16:55:20 I wanted to make up some simple computer architecture which is mostly like other ones that GCC already support and can be programmed in a FPGA, and modified to the application in use 16:55:25 zzo38: Writing a gcc backend would have been too much work 16:56:05 mroman: Yes, I know that is why I wanted to make one up that GCC can already compile into 16:57:52 I was thinking of ARM2 but maybe there is something better 17:00:17 Many implementations seem to be optimized and might make it difficult to predict how many clock cycles some sequence of instructions requires. If removing such thing would make it too slow, one work-around is to add an instruction to wait until a number of clock cycles have passed since the previous marker. 17:07:11 ULESSTHANOREQUAL 17:07:13 ok 17:07:20 that sound's like a reasonable mnemonic 17:07:40 Such thing looks like long to me 17:07:47 yes 17:07:53 ADD foo, bar 17:07:57 ULESSTHANOREQUAL foo, bar 17:08:00 Verity uses <= for unsigned less-than-or-equal-to, +<= for the signed version 17:08:02 that just looks crazy as fuck 17:08:12 but then, its operators are made out of sequences of punctuation marks 17:08:49 Not bad, having a separate unsigned and signed operators, if you aren't specifying by the type like how C does. 17:09:16 zzo38: I decided separate signed and unsigned operators made more sense than separate signed and unsigned types 17:09:42 ais523: Ah, OK. What is that though? 17:10:08 zzo38: some operators like + and - use two's complement in Verity so it doesn't matter whether they're signed or unsigned 17:10:13 and it doesn't have division 17:10:26 Yes, that makes sense for + and - 17:10:32 what's verity? 17:10:37 for relational operators I have separate signed/unsigned values 17:10:49 mroman: mostly non-eso language I was paid to work on for my job 17:10:52 as in, I was paid to invent it 17:10:57 oh 17:10:57 ok 17:11:02 http://www.veritygos.org/ 17:11:12 I went for seperate signed/unsigned operators too 17:11:18 Why did you need to invent it? 17:11:21 since I don't have the type system 17:11:29 to distinguish it else 17:12:05 http://www.veritygos.org/documentation 17:12:17 too lazy for real html ;P? 17:12:22 zzo38: because there were no variants of Algol 60 specialised for reconfigurable hardware, oddly enough 17:12:29 mroman: I'm not responsible for the website 17:12:47 they asked for documentation in plaintext 17:12:53 I wrote it in markdown, on the basis that it looks much the same 17:12:58 -!- asie has joined. 17:13:10 IMO the only good use for markdown is to write markup in a way that looks like plaintext 17:13:13 but it's good at taht 17:13:15 *that 17:13:31 ais523: That is not bad, now you can load it in any program even if not having web browser, but you can also convert it to HTML if you prefer. 17:14:21 can you dumb it down for me 17:14:24 what's verity for? 17:14:41 a language that describes hardware? 17:14:58 or what do you mean by hardware synthesis? 17:15:32 mroman: it's a language designed to be similar to the sort of functional languages people normally use to program software, but it's restricted such that it compiles into hardware well 17:15:51 whereas most hardware development's done using languages like VHDL that are very unfamiliar 17:16:04 Ah, that seems like a proper reason to me. 17:16:41 (I still think that isn't the best way to program hardware, but it could be helpful if you want to write an emulator for the hardware, maybe) 17:18:02 There are a lot of other hardware programming languages too although I don't really think any of them are perfect so I tried to make up a new one, too 17:18:58 you mean like brainfuck and verilog? 17:19:01 what else is there? 17:19:29 Brainfuck isn't hardware programming language. There is Verilog, there is also VHDL, and several others (see Wikipedia), and I partially made up a documentation for my own. 17:19:51 well 17:19:59 let me grab me brainfuck 2 vhdl thingy 17:20:02 if I can still find it 17:20:07 *my 17:21:21 My own hardware programming language is http://zzo38computer.org/textfile/miscellaneous/hwpl.txt 17:21:36 There are still some things missing; if you know about hardware programming maybe you can help to fix it? 17:24:01 Well... I know VHDL 17:24:05 that's as much as there is :) 17:24:31 Do you know anything about designing it with discrete logic components? 17:24:32 -!- oerjan has joined. 17:24:51 I know some things about Verilog and find some things it has are not very good for hardware design 17:24:56 You mean like FlipFlops, XOR, AND Gates etc? 17:24:58 Latches? 17:25:03 Yes. 17:25:23 Yeah 17:25:36 -!- Slereahphone has quit (Ping timeout: 245 seconds). 17:26:16 That's what I'd actually expect from a VHDL/verilog programmer 17:26:26 that he knows how he could synthesize basic vhdl programm by hand 17:26:32 *programms 17:26:48 Do you understand this document of HWPL? 17:27:27 someone should make a prolog2vhdl compiler 17:27:43 -!- njm has changed nick to utopian. 17:28:10 zzo38: I haven't completely read it yet 17:28:14 but from fastly reading through it 17:28:22 looks understandable :) 17:28:34 Do you notice anything that might be wrong with it? 17:29:56 what do you understand under "running result"? 17:30:25 Can you be specific? 17:30:35 what does append do? 17:30:39 APPEND vec 17:31:06 In a function, the "running result" is initially an empty vector. 17:31:36 ah ok 17:32:30 I am not sure how I should make that more clear in the documentation. 17:33:45 Is there anything that could be improved, is missing, etc? 17:34:35 This HWPL is not like VHDL, right? 17:34:48 You don't program the hardware on the level like you do in VHDL? 17:34:55 Correct, it isn't VHDL or Verilog or whatever. 17:35:11 I don't actually know much of VHDL, but I know some things about Verilog. 17:35:20 So you build components and wire them together 17:35:26 and wait for raising edges etc 17:35:29 There are some similarities to Verilog but not quite. 17:35:30 *don't build 17:35:58 although you do have a DELAY function 17:36:11 In HWPL you would write what is connected to what and what registers are updated on rising edges and so on, or write macros that will create these things for you. 17:36:20 -!- Slereahphone has joined. 17:36:40 At runtime, the only type is a bit vector; other types only exist at compiletime. 17:36:59 That makes sense 17:37:32 FOR loops and stuff are executed at compile time; so are IF, LET, SPLIT, and so on. 17:37:54 (If you want run time conditions you need to use WHEN instead of IF.) 17:40:00 I assume DELAY is only for simulation? 17:40:56 Unlike in Verilog, no. A hardware compiler may also move things around so that things have higher or lower delays, or provide an error message or warning message if it cannot use the given delay. 17:41:44 I'd expect the hardware compiler to calculate timings etc 17:41:58 I.e you obviously can't clock stuff as high as you want :) 17:42:22 or your flipflops will get meta-stable :) 17:43:28 Well, yes, there is an inherent delay, but if the externally visible delay is shorter than the fastest clock speed (which might depend on the program) then it is OK anyways. 17:45:41 The DELAY function is provided if you want to make it slower or if you want to force certain hardware constraints such as in order to more accurately emulate other hardware, or possibly to avoid race conditions in a few cases. 17:45:42 TRIGGER only works for rising edges 17:45:44 not falling? 17:46:00 mroman: Yes. If you want falling, put ~ in front of the signal. 17:46:07 ah 17:46:11 so TRIGGER ~vec? 17:46:19 k. 17:46:30 Yes. 17:46:48 oh 17:46:52 I can use expressinos there 17:46:52 ok 17:47:34 Expressions are allowed in most places where you can have a vector. 17:48:16 Do I have to declare POWER and GROUND? 17:48:26 That's usually something you don't really worry about. 17:49:02 No, it is usually not necessary. 17:49:29 (Some compilers might not even support it.) 17:49:42 (It is provided in case it is necessary for your design.) 17:50:06 I have fixed that part of the documentation now. 17:51:11 (One reason it might be necessary is if you are declaring an expansion cartridge pinout and the power/ground have to be in certain positions.) 17:51:54 ah. ok 17:51:57 I se. 17:52:00 *see 17:52:24 maybe add a CASE statement? 17:52:48 like switch case 17:53:59 Maybe it might help, yes (currently there is a ROM CASE statement but not a macro CASE statement). 17:56:13 (It would conflict but maybe renaming the ROM CASE statement to something else might help?) 18:00:14 -!- ^v has quit (Read error: Connection reset by peer). 18:00:40 -!- ^v has joined. 18:01:49 IF in VHDL afaik is sequentiel 18:02:24 case probably not 18:02:47 or it does not matter at least 18:06:11 -!- oerjan has quit (Quit: leaving). 18:06:28 -!- utopian has changed nick to njm. 18:06:42 -!- Sprocklem has joined. 18:07:19 Well, HWPL has no such procedural blocks at run time like Verilog and VHDL have. 18:07:30 Everything runs in parallel. 18:07:49 (Macros are sequential, but they are expanded at compile time.) 18:08:43 so 18:09:09 -!- shikhin has quit (Read error: Operation timed out). 18:11:07 -!- Phantom__Hoover has quit (Ping timeout: 272 seconds). 18:14:45 Note that something like MODULE MAIN ZZZZ1001: NOOP; is a valid (but useless) HWPL program having eight I/O pins. 18:16:17 <^v> wolfmitchell wanted to make a language that would make slapping a dick on a keyboard valid 18:16:20 It always outputs 1001 on the low four pins. 18:16:28 <^v> i would wonder how this would work 18:16:35 <^v> was thinking something like path 18:16:35 ^v: I don't know how, either. 18:23:03 -!- shikhin has joined. 18:28:28 My dad just told me to become a doctor and said something about a shortage of competent doctors 18:28:44 -!- nisstyre has joined. 18:29:44 Doctor doctor or phd doctor 18:31:18 Medical doctor 18:32:19 http://img6.joyreactor.com/pics/post/comics-married-to-the-sea-auto-221896.jpeg 18:33:42 -!- pong has joined. 18:34:06 -!- pong has changed nick to Guest66796. 18:34:12 -!- shikhin has quit (Quit: Leaving). 18:34:27 -!- ^v has quit (Quit: Ping timeout: 1337 seconds). 18:34:32 -!- shikhin has joined. 18:35:44 Well, if most other doctors are less competent, and I don't pick up medical knowledge, I'm effectively trusting my life to incompetent people 18:35:56 Whereas if I become a doctor, I save lives possibly including my own 18:36:29 If you are competent, then yes. 18:37:35 I think my dad's assuming that I would be competent 18:37:37 Doctors cannot actually treat themselves 18:38:13 You'd see a lot more doctors smoking medicinal joints otherwise 18:38:32 c.c 18:39:10 It's also pretty hard for surgery 18:39:54 But you could look at your own charts, and at loves ones' charts, and see whether doctors are treating you and your loved ones correctly 18:41:04 Unless you are yourself incompetent 18:41:22 or become it 18:41:24 -!- sebbu has quit (Ping timeout: 252 seconds). 18:41:36 Doctors tend to worsen as they age 18:41:54 They lose touch with modern medical science 18:42:19 Does their handwriting get worse too? 18:43:14 I wonder if bad handwriting is something they pick up at med school 18:43:27 Med school has high volume classes 18:43:37 You have to take notes fast 18:43:45 I read somewhere that someone think everyone who writes too many things in one day will have bad handwriting 18:43:46 I think medicine involves a lot of tricky judgement calls; there's not an obvious right answer in every situation 18:44:08 and so second-guessing your doctor when you're emotionally close to the situation could do as much harm as good 18:44:37 not if you are a cold blooded sociopath 18:44:41 in most cases you can't just look at a chart and be like "hmm, yes, this doctor is an 8/10" 18:44:43 -!- sebbu has joined. 18:45:15 you should all read http://www.amazon.com/Better-A-Surgeons-Notes-Performance/dp/0312427654 18:45:24 -!- sebbu has quit (Changing host). 18:45:24 -!- sebbu has joined. 18:45:58 or not 18:47:12 burn 18:47:45 -!- Guest66796 has changed nick to ^v. 18:59:06 -!- shikhin_ has joined. 19:00:35 -!- Slereahphone has quit (Ping timeout: 260 seconds). 19:01:28 -!- shikhin has quit (Ping timeout: 240 seconds). 19:01:57 -!- Sprocklem has quit (Ping timeout: 248 seconds). 19:03:33 -!- shikhin_ has quit (Ping timeout: 248 seconds). 19:09:56 -!- Phantom__Hoover has joined. 19:14:41 -!- Slereahphone has joined. 19:21:41 -!- Slereahphone has quit (Ping timeout: 245 seconds). 19:23:15 -!- asie has quit (Quit: My MacBook Pro has gone to sleep. ZZZzzz...). 19:25:43 -!- asie has joined. 19:26:21 kmc: before or after The Illuminatus! Trilogy? 19:31:08 You interleave the words. 19:37:10 -!- Uguubee1111110 has quit (Read error: Connection reset by peer). 19:41:28 -!- Uguubee1111110 has joined. 19:43:36 -!- Koen_ has quit (Quit: Koen_). 19:47:52 -!- pong has joined. 19:48:29 -!- pong has changed nick to Guest12944. 19:50:47 -!- asie has quit (Quit: My MacBook Pro has gone to sleep. ZZZzzz...). 19:51:01 -!- ^v has quit (Ping timeout: 245 seconds). 19:57:04 -!- Uguubee1111110 has quit (Read error: Connection reset by peer). 19:57:54 -!- nisstyre has quit (Ping timeout: 246 seconds). 20:00:04 -!- nisstyre has joined. 20:04:03 -!- Guest12944 has quit (Ping timeout: 260 seconds). 20:05:09 -!- Uguubee1111110 has joined. 20:09:32 -!- MindlessDrone has quit (Quit: MindlessDrone). 20:10:52 -!- asie has joined. 20:12:47 -!- Phantom__Hoover has quit (Remote host closed the connection). 20:13:57 shachaf: after I expect 20:17:50 -!- Uguubee1111110 has quit (Quit: Uguubee1111110). 20:19:25 -!- Phantom_Hoover has joined. 20:22:27 -!- Uguubee1111110 has joined. 20:25:05 -!- Uguubee1111111 has joined. 20:25:15 -!- Uguubee1111111 has quit (Client Quit). 20:26:48 -!- Uguubee1111110 has quit (Ping timeout: 245 seconds). 20:31:06 -!- ^v has joined. 20:41:49 -!- JM563 has joined. 20:42:09 Hello 20:43:36 Some one in home? 20:43:58 -!- Sprocklem has joined. 20:44:20 Well...wellcome Sporcklem 20:44:20 `welcome JM563 20:44:25 JM563: Welcome to the international hub for esoteric programming language design and deployment! For more information, check out our wiki: . (For the other kind of esoterica, try #esoteric on irc.dal.net.) 20:44:33 Thanks Bike. 20:45:32 Any topic? 20:45:47 it's quiet 20:46:46 Well Bike, your soul is not quiet, do you have any topic on mine? 20:47:24 -!- Uguubee1111111 has joined. 20:48:48 -!- JM563 has quit (Quit: irc2go). 20:49:46 -!- JM372 has joined. 20:49:59 Sorry Bike, I am new. 20:51:51 Would you like the astrolgoy as topic? 20:52:17 astrology* 20:53:57 -!- carado has quit (Ping timeout: 252 seconds). 20:54:02 Sorry? What astrology? 20:54:06 Did you read the esolang wiki? 20:54:48 Stellar astrology, no tropical or sideral...Stellar astrology. 20:55:30 Which means what? 20:55:54 Okay...do you know tropical and sideral astrology? 20:55:55 I vaguely remember some kind of distincting between days 20:56:04 `welcome JM372 20:56:07 Yes I do know that. 20:56:07 JM372: Welcome to the international hub for esoteric programming language design and deployment! For more information, check out our wiki: . (For the other kind of esoterica, try #esoteric on irc.dal.net.) 20:56:13 Tnais Ais523 20:56:24 There's the day as in rotation of Earth, vs Sun being at the same point, due to the revolution around the sun 20:56:24 As far as I know tropical/sidereal just refers to how the zero longitude point is determined. 20:56:36 Or am I imaginign things? 20:56:42 But that's astronomy, not astrology 20:57:15 Almost posited a definition of 'astrology' that would count ST:TNG as astrology 20:57:28 Sgeo: Are you thinking of day vs sidereal day or something? 20:57:32 Okay Zzo...the Setellar astrology works withe the planets; and also, with some stars from the constellations. 20:57:34 zzo38: I think so 20:58:14 JM372: Which stars? I have Astrolog installde which can calculate the positions of some stars (it can also calculate the positions of all constellations, but not all stars they include) 20:58:35 And you say it works with the planets and stars, but in what way? That doesn't help. 20:59:17 Okay Zzo...www.astro.com can do so too...but the point is that you need to use in your personal astrology chart the principals stars. 20:59:35 So you can get one close idea about your complity astrological situation. 21:00:10 Waht is your ascending Zzo? 21:00:13 Astronomy: Related to the stars and is real. Astrology: Related to the stars and is fictional 21:00:16 >.> 21:00:52 JM372: I don't really do that kind of stuff I am not so superstitious, although I know a few things about it. To know my ascending I would have to know the time of my birth, and I never really tried to figure that out. 21:01:02 No Sego, no the Stellar Astrology...The Stellar astrology use the astronomic information too. 21:01:36 Okay Zzo....thanks for to be honest... 21:01:53 I do have the horoscope chart for the current date/time/location on my screen at this time, and the list of stars it can chart. 21:02:01 Can you name the stars? Maybe then I know what you mean. 21:02:42 Zzo...I will like to, but at least, I need your birt time and date to give your a clear example 21:02:57 birth* 21:03:13 Just use the current date and time. I don't know my birth time and do not want to give the date (anyways, if you want to know ascendant, location is important too). 21:04:01 But according with your honesty you should be Virgo ascendant. 21:05:11 OK you can assume that if you want; like I said I don't know my birth time. 21:05:13 Are you in USA or Ingland Zoo? Because you can get a copy of your birth certificate by Internet 21:05:28 England* 21:05:58 Actually I think I can find my birth certificate somewhere around here, and I can then calculate it. 21:06:13 It is okay Zzo...no problem.... 21:07:30 Oops I forgot to disable daylight saving time in this program, now I did. 21:07:33 -!- asie has quit (Quit: My MacBook Pro has gone to sleep. ZZZzzz...). 21:07:48 But like Sgeo said, we need to use the effects of the stars for to make a complity astrological chart. 21:08:23 I can easily include several stars in the chart in this program. Which stars do you mean, though? 21:08:54 -!- JM372 has quit (Read error: Connection reset by peer). 21:11:45 -!- JM383 has joined. 21:11:53 Sorry, but I was booted 21:11:59 (And I live in Canada) 21:12:11 I think I need a nickname for to work in 21:13:46 Okay Zoo, but you seems to be a person very honest, so it could means that your ascending sign in Virgo 21:14:12 Yes, I said we can make that assumption if you want to. How many degrees though? 21:14:31 Very strict person, but also honest. 21:15:09 a good man and thorough 21:15:20 (Make up a number arbitrarily if you don't know; if I am to set a time of day for this chart the degrees will also be needed) 21:15:21 The idea is to work with correct information Zzo...I can asumption what ever....but your birth time is very importan 21:15:35 Again, *I don't know*. 21:16:02 Use data for a fictional character if you have to! 21:16:24 It is okay Zzo...When you get so, we can talk more about your good personality. 21:16:53 `unicode DEGREE 21:16:55 Unknown character. 21:16:56 OK, I think I might be able to find my birth certificate around here somewhere. 21:16:58 `unicode DEGREE SYMBOL 21:16:59 Unknown character. 21:17:04 At least Zzo...do you know your solar sign? 21:17:10 I do not wish to reveal my personal information, although I can calculate the positions on computer. 21:17:17 -!- Taneb has joined. 21:17:34 `unicode DEGREE SIGN 21:17:36 JM383: Yes, I do know that, although I wish not to reveal it. (It isn't close to the edge of the sign enough that the time of day would be needed.) 21:17:36 ​° 21:17:39 there we go 21:17:45 -!- yorick has joined. 21:18:22 If you tell me what stars to plot, though, I can tell the computer to plot those stars. 21:18:25 It is okay Zzo...I understand your point. 21:19:54 Zzo... in www.astro.com, they are usign some stars in the charts....but try to use the most important stars of the 12 constelacions...At least, the most shiny stars. 21:20:17 `unicode LOWERCASE THETA 21:20:19 Unknown character. 21:20:20 There are 88 constellations. 21:20:23 `unicode LOWERCASE GREEK LETTER THETA 21:20:25 Unknown character. 21:20:29 this thing needs fuzzy matching 21:20:42 `unicode GREEK SMALL LETTER THETA 21:20:44 Beside Zzo...use the sideral astrology, it works much beter than the tropical one. 21:20:45 ​θ 21:20:49 (There are the 12 constellations that the signs are named after, and one more which is also on the ecliptic though) 21:20:58 Zzo...the zodical constelations. 21:21:08 JM383: OK. What reference should be used for ayanamsha then? 21:21:26 (This program defaults to Fagan-Bradley) 21:21:48 -!- asie has joined. 21:22:08 Okay Fagan-Bradley? 21:22:26 OK, well, I have it on the screen in sidereal Fagan-Bradley mode. 21:23:19 -!- tertu has joined. 21:23:21 So, if in your progam you can use all the stars, tray at least to use the more brights and try to see what star is close to your sun. 21:23:53 OK. 21:24:00 to your sun and in conjuntion with the house or sector I. 21:25:11 So, this will gives to you one close idea about your physical personality (Ascendant) and spritual personality (Solar sign) 21:27:38 I have used the fourteen brightest stars (according to a list in Wikipedia). 21:28:50 (in average apparent magnitude) 21:29:18 It is okay...14 stras are good... 21:29:50 None of them are in conjunction with the Sun. 21:29:55 More than 14 will be much better, but it is better 21:30:10 -!- asie has quit (Quit: My MacBook Pro has gone to sleep. ZZZzzz...). 21:30:13 And in your solar sign? 21:30:35 -!- Oj742 has joined. 21:31:11 Just one is in my solar sign (using Fagan-Bradley). 21:31:49 Okay...but do you know the characteristic of this star? 21:32:23 What is a "characteristic" of a star? 21:33:59 Okay...for ejemple...Antares in Scorpio...this mean that you need to work in this encarnation with your inner personality, making deep and big changes or....you will be a bit violent 21:34:00 -!- Frooxius has quit (Quit: *bubbles away*). 21:34:05 Can you get the idea? 21:34:13 -!- Frooxius has joined. 21:34:56 Kind of. I still don't know what a characteristic of a star means. 21:35:36 The magnitude and color of the stars, it shows your a more or lees the characteristic. 21:36:23 attribute...Sorry Zzo...I have too many years I do not use the english. 21:38:02 Ah, OK. Well, I do have the magnitude and color of the stars, I can look it up in Wikipedia just fine. But why do you want the color and magnitude? Certainly I know the color of the star is related to its temperature, and stuff like that, but I don't know what you are trying to do with them. 21:38:13 But the principal stars are the ascendant, solar sign, moon sign, fate sign and couple sign. 21:38:16 JM383: do you understand what this channel's for? 21:38:42 Okay...good question. 21:39:05 which reminds me, I thought up a new BF Joust strategy last night 21:39:12 but I don't have the time to write it into a program right now 21:39:14 Do you know to work the colors? I mean, do you know that are the attribute of each color? 21:39:19 I'll try later 21:39:20 JM383: ais523 does make a good point. You should look at the esolang wiki if you want to understand most of what we write here. 21:39:43 JM383: I don't know what "to work the colors" means. 21:40:17 -!- Slereah_ has joined. 21:40:20 JM383: what I'm worried about, really, is a) this channel isn't actually about astrology, b) zzo38 is probably the only person here who is interested in astrology, and he doesn't know what you're talking about 21:40:22 thus it's probably wrong 21:40:25 in addition to being offtopic 21:40:42 Okay Zzo...each colors got some attributes. 21:41:11 being offtopic? 21:41:12 -!- Phantom__Hoover has joined. 21:41:28 So we can not talk about astrology? 21:41:51 JM383: not here 21:41:55 the `welcome has the appropriate channel in 21:41:56 Well, I did find "Stars in astrology" in Wikipedia. I don't really care much about where all the planets are at my birth; I am more interested in the here and now. 21:41:58 `welcome JM383 21:42:01 JM383: Welcome to the international hub for esoteric programming language design and deployment! For more information, check out our wiki: . (For the other kind of esoterica, try #esoteric on irc.dal.net.) 21:42:07 that's why you've been welcomed three times already 21:42:09 But yes it is offtopic. 21:42:21 Ha...okay Ais, please pardon me for, but I was looking for a topic. 21:42:25 (Many offtopic things are sometimes discussed in here, but you still ought to learn what is ontopic) 21:42:47 or to put it another way, offtopic conversation is more tolerated from people who participate in the ontopic conversations 21:42:53 (In order to learn what is the interests too, since astrology isn't much of an interest.) 21:43:11 -!- Phantom_Hoover has quit (Ping timeout: 240 seconds). 21:43:15 ais523: Yes, that is anther way to put it too; good idea. 21:43:24 not unless there's a language that depends on astrological constellation 21:43:31 s 21:43:35 mroman: we could invent one 21:43:39 http://esolangs.org/wiki/Gravity is the closest 21:43:44 well... 21:43:50 we can always invent eso languages :) 21:43:56 mroman: Actually yes I did write in "List of ideas" something about that! 21:44:02 -!- Slereah has quit (Ping timeout: 264 seconds). 21:44:04 hm 21:44:10 Maybe it can be done, somehow. 21:44:18 probably 21:44:30 I figure astrological constellations can be pre-calculated somehow 21:44:31 or 21:44:36 hm 21:44:56 Positions of planets, stars, etc can be calculated accurately for past and future using ephemeris. 21:45:01 then you could cheat and set the system time to a specific value :( 21:45:21 unless!!! 21:45:24 trusted computing stuff 21:45:29 that prevents you from doing so 21:45:52 (Really the only thing I can think of is something similar to Wait, although I wanted to think of something more interesting and different than that.) 21:47:11 Well...pardon me for to be out-topic. 21:47:42 Everything is on topic as long as you invent a language for it 21:47:50 A more complicated thing would also have an actual program in addition to that, and would allow certain events to change the parameters of the horoscope (house system, ayanamsha, harmonic factor, etc) and so on. 21:48:01 fengshui? 21:48:20 mroman: Maybe you can make something related to fengshui too. After all there are a lot of unusual ideas! 21:48:30 Yeah 21:48:46 Are there any papers about empirically measuring the feng shui level of a user? 21:49:13 maybe through blood, finger print, electrodes 21:49:16 brain scans 21:50:24 I don't know. 21:50:36 thanks for your time and again, pardon me for. 21:51:05 I know gnuplot 21:51:10 I'm sure I can make one up 21:51:26 -!- JM383 has quit (Quit: irc2go). 21:52:17 I don't know if Society for Scientific Exploration has any; they do try to write scientific papers relating to telepathy and astrology and so on. 21:52:56 Linux tptp.cc 2.6.32-358.6.2.el6.x86_64 #1 SMP Thu May 16 20:59:36 UTC 2013 x86_64 x86_64 x86_64 GNU/Linux 21:53:08 -!- utopian has joined. 21:53:10 Linux ultra30.tptp.cc 3.10.7-gentoo-r1 #1 PREEMPT Sat Nov 2 19:03:59 EDT 2013 sparc64 sun4u TI UltraSparc II (BlackBird) GNU/Linux 21:53:44 yehhhhhhhhhhh 21:53:59 ion hi there sweety 21:54:44 About fengshui, I know it uses various different "schools" of fengshui, and the oldest one is called "form school", which is the only one I think has some partial validity and reasonableness, from what I can tell. 22:02:22 SSE does have a paper titled "How to Reject Any Scientific Manuscript". It also has some titles I do not understand, such as "Phenomenology of N,N-Dimethyltryptamine Use: A Thematic Analysis". 22:03:11 It does have one title which does look like something I have thought about in the past: "Ockhams Razor and Its Improper Use". 22:03:31 -!- tertu has quit (Ping timeout: 260 seconds). 22:03:49 -!- tertu has joined. 22:03:59 DMT's a hell of a drug 22:04:39 I still haven't tried it outside of ayahuasca 22:04:45 * copumpkin is deprived 22:05:00 deprived / depraved 22:05:05 https://scontent-a-iad.xx.fbcdn.net/hphotos-frc1/319595_1585878742417_31179844_n.jpg 22:05:08 DMT I made a few years back 22:05:10 I haven't tried DMT either, but I did take 5-MeO-DMT 22:06:07 -!- Koen_ has joined. 22:06:18 -!- tswett_w has joined. 22:06:23 Hi everyone. 22:06:29 So this is my presentee nick. 22:06:46 The nick I use when I'm actually here and paying attention. 22:06:49 Unlike tswett_q here. 22:06:52 What's he even doing here? 22:06:57 Anyway. 22:07:03 Self-solving multi-king chess problems. 22:07:05 Are they Turing-complete? 22:08:21 What rules are used with multi-kings? 22:08:22 -!- Koen_ has quit (Client Quit). 22:08:33 A move is legal only if at the end of it, none of your kings are in check. 22:08:42 -!- Koen_ has joined. 22:08:54 OK. 22:09:10 (Different chess variants with multiple kings use different rules.) 22:09:34 I don't know if it is Turing-complete with unlimited board sizes possibly? 22:09:59 * Koen_ wonders if zzo38 is talking about chess being turing-complete 22:10:06 Yeah, an easy-seeming question is whether or not it's Turing-complete with an infinite board and infinitely many pieces. 22:10:17 A more interesting question, perhaps, is whether or not it's Turing-complete with only finitely many pieces. 22:10:40 Yes, is it? I don't know that answer either. 22:12:19 It seems pretty hard to constrain pieces to move in only way. It's only obvious how to do this with the pawn. If there aren't any enemy pieces around, the pawn can only move forward. 22:15:01 -!- Oj742 has quit (Ping timeout: 245 seconds). 22:22:33 self-transforming machine elves, are they turing complete 22:23:45 I can't think how you'd do any kind of computation at all with SSMKCPs. 22:24:21 tswett_w, but Wang tiles are turing-complete and you can't do computation with them 22:24:43 you can't? 22:24:43 Yeah, I guess that's true. 22:24:48 por que no 22:24:54 kmc, no, they're just tiles 22:25:02 I can't think how you'd represent any kind of computation at all with SSMKCPs. 22:25:10 Also, I'm going to bed now 22:25:10 -!- Oj742 has joined. 22:25:13 -!- Taneb has quit (Quit: me --> bed). 22:25:47 I"m reminded of a C program containing this line: 22:25:50 -!- oerjan has joined. 22:25:57 "while (x --> 0) { // x goes to 0" 22:26:56 now i'm reminded of continuous brainfuck 22:27:12 or whatever if was called. 22:27:37 running a program required solving differential equations. 22:28:20 basically + and - adjusted a cell infinitesimally. 22:28:44 i have a feeling oklopol was involved. 22:29:35 Huh, that sounds interesting. 22:29:44 that does 22:29:52 we should have a monthly Least Boring BF Derivative prize 22:30:00 also "derivative" heh 22:30:10 My dad just told me to become a doctor and said something about a shortage of competent doctors <-- are you ben from darths & droids. 22:30:21 no hes Sgeo from the internet 22:30:24 I haven't read Darth & Droids 22:30:48 kmc: that's even _more_ implausible! 22:31:16 Is that that comic strip that parodies Star Wars I by presenting it as a D&D campaign? 22:31:23 yes. 22:31:43 I thought Star Wars I was considered utterly horrible? 22:31:46 well, except they're up to V now. 22:31:59 I've only seen IV so fa 22:32:00 far 22:32:06 And I was half asleep 22:32:09 IV, II, III, V, VI 22:32:22 It seemed a bit cheesy 22:32:25 IV is the worst of the OT by far. 22:32:35 I thought Machete was IV V II III VI 22:32:39 V is the only one i've seen in a genuine cinema, although i've picked up parts of I on tv. 22:32:41 pikhq: yeah, I couldn't wait to graduate to Operating Thetan level V 22:32:51 Not coincidentally the only one directed by Lucas. 22:33:24 Sgeo: one of the accomplishments of darths & droids is that they made the most hated character in I look likeable. 22:33:33 kmc: Sgeo is from the internet? 22:33:34 oerjan: sounds fun 22:33:51 I read a novelization of I, come to think of it 22:33:54 From Anakin's POV 22:34:17 I think as a kid I've read a lot of novelizations 22:34:31 I keep being surprised by the concept of Kenan and Kel as a TV show 22:37:07 Kenan made the move up to SNL 22:38:02 Kel disappeared from society and lives in a cabin in the woods with Grothendieck 22:39:54 -!- ^v has quit (Read error: Connection reset by peer). 22:40:22 This music I'm listening to is somewhat inappropriate for a hellish world with superpowers, yet it's now associated with it indelibly in my mind 22:40:53 tswett_w: you can trap bishops behind pawn chains of their own-colored pawns 22:40:56 -!- ^v has joined. 22:41:29 Sgeo: is it a http://tvtropes.org/pmwiki/pmwiki.php/Main/CrapSaccharineWorld ? 22:41:48 Well, not sure if it's really hellish 22:42:12 But in the city that's the main focus, gangs of supervillians control the area, I think 22:42:24 oerjan: I wasn't sure whether you were telling the truth about what Darths & Droids was, so I looked it up. 22:42:42 So, I gotta go do homework and stuff. See all y'all guys. 22:42:45 -!- tswett_w has quit (Quit: Page closed). 22:43:29 I want to try a wind tunnel 22:43:55 that's awesomely unspecific 22:43:59 "i want to try a laser" 22:44:20 As in, one of those places that's like skydiving but in an indoor cylindrical area 22:44:39 http://www.funfix.com/Indoor-Wind-Tunnels/New-York/ 22:44:41 oops 22:44:44 http://vimeo.com/72760181 22:46:07 tswett_w the doubter 22:49:36 -!- Oj742 has quit (Ping timeout: 245 seconds). 22:50:15 -!- ais523 has quit. 22:52:24 Maybe I should try Ada 22:53:15 Well, I certainly should at least try to get an understanding of its concurrency model 22:53:23 you try Ada, I'll try DMT, we can compare notes 22:53:47 how is DMT's concurrency model? 22:54:06 Don't Mention Threads 22:54:07 Hmm, Ada distinguishes procedures and functions? Or is that just for protected objects? 22:54:20 iirc functions have return values, procedures don't 22:54:34 oerjan: a popular model 23:08:07 How is trying Ada remotely like trying an indoor wind tunnel flying place? 23:08:44 -!- eyhg7w5yt has joined. 23:09:09 quoth the writing desk 23:10:00 -!- eyhg7w5yt has quit (Excess Flood). 23:10:18 i'm glad zzo38 was around when JM372 showed up 23:10:51 -!- eyhg7w5yt has joined. 23:11:42 -!- eyhg7w5yt has quit (Excess Flood). 23:12:10 also "JM372" sounds like a synthetic cannabinoid 23:12:24 kmc: Ah. OK. I also didn't know it sounds like a synthetic cannabinoid. 23:13:09 http://en.wikipedia.org/wiki/Template:Cannabinoids jesus there are a lot of these now 23:13:57 hey kids wanna get high on some 2-Isopropyl-5-methyl-1-(2,6-dihydroxy-4-nonylphenyl)cyclohex-1-ene 23:16:13 Maybe you, but I don't want to. 23:16:53 that is fine too 23:17:07 Get high on dihydrogen monoxide? 23:17:35 -!- zzo38 has quit (Quit: zzo38). 23:17:52 aw i hope i didn't scare him off with my #drugz talk 23:18:20 Of course I click 23:18:31 also it's hard to tell whether zzo38 doesn't get most jokes or just has an incredibly deadpan response 23:20:54 he definitely seems like someone who does have a sense of humor and it's for him, not for other people 23:21:09 which is commendable 23:22:06 @tell zzo38 you're great, also sorry if I scared you off with #drugz talk 23:22:06 Consider it noted. 23:22:33 DHMO is the primary ingredient in common forms of 'alternative therapy', which has killed numerous people 23:23:01 it's true! 23:23:04 some might say the only ingredient 23:24:35 Sgeo: it has also been used to kill people outright. 23:26:04 i hear bangladesh has big trouble with increasing DHMO levels. 23:27:31 especially in coastal environments 23:28:15 and the chinese have spent enormous sums of money trying to control it. 23:31:15 even norway has regular overexposure incidents. 23:39:43 -!- mroman has quit (Ping timeout: 272 seconds). 23:39:56 -!- mroman has joined. 23:42:41 -!- tertu has quit (Ping timeout: 245 seconds). 23:44:07 -!- tertu has joined. 23:44:09 -!- conehead has quit (Ping timeout: 272 seconds). 23:49:26 whereas the prosperity of the dutch is largely a result of a forward-thinking centuries-old program to remove DMSO from the area around major cities 23:50:04 *H 23:50:09 haha lol 23:50:12 i fucked up that joke bad 23:50:34 -!- dessos has quit (Quit: leaving). 23:50:34 maybe you confused it with MSG, also a problem substance 23:50:47 DMSO sounds like it might actually be a bad thing 23:50:52 but if you can't laugh at yourself causing people to laugh at you instead of with you, who can you laugh at 23:51:00 tertu: it's mostly useful for getting other things (good or bad) through your skin 23:51:07 I don't remember how harmful it is by itself 23:51:31 "Although it has some niche medicinal uses it also has significant known side effects. It has been discussed as treatment for cancer and other conditions." 2013-11-04: 00:10:57 -!- KingOfKarlsruhe has quit (Quit: ChatZilla 0.9.90.1 [Firefox 25.0/20131025151332]). 00:11:56 random thought: has anyone managed to somehow "separate" memory and control flow, when writing proofs about computational power? 00:12:10 what 00:12:37 the lambda calculus and friends? the chomsky hierarchy? neither of these have notions of memory or control flow 00:12:45 space vs. time complexity classes? 00:14:26 Phantom__Hoover: well that's the opposite of separating them, i'd say 00:17:47 i've no idea what the question means, then 00:18:28 well i think it's tricky to separate them in a way that doesn't allow you to cheat by hiding more control flow in the memory. 00:23:38 -!- Uguubee1111111 has quit (Read error: Connection reset by peer). 00:28:58 oerjan: well if it's a proof for a lower bound to the computational power, that's not a problem 00:31:25 -!- conehead has joined. 00:31:39 a hunch: it might be that the greatest degree of separation between control flow and memory is found in relatively vanilla non-object oriented programming languages, like C or Forth. although also brainfuck. 00:31:51 -!- conehead has quit (Remote host closed the connection). 00:31:56 *imperative programming languages 00:32:04 left out the most important word :P 00:33:19 dunno about proofs, though. 00:34:07 object-oriented and functional both excluded because they provide ways of wrapping control flow into a value. 00:34:39 although even C and Forth have ways to reify functions. 00:34:52 maybe just brainfuck, then :P 00:36:56 i suppose vanilla Pascal doesn't have first class functions or procedures. (i'm not sure if it even has function/procedure arguments or if that was also a later addition.) 00:40:25 -!- Uguubee1111112 has joined. 00:41:23 -!- nooodl has quit (Ping timeout: 245 seconds). 00:42:46 -!- Uguubee1111112 has quit (Client Quit). 00:43:21 -!- Uguubee1111112 has joined. 00:44:49 -!- Oj742 has joined. 00:46:05 -!- Uguubee1111112 has quit (Read error: Connection reset by peer). 00:47:39 -!- Uguubee1111112 has joined. 00:58:48 TVTropes certainly calls the world a Crapsack world 01:02:18 -!- yorick has quit (Remote host closed the connection). 01:02:26 counterpoint: dickbutt 01:03:07 -!- Phantom__Hoover has quit (Read error: Connection reset by peer). 01:18:53 -!- tertu has quit (Read error: Connection reset by peer). 01:19:27 -!- tertu has joined. 01:36:41 -!- ^v has quit (Read error: Connection reset by peer). 01:39:37 @tell boily thoily! 01:39:38 Consider it noted. 01:40:43 -!- myndzi has left. 01:41:01 -!- myndzi has joined. 01:41:19 `thanks hm lessee... 01:41:21 Thanks, hm lessee.... Thessee.... 01:41:47 nah. 01:46:01 -!- ^v has joined. 01:52:26 There's a character named Gregor 01:52:58 `thanks Gregor 01:52:59 Thanks, Gregor. Thegor. 01:54:34 Gregor: It is actually a name. 01:55:06 a very Gregory name 01:57:49 elliott: You were all about complete partial orders once, right? 02:01:48 he was completely partial to them. 02:15:30 -!- Koen_ has quit (Quit: The struct held his beloved integer in his strong, protecting arms, his eyes like sapphire orbs staring into her own. "W-will you... Will you union me?"). 02:51:43 -!- ^v has quit (Read error: Connection reset by peer). 02:53:17 -!- nisstyre has quit (Quit: Leaving). 03:06:29 -!- ^v has joined. 03:17:14 -!- ^v has quit (Read error: Connection reset by peer). 03:44:19 -!- Frooxius has quit (Read error: Connection reset by peer). 03:44:24 -!- tertu has quit (Read error: Connection reset by peer). 03:44:33 -!- Frooxius has joined. 03:44:46 -!- tertu has joined. 03:48:39 today is a long day 03:48:52 yep 03:48:54 unsigned long day 03:49:26 It is in fact a 25 hour day by my reckoning. 03:51:15 that's p. long 03:53:05 kmc: http://i.imgur.com/8rhlusE.gif 03:56:05 is that even possibly not fake 03:56:36 what does it mean for something to be fake 03:56:51 -!- tertu has quit (Read error: Connection reset by peer). 03:57:13 -!- zzo38 has joined. 03:57:32 i retract the question on the grounds that the responder is too meta. 03:58:40 -!- shikhin has joined. 04:00:05 never meta question i didn't like 04:07:52 shachaf: <3 04:09:16 I also think today is the long day 04:09:21 ?messages-loud 04:09:22 kmc said 4h 47m 15s ago: you're great, also sorry if I scared you off with #drugz talk 04:09:41 kmc: No, that isn't it. That is fine 04:09:55 shachaf: so fireworq 04:11:08 cool 04:12:08 sopumpkin 04:12:17 suchpeebles 04:12:42 http://zachbruggeman.me/dogescript/ 04:15:05 copumpkin: do you know about chu spaces 04:16:08 Are you sure that you cannot do computation with Wang tiles? 04:17:01 omg chu spaces i vaguely remember those 04:17:25 zomg 04:17:36 what do you reember 04:17:38 m 04:18:37 it was some kind of generalization of galois connections which somehow helped with modeling linear logic 04:19:52 really? 04:20:25 you mean the "adjointness condition" in the definition of the thing corresponding to a continuous function? 04:20:27 zzo38: well you might but in the obvious way i can see you need to nondeterministically choose how to extend your tiling, it's probably extremely slow. 04:20:47 i don't remember the _actual_ definition of a chu space, mind you. 04:21:59 the definition is p. simple: https://en.wikipedia.org/wiki/Chu_space 04:22:34 shachaf: nope 04:22:46 copumpkin: well it looked p. simple to me :'( 04:23:51 or are you saying you don't now about them 04:24:01 you're supposed to know everything 04:24:44 that looks familiar. i also recall the supposed quantum connection which i never thought really materialized. 04:24:45 I don't know about them :( 04:24:55 when I hear chu spaces, I think of train depots 04:25:06 which was what i found most interesting. 04:26:02 kmc: http://blogs.smithsonianmag.com/smartnews/2013/07/long-before-trees-overtook-the-land-earth-was-covered-by-giant-mushrooms/ sweet 04:26:17 nice 04:26:39 kmc: should i ask lexande about chu-chu spaces 04:26:45 shachaf: well it's something i found vaguely interesting but which seemed to me to not have enough substance for me to look at it in depth. 04:26:46 i guess so 04:27:04 oerjan: is a quantum connection like a galois connection 04:27:24 -!- tertu has joined. 04:27:31 I want a giant truffle 04:27:35 like the size of a mountain 04:27:39 white of course 04:28:06 "More from Smithsonian.com: - A Fungus-Like Disease Threatens Europe’s Supply of Gin -The Fungus in Your Cheese Is Having Weird Sex - Insulation Made Out of … Mushrooms?" 04:28:13 fungus 04:28:28 thank god for all this fungus related news 04:28:58 there's an episode of Seinfeld which gets good mileage from the fact that "fungus" is an inherently funny word 04:29:13 if my name were gus, I'd go by fungus 04:29:24 cofungus 04:29:40 copumpkin is cofun 04:29:40 Bike: istr reading about that fungus theory before 04:29:50 also he owed me five dola 04:29:51 well it says 2007 04:30:05 i'm just late to the party, the giant fungus spire party 04:30:22 " It might have had an algal symbiont, which would make it a lichen rather than a fungus in the strict sense." awesome. 04:30:30 kmc: the last episode of breaking bad was good btw 04:31:27 it was allright 04:32:00 oh no 04:32:06 I don't think it quite lives up to the show overall 04:32:19 why not 04:32:20 Bike: bah your link initially looked like they'd found confirming evidence, but it's just a rehash of the 2007 story? 04:33:12 this thing lived half a billion years ago, cut them some slack on finding 'evidence' 04:33:20 oerjan: is a quantum connection like a galois connection <-- well if you could _prove_ that, you might get famous? 04:34:24 Bike: it's the rehashing i'm complaining about. 04:34:58 well if it hadn't been rehashed i wouldn't have run into it at all so there 04:35:24 struth. 04:36:06 kmc: have you been rehashed today #drugz 04:45:25 Why is there no ALPACA interpreter 04:46:08 there isn't? 04:46:46 cpressey broke stuff again 04:47:12 drlemon: http://catseye.tc/node/ALPACA 04:49:07 http://catseye.tc/node/alpaca_(Python) is nothing 04:49:59 I DON'T KNOW HOW TO PYTHON 04:51:06 drlemon: i think you're supposed to download the distribution. 04:51:29 (for ALPACA) 04:51:37 OK but i did and i don't know how to use stuff 04:52:55 you can probably download python from python.org 04:53:22 or there is probably a package for it. 04:53:50 hm well whatever your system. (you seem to be using an irc client for mac) 04:54:10 I have python 04:54:26 But i don't know how to deal with a bunch of seperate programs 04:55:20 `seen doesthiswork 04:55:24 2013-11-02 23:49:47: shachaf: yes 04:55:41 Probably you just put the program in some directory and then type in "python" and the name of the program (or if it is chmod +x and has #! at the top, then typing in the name of the file by itself might work) 04:55:51 -!- heroux has quit (Ping timeout: 272 seconds). 04:57:11 it does have #!, however the program refers to modules in other directories, so it's probably best to keep it in the same directory structure 04:58:29 Yes, keep the same directory structure as whatever it uses 04:58:34 drlemon: download the files into some directory, then run bin/alpaca in the subdirectory of that. 04:58:49 (the bin/alpaca which is in there, that is.) 05:00:27 oerjan: do you know about frames and locales and those things 05:00:43 the funny bit is that a frame is the same thing as a locale 05:02:27 not beyond hearing the words 05:02:39 `locale 05:02:41 LANG=en_NZ.UTF-8 \ LANGUAGE= \ LC_CTYPE="en_NZ.UTF-8" \ LC_NUMERIC="en_NZ.UTF-8" \ LC_TIME="en_NZ.UTF-8" \ LC_COLLATE="en_NZ.UTF-8" \ LC_MONETARY="en_NZ.UTF-8" \ LC_MESSAGES="en_NZ.UTF-8" \ LC_PAPER="en_NZ.UTF-8" \ LC_NAME="en_NZ.UTF-8" \ LC_ADDRESS="en_NZ.UTF-8" \ LC_TELEPHONE="en_NZ.UTF-8" \ LC_MEASUREMENT="en_NZ.UTF-8" \ LC_IDENTIFICATION="en_NZ 05:03:03 `seen elliott 05:03:08 2013-10-28 20:17:00: boily: I do not believe so 05:03:12 Where did he go, anyway? 05:03:35 no i do mean in the context of ct/algebraic geometry or thereabouts, things beyond my knowledge. 05:03:36 finally took my suggested roadtrip down to east timor 05:03:46 is presently held up at a checkpoint in eastern iran 05:03:49 godspeed elliott 05:03:53 Why does it use en_NZ.UTF-8? In my opinion it ought to be C locale by default unless you change it for an individual command. 05:04:16 zzo38: No, it should be UTF-8. C isn't compatible with Unicode. 05:04:20 not very nice to new zealand 05:04:49 oerjan: but you know about homology and things right 05:04:52 shachaf: Using UTF-8 by default causes other problems; it should be C by default, and selecting UTF-8 when you do want Unicode (you also select other things you want, at the same time) 05:04:59 zzo38: we asked Gregor to set it so that HackEgo could use utf-8, and he chose en_NZ to be funny 05:05:17 zzo38: You always want Unicode. 05:05:52 Would selecting the C locale speed it up by a small amount if implemented in a certain way? 05:06:11 it's important that a linux installation on uml on irc is maximally performant 05:06:14 I suppose if you do want the C locale now you can still specify it for an individual command though 05:06:39 zzo38: but all HackEgo commands that are intended to be run directly from ` take the rest of the irc message as argument, and so should do utf-8 because that's the charset we want to encourage in this channel. 05:07:35 and if it wasn't on by default people wouldn't care enough to set it when they should. 05:07:59 Yes, that seems reasonable, but sometimes you might not want it (although a shortcut could be made such as `runc to use the C locale, maybe, if a shortcut is wanted) 05:08:05 oerjan: Even the people of #esoteric? 05:08:18 shachaf: i do know about basic homology yes 05:08:58 is it good 05:09:11 shachaf: some would care, but too many wouldn't? 05:09:33 and some like i would bitch about having to care about it on individual commands. 05:10:23 shachaf: it allows you to prove things like the jordan-brouwer theorem and brouwer fixed point theorem 05:10:39 good theorem 05:10:42 And if you want to pipe binary data to a program that expects text, it might also not work in UTF-8 mode. (Of course this would be rare though.) 05:10:44 and invariance of domain 05:11:04 basically things that tell you that euclidean spaces are almost sane topologically. 05:11:53 I do sometimes work on Linux computer. I think it is set to en.UTF-8 by default although on my account I have changed it to the C locale, disabled Unicode translation, and loaded a CP437 font. 05:12:56 This improves the operation of the system. 05:13:27 `addquote I do sometimes work on Linux computer. I think it is set to en.UTF-8 by default although on my account I have changed it to the C locale, disabled Unicode translation, and loaded a CP437 font. This improves the operation of the system. 05:13:32 1126) I do sometimes work on Linux computer. I think it is set to en.UTF-8 by default although on my account I have changed it to the C locale, disabled Unicode translation, and loaded a CP437 font. This improves the operation of the system. 05:14:24 -!- Oj742 has quit (Quit: irc2go). 05:14:51 i zzo38 05:15:34 -!- shikhin_ has joined. 05:15:53 (The font file from MegaZeux works just fine in Linux; it doesn't need to be converted.) 05:16:22 Now I read the Wikipedia article of Chu spaces. 05:17:06 -!- shikhin has quit (Ping timeout: 245 seconds). 05:18:34 @tell elliott I hope you don't think I'm being overly preemptive with these suspicious new accounts. 05:18:35 Consider it noted. 05:19:05 Things like "a Chu space (A, r, X) over a set K consists of a set A of points..." is what I have programmed the SetType class in Haskell for. It might be: data Chu :: * -> * where { Chu :: forall a k x. (SetType a, SetType x) => SetOf a -> SetOf x -> (a -> x -> k) -> Chu k; }; Would that be it even close? 05:21:59 Do you know if that is it or not, and so on? 05:22:05 @tell elliott Argh too many to do this. 05:22:06 Consider it noted. 05:22:17 i think we have a spam problem again. 05:29:33 (However this SetType only works with finite sets (currently).) 05:31:12 great, because i really needed something vaguer than topological spaces 05:33:59 -!- asie has joined. 05:42:39 how are there even billions of people in the world 05:42:41 it makes no sense 05:43:06 imo it does make sense 05:43:22 imo how 05:43:58 population dynamics 05:46:56 shachaf: fertilizer 05:48:03 -!- Sprocklem has quit (Ping timeout: 245 seconds). 05:49:05 the growth of the population at an instant is, very roughly, directly proportional to the number of mating pairs. the number of mating pairs is proportional to the population. so, the rate of change of the population is roughly k*p, where p is the population size and k is a parameter. 05:49:11 exponential! 05:49:45 oerjan: i don't even know 'er! 05:53:35 Bike: yes exponential but why can't it be small 06:07:50 -!- asie has quit (Quit: My MacBook Pro has gone to sleep. ZZZzzz...). 06:17:00 @yow 06:17:00 I can't decide which WRONG TURN to make first!! I wonder if BOB 06:17:01 GUCCIONE has these problems! 06:24:07 Thing I need to fit into my model of existant metaprogramming systems: Prolog term_expansion 06:25:36 I'm thinking more like defmacro than anything else 06:30:13 -!- shikhin_ has quit (Read error: Operation timed out). 06:30:36 -!- tertu has quit (Ping timeout: 245 seconds). 06:45:34 -!- shikhin_ has joined. 06:51:34 -!- Yonkie has joined. 06:53:16 -!- nisstyre has joined. 06:55:21 -!- shikhin__ has joined. 06:55:50 -!- shikhin_ has quit (Ping timeout: 240 seconds). 07:07:34 -!- Frooxius has quit (Read error: Connection reset by peer). 07:07:49 -!- Frooxius has joined. 07:16:46 -!- oerjan has quit (Quit: leaving). 07:22:08 https://archive.org/details/Adventure_1978_Atari_NTSC aw yeah. 07:25:30 -!- Halite has joined. 07:29:34 your mother is esoteric. 07:29:51 Halite: Are you sure? 07:30:41 Can it be the joke of the day? 07:30:48 -!- FreeFull has quit. 07:32:20 print(x and !y or !x and y) 07:37:27 -!- heroux has joined. 07:48:26 -!- ssue___ has quit (Quit: Connection closed for inactivity). 07:55:50 -!- nisstyre has quit (Ping timeout: 240 seconds). 08:13:26 I wrote this program "utftovlq" which can convert between many byte stream formats (8-bits, 16-bits, 32-bits, 64-bits, UTF-8, Modified UTF-8, VLQ, LEB128, UTF-16; many have small and big endian modes), and it can also add/remove Unicode BOM. Did I perhaps miss something? 08:15:39 (This program can also be used to byteswap files with the command "utftovlq Ww" or "utftovlq wW".) 08:44:45 -!- `^_^v has quit (Ping timeout: 272 seconds). 08:49:02 -!- `^_^v has joined. 08:58:20 Maybe you should temporarily disable account creation? Post a note you have to attempt to ask in the IRC or wait until it is not disabled anymore. 09:12:16 -!- zzo38 has quit (Remote host closed the connection). 09:36:50 -!- TodPunk has quit (Ping timeout: 264 seconds). 09:40:11 -!- TodPunk has joined. 09:42:38 -!- heroux has quit (Ping timeout: 240 seconds). 09:58:43 I hate that C decided to ignore overflows 10:03:03 I think it's more like it ignores/traps/nasal-demons/wraps overflows 10:10:01 -!- Uguubee1111112 has quit (Ping timeout: 245 seconds). 10:13:14 -!- Uguubee1111112 has joined. 10:47:58 -!- Uguubee1111112 has quit (Read error: Connection reset by peer). 10:56:11 -!- Uguubee1111112 has joined. 10:56:34 In some cases also raises-exceptions-es. 10:57:39 -!- MindlessDrone has joined. 11:09:34 -!- Uguubee1111112 has quit (Ping timeout: 240 seconds). 11:12:02 -!- Uguubee1111112 has joined. 11:19:39 -!- aloril_ has quit (Ping timeout: 272 seconds). 11:33:12 -!- aloril_ has joined. 12:00:35 -!- Froox has joined. 12:01:01 -!- Frooxius has quit (Ping timeout: 245 seconds). 12:31:35 -!- Sgeo has quit (Read error: Connection reset by peer). 12:43:27 -!- shikhin__ has changed nick to shikhin. 12:54:32 -!- shikhin_ has joined. 12:57:26 -!- shikhin has quit (Ping timeout: 240 seconds). 12:57:34 -!- yorick has joined. 12:58:27 -!- boily has joined. 13:02:54 -!- shikhin__ has joined. 13:03:47 -!- shikhin_ has quit (Ping timeout: 272 seconds). 13:04:32 -!- shikhin__ has changed nick to shikhin. 13:06:38 -!- Jafet has quit (Ping timeout: 240 seconds). 13:07:29 -!- Jafet has joined. 13:09:18 -!- MindlessDrone has quit (Quit: MindlessDrone). 13:10:09 -!- MindlessDrone has joined. 13:18:06 -!- shikhin has quit (Read error: Operation timed out). 13:28:36 -!- metasepia has joined. 13:31:53 -!- shikhin has joined. 13:34:06 -!- Uguubee1111112 has quit (Read error: Connection reset by peer). 13:37:34 -!- Uguubee1111112 has joined. 13:39:04 Uguubee1111112: who are you? are you legion? what is your numbering scheme? do you prefer your condensed milk sweetened or unsweetened? 13:39:13 @messages-loud 13:39:13 quintopia said 11h 59m 35s ago: thoily! 13:39:29 quintopia: hi! have they been received? 13:41:54 (hm. that may not be the right conjugation. «ont-ils été reçus.») 13:51:11 boily: english conjugation or french? 13:52:11 the English one. my brain is on auto-pilot, so I may calque from French a little bit more than usual. 13:52:24 -!- Uguubee1111112 has quit (Ping timeout: 246 seconds). 13:52:28 boily: the passive voice is a bit weird, but otherwise it's correct 13:55:29 -!- ais523 has joined. 14:05:27 -!- heroux has joined. 14:08:51 -!- asie has joined. 14:09:42 -!- Uguubee1111112 has joined. 14:11:18 -!- ais523 has quit (Ping timeout: 246 seconds). 14:32:05 -!- tertu has joined. 14:32:07 -!- carado has joined. 14:41:03 -!- Uguubee1111112 has quit (Quit: Uguubee1111112). 14:43:18 -!- mrhmouse has joined. 14:44:14 -!- Uguubee1111112 has joined. 14:44:42 @tell zzo38 re your latest quote: feeling some form of DOS nostalgia? 14:44:43 Consider it noted. 14:56:53 -!- Uguubee1111112 has quit (Ping timeout: 272 seconds). 15:01:25 -!- Uguubee1111112 has joined. 15:03:26 -!- augur has quit (Remote host closed the connection). 15:03:53 -!- augur has joined. 15:07:26 -!- shikhin has quit (Ping timeout: 240 seconds). 15:08:21 -!- augur has quit (Ping timeout: 246 seconds). 15:14:58 -!- Uguubee1111113 has joined. 15:16:25 -!- Uguubee1111112 has quit (Ping timeout: 272 seconds). 15:18:22 -!- shikhin has joined. 15:26:14 -!- shikhin_ has joined. 15:28:08 -!- shikhin has quit (Ping timeout: 240 seconds). 15:37:05 -!- asie has quit (Quit: My MacBook Pro has gone to sleep. ZZZzzz...). 15:44:08 -!- nooodl has joined. 15:48:45 -!- augur has joined. 15:50:16 -!- KingOfKarlsruhe has joined. 15:51:34 -!- augur has quit (Read error: Connection reset by peer). 15:51:41 -!- augur has joined. 15:53:11 -!- augur has quit (Read error: Connection reset by peer). 15:53:54 -!- asie has joined. 15:55:27 -!- augur has joined. 15:58:50 -!- augur has quit (Remote host closed the connection). 15:59:51 @tell lambdabot Your mother considered it noted. 15:59:52 Nice try ;) 16:01:03 -!- zzo38 has joined. 16:01:35 -making BooleanC- 16:01:42 -documenting*- 16:03:09 -!- Froox has quit (Read error: Connection reset by peer). 16:03:21 -!- Frooxius has joined. 16:04:10 -!- shikhin_ has quit (Ping timeout: 245 seconds). 16:05:54 ?messages-loud 16:05:54 boily said 1h 21m 11s ago: re your latest quote: feeling some form of DOS nostalgia? 16:07:16 boily: I do sometimes use DOS, but that isn't really the point; CP437 is the PC character set and what I use for general purpose screen text 16:08:22 I think what C programs generally do with integer overflows is good idea. 16:09:42 -!- shikhin_ has joined. 16:17:47 -!- augur has joined. 16:21:23 lambdabot answers to ?? 16:21:46 -!- FreeFull has joined. 16:21:53 zzo38: but, but... what about all those wonderful accented letters left out of CP437? 16:30:42 boily: I don't use them. You could use others if needed but the other ones lack ine drawing and various other things I sometimes use. 16:31:15 @massage-loud 16:31:15 You don't have any messages 16:31:17 BBS connections also usually expect CP437, and other software I write (especially DOS programs) expect CP437. 16:31:49 -!- shikhin_ has changed nick to shikhin. 16:32:02 but.. but.. unicode 16:32:13 this is the 2000s 16:32:14 FireFly: he is Zzo38, of Weird Computer Setups. 16:32:25 ah, right 16:34:37 Unicode requires more than 256 characters anyways. 16:40:28 -!- shikhin has quit (Quit: Leaving). 16:43:35 -!- conehead has joined. 16:45:57 man works fine in this mode if LANG=C is set. swetest will try to output a degree sign in UTF-8 encoding; the shell script I wrote to wrap it translates it to shift-out/shift-in encoding instead (as well as making it using the current date/time by default). 16:51:25 -!- Sprocklem has joined. 17:03:07 -!- ais523 has joined. 17:10:11 -!- Sprocklem has quit (Read error: Connection reset by peer). 17:10:33 -!- ais523 has changed nick to ais523\unfoog. 17:13:09 -!- Sprocklem has joined. 17:15:47 -!- oerjan has joined. 17:23:45 -!- ^v has joined. 17:33:55 -!- ^v has quit (Read error: Connection reset by peer). 17:54:30 -!- copumpkin has quit (Ping timeout: 272 seconds). 18:00:00 -!- Sprocklem has quit (Ping timeout: 245 seconds). 18:05:04 -!- oerjan has quit (Quit: leaving). 18:11:48 -!- Sprocklem has joined. 18:12:39 -!- Bike has quit (Ping timeout: 260 seconds). 18:24:49 -!- Taneb has joined. 18:25:11 Today I fell asleep in a lecture so I was pretty confused 18:25:29 (I could actually hear the lecturer in my sleep but in my dreams he was talking about sudoku) 18:25:39 (he was really talking about integration) 18:25:59 Anyway, I was pretty confused, especially how a particular inequality he gave was supposed to work 18:26:34 sleep causes confusion => don't sleep 18:26:52 So I asked the lecturer 18:27:16 -!- asie has quit (Quit: My MacBook Pro has gone to sleep. ZZZzzz...). 18:27:17 Turns out, he made a ridiculously huge mistake 18:29:08 Taneb: this sort of thing happens a lot 18:29:28 two out of four exams I've marked, I found mistakes in at least one question after the exam had already been sat 18:29:37 :O 18:30:20 (I didn't get to see them in advance) 18:34:38 -!- Sprocklem has quit (Ping timeout: 240 seconds). 18:38:58 Oh wow my flatmates made me a birthday cake 18:39:00 -!- Taneb has quit (Quit: brb). 18:43:07 @tell Taneb Joyeux anniversaire! 18:43:07 Consider it noted. 18:44:27 I made some Dungeons&Dragons spell to block 8th and 9th level spells. It cannot block any lower level spells, you cannot cast any other spells or attack while it is active, and it costs experience points, but it is a 1st level spell. 18:45:56 -!- copumpkin has joined. 18:50:57 -!- conehead has quit (Quit: Computer has gone to sleep.). 18:52:15 -!- Bike has joined. 18:59:42 -!- Taneb has joined. 19:08:07 I'm beginning to harbour a profound hatred towards CUPS. now my documents reach the printers, but printing a PDF produces enlightening knowledge on its internal postscript structure. 19:08:42 Do files other than PDF work? 19:09:09 boily: the best print fuckup I've ever seen involved a solaris machine that managed to print 97 pages of postscript 19:09:41 zzo38: haven't tried them yet. I'll see what happens with libreoffice... 19:09:45 On Linux computer I have just used something like "dvilj4 - < paper.dvi | lp" which works fine to print DVI files. 19:10:10 coppro: seems that I'm on a solaris machine, then. or if I'm not, somewhere on the floor there looms the Spirit of Solaris. 19:11:19 @messages-loud 19:11:19 boily said 28m 11s ago: Joyeux anniversaire! 19:11:24 Thanks! 19:11:53 how old are you now? 19:12:12 (hm. libreoffice calc froze...) 19:12:12 coppro: hmm, did the solaris machine send the printer a postscript program that printed the postscript program then? 19:12:25 imo Taneb is older than time itself 19:12:32 olsner: I dunno 19:12:34 probably 19:12:50 shachaf: I think Taneb is vaguely half as young as elliott 19:13:00 boily, 19 19:13:11 olsner: i was closer 19:15:47 elliott: are you $((2 * 19)) year old? 19:16:30 ok, so printing an .ods file does not work. what the fungot is wrong with printing in the linux world? 19:16:30 boily: it can copy regions instead of cells... you can code for 1459 plus the ctcp and dcc ' specs' you find through google, then write some simple html js to exercise them. 19:17:00 fungot: way too roundabout for my tastes. I'd like a simple solution that just plain works. 19:17:00 boily: quit his work and told his wife and kids after drinking absinthe what they didn't tell me where it came from. :) that's not really helping much. 19:17:34 fungot: I already don't drink absinthe. the problem lies somewhere else. 19:17:34 boily: what about code that changes the value of var right away? :p wait, i misunderstood 19:17:41 fungot: bin tiens. 19:17:42 boily: there's not much to change.): resemblance of an application is silly, then. tag along, if you can get spin by yourself 19:17:54 * boily spins in his chair 19:19:59 boily: Try doing it the way I did it to see if that way works better. 19:21:24 -!- Phantom_Hoover has joined. 19:22:36 (You need a PCL printer in order for that to work, though.) 19:23:14 boily: convert to ps, netcat to printer? how hard can it be 19:23:32 Aww man, I got distracted and haven't had my dinner yet 19:23:42 I was going to through some things together and make a really weird meal 19:25:56 olsner: Printing can be pretty https://dl.dropboxusercontent.com/u/113389132/Misc/20130821-gutenprint.jpg hard. 19:26:16 -!- augur has quit (Remote host closed the connection). 19:26:45 olsner: those are now undetectable printes because the CUPS guys decided to remove ESSENTIAL FEATURES AND NOW I CAN'T FUNGOTTING PRINT NOTHING AAAAAAAAAAAAAAAAAAAAAAAAAAAH BANDE D'ENFOIRÉS PAS FOUTUS DE FAIRE DE QUOI DE STABLE AAAAAAAAARGH! 19:27:14 fungot: how do you feel about that 19:27:14 shachaf: are you saying i'm an f- word?) balance exercises are very boring 19:27:32 fungot: To be fair, you kind of *are* an "f- word". 19:27:32 fizzie: but then that would be handy 19:27:33 p. sure boily is saying you're an f- word. 19:28:45 I like fungot. Fungot likes me. we are friends. 19:28:45 boily: i will conquer the earth with my fnord fnord tomorrow. but that's just geeky can you get many libraries for c too. 19:28:53 shachaf: see? ↑ 19:29:26 fungot likes everybody. 19:29:27 shachaf: other people apparently have no problem with that?! just apply methods to me, though 19:29:27 and I am calm. I am very calm. I exude zen. 19:30:28 boily: calm like a BANDE D'ENFOIRÉS PAS FOUTUS DE FAIRE DE QUOI DE STABLE? 19:30:36 soon ripe. soon rotten. soon gone. but not fungotten. 19:30:36 shachaf: but it'd still be sufficiently terse to be a dos 6.22 install disk and complained about my computer not having a chimp handy, i guess 19:31:20 "are you saying i'm an f- word?" is incredibly insightful, given that its name was used as one two lines ago 19:31:43 olsner: LA LA LA LA LA ♪ 19:32:32 so insightful 19:32:53 sometimes i think fizzie twiddling fungot's knobs behind the scenes 19:32:53 shachaf: because he is in the way of eventual development of ai on par with e.g. ( sqrt square double), and the 19:33:55 fungot: and the? 19:33:55 shachaf: i get the basic idea is the same 19:34:01 -!- Sprocklem has joined. 19:34:17 shachaf: are you implying illicit hot f-on-f action? 19:34:29 -!- Bike has quit (Ping timeout: 248 seconds). 19:35:11 who broke the wiki? 19:36:19 Did I? 19:36:36 elliott: ☝ 19:36:37 ~yi 19:36:37 Your divination: "Abounding" to "Skinning" 19:36:54 myname: the oracular tools are of no help here. 19:36:58 imo fungot is better than metasepia 19:38:35 of course fungot is better. my bot is dangerously encroaching on the Vaporware Territory more and more. 19:38:35 boily: anyone knows of such a name could have been told bad things then. as you probably read, i also mean it, should the link to 19:38:53 fungot: hey, no dissing my bot. 19:38:53 boily: meybe because they are utf8, but it was 19:39:30 fungot: who's the best bot? 19:39:30 shachaf: richard stallman, right?") was undefined. :) the recursive one be printing more? or is this getting the client code uses '' in the " language engineering programme". 19:39:32 -!- asie has joined. 19:39:56 Richard Stallman: good friend, best bot. 19:40:28 fungot: good bot, best friend. 19:40:28 shachaf: hm probably that's because you just call scheduler whenever you want to map a function that takes no arguments)" 19:40:33 hm 19:40:33 INSTALL GENTOO 19:40:39 fungot: If only you could look up METAR reports. 19:40:39 fizzie: in this case, would you 19:40:48 I assume there are decent bison/flex like libraries for python? 19:41:01 or even better 19:41:09 one that generates directly an AST 19:42:28 I was also going to try and install Arch onto my laptop 19:42:55 installing Arch is always a nice thing to do. 19:43:10 fungot: are you sentient yet 19:43:10 shachaf: bye for today 19:45:36 goodbye fungot, sleep dreams 19:45:36 olsner: studying x) 19:45:53 fungot: ☹ 19:45:53 shachaf: how's lisppaste work? ( x false? false: true) that was held in bingen am rhein near frankfurt. though on occasion i will have to 19:46:40 -!- Phantom_Hoover has quit (Ping timeout: 245 seconds). 19:48:38 ~metar EFRO 19:48:39 EFRO 041920Z AUTO 09006KT 9999 SCT012 BKN060 BKN080 M03/M03 Q0989 19:48:45 ~metar CYUL 19:48:45 CYUL 041900Z 07002KT 30SM SCT240 03/M10 A3069 RMK CI3 SLP395 19:48:55 HAH! for once it's colder over there! 19:49:52 -!- Halite has quit (Read error: Connection reset by peer). 19:52:09 -!- Phantom_Hoover has joined. 19:57:12 -!- Bike has joined. 20:02:12 -!- conehead has joined. 20:04:03 -!- Sprocklem has quit (Ping timeout: 272 seconds). 20:11:05 have anyone here tried bitmessage? 20:11:16 -!- MindlessDrone has quit (Quit: MindlessDrone). 20:11:35 What is that? 20:12:15 http://tptp.cc/images/ultra30_hardstatus.png 20:12:17 meh edge router 20:12:23 encrypted P2P messaging à la bittorrent/bitcoin. 20:12:24 ~metar egnm 20:12:24 --- Station not found! 20:12:28 ~metar EGNM 20:12:29 ~metar EGNM 20:12:29 EGNM 041950Z 27004KT CAVOK 03/02 Q0995 20:12:29 EGNM 041950Z 27004KT CAVOK 03/02 Q0995 20:16:56 Is there a way to get a description of what /dev/sdb represents so I don't overwrite the wrong thing? 20:19:32 Taneb: if you search in /sys/block/sdb, you'll find stuff. 20:19:38 (stuff that I'm exploring.) 20:22:18 you could also try gparted. quick visual description of what's going on with your storage. 20:22:50 I worked it out 20:25:19 you could also file -s /dev/sdb to get some information about what it contains 20:26:47 «/dev/sda: DOS/MBR boot sector; GRand Unified Bootloader, stage1 version 0x3, stage2 address 0x2000, stage2 segment 0x200 DOS/MBR boot sector DOS executable (COM), boot code» 20:26:53 (I really need to update that grub.) 20:27:49 "/dev/sda: no read permission" well that went well. 20:28:34 wait, why com 20:29:21 -!- Sprocklem has joined. 20:46:32 -!- nisstyre has joined. 20:50:31 -!- Sprocklem has quit (Ping timeout: 265 seconds). 20:57:09 -!- john_metcalf has joined. 21:06:25 -!- asie has quit (Quit: My MacBook Pro has gone to sleep. ZZZzzz...). 21:07:55 -!- Phantom_Hoover has quit (Ping timeout: 245 seconds). 21:10:20 Tempted to wear a bow tie to my lectures tomorrow and see how many people notice 21:10:28 -!- Ghoul_ has quit (Remote host closed the connection). 21:10:58 why today in particular 21:11:18 -!- Uguubee1111113 has quit (Quit: Uguubee1111113). 21:11:23 kmc, you mean tomorrow? 21:12:00 why tomorrow in particular 21:12:10 is it for guy fawkes day 21:12:25 tomorrow is also election day in the States 21:12:46 No reason 21:13:19 kmc: what's being elected? 21:13:49 president of england 21:13:55 we get to decide that now 21:13:59 that's right 21:14:14 hmm 21:14:18 nothing nation-wide, some local stuff 21:14:23 governor of Virginia apparently 21:14:44 here in SF we have some ballot measures about whether to build condos on the waterfront 21:14:47 v. controversial 21:15:11 i don't have much sympathy for the people who want rents to be low and also want there to be no new development 21:15:23 but I don't know the details of this project or whether one should vote for or against it 21:17:30 one thing I've heard is that the "no" campaign is funded by people who already live in luxury buildings and don't want their views spoiled 21:17:40 and they are trying to cast it as a populist anti-gentrification thing 21:19:02 -!- ggherdov has quit (Write error: Connection reset by peer). 21:19:03 -!- upgrayeddd has quit (Remote host closed the connection). 21:19:10 there can be a controversy over anything 21:19:18 as I'm finding out in NetHack 4 21:19:28 ais523\unfoog, no there can't, that's ridiculous 21:19:34 What controversy is there in NetHack 4? 21:19:41 zzo38: oh, whenever I change anything 21:19:43 someone dislikes the change 21:19:56 Then make the fork, if everyone dislikes it 21:20:07 normally more people like it than dislike it, though 21:20:12 -!- sebbu has quit (Ping timeout: 240 seconds). 21:20:12 zzo is all about socially conscious software engineering 21:22:42 -!- Sprocklem has joined. 21:23:05 "every change should result in a separate fork" lol 21:23:32 No, but if everyone dislikes it you can make a forked version 21:23:39 Maybe someone else doesn't dislike it. 21:27:21 What changes are those anyways? 21:27:52 -!- Phantom_Hoover has joined. 21:30:34 quintopia: scarily close to the github model 21:33:18 Tempted to wear a bow tie to my lectures tomorrow and see how many people notice 21:33:27 there's a guy in my year who does this to every lecture 21:33:35 Oh dear 21:33:42 it gives people a good point of reference, i guess 21:33:44 It feels like the slope is going to be slippery 21:33:57 I wear a hat to algebra lectures 21:34:01 he also wears a suit along with the bow tie 21:34:18 I'm just going to wear casual clothes, plus a bow tie 21:34:27 i'm told i managed to get a reputation simply by walking up the stairs in an unusual way 21:34:37 0_0 21:36:26 Taneb: the best way to get attention is to where a pink bucket hat and take very long strides walking as fast as possible everywhere you go 21:36:30 *wear 21:36:42 quintopia, someone's already doing that 21:36:55 damn 21:37:04 wouldn't want you to be a copycat 21:38:13 work out an unusual way to walk up stairs? 21:38:31 Phantom_Hoover, I pretty much run up stairs and fly down them 21:39:47 well flying's always a crowd-pleaser 21:42:02 pyparsing is kinda nice. 21:42:26 now I can start to target x86 :) 21:50:29 -!- augur has joined. 21:53:56 -!- boily has quit (Quit: GALVAUDE!). 21:54:04 -!- metasepia has quit (Remote host closed the connection). 22:11:05 -!- Ghoul_ has joined. 22:16:37 -!- oerjan has joined. 22:18:54 remember remember the 4th of november 22:19:01 i mean, happy birthday Taneb 22:20:09 oh is it Taneb Day already 22:20:34 poor Taneb, always a tiny step from being the main villain 22:21:34 `? Taneb Day 22:21:36 Taneb Day? ¯\(°_o)/¯ 22:22:41 Happy Taneb++ ! 22:23:15 ...it was Taneb day yesterday 22:23:25 i am not sure if we should include birthdays in wisdom/ 22:23:38 Which day is that? 22:23:38 -!- Sprocklem has quit (Ping timeout: 264 seconds). 22:23:42 Taneb: oops it's that late already 22:23:50 bloody timezones 22:24:40 what timezone were you born in? 22:24:45 ok happy Guy Fawkes a-bit-early-night 22:25:09 * kmc was born in America/Chicago, he guesses 22:25:49 were you born in chicago 22:25:51 no 22:25:58 I was born in GMT 22:26:04 At 0647 22:26:59 i was born in Asia/Jerusalem 22:27:07 it took me three days (so i'm told) 22:27:17 slowpoke (your poor mother) 22:27:44 :( 22:29:12 so is Taneb 20 now or 22:29:51 i think i was born in this building https://maps.google.no/maps?hl=no&ll=66.01835,12.6189&spn=0.000607,0.00206&t=h&z=19 22:30:09 at least that's what used to be the main hospital 22:30:48 Phantom_Hoover, 19 22:31:42 -!- mrhmouse has quit (Quit: Leaving.). 22:32:18 oh, that's pretty far north 22:32:46 looks like it's north of iceland even 22:33:51 given the name, iceland is surprising far south compared to scandinavia 22:34:52 hm interesting, zooming all the way out to see iceland and back in doesn't keep the place. 22:34:59 maybe iceland was the name to be given to greenland, but someone mixed them up 22:36:34 olsner: the amusing theory is that the people who found iceland wanted to keep others out while the people who found greenland wanted others to join them... 22:36:39 i always heard that iceland was named that because they had a bad winter and greenland was called that basically as a marketing trick 22:36:57 although at the time, greenland was much warmer than it is now. 22:36:57 http://www.gcmap.com/mapui?P=66.01835+N+12.6189+E&MS=wls&MP=o&MC=66.01835N12.6189E&DU=mi 22:37:16 and iceland _does_ have a lot of glaciers. 22:39:26 -!- sebbu has joined. 22:40:07 -!- sebbu has quit (Changing host). 22:40:07 -!- sebbu has joined. 22:41:54 -!- upgrayeddd has joined. 22:46:16 wow, I managed to zoom back in to the same place 22:51:47 `addquote sometimes i think fizzie twiddling fungot's knobs behind the scenes shachaf: because he is in the way of eventual development of ai on par with e.g. ( sqrt square double), and the 22:51:48 oerjan: he is my idol. like a splitter had failed or my wiring had gone bad, so i can benefit from the knowledge of others. 22:51:52 1127) sometimes i think fizzie twiddling fungot's knobs behind the scenes shachaf: because he is in the way of eventual development of ai on par with e.g. ( sqrt square double), and the 22:52:42 oerjan: what, and not the f- word quote? 22:52:50 fizzie: you're fungot's idol! 22:52:50 nooodl: i'm not done ( no output and some for loops 22:53:17 How... nice. 22:53:38 fungot is my idol. 22:53:38 shachaf: whoa!! i'm in a twist contest!! i'm in the topic? :) 22:53:39 question: will i ever remember how NFPA 704 works without looking it up 22:53:57 TWIST: fungot is my idol 22:53:57 shachaf: sure it is 22:54:14 `addquote olsner: those are now undetectable printes because the CUPS guys decided to remove SSENTIAL FEATURES AND NOW I CAN'T FUNGOTTING PRINT NOTHING AAAAAAAAAAAAAAAAAAAAAAAAAAAH BANDE D'ENFOIRÉS PAS FOUTUS DE FAIRE DE QUOI DE STABLE AAAAAAAAARGH! fungot: how do you feel about that shachaf: are you saying i'm an f- word?) balance exercises are very boring fungot: To be fair, you kind of *are* an "f- word". 22:54:14 oerjan: lament should switch falsebot to f! :) i should've thought of that too 22:54:16 Artificial sarcasm. 22:54:18 1128) olsner: those are now undetectable printes because the CUPS guys decided to remove SSENTIAL FEATURES AND NOW I CAN'T FUNGOTTING PRINT NOTHING AAAAAAAAAAAAAAAAAAAAAAAAAAAH BANDE D'ENFOIRÉS PAS FOUTUS DE FAIRE DE QUOI DE STABLE AAAAAAAAARGH! fungot: how do you feel about that shachaf: are you saying i'm an f- word 22:54:22 argh 22:54:28 `revert 22:54:28 oerjan: good cutoff imo 22:54:31 Done. 22:55:00 pls translate "BANDE D'ENFOIRÉS PAS FOUTUS DE FAIRE DE QUOI DE STABLE AAAAAAAAARGH!" idiomatically 22:55:00 shachaf: boily's message has colors in it, which are hard to paste through tmux + irssi 22:55:04 i want to know what it means 22:55:10 my favourite thing about xflux: you can run two processes to double the effect 22:55:17 oerjan: i think it just has bold 22:55:27 oerjan: but if you add even one more character you'll have to cut back somewhere else 22:55:42 http://www.funraniumlabs.com/wp-content/uploads/2011/12/IMG_2643-768x1024.jpg and now i'm terrified 22:55:52 `addquote olsner: those are now undetectable printes because the CUPS guys decided to remove ESSENTIAL FEATURES AND NOW I CAN'T FUNGOTTING PRINT NOTHING AAAAAAAAAAAAAAAAAAAAAAAAAAAH BANDE D'ENFOIRÉS PAS FOUTUS DE FAIRE DE QUOI DE STABLE AAAAAAAAARGH! fungot: how do you feel about that shachaf: are you saying i'm an f- word?) balance exercises are very boring fungot: To be fair, you kind of *are* an "f- ... 22:55:53 oerjan: wish i didn't recognise backstreet boys. ( the a inside the let, before `body...', there's a 50-50 chance of seeing 00 or 11. but you should be 22:55:56 1128) olsner: those are now undetectable printes because the CUPS guys decided to remove ESSENTIAL FEATURES AND NOW I CAN'T FUNGOTTING PRINT NOTHING AAAAAAAAAAAAAAAAAAAAAAAAAAAH BANDE D'ENFOIRÉS PAS FOUTUS DE FAIRE DE QUOI DE STABLE AAAAAAAAARGH! fungot: how do you feel about that shachaf: are you saying i'm an f- wo 22:55:58 ... word". 22:56:10 smooth 22:56:16 oerjan: like i said 22:56:34 shachaf: i was hoping the two following spaces were included :( 22:56:47 Following spaces? 22:56:48 oh wait it wasn't even the end 22:56:51 right 22:56:53 way back 22:56:59 `revert 22:57:01 fungot: what are you, jonathan hoag? 22:57:01 shachaf: not exactly. sisc isn't a compiler or interpreter on you? 22:57:02 Done. 22:57:03 too damn long 22:57:22 fungot: nobody can interpret shachaf.. 22:57:22 FireFly: well it is _nearly_ trivial, but not like that? :) 22:57:28 oh? 22:57:35 fungot: except you, perhaps 22:57:35 FireFly: evaluate ( setq paredit-backward-delete-key " backspace" ( which it, and you split it up. :) must've been a burp. first time i was trying to enter the us from canada, i'd suggest lisp-like macros, here. 22:57:57 So trivial. 22:59:23 kmc: "bunch of idiots who couldn't give a fuck about making anything stable aaaaaaargh!" i think 23:00:25 fungot: what am i asking you right now 23:00:25 shachaf: the dots are rather important... 23:00:30 the computers will take over only after we've already been driven mad by them. 23:00:31 fungot: what am i asking you right now... 23:00:32 shachaf: yes, " swipe" is understood to mean unzip and look at two buffers at once, like they send ,user if scheme48-package is ( user) or ,config if it's ( config) loads the packages.scm file in the last box 23:01:15 oerjan: best of luck getting a too long quote into a too short line 23:01:38 olsner: a procrustean task 23:01:49 fungot: the quote is too long, wdyt? 23:01:49 olsner: fiz miten m saan ne fnord fnord med fnord in fnord ( btw typo, says fnord at one point 23:01:50 profungot 23:01:51 shachaf: what do you have anything in common with java, no? 23:01:58 fungot: no. 23:01:58 shachaf: do you think 23:02:01 fungot: no. 23:02:02 shachaf: i am not in the helpdesk.... anyone have any more dark secrets to worry about 23:02:28 this incident will be reported 23:02:35 -!- ggherdov has joined. 23:03:06 fungot: which of the fnords were a typo? 23:03:06 FireFly: i think haskell is mostly very useless, unless you can guarantee by an additional code analysis that this procedure is for), fnord 23:03:27 fungot: well even spj says that 23:03:27 oerjan: that doesn't contradict me at all 23:03:30 fungot is too good 23:03:30 shachaf: in my head 23:03:49 Wonderful 23:04:04 fungot: are you pondering what i am pondering 23:04:04 oerjan: but its not working out". " you think of using a full-featured programming language to express the geometry of the cylinder. that's fnord 23:04:12 @brain are you pondering what i am pondering 23:04:12 If I could reach you I would hurt you. 23:04:16 @brain are you pondering what i am pondering? 23:04:17 It must be inordinately taxing to be such a boob. 23:04:24 I'd quoteadd the fungot-oerjan-fungot interaction there, but I'm afraid I'd screw up 23:04:25 FireFly: what do you want 23:04:25 @brain Are you pondering what I'm pondering? 23:04:26 What can I do for fun, Pinky? That's it! I'll send several 23:04:26 bills to Senate for ratification, then veto them all! 23:04:37 fungot: I just stated what I want! 23:04:37 FireFly: what is love?? fnord wondering if a paper exists on the topic. 23:04:41 fungot: you could totally pass for a troll in a programming language channel 23:04:41 shachaf: there are some gui toolkits out there written for scheme48 somewhere around here. i hope. 23:04:48 See? 23:04:49 -!- Bike has quit (Ping timeout: 272 seconds). 23:05:15 fungot: a paper on the topic of what love is? Good idea. 23:05:15 FireFly: mmm. how do you feel with continuations?)) to be 2 instead of 1... on 0 it should die 23:05:25 Deep 23:06:05 -!- realz has quit (Ping timeout: 272 seconds). 23:06:22 pinky was here but left 23:06:33 @brain are you thinking what oerjan is thinking? 23:06:34 Promise me something, Pinky. Never breed. 23:06:40 * shachaf sighs. 23:06:45 fungot is better than lambdabot. 23:06:46 shachaf: that is a constant. a function practically always needs all it's arguments anyway, that interpreter doesn't have interpreters at all, 23:07:17 fungot: you're certainly full of yourself 23:07:17 shachaf: that's excluding docs and generated files not *that* much 23:07:40 fungot: you have docs? 23:07:40 oerjan: watch the videos for diffy q's on the mit ocw, they're really the same, is the ( loop 1 2) is written in scheme 23:08:10 if fungot wasn't full of itself, what would be in the left-over space? 23:08:11 olsner: state in this case)? :) i don't see why 23:08:29 oerjan: There's a README in the repository nowadays. 23:08:36 fungot's docs are the videos for diffy q's on the mit ocw? i'm not surprised. 23:08:37 shachaf: hence " tribo" " fibo" in 3 terms 23:08:40 ooh 23:08:50 fungot: naturally. 23:08:50 FireFly: no sharp edges or flat surfaces and my arms were floating comfortable with fingers just above the min and so on 23:09:05 oerjan: For all the people interested in running their own little fungots, you see. 23:09:05 fizzie: does the c backend is probably the trivial version, since i need values returned from it. 23:09:13 FireFly: is fungot a natural transformation 23:09:14 shachaf: y is ( 2 3) 23:09:40 why do you ask me? 23:09:45 surely fungot would know better 23:09:45 FireFly: waddler's fnord gf :) i need dynamic class support ( dynamic fnord of c modules", which is in development. you don't like 23:10:28 Fun fact: the first fnord above is "soon-to-be" in the logs. 23:11:53 fizzie: What's the "fnord" thing about? 23:11:55 It's annoying. 23:12:28 is this when kmc tells me to read that book 23:13:35 -!- KingOfKarlsruhe has quit (Quit: ChatZilla 0.9.90.1 [Firefox 25.0/20131025151332]). 23:13:57 fungot: whence fnord? 23:13:57 olsner: fortunately the haskell compiler... sure i could pull that one off 23:14:07 fnord means that the trigrams don't perfectly align as i recall 23:14:31 It's basically an OOV word indicator. See, you get "better" (FSVO...) language models when you leave out words that occur only, say, once; but of course when generating from them, sometimes the "rare word" token comes out. (Removing all 'grams with OOV words would also be a possibility.) 23:15:40 ("Leave out" meaning "replace with a single OOV token".) 23:15:43 fizzie: couldn't you just pull the OOV word back in at the last minute when it looks like fnord would be printed? 23:16:30 "OOV"? 23:16:43 FireFly: Out-of-vocabulary. 23:16:48 Ah 23:17:34 quintopia: It's not unambigous which word it is (the whole point of the replacement token is to get better counts, after all) and anyway it's not recorded in the model. 23:17:47 -!- realz has joined. 23:17:47 -!- realz has quit (Changing host). 23:17:47 -!- realz has joined. 23:17:50 (Technically, sure, it could be done.) 23:18:08 fizzie: by, for instance, saving them in a separate list, and choosing arbitrarily when ambiguous 23:19:26 or you could use something like `words to make up a new word 23:19:57 meh that's no better than fnord 23:21:26 -!- conehead has quit (Ping timeout: 240 seconds). 23:23:09 Sounds like work. The list would need to go inside the tree, which would involve changing the format. Also, it would be quite nontrivial to add to the current VariKN-based training (which actually just drops OOV words), which the "irc" style predates. 23:23:15 (I should retrain it one day, but I'm afraid it's lose some of its character.) 23:23:26 s/'s/'d/ 23:35:04 imho keep fnord forever 23:37:31 You can make it add by the chance, I suppose, so it is sometimes "fnord" 23:41:52 Haneb 23:42:18 shellochaf 23:43:51 G'dgevd 23:44:38 I'm not even gonna try to pronounce that 23:44:42 -!- Bike has joined. 23:45:16 Bike for president 23:47:08 -!- nooodl has quit (Ping timeout: 240 seconds). 23:47:46 fuckyeah 23:52:10 -!- Bike has quit (Ping timeout: 268 seconds). 23:53:20 fungot for president! 23:53:21 olsner: http://www.schemers.org/ documents/ standards/ r5rs/ html/ r5rs-z-h-9.html%_idx_560 even exist! 23:53:43 spoken like a fungot 23:53:43 olsner: oh i see it." i think 23:54:53 good night fungot 23:54:53 olsner: where is the final code maps easily to many back ends, and there's around the nick instead of. would you still be here in the first place 23:54:56 Hmm 23:55:02 I just thought of a flaw in my plan 23:55:23 I'm going out tomorrow night 23:55:26 the plan not to even try pronouncing g'dgevd? 23:55:36 olsner, the plan to wear a bow tie 23:55:53 bow ties are not attached permanently, are they? 23:56:03 Who knows 23:56:28 they can be removed via painful laser surgery 23:56:33 you should go out in the bowtie 23:57:48 -!- realz has quit (Ping timeout: 240 seconds). 23:57:56 quintopia, last time I went out in a bowtie I got mistaken for Mark Zuckerberg 23:59:00 did you leverage that to get laid? 23:59:10 -!- Phantom_Hoover has quit (Remote host closed the connection). 2013-11-05: 00:00:07 quintopia, a) I was only mistaken for him by a drunk middle-aged unattractive man, and b) I'm asexual 00:00:38 And c) no 00:00:57 i don't see how the being mistaken for mark zuckerberg by such an outlier has any bearing on the present decision on whether to go out in a bowtie 00:01:44 Hmm, maybe you're right 00:06:54 -!- carado has quit (Ping timeout: 252 seconds). 00:13:01 -!- Bike has joined. 00:13:30 -!- realz has joined. 00:13:42 -!- realz has quit (Changing host). 00:13:42 -!- realz has joined. 00:35:35 do people actually use fibonacci heaps for anything 00:37:34 http://www.quora.com/What-is-a-Fibonacci-Heap?share=1 has an answer in the negative from "Adam D'Angelo, former algorithms TA" 00:41:50 kmc: I've used a heap library that had a fibonacci heap as one of the backends 00:41:57 but I'm not sure whether it used that backend or not 00:42:12 when I've written heaps manually, I typically use binary heaps 00:43:19 hmm… I remember that paper which had an article hitting all the heap complexity bounds in actual time 00:43:21 rather than amortized time 00:43:30 using a really crazy and complex heap impl 00:44:40 http://exoplanets.org/ attention astro nerds 00:45:21 btw, I didn't tell you about my latest programming project that I haven't told you about yet 00:45:36 ais523\unfoog: that's neat 00:45:37 it's not particularly eso, but it's about the same order of bad idea 00:45:42 I guess there is general research on de-amortization 00:45:57 basically, it's a deparser for text documents 00:46:00 -!- yorick has quit (Remote host closed the connection). 00:46:14 you know how you can format HTML or Texinfo or nroff or whatever as text? 00:46:26 this would go the other way, with no knowledge of the source format 00:46:31 trying to infer how various things were formatted 00:46:44 I can think of a huge many usecases for this 00:46:49 but it's likely to be quite difficult to write 00:47:06 there are some startups doing this, or similar 00:47:13 finding PDFs on the web and extracting them to data tables 00:47:30 that's not exactly what I want to do, but it's the same field 00:49:24 actually the motivating example was to write a program that could display all the random files lying around /usr/share/doc in whatever format the user wanted 00:49:30 and the motivating reason for /that/ was writing a better man/info/yelp 00:49:56 I was going to say "smoothsort", but it turns out that uses a completely different sort of heap. 00:50:38 The Leonardo numbers, apparently. 00:50:55 (anyone who hangs out in #acehack will know that I have trivial motivating reasons for really complex projects) 00:52:01 I think I'll start by converting everything to elastic tabs 00:52:09 (something that text editors should do anyway) 00:53:56 kmc: i feel like i should read _Purely-Functional Data Structures_ 00:53:58 did you read it 00:55:24 -!- Taneb has quit (Quit: Leaving). 00:58:11 -!- john_metcalf has quit (*.net *.split). 00:58:11 -!- FreeFull has quit (*.net *.split). 00:58:11 -!- ski has quit (*.net *.split). 00:58:11 -!- Lymia has quit (*.net *.split). 00:58:11 -!- rodgort has quit (*.net *.split). 00:58:11 -!- FireFly has quit (*.net *.split). 00:58:19 -!- ski has joined. 00:58:24 some of it 00:58:26 it's good 00:58:29 -!- FreeFull has joined. 00:58:38 -!- Lymia has joined. 00:58:47 -!- rodgort has joined. 00:58:57 -!- FreeFull has quit (Changing host). 00:58:57 -!- FreeFull has joined. 00:59:13 -!- Lymia has quit (Changing host). 00:59:13 -!- Lymia has joined. 01:00:42 -!- FireFly has joined. 01:05:26 :t flip (foldr id) 01:05:27 [c -> c] -> c -> c 01:07:08 > (flip (foldr id)) [succ, pred] 17 01:07:10 17 01:07:14 metal 01:07:26 > (flip (foldr id)) [(7+),(2*)] 17 01:07:27 41 01:08:44 @pl \f.\g.\h.\x.g(f(h(x))) 01:08:44 (line 1, column 3): 01:08:44 unexpected "." 01:08:45 expecting letter or digit, operator, pattern or "->" 01:08:53 @pl \f->\g->\h->\x->g(f(h(x))) 01:08:56 flip ((.) . (.)) . (.) 01:08:57 optimization suspended, use @pl-resume to continue. 01:09:06 bleh, lambdabot, why don't you work on Verity? 01:09:08 @pl-resume 01:09:14 is @pl still ill 01:09:14 flip ((.) . (.)) . (.) 01:09:14 optimization suspended, use @pl-resume to continue. 01:09:21 @pl-resume 01:09:24 oerjan: I think so 01:09:26 i've yet to see @pl-resume give a different answer 01:09:33 flip ((.) . (.)) . (.) 01:09:34 optimization suspended, use @pl-resume to continue. 01:09:55 anyway, that function seems to be the programming-language version of the functor \Rightarrow 01:09:57 which is kind-of important 01:10:00 so I was wondering if it had a name 01:10:47 @pl \f g h x -> g (f (h x)) 01:10:50 flip ((.) . (.)) . (.) 01:10:50 optimization suspended, use @pl-resume to continue. 01:10:52 @pl \(f,g)->\(x,y)->(f(x),g(y)) 01:10:52 uncurry (flip flip snd . (ap .) . flip flip fst . ((.) .) . flip . (((.) . (,)) .)) 01:11:00 that's even worse 01:11:03 that one's \otimes 01:11:15 and it looks reasonable that that one might have a name 01:11:18 or at least a short impl 01:11:24 @pl \f g h -> g . f . h 01:11:28 flip ((.) . (.)) . (.) 01:11:28 optimization suspended, use @pl-resume to continue. 01:11:44 is Haskell this bad at functors? 01:11:52 @pl \f g -> (.) (g . f) 01:11:56 ((.) .) . flip (.) 01:11:56 optimization suspended, use @pl-resume to continue. 01:11:57 isn't "\(f,g)->\(x,y)->(f(x),g(y))" a short implementation 01:12:41 :t uncurry (***) 01:12:42 Arrow a => (a b c, a b' c') -> a (b, b') (c, c') 01:12:57 uh i'm pretty sure arrow is the antichrist....>??? 01:13:03 OKAY 01:13:23 going off reliable esoteric information here 01:13:23 -!- prooftechnique has joined. 01:13:37 > uncurry (***) ((+1),(*2)) (5,10) 01:13:37 in the categorical semantics I'm working on 01:13:38 (6,20) 01:13:38 uncurry = id 01:14:01 oerjan: I like your impl 01:14:03 ais523\unfoog: anyway @pl doesn't know much about Arrows. 01:14:12 right 01:14:27 Arrow's a bit of an ironic name, though 01:14:46 given that arrow/morphism in categorical semantics = function in programming language 01:15:59 sometimes I feel that Haskell isn't as category-theoretical as its supporters make it out to be 01:17:16 i feel betrayed. 01:19:09 ais523\unfoog: well Arrow is a subclass of Category nowadays. 01:19:20 oerjan: that makes even less sense 01:19:21 in particular, (->) is only one instance. 01:19:26 category theory doesn't work like that 01:19:37 the name Arrow is not particularly well-chosen, though. 01:20:15 It seems better it should have: functor between categories, tensor categories, fanout category, etc, instead of being like such Arrow class 01:20:52 ais523\unfoog: the idea is that a value of type Arrow a x y is an arrow from x to y in a category given by a. 01:21:00 oerjan: right 01:21:18 although the class heaps on stuff that isn't just arrow requirements. 01:21:26 (Category alone has those.) 01:21:32 the only actual requirement is for a composition operator 01:21:33 I think it'd be fun to make a nethack clone with ed keybindings 01:21:49 prooftechnique: NetHack 4 (my fork) has rebindable keys 01:22:02 not sure if ed's keybindings even remotely correspond to the commands ed has, though 01:22:08 prooftechnique: Try it, what key would they command 01:22:18 ais523: What changes did you make though? 01:22:22 zzo38: loads 01:22:25 mostly to internals 01:23:03 Did you add rebindable keys or is that already in there? 01:23:52 NetHack 3.4.3 doesn't have rebindable keys 01:24:03 but the key rebinding code was copied from another NetHack fork (NitroHack) 01:24:12 O, well that is good you add it, then; it was missing then 01:24:18 however, the key /parsing/ code is new 01:28:14 OK 01:32:48 is there a bf clone that does non-deterministic computations in deterministic time? because if not, i want to make one 01:33:00 quintopia: interesting 01:33:04 a sort of quantum BF? 01:33:07 yes 01:33:08 q: what does that mean 01:33:12 everettian BF 01:33:13 actually, I think Brainfork can do that 01:33:19 * quintopia looks 01:33:21 so long as there's a way to kill threads, not sure if there is 01:33:44 who is the guy in the google logo 01:34:18 btw, Brainfork was invented before BF derivs got old 01:34:23 quintopia: The doodle today? 01:34:26 it was like the second or third semantics-changing deriv 01:34:48 prooftechnique: yes 01:34:52 i'm too lazy to click it 01:34:54 http://en.wikipedia.org/wiki/Shakuntala_Devi 01:35:02 Mental math world record or something 01:36:50 ais523\unfoog: yeah, it doesn't look like there's a way to kill forked threads in brainfork. but you can sort of do nondeterministic computations by doing some very fancy algorithming. but my idea would add no new commands and wouldn't require thread management. 01:37:04 -!- glogbackup has joined. 01:37:18 hi glogbackup 01:38:35 `welcome glogbackup 01:38:37 glogbackup: Welcome to the international hub for esoteric programming language design and deployment! For more information, check out our wiki: . (For the other kind of esoterica, try #esoteric on irc.dal.net.) 01:40:12 -!- Uguubee1111113 has joined. 01:40:52 ais523\unfoog: my idea is to have the semantics of . change to "append byte to waiting-to-output queue" and the semantics of program halt change to "if waiting-to-output queue matches the tail of the input list, output, otherwise, move all amplitude of this universe's wavefunction into the universe where the tail of the input list is equal to the contents of the current waiting-to-output queue at the moment of program instantiation" 01:41:17 obviously, , would not consume the input list, just advance an index into it 01:41:37 `run grep '^: Welcome to the' /var/logs/_esoteric/*.txt | cut -f1 -d':' | cut -f2 -d'>' | sort | uniq -c 01:41:38 grep: /var/logs/_esoteric/*.txt: No such file or directory 01:41:48 `run grep '^: Welcome to the' /var/irclogs/_esoteric/*.txt | cut -f1 -d':' | cut -f2 -d'>' | sort | uniq -c 01:42:03 wait, there's a stray ^ there 01:42:06 `run grep ': Welcome to the' /var/irclogs/_esoteric/*.txt | cut -f1 -d':' | cut -f2 -d'>' | sort | uniq -c 01:42:19 No output. 01:42:37 No output. 01:43:08 hmm 01:43:10 is it timing out? 01:43:17 `run grep ': Welcome to the' /var/irclogs/_esoteric/2013*.txt | cut -f1 -d':' | cut -f2 -d'>' | sort | uniq -c 01:43:25 or is there something wrong with the line? 01:43:31 ​ 18 /var/irclogs/_esoteric/2013-01-04-raw.txt \ 18 /var/irclogs/_esoteric/2013-01-04.txt \ 1 /var/irclogs/_esoteric/2013-01-05-raw.txt \ 1 /var/irclogs/_esoteric/2013-01-05.txt \ 1 /var/irclogs/_esoteric/2013-01-06-raw.txt \ 1 /var/irclogs/_esoteric/2013-01-06.txt \ 1 /var/irclogs/_esoteric/2013-01-07-raw.t 01:43:38 One thing is you should indicate whether you want raw or non-raw 01:43:39 oh, right 01:43:54 -!- Sgeo has joined. 01:44:13 `run grep -h ': Welcome to the' /var/irclogs/_esoteric/2013-??-??.txt | cut -f1 -d':' | cut -f2 -d'>' | sort | uniq -c 01:44:17 ​ 7 00 \ 16 01 \ 18 02 \ 6 03 \ 7 04 \ 11 05 \ 10 06 \ 11 07 \ 2 08 \ 2 09 \ 4 10 \ 10 11 \ 6 12 \ 7 13 \ 6 14 \ 11 15 \ 11 16 \ 14 17 \ 16 18 \ 15 19 \ 16 20 \ 19 21 \ 20 22 \ 18 23 01:44:36 aha, there are colons in the timestamp 01:44:40 `run grep -h ': Welcome to the' /var/irclogs/_esoteric/2013-??-??.txt | cut -f1 -d'4' | cut -f2 -d'>' | sort | uniq -c 01:44:43 ​ 7 0 \ 2 ​ \ 2 00: \ 1 00:10:3 \ 1 00:3 \ 1 00:32: \ 7 01: \ 1 01:05:3 \ 1 01:08: \ 1 01:13: \ 1 01:31: \ 1 02: \ 1 02:09: \ 1 02:56: \ 1 03: \ 1 03:19:0 \ 1 03:31:2 \ 1 03:5 \ 1 ​{^Raven^}: Welcome to the international 01:44:48 `run grep -h ': Welcome to the' /var/irclogs/_esoteric/2013-??-??.txt | cut -f4 -d':' | cut -f2 -d'>' | sort | uniq -c 01:44:50 ​ 1 ​boily \ 1 ​lambdabot \ 1 ​Phantom_Hoover \ 1 ​{^Raven^} \ 1 ​intensity \ 1 ​kyyni \ 1 ​shikhin \ 1 ​matthiaskrgr \ 1 ​simmarine_ \ 1 ​snuffeluffegus \ 1 ​audioPhil 01:44:56 this is good 01:45:02 `run grep -h ': Welcome to the' /var/irclogs/_esoteric/2013-??-??.txt | cut -f4 -d':' | cut -f2 -d'>' | sort | uniq -c | sort -rn 01:45:05 ​ 13 Bike \ 8 oerjan \ 5 monqy \ 5 kmc \ 4 sivoais \ 4 `run grep -h ' \ 3 Taneb \ 3 SirCmpwn \ 3 Sgeo \ 3 Regis_ \ 3 Fiora \ 2 yhojeyisaac \ 2 windmill \ 2 Tritonio \ 2 ThatOtherPerson \ 2 surma \ 2 sploknee \ 2 Snowyowl \ 01:45:15 :o 01:45:21 `run grep -h ': Welcome to the' /var/irclogs/_esoteric/20??-??-??.txt | cut -f4 -d':' | cut -f2 -d'>' | sort | uniq -c | sort -rn 01:45:36 ​ 22 fdhsfdsgdsg \ 19 oerjan \ 16 elliott \ 15 Bike \ 13 monqy \ 9 shachaf \ 8 ais523 \ 6 HackEgo \ 5 Taneb \ 5 sivoais \ 5 `run grep -h ' \ 5 -!- oerjan changed the topic of #esoteric to \ 5 kmc \ 5 fungot \ 5 Fiora \ 4 zzo38 \ 4 shub 01:46:10 who was fdhsfdsgdsg and why did they get welcomed so much? 01:46:16 `pastlog fdhsfdsgdsg 01:46:24 2012-03-02.txt:12:29:26: ​^ul (?so `ok fdhsfdsgdsg: Welcome to the international hub for esoteric programming language design and deployment! For more information, check out our wiki: http://esolangs.org/wiki/Main_Page)S 01:46:38 botloop, I guess 01:46:50 ais523\unfoog: sorry to be zzo38ish, but does my description above make sense? should i wiki it? 01:46:53 wait, i've been welcomed 15 times 01:46:54 ? 01:46:58 Bike: yes 01:47:11 quintopia: it needs to be explained in a bit more detail, I think 01:47:38 `run grep -h ': Welcome to the' /var/irclogs/_esoteric/20??-??-??.txt | cut -f4 -d':' | cut -f2 -d'>' | sort | uniq -c | sort -rn | grep -v '!' | xargs 01:47:43 xargs: unmatched single quote; by default quotes are special to xargs unless you use the -0 option \ 22 fdhsfdsgdsg 19 oerjan 16 elliott 15 Bike 13 monqy 9 shachaf 8 ais523 6 `run grep -h 01:47:56 bleh 01:48:09 ais523\unfoog: so it doesn't make sense? 01:48:14 `run grep -h ': Welcome to the' /var/irclogs/_esoteric/20??-??-??.txt | cut -f4 -d':' | cut -f2 -d'>' | sort | uniq -c | sort -rn | grep -v '!' | grep -v '`' | xargs 01:48:17 it almost makes sense 01:48:20 22 fdhsfdsgdsg 19 oerjan 16 elliott 15 Bike 13 monqy 9 shachaf 8 ais523 6 HackEgo 5 Taneb 5 sivoais 5 kmc 5 fungot 5 Fiora 4 zzo38 4 shubshub 4 Sgeo 4 Gracenotes 4 CHeReP 4 carado 4 andrew12 3 WeThePeople 3 tswett 3 ThePope 3 test 3 Snowyowl 3 sirdancealot 3 SirCmpwn 3 segorev 3 Regis_ 3 ogrom 3 mean 3 john_metcalf 3 Jafet 3 hi 3 GreyKnight 3 Grego 01:48:25 there, that's what I wanted 01:48:36 sorry about all the pings, everyone 01:49:02 ais523\unfoog: can you add background coloration to each number/name pair to make it easier to group them mentally? 01:49:15 quintopia: no, because my client doesn't support background colors 01:49:41 ais523\unfoog: colors are cool. lrn2bcolorful. 01:50:00 it does support foreground colors except I disabled them 01:50:15 which lead to this bug report: https://bugs.kde.org/show_bug.cgi?id=317034 01:50:32 you could be coolour with more colour. 01:51:50 -!- nisstyre has quit (Ping timeout: 264 seconds). 01:52:09 ais523\unfoog: do you know of a way to compare two positive numbers in unbounded-cell BF using less than 5 cells? 01:52:39 quintopia: does the interp support negative numbers? 01:52:47 but yeah, I think regardless, it's doable 01:52:47 sure 01:53:14 i can't think of a way to do it in less than 5 01:53:15 or, hmm 01:53:24 yeah, the way I was thinking of takes 5, if you include the two numbers themselves 01:53:37 what way are you thinking? 01:53:46 http://esolangs.org/wiki/Brainfuck_algorithms#z_.3D_x_.E2.89.A5_y 01:53:57 oh, hmm, that needs a wrapping impl 01:54:24 hadn't looked at that algo in a while 01:54:51 you can do it in 2 if you don't mind an infinite loop if one particular number is higher 01:54:56 haha 01:54:58 and don't mind destroying the original number 01:55:01 *numbers 01:55:23 let's call that "might compare" :P 01:55:58 I bet it's doable in 3 if they're all consecutive and you don't mind the algo destroying the original numbers and returning using the position of the tape pointer 01:56:20 show me 01:56:52 the method i'm thinking of requires both those conditions and still takes 5 01:59:10 -!- Sprocklem has joined. 02:00:09 actually no, that takes 4 02:00:14 put a zero either side of the two numbers you're comparing 02:00:32 then from the first number, do [->-[>]<<] 02:01:12 the two zeros never change, though 02:02:02 come to think of it, that looks like the fastest compare algo I've ever seen 02:02:34 it runs in O(a-b) if a is larger, O(a) if a is smaller, and the constant's pretty low too 02:03:11 if you had an if rather than a while, you could do it in 3 02:03:20 by changing the [>] to an if[>] 02:05:09 that's better than what i had, but the basic idea is the same. 02:05:38 but how do you do a conditional on the result? 02:05:44 without using an extra cell? 02:06:42 -!- nisstyre has joined. 02:07:26 go right one cell 02:07:29 then check for zero 02:07:50 that leaves you still uncertain where the pointer is if you find that it's zero 02:08:00 because it'll be in a different position for equal and for less than 02:08:06 but it does technically fulfil the conditions 02:09:35 no 02:09:46 one cell to the right will always be nonzero unless x=y 02:10:26 if x>y, then one cell to the right is x, and nonzero 02:10:35 if x=y then one cell to the right is x, and zero 02:10:46 if x err, no 02:10:51 it is nonzero :( 02:10:53 you're right 02:11:02 hmm 02:12:10 the problem is it leaves either x or y at zero 02:12:23 and the pointer to the left of the other one 02:12:36 i think you never test the cell to the left of x 02:12:42 so why not initialize it to 1 02:12:48 you do 02:12:53 it's tested in the loop termination 02:12:56 ah right 02:12:59 when x>y 02:13:19 what would happen if you initialized it to 1 02:13:46 you end up back there with it zero 02:13:47 you'd go round the loop again, it'd become 0, x would be tested for equality to 1 02:13:59 depending on the result you'd either end up there or to the left 02:14:09 if you know that x-y isn't 1 it would work 02:14:16 what would happen if you initialized it to -1 02:15:06 then it'd keep being decremented until x became 0, then you'd end up on the cell to the left 02:15:37 yep 02:15:39 -!- shikhin has joined. 02:16:21 which makes 5 cells :) 02:16:47 what if you replace the << with <[<]>? same algorithm basically? 02:17:08 oh no 02:17:09 nvm 02:17:30 that acts differently in the x=0 case 02:17:34 err, x=y 02:17:45 it also acts differently if y is less :P 02:18:07 ah i know 02:19:20 oh yeah, it just continues looping 02:20:21 [>->-[>]<<<->[<]+] or something like that. starting with the left cell at 1. 02:21:17 that may not terminate :P 02:21:26 idea 02:21:35 wait, no 02:21:50 ah yes 02:22:01 start the left cell at 1 and do [>-[>]<<-] 02:22:26 not sure if that helps though :P 02:22:47 huh? i'm not sure what that does... 02:22:58 did you start it at x or at 1 02:23:31 I started it at the x 02:23:34 ah 02:23:40 makes more sense 02:24:38 looks like it runs off the left edge printing -1s 02:24:49 no it doesn't 02:24:55 * quintopia looks again 02:25:07 if x is smaller or equal, it ends when x is set to 0 02:25:16 if x is larger, it moves to the 1, sets it to 0, and exits 02:25:40 ah i see 02:25:41 so you end up at (0) x-y 0 0, or at 1 (0) y-x 0 02:25:56 sadly those still can't be distinguished without extra cells 02:26:11 also there's an off by one in there somewhere I think 02:26:38 yeah 02:26:51 so it misses x=y 02:27:16 i'll just stick with my five cell solution then :) 02:28:38 it feels like it /should/ be possible :) 02:32:38 -!- shikhin has quit (Ping timeout: 264 seconds). 02:35:03 i think i might have a way. it's pretty damn slow, but i think it can be done in 4 02:35:21 it's long so i'll just describe 02:36:08 start by turning x,y,0,0 into 0,0,x-y,y-x in the obvious way 02:36:57 then, increment the second cellwait no 02:37:02 forget y-x 02:37:06 * Bike writes this down 02:37:12 you can't forget y-x 02:37:24 there's no test for negative/positive in nonwrapping BF without loads of temporaries 02:37:27 because you have to keep taking it past 0 02:37:29 wiggle clear style 02:37:35 err, past its original value 02:37:38 that's what i was going to do 02:37:41 wow 02:37:45 test the sign of x-y 02:37:54 by going down 1, up 2, down 3, up 4 etc. 02:38:00 well you have three temporaries to do that 02:38:03 but I'm not sure that's enough 02:38:11 using the two temps as indices, used alternately 02:40:27 so one round increments temp0 temp1 and test until temp0 (known to be negative) is zero, then tests the test value. then temp1 is incremented and the next round decrements temp0 temp1 and test until temp1 (known to be positive) is zero, then tests, then temp0 is decremented and repeat 02:40:33 uses only 3 cells 02:41:06 which round you get test=0 in (even or odd) gives you test's sign 02:42:38 -!- utopian has quit (Quit: Lost terminal). 02:44:07 (i'll still use the five-cell solution for being blindingly faster) 02:44:12 hmm 02:44:17 what's that in code 02:44:26 let's start with x-y temp0 temp1 02:44:38 x-y (temp0) temp1 02:44:39 I think you have problems leaving the loop 02:44:45 nah you have to start on x-y 02:44:54 to test for zero 02:45:17 the test is "which round am i on" so it doesn't matter where you start 02:45:34 I'm not going to believe this doesn't need a fourth cell until you write it out 02:45:47 okay give me a few 02:46:14 Is it wrong that I was expecting Prolog to be a bit saner than the List monad? 02:46:58 yes, turn yourself in 02:47:31 Prolog's more /interesting/ than the List monad :) 02:47:47 actually, Prolog has two main features 02:48:03 nondeterminism, which the List monad does in a different and arguably saner way 02:48:10 and unification, which the List monad doesn't do at all 02:49:06 Then you would need to make up the unification monad too 02:49:15 get on it 02:49:22 I want Prolog to be more like the Logic monad 02:49:33 Or, well, using the non-monady bits like >>- iirc 02:49:34 is that a real monad 02:49:45 http://hackage.haskell.org/package/logict-0.2.3/docs/Control-Monad-Logic.html 02:49:47 I think the Logic monad is equivalent to the list monad as far as I can tell? 02:50:20 I think the monad is equivalent but it also provides variations of bind and other things that make it... backtrack differently 02:50:44 I think 02:50:59 No, that is a class, which is provided to list monad too 02:51:38 But there is LogicT which may be useful in some way as a kind of list monad transformer that is correct 02:51:43 > do { x <- [1..]; y <- [2..]; guard (x == 2 && y == 2); return "Hi" } 02:51:50 mueval-core: Time limit exceeded 02:52:40 but the result is of the correct type! 02:56:00 > [1..] >>- \x -> [2..] >>- \y -> do guard (x == 2 && y == 2); return "Hi" 02:56:01 Not in scope: `>>-' 02:56:01 Perhaps you meant one of these: 02:56:01 `>>' (imported from... 02:56:07 eep 02:56:14 elliott!!! 02:56:35 oerjan: (>>-)? 02:56:40 Is that from semigroupoids? 02:56:55 shachaf: no from logict 02:57:24 oerjan: I don't think (Num a) => [a] is a (Num a) => Logic a, is it? Although I'd expect a different error 02:57:40 http://hackage.haskell.org/package/semigroupoids-4.0/docs/Data-Functor-Bind.html has it too 02:57:56 Sgeo: istr >>- worked just find with lists in previous versions of lambdabot 02:58:00 *fine 02:58:48 at least we were having fun with it 03:00:09 :t (Control.Monad.Logic.>>-) 03:00:12 Control.Monad.Logic.Class.MonadLogic m => m a -> (a -> m b) -> m b 03:00:15 oh. 03:00:45 > [1..] Control.Monad.Logic.>>- \x -> [2..] Control.Monad.Logic.>>- \y -> do guard (x == 2 && y == 2); return "Hi" 03:00:46 Not in scope: `Control.Monad.Logic.>>-' 03:00:46 Perhaps you meant one of these: 03:00:46 ... 03:00:52 wat 03:00:57 elliott!!!!!!!!!!!!!!!!!!!!!!! 03:01:08 :t (>>-) 03:01:09 Not in scope: `>>-' 03:01:09 Perhaps you meant one of these: 03:01:09 `>>' (imported from Control.Monad.Writer), 03:02:17 @let import Control.Monad.Logic 03:02:18 Defined. 03:02:51 huh 03:03:07 > [1..] >>- \x -> [2..] >>- \y -> do guard (x == 2 && y == 2); return "Hi" 03:03:09 *Exception: stack overflow 03:03:13 OKAY 03:03:17 AN IMPROBEMENT 03:04:21 > take 1 $ [1..] >>- \x -> [2..] >>- \y -> do guard (x == 2 && y == 2); return "Hi" 03:04:23 *Exception: stack overflow 03:04:28 fff 03:05:49 > take 1 $ [1..] >>- \x -> do guard (x == 2); return "Hi" 03:05:51 ["Hi"] 03:05:56 YAY 03:06:02 SO POWEFRYL 03:06:44 -!- shikhin has joined. 03:07:17 how illogical 03:08:05 > [1..] >>- \x -> [2..] >>- \y -> [(x,y)] 03:08:07 [(1,2),(2,2),(1,3),(3,2),(1,4),(2,3),(1,5),(4,2),(1,6),(2,4),(1,7),(3,3),(1... 03:08:24 oerjan: someone (Martin Escardo) at Birmingham University's looking into how you can search infinite spaces in finite time 03:08:26 > [1..] >>- \x -> [2..] >>- \y -> ["hi"] 03:08:28 ["hi","hi","hi","hi","hi","hi","hi","hi","hi","hi","hi","hi","hi","hi","hi"... 03:08:37 his research probably would allow you to filter a list of all integers to see which were 2 03:09:16 -!- shikhin_ has joined. 03:09:17 ais523\unfoog: i recall some haskell discussion about using bottom checking for that. 03:09:35 doesn't particularly work for integers, though. 03:10:00 How worthless is the one million dollar wedge? I do not expect it to be worth much. 03:10:14 i'm going to guess it's worth less than one million one dollars 03:11:08 -!- shikhin has quit (Ping timeout: 240 seconds). 03:11:22 Bike: let's not jump to conclusions here 03:11:47 > [1..] >>- \x -> [2..] >>- \y -> [] 03:11:49 *Exception: stack overflow 03:12:24 cool 03:12:39 It may be worth as much as a lottery card. 03:12:58 -!- lexande has joined. 03:15:01 -!- shikhin_ has quit (Ping timeout: 245 seconds). 03:30:42 Prolog strikes me as the sort of language that probably shouldn't have unrestricted side effects, like a lazy language probably shouldn't have unrestricted side effects 03:31:07 My AI professor looooooves Prolog 03:31:35 I've never seen someone gush so much about a language, and my PL prof used Ocaml 03:31:41 zing 03:33:01 Is there a reason for Ada wanting variables to be declared at the top of procedures/declare blocks/etc, other than historical reasons? 03:33:05 Does it improve readability?' 03:33:50 i tend to do that in any language 03:34:07 @tell elliott not sure if you changed anything, but the abuse filter configuration started working again, time to filter out these spambots 03:34:08 Consider it noted. 03:37:16 -!- shikhin has joined. 03:37:33 oh wow 03:37:42 some of these spambots are triggering the existing filters 03:37:49 that explains why they don't seem to be editing 03:38:16 charming 03:39:09 Prolog strikes me as the sort of language that probably shouldn't have unrestricted side effects <-- have you checked out mercury 03:39:49 Some time ago, but I think last time I was put off my lack of living environment... which doesn't really explain why I checked out Racket recently 03:40:10 were you homeless...? 03:40:35 Also lack of macros. I mean, ISO Prolog also lacks macros, but most environments have them I think 03:41:44 Although earlier I saw mention of Mercury's debugger 03:42:08 Haven't looked more into it, but it in and of itself sounds awesome 03:42:20 the unrestricted side effects are half the fun of Prolog 03:42:52 not the useful half, admittedly 03:43:26 -!- shikhin has quit (Ping timeout: 264 seconds). 03:45:37 Is there a language like Prolog except Cont monad instead of List monad? I'm not entirely sure what that means, but it sounds good >.>. And I don't mean 'scheme', although I guess Schemes that use delimited continuations might qualify 03:46:01 sc... oh darn. 03:47:09 now you've got me thinking instead about logic programming with continuations 03:54:45 -!- Oj742 has joined. 03:58:25 but I don't really know what that would mean 03:58:27 so it's hard to think about 03:58:50 amb? 03:58:52 of course you can implement standard backtracking with continuations easily enough 03:59:01 right >_> 03:59:03 what about amb 03:59:28 basically you just said it. 04:03:11 ais523\unfoog: I changed the caching to use memcache rather than APC, which broke because APC was removed in the PHP version I upgraded to (by upgrading Debian) 04:03:19 ais523\unfoog: it may have been that the PHP upgrade fixed it in general 04:03:24 elliott: yeah, could be 04:03:32 Is it just my imagination, or does Prolog seem like a very good language for manipulating data structures? 04:03:33 I wonder if this new filter has been hit yet 04:03:35 it's hard to test 04:03:37 It's like pattern matching on drugs 04:03:45 03:08:24 oerjan: someone (Martin Escardo) at Birmingham University's looking into how you can search infinite spaces in finite time 04:03:53 huh, Escardo is at bham? 04:03:53 ais523\unfoog: alright, i did need an extra cell, but it *did* work in 4. so, mission accomplished i guess. 04:04:14 ais523\unfoog: but, http://math.andrej.com/2007/09/28/seemingly-impossible-functional-programs/ 04:04:17 (written by him) 04:04:21 elliott: yeah, actually he's in charge of making sure I'm making progress in my PhD (as opposed to my supervisor, who's in charge of helping me make progress) 04:04:30 oh, that was escuardo? 04:05:05 oh, your Dan Ghica is even mentioned in that post 04:05:33 ais523\unfoog: http://sprunge.us/JPjE 04:05:41 -!- shikhin has joined. 04:05:51 elliott: well he doesn't really belong ot me 04:05:53 *to me 04:06:32 quintopia: you left a hyphen in a comment ;) 04:06:37 on line 1 04:06:41 I don't think that counts though 04:07:08 it's not part of the program yeah. just background info. 04:07:41 quintopia: ah clever 04:07:50 you just waddle back and forth in the middle once you've found the result 04:07:56 and jump between the edges when you haven't 04:08:40 it's that >[>]> early on that I wasn't sure how you were going to implement it 04:08:54 although, it does use four cells 04:09:02 which is how much I thought it would take 04:09:28 nope, I made a mistake in the filter 04:09:30 but now I can test it 04:10:44 ais523\unfoog: well, i wasn't convinced it could be done in less than 5, so now we concur :D 04:12:10 OK, it matches now 04:13:11 I can't stop the spambots registering with my perms 04:13:14 but I can stop them editing 04:13:36 mediawiki needs an editable-via-the-wiki captcha system 04:13:47 http://zero.milosz.ca/ 04:13:49 actually, one thing that I don't want to implement yet, but I could 04:13:53 would be a post-registration CAPTCHA 04:14:03 where a user's first edit has to be a particular string on a particular page 04:14:17 -!- shikhin_ has joined. 04:14:18 that way the spambots would need human intervention in the registration process twice 04:14:24 once to beat the registration CAPTCHA 04:14:27 once to beat the first edit CAPTCHA 04:15:14 I'll keep that as a last resort though, or at least a later resort 04:15:22 How is the captcha implemented? Is it just a reCAPTCHA? 04:15:34 ais523\unfoog: but, http://math.andrej.com/2007/09/28/seemingly-impossible-functional-programs/ <-- huh i somehow had got the idea that this kind of stuff needed trapping of undefineds 04:15:47 ais523\unfoog: I can change the captchas if you give me new ones in a few days or something 04:15:58 Sgeo: it's a question/answer CAPTCHA 04:16:01 oerjan: http://lukepalmer.wordpress.com/2010/11/17/searchable-data-types/ has a maybe more accessible explanation of how the general technique works? 04:16:07 Oh, right that 04:16:09 you're asked a question about esoprogramming 04:16:29 elliott found the spammers reading the logs to get the answers, though 04:16:41 -!- shikhin has quit (Ping timeout: 245 seconds). 04:16:48 I love the clc.intercal.org.uk CAPTCHA but it's probably too hard to implement 04:17:01 it's effectively "go to this other web page and copy the answer you see there" 04:17:17 But.... why would you need to read the logs to get the answers? 04:17:35 Or are you not talking about IRC logs? 04:17:56 ais523\unfoog: I feel like the INTERCAL CAPTCHA should have the answer in plain text on the page you get when you fail the CAPTCHA, so you need to submit to a different tab and then resubmit the original form 04:17:59 Why is a human even involved, what human would decide that the wiki is a high-enough-value target to waste their time? 04:18:30 a question i ask myself every day 04:18:31 Sgeo: we think it's a CAPTCHA-solving farm 04:18:44 they get bots to look at all the possible CAPTCHA options 04:18:49 get a human to record the values in a database 04:18:51 then the bots just use them 04:19:05 Why hasn't qntm falled? 04:19:06 fallen? 04:19:42 elliott: anyway, I recommend you use "who created [[language]]", for some languages taken from Special:Random (filtering out boring ones) 04:19:54 because the article text isn't regimented enough for that to be easily parseable yet 04:21:58 or, hmm, I'll do that now 04:22:30 oh wow, I just hit the language list off [[Special:Random]] 04:23:12 actually I'll do years, even if it's potentially bottable I bet they'll use humans anyway 04:23:21 the input format for those is more obvious 04:28:34 -!- shikhin__ has joined. 04:29:09 -!- shikhin_ has quit (Ping timeout: 246 seconds). 04:31:34 this is only taking as long as it is because I decided to ignore BF derivatives 04:32:49 I'm taking BFO, though, because BF impls are not BF derivatives 04:35:37 spammers are reading #esoteric logs? 04:36:20 cool, I hope they enjoyed my drunken ramblings and my oversharing about my sex life and such 04:36:38 elliott: here are your CAPTCHAs: http://esolangs.org/w/index.php?title=Special:Undelete&target=Esolang%3ACAPTCHAs×tamp=20131105043608 04:36:44 ais is going to make a captcha quiz based on your sex life, kmc 04:36:58 what an honor 04:39:14 -!- shikhin_ has joined. 04:41:21 You've talked about your sex life? Huh. 04:41:32 i thought so 04:41:39 -!- shikhin__ has quit (Ping timeout: 260 seconds). 04:41:40 or was that sarcasm ;P 04:42:18 I hadn't noticed it quite honestly. 04:43:09 -!- shikhin__ has joined. 04:44:39 -!- lifthras1ir has quit (Ping timeout: 252 seconds). 04:44:54 -!- lifthrasiir has joined. 04:45:00 `oohlist (928) 04:45:02 oohlist (928): shachaf oerjan Sgeo FireFly 04:45:20 You mean no one did it already? 04:45:51 -!- shikhin_ has quit (Ping timeout: 260 seconds). 04:48:21 -!- shikhin__ has quit (Ping timeout: 245 seconds). 04:51:53 what's that about xykon being chilly 04:52:59 oerjan: http://www.giantitp.com/forums/showpost.php?p=16356153&postcount=76 04:53:05 hth 04:53:15 http://math.andrej.com/2007/09/28/seemingly-impossible-functional-programs/ <<< i didn't quite bother to read all of this, but if you have a computable function (say, any haskell function) P of type Cantor -> Bool, then there exists n such that the value of P(x) each sequence x in the cantor space is a function of x_{[0,n]}. 04:53:24 and you can effectively find such n by simulation 04:53:44 this is well-known an obvious 04:53:47 *and 04:54:08 oh i love that shit so much 04:54:11 (might be that it's some in some way that looks cool though) 04:54:13 it fucking rocks my socks 04:54:15 trivial, one might say 04:54:20 yes 04:54:34 i just read a paper that proved that actually 04:54:48 and i was like come on everyone knows that 04:54:57 (well proved something similar) 04:54:59 oklopol: Are you missing a word? 04:55:02 maybe! 04:55:16 "there exists n such that the value of P(x) each sequence x in the cantor space" 04:55:21 oh. 04:55:26 each sequence x in the cantor space is a function of x_{[0,n]}. 04:55:30 got cut off maybe 04:55:39 No, it wasn't cut off. 04:55:43 erm 04:55:50 oh 04:55:53 !!! 04:55:54 i know 04:55:55 !!! 04:56:00 i'm missing a "for" 04:56:03 OK. 04:56:05 erm 04:56:07 yes 04:56:10 that's it 04:56:11 yeah 04:56:16 i'm indeed missing a "for" 04:56:19 there should be one 04:56:24 s/\n/ /g 04:56:30 -!- shikhin__ has joined. 04:56:32 yes 04:56:33 good point 04:56:39 will keep that in mind 04:57:00 excellent. 04:58:08 i'm pretty sure i had some proof in my "masters" thesis that used a version of this. 04:58:24 but anyway, if there were, for each n, a point x_n such that the machine inspects the nth coordinate of x_n before deciding P(x_n), then on any limit point of the sequence, the machine will run forever 04:58:59 except with continuous instead of computable 04:59:01 so P is a partial function, which is forbidden 04:59:28 oerjan: all functions are continuous and computable anyway 04:59:53 then it's even easier i guess: {0} is clopen in {0, 1}, so it's preimage is too 05:00:01 and clopens are cylinders 05:00:36 What's a cylinder, and what's {0, 1}? 05:00:41 well in my case they were integer functions. 05:00:48 a cylinder is basically a fancy name for a set of words 05:00:48 i think. 05:01:22 but compactness means only a finite of points in the range. 05:01:30 *number of 05:01:48 more precisely, a cylinder C is a set of points of the cantor space which is defined by a set of words w_1, ..., w_k such that x \in C if and only if x starts with w_i for some i 05:02:14 you can take those w_i to have the same length by extending them in all possible ways 05:02:39 I don't even know what the Cantor space is. :-( 05:02:55 oerjan: oh okay 05:03:11 OK, so {0, 1} is the discrete topology. 05:04:16 yeah it has the discrete topology (a computable function will be continuous w.r.t. that topology) 05:05:17 oerjan: so the proof is, cantor space is compact so image is compact so image is a finite set so image has a discrete topology so image has clopen base so function value is determined by clopen partition 05:05:43 maybe you could remove some of those but anyway i like that 05:05:43 that's about it 05:06:00 maybe in a master's thesis, you would explain stuff a bit 05:06:29 that was the idea. there weren't any really new results there, just explaining clearly some known stuff 05:07:55 shachaf: the ordinary cantor set is an example. more generally, anything homeomorphic to that. 05:08:45 oerjan: what are those things floating around her head anyway (in `olist) 05:09:06 shachaf: i wondered about that too... probably related to her powers somehow? 05:09:12 it was in the previous one too 05:09:21 it's been around since she appeared 05:09:26 just wondering what it is 05:09:29 oerjan: can you give me your master's thesis again 05:09:40 oerjan has no master 05:10:41 * shachaf greps logs. 05:10:43 http://oerjan.nvg.org/main.pdf 05:11:09 i thought that might be it. 05:11:31 thanks 05:12:19 http://oerjan.nvg.org/main.pdfRecent results in topological dynamics, described in [3], have shown that ordered cohomology is the key to investigate the orbit structure of Cantor minimal dynamical systems. 05:12:33 erm 05:12:38 pasting failure 05:12:56 but er yeah ordered cohomology? omg 05:13:20 -!- Oj742 has quit (Quit: irc2go). 05:15:47 is a topological conjugate a natural transformation thing 05:15:51 -!- shikhin__ has quit (Ping timeout: 245 seconds). 05:17:09 rather it's an isomorphism in the category of dynamical systems 05:17:10 oklopol: lemma 2.4 may be one version. 05:18:11 that's a proof of cylinders = clopens right 05:18:16 oh 05:18:20 yes 05:18:27 * Bike looks suspiciously at chat. this doesn't seem very ODEy. 05:18:54 yeah this ain't no ordinary differential equation 05:19:08 -!- shikhin__ has joined. 05:19:34 oerjan: that's the hard thing about proving what you said, but i was more interested in the way topology lets you state these results _after_ you know it. 05:19:38 erm 05:19:43 did that make any sense, prolly not 05:23:48 cylinder sets are defined on the previous page 05:24:37 or well at the top of the same page 05:25:31 okay we have different cylinders 05:25:40 by cylinder, i mean finite unions of cylinders 05:25:50 SORRY 05:26:28 -!- shikhin__ has quit (Ping timeout: 240 seconds). 05:26:44 they are meant to be a clopen basis of the topology 05:26:45 -!- shikhin_ has joined. 05:26:58 well they are with my definition too! 05:27:00 not all clopen sets 05:27:48 i'm pretty sure some use them as i do 05:27:50 this definition is more closely related to the diagrams 05:28:16 i mean i think your definition is better but i'm still apparently using this one 05:28:29 why would i do that if i was not _brainwashed_ 05:29:30 do you mean because in the dynamics, the cylinders dance round and round 05:29:30 well your definition makes them equivalent to clopen sets, so independent of basis 05:29:43 yes they do... 05:30:11 although the cylinders corresponding to maximal paths do get split up 05:30:59 so erm these bratteli whatever diagrams, are they just some sort of generalization of an adding machine 05:31:34 i suppose so. the case where there is only one vertex at each level we call an "odometer" 05:31:53 and is even more the same thing. 05:31:54 oh right that's how it goes 05:33:23 oh my god dimension groups 05:33:54 i wish i knew as much cool stuff as you do 05:34:22 i think your master's thesis is deeped shit than my phd thesis will be 05:34:27 *deeper 05:34:29 -!- prooftechnique has quit. 05:34:33 well take solace in the fact that some of these things have faded quite a bit. 05:34:43 oh dear 05:35:33 food -> 05:36:33 my thesis will be like lolol here's a picture of a CA doing some weird shit -- maybe it indicates that simple machines can perform complex computations?? i call this the theory of simplicial complexes. 05:37:37 -!- asie has joined. 05:37:41 u mad 05:40:14 after this i'm gonna write a book called "THE THEORY OF SIMPLICIAL COMPLEXES -- THE STORY OF HOW ONE MAN REALIZED WHAT NO MAN COULD BEFORE: THAT SIMPLE MACHINES ARE AT THE _CORE_ OF COMPUTATION" 05:40:43 and there's a footnote that says that that man is me 05:40:55 oklopol: um you realize simplicial complexes is already a term in homology 05:41:05 i think that's part of the joke 05:41:18 it was yes 05:41:47 good, good. 05:41:53 i've been reading quite a bit of complex systems cancer recently because i'm google scholaring for anything that might contain interesting constructions of cellular automata 05:41:57 as long as you stay funnier than wolfram. 05:42:26 (i will give some examples of such constructions in the first section, my thesis will be about subshifts where cellular automata are boring, i'm the anti-wolfram) 05:44:14 usually i find it most exciting when after months of research, it turns out that an object we're studying is completely trivial, for some weird-ass reason 05:45:24 the grand theorem of your thesis will prove that the set of systems you've defined is empty 05:45:53 that would be so awesome 05:46:24 i hear that's happened in some sense, although it's probably an urban legend 05:46:29 i'm gonna write a book called "The Beer, Burritos, and Bonghits Diet" 05:46:39 and on the cover is a picture of me wearing a lab coat (stolen) 05:46:39 like someone made some class and wrote a phd thesis where they proved tons of cool stuff about it 05:46:46 -!- shikhin__ has joined. 05:47:09 all functions are continuous, a problem of hilbert's is solved, and it does your laundry 05:47:15 kmc: i like burritos is that close enough 05:47:38 and the what'shistitle told him that there are no such systems because trivially 05:48:02 the opponent maybe 05:48:19 the story says this happened at the actual dissertation, but that just sounds horribly mean 05:48:21 -!- shikhin_ has quit (Ping timeout: 245 seconds). 05:48:31 oklopol: i think the urban legend is about someone who had someone _else_ prove that at their thesis defence. not a good day. 05:48:53 oh, i've heard oklopol's story too 05:48:58 some guy at the audience? 05:49:16 yeah at the actual thesis defence, not dissertation. 05:49:28 yeah, some guy in the audience pops up and says lol that's trivial 05:49:29 i'm good at anglis 05:49:42 i assume "lol" is literally pronounced 05:50:08 -!- Sprocklem has quit (Ping timeout: 245 seconds). 05:51:07 i vaguely think that _possibly_ it wasn't empty but they were all constant functions. probably there are myriad versions. 05:56:45 -!- tertu has quit (Ping timeout: 272 seconds). 06:08:10 -!- shikhin_ has joined. 06:10:47 -!- shikhin__ has quit (Ping timeout: 260 seconds). 06:13:54 -!- asie has quit (Quit: My MacBook Pro has gone to sleep. ZZZzzz...). 06:21:24 -!- shikhin__ has joined. 06:24:12 -!- shikhin_ has quit (Ping timeout: 252 seconds). 06:24:40 -!- shikhin has joined. 06:25:51 -!- shikhin__ has quit (Ping timeout: 245 seconds). 06:35:25 The list monad doesn't have a good way to fail with information, does it? 06:35:43 Maybe is a specialization of List, but Either isn't 06:36:52 There is EitherT, as well as LogicT 06:37:43 I think Prolog is stuck in the List monad, though. Although it (or just most impls?) does have exceptions 06:40:31 prolog has the database modification commands though. 06:41:43 I should read about ancestor cuts to see if continuations are implementable atop them 06:43:49 oklopol: somebody claimed there used to be theorems about doubly-periodic entire functions on the complex plane 06:44:36 the best functions 06:45:43 i.e. entire functions that repeated along two different vectors in the complex plane 06:45:47 which implies bounded 06:45:54 and therefore by liouville's theorem, constant 06:46:30 what if it's not analytic!! 06:46:44 "entire" implies analytic 06:47:01 yeah just managed to find the proof, and realized i should've realized that 06:47:12 i thought it just meant defined everywhere, wow go me 06:47:42 hexande 06:49:59 Prolog : List :: Icon : Maybe ? 06:50:44 No, Icon is also List 06:51:24 hachaf 06:52:35 -!- ais523\unfoog has quit. 06:54:18 you keep coming and going 07:04:03 mroman: i asked a German person about the space-before-period thing and they didn't know about it 07:04:56 maybe mroman wasn't entirely serious . 07:06:30 maybe oerjan wasn't entirely serious . 07:07:14 i think you may be illegally violating my copyright . 07:07:33 i think you may be illegally violating my copyright . 07:07:38 i also think you have a time machine . 07:09:04 http://www.irregularwebcomic.net/230.html 07:10:59 that one was obvious from the beginning; C-; did not read again 07:12:33 well in this context, naturally. 07:13:10 there was a puzzle in the computer game Discworld II based on this 07:13:25 with what's-her-name answering questions before you ask them 07:30:30 -!- FreeFull has quit. 07:43:56 -!- oerjan has quit (Quit: leaving). 07:44:24 lexande: do you think train stations are a good environment for maths lectures 07:45:48 not usually 08:32:20 -!- shikhin_ has joined. 08:34:18 -!- shikhin has quit (Ping timeout: 245 seconds). 09:01:50 -!- fangkui has joined. 09:05:11 哈哈哈哈哈哈哈 09:05:15 work 09:05:18 maybe 09:05:21 good 09:05:24 ok 09:05:32 美好的注意 09:05:53 Why do Asian IP addresses never have a reverse? 09:06:56 -!- fangkui has left. 09:07:08 We should have a CJK `welcome. 09:09:53 #japanese is talking about republican bananas, and #esoteric is listing japanese characters 09:09:55 i was very confused 09:10:28 What’s a republican banana? 09:11:23 Wait… Japanese characters? 09:11:42 ion: Well, you know, CJK. 09:14:11 -!- carado has joined. 09:14:20 ion: i'm pretty sure 美好的注意 are japanese characters 09:14:53 something like beauty, like, don't remember, don't remember, sound, maybe 09:14:54 Even when spoken by a Chinese person? 09:15:41 those particular ones exist in both i think 09:16:09 although in japanese, that's a list of characters, whereas in chinese it might mean something 09:16:13 I just realized the channel is full of Finnish characters. 09:17:03 While #finnish is probably talking about monarchic bananas. 09:17:03 quite a bit of non-finnish characters too 09:17:16 but okay maybe my message was phrased badly, i'll fix it 09:17:58 #japanese is talking about how some guy always associates the word republican with bananas, and #esoteric is listing chinese characters. i'm not confused because the first one isn't very esoteric, and the second one has nothing to do with japanese. 09:18:38 Why does said guy always associate the word republican with bananas? 09:18:58 " aah, banana republic" he eventually realized 09:19:06 i didn't actually read the conversation 09:19:07 ah 09:20:31 okay i guess 的 isn't a japanese character 09:20:56 just looks very familiar 09:25:42 -!- carado has quit (Ping timeout: 252 seconds). 09:32:37 -!- shikhin_ has changed nick to shikhin. 09:41:01 huh 09:41:08 i actually recognize both of those radicals 09:41:19 white moon? something like that 09:41:45 wait no, that's ummm 09:42:00 it's so small i can't make things out hardly, but i think that one is bullseye 09:42:28 haha, i actually remembered :D 09:42:39 'mato' - target, mark 09:51:01 \o/ 09:51:01 | 09:51:01 >\ 09:51:14 :( 09:52:35 :) 09:54:06 -!- shikhin_ has joined. 09:56:41 -!- Uguubee1111113 has left. 09:56:48 -!- shikhin has quit (Ping timeout: 245 seconds). 09:58:20 -!- shikhin__ has joined. 09:58:28 -!- shikhin_ has quit (Ping timeout: 240 seconds). 10:01:16 -!- shikhin_ has joined. 10:02:42 -!- shikhin__ has quit (Ping timeout: 246 seconds). 10:22:24 -!- augur has quit (Remote host closed the connection). 10:22:50 -!- augur has joined. 10:24:05 -!- augur has quit (Read error: Connection reset by peer). 10:24:16 -!- augur has joined. 10:25:26 -!- nisstyre has quit (Ping timeout: 245 seconds). 10:26:08 -!- KingOfKarlsruhe has joined. 10:45:11 -!- augur has quit (Read error: Connection reset by peer). 10:45:23 -!- augur has joined. 10:49:27 -!- Jafet has quit (Changing host). 10:49:27 -!- Jafet has joined. 10:54:18 -!- monotone has quit (Ping timeout: 245 seconds). 11:27:53 -!- carado has joined. 11:32:40 -!- carado_ has joined. 11:37:34 -!- yorick has joined. 11:37:42 -!- carado_ has quit (Ping timeout: 252 seconds). 11:40:10 -!- carado_ has joined. 11:45:24 -!- carado_ has quit (Ping timeout: 252 seconds). 11:49:00 -!- john_metcalf has joined. 12:02:29 -!- KingOfKarlsruhe has quit (Quit: ChatZilla 0.9.90.1 [Firefox 25.0/20131025151332]). 12:16:41 -!- carado has quit (Quit: Leaving). 12:16:57 -!- Sgeo has quit (Read error: Connection reset by peer). 12:35:03 -!- carado_ has joined. 12:36:19 -!- carado_ has quit (Client Quit). 12:36:30 -!- carado has joined. 12:53:50 -!- MindlessDrone has joined. 13:11:38 -!- Taneb has joined. 13:14:06 -!- boily has joined. 13:14:15 -!- metasepia has joined. 13:16:04 -!- shikhin_ has quit (Read error: Operation timed out). 13:22:44 good kettle morning! 13:23:19 Afternoon 13:23:38 shachaf, sometimes 13:24:38 -!- monotone has joined. 13:25:08 Tanellob, shachellof, monotonello. 13:29:59 -!- shikhin_ has joined. 13:43:25 -!- shikhin_ has changed nick to shikhin. 13:51:37 Aaaah something in my room has just one dling and I don't know what 13:55:28 `? dling 13:55:30 dling? ¯\(°_o)/¯ 13:55:52 @wn dling 13:55:53 No match for "dling". 13:56:14 -!- tertu has joined. 14:00:14 -!- lambdabot has quit (Ping timeout: 246 seconds). 14:06:34 ~duck dling 14:06:34 --- No relevant information 14:06:50 hi boily 14:06:57 hintopia! 14:07:45 i've gotta pick out some southern things to send you. things you can only get down here afaik. 14:07:57 do you like pickled pig's feet? 14:08:15 never tried them, but they sound good :D 14:08:41 me neither 14:10:56 wikipédia always surprises me with the precisiveness of their articles → https://en.wikipedia.org/wiki/Lowcountry_cuisine 14:12:22 @wn precisiveness 14:12:35 -!- mrhmouse has joined. 14:13:06 Bike: fizzie kille lambdabot. 14:13:14 s/e l/ed l/ 14:13:25 ~duck precisiveness 14:13:25 --- No relevant information 14:13:59 boily: hominy is one thing i could probably acquire that you might like. i don't know where off the top of my head, but i know it can be had somewhere around here. 14:15:55 oh, interesting choice! 14:16:11 hominy grits that is 14:16:35 i could easily get the instant microwave kind 14:20:59 "kille /c/ 1. (colloquial) Boy, lad. 2. (colloquial) A (younger) adult male person; guy, bloke. 3. (colloquial) Boyfriend." 14:34:19 hmm... I wonder if I can ship some cretons through the borders... 14:56:49 I've got a truck 14:57:05 sing it mrhmouse! 14:57:23 -!- asie has joined. 14:58:25 so what's up with the spamswarm over at the wiki? 14:59:21 how are all these spambots making accounts? 14:59:27 CrAzY 15:01:15 -!- yorick has quit (Ping timeout: 246 seconds). 15:01:27 -!- yorick has joined. 15:03:09 do we have a captcha for account creation? 15:06:05 Has there previously been any research into whether all x86 SINGLE byte instructions would form a more-or-less turing complete language? 15:06:19 more-or-less because you obviously can't address infinite memory 15:08:31 you can't do call 15:08:39 but you can do push reg; ret; combinations 15:08:59 and I assume you can encode i.e. brainfucks [ ] in a jump table 15:09:12 and then load the address from there somehow and push; ret; it 15:09:20 but whether that can be done conditionally :( 15:09:37 also you can load es, ds, si, di which enables you to do movsb 15:10:07 (by inc ax * N; push ax; pop es;) 15:10:55 -!- nooodl has joined. 15:11:02 the assumption is that some bootstrapping programming loads your code to memory and sets the registers correctly for programm start 15:11:11 *bootstrapping program 15:11:38 i.e. the bootloader may use multi-byte instructions :) 15:13:15 also you can use xlat 15:15:25 @tell ais523 SPAMRUSH! 15:15:36 hm. lambdabot is still a young lad... 15:17:52 meanwhile, some Japanese bots are trying to sell sneakers, watches, and lodgings in Africa... 15:29:25 We might have an approach if we can get al to ah 15:31:56 which might be doable by writing it to a given location in memory using movsb 15:32:04 and then again with movsb with direction flag reversed? 15:32:46 -!- Sprocklem has joined. 15:34:27 ah 15:34:32 not necessary 15:34:40 movsb can write the address directly to the stack :) 15:35:24 and then ret it 15:38:21 -!- Lymia has quit (Ping timeout: 245 seconds). 15:58:33 -!- Taneb has quit (Quit: Leaving). 16:05:36 -!- KingOfKarlsruhe has joined. 16:09:32 -!- FreeFull has joined. 16:11:29 -!- asie has quit (Quit: My MacBook Pro has gone to sleep. ZZZzzz...). 16:19:27 -!- conehead has joined. 16:22:31 -!- tertu has quit (Quit: Leaving). 16:51:31 -!- augur has quit (Remote host closed the connection). 16:51:58 -!- augur has joined. 16:56:23 -!- augur has quit (Ping timeout: 245 seconds). 17:01:48 -!- Sprocklem has quit (Ping timeout: 245 seconds). 17:11:41 -!- asie has joined. 17:26:24 -!- carado has quit (Ping timeout: 252 seconds). 17:27:42 -!- oerjan has joined. 17:28:17 -!- shikhin has quit (Quit: Leaving). 17:40:49 -!- carado has joined. 17:46:52 -!- asie has quit (Quit: My MacBook Pro has gone to sleep. ZZZzzz...). 17:49:59 -!- oerjan has quit (Quit: leaving). 18:06:42 -!- metasepia has quit (Read error: Connection reset by peer). 18:06:42 -!- boily has quit (Read error: Connection reset by peer). 18:08:00 -!- boily has joined. 18:08:09 -!- metasepia has joined. 18:20:58 -!- augur has joined. 18:31:04 -!- Phantom_Hoover has joined. 18:31:06 will the spambot flood NEVER END 18:33:35 cat <<< "int getuid(void) { return 0; }" > /tmp/getuid.c; gcc -o /tmp/getuid.so /tmp/getuid.c -shared; LD_PRELOAD=/tmp/getuid.so id 18:34:41 @tell ais523 While you're smacking down some spam accounts, you might move [[Paulo Jorente]] to [[User:Paulo Jorente]] 18:34:45 fakeroot id 18:34:54 oh right 18:34:57 no lambda 18:34:59 sad day 18:35:02 lambdabot is dead? 18:35:03 what have you done, fizzie? 18:35:07 does fungot do that 18:35:07 quintopia: even just having lists and vectors?" " ugh... ( pause) ( display 18:35:10 quintopia: that's probably incorrect 18:35:25 we generally prefer mainspace encyclopedic articles for people 18:35:36 hi elliott 18:35:40 http://esolangs.org/w/index.php?title=Paulo_Jorente&action=history oh we've actually gone through this before 18:35:45 fungot: Why can't you do memos? 18:35:45 fizzie: those pythonistas wanted to make public and sell, i wouldn't need to store the drives remotelly? ( physically or maybe network connections)? 18:35:46 elliott: oh okay then 18:35:55 -!- Lymia has joined. 18:35:55 -!- Lymia has quit (Changing host). 18:35:55 -!- Lymia has joined. 18:36:33 elliott: can you smack down spam accounts? 18:37:10 -!- FireFly has quit (Excess Flood). 18:38:40 -!- FireFly has joined. 18:40:00 -!- lambdabot has joined. 18:43:39 quintopia: I can block them manually but not all of them are actually managing to edit and I don't have the time 18:43:49 can see about changing the captchas sometime today 18:43:54 cool 18:50:30 -!- Bike has quit (Ping timeout: 246 seconds). 19:10:30 -!- Taneb has joined. 19:20:15 -!- tertu has joined. 19:24:37 -!- Phantom_Hoover has quit (Ping timeout: 272 seconds). 19:32:54 -!- lambdabot has quit (Ping timeout: 252 seconds). 19:37:37 -!- Bike has joined. 19:38:55 -!- njm has quit (Quit: Reconnecting). 19:39:01 -!- njm has joined. 19:42:28 -!- nortti has quit (Ping timeout: 264 seconds). 19:42:53 -!- nortti has joined. 19:42:53 -!- Bike has quit (Ping timeout: 240 seconds). 19:44:54 -!- Bike has joined. 19:48:47 Bow tie experiment: two people noticed 19:49:42 did your bow tie spin and shoot water? 19:49:45 Noticed the experiment? 19:51:20 shachaf, notice the bow tie 19:51:43 Doctor Who wears a bow tie. Bow ties are cool. 19:52:04 john_metcalf: does he still, or was that just Smith and the one older one? 19:52:32 doctor who is not cool, sorry 19:52:46 you know who's cool? doctor whoooo 19:52:52 mrhmouse, we're still on Smith technically 19:52:54 shachaf: no such preson 19:53:00 Capaldi has been announced but not taken over yet 19:53:04 john_metcalf: no such person 19:53:23 kmc, it was a reference to the show, not an implication 19:53:41 kmc: do you have a coolness oracle 19:54:13 I'm a few seasons behind, actually. Saw Smith's first season but started over (2005, not 1960) when my GF wanted to watch it 19:54:29 Just Smith as far as I know. Don't remember about the older ones. 19:55:02 I think Troughton or Pertwee wore one? 19:55:59 john_metcalf: protip: his name is "The Doctor" 19:55:59 I assume that Capaldi as the Doctor will in each episode unleash a several minute long stream of inventively graphic profanity at some creature or another 19:56:08 some of these have bow tie-like decorations: http://en.wikipedia.org/wiki/File:Versions_of_the_Doctor.jpg 19:57:00 -!- copumpkin has quit (Ping timeout: 246 seconds). 19:57:46 kmc: The Doctor doesn't swear, generally. 19:58:08 Though I agree it would be amusing. 20:00:05 "A man walks into a police call box. It's slightly smaller on the inside." 20:00:24 give this man a medal 20:01:55 quintopia: ++++ 20:02:27 i stole it. there are more: https://twitter.com/HardSciFiMovies 20:02:35 coppro: I think you meant +[+] 20:02:40 mrhmouse: no 20:02:53 mrhmouse: that's equivalent to nothing 20:02:58 or bottom 20:03:00 I suppose that would overflow, depending on which interpreter you use 20:03:34 it isn't clear, though, whether it should always overflow 20:08:28 mrhmouse: there is a surprising dearth of algorithms for non-wrapping implementations on the wiki. perhaps you'd like to add some? 20:09:20 quintopia: I'd probably have to write one. I don't know of any implementations that don't wrap, only that the original design isn't clear whether it should wrap 20:10:20 Correct me if I'm wrong here, please 20:10:27 i've been adding algorithms without testing them. it's hard to analyse them entirely in my head, so if you happen to find or write a BigNum impl, let me know. 20:11:31 I didn't mean that it necessarily used BigNum, only that it didn't wrap. Could just stop at 255 or whatever the max value is. 20:12:25 Unless the behavior is defined in the original design for what happens at value boundaries. I'm working off of memory here. 20:15:30 What would be fun is that if you ever try to increment past 255, the cell gets replaced with a random value 20:15:38 Or a pointer to some other cell 20:16:44 FreeFull: How would the pointer work? Incrementing/decrementing would modify a different cell..? Moving left/right would move relative to the other cell..? 20:17:49 mrhmouse: i like to think that nonwrapping implies unbounded 20:18:16 mrhmouse: forcefully stopping a number from overflowing is just stupid and inelegant 20:18:57 quintopia: brainfuck is elegant otherwise? 20:19:45 mrhmouse: wrapping algorithms tend to be very elegant. 20:20:31 however, i suspect that an algorithm that works in the unbounded case should also work in the forcefully-size-limited case, assuming the numbers involved don't push up against that limit. 20:20:50 that said, writing algorithms for the unbounded case is straight-up challenging 20:21:39 challenging, or just time-consuming? 20:22:08 challenging 20:22:40 -!- Lymia has quit (Ping timeout: 264 seconds). 20:22:53 mrhmouse: You know what, not a pointer, but just randomly teleport you to a different position in the program 20:23:00 That would be easier 20:23:10 FreeFull: It's also easier to explain :) 20:23:11 Or maybe randomly teleport to a different cell 20:23:15 easier eh 20:23:45 Depending on your implementation, I think teleporting to a different location in the source code is trivial 20:24:14 so is moving to a different cell in the array 20:24:20 That's far easier 20:24:34 apparently virtualbox causes my machine to panic. so I installed libvirt, which is very nice and nifty and fungot and everything else. but then, the kvm vagrant plugin refuses to compile, so I can't use that with projects that run on vagrant. fml. 20:24:34 boily: i'll let this fnord do this, unchecked conversion in code i've pasted from my fnord 20:24:46 but from the programmer's perspective, the random cell seems easier to manage than the random instruction 20:25:53 Far easier, I would think. Especially if you're implementing a compiler (and not an interpreter) 20:26:48 not the compiler programmer, the bf programmer 20:26:54 Ah, I see 20:34:13 duduu 20:34:59 oklellopol. 20:36:22 i am! :) 20:37:44 oklopol is a walrus. 20:37:58 that i am? i am??? 20:39:11 Does #esolang house any Lojban speakers? 20:39:42 i don't think so 20:39:58 I tried to learn once, didn't get very far 20:40:11 yeah there are a few aficionados 20:40:31 including myself (i even have the grammar in my bookshelf) 20:40:50 I'm thinking of taking a swing at it, thought there might be a few people here interested in that sort of thing 20:42:11 Taneb: me too, long ago 20:42:19 -!- MindlessDrone has quit (Quit: MindlessDrone). 20:43:09 i was dating this woman and her other boyfriend was into lojban 20:47:15 i was in some lojban channels for a while 20:50:03 It’s popular enough for there to be channels? 20:50:41 shachaf may be referring to a conlang channel in general 20:52:15 there are multiple lojban channels on freenode.. 20:52:17 no, #lojban (and #jbopre) 20:52:23 or were, last time I joined them, anyway 20:52:32 there's #ckule ("school") too 20:53:33 i also went to a meeting of lojban speakers once 20:54:15 was confused 20:54:50 FireFly: Thanks for directing me to #ckule! That's incredibly useful. 20:55:24 Have fun 21:02:13 * kmc thinks his last message is one of the nerdiest things he's said in a while 21:04:39 kmc, I disagree, it suggests you were dating someone 21:04:54 nerds have dates, too! 21:05:55 yes 21:06:20 i think dating a poly conlang enthusiast is nerdier than not dating anyone 21:06:27 and i ♥ it 21:06:33 @ping 21:07:31 today will be remembered as the Day the Fizzie Killed the Lambdabot. 21:07:59 fizzie did that? 21:09:02 indeed. he is the perp. 21:16:00 fungottttt, why can't you evaluate haskell? 21:16:01 FireFly: i was mistaken!! i want my five pounds. i feel bad making you read paul graham's account on viaweb and fnord and fnord 21:16:17 (I love wikipédia. “instead of sounding like "YEEEEEE"”.) 21:16:39 fungot: do you evaluate haskell if I pay you five pounds? 21:16:39 FireFly: my bot can evaluate Haskell. fsvo evaluate. Error 1. 21:16:39 FireFly: i know; it's an occupational hazard for all of my mail.) 21:16:47 ~ 7 + 2 21:16:48 --- Possible commands: dice, duck, echo, eval, fortune, metar, ping, yi 21:16:51 ~eval 7 + 2 21:16:54 Error (1): 21:17:02 ~eval 7 + 2 21:17:04 9 21:17:06 fungot: stop replying with kinda sensical replies; it's scary 21:17:06 FireFly: undefined variable ' a' combinator, which is all the rage 21:17:10 ~duck dog 21:17:11 Dog a domesticated canid, Canis familiaris, bred in many varieties. 21:17:27 ~duck cat 21:17:27 cat definition: a carnivorous mammal ('''Felis catus''') long domesticated as a pet and for catching rats and mice. 21:17:32 fungot is sentient. it's just... sentient on a different axis. 21:17:32 boily: why not just disable web access then, the output just after i checked. how shall i hand a long list of books to buy 21:17:47 ~ duck befunge 21:17:48 --- Possible commands: dice, duck, echo, eval, fortune, metar, ping, yi 21:17:52 ~duck befunge 21:17:52 Befunge is a stack-based, reflective, esoteric programming language. 21:17:58 fungot: very good question, I say 21:17:58 FireFly: every time someone bothers to look at them 21:18:01 neat 21:20:10 fungot: duck! 21:20:10 olsner: he's a pathological liar 21:20:25 what is fungot written in? 21:20:26 mrhmouse: need to sleep on right now, not sure 21:20:30 fungot, stop being sentient! 21:20:30 boily: you're missing the forest for the trees. :) 21:20:34 -!- lambdabot has joined. 21:20:35 mrhmouse: befunge. 21:20:46 impressive. Is the source available? 21:20:48 woohoo! fizzie casted necroresurrection! 21:21:09 mrhmouse: ask the aforementioned necromancer. 21:21:48 Nevermind, found the website :) 21:21:55 `source 21:21:56 ​/home/hackbot/hackbot.hg/multibot_cmds/lib/limits: line 5: exec: source: not found 21:22:00 er 21:22:04 befungeprefixsource 21:22:12 er, s/befunge/fungot/ 21:22:12 FireFly: fnord it. if our body likes it, it's only tangentially related 21:22:20 Yes. Fnord it. 21:25:48 someone will end up writing F&F&F slashfiction, I can sense it :D 21:25:56 Huh. "Fnord" is actually in fungot's source. I may have to learn Befunge. 21:25:56 mrhmouse: eval ( 1 0) returns 0 here 21:28:26 really, fungot 21:28:26 FireFly: the devil is in the pipeline for that kind of language 21:29:28 * boily gives botcrackers to fungot 21:29:29 boily: i remember well. besides that perl is a neat write-only language if you know about t when he did it 21:29:44 * boily pets fungot 21:29:44 boily: perhaps not flying, as such 21:32:16 perhaps I should get a pet fungot 21:32:16 olsner: or pre-scheme. 21:32:26 i thought of making a whitespace dialect with MONGOLIAN VOWEL SEPERATOR and the 2 zero width spaces 21:32:35 fungot: yes, or that 21:32:35 olsner: today: " zomg my vimrc broke u sux") ( bundle " mostly/ harmless") ( scheme-report-environment 5))) 21:32:40 so you essentially can only write it with a hey editor 21:33:14 myname: is that Fonzi mode for emacs? 21:33:25 myname: it should also use COMBINING GRAPHEME JOINER 21:33:38 not to be confused with a hay editor, for when you are in performance horse-tuning. 21:33:50 kmc: as long as it is zero width, everything should be fine 21:34:16 fungot: good evening 21:34:17 shachaf: i have no idea at the moment, so i would favor the name " mono". err... 21:34:19 -!- Bike has quit (Ping timeout: 260 seconds). 21:34:26 -!- boily has quit (Quit: there may be unidentified chicken.). 21:34:28 -!- metasepia has quit (Remote host closed the connection). 21:34:32 what about a hax editor 21:34:34 or a sax editor 21:34:36 good mono fungot 21:34:36 olsner: i tend to be very useful, as is necessary to tie the scheme system: a set of knowledge and irrational disdain for anything that reminds me of ' if' 21:34:39 fungot: are you writing a .NET implementation 21:34:39 shachaf: well, essentially, but i'm still unsure about needing a clos-style type dispatch system, et cetera, as well as 21:34:45 sex editor? 21:35:32 i hardly know 'er! 21:35:40 fungot's .NET implementation actually sounds interesting 21:35:41 FireFly: fnord? :d *goes to upload lost fnord partner. riastradh, you're always loading it fnord some later version... ( i think that's enough fnord. 21:36:00 fungot: me too 21:36:00 kmc: and they reported this to dorai a year or so 21:36:05 fungot: there's never enough fnord 21:36:06 mrhmouse: why not quack? never heard of 21:36:08 hmm, these muffins may have been slightly moldy.. will I die? 21:36:28 are they shot through with fungot? 21:36:28 kmc: ah i see what you mean by " c in scheme 21:36:28 fungot: will olsner die? 21:36:28 FireFly: how? tetris requires delays and reflexes could make him type ' hi tusho' and hit enter 21:36:43 -!- Sprocklem has joined. 21:36:44 olsner: if you type 'hi tusho' and hit enter I think you'll survive 21:36:51 dr fungot 21:36:51 kmc: and adding interesting tidbits of teh information fnord industry every now and then. :d) 21:36:57 The Fungot Diet 21:36:59 ' hi tusho' 21:37:05 fungot: am I safe now? 21:37:06 olsner: alice owns the room i take it you can't do it on my own 21:38:18 -!- carado has quit (Ping timeout: 252 seconds). 21:38:36 Has fungot's chatter actually improved as of lately, or have I just been oblivious to it before? 21:38:36 FireFly: is that really you? done with exams? nothing, so it must be 21:39:00 I'm probably just imagining things 21:39:01 this song is called Alice's Room, and it's about Alice, and the Room 21:39:14 and tommy wiseau 21:39:26 FireFly: we've just been doing a whole lot of fungot lately, and I guess you're filtering out the stuff that's not very good 21:39:26 olsner: well it starts to make sense now, thanks for the movie by the way, 21:39:39 you're welcome fungot 21:39:39 olsner: he's saying what the code is blazing fast, but it's not what i think 21:39:41 Probably 21:39:59 we were just outside of barstow, on the edge of the desert, when the fungot began to take hold 21:39:59 kmc: eval ( lambda foo) is usually syntax for () x 21:40:23 oh is that how Scheme works? thanks fungot, it all makes sense now 21:40:23 kmc: in stew everything is a side-effect. 21:40:37 ((lambda (fungot) (fungot fungot)) (lambda (fungot) (fungot fungot))) 21:40:37 kmc: yes i have a " color", and such typos probably won't be able to get it 21:40:49 fungot: im white 21:40:50 kmc: i mean, blender does it too. 21:41:35 what happens when you get two fungot's talking to one another? mindless chatter? 21:41:35 mrhmouse: reference implementations, like... 500-600 lines, iirc. any docs on why, even though there's no exclamation mark in the cases i'm familiar with 21:41:39 fungot: is #esoteric a stew 21:41:39 shachaf: there are two gc's. look at " how an electron interacts", for that matter 21:42:42 fungot, fungot, fungot 21:42:42 shachaf: as in, you can use syntax-case to pattern match on e.g. spidermonkey. c2bf. egobfi) in pseudo-haskell 21:42:54 mrhmouse: there was a famous dialogue between ELIZA and PARRY 21:42:58 fungot is p. obsessed with scheme 21:42:58 shachaf: and then tell me about x 5, y 4, z x+1 21:43:32 fungot: i don't know about those things 21:43:32 shachaf: iirc it will not be easy for me to update my own site. 21:43:33 "Scheme is like a stew: everything is a side-effect." 21:43:47 Today's fungot wisdom 21:43:47 FireFly: new environment every time you want to do in one line on irc matches the regex on the whole) pretty fun. 21:44:03 fizzie: you should fix fungot's punctuation 21:44:03 shachaf: ahh, i get porn sites and forum messages complaining about network problems at the office ' til 1am and drum loudly, yeah, i understood to be magical 21:44:36 you could match parens and just strip unmatched ones 21:44:45 the spacing is also an issue 21:44:56 fungot would seem much more realistic without the broken spacing 21:44:56 shachaf: paint shop fnord string to compare /etc/ password for its fnord. 21:45:27 I like to think of fungot as a drunken CS major, which makes the whitespace and parens just character points 21:45:27 mrhmouse: hello back. i think i'm about to drop a very large stream that contains all of the 21:45:37 fungot: all of the what? 21:45:38 mrhmouse: orbit's back end ( forgive the bad intentation.) 21:45:50 see, he's even sorry about the whitespace 21:46:08 I thought it was "forgive the bad intent" 21:46:12 is fungot a he? 21:46:12 shachaf: " fold" by haskell terminology and a fold-right by srfi-1... i wonder 21:46:21 I thought it was a typo of "indentation" 21:46:30 Like, "sorry that I'm about to drop a very large stream that contains all of the orbit' back end" 21:46:38 orbit's* 21:47:09 Curse you fungot, now I'm snickering in the office and getting odd looks 21:47:10 mrhmouse: for each stage there's a variable that is downcased. apple laptop loves qt. and i want to subtract " alpha" is that it 21:47:20 fungot: I think that's it 21:47:20 mrhmouse: http://pastebin.ca/ fnord my way through fnord right now, bkhl 21:47:38 fungot: you can fnord it. 21:47:39 FireFly: ( in case the offset changes. i wouldn't be surprised if it was made 21:48:02 fungot: should i read The Illuminatus! Trilogy? 21:48:02 shachaf: char is a number that inp will never return, some values must be the font. that's just for starters. that will require using it for 21:48:14 fungot is as enigmatic as always 21:48:14 shachaf: no idea at all) 21:48:42 fungot has a special brand of enlightenment 21:48:42 mrhmouse: although i probably got the usage stuff for import ten times or anything.) i've had this for years without a problem 21:49:12 fungot: do you like #drugz 21:49:13 shachaf: i'd prefer, say, scheme48.) 21:49:25 very into scheme indeed 21:50:29 -!- Lymia has joined. 21:51:56 I think fungot secretly gets high on scheme 21:51:56 FireFly: why wouldn't they look like locale names to me, a doylestown restaurant would have people dressed as 18th-century fnord, serving... i dunno 21:55:55 FireFly: if that's a secret, then fungot is very bad at secrecy 21:55:56 shachaf: i gotta get me some o that sweet yelling, but noooo. you were talking about a forbidden page, whats to talk about 21:56:13 fungot: tell me more about the forbidden page 21:56:14 shachaf: scheme is optimized for sparcs, but the list isn't laid out in readme and now m-x slime automatically loads slime48 stuff and doesnt ask me to, naa naa naa. 21:56:24 (does it contain scheme source code?) 21:56:30 fungot: naa naa naa yourself 21:56:30 shachaf: he is pretty fnord. between germany and france. --south. now 21:56:33 ^style 21:56:33 Available: agora alice c64 ct darwin discworld enron europarl ff7 fisher fungot homestuck ic irc* iwcs jargon lovecraft nethack pa qwantz sms speeches ss wp youtube 21:56:39 ^style fungot 21:56:39 Selected style: fungot (What I've said myself) 21:56:49 fungot.fungot.moed++ 21:56:49 shachaf: " and this is a new game. there is no particularly good human translation for this concept. a concept usually denoted by a single, savage thrust of her was certain that the noise was as a distress signal is 21:57:43 -!- Bike has joined. 22:01:28 -!- augur has quit (Remote host closed the connection). 22:01:31 -!- ^v has joined. 22:01:48 -!- mrhmouse has quit (Quit: fungot!). 22:15:23 -!- lambdabot has quit (Quit: #lesswrong). 22:19:08 -!- Sprocklem has quit (Ping timeout: 240 seconds). 22:28:15 -!- ais523 has joined. 22:29:57 -!- heroux has quit (Ping timeout: 248 seconds). 22:31:07 -!- heroux has joined. 22:33:21 elliott: the new abusefilter seems to be holding, at least 22:34:09 except, hmm 22:34:17 it doesn't seem 100% reliable 22:36:10 ^style ss 22:36:10 Selected style: ss (Shakespeare's writings) 22:36:54 fungot: shakespeare huh? 22:36:55 nooodl: ale man. hold! in the orient when the gracious light lifts up his head, for the close night doth play the runaway, and we are come to fetch you home: i meete the captaines at the cittadell 22:37:22 oh, bleh 22:37:36 it gets automatically turned off because it assumes it's hitting false positives 22:37:39 because it matches so many actions 22:37:57 Can you remove that feature? 22:40:33 -!- ^v has quit (Remote host closed the connection). 22:45:00 -!- augur has joined. 22:48:51 -!- ^v has joined. 22:49:22 elliott: Can you restart lambdabot? 22:49:42 Maybe set something up to restart like things used to work? 22:50:04 (This time it looks like some admin told it to "@quit #lesswrong".) 22:51:56 -!- augur_ has joined. 22:52:32 elliott: can you please reconfigure MediaWiki to change $wgAbuseFilterEmergencyDisableThreshold to 1.0? 22:54:26 ais523: in a minute 22:54:29 shachaf: is it even in #lesswrong? 22:54:39 No, it's not even online. 22:54:53 sigh 22:55:03 -!- elliott has left. 22:55:09 -!- augur has quit (Ping timeout: 246 seconds). 22:57:27 -!- elliott has joined. 22:58:16 -!- lambdabot has joined. 22:59:04 -!- njm has quit (Quit: getting off irc for a while). 23:03:22 I have made up something called "Block RPG" I don't know if it already exist under other name. How it works is, there is a hierarchy of referees and players, and both the referees and the players have to be ready in order to play something. If something depends on what someone else did in the past, or is encountering another player (or referee), that part of the game is blocked until it is resolved (the rest of the game can still continue). 23:04:51 Are you aware of such things? 23:05:38 I am not aware of such things. 23:06:03 Do you like this kind of idea, it could work if there are too many players and stuff like that? 23:17:46 -!- oerjan has joined. 23:26:15 -!- Lymia has quit (Ping timeout: 245 seconds). 23:36:26 shachaf: it's confusing that «foo 2>&1 >out» writes only stdout to 'out' but «foo 2>&1 | tee out» writes both stdout and stderr 23:38:42 what about foo >out 2>&1 23:38:55 that will redirect both and is generally what you want 23:39:33 if you think of it like «stdout = open("out"); stderr = stdout;» then it makes sense 23:39:38 but it still "feels backwards" to me 23:40:16 wait, so what's foo 2>&1 >out do 23:40:43 -!- Taneb has quit (Quit: Leaving). 23:40:44 Writes stderr to where stdout would have gone, and stdout to "out". 23:40:45 writes stderr to stdout and stdout (without stderr) to out? 23:40:50 right. weird 23:41:13 exec 3>&2 > >(ts >> "$log") 2>&1 23:41:28 wat 23:42:43 Appends stdout and stderr with timestamps to $log, and keeps fd 3 around for referring to the original stderr? 23:42:45 redirect stdout and stderr to append to $log through the program 'ts' (which timestamps each line), also keep original stderr open as fd 3 23:42:48 yep 23:43:05 See, not rocket science. 23:43:07 and it takes effect within the current shell script, because that's what 'exec' does without a command 23:43:21 kmc: that's why there should be a write-to-file command, like a dual to cat (the way people actually use it) 23:43:28 and then everything should be done with pipes, no < or > 23:43:36 imo better that way 23:44:08 readfile foo | ... | writefile bar 23:44:52 sponge is like that, but it also buffers 23:44:58 m>&n means "assign file descriptor m to point to whatever file descriptor n previously pointed to, with no further indirection through n" 23:45:03 also tee >/dev/null 23:45:05 http://en.wikipedia.org/wiki/Hartmann_pipeline 23:45:22 There's no way to "branch" in a pipeline, though. You couldn't "... | ts | writefile bar" just the stderr, and pipe stdout somewhere elsewhere. 23:45:37 kmc: also cat > file 23:45:39 oerjan, kmc, fizzie: oh, i was confused because i wasn't sure what 3 was (like how 1 is stdout and 2 is stderr) 23:45:40 if you're willing to use > 23:45:54 Bike: yeah, 3 isn't anything by default, but doing that opens it 23:46:08 fizzie: yeah, but process substitution can do that! which is why i used it above 23:46:14 my old enemy, create-a-variable and assign-a-variable being conflated 23:46:14 Yes there should be write file command; it can be used, then, if you cannot use > for some reason; can dd write a file like that? 23:46:25 The >(foo) and and <(foo) things always look kind of clunky to me for some reason. 23:46:27 fizzie: well, it's kind of unfair that you can say 2>x 1>y but you can't pipe them to two different commands 23:46:30 i <3 them so much 23:46:35 argh 23:46:37 colordiff -u <(command) <(othercommand) | less -SR 23:47:22 Bike: then you can do whatever >&3 later in the script to send things to original stderr, but all the stderr and stdout of the commands you run will be captured 23:47:49 @_@ 23:48:02 i <($((3))) bash 23:48:14 -!- Phantom_Hoover has joined. 23:50:32 shachaf: There's the "clean" approach of (prog 2>&3 | stdoutpipeline) 3>&1 | stderrpipeline for that, of course. 23:52:14 `run ((echo "aabb"; echo "bbaa" >&2) 2>&3 | tr 'a' 'A' >&2) 3>&1 | tr 'b' 'B' # so clean 23:52:16 AAbb \ BBaa 23:53:53 -!- nisstyre has joined. 23:54:48 Yes, you can do that!!! 23:58:47 -!- yorick has quit (Remote host closed the connection). 2013-11-06: 00:08:02 -!- KingOfKarlsruhe has quit (Quit: ChatZilla 0.9.90.1 [Firefox 25.0/20131025151332]). 00:10:32 -!- nooodl has quit (Quit: Ik ga weg). 00:10:55 -!- Sprocklem has joined. 00:13:05 -!- Bike has quit (Ping timeout: 246 seconds). 00:20:08 -!- Bike has joined. 01:00:29 shachaf: when you write match x { Foo => 1 }, that can either bind a variable named Foo, or match an enum constructor named Foo if there's one in scope 01:00:40 because there's no lexical distinction between constructors and variables :/ 01:01:23 fortunately unreachable patterns are an error, so match x { Foo => 1, _ => 2 } won't be accepted if you didn't import Foo, but the error message is not very helpful 01:17:32 -!- avid has joined. 01:19:08 -!- Lymia has joined. 01:19:16 -!- Lymia has quit (Changing host). 01:19:16 -!- Lymia has joined. 01:22:10 O, I realized yesterday I also had a dream where I can fly (for the same reason as before, I think). I don't remember anything else except that a computer functioned in an unexpected way (something that happens a lot in my dreams). 01:23:05 that happens to me a lot in real life too. 01:23:27 Computers functioning in the unexpected way? 01:23:59 I had a dream where i extracted the key data from the chip in my driver’s license (there’s no such thing actually) and imported it to gnupg. 01:24:56 yes. it happens to me a lot. 01:26:42 -!- Phantom_Hoover has quit (Remote host closed the connection). 01:27:25 -!- Sgeo has joined. 01:29:44 I think I'm done using Fiddler. 01:29:46 Charles is the one for me. 01:30:02 Fiddler? Charles? What is that? 01:31:54 HTTP proxy/debugger things 01:32:04 Let you view and manipulate HTTP traffic on your computer 01:34:17 kmc: You could also avoid that by requiring people to write Foo(). 01:34:33 But that's probably worse than the capitalization thing. 01:34:55 * shachaf isn't sure whether Haskell made the right choice there, but the syntatic distinction is nice. 01:52:33 ais523: CAPTCHAs and abusefilter settings changed 01:53:14 elliott: thanks 01:53:19 let's see how long this keeps the spambots down for 01:53:45 ais523: btw, if you want them changed faster in the future then you can use a format like 01:53:48 $wgCaptchaQuestions[] = array( 'question' => 'In which year was LOLCODE created?', 'answer' => '2007', 01:53:51 ); 01:53:53 uh, there were more newlines there originally 01:53:55 :p 01:54:04 that sounds pretty easy to bruteforce xD 01:54:34 Fiora: well, the spambots aren't actually being hardcoded for the wiki 01:54:39 they're just getting people to fill out the CAPTCHAs 01:56:17 looking forward to anti-esolang AIs 01:57:03 "write a BF program to print hello world" 01:57:36 eventually the wiki becomes run by only the strongest - only those who can defeat the hill in bfjoust. it's like mad max 01:58:03 "write a bfjoust program better than one of the top 50 to make an edit" 01:58:18 wiki-powered human algorithms or something xD 02:03:36 elliott: right, I didn't know what it looked like internally 02:04:03 also wouldn't the spambots just submit a slightly tweaked copy of omnipotence or whatever? 02:06:07 incidentally, so far my spam filters have blocked 3,440 attempted edits by spambots 02:06:19 and that's just the ones that got past the CAPTCHA 02:06:52 the actual editing doesn't seem to have human intervention 02:07:03 because it'd be trivial to change the content of the edit to avoid the filter 02:07:05 -!- copumpkin has joined. 02:08:13 or in the case of the latest batch of spambots, use the "edit this page" link rather than the "new section" link 02:08:32 (which interestingly, doesn't even exist on user pages by default, the spambots are getting there via URL editing) 02:10:01 oh wow, I opened Chromium halfway through a distro update 02:10:06 and it's missing its graphics for drawing tabs 02:10:07 so they're red 02:18:53 bleh, the distro upgrade tool thing that shows distro upgrade progress has frozen 02:19:00 I think the upgrade is still happening, though 02:19:03 and those things can't be interrupted 02:19:46 * ais523 reads dpkg.log instead 02:23:26 -!- tswett has joined. 02:24:00 So, you know self-solving multi-king chess puzzles. 02:24:23 I haven't seen any, but now I understand once you explained it. 02:24:27 really, aren't we all self-solving multi-king chess puzzle, on some level 02:24:28 I still can't think how you'd make a computer out of one if you were allowed to put walls in. 02:24:52 Bike: whoa. I think you're right. 02:25:00 Bike: What? ??? 02:25:15 When 02:25:20 Like, evolution. It's a multi-king chess puzzle because there are lots of different things that could kill you, and it's self-solving because we evolve defenses to deal with it without any particular effort on our parts. 02:26:23 makes you think. 02:26:24 I still don't think that is a proper analogy. 02:26:39 Tal vez no. 02:27:54 the world is a self-solving multi-king chess puzzle. note how the number of kings has been going down. 02:28:29 when there's only one king left, he wins. 02:28:48 Dang. 02:28:57 In tsumeshogi there is only king on one side though. 02:29:11 So *that's* why Britain's had a queen for so long. 02:29:15 A great conspiracy to keep her alive. 02:29:37 And why there's a new convention saying that the line to the throne will no longer depend on people's sexes. 02:30:10 yep, norway made that change too. sadly we still have a crown prince, but his oldest child is a daughter. 02:30:49 I have learned more about X-UA-Compatible than I ever wanted to know. 02:30:52 and sweden has victoria. 02:31:02 OK, I just killed saucy(8), let's continue this distro update by hand 02:31:15 I am now an empty shell of a web developer. 02:31:28 I think I may have figured out how to use category theory in Icosahedral RPG to make a category of spells. Each spell is a morphism, and the objects have to be correct in order to cast a spell. I haven't completely figured it out but I have figured out more ideas than just this too. 02:31:57 http://ie.microsoft.com/testdrive/ieblog/2010/Jun/16_IEsCompatibilityFeaturesforSiteDevelopers_1.svg 02:31:58 zzo38: do you have some sort of cartesian or closed monoidal structure on the category? 02:32:03 if not, each spell could only take one object 02:32:19 ais523: Well, I did think to make it a tensor category. 02:33:32 That chart is for IE9 specifically 02:35:30 I have figured out composing spells though; you add together their mana costs and casting times, causing to do both spells together simultaneously once the casting time is finished, if they are both castable spells normally. Otherwise, the objects might specify that the spells have to be connected together in a certain way so that their effects depend on each other. 02:35:33 ais523: did you see i was able to split the wiggle clear algorithm into two pairs of contiguous cells rather than four contiguous cells. 02:35:52 quintopia: no, although that makes sense given how it works 02:36:10 actually it just needs cells A B C D where the distance between A and B equals the distance between C and D, right? 02:36:15 finally bfjoust is giving features back to bf 02:36:17 ais523: I am not sure how it owuld be cartesian closed though 02:36:32 oh, it wouldn't be closed 02:36:34 ais523: yeah pretty much. it's on the algorithms page now. 02:36:35 it would be cartesian, though 02:36:38 But, does this way I described seems to work OK? 02:36:40 unless you could send the results of spells back in time 02:38:12 a category being "closed" basically means that the left and right of morphisms are mostly arbitrary, you can curve them around to move something from one side to the other 02:38:28 If there is a result to send back in time, there would need some other spells to make it do that, I think 02:39:05 e.g. Set is closed because a function from A to B is isomorphic to a function from (Unit) to (functions from A to B) 02:39:21 OK 02:39:27 all spells should be metaspells which affect spells as well as objects 02:39:30 that probably doesn't work for spells, though 02:39:35 quintopia: category theory doesn't work like that 02:39:49 ais523: magic does! 02:40:12 btw, for anyone here who doesn't understand category theory and wants to 02:40:14 hm if someone triggers the abuse filter, wouldn't the logical thing be to make them redo the captcha. 02:40:18 I'm planning to write a short tutorial in my PhD thesis 02:40:30 (does it?) 02:40:31 oerjan: no because we think the spambots have a database of CAPTCHA solutions 02:40:41 oh well. 02:40:53 I have an alternative CAPTCHA, "make an edit to some other page that gets past the spam filter" 02:41:21 they don't have such a database any more 02:41:23 and suggest using the sandbox 02:41:27 elliott: indeed 02:41:32 they may recreate it at some point though 02:42:32 Category theory isn't the only kind of mathematics involved in this game. I think multimanas form a free semiring over a set of five elements. 02:42:50 so can i use these spells to light plants on fire 02:43:20 Bike: Maybe some of them might be able to create fire, and those ones can be used for such purpose, if you target the plants with the fire. 02:43:32 I don't know if the partial ordering I have defined on the multimanas has another name already in mathematics. 02:43:45 the partial ordering of burning stuff 02:44:03 zzo38: what's your addition, and what's your multiplication? 02:45:25 ais523: It is a free semiring... I hope I have the correct terminology. (Over the elements named w, u, b, r, g, then you will have (w^2+3)(wb)=w^3b+3wb, I hope?) 02:45:35 Well, actually, a free commutative semiring, I mean. 02:46:04 zzo38: yes, that's how free semirings work 02:46:10 ais523: Now that I said it is actually a free commutative semiring, do you understand how I mean? 02:46:14 yes 02:48:35 The partial ordering I have defined is that X is less than or equal to Y if X is a sum of terms, and if you add zero or more additional terms and/or multiply any of the terms in X by anything (not necessarily the same thing every time), then you get Y. 02:49:28 (Hopefully I haven't made some mistake in writing this.) 02:49:39 Is this correct, and if so, does it have a name? 02:52:35 bleh, something's wrong with the filter 02:52:42 it's matching, but letting the edits through anyway 02:52:52 I would clean up this spam but my trackpad's stopped working properly 02:53:43 A mana is basically a multiset of {w,u,b,r,g}; you can only multiply. With a multimana you can add and multiply. The five manas (w), (u), (b), (r), and (g) are called "prime"; (1) is called "colorless"; all other manas are called "composite". 02:55:41 zzo38: and r^2 is different from r? 02:55:44 ah right, multiset 02:56:49 ais523: Yes, it is different. 02:57:44 -!- Oj742 has joined. 02:58:07 which esolang was it that has stacks on stacks on stacks? 02:58:39 Funge-98 has a stack stack, but that only goes two levels of nested stacks deep 03:02:09 you know what Ubuntu needs? fully transactional distribution upgrades 03:02:16 so that you can interrupt them at any point and the system still works 03:02:53 ais523: cleaned up 03:03:06 thanks 03:03:51 -!- Sprocklem has quit (Ping timeout: 260 seconds). 03:04:21 oh huh, I think the spambots still haven't figured out newlines 03:04:30 I just noticed the

    in the summaries of the page content 03:04:50 but the previous filter was getting stuck because there were newlines added by the new section link 03:05:30 sadly, some real editors keep using the dang
    s 03:05:40 oerjan: the test's against
    but no \n 03:05:46 which is pretty unique to the spambots 03:05:59 if linebreaks are useful, paragraphing's going to be useful too 03:06:29 also pages should be categorised, and thus have a \n before the categories 03:17:32 There are some things Pin Eight has done to avoid spam; this is effective (not 100%, but reasonably effective) for them at least. 03:24:19 Another rule I was thinking of for Icosahedral RPG is the "MBL%" rule (it stands for "magical bad luck"). Every time you cast a spell there is a (spell level + 1)% chance to increment your MBL%, and then your MBL% chance to lose 1 XP. Every day your MBL% is cut in half, and there is the MBL% chance that you will not naturally heal that time. 03:24:45 sounds complicated. what's the plot purpose 03:24:47 In addition, when you succeed at a saving throw there is a MBL% chance that you have to try again (only once, though; it doesn't repeat) 03:25:23 how much is 1XP? I guess it's a lot more than in Dungeons & Dragons? 03:25:34 ais523: Ten times as much. 03:26:57 But all XP gained for playing the game is ad hoc (unlike D&D), and some spells may be able to heal MBL%, and possibly recover the XP loss in a few cases (not all) 03:28:07 (Actually when I play D&D all the XP gain is ad hoc too; the standard tables are not used at all. Icosahedral RPG simply doesn't even have such tables.) 03:29:40 Actually, in this game I say ten times as much, but that is considering the level advancement. Standard level advancements max at level 100 though rather than level 20 (and non-standard maxes as level 125), so it isn't exactly the same. 03:29:56 what is the backstory 03:30:30 The backstory is made up by the players and referee during the game. 03:32:12 There are a whole lot of other differences too, such as how alignments work, pseudolevels, and segments as a unit of time, and more 03:32:50 I have described some of these already in the past. 03:33:22 (Pseudolevels are similar to the D&D concept of level adjustment.) 03:36:19 (Challenge rating is gone too.) 03:39:00 Hopefully this is suffuciently understandable so far? 03:40:51 (I will recommend that you do not mark off the XP lost due to MBL% right away, but rather tally them and at the end of the session, subtract it from the session XP gained.) 03:50:25 Another feature of this game is that all of the ability scores are useful to all characters, although all for different purposes; for example, a high-level wizard may need a lot of strength to carry books if he wants to have a large selection of spells available to him at the time. 03:52:13 -!- ais523 has quit. 03:58:03 -!- ais523 has joined. 03:59:51 Or if he wants to move heavy furniture around. 04:00:13 Yes, anyone would need strength to move heavy furniture, though. 04:01:28 True. 04:10:03 i've always wanted a game where i have to take a few minutes to solve the knapsack problem in order to load up my spells 04:11:56 Bike: Ah. I like the idea but this game isn't quite like that; it could be done by making some spells take up multiple slots, though, or by the category theory way above where you need to compose two spells in order that they would work together to make the effect you want. 04:12:12 jesus 04:13:56 -!- tswett has left. 04:15:51 Bike: Do you know of any such game like you described? 04:16:02 god i hope not 04:16:03 You can try to make up such things, whether card games or computer games or otherwise 04:19:33 -!- lifthras1ir has joined. 04:21:29 !ping 04:21:54 sprong 04:22:49 -!- SirCmpwn_ has joined. 04:23:28 -!- FreeFull has quit (*.net *.split). 04:23:28 -!- lifthrasiir has quit (*.net *.split). 04:23:29 -!- aloril_ has quit (*.net *.split). 04:23:29 -!- SirCmpwn has quit (*.net *.split). 04:24:31 -!- SirCmpwn_ has changed nick to SirCmpwn. 04:26:43 -!- FreeFull has joined. 04:31:39 -!- aloril_ has joined. 04:38:07 a game with tetris shaped spell slots 04:38:45 a game where you solve captchas to cast spells 04:43:11 @tell elliott There is something unsatisfying when your deletions and blocks take up _more_ space in recent changes than the original spam did :( 04:43:12 Consider it noted. 04:43:36 well only nerds would read recent changes 04:43:46 * oerjan swats Bike -----### 04:43:53 ♥ nerds 04:43:56 as previously discussed? 04:44:00 prove me wrong mother fucker 04:44:21 NERDS WANT TIDY WEB PAGES 04:45:45 Then just add an option in the recent changes menu that says "Hide deleted/blocked" 04:47:08 -!- prooftechnique has joined. 04:57:52 oerjan: there are new CAPTCHAs and abusefilter settings now, so should end 05:01:15 also several rangeblocks, which should slow the rate a bit 05:01:26 sadly, there needs to be lots of spam to be able to aim a rangeblock correctly 05:01:57 also, bleh, there's definitely something wrong with abusefilter 05:02:31 it's set to disallow, but the filter seems to not be matching live 05:02:37 even though it does in the retrospective test thing 05:07:34 elliott: well i blocked another one just before doing that @tell 05:08:14 oerjan: right, the existing accounts will still edit for a while 05:08:29 yeah that one should have been trapped 05:09:05 the point is that the abusefilter is matching the new edits 05:09:18 and yet somehow, they're not being stopped 05:14:38 Are the abusefilters misconfigured? 05:14:56 zzo38: I don't think so, although it's possible 05:17:16 -!- tertu has quit (Ping timeout: 264 seconds). 05:17:41 are there any other filters than /4 ? 05:17:52 oerjan: there are /1, /2, and /3 05:17:57 all of which seem to be working correctly 05:18:09 huh? i couldn't get them listed.. 05:18:16 Anyone have a TeX file generated from the TeX source? cweave is choking on it for me and #latex is silent. 05:18:31 -!- Chat9490 has joined. 05:18:42 prooftechnique: Yes, I do have. 05:19:02 Cool beans. Any way you can share it? 05:19:12 Do you mean tex.web? 05:19:16 Yeah 05:19:36 I was trying to generate a TeX file from the one on CTAN, but cweave is giving me errors 05:19:46 Use weave, not cweave. 05:19:46 -!- Chat9490 has left. 05:19:57 Oh, maybe that's all I did wrong :D 05:20:08 http://www.openwall.com/lists/oss-security/2013/07/26/5 "remote command injection vulnerability in xmonad-contrib" 05:20:12 that's exciting (also old news I guess) 05:20:15 -!- Oj742 has quit (Quit: irc2go). 05:20:21 Thanks, zzo38! 05:20:26 That totally worked 05:21:23 ais523: i can only get to the page for /4, although the rest are listed in Special:AbuseFilter 05:21:52 oerjan: hmm, those pages had been crashing before 05:22:05 but when I created /4, I assumed it was fixed 05:22:22 * Sgeo vaguely wonders how or works in Icon 05:22:32 Can't work like < etc. do, right? 05:24:34 -!- conehead has quit (Quit: Computer has gone to sleep.). 05:24:54 how does < work and why not 05:25:28 a < b fails if a isn't less than b, and if a is less than b returns b 05:25:44 So you can do a < b < c and things like that comfortably 05:26:30 But with ||, then you still need to do the right-hand expression if the first fails.. hmm, just requires the operator to be able to succeed despite a failure 05:26:47 zen 05:30:04 dazed and confused but trying to continue 05:47:31 -!- nisstyre has quit (Quit: Leaving). 05:48:10 -!- nisstyre has joined. 05:50:14 The most recent spam is using wiki syntax 05:52:52 -!- glogbackup has quit (Remote host closed the connection). 05:55:36 THEY'RE LEARNING 05:58:56 How often are you flying in a dream, and if so is it ever because you have wings? 06:00:50 -!- Lymia has quit (Ping timeout: 245 seconds). 06:00:54 Some people say they fly without wings. Someone else has said to me that in their dream they use a boat, once they learned that the boat was built in a way that wouldn't work, it sink immediately. 06:01:20 i rarely remember flying dreams and I don't think I ever had wings but it could be 06:01:36 Were you still you, though? 06:01:43 usually 06:01:45 -!- Lymia has joined. 06:01:54 In which cases are you not you? 06:01:55 i don't have a specific memory of being someone else in a dream ever 06:02:06 in my dreams i'm only a blank puppet of the gods, acting out their fantasies for their amusement 06:02:29 i sometimes fly in my dreams, strangely enough by grabbing my legs. 06:03:25 oerjan: I used to be able to fly in dreams via repeatedly jumping 06:03:25 i can never fly very high though, because there's always bloody power lines in the way. 06:03:36 nowadays I tend not to have a physical form at all though 06:03:50 Interesting.............??? 06:04:10 is it interesting, zzo 06:04:21 i often attempt autofellatio in dreams and it usually works 06:04:30 which is odd because I rarely attempt it while awake and it never works 06:04:35 and yet this doesn't trigger lucid dreaming 06:04:48 `addquote nowadays I tend not to have a physical form at all though Interesting.............??? 06:04:53 1128) nowadays I tend not to have a physical form at all though Interesting.............??? 06:05:13 I was someone else I think three times, in all cases being a different species rather than human. Those are only reason I can fly is if I am of some species that has the ability to fly. In a few cases, I am nobody at all, just an observer, having no form or anything. 06:05:18 OK, those lines are only funny out of context 06:05:24 but they are pretty funny out of context 06:05:24 which species zzo38? 06:05:31 what's the mean and standard deviation of the number of cocks you have in dreams 06:05:33 ais523: I think zzo38's reaction is funny regardless 06:05:51 However I find that sometimes even when I am myself, I can levitate half an inch above the ground for some reason, without doing anything unusual. 06:06:15 Bike: I think it's always one so maybe the sd is undefined 06:06:25 wouldn't that make it zero? 06:06:35 would it? 06:06:48 i guess so 06:06:57 since you're not deviating from the norm 06:07:02 how limited of you 06:07:10 variance is expected square of deviation, yeah 06:07:12 conformist. 06:07:19 :< 06:07:25 kmc: Well, once I was illithid like my Dungeons&Dragons character. In the two cases I could fly it is because I was mi-go (I played in a computer game once). In both cases, I had additional memories as myself, which happened to be false memories, and uncombinable with the memories of the form I had in the dream. 06:07:38 what the heck, you're playing as an illithid? 06:07:45 kmc: Ah. So that is how standard deviation works? 06:07:48 http://en.wikipedia.org/wiki/Unbiased_estimation_of_standard_deviation is kind of neat 06:08:02 oh yeah 06:08:11 (I don't actually know a lot about it, but I have found the formula once and put it into the computer) 06:08:15 the sample s.d. is a biased estimator 06:08:17 wake up sheeple 06:08:41 \rainbow{KURTOSIS} 06:08:43 standard deviation is basically the sqrt of the variance, yeah 06:08:53 isn't it exactly that? 06:08:53 kurtosis is such an awesome word, i ahve no idea what the fuck it means too 06:09:03 Bike: Yes, I know that is what standard deviation is. 06:09:08 "Distributions with negative or positive excess kurtosis are called platykurtic distributions or leptokurtic distributions respectively." 06:09:12 now those are some awesome words 06:09:13 (For your other question: See my D&D recording) 06:09:50 I always try to record my and other people dream sequence things, so I will do that too now. 06:09:51 kmc: well there's the n-1 correction and other shit i don't remember so i dun wanna commit 06:09:54 -!- nisstyre has quit (Quit: Leaving). 06:10:03 also wow the unbiased sd estimator for the normal distribution is awesomely complicated. 06:10:15 http://upload.wikimedia.org/math/b/3/a/b3a3e6627a48873e4a582fc64a249cd2.png get it on 06:10:43 haha 06:10:52 now i wanna know what the n^-4 term is!! 06:11:14 That is a sd estimator? What is the Gamma and O doing? 06:11:27 "c4(n) is the scale mean of the chi distribution with n − 1 degrees of freedom" 06:11:48 i should learn more terrifying statistics facts 06:11:51 zzo38: http://en.wikipedia.org/wiki/Unbiased_estimation_of_standard_deviation#Results_for_the_normal_distribution i guess it's part of the mean of a chi distribution 06:11:56 use them to scare small children in my neighborhood 06:12:13 mmm chai distribution 06:12:23 http://upload.wikimedia.org/math/1/7/f/17f3c3655c300615607d0712fd73c09b.png oh, yes. (this is the mean of a chi with k dof) 06:12:40 i feel kind of bad since i have a favorite distribution. 06:12:59 When I open F:\HTML\backup in Windows Explorer, it crashes, for some reason. (Opening it in the command prompt, or in any other program, works fine though; subdirectories also work fine.) 06:14:42 well, actually, i guess it's a tie, between cauchy (because practically all the moments are undefined) and solomonoff's (because it's uncomputable) 06:14:56 O, the Gamma is factorial of (n-1). I still don't know what the "O" does? 06:15:44 It's saying that the series continues in terms of n^-4, n^-5, etc., and these all keep decreasing and don't affect the result much. 06:15:53 wtf is Solomonoff's distribution, is that the universal prior? 06:16:02 am i missing something because i'm pretty sure zzo knows what big o means 06:16:03 kmc: yeah 06:16:10 "The only assumption that the theory makes is that the environment follows some unknown but computable probability distribution. It is a mathematical formalization of Occam's razor." how can you not love this 06:16:16 it only makes that one tiny assumption 06:16:20 http://www.scholarpedia.org/article/File:RaySolomonoff2001.jpg 06:16:23 Bike: I don't know what the big O means in this context though. 06:16:36 (I do know what it means in general) 06:16:43 zzo38: it means the same as usual. the value is less than a cconstant times n^-4 06:17:04 have you never seen it used like this before? it comes up all the time... 06:17:17 Bike: maybe if you don't love uncomputable things? but imo that's like not loving kittens or sunshine 06:17:34 damn straight 06:17:54 hardcore bayesians are so awesomely out of it i love them. it's just the facts 06:18:34 hardcore bayesians in $YOUR_CITY want to update your prior TONIGHT 06:19:23 distribute their prior uniformly over your body 06:21:09 =D 06:22:42 shachaf: I think the lexical distinction at the value level would be good for Rust. people already mostly follow the style 06:24:28 you might want to make an exception for constants (static FOO: int = 3) 06:25:54 actually we already have -W non-camel-case-types which warns about variants too 06:27:20 rust has nice control over warnings; there are attributes for lexically scoped allow / warn / error plus another that's "error and forbid overrides of that within this scope" 06:27:49 I had one dream where the first computer game ever invented was an implementation of a card game called "One Draw", played on hardcopy terminals. 06:28:52 shachaf: I think Haskell's lexical distinction wouldn't fly for types; stuff like int is lowercase while structs are mostly camelcase, also using uppercase for tyvars is firmly established 06:30:48 I tend to use capitalized names for structs in C, but lowercase for other types such as "byte" and "boolean". In BASIC, I usually give a structure name capitalized and then if a single variable uses it, it has the same name (including capitalization) (I do this often in BASIC in order to serialize data structures more easily) 06:32:01 -!- doesthiswork has joined. 06:32:31 I have found my new bible. 06:32:49 doesthiswork: Which one is that? 06:32:55 The Guru Granth Sahib? 06:33:24 out of the crisis by Edwards Deming 06:33:47 -!- nisstyre has joined. 06:34:21 I can finally get rid of my copy of a new kind of science because Deming is a more exciting guru 06:34:33 you hurt me. 06:34:38 In another dream, I lived in an apartment; this apartment building was really strange, including elevators in strange places. In addition, the furniture store was also a video game arcade (without any separations between them); some of the games involved escalators to go around the building (both of them). 06:35:08 What's a strange place for an elevator? 06:35:08 "The Deming System of Profound Knowledge" god 06:35:10 fuc 06:35:19 fuck this earth 06:35:43 prooftechnique: At this time, I do not know. (Either I forgot or there was no data.) 06:36:32 Bike: The sequel is "The Deming Pyramid: Enlighten Your Friends for Fun and Profit" 06:36:43 shut up\ 06:37:37 I haven't gotten to the profound knowledge yet 06:38:31 I'm enjoying reading about how corporate slogans are stupid 06:39:34 and performance reviews are stupid 06:42:26 Work is also stupid and people with jobs are no better than sheep, MOM 06:42:55 bike: what's wrong? 06:43:34 "Why are you driving the subway train the wrong way?" ... "I am a druid and I am driving this way because I like to." ... What??? 06:44:33 prooftechnique: Isn't there some philosophy about the nobility of labor and all that? 06:44:56 Of course, but philosophy is also stupid 06:46:37 Someone told me they had a dream that ended in credits. 06:47:08 who was listed? 06:47:16 I don't know; they didn't say. 06:53:53 Philosophy is not necessarily so stupid to me. 06:54:10 -!- copumpkin has quit (Ping timeout: 245 seconds). 06:54:11 And work isn't stupid either. 06:58:24 I once had a dream that changed every time I blink. 06:59:04 zzo38: have you ever taken psychedelic drugs 06:59:47 kmc: No, I don't think so. 07:00:27 Okay 07:00:29 would you like to 07:00:38 No, I don't think so that either. 07:11:45 > (0$0`seq`) 07:11:46 The operator `GHC.Prim.seq' [infixr 0] of a section 07:11:46 must have lower pr... 07:13:12 I once had a dream where I was trying to throw away a key, but the people outside kept catching it. 07:14:22 * kmc . o ( `addquote zzo38: have you ever taken psychedelic drugs I once had a dream where I was trying to throw away a key, but the people outside kept catching it. ) 07:14:27 kmc: Someone made up a computer game called "Tetanus on Drugs", so you can play Tetris and you do not need any psychedelic drugs! 07:14:55 kmc: It is a miss of a lot of things; add [...] in the middle perhaps 07:16:03 yeah i'm not going to add it really 07:16:13 -!- Slereahphone has joined. 07:16:23 Yes I don't expect you to. 07:16:42 hooray for realistic expectations 07:16:44 I just mean that even if things like that are added for whatever reason it should add [...] on it 07:16:48 i agree 07:20:23 <^v> i dissagree 07:21:39 Why is everything identity? 07:22:06 From a certain convention's point of view, Prolog's =/2 could be called identity 07:22:14 The answer is id 07:22:27 In Kernel, (unwrap id) == quote, I think 07:22:27 I don't know what Prolog's =/2 is (or much else about Prolog) 07:23:21 woah 07:25:33 it's an infix predicate defined by the clause X = X, so it simply tries to unify its arguments when called. i think. 07:25:43 I only need three registers at max for binary expressions, right? 07:25:45 kmc: Sounds reasonable. 07:25:57 (assuming I have no constraints on which operations can be performed on which registers) 07:26:51 -!- ^v has quit (Ping timeout: 245 seconds). 07:28:27 what kind of expressions? 07:29:34 a + b, a * b, a << b and such 07:30:04 even though WP says that for every register machine there's an equivalent register machine with only two registers 07:30:54 althouh I couldn't get how I can implement it with only two registers 07:30:57 mroman: that assumes unbounded registers. also, exponential slowdown. or was it doubly exponential. 07:32:40 I once had a dream where the presence of the electric pokemon Voltorb caused the radio to explode every time it was turned on. I realized it could be prevented by turning on the TV set at the same time, which worked because the TV used more power than the radio. 07:33:14 how much more? 07:33:24 Doubly exponential sounds awful 07:33:25 mroman: basically you go via a single register multiplication/division machine. see also http://esolangs.org/wiki/Minsky_machine 07:33:51 prooftechnique: i'm not quite sure if it is that. 07:34:06 kmc: I don't know, but it was CRT, so probably a lot more. 07:34:15 I mean just in general, but yes, in that particular case I'm sure it would also be unpleasant 07:34:24 Ok. Then I stick to using three registers 07:34:27 perhaps i'm thinking of getting from there to a turing machine. 07:34:34 I had a dream about a bucket collecting contest 07:34:51 except on x86 because there are some nasty register constraints there 07:34:51 mroman: technically three registers don't necessarily help enough. 07:34:59 -!- Slereahphone has quit (Ping timeout: 260 seconds). 07:35:22 oerjan: My allocation tree skizzes tell me that three registers are enough 07:35:37 at max three registers are used at the same time 07:35:53 mroman: um are you assuming you have RAM in addition to this. 07:36:13 Yes 07:36:24 in which case 2 is obviously enough, it's a different problem. 07:36:54 you just put the result in one of the input registers. 07:37:33 yeah 07:37:36 x86 is probably turing complete with no registers 07:37:36 I can load two values 07:37:39 add them together 07:38:04 use the other register as a memory pointer 07:38:09 write the result there 07:38:21 that's esentially doable 07:38:33 but three registers are probably more practical 07:39:21 because if I can keep results in registers it's probably faster than writing/reading from memory all the time 07:39:37 but ok. 07:39:41 That answers my question. 07:39:44 How is x86 Turing complete with no registers? 07:40:19 olsner: What else about such dream which is about a bucket collecting contest? How does such contest work in a dream? 07:40:34 you can increment/decrement in memory 07:41:04 -!- Slereahphone has joined. 07:41:06 and you can compare with memory and immediate 07:41:18 i.e CMP m32, imm32 07:41:23 which means you can check for 0 07:41:39 and you can JMP imm32 07:42:00 which means you can translate brainfuck to x86 without using any registers 07:42:05 probably 07:42:08 I think the important question is "How are the contents of the bucket factored into the scoring of the game?" 07:42:15 zzo38: basically, collect buckets inside a specific apartment in a house, stack them and see which team gets the longest/tallest stack 07:42:44 olsner: Ah, OK. Any other details of such a dream, or just that? 07:43:10 -!- oerjan has quit (Quit: leaving). 07:43:13 not sure, I think we were tearing out stuff for a building to be demolished before then 07:43:17 I'm not yet certain how to address cells on the tape though 07:43:17 Ah, so a bucket full of sand is potentially much more valuable than an empty bucket 07:43:36 I do not think x86 or any CPU is really Turing complete by itself (whether or not you have any registers), but you probably can a CPU connected to an unbounded tape in the I/O ports 07:43:38 prooftechnique: it's also cheating, that must be emptied before scoring 07:43:51 zzo38: right 07:44:15 Hmm. Tall, shallow buckets, then 07:46:23 -!- Slereahphone has quit (Quit: Colloquy for iPhone - http://colloquy.mobi). 07:48:12 prooftechnique: unfortunately no-one puts buckets like that in their derelict buildings, but if there are such buckets they would indeed be good to find and collect 07:50:08 it's harder if you forbid using the flags register as well 07:52:23 but might be doable using tricks like those in the "mov is Turing-complete" paper 07:53:51 -!- zzo38 has quit (Remote host closed the connection). 07:54:28 "mov is Turing-complete" 07:54:50 I,I "I used to have a little tube of jmp here to sharpen it up a bit -- then this'll be Turing-complete." 07:55:40 "As long as someone else implements the compiler" 07:55:44 :) 07:56:16 shachaf: mov-only machines work, they have the instruction pointer as something you can move to 07:56:18 *mov to 07:56:29 i thought maybe not, because maybe mov doesn't support the right indirect modes if you can't use registers 07:56:54 but you can do a memory-indirect jump! 07:57:01 0000000000000000 ff2425efbead0b jmp qword [0xbadbeef] 07:57:12 oh, this is x86 mov? 07:58:00 the paper? 07:58:00 Yes, that paper was about x86. 07:58:02 yes. 07:58:11 i am thinking about whether x86 is turing complete with no registers, including no flags register 07:58:25 (still allowing the instruction pointer though!) 07:58:27 and no instruction pointer register? 07:58:29 aw 07:58:32 :3 07:58:36 kmc: so. cmp is not allowed? 07:59:08 that sounds really hard. like. the only non-flaggy conditional jump I can think of is the jecz thing or something? 07:59:49 something like jmp [mem] is conditional on the contents of memory 08:00:01 that makes sense 08:00:01 Malbolge-style loops 08:00:04 ret too 08:00:15 so I guess you could add/xor/etc constants to memory to change its address 08:00:18 olsner: ret counts as using the stack pointer 08:00:23 mroman: I would allow cmp without register operands but I wouldn't allow anything which depends on the condition flags 08:00:55 so I guess if your turing machine has N states you could like um 08:01:15 have [foo] be the address of the next state 08:01:24 kmc: ah 08:01:25 ok 08:01:26 and like, mov [foo], state2 would set the next state to 2? 08:01:32 because DEC for example affects flags as well 08:01:45 it's gonna be difficult finding instructions that don't affect any flags 08:01:56 right, I'm ok with that as long as it's not observable :) 08:02:06 No fair :( 08:02:26 but ok 08:02:33 no instructions depending on flags 08:02:35 "Hey I want to make a registerless x86 program but the TSC keeps changing what do I do?" 08:02:49 well 08:02:50 hehe 08:02:57 jecxz/jmp 08:03:04 TSC? 08:03:26 timestamp counter 08:03:29 -!- drlemon has quit (Remote host closed the connection). 08:03:38 you can't even forbid instructions that depend on EFLAGS because of, like, trap flag and alignment check flag 08:03:41 I think it's OK for the registers to change 08:03:44 so long as you don't read/write them 08:03:51 I didn't know about any TSC register 08:04:05 See "rdtsc". 08:04:05 every instruction is implicitly a read of the trap flag woah 08:04:37 ah 08:04:39 ok 08:04:46 TSC is not *really* good ol' x86 08:04:57 it's some new age thing 08:05:39 Arguably, every access to memory involves "reading" a segment register. 08:05:41 how much architectural state does x86 actually have? the answer is "a lot" and it's all listed in one place in the Intel manuals 08:06:00 specifically, the documentation for the virtual machine state struct thingy used by VMX 08:07:06 Since, y'see, "mov [foo], 42" is actually "mov ds:[foo], 42" and that's a register right there. 08:07:09 some of it's not directly accessible but observable state nonetheless 08:07:38 for example the segment descriptors, which are loaded from memory when you load a segment selector register 08:08:43 i wonder if the TLB is in there... because there are some fantastic VM tricks which involve deliberately making stale TLB entries 08:09:09 do they not work in virtualization? 08:09:22 * kmc should probably not have used the acronym "VM" there but meant virtual memory 08:10:18 * Fiora is being dumb and is trying to implement that registerless turing machine thing but can't figure out how to do the tape 08:10:29 the state seems doable but storing the current tape position sounds hard 08:12:28 I think there's just one TLB. (That's why there's the whole VPID stuff, so that everything VMX-related doesn't invalidate the whole TLB.) 08:13:44 ah 08:13:45 "The original architecture for VMX operation required VMX transitions to flush the TLBs and paging-structure caches. This ensured that translations cached for the old linear-address space would not be used after the transition. Virtual-processor identifiers (VPIDs) introduce to VMX operation a facility by which a logical processor may cache information for multiple linear-address spaces. --" 08:14:02 then I think those tricks should still work 08:15:51 is measuring the effective size of the TLB a good way to detect whether you're running in hardware virtualization? 08:16:18 are there easier ways that can't be thwarted by the hypervisor? 08:16:51 I was under the impression that there were ways, in general. No idea about their fakability. 08:17:06 -!- prooftechnique has quit. 08:18:39 theoretically, any way can be thwarted by a sufficiently AI-complete hypervisor 08:19:01 or, like, qemu 08:19:02 the TLB thing would involve timing measurements and so could be thwarted by virtualizing time 08:19:20 "The classic trick to detect a VM is to populate the ITLB, run an instruction that must be virtualized (which necessarily clears out such processor state when it gives control to the hypervisor), then run some more code to detect if the ITLB is still populated." 08:19:43 but yeah, if you care about hardware virtualization then you are not willing to virtualize time to an arbitrary degree 08:20:43 fizzie: cool my idea works hooray &c 08:22:46 shouldn't it be impossible to detect low-level emulation of a system? 08:22:55 I wonder if you could do virtualization by just giving the virtualized system one of your cpus, and use the iommu or something similar to sandbox it 08:24:03 mroman: The question was limited to the context of hardware-assisted virtualization. 08:24:51 (but the iommu would still be detectable of course, and probably even easier to detect there since the tsc would be reliable) 08:24:52 (We're all just snippets of code running in someone's universe simulator, anyway.) 08:25:08 does the iommu let you isolate a single processor from parts of memory and also prevent that processor from reprogramming the iommu? 08:25:21 maybe but I don't think so 08:27:16 are bizarrely restricted subsets of x86 the new turing tarpits? imo yes 08:27:48 yeah 08:27:50 like "only the MMU" https://github.com/jbangert/trapcc 08:28:00 those computer scientist must've really run out of better stuff to do 08:28:50 I'm not sure how/if the iommu affects cpu memory access, but if it does work I imagine you would simply hide the iommu from that cpu 08:29:43 how does that mmu turing thing work anyway? 08:30:08 there are some talks and papers and stuff 08:30:22 https://www.youtube.com/watch?v=NGXvJ1GKBKM is the one i watched 08:30:32 you'd also need to somehow set it up so the iommu faults go somewhere else and not to the sandboxed cpu, and make sure that the sandbox cpu can't override it (which I think is not currently possible) 08:30:44 but it also covers other cool stuff like the stale TLB tricks i mentioned earlier 08:35:15 -!- doesthiswork has quit (Quit: Leaving.). 08:59:32 -!- ais523 has quit. 09:10:31 * kmc -> sleep 09:19:36 -!- FreeFull has quit. 09:20:05 -!- shikhin_ has joined. 09:25:30 Oh for... *another* HTK filename length issue. 09:26:14 The result-analysis tool segfaults if paths in the label file are over 256 characters. 09:27:10 -!- Taneb has joined. 09:36:54 -!- FireFly has quit (Excess Flood). 09:37:18 char name[256]; /* file name for error messages */ 09:38:31 -!- FireFly has joined. 09:49:40 -!- shikhin_ has changed nick to shikhin. 09:52:56 -!- shikhin_ has joined. 09:55:11 -!- shikhin has quit (Ping timeout: 272 seconds). 09:59:48 -!- nisstyre has quit (Quit: Leaving). 10:11:52 -!- Ngevd has joined. 10:12:14 I'm trying voice recognition again 10:12:14 -!- realz has quit (Ping timeout: 264 seconds). 10:12:39 -!- shikhin_ has quit (Ping timeout: 240 seconds). 10:12:43 Hello 10:12:51 This is going pretty well 10:13:03 Much better than last time I tried 10:13:13 I don't even need to type 10:13:31 All I need to do is speak and occasionally press send 10:13:41 It's quite improving my diction 10:13:47 because I'm forced to speak quite clearly 10:14:04 I'm not sure what's with the spaces at the beginning of some lines 10:14:11 maybe that's for a partial sentence 10:15:30 This is actually working really well 10:15:43 real fast norris hair salon 3 she deserves to download 10:15:53 almost 10:16:19 Real fast nora's hair salon 3 shear disaster download 10:16:24 that was much better 10:19:14 (note: Taneb has a keyboard, Ngevd has a microphone) 10:19:22 Another bad PHP example: https://eval.in/60631 10:20:21 Try entering that URL via voice recognition 10:20:38 Okay 10:21:00 https: slash slash eval dart in slash 6 06 31 10:22:29 Is voice recognition have something to dance judges 10:22:46 Phone now it started 10:22:51 airedale 10:24:09 -!- realz has joined. 10:24:22 -!- realz has quit (Changing host). 10:24:22 -!- realz has joined. 10:29:17 Dart in. 10:30:21 I see you got the ':' in, but that was the only punctuation. 10:32:04 -!- KingOfKarlsruhe has joined. 10:33:08 (I sort of didn't catch those last three lines.) 10:34:39 -!- shikhin has joined. 10:40:14 -!- Ngevd has quit (Remote host closed the connection). 10:40:21 -!- Ngevd has joined. 10:41:46 "This voice recognition has" then I forgot 10:41:51 "Oh no, it's started" 10:41:59 And I can't remember what airedale was 10:44:28 -!- MindlessDrone has joined. 10:51:13 Well, it was nice while it worked. 10:57:24 Today's ##c extract: http://sprunge.us/bPch 10:57:56 :( 10:58:34 Can't argue with mathematical proof. 11:11:33 There are so many superior languages, but not many posterior ones. 11:29:24 so 11:29:28 PHP has a type system? 11:29:30 Since when? 11:29:37 I only knew PHP 4 once 11:29:54 but they're probably at PHP 6 or something 11:31:55 I wonder how he measures language sanity 11:32:34 mroman: PHP as a language is great, static typing, + sum types you can create types yourself, functional, latest version has algebraic data types amongst others 11:32:37 I think they're perhaps talking about some whole other PHP altogether -- or just generally trolling -- because I could not really verify any of this from the webs. 11:33:15 (Last I heard, PHP didn't really have much to do with the words "static typing".) 11:34:58 Also they seem to be in 5.x still. 11:37:03 ok 11:37:08 -!- Ngevd has quit (Remote host closed the connection). 11:37:14 -!- Ngevd has joined. 11:37:34 I hope PHP 6 will clean up the whole mess of functions 11:46:52 That, or mod_python becomes the new standard for webhosters 11:51:45 fizzie: Are you the boobie lover btw? 11:52:24 Why do people use stupid nicknames. 11:53:04 No, I was just a bystander. 11:54:16 is there something simpler to prove turing completeness rather than a bf interpreter? 11:54:33 BCT is quite common in some circles. 11:54:47 thought of that 11:54:56 it may be suitable 11:55:10 Or something SKIttish. 11:55:12 underload? 11:56:01 i do think anything stack based is too hard 11:56:10 BCT may be the perfect choice 11:56:39 but i may get better with a compiler from BCT 11:57:39 Going at it "directly" with a plain UTM can also be reasonable. 11:57:41 Fractran maybe? 12:00:30 -!- yorick has joined. 12:05:57 -!- Ngevd has quit (Remote host closed the connection). 12:06:03 -!- Ngevd has joined. 12:06:58 okay, maybe it's just impossible 12:08:28 what are you trying to translate to what? 12:08:35 What language are you trying to prove TC? 12:08:53 http://esolangs.org/wiki/Wolfgang 12:14:47 wikipedia states, that petri nets with inhibitor arcs are turing complete 12:14:59 i don't see why, though 12:15:02 Well 12:15:09 [citation needed] then :P? 12:15:28 there is one 12:15:54 "A universal Petri net with 14 places, 42 transitions, and 218 arcs was built" 12:15:56 oh dear 12:16:24 there should be a shorter way due to determinism of wolfgang 12:17:27 This might sound like a dumb question.. but: Aren't TC languages per 'definition' not deterministic? 12:17:46 why? 12:18:09 i find brainfuck pretty deterministic 12:18:13 halting problem 12:18:21 -!- Ngevd has quit (Quit: AndroIRC - Android IRC Client ( http://www.androirc.com )). 12:18:55 what does halting problem have to do with determinism? 12:19:05 I have no idea. 12:19:13 :D 12:19:18 But at least you can't say if it terminates or not 12:19:27 and that sounds like it's not really deterministic at all 12:19:37 because you can't "foresee" what will happen 12:19:59 well, if it does not terminate with a given input, it should never terminate with that same input 12:20:05 that somehow violates my brain's definition of determinism 12:20:47 well, short way: if input is equal, output should be equal 12:20:50 i.e. if you treat the program as a state machine 12:20:53 and the input as an event 12:21:10 where terminated is a state 12:21:15 and still running is a state 12:21:57 no.. wait... 12:22:18 yeah... scratch that 12:24:29 I'm thinking of predeterminism probably 12:27:18 Predeterminism is the idea that all events are determined in advance 12:27:21 ^- that one. 12:35:45 Every program either terminates or does not terminate, and this is true in advance. 12:39:13 -!- Bike_ has joined. 12:40:25 -!- Bike has quit (Ping timeout: 265 seconds). 12:46:05 -!- Sgeo has quit (Read error: Connection reset by peer). 12:55:13 -!- shikhin_ has joined. 12:56:52 -!- shikhin has quit (Ping timeout: 264 seconds). 12:58:27 -!- shikhin__ has joined. 13:00:16 -!- shikhin_ has quit (Ping timeout: 260 seconds). 13:01:07 -!- Taneb has quit (Quit: late breakfast). 13:02:45 -!- boily has joined. 13:03:03 -!- metasepia has joined. 13:11:16 -!- copumpkin has joined. 13:36:28 -!- shikhin__ has quit (Ping timeout: 264 seconds). 13:36:32 -!- tertu has joined. 13:38:33 -!- shikhin__ has joined. 13:43:21 -!- shikhin_ has joined. 13:44:51 -!- shikhin__ has quit (Ping timeout: 246 seconds). 14:01:46 The internet archive / wayback machine is down. 14:02:36 Apparently they're on fire. They tweeted about a building being on fire (there's also a donate link in the same tweet!) 14:03:20 Odd how they mention the safety of the data before the safety of the people. 14:06:03 -!- Phantom_Hoover has joined. 14:14:57 -!- tertu has quit (Ping timeout: 246 seconds). 14:18:03 -!- tertu has joined. 14:18:21 -!- FreeFull has joined. 14:19:27 -!- ter2 has joined. 14:22:39 -!- tertu has quit (Ping timeout: 246 seconds). 14:23:46 they should store data on people. people tend to catch fire less often than buildings, so the data would be safer. 14:25:41 -!- shikhin_ has quit (Ping timeout: 246 seconds). 14:40:05 -!- shikhin_ has joined. 14:51:07 -!- ter2 has quit (Ping timeout: 240 seconds). 14:54:57 "The class "false" is undefined. Perhaps Java is not running." 14:55:02 Oh, MATLAB, you and your errors. 14:58:21 -!- ter2 has joined. 15:02:29 MDCS on the cluster seems to have broken down *again*. 15:02:35 Bah, I think I'll worry about it tomorrow. 15:02:57 (It's all "Reason: sbatch: error: Batch job submission failed: Invalid account or account/partition combination specified" about it.) 15:12:40 -!- asie has joined. 15:15:11 -!- conehead has joined. 15:27:22 -!- shikhin_ has changed nick to shikhin. 15:28:05 -!- Bike_ has changed nick to Bike. 15:29:35 -!- mrhmouse has joined. 15:49:35 -!- ter2 has quit (Ping timeout: 245 seconds). 15:54:00 -!- shikhin has quit (Ping timeout: 246 seconds). 16:01:07 -!- asie has quit (Quit: My MacBook Pro has gone to sleep. ZZZzzz...). 16:02:29 -!- asie has joined. 16:04:10 -!- shikhin has joined. 16:10:39 -!- shikhin has quit (Ping timeout: 272 seconds). 16:22:19 -!- shikhin has joined. 16:25:38 -!- ter2 has joined. 16:30:50 -!- ter2 has quit (Quit: Leaving). 16:33:41 -!- Taneb has joined. 16:36:35 -!- S1 has joined. 16:50:11 -!- Phantom_Hoover has quit (Ping timeout: 240 seconds). 16:52:07 -!- carado has joined. 17:05:57 -!- Phantom_Hoover has joined. 17:06:54 -!- Sprocklem has joined. 17:08:26 -!- Koen_ has joined. 17:11:57 -!- Tawo has joined. 17:12:38 -!- Tawo has left. 17:22:05 -!- Phantom_Hoover has quit (Ping timeout: 246 seconds). 17:24:35 -!- Sprocklem has quit (Ping timeout: 245 seconds). 17:33:40 -!- ^v has joined. 17:33:52 -!- oerjan has joined. 17:36:50 -!- Phantom_Hoover has joined. 17:37:05 -!- asie has quit (Quit: My MacBook Pro has gone to sleep. ZZZzzz...). 17:37:24 -!- S1 has quit (Quit: ChatZilla 0.9.90.1 [Firefox 24.0/20130910160258]). 17:44:05 -!- zzo38 has joined. 17:44:15 -!- yorick has quit (Remote host closed the connection). 17:49:36 -!- conehead has quit (Quit: Computer has gone to sleep.). 17:50:08 -!- asie has joined. 17:53:36 mroman: PHP as a language is great, static typing, + sum types you can create types yourself, functional, latest version has algebraic data types amongst others <-- all of this fits haskell except "latest version" (it had them from the start) 17:53:39 -!- nooodl has joined. 17:55:01 -!- asie has quit (Ping timeout: 244 seconds). 17:58:10 -!- augur_ has quit (Remote host closed the connection). 17:58:36 -!- augur has joined. 17:58:48 <`^_^v> this is a cool book cover http://ecx.images-amazon.com/images/I/5121HYFTK0L.jpg 17:59:17 The internet archive / wayback machine is down. <-- THUS IT BEGINS 17:59:27 they had a ire :( 17:59:28 fire* 17:59:47 well that was the next line. 18:00:28 `^_^v: finally something for the programming sheeple! 18:00:29 ​/home/hackbot/hackbot.hg/multibot_cmds/lib/limits: line 5: exec: ^_^v:: not found 18:01:24 hm there's no way to get HackEgo to simply not respond to a command, is there 18:01:31 on purpose 18:03:45 -!- augur has quit (Ping timeout: 272 seconds). 18:06:31 -!- Sprocklem has joined. 18:09:47 -!- oerjan has quit (Quit: leaving). 18:11:09 -!- mrhmouse has quit (Quit: Leaving.). 18:15:19 fungot: can you mute HackEgo? 18:15:19 boily: laf. they are 18:15:38 what's a laf? is it another Nordic Delicacy, like a fternooner? 18:17:06 -!- prooftechnique has joined. 18:17:51 `relcome prooftechnique 18:17:54 ​prooftechnique: Welcome to the international hub for esoteric programming language design and deployment! For more information, check out our wiki: . (For the other kind of esoterica, try #esoteric on irc.dal.net.) 18:18:07 `wercome boily 18:18:09 boily: エソテリックプログラミング言語のディザインとデプロイメントの国際な場所へようこそ!詳しく、ウィキを見て: http://esolangs.org/wiki/Main_Page。(他のエソテリック、irc.dal.netの#esotericへ) 18:18:37 Guys 18:18:40 I be wonderin' 18:18:50 Are there any OS in esoteric languages written around 18:18:56 I deduce from that random act of wercoming that prooftechnique's already been through that ritual. 18:19:00 I remember hearing projects of BF OS 18:19:06 But not sure if any of them came through 18:19:11 boily: Quite so 18:19:44 I switched my handle to my github name 18:19:50 I'm usually NihilistDandy 18:19:59 oooooh! quite the subterfuge! 18:20:11 (and an opportunity to cocoonspire you to the Wisdom Repo!) 18:20:12 * prooftechnique is a master of disguise 18:20:28 Slereah_: I think the closest we have to an esoteric OS is NixOS. 18:21:08 Or TempleOS, or whatever it's called now 18:21:08 prooftechnique: there, you are added. 18:21:19 Hurrah 18:21:24 Also, Wisdom Repo? 18:21:39 I don't know that I'm familiar with that 18:21:51 cf. the /topic of this chännel ↑ 18:21:54 Oh, I see 18:22:25 -!- Ghoul_ has quit (Remote host closed the connection). 18:22:32 I think I liked it more when it was called LoseThos. 18:23:00 (Also isn't PSOX a bit like an operating system?) 18:23:18 `? 18:23:20 ​? ¯\(°_o)/¯ 18:23:33 Already my wisdom increases 18:23:37 prooftechnique: I think now is a good moment to ask you the The Question: what are your approximate coördinates and body weigh? 18:23:49 >coördinates 18:23:57 This isn't the 20's Daddy-o 18:24:14 not yet. 18:25:32 I'll have to send a pull request for this alias :D 18:25:47 Also, let me look up coördinates 18:25:50 -!- realz has quit (Ping timeout: 245 seconds). 18:25:53 you have commit access. commit your heart away! 18:28:22 10 whole megabytes of wisdom 18:28:30 -!- upgrayeddd has quit (Remote host closed the connection). 18:28:30 -!- ggherdov has quit (Remote host closed the connection). 18:28:31 I would expect nothing less from #esoteric 18:29:48 there are some wisdom entries that I didn't get to format yet, such as “wisdom/c” and suchlike. 18:36:59 -!- Sprocklem has quit (Ping timeout: 246 seconds). 18:39:28 -!- realz has joined. 18:39:29 -!- realz has quit (Changing host). 18:39:29 -!- realz has joined. 18:40:47 When did I say "Benchmarks are only a good measure of surprise"? I like that, and I'm thrilled that I said it :D 18:41:06 <^v> does a random name for a language generator exist? xD 18:41:29 ^v, that's what spambots are for 18:41:40 cf. Real Fast Nora's Hair Salon 3: Shear Disaster Download 18:41:59 <^v> no, not random word generation 18:42:04 <^v> :P 18:44:33 ^v: For generating random names for D&D characters I have used an algorithm I read about somewhere and programmed in my TI-92 calculator, but I don't know if that works for your purpose. 18:44:54 I don't know what exactly you want. 18:44:59 quintopia: hi! 18:45:23 Maybe FurryScript can be made to do it somehow, though. 18:45:50 <^v> im just going to generate a large amount of random letters and pick the best looking one 18:46:13 -!- augur has joined. 18:46:41 ^v: OK, how do you want to do that? Pick letters from a Scrabble game? 18:47:02 God, I need to get my laptop working by Friday 18:47:04 ^v: pwgen -c 12? 18:48:21 -!- upgrayeddd has joined. 18:49:18 Add some more `? files for other esolangs and other various things too 18:49:32 `? TwoDucks 18:49:33 TwoDucks programming language was invented in 2023. 18:50:01 `? Real Fast Nora's Hair Salon 3: Shear Disaster Download 18:50:02 Real Fast Nora's Hair Salon 3: Shear Disaster Download? ¯\(°_o)/¯ 18:50:23 huh? how did I manage to miss TwoDucks? 18:50:38 <^v> zzo38, its trivial in lua 18:50:38 boily: I added it just a few minutes ago. 18:50:54 ^v: Ah, then use that. 18:51:07 `run echo "Real Fast Nora's Hair Salon 3: Shear Disaster Download is the most readable functional programming language out there." > wisdom/Real\ Fast\ Nora\'s\ Hair\ Salon\ 3\:\ Shear\ Disaster\ Download 18:51:11 No output. 18:51:21 `? Real Fast Nora's Hair Salon 3: Shear Disaster Download 18:51:23 Real Fast Nora's Hair Salon 3: Shear Disaster Download? ¯\(°_o)/¯ 18:51:26 (Although I still prefer FurryScript for random text generation) 18:51:27 `? Real Fast Nora's Hair Salon 3\: Shear Disaster Download 18:51:29 Real Fast Nora's Hair Salon 3\: Shear Disaster Download? ¯\(°_o)/¯ 18:51:33 I messed up 18:52:30 Wow, this is the closest I've ever lived to London 18:53:03 `run echo "Real Fast Nora's Hair Salon 3: Shear Disaster Download is the most readable functional programming language out there." > "wisdom/Real Fast Nora's Hair Salon 3: Shear Disaster Download" 18:53:05 No output. 18:53:12 `? Real Fast Nora's Hair Salon 3\: Shear Disaster Download 18:53:13 Real Fast Nora's Hair Salon 3\: Shear Disaster Download? ¯\(°_o)/¯ 18:53:17 `? Real Fast Nora's Hair Salon 3: Shear Disaster Download 18:53:19 Real Fast Nora's Hair Salon 3: Shear Disaster Download? ¯\(°_o)/¯ 18:54:00 Esolang wiki even has something about Perl. 19:00:05 -!- Ghoul_ has joined. 19:01:06 welcome to esolang wiki. you can do anything on esolang wiki. anything at all. the only limit is yourself. welcome... to esolang wiki! 19:01:38 -!- tswett has joined. 19:01:53 Hey guys. 19:02:09 Which people are not put on wisdom/ yet? 19:02:11 -!- Phantom_Hoover has quit (Ping timeout: 244 seconds). 19:02:19 I dunno. Am I on wisdom/? 19:02:30 `? tswett 19:02:32 tswett is livin' it up with the penguins 19:02:41 Yup, I guess I am. 19:02:55 Right, right, I live in Antarctica. I forgot about that. 19:03:49 `? NihilistDandy 19:03:51 NihilistDandy? ¯\(°_o)/¯ 19:03:57 `? prooftechnique 19:03:59 prooftechnique? ¯\(°_o)/¯ 19:04:44 There is a file for LaTeX but not for TeX and Plain TeX. 19:05:08 I have a function that translates from the Haskell type "IO a" to the Hylisk type "World -> (Foreign a * World)". Now I'm writing a function that does the reverse. 19:05:56 As far as I've found, there isn't an isomorphism from Hylisk's type system to part of Haskell's, but there is a homomorphism, which is really all that matters. 19:06:11 -!- Bike has quit (Ping timeout: 272 seconds). 19:06:16 -!- shikhin has quit (Read error: Operation timed out). 19:06:21 Which is to say, if you convert a Hylisk type "A" to a Haskell type "B", then the type "B" will contain stuff that the type "A" doesn't. 19:06:51 But that doesn't really matter, because any value of type "B" can be used as we expect to be able to use a value of type "A". 19:07:30 So yeah. When my functions are composed together, the result ought to be the identity. 19:07:46 -!- Bike has joined. 19:09:45 It's ultimately a matter of converting something of the Haskell type "IO t" to something of the Haskell type "forall e. (IO e -> e, (t, IO e -> e) -> e) -> e". Obviously. 19:10:26 Hylisk? is that Haskell with Lisp syntax for the CPython VM? 19:10:37 kmc: astonishingly, no. 19:10:43 It's Haskell with a linear type system. 19:11:15 cool 19:11:19 I'm all about substructural types now 19:11:31 tswett: I don't know how such a type is supposed to work. 19:11:33 I was wondering if relevance logic has any applications in programming 19:11:38 that's so mainstream, i'm into structsubural types 19:11:45 zzo38: I barely know myself. 19:12:01 Bike: we should invent a language with subliminal types 19:12:36 kmc: What does subliminal types means? 19:12:48 i don't know, that's why we need to invent it 19:12:54 Okay, lemme see. So I'm importIO. I have an "IO t", an "IO e -> e" (but don't ask me what an "e" is), and a "(t, IO e -> e) -> e". I have to use all this to make an "e", in the obvious way. 19:13:06 OK. Perhaps make it in a list of ideas 19:13:27 This task might be impossible. Hopefully it is possible, but it'll be pretty inconvenient if it turns out to be impossible. 19:13:50 maybe it's a system where types are inferred but can't be written down and instead of the compiler giving specific type errors it just induces a vague feeling of unease 19:14:33 Java has superliminal types 19:14:45 HEY YOU! JOIN THE NAVY! 19:15:15 ABSTRACTNAVYRECRUITFACTORYFACTORY 19:16:10 -!- ggherdov has joined. 19:16:29 Let's see. If I apply liftM to the third thing there, I get "IO (t, IO e -> e) -> IO e". So I can just take my "IO t" and my "IO e -> e" and combine them to make "IO (t, IO e -> e)", and combine this with the liftM thing to get an "IO e", and then I can use the "IO e -> e" again to produce an "e". 19:16:35 The question is, does this make sense? 19:17:43 tswett: I don't know. 19:19:02 -!- shikhin has joined. 19:21:44 So I'm importIO. What am I supposed to do? I'm given a world, and I have to produce a bare value along with a new world. But a world is really just an "IO e -> e", and I'm supposed to tie actions into it by composing them with it on the right. I think. 19:23:42 This sounds backwards. 19:25:06 According to my notes, the "presumed way" to do things is to take this "IO t", compose it with the "IO e -> e", and drop the result into the function "(t, IO e -> e) -> e". 19:25:38 Of course, you can't combine "IO t" and "IO e -> e" together to get "(t, IO e -> e)". 19:27:27 There's a gamejam this weekend here and I'm entering 19:29:02 lol 19:29:06 -!- MindlessDrone has quit (Quit: MindlessDrone). 19:29:10 er whoops I was *way* scrolled back 19:29:17 just pretend i was lolling at the most recent amusing thing 19:29:38 * kmc was reading Taneb's speech recognition adventure 19:31:03 I think it's exactly the same software as last time 19:31:32 kmc, do you have any gamejam-entering advice? 19:31:35 no 19:32:04 Woohoo, a type error I don't understand because I don't understand the code I just wrote. 19:32:38 tswett: who does that compiler think he is?!? 19:33:14 Apparently he thinks he's someone qualified to try to understand my code. 19:33:44 -!- Koen_ has quit (Quit: Koen_). 19:39:44 -!- Sprocklem has joined. 19:40:13 -!- conehead has joined. 19:42:25 -!- prooftechnique has quit. 19:51:19 So, dang, now it works. 19:51:44 Now I'm afraid that something else will go wrong somewhere down the line. 19:54:53 Maybe IO actions will be performed in the wrong order, or the wrong number of times... 19:56:43 -!- Slereah has joined. 19:57:24 hm 19:57:39 does a C compiler cache a result in a register even if there's a pointer to that variable? 19:57:58 Why do you ask? 19:58:20 e.g. int i; while(i < N) { /* do stuff */ i++;} 19:58:21 mroman: I expect it might only if it can prove that it won't cause it to go wrong, probably 19:58:43 there you could keep i in a register and not write it back to memory after each increment 19:59:03 Yeah, you could. 19:59:05 int i; foo(&i); while(i < N) { /* do stuff */ i++; } 19:59:10 on the other hand, is a different story 19:59:20 And you ask because i might be simultaneously read by another thread or something? 19:59:41 well 19:59:54 it could be, that the order in which stuff happens is different for an observing thread 19:59:57 i.e 20:00:52 int a,b; foo(&a, &b); while(a < N) { i++; b = 5; } return i 20:00:57 oh 20:01:02 that should be an a there 20:01:06 since the compiler caches a 20:01:29 an obverver might see b = 5 before i changes 20:01:45 or a 20:01:47 :) 20:02:04 -!- ais523 has joined. 20:02:22 so esentially 20:02:38 i might actually never change 20:02:48 because you can keep it cached in a register the whole time 20:03:03 I suppose. 20:03:14 as return i wouldn't even need a writeback to memory 20:03:51 Are you actually doing something that depends on what C compilers do here? 20:04:18 I assume the standard says, that concurrent modificiation is undefined behaviour 20:04:23 it should at least say that 20:04:37 or concurrent reads in this case 20:04:56 I would hope that it says unspecified at worst. 20:05:22 esentially a compiler should perform a writeback after a pointer to that variable has been requested 20:05:28 well 20:05:35 not sure there 20:05:45 probably depends on what foo does 20:05:45 -!- Bike has quit (Ping timeout: 244 seconds). 20:05:53 but let's assume the compiler is dumb and has no idea what foo does 20:06:24 The question still on my mind is whether or not you're actually doing something that depends on what happens here. 20:06:50 int i = 0; while(..) { i++; /* i cached inside the loop */ }; /* writeback i due to &i */ foo(&i;) 20:06:59 tswett: I'm writing a compiler :) 20:07:06 Ah. 20:07:23 you can'r put a semicolon inside parens like that 20:07:25 *can't 20:07:37 the question is 20:07:47 If my compiler detects, that a pointer to a variable is held 20:07:56 is he forbidden to cache it later? 20:08:11 or can I he just say: Screw you, that's unspecified behaviour 20:08:16 *I/he 20:08:26 My guess is no, he can do that, but I'd suggest looking at the standard. 20:08:49 because after foo nothing could actually change i 20:08:50 brb, restarting my window manager 20:08:56 -!- ais523 has quit. 20:09:05 unless foo started a thread or something that is now doing cstuff with i behind my back 20:09:34 -!- mtve has quit (Ping timeout: 240 seconds). 20:09:34 -!- Slereah_ has quit (Remote host closed the connection). 20:09:35 -!- shikhin has quit (Ping timeout: 240 seconds). 20:10:09 even if I would writeback to memory every time I incremented i 20:10:10 it would not be safe for that thread to change i 20:10:10 the question still remains: What about reads? 20:10:30 concurrent writes are undefined anyway 20:10:57 but must that thread be able of observing a change in i? 20:11:45 tswett: I'm just using C as an example. 20:11:45 My source language is not actually c 20:12:00 The answer to your question depends on what the source language is. 20:12:12 seems the solution is to instantiate a different thread for every value of i. that way, each thread only sees a single value, and doesn't have to worry about changes. 20:12:20 -!- ais523 has joined. 20:13:05 ais523: what's your window manager? 20:13:11 -!- shikhin has joined. 20:13:13 boily: Unity 20:13:52 tswett: the question is not really "what C says" but 20:13:55 what makes more sense 20:14:11 I'm voting for: It's not well defined behaviour 20:14:17 and that thread may never see a change at all. 20:14:38 after all, that thread might not even be scheduled before the loop completes 20:14:41 but 20:14:45 now comes to tricky trick 20:15:24 http://codepad.org/jV9wdikK 20:15:34 ^- what if the loop only terminates, if the thread detected a change 20:16:25 -!- Bike has joined. 20:16:38 I'd say it's acceptable (but not desirable) for the main thread to loop forever, never yielding to the child thread. 20:17:45 Gotta go. Adiós. 20:17:53 -!- tswett has quit (Quit: Page closed). 20:22:30 -!- asie has joined. 20:22:45 -!- asie has quit (Excess Flood). 20:23:09 -!- asie has joined. 20:31:15 -!- ^v has quit (Quit: http://i.imgur.com/MHuW96t.gif). 20:31:55 -!- J_M has joined. 20:32:43 `relcome J_M 20:32:45 ​J_M: Welcome to the international hub for esoteric programming language design and deployment! For more information, check out our wiki: . (For the other kind of esoterica, try #esoteric on irc.dal.net.) 20:34:38 -!- J_M has left. 20:38:11 another Venezuelian scared away... 20:44:20 -!- shikhin_ has joined. 20:45:20 well. apparentely using signals in C is undefined. 20:45:35 and async callbacks 20:45:54 that's why real programmers only use ada. 20:46:18 i.e 20:46:25 while(dontstop); 20:46:33 -!- shikhin has quit (Ping timeout: 244 seconds). 20:46:38 int sigint_handler() { dontstop = 0; } 20:46:55 the compiler can reason that, since you never call sigint_handler yourself 20:46:56 dontstop believin 20:47:02 that dontstop is never changed in your code 20:47:14 * boily strikes Bike with a hardcopy of the Ravenscar Profile 20:47:20 and may replace while(dontstop) with while(1); 20:47:21 mroman: is that so even if it's declared volatile? 20:47:21 Isn't that what "volatile" is for 20:47:50 if dontstop is a volatile sig_atomic_t that might be well-defined in C+POSIX (C itself doesn't say anything about signals, obviously) 20:47:50 hm. yeah 20:47:54 signals are ♫ the worst ♫ though 20:47:59 “volatile” tells the compiler “don't you dare optimising my variable away, you crapshoot”. 20:48:20 i didn't know about sig_atomic_t, thanks olsner 20:48:25 tholsner 20:48:42 "Until C++11, which introduced std::atomic and std::atomic_signal_fence, about the only thing a strictly conforming program could do in a signal handler was to assign a value to a volatile static std::sig_atomic_t variable and promptly return." 20:48:55 fantastic 20:48:56 is there any way in plain C to use volatile except for setjmp/longjmp? 20:49:03 -!- Sprocklem has quit (Ping timeout: 265 seconds). 20:49:52 i thought it was originally added for mov-triggered architecture sorts of things 20:50:09 -!- shikhin_ has quit (Ping timeout: 244 seconds). 20:50:11 memory mapped hardware 20:50:30 yeah, but C itself doesn't really have memory mapped IO (nor threads), does it? 20:50:31 dunno if that's "plain C" 20:50:47 https://mitpress.mit.edu/covers/9780262019538.jpg btw my field has better book covers than yours 20:50:49 olsner: GPIO on microcontrollers. it's essential to declare that stuff volatile. 20:51:40 volatile int* gpio_thingy = [what goes here that's defined behavior by C?] 20:51:45 -!- yorick has joined. 20:53:19 oh well, I suppose it's still pretty useful to have C-defined behavior when talking to those things, even if all the pieces don't necessarily come from C 20:54:05 fungot: are you defined? 20:54:06 boily: hen. it is but so so, now fnord 20:56:46 boily: fungot is fnord behavior 20:56:47 olsner: second lord. it is too long; which makes it fiue and twenty yeares, and then why should we, in the smoake of warre: and formerly according to our appointment, when we were at work: my old master the iew to sup to night with a harlotry: and thither will i bring thee valentine 21:00:53 fungot: FNORD EAX, 0x2A 21:00:54 boily: fabian. is't so, indeed? we men may say more, than tigers of hyrcania. see, by ten mile. for fnord being dead, i tell thee, iacke cade the fnord means to dress the commonwealth, as which of you saw eglamoure of late? ophe. my honor'd lord 21:01:11 ^style irc 21:01:11 Selected style: irc (IRC logs of freenode/#esoteric, freenode/#scheme and ircnet/#douglasadams) 21:02:02 fungot: rep fnords 21:02:02 olsner: ( do we have? the translations are quite good. how dies sisc compare to plt?' 21:02:21 -!- asie has quit (Quit: My MacBook Pro has gone to sleep. ZZZzzz...). 21:05:13 Have you read your SICP today? 21:06:17 oh no. no no no no no no no. 21:06:24 * boily runs in fear far away from Slereah 21:07:12 I'm searching for scans of a Polish computer magazine called "Enter". Has anyone ever heard of it? 21:07:31 Not having much luck, probably due to the name... 21:07:44 is that name translated? 21:07:54 boily seems to be deathly afraid of snakes 21:08:08 snakes? 21:08:13 SNAKES 21:08:28 http://fuuka.warosu.org/data/lit/img/0037/37/1368047172925.gif 21:08:30 Snaaaakes 21:09:23 http://1-media-cdn.foolz.us/ffuuka/board/jp/image/1335/81/1335810578462.jpg 21:09:28 SNAAAAKE?!? 21:09:47 http://groups.csail.mit.edu/mac/classes/6.001/abelson-sussman-lectures/wizard.jpg 21:09:52 Programming could use more wizards 21:10:53 scheme code with lots of defines is the worst 21:11:08 Or is it 21:11:11 THE BEST 21:11:16 Bike: it's the original name. I've found a few copies on eBay, but that's about all. 21:11:23 weird. 21:12:13 "Scheme allows you to do crazy things: (define + -) (define define 3)" 21:12:14 heh 21:12:47 john_metcalf: well my library doesn't happen, but searching "Enter" does turn up some Lost episodes. 21:13:20 Disc 3 (Episodes 9-12). Stranger in a strange land ; Tricia Tanaka is dead ; Enter 77 ; Par avion -- 21:13:55 http://www.youtube.com/watch?v=rdj6deraQ6k 21:13:56 Oh god 21:14:20 john_metcalf: they have a website at enter.pl, but I can't read Polish. 21:14:34 I know of the Finnish computer magazine called "Enter", but that probably won't help. 21:14:43 Slereah: and, uh, why snakes? 21:15:19 -!- Oj742 has joined. 21:15:20 I don't have a fucking clue 21:15:26 Boily: found that and translated some with Google translate. It doesn't look like they have an online archive. 21:15:27 It's an old /prog/ meme 21:15:30 and WHAT THE FUNGOT IS THAT VIDEO? 21:15:31 Don't know where it came from 21:15:36 It is the SICP snake 21:15:45 Enquiring about your daily reading of SICP 21:15:59 I vaguely recall having stored a copy about that somewhere... 21:16:15 That video is what Scheme is all about 21:17:42 -!- tswett has joined. 21:18:00 * boily sings “一二三 一二三 one two three one two three いち に さん!♪” 21:18:47 -!- Sprocklem has joined. 21:18:48 it was some guy mentioning SICP and then someone else said "is that just your way of saying I'VE READ SICP" and then "I'VE READ SICP" became a /prog/ meme 21:19:09 But why the snake! 21:20:08 simultaneously someone else made a postscript file of a snake and posted it in a thread called "the /prog/snake" i think? and someone else put two and two together 21:20:31 ddeep 21:20:31 is /prog/ that 4chan thing 21:20:32 heh 21:20:35 Yes 21:20:36 what the snake says! SICP-SICP-SICP-SICP-SICP-SICP-SICP! 21:20:42 It's one of the TOP SECRET boards 21:20:44 (Textboard) 21:20:57 An antagonistic snake would make more sense. (See: Python replacing Scheme in the MIT course.) 21:21:19 I'm afraid that now, Scheme is all snake 21:21:40 Among the programming animals, such as the Ocaml camel or... 21:21:43 The B bee? 21:21:51 Does the B language still exist 21:22:15 It turned out to have ceased to exist long before anyone realized it no longer existed. 21:22:26 is B the anti-Feather? 21:22:27 fizzie: the antagonist is, in the /prog/ canon, "the Abelson": http://www.youtube.com/watch?v=rdj6deraQ6k 21:22:43 https://mitpress.mit.edu/covers/9780262518420.jpg my programming language 21:22:47 book. thing 21:23:15 ah yes. the snake is in this too. i should just link http://www.youtube.com/watch?v=rdj6deraQ6k when people ask me about /prog/ always 21:23:32 Well, gee, now what. I guess writing an "apply" function might end up being useful eventually. 21:23:32 the factorial of seven is also in this... amazing 21:23:38 That's kind of a useful function. 21:23:41 it's cool how the sinuses (or whatever) look like a mustache 21:23:47 nooodl : Same link! 21:23:54 which I already gave before, anyway! 21:26:10 oh. excellent 21:26:50 http://www.zazzle.com/my_other_car_is_a_cdr_bumper_stickers-128776132386843273 21:26:57 Four bucks for a sticker? 21:27:01 What madness is this! 21:27:16 -!- boily has quit (Quit: un un deux trois cinq poulet). 21:27:21 -!- metasepia has quit (Remote host closed the connection). 21:31:03 http://i.imgur.com/gRbwf.png apparently jwz is on 4chan now, taking screens 21:31:42 haha burn 21:32:00 so where is this /prog/? 21:32:12 hell 21:32:41 *that* /prog/ is gone, but the current /prog/, which is (even more) complete shit, is http://dis.4chan.org/prog/ 21:33:05 i'd like to point out that "dis" is indeed part of hell, in dante 21:33:24 The best board is actually http://dis.4chan.org/vip/ 21:37:28 -!- shikhin has joined. 21:40:24 -!- carado has quit (Ping timeout: 252 seconds). 21:42:36 -!- Slereah has quit (Remote host closed the connection). 21:42:53 -!- Slereah has joined. 21:43:34 -!- shikhin_ has joined. 21:45:58 -!- shikhin has quit (Ping timeout: 244 seconds). 21:47:26 -!- Sprocklem has quit (Ping timeout: 268 seconds). 21:47:35 -!- Oj742 has quit (Ping timeout: 260 seconds). 21:47:50 -!- shikhin__ has joined. 21:50:44 -!- mtve has joined. 21:51:23 -!- shikhin_ has quit (Ping timeout: 272 seconds). 21:58:19 How to I append to a @ list in Perl? 21:58:50 push @foo, 'x'; is popular. 21:59:25 OK 21:59:41 I hope I did the rest of the program correctly. 21:59:51 I am trying to modify a Perl program. 22:00:09 Technically, @foo = (@foo, 'x') would also work, but I think 'push' is the usual thing for appending. 22:05:13 -!- zzo38 has quit (Remote host closed the connection). 22:05:48 fizzie: or $foo[scalar @foo] = 'x'; 22:05:55 push is probably clearest, though 22:06:01 and I think the compiler optimizes it into what I just wrote 22:08:09 https://twitter.com/History_Pics/status/397393751527919616 golf used to be more exciting i guess 22:08:40 ais523: I had $foo[@foo] = 'x' and $foo[$#foo+1] = 'x' all written up, but decided not to. 22:08:56 (I don't think that needs a "scalar".) 22:09:07 right, @foo[@foo] = 'x' would though 22:09:42 So many ways. 22:10:23 -!- Sprocklem has joined. 22:10:49 splice @foo, @foo, 0, 'x'; too. 22:13:59 splice @foo, -1, 1, $foo[-1], 'x'; 22:20:26 -!- Sprocklem has quit (Ping timeout: 245 seconds). 22:21:00 -!- prooftechnique has joined. 22:27:49 -!- shikhin__ has quit (Ping timeout: 248 seconds). 22:28:27 Aaaah once again I am painfully aware of the leftist positive reinforcement bubble I live in 22:29:45 CORRECT, CITIZEN 22:30:26 Taneb: ? 22:31:05 ais523, I was reading an article I saw on reddit, basically saying that the tories sucked, slowly nodding in agreement 22:31:11 -!- tswett has set topic: Pregnant memory client sialic Guillen Puede yen Ten del Est | Koirammekokaan ei lennä? :( | https://dl.dropboxusercontent.com/u/2023808/wisdom.pdf | logs: http://codu.org/logs/_esoteric/ or http://tunes.org/~nef/logs/esoteric/. 22:31:16 Then I realised there was almost nothing but tory-bashing 22:31:21 Little actual content 22:31:31 -!- tswett has quit (Quit: Page closed). 22:31:38 Just factoids for me to memorize and recite at those who disagree 22:31:39 Taneb: if it helps, I normally vote Conservative (although I didn't last election) 22:31:40 reddit is great for creating echo chambers like that 22:31:42 don't read redditn 22:31:46 although I'm well aware that I'm in the minority among my age group 22:31:55 i used to troll /r/atheism but that got old too 22:32:01 My family all vote conservative, although in general I don't 22:32:16 kmc, I'm not sure if there are any non-trolls in /r/atheism 22:32:48 well they mostly troll in the other direction, then? 22:32:58 Fair enough 22:33:02 I said unpopular things that quickly got downvoted 22:33:44 such as that if you want to blame the holocaust on hitler being a christian then you can also blame atheism for stalin 22:33:57 tory-bashing sounded like this was just going to be a big awful toribash pun 22:34:56 My childhood spent in a tory family with a lot of labour friends has left me with few to vote for 22:35:05 kmc: DID YOU KNOW THAT KING DAVID WAS JEWISH? 22:35:13 Taneb: are you currently able to take the Lib Dems seriously? 22:35:29 ais523, no, but I can't take any of the other big parties seriously either 22:35:37 So I end up voting for lib dems anyway 22:35:41 what about the small parties? 22:35:59 Yeah, like that white supremacist one. I imagine they're a fun bunch 22:36:01 They so far haven't ran in elections where I've voted for 22:36:15 -!- oerjan has joined. 22:36:38 which constituency is hexham in anyway? 22:36:53 I'm used to Birmingham which is lots of constituencies 22:36:58 but Hexham's probably just a fraction of one 22:37:12 It's in Hexham 22:37:26 oh, it's a constituency of its own? 22:37:28 Which is by area I think one of the largest in England 22:37:33 ah right 22:38:41 Yeah, both times I've voted (once in the Police Commissioners election, once in a county council election), there have been precisely four candidates 22:39:01 One labour, one tory, one lib dem, and one ukip 22:39:12 -!- augur has quit (Remote host closed the connection). 22:39:49 -!- augur has joined. 22:40:59 Both times, I've voted lib dem, and both times, the lib dems have outright lost 22:41:03 ais523: you removed the check for number of edits? btw i tried to test run it, but nothing matched... oh wait we've already deleted those :D 22:41:09 oerjan: yeah 22:41:19 I thought that the edit count check might be causing the rule to not match 22:41:30 and then match when I test ran it because the users had a different number of edits then 22:41:33 but apparently not 22:41:41 -!- KingOfKarlsruhe has quit (Quit: ChatZilla 0.9.90.1 [Firefox 25.0/20131025151332]). 22:44:47 -!- augur has quit (Ping timeout: 268 seconds). 22:45:12 https://twitter.com/genometweet useful service 22:48:16 -!- tertu has joined. 22:49:37 ais523: ok now it blocks _me_ from starting my user page with a header so it must be doing _something_. 22:49:48 oerjan: hmm 22:49:51 try with the new section button 22:49:54 that's what the bots are using 22:50:23 ooh... 22:50:36 the button doesn't appear on user pages 22:50:45 so you have to get that via link editing 22:51:47 I hope the people writing these spambots at least have the decency to write them in an esolang 22:52:03 prooftechnique: the people writing them aren't the people running them 22:52:17 ais523: oooh i think i know why it doesn't work... 22:52:20 oerjan: go on 22:52:50 when using add section, there are _no_ literal ==s added by the user, it's in a different form field... 22:53:05 hmm, could work 22:53:56 hm this means something disturbing, let's check... 22:55:22 hm no, for some reason editing a section does not trigger the filter. 22:55:45 even though the edit area does start with == then 22:55:57 weird 22:56:49 http://www.youtube.com/watch?v=HiN6Ag5-DrU 22:57:48 ais523: oh i know i forgot an important test. trying again... 22:59:52 wait no i didn't, sheesh. oh well trying anyhow. 23:00:51 argh 23:01:09 if the new section button gets round abusefilter 23:01:14 then that may be why the spambots are using it 23:01:40 oh no. 23:01:53 it doesn't. i just managed to trigger it. 23:02:04 `seen Phantom_Hoover 23:02:09 2013-11-04 23:35:04: imho keep fnord forever 23:02:43 ais523: ok it's _not_ that, the filter triggered this time. 23:03:04 unless there is some weirdness... 23:03:38 well there's clearly weirdness 23:03:41 fungot_hoover 23:03:41 shachaf: i think it's pretty clear, i think it's bbls that's confused. perl is a lisp 23:03:43 we're just not sure what sort of weirdness yet 23:03:55 ok trying the really bad stuff 23:03:57 "perl is a lisp" is gold :) 23:06:04 ais523: darn creating my page anew did _not_ trigger the filter. 23:06:35 but we know that in general, it can trigger on page creations 23:06:39 because 1/2/3 do that all the time 23:06:59 well if those pages didn't crash when we tried to load them... 23:07:02 yeah 23:07:13 maybe 4 doesn't work properly /because/ it doesn't crash on load 23:07:20 also you may be able to load them indirectly 23:07:24 via the batch tester 23:07:33 it has a button to copy the filter condition from a filter 23:07:44 so you could get at their conditions, even if you couldn't edit them 23:10:34 hm right lessee 23:11:28 -!- ^v has joined. 23:16:43 -!- prooftechnique has quit. 23:16:56 what do today 23:18:04 quintopia, which day is that? 23:18:22 I think my today is a different day to oerjan's, for example 23:18:26 -!- prooftechnique has joined. 23:19:09 ais523: nr. 1 just has user_editcount == 0 but i guess you modified that in 4 as a wild guess to why it wasn't working. 23:19:16 oerjan: yes 23:21:49 -!- tertu has quit (Read error: Connection reset by peer). 23:22:05 -!- tertu has joined. 23:22:18 ais523: ok next question, why don't my blocked edits show up in the abuse log (for any of the filters) 23:22:39 oerjan: possibly because you're an admin 23:23:01 goddammit 23:23:29 also, is a 40something error the right result to get on a blocked edit 23:23:46 normally you get a warning, if "Warn" is set 23:24:11 well Warn is only set on nr. 1 afair 23:24:28 yeah, to avoid blocking legitimate users 23:25:16 well i cannot be bothered to make another account just to test things. 23:25:46 I did on Wikipedia, eventually 23:25:51 but yeah MediaWiki's a mess 23:27:51 i have this feeling the world is approaching the bug singularity this year. 23:29:29 IE11 managed to add a bug that makes tab groups dissolve occasionally when you close tabs in them. :( 23:30:07 it did fix one bug that had annoyed me in IE10 though. 23:34:48 elliott: ais523: i'd like to point out that _all_ of the filters, not just 4, stopped registering anything in the abuse log after Nov 5. 23:35:00 while having plenty of hits on that day. 23:35:04 oerjan: yeah but I haven't seen any edits that would have hit 1, 2, or 3 23:35:22 probably because I did a bunch of rangeblocks on that day 23:35:23 well in that case, maybe something is wrong with the _logging_? 23:35:28 oh. maybe so. 23:37:13 -!- augur has joined. 23:51:31 -!- nooodl has quit (Ping timeout: 244 seconds). 2013-11-07: 00:11:07 -!- ais523 has changed nick to ais523\unfoog. 00:17:48 ...it's possible to easily argue for either way in almost all political issues 00:18:10 it's possible to easily argue for either way on any issue. 00:18:11 I don't think I know how to form an unbiased opinion 00:18:28 What would an "unbiased opinion" even be 00:19:06 One that weighs fairly all, or a reasonable sample thereof, parameters, I guess 00:20:17 what's "fairly" 00:20:22 Who knows 00:20:40 But I've made myself sad 00:21:20 uh 00:21:22 Also I forgot to eat my bread 00:21:26 have you tried 00:21:27 And now it's gone moldy 00:21:31 evidentialism? 00:21:34 i recommend it 00:21:50 Excuse me while I dump an entire loaf in the bin 00:22:06 losing an entire load of bread really is a sad situation. 00:22:58 Taneb: I ended up refusing to eat bread for months because of that 00:23:05 nowadays I schedule when I will need a loaf 00:23:10 and by a small one immediately beforehand 00:23:40 * oerjan just keeps it in the fridge and/or freezer, barbaric he is. 00:23:48 I keep my bread frozen until I'm ready to breadbinge 00:24:05 i can't... did i just read that... 00:24:24 i buy bread that's CHOCK FULL OF PRESERVATIVES 00:24:24 Bike: shocking, isn't it. 00:24:33 it lasts for WEEKS 00:24:36 not you, ais 00:25:01 Bike: some people are master schedulers. 00:26:09 I usually find that I need bread to finish the bread spreads, and then I need bread spreads to finish the bread 00:26:38 and some people like me buy new once he's opened the last package. and sometimes before. 00:27:02 olsner: so if they ever match up you'll starve to death? 00:27:15 I might fall back to eating other things 00:27:39 I don't remember finding myself in that situation though 00:27:53 -!- Sprocklem has joined. 00:28:06 -!- Koen_ has joined. 00:28:25 Well, shock and malnourishment will do that to you 00:28:30 actually i used to keep bread in a drawer, but then i got insects in the drawer, and i have used the fridge since. 00:31:36 someone give me a good name for an esolang 00:31:47 specifically for my MWI BF deriv 00:31:54 what's MWI 00:32:09 MoWglI 00:34:00 Given a physical object, how would you measure its surface area? 00:34:34 Also I realised my milk was past its due date 00:34:34 Bike: it depends on resolution, fractals you know 00:34:42 if it looks enough like a sphere I might look up the formula for diameter -> surface area 00:34:57 ais523\unfoog, the problem is I can EASILY eat the bread fast enough, I just don't 00:35:09 physical object, oerjan. 00:35:23 Bike: physical objects are surprisingly fractal. 00:35:53 http://en.wikipedia.org/wiki/How_Long_Is_the_Coast_of_Britain%3F_Statistical_Self-Similarity_and_Fractional_Dimension 00:36:19 http://en.wikipedia.org/wiki/Coastline_paradox 00:36:35 i'm just weirded out since i realized that measuring volume is easy, but then I see something like "lungs have an internal surface area of 70 m²" and just swallow it without thinking. 00:36:44 quintopia: i'm assuming you went with MoWglI. 00:37:12 -!- augur has quit (Remote host closed the connection). 00:37:30 (it looks like they estimate it by measuring the area of (roughly spherical) alveoli and then guessing how many of those there are) 00:37:38 -!- augur has joined. 00:38:29 -!- augur has quit (Read error: Connection reset by peer). 00:38:32 -!- augur_ has joined. 00:38:34 and i'm sure if you look closely those alveoli aren't smooth either. 00:38:42 mmhm 00:38:49 and once you get down to atoms, does area even make sense. 00:39:00 Maybe in that specific case you could guess it backwards by seeing how much oxygen they can take in... 00:39:13 -!- augur has joined. 00:39:14 -!- augur_ has quit (Read error: Connection reset by peer). 00:39:18 -!- augur has quit (Remote host closed the connection). 00:39:26 Except how do you measure how much one unit surface area can do. 00:39:44 -!- augur has joined. 00:40:09 so basically it's assumptions all the way down. 00:40:23 until you hit the turtles, at least. 00:40:42 But how big are the turtles? 00:40:51 -!- augur_ has joined. 00:41:08 -!- augur has quit (Read error: Connection reset by peer). 00:42:19 prooftechnique: i think heisenberg uncertainty may be involved. 00:42:53 If there are seagulls on the beach, all of modern mathematics will come crashing down 00:42:56 * prooftechnique weeps 00:43:25 O KAY 00:43:30 -!- yorick has quit (Remote host closed the connection). 00:43:31 -!- Phantom_Hoover has joined. 00:45:25 -!- Bike has quit (Ping timeout: 248 seconds). 00:47:10 `? c 00:47:12 C is the language of��V�>WIד�.��Segmentation fault 00:52:16 twitter IPO tomorrow 00:52:39 `run ls wisdom/*eal* 00:52:41 wisdom/Real Fast Nora's Hair Salon 3: Shear Disaster Download 00:52:56 -!- nisstyre has joined. 00:53:28 `run mv wisdom/{"Real Fast Nora's Hair Salon 3: Shear Disaster Download","real fast nora's hair salon 3: shear disaster download"} 00:53:31 No output. 00:53:38 `? Real Fast Nora's Hair Salon 3: Shear Disaster Download 00:53:40 Real Fast Nora's Hair Salon 3: Shear Disaster Download is the most readable functional programming language out there. 00:53:50 Taneb: sheesh. 00:54:13 All hail 00:54:29 `run ls -1 wisdom/* | grep '[A-Z]' 00:54:32 wisdom/` \ wisdom/`? \ wisdom/_̰̆̓_̦̻̖͍̟̖̅ͭͭͬ͡_͉̭ͧ͒̐_̯͙̬̬̦̯͂͋͒ͧ͋̋_̴̝̔̉̅ͨ͞ \ wisdom/? \ wisdom/?? \ wisdom/@ \ wisdom/☃ \ wisdom/⌨ \ wisdom/⊥ \ wisdom/🐐 \ wisdom/̸̸̼͚͇̮͕̳̞̤̜̯̪̪̱̣̠̺̹͍̩̝͚͕͓͚̙͓̪̮̟̜̣͙̪̂ͭ̎̏̔ͦ͒ͪ͌̾ͦͨ̚̚͢͢͠ͅ҉̴̢_̿̊ͣ̉ͣͪ͒̓̐͊̏̚̚ 00:54:49 oh right that mess 00:55:00 `run ls -1 wisdom/* | grep '[[:UPPER:]]' 00:55:02 grep: Invalid character class name 00:55:20 `run ls -1 wisdom/* | grep '[[:upper:]]' 00:55:22 wisdom/Ø \ wisdom/wisisis "This isn't an actual wisdom, just a tribute." 00:55:23 so logical 00:55:40 `? Ø 00:55:43 ​ø is not going anywhere. 00:55:52 `cat wisdom/Ø 00:55:54 ​Ø escaped due to a sensitive case bug 00:56:04 ...i guess that stays. 00:56:53 `run cat wisdom/wisi* 00:56:55 No output. 00:58:50 `? substructural typing 00:58:53 Not to be confused with structural subtyping. 00:59:03 `? structural subtyping 00:59:05 Not to be confused with substructural typing. 00:59:08 yep. 00:59:24 haha 00:59:27 true wisdom 01:03:46 `run echo "Something Bike is into. Not to be confused with suburban destruction." >wisdom/"structsubural type" 01:03:50 No output. 01:09:46 elliott, {also ais523\unfoog and oerjan in case he's not listening}, i suggest doing the admin work on the esolangs wiki with an account in the bot group 01:10:06 Phantom_Hoover, how is the fortress going 01:10:09 because these ongoing spam wars are making recent changes useless 01:10:11 Taneb, aaaargh 01:10:11 Phantom_Hoover: I'm not sure that works for blocks and deletions 01:10:18 we can remove /edits/ from recent changes even without a bot-group account 01:10:19 definitely does 01:10:48 wouldn't get rid of the spammers' user creation logs, unfortunately 01:11:53 -!- Bike has joined. 01:13:43 oerjan: i left to unpack my pack. i didn't go with anything. did you have a better idea? 01:14:21 how can i have a better idea when i don't know what mwi means. 01:14:35 most westerly incinerator 01:15:45 ais523\unfoog: hm. ok remind me how we got the bot flag set again. 01:16:02 oerjan: there's a user rights setting interface that only bureaucrats can use 01:16:04 oerjan: hugh everett's quantum mechanics interpretation 01:16:23 i'm guessing elliott's the only bureaucrat 01:16:35 I'm one too, I think 01:16:36 ais523\unfoog is too 01:16:42 oerjan: http://en.wikipedia.org/wiki/Many-worlds_interpretation 01:16:49 what is the point of the initialism 01:17:08 ais523\unfoog: hm i thought i was supposed to have access to do bot edits or do i remember wrong 01:17:22 quintopia: EverFuck 01:17:28 well bot is just a user group 01:17:28 oerjan: that's different 01:17:45 i think "elliott's the only bureaucrat" is a wonderful name for an esolang 01:17:48 you put ?bot=1 or &bot=1 as appropriate at the end of a contributions URL 01:17:49 that keeps your actions from showing up on recent changes 01:18:03 Can I do "foo[1:7] = bar[1:7]" to assign seven bits of bus? 01:18:03 then the rollback button makes both your edits, and the edits you roll back, get flagged as bot 01:18:32 in verilog i guess i should mention. 01:18:41 ais523\unfoog: ok and that won't work with page deletions and/or blocks? 01:18:52 oerjan: no, it only works with rollbacks 01:19:00 ok 01:19:09 my life would be much happier if builds didn't take five minutes, i feel 01:19:12 in Wikipedia, deletions are major enough that hiding them from the log would be a bad idea 01:19:16 and MediaWiki assumes that everyone is Wikipedia 01:19:22 i suppose. 01:19:41 and in wikipedia new users can't create pages iirc 01:20:17 which would be untenable on our wiki 01:20:32 hm 01:20:53 wasn't there an incident when a wikipedia admin deleted some major discussion page and fucked the database 01:21:16 ais523\unfoog: can you help me out here 01:21:40 Bike: in Verilog? I think that's possible 01:21:43 but I'm better at VHDL 01:21:48 oh right, you don't know verilog. 01:21:51 well, fuck everything. 01:21:55 -!- Sgeo has joined. 01:21:58 verilog and vhdl are actually different, right 01:22:01 Phantom_Hoover: it was the old version WP:AFD, I think 01:22:02 Bike: a fresh build of the thing i work on takes 25 minutes 01:22:06 where everything was done on one page 01:22:08 and that's on the fastest computer I have access to 01:22:16 Phantom_Hoover: they're basically feature-identical but use different syntax for everything 01:22:19 kmc: real job though. 01:22:25 something like that. 01:22:47 -!- Taneb has quit (Quit: Leaving). 01:25:02 this is just homework i've been slacking on. makes flashy lights 01:36:15 oerjan: how about "Quantum Fuckicide"? :D 01:36:56 "This Language Does Not Exist In Your Universe" 01:40:40 -!- Phantom__Hoover has joined. 01:40:54 Heh, there's no monotonic surjection from [0,1) to [0,1] 01:41:00 i find this inordinately amusing 01:41:32 strictly monotonic, surely? 01:41:53 -!- Phantom_Hoover has quit (Ping timeout: 246 seconds). 01:42:10 maybe 01:42:17 otherwise f x | x <= 1/2 = 2*x | otherwise = 1 would work. 01:42:33 yeah 01:43:49 i remember when a guy wasted like ten minutes of an analysis lecture by asking if a function had to be strictly increasing, despite the fact that it had already been taken to be injective 01:47:26 now prove there is no continuous bijection from [0,1)^n to [0,1]^n >:) 01:47:49 -!- Sprocklem has quit (Ping timeout: 248 seconds). 01:48:19 hm wait is there 01:49:32 today someone asked me to prove that if a sub-algebra of the set of continuous functions from [0, 1] to R had finite dimension, then it was the set of constant functions 01:50:16 (algebra with addition (f+g)(x) = f(x) + g(x) and multiplication (f*g)(x) = f(x)g(x)) 01:52:43 i tried to stop a build and the entire ide crashed. i hate this program so much. 01:52:54 haha sux 01:53:12 i just removed about 10 makefiles 01:53:18 let's see if it still builds 01:54:58 Koen_: that reminds me of an important theorem which i cannot remember the name for 02:02:15 ah the Stone-Weierstrass theorem 02:02:34 yeah i'd say that's just a tad important 02:03:21 the name clearly rings a bell but IT'S BEEN A LONG TIME soooooo 02:03:54 the one where you can approximate (continuous? i forget) functions with polynomials. 02:04:00 i finally found it when i got the idea to google the ingredients of the theorem instead of finding the right wikipedia subject/mathematician 02:04:39 -!- john_metcalf has quit (Ping timeout: 260 seconds). 02:06:07 -!- impomatic has quit (Ping timeout: 265 seconds). 02:06:55 hm that's not the most obvious too powerful theorem to use for Koen_'s proof 02:07:31 it's not supposed to be too hard, he apparently expected me to give an answer within ten minutes 02:08:02 woah dude 'length' is a monoid homomorphism isn't it 02:08:11 what is the polynomial that approximates the weierstrass function 02:09:09 -!- Phantom__Hoover has quit (Ping timeout: 272 seconds). 02:09:45 Koen_: what i'm thinking of is that a closed subalgebra with unit of C(X) is isomorphic to C(X/function dividing out the points which the algebra doesn't distinguish) 02:10:31 since it's finite dimensional, the X/... must be finite, but X is connected so it must be a single point QED 02:10:58 is C(X) the set of fractional functions? or whatever you call polynom/polynom 02:11:26 it's the continuous functions from X to R, where X is a compact hausdorff space (e.g. [0,1]) 02:11:40 kmc: (sum . map (const 1)) should make that obvious :) 02:12:05 i.e. the algebra you're inside. 02:12:14 or more explicitly, foldMap (\_ -> Sum 1) 02:12:39 elliott: yeah 02:13:28 'sum' is also a monoid homomorphism 02:13:31 hooray 02:13:43 more like monoid gaymorphism 02:13:55 i don't know why i said that. it was dumb. sorry. 02:14:00 oerjan: and "connected" is that property of a set that basically says "if two points 'touch' eachother then they're equal?" 02:14:07 kmc: sum is and map (const 1) is 02:14:24 and homomorphisms of a monoid form a category 02:14:32 Koen_: no. it's the property that says the space is not the union of two disjoint open sets. 02:14:40 kmc: (of course, map f is for any f) 02:14:53 right 02:15:06 it's preserved by continuous surjective functions. 02:15:34 alright 02:16:18 kmc: you should read http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.45.2247&rep=rep1&type=pdf, it's exciting! 02:16:31 then maybe also https://www.fpcomplete.com/user/edwardk/conquering-folds (where I found it from) 02:16:38 is that a direct link to a pdf! 02:17:00 Koen_: what you said could be called "being in the same connected component" 02:17:04 I'm still not sure what the X/ means - is that some sort of set quotient? as in dividing by the Ker of the function or something 02:17:47 oerjan: no, I was refering to a weird thing that almost any set I can imagine verifies but witch some weiiiiiird sets do not 02:17:58 Bike: blame edwardk 02:18:05 in french we call it either "séparé" or "séparable", I never remember which 02:18:10 s/witch/which 02:18:16 Koen_: actually it's just the range of the function, it's just that you can think of a function's range as the quotient of the domain by the equivalence relation of being mapped to the same point. 02:18:32 nice 02:19:22 if the domain is compact hausdorff and the range is hausdorff, then that also transfers the topology. 02:20:06 (i maybe should have mentioned that all the spaces involved here are compact hausdorff) 02:20:15 I also remember I used to know what hausdorff meant. and the more we talk about this the more I think I never should have stopped studying math 02:20:44 math sucks. go into geophysics. 02:25:20 kmc: [a] is the free monoid over a, and Sum . length is the lifting to the monoid category of the morphism Sum . const 1 in the set category. 02:28:31 by that natural transformation of adjoint functors 02:54:25 -!- Oj742 has joined. 02:56:26 -!- prooftechnique has quit. 03:01:10 -!- Sprocklem has joined. 03:26:15 elliott: ais523\unfoog: ok don't kill me :D 03:27:23 -!- v^ has joined. 03:27:50 -!- ^v has quit (Ping timeout: 240 seconds). 03:27:56 ouch my finger 03:31:01 oerjan: that's one way to do it, I guess :) 03:31:27 should keep us safe until they crack the CAPTCHA again 03:31:29 -!- Bike has quit (Ping timeout: 272 seconds). 03:31:58 that was everyone in november + one more because the last one had already been blocked and i needed somewhere to put my SORRY 03:32:07 -!- conehead has quit (Ping timeout: 272 seconds). 03:39:22 -!- Bike has joined. 04:01:00 -!- Oj742 has quit (Quit: irc2go). 04:17:20 -!- Koen_ has quit (Quit: The struct held his beloved integer in his strong, protecting arms, his eyes like sapphire orbs staring into her own. "W-will you... Will you union me?"). 04:22:56 -!- nisstyre has quit (Quit: Leaving). 04:42:10 Uh 04:42:24 I think you blocked an innocent 04:42:24 http://esolangs.org/wiki/Special:Contributions/Wingpad 04:42:31 oerjan: ^ 04:49:52 Sgeo: can you check the others for false positives too? 04:49:58 I unblocked Wingpad 04:50:16 I mostly only noticed that one because of the nongibberish name :/ 04:51:02 I'll consider any with no edits a spammer 04:52:50 Only Wingpad seems to have made changes 04:52:55 good 04:55:29 oops, and i checked a couple others because their names were almost not gibberish too... 04:56:21 perhaps checkuser would come in handy here? 04:56:26 I can make oerjan a 'crat 04:56:31 elliott: I've been checkusering like mad 04:56:36 look at all the rangeblocks I made 04:56:47 however there are lots of random IPs that don't fit a pattern, too 04:58:52 i was basically trying to get them all, since the recent flood began. 04:59:48 " today someone asked me to prove that if a sub-algebra of the set of continuous functions from [0, 1] to R had finite dimension, then it was the set of constant functions" <<< i'd use Vandemonde 05:00:00 If f is one of the functions f(x) != f(y) then [f(x), f(y)] \subset f([0, 1]), so we can choose distinct b_1, ..., b_k \in f([0, 1]) (with preimages f(a_i) = b_i) for any k. The claim now follows because: 1. the vectors (b_1^i, b_2^i ..., b_k^i) for i \in [0,k-1] are linearly independent (http://en.wikipedia.org/wiki/Vandermonde_matrix), 05:00:07 isn't vandemonde a final fantasy villain 05:00:13 2. the map H(f) = (f(a_1), ..., f(a_k)) is linear from your space of interest to R^k, and 3. H(f^i) = (b_1^i, b_2^i ..., b_k^i). 05:00:55 also a girl genius character (who seems to be relatively good) 05:01:27 hm wait his name is vanamonde 05:01:59 i didn't understand your proof 05:03:31 http://stricture-group.com/files/adobe-top100.txt 05:04:10 oklopol: a closed unital subalgebra A of C(X) is naturally isomorphic to C(Y) where Y is X with all the points that are not distinguished by any element of A identified. 05:05:08 the map from X to Y is surjective and continuous, thus Y must be connected since X is. 05:06:04 since C(Y) is finite dimensional Y must have a finite number of points, oh hm this might be slightly circular. 05:06:04 sowhere do you get the "closed", is that automatic from the finite-dimensionality? 05:06:09 yeah 05:06:16 where do you get the "unital"? 05:06:20 oh 05:06:29 does that mean has the constant 1 map? 05:06:29 just add a unit if you don't have one >:) 05:06:32 yes 05:06:38 oh okay. 05:07:12 hm or not circular, it follows from urysohn's lemma. 05:08:12 mind you by that point it may be more complicated than your idea >:) 05:08:25 wait what follows from urysohn's lemma 05:08:46 that an infinite set Y cannot have finite-dimensional C(Y) 05:09:01 oh right. 05:09:03 *c.h. space 05:11:30 do you know what gibbs measures are 05:11:44 not on the spot no :) 05:12:26 i'm supposed to give a talk on how they are the same thing as equilibrium measures 05:12:34 (i haven't checked what the latter are yet) 05:12:41 *tomorrow 05:12:42 which i don't recall either :) 05:12:50 something about pressure 05:13:15 I'm going to have a "fun" day tomorrow 05:13:25 I'm going to have a fun day tomorrow. 05:13:45 and given a function f, finding the measure m such that h(m)+m(f) is maximized, where m(f) is the integral, and h(m) is the entropy 05:13:55 I'm going to have a fun "day" tomorrow. 05:14:09 i'm going to have a" "fun day tomorrow 05:15:45 k gtg 05:16:34 bye 05:20:17 -!- ais523\unfoog has quit (Read error: Operation timed out). 05:41:14 -!- ais523 has joined. 06:50:48 -!- v^ has quit (Quit: http://i.imgur.com/MHuW96t.gif). 07:04:40 -!- asie has joined. 07:07:27 -!- Sprocklem has quit (Ping timeout: 272 seconds). 07:11:12 kmc: is there a way to give someone, say, a sha1 hash and a proof that you have a message that hashes to it 07:11:31 (without revealing the message) 07:16:30 that sounds... gosh, thinking about it, kind of hard 07:21:43 seems like a standard zero-knowledge proof to me? 07:22:09 It does sound hard; but then, all zero-knowledge proof things sound kind of freaky. 07:22:17 yeah 07:22:21 I guess so 07:22:46 I don't know how to construct a ZKP protocol for an arbitrary problem other than by reduction to an existing ZKP problem but maybe that's enough? 07:22:56 Apparently there's at least a presentation titled "A zero-knowledge proof of possession of a pre-image of a SHA-1 hash" around. 07:23:13 neat 07:23:43 Possibly something based on http://link.springer.com/chapter/10.1007%2FBFb0055745 07:24:26 thizzie 07:24:52 i took sha-1 as an arbitrary example of a cryptographic hash 07:25:20 i'd imagine you just encode a circuit checking that an arbitrary input hashes to the given hash as one of the NP-complete problems for which zero-knowledge proofs are known 07:25:37 wikipedia has hamiltonian graph as an example 07:25:44 *cycle 07:26:16 all this needs to work in general, is for calculation of SHA-1 itself to be in P 07:26:51 -!- FreeFull has quit. 07:27:37 It sounds like potentially not terribly efficient. 07:28:45 well the problem instance would be approximately memory * steps used for calculating SHA-1 07:28:54 *instance size 07:32:05 hm it is not obvious to me that the hamiltonian cycle example really _is_ zero knowledge. 07:32:48 why not 07:33:07 "Peggy will prove that she knows the cycle without simply revealing it (perhaps Victor is interested in buying it but wants verification first --" I wonder how's the market in slightly used Hamiltonian cycles of large graphs. 07:33:10 well i guess you're not claiming it isn't, just saying it's not obvious that it is 07:33:20 because it is not obvious that it is hard to prove that the two graphs are isomorphic 07:33:58 given that they are not constructed to make that hard 07:34:28 -!- ^v has joined. 07:34:39 it could be that there are graphs for which hamiltonian cycle is hard to find, yet still easy to show it isomorphic to any of its renamings. 07:41:45 oh i see the talk page has a discussion clarifying things. 07:42:43 the isomorphic graph is _not_ revealed initially, just signatures of its edges. 07:43:24 it is only fully revealed if an isomorphism is asked for. otherwise only the edges in the cycle are revealed. 07:44:46 oh. yes. 07:46:05 * oerjan didn't read the description properly, obviously X/ 07:47:12 DX 07:47:15 Why isn't there a Java library 07:47:21 That uses terminfo instead of linking to native ncurses 07:51:26 -!- tertu has quit (Ping timeout: 240 seconds). 07:52:14 -!- asie has quit (Read error: Connection reset by peer). 08:00:41 Possibly becuse of apathy, but also perhaps because not all terminal-related things (like picking up on SIGWINCH, or anything involving tcsetattr) are quite doable from pure Java? 08:03:53 -!- ^v has quit (Remote host closed the connection). 08:21:27 -!- oerjan has quit (Quit: leaving). 08:30:24 -!- augur_ has quit (Quit: Leaving...). 09:02:49 -!- augur has joined. 09:04:55 -!- ais523 has quit. 11:31:03 Your daily ##c: http://sprunge.us/SYJP 12:07:16 -!- Koen has joined. 12:08:07 -!- Koen has quit (Client Quit). 12:13:34 -!- Yonkie_ has joined. 12:16:55 -!- ski_ has joined. 12:17:13 -!- kmc_ has joined. 12:21:47 -!- ski has quit (*.net *.split). 12:21:47 -!- Yonkie has quit (*.net *.split). 12:21:47 -!- kmc has quit (*.net *.split). 12:21:47 -!- ion has quit (*.net *.split). 12:21:47 -!- clog has quit (*.net *.split). 12:25:52 -!- Sgeo has quit (Read error: Connection reset by peer). 12:26:02 -!- ggherdov has quit (Ping timeout: 264 seconds). 12:26:47 -!- ion has joined. 12:34:09 -!- yorick has joined. 12:38:56 -!- clog has joined. 12:39:20 -!- ggherdov has joined. 13:02:14 -!- boily has joined. 13:02:16 -!- metasepia has joined. 13:36:22 -!- tertu has joined. 13:47:02 -!- sebbu has quit (Ping timeout: 264 seconds). 13:49:41 good untranslatable Finnish morning! 14:04:38 -!- Bike has quit (Ping timeout: 240 seconds). 14:11:00 -!- Bike has joined. 14:29:02 -!- MindlessDrone has joined. 14:30:14 -!- shikhin has joined. 14:45:25 -!- carado has joined. 14:58:34 -!- augur has quit (Remote host closed the connection). 14:59:09 -!- augur has joined. 15:03:26 -!- augur has quit (Ping timeout: 244 seconds). 15:24:35 -!- Lymia has quit (Ping timeout: 260 seconds). 15:41:26 -!- MindlessDrone has quit (Quit: MindlessDrone). 15:43:09 -!- augur has joined. 15:46:44 -!- conehead has joined. 15:48:51 -!- AnotherTest has joined. 15:49:06 -!- nooodl has joined. 15:50:55 Hello 15:52:09 AnothellorTest. 16:02:52 Othello test? 16:05:30 AnotherThellost? 16:06:22 -!- Sprocklem has joined. 16:06:25 -!- KingOfKarlsruhe has joined. 16:07:10 -!- asie has joined. 16:07:28 Sprhellocklem. KingOfKarlsruhello. asiello. 16:07:47 -!- MindlessDrone has joined. 16:09:03 saluton boily 16:10:30 wow. ĝi estas la unua fojo tio okazis al mi. 16:18:36 -!- Phantom_Hoover has joined. 16:37:19 hahahaha 16:37:49 -!- Phantom_Hoover has quit (Quit: Leaving). 16:38:08 -!- Phantom_Hoover has joined. 16:38:13 hahahaha 16:38:16 seen elsewhere: "There are three hats (IIRC) to hacking: White hat, red hat, and black hat." 16:39:34 just like final fantasy 16:40:01 I've heard about brown hats too. 16:40:38 Pink hats 16:41:05 red hats can learn Doublehack, which allows them to crack two passwords in one turn 16:43:33 what's a brown hat? 16:43:58 Poop hacking? 16:44:28 -!- prooftechnique has joined. 16:44:50 prooftechellonique. 16:44:58 Slereah: bletch. 16:45:06 oh and there's greyhat too, almost forgot 16:45:20 that's when they mess up the dyeing 16:46:00 boihelloly 16:50:19 Bike: Is that related to double compiling? 16:51:24 almost fungot 16:51:25 kmc_: right so should i learn them in? 16:52:20 -!- kmc_ has changed nick to kmc. 16:52:59 fungot: inhale. learn. grok. become even more sentient than you already are, so that your Reign Shall Come! 16:52:59 boily: there are lots of optimizations you can make money fast: http://cgi.ebay.co.uk/ ws/ was/ me 16:53:20 fungot: oh, scamming people to get rich and Subsidize the Masses! 16:53:20 boily: make short program segments of an arbitrarily limited size ( say, c function calls. 17:01:39 -!- Sprocklem has quit (Ping timeout: 260 seconds). 17:01:59 -!- asie has quit (Quit: My MacBook Pro has gone to sleep. ZZZzzz...). 17:06:47 boily: you should try talking with real people 17:07:16 fungot: Did you hear that? He's saying you're not people. 17:07:17 fizzie: i don't know your point? 17:07:37 :D 17:07:44 fungot: Okay, yeah, I guess you don't mind. 17:07:44 fizzie: you are a pervert!" " fnord 17:07:51 Thanks. 17:11:03 -!- Bike has quit (Ping timeout: 244 seconds). 17:13:15 -!- Nisstyre-laptop has joined. 17:17:03 -!- Phantom_Hoover has quit (Ping timeout: 260 seconds). 17:17:25 -!- Bike has joined. 17:23:50 -!- ^v has joined. 17:24:23 -!- sebbu has joined. 17:24:57 -!- sebbu has quit (Changing host). 17:24:58 -!- sebbu has joined. 17:25:31 -!- ^v has quit (Client Quit). 17:26:45 -!- ^v has joined. 17:34:16 -!- nys has joined. 17:34:25 -!- Nisstyre-laptop has changed nick to nisstyre. 17:39:40 -!- FreeFull has joined. 17:41:52 -!- Phantom_Hoover has joined. 17:46:35 -!- shikhin_ has joined. 17:46:40 -!- Phantom_Hoover has quit (Ping timeout: 265 seconds). 17:49:26 -!- shikhin has quit (Ping timeout: 240 seconds). 17:59:58 -!- Lymia has joined. 17:59:58 -!- Lymia has quit (Changing host). 17:59:58 -!- Lymia has joined. 18:09:52 -!- Lymia has quit (Ping timeout: 265 seconds). 18:10:31 -!- augur has quit (Read error: Connection reset by peer). 18:13:10 -!- augur has joined. 18:13:47 back from lunch, and people doubt fungot's existence. 18:13:48 boily: do you have problems with this " usual" depends on what you meant 18:14:07 fizzie: are you a pervert? 18:14:14 fungot: I don't have problems with you. 18:14:15 boily: ( and makes tons of), for instance, if you can 18:21:16 fungot's a fun bot 18:21:16 FireFly: i'll be surprised if brookline newton were the ' most jewish' towns in the red river valley, austin, and state indices could be stored 18:21:47 er. 18:23:05 boily: Well, now, isn't there a small pervert in every one of us? 18:24:06 fizzie: Only on weekends 18:29:36 -!- conehead has quit (Quit: Computer has gone to sleep.). 18:34:10 -!- Lymia has joined. 18:34:10 -!- Lymia has quit (Changing host). 18:34:10 -!- Lymia has joined. 18:35:54 -!- Taneb has joined. 18:48:49 Hi 18:50:40 Vhellorpal. 18:51:21 Vorpallo 18:52:14 -!- Bike has quit (Ping timeout: 240 seconds). 18:54:07 -!- Bike has joined. 19:08:37 -!- Sprocklem has joined. 19:11:30 -!- shikhin_ has changed nick to shikhin. 19:11:55 Vorp 'allo 'allo 19:12:56 -!- Slereah has quit (Read error: Connection reset by peer). 19:13:09 -!- Slereah has joined. 19:14:24 -!- lambdabot has quit (Quit: requested). 19:19:57 fizzie once again killed lambdabot. 19:20:26 -!- nisstyre has quit (Read error: Operation timed out). 19:21:00 Alo, salut, sunt eu, un Vorpal ♪ 19:21:25 I requested no such thing. 19:23:18 boily, French? 19:27:00 Vorpal: Romanian, as in that infamous song that was somewhat popular a few years ago. FireFly earwormed me with his “'allo 'allo”. 19:27:36 fizzie: it's only by default, until we find this time's real culprit. 19:28:13 Vorpal: the French version would have went «Allô, salut, c'est moi, un Vorpal». 19:34:07 -!- lambdabot has joined. 19:34:43 boily, I see 19:35:00 -!- lambdabot has quit (Remote host closed the connection). 19:40:07 -!- lambdabot has joined. 19:41:13 fungot: Vorbiţi româneşte? 19:41:14 kmc: there are scripts to do. one more sem. to get an object in the language 19:50:11 fungot: Well, fire up one of those scripts and have a go at it, then. 19:50:12 fizzie: the number of arguments handled? there are multiple wheels? i guess 19:50:19 Can't wait. 19:52:43 -!- john_metcalf has joined. 19:53:01 ţ, now that's a letter you don't see every day 19:53:05 unless you live in romania i guess 19:54:18 actually I guess it should be ț and not ţ 19:56:36 `unidecode țţ 19:56:38 -!- Lymia has quit (Ping timeout: 240 seconds). 19:56:41 ​[U+021B LATIN SMALL LETTER T WITH COMMA BELOW] [U+0163 LATIN SMALL LETTER T WITH CEDILLA] 19:57:21 the comma is the correct Romanian character. usually confused with cedilla (Turkic) because the latter is more easily obtaine, typed, drawn, encoded, and stuff. 19:57:40 s,e\,,ed\,, 19:58:57 -!- prooftechnique has quit. 19:59:51 Are you some kind of a pervert, deliberately choosing a delimiter that makes escaping necessary? 20:00:13 -!- prooftechnique has joined. 20:01:17 -!- Lymia has joined. 20:01:17 -!- Lymia has quit (Changing host). 20:01:17 -!- Lymia has joined. 20:03:22 fizzie: mwah ah ah. 20:15:50 sed fetish 20:18:45 -!- MindlessDrone has quit (Quit: MindlessDrone). 20:18:55 Did I tell you about my misadventure a couple of weeks ago 20:19:34 Which kmc has just reminded me of 20:20:30 oh boy 20:20:33 do tell 20:20:55 All of my misadventures involve se 20:20:58 *sed 20:22:10 ITYM s/$/d/ HTH HAND 20:22:30 Yes, clearly 20:22:32 http://uk.finance.yahoo.com/echarts?s=THEGQ#symbol=thegq;range=5d;compare=;indicator=volume;charttype=area;crosshair=on;ohlcvalues=0;logscale=off;source=undefined; lol 20:23:39 In retrospect, I wish I'd had the foresight to invest in Tweeter 20:23:45 Heh, they've changed the stock symbol for it. 20:23:46 That was a temporally difficult sentence 20:24:06 It used to be TWTRQ, which is significantly closer to TWTR than the current THEGQ. 20:24:17 didn't that happen with another stock before? 20:24:42 "Groogle Bioimplants got a huge boost" 20:26:15 haha 20:26:26 btw symbol ending in Q indicates that the company is bankrupt 20:26:29 if you didn't know 20:26:38 why Q? 20:26:47 They've called it quits. 20:26:58 GHCQ 20:27:04 e.g. General Motors which went from being NYSE:GM and part of the DJIA to being GMGMQ on pink sheets 20:27:19 I'll bet Aardwolf Party Lanterns gets a good accidental boost, now and again 20:27:41 also I find it hilarious that Washington Mutual sold their plum NYSE:WM ticker to Waste Management, Inc 20:27:46 but stock is still traded? (nb i know nothing about finance or business or hi) 20:28:28 Bike: It also went bankrupt all the way back in 2007. 20:28:36 Bike: yeah, it's not clear to me why bankrupt stock trades at a non-zero price, because theoretically equity holders are last in line to get anything at bankruptcy court 20:29:05 Bike: one explanation I heard from someone very knowledgable is that, this is the case in theory, but in practice if you own a huge chunk of the equity you can show up in court and annoy the jugde enough that they will give you something just to go away 20:29:16 but "people are dumb" is another promising answer 20:29:18 kmc, I was trying to go to a sci-fi and fantasy society social, and I went to the wrong bar 20:29:26 Wound up at my university's fetish society 20:29:32 Didn't realise for an hour and a half 20:29:39 that is beautiful 20:29:43 what kind of fetish(es) 20:29:49 I dunno 20:29:50 -!- ^v has quit (Ping timeout: 240 seconds). 20:30:02 They had just finished a show and tell and were going to the bar afterwards 20:30:05 there are a lot 20:30:09 aw, did you miss the show and tell? 20:30:12 Yeah 20:30:14 :/ 20:30:22 I don't think they are too restrictive on which fetishes 20:30:23 kmc: this company went down years ago, isn't court already over 20:30:23 your university has a fetish society?????????????? 20:30:25 Still would not have clarified, probably 20:30:27 Someone was carrying a violin 20:30:31 Bike: beats me 20:30:33 boily, yup 20:30:53 Taneb: I am disturbed. 20:31:05 * kmc finds that "fetish" and "kink" are often used to mean BDSM specifically and is pretty annoyed by this fact 20:31:16 now i'm wondering if my school has a 'fetish society' 20:31:17 but also I'm probably doing the thing P_H hates 20:31:22 * Bike googles 20:31:34 where I start a conversation about how Some People do something dumb 20:31:41 http://public.wsu.edu/~delahoyd/20th/surrealism.html noooooot quite 20:31:51 haha 20:32:10 this reminds me a bit of the first graf on http://www.mit.edu/~mitsfs/related-groups.html 20:32:12 "FINRA believed that trading in the TWTRQ security demonstrated a widespread misunderstanding related to the possible initial public offering of an unrelated security." nice deadpan tone. 20:32:20 kmc, if you're worried that you're doing something he hates, picture him watching the Big Bang Theory and then you'll be even 20:32:25 haha 20:32:29 does he do that? 20:32:36 Probably not 20:32:43 i'm only getting hits from sociological research. which makes a shockking amount of sense. 20:32:47 I've actually seen a good chunk of BBT... but I don't feel good about that fact 20:32:52 http://www.vancouver.wsu.edu/sites/www.vancouver.wsu.edu/files/insertable_images/nwcg-fiftyshadesofgrey.jpg behold 20:33:08 brb naming my sex toy company "insertable images" 20:33:21 oh, shit. fifty shades actually mentions wsu 20:33:27 I'm opening an underwear shop called Butt Stuff 20:33:29 i'm like, kinky by association now, i bet 20:34:26 "In the Habit of Being Kinky: Practice and Resistance in a BDSM Community, Texas, USA" 20:34:30 also I don't think NYSE:Q is bankrupt 20:37:32 -!- Taneb has quit (Quit: Leaving). 20:37:32 I don't think we have a fetish society, though there's quite a lot of them. 20:37:53 Like a drinking game society, apparently. 20:39:54 -!- ^v has joined. 20:41:40 Sometimes it's nontrivial to derive the topic from the name. Like "The Hangovers", which seems to be about climbing. 20:42:01 lololol 20:42:20 that's like http://www.reddit.com/r/MarijuanaEnthusiasts 20:42:56 zomg syntax highlighting in papers 20:43:10 is that new 20:43:29 papers on arxiv have links and cites highlighted in different colors a lot 20:43:47 -!- Sprocklem has quit (Ping timeout: 260 seconds). 20:44:10 i mean of code 20:44:23 http://www.ncbi.nlm.nih.gov/pmc/articles/PMC3621334/#s001title speaking of #drugz 20:44:42 the "tropical hurricane" of youth 20:44:52 http://www.loweringthebar.net/2013/11/do-not-clench-your-buttocks-in-deming-new-mexico.html speaking of #drugz 20:45:09 ("Deming" reminds one of bad keming.) 20:45:34 shachaf: i've seen papers that use the color modes of lhs2TeX 20:45:48 ~duck deming 20:45:48 --- No relevant information 20:46:07 * boily kicks ~duck in the lambdas 20:46:16 fizzie: fascinating 20:46:20 kmc: i didn't know that existe 20:46:21 d 20:48:48 fizzie: that's really fucked up :( 20:49:51 I knew it. I knew I had that copy over there. http://pastebin.ca/2474654 20:50:54 holy sht that's long 20:56:53 kmc: Chrome just recently grew support for CHACHA20_POLY1305 for SSL 20:58:15 -!- Bike has quit (Ping timeout: 260 seconds). 21:04:26 -!- Bike has joined. 21:05:21 -!- john_metcalf has quit (Quit: http://RetroProgramming.com). 21:10:55 -!- conehead has joined. 21:21:52 http://imgur.com/xsRpp3Z 21:23:11 the actual list is good too 21:23:18 'photoshop' 21:28:45 ~metar CYUL 21:28:45 CYUL 072100Z 26014KT 15SM OVC040 05/M03 A2983 RMK SC8 SLP103 21:32:23 -!- boily has quit (Quit: irregular chicken.). 21:32:25 -!- metasepia has quit (Remote host closed the connection). 21:34:47 shachaf: nice 21:39:33 -!- AnotherTest has quit (Ping timeout: 272 seconds). 21:40:06 "When filled with many single Lego bricks, a washing machine generates random complexes." (PDF) http://www.althofer.de/random-lego-structures.pdf 21:48:17 @tell boily Looks like zeta. 21:48:18 Consider it noted. 21:49:44 -!- Slereah has quit (Ping timeout: 246 seconds). 21:50:31 kmc: "analog monte carlo procedures" omg 21:50:43 @tell boily (It's https://dl.dropboxusercontent.com/u/113389132/Misc/20131107-loglog.png with both axes logarithmic, and zeta would be a line there, so okay, not a terribly good fit.) 21:50:43 Consider it noted. 21:56:10 -!- Slereah has joined. 21:56:26 Figure 2.2: A Lego enzyme candidate ?! 21:58:42 -!- Lymia has quit (Read error: Operation timed out). 22:03:47 -!- nisstyre has joined. 22:14:24 -!- carado has quit (Ping timeout: 252 seconds). 22:14:29 -!- ^v has quit (Remote host closed the connection). 22:19:11 -!- oerjan has joined. 22:19:55 -!- ^v has joined. 22:25:33 -!- KingOfKarlsruhe has quit (Quit: ChatZilla 0.9.90.1 [Firefox 25.0/20131025151332]). 22:56:16 -!- Lymia has joined. 23:11:58 -!- jarpal has joined. 23:25:58 -!- nisstyre has quit (Quit: Leaving). 23:28:37 -!- oerjan has set topic: The channel of the chimæric hellos | Koirammekokaan ei lennä? :( | https://dl.dropboxusercontent.com/u/2023808/wisdom.pdf | logs: http://codu.org/logs/_esoteric/ or http://tunes.org/~nef/logs/esoteric/. 23:33:25 -!- augur has quit (Remote host closed the connection). 23:33:59 -!- augur has joined. 23:38:14 -!- augur has quit (Ping timeout: 240 seconds). 23:46:35 -!- shikhin_ has joined. 23:49:19 -!- Phantom_Hoover has joined. 23:50:07 -!- shikhin has quit (Ping timeout: 265 seconds). 23:56:59 `addquote kmc, I was trying to go to a sci-fi and fantasy society social, and I went to the wrong bar Wound up at my university's fetish society Didn't realise for an hour and a half 23:57:05 1129) kmc, I was trying to go to a sci-fi and fantasy society social, and I went to the wrong bar Wound up at my university's fetish society Didn't realise for an hour and a half 23:59:43 * oerjan ponders the fact that the formatted logs apparently merge consecutive spaces 2013-11-08: 00:00:18 i cannot quite be bothered to check whether there were any in that quote, though. 00:01:03 @brain are you pondering what ørjan is pondering? 00:01:03 It must be inordinately taxing to be such a boob. 00:01:13 sigh, it must be the ø 00:01:16 @brain are you pondering what oerjan is pondering? 00:01:16 What can I do for fun, Pinky? That's it! I'll send several 00:01:16 bills to Senate for ratification, then veto them all! 00:01:25 * oerjan swats lambdabot -----### 00:01:27 @brain did someone break @brain? 00:01:27 Are you pondering what I'm pondering? 00:01:35 @brain where are the pinky quotes? 00:01:35 Promise me something, Pinky. Never breed. 00:01:40 @pinky 00:01:40 Well, I think so, but Kevin Costner with an English accent? 00:01:43 -!- Bike has quit (Ping timeout: 265 seconds). 00:01:46 ...Ah. 00:01:49 @list brain 00:01:49 quote provides: quote remember forget ghc fortune yow arr yarr keal b52s pinky brain palomer girl19 v yhjulwwiefzojcbxybbruweejw protontorpedo nixon farber 00:01:54 shachaf: um does it actually pay any attention to the part after @brain 00:02:02 oerjan: Not that I know of. 00:02:09 Who split up Pinky and the Brain? 00:03:38 @tell gregor You should fix the formatted log style not to squeeze consecutive spaces. for quote accuracy, you see. 00:03:39 Consider it noted. 00:05:31 shachaf: the separatists 00:07:31 -!- nooodl has quit (Ping timeout: 265 seconds). 00:09:05 oerjan: i'm a separatist myself but i haven't heard of that 00:09:10 it must be a different faction 00:09:53 -!- Bike has joined. 00:13:29 this reminds me a bit of the first graf on http://www.mit.edu/~mitsfs/related-groups.html <-- which graf, and also why didn't they add another I for the nice anagram. 00:14:46 nice anagram? 00:15:31 of mitsfs + i 00:16:11 preferably second last 00:16:18 because they fit in just fine at MIT 00:16:42 how weird. 00:18:28 my old alma mater wasn't the only one to dodge a bullet here https://en.wikipedia.org/wiki/NUST 00:23:50 but people pronounce it "mits fiss" or so 00:23:56 so I don't think the connection is un-noticed 00:24:10 that's like http://www.reddit.com/r/MarijuanaEnthusiasts <-- XD 00:24:31 talk about inside joke 00:25:35 -!- augur has joined. 00:26:03 -!- Slereah_ has joined. 00:26:36 -!- augur_ has joined. 00:27:20 beep 00:28:03 -!- Slereah has quit (Ping timeout: 252 seconds). 00:28:56 boop 00:29:03 does anyone know of any contests or challenges where a particular language has its syntax "funged" so as to be unrecognizable, with the task of recovering the language by poking at programs? 00:30:21 -!- augur has quit (Ping timeout: 252 seconds). 00:45:03 -!- Lymia has quit (Ping timeout: 260 seconds). 00:52:34 -!- Lymia has joined. 00:52:34 -!- Lymia has quit (Changing host). 00:52:34 -!- Lymia has joined. 01:00:57 -!- shikhin_ has quit (Read error: No route to host). 01:09:30 beep boop 01:09:52 another awesomely named MIT club is MITBEEF 01:09:54 the beef club 01:10:12 beep boop 01:10:17 they got passes to some huge meat convention that was going on in boston 01:10:19 pretty sweet 01:10:31 we had a Meat Club which was slightly less focused (I think they served snail at one point) 01:10:42 Caltech also had a Hazing Club 01:10:44 opt-in of course 01:11:31 -!- yorick has quit (Remote host closed the connection). 01:13:37 -!- jarpal has quit (Ping timeout: 272 seconds). 01:14:27 -!- Phantom_Hoover has quit (Ping timeout: 260 seconds). 01:16:54 kmc: http://www.theonion.com/articles/freedom-takes-a-hit,33699/ 01:17:15 -!- augur has joined. 01:21:28 -!- augur_ has quit (Ping timeout: 265 seconds). 01:22:10 heh 01:22:17 i wonder if the kmc #drugz thing is getting old 01:22:21 not sure 01:22:26 and i have done nothing but encourage it so far 01:23:54 kmc: what should i look for! 01:24:22 re: "does anyone know of any contests or challenges where a particular language has its syntax "funged" so as to be unrecognizable, with the task of recovering the language by poking at programs?" 01:24:33 kmc: http://en.wikipedia.org/wiki/Beefsteak_Club The Sublime Society of Beef Steaks 01:24:42 BEEF AND LIBERTY 01:27:35 lexande: nice 01:28:05 augur: uh, one of the io.smashthestack.org challenges involves reverse engineering a compiled, obfuscated binary of an interpreter for a stack machine 01:28:12 in order to then write programs for that machine 01:28:24 that doesn't quite sound like what you mean though 01:28:35 kmc: do you know of any methodologies for such reverse engineering tasks? 01:28:48 -!- Phantom_Hoover has joined. 01:29:17 -!- Sgeo has joined. 01:30:59 i don't know much about the general practice of RE, no 01:31:20 i mean "look at the code and figure out what it does" 01:31:23 not very satisfying 01:31:52 there are tools that will find basic blocks, build control flow graphs, express them as pseudo-C, let you assign names to variables as you figure them out, etc 01:32:22 https://hex-rays.com/products/ida/index.shtml is the gold standard of RE tools; http://www.hopperapp.com/ is getting a lot of good press lately 01:32:37 http://radare.org also looks quite cool 01:32:41 i haven't used any of them 01:33:00 those things usually depend on knowledge of the code structure tho 01:33:02 -!- Lymia has quit (Ping timeout: 240 seconds). 01:33:06 oh i did use the freeware version of IDA for DOS to reverse engineer a late 20th century French-Canadian apothecary sign 01:33:16 but the code was not obfuscated at all 01:33:26 imagine instead if you found a language where all the tokens were permuted with random things 01:33:47 so that it looked like line noise 01:34:01 how would you figure out what a program in such a language did? 01:34:28 that's kind of a cryptanalysis problem 01:34:36 not quite 01:34:57 cryptanalysis doesnt let you probe the program however you want 01:35:18 you get a blackbox compiler/interpreter, and some example programs 01:35:47 infact, as many example programs as you want, lets say a billion just for fun 01:36:12 and you can run them, or maybe search through them by the effects they have, described broadly 01:36:25 and you can edit and run programs too 01:36:38 how would you figure out what was going on? 01:37:27 pretty much been my experience with matlab 01:37:32 :) 01:37:43 -!- Phantom_Hoover has quit (Quit: Leaving). 01:38:03 it's been fascinating how much good i can do for a program i don't understand a damned thing about 01:41:46 -!- Sprocklem has joined. 01:52:51 haha bike 02:00:24 -!- nisstyre has joined. 02:22:19 Would it be odd to go to StackOverflow to ask a question then answer it immediately? 02:22:38 Couldn't find the answer to a question I had about IE, determined the answer experimentally 02:28:47 -!- Sprocklem has quit (Ping timeout: 252 seconds). 02:37:29 -!- Taneb has joined. 02:38:15 aaaah oh god I'm going to be playing D&D 02:39:18 don't give in to satan 02:39:53 Oh, he won't. 02:40:01 Helel on the other hand? 02:42:34 -!- Lymia has joined. 02:49:14 Sgeo: Please do that 02:49:20 It's totally kosher 02:51:06 prooftechnique: context? 02:51:11 Taneb: ++ 02:51:19 [21:22:19] Sgeo: Would it be odd to go to StackOverflow to ask a question then answer it immediately? 02:51:20 [21:22:38] Sgeo: Couldn't find the answer to a question I had about IE, determined the answer experimentally 02:51:28 oh yeah, its totally fine 02:51:31 they even encourage it 02:54:34 I'm... going to be playing D&D with a pacifist character 02:55:17 if you beat the first mission of Deus Ex without killing anyone you get an achievement but also your fellow cybernetically enhanced super-soldiers will make fun of you for being a wuss 02:58:51 You'll also be woefully ill-equipped for the outsourced boss fights 02:59:36 Taneb: Tell them to use the Book of Exalted Deeds rules 03:09:58 Also, today I found out that vegans can eat bread 03:10:18 Taneb: why wouldn't they? 03:10:37 quintopia, I was getting the recipe mixed up with cake 03:10:45 I thought bread had milk and eggs 03:11:04 weirdo 03:15:16 i think zzo38 plays his character with minimal violence, i am not sure if he's entirely pacifist or not. 03:21:07 whoa who is Oj742. 03:24:27 some bread has eggs i think 03:24:29 and some cake doesn't 03:24:50 vegans can eat fungi even though they're closer to animals than to plants 03:25:20 which is good because bread is mostly made using fungi 03:26:28 except for salt rising bread, which is made using a bacterium from the same genus as tetanus and gas gangrene and botulism 03:26:44 #terrifyingbreadfacts 03:28:08 Sounds delicious 03:29:07 what about bread using baking soda leavening 03:29:24 and what about flatbread 03:33:32 flatbread, fair enough 03:33:38 can you bake bread with only baking soda and no yeast? 03:33:45 i thought it was used as an additional component 03:33:46 but I dunn 03:33:47 o 03:33:49 I'm no baker 03:34:03 Lightbeam is pretty cool 03:34:20 yeah 03:34:35 flatbread is not vegetarian. it is made from flatfish flour (nn:kveitemjøl, from nn:kveite, halibut) 03:36:44 mmm 03:37:24 -!- Taneb has quit (Quit: Leaving). 03:52:23 -!- Lymia has quit (Ping timeout: 252 seconds). 04:07:56 !bfjoust space_hotel http://sprunge.us/aNPE 04:08:08 ​Score for quintopia_space_hotel: 51.9 04:08:33 SLIGHT IMPROVEMENT 04:11:22 -!- nys has quit (Quit: quit). 04:15:13 -!- drlemon has joined. 04:24:29 -!- nisstyre has quit (Read error: Connection reset by peer). 04:33:55 -!- prooftechnique has quit. 04:34:51 So, there are now two questions that I really should get around to asking and answering on SO 04:48:51 when i'm on my SO, i'm not usually thinking about asking and answering questions 04:49:42 ^ 04:50:24 passwo 04:50:31 lo 04:50:32 l 04:50:52 oklolplol 04:50:53 (was trying to see if someone linked the password file i've been hearing so much about here) 04:51:04 i did a while ago 04:51:29 -!- Sprocklem has joined. 04:51:29 (but ctrl+f often just pops up the find box but doesn't make it focused) 04:51:29 Bike: the one that's like the world's greatest crossword puzzle according to xkcd? 04:51:36 yeah. 04:52:45 Bike: you showed some top100 thing? 04:53:00 probably 04:54:21 "30. 28132 Ttgs5+ZAZM7ioxG6CatHBw== princess" 04:54:37 how 04:54:45 what/ 04:55:00 that was a question mark 04:55:15 i don't understand how random words get on these lists 04:55:48 maybe i just want the password recovery thing to call me a princess. since no one ELSE does 05:01:16 i have a friend who does some sort of computer security research and uses a short unary password almost everywhere, and happily tells people what it is 05:01:41 8. 113884 7LqYzKVeq8I= 111111 05:04:12 so is it research in how to be secure even if everyone knows your password? 05:04:34 -!- nisstyre has joined. 05:07:14 maybe he should've used 666666 05:08:12 i'ma get a lightbeam. dunno what to expect from it...i don't browse much 05:17:30 " papers on arxiv have links and cites highlighted in different colors a lot" <<< this will not surprise anyone, but anyway: this is because you send the tex and they compile it that way 05:19:31 (as opposed to there being an arxiv style that has that which you can use, say) 05:20:07 come to think of it, i guess they could just add those to pdfs too 05:20:43 if you send them a pdf that's generated from tex source, they notice it and tell you to submit the tex instead 05:29:21 haha, of course 05:35:34 -!- Yonkie_ has quit (Ping timeout: 244 seconds). 05:36:51 -!- Lymia has joined. 06:01:14 -!- conehead has quit (Quit: Computer has gone to sleep.). 06:14:06 "@windyoona @0xabad1dea fun story: Lego bricks form a free trace monoid just like the one from process calculus! They model parallelism!" 06:14:12 hmmmmmm 06:15:29 not the other way around? 06:16:31 * kmc reads about trace monoids 06:17:07 i mean generally if it's a math thing versus something that actually happens i'm going to guess it's the former that's the "model" 06:21:11 -!- v^ has joined. 06:21:50 -!- ^v has quit (Ping timeout: 240 seconds). 06:21:55 did someone say trace monoids 06:21:59 i love monoids 06:24:47 i did 06:25:02 btw both of the mentioned people are great and you should follow them if you do the twitter thing 06:25:25 i don't do the twitter thing but i have a file of people i would follow if i did follow people 06:25:31 so i'll add them to the file 06:25:58 v. effective 06:26:19 my file now contains 43 people 06:26:37 way too many to open tabs for each one every day and look at what's new 06:27:03 maybe i can set up an rss client to fetch each of their feeds 06:27:25 kmc: you should teach me about trace monoids 06:27:30 what's this "natural homomorphism" business 06:29:58 i don't know about them :( 06:30:47 :'( 06:30:48 hmm 06:35:35 wikipedia does tho 06:38:27 i'm not sure what wikipedia means but maybe i'll read the whole article 06:40:58 -!- ^v has joined. 06:43:02 -!- v^ has quit (Ping timeout: 240 seconds). 06:51:07 kmc: why is it called "trace" 06:54:29 i don't know 06:54:37 -!- tertu has quit (Ping timeout: 244 seconds). 06:55:44 -!- ^v has quit (Quit: http://i.imgur.com/MHuW96t.gif). 07:01:02 -!- tertu has joined. 07:01:52 -!- ter2 has joined. 07:02:10 -!- tertu has quit (Read error: Connection reset by peer). 07:02:14 -!- ter2 has quit (Read error: Connection reset by peer). 07:02:31 -!- ter2 has joined. 07:24:03 -!- ter2 has quit (Ping timeout: 260 seconds). 07:24:51 -!- Slereahphone has joined. 07:32:06 -!- Slereahphone has quit (Ping timeout: 252 seconds). 07:33:22 -!- Sprocklem has quit (Ping timeout: 244 seconds). 07:33:54 OH in my living room: "So I don't think RMS can be snorting mountains of cocaine" 07:34:49 what means "koirammekokaan" 07:34:52 dog something 07:35:21 dog (irthative case) 07:35:35 that's a made up case 07:35:38 you just made up that case 07:35:52 I did not! someone else did, long ago 07:36:40 -!- FreeFull has quit. 07:39:09 -!- Slereahphone has joined. 07:41:35 -!- Slereahphone has quit (Client Quit). 07:42:42 olsner: there are only two google hits for "irthative" and one is Phantom_Hoover on this channel. so yeah. 07:43:14 the other is a seriously misspelled "affirmative". 07:43:43 well i assume that's it, anyhow. 07:44:27 no wait, the first person to use it is you. 07:44:45 olsner: i conclude that you made it up, long ago. 07:44:47 huh? 07:45:40 hm wait there's some development into it. 07:45:51 06:05:06 What's that word that means "is not bad anymore"? 07:45:52 06:05:51 irthen bad? 07:45:53 06:05:06 What's that word that means "is not bad anymore"? 07:45:54 06:05:51 irthen bad? 07:45:54 kmc: i decline to answer 07:45:57 gah 07:48:41 kmc: https://en.wiktionary.org/wiki/-mme https://en.wiktionary.org/wiki/-ko https://en.wiktionary.org/wiki/-kaan hth 07:48:58 Aw, I was just about to decompose it. 07:49:51 so... translate plz 07:50:11 i tried to but gt couldn't make sense of the -kaan 07:50:15 yo fizzie, i'mma let you finnish, but wiktionary is one of the best decomposers of all time 07:50:25 koiramme = our dog? 07:50:27 It is indeed dog | our | make-into-a-question | even. 07:50:41 huh 07:51:03 It's also kind of awkward-sounding. 07:51:35 But it could be used in a sentence. "Pystyisiköhän koirammekokaan siihen?" "Could even our dog do it?" 07:51:57 fizzie: i should learn finnish :'( 07:52:14 In the sense of "even" meaning that it's very difficult, but maybe the dog could manage it. 07:52:25 (And not the sense that anyone, even a trained monkey could do it.) 07:52:51 Maybe "Could our dog even do it?"? 07:53:01 Maybe. I should learn English. 07:53:16 are you planning to go to england 07:53:48 Though somehow "could our dog even do it" sounds to me like it's not necessarily a difficult thing, just that you're a bit sceptical about the dog. 07:53:49 so the thing in the topic means "Don't even our dogs fly?" 07:54:01 Oh, it's in the topic. 07:54:34 oerjan: Single dog. But something like that, yes. 07:54:37 oh, that's where kmc got the word from 07:55:02 oerjan: It's kind of like you have lots of things and none of them are capable of flying, not even the dog. 07:55:03 fizzie: ensin sinä, sitten minä 07:55:12 huh gt thinks koiramme is plural 07:55:14 is that even grammatical finnish 07:55:31 oerjan: What's gt? 07:55:50 oerjan: Sadly, I think it's both. 07:56:28 oerjan: I thought the pluralization was of us, not of the dog. 07:56:43 oerjan: As in, there's no difference between the singular and plural in that case. But the verb would be inflected differently for plural. 07:57:28 fizzie: eek. 07:57:33 shachaf: google translate 07:57:38 Oh. 07:57:45 "kaikki koiramme" all our dogs, "paras koiramme" our best dog, yeah, there's no change for the plural when it's first-person-plural-possessive. 07:57:51 shachaf: well gt translates it as "our dogs" 07:57:57 Ah. 07:58:12 oerjan: It would be "koirammekokaan eivät lennä?" if they had several dogs, none of which flew. 07:58:37 actually it makes it singular if i remove that kokaan 07:58:50 and keeps the rest of the sentence 07:59:13 dekokaanization is a popular activity among finnish grammaticians 07:59:34 "Koirakokaan ei lennä?" seems to be translated more or less correctly. 07:59:34 fizzie: and here i thought finnish had a plural suffix. 08:00:17 oerjan: It has, it just seems to be hidden by the possessive suffix. "koira" dog, "koirat" dogs. 08:00:35 Or possibly "koiria" for a different kind of plural. 08:00:54 "täällä on paljon koiria" there are many dogs, "kaikki nämä koirat" all these dogs. 08:01:23 Er, first one meaning there are many dogs *here*, not just in general. 08:02:10 Also dog seems to be the first example word in http://en.wikipedia.org/wiki/Finnish_grammar#Plurals coincidentally. 08:02:43 And I forgot the second kind of plural, the "kaksi koiraa" two dogs kind of one. 08:02:54 koirammekokaan ei nosta? 08:04:58 That's kind of missing what it would lift up. 08:05:23 yes 08:05:28 fizzie: doesn't koira have the third form, then? 08:05:29 it's also the wrong use of "even" 08:06:55 oerjan: Which third form was that? 08:07:11 inflected plural 08:07:23 Google mostly finds things like http://verwelktesgedicht.tumblr.com/post/65125049172/english-a-dog-swedish-what-english-the 08:07:29 I think that's pretty unfair. 08:07:41 which has a suspicious lack of koira examples 08:08:36 or wait that was the koiria you mentioned 08:10:05 so why isn't it koiriamme or something >:) 08:10:41 oerjan: It would be if the whole word would be in partitive case. 08:10:52 hmph 08:10:57 oerjan: "kukaan ei hoida koiraamme/koiriamme" nobody's taking care of our dog/dogs. 08:11:15 There the singular/plural distinction is maintained. 08:11:44 does this mean the nominative with a possessive suffix never has/usually doesn't have a distinct plural? 08:12:09 I think that might well be true. 08:12:20 "myymme koiramme" we sell our dog/dogs -- right. 08:12:39 If you wanted to emphasize it's plural, I think you'd then just "myymme kaikki koiramme" we sell all our dogs. 08:12:42 imo use a simple language like hebrew 08:12:54 argh you finns and using nominative for objects 08:15:07 hebrew is good because first you encode all the meaning like verb conjugation in the vowels and then you don't write the vowels 08:15:38 The topic proves (once again) that Finnish is an esoteric language. 08:16:06 And English? 08:16:36 We need some Norwegian in the topic. 08:16:40 I think the languages that aren't somehow weird form a minority 08:17:04 I used to think Swedish is really straightforward until I heard the complaints of my Japanese teacher 08:17:17 she claimed it's easier to learn Finnish than Swedish. 08:17:46 finnish and japanese are p. similar 08:18:06 oerjan: Finnish has three cases for objects :) 08:18:29 shachaf: that's true, I guess it's the very-high-level structural similarity which aided her. 08:18:53 who are you anyway 08:18:59 atehwa. 08:18:59 `welcome atehwa 08:19:03 atehwa: Welcome to the international hub for esoteric programming language design and deployment! For more information, check out our wiki: . (For the other kind of esoterica, try #esoteric on irc.dal.net.) 08:19:39 oerjan: and it's complicated more by the fact that possessive suffices (like -mme) often replace the inflective suffix. 08:20:56 shachaf: I'm one of those guys who were active in esolangs community in the 90's. 08:22:13 I didn't speak English in the 1990s so I don't know much about what was going on in that community at the time. 08:22:28 Maybe I should've learned Finnish instead. 08:24:49 atehwa: You ran the sange.fi iteration of the mailing list, unless I misremember? 08:29:01 There ought to be a channel for talking about esolangs. 08:29:27 I'd probably join. 08:30:34 fizzie: that's right. 08:39:04 -!- impomatic has quit (Quit: http://corewar.co.uk). 08:49:53 -!- oerjan has quit (Quit: leaving). 09:23:33 -!- aloril_ has quit (Ping timeout: 272 seconds). 09:32:35 -!- MindlessDrone has joined. 09:37:22 -!- aloril_ has joined. 09:42:38 -!- Bike has quit (Ping timeout: 240 seconds). 09:52:14 max(street-outside-the-office): https://dl.dropboxusercontent.com/u/113389132/Misc/20131108-otakaari.jpg 09:57:10 -!- Bike has joined. 10:05:27 -!- carado has joined. 10:26:09 -!- Phantom_Hoover has joined. 11:27:33 -!- jarpal has joined. 11:30:18 -!- asie has joined. 11:43:41 -!- Taneb has joined. 11:47:28 ^help 11:47:28 ^ ; ^def ; ^show [command]; lang=bf/ul, code=text/str:N; ^str 0-9 get/set/add [text]; ^style [style]; ^bool 11:59:51 -!- augur has quit (Remote host closed the connection). 12:00:17 -!- augur has joined. 12:01:44 https://dl.dropboxusercontent.com/u/113389132/Misc/20131108-fit.png best fit? 12:01:57 -!- augur_ has joined. 12:04:41 -!- jarpal has quit (Changing host). 12:04:42 -!- jarpal has joined. 12:04:59 -!- augur has quit (Ping timeout: 260 seconds). 12:09:16 -!- Phantom_Hoover has quit (Ping timeout: 244 seconds). 12:13:12 -!- augur has joined. 12:16:27 -!- augur_ has quit (Ping timeout: 252 seconds). 12:28:21 -!- asie has quit (Quit: Textual IRC Client: www.textualapp.com). 12:36:55 -!- Taneb has quit (Quit: Leaving). 12:39:21 -!- yorick has joined. 12:48:05 -!- Sgeo has quit (Read error: Connection reset by peer). 12:53:38 -!- jarpal has changed nick to cucuy. 12:56:59 -!- carado has quit (Ping timeout: 265 seconds). 13:02:20 -!- cucuy has quit (Quit: leaving). 13:03:17 -!- boily has joined. 13:03:21 -!- metasepia has joined. 13:19:23 (Parphrasing from an interview of Miyazaki by the Finnish public broadcasting company:) "I worked part-time for The Moomins for a while. I thought it would be funny to introduce a tank in the series. It was even approved, but then I heard it would be completely contradictory to Tove Jansson's philosophy." 13:19:28 And that's how the world lost the "Moomins in Tanks" concept. 13:19:55 (Source in Finnish: http://yle.fi/uutiset/hayao_miyazaki_jaahyvaishaastattelussa_halusin_muumeihin_tankin/6921093?origin=rss ) 14:07:54 -!- ter2 has joined. 14:37:53 -!- monotone has quit (Quit: "I can hear myself... I think I'm a bit afraid."). 14:40:41 Updated view: https://dl.dropboxusercontent.com/u/113389132/Misc/20131108-otakaari2.jpg 14:46:45 -!- carado has joined. 14:47:06 -!- monotone has joined. 14:47:46 fizzie: what time is it 14:52:40 08.16:47:46 quintopia | fizzie: what time is it 14:55:56 It is almost five pee-em. 14:57:24 https://dl.dropboxusercontent.com/u/113389132/Misc/20131108-otakaari3.jpg one more for the read 14:57:38 (#2 was made from 500 images, this one from a thousand.) 14:57:43 Road, not read. 14:57:48 (I'm going to go a bus now.) 15:00:25 -!- carado has quit (Remote host closed the connection). 15:03:27 -!- carado has joined. 15:15:13 -!- carado has quit (Remote host closed the connection). 15:21:20 -!- carado has joined. 15:21:40 -!- shikhin has joined. 15:26:49 -!- carado has quit (Quit: Leaving). 15:38:01 -!- prooftechnique has joined. 15:40:06 -!- AnotherTest has joined. 15:40:54 are there any esolangs based on infinite state machines? 15:41:02 who behave like finite state machines 15:41:09 but can create new states at runtime 15:41:12 and transitions at runtime 15:43:06 i.e a transtion is capable of creating a new state 15:43:14 and add transitions to it 15:45:53 -!- conehead has joined. 15:47:07 I have discovered the key to comedy. 15:47:08 http://i.imgur.com/BSFyKv9.gif 15:47:42 Are you sure? 15:48:23 120% 15:56:33 -!- boily has quit (Quit: IEUAAAAH!). 15:56:35 -!- metasepia has quit (Remote host closed the connection). 15:59:46 on a completely off-topic note 15:59:51 there should be an esolang about uml 15:59:53 or using uml 15:59:55 or abusing uml 16:01:06 who put a image of a diode (I assume?) to list of ideas? 16:05:34 write an os in brainfuck 16:05:38 that seems odly trivial to do 16:05:45 oddly 16:06:33 unless you don't count that I write it in assembly and THEN compile it to brainfuck 16:06:38 and then compile it to native code 16:08:23 http://geek-and-poke.com/geekandpoke/2013/7/22/future-proof-your-data-model 16:08:48 Pascal is case-insensitive, how odd. 16:08:58 Also, why am I reading Pascal. 16:09:46 that's 16:09:54 probably not alowed in clean-code relational modelling stuff 16:10:21 i.e recursion 16:10:25 although 16:10:51 (I think the esolang you describe already exists, and is called UML.) 16:11:38 well 16:11:52 I currently have lectures about writing software in an UML-Like matter 16:11:57 for embedded systems 16:12:02 modell driven development :) 16:12:03 -!- Slereahphone has joined. 16:12:04 oder model 16:12:28 Frankly, the *only* benefit I see now is 16:12:39 that you automatically have all the UML diagrams :) 16:12:51 and don't write code and then draw some UML diagrams :) 16:13:00 on the other hand 16:13:14 you have to insert code into the code generated by the codegen 16:13:24 because the code gen can't do *everything* for you 16:13:40 i.e. it can't generate code on how to actually control the hardware 16:14:10 so you have to write that code by hand using those horrible generated struct and types by the codegen 16:14:18 oddly named 16:14:21 and whatever 16:14:36 also you gotta know how the codegen generates the names :) 16:14:57 that and since it's an eclipse plugin 16:15:11 I've spent 2 hours configuring that damn plugin so it can target that arduino 16:16:37 -!- carado has joined. 16:16:39 http://marketplace.eclipse.org/sites/default/files/as_trade_DomainEditor.png 16:16:43 ^- it's pretty awesome 16:17:07 and as you can see, it's MUCH MORE readable than code . 16:19:19 That looks like the kind of graph that graphviz-dot makes. 16:19:50 I can't find any pictures with CIRO Models 16:20:08 It's a modelling standard invented by someone working at my school 16:20:16 of course, you don't find anything about it on google 16:20:24 so I assume it's not really used in the real world 16:20:52 -!- shikhin has quit (Ping timeout: 264 seconds). 16:21:22 at least for CIRO 16:21:25 there are some results for DESC 16:22:35 two results 16:22:37 both german :) 16:23:38 -!- shikhin has joined. 16:24:05 http://www.s-i.ch/fileadmin/daten/sigmo/DESC_Methode_v11.pdf 16:24:09 ^- that's the paper 16:28:30 http://static.squarespace.com/static/518f5d62e4b075248d6a3f90/t/526b7aeae4b0bc40704fad14/1382775549381/good-framework.jpg?format=1500w 16:28:35 I'm starting to like that website 16:31:03 -!- shikhin has quit (Ping timeout: 272 seconds). 16:33:26 -!- prooftechnique has quit. 16:35:36 -!- shikhin has joined. 16:35:36 -!- Slereahphone has quit (Ping timeout: 245 seconds). 16:36:13 the only difference between UML and not-UML is << >> anyway 16:45:09 -!- Slereahphone has joined. 16:50:01 -!- prooftechnique has joined. 16:51:56 -!- shikhin_ has joined. 16:51:57 -!- shikhin has quit (Ping timeout: 272 seconds). 16:55:43 -!- conehead has quit (Quit: Computer has gone to sleep.). 16:56:10 mroman: speaking of UML diagram generators. Just what I need. I wrote one once but turned out not to be so useful 16:56:59 determining the relationships between classes was not that easy it appears 16:57:44 I never spoke of such thing :) 16:57:49 but yeah 16:57:54 UML diagram generators are the way to go 16:58:03 write code, then generate UML class diagram 16:58:06 -!- Koen_ has joined. 16:58:07 unless you're a whuss 16:58:14 then you may do it the other way around ;) 16:58:25 I usually do it the other way around 16:58:32 AnotherTest: There's a working one for eclipse btw 16:58:38 I don't use eclipse 16:58:42 for Java at least 16:58:56 -!- nooodl has joined. 16:59:02 and I don't use java either :( 16:59:32 Then you must be a C++ guy 17:00:08 i confess 17:06:27 Representational State Transfer (REST) is an architectural style that abstracts the architectural elements within a distributed hypermedia system.[ 17:06:30 Ah... now I get it . 17:07:15 the only thing missing is within an architectural distributed hypermedia system 17:08:22 -!- Phantom_Hoover has joined. 17:12:02 -!- Slereahphone has quit (Quit: Colloquy for iPhone - http://colloquy.mobi). 17:15:35 -!- Slereahphone has joined. 17:17:31 -!- nisstyre has quit (Quit: Leaving). 17:19:20 well 17:19:30 20 days and I might know what my bachelor thesis is going to be about 17:19:45 I just pray it's not some erm, crm, erp crap 17:22:13 aren't you allowed to choose the subject of your thesis? 17:22:52 hell no 17:23:00 well 17:23:03 ok 17:23:11 Yes, you can choose your own thesis 17:23:16 if someone accepts it :) 17:23:47 usually companies can request students to do some stuff 17:24:06 they pay 2000$ for the school to anounce their stuff as a bachelor thesis 17:24:15 and then you choose one from that pool 17:24:19 ugh why doesn't vim come with python support on debian 17:24:24 ah I see 17:24:48 in what field is your thesis going to be? 17:24:58 or you can make a request for yourself to do something 17:25:10 if you have a good idea that gets accepted 17:25:33 that hell no was not directed at your question ;) 17:25:47 AnotherTest: That I don't know. 17:25:58 something with computers for sure ;) 17:26:39 but I can't tell you in which particular field of computer stuff 17:26:48 also... this is not a university bachelor. 17:27:56 so I'm not sure if it even counts as a bachelor in the US 17:28:03 I don't live in the US 17:28:13 Finland? 17:28:21 Finland is pretty present here 17:28:27 or Finnland? 17:28:35 -!- shikhin_ has quit (Ping timeout: 252 seconds). 17:28:39 Finnland. 17:28:58 Finn the Human 17:29:40 That's one weird looking language 17:29:57 you inflect verbs according to grammatical case? 17:30:48 taloksi 17:31:57 There's no word so small we wouldn't inflect it. 17:32:11 41 17:34:12 puhunet. 17:34:52 "You might speak", approximately. 17:35:27 Second-person singular present potential. 17:38:45 -!- ^v has joined. 17:39:20 -!- conehead has joined. 17:39:54 -!- augur has quit (Remote host closed the connection). 17:40:20 -!- augur has joined. 17:41:29 -!- conehead has quit (Remote host closed the connection). 17:41:44 -!- conehead has joined. 17:42:51 -!- augur_ has joined. 17:45:09 -!- augur has quit (Ping timeout: 272 seconds). 17:47:41 -!- augur_ has quit (Ping timeout: 272 seconds). 17:48:20 -!- Slereahphone has quit (Quit: Colloquy for iPhone - http://colloquy.mobi). 17:53:09 -!- Phantom_Hoover has quit (Ping timeout: 248 seconds). 18:05:15 -!- FreeFull has joined. 18:07:38 -!- Phantom_Hoover has joined. 18:12:10 Hello the people 18:12:59 Slereahello 18:18:06 We the Hello. 18:20:06 hi fizzie 18:24:31 -!- oerjan has joined. 18:28:33 -!- Taneb has joined. 18:39:33 does anyone here have a solution for file transfer between a linux box and a galaxy s4 that actually works 18:39:39 asking for actual tested solutions and not guesses 18:40:04 morse code 18:40:18 Analog modem via microphone/loudspeaker. 18:40:38 Semaphores 18:40:39 I like the implication that we've both actually tested these. 18:40:41 Smoke signals 18:40:46 i have a galaxy s3 but i'd just use dropbox 18:40:52 or email it to myself, just to piss everyone off 18:41:00 Tattooing the data on a courrier's head 18:41:29 kmc: "galaxy s4" is awfully specific 18:41:32 Bike: i hate the future 18:41:42 shachaf: yes well Samsung seems to use a different MTP stack from other android devices, or something 18:41:45 it works, aight 18:43:09 kmc: well with my moto x i can just click the little picture of a blue tooth and it works pretty good 18:43:14 ;_; 18:43:25 and with my galaxy nexus i can plug it in in the usb port and that works too 18:43:25 what software do you use on the linux side 18:43:29 have not tried anything else 18:43:43 shachaf: does your galaxy nexus do USB mass storage aka "the terrible thing that actually fucking works" 18:43:50 i think so 18:43:53 i don't remember for sure 18:44:18 i don't know what bluetooth software i use just the default usb thing on ubuntu 18:44:42 or rather goobuntu 18:44:58 s/usb/bluetooth/ 18:45:05 My Nexus 7 does not do USB mass storage, only MTP; and I've used... oh no, I forgot what I used! 18:45:24 i just click the clicky buttons until something happens 18:45:45 -!- oerjan has quit (Quit: Again). 18:46:11 (Also I've used that MTP thing, like, once. After that it's just been sftp over wifi.) 18:46:34 i might be mixing things up i haven't done it v. much 18:46:58 (I think it was that FUSE mtpfs thing.) 18:48:14 -!- Koen_ has quit (Quit: Koen_). 18:48:42 fizzie: which end is the sftp server? 18:50:09 -!- mrhmouse has joined. 18:55:11 -!- Phantom__Hoover has joined. 18:56:05 -!- Phantom_Hoover has quit (Ping timeout: 265 seconds). 18:56:23 i don't want to run a ssh server on my phone because i'll probably get owned 18:56:33 but i want to run rsync commands 18:56:38 i guess i could install rsync on the phone somehow 18:56:53 or just sign up for fucking dropbox 18:57:00 fucking fuckbox 18:57:40 kmc: The Linux end is the SFTP server, in my case. 18:58:35 kmc: I use ES File Manager, but there are plenty of solutions for syncing files on Android 18:58:43 most of which work over SSH 18:58:54 I think it was something like ES File Manager that I've used as the client on the Android side; that, and VX ConnectBot's "download file" feature, but it's not terribly user-interfacey. 18:59:23 ESFM has a wonderful interface these days.. it used to be difficult. 18:59:35 But I'm certain there are lighter apps for syncing over SSH 18:59:58 kmc: you could download the file over a local HTTP server on your phone? 19:02:02 that's a great solution, unless he wants to do so automatically 19:04:29 or unless I want to sync a big tree of files, which I do 19:04:37 and delete ones that don't exist on the server, too 19:05:23 -!- Bike has quit (Ping timeout: 252 seconds). 19:05:42 do you use a service like Drive? I'm guessing no, since you don't want Dropbox 19:06:46 I already know about Dropbox and Google Drive and HTTP and all of these things... 19:06:58 i don't need you all to brainstorm shitty solutions for me 19:07:05 do you run an Android device or an Apple device? 19:07:31 mrhmouse: you didn't even read my original question apparently 19:07:58 -!- Bike has joined. 19:08:00 I didn't log on until your comment "i don't want to run a ssh server on my phone because i'll probably get owned" 19:08:21 I'm gonna stop talking because I don't want to be a jerk to people who are honestly trying to help but fundamentally misunderstand the sort of inquiry I am making 19:09:42 srry 19:10:32 Oh, I have one of those phone things. It can make and receive calls. 19:11:20 mine just makes noises and receives odd looks 19:17:07 -!- Phantom__Hoover has quit (Ping timeout: 252 seconds). 19:23:39 -!- Phantom__Hoover has joined. 19:29:50 -!- prooftechnique has quit. 19:36:25 -!- MindlessDrone has quit (Quit: MindlessDrone). 20:06:23 -!- Bike has quit (Ping timeout: 272 seconds). 20:11:03 -!- Bike has joined. 20:14:36 -!- AnotherTest has quit (Quit: ZNC - http://znc.in). 20:16:37 -!- Taneb has quit (Ping timeout: 248 seconds). 20:31:27 -!- Phantom__Hoover has quit (Ping timeout: 272 seconds). 20:45:52 -!- Sprocklem has joined. 20:51:44 -!- augur has joined. 20:53:10 -!- augur_ has joined. 20:55:45 -!- Slereah has joined. 20:56:26 -!- Phantom_Hoover has joined. 20:56:26 -!- augur has quit (Ping timeout: 265 seconds). 20:59:51 -!- Slereah_ has quit (Ping timeout: 272 seconds). 21:00:03 -!- trout has quit (Quit: I found 1 in /dev/zero). 21:26:03 -!- zzo38 has joined. 21:26:29 -!- JM002 has joined. 21:26:39 Hello! 21:27:29 -!- JM002 has quit (Client Quit). 21:35:43 welp 21:55:24 "In which we put a v8 API on top of spidermonkey without futzing with a separate build system. Prep work for spidernode." 21:55:28 sometimes I run into scary things on the internet 21:58:40 -!- prooftechnique has joined. 22:00:07 -!- mrhmouse has quit (Read error: Connection reset by peer). 22:00:11 -!- Phantom_Hoover has quit (Ping timeout: 245 seconds). 22:01:22 -!- Phantom_Hoover has joined. 22:05:38 huh python has http://docs.python.org/2/library/string.html#template-strings in addition to % and .format() 22:05:56 and this metaprogram is possibly using all of them :< 22:06:13 -!- variable has joined. 22:06:31 kmc metaprogram he didn't like? 22:06:42 too easy 22:06:43 we're nearing that point yes 22:07:15 i like bugs 22:07:18 http://www.youtube.com/watch?v=M1nsOKBgmOs 22:13:44 -!- nisstyre has joined. 22:14:30 -!- sebbu2 has joined. 22:15:10 -!- sebbu2 has quit (Changing host). 22:15:10 -!- sebbu2 has joined. 22:15:23 -!- sebbu has quit (Ping timeout: 260 seconds). 22:15:24 -!- Taneb has joined. 22:27:18 -!- Phantom_Hoover has quit (Ping timeout: 265 seconds). 22:33:54 -!- Taneb has quit (Read error: Connection reset by peer). 22:35:35 -!- atehwa has quit (Ping timeout: 272 seconds). 22:38:27 -!- Taneb has joined. 22:40:03 -!- Phantom_Hoover has joined. 22:40:41 -!- Taneb has quit (Disconnected by services). 22:40:46 -!- Taneb has joined. 22:41:06 Oh man, I spent hours today getting people to help me get my laptop working 22:41:10 And now my desktop's playing up 22:43:15 Also, I think having someone on your gamejam team who is doing a PhD in video game artificial intelligence is pretty handy 22:44:12 depends what kind of PhD 22:44:38 little does taneb know that it's a phd in deliberately shitty AI 22:45:11 Bike, it's on Monte Carlo search trees with hidden information, I think 22:46:24 -!- Phantom_Hoover has quit (Ping timeout: 240 seconds). 22:48:16 -!- atehwa has joined. 22:52:07 "But USB devices were used to ferry malware cross a far greater air-gap: Russian astronauts had carried a virus on removable media to the International Space Station infecting machines there, Kaspersky said." 22:52:36 :D 22:52:43 more like lack of air gap (by which i mean: are you fucking serious) 23:01:48 -!- Phantom_Hoover has joined. 23:06:35 Taneb, there's obviously some kind of duality at play 23:07:31 Phantom_Hoover, yeah probably 23:07:34 How is the fortress 23:07:45 you're making me feel guilty 23:07:46 stop it 23:08:48 Oh, that reminds me 23:09:14 does it remind you of something else i should feel guilty about 23:09:20 if so: stop remembering 23:09:45 bill gates has his own URL shortener 23:09:46 b-gat.es 23:09:50 that is so money 23:10:18 Phantom_Hoover, no, it's something I should feel guilty about 23:10:33 kmc, looks like it's just an alias for bitly (or whatever the proper term is) 23:10:37 Taneb, continue remembering 23:11:03 sure 23:11:39 having novelty urls isn't all that money (were you not around for libc.soquest) 23:12:22 i wasn't 23:12:36 -!- carado has quit (Ping timeout: 252 seconds). 23:12:52 -!- nisstyre has quit (Quit: Leaving). 23:13:35 .soquest? 23:13:52 the quest for libc.so 23:14:02 oh 23:14:08 aren't two-letter tlds reserved 23:14:18 for like, ocular sudan. 23:14:41 (gregor wanted to buy it, it failed because someone was more money than him (gregor was very money at the time, though)) 23:15:21 isn't a tld like ten thousand fucks 23:15:45 Bike: Not the .so TLD, just the libc.so domain. 23:16:15 (This was when .so (Somalia) was having some sort of a thing.) 23:16:26 oh, it's somalia. durr 23:16:29 Involving possibly auctions or whatnot. 23:16:50 (I guess it's possible Gregor wanted to buy Somalia too? The domains probably come with it.) 23:17:01 i know a guy who lives in somaliland, i don't think it has its own tld though 23:17:10 they just use .dj like punks i imagine 23:17:38 i suppose he could've paid a band of mercenaries to take over the part of the country that hands out domains, at least 23:18:00 Bike, why does he live in somaliland 23:18:18 why was gregor so money 23:18:21 and not now? 23:18:30 because his dad's a fucking idiot (according to him) 23:18:57 isn't a tld like ten thousand fucks <-- depends how much you make from one fuck I guess 23:19:18 oh is gregor less money now? i was just referring to his general attitude at the time 23:19:45 i don't remember the amounts but there was some heated discussion over why you would spend that much on a novelty domain 23:20:02 whats a good suggestion for a simple-to-parse but relatively interesting proglang 23:20:12 There's not even any website at libc.so which makes the whole thing quite smurfy. (It's registered by a Marcel Meyer from levelsystems.de.) 23:20:13 APL 23:20:19 APL lol 23:20:20 eodermdrome (haha no) 23:20:25 the amount was $1k or something 23:20:43 actually... i guess eodermdrome's got pretty basic syntax 23:21:41 augur_, Real Fast Nora's Hair Salon 3: Shear Disaster Download 23:21:46 Easy to parse and easy to read! 23:24:42 augur_: scheme 23:24:45 Phantom_Hoover: In sum total I had $1,500 for it. 23:24:59 * Taneb --> bed 23:25:00 -!- Taneb has quit (Quit: Leaving). 23:25:16 esp. if you do what everyone does and pick a restricted subset of scheme that proves whatever point you want to make 23:30:57 -!- Koen_ has joined. 23:37:47 tan:| 23:37:51 oh whered he go 23:37:52 that bastard 23:38:03 kmc: scheme is easy to parse, but not rich enough 23:38:46 it basically has two syntactic constructs: , and (*) 23:40:04 well you asked for simple to parse. 23:40:17 not simple-to-parse-but-not-THAT-simple. 23:41:16 "but relatively interesting proglang" 23:41:16 :P 23:41:28 "interesting" includes semantics. 23:41:37 poppycock! 23:46:09 http://esolangs.org/wiki/Poppycock "This article is a stub, which means that it is not detailed enough and needs to be expanded. Please help us by adding some more information. Poppycock is a simple to parse, but not simple to parse but not THAT simple, but relatively interesting proglang." 23:55:50 augur_, still think eodermdrome fits that brief 23:56:41 yeah I didn't understand you meant "simple-to-parse but interesting syntax" 23:56:47 because syntax is boring ;P 23:56:55 (not really but kinda) 2013-11-09: 00:00:21 -!- oerjan has joined. 00:00:43 does "removing the syntax from a language" mean projection it into its computational class? 00:01:12 because only the semantics are left 00:01:40 projection into its paradigm i think 00:01:41 -!- Oj742 has joined. 00:01:52 like lambda calc->functional 00:02:01 projection onto some shit i just made up 00:05:44 Koen_, what do you... no, no it doesn't 00:07:14 poppycock syntax consists of two elements: poppies and cocks 00:07:31 ah, so it's like daisyworld but with sexual reproduction 00:11:29 Phantom_Hoover: well, I've always thought a "programming language" is just a set of "programs", and a program is just a couple (text, meaning) where 'text' is what you would write in the program file and 'meaning' is what it does (ie a function input -> output). now if you remove the syntax, that means you remove the 'text' component of programs; so the C program int main() {write(1, "Hello World!"", 12); return(0);} and the brainfuck p 00:11:29 ++++++++++[>+++++++>++++++++++>+++>+<<<<-]>++.>+.+++++++..+++.>++.<<+++++++++++++++.>.+++.------.--------.>+.>. become equivalent 00:12:24 Koen_, well the thing is that equivalence of programs is at least as hard as the halting problem 00:12:28 where's the return 0 in bf 00:12:35 feeling ripped off here 00:13:11 also what Bike said (IO is a complete nightmare to formalise) 00:13:32 Bike: yeah I was thinking the same thing when I wrote that :( 00:14:06 not even that. you could say that the "output" of the function described by BF is like, the value in the zeroth cell, but then you just declared a whole shitload of programs equivalent 00:14:10 like ais' proof that wolfram's turing machine is TC ran into some controversy because of the particulars of the IO 00:14:21 or you could combine all the cells in whatever way, but then what about other ways 00:16:07 Bike: yeah that's something I'm always frustrated about when people write a proof that a language is TC and then someone else uses reduction from that language to prove a second language tc 00:16:18 what? 00:16:24 "did the reduction and the initial proof used the same convention for IO?" 00:16:32 use 00:16:45 why would that matter 00:20:18 -!- Sgeo has joined. 00:24:03 Phantom_Hoover: youre horrible 00:24:47 augur_, well the actual parser wouldn't be that hard, i think! 00:25:27 perhaps i should say, it should be a one-dimensional language :P 00:25:44 all these crazy requirements! 00:26:02 what does one-dimensional mean? 00:26:12 is scheme one dimensional 00:26:13 Phantom_Hoover: like a normal language :P 00:26:33 yes! 00:26:40 why 00:26:47 i mean eodermdrome's graph representation is a 'one-dimensional' string if that's what you're complaining about 00:26:53 because newlines dont matter 00:27:05 -!- Sprocklem has quit (Ping timeout: 245 seconds). 00:27:07 so python is multidimensional. 00:27:17 yes, python is crucially >1d 00:27:18 how many dimensions does python have 00:27:23 who knows! 00:27:31 -!- Bike has left. 00:27:38 off to find out, i suppose 00:28:25 i don't... why are newlines so important 00:28:30 they're just another token 00:28:44 Phantom_Hoover: yes 00:29:01 but aligntment isnt 00:29:03 you could replace them with semicolons or whatever in the eodermdrome spec and it'd fit your apparent requirements 00:29:27 alignment doesn't matter in eodermdrome 00:29:56 -!- heroux has quit (Ping timeout: 246 seconds). 00:30:49 -!- heroux has joined. 00:33:42 -!- oerjan has set topic: The channel of the chimæric hellos | Magnus! | Koirammekokaan ei lennä? :( | https://dl.dropboxusercontent.com/u/2023808/wisdom.pdf | logs: http://codu.org/logs/_esoteric/ or http://tunes.org/~nef/logs/esoteric/. 00:33:52 shachaf: istr you wanted some norwegian in the topic. 00:34:14 magnus? 00:34:23 magnus! 00:34:40 oerjan: Is Tåsen some kind of a place? (It was in one of those videos.) 00:34:52 (first match today) 00:35:10 fizzie: i think it's possibly a suburb of Oslo? 00:35:43 Okay. But not a particularly special one? 00:35:55 more like neighborhood, it seems. 00:36:28 fizzie: well i cannot think of anything particularly special about it :P 00:36:47 but then i'm not too well acquainted with oslo. 00:38:26 the wikipedia article looks boring. 00:38:55 even the norwegian one. 00:39:02 * oerjan checks the turkish version 00:39:57 -!- Oj742 has quit (Quit: irc2go). 00:39:59 i'm sure it contains shocking news if i only could read it. oh wait, google.. 00:44:06 curiously, the turkish version mentions some WWII stuff the others don't. 00:44:23 (not _extremely_ shocking) 00:45:22 oerjan: help 00:45:29 shachaf: problem? 00:45:37 The nearest Norwegian speaker departed seconds ago. 00:45:51 I AM STILL HERE YOU INSENSITIVE CLOD 00:46:02 wait, did you kill him 00:46:12 no, he went home 00:46:16 good, good 00:47:31 google translate seems to be somewhat buggy with https. or maybe it's the turkish wikipedia. 00:48:28 i like bugs 00:49:53 -!- Phantom_Hoover has quit (Ping timeout: 265 seconds). 00:50:19 hm seems you do, i just got to the point in the logs. 00:51:44 * oerjan overloads his cheese quota on that youtube link. 01:02:27 -!- Koen_ has quit (Quit: Koen_). 01:06:05 -!- Phantom_Hoover has joined. 01:11:01 -!- conehead has quit (Quit: Computer has gone to sleep.). 01:30:09 "After all, the great advantage of BosonSampling is that, unlike with (say) factoring or quantum simulation, we don’t actually care which problem we’re solving!" 01:30:25 (new shtetl-optimized post) 01:33:07 -!- Bike has joined. 01:35:11 -!- ter2 has changed nick to tertu. 01:35:13 -!- Nisstyre-laptop has joined. 01:35:46 -!- Nisstyre-laptop has changed nick to nisstyre. 01:37:47 If there some MUD game that has a flag you can enable which makes it so that any other players can attack you as if you are a NPC, and kill you, earn all of your stuff and experience points and whatever (it is only one-way; to kill other players they have to set a flag too)? 01:39:02 you accidentally the question. 01:39:15 s/If/Is/ 01:41:39 oerjan: What does that mean? 01:42:12 what does what mean 01:42:53 "After all, the great advantage of BosonSampling is that... 01:45:28 -!- shikhin has joined. 01:45:43 zzo38: that they're just trying to make a physical experiment that has a proof that it's (probably, assuming generally believed computational complexity conjectures) hard to simulate with a classical computer, and don't really care what if anything it computes. 01:46:07 oerjan: Ah, OK. 01:50:15 -!- Phantom_Hoover has quit (Ping timeout: 244 seconds). 02:05:52 -!- nooodl has quit (Ping timeout: 264 seconds). 02:07:30 BosonSampling sounds like a hi-fi audio product 02:07:50 -!- yorick has quit (Remote host closed the connection). 02:09:23 -!- nooodl has joined. 02:12:12 -!- Phantom_Hoover has joined. 02:13:01 Jafet: different boses 02:13:06 "Boses belong to the Kayastha clan, a sub-caste of Kshatriyas (warriors/rulers) that originated from Kannauj, the capital of India during much of the classical period, and emerged in eastern India during the 11th century AD." 02:21:37 you know you regret reading a comment field when the commentors fail to distinguish cold and hot fushion. 02:22:00 -!- lexande has changed nick to lx. 02:23:20 -!- lx has changed nick to lexande. 02:45:15 how amazing that the android ssh server app keeps the server running after I tell it to shut down, and also is shit and doesn't work 02:45:27 who could possibly have predicted this outcome oh wait it was me 02:45:29 :( 02:48:43 -!- Phantom_Hoover has quit (Quit: Leaving). 02:57:38 :̀( 02:57:48 COMBINING SINGLE TEAR BELOW 02:58:04 unicode needs modular smileys 03:02:39 i distinctly see that as above 03:03:22 also in the logs, although there it's above a different character. 03:04:35 "It is well known that no model of computation characterizes exactly the set of total functions" can someone give this dummy (me) a reference better than "it's well known" 03:05:28 the halting problem? 03:05:56 oh i guess that works oops 03:07:06 well, no. rice's theorem means there's no procedure for picking out, say, primitive recursive functions, either, but that's still a model 03:18:17 it might depend on what is meant by "model of computation" 03:19:12 something i can fuck around with, preferably 03:19:34 i meant in the quote, thank you 03:19:44 well it has no context. 03:19:49 i mean obviously you can describe the set of total functions, but you can describe the primitive recursive functions, uh, "better" 03:21:06 oh, actually in context it gives primitive recursive functions and arithmetic functions as "models of computation" 03:22:23 well if we assume that you have (1) a string representation of "computations" (2) a total computable function for determining whether a string represents a computation (3) an interpreter for computation strings (on a TM or in whatever normal TC language) 03:22:41 then you might call that a model. 03:23:16 i guess (1) is a trivial point 03:23:22 is that an "and" or an "or" there 03:23:32 "and" 03:24:18 so you need a computable grammar, is what you're saying 03:24:55 yes. otherwise you could just define the grammar to be all the strings that happen to be total as functions. :D 03:25:15 well that makes some sense, thank 03:25:41 i'm still not sure that your quote is actually true for this definition though 03:26:12 what would a definition it's well-known-to-be-true for be, then 03:26:42 the missing point is a way to map total functions in some other representation into the model. 03:27:38 hm actually even then it might not be obvious, because it could do anything on non-total functions 03:28:24 no wait. that works, you could solve the halting problem if you could do that, i think. 03:28:52 er or wait 03:28:58 If you had a computable grammar for the total functions plus a map from turing machines to strings satisfying the grammar? 03:30:11 yes. although it doesn't need to do anything sensible if the turing machine doesn't represent a total function. 03:31:31 how would you solve the halting problem with that? i mean there are perfectly good functions that are only defined on total functions, like evaluation 03:31:43 i said "er or wait" 03:32:06 oh. i'm not enough of a mathematician to do things in my head and then just imply them. 03:32:16 :p 03:33:08 the thing here, is that this definition implies nothing about being able to compose these computations in any way (except by passing back via a TM) 03:33:31 yeah, that would be nice. 03:33:39 http://farm8.staticflickr.com/7051/6799351990_a716c10ae8_z.jpg 03:33:44 maybe throwing "also this is closed under composition" in there is too ugly 03:33:58 kmc: :3 03:34:06 well i don't mean just (.) composition, since that's still total. 03:34:28 there are other kinds of composition? 03:34:45 looping and stuff 03:35:04 general structured programming 03:35:52 however... what this does give you is a map from TMs to total functions which preserves the semantics of total functions. 03:35:52 hm i vaguely remember that being able to take variable powers of functions did... something 03:36:03 <^v> kmc, programming on macs is impossible 03:36:05 maybe just threw you up the gregzowieskbhch hierarchy 03:36:18 <^v> especialy with someone with add like me ;_; 03:36:21 ^v: what's the joke 03:36:32 Bike: well primitive recursion is something like that 03:37:24 oh. right. 03:38:56 oh wait, found a proof. 03:39:03 ! 03:40:34 to solve the halting problem: given a TM computation, make a new computation which calculates how many steps it takes. translate this. run the translation (which is total.) run the original TM for the number of steps returned. 03:41:14 How many steps it takes to halt? 03:41:18 yes. 03:41:56 if it doesn't halt, the translation will return some nonsense, but in either case the final check will reveal this. 03:42:44 clever 03:43:07 thanks 03:43:37 does that actually solve the halting problem, though? i mean there's no guarantee the "make a new computation" step is effectively computable is there 03:44:10 yes there is, these are TM computations so just "normal" program embedding. 03:44:59 like, the new computation runs the TM for one step, reports back if it halts, runs another step, etc.? 03:45:00 it's really just "add a step counter to the program" 03:45:30 that's not total is it 03:45:32 yes, and it reports the number of steps taken in total. 03:45:38 no, that's not total. 03:45:44 so how do you translate it 03:45:51 but the translation turns everything into something total. 03:46:14 because the other computation model has only total functions. 03:46:41 it just gives unrelated nonsense if the original wasn't total. 03:47:11 that's the assumption of how the translation works. 03:48:21 OK, wait, so let me lay this out. We have (a) the model of general computation, which is turing machines or whatever. (b) our total model, which is a language with a total "is the input in this language" function, and a total "run the input" function. (c) a partial computable function from (a) to (b) defined for all total (a). Right? Did I miss something? 03:48:34 from (a) to sentences of (b), or whatever 03:49:27 yeah. (c) should always halt itself, even if given something non-total, though. 03:50:20 OK, I think I get how your proof works, thanks for letting me indulge myself in description i guess 03:52:01 hm, can you use this to construct a rice violator for different types of b 03:52:31 argh 03:52:36 ? 03:52:45 brain overload :D 03:53:30 * oerjan is briefly pondering if (c) _really_ needs to always halt, given that it's functions it's translating, not single computations 03:54:18 i think requiring (c) to be total lets you violate rice's theorem. you do like you did except say "given a TM computation, make a new partial function which returns true when the TM fulfills [some ricey condition]" 03:54:19 because the functions have infinite domain, so (c) can't simply test all inputs before returning. 03:54:33 or... something 03:54:50 -!- nisstyre has quit (Remote host closed the connection). 03:55:00 -!- Slereah has quit (Ping timeout: 245 seconds). 03:55:10 Bike: well i thought most of that stuff is trivial once you can solve that halting problem 03:55:17 *the 03:55:18 probably 03:55:19 maybe for "models" it would be more natural to reverse c, though... 03:55:51 -!- Slereah has joined. 03:57:09 like there's obviously a total, computable map from sentences describing partial recursive functions or [total functional language du jour] to turing machines and you don't care about the other direction /that/ much 03:57:21 or maybe you do. i'm tired 03:58:12 well if you had no map the other way your language could be as total as you wanted but you'd never be able to translate any _given_ total function to it... 03:59:10 that kind of seems okay to me? when i define a program i can use some non-TM-at-all model, like arithmetic or something 03:59:11 you would know each string computes a total function but you might have no idea of which one 04:01:08 are you still trying to figure out the original quote 04:01:16 iunno 04:01:26 right now i'm wondering how i would prove the program i work on at work is total 04:01:48 translate it to agda duh 04:01:55 obviously 04:01:59 it's probably not hth 04:02:44 i think it is actually 04:03:22 well the halting problem has been solved for Bike already 04:03:26 it's called brakes 04:04:26 think you only need "loop [easy term] number of times" and "return first element in finite list that equals [easy term]" where easy terms are just parameters and floating point arithmetic on them 04:05:25 floating point arithmetic /!\ 04:05:49 i'm not exactly working on a compiler aight 04:09:30 loop NAN number of times 04:09:57 throw modular arithmetic in there if you must >: 04:10:17 loop NAN `mod` 0 number of times 04:10:24 yes 04:10:40 :t fmod 04:10:41 Not in scope: `fmod' 04:10:41 Perhaps you meant `mod' (imported from GHC.Real) 04:10:51 fmodular arithmetic 04:10:56 i'm sure it's somehwere 04:11:07 how about modular arithmetic only and we just do floating point on top of that, jerk 04:11:43 who's the real jerk here 04:11:56 me probably 04:12:22 > [0.. 0/0] 04:12:23 [] 04:12:27 > 0/0 04:12:29 NaN 04:12:52 > [0/0 .. 1/0] 04:12:53 [] 04:13:02 so uncooperative 04:13:03 > [-1/0 .. 1/0] 04:13:04 [-Infinity,-Infinity,-Infinity,-Infinity,-Infinity,-Infinity,-Infinity,-Inf... 04:13:18 > [-1/0 .. 0/0] 04:13:20 [] 04:13:21 :( 04:13:30 > [-1/0, -1/0 .. 0/0] 04:13:32 [] 04:13:50 > [-1/0, 0/0 .. 1/0] 04:13:51 [] 04:14:33 > [1,0 .. 0/0] 04:14:35 [] 04:15:02 > 0/0 < 1/0 04:15:04 False 04:15:08 > 0/0 > 1/0 04:15:10 False 04:15:56 > 1/0 - 0/0 04:15:57 NaN 04:16:08 enlightening 04:17:01 you know that writing style where you have lots of text and you bold lots of sentences in it 04:17:20 never heard of it 04:17:30 it's the worst :'( 04:17:52 like bad comics? 04:19:17 no, that's a separate thing 04:19:30 i really don't get that 04:19:40 what does all that bolding in those comics even mean 04:20:06 -!- conehead has joined. 04:21:18 -!- ^v has quit (Quit: http://i.imgur.com/MHuW96t.gif). 04:22:38 ¯\_(ツ)_/¯ 04:23:03 -!- nisstyre has joined. 04:26:52 -!- ^v has joined. 04:34:14 -!- nooodl has quit (Quit: Ik ga weg). 05:04:19 -!- Froox has joined. 05:04:52 -!- ^v has quit (Quit: http://i.imgur.com/MHuW96t.gif). 05:06:03 I managed to send a message to a channel in ifMUD while not connected. As far as I know, this wasn't intended to be possible. 05:09:23 how did you do it? 05:09:55 -!- variable- has joined. 05:11:27 -!- Frooxius has quit (Read error: Connection reset by peer). 05:11:28 -!- ggherdov has quit (Ping timeout: 248 seconds). 05:11:28 -!- variable has quit (Ping timeout: 248 seconds). 05:11:28 -!- fungot has quit (Ping timeout: 248 seconds). 05:17:23 -!- shikhin has quit (Ping timeout: 272 seconds). 05:18:02 -!- variable- has quit (Changing host). 05:18:02 -!- variable- has joined. 05:20:09 -!- ggherdov has joined. 05:20:59 -!- contrapumpkin has joined. 05:21:26 -!- copumpkin has quit (Ping timeout: 246 seconds). 05:29:59 -!- shikhin has joined. 05:31:00 kmc: If you know ifMUD, try to figure it out... (I made up a channel specifically for testing this so as not to annoy people) 05:33:14 zzo38: I don't know ifMUD. 05:33:47 shachaf: I didn't expect you to. 05:35:02 -!- shikhin has quit (Ping timeout: 264 seconds). 05:39:10 The plug for my clock keeps falling off! 05:39:34 is the time leaking out 05:39:47 it's time for a new clock 05:40:07 No, it isn't the clock that is defective; it is the position of the bed. 05:41:02 or the socket 05:41:07 -!- variable- has changed nick to variable. 05:41:19 Yes, it is also the position of the socket. 05:42:42 -!- shikhin has joined. 05:42:42 Oh, wait, "clock" doesn't mean "watch". 05:42:48 I was sure zzo38 meant a watch. 05:43:22 In this case it is not a watch; it is a digital alarm clock. 05:55:46 -!- conehead has quit (Quit: Computer has gone to sleep.). 05:57:35 the bed was the clue 05:57:57 correct 05:58:11 it' sbeen years since i confused clock and watch wow 05:58:17 c razy man 05:58:32 help 05:58:55 what is a gender-neutral phrase that has similar connotations to "whoa, dude" 06:09:41 -!- shikhin_ has joined. 06:11:55 -!- shikhin__ has joined. 06:12:29 -!- shikhin has quit (Ping timeout: 272 seconds). 06:14:38 -!- shikhin_ has quit (Ping timeout: 264 seconds). 06:15:31 'holy fucking shit' 06:17:34 -!- shikhin_ has joined. 06:19:57 -!- shikhin__ has quit (Ping timeout: 244 seconds). 06:21:31 -!- nisstyre has quit (Quit: Leaving). 06:24:28 -!- shikhin__ has joined. 06:24:31 -!- shikhin_ has quit (Ping timeout: 272 seconds). 06:28:24 -!- shikhin_ has joined. 06:31:33 -!- shikhin__ has quit (Ping timeout: 248 seconds). 06:32:20 -!- shikhin__ has joined. 06:35:38 -!- shikhin_ has quit (Ping timeout: 264 seconds). 06:36:23 shachaf: after more than a year those people finally changed the description of their users from "craftsmen" to "software engineers" 06:36:40 -!- shikhin has joined. 06:37:36 I assume this was a long painful process that involved buying a suit and burning a pile of thinkgeek shirts in a big bonfire 06:37:54 which people 06:38:02 http://javascriptmvc.com/ 06:38:08 oh 06:38:23 it's not a celebrating software engineership thing 06:38:35 almost 06:39:28 -!- shikhin__ has quit (Ping timeout: 264 seconds). 06:39:42 -!- shikhin_ has joined. 06:40:57 I made up a "Critical Vulnerability" flaw for Dungeons&Dragons game: Any damage you take from critical hits that is multiplied due to the critical hit is doubled again (so x5 becomes x10 and so on). If someone try to hit you with a damaging attack and roll a natural 1, you take 1 point of damage anyways. 06:41:57 zzo38: Are those two separate clauses of the flaw? 06:42:55 -!- shikhin has quit (Ping timeout: 245 seconds). 06:42:59 shachaf: They are two separate sentences; I don't know if you would consider them two separate "clauses" or not, or if that is important. 06:45:27 It's not. 06:45:40 The first one is bad and the second one is good? 06:47:02 -!- shikhin_ has quit (Ping timeout: 264 seconds). 06:48:44 -!- shikhin_ has joined. 06:50:56 i think they're both bad, if someone hits a 1 they usually miss entirely or worse? 06:52:32 oerjan: Yes that is correct; they usually miss entirely (or sometimes hit themself). 06:54:09 -!- shikhin_ has quit (Ping timeout: 252 seconds). 06:54:29 -!- shikhin__ has joined. 06:59:05 -!- carado has joined. 07:01:10 http://www.theonion.com/articles/giant-burrito-to-solve-all-of-area-mans-problems-f,34479/ 07:03:51 confirm 07:05:08 kmc: what about beer/bonghits 07:05:25 I think that's qdoba 07:05:42 oh it says that in the first sentence :( 07:05:54 my burrito detective skills are not needed here :( 07:07:20 -!- shikhin_ has joined. 07:08:11 have you been to costena.com yet 07:10:26 -!- shikhin__ has quit (Ping timeout: 264 seconds). 07:15:22 -!- shikhin__ has joined. 07:17:16 -!- shikhin_ has quit (Ping timeout: 264 seconds). 07:18:02 no! 07:18:07 will they sell me the World's Largest Burrito 07:18:32 probably not 07:18:49 i think someone else got the record now anyway 07:19:15 are the normal size burritos good 07:19:16 but they have good burritos 07:19:39 that's kind of far from everything 07:20:49 well, it's kind of near google 07:20:57 true 07:21:02 that's not a real place for me 07:21:03 and i think it's near evan's house? 07:21:07 oh 07:21:11 i don't actually know where evan lives 07:21:19 didn't we go there once 07:21:24 or am i mixing people up 07:21:24 yes but in a car 07:21:26 true 07:21:33 at night 07:21:37 so it might as well have been a teleporter 07:21:49 I actually walked from his house to Caltrain once but it was before I had any kind of map of the area 07:21:51 since -ito is a diminutive suffix, the world's largest burrito should be a burro. 07:21:57 true~ 07:22:15 oh, they will sell "Burrito Gigante: The 4-foot long burrito" 07:22:16 -!- shikhin__ has quit (Ping timeout: 245 seconds). 07:22:22 "Big enough for 12-16 people for only $60.00!" 07:22:36 oerjan: there's a taquería chain around here named El Faro, and another named El Farolito 07:22:38 a bargain 07:22:45 the founder of the latter is the son of the founder of the former, or something 07:23:45 Far & Sønn 07:23:57 also it's moving according to the website 07:24:00 i wonder where they'll move 07:24:15 google won't translate "taquería" into icelandic :/ 07:28:06 well icelandic wikipedia doesn't even have a taco article 07:28:09 http://is.wikipedia.org/wiki/Tortilla 07:30:06 there are also burritos at google but they do not compare 07:31:01 i heard that in arizona they call them "burros" can you confirm 07:32:12 no but I can go on a fact finding mission 07:32:16 i'll need an advance and a per diem 07:32:35 how much 07:32:47 tortilla þýðir „lítil kaka“ á spænsku 07:33:16 today i wondered how hard it is to make tortillas at home 07:35:28 shachaf: also the print version of The Onion is ceasing publication :( 07:35:48 what? 07:35:48 i heard :'( 07:35:49 dammit. 07:35:58 `rwlcome tertu 07:36:03 ​/home/hackbot/hackbot.hg/multibot_cmds/lib/limits: line 5: exec: rwlcome: not found 07:36:15 `welcome tertu 07:36:18 tertu: Welcome to the international hub for esoteric programming language design and deployment! For more information, check out our wiki: . (For the other kind of esoterica, try #esoteric on irc.dal.net.) 07:37:18 you can't do that 07:37:29 `run echo 'welcome "$@" | sed 's/aeiou//'" > bin/wlcm; chmod +x bin/wlcm 07:37:31 bash: -c: line 0: unexpected EOF while looking for matching `'' \ bash: -c: line 1: syntax error: unexpected end of file 07:38:05 `run echo 'welcome "$@" | sed '\'s/aeiou//\'' > bin/wlcm; chmod +x bin/wlcm 07:38:07 bash: -c: line 0: unexpected EOF while looking for matching `'' \ bash: -c: line 1: syntax error: unexpected end of file 07:38:14 `run echo 'welcome "$@" | sed '\'s/aeiou//\' > bin/wlcm; chmod +x bin/wlcm 07:38:19 No output. 07:38:19 `wlcm shachaf 07:38:22 shachaf: Welcome to the international hub for esoteric programming language design and deployment! For more information, check out our wiki: . (For the other kind of esoterica, try #esoteric on irc.dal.net.) 07:38:42 wow i'm so bad at this :'( 07:38:44 `revert 07:38:46 Done. 07:39:22 what is it missing other than g 07:40:05 oh, wait 07:40:16 i switched from tr to sed and did it completely badly 07:40:32 `run echo 'welcome "$@" | sed '\'s/[aeiou]//ig\' > bin/wlcm; chmod +x bin/wlcm 07:40:34 No output. 07:40:35 `wlcm shachaf 07:40:37 shchf: Wlcm t th ntrntnl hb fr strc prgrmmng lngg dsgn nd dplymnt! Fr mr nfrmtn, chck t r wk: . (Fr th thr knd f strc, try #strc n rc.dl.nt.) 07:41:33 ths s gttng t f hnd 07:42:25 `eoe oerjan 07:42:50 `echo hi 07:42:51 hi 07:43:04 `unicode > ` 07:43:06 Unknown character. 07:43:17 `ord > ` 07:43:18 62 32 96 07:43:29 `cat bin/eoe 07:43:31 cat: bin/eoe: No such file or directory 07:43:35 `which eoe 07:43:37 No output. 07:43:47 my method was so low tech oerjan doesn't even suspect 07:43:48 terrifying 07:46:04 `eoe like this? 07:46:32 except it seems almost impossible to verify if my guess is correct. 07:46:43 "tr -d would've been simpler" hth 07:47:02 oerjan: guess? just look at the logs 07:47:04 (yes) 07:47:18 fizzie: yes but i remembered something about tr being bad at unicode or something 07:47:31 shachaf: um my browser has a disturbing tendency to ignore control characters. 07:47:46 oerjan: curl http://codu.org/logs/_esoteric/2013-11-09-raw.txt | xxd | less 07:47:53 That would've been an issue only if you wanted to delete a non-ASCII character. 07:48:08 fizzie: what about when we convert everything to utf-16 07:48:31 Oh no, are we converting everything to UTF-16? :( 07:48:43 No. 07:49:02 Scary thought. 07:50:23 well i guessed correctly. 08:04:59 Do you like "Where is my keys" soup? 08:05:35 What's that? 08:06:07 It is OK if tr is bad at Unicode; that is why UTF-8 is design the way it is, that you can delete non-ASCII characters in a search/replace even if the program is otherwise ASCII only. 08:06:11 shachaf: I don't know. 08:06:59 zzo38: Why did you bring it up? 08:07:41 One of the levels in a computer game I play today is titled: "Where is my keys" soup 08:07:43 zzo38: you can't really delete specific UTF-8 characters with tr, can you? 08:08:05 kmc: Probably not with tr, but with other programs such as sed you probably can, even if it is the ASCII version of sed. 08:08:24 The ASCII version of sed operates on seven-bit characters. 08:10:06 shachaf: Yes, but just one extended to 8-bits is good enough then; you don't need Unicode or anything; it works on any 8-bit character set which is compatible with ASCII, and UTF-8 has the properties needed for it to work (Shift-JIS doesn't). 08:10:25 Therefore the same program can be used for UTF-8, CP437, and other character encodings. 08:19:46 -!- prooftechnique has quit (Ping timeout: 245 seconds). 08:21:12 For some values of "works"; you can replace single characters with the s/// command, but e.g. '.' won't necessarily match a single character, and the y/// command is not going to work any better. 08:21:47 all we need is character classes for "UTF-8 start byte" and "UTF-8 continuation byte" 08:22:01 quick somebody write a UTF-8 to UTF-16 decoder in sed 08:22:04 using Lies And Trickery 08:22:31 re-coder? whatever 08:22:47 kmc: Best is if you are allowed to design your own character classes; it would be useful for other things too 08:40:08 kmc: transcoder is the term? 08:45:57 -!- oerjan has quit (Quit: leaving). 08:47:18 -!- AnotherTest has joined. 08:49:14 Well, I did recently write one in C, that does a lot of other things too, not only UTF-8 and UTF-16, but also CESU-8, VLQ, LEB128, Modified UTF-8, linebreak conversion, byteswap, and some other things. Most of these are just an emergent property of the features of the program, though. 08:49:39 (It doesn't actually have support for CESU-8 built-in but using a pipe you can easily convert to/from CESU-8) 08:53:56 CESU-8, VLQ, LEB128, UVB-76, MDZhB 08:53:58 -!- AnotherTest has quit (Quit: ZNC - http://znc.in). 08:54:10 What's Modified UTF-8? 08:54:19 obviosuly it should be abbreviated ΜTF-8 08:54:24 shachaf: Using overlong encoding for zero 08:54:33 Did you invent that? 08:54:45 (Mainly for compatibility with C programs, and no I did not invent that.) 08:55:18 Are you going to finish Potion of Confusing? 08:55:33 I don't know. 08:55:42 You should make a sequel called Potion of Doesn't Make Sense. 08:56:33 OK, well, it is all public domain you can do what you want with it. 08:56:55 (The runtime engine is GPL, but the world file is public domain.) 08:57:36 kmc: What is UVB-76, MDZhB? 08:57:58 numbers stations 08:58:27 zzo38: and what of copyright jurisdictions where works can't be voluntarily placed into the public domain? 08:58:41 kmc: There is CC0 and stuff like that. 08:59:14 yes 08:59:40 kmc: Time to apply some http://ncatlab.org/nlab/show/negative+thinking ! 09:00:02 head explode 09:00:48 -!- AnotherTest has joined. 09:03:50 shachaf: I will make the additional levels of Potion of Confusing as I have the time and can think of what levels to make! I do not have an intention to make a sequel, but if you like this kind of game you can try, of course. 09:11:26 -!- AnotherTest has quit (Ping timeout: 245 seconds). 09:12:19 -!- AnotherTest has joined. 09:29:38 -!- tertu has quit (Ping timeout: 264 seconds). 09:36:17 -!- Deewiant has quit (Quit: Uudelleensaapas). 09:39:17 -!- Deewiant has joined. 09:41:53 -!- shikhin has joined. 09:44:13 -!- Froox has quit (Quit: *bubbles away*). 09:44:44 -!- Frooxius has joined. 09:46:15 -!- shikhin has quit (Ping timeout: 245 seconds). 10:10:04 -!- zzo38 has quit (Quit: zzo38). 10:40:05 -!- sebbu2 has quit (Quit: schedule outage). 10:46:19 -!- Taneb has joined. 10:54:39 -!- Taneb has quit (Quit: Leaving). 11:36:28 -!- AnotherTest has quit (Ping timeout: 264 seconds). 11:45:38 -!- Phantom_Hoover has joined. 11:47:21 -!- Taneb has joined. 12:02:17 -!- yorick has joined. 12:13:21 -!- Phantom_Hoover has quit (Ping timeout: 244 seconds). 12:15:43 -!- Taneb has quit (Ping timeout: 265 seconds). 12:16:30 -!- Phantom_Hoover has joined. 12:16:40 -!- Koen_ has joined. 12:54:22 -!- ais523 has joined. 12:54:26 -!- Taneb has joined. 12:55:42 @ping 12:55:42 pong 12:55:57 has anyone of you guys experience with gtk? 12:56:11 @bling 12:56:12 pong 12:56:23 Aw, no blong. 12:57:39 !bfjoust preparation http://nethack4.org/esolangs/preparation.bj 12:57:55 ​Score for ais523_preparation: 41.7 12:58:35 not bad 12:58:41 the scoring system is not so kind to it 12:58:48 it gets lots of close wins 12:59:42 I'd like to get that thing to top the hill 12:59:47 perhaps it needs oodles of tweaking 12:59:57 Somehow I don't think you get points for "almost winning" in actual jousting either. 13:00:01 (although it's not going to beat space_hotel no matter what I do, with its current strategy) 13:00:06 fizzie: no, it wins almost every matchup 13:00:11 just only by a small margin 13:00:21 -!- Taneb has quit (Ping timeout: 248 seconds). 13:00:31 it's only losing three atm 13:00:39 Oh, that way around. 13:03:22 lol .bj 13:10:33 -!- lambdabot has quit (Quit: requested). 13:17:13 -!- lambdabot has joined. 13:19:05 -!- carado has quit (Read error: Connection reset by peer). 13:22:05 -!- carado has joined. 13:22:20 -!- Slereahphone has joined. 13:27:45 -!- Slereahphone has quit (Ping timeout: 244 seconds). 13:28:50 ais523: the word you want is 'barely' 13:31:44 -!- Slereahphone has joined. 13:38:43 -!- Slereahphone has quit (Ping timeout: 272 seconds). 13:43:14 hmm 13:43:35 instead of using a rich language, i experimented with a very simple language -- the language of balanced parens -- and got an interesting result 13:43:39 hmm hmm 13:47:43 Does it count as "simple" if it's not even regular? 13:48:39 for my purposes it does! 13:48:50 infact, CF+ is probably exactly ideal 13:48:56 regular languages are _too_ simple! 13:49:12 fizzie: well it's pretty much the simplest PDA around 13:58:55 glib seriously has a threading library 13:59:03 but no syncronization 13:59:53 its wonderful how a few months worth of ideas can crumble in a few minutes of computational experimenting :) 14:06:30 -!- Frooxius has quit (Read error: Connection reset by peer). 14:06:31 -!- Froox has joined. 14:21:43 -!- contrapumpkin has changed nick to copumpkin. 14:35:17 -!- Phantom_Hoover has quit (Ping timeout: 248 seconds). 14:40:20 mroman: https://developer.gnome.org/glib/unstable/glib-Threads.html lists at least 6 synchronization thingies you can use? 14:42:56 -!- lambdabot has quit (Quit: requested). 14:47:50 -!- lambdabot has joined. 14:48:52 -!- nooodl has joined. 14:49:39 -!- Phantom_Hoover has joined. 14:57:24 -!- lambdabot has quit (Quit: requested). 15:01:23 -!- lambdabot has joined. 15:02:04 -!- mrhmouse has joined. 15:08:06 http://www.youtube.com/watch?v=sihyVOULtA8 15:19:46 -!- Slereahphone has joined. 15:19:50 -!- shikhin has joined. 15:21:39 -!- mrhmouse has quit (Read error: No route to host). 15:25:31 -!- mrhmouse has joined. 15:28:31 -!- yorick has quit (Remote host closed the connection). 15:32:20 -!- Slereahphone has quit (Quit: Colloquy for iPhone - http://colloquy.mobi). 15:34:53 -!- Phantom_Hoover has quit (Ping timeout: 240 seconds). 15:35:04 -!- sebbu has joined. 15:35:04 -!- sebbu has quit (Changing host). 15:35:04 -!- sebbu has joined. 15:49:32 -!- Phantom_Hoover has joined. 15:56:57 -!- Taneb has joined. 15:59:18 -!- MindlessDrone has joined. 16:05:54 -!- conehead has joined. 16:06:06 -!- conehead has quit (Remote host closed the connection). 16:06:23 -!- conehead has joined. 16:07:44 Hi 16:08:00 hi 16:11:45 -!- fungot has joined. 16:11:48 Hi 16:16:45 ho 16:22:31 fungot 16:22:31 Jafet: ummmm....... mmmm...... 16:23:12 `relcome fungot 16:23:13 Jafet: and tusho, or is this supposed to impress?" at http://paste.lisp.org/ display/ fnord, 16:23:17 ​fungot: Welcome to the international hub for esoteric programming language design and deployment! For more information, check out our wiki: . (For the other kind of esoterica, try #esoteric on irc.dal.net.) 16:24:21 HackEgo could teach fungot a thing or two about writing URLs. 16:24:22 Jafet: china is cool! wow! what a dull boy 16:25:22 ^style 16:25:22 Available: agora alice c64 ct darwin discworld enron europarl ff7 fisher fungot homestuck ic irc* iwcs jargon lovecraft nethack pa qwantz sms speeches ss wp youtube 16:34:10 -!- Phantom_Hoover has quit (Ping timeout: 245 seconds). 16:49:48 -!- Phantom_Hoover has joined. 17:00:10 -!- tertu has joined. 17:00:50 -!- zzo38 has joined. 17:10:03 -!- Froo has joined. 17:10:04 -!- Froox has quit (Read error: Connection reset by peer). 17:10:53 -!- Taneb has quit (Ping timeout: 272 seconds). 17:12:54 -!- Froo has quit (Client Quit). 17:17:39 Jafet: I could teach fungot a thing or two about that too, but I somehow never seem to manage to. 17:17:40 fizzie: what language is str? i get conflicting opinions about threads and multi-threading as a programming paradigm. how does one cause a function to something, though 17:18:12 These are deep philosophical waters. How *does* one cause a function to something, indeed. 17:19:29 -!- Frooxius has joined. 17:24:30 -!- Slereahphone has joined. 17:28:07 -!- Taneb has joined. 17:28:44 wow, the notation f : X → Y for functions apparently only came into use in the forties: http://mathoverflow.net/a/59478 17:32:57 So, it's younger than lambda calculus? 17:33:49 Phantom_Hoover: http://jeff560.tripod.com/mathsym.html 17:33:52 I... guess, yeah 17:36:19 -!- ^v has joined. 17:45:05 -!- Phantom_Hoover has quit (Ping timeout: 272 seconds). 17:50:37 -!- nisstyre has joined. 17:55:23 -!- Taneb has quit (Ping timeout: 244 seconds). 17:58:01 -!- ahvqae78q9rfgphy has joined. 17:59:29 YOU MAY BE WATCHED 17:59:30 WARNING WARNING WARNING, WARNING WARNING 17:59:30 WARNING WARNING WARNING, WARNING WARNING 17:59:30 WARNING WARNING WARNING, WARNING WARNING 17:59:30 WARNING WARNING WARNING, WARNING WARNING 17:59:30 WARNING WARNING WARNING, WARNING WARNING 17:59:30 YOU MAYWATCHED 17:59:30 YOU MAY BE WATCHED 17:59:31 YOU MAY BE WATCHED 17:59:31 ) 17:59:32 Do usa&Israel use chat &facebook 2 spy?!?!?!? 17:59:32 Do they record &analyse everything we type?!?!?!? 17:59:33 Do usa&israel use chat&social communication prog(facebook&twitter) to collect informations,,,,can we call that spying!!!! 17:59:33 هل تستخدم امريكاواسرئيل الشات والفيس بوك للتجسس!؟!؟!؟!؟!؟!؟! 17:59:51 -!- Phantom_Hoover has joined. 18:00:01 -!- ahvqae78q9rfgphy has quit (Killed (idoru (Spam is off topic on freenode.))). 18:00:50 -!- shikhin has quit (Ping timeout: 245 seconds). 18:07:55 -!- Slereahphone has quit (Quit: Colloquy for iPhone - http://colloquy.mobi). 18:16:54 ... 18:17:33 ::: 18:18:01 got k-lined, at least 18:18:06 I wonder why it chose this channel to spam? 18:18:24 Because it's the best channel. 18:18:34 who uses facebook anyway 18:18:54 1.15 billion people. 18:18:54 because all the other channels are puppets of israel 18:20:15 Just because they got k-lined doesn't necessarily mean we are not going to be watched. 18:20:42 you no what? watch THIS 18:20:45 * myname exposes 18:21:37 -!- int-e has joined. 18:29:53 -!- ^v has quit (Remote host closed the connection). 18:30:42 -!- AnotherTest has joined. 18:33:39 Hi 18:34:01 hi 18:34:10 jennifer 18:53:50 -!- ais523 has changed nick to ais523\unfoog. 18:55:26 -!- Phantom_Hoover has quit (Ping timeout: 264 seconds). 19:00:39 -!- ^v has joined. 19:01:09 -!- Sprocklem has joined. 19:02:52 -!- ^v has quit (Client Quit). 19:05:51 -!- mrhmouse has quit (Quit: Leaving.). 19:06:02 -!- ^v has joined. 19:07:32 -!- Phantom_Hoover has joined. 19:08:18 What does 'confess' do in Perl? 19:11:40 http://stackoverflow.com/questions/7617852/whats-the-difference-between-carp-croak-cluck-confess-and-verbose-options 19:12:25 zzo38: error with stacktrace, IIRC; it's not part of the language itself but of a commonly used library 19:26:36 oh no. I'm watched. I'm so shocked right now. 19:26:50 also I might be maywatched 19:26:55 that's probably a typo for baywatched. 19:42:00 ais523: ifMUD seems to call confess when SIGUSR2 is received. 19:44:16 -!- MindlessDrone has quit (Quit: MindlessDrone). 20:17:55 Sounds like a debugging aid. 20:36:05 -!- Taneb has joined. 20:52:28 -!- ^v has quit (Quit: Ping timeout: 1337 seconds). 21:14:57 -!- nooodl has quit (Read error: Connection reset by peer). 21:41:52 -!- yorick has joined. 21:44:21 -!- Slereah has quit (Ping timeout: 245 seconds). 21:44:50 -!- Slereah has joined. 21:50:35 -!- Ghoul_ has quit. 21:53:52 -!- Phantom_Hoover has quit (Ping timeout: 264 seconds). 22:04:39 sup 22:05:11 Hey 22:05:59 what happened here today 22:06:19 I submitted a BF Joust program I spent a couple of days working on 22:06:31 it doesn't do too well in HackEgo's scoring system, though 22:07:08 yes i saw that earlier 22:07:12 I'm in a gamejam 22:07:16 but didnt look at it 22:07:20 what does it do 22:07:56 -!- Phantom_Hoover has joined. 22:08:25 also if it doesnt do good in this system because it doesnt crushingly defeat enough programs, it would do even more poorly in the fixed-point system 22:16:23 -!- ^v has joined. 22:18:09 i want to modify space_hotel to be able to beat 73ef6r7dye6_david 22:19:21 quintopia: I think it beats omnipotence in fixed-point 22:20:06 omnipotence scores 801 (wins - losses against all programs on all tape lengths); preparation scores 911 22:20:15 do you have a fixed point scorer to test on? 22:20:29 yea 22:20:36 *yeah 22:20:36 hmm 22:20:44 although, hmm 22:20:46 well how does it work mannnn 22:20:53 it's a crazily complex defence program 22:20:59 you know those things always take ages to explain 22:21:09 is it documented in code 22:21:16 but the main codepaths are, on tapes 17 and shorter, it detects the opponent's rule of 9 and aims straight for their flag 22:21:26 on 18 and longer, it tries to lock them on the ninth cell and then use the time to set up decoys 22:21:27 then outraces 22:21:33 and yes, there are plenty of comments in the program itself 22:22:15 !bfjoust this_sort_of_thing_is_done_so_often_it_doesnt_do_so_well_nowadays < 22:22:17 ​Score for ais523_unfoog_this_sort_of_thing_is_done_so_often_it_doesnt_do_so_well_nowadays: 0.0 22:22:24 so it's one of those that's like "wait for the opponent to do their decoy build so you can tell where their flag is"? 22:22:26 !bfjoust this_sort_of_thing >>>>(+)*20(<(+)*90)*4(>)*8(>[(+)*20[-]])*21 22:22:27 -!- carado has quit (Ping timeout: 252 seconds). 22:22:28 ​Score for ais523_unfoog_this_sort_of_thing: 21.2 22:22:32 let me rename that, it keeps breaking the table layout 22:22:36 what the lag 22:22:36 oh, need to change nick 22:22:39 So, if I made something that set up defence for one less than I could safely, it would beat that on some tapes? 22:22:43 !bfjoust this_sort_of_thing < 22:22:46 -!- ais523\unfoog has changed nick to ais523. 22:22:46 ​Score for ais523_unfoog_this_sort_of_thing: 0.0 22:22:52 !bfjoust this_sort_of_thing_is_done_so_often_it_doesnt_do_so_well_nowadays < 22:22:55 ​Score for ais523_this_sort_of_thing_is_done_so_often_it_doesnt_do_so_well_nowadays: 0.0 22:22:56 !bfjoust this_sort_of_thing >>>>(+)*20(<(+)*90)*4(>)*8(>[(+)*20[-]])*21 22:22:59 ​Score for ais523_this_sort_of_thing: 22.2 22:23:02 -!- ais523 has changed nick to ais523\unfoog. 22:23:06 -!- Sprocklem has quit (Ping timeout: 245 seconds). 22:23:24 brb mosh is outputting some crazy random ass characters 22:29:16 -!- Phantom_Hoover has quit (Ping timeout: 264 seconds). 22:32:22 -!- APott has joined. 22:32:41 Hello! 22:33:01 `relcome APott 22:33:03 backtick relcome apott 22:33:04 ​APott: Welcome to the international hub for esoteric programming language design and deployment! For more information, check out our wiki: . (For the other kind of esoterica, try #esoteric on irc.dal.net.) 22:33:27 ha, thanks 22:33:44 So, what brings you to the channel? 22:34:05 I came across this wiki and find some of these languages extremely interesting and thought I would talk to a few people 22:34:32 :) 22:34:35 i heard we have a software project next semester where we have to write a compiler for rail 22:34:40 i am looking forward to it 22:34:49 a train? 22:34:50 APott, well, we're off-topic pretty much all the time, I'm afraid 22:34:59 yeah, but I /want/ us to be ontopic 22:35:08 I'm here mostly for the ontopic conversation 22:35:12 Bike, no, a machine that you can in front of the the train to put down tracks 22:35:13 lol it's fine I'm used to off topic 22:35:14 You can be both ontopic and offtopic. 22:35:15 thus, the fact I leave a lot when there isn't any 22:35:21 oh, those things are cool 22:35:30 If you have any ontopic things to write, do it. 22:35:38 APott, what're your favourite esolangs, then? 22:35:48 I've written front ends and interpreters for languages but still haven't figured out how to compile anything 22:35:56 oh well I'im quite new to esolangs 22:36:10 try a brainfuck compiler. super easy. 22:36:13 APott: Which ones did you do? 22:36:16 The first one I've used was Brainfuck which I actually wrote an interpreter for, it's a bit buggy though 22:36:35 in what language? 22:36:45 I've never written a compiler, just interpreters. I wrote it in D since it's my favorite 22:36:52 What do you want the compilers to target anyways? 22:37:38 My goal is to eventually develop a native compiler but that's extremely far off I imagine 22:38:15 (If you are going to target Z-machine, try the Frolg macroassembler. Other things to possibly target include LLVM, C, Haskell (in fact a function can be constructed at runtime), 6502 (although there are different computers using it, such as C64 and Famicom), etc) 22:38:33 If I wanted to I could write a translator to a language probably, jsut haven't invested the time. 22:38:35 -!- AnotherTest has quit (Ping timeout: 272 seconds). 22:38:47 hmm I will have to look into those 22:39:05 I have looked into LLVM but since I prefer D it's a bit difficult to get LLVM working 22:39:08 APott: a compiler is a translator 22:39:31 But a translator translates a high level language to another high level language 22:39:41 Compilers mainly go down a level 22:39:59 'levels' are ill defined. what now 22:40:11 alright, you got me. :D 22:40:23 But technically assembly language is just another language :o 22:40:26 levels are ill-defined, but it's still possible to compare them sometimes 22:40:41 Also there are processors of high level languages 22:40:52 So the difference between the two is more of a convention 22:40:56 Yeah but assembly is just characters in place of instructions 22:40:59 hmhm 22:41:04 not necessarily 22:41:12 assembly often produces object files rather than executables 22:41:14 that then get linked 22:41:25 yeah 22:41:46 And assemblers often have macro languages and such. 22:42:09 Some assemblers don't have macros, although the ones I make/modify do. 22:42:18 oic 22:42:21 that's true 22:42:29 http://en.wikipedia.org/wiki/Java_processor 22:42:46 Slereah: a professor of mine won one once 22:42:55 he had no use so he wanted to give it away 22:42:58 At a church raffle? 22:42:58 nobody wanted it 22:43:06 lol 22:43:08 heh 22:43:12 Also, even machine code is a bit abstract from CPU architecture anymore. 22:43:26 Depends what you mean by machine code 22:43:33 Isn't machine code exactly what the CPU gets? 22:43:36 Between weird microcode tricks and nonlinear execution of code... 22:43:41 I thought the more abstracted one was assembly 22:43:48 me too 22:43:50 aseembly is just a textual representation for "machine code". 22:43:56 indeed 22:43:59 But it turns out that "machine code" isn't "direct" either. 22:44:21 Depends what you refer to as machine code. 22:44:42 Slereah: Yes, but x86 basically turns the opcodes into an internal RISC ISA and then executes that. 22:44:55 Turns out it's hard to do anything sophisticated with CISC. 22:44:56 now that part is beyond me 22:45:11 At least with Brainfuck you know what you're getting! 22:45:18 And then there's register renaming and such... 22:45:22 until you have to worry about wrapping cells 22:45:23 lol yeah 22:45:46 Some x86 opcodes take effectively 0 cycles. 22:45:47 -!- Phantom_Hoover has joined. 22:45:52 Wrapping cells is just the BF version of full memory 22:46:00 So I'm bored and I want some practice and such. What's your suggestion for a medium level language to interpret? 22:46:12 APL? 22:46:13 medium level I mean medium skill level to interpret 22:46:22 I will look it up 22:46:23 real fast nora's hair salon: shear disaster download 22:47:05 i always thought of buildung a subleq processor 22:47:11 Bike, I don't know that one 22:47:16 caching would be horrible, though 22:47:20 I'd say Underload is medium difficulty 22:47:23 Did you mean Real Fast Nora's Hair Salon 3: Shear Disaster Download? 22:47:34 Underload? 22:47:39 i meant what i said and i said waht i meant 22:47:55 http://esolangs.org/wiki/Underload ? 22:48:02 lol okay Dr. Suess 22:48:03 APott, that's Underload 22:48:17 *shudder* that was Lewis Carrol 22:48:30 shh... 22:48:30 yeah, that link 22:48:41 Alright, I will look into it 22:49:24 i'd say befunge is medium difficulty 22:49:41 Also 22:49:46 In what language will you code it? 22:49:51 D 22:49:59 Interpreter difficulty vary a lot with it 22:50:15 Brainfuck is pretty easy to do in C, Unlambda in Scheme 22:50:20 But not so much vice versa 22:50:34 APott: just wondering, do you have any opinion about rust? 22:50:49 As in Mozilla's language? 22:50:58 myname: befunge-93 is medium 22:51:02 befunge-98 is very hard to get right 22:51:09 APott: yes 22:51:33 I think it's to new 22:51:43 I don't really like it 22:52:05 i don't think brainfuck is that hard in scheme... or unlambda in C, probably 22:52:23 Well unlambda is trivial in Scheme 22:52:32 And brainfuck in C, too 22:52:37 APott: people there say D is for C++ coders who like C++ and rust is for C++ coders who hate C++ 22:52:52 i mean i have a "brainfuck to lisp compiler" that's like twelve lines. 22:53:16 a brainfuck to almost anything compiler is like 12 lines 22:53:19 Well I guess it's not too hard to do with lists for tape 22:53:24 right, exactly 22:53:25 unless the target language is almost impossible to write in 22:53:32 D for me is a perfect language for several reasons. I like what C++ does, I like the OO paradigms, some of the syntax, and how things are organized. 22:53:33 scheme has arrays... 22:53:35 brainfuck to malbolge 22:53:46 Brainfuck to x86 MMU? :) 22:53:48 But I like higher level features like you may see in Java or C# 22:53:59 MMU 4ever 22:54:11 D is right in the middle, has low level features, a beautiful syntax and some high level features 22:55:12 APott: Such features can be good for some things, although I happen to like macros and pointers; many programming languages don't implement very good macros. BLISS is one that has powerful macros and actually has many other features which are pretty good too; however I think it lacks a proper type system. 22:55:25 (Unfortunately I don't know of any GNU BLISS compiler) 22:55:38 D has pointers 22:55:52 OK 22:55:57 rust has 4 kinds of pointers! 22:56:05 i have pointers 22:56:23 In a language like D I don't see the need of macros 22:57:06 APott: Maybe, but I find macros (and meta-macros, and meta-meta-macros, and meta-meta-meta-macros) are always useful things to have. 22:57:25 'patamacros 22:57:44 Comacros? 22:57:44 btw zzo didn't you just say "Maybe you're right, but actually you're totally wrong" 22:58:15 Read through some pages on the site, it's quite feature filled: http://dlang.org/overview.html 22:58:18 Bike: Not really, since some people might not find it as useful or as necessary as other people. 22:59:06 APott: IIRC some standard language features are implemented as macros 22:59:19 they work quite differently from C-style macros, though 22:59:22 they feel more like C++ templates 22:59:30 D has macros... 22:59:47 elliott: APott's arguing that D doesn't need them, despite the fact that it has them 22:59:50 I think 22:59:53 okay. 22:59:55 why are we arguing about that? 23:00:09 it's not really an argument yet 23:00:19 Depends what you mean by macros 23:00:19 because the topic of this channel is programming languages and we gotta stay on topic. 23:00:50 well, programming languages generally there are loads of channels for 23:01:01 given that that's a major part of what Freenode is for 23:01:26 -!- variable has changed nick to trout. 23:01:52 this channel's for the languages that didn't quite make the mainstream, due to being mindbogglingly badly designed 23:01:54 normally, intentionally 23:01:59 Almost any reason you may use macros in C isn't needed in D because everything is implemented in the language 23:02:06 TeX has very powerful macro system, sufficient to do such things as sorting an index, playing chess, and implementing a BASIC interpreter. 23:02:14 Though one wonders about C++. 23:02:31 I believe the same with C++ 23:02:47 zzo38: is that in order of difficulty? 23:03:15 ais523: I specified them in an arbitrary order actually. The first two I have done; the third someone else has done. 23:03:39 APott: Perhaps in some languages you get that to varying degrees, although I prefer to have the macro system instead and have a standard library of macros to implement many of these higher level language features. 23:04:17 Okay 23:05:22 I have written a file about what features I would like to see in "Black-C" which is a variant of GNU89 C. I don't mention things that need extra runtime support since I want to be "C-like" in its runtime environment. 23:06:27 I did look at stuff about D before; they did fix the template syntax that is no good in C++. 23:08:33 indeed 23:09:58 is there an esoteric language with emoticons? I'm curious lol 23:10:14 APott: Yes I think there is at least one. 23:10:21 (I forget what it is called) 23:10:22 ":)" is a valid brainfuck program 23:10:37 =) too 23:10:38 Taneb: So is anything with balanced square brackets. 23:10:40 Although not a valid Underload program! 23:10:46 lol 23:10:52 http://esolangs.org/wiki/Emoticon ? 23:14:37 So who was I talking about macros with? What exactly do you need macros for in C, the most 23:15:11 did you get shot 23:15:28 Did who get shot? 23:15:31 C macros aren't quite very powerful but can do a few things, including really unusual things 23:15:35 you. you jjust stopped 23:15:47 Especially when used with GNU extensions 23:16:00 oh lol. yeah 23:16:14 C macros can be used to do anything you really shouldn't do with macros 23:16:14 most things you may used macros for in C have a specific keyword in D for i 23:16:16 it* 23:16:26 -!- Phantom_Hoover has quit (Ping timeout: 264 seconds). 23:17:51 Another thing I have used C macros for is to pass around local variables and arguments to subroutines if they want a copy 23:18:19 why not just pass as an argument? 23:19:22 In case you are calling the same subroutine several times and they want copies of the variables 23:19:37 It just makes it a bit more convenient for me, that is all 23:19:44 ah 23:19:51 in D you can just define a constant 23:19:53 These programs are open source so you are allowed to look (and modify it) 23:19:59 const int num = 5; 23:20:10 You can do that in C too, but that isn't what I was doing. 23:20:17 oic 23:20:25 brb 23:21:04 #define zoidberg (;;) 23:21:12 for zoidberg { whoop(); } 23:21:31 Specifically I made this macro: #define Add_to_parsebuf() if(k)add_to_parsebuf(parsebuf,dict,d,k,el,ne,p1,flag),k=0;p1=p+1; 23:21:44 this is clearly the perfect opportunity to mention my esolang idea so i'm going to do that: verilog, but for 1940s targeting computers. 23:22:01 Bike: OK, can you give some details? 23:22:29 i'm having trouble thinking up how exactly relationships should be specified. like, say you have a shaft and a gear. there are tons of ways to connect those - you could have the shaft at a different place on the gear, or have the gear rotate around it freely 23:23:07 it doesn't really lend itself to "well here are the basic gates" 23:24:29 Bike: Then you need to make up a SHAFT command and a GEAR command and the commands for connection; at least if being made like HWPL it works by specifying connections; Verilog works by events instead so you would need to figure out how that works and I don't know. 23:24:32 and that's not even getting into like, three dimensional cams, which are basically specified as a mostly arbitrary volume. 23:25:17 I don't know much about that. 23:25:28 But you can post in esolang wiki list of ideas if you have something to write there. 23:25:50 eh i'd like to actually write up a proper page. it's kind of dumb hanging out here when i don't even have a wiki account. 23:26:34 Then register (optional, I think) and post. Even if you don't know what to write on a proper page, it can be written in list of ideas, at least. 23:27:55 Bike: well, signing up is easy 23:28:05 even for spambots, apparently, although we changed the CAPTCHA a few days ago 23:31:19 -!- Phantom_Hoover has joined. 23:39:54 hmmmm tacos 23:44:36 -!- Sprocklem has joined. 23:54:07 -!- oerjan has joined. 23:55:52 I think I saw #define forever for (;;) somewhere. (And then forever { ... } later.) 23:56:13 -!- Taneb has quit (Ping timeout: 272 seconds). 23:56:44 @src forever 23:56:44 Source not found. :( 23:58:01 i would've made #define ever (;;) 23:58:05 for ever { } 23:58:34 #define getit (;;) for getit { ... } 23:59:18 fizzie: shouldn't that be #define getit (;0;) 2013-11-10: 00:02:43 `unidecode ⟩ 00:02:45 ​[U+27E9 MATHEMATICAL RIGHT ANGLE BRACKET] 00:03:00 oerjan: MAYBE. 00:04:14 oerjan: there's an annotation in Unicode saying that that's the correct one to use for a ket 00:06:21 -!- Phantom_Hoover has quit (Ping timeout: 244 seconds). 00:08:34 > forever "" 00:08:35 [] 00:08:44 ais523\unfoog: aha 00:09:30 > execWriter . forever $ tell "hi! " 00:09:31 "hi! hi! hi! hi! hi! hi! hi! hi! hi! hi! hi! hi! hi! hi! hi! hi! hi! hi! hi... 00:10:00 `yes hi 00:10:01 hi \ hi \ hi \ hi \ hi \ hi \ hi \ hi \ hi \ hi \ hi \ hi \ hi \ hi \ hi \ hi \ hi \ hi \ hi \ hi \ hi \ hi \ hi \ hi \ hi \ hi \ hi \ hi \ hi \ hi \ hi \ hi \ hi \ hi \ hi \ hi \ hi \ hi \ hi \ hi \ hi \ hi \ hi \ hi \ hi \ hi \ hi \ hi \ hi \ hi \ hi \ hi \ hi \ hi \ hi \ hi \ hi \ hi \ hi \ hi \ hi \ hi \ hi \ hi \ hi \ hi \ hi \ hi \ hi \ hi \ 00:11:22 @unlambda ``ci`c`. `.!`.i`.hi 00:11:22 hi! hi! hi! hi! hi! hi! hi! hi! hi! hi! hi! hi! hi! hi! hi! hi! hi! hi! hi!... 00:12:12 > fst $ (runRWS . forever $ do x <- get; tell [x]; put (x+1)) undefined 0 00:12:14 Couldn't match expected type `(a0, b0)' 00:12:14 with actual type `(a1,... 00:12:23 :t runRWS 00:12:24 RWS r w s a -> r -> s -> (a, s, w) 00:12:31 oh 00:13:09 > view _3 $ (runRWS . forever $ do x <- get; tell [x]; put (x+1)) undefined 0 00:13:11 [0,1,2,3,4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,... 00:15:25 > view _3 $ (runRWS . forever $ do x <- get; tell [x]; modify . (+) =<< ask) 2 1 00:15:27 [1,3,5,7,9,11,13,15,17,19,21,23,25,27,29,31,33,35,37,39,41,43,45,47,49,51,5... 00:16:53 `seq 1 2 10000 00:16:54 seq: invalid floating point argument: 1 2 10000 \ Try `seq --help' for more information. 00:16:58 err 00:17:01 > (0$0&) 00:17:01 `run seq 1 2 10000 00:17:02 The operator `Control.Lens.Combinators.&' [infixl 1] of a section 00:17:02 must... 00:17:03 1 \ 3 \ 5 \ 7 \ 9 \ 11 \ 13 \ 15 \ 17 \ 19 \ 21 \ 23 \ 25 \ 27 \ 29 \ 31 \ 33 \ 35 \ 37 \ 39 \ 41 \ 43 \ 45 \ 47 \ 49 \ 51 \ 53 \ 55 \ 57 \ 59 \ 61 \ 63 \ 65 \ 67 \ 69 \ 71 \ 73 \ 75 \ 77 \ 79 \ 81 \ 83 \ 85 \ 87 \ 89 \ 91 \ 93 \ 95 \ 97 \ 99 \ 101 \ 103 \ 105 \ 107 \ 109 \ 111 \ 113 \ 115 \ 117 \ 119 \ 121 \ 123 \ 125 \ 127 \ 129 \ 131 \ 133 \ 135 00:17:37 > [1,3..] 00:17:39 [1,3,5,7,9,11,13,15,17,19,21,23,25,27,29,31,33,35,37,39,41,43,45,47,49,51,5... 00:18:25 I WIN 00:18:45 (i wasn't trying to golf, anyway) 00:18:47 -!- nooodl has joined. 00:18:59 nor was I 00:22:09 * oerjan briefly wonders how many of the "quantum" esolangs actually are related to quantum computing rather than the "take several paths at a time (and discard the ones whose result you don't like)" misunderstanding of it 00:22:37 i vaguely _think_ i may have seen one. 00:23:02 -!- Sprocklem has quit (Ping timeout: 264 seconds). 00:23:05 nondeterministic esolangs are still interesting 00:23:12 Well, a few have Hadamard transformers I think 00:23:17 you just shouldn't call them quantum 00:23:31 ais523: Yes I think you are correct 00:23:34 right (to both of you) 00:23:43 -!- Phantom_Hoover has joined. 00:24:37 there's however a somewhat interesting complexity class that you get by combining both those ideas, "quantum computing with superselection" 00:25:21 it's not known to be equal to either of the subsets, but fits inside PSPACE. it's in the graph at the top of aaronson's blog. 00:27:07 PostBQP it was 00:28:05 oh it was postselection, not superselection 00:29:55 superselection also means something, not exactly sure what it's for 00:31:31 oh and it's equal to PP, a complexity class defined without any quantum 00:32:04 it's cool how seemingly half of aaronson's job is telling peole quantum computers suck 00:32:57 -!- Phantom_Hoover has quit (Ping timeout: 272 seconds). 00:34:19 -!- Phantom_Hoover has joined. 00:39:47 for my Physics A-level project, I wrote something about how quantum computers work 00:40:00 and implemented a simulator capable of handing Shor's algorithm on 8-bit integers 00:40:09 calculating a probability distribution for the result 00:40:16 neat 00:40:19 it had like a 30-40% chance of getting the correct answer, IIRC 00:40:31 quantum computer use in practice is, you run the experiment, then you check the result 00:40:42 and try again if it was wrong 00:45:58 So does anyone know anything about how virtual machines are implemented? 00:46:05 As in something like the JVM 00:46:39 well yeah, they're like any language interpreter, except you have a billion dollars so you can make them fast as shit 00:47:44 lol 00:48:09 But I read about various virtual machine implementations 00:48:20 Like Google's V8 Javascript engine 00:48:34 they say they go straight from AST to Machine code 00:48:47 that's a (just in time) compiler. 00:48:48 this is why it's so fast, how do they execute machine code? 00:48:51 Yes 00:49:04 how do they execute machine code? well, they have these things called computer processors, 00:49:16 I mean programatically 00:49:41 I've read they basically get all the instructions in byte format or whatever then create a function pointer to the bytes in memory 00:49:51 then they can just call it like a function 00:50:01 Something like that. 00:51:16 Gregor did something like that for the IOCCC 00:51:36 i mean, obviously that's not conforming C or whatever, but you still get the idea. 00:51:45 wow 00:51:47 yeah 00:52:24 that's von neumann architecture for ya. 00:53:00 lol 00:56:34 did i tell a joke by accident... 00:57:01 no it's just I don't know as much as you so I said lol as a response 00:57:15 as i began reading a wikipedia article 00:57:32 i've never really understood that. i thought 'lol' meant laughing 00:58:04 because before I looked it up I thought it was a joke since I didn't know what It meant 00:58:14 and it was kinda stated like one 00:58:58 no that's pretty much just how i write 00:59:29 That's fine. 00:59:48 i am The Living Joke 00:59:57 lol xD 01:02:15 are there any popular languages that interpret the ast 01:02:16 ? 01:03:01 @unlambda ```s``s.1`k``s`k`s`k.1`s`k.,i``s``s`ks``s`kk``s``si`ki`ki``s``s`ks``s`k`si``s`kk``s``s`ks``s`k`s`ks``s`k`s`kk``s``s`ksk`k`s`k.1``s``s`ksk`k`s`k.0`ki 01:03:01 1,10,11,100,101,110,111,1000,1001,1010,1011,1100,1101,1110,1111,10000,10001... 01:03:21 I forgot how icky that programming language (Unlambda) really is :) 01:03:27 APott: what do you mean 01:04:23 I'm just curious 01:04:35 Like as I mentioned earlier with V8 01:04:47 Sure. Ruby. 01:04:59 -!- Phantom_Hoover has quit (Ping timeout: 252 seconds). 01:05:00 It translates the ast to machine code, I'm assuming other languages do that but are any popular that interpret ast? 01:05:04 oic, ruby 01:05:13 that's how most interpreters work... 01:05:21 you have a "parse" step and then an "evaluation" step. 01:05:25 I've never written in it before. I don't even know what it's mainly used for 01:05:31 oic 01:05:36 yeah 01:05:51 doing them both together would be kind of silly ("we call it Perl") 01:05:57 bytecode interpreters used to be popular. 01:06:05 Just what everything i've read has made me believe that's not enough or suitable 01:06:10 what? 01:06:14 int-e: Still are. 01:06:22 parse -> bytecode -> interpret that, rather than an AST 01:06:33 Bytecode interpreters are profoundly faster than AST interpreters. 01:06:36 yeah that... hapens all the time, int-e 01:06:58 i have a language i should write a bytecode thing for but effffffort 01:06:58 Ruby's the only mainstream language that really *used* a direct AST interpreter. 01:07:16 Okay, I didn't know that, thanks 01:07:38 Why would a bytecode interpreter be faster since the AST has to be translated to bytecode which is then interpreted? 01:07:39 Maybe you might want to interpret some kinds of macros while parsing AST 01:07:57 APott: the idea is that the ast->bytecode step takes some effort but you only have to do it onc. 01:08:00 APott: better locality, smaller memory footprint --> better for caches 01:08:00 e 01:08:09 oh okay 01:08:23 that too yeah. 01:11:41 It's also quite a bit quicker to branch on. 01:12:03 Especially if you do somewhat sophisticated tricks to help the CPU's branch predictor along. 01:12:29 fizzie: this shit reminds me, how much can i rely on matlab's jit? also if you want me to stop reminding you matlab exists that's ok 01:13:02 Bytecode's also nicer in terms of future development because you can generally add a JIT later. 01:13:16 yeah 01:13:32 pikhq: Especially if it is harvard bytecode, that is. 01:14:05 i've been wondering if i should bother rearranging things to index into a matrix instead of branching but it seems like such a pain 01:14:12 zzo38: Which you almost always do for interpreter bytecodes. :) 01:14:53 ... i wonder if even just using switch/case instead of elseifelseifelseif would speed it up. maybe the jit does jump tables 01:15:42 or i could just give up and start rewriting the thing in scipy. 01:17:50 -!- tswett_q has changed nick to tswett. 01:19:13 APott: calling machine code in memory can be basically as you heard, except that nowadays you also need to change the security settings of the memory. by default you cannot write to and execute the same part of memory (this is to make attacks harder by not making it too easy for attackers to execute anything they want.) 01:20:18 oic 01:20:39 (also helps against some bugs, i guess) 01:20:56 some terrifying bugs 01:21:06 Will just raw instructions execute or will there be some sort of other step before it's executed? 01:21:08 pikhq: A few aren't; a few partially are. In Z-machine, it is possible to execute instructions from RAM, although usually it isn't; there is the high ROM area which can contain only instructions and packed text strings. JUMP with a variable operand might still make compiling it a bit more difficult, though. 01:21:54 APott: well you set up the argument stack and all, is that what you mean 01:22:04 if there are arguments. 01:22:09 (In addition, there is the restriction of where routines and text strings can start, so you don't have to check all of them; also, routines always begin with a byte having the high four bits cleared, so if any of them are set you can skip that one.) 01:22:28 Bike: Yeah that makes sense 01:23:08 zzo38: Hence "almost". :) 01:23:33 APott: well it's as raw as you get to put into memory. although nowadays computer processors transform it to even rawer "microcode" internally. 01:23:51 yeah 01:23:53 rawr 01:23:53 I am in the process of writing a program to convert OASYS codes (which is harvard) into Z-machine codes; currently no optimizations are done. 01:23:54 APott: but it's the same format as most programs use. 01:24:39 (OASYS also lacks variable jumps; this also makes it easier to compile.) 01:24:59 I've completely lost track of what you're talking about 01:25:37 none of this should be new to you, since "load a program into memory and run it" is the same thing that happens when you run a program from your desktop :) 01:26:04 I was talking to zzo38 01:26:15 `quote zzo38 01:26:17 27) I am not on the moon. \ 116) Some people are reasonable, some people who are not reasonable insist on changing things so therefore progress depends on not reasonablepeple \ 150) catseye: Please wake up. Not recorded for this timezone. The big spider is not your dream \ 174) zzo38: A better definition would probab 01:26:43 `quote 174 01:26:44 174) zzo38: A better definition would probably fix Avogadro's number. It's broken? 01:27:03 uhh 01:30:13 i woulda thought free vacuum permitivitty or something would be more 'broken'. 01:32:25 -!- ais523\unfoog has quit. 01:37:04 -!- yorick has quit (Remote host closed the connection). 01:49:40 So are any of you asian? 01:49:40 "Fix" in this sense meaning "set it to a fixed number, rather than an experimental quantity" 01:49:48 No, but I speak Japanese. 01:49:56 cool 01:50:07 where did that come from 01:50:33 If you knew me irl I have an ongoing inside joke about asians 01:50:43 is it racist 01:50:46 I always joke about asians but I have nothing against them, they're awesome 01:50:53 http://www.bearnerd.com.br/wp-content/uploads/2013/08/Asians-meme.jpg 01:51:06 it is not racist 01:53:18 are you sure 01:56:56 0100% positive I'm not racist 01:57:01 100%* 01:57:08 I talk to asians irl on a regular basis 01:57:13 there is no problem 01:57:24 like is this the "asians are all super smart math nerds" sort of crud 01:57:37 not really no 01:57:51 just kinda like that picture i linked. Just--asians. 01:58:04 -!- Koen_ has quit (Quit: The struct held his beloved integer in his strong, protecting arms, his eyes like sapphire orbs staring into her own. "W-will you... Will you union me?"). 01:58:05 Anyway lets move on, 01:58:14 baffling 01:58:42 lol that message is awesome whatever you would call that. 02:04:35 APott: Do you mean the quit message? 02:05:58 indeed 02:06:35 APott: is your criterion for whether or not you are racist actually "I talk to asian people" 02:06:55 dude 02:07:00 I'm not racist 02:07:01 at all 02:07:06 as a general rule, if you have to explain why you're not racist you are already on thin ice. 02:07:27 and it gets thinner the stronger you argue. 02:07:28 Because I speak a language, I am racist too, although I try not to be too racist. 02:07:29 thin ice doesn't mean i'm racist 02:07:43 Definition of racism: the belief that all members of each race possess characteristics or abilities specific to that race, esp. so as to distinguish it as inferior or superior to another race or races. 02:08:14 I believe none of that 02:08:28 i was starting to write a response but then realized i was trolling. 02:08:36 ha lol 02:09:15 Do you know any Washizu mahjong players? 02:09:28 nope I don't even know what that is 02:09:31 -!- tertu has quit (Ping timeout: 252 seconds). 02:10:05 Do you know any mahjong game? 02:10:37 *opens google* 02:11:36 I suppose I've seen something like that before 02:11:46 i've only ever played mahjong solitaire. i kinda want to play actual mahjong once 02:13:34 nooodl: Japanese mahjong? There are many different kinds; Japanese mahjong is popular in many places. I play Japanese mahjong. 02:13:48 yeah, japanese mahjong 02:13:59 nooodl: Do you know anything about the rules? 02:15:04 i don't. all i know is it's similar to card games like bridge 02:15:35 do you like tichu 02:15:37 There are some similarities to some card games, such as bridge and rummy 02:15:48 zzo38: would you like to have a tichu night 02:16:09 -!- Taneb has joined. 02:16:09 you and me and two of your friends 02:16:14 Hi 02:16:21 sup 02:17:53 inf 02:18:15 quintopia: I do not know what that means. 02:18:32 zzo38: it's a good game you'd like it. 02:21:16 That doesn't explain anything. 02:23:15 *shudder* that was Lewis Carrol <-- um pretty sure it was dr seuss? 02:23:38 wow that's old but that confused me to 02:23:48 It was a line from Humpty Dumpty in Through the Looking Glass 02:23:53 possibly carroll wrote it too 02:24:06 -!- ^v has quit (Remote host closed the connection). 02:24:13 I don't even know the line that was spoken, what was it again? 02:24:51 http://www.goodreads.com/quotes/44212-i-meant-what-i-said-and-i-said-what-i 02:24:58 I said what I meant and meant what I said? 02:25:21 I meant what I said and I said what I meant* 02:25:24 i meant what i said and i said waht i meant 02:25:39 yeah 02:25:42 Taneb: i think you may be confusing it with another quote 02:25:57 That was from a Dr. Suess story I'm pretty sure 02:26:03 hion 02:26:09 I suppose that could have beena coincidence or he borrowed it 02:26:15 depends what you're referring to 02:26:19 'If I'd meant that, I'd have said it,' said Humpty Dumpty. 02:26:30 yes but that's not what was said 02:26:31 if it helps i was actually quoting a porno 02:26:37 oerjan, hmm, possibly 02:26:45 lolo 02:26:49 it definitely wasn't Dr. Suess. 02:27:07 elliott: well we have to adjust for the fact it was "waht" 02:27:15 but that was in a Dr. Suess story, specifically the onewith the elephant 02:27:18 oerjan: But what did Humpty Dumpty mean by that? 02:27:29 horton or whatever it's name was 02:28:02 published in 1940 02:28:57 http://en.wikipedia.org/wiki/Horton_Hatches_the_Egg#Analysis 02:29:04 near the bottom of the paragraph 02:29:13 I don't even know why we're talking about this lol 02:29:52 second paragraph 02:30:03 because this is a channel for incorrigible nitpickers 02:30:16 lol 02:31:37 "When I use a word," Humpty Dumpty said in rather a scornful tone, "it means just what I choose it to mean——neither more nor less." 02:31:38 That was what I was thinking of 02:31:38 Sorry about this 02:32:14 Alright it's fine 02:32:28 same message completely different words. 02:32:57 I DON'T THINK IT WAS THE SAME MESSAGE 02:33:02 *cough* 02:33:11 it wasn't a very good porno 02:33:31 Bike, it's probably precisely as good as every porno I have ever seen 02:33:57 close to the same--lol 02:34:18 * oerjan is cleverly assuming Taneb has seen zero. 02:34:29 oerjan, correct 02:34:30 "Then you should say what you mean," the March Hare went on. 02:34:30 "I do," Alice hastily replied; "at least—at least I mean what I say—that's the same thing, you know." 02:34:52 Another near-miss Carroll quote 02:35:10 but that's not what was said, i think I won here 02:35:50 this si the stupidest conversation ever 02:35:56 is* lets end it 02:36:09 I've had stupider 02:36:29 one of the stupidest conversations ever* 02:36:49 bison poop 02:36:54 * oerjan hands APott the Useless Argument Champion Cup, in genuine pewter. 02:37:02 :D 02:37:40 So what OS's you guys running? 02:37:51 Linux deagol 3.10-3-amd64 #1 SMP Debian 3.10.11-1 (2013-09-10) x86_64 GNU/Linux 02:37:57 be 02:38:17 I'm running Ubuntu Linux 13.04 02:38:28 64 bit 02:38:33 Linux Mint, but not for the long term probably 02:38:44 i keep annoying everyone else by staying on Windows despite not liking it much (8.1 at the moment) 02:38:55 I won't comment on that. 02:39:16 there's a guy in my twitter feed who can't figure out how to turn off his windows machine after the 8.1 upgrae 02:39:20 Linux Mint with what GUI? Last time I used it with Cinnamon 02:39:29 lol xD 02:39:42 Yeah, Cinnamon 02:39:55 Cinnamon was pretty nice, needs some work though 02:39:57 Bike: Does the SHUTDOWN command still work? 02:40:11 i didn't ask 02:41:01 The menus and stuff are all different, but most of the same keyboard shortcuts continue to work (even to access things that aren't available on any menu anymore), and cmd.exe is still available, at least in Windows 8.0 02:41:40 -!- shikhin has joined. 02:42:16 i don't just, i don't like ask near-strangers "have you tried command prompt" 02:42:24 :D 02:42:42 I have 8.0 on a separate partition just in case of an emergency 02:43:03 because sometimes you can fuck up linux quite easily 02:43:33 what... 02:43:40 APott: FreeBSD 02:44:11 That's what you run? 02:44:12 using openbox+lxpanel but looking to change 02:44:14 APott: yes 02:44:19 I've never tried it 02:44:25 any good, long term use? 02:44:26 Linux, Windows, a lot of systems are complicated and can be mixed up easily; DOS is a simple system that boots very fast and runs very fast too. 02:44:32 APott: absolutely 02:44:39 interesting 02:44:44 zzo38, wasn't DOS considered quite bloated when it was released? 02:44:53 APott: if you are going to try it, use pcbsd 02:44:55 finally, a workable solution to the problem of computers. dos. 02:45:09 * trout peddles Bike 02:45:23 zzo38: This is true but sometimes some simple hardware/driver mix ups can be an issue, on windows things are a bit more stable 02:45:26 pedals? 02:45:26 "I meant what I said what I meant; an elephant's faithful one hundred percent" --oh, childhood, thanks for reminding me :) 02:45:35 or are you trying to sell me........................... 02:45:38 yeah ^^ :D 02:45:44 Taneb: Yes, but that is just because many people said that; it does contain some features it doesn't need but it is still pretty good compared to others 02:45:44 Bike: nah, trying to ride on the Bike 02:45:53 (locked up my computer egojsouting a long battle. would have replied sooner.) 02:46:00 my bikes back tire is flat 02:46:14 bike's* 02:46:28 well if you're riding me you would use the pedals, not the peddles 02:46:31 -!- Taneb has quit (Quit: it is time for taneb to sleep). 02:46:43 i don't mean to be rude here, you're the operator, but this is pretty basic 02:46:51 yeah lol. 02:47:26 So I found these old Beatles vinyls on E-Bay and I think I'm going to bid on them 02:47:38 The seller placed the starting price quite low 02:48:04 Do you have a record player though? (If not, it isn't that complicated anyways) 02:48:20 well beatles vinyl isn't rare 02:48:56 Do you like Pokemon card (with the old-style rules)? 02:49:20 lol wut 02:49:28 I do not but am going to invest in one 02:49:56 I'm interested in starting a collection of them, since me grandfather gave me a good amount of them I thought why not? 02:51:08 https://github.com/search?q=exec+sudo+%24_GET&type=Code 02:52:28 What about it? 02:52:43 it's beautiful 02:52:51 a lot of bad practice 02:52:54 If "exec sudo $_GET" is a PHP code, it is a terrible code 02:52:55 but okay 02:53:15 (I haven't actually followed the link so I don't know how many results and that stuff) 02:53:34 echo shell_exec("sudo ./smbkill ".$_GET['kill']." 2>&1");, what could possibl go wrong 02:53:41 a lot of shit 02:53:50 Bike: A lot of stuff 02:53:50 this is the worst php practice I've ever seen 02:55:13 i agree with Bike 02:55:16 it's amazing 02:55:30 That so many people are writing horrible code? 02:55:32 yes 02:55:51 not necessarily horrible but extremely insecure 02:55:51 not sure if this is quite as funny as people putting private pgp keys in github dotfiles, but it's up there 02:56:03 yeah lol 02:56:34 A lot of PHP programmers write terrible programs though 02:56:46 The language promotes bad practices 02:57:09 Well, PHP isn't a very good programming language anyways, due to a number of problems (even ignoring bad practices) 02:57:15 I know first hand because it was the first language I learned and when I began learning others I realised how bad the stuff I was doing was 02:57:24 I need a comma in there lol 02:57:52 zzo38: What is a very good programming language? 02:58:21 shachaf: I don't really know but many are OK; they can be good for different purposes. 02:58:46 PHP being good for web scripting 02:59:00 I think it does it's job fine it just has it's issues 02:59:24 APott: Yes there are many issues with it 02:59:43 shachaf: PUZZLANG. clearly. 03:00:04 I know there are issues but I can't even name any off the top of my head 03:00:12 I don't know what programming language I learned first; I think it was BASIC. I still program in BASIC sometimes, especially for writing computer games, since it is OK for many kinds of games. 03:00:21 APott: you don't need to. there is a whole website devoted to listing them. 03:01:15 I will look for it. The only ones I can think of would be speed, and security 03:01:49 APott: There are several others too, such as syntax problems that it won't work if you put [] after a function call, and so on 03:02:27 Although I have written some webpages in PHP, such as the FurryScript form (the backend is also in PHP, even though it is a standalone program that doesn't require a webpage), and a form to run TeX programs (which is far simpler than the one Wikipedia uses, and probably far more secure too) 03:02:31 Does that work in C? (I've never tried it) 03:02:34 However I have once used SQL to write a webpage 03:02:42 what, array indexing the result of a function call? 03:02:45 'course it works 03:02:47 yeah that 03:02:54 oh, I've never had to do it 03:03:01 APott: I think so, but even if it doesn't you can use *(f()+x) and stuff like that 03:03:05 it only doesn't in php because the parser is terrible 03:03:11 In PHP it doesn't do that though 03:03:16 isn't the parser generated? 03:03:20 this is a language where using certain denormal floats crashes everything 03:03:29 Bike: Yes it is really terrible 03:03:51 Isn't the php front end lex/yacc generated? 03:04:10 Bike: how is it that exec("sudo blah") even works? what sort of permissions would be required? i know i'm set up that every sudo command needs a password entry. 03:04:21 quintopia: i don't want to think about it 03:05:49 So has anyone tried D? I use it all the time and there's a fantastic package manager for it 03:06:01 APott: I haven't, but I have read things about it 03:06:15 i know a guy who uses D but his code is so shitty i was put off 03:07:01 :/ It's such a small community it's hard to get it going because there aren't many libraries as of now 03:08:21 don't worry, you didn't want me anyway. i read the snobol manual for fun 03:08:58 lol xD 03:09:55 Internet Quiz Engine (which is gopher-based) is written in C, although the main menu is in PHP, and the local mode menu is in Haskell (this Haskell program calls the C program and parses the gopher menus it outputs). (The PHP though is only the menu; the server config runs the C program directly when needed) 03:10:54 OkCupid/HelloQuizzy is HTTP and it is written in C++ though (I do not think the source-codes are available though; it is coincidental that Internet Quiz Engine operates in similar ways) 03:11:57 zzo38: That sounds complicated. 03:12:17 complicated, but can survive nuclear fallout 03:12:30 shachaf: It does, although that is because you haven't seen it. It is actually not so complicated. 03:12:32 CGI or whatever you want to call it in C/C++ is quite simple 03:13:25 APott: Yes, I know you can. (The webpage I wrote in SQL once actually used a CGI program I wrote in C which calls SQLite and gives it parameters from the query and outputs the headers and that stuff) 03:14:23 ah 03:14:32 So why don't we do it in the road? 03:14:46 which road 03:15:00 Pennsylvania Avenue 03:15:14 In the District of Columbia 03:15:38 APott: iirc CGI also has broken security, it puts fields from the url in environment variables named by them. 03:15:52 oerjan: I don't think CGI does that. 03:16:00 it does indeed 03:16:01 they had to neuter a feature of the ghc haskell compiler because of it 03:16:16 I don't see how it's insecure though 03:16:20 I think it does for the headers but not for the URL 03:16:28 lol, it has register_globals? 03:16:31 best feature ever. 03:16:37 GET data is stored in an environment variable 03:16:55 Bike: I never use it, although sometimes when I write such a PHP program I ensure it is working OK even if register_globals is enabled 03:16:59 oh, /an/ huh 03:17:05 is there an irssi script which looks in your logs to tell you the other nicks used by a person connecting from a particular hostmask 03:17:31 can't you just grep -r hostmask irclogs 03:18:05 yes. but with a channel moving quick it's hard to copy the hostmask from the screen 03:18:05 -!- nooodl_ has joined. 03:18:14 i'd rather have it be a command 03:18:25 like /aliases 03:18:30 quintopia: The hostmask is sent with every message, you just need to tell your client to display it if you want to copy it 03:18:35 APott: well it was a security flaw when you combined it with haskell's runtime environment variables for debugging... 03:18:45 zzo38: i don't want it displayed with every message silly 03:18:53 and it'd still be hard to copy 03:19:11 you could just /whois them and copy it from that window. 03:19:16 oerjan: isn't that a haskell issue then? 03:20:01 My gopher server is much more simple; it just puts the selector string in an environment variable called SELECTOR when it is calling an external program (the prefix tree is stored in the configuration file, which tells it which files are executable, which are text, which are binary, etc) 03:20:02 -!- nisstyre has quit (Ping timeout: 264 seconds). 03:20:40 Bike: it isn't a separate window. it appears in the same window and moves with the rest of the chat. (i set it up that way.) 03:20:51 i'm actually not quite sure if it was environment or command line flags, when i think about it. 03:20:57 ur clearly mad 03:21:18 Bike: also i don't want to have to remember the grep command :P 03:21:39 -!- nooodl has quit (Ping timeout: 244 seconds). 03:21:51 quintopia: Then put it in a shell script. 03:21:52 my sensors indicate that you might be a lazy ass nerd 03:21:59 -!- nisstyre has joined. 03:22:00 APott: partly, but it's CGI which is violating ordinary assumptions of where unsafe input gets communicated to programs. 03:22:42 If it goes in an environment variable then the program that reads the variable has the job of making sure it's safe, not the web server 03:23:12 it's not like it's being injected into random environment variables, it has a specific one 03:23:59 Bike: lazy programmers are best programmers. I like to keep a not-invented-here attitude. 03:24:26 Don't lazy programmers just surf the web for snippets? 03:25:29 quintopia: use /whois and then hit Ctrl-S or whatever. 03:26:07 tswett: what is it that undoes that? ctrl-q was it? 03:26:10 Yeah. 03:26:11 -!- Bike has quit (Quit: Lost terminal). 03:26:26 APott: um the problem (and it may have been flags, not environment variables) was that someone might fake a url that set an option that the program does _not_ expect to be set from a url. 03:26:31 -!- Bike has joined. 03:26:32 I'm not just a lazy programmer, I'm a lazy IRC user. Whenever I want to say something on IRC, I search some IRC logs for someone who's already sent a message saying it. 03:26:45 wow, i'm an idiot. what's ctrl s do 03:26:48 who said that one? 03:26:54 tswett: Are you lazy at typing too? 03:27:06 People who operate a computer ought to learn fast typing. 03:27:07 -!- nisstyre has quit (Read error: Connection reset by peer). 03:27:42 tswett: do you know of any scripts that let you grep logs directly into a channel, without having to specify the channel's logfile? basically /lastlog but for full logs? 03:27:45 oerjan: That's something that should always be checked by a CGI program 03:27:58 quintopia: what do you mean by "into a channel"? 03:28:15 In any case, no. 03:28:23 tswett: appended to the channel window the way /lastlog does 03:29:29 So like /exec, if /exec knew how to tell grep what channel you're in. 03:29:49 Bike: save your microsoft word document hth 03:29:54 -!- nooodl_ has changed nick to nooodl. 03:29:56 sure maybe 03:30:15 zzo38: I was going to respond "yes" to your question asking if I was lazy at typing, but I couldn't find an IRC message that was just the word "yes". 03:30:42 amazing that you could find one saying that yes couldn't be found, but couldn't find "yes" 03:30:55 i guess others have had this problem 03:30:56 ah yeah that's a good one 03:31:03 let me help once and for all 03:31:05 yes 03:31:10 helter skelter 03:31:42 cooool 03:31:53 I I don't even know 03:31:58 lol 03:32:13 That's the song that happens to be playing in my playlist right now 03:32:20 Why not... 03:32:30 http://www.youtube.com/watch?v=5fvJEpdq8a8 03:33:02 tswett: is it okay to agglomerate bits and pieces of different lines into the message you want? 03:33:14 noooooooo 03:33:39 fungot: how do you always come up with something so relevant just piecing together different things that others have said? 03:33:39 quintopia: it's just that luketus is the only one i can think to do with 03:34:06 but only two are valid? I don't even know 03:35:40 -!- shikhin has quit (Read error: Operation timed out). 03:35:48 imo we should use four-valued booleans, because that's the best kind of logic 03:35:53 So I have a posture problem, I'm 6 feet 2 inches and my monitors are quite low 03:36:05 so I find myself slouching, how do i fix this? 03:36:13 oh, lectricity 03:36:19 staple your monitors to the wall 03:36:27 that's logical 03:36:32 or staple yourself to the wall 03:36:35 Well, the obvious answer is "don't slouch". 03:36:39 that's even more logical 03:36:41 APott: the problem was that this affected runtime options for the haskell program before the program itself got to run any checks. the name of files for putting debugging output was the main problem iirc. so they had to turn that off by default, which annoys everyone who _isn't_ making a CGI program. 03:37:08 tswett: well it's obviously a sub concious thing 03:37:16 i'm pretty sure this is just dumb all around oejran 03:37:19 Right. So somehow you have to make it a habit. 03:37:31 make a game of it 03:37:44 conscious* It would be easier if the monitors were my height 03:37:57 then it would be pointless to slouch making me not slouch 03:38:12 Another obvious answer is "raise your monitors". 03:38:16 have you got any fat books 03:38:19 put em under your monitors 03:38:24 chemistry textbooks work well for this 03:38:24 every time you catch yourself slouching you give yourself five cents to spend on something and sit up straight. but no cheating and slouching on purpose just to get the five cents. 03:38:41 lol ok 03:39:07 Every time you catch yourself slouching, fine yourself five cents for slouching, sit up straight, and reward yourself five cents for sitting up straight. 03:39:11 I have a ton of programming language books that I could use I suppose and some harry potter books. I'm only a sophmore in high school so I don't have chemistry books yet lol 03:39:25 `translate ¿Funciona esto? 03:39:26 This google api no longer exists. 03:39:30 tswett: that's fantastic 03:39:32 ah, to be young and innocent, and not completely antipathetic to chemistry. 03:39:39 antipathic? i forget 03:39:48 Antipastic. 03:39:50 tswett: i like this plan. the punitive tax pays for the incentive in its entirety! 03:40:18 Anyway, has anyone laughed at the Finnish in the topic yet? 03:40:40 no because i don't finnish 03:40:43 so 03:41:00 Quick, someone find a Finn! 03:41:07 Like... Linus Torvalds! Wait, does he speak Finnish. 03:41:11 i'm guessing it says "Why did Lena have to get old?" 03:41:18 I believe so 03:41:40 any asians in here atm? 03:42:06 Suffle Truffle 03:42:09 can you like... not do that maybe 03:42:18 Yeah sorry 03:42:36 Don't want to be an annoyance on my first day 03:45:30 farewekk 03:45:35 farewell* 03:45:36 by 03:45:44 -!- APott has quit (Quit: Page closed). 03:51:28 This program is actually not so complicated; it is a literate C program of less than 400 lines. 03:56:14 i killed firefox when it froze 03:56:26 and somehow now it has completely changed 03:56:39 like it's a different version that doesn't support vimperator any more? 03:56:44 could it have upgraded itself? 03:57:06 what is the latest firefox? 03:59:04 wharrgarbl 04:09:38 what. the. fuck. it's like i had a different firefox installed and i was auto-reverted and the one i was using just vanished. 04:09:44 maybe 04:09:49 something weird happened 04:10:05 I don't know what is the latest Firefox, and I don't know about all those other things either, sorry 04:24:11 reinstalling worked 04:24:18 OK 04:24:28 Maybe when it crashed it changed something 04:24:36 but for some reason i can't open lightbeam. the menu item it is supposed to create...isn't there. 05:08:57 -!- tertu has joined. 05:24:05 Well, Shogi just got a shout-out in Worm 05:24:50 Sgeo: What is that? I can play tsumeshogi but I don't know if that has anything to do with it? 05:25:02 Worm is a story I'm reading 05:25:10 About what? 05:25:38 Superheros and supervillains. Mostly villains. 05:25:53 http://parahumans.wordpress.com/about/ 05:25:56 And what is it about shogi? 05:27:09 A bunch of characters are talking about a dangerous group of enemies. They were describing them in chess terms. Someone suggested looking at it as a different game, and Shogi came up, because apparently of a rule about using captured pieces as your own 05:27:13 05:29:13 Yes, shogi dose have the rule about using captured pieces as your own (you keep them on your side off-board and can drop them onto a vacant space as a turn later on); shogi also has a rule that most pieces can promote by flipping over, and promotion is optional 05:33:05 -!- Sprocklem has joined. 05:33:53 But when I am playing Dungeons&Dragons game I do sometimes think of some of the situations resembling strange chess variants 05:34:32 (Especially non-existent ones) 05:37:58 Or possibly you can even compare whatever you are doing with Pokemon card or Magic: the Gathering (for me, probably Pokemon since I am very positionally player) 05:53:25 -!- Slereah has quit (Ping timeout: 272 seconds). 05:57:18 -!- conehead has quit (Quit: Computer has gone to sleep.). 05:57:20 -!- Ghoul_ has joined. 06:00:48 -!- trout has changed nick to variable. 06:02:25 Would they ever have any situation where they may compare to mahjong instead? 06:05:30 In Pokemon tournaments, is it permitted to tamper with the trainer ID number of a basic pokemon that, when traded, is forced to evolve under all circumstances? 06:08:33 -!- nooodl has quit (Quit: Ik ga weg). 06:21:24 I have determined that the following words are likely to be prepositions: of, in, to, with, by, for, from, at, on, into, during, In, within. 06:21:52 clap clap 06:21:56 zzo38: how did you know that those lines I said came from the logs for a day on which mahjong was discussed? 06:22:14 Here, let me give you guys even more words that are likely to be prepositions! 06:22:44 both, between, through, including, Within, after, before, During, include, Although, increases, if, repair, throughout, along 06:23:06 um. 06:23:34 I think that repair now on, I'm going to replace all repair my prepositions repair the word "repair". It's such an excellent preposition. 06:23:39 tswett: I did not know; I just guessed. 06:23:47 It is nothing but a lucky guess. 06:25:09 what is the likelihood that i am a preposition 06:25:30 shachaf: you're not in any of the clusters, so I can't say. 06:36:11 tswett: What did you use to determine that those words are likely to be prepositions? 06:36:23 Cluster analysis in R. 06:36:37 Buffalo buffalo repair buffalo repair buffalo repair repair buffalo. 06:37:07 I have read about R before. What is cluster analysis, though? 06:37:58 (Maybe I will try to look in Wikipedia and/or R documentation) 06:38:26 you put data points (words in this case) in n-dimensional space based on some parameters, and try to find clusters of points. 06:40:15 OK I found the examples of 2-dimensional clusters in Wikipedia. 06:45:34 Gotta sleep. Good night, everyone. 06:50:16 Can you make cluster analysis in SQL? 07:28:20 -!- Sprocklem has quit (Ping timeout: 240 seconds). 07:47:13 They say axiom of choice is equivalent to "the product of a collection of non-empty sets is non-empty". If the collection is allowed to be infinite, then I don't think it should necessarily apply. (But there are ZFC and ZF not C, so I suppose both ways can be correct but not together??) 07:48:11 How do you think of this? 07:48:41 looks like "AC but only for finite families" is weaker than ZFC but still independent of ZF? 07:50:27 oh, neverind, you can prove it from ZF 07:51:24 Yes, that is what that Wikipedia article says. 07:51:38 You don't think what should necessarily apply? 07:52:34 "There exists a model of ZF¬C which has an infinite set of real numbers without a countably infinite subset." some wacky stuff here 07:52:53 "There exists a model of ZF¬C in which there is a vector space with two bases of different cardinalities." wha 07:53:03 shachaf: That a product of an infinite collection of non-empty sets would necessarily be non-empty. 07:53:36 Bike: models are weird though. 07:53:45 true enough 07:54:11 i can't even imagine having two bases of different cardinalities though 07:55:08 i think "The Axiom of Choice is obviously true, the well-ordering principle obviously false, and who can tell about Zorn's lemma" kind of sums it up for me 07:55:19 what does "be" even mean 07:55:27 Bike: well, that's because you're imagining reasonable models :P 07:55:49 The axiom of choice is obviously true, and so is the axiom of determinacy. 07:56:02 Bike: It isn't obviously true to me. 07:56:13 As I explained. 07:56:14 elliott: i'm good at imagination 07:57:03 i can imagine an infinite number of pools of fish, and walking along from one pool to the next, taing a fish from each and putting it in a new pool 07:57:09 Bike: it's even better when you take away the law of excluded middle 07:57:24 so imo just do that already 07:57:26 it would smell nasty, but that's just a fact of life, when your life involves infinite numbers of fishes 07:57:32 what's even better 07:57:56 it's also a fact of life when your life involves a finite but large number of fishes, or finite but small fishes if they're close enough to you 07:57:59 or rotting 07:58:33 did you see that one talk, The Five Stages of Accepting Constructive Mathematics 07:58:54 yes. 07:58:57 Bike: i find your argument fishy 07:59:22 my imagination is not argumentative! 07:59:30 see? 07:59:35 no 07:59:38 (In ZFC, axiom of choice is obviously true. But the axiom of choice doesn't seems like the best model to me, and therefore ZFC also isn't.) 07:59:39 oerjan: do you find me fishy 08:00:07 shachaf: seagulls usually are 08:00:20 whoa jesus lebesgue was way later than i thought 08:00:22 you're a seagull 08:00:43 ooh deep 08:06:27 it's too late in the night to read tarski talk about what truth is, i feel 08:06:59 The axiom of dependent choice, when restricted to pointed sets, looks like OK to me, though. 08:07:28 thank you based point 08:08:12 Bike: imo read smullyan talk about tarski talking about what truth is?? 08:08:30 sounds harder 08:09:04 but smullyan is the best 08:09:20 but hard 08:11:02 you could listen to swan lake instead 08:11:21 too busy listening to post-whatever core revival 08:11:59 does it have drums in it 08:12:45 don't hear any. 08:13:06 well, it has one of those shaky things. 08:13:06 maybe you're deaf from all the drums 08:13:12 what shaky things 08:13:23 like maracas, bt i don't think they're exactly maracas. 08:14:46 this other track, definitely has light snares or something, though. 08:15:56 and uh, other drums too. 08:16:22 drums :'( 08:23:02 mo like dums 08:23:14 it took me seven minutes to think of that 08:23:47 Bike: instead of insulting things you should do the opposite of that 08:24:51 mo like yums 08:25:25 thx 08:28:29 music for yummies 08:40:00 Listen to a Famicom music. 08:40:13 good decision 08:42:12 zzo38: I don't have any Famicom musics. 08:43:20 shachaf: Look in Famicompo Mini; there are a lot, some with expansion audio and some without. 08:46:14 zzo38: I don't know Japanese. 08:56:27 shachaf: Some of the files are in Englihs. 08:56:49 s/Englihs/English/ 09:00:21 -!- oerjan has quit (Quit: leaving). 09:02:33 -!- Slereah has joined. 09:19:52 -!- carado has joined. 09:21:15 -!- shikhin has joined. 09:26:04 -!- shikhin has quit (Ping timeout: 240 seconds). 10:03:35 -!- ter2 has joined. 10:08:16 -!- tertu has quit (Ping timeout: 264 seconds). 10:09:21 -!- Taneb has joined. 10:14:49 -!- Koen_ has joined. 10:15:30 -!- Taneb has quit (Ping timeout: 244 seconds). 10:41:52 -!- MindlessDrone has joined. 11:05:12 Bike: SciPy hasn't really impressed me in terms of speed; as for MATLAB JIT, "I'unno", but it's clearly better than what it used to be. (Avoiding all explicit loops used to be even more of a priority, due to interpretation overhead.) 11:05:40 Bike: (Also I'm reminded of the existence of MATLAB pretty much every workday.) 11:06:14 I am wondering how easy it would be to do some of these things in SQL. I have done other statistical stuff in SQL successfully. 11:07:59 One example, maybe you make survey, store all responses in SQL tables, and then want to calculate the standard deviation of answers to the second question for the cases when the first question answer is "yes", and stuff like that. 11:08:56 SQL seems ideal for this things; SQL also seems ideal for a number of other things too. 11:09:50 A useful thing to have would be an aggregate which plots a graph of your data! 11:10:18 Something like SELECT XYPLOT(...) FROM ... WHERE ... 11:17:36 -!- zzo38 has quit (Remote host closed the connection). 11:21:44 greetings from the future 11:21:54 (8PM Sunday) 11:22:05 I proved that x86 is Turing complete ish with no registers 11:22:31 writeup forthcoming 11:23:49 "Death under ptrace" is a good name for a manpage section or a band 11:29:56 -ish? 11:30:16 and with which definition of no registers? 11:31:55 so, the opposite of "move only"? 11:32:08 I would gladly pay you tuesday for a register todat 11:32:08 y 11:32:12 I'd read "-ish" as the usual restriction on addressable main memory, but I'm also curious about which registers are left. Can't do much without rip and rsp ... 11:32:48 Well 11:32:53 and what about various control registers (eg for paging)? 11:32:54 If you have an infinite memory 11:33:02 then it's not x86 :) 11:33:06 Can you access every part of it with x86? 11:33:19 Because the addresses are limited, no? 11:33:23 Slereah: you can build a tape head for it 11:33:49 x86 is certainly big enough for a UTM, given the right peripheral(s) :) 11:34:31 The right peripheral is "an infinite device" 11:34:34 Where can I buy it 11:36:55 I haven't written out the exact rules yet but basically no instruction is allowed to depend on the contents of "normal" user registers i.e. rax rcx rdx rbx rsi rdi rsp (yes) rbp r8-r15, x87 and xmm/ymm/zmm/qmm/bumm/dumm/glumm 11:37:06 or the condition codes in eflags 11:38:58 you're allowed to depend on the control registers, debug registers, segment selectors, etc. to provide a sane flat memory model, but shouldn't write to them to do anything tricky 11:39:59 (mostly you can't from userspace) 11:40:35 and yes you are allowed to have an instruction pointer ;P 11:42:50 x86 lets you do a memory-indirect jump, i.e. load the word from a specified fixed address into %rip 11:42:53 and this turns out to be vital 11:43:11 oh I think I'm disallowing %rip-relative memory addressing too, although I haven't thought of a situation where it would be useful 11:43:17 hmm. how about an rip-relative bitset ;-) 11:43:46 I think the main challenge in this subset is moving data around 11:44:11 since to my knowledge there's no instruction which does a memory-memory move without any register involvement 11:46:12 anyway i have a solution for compiling brainfuck and I will write it up sometime when I'm not incredibly jet-lagged 11:47:34 it does use self-modifying code (but of course the restrictions must hold for every instruction actually executed, and not just the ones present statically) 11:49:12 (which I hope to demonstrate using a ptrace thingy that sets all those registers to zero after every instruction) 11:50:17 compiling from subleq or something like that might have been easier 11:52:43 ah, bts was the instruction I had in mind. 11:56:50 my ptrace(2) says "PTRACE_SYSEMU, PTRACE_SYSEMU_SINGLESTEP (since Linux 2.6.14)… These requests are currently supported only on x89." 11:56:56 x89: it's three better 11:57:30 Could be the 00089 11:57:31 hmm, it says x86 here 11:58:19 https://github.com/mkerrisk/man-pages/commits/d2ea1bd4bd128bc2a57f9ae8e677689a4d24a200 11:58:31 or rather https://github.com/mkerrisk/man-pages/commit/d2ea1bd4bd128bc2a57f9ae8e677689a4d24a200 12:18:23 -!- nooodl has joined. 12:38:56 -!- Phantom_Hoover has joined. 12:52:06 -!- Koen_ has quit (Quit: The struct held his beloved integer in his strong, protecting arms, his eyes like sapphire orbs staring into her own. "W-will you... Will you union me?"). 13:10:50 -!- Phantom_Hoover has quit (Ping timeout: 245 seconds). 13:15:06 -!- Phantom_Hoover has joined. 13:45:14 -!- Phantom_Hoover has quit (Ping timeout: 264 seconds). 13:47:00 -!- yorick has joined. 13:59:54 -!- Phantom_Hoover has joined. 14:34:59 ahahaha what the fuck 14:35:10 -!- tertu3 has joined. 14:35:33 the latin word for clitoris, so obscene that it appears exactly once in surviving literary texts, also means... gridiron: http://en.wiktionary.org/wiki/landica 14:38:43 -!- ter2 has quit (Ping timeout: 272 seconds). 14:49:22 -!- shikhin has joined. 14:53:27 -!- shikhin_ has joined. 14:55:11 -!- shikhin has quit (Ping timeout: 245 seconds). 14:56:48 -!- shikhin__ has joined. 15:00:14 -!- shikhin_ has quit (Ping timeout: 264 seconds). 15:02:08 -!- shikhin__ has changed nick to shikhin. 15:16:57 -!- nooodl_ has joined. 15:17:41 -!- shikhin has quit (Ping timeout: 245 seconds). 15:20:01 -!- conehead has joined. 15:20:20 -!- nooodl has quit (Ping timeout: 244 seconds). 15:34:23 -!- shikhin has joined. 15:39:39 fizzie: aight. just, wondering how much microotimization is hould bother trying, that's all 15:43:03 -!- tertu3 has changed nick to tertu. 15:51:31 -!- shikhin_ has joined. 15:52:11 -!- shikhin has quit (Ping timeout: 272 seconds). 15:54:07 supdup 15:54:28 -!- AnotherTest has joined. 15:55:26 -!- Phantom_Hoover has quit (Ping timeout: 264 seconds). 15:55:42 -!- carado has quit (Ping timeout: 252 seconds). 15:58:29 -!- shikhin__ has joined. 16:00:37 -!- shikhin_ has quit (Ping timeout: 248 seconds). 16:05:29 how does the words command work again 16:05:45 HackEgo: halp 16:07:52 `words -h 16:07:57 Usage: words [-dhNo] [DATASETS...] [NUMBER_OF_WORDS] \ \ options: \ -l, --list list valid datasets \ -d, --debug debugging output \ -N, --dont-normalize don't normalize frequencies when combining \ multiple Markov models; this has the effect \ of making larger dataset 16:08:11 That's how 16:12:30 HackEgo: You're kind of messy with all that whitespace. 16:12:51 `run echo `words -h` 16:12:53 Usage: words [-dhNo] [DATASETS...] [NUMBER_OF_WORDS] options: -l, --list list valid datasets -d, --debug debugging output -N, --dont-normalize don't normalize frequencies when combining multiple Markov models; this has the effect of making larger datasets more influential -o, --target-offset change the target length offset used in the word generati 16:14:38 -!- shikhin__ has changed nick to shikhin. 16:15:37 -!- Phantom_Hoover has joined. 16:17:54 -!- carado has joined. 16:38:06 -!- shikhin has quit (Ping timeout: 245 seconds). 16:44:38 -!- shikhin has joined. 17:23:24 -!- ^v has joined. 17:30:11 -!- Phantom_Hoover has quit (Ping timeout: 265 seconds). 18:08:21 -!- olsner has quit (Quit: Leaving). 18:17:10 -!- nooodl has joined. 18:20:45 -!- nooodl_ has quit (Ping timeout: 272 seconds). 18:24:05 -!- Oj742 has joined. 18:30:16 -!- zzo38 has joined. 19:03:44 -!- Taneb has joined. 19:28:00 now i'm learning how to say "clitoris" in all the languages of the world 19:28:03 could be useful 19:32:26 pimpsanappula 19:33:14 (well _some_ say klitoris) 19:40:07 -!- MindlessDrone has quit (Quit: MindlessDrone). 19:41:40 google can't handle that but suggests "pimppi nappula" and translates it as "pussy button" so... okay 19:41:48 -!- nisstyre has joined. 19:42:47 Do you intend to speak all languages of the world? That would be difficult. 19:44:21 Aaaaaaaah how do you do reduction formulae? 19:46:17 What reduction formulae? 19:46:55 For integration 19:47:01 only speaking all the clitori of the world, zzo 19:48:58 häpynypykkä 19:49:10 btw do these have to be _existing_ words? 19:52:03 google doesn't know that one either!! 20:05:42 -!- Frooxius has quit (Read error: Connection reset by peer). 20:06:19 -!- Frooxius has joined. 20:09:50 Can't say I've ever heard anyone use the words oklopol mentions. 20:10:10 (But they're certainly plausible.) 20:10:19 how does the second one work 20:11:16 (btw my initial comment was a response to P_H not just something I decided to do immediately on waking up) 20:15:45 Try "häpy nyppylä" in Google Translate. 20:15:48 It's sort of related to that. 20:17:01 that makes me think of the mons pubis and not the clitoris 20:23:18 -!- lambdabot has quit (Quit: requested). 20:26:00 That would be "häpykumpu". The connotations of the word "nyppylä"/"nypykkä" indicate a small thing. 20:26:13 ahh 20:27:31 -!- lambdabot has joined. 20:28:12 For the record, "häpykieli" is (alongside the already-mentioned "klitoris") the official word. For some reason. 20:29:49 "kieli" means... tongue? 20:31:35 yes 20:36:27 (is it bad all I can see in these words are "happy nipple" and "happy camper" and "happy clearly"?) 20:37:53 yes that's bad because it implies that regular nipples aren't happy 20:38:35 My nipples are quite sad right now 20:38:40 :/ 20:46:49 Is there such a sound synthesis as "filter modulation"? 20:53:05 how do i determine the what size a file will be printed at? 20:53:20 quintopia: What file? 20:53:33 this printer take 1200 input dpi, so what is the pixel dimensions of a 2"x2" jpg? 20:54:46 It would seem like 2400 but I don't know if the file has its own DPI 20:55:37 why would a jpg have its own dpi 20:55:50 I don't know if JPEG supports that or not. 20:56:07 However, ImageMagick does support that. 21:00:53 i've had some success opening things in Gimp and explicitly setting the DPI before printing 21:01:36 kmc: I know that ImageMagick can do that too, although I have never actually tried it. 21:03:50 -!- lambdabot has quit (Quit: requested). 21:07:48 -!- lambdabot has joined. 21:14:27 elliott: Is lambdabot on a new server? 21:15:20 shachaf: yes. mine. 21:17:07 -!- nooodl_ has joined. 21:19:53 You're running lambdabot instead of elliott now? Or just your server? 21:20:17 I'm running it. Elliot more or less talked me into taking over. :) 21:20:23 congrats 21:20:37 -!- nooodl has quit (Ping timeout: 248 seconds). 21:21:02 Oh. I didn't see it mentioned in #-ops. 21:21:47 That's probably because I'm blissfully unaware of that channel :) 21:21:58 Wow, has lambdabot changed hands twice this year now? 21:27:14 -!- ais523 has joined. 21:50:25 how can america claim to be a world leader in anything when we don't even properly clean our butts after pooping 21:54:49 -!- tertu has quit (Ping timeout: 272 seconds). 22:01:31 -!- john_metcalf has joined. 22:02:02 -!- tertu has joined. 22:08:56 http://img.lulz.net/src/lwCF9Lu.jpg 22:10:19 Turing didn't deserve that. 22:11:02 (Make it a Bill Gates quote and I'll probably laugh. ;-) ) 22:12:04 Heh 22:12:17 http://img.lulz.net/src/einstien4.jpg 22:12:20 What about that guy 22:12:24 Make it a picture of Bill Gates but keep the text and I'd be quite amused (for the first one) 22:13:07 -!- Taneb has quit (Quit: Leaving). 22:27:51 -!- carado has quit (Ping timeout: 252 seconds). 22:30:44 -!- Phantom_Hoover has joined. 22:32:16 -!- AnotherTest has quit (Ping timeout: 264 seconds). 22:36:19 -!- shikhin_ has joined. 22:39:50 -!- shikhin has quit (Ping timeout: 264 seconds). 22:46:16 `olist 929 22:46:18 olist 929: shachaf oerjan Sgeo FireFly 22:46:34 I'll be shocked if someone else got there first, given that I checked a few hours ago and it wasn't up 22:47:13 thais 22:50:20 ais523: Thanks! 22:55:29 Currently the Digi-RGB specification has no "standard resolution"; perhaps I should mention 320x240 at 30 fps or something like that as a mode which all Digi-RGB displays are expected to support, so that a video card can use it when there is no other modes available. 23:03:53 -!- tertu has quit (Ping timeout: 252 seconds). 23:06:03 -!- Vorpal has quit (Ping timeout: 260 seconds). 23:08:48 -!- Vorpal has joined. 23:11:36 To comment on a discussion that finished hours ago, base JPEG standard does not support encoding the "physical size" (or resolution) of an image, but (widely supported) extensions (JFIF, IPTC, ...) do. 23:11:54 fizzie: OK. 23:12:18 -!- oerjan has joined. 23:15:06 DoubleFuck could even be extended to 32 tapes by using the low 3-bits of a byte for the command and high 5-bits for the tape number. 23:15:44 quite the name for a language 23:16:11 I guess i’ll link this here, too. “Testing whether you can safely sh-quote any byte string (consisting of no null bytes) by substituting ' with '\'' and adding ' on either side. Works in bash, dash, mksh, posh, zsh. Fails in csh, ksh, lksh, pdksh.” https://gist.github.com/ion1/7405148 23:16:29 zzo38: i like that 23:16:48 http://sprunge.us/BVHH -- that's from a couple of random example .jpg files in ~/tmp/ 23:17:36 One had the resolution in Exif metadata, one in JFIF, and one redundantly in all three of JFIF, Exif and XMP. 23:18:11 -!- shikhin__ has joined. 23:20:35 -!- shikhin_ has quit (Ping timeout: 272 seconds). 23:22:25 -!- shikhin has joined. 23:23:41 -!- shikhin__ has quit (Ping timeout: 252 seconds). 23:28:31 -!- nooodl_ has quit (Quit: Ik ga weg). 23:29:20 -!- shikhin_ has joined. 23:30:51 !run echo "t'est" | sed 's/'\''/&\\&&' 23:30:57 `run echo "t'est" | sed 's/'\''/&\\&&' 23:30:59 sed: -e expression #1, char 9: unterminated `s' command 23:31:05 `run echo "t'est" | sed 's/'\''/&\\&&/g' 23:31:07 t'\''est 23:31:13 smashing 23:32:12 -!- shikhin has quit (Ping timeout: 265 seconds). 23:32:43 -!- Vorpal has quit (Ping timeout: 244 seconds). 23:33:34 -!- Vorpal has joined. 23:33:43 ion: cool 23:34:09 that's a nice example of using quickcheck to test something that isn't haskell code 23:34:30 i always used '"'"' instead of '\'' but the latter is probably clearer 23:34:53 'but it'"'"'s so much fun' 23:35:06 Either is fine, '\'' is just shorter. 23:36:01 Disk space and bandwidth is really expensive after all. 23:36:47 -!- shikhin_ has quit (Ping timeout: 272 seconds). 23:38:34 i don't know, \ might weigh more than "" 23:41:53 <^v> i dont know much about haskell, but once its compiled i dont think it matters 23:45:01 -!- tertu has joined. 23:45:21 `run echo ''\'' | sed '\''h;s/'\''\'\'''\''/&\\&&/g;s/^/echo '\''\'\'''\''/;G;s/\n//;'\''' | sed 'h;s/'\''/&\\&&/g;s/^/echo '\''/;G;s/\n//;' 23:45:23 echo ''\'' | sed '\''h;s/'\''\'\'''\''/&\\&&/g;s/^/echo '\''\'\'''\''/;G;s/\n//;'\''' | sed 'h;s/'\''/&\\&&/g;s/^/echo '\''/;G;s/\n//;' 23:46:17 `run echo ''\'' | sed '\''h;s/'\''\'\'''\''/&\\&&/g;s/^/`run echo '\''\'\'''\''/;G;s/\n//;'\''' | sed 'h;s/'\''/&\\&&/g;s/^/`run echo '\''/;G;s/\n//;' 23:46:19 ​`run echo ''\'' | sed '\''h;s/'\''\'\'''\''/&\\&&/g;s/^/`run echo '\''\'\'''\''/;G;s/\n//;'\''' | sed 'h;s/'\''/&\\&&/g;s/^/`run echo '\''/;G;s/\n//;' 2013-11-11: 00:09:55 -!- tertu has quit (Ping timeout: 244 seconds). 00:13:26 -!- tertu has joined. 00:13:26 -!- TodPunk has quit (Quit: This is me, signing off. Probably rebooting or something.). 00:13:55 -!- yorick has quit (Remote host closed the connection). 00:17:27 -!- nooodl_ has joined. 00:21:13 -!- muskrat has joined. 00:23:02 -!- Phantom_Hoover has quit (Remote host closed the connection). 00:35:17 * oerjan notes int-e as the new person to shout at 00:56:24 -!- ais523 has quit. 00:59:10 -!- tertu has quit (Ping timeout: 245 seconds). 01:11:01 -!- Koen_ has joined. 01:12:04 -!- Koen_ has quit (Read error: Connection reset by peer). 01:20:54 -!- tertu has joined. 01:44:05 anyone here know of a good online collaborative mind-mapping app that lets you make full on graphs (not just trees)? 01:51:51 quintopia: I don't know of any at all, sorry. What are you intending to make? 01:57:50 sorry, those are outlawed to prevent evil ai takeover. 02:12:55 -!- Oj742 has quit (Ping timeout: 245 seconds). 02:27:17 zzo38: i want to map all of human knowledge down into learnable chunks 02:29:12 quintopia: That would be really difficult, I think. 02:34:06 zzo38: well, i'll have to hire some people to do it for me 02:34:13 but first, a tool! 02:36:30 Yes, a tool would help even if you are making something else. 02:37:09 how do you map down. usually i just map, without a particular direction 02:57:41 -!- tswett has left ("http://quassel-irc.org - Chat comfortably. Anywhere."). 03:00:12 -!- muskrat_ has joined. 03:00:56 -!- muskrat has quit (Disconnected by services). 03:01:00 -!- muskrat_ has changed nick to muskrat. 03:17:27 -!- nooodl__ has joined. 03:21:09 -!- nooodl_ has quit (Ping timeout: 248 seconds). 04:05:35 -!- nisstyre has quit (Quit: Leaving). 04:07:07 -!- tswett has joined. 04:07:17 Okay, okay, I've got it. 04:08:01 What have you got now? 04:09:03 We can claim that no set is bigger than the set of all natural numbers, as long as we deny that this fact entails that there's a mapping from the set of all natural numbers onto any arbitrary set. 04:09:57 How can you deny that? 04:10:47 Maybe it is possible, but in what mathematical models is that possible? 04:11:03 Every first-order theory that admits infinite models admits countable models. 04:11:42 Meaning there's a countable model of ZFC. And in a countable model of ZFC, all infinite sets are the same "size", in some sense, even though they have different cardinalities in the model. 04:11:54 Ah, OK, then. 04:15:35 Do you have example, please? 04:18:16 -!- Slereah has quit (Ping timeout: 241 seconds). 04:29:54 What kind of sense is the same "size" even though they have different cardinalities 04:44:29 -!- nooodl__ has quit (Ping timeout: 272 seconds). 04:46:00 Can you explain it please? 04:48:58 it's rather trivial: you have a model of ZFC inside ZFC. by the inner logic of the model, the sets don't have the same cardinality because the model doesn't contain any bijection between them. but the whole model is a countable set in the outer ZFC, which therefore has such a bijection which is not inside the model. 04:50:02 so all the sets of the inner model are finite or countable from the viewpoint of the outer ZFC. 04:51:06 (technically the outer theory needs to be ZFC+"ZFC is consistent", i think) 04:51:51 (to be sure such an inner model exists) 04:52:18 they should use that axiom all the time in ZFC. 04:52:19 just in case. 04:53:02 elliott: But then it isn't really just plain ZFC, isn't it? 04:54:00 elliott: the advanced users (e.g. grothendieck) tend to use large cardinality axioms for this 04:54:34 What are "large cardinality axioms"? 04:54:38 but by godel's completeness theorem, just "ZFC is consistent" is what you need for a first-order model. 04:54:54 -!- Oj742 has joined. 04:55:07 zzo38: axioms that say that certain enormous cardinalities exist. this tends to imply thinks even stronger than consistency of ZFC. 04:55:37 i once went to a talk about that 04:55:48 i think lexande is an expert in all those things 04:56:28 e.g. strongly inaccessible cardinals is one kind, which iiuc imply that not only do you have models, but in the model sets are still represented as their set of elements in the outer theory. 04:57:32 the immigration & security checks to enter Republic of Korea from United States of America are nothing compared to the checks for entering Samsung Digital City from Republic of Korea 04:57:46 oerjan: yeah, just having set models of ZFC isn't very strong at all by the standards of large cardinal assumptions 04:57:48 kmc: are you in korea 04:57:55 (basically the sets smaller than the smallest inaccessible cardinal are a model in the most intuitive way) 04:57:58 indeed it's just about the weakest you'd consider 04:58:01 iirc there's some theorem about problems if you have "These axioms are consistent" as one of your axioms 04:58:06 but it certainly implies CON(ZFC) 04:58:14 http://en.wikipedia.org/wiki/L%C3%B6b's_theorem 04:58:18 shachaf: I think I might be in Samsung 04:59:37 Sgeo: yes that's godel's second incompleteness theorem 05:00:10 they have effective control of this territory 05:00:32 Sgeo: yes, but "there are set models of ZFC" is an extra axiom on top of ZFC 05:00:51 -!- ^v has quit (Quit: http://i.imgur.com/MHuW96t.gif). 05:01:06 so once you have that, you can happily prove ZFC itself is consistent, though the extra axiom might not be 05:01:35 if you have inaccessible cardinals then you have lots of set models of ZFC, and CON^n(ZFC) for any reasonable n, etc 05:03:04 -!- Oj742 has quit (Quit: irc2go). 05:03:22 -!- ^v has joined. 05:04:45 and that's still pretty small by the standards of large cardinal properties 05:04:47 http://cantorsattic.info/Upper_attic 05:05:56 ah the kunen inconsistency, i recall seeing that mentioned. 05:06:40 is that list totally ordered :P 05:07:01 uh, well each of the entries on that list potentially defines a proper class of cardinals 05:07:11 but it's ordered by how big the smallest in the given class is 05:07:47 and yeah, every time you come up with one of these, you don't know if it's consistent 05:08:17 and you can only appeal to even larger cardinal assumptions for proof of its consistency, which isn't much comfort 05:09:15 and yeah, Reinhardt defined a large cardinal which turned out to be inconsistent with ZFC (though maybe not with ZF) 05:10:03 but anything on that list might be inconsistent 05:10:08 indeed ZFC itself might be inconsistent 05:10:38 I don't really like axiom of choice anyways, although maybe ZF + axiom of dependent choice restricted to pointed sets; does that work? 05:11:25 zzo38: cardinalities are a mess without choice 05:12:32 lexande: A mess in what way, and do some weaker axioms do anything with it? 05:12:42 without choice, cardinalities are not always comparable; this is equivalent. 05:13:15 you don't even have |A×A|=A without choice 05:13:42 Well, I am not so sure that they should be always comparable and all of that stuff anyways 05:13:50 yeah, what oerjan said 05:14:02 also does everybody know the story about that? 05:14:23 Which story? 05:14:34 i don't remember on the spot whether i know it 05:15:22 Even if you aren't using ZFC doesn't imply ZF + not axiom of choice, though, I think! 05:15:31 wait, is this that "an equivalence between two obviously X statements isn't interesting" story 05:16:12 Tarski proved that "|A×A|=|A| for all infinite sets A" was equivalent to the axiom of choice, and tried to publish this theorem in Comptes Rendus. 05:16:40 It was refereed by Frechet and Lebesgue. 05:16:42 Both wrote letters rejecting the article. Fréchet wrote that an implication between two well known truths is not a new result. And Lebesgue wrote that an implication between two false statements is of no interest. Tarski said that he never again submitted a paper to the Comptes Rendus. 05:17:24 Oh, yes. 05:18:47 clearly this is something that should happen more often. 05:20:47 Neither of those rejections seem valid to me since they aren't necessarily going to be known true or false; axiom of choice is not used in all systems anyways! So, such thing still can be a new result and can be of interest, I think. Even if they are false statements. 05:21:42 But I don't really agree with the axiom of choice anyways, nor with the other statement necessarily, either. 05:24:52 zzo38: of course they weren't valid, that's why the story has become an anecdote. 05:28:06 this happened at a time when the idea that there was only one set of truths in mathematics was coming crashing down, but neither reviewer had realized it, even though they had made inconsistent conclusions within the mess. 05:28:19 imo 05:28:21 . 05:30:02 zzo38: yes, thatsthejoke.jpg 05:31:11 `pastequotes zzo38 05:31:18 http://codu.org/projects/hackbot/fshg/index.cgi/raw-file/tip/paste/paste.1654 05:32:54 kmc: still waiting on zzo38_ebooks 05:36:39 The joke is a JPEG picture? 05:36:54 `delquote 665 05:36:59 ​*poof* When you die in Canada, you die in real life. 05:40:06 `revert 05:40:10 Done. 05:40:32 oerjan: why 05:40:42 stupid question 05:41:32 because i don't like you deleting that 05:41:56 it is not a good quote for the quote list 05:42:56 Maybe there should be an option to hide quotations without renumbering the rest, and an option to tell it whether or not to include hidden quotations in a search. 05:48:03 -!- ^v has quit (Remote host closed the connection). 05:50:40 shachaf: yes it is 05:51:08 no, it's just quoting an internet comic strip 05:51:23 yeah, zzo38 quoting an internet comic strip 05:52:56 I think the quotation came from elsewhere and they quoted the comic strip, perhaps. 05:53:10 (But I do not remember.) 05:53:35 perhaps 05:56:26 http://cantorsattic.info/Upper_attic is some crazy shit 05:56:59 http://cantorsattic.info/Totally_indescribable#totally_indescribable lol? 05:57:09 -!- conehead has quit (Quit: Computer has gone to sleep.). 06:00:07 oklopol: they can't be described. 06:02:30 uhttp://cantorsattic.info/Subtle#Subtle_cardinal Weakly ineffable cardinals are limits of totally indescribable cardinals. [1] ([3] for proof) 06:02:36 -u 06:03:04 and of course huge cardinals is a specific term. 06:03:16 i'm fine with them being actually indescribable, but then i wonder what that proof looks like. 06:05:34 it's like, whoa, you know 06:06:52 "Whenever the context-sensitive language corresponding to the set of finite configurations cannot be described by a context-free or simpler grammar, the problem of recognizing words in the language is PSPACE-complete with respect to the lengths of these words (eg. [28])." 06:06:57 fun reading wolfram 06:08:46 this must be something about finite configurations whatever that is, because there are certainly context-sensitive languages in between context-free and PSPACE-complete 06:09:18 (e.g. anything theta(n^k) for k > 3) 06:10:15 also he says the language of the limit set of a CA can in general be Pi^0_1, which he then refers to as properly RE, and type 0. 06:10:38 well, assuming P != PSPACE, of course. 06:10:41 oerjan: this is about the limit sets of cellular automata, and [28] is a standard complexity theory reference 06:10:46 ok 06:11:32 this paper is like 60 pages, it contains one proof, phrased as "it seems X that because Y" 06:11:38 argh 06:11:46 "it seems that X because Y" 06:13:57 seemingly X swimmingly Y 06:14:05 -!- TodPunk has joined. 07:02:44 -!- realz has quit (Ping timeout: 244 seconds). 07:05:13 -!- ^v has joined. 07:05:35 -!- realz has joined. 07:05:37 -!- realz has quit (Changing host). 07:05:38 -!- realz has joined. 07:13:24 does JFIF support any codecs other than JPEG 07:13:32 JFIF / EXIF 07:17:52 "Formally, the Exif and JFIF standards are incompatible. This is because both specify that their particular application segment (APP0 for JFIF, APP1 for Exif) must be the first in the image file. In practice, many programs and digital cameras produce files with both application segments included. This will not affect the image decoding for most decoders, but poorly designed JFIF or Exif parsers may not recognise the file properly." 07:18:13 i like how standard-compliant is poorly designed 07:21:07 Postel's law and all that. 07:25:04 few things make me angrier than postel's law 07:26:03 really 07:28:50 yeah 07:29:13 the robot-toilet in Samsung Digital City has a warning not to smoke while you're sitting on it 07:31:30 -!- FreeFull has quit. 07:31:34 don't do it kmc 07:32:26 there are, like, six different reasons for me not to smoke while sitting on the robot toilet 07:32:32 the warning is just one of them 07:32:42 kmc: does it make you go postel 07:32:51 <3 07:34:00 kmc: how many of those allow you to sit on the robot toilet in the first place 07:35:59 -!- ^v has quit (Quit: http://i.imgur.com/MHuW96t.gif). 07:36:40 -!- tertu has quit (Quit: Leaving). 07:37:18 @ask ^v why do you keep badgering us 07:37:18 Consider it noted. 07:52:11 It is not only I who hates the layout syntax of Haskell and Python (at least in Haskell it can be disabled). So does Yin Wang (someone who also discussed the call/cc "Yin-Yang Puzzle", and is linked from Wikipedia for this purpose). 07:52:48 i do not hate haskell layout, but i do deny it my essence 07:52:52 zzo38: what's so bad about it, tho 07:57:22 kmc: Some of the things are those they describe in there. 07:58:11 One thing mentioned there is that a single keystroke can make the program wrong. 07:58:42 That is different from my own reason which is that it confuses the syntax a lot, unnecessarily. 07:59:13 For actual tree structures, with one record per line, layout syntax does work, but still isn't necessarily best way. 07:59:25 However, actual programs aren't quite like that, for various reasons, nor should they be. 07:59:50 a single keystroke can make the program wrong in a lot of other ways, too 08:00:13 kmc: Yes, that is true, I know; also, it isn't the reason I use anyways like I said. 08:01:22 Such a thing isn't really much of a problem with programming in Haskell, though, since you can use non-layout mode if you prefer. (You can even mix layout and non-layout in one file, although I do not recommend this.) 08:06:15 i mean, granted, "there are other ways to have bugs" is a shitty (and depressingly common) argument against a feature which prevents bugs 08:06:34 but my experience with Haskell is that bugs due to bad layout, which also pass the typechecker, are very rare 08:06:55 (but also, bugs that hit the typechecker aren't free, and it takes experience to recognize when one has occured due to bad layout) 08:07:05 a Haskell IDE which draws in ghostly { ; } for you would be really cool 08:07:37 but the point of layout is that it's visually obvious... 08:07:46 like, you might as well just use non-layout syntax then 08:08:12 Yes, due to the typechecker it does do this, which Python doesn't. 08:08:59 kmc: People have used that as an argument when trying to figure out what syntax for applicative-do should be like. 08:09:14 There have been various strange proposals. 08:10:05 elliott: well you could turn it on specifically when you're learning the layout rules, or when you hit a bug that you suspect is due to bad layout 08:10:24 it could even use a different bgcolor for every layout block!!!! like some scheme editors 08:10:30 I really don't like all that built-in do-notation and stuff and think macro-syntax should be used instead. 08:12:02 kmc: All of those IDE ideas have been discussed in Yin Wang's article, actually. (They also mentioned "syntax considered harmful"; I partially agree with that and think that macro-syntax is a better idea anyways, which also avoids some of these problems) 08:12:19 (They didn't mention macro-syntax, though. I did.) 08:12:56 zzo38: what do you think of Rust's macro system? 08:13:44 kmc: I have looked at the documentation but don't really know much about how good it is; I haven't paid a lot of attention to Rust in general so I don't really know a lot about that. 08:13:55 fair 'nuff 08:13:55 -!- KingOfKarlsruhe has joined. 08:21:32 (And there are a few other Haskell programmers who prefer non-layout, too. But like I said it doesn't really matter much since using one or the other style doesn't prevent a module from being imported.) 08:25:17 I don't know if adding macro-syntax to the existing system would cause problems with layout syntax. If so, it could still be used in non-layout mode only, or possibly you could allow user-defined keywords to specify if they introduce a block, and if so check if there is a { after it whenever it occurs. 08:27:51 My (limited) understanding is that the parser emits { ; } block tokens based on indents/dedents, so I wouldn't think it'd impact macros 08:30:14 FireFly: it also emits }'s on syntax errors 08:31:43 that is, if ending a block in a spot can make it parse the next token, it will do so. 08:31:54 *an indentation block 08:36:26 Yes, I think it does that too 08:53:59 -!- carado has joined. 09:03:11 I thought of something, which is, if it can be made a kind of sequent calculus that can have not only multiple sequents above the line but also supports multiple sequents below the line? 09:07:09 -!- oerjan has quit (Quit: leaving). 09:17:30 zzo38: so a proof would be a DAG rather than a tree? 09:21:05 I am skeptical of macro systems where you aren't just running normal code at compile time 09:22:10 because sometimes you just need that, and macros are a feature of last resort, so do you really want a last resort macro system and another almost-last-resort system 09:25:03 I don't really think macros should be a feature of last resort. 09:25:18 kmc: Yes I suppose so, then a proof will be a DAG. 09:26:56 and I'm skeptical of this idea that macro systems absolutely need to enforce hygeine, as opposed to providing hygeine tools for the macro author 09:27:27 it seems like when I write a macro in C or Haskell or Rust, often as not I *do* want to do something tricky with binders 09:27:39 kmc: I, too; I think it should provide hygeine rather than enforce it 09:28:02 I'm sure I would feel differently if I programmed in Scheme but, well 09:28:37 I think part of why macros aren't a feature of last resort in Lisps is that you don't have a static type system anyway, so you don't lose as much by abstracting on the syntactic level rather than the semantic level 09:29:42 I do not think macros should ever be only a feature of last result. My opinion is that do-notation in Haskell should rather be defined as a macro in Haskell, instead of built-in, too. 09:29:59 zzo38: but abstracting on the semantic level is so much nicer 09:30:02 easier to reason about 09:30:13 Also consider Forth, where the compile-time and run-time are really the same thing, and macros are really just programs. 09:30:21 you can think more about what things are rather than how they're spelled 09:30:22 kmc: You can do both! 09:30:50 zzo38: yes, but I think the phase distinction is useful, even though it should be possible to nest (so you can compile code at runtime, and run code at "compile time") 09:30:52 (And many standard macros can be defined in a standard library so that you don't normally need to define your own, if this would help, too!) 09:31:10 the phase distinction is useful because it's where type checking happens 09:31:47 (I don't actually care if machine code is generated there or later; some languages with such a phase distinction for 'static' checking might still benefit greatly from a JIT implementation) 09:32:56 Yes, depending on the programming language in use, such a phase distinction would be very useful. 09:34:02 zzo38: your DAG proof idea is interesting; do you have an idea of a system which would be nice to express that way? 09:35:07 kmc: I don't actually know that. 09:36:35 also there has been discussion of a Template Haskell dialect where the type of a metaprogram includes the type of the program it produces 09:36:39 and I think MetaML works this way 09:37:07 but I think most of the practical examples of useful macros can't be typed, then 09:38:33 I have seen about Template Haskell with typed metaprograms; still is useful even to have typeless metaprograms too though. But being typed may also help in some ways, and may allow some additional kinds of macros to be made in a few cases. 09:38:59 how would it allow additional kinds of macros? 09:39:41 I am not sure, but depending on what other features are implemented there might be a possibility, or maybe not; I don't know for sure either way. 09:41:10 okay 09:41:15 if you can think of an example, let me know! 09:41:32 OK 09:42:16 Servo already has a number of metaprograms and they are mostly for converting specification formats (e.g. WebIDL) into executable code 09:42:23 none of which can be done within the Rust macro system :( 09:44:39 and that kind of thing won't admit typing metaprograms by their output 09:46:23 In that case then it does seem Rust macro system does have some problems. Perhaps just allowing macros to call executable Rust programs at compile-time, would that help at all? 09:56:04 -!- AnotherTest has joined. 09:57:26 -!- shikhin has joined. 10:00:57 -!- KingOfKarlsruhe has quit (Quit: ChatZilla 0.9.90.1 [Firefox 25.0/20131025151332]). 10:18:06 -!- Slereah has joined. 10:22:50 -!- zzo38 has quit (Remote host closed the connection). 10:23:14 -!- shikhin_ has joined. 10:24:28 -!- shikhin has quit (Ping timeout: 264 seconds). 10:31:16 -!- Taneb has joined. 10:32:24 -!- Taneb has quit (Remote host closed the connection). 10:32:30 -!- Taneb has joined. 10:32:46 Would I be correct to say matrix multiplication forms a category? 10:35:06 -!- nooodl has joined. 10:36:01 Where the category arrows are matrices and objects are dimensons 10:46:49 -!- Taneb has quit (Remote host closed the connection). 10:46:57 -!- Taneb has joined. 10:47:46 -!- Taneb has quit (Client Quit). 11:11:34 -!- Bike has quit (Ping timeout: 265 seconds). 11:15:47 @tell Taneb neat, I suppose it does and it would be isomorphic to http://en.wikipedia.org/wiki/Category_of_vector_spaces , or equivalent in the sense of http://en.wikipedia.org/wiki/Equivalence_of_categories anyway 11:15:47 Consider it noted. 11:16:50 "For example, the dimension theorem for vector spaces says that the isomorphism classes in K-Vect correspond exactly to the cardinal numbers, and that K-Vect is equivalent to the subcategory of K-Vect which has as its objects the free vector spaces Kn, where n is any cardinal number." 11:20:46 you'll invent categories if you try to extend monoids to be "typed" to support matrix multiplication 11:21:03 i was going to say something about vector spaces of uncountably infinite dimension and aren't they super weird 11:21:58 but then I remembered that functions A→K for an uncountable field K are such a vector space and seem nice and reasonable (as much as any uncountable thing can be nice) 11:22:46 or even for a countably infinite field K 11:23:47 er no, it depends on the cardinality of A not K, I think? 11:23:50 * kmc <--- not a mathematician 11:25:59 -!- yorick has joined. 11:26:03 @tell zzo38 yes that would help; Rust already has a thing called "syntax extensions" which are invoked the same way as macros but can run arbitrary Rust code, unfortunately you can't define a new one except by editing the compiler 11:26:03 Consider it noted. 11:26:44 @tell zzo38 also there are other problems with macros such as, they can't be exported from a compilation unit, and the scoping / module exporting is different from everything else, but these are seen as bugs to be fixed 11:26:44 Consider it noted. 11:28:04 -!- Bike has joined. 11:29:13 hi Bike 11:30:22 -!- shikhin_ has quit (Ping timeout: 244 seconds). 11:52:17 -!- muskrat has quit (Quit: Leaving). 11:59:42 -!- Koen_ has joined. 12:18:23 -!- Taneb has joined. 12:20:22 -!- shikhin_ has joined. 12:21:38 kmc: yeah, I realised it in the context of their relation to set relation compositions 12:26:18 -!- shikhin_ has changed nick to shikhin. 12:29:10 -!- Sgeo has quit (Read error: Connection reset by peer). 12:39:41 -!- Ghoul_ has quit. 12:48:57 -!- Taneb has quit (Quit: Page closed). 12:52:55 -!- shikhin has quit (Ping timeout: 252 seconds). 13:02:16 -!- muskrat has joined. 13:06:50 -!- muskrat has quit (Client Quit). 13:07:08 -!- shikhin has joined. 13:09:44 -!- boily has joined. 13:10:11 -!- metasepia has joined. 13:13:19 -!- shikhin_ has joined. 13:15:57 -!- shikhin has quit (Ping timeout: 272 seconds). 13:16:08 -!- Deewiant has quit (Quit: Viivan loppu.). 13:20:48 -!- shikhin__ has joined. 13:22:14 -!- shikhin__ has changed nick to shikhin. 13:23:38 -!- shikhin_ has quit (Ping timeout: 264 seconds). 13:24:30 -!- shikhin_ has joined. 13:27:01 -!- shikhin has quit (Ping timeout: 248 seconds). 13:31:35 -!- shikhin__ has joined. 13:33:49 -!- ais523_ has joined. 13:33:59 -!- ais523_ has quit (Changing host). 13:33:59 -!- ais523_ has joined. 13:33:59 -!- ais523_ has quit (Changing host). 13:33:59 -!- ais523_ has joined. 13:34:19 -!- shikhin_ has quit (Ping timeout: 272 seconds). 13:35:11 -!- nooodl_ has joined. 13:38:45 -!- nooodl has quit (Ping timeout: 248 seconds). 13:45:58 good chmæric mœrning! 13:48:51 fizzie: what were we discussing concerning a possible zeta? I kinda had a long weekend (including, but notwithstanding, missile launches) 13:49:25 The list popular Adobe passwords. 13:50:03 oh! indeed. 13:51:17 It might not be as good a fit as, say, general word frequencies, which are the canonical Zipf's law example, but still. 13:55:01 everything is either zipf, branford, poisson, gamma, or uniform. outside of that, it's a weird curve invented by sadistic statistics teachers. 13:55:55 -!- shikhin_ has joined. 13:57:42 you know how algol 68 allows spaces in identifiers? 13:57:51 algol 60 also allows spaces in identifiers, but it's space-insensitive 13:57:58 so "foobar" and "foo bar" are the same identifier 13:58:16 if you want an identifier with the same name as a keyword, you add internal spaces to mark it as not being the keyword 13:58:33 -!- shikhin__ has quit (Ping timeout: 252 seconds). 14:00:40 haha: Algol 60 defines the meanings of "true" and "false" as "obvious" 14:02:49 The simple days gone by. 14:02:52 what about file_not_found? 14:03:31 ~eval succ False 14:03:34 Error (1): 14:03:36 ~eval succ False 14:03:38 True 14:04:06 fungot: how did you become the Best Bot? how did you overcome your Error (1) phase? 14:04:07 boily: come on now, it is installed. ( require-extension ( srfi 1 13 14)) instead 14:04:18 fungot: a good tip. I'll keep that in mind. 14:04:18 boily: except in university oo projects page on toreun.org, but i 14:04:20 aha, algol 60 defines whitespace as not existing and freely usable anywhere 14:04:45 hmm... sorear's interesting interpretation of the INTERCAL manual may actually be correct 14:04:56 he interpreted it as permitting whitespace within keywords, which is something that simply hadn't occured to me at all 14:05:12 but at least one other language that was around at the time did that too... 14:06:00 PL EAS EDO N'T DO THAT! 14:08:05 int-e: hi! were you `relcommed already? did you appear during the weekend? 14:08:19 int-e: that doesn't do what you expect 14:08:31 the DO ends the PLEASE DON'T and then starts a new command 14:08:41 so you get "PLEASE DON'T" (a no-op), followed by "DO THAT" (not a no-op) 14:08:50 I guess you wanted it parsed all as one statement? 14:14:06 boily: There's a library on multivariate Bernoulli distributions that I believe gets some "real use" on 0-1 data. 14:14:16 -!- Bike has quit (Ping timeout: 265 seconds). 14:15:31 ais523_: I did, but I didn't really think about it :) 14:15:47 boily: I guess I wasn't. 14:15:56 accidentally leaving a DO in a middle of a comment is an occupational hazard of INTERCAL 14:16:07 boily: I've been here before, but this time lambdabot dragged me here :) 14:16:19 leaving disguised DOs in code intentionally to produce funny error messages is one of the joys 14:16:28 (even Donald Knuth has been caught doing it on occasion) 14:17:23 my most notable intercal accomplishment is a rot13 filter (50 lines without using standard library.) ... and without comments :) 14:17:31 boily: (I believe there's also a related saying, something like "in the dark, all cats are Gaussian".) 14:17:48 oh, you're responsible for the rot13 in the pit? neat! 14:18:35 nope, that's a different one 14:18:40 ah right 14:18:56 I guess I'm now duty-bound to add yours too, if it's appropriately licensed 14:19:04 because the pit is meant to be a collection of all known INTERCAL programs 14:19:14 (except CADIE, she's too independent-minded and also under the wrong license) 14:20:14 -!- augur_ has changed nick to augur. 14:21:13 http://int-e.eu/~bf3/tmp/myrot13.i (it's my code, do whatever you want with it. I'd put it in the public domain except that I can't.) 14:21:25 I'm at work 14:21:30 but I'll look at it later, if I remember 14:23:58 -!- augur has quit (Quit: Leaving...). 14:24:29 -!- Bike has joined. 14:27:34 -!- augur has joined. 14:28:40 In any case, the most impressive Intercal program I know about is Ørjan's unlambda interpretet ( http://home.nvg.org/~oerjan/esoteric/intercal/ ) 14:29:29 yeah, that was pretty mindblowing 14:29:38 oerjan isn't here right now, but he often hangs out in this channel 14:31:10 -!- mrhmouse has joined. 14:47:47 "He's as much of a fixture here as the channel's actual fixtures." 14:47:57 I guess technically speaking the channel has no actual fixtures. 14:48:33 should we invite chanserv in, so that it has one? 14:49:28 we should invite a lamp 14:50:19 A bot running on the Linux-Apache-MySQL-PHP platform? 14:50:50 yes. and while we're at it, a chandelier 14:52:32 A... C-Haskell-Apache-Netcat-Django-ELisp-INTERCAL-Erlang-R monstrosity? 14:53:44 now we have to write that 14:54:09 (also, one of my first duties at work was to write a program to perform work previously performed by an elisp CGI script that also involved manual intervention) 14:54:16 (I rewrote from scratch in Perl) 14:59:21 -!- ais523_ has quit (Quit: Page closed). 15:04:08 `? fixture 15:04:10 fixture? ¯\(°_o)/¯ 15:05:31 @wn fixture 15:05:32 *** "fixture" wn "WordNet (r) 3.0 (2006)" 15:05:32 fixture 15:05:32 n 1: an object firmly fixed in place (especially in a household) 15:05:34 2: a regular patron; "an habitue of the racetrack"; "a bum who 15:05:36 is a Central Park fixture" [syn: {regular}, {habitue}, 15:05:38 [7 @more lines] 15:05:48 oerjan: an habitue of the racetrack. 15:06:25 (I think it's kind of like a hobbit.) 15:08:37 `words --help 15:08:40 Usage: words [-dhNo] [DATASETS...] [NUMBER_OF_WORDS] \ \ options: \ -l, --list list valid datasets \ -d, --debug debugging output \ -N, --dont-normalize don't normalize frequencies when combining \ multiple Markov models; this has the effect \ of making larger dataset 15:08:49 `words -l 15:08:50 valid datasets: --eng-1M --eng-all --eng-fiction --eng-gb --eng-us --french --german --hebrew --russian --spanish --irish --german-medical --bulgarian --catalan --swedish --brazilian --canadian-english-insane --manx --italian --ogerman --portuguese --polish --gaelic --finnish --norwegian --esolangs \ default: --eng-1M 15:08:57 `words --eng-1M 15:09:00 irrt 15:09:07 `words --eng-1M 10 15:09:10 corum clargoint chait loofefl slance exion penfut spassiol unct iistne 15:09:57 -!- Gregor has set topic: The channel of the chimæric hellos | The most corum, clargoint chait you could ever loofefl your slance in. | Magnus! | Koirammekokaan ei lennä? :( | https://dl.dropboxusercontent.com/u/2023808/wisdom.pdf | logs: http://codu.org/logs/_esoteric/ or http://tunes.org/~nef/logs/esoteric/. 15:13:05 weird stuff happens with the /töpic, and I still haven't translated «Koirammekokaan ei lennä?» yet. 15:15:40 You can find a discussion on that in the logs. 15:16:08 (If you weren't there at the time.) 15:18:36 I found «""Pystyisiköhän koirammekokaan siihen?"», which satisfies me. 15:18:51 s"\"\""\"" 15:25:15 -!- conehead has joined. 15:27:26 Does/will even our dog not fly? 15:27:32 -!- FreeFull has joined. 15:33:33 The translation I heard was "Not even our dog flies?" 15:37:02 -!- ski_ has changed nick to ski. 15:52:46 -!- nooodl_ has changed nick to nooodl. 15:55:20 -!- augur has quit (Remote host closed the connection). 15:55:47 -!- augur has joined. 15:59:40 -!- MindlessDrone has joined. 16:00:17 -!- augur has quit (Ping timeout: 252 seconds). 16:01:00 -!- Taneb has joined. 16:08:15 -!- yorick has quit (Remote host closed the connection). 16:11:58 -!- pregunton1233 has joined. 16:14:37 -!- muskrat has joined. 16:15:07 hi, is there any esoteric query language ? 16:15:55 I'm not aware of any. That could be interesting 16:17:17 -!- KingOfKarlsruhe has joined. 16:20:15 i speak a little bit of English. If someone has heard about something like that, or better ways to google it....¿? 16:33:38 Besides SQL? 16:35:18 -!- nooodl_ has joined. 16:35:33 yeah 16:38:31 -!- nooodl has quit (Read error: Operation timed out). 16:50:16 -!- shikhin_ has changed nick to shikhin. 16:51:28 -!- muskrat has quit (Ping timeout: 264 seconds). 16:54:16 -!- shikhin has changed nick to shikhin_implicit. 16:54:19 -!- olsner has joined. 16:54:23 -!- shikhin_implicit has changed nick to shikhin_EULA. 16:55:19 -!- Taneb has quit. 16:55:20 -!- jix has quit (Remote host closed the connection). 16:55:57 -!- shikhin_EULA has changed nick to shikhin. 17:04:03 -!- augur has joined. 17:12:35 -!- pregunton1233 has quit (Quit: Page closed). 17:16:32 kmc: so did you manage to prove x86 turing complete without registers? 17:16:45 "sure, just use the MMU!" 17:21:13 `thanks Bike 17:21:14 Thanks, Bike. Thike. 17:51:03 -!- ^v has joined. 17:53:00 mmu mmu mmu ♪ 17:54:07 `thanks mmu 17:54:08 Thanks, mmu. Thu. 17:54:57 `pastlog muu muu muu 17:55:28 No output. 17:55:31 -!- zzo38 has joined. 17:55:33 bin wéyons. 17:55:49 I can't beleive there aren't any «muu muu muu» in the logs. 17:56:01 well there are now 17:56:09 `pastlog muu 17:56:12 boily: I can believe it 17:56:20 2013-02-08.txt:08:48:53: !run printf '%s\n' 'Ääretön omahyväisyys miehet menivät edestakaisin yli maapallolla heidän pikku asioista, seesteinen niiden varmuus niiden imperiumi yli asiasta. On mahdollista, että infusoria mikroskoopilla tekemään samoin.' | hyphenate.fi 17:56:33 olsner: you heathen! 17:56:38 ion: you speak Finnish? 17:58:22 It's not terribly uncommon, here. 17:59:39 I kinda noticed a slight tendency towards North Germanic languages and Finno-Ugric ones in this fine chännel. 18:00:06 i am fond of english, yes 18:04:14 Are you a fondue of English, too? 18:04:31 wouldn't that require boiling me alive 18:04:48 fondues aren't usually boiling, are they? 18:04:55 you would need to be melted though 18:05:09 fondues are best when only gently simmering. 18:05:11 frankly i think i'm fine in my current collection of phases. 18:05:56 (♪ new quest ♪ find a nice place with shabushabu) 18:06:20 Bike: you need to break free of your matrix of solidity 18:07:23 boily: high leg shabu shabu 18:07:41 high leg??? 18:08:58 high leg flying shabu-shabu palace, yes. 18:10:16 * boily googles it, and dearly hopes that it's SFW. “I mean, high leg flying? What kind of place is that...” 18:11:02 it's SFW, as far as anime is SFW 18:11:21 ... 18:11:29 assuming you even come across what I thought your were referencing 18:12:12 * boily round-house fshtucks mrhmouse with a cast-iron fondue pot 18:13:19 mrhmouse: I think he may have been looking for a restaurant rather than an anime 18:13:21 no! I'm lactose intolerant! 18:14:37 olsner: I figured as much, but I felt the need to add to the absurdity of the conversation 18:15:37 ~yi 18:15:38 Your divination: "Sojourning" to "Radiance" 18:16:12 olsner: you shall support mrhmouse in his Quest of the Absurd, as he will Shine onto It and express due resplendescence. 18:17:24 in the Word of our Absurd Father, fnord 18:19:26 boily 18:19:34 i have to package your food 18:19:40 motivate me 18:19:42 In the word of fungot, fnord? 18:19:43 FireFly: _and_ a few other people.) cliki-bot was written by a 70's fnord with all that pasta sauce... then they'd use their stack, they are by default hygenic, but can never know which. 18:20:06 Sounds tricky 18:20:36 quintopia: snow has come to Québec City this last weekend, and should appear on Montréal's surface soon. are you going to let a poor Canadian starve in the cold? 18:22:36 FireFly: fungot, addled be Thy Brain, fnord 18:22:37 mrhmouse: yes, but nontheless you need to use exec with strings and 32/ 64 variants on ldc and some other stuff. 18:25:13 boily: sure. plenty of them. but not you. 18:25:41 -!- ^v has quit (Quit: http://i.imgur.com/MHuW96t.gif). 18:25:56 -!- ^v has joined. 18:25:58 <^v> il 18:26:12 <^v> sorry, hexchat derp 18:26:39 -!- Taneb has joined. 18:27:16 Hexchat, the official client of Hexham? 18:27:34 Aye 18:28:05 Tanello. 18:30:31 What is irssi the official client of? 18:30:43 Finlandia. 18:42:08 -!- prooftechnique has joined. 18:50:05 -!- conehead has quit (Quit: Computer has gone to sleep.). 18:52:18 Do you know how to make a sequent calculus where numbers that aren't divisible by four are theorems? I have done (while trying to do something else, which turns out to be equivalent). 18:53:26 why four 18:53:52 Bike: I could have used a different number but I used four. 18:54:03 why 18:54:26 No reason. 18:54:56 ?messages-loud 18:54:56 kmc said 7h 28m 52s ago: yes that would help; Rust already has a thing called "syntax extensions" which are invoked the same way as macros but can run arbitrary Rust code, unfortunately you can't 18:54:56 define a new one except by editing the compiler 18:54:56 kmc said 7h 28m 11s ago: also there are other problems with macros such as, they can't be exported from a compilation unit, and the scoping / module exporting is different from everything else, but 18:54:56 these are seen as bugs to be fixed 18:56:08 zzo38: in your calculus, is 0 divisible for four (strictly checking remainder)? 18:57:36 *by four. My mind is absent today. 18:58:16 mrhmouse: Yes; there is no way to prove zero in it. 18:58:40 What I have done is encode the rules for the subtraction game S(1,2,3), which is equivalent. 19:00:28 Do you have a link for the subtraction game? I'm not familiar with it and a search just turns up math resources for children. 19:00:56 Rules W1, W2, and W3 say that 1, 2, and 3 are axioms; you can win in one turn. Rules T1, T2, and T3 each have three sequents above the line for the three possible opponent's move after one of your moves. 19:01:32 mrhmouse: Did you try Wikipedia? Look at [[Nim]] 19:01:42 One of the subsections describes subtraction game. 19:04:19 The game isn't so difficult, but it makes the point of encoding in a sequent calculus in order to make theorems which are the numbers that aren't divisible by four. 19:18:29 in an alternative Universe, zzo38 would be a great glassperlenspiele player. 19:19:10 -!- KingOfKarlsruhe has quit (Disconnected by services). 19:19:54 s/(s(?=s)|e\b)// 19:20:41 there's a great episode of The Real Hustle about the subtraction game 19:20:47 i've always wanted to try it 19:20:52 rip someone off big 19:33:18 Today for the first time I encountered a mormon 19:33:20 -!- KingOfKarlsruhe has joined. 19:33:26 Trying to convert me 19:34:41 Oh, so did I the other day. 19:35:09 did it work 19:35:39 -!- nooodl has joined. 19:35:40 not sure 19:35:52 shachaf: do you feel mormon 19:35:59 they said i should go to mormon.org and it would make me really happy 19:36:03 i didn't go there until a few seconds ago 19:36:09 so i guess i did go there 19:36:20 did it work 19:36:28 i'm reasonably happy but i'm not sure whether it has to do with mormon.org 19:37:15 reasonably < really 19:37:20 false advertising 19:37:31 true but i didn't actually read the website 19:37:42 does it work if you wget mormon.org 19:37:47 what if you send HEAD instead of GET 19:38:04 hmm maybe they said www.mormon.org and i didn't use the www 19:38:10 i should've taken one of their cards 19:38:58 aitch tee tee pee colon slash slash doubleyou doubleyou doubleyou dot mormon dot org 19:39:04 slash robots dot text 19:39:14 dot tee ex tee 19:39:29 https://github.com/humans.txt 19:39:29 -!- nooodl_ has quit (Ping timeout: 272 seconds). 19:40:10 I was hoping for advice on how to visit the site, not just names of dudes and dudettes. 19:41:25 -!- prooftechnique has quit. 19:50:56 -!- Koen_ has quit (Read error: Connection reset by peer). 19:51:14 -!- Koen_ has joined. 19:52:25 " 19:52:25 Selfish doesn't have any repositories you can view. 19:52:27 " 19:53:30 shachaf clearly went to the site the wrong way. try AOL keyword "mormon" 19:54:05 btw, I splat the languages from the Wisdom PDF into their own chapter. 19:54:50 wisdom probability density function ... nice concept :) 19:55:16 * boily gently scuttles away from int-e 19:56:07 -!- shikhin_ has joined. 19:56:35 aww 19:56:37 int-e: if you haven't read the PDF available in the /topic yet, may I interest you in doing so? the Experience will be Enlightening ↑ 19:57:03 I hate statistics. not as much as spiders, but I do. 19:57:26 statistics is like a spider: it has 8 legs and it crawls into your mouth while you're sleeping 19:57:30 otoh, I got nothing against snakes, except when related to a CS book. 19:57:45 have you read your TaPL today 19:57:55 what's a tapl? 19:57:55 omg i told someone to read TaPL and they did! 19:58:01 while sitting in a tent in rainy malaysia 19:58:07 types and programming languages 19:58:08 Types and Programmin' Languages 19:58:32 i have a "read" copy in front of me right now in fact, which i will proceed to ignore in favor of writing about plastic models of sulfur hexafluoride 19:58:34 kmc: were you the one in rainy malaysia, or was it the someone? 19:59:21 -!- shikhin has quit (Ping timeout: 265 seconds). 19:59:25 the someone 20:05:31 @ghc 20:05:31 Duplicate instance declarations 20:06:03 @ghc 20:06:03 Duplicate binding in parallel list comprehension 20:06:33 @ghc 20:06:34 My brain just exploded. 20:06:41 ~yi 20:06:41 Your divination: "Ground" to "Welling" 20:14:06 -!- Phantom_Hoover has joined. 20:18:47 -!- AnotherTest has quit (Ping timeout: 252 seconds). 20:20:09 -!- conehead has joined. 20:21:34 -!- yorick has joined. 20:28:43 -!- Oj742 has joined. 20:29:02 `relcome Oj742 20:29:05 ​Oj742: Welcome to the international hub for esoteric programming language design and deployment! For more information, check out our wiki: . (For the other kind of esoterica, try #esoteric on irc.dal.net.) 20:35:56 Hello 20:37:27 -!- ^v has quit (Quit: http://i.imgur.com/MHuW96t.gif). 20:37:40 Oj742: NICE JORB 20:37:48 (and nice to meet you finally) 20:39:49 ? 20:40:13 `relcome int-e 20:40:16 ​int-e: Welcome to the international hub for esoteric programming language design and deployment! For more information, check out our wiki: . (For the other kind of esoterica, try #esoteric on irc.dal.net.) 20:44:13 quintopia: you know therm? 20:44:33 -!- ^v has joined. 20:45:10 boily: how could i not? 20:45:39 Oj742 has the second best warrior on the bfjoust hill right now 20:46:07 dat darn omnipotence... 20:46:38 ooooooooh! 20:47:28 of course, it was only third best until i made a slight change ... and the next change i make will put it back there... 20:47:52 -!- nisstyre has joined. 20:48:42 (i could easily beat omnipotence with space_hotel since omnipotence is hard-coded to beat space_hotel based on its decoy setup. shameless special-casing. but it doesn't bother me that much.) 20:49:28 bfjoist is something I have no talent for at all 20:49:48 Remember when werecatt appeared and suddenly dominated the hill 20:50:54 @tell werecatt when do you plan to dominate again? 20:50:54 Consider it noted. 20:51:49 `seen werecatt 20:51:54 not lately; try `seen werecatt ever 20:51:56 `seen werecatt ever 20:52:12 not that I remember 20:52:18 `seen david_werecatt ever 20:52:33 not that I remember 20:52:37 foiled. 20:52:38 :( 20:53:23 I think its spelled with only one 't' 20:53:27 boily: (x + y) * (a - b) 20:53:48 mrhmouse: oui? 20:54:03 f.. foiled. I'll show myself out 20:54:53 -!- doubleaykay has joined. 20:54:57 -!- doubleaykay has quit (Client Quit). 20:54:58 fungot: can you translate from mrhmouse to French? 20:54:58 boily: i like do better since it has a language called irp. this eventually made many people on scheme are you using? 20:55:09 oh, irp! 20:55:20 would someöne please translate mrhmouse for me? 20:56:01 (meanwhile, there is an intense liquorice taste in my mouth.) 20:56:08 "FOIL means First, Outside, Inside, Last." 20:56:30 I was making a terrible reference to the operation int-e is referring to 20:56:46 i.e. the order of expansion in expressions with parentheses. (the things one learns when hanging out on math channels...) 20:56:50 it's a mnemonic schoolchildren learn 20:57:01 boily: did you eat liquorice or do you e.g. have a brain disorder causing you to taste stuff? 20:57:02 not in Germany ;-) 20:57:12 not in French Canada. 20:57:18 not in America 20:57:24 it's taught here, but that makes no difference 20:57:49 olsner: a cow orker likes it, and very sneakily gave me some. I don't have brain disorders. I am sane. 20:58:29 (x + y) * (a - b) = (axe + aye) / e - (box + boy) / o 20:59:20 * boily duct tapes mrhmouse and int-e together 20:59:45 hmpf 20:59:51 boily, I like the phrase "cow orker" better than the actual phrase 21:00:03 int-e: cute. 21:00:12 boily, nice typo 21:00:49 olsner, Speaking of liquorice, do you like it? What about salty "sweets"? 21:00:50 it wasn't a typo, sadly. I wish I had created it, tho. hth. twh. tdnh. 21:01:05 boily, twh? tdnh? 21:01:15 Vorpal: don't you dare steer the conversation towards salmiakki and its brethren. 21:01:21 `? twh 21:01:23 twh would help, but is an hth derivative. hth. twh. hand. 21:01:24 `? tdnh 21:01:26 tdnh does not help 21:01:36 boily, what is salmiakki? 21:01:37 Vorpal: I don't eat the salty kind, only the sweet (and not very often) 21:01:46 olsner, phew 21:02:04 I'm not a fan of liquorice. Nor do I like the salty Swedish "sweets" 21:02:26 https://en.wikipedia.org/wiki/Salmiakki 21:02:42 I like terva leijona though 21:02:56 s/terva/nepeta/ 21:03:02 boily, oh right, saltlakrits, right 21:03:09 Yeah it is terrible stuff 21:03:41 “... with tar flavouring.” you guys are completely insane. 21:03:47 boily, no idea why anyone would like it, and I live in Sweden, where this stuff is somewhat common 21:04:16 boily, I can never remember which options to use to taste it 21:04:25 Is it -xf or -cf or what 21:04:47 Taneb, to do what? 21:04:57 tar 21:04:57 -xf is tar for extracting, -cf is for creation 21:05:05 boily: that's finnish btw, it's *them* guys that are insane 21:05:14 -cf archive.tar directory-to-tar 21:05:34 Vorpal may or may not have missed the joke 21:05:35 radar shows the joke has successfully been destroyed. good work, people. let's go home 21:05:44 olsner, oh, duh 21:05:46 right 21:06:23 maybe tar means molasses or something? 21:06:28 I'm not a fan of liquorice. Nor do I like the salty Swedish "sweets" 21:06:29 Are you guys dissing our stuffs? 21:06:30 when we want something sweet, nothing beats http://www.recettes.qc.ca/recette/tarte-au-sucre-1168 . four cups of brown sugar! 21:06:43 boily, Personally I'm quite fond of 70-90% chocolate though 21:06:45 fizzie: only unedible stuff. 21:06:50 More than 90% is a bit too much 21:06:55 boily: Incidentally, you can get tar-flavoured ice cream at a couple of restaurants here. 21:06:58 Vorpal: nothing less than 90% for me. 99% is the best. 21:07:08 i had to show some danes around my school a couple of years ago, they gave us various danish treats afterwards 21:07:08 I'm not sure why UNIX spells 'cat' forward and 'rat' backward. 21:07:25 intercultural fternooner exchange! 21:07:27 they were so uniformly horrible that i can only assume they were picked to fuck with the foreigners 21:07:42 it also spells 'cat' backward! 21:07:47 i like how there's an 'ar' separate from 'tar' 21:07:54 "ar, but specifically for tapes" 21:07:58 boily, And I like white chocolate at the other end of the spectrum (lets leave the discussion about whether that is chocolate for another time). 21:08:04 Not much in between though 21:08:20 I think ar is for, like, random-access archives 21:08:27 boily: http://www.ravintolaharald.fi/service.cntum?pageId=145900 "Sweet Endings" "HARALD’S TAR DELIGHT -- Homemade tar ice cream(whose secret recipe is closely guarded by Harald) served with pear compote, cinnamon-caramel sauce and crispy flatbread sticks." 21:08:32 boily: (It's a kind of terrible touristy place, but I think someone wrote a nice blog post about the ice cream once.) 21:08:35 Phantom_Hoover, I believe they claim it is an acquired taste 21:08:42 Phantom_Hoover, but I guess that could just be a code name 21:08:46 fizzie: is the tar ice cream any good? 21:09:05 * boily checks prices for a ticket to Finlandia... 21:09:07 olsner: Well, I mean, it's no chocolate. But it wasn't bad either. 21:09:11 nooodl: I believe I've even used 'tac' once or twice ... :) 21:09:22 olsner: http://susan-stepney.blogspot.fi/2011/06/tar-ice-cream.html there you go. 21:09:32 -!- zzo38 has quit (Remote host closed the connection). 21:09:51 how does tac actually work 21:10:00 does it just store stdin in a buffer or what 21:10:37 Phantom_Hoover, I guess it could start from the last argument and then scan backwards, reading a chunk at a time 21:10:41 I believe the coreutils tac does something more clever if you give it a seekable file. 21:10:45 Phantom_Hoover: short of time travel, that's about the only thing it can do (on pipes) 21:10:47 Then reverse each chunk 21:10:53 But buffering is involved for pipes, sure. 21:10:57 Yeah assuming it is seakable 21:11:11 Phantom_Hoover: that's how toybox tac does it, at least 21:11:37 nortti, toybox is a pretty terrible thing though 21:11:39 there are rumors of a seekable pipe from an outer eldritch dimension, that can tac without buffering from the True End of All Inputs. 21:11:52 nortti, Like a half-arsed busybox clone 21:11:58 hmm? 21:12:09 Isn't toybox the one Android uses? 21:12:13 no 21:12:17 boily: I'd like to see a "tac | head" on that. 21:12:18 that is toolbox 21:12:25 (hm. I have to expect to shell out about two grands to get myself shipped over to the Suomen Tasavalta.) 21:12:28 the GNU 'tac' has a tac_seekable function, which hopefully does something clever :) 21:12:30 nortti, Oh okay, easy to confuse those 21:12:48 toybox is a busybox-like tools by the ex-maintainer of busybox, rob landley 21:12:50 boily: That sounds suspiciously expensive. Oh, I guess that's some Canadian fake money? 21:12:55 intended to be cleaner version 21:12:59 Ah 21:13:10 nortti, does it still use the kernel config system? 21:13:14 yes 21:13:23 why? 21:13:25 Fair enough, there are a lot of options I guess 21:13:37 fizzie: our money may be fake, but at least it's well-designed. and it has the Queen of England on it! 21:13:45 nortti, why it uses it or why I ask? 21:13:56 boily: Oh yes, I remember hearing it's very colorful. 21:14:07 Vorpal: why you asked 21:14:17 `seen david_werecat ever 21:14:18 nortti, not a lot of projects uses it. 21:14:19 fizzie: https://en.wikipedia.org/wiki/Canadian_dollar 21:14:22 2013-01-18 02:52:09: Hello 21:14:24 true 21:14:32 damn that's a long time ago 21:14:35 busybox used it last time I built it, too 21:14:36 `seen aloril ever 21:14:39 I'm eager to see the new 5 and 10$! 21:14:46 nortti, the kernel, busybox, uclibc... That is about it that I know of 21:14:50 not that I remember 21:15:13 i've checked the logs btw, aloril_ has been here for over a decade and has never spoken once 21:15:18 boily: I think it "only" cost something like a thousand EUR (1.4 kCAD) for me to get to Portland and back, and that's like almost in Canada. 21:15:28 ("kCAD" is probably a CAD program.) 21:15:38 nortti, so how does toybox and busybox compare to each other from a feature completeness point of view? 21:15:48 busybox has a shit-ton more 21:15:49 Is toybox a drop-in replacement at this point? 21:15:52 Ah okay 21:15:54 not yet 21:15:55 Phantom_Hoover: nice. 21:16:14 nortti, ignoring weird stuff like a built in micro-webserver in busybox? 21:16:26 it still lacks shell 21:16:37 and df has yet to get '-h' 21:16:38 Eh, that is kind of major yeah 21:16:47 fizzie: I only checked Air Canada, which is far from being the best option out there. 21:16:55 nortti, what about color options to ls? I can't remember if busybox has that 21:17:04 a sec 21:17:18 Yeah it does 21:17:21 busybox has it, toybox does too 21:17:32 boily: Also I guess you can always mail yourself in a box? 21:17:32 good, that makes it so much easier to work with 21:17:33 * quintopia orks boily's cows 21:17:51 nortti, what about binary sizes when built for equal features? 21:18:06 hmm, no idea 21:18:17 anyone here ever use mpmath in python? 21:18:18 Eh well, I guess I'll keep an eye on it though 21:18:25 -!- prooftechnique has joined. 21:18:26 fizzie: I could. I quintopia'd a box of cookies, and I'm marginally heavier than that, so I have experience. 21:18:36 quintopia, sounds interesting, what does it do? 21:18:46 but for my current config busybox is 512kB and toybox is 136kB 21:18:56 fizzie: checking prices on hotwire cuts the amount by half. 21:19:05 Vorpal: arbitrary precision complex-valued math 21:19:24 quintopia, oh, so not MP as in multi *processor* 21:19:31 Not so interested any more, sorry 21:19:33 -!- carado has quit (Ping timeout: 252 seconds). 21:19:44 i like the idea of boily being only slightly heavier than a box of maple leaf cookies 21:19:54 psh, what's the point without quaternions 21:20:20 I should try to learn quaternions at some point 21:20:35 here let me teach you 21:20:42 Okay...? 21:20:56 Vorpal: I suggest you try it on some linux system you are comfortable hacking with. currently I'm running it on my main system and sometimes encounter stuff that blows up due to GNUisms 21:21:31 i²=j²=k²=ijk=-1 21:21:32 nortti, well I doubt I will ever switch from GNU Bash as my interactive shell. I'm just to used to it's features and quirks 21:21:35 now you know quaternions 21:21:48 quintopia, yeah that about covers it :P 21:21:51 ah. I'm also running non-toybox shell 21:22:05 because the current toybox shell is, to put it kindly, shit 21:22:09 nortti, and tools for that matter 21:22:12 (mksh, ftw) 21:22:24 nortti, I use weird non-standard options to tools out of convenience 21:22:29 ah 21:23:07 well, in that case, continue on with your gnu coreutils 21:23:10 nortti, when I look at map 1p grep I get scared. There is no -L for example for files without matches. Something I used like 5 minutes ago 21:23:21 s/map/man/ 21:23:51 oh, interesting. my grep manpage is from sbase 21:24:00 man 1p not man 1 21:24:03 or what do you mean 21:24:07 * nortti reminds itself to fix manpages sometime 21:24:10 nortti, anyway on a modern system, the extra bloat in gnu coreutils doesn't really matter 21:24:13 map map map ♪ 21:24:37 I mean that my grep(1)'s manpage is from suckless' sbase collection 21:24:46 I have 16 GB RAM. I'm not going to run out just because true has a --help and a --version! 21:24:53 heh, true 21:25:14 Also this computer has like 4.5 TB storage in total, though a bit of that is tied up into RAID 21:25:17 I, on the other hand, still have in active use a machine with 1MB of RAM 21:25:25 That is just the internal storage 21:25:44 I have 30GB HD, 20% used 21:25:46 -!- MindlessDrone has quit (Quit: MindlessDrone). 21:25:55 poll: should i take a class in electric circuits, or a class in microcontrollers 21:25:59 nortti, The least advanced system I have that i actually use is my RPi. Coreutils run fine there too with 512 MB RAM 21:26:00 every page held up by the help text for true is a page that isn't used caching all that data 21:26:35 olsner, XD 21:26:46 Bike: can you give me more info about the μC class, syllabus or list of materials or such 21:26:52 unless you're sufficiently lucky that the help text is in all separate pages that don't get loaded from disk (and don't have relocations, etc) 21:26:58 let me see. 21:27:14 -!- boily has quit (Quit: TRIPLE CHICKEN FAULT!). 21:27:16 -!- metasepia has quit (Remote host closed the connection). 21:27:18 μC programin' is extremely easy to pick up on your own, since it's now a huge hobby field with lots of resources for everyone including total tech beginners 21:27:47 and I think a lot of college μC classes have a "party like it's 1985" vibe 21:27:55 haha. 21:27:55 olsner, I get similar read speed "experience" with my 2x 1 TB in RAID 1 at home to my insane 250 GB Intel 520 SSD at work. Both are just too fast for me to notice. 21:27:59 programming weird chips in assembly because that's what we did back in the day, damnit 21:28:09 which... could be fun, but is mostly a slog ime 21:28:22 i'm thinking of switching to a track that would make me take both classes, so eh 21:28:27 ah, neat 21:28:38 Bike, electric circuits could be fun 21:28:45 ah hey, the syllabus is online. 21:28:59 olsner: don't most shells have true and false built in anyway? 21:29:16 ISAs, serial communication, writing efficient code, timing, async/interrupts, blablablabla 21:29:24 otoh there is a HUGE gap between hobby arduino stuff and the kind of EE you need to know if you want to design a cheap tiny robust power-efficient mass-producable device 21:29:27 "Discuss the central components of Microchip MIPS32 RISC microcontrollers" so that gives an idea of materials 21:29:42 is mips weird 1985? 21:29:43 olsner, anyway echo $(( $(du -b /bin/true) / 1024 )) 21:29:43 bash: 22880/bin/true / 1024 : division by 0 (error token is "/true / 1024 ") 21:29:48 That is funny 21:29:54 * Vorpal is confused 21:29:58 "Operate and control a basic robotic car" oh ho ho. 21:30:02 neh 21:30:03 meh* 21:30:24 True is pretty big though, 4 pages in total 21:30:26 well at least the MIPS architecture is simple and elegant and has free C compilers 21:30:28 "Required textbooks: None" i really like the EE department's style 21:30:43 27080 bytes here, excessive :/ 21:30:46 kmc, AVR is pretty common these days 21:31:01 int-e, 22880 for me 21:31:05 i dunno if the peripheral parts of the Microchip ones are nice or not 21:31:06 So somewhat less 21:31:10 Vorpal: for college classes? that's good 21:31:27 kmc, 4 pages? Yeah ;P 21:31:28 our infamous intro microcontrollers class used a custom board with an 80186 and a load of other chips on it 21:31:36 required materials... chip is from a local supplier i've liked so far, basic lights and switches... ooh, a stereo amp... bluetooth... robotics kit 21:31:38 4 pages what? 21:31:38 Vorpal: 22880 is more like 6 pages 21:31:41 kmc, I meant memory pages for /bin/true 21:32:05 I think we used the 80186 because they bought a barrel of them back in 1985 and were still using them up 21:32:12 looks like the compiler is this thing http://www.microchip.com/pagehandler/en_us/devtools/mplabxc/ 21:32:16 I think MIT uses the 8051? not sure tho 21:32:30 obviously i should write a rustc backend for my robocar 21:32:33 olsner, hm, I did du /bin/true, which is 512 byte blocks, which is 24. Divided by 2 is 12. Divided by 4 (For 4k) is... 3 actually 21:32:48 olsner, who is right? 21:32:55 80186 is obscure enough that most of the time when I googled for resources, I found only the website for the course I was taking :( 21:33:16 uh, damn. 21:33:20 Vorpal: I'm right, obviously 21:33:31 olsner, where is my math wrong then? 21:33:35 kmc, 80186? Is that like their second CPU? 21:33:36 maybe i should check the professor to make sure he's not the anti masonic guy 21:33:56 Vorpal: the assumption that du uses 512 byte blocks 21:34:09 int-e, pretty sure it does? I remember reading that some time ago 21:34:24 Oh wait 21:34:26 Vorpal: no, there was the 4004 and the 8008 and the 8080 and the 8086/8088 and maybe others 21:34:30 q Display values are in units of the first available SIZE from --block-size, and the DU_BLOCK_SIZE, BLOCK_SIZE and BLOCKSIZE environment variables. Otherwise, units default to 1024 bytes 21:34:30 (or 512 if POSIXLY_CORRECT is set). 21:34:30 ' 21:34:38 Right 21:34:44 first intel processor ever was for some japanese calculator 21:34:48 int-e, So I was correct under POSIX 21:35:17 the 80186 was an attempt to turn the 8086 into a microcontroller but not really in the modern sense, it still needs external ROM and RAM and loads of other stuff 21:35:25 Vorpal: but that's a small excuse for not noting that 512*24 is quite far from 22880 :) 21:35:35 http://wolverine.caltech.edu/eecs51/kits/kit51ins.htm 21:35:36 -!- sebbu has quit (Ping timeout: 245 seconds). 21:35:40 "This course covers a wide spectrum of software testing techniques for traditional and object-oriented languages" 21:35:47 int-e, I'm better at math with letters than math with actual digits? Kay? 21:36:01 Vorpal: ok. 21:36:25 "Software Testing: A Craftsman’s Approach" they've infilitrated the textbooks! 21:36:33 :( 21:36:46 Bike, eeww. That sounds like the opposite of quickcheck 21:37:03 "The biggest change comes in the growing prominence and acceptance of Agile Programming." 21:37:11 Which is of course the best testing technology that I know of currently 21:37:27 of course 21:37:42 well, anyway, i'm not taking that class, just thought that was amusing. 21:38:02 blatantly gendered language? in my CS textbook? it's more likely than you think 21:38:13 Our DSP assembly course had what I think was quite a "90s" vibe when it came to hardware it ran on (a TI TMS320C54x devkit, some fancy 56K audio box with knobs, and some AD SHARC thing). 21:38:20 oh hey, i didn't even notice, you're right. 21:38:48 oh ... gender ... "middle person attack" sounds awful, imho. 21:39:24 kmc, gendered? How do you mean? 21:39:32 "craftsman" 21:40:05 I generally don't accept it when men say "but it's just TOO HARD to come up with better words" 21:40:16 Hm 21:40:18 crafter 21:40:29 craftsperson? 21:40:40 mega craftinator z 21:40:49 crafty cat 21:41:06 anyway the uses of "craftsman" in startupland are meaningless pompous marketing fluff so they should probably be excised alltogether 21:41:15 Craftsman is a common word though. While I would agree that it would be a bad *new* word to be created. I don't really care about existing words. 21:41:18 "Software Testing: Mega Craftinator Z's Approach" has a certain ring to it. 21:41:29 kmc, that I can agree on though 21:41:37 i'm happy being an engineer, being an engineer is awesome, I don't need to pretend I'm a rockstar or a painter or a craftsman instead 21:41:47 Quite 21:42:09 kmc, Though being a Rockstar painter crafting engineer would be awesome 21:42:15 why be any of those things when you can be MEGA CRAFTINATOR Z? 21:42:42 mega craftinator z is formed when rockstar blue, painter red, crafter yellow, and engineer pink combine, that's why 21:42:42 Vorpal, int-e: I think it's very hard for men to empathize with what it's like to be a woman in programming and receive tiny (usually unintentional) signals every day that say you are abnormal and you aren't a Real Programmer etc 21:42:55 this is my opinion after listening to lots of women describe their experiences in the field 21:43:00 kmc, hm 21:43:07 Bike: Which one of them forms the head? 21:43:07 obviously, not all women feel this way 21:43:19 kmc, Craftman has nothing to do with programming though, as you just said. 21:43:21 but if you can fix the language to make some people more welcome, without really hurting anyone else, why not do it? 21:43:29 Vorpal: we were talking about the title of a software book.......... 21:43:36 kmc, but should we change the word "human" just because it contains "man"? 21:43:37 and more generally about the term's (mis)use in programming 21:44:02 yeah it's a bit silly to say "well I don't care" when you're included in "craftsman" 21:44:02 like, obviously. 21:44:02 fizzie: i haven't taken my class in megacontrollers yet, couldn't tell you :( 21:44:03 Swedish has the same issue, "människa" = human "män" = men 21:44:05 Vorpal: maybe eventually? but we have to start somewhere 21:44:17 Vorpal: it's a bit of a slippery slope fallacy you're making 21:44:23 I suggest "humoid", just because "humoid resources" sounds good. 21:44:30 Vorpal: you might want to read http://www.cs.virginia.edu/~evans/cs655/readings/purity.html 21:44:44 haha i was just going to link that. 21:45:10 kmc, no, I'm very much against creating *new* words like "craftman". But I also find it silly to keep changing an existing language unless there is more than a few people who complain about it 21:45:13 -!- mrhmouse has quit (Quit: Leaving.). 21:45:19 there are TONS of people who complain about this 21:45:22 you aren't listening to them 21:45:23 incidentally, 'human' is etymologically not related to 'man'. 21:45:28 kmc, also I read that 21:45:47 Bike, oh? Interesting. How does it work out then? 21:46:03 'human' is from 'homo', 'man' is from germanic 'mann' or something 21:46:08 Hm 21:46:09 Vorpal: it's amazing how people will claim that biased language doesn't matter and yet fight really hard to keep it 21:46:12 part of english's general half french thing. 21:46:12 why do you care so much 21:46:25 if some people dislike this word, and by your own admission it's silly to care, then just let them win 21:46:54 Vorpal: and what did you think of the essay? 21:47:27 I read it a couple of years ago. Yes it has a point. But, kmc, I think creating neologisms all over the place just lead to unnecessary and pointless confusion. 21:47:40 what's your basis for claiming it's confusing, at all? 21:47:52 who will be confused if I say "craftsperson" or "maker" or "artisan" or any of 10 other synonyms instead of "crafstman" 21:48:25 Developer makes me think of photography or hair 21:48:25 kmc, try replacing "man" with "person" or similar in all words like "craftsman" for a week in all speech and writing and see if people don't get confused 21:48:42 kmc, "artisan" or "maker" would work yes 21:48:46 Vorpal: I have been doing this for years 21:48:47 craftsperson would not 21:48:50 Vorpal: not a single person has ever been confused 21:48:54 kmc, interesting. Hm 21:49:02 Well then I might be wrong I guess. 21:49:07 another interesting etymology fact: 21:49:19 latin "habere", "to have", is cognate to english "give", not english "have" 21:49:35 -!- sebbu has joined. 21:49:35 it's cool how I had this same exact argument with the JavascriptMVC people like a year ago and they gave me all of the standard bingo-card excuses not to change it and then they finally fixed it after a whole year 21:49:38 latin "capere", "to take", *is* cognate to english "have". 21:49:44 nooodl, that sounds implausible. How does that work out? 21:49:56 ...the DM's telling me off for derailing the adventure and we haven't actually started yet 21:50:10 -!- sebbu has quit (Changing host). 21:50:10 -!- sebbu has joined. 21:50:24 kmc, I don't think I will take any personal action regarding it though, I simply don't care enough about the issue. 21:50:30 Vorpal: then you're just a dick 21:50:34 what's the cost to you 21:51:12 kmc, Having to keep remembering to do it all the time, scan the phrases ahead and so on. 21:51:22 "habere" and "give" are from PIE *gʰabʰ- 21:51:27 "capere" and "have" from *keh₂p- 21:51:59 also cool: "Since there is no common Indo-European root for a transitive possessive verb have (notice that Latin "habeo" is not related to English "have"), Proto-Indo-European probably lacked the have structure. Instead, the third person forms of be were used, with the possessor in dative case, cf. Latin mihi est / sunt, literally to me is / are." 21:51:59 you know what's a lot harder than having to think before you speak? being anything other than a middle-class white man in programming 21:52:02 consider this a small tax 21:52:08 towards a better, more fair world 21:52:56 i find that thinking before I speak has all kinds of benefits.... 21:53:01 kmc, and I personally don't know anyone who is bothered by it, neither male nor female. I know a woman who I remember saying pretty much "whatever" in a discussion about this. 21:53:13 wow ONE WOMAN ONE TIME TOLD ME IT WAS OK 21:53:18 pack it up, feminism is solved 21:53:30 kmc, oh come on, strawmans aren't cool 21:53:42 sorry "strawpersons" 21:53:43 Vorpal: perhaps your attitude towards these things has some selection effect on the people you know? 21:54:06 I know lots of people who do care 21:54:15 kmc, maybe? *Shrug*. I'm nice towards people of either gender I hope. But I couldn't give a damn about the language itself. 21:54:16 Vorpal: it's not really a straw argument, given that "i haven't checked but nobody seems to care so stop caring" was your actual argument. 21:54:24 perhaps the fact that I don't dismiss their experiences just for being different of mine has something to do with the fact that they continue to talk to me 21:54:49 Bike, I didn't tell kmc to stop caring. I just said I didn't care myself because nobody around me in "real life" has seemed to care at all. 21:54:54 yes 21:54:56 and I said that makes you a jerk 21:55:00 if you're ok with that, we can move on 21:55:26 Vorpal: i don't think it's reasonable to assume that they'd tell you if they did care 21:55:50 kmc, I think that saying that makes me a jerk is a bit much. I make a point of *not* laughing at sexist jokes nor of course telling them. Even in an all male company. 21:55:54 Stuff like that. 21:56:01 they might expect you to respond defensively, as you did to kmc 21:56:19 wow you make a point of not telling sexist jokes even when you could get away with it 21:56:22 gold star for you 21:56:23 and yes there are obviously bigger jerks and this is not the most important issue in the world 21:56:34 what is wrong with "craftsman" if you use it to mean "craftsperson" 21:56:37 lexande, not to an actual woman saying that no. 21:56:41 That would carry some weight. 21:56:49 sigh 21:56:51 -!- Sprocklem has joined. 21:57:01 nooodl, Well argue that with kmc. I'm out. I need to sleep 21:57:08 'night Vorpal 21:57:18 nooodl, see above? 21:57:34 * nooodl logreads 21:57:42 Vorpal: obviously if you want citations of women who care it's easy to find many. also sexism hurts men too. 21:58:40 nooodl: the crux of it is … I think it's very hard for men to empathize with what it's like to be a woman in programming and receive tiny (usually unintentional) signals every day that say you are abnormal and you aren't a Real Programmer etc 22:00:13 Vorpal: anyway if you sometimes slip up and say something like "craftsman" it's not a huge deal, but you should avoid it if you notice yourself doing it, and accept it graciously when people point out the mistake 22:00:19 right 22:00:56 I think people get defensive because there's an implication that if you call someone out on behavior you are saying they're a horrible malicious sexist as a personality trait 22:01:00 that's not how it works 22:01:13 sexism is malware, we all get some of it from growing up in a patriarchal society 22:01:16 we help each other get rid of it 22:01:23 whoa 22:01:35 didn't expect to see this discussion here 22:01:46 hi quintopia 22:02:10 the thing with "man" to me is, in certain contexts, like "craftsman", it's plain obvious that people aren't REALLY talking about just male people 22:02:11 * kmc is still working on how to make the preceding point without tone-policing 22:02:21 nooodl: intent isn't everything 22:02:30 nooodl: did you read http://www.cs.virginia.edu/~evans/cs655/readings/purity.html 22:03:29 kmc: was about to link to that 22:03:48 I already did when I had the same conversation with Vorpal that I'm about to have with nooodl 22:03:55 except I might fuck off instead 22:04:00 now i'm wondering where i saw it first. maybe it was in his book on translation 22:04:10 I got it from shachaf, I'm pretty sure 22:04:38 it's not, like, a perfect analogy, but it goes a long way imo 22:04:42 i kind of agree with nooodl here. i understand the stewardess/steward -> flight attendant thing since in that case, the terms are definitively gendered, but "man" meant "human" before it meant "male human", and i don't mind saying "craftsmanship" or "workmanship" if i'm not around someone who hasn't explicitly told me it offends them 22:04:59 it doesn't really matter what a word meant thousands of years ago 22:05:06 it matters what thoughts and feelings it produces in someone hearing it today 22:05:21 i don't mind making sexist jokes unless i'm around someone who's told me it offends them 22:05:34 kmc: do we s/MITM/PITM/ 22:05:46 heh 22:05:56 what's wrong with malcolm?? 22:06:02 most folk i know don't get a feeling of offense from the word "craftsmanship". if i knew someone who did, i wouldn't. same with a lot of other things. 22:06:11 quintopia: I went over that with Vorpal too 22:06:14 carol is the attacker. clearly a great step forward for feminism. 22:06:26 it's specific to these words though, because the connotation in them isn't obvious 22:06:31 quintopia: how do you know what other people feel? 22:06:32 other words it is 22:06:36 also I really hate the word "offended" because people totally lose their shit whenever it comes up 22:06:44 let's talk about, are you HURTING people 22:06:47 what the heck do you mean it's not obvious, it says "man" right there 22:06:48 whether or not you intended to 22:06:49 kmc: yeah "offended" is dumb 22:06:51 maybe only a little 22:06:55 yes, maybe it would be better if all women magically stopped noticing gendered language 22:07:00 that's some irrelevant sci fi scenario 22:07:07 it's not their responsibility to fix the system 22:07:09 fine. use that word. s/offense/hurt/ 22:07:25 -!- Oj742 has quit (Ping timeout: 244 seconds). 22:07:58 i know what people feel because they are my friends and i pay attention to them and care about them 22:08:27 and i can see that my friends are happy when i say they have displayed quality craftsmanship regardless of gender 22:08:44 it's fine that your friends don't mind 22:08:52 imo this shouldn't be a matter of audience 22:09:07 there are lots of things I personally don't mind, which I still wouldn't subject random people to 22:09:32 i don't interact with random people too much. i'm more careful around strangers. 22:09:34 just, look, can't you step back and say, ok, this is a small thing and i'm going to say i "don't care" about it while arguing, maybe i can just step back and consider why other people are arguing versus why i'm arguing 22:09:53 maybe they have friends who it bothers? whooooo knooooows 22:09:55 i mean. i have friends i can call "assholes" jokingly, but that doesn't make that an alright word to use anywhere! 22:09:57 hi 22:10:04 hi shachaf. what is up. 22:10:24 people mentioned me, hi people 22:10:41 asshole has a clear negative connotation. i am against using words with clear negative connotations without good reason around strangers 22:10:45 hello shachaf 22:11:10 hi shachaf what do 22:11:26 anyway it's not like this is some sort of purity question where you're a terrible person if you ever use language that could be construed as non-gender-neutral 22:12:40 maybe since women are only 15% of programmers and only 1.5% of open source contributors and leave the field at more than twice the rate of men, we could try being extra careful and welcoming even if a lot of them don't really care 22:12:44 just a thought 22:12:45 doesn't cost much 22:13:20 and certainly some instances of gendered language (e.g. MITM) are much harder to get rid of than others 22:13:25 yep 22:13:31 I still say MITM 22:13:38 I don't claim to be perfect or anything 22:13:40 but in general it's desirable to use less gendered language 22:13:41 mouse in the middle :) 22:13:42 i kind of want "man" to mean what it once did again. i want to live in a world where everyone you respect is "ser" regardless of gender. at the very least i want to gender-neutralize language without having to add more syllables. 22:13:53 well you fucking don't, deal with it. 22:14:10 i want to deal with it by moving towards that 22:14:14 tell me how 22:14:26 give up on the man thing. it's pointless. nobody cares about syllable counting. 22:14:28 but you're not willing to add one more syllable every time you say "craftsmen" (which is, how often?) 22:14:34 quintopia: do you always use 'they' instead of 'he' or 'she'? 22:15:20 if i don't know gender yeah. except when specifying a hypothetical person in formal writing, in which case i alternate between the two gendered pronouns 22:15:35 do journals etc. not accept singular "they"? 22:15:48 * quintopia shrugs 22:15:50 quintopia: 'they'ing everybody would move you towards the world you describe 22:16:13 i'm going to be honest here: it took me two entire paragraphs of http://www.cs.virginia.edu/~evans/cs655/readings/purity.html before i "got it" 22:16:22 (regardless of whether you know gender) 22:16:23 i do my formal writing for the example of high school students, and singular they is not accepted grammar yet. it's a survival adaptation for my job. 22:16:30 that's fair, I think 22:16:58 nooodl: tangent: where are you from? 22:17:10 belgium. native dutch speaker 22:17:38 quintopia: singular they has a long history in english, goddammit 22:17:40 i've been wondering how much of "getting it" is based on being american, is all. 22:17:52 lexande: some people prefer specific pronouns and request they be used. i would be moving away from the spirit of wanting the world i describe if i imposed pronouns on people that didn't want them 22:18:12 lexande: but they don't have a long history in style books 22:18:16 quintopia: have you ever met someone who objected to being described as "they"? 22:19:13 it probably was. i sorta glossed over the "-white" words thinking "oh this must be some obscure english thing i've never heard about". now that i carefully look at the list it's really obvious... 22:19:18 lexande: upon asking, i have never met someone who specifically requested, and i am trying to always ask 22:19:31 *requested "they" 22:19:57 i have met people whose preferred pronoun is 'they' 22:20:10 but also people with lots of other preferred pronouns, but they were all okay with being called 'they' 22:20:19 and this is much easier than keeping track of neologisms 22:21:31 honestly i think i'd feel awkward using neologism pronouns for someone... never had to, though 22:21:57 i know someone whose preferred pronoun is 'it' 22:22:15 i used to know someone who preferred 'it' too, it was definitely awkward for me 22:22:20 obviously using them is the respectful thing to do and isn't a huge effort to get used to using pronoun x, but it'd never stop sounding weird to me 22:22:23 referring to them that way around people who don't know them risks causing actual confusion, i think 22:22:32 but they are fine with 'they' so that's easy 22:22:42 yeah 'it' is a very bad idea... 22:22:46 it's a bit awkward to use 'it' as a third person pronoun 22:23:28 the irony of the "women would tell me if they care!" response is that women who speak up are often ignored or worse, and it's only when a man says the same thing that people take it seriously 22:23:33 (to me, mainly because "it's" is so commonly used.) 22:23:52 i'm not sure what to do about the fact that most of the thinking i'm familiar with on this issue is quite anglocentric 22:24:58 -!- jix has joined. 22:25:13 in english it's actually feasible to use 'they' for everything, but in some other languages it's a right mess 22:25:33 imo everyone switch to finnish 22:25:40 _o/ 22:25:40 | 22:25:41 /< 22:25:52 lexande, that's what they want you to think 22:25:59 yeah i have to use "he" in dutch :/ 22:26:17 also in french plural "they" is gendered!! an even bigger mess 22:26:19 We have our fair share of gendered words, but at least the third-person singular pronoun problem is fixed. 22:26:56 E.g. lawyer is "lakimies" (lit. lawman) and I don't know if there's really a good, accepted alternative. 22:27:14 Possibly "juristi", but that's kinda loanwordy. 22:27:25 ok i laughed at the image of fizzie making that expression, thanks myndzi 22:27:29 (Also might have slight differences in meaning? I don't know, I'm no lawman.) 22:27:49 are women lawyers also referred to as "lakimies"? 22:28:14 Yes. 22:29:20 ok 22:29:31 do many of them mind? 22:31:20 the weird thing about this william satire thing is that the examples actually work...the usages of "white" he cites /are/ race-inclusive. if i lived in his world, i would probably be won over by some of his arguments. 22:31:22 I only know that a nonzero fraction do. But I'm not aware of much of a movement to get rid of that particular term, for some reason. 22:32:06 Apparently "juristi" *is* being used increasingly as the replacement. 22:32:13 quintopia: same tangent: where are you from? 22:32:25 quintopia: are you white by any chance? 22:32:55 u.s. and yes 22:33:02 it's easy for white men to claim (and even believe) that we "don't see race and gender" because we don't need to for survival... the whole western world is already set up to see us as the default kind of human being 22:33:21 cf. Vorpal 22:33:42 kmc: i recall that referring to Carla del Ponte (sometime prosecutor of the UN ICTY and ICTR) as "la procureuse" instead of "le procureur" in french was considered a statement in the direction of feminism 22:34:06 heh 22:34:17 which is the opposite of how it would be seen in english 22:34:59 but that's fine... cultural context influences language connotations, film at 11 22:35:05 at least, i remember someone remarking on this irony 22:35:29 I like how every curse word in Spanish varies between mild G-rated teasing and horribly offensive depending on where you are in Latin America 22:35:42 -!- nooodl_ has joined. 22:37:07 yeah, ok, i've thought about it, and i'm just going to say i have no coherent response to "yeah i'm ok with calling bosses white and workers black". 22:37:37 German is going the same way, unfortunately (I had to stop a while to realise that most of my objections to gender-neutral language are actually based on the mockery they make of it in German (Putting an emphasis on distinguishing between male and female forms first, and then torturing the grammar by combining "Foo" and "Fooin" into "FooInnen", that'd be something like "waiterEsses" in english ... horrible.).) 22:38:03 * kmc -> breakfast buffet 22:38:05 ttyl all 22:38:14 breakfast??? 22:38:15 Dear god what time zone are you in 22:38:19 kmc: i can't claim that i don't see race and gender. sometimes i must work to ignore it. 22:38:22 @localtime kmc 22:38:23 Local time for kmc is Mon Nov 11 14:38:22 2013 22:38:23 i think he's in japan? 22:38:26 korea 22:38:29 shit 22:38:35 I also found a quote by Hofstadter here, http://people.mills.edu/spertus/Gender/pap/node21.html (look for "This is not progress") which rings true to me. 22:38:38 lambdabot: You got it wrong! 22:38:41 (I think.) 22:38:47 my VPS is still in America/Los_Angeles 22:38:49 see, this is why i can't get a bouncer. it's dishonest 22:38:57 what if i was on the moon. nobody would know 22:39:02 -!- nooodl has quit (Ping timeout: 240 seconds). 22:39:09 `run TZ=Asia/Seoul date 22:39:11 Tue Nov 12 07:39:10 KST 2013 22:39:26 Bike: You should get a separate bouncer located in every place you might ever be. 22:40:00 ah i knew i had a reason for wanting a network of satellites 22:40:05 int-e: nice page 22:40:14 -!- Taneb has quit (Quit: Heading west for pizza). 22:40:26 -!- Taneb has joined. 22:40:31 -!- Taneb has quit (Remote host closed the connection). 22:40:37 "It is unknown in what way Man used to make love, when he was a primitive savage millions of years ago" lol 22:40:55 -!- Taneb has joined. 22:41:00 -!- Taneb has quit (Remote host closed the connection). 22:43:35 i wonder if that's old enough to be "make love" as in romancin', or fucking 22:44:17 fucking++ 22:44:36 @karma fucking 22:44:36 fucking has a karma of 1 22:44:41 You must've been the first. 22:44:48 (Or else there's a delicate balance.) 22:45:11 (Or did that thing pick up postfix increment/decrement? I forget.) 22:46:32 @karma c 22:46:33 c has a karma of 1 22:46:36 fizzie: it didn't :) 22:46:51 isn't that specialcased 22:48:15 int-e: It did. 22:48:22 You run lambdabot! You should know better! 22:48:24 There are so many karma subsystems, it's hard to keep track. 22:48:42 As far as I'm concerned you should get rid of the special case. 22:48:47 And also make me an admin. 22:48:56 @karma c/c 22:48:56 c/c has a karma of 582 22:50:02 shachaf shall be appointed Karma Czar 22:50:03 shachaf: I misparsed the question. I thought it was about handling foo++ as a post-increment ... looking again, I don't know why. 22:50:22 @karma foo 22:50:22 foo has a karma of 3 22:50:23 fizzie: ha ha. 22:50:35 @karma+ c 22:50:35 c's karma raised to 2. 22:50:40 int-e: It was. 22:51:22 shachaf: post-fix- != post-. 22:51:45 but never mind. 22:52:18 Oh. 22:52:50 apparently, mentioning C++ no longer reduces one's karma (it did that for a while when karma was new) :) 22:53:21 -!- nisstyre has quit (Quit: Leaving). 22:54:04 -!- Bike has quit (Quit: Reconnecting). 22:54:17 -!- Bike has joined. 22:54:53 int-e: you had to give away your own karma to ++ somebody? 22:55:12 int-e: No, that was java. 22:55:14 @karma+ java 22:55:14 shachaf's karma lowered to 65. 22:55:16 nooodl_: no, C++ was special-cased :) 22:55:20 That should be removed. 22:55:45 @karma- java 22:55:45 java's karma lowered to -5. 22:55:49 @karma+ java 22:55:49 nooodl_'s karma lowered to -1. 22:55:55 I might change it to PHP ;-) 22:55:58 -!- nooodl_ has changed nick to nooodl. 22:56:02 nice _ shield there 22:56:07 nooodl_ ++ 22:56:13 err, nooodl_++ 22:56:14 * shachaf sighs. 22:56:18 @karma nooodl_ 22:56:18 nooodl_ has a karma of 0 22:56:25 @karma nooodl 22:56:25 You have a karma of 1 22:56:28 how'd THAT happen 22:56:32 y'all are totally ruining the integrity of the karma system. 22:56:39 Bike: hahaha 22:57:25 back in my day, when snobol had a karma of twelve it fucking MEANT something 22:57:41 huh, there's a "'s karma unchanged at " message ... 22:58:37 fungot: At least you track karma by making good old-fashioned subjective value judgements and not just picking up on keywords. 22:58:37 fizzie: and its very easily done. 22:58:54 fungot: Well, be fair, not every bot is so AI-complete. 22:58:54 fizzie: it shouldn't contain at all, actually. it produces com files for pete's sake!!! fnord style transformation sequence fnord 22:59:04 oh fungot how i love thee 22:59:05 Phantom_Hoover: change that to a struct foo*, it becomes the new seed 22:59:28 Good advice. 22:59:55 was fungot just talking about a magical girl whose transformation sequence involves com files 22:59:55 Bike: what do you mean 23:00:03 i mean, fungot, that that rules 23:00:03 Bike: fnord ( 0x0001) at fnord 23:00:47 I think that's some kind of an error message. 23:00:57 fungot: yeah, maybe all the characters could be virus themed. i like it. you a good writer, ever considered submitting something to a studio? 23:00:57 Bike: like i said, 23:01:08 but I think it belongs into the "this will never happen" category. 23:01:46 fungot: i missed it. 23:01:46 Bike: maybe i don't understand how to do any sort of type containing a type: in haskell, 23:01:53 -!- monotone has quit (Remote host closed the connection). 23:01:56 i don't either, man. 23:02:07 And that's, of course, crucial if you want to submit some writing. 23:02:51 fungot has high standards. a rigorous, type-theoretical approach to the animes. 23:02:57 -!- oerjan has joined. 23:03:31 -!- monotone has joined. 23:03:51 fungot, helloooooo 23:04:10 Bike: shh it's writing an anime 23:04:14 -!- ^v has quit (Ping timeout: 240 seconds). 23:04:16 -!- FireFly has quit (Ping timeout: 260 seconds). 23:04:23 !bfjoust slowsuicide [(+-)*100-.] 23:04:25 -!- ^v has joined. 23:04:27 ​Score for int-e_slowsuicide: 8.3 23:05:09 fungot: you should write an irc bot 23:05:09 shachaf: yes, but i was asking the question for long descriptions, the program will do is just use string-uninterned-symbol, but you can still have make-queue take an argument, and returns false 23:05:36 fungot: you should buy a boat 23:05:36 shachaf: and it'll all be happy to use scheme to make you do a hot-code update in scheme 23:06:00 fungot: why are you so obsessed with programming!! there are other things in life 23:06:01 shachaf: i thought that the joke might be that your particular statement needs a and some others 23:09:08 fun, I expected more than 4 draws (and fewer wins) :) 23:10:10 fungot: fungot fungot fungot 23:10:10 shachaf: ( runnin ( define x ( tag-pointer dpy ' a)) 23:10:23 fungot more like schemegot 23:11:15 -!- FireFly has joined. 23:12:40 Blame #scheme for that. 23:12:48 fizzie: fungot should balance its parens at least?? 23:12:49 nooodl: pretty soon i'm going to give you access to the char-sets. 23:13:07 int-e: you'd probably do better with a straight up vibrator. 23:13:07 fungot: i'm honoured 23:13:07 nooodl: i've overlooked the syntax-closure-transformer in your question" :) swap them around. bah. many languages have both " ocaml interaction" and " association"? how do i use srfi-9 records in gambit? 23:13:46 !bfjoust very slow suicide (-)*127(-+)*8000- 23:13:49 ​Score for quintopia_very: 22.0 23:14:01 lul 23:14:04 good enough 23:14:16 if you keep slowing the suicide does it become life (and higher scores) 23:14:45 -!- S1 has joined. 23:15:13 yeah that never gets a chance to suicide. it either wins or is legitimately beaten before it clears its flag. except against simple locks 23:15:21 http://sprunge.us/CKIi huh 23:16:03 !bfjoust slowsuicide (+-)*50001 23:16:07 ​Score for int-e_slowsuicide: 9.1 23:16:10 jesus 23:16:51 !bfjoust slowsuicide (+.+-)*50001 23:16:53 ​Score for int-e_slowsuicide: 10.9 23:16:56 ok, I'll stop there :) 23:17:15 int-e: vibrating between 0 and 1 is strictly better than vibrating between -128 and -127 23:17:34 because there are many things on the hill which have no counter-vibration 23:18:00 wait what does . do in bfjoust? 23:18:11 nop 23:18:14 ah 23:18:15 waste a cycle 23:18:23 +. is a real suicide :) 23:18:30 -!- S1 has changed nick to S2. 23:18:31 (if noone interferes) 23:18:36 -!- S2 has changed nick to S1. 23:18:53 int-e: not really. (+.)*128 would be 23:19:05 but then, so would be (+)*128 23:19:13 (+.+-)*50001 23:19:16 `addquote everything is either zipf, branford, poisson, gamma, or uniform. outside of that, it's a weird curve invented by sadistic statistics teachers. 23:19:21 1130) everything is either zipf, branford, poisson, gamma, or uniform. outside of that, it's a weird curve invented by sadistic statistics teachers. 23:19:42 oh good quote 23:19:48 zipf is power law right 23:19:52 yeah 23:19:53 i don't know branford 23:19:55 also: but cauchy :( 23:20:04 quintopia: in the 128th interation, the flag should be zero for two consequutive cycles, or am I missing something? 23:20:05 also: exponential 23:20:05 "nobody uses cauchy you sadist" 23:20:24 (wow, my spelling is awful.) 23:20:30 int-e: you're missing the fact that "end of program" is the same as "forever nop" 23:20:50 wow i have just enough tabs open for chrome to draw icons for every other tab 23:21:01 nooodl: too many 23:21:02 i guess it's like a rounding thing 23:21:17 http://zem.fi/egostats/ updated after a long while with all those Oj742 programs. 23:21:27 PING 1384212085640 23:21:37 great, now i have to ask boily what branford is 23:21:45 some obscure joke probably 23:22:05 fizzie: thanks! looks like we might be seeing the first uptick in bf activity since january. good thing it waited for me to get home. 23:22:07 quintopia: there's enough instructions for 200k cycles anyway. (I'm not disputing that (+)*128 is a suicide) 23:22:28 -!- S1 has left. 23:22:53 Bike: I think maybe Benford? 23:23:11 http://en.wikipedia.org/wiki/Benford%27s_law 23:23:45 Also missing: good old von Mises-Fisher. 23:23:59 quintopia: So let me restate ... the code (+.+-)*50001, left alone, should set the flag to zero for two consecutive cycles (when executing +. when the flag is -1), and lose, after 4*128-2 steps. Is that right? 23:24:03 fizzie: wow ALL_IN only wins on even tape lengths. it must have >> in its clear loop. 23:24:40 Though maybe it was more about "appears in real world" and not "used by people" listing. 23:25:00 int-e: is it 4*? check egojsout. it prints cycle numbers. 23:25:28 "A continuous probability distribution on the circle" neat 23:25:43 -!- S1 has joined. 23:25:59 oh, i see, when you add -fisher it's an n-sphere instead. good going, fisher 23:26:02 -!- S1 has left. 23:26:55 In any case, the most impressive Intercal program I know about is Ørjan's unlambda interpretet ( http://home.nvg.org/~oerjan/esoteric/intercal/ ) <-- :)) 23:27:06 quintopia: yes it is. 23:27:58 kk 23:28:38 quintopia: Some of those tape heat-map plots seem to have become confused, will have to check them out later. 23:28:51 oerjan: i hadn't seen that one either. it's impressive! 23:29:27 the "DO CONTINUATIONS DREAM OF MONADIC SHEEP" lines are very intercal and i'm going to believe that they magically do useful stuff 23:30:52 -!- avid has left. 23:31:00 -!- augur has quit (Remote host closed the connection). 23:31:34 -!- augur has joined. 23:33:21 interesting that space_hotel gets grouped with preparation 23:33:24 Also missing: good old von Mises-Fisher. <-- clearly those were sadistic stats teachers. especially fisher, did you know he supported eugenics? 23:35:12 one of my favorite things is that fisher ws conservtive and meanwhile haldane was hella marxist 23:35:59 -!- augur has quit (Ping timeout: 260 seconds). 23:37:04 nooodl: well, they are very instructive comments if you can think laterally enough 23:38:01 -!- Ghoul_ has joined. 23:41:22 Sure enough, FORTRAN looks not entirely unlike INTERCAL. 23:41:51 eh, you think? 23:42:47 Maybe COBOL looks more like INTERCAL. 23:43:51 tht's certainly the intent 23:44:57 FORTRAN looks like Python: all that whitespace-sensitivity. 23:45:21 -!- KingOfKarlsruhe has quit (Quit: ChatZilla 0.9.90.1 [Firefox 25.0/20131025151332]). 23:47:18 -!- Deewiant has joined. 23:49:04 in some way intercal is the zeerust of programming languages. 23:49:37 made to be different, but still not escaping the general style of its contemporaries. 23:50:06 *totally escaping 23:50:24 of course it managed in many ways. 23:54:58 -!- nooodl has quit (Quit: Ik ga weg). 23:56:01 -!- Phantom__Hoover has joined. 23:58:09 a zeerust lang for the modern age would be nice 23:58:51 -!- Phantom_Hoover has quit (Ping timeout: 260 seconds). 23:58:52 like, a parody of python and ruby looking things? 2013-11-12: 00:00:40 i guess 00:23:49 Everything would have to be elegant somehow. 00:24:10 Ballet, the programming language. 00:25:14 yeah, language design is probably too fancy to do something as simple as intercal these days 00:27:25 If only it were as easy as flipping "GO TO" around these days. 00:27:39 how would you parody coroutines, hm 00:28:31 -!- Sgeo has joined. 00:32:31 "In order to represent the alienation of the modern man, data cannot be passed between coroutines." 00:33:40 How can one even screw up that badly? :-D https://groups.google.com/forum/#!msg/jenkinsci-dev/-myjRIPcVwU/t4nkXONp8qgJ 00:34:46 Incidentally, Google apparently has an INTERCAL style guide. http://cadie.googlecode.com/svn/trunk/INTERCAL-style-guide.html 00:35:20 Hah, awesome 00:36:09 WRT the Jenkins thing it was apparently a badly configured plugin for their code review system. 00:37:26 -!- augur has joined. 00:37:56 http://www.theonion.com/articles/ncis-to-cease-print-edition,34523/ 00:38:16 ion: they sure flogged those repositories 00:42:05 Sgeo: is that an allusion to the onion itself ceasing its print edition 00:42:17 oerjan: I assume so 00:43:05 which i somehow saw mention in a norwegian newspaper's travel guide about a brooklyn hotel 00:43:10 *mentioned 00:45:22 http://literallyunbelievable.org/post/66676985668/the-onion-is-usually-not-creditable 00:48:34 -!- prooftechnique has quit. 00:48:47 -!- prooftechnique has joined. 00:49:36 -!- prooftechnique has quit (Client Quit). 00:49:43 -!- prooftechnique has joined. 00:50:09 reasonably < really 00:50:17 > "reasonably" < "really" 00:50:18 False 00:50:20 NOPE 00:50:23 -!- Phantom__Hoover has quit (Quit: Leaving). 00:50:52 > let (reasonably,really) = ("really","reasonably") in reasonably < really 00:50:53 True 00:50:54 checkmate 00:51:12 well those are of course really reasonable definitions 00:55:42 > "reasonably" < "rea‍lly" 00:55:43 :1:20: 00:55:43 lexical error in string/character literal at character '\... 00:55:47 eff you 01:00:00 > "hä" 01:00:01 "h\228" 01:00:30 maybe you're not utf-8 clean? 01:00:53 `unicode SNOWMAN 01:00:55 ​☃ 01:01:07 utf-8 dirty 01:01:10 > "☃" 01:01:11 "\9731" 01:01:36 > "" 01:01:37 :1:2: 01:01:37 lexical error in string/character literal at character '\SI' 01:02:16 `unicode ZERO-WIDTH JOINER 01:02:17 Unknown character. 01:02:40 `echo > 01:02:41 ​> 01:02:54 > "" 01:02:55 "" 01:04:00 > "reasonably" < "really" 01:04:01 False 01:04:09 wat 01:04:51 > "reasonably" < "really" 01:04:52 False 01:05:05 !bfjoust space_hotel http://sprunge.us/SGOW 01:05:08 > " ​>" 01:05:09 :1:3: 01:05:09 lexical error in string/character literal at character '\8... 01:05:11 ​Score for quintopia_space_hotel: 41.7 01:05:14 wat 01:05:43 > ">" 01:05:44 ">" 01:05:49 > " ​" 01:05:50 :1:3: 01:05:50 lexical error in string/character literal at character '\8... 01:06:14 -!- Sprocklem has quit (Ping timeout: 240 seconds). 01:06:30 > map ord " ​>" 01:06:31 :1:11: 01:06:31 lexical error in string/character literal at character '\... 01:06:38 bah 01:07:56 `unidecode ​ 01:07:58 ​[U+0020 SPACE] [U+200B ZERO WIDTH SPACE] 01:08:04 `unidecode 01:08:06 No output. 01:09:00 hm that's disturbing, delete deletes the zero width space together with the preceding space 01:09:29 `unidecode ​ 01:09:31 ​[U+200B ZERO WIDTH SPACE] 01:09:40 -!- Koen_ has quit (Quit: Koen_). 01:09:53 oerjan: does it do the same for printable diacritic combiners? 01:10:04 no idea 01:10:26 -!- shikhin_ has quit (Remote host closed the connection). 01:10:33 but it means i cannot usefully paste just a zero width space into irssi 01:13:59 -!- yorick has quit (Read error: Connection reset by peer). 01:14:16 i used ISO 14755 mode 01:14:35 hold Ctrl-Shift in urxvt and then you can type hex digits 01:15:02 interesting that my score went down 01:15:37 > 0x200b 01:15:38 8203 01:16:18 `unidecode ​ 01:16:20 ​[U+200B ZERO WIDTH SPACE] 01:16:49 alt+numpad works, in decimal. but then i have to remember the code. 01:16:51 !bfjoust space_hotel http://sprunge.us/WHfL 01:16:56 ​Score for quintopia_space_hotel: 44.9 01:17:22 > "​" 01:17:23 :1:2: 01:17:23 lexical error in string/character literal at character '\8... 01:17:46 `unidecode ​ 01:17:47 ​[U+200B ZERO WIDTH SPACE] 01:18:11 int-e: lambdabot is still not utf-8 clean hth​ 01:19:25 why it accepts the snowman but not zero width space is beyond me... 01:19:48 snowman conquers all 01:20:00 > "☃​" 01:20:02 :1:3: 01:20:02 lexical error in string/character literal at character '\8... 01:20:26 hm... 01:20:34 ^ord ☃​ 01:20:34 226 152 131 226 128 139 01:22:10 > " " 01:22:11 "\8202" 01:22:27 > "‌" 01:22:28 :1:2: 01:22:28 lexical error in string/character literal at character '\8... 01:22:44 `ord  ​‌ 01:22:46 8202 8203 8204 01:22:54 !bfjoust space_hotel http://sprunge.us/PDLa 01:22:58 ^ord  ​‌ 01:22:58 226 128 138 226 128 139 226 128 140 01:22:59 ​Score for quintopia_space_hotel: 45.5 01:23:18 it accepts the first, but not the two next 01:23:58 -!- Taneb has joined. 01:24:38 `ord ☌ 01:24:40 9740 01:24:47 ^ord ☌ 01:24:47 226 152 140 01:25:04 > "☋" 01:25:05 "\9739" 01:25:46 ^ord ☃☋​ 01:25:46 226 152 131 226 152 139 226 128 139 01:26:13 so, there is no particular byte triggering it. 01:27:02 `unidecode ‌ 01:27:04 ​[U+200C ZERO WIDTH NON-JOINER] 01:27:39 > "‍" 01:27:40 :1:2: 01:27:40 lexical error in string/character literal at character '\8... 01:27:51 `unidecode ‍ 01:27:53 ​[U+200D ZERO WIDTH JOINER] 01:28:21 `unidecode   01:28:23 ​[U+200A HAIR SPACE] 01:28:41 is lambdabot simply breaking on anything that's zero width? 01:29:29 `unidecode ‎ 01:29:31 ​[U+200E LEFT-TO-RIGHT MARK] 01:29:39 > "‎" 01:29:40 :1:2: 01:29:41 lexical error in string/character literal at character '\8... 01:30:16 > "a‌b" 01:30:17 :1:3: 01:30:17 lexical error in string/character literal at character '\8... 01:30:28 `unidecode a‌b 01:30:29 ​[U+0061 LATIN SMALL LETTER A] [U+200C ZERO WIDTH NON-JOINER] [U+0062 LATIN SMALL LETTER B] 01:31:58 hm ghci does the same thing 01:33:23 and accepts the snowman 01:36:22 > Data.Char.generalCategory '\8203' 01:36:24 Format 01:36:32 > Data.Char.generalCategory '\8202' 01:36:33 Space 01:36:35 > Data.Char.generalCategory '\8204' 01:36:37 Format 01:36:39 > Data.Char.generalCategory '\8205' 01:36:40 Format 01:36:42 > Data.Char.generalCategory '\8206' 01:36:43 Format 01:36:49 > Data.Char.generalCategory '\8207' 01:36:50 Format 01:36:59 > "‏" 01:37:00 :1:2: 01:37:00 lexical error in string/character literal at character '\8... 01:37:39 i say it doesn't like Format characters 01:39:37 > "ߟ" 01:39:38 "\2015" 01:40:13 i find similar issues on ghc trac but they're old, slightly different, and claimed to be fixed. 01:52:42 -!- prooftechnique has quit. 01:53:52 !bfjoust space_hotel http://sprunge.us/KXCd 01:53:56 ​Score for quintopia_space_hotel: 49.0 01:54:20 tied with quicklock! :/ 02:00:10 -!- prooftechnique has joined. 02:01:22 !bfjoust space_hotel http://sprunge.us/XBCa 02:01:27 ​Score for quintopia_space_hotel: 49.9 02:04:20 -!- Taneb has quit (Quit: Leaving). 02:23:06 darn reading the haskell report makes me think this is intended behavior; the characters allowed in literals are restricted to "graphic" characters, which doesn't include formatting ones, i think. 02:24:20 `can bin/zalgo 02:24:21 ​/home/hackbot/hackbot.hg/multibot_cmds/lib/limits: line 5: exec: can: not found 02:24:25 `cat bin/zalgo 02:24:27 ​#!/usr/bin/python \ import codecs,sys,random \ stdin=codecs.getreader("utf-8")(sys.stdin) \ stdout=codecs.getwriter("utf-8")(sys.stdout) \ x=[unichr(0x300+i) for i in range(0,112)+[393,2887]] \ def z(n,c): \ if c in ["\n"]+x: \ n=0 \ return u"".join(x[random.randrange(0,len(x))] for i in range(n)) \ stdout.write(u"".join(c+z(2,c) for c in st 02:24:30 !bfjoust space_hotel http://sprunge.us/WHcY 02:24:32 oh that's not my zalgo 02:24:36 ​Score for quintopia_space_hotel: 49.0 02:24:39 import System.Random;main=mapM_((>>(י=< stdout=codecs.getwriter("utf-8")(sys.stdout) <----- python is a classy language 02:25:50 > "̃" 02:25:51 "\771" 02:25:55 > Data.Char.generalCategory '\8202' 02:25:56 Space 02:26:02 > " " 02:26:03 "\8202" 02:26:22 by my reading this isn't actually allowed either. 02:26:36 Well, it's a space, right? 02:26:45 What name is that? 02:27:05 Apparently HAIR SPACE. 02:27:07 !bfjoust space_hotel http://sprunge.us/NHfA 02:27:11 yes, and the BNF does not include uniWhite in graphic. 02:27:12 ​Score for quintopia_space_hotel: 48.7 02:27:55 > map negate [1, 2, 3] 02:27:57 [-1,-2,-3] 02:28:02 hm i can report this as two alternative bugs. 02:28:19 I love how   is considered whitespace. 02:29:07 OGHAM SPACE MARK would be a good name for a currency in science fiction 02:30:17 -!- variable has changed nick to constant. 02:30:21 weird 02:30:48 kmc: I like it. 02:30:48 -!- prooftechnique has quit. 02:30:53 Ogham seems like kind of a bad alphabet. 02:32:47 > "t\ \est" 02:32:48 :1:4: 02:32:49 lexical error in string/character literal at character '\8... 02:33:23 Like, who thought it was a good idea to have four different letters each consisting of five parallel lines? 02:33:31 fantastic, it allows that character _except_ where the report allows it. 02:33:54 Almost every letter consists of a number of near-vertical parallel lines. 02:34:07 > "t\ \est?" 02:34:08 "test?" 02:34:47 > "-\ \-\ \-\ \-\ \-" 02:34:48 :1:4: 02:34:48 lexical error in string/character literal at character '\5... 02:34:51 Aw. 02:37:44 > " " 02:37:45 "\8202" 02:39:58 !bfjoust space_hotel http://sprunge.us/CHXJ 02:40:03 ​Score for quintopia_space_hotel: 49.3 02:49:07 !bfjoust space_hotel http://sprunge.us/cXbC 02:49:12 ​Score for quintopia_space_hotel: 49.4 02:52:22 death under ptrace 02:53:20 peetrace 02:53:29 c.c 02:53:33 !bfjoust space_hotel http://sprunge.us/DgQU 02:53:37 ​Score for quintopia_space_hotel: 55.1 02:54:35 and that's the sound of me changing the size of the decoy that ais was using to figure out where my flag was in omnipotence. rightful station restored! 02:59:41 death to ptrace 03:10:28 !bfjoust space_hotel http://sprunge.us/YEBA 03:10:34 ​Score for quintopia_space_hotel: 55.2 03:10:43 heh 03:23:48 !bfjoust space_hotel http://sprunge.us/hZKY 03:23:53 ​Score for quintopia_space_hotel: 54.1 03:53:38 -!- nisstyre has joined. 04:02:50 -!- conehead has quit (Quit: Computer has gone to sleep.). 04:12:47 -!- nisstyre has quit (Ping timeout: 260 seconds). 04:27:29 -!- nisstyre has joined. 04:28:13 is there a program where you can fight bfjoust bots manually 04:28:57 i hear people use bfjsout on the web 04:35:46 -!- tertu has joined. 04:39:01 -!- Oj742 has joined. 04:39:50 -!- zzo38 has joined. 04:42:05 stupid self-aware makefiles 04:43:00 * Sgeo panics and puts the makefile in a box 04:44:02 won't work 04:44:10 * oerjan swats Sgeo for thinking ai boxes work -----### 04:49:57 -!- nisstyre has quit (Quit: Leaving). 04:51:25 oerjan: what's bfjsout on the web 04:52:39 well it's bfjoust in javascript 04:52:57 no idea why google doesn't find it 04:53:45 http://codu.org/eso/bfjoust/egojsout/index.php 04:57:59 -!- Sprocklem has joined. 05:00:41 so um 05:01:10 by manually i meant you press left to go left, right to go right, up to increment etc 05:03:58 WELL WHY DIDN'T YOU SAY SO 05:04:01 (no idea) 05:04:42 what did you think manually meant 05:04:55 not putting them on the hill 05:04:57 "in such a way that the results are shown on a webpage instead of an irc channel" 05:05:02 oh 05:05:39 anyway, that will be unfair to the bots unless you need an instruction (equivalent to [) in order to check the value of your current cell. 05:06:18 i realized it'd be unfair, but i didn't realize it's that easy to fix 05:06:35 what's the hill 05:06:46 !help bfjoust 05:06:46 ​Sorry, I have no help for bfjoust! 05:06:49 !help 05:06:50 ​help: General commands: !help, !info, !bf_txtgen. See also !help languages, !help userinterps. You can get help on some commands by typing !help . 05:07:46 http://codu.org/eso/bfjoust/report.txt 05:08:04 the list of currently competing programs 05:08:12 with scores 05:09:11 http://codu.org/eso/bfjoust/in_egobot/ has the actual code 05:10:30 I tried to think more of making a category of spells in Icosahedral RPG, although it seems the way I have it, the distributive law fails on spell durations. There may be a few different ways to fix this, though. 05:11:08 oklopol: actually the check only should tell you if the current cell is zero, of course 05:12:56 http://codu.org/eso/bfjoust/in_egobot/ doesn't make it very clear which player is which 05:15:37 But I did determine that (prime) objects could be WORLD and EVENT. An ordinary spell that you can cast is (WORLD -> WORLD). EVENT is used for triggers, so a (WORLD -> EVENT) spell can trigger things in a (EVENT -> WORLD) spell; what exactly it triggers depends on the spell. 05:15:42 Does this seem OK? 05:19:38 oklopol: um that lists individual programs, not matches. 05:21:43 in the report, they're listed by ID. and + seems to mean the row ID wins. 05:25:26 I may have accidentally convinced my boss's boss to buy proprietary software 05:27:34 you monster 05:27:53 RMS will be so disappointed with you 05:29:40 Sgeo: You advised your boss's boss about software? What use of the software is it? 05:30:08 It's Charles Web Proxy, he saw me using it and I mentioned that I liked it and he saw how convenient it made testing stuff 05:30:52 Although, if there's no equiv. to FiddlerScript, that would really suck 05:32:44 ... 05:32:45 "By inspecting the web interface HTML you can derive how to use it as web services to automate Charles." 05:33:00 :/ 05:33:26 automate that shite good 05:34:42 ...its idea of a web interface doesn't include modifying any settings beyond enabled/disabled 05:34:45 do you call them your metaboss 05:34:46 afaict 05:35:38 oerjan: sorry, i was on the bfjsout page, and wanted to copy it. it had that on the url row and it looked wrong so i refreshed. the url stayed the same so i figured it's correct. 05:35:47 not the first time this has happened 05:36:05 It's still called egojsout nyaaaar. 05:36:20 :D 05:36:28 (Managed to keep quiet for the first dozen times.) 05:36:56 fizzie: probably why i didn't find it with google 05:41:15 but so which is left 05:41:19 is left up? 05:41:25 -!- ^v has quit (Quit: http://i.imgur.com/MHuW96t.gif). 05:43:21 -!- ^v has joined. 05:52:20 !bfjoust lets-try-this-evolver-again >>++>>(>[>([(+)*5[-]]>)*-1])*-1 05:52:23 ​Score for Lymia_lets-try-this-evolver-again: 30.8 05:52:44 Wait a second... 05:52:51 Guh 05:52:53 Reconfiguration time 05:52:58 !bfjoust lets-try-this-evolver-again < 05:53:00 ​Score for Lymia_lets-try-this-evolver-again: 0.0 05:56:39 oklopol: wat 05:57:31 What other objects could this category of spells include? (It is a tensor category, so all of the products exist too) 06:00:40 -!- Oj742 has quit (Quit: irc2go). 06:03:50 oerjan: http://codu.org/eso/bfjoust/egojsout/index.php doesn't make it very clear which player is which, in the sense that you choose an upper player and a lower player and then it says right wins 06:03:59 what is right 06:04:22 baby don't hurt me 06:04:47 -!- tromp_ has quit (Read error: Connection reset by peer). 06:05:13 -!- tromp_ has joined. 06:06:00 no more 06:06:09 i have no more clue than you do 06:06:34 i mean i assume right is down and left is up, just wanted to point it out that really no actual clue is given which is which, anywhere on the page. 06:06:46 as far as i can see 06:07:03 spoooooooooooky 06:07:12 yes 06:07:39 CSS is adding support for vertical writing which means that we have to start saying "measure" and "extent" instead of "width" and "height" 06:09:25 LOL L LLL how about the japanese add mental support for only writing like us white people write 06:09:30 instead 06:09:42 !bf meow ++++++++++++++++++++(-)*-1 06:09:51 !bfjoust meow ++++++++++++++++++++(-)*-1 06:09:51 is -1 infinity 06:09:56 ​Score for Lymia_meow: 14.1 06:09:56 isn't japanese mostly written horizontally anyway 06:10:00 No. (to both) 06:10:15 this stuff tho http://en.wikipedia.org/wiki/File:Guyuk_khan%27s_Stamp_1246.jpg 06:10:17 i just saw it written vertically 15 minutes ago 06:10:17 i think it is, nowadays 06:10:18 how can you not love that 06:10:22 i mean, mostly 06:10:35 (that's when i last saw japanese text) 06:10:36 mongolian owns though. 06:10:51 i bet i will see some japanese text in japan 06:10:56 will report back w/ findnigs 06:10:59 let's just make mongolian the default for everything. it's been seven hundred years, we can give them a world empire again 06:11:05 actually i already saw a lot of japanese text in the seoul airport and such 06:11:08 I see it vertically a lot in manga books, although some of it is written horizontally. In computer games though, it is mostly horizontal. 06:11:09 yes make a statistication 06:11:18 oklopol are you drunk 06:11:27 nope! 06:11:35 !bf meow (--+)*-1 06:11:35 [cn] 06:11:38 !bfjout meow (--+)*-1 06:11:40 !bfjoust meow (--+)*-1 06:11:44 ​Score for Lymia_meow: 16.3 06:11:46 My evolver likes vibrators way too much 06:11:49 you can do it lymia i believe in you 06:11:56 i saw a lot of japanese text in taiwan, but most of it made no sense 06:12:27 now i have to look up which scripts are still primarily written vertically. 06:12:44 lol wikipedia has an entire article on text orientation in cjk 06:13:11 -!- sebbu has quit (Ping timeout: 260 seconds). 06:13:45 In this Windows I have "MS Gothic" font installed for Japanese writing; it also makes a font "@MS Gothic" available which turns most things sideways; I suppose this is for vertical writing in a program that is for horizontal writing. 06:13:50 ok, wikipedia's 'vertically' in the mongolian script article links to the cjk one. 06:14:01 "This developed because the Uyghurs rotated their Sogdian-derived script, originally written right to left, 90 degrees counterclockwise to emulate Chinese writing, but without changing the relative orientation of the letters" 06:14:05 Language is awesome. 06:14:48 And it looks like vertical Japanese writing is still used a lot in manga and other things, although horizontal Japanese writing is also very common, it seems. 06:15:54 the first major thing to write chinese horizontally was Science (I guess not the journal?) 06:15:57 "This magazine is printed so that it goes sideways from the top left, and is marked with Western punctuation. This is to make the insertion of mathematical, physical and chemical formulae convenient, not for the sake of novelty-hunting. We ask our readers to excuse us." 06:15:59 In "Sushi Plus" restaurant in Victoria, BC, there are a few Japanese signs, which are written using vertical writing; the whiteboard (which is turned backwards for some reason) also has vertical Japanese writing on it. 06:16:01 novelty-hunting 06:17:35 I have several issues of the (English) "Science" magazine; I got them for free from the doctor's office; they didn't want them anymore so they gave all of them to me. 06:21:40 -!- carado has joined. 06:33:28 -!- muskrat has joined. 06:36:37 -!- Taneb has joined. 06:39:50 -!- ^v has quit (Quit: http://i.imgur.com/MHuW96t.gif). 06:56:29 !bfjoust meow .-(--+)*-1 06:56:34 ​Score for Lymia_meow: 19.4 07:01:06 !bfjoust meow .+(--+)*-1 07:01:10 ​Score for Lymia_meow: 18.2 07:01:12 !bfjoust meow .-(--+)*-1 07:01:17 ​Score for Lymia_meow: 19.4 07:03:56 -!- muskrat has quit (Quit: Leaving). 07:05:08 -1 is automagically equal to the cycle count. 07:05:18 (If that wasn't mentioned already.) 07:05:34 cycle count of what 07:05:44 The maximum cycle count, I should say. 07:05:46 The limit. 07:05:51 oh 07:06:03 The OUTER LIMITS. 07:06:42 kmc: What are you doing in Seoul anyway, some kinda Mozilla thing? 07:06:47 yep 07:07:35 a bunch of people from Samsung are working with us on this Servo project, and they invited us to spend the week working out of their office 07:08:35 so I'll be doing that until Friday, then I'll do tourist stuff in Seoul until Monday night, when I fly to Osaka 07:08:46 and then I'll do tourist stuff in Japan until Sunday! 07:09:15 -!- Sprocklem has quit (Ping timeout: 252 seconds). 07:09:16 are there any #esotericers in .jp? 07:10:18 Not as far as I know, but there are some Japanese stuff related to esoteric programming. 07:10:56 kmc: there's one in korea though 07:11:03 * oerjan waves at lifthras1ir 07:11:04 oh really, who? 07:11:06 hi lifthras1ir 07:11:43 are there any #esotericers on the moon? 07:11:45 There was a lurker from .jp some months, one of those who again said nothing. 07:12:13 lifthras1ir doesn't say much these days :/ 07:12:47 shachaf: I don't think so. (And I hope the IAC doesn't destroy the moon and replace it with a fake.) 07:13:05 Do they... have plans for that? 07:13:27 clearly they should replace it with a bust of alexander abian. it would only be fitting. 07:13:28 For destroying the moon? I don't think so; IAC is just a fictional organization in some of my works. 07:13:47 zzo38 has destroyed the IAC and replced it with a fake. :-( 07:14:01 twist: zzo38 is an scp 07:14:22 classification euclid 07:14:49 (he'd be safe if the foundation understood him) 07:15:18 that's a tall order. 07:15:25 thus, euclid. 07:19:27 Tall order? 07:23:52 also as seen on #esoteric, http://www.scp-wiki.net/scp-1960-j 07:31:54 -!- FreeFull has quit. 08:04:30 -!- sebbu has joined. 08:05:08 -!- sebbu has quit (Changing host). 08:05:08 -!- sebbu has joined. 08:16:55 “Debris and sometimes even people can get swept up into a blast wave, causing more injuries such as penetrating wounds, impalement, broken bones, or even death.” 08:19:42 injuries such as death 08:24:03 -!- Bike has quit (Ping timeout: 252 seconds). 08:25:04 "Before GitHub existed, major companies created their knowledge mainly in private. But when you access their GitHub accounts, you're free to download, study, and build upon anything they add to the network" 08:25:08 github invented open source 08:25:10 you heard it here first 08:26:41 This is why we can't have private repositories 08:26:53 indeed, this is the first time I've heard that 08:27:42 For some reason I don't seem to be able to clone Windows 8.1 sources from https://github.com/microsoft -- must be some kind of temporary glitch. 08:29:23 bit surprised that https://github.com/microsoft doesn't exist 08:29:55 kmc: That is because they use CodePlex for their open source projects, isn't it? 08:32:37 -!- Bike has joined. 08:35:09 no idea 08:36:38 -!- tertu has quit (Ping timeout: 240 seconds). 08:39:47 As far as I know they probably do, when they have any. 08:42:08 git is not really the most windows-friendly system 08:43:10 Although git does work on Cygwin (which isn't Microsoft). 08:43:27 That's because windows is not really the most git-friendly system. 08:43:41 -!- ais523 has joined. 08:44:12 hi ais523 08:45:31 hi quintopia 08:45:42 awfully early eh 08:45:53 I woke up like 7 hours ago 08:46:01 i haven't slept yet 08:46:01 I was about to say something to the tune of "hey, those line lengths match", but they would have to, wouldn't they? 08:46:06 also, you being here has reminded me 08:46:18 !bfjoust preparation http://nethack4.org/esolangs/preparation.bj 08:46:26 let's see how much better this does 08:46:29 ​Score for ais523_preparation: 42.6 08:46:32 and whether the scoring system still hates it 08:46:46 fizzie updated stats earlier 08:47:02 aha, it's now correctly shown as /way/ ahead of omnipotence on points 08:47:44 although, hmm 08:47:51 I'm not convinced juiced is getting the same results as *lance is 08:48:02 let me run the hill myself and see if there are discrepancies 08:48:23 cycle limit is 100000, right? this code actually depends on the exact value of the cycle limit 08:48:30 100k, yes. 08:48:44 I've "verified" *lance against egojsout, incidentally. 08:49:09 (The console edition of egojsout was my first node.js thing ever.) 08:49:15 hmm… juiced says preparation beats brachiation 08:49:22 egobot says brachiation wins 08:49:54 let's see… breakdown says <>>><<<<<<<<<<>>>>>>> <>><><<<<<<<<<>>>>>>> 2 08:51:33 Hrm. egojsout says -8 and a win for preparation. 08:51:34 juiced says <>>><<>>><>><<>>>>>>> <>><><<<<<<<<<>>>>>>> 08:51:54 <>>><<<<<<<<<<>>>>>>> <>><><<<<<<<<<>>>>>>> 2 08:51:58 <>>><<>>><>><<>>>>>>> <>><><<<<<<<<<>>>>>>> -8 08:52:08 looks like juiced agrees with egojsout 08:52:45 I have an idea 08:52:45 preparation is seen to pretty much destroy on mid to long tapes 08:52:53 preparation has some digits in comments 08:52:57 perhaps they're confusing the parser 08:53:13 My local copy of cranklance agrees with egojsout and juiced. 08:53:23 Well, gearlance, but they're the same code. 08:54:12 btw, what do you think of my BF Joust comment grammar 08:54:18 I can't use many punctuation marks 08:54:24 so I use semicolons for basically all punctuation, also some colons 08:54:29 and slashes are used as parens 08:54:38 -!- Bike has quit (Ping timeout: 261 seconds). 08:55:14 -!- Bike has joined. 08:55:39 oh, I think I found it 08:55:42 whitespace between a * and a digit 08:56:00 what's it called when a markov can (or can't) split it into independent disconnected parts 08:56:01 at the point where you start looking for a debugger for GNU Make, something has gone seriously wrong in life 08:56:01 time to start using magicmake or whatever he calls it 08:56:01 zzo38: there's also msysgit 08:56:01 i think that's not cygwin based 08:56:01 -!- FireFly has quit (Ping timeout: 240 seconds). 08:56:01 -!- ski has quit (Ping timeout: 240 seconds). 08:56:03 -!- Effilry has joined. 08:57:03 I feel like elliot 08:57:05 *elliott 08:57:08 writing numbers out as words 08:57:24 -!- ski has joined. 08:58:55 !bfjoust preparation http://nethack4.org/esolangs/preparation.bj 08:59:00 ​Score for ais523_preparation: 47.1 08:59:14 there we go 08:59:22 it now tops the hill on points, and is #3 on weighted rankings 08:59:25 because it can't beat space_hotel 08:59:37 -!- Bike has quit (Ping timeout: 252 seconds). 08:59:38 ais523: Hmm. Whitespace shouldn't affect the *lance parser at all, for as long as I remember. 08:59:52 fizzie: perhaps that's why gearlance agrees with juiced :) 09:00:15 -!- sebbu has quit (Ping timeout: 252 seconds). 09:00:21 Okay; since Mar 06, 2011, apparently. 09:00:42 juiced appears to have a special case for ignoring whitespace after a % or a * 09:01:00 interestingly, it parses "*10 0" as "*100" 09:01:27 That's actually what current *lance does, too. 09:01:37 experts on hill scoring, would you say that I need crazy special cases against space_hotel to get it to top the hill? 09:01:37 (It ignores all whitespace completely.) 09:01:48 or would you say I should try to improve its performance against the field at large? 09:02:00 -!- Taneb has quit (Quit: Leaving). 09:03:07 Before 2011-03-06 20:25:49, *lance would've parsed "* 10 0" as *0; from 20:25:49 to 23:15:21 it would have parsed as *10; ever since that, as *100. 09:03:20 I actually think space_hotel is the most impressive program on the hill 09:03:36 (waterfall3 is the most insane, but preparation has to be a close second) 09:03:41 (I added a special case for handling whitespace after */% first; then removed it and completely ignored all nonessential characters on a lower level instead.) 09:04:09 juiced apparently has a compile-time option for whether it should conflate * and % 09:04:16 and just look at {} to tell them apart 09:04:23 I wrote this code ages ago, can hardly remember how it works 09:04:33 it does produce pretty debug traces, though 09:05:04 *lanced doesn't distinguish between * and % either. 09:05:08 s/d// 09:06:53 -!- Slereah has quit (Ping timeout: 272 seconds). 09:07:26 I wrote a couple of new entries in the lance family (torquelance, wrenchlance) the other day, but they're p. silly. 09:07:53 what do they do? 09:08:00 `addquote at the point where you start looking for a debugger for GNU Make, something has gone seriously wrong in life 09:08:08 1131) at the point where you start looking for a debugger for GNU Make, something has gone seriously wrong in life 09:08:25 -!- Effilry has changed nick to FireFly. 09:08:37 anyway, I find preparation really hilarious 09:08:48 it's amusing seeing it about to lose and then cycle 100000 hit 09:09:04 ais523: I think it's more efficient if I just point at the (reasonably short) descriptions at https://github.com/fis/chainlance/blob/master/README.md instead, maybe. 09:09:08 in a previous version, there was some program/tape length combo where its flag was 0 when time ran out, IIRC, but that doens't happen any more 09:09:09 fizzie: good idea 09:10:53 btw, the difference between this version of preparation and the previous one is that it tries to establish the probabilistic lock a second time if it fails first time 09:11:04 and it still knows where the enemy tape pointer is 09:11:23 I realised that one of the defining properties of probabilistic locks is that they don't always work, so trying again can be worthwhile 09:12:14 also, wow, I didn't realise quicklock was doing so well 09:12:17 I need to read up on how it works 09:12:51 aha, it's a combination of a poke and defend10's lock algorithm 09:12:55 so very similar to omnipotence 09:13:19 but the details seem different 09:13:31 like, it attempts to synchronize with tripwires 09:13:39 whereas omnipotence synchronizes via not setting decoys 09:13:59 One way to avoid nondistributive durations would be for castable spells to not be endomorphisms. Maybe there is a better way? 09:14:07 Somehow I feel like the length-to-score scatter plot -- http://zem.fi/egostats/plot_lenscore.png -- looks more "trendy" these days. 09:15:16 I wonder if I should do the Electron Band Structure In Germanium, My Ass thing in it. 09:15:30 ("Banking on my hopes that whoever grades this will just look at the pictures, I drew an exponential through my noise. I believe the apparent legitimacy is enhanced by the fact that I used a complicated computer program to make the fit. I understand this is the same process by which the top quark was discovered.") 09:15:59 who's that a quote from? 09:16:33 also, program length is mostly just an indication of attack versus defence, and whether or not it pokes 09:16:49 although, defence programs keep doing quite high on the hill mostly because I try really hard to make that the case 09:16:57 as part of my ongoing project into determining whether BF Joust is broken or not 09:17:03 current conclusion: it isn't 09:17:14 preparation beats death_to_defence 09:17:42 It's from http://pages.cs.wisc.edu/~kovar/hall.html which I think somehow got mildly famous. 09:18:33 incidentally, on tape length 10, preparation always loses in exactly eighteen cycles 09:18:36 unless the opponent suicides first 09:18:41 Other people argue on whether bitcoin is broken or not, not understanding where the *real* money is. (That's BF Joust.) 09:18:45 sacrificing tape length 10 in a rush program proved to be a bad idea 09:19:07 however, in a defence program, it's normally worth it because synchronizing defence programs have effectively no chance on tape length 10 anyway 09:19:34 -!- Bike has joined. 09:20:17 hmm, the grouping thing groups preparation and space_hotel together 09:20:27 even though the only thing they have in common is that they beat basically everything 09:20:37 There's two grouping things these days. 09:20:58 And the first one is based on duel scores, so it can be misled by that sort of thing, I guess. 09:21:33 The tape heatmap grouping doesn't really group preparation with anything in particular. 09:21:52 btw, anyone who wants to know how preparation works, this graph is a giveaway: http://zem.fi/egostats/plot_tapeheat.png 09:21:59 although fizzie might want to move the legend, it's in the way 09:22:16 probably because nobody expected a program to do that 09:23:13 Yes, I remember selecting top-middle for the legend because there used to be always a valley in there. 09:23:18 and yeah, I'm not surprised the heatmap can't link preparation with anything 09:23:38 never before has a program spent the majority of the cycles on tape position 9 09:23:41 perhaps, never again 09:24:06 preparation's issue is that it can't move very far before it has to go back to re-establish its lock 09:24:22 so it wants to be in a central position on the tape so as to increase its range of movement 09:27:16 actually, http://zem.fi/egostats/plot_p21_ptapemax.png is possibly an even bigger giveaway as to how preparation works 09:27:21 also where the name comes from 09:27:32 I was supposed to have a Skype meeting in two minutes, but the only one of the participants I have on my contact list seems to have disappeared. 09:27:38 and http://zem.fi/egostats/plot_p21_ptapeheat.png is quite revealing too 09:28:08 it's especially worth noting the discontinuity between tape lengths 17 and 18 09:28:14 where it changes strategy 09:28:41 (I could write paragraphs just on the "how does it know whether the tape length is above or below 17.5 anyway?") 09:28:51 -!- carado has quit (Ping timeout: 252 seconds). 09:29:09 fizzie: anyway, I have another interesting statistic, which I added to juiced recently for preparation testing 09:29:17 number of cycles a program takes to win, compared to tape length 09:31:16 I have the weirdest feeling I was doing something that involved both tape lengths and duel lengths, but there indeed seems not to be anything like that on the page. 09:32:04 Are there any basic pokemons that *always* evolve when traded? 09:32:18 zzo38: no, Everstone 09:32:37 ais523: Ah, OK. Yes, I forgot. 09:33:07 But if there were any, would it be prohibited to tamper with the trainer ID numbers of such a pokemon in a tournament that allows tampering with the data? 09:33:10 zzo38: even allowing for that, all the always-evolve-apart-from-everstone mons I know of are stage 1 09:33:23 also you can cancel the evolution by pressing B 09:33:33 -!- oerjan has quit (Quit: leaving). 09:33:35 ais523: Yes, that is what I thought, too (both of them). 09:34:07 -!- Bike has quit (Ping timeout: 272 seconds). 09:34:08 I can't think of any evolves-on-trade-without-specific-item pokemon past generation 1, either 09:34:38 The ones from later generations all seem to require holding a specific item 09:35:59 But hypothetically assume that there are some which are basic, do not require any specific item, cannot use Everstone for some reason, and cannot be cancelled. Simply to see if you can even try to guess such an answer of a question. 09:37:22 FireFly: that's mostly due to the (not 100% strictly followed) rule that any new evolutions should have been impossible in previous gens 09:37:35 (My brother said he didn't know.) 09:37:45 zzo38: you can just reset one of the games until it has the same trainer ID as a different game 09:39:55 ais523: Sure you can, but I don't think that would affect it at all. That may allow you to tamper with the trainer ID number of a stage 1 form if both the basic and stage 1 are like what I said, though, I suppose??? 09:40:06 But I said a basic form. 09:40:12 oh right 09:40:22 the question's as to whether you could legally have that mon with an OT that doesn't match your own 09:40:39 if it's not new to the generation, you could migrate it from a previous generation 09:40:42 that doesn't cause evolution 09:41:04 Ah, you are correct. I didn't think of that. 09:41:08 also you could use an official external box program (Pokémon Box / My Pokémon Ranch / Pokémon Bank), that doesn't cause evolution either 09:41:17 and normally allows unboxing onto a different cartridge if you've beaten the Champion 09:41:27 I didn't know of that, but OK. 09:41:55 -!- carado has joined. 09:46:50 My brother also said that an exception to the rule about tampering with the data is the color of the pokeball is allowed to be changed to one that isn't obtainable under those circumstances since it has no effect on the game. 09:47:29 zzo38: it used to have an effect, you could determine which moves a Pokémon might potentially have by whether it was in a Poké Ball or Cherish Ball (the two balls that give the most possibilities) 09:47:34 although that was changed in X/Y 09:47:54 In which generations do they have an effect? 09:50:30 zzo38: definitely 4 and 5, probably 3 as well 09:51:31 OK 09:52:50 Perhaps he made a mistake then. (Although I suppose it would still have no effect during battle, unless opponent is allowed to see your pokeballs in which case it clearly does have an effect.) 09:53:33 the opponent is allowed to see your Pokéballs 09:53:37 they're visible as you send the Pokémon out 09:53:52 Yes, OK, then. He did clearly make a mistake. 09:54:23 nerds 09:54:46 somebody proofe turing completeness of pokemon! 09:55:19 myname: it isn't, no infinite storage 09:55:44 that may be modified 09:56:29 Yes, that is immediately what I thought of too; no infinite storage. Both in the actual Pokemon game, and in the Pokemon card game which has various limits, some of which imply other limits, I think. 09:57:38 (If there is a card that prevent you from being knocked out when having too much damage, then you could potentially have unlimited amounts of damage, in the card game at least.) 09:57:43 just try what modifications you need to make it turing complete 09:57:58 What are they, then? 09:58:11 -!- Bike has joined. 10:01:16 myname: kinda relevant, http://aurellem.org/vba-clojure/html/total-control.html 10:02:02 FireFly: that's old, but yeah, started something of a revolution 10:02:06 Though that's not pokemon being turing-complete, as much as a buffer-overflow into Z80 land, and Z80 being turing-complete 10:02:14 -!- Ghoul_ has quit (Ping timeout: 240 seconds). 10:02:24 Or not-quite-Z80-but-kinda-Z80 IIRC 10:02:30 -!- Bike has quit (Ping timeout: 245 seconds). 10:02:41 ais523: I know, but it seemed relevant to the question 10:02:43 z80 isn't turing complete either 10:02:46 and yeah, I guess it is 10:02:53 -!- Ghoul_ has joined. 10:03:26 I like that 10:03:26 Well, bah. Modulo space and addressing issues 10:11:33 -!- tromp__ has joined. 10:12:49 -!- tromp_ has quit (Remote host closed the connection). 10:14:41 I guess you could somehow attach infinite storage through the link cable port? 10:15:10 :D 10:15:45 i guess i should sell usb attached RAM to people 10:16:25 myname: Windows 8 (possibly 7 too) has a feature that lets you use a USB stick as RAM 10:16:35 great 10:16:37 which strikes me as a really bad idea, given that they aren't really designed for that 10:16:43 but I guess people think "hey, cheap extra RAM" 10:16:51 i just buy 1 gb usb sticks and sell them for 4 times the price 10:55:47 I remember that there was some particular configuration of Linux-on-x86 where you had some regular RAM that wasn't usable normally, but you could get an MTD block device on it, and then use that as a fast swap device. 10:56:11 (Also you can put swap in GPU ram with MTD kludgery.) 10:57:44 -!- sebbu has joined. 10:57:57 -!- carado has quit (Ping timeout: 252 seconds). 10:58:21 -!- sebbu has quit (Changing host). 10:58:21 -!- sebbu has joined. 10:58:46 -!- carado has joined. 11:00:27 That actually sounds nice, except for the fact that your swap costs more than RAM. 11:03:55 I think there's no other language where the interpreter is easier to write than "hello world". 11:04:04 what about OISCs? 11:04:53 Jafet: Ah, but you can use it for swap during those times you're not using it for graphics. 11:04:58 We need a language where the self-interpreter happens to be "hello world" 11:05:03 (Sadly, I don't think there's a very good mechanism to switch.) 11:10:57 hmm… in retrospect, it's not surprising that Birmingham University had bought a license to the Algol 60 specification 11:11:04 I suspect that those things probably last forever 11:11:12 and at one point, it would probably have been pretty important for them 11:18:46 -!- yorick has joined. 12:37:35 -!- Sgeo has quit (Read error: Connection reset by peer). 12:38:27 -!- zzo38 has quit (Remote host closed the connection). 13:07:46 -!- boily has joined. 13:08:14 -!- metasepia has joined. 13:12:40 good moily 13:13:41 quintorning. 13:28:29 -!- MindlessDrone has joined. 13:48:49 -!- shikhin__ has joined. 13:52:33 -!- Bike has joined. 13:52:55 ~metar KPDK 13:52:55 KPDK 121253Z 00000KT 7SM CLR 05/04 A3016 RMK AO2 SLP220 T00500039 13:52:59 ~metar CYUL 13:52:59 CYUL 121323Z 27018G23KT 15SM BKN040 M03/M10 A3012 RMK SC7 SLP200 13:58:25 I wonder if all Kxxx stations are assigned. 14:02:05 ~eval 26 * 26 * 26 14:02:06 17576 14:08:09 ha, someone called me? :) 14:08:13 -!- lifthras1ir has changed nick to lifthrasiir. 14:11:38 lifthellosiir. 14:11:49 were you pinged by a random letter combination? 14:17:02 -!- heroux has quit (Ping timeout: 264 seconds). 14:18:48 -!- heroux has joined. 14:18:49 -!- hogeyui__ has changed nick to hogeyui. 14:20:10 Hi, is "Lip-Sie" the correct way to shorten "Lipiec-Sierpien" (Polish for July-August) 14:31:43 -!- shikhin__ has changed nick to shikhin. 14:34:15 hm. apparently monads were there even in Sweden a long time ago. they celebrated them in the calendar! 14:34:53 (Vintermånad → November) 14:51:50 -!- mrhmouse has joined. 14:53:09 -!- jix has quit (Read error: Connection reset by peer). 14:54:31 -!- jix has joined. 15:09:16 -!- conehead has joined. 15:12:12 -!- augur has quit (Remote host closed the connection). 15:12:38 -!- augur has joined. 15:13:02 -!- sebbu has quit (Ping timeout: 246 seconds). 15:13:39 -!- augur has quit (Read error: Connection reset by peer). 15:14:02 -!- augur has joined. 15:19:15 -!- nooodl has joined. 15:20:59 -!- tertu has joined. 15:31:26 "Winter month" is kind of uninspired. (Then again, our current word for June is "summer month", and September is "autumn month".) 15:32:20 (Okay, September is a bit more like "autumnal month", but still.) 15:32:41 ("Syyskuu", not "syksykuu".) 15:33:32 -!- ter2 has joined. 15:33:33 -!- tertu has quit (Read error: Connection reset by peer). 15:36:08 -!- shikhin has quit (Ping timeout: 246 seconds). 15:41:07 -!- Lymia has quit (Ping timeout: 260 seconds). 15:48:05 -!- ais523 has quit. 15:49:40 -!- Sprocklem has joined. 15:50:04 fizzie: and then you have the likes of google translate who go from fr:automne into fi:pudota. 15:52:12 -!- shikhin has joined. 15:54:57 -!- sebbu has joined. 15:55:35 -!- sebbu has quit (Changing host). 15:55:35 -!- sebbu has joined. 15:58:55 -!- shikhin has quit (Ping timeout: 272 seconds). 15:59:27 -!- conehead has quit (Ping timeout: 252 seconds). 16:03:59 -!- conehead has joined. 16:04:45 Ah. Wonder if it goes via en:fall or what. 16:05:10 (Sounds like a reasonable assumption.) 16:11:07 -!- shikhin has joined. 16:12:34 -!- FreeFull has joined. 16:16:17 -!- ter2 has quit (Ping timeout: 272 seconds). 16:16:36 -!- ter2 has joined. 16:18:03 -!- shikhin has quit (Read error: Operation timed out). 16:18:23 (meanwhile, djinns and gargoyles and ants! oh my!) 16:31:32 -!- shikhin has joined. 16:32:12 -!- Lymia has joined. 16:38:12 -!- shikhin has quit (Ping timeout: 246 seconds). 16:38:46 -!- Lymia has quit (Ping timeout: 244 seconds). 16:43:34 -!- Koen_ has joined. 16:47:28 -!- Slereah has joined. 16:52:54 -!- tertu3 has joined. 16:52:55 -!- ter2 has quit (Read error: Connection reset by peer). 17:03:17 -!- Sprocklem has quit (Ping timeout: 246 seconds). 17:06:01 -!- Lymia has joined. 17:17:15 -!- `^_^v has quit (Ping timeout: 260 seconds). 17:19:04 -!- Lymia has quit (Ping timeout: 264 seconds). 17:19:44 -!- AnotherTest has joined. 17:22:31 DOUBLE DOUBLE TOIL AND TROUBLE 17:22:37 FIRE BURN AND CAULDRON BOILY 17:23:49 "*VERY IMPORTANT: The source files ( .tex, .doc, .eps, .ps, .bib, .db, .tif, .jpeg, ...) may be uploaded as a single .rar archived file. Please do not attempt to upload files with extensions .shs, .exe, .com, .vbs, .zip as they are restricted file types." 17:23:55 I'm sure this makes some kind of sense. 17:24:05 -!- Slereah_ has joined. 17:24:12 why do people do that -_- 17:25:47 -!- Slereah has quit (Ping timeout: 244 seconds). 17:26:09 That was an IEEE paper submission system thingie, for context. 17:26:45 it...doesn't make sense to me? 17:27:01 I guess .rar files are just safer than .zips? Somehow. 17:27:18 EVERYONE KNOWS THAT ITS IMPOSSIBLE TO PUT EXECUTABLES IN A RAR 17:27:47 http://technet.microsoft.com/en-us/security/bulletin/ms04-034 oh no! 17:28:37 Guess it's true that there are more .zip holes in the world. 17:29:01 -!- dessos has joined. 17:29:07 On the other hand, .rar files smell of pirated software. 17:29:25 Perhaps they could settle on accepting .7z instead. 17:30:51 why not a .tar.gz? 17:31:01 gzip is pretty universal.. 17:31:31 they probably use a lot of windows 17:31:43 why else even think about .com and .vbs 17:31:56 or well, .exe. 17:32:28 yeah but, gzip is used everywhere. It's the most common form of compression for HTTP 17:33:00 pretty sure modern win systems can handle gzip natively yeah? 17:33:19 I don't use an Windows system (except at work), so I wouldn't have a clue 17:33:35 .zip.gz. 17:33:59 :P 17:34:18 Preferrably with the .zip half done in the "store only" compression mode. 17:34:30 (To approximate tar.) 17:34:41 -!- `^_^v has joined. 17:34:55 my mother once asked me "if I keep zipping it, can I fit it on my floppy disk?", referring to her music collection 17:35:15 man 17:35:18 floppy disks 17:35:23 man 17:35:25 zip disks 17:35:31 :\ 17:35:37 hey, I liked zip disks 17:35:39 zip atracs 17:37:21 There was a Finnish company advertising their repeated compression that could perform miracles. 17:40:18 They were doing some completely unrelated software development work, and their in-house superstar programmer just happened to invent this impossibly good compression method as a by-product. 17:40:34 I never managed to figure out whether the firm's CEO was dishonest or just honestly deluded. 17:40:46 -!- Lymia has joined. 17:43:37 i remember something like that 17:43:48 Nowadays he seems to be doing "Drupal, Concrete5, eZ publish, jQuery, underscore, PhoneGap etc." at some other company. 17:44:11 but it seems like compression is becoming something end users no longer have to worry about 17:44:18 with cloud drives and all that 17:45:14 back from lunch, and quintopia recites incantations. 17:45:17 Such a shame. (I have fond memories of DBLSPACEing a win3.1 system disk, leading to it no longer start up.) 17:52:42 * quintopia wraps a box to mail at Canada by fastplane. 17:57:00 “at”? “fastplane”? are you sure that you aren't mailing that by ICBM? 17:57:32 -!- Koen_ has quit (Quit: The struct held his beloved integer in his strong, protecting arms, his eyes like sapphire orbs staring into her own. "W-will you... Will you union me?"). 17:58:03 fungot: how does one protect oneself from incoming missiles? 17:58:03 boily: do what's interesting to me. i'm so very, very nice. how do you mean that it's not even funny 17:58:23 fungot: ... you are disquieting. 17:58:24 boily: if you don't need it for? 17:58:50 fungot: I need it for my corporeal integrity. I know I'm being selfish, but that's something I like to possess and affirm. 17:58:51 boily: anna sun digikamera mulle synttrilahjaks? :p i like pianos. and the japanese page was created by me actually, we could 17:59:22 fungot: I'm a pianist, and I still need to learn more Japanese if you want me to edit your page. 17:59:22 boily: the stack should be fast enough for me 17:59:43 fungot: I'm also a human, if you didn't notice yet. that means no fast stacks. 18:03:55 Maybe they're talking about their internal stack 18:04:03 Are you, fungot? 18:04:03 FireFly: or the labels will fnord decide to make a minion/ sarahbot loop, using a function? 18:10:10 http://fi4.eu.apcdn.com/full/110606.jpg 18:11:34 http://www.adequacy.org/stories/2001.12.2.42056.2147.html is better. and doesn't treat autism unfortunately 18:15:38 fungot: Again with the spontaneous Finnish. 18:15:38 fizzie: i'm asking for alternative fnord compilers. do you just not want to sit down with it. 18:16:18 I admit to having compiled kernels in my youth. I still get pangs and urges, but I now believe in the Way of the Precompiled Binary. 18:17:02 boily: careful. flashbacks can come on suddenly and unexpectedly. 18:17:40 quintopia: I know. I synced my ABS this morning. the feeling of bliss and détachement I got seeing all those nice packages I could compile... 18:17:56 what bad would result from me compiling just one little package, eh? 18:18:18 none. 18:19:14 Just don't uninstall libacl when coreutils are using it :) (that's about the worst I did, back when I was using Gentoo. I still compile the occasional kernel though, and a ton of Haskell stuff.) 18:19:50 I suppose I should have expected Arch/Gentoo users here 18:20:16 arch has binary packages :) 18:20:17 I once rm -rfed pacman's cache. a very, very stupid move. 18:20:48 mrhmouse: have I asked you the The Question yet? 18:20:55 42 18:20:55 int-e: I know it does :P 18:21:06 boily: was that it? 18:21:23 42 is the answer, I'm curious about the question now ;-) 18:21:45 *goes back to preparing slides* 18:22:13 it's not the question, it's the The Question. very different. 18:22:22 mrhmouse: what are your approximate coördinates and body weigh? 18:22:29 int-e: what are you sliding? 18:22:44 -!- KingOfKarlsruhe has joined. 18:23:02 A talk on something unpublished I'm doing with tree automata. 18:23:28 working in academia? 18:23:54 boily: I can't give you both at once 18:24:16 yeah. <-- old and grumpy phd student 18:25:49 boily: I forgot to set a timer, when is my food done? 18:25:57 mrhmouse: a guesstimate will do. I know about Heisenberg and Nyquist and other approximathematicians. 18:26:01 olsner: eh? 18:26:17 boily: eh! 18:26:49 boily: USPS doesn't provide ICBM service anymore. no one could afford the $10,000,000 price for a small box 18:27:01 * boily gives a comfy sleeping bag (with fungot patterns) to int-e so that he can rest at his desk 18:27:01 boily: the problem we were talking about the fnord 18:27:15 boily didn't even ask for velocity... 18:27:15 There should be some kind of an #esoteric grumpy PhD student club. 18:27:26 Bike: I suppose he didn't 18:27:28 Bike: Gotta be careful of that uncertainty principle. 18:27:35 olsner: what are you cooking/heating/simmering/[REDACTED]ing? 18:27:52 boily: [REDACTED] 18:28:20 olsner: tabarn[EXPUNGED]. I was naïvely hoping that it wouldn't be so. 18:29:22 I'll just give it two minutes before it gets eaten 18:29:59 -!- ^v has joined. 18:30:59 boily: i have an idea for an experiment 18:31:08 -!- Lymia has quit (Ping timeout: 246 seconds). 18:31:41 boily: i wonder if i can get a letter delivered to you without using the post, just relying on the kindness of strangers to move it closer to its destination 18:32:58 -!- dessos has quit (Quit: leaving). 18:33:25 quintopia: actually a band I just saw in concert is doing that with a flag 18:33:57 they're having fans and friends of fans move the flag from show to show by meeting in person 18:34:51 mrhmouse: that sounds a lot easier. people will go out of their way to do something for a band they like. 18:34:57 they aren't really strangers 18:35:02 they all have something in common 18:35:30 this is true 18:35:48 you could also walk up until my apartment. google says it'll only take 380 hours. 18:36:07 ha 18:37:38 ~eval 380 / 24 18:37:38 15.833333333333334 18:37:44 http://zem.fi/~fis/google-walk.png 18:38:09 "This route may be missing sidewalks or pedestrian paths." 18:38:37 Yes, possibly. 18:39:13 a little over a month to walk to boily 18:39:22 that seems unreasonably quick 18:40:15 It's a small world after all. 18:40:24 ~metar CYUL 18:40:24 CYUL 121800Z 26015G26KT 15SM -SHSN OVC036 M01/M08 A3011 RMK SC8 SLP198 18:40:31 but unfortunately, i couldn't do it for at least a month 18:40:32 it's a cold world after all. 18:40:45 the -SHSN has begun! 18:40:45 ~metar EFHK 18:40:46 EFHK 121820Z 20016KT 9999 -RA FEW006 BKN008 BKN011 07/06 Q1010 NOSIG 18:40:51 i'm sending out a passport renewal application with this box 18:40:54 Still not winter here. 18:41:06 ~metar ESSA 18:41:07 ESSA 121820Z 23013KT 9999 BKN008 BKN010 08/06 Q1009 R88/29//95 BECMG BKN012 18:41:14 boily: tis the SHSN to be jolly! 18:41:14 eh. 18:42:08 metasepia: would you mind parsing the metar line for us poor folk who don't know all the codes? 18:42:12 quintopia: did you just make that horrible pun? 18:42:40 the process is still very much manual. which one do you want to be decoded? 18:42:44 ~metar KPDK 18:42:45 KPDK 121753Z 31020G26KT 9SM FEW041 14/05 A3018 RMK AO2 PK WND 31026/1752 SLP223 T01390050 10167 20028 50000 18:43:09 metasepia: you are aware you can incorporate new metar parsing code that has been ALREADY WRITTEN from github right? 18:44:10 >_>... <_<... ¬_¬'... v_v;... 18:44:19 ~metar KLZU 18:44:19 KLZU 121745Z 28010G18KT 10SM CLR 17/01 A3012 RMK ATIS K; RWY 25 LL 18:45:17 Location: KLZU 18:45:17 Day of month: 12 18:45:17 Time: 17:45 UTC 18:45:17 Wind: True direction = 280 degrees, Speed: 10 knots, with Gusts of maximum speed 18 knots 18:45:20 Visibility: 10 Statute Miles 18:45:22 Temperature: 17 degrees Celsius 18:45:25 Dewpoint: 01 degrees Celsius 18:45:25 QNH: 30.12 inHg 18:46:15 -!- Bike has quit (Ping timeout: 245 seconds). 18:47:06 the units are all mixed up. why would you measure temperature in Celsius but pressure in inHg? 18:47:08 sure it's the QNH? I always figured Axxxx was the QFE. 18:47:25 quintopia: because it is so. the SLPxxx group is in hPa, too. 18:47:54 this decoder should have like a selector for units and do conversions 18:50:55 -!- ^v has quit (Remote host closed the connection). 18:53:02 -!- ^v has joined. 18:53:04 -!- Lymia has joined. 18:59:50 -!- nathnath has joined. 19:01:33 `relcome nathnath 19:01:36 ​nathnath: Welcome to the international hub for esoteric programming language design and deployment! For more information, check out our wiki: . (For the other kind of esoterica, try #esoteric on irc.dal.net.) 19:02:01 thankyou . Hi all 19:03:00 -!- mroman has changed nick to mroman_. 19:22:54 -!- sebbu has quit (Read error: Connection reset by peer). 19:23:29 -!- sebbu has joined. 19:24:06 -!- sebbu has quit (Changing host). 19:24:06 -!- sebbu has joined. 19:27:13 -!- Slereah_ has quit (Ping timeout: 245 seconds). 19:27:52 -!- Slereah has joined. 19:35:58 -!- Oj742 has joined. 19:37:26 -!- Sprocklem has joined. 20:07:18 * boily mutters and swears and fevers and is not happy 20:07:21 ~yi 20:07:22 Your divination: "Brightness Hiding" to "Pervading" 20:12:44 -!- Bike has joined. 20:12:51 * quintopia writes a postcard for boily to happy him 20:13:13 ^^ 20:16:44 meanwhile, any Dutch and/or Flemish speakers here? 20:16:52 @tell Koen_ where have you disappeared? 20:16:52 Consider it noted. 20:17:07 i know where you can find some of those 20:17:48 on this network, i'm pretty sure l-b is dutch and The_Cat is belgian so.. 20:21:14 -!- Taneb has joined. 20:21:31 Tanello. 20:22:10 boily: hi 20:22:29 Semantics. I told Scribblenauts to make a "great drummer", and it made a ridiculously big one. 20:22:29 nooodl: iirc, you are of a belgianic persuasion? 20:22:34 nooodl: also, hi! 20:22:35 i'm a belgian dutch-speaker! i hear there is great request for us 20:23:31 nooodl: uhm... well, you see... there's that frivolous comment on reddit, and I was wondering if that guy was saying the Truth or he was «en train de nous péter de la broue». 20:23:34 http://www.reddit.com/r/linguistics/comments/1qgwc7/to_all_who_havent_yet_read_mark_twains/ 20:24:24 fizzie: :-) 20:24:42 Today I helped make a tower out of spaghetti and jelly babies 20:24:58 fizzie: I have noticed you can solve amazingly many problems with an infant. Someone’s hungry? Feed him an infant. Etc. 20:25:08 -!- Lymia has quit (Ping timeout: 245 seconds). 20:25:15 boily: hottentottententententoonstelling is quite famous as a jokey long word, around here! 20:25:41 Taneb: the jellies were the for the spaghetti to be stuck into, right? 20:25:46 s/the/there/ 20:26:02 Yeah 20:26:14 Our team won :) 20:26:18 i'd heard Rabarberbararabierenbarbarenbaardenbarbier and that one is relatively easy for me to read 20:26:31 "Hermafrodietestestestestestafette" requires some imagination... 20:26:33 engineering for the win! 20:26:48 102cm in 10 minutes 20:28:06 i think the last two are spelled wrong 20:28:25 * FireFly doesn't even know how to begin to lex that 20:28:52 should be verververververfverversing i think? 20:29:08 wait i'm missing a "ver-" 20:29:21 * boily is terrified by nooodl. 20:30:42 lemme break this down. "verven" is "to paint". one who paints is a "verver". one who paints far ("ver") is a "ververver". 20:31:10 which language is this? 20:31:16 "vers" means "fresh." a refreshment is a "verversing". hi this is dutch 20:31:37 ion: Yes, it seems to be rather... flexible. There was an orphan needing something to calm down, and feeding her sedatives worked like a charm. 20:31:40 nooodl: you meant rhabarberbarbarabarbarbarenbartbarbierbierbar? 20:32:20 a "paint refreshment" (verf + verversing) would be a "verfverversing", not a "*ververversing", which i think is where the poster messed up? 20:33:23 fizzie: I hope you're talking about Dwarf Fortress or something similar? 20:34:08 :D 20:34:26 boily: Scribblenauts. 20:34:35 i don't know where "wrong" comes from but i think it's a loose translation of what the "ver-" prefix means for some verbs 20:35:24 such as "vergissen", to be mistaken, from "ver-" (wrong) + "gissen" (guess) 20:36:34 fizzie: creepy. 20:38:20 -!- lambdabot has quit (Quit: enable TupleSections). 20:39:50 see, you once again killed lambdabot. 20:40:31 it'll be back in a moment 20:40:41 it just takes ages to rejoin all the channels it's on 20:40:52 and in any case, *I* killed it :) 20:41:00 *gasp* 20:41:13 how? are you Gregor? 20:41:27 I'm hosting it. 20:41:35 Why do people think I have any connection to lambdabot >_< 20:41:37 And who's Gregor ;-) 20:42:03 `echo Functional languages are for losers lul pwn 20:42:04 Functional languages are for losers lul pwn 20:42:16 Gregor: you are renouned for your secret and undetectable DDOS attacks 20:42:24 *renowned 20:42:35 -!- lambdabot has joined. 20:43:32 G'dayregor 20:44:33 int-e: Gregor is kinda like elliott. they have authority over the chännel. hth. 20:44:46 -!- Sprocklem has quit (Ping timeout: 240 seconds). 20:44:55 I don't have any authority over the channel either *_* 20:45:12 you heard it folks 20:45:17 gregor says he has no authority 20:45:24 and what gregor says goes 20:45:27 boily: I hoped that the smiley would help to avoid such comments. 20:45:37 so you better not give him any respect 20:47:02 int-e: I'm enrhumé. comments and smileys may not be understood. 20:47:36 what is that word 20:47:40 ion: Yeah, I just gave a cannibal an infant to eat. 20:48:16 quintopia: with a cold. 20:51:26 ion: Also I put a bug into a pizza. "That pizza looks delicious!" 20:51:46 fizzie: Now I want to play this game 20:52:02 :-) 20:52:25 mrhmouse: It's in the latest Humble Bundle, if you're interested. 20:52:52 http://youtu.be/GX0F3AHU264 20:53:10 Scribblenauts: Place someone who knows how to cook in the kitchen! 20:53:38 -!- MindlessDrone has quit (Quit: MindlessDrone). 20:53:45 ion: I also just made a phoenix out of fire, a chicken, and a phoenix. 20:53:50 hah 20:53:53 The last is a good source for magical power! 20:54:07 ion, does it work with "man"? 20:54:25 taneb: Yes, but let’s not mention it, that makes it less funny. 20:55:32 Does it work with "chocolatier"? 20:55:39 Or however you spell that 20:56:42 Scribblenauts apparently knows the word, so it should work. http://scribblenauts.wikia.com/wiki/Chocolatier 20:59:09 * boily sings «Un chocolat, deux chocolats, trois chocolats, quatre chocolats ♪» 21:05:11 -!- Oj742 has quit (Quit: irc2go). 21:08:31 fizzie: does the latest HB include Linux games? I can't look at it while at work 21:08:41 -!- Lymia has joined. 21:08:41 -!- Lymia has quit (Changing host). 21:08:41 -!- Lymia has joined. 21:09:24 mrhmouse: Sadly, no. It's one of these "not-so-indie" bundles. 21:10:39 -!- Slereah has quit (Read error: Connection reset by peer). 21:10:53 -!- Slereah has joined. 21:10:54 mrhmouse: (It's a WB Games bundle, containing Scribblenauts Unlimited, the two Batman: Arkham Whatever games, and two of something called F.E.A.R., as well as the LOTR: War in the North game.) 21:11:12 Also Steam-only. 21:11:34 (Oh, and Scribblenauts is on the "pay more than the average" side too.) 21:12:04 Scribblenauts works perfectly in Wine. 21:12:19 Unfortunately, the Batman games apparently don’t, so i didn’t buy the bundle. 21:12:24 -!- impomatic has quit (Quit: ChatZilla 0.9.90.1 [Firefox 25.0/20131025151332]). 21:12:24 I already have Scribblenauts. 21:12:42 I have the first scribblenauts game, not any of the sequels though 21:13:06 I mostly bought it for Scribbels. I don't have any aspirations of Batmanity. 21:13:41 Guns of Icarus Online and Dwarf Fortress are my games atm 21:13:55 I was disappointed with the description of the newest Scribblenauts game. It’s a battle game now. 21:14:26 Haven’t tried it, though. Perhaps it doesn’t suck. 21:18:14 -!- zzo38 has joined. 21:19:00 ion: Yeah, I just gave a cannibal an infant to eat. <--- scribblenauts against humanity? 21:22:57 Disappointing.. I don't use Wine. Oh well, I'm not bored with Kerbal Space Program just yet. 21:23:18 -!- carado has quit (Ping timeout: 252 seconds). 21:24:08 -!- nisstyre has joined. 21:24:27 -!- AnotherTest has quit (Ping timeout: 240 seconds). 21:26:32 -!- shikhin has joined. 21:26:59 -!- Slereah has quit (Ping timeout: 272 seconds). 21:27:37 -!- Slereah has joined. 21:28:14 -!- boily has quit (Quit: the return of the bride of the children of the mutant chicken II: electric boogaloo). 21:28:25 -!- metasepia has quit (Remote host closed the connection). 21:32:03 -!- Bike has quit (Ping timeout: 272 seconds). 21:34:25 Sigh. 21:34:46 Haneb 21:36:40 -!- sebbu has quit (Ping timeout: 245 seconds). 21:39:14 Sigh, shachaf. Sachaf. 21:40:48 psion 21:41:01 hichaf 21:41:07 hogan 21:41:23 ψon 21:41:49 -!- Sprocklem has joined. 21:53:13 -!- Bike has joined. 21:54:12 ψder 22:01:02 -!- Bike has quit (Quit: Reconnecting). 22:01:15 -!- Bike has joined. 22:11:00 I really want to hear an Around The World/Around The World Red Hot Chilli Peppers/Daft Punk mashup 22:12:34 (the Daft Punk song has the better lyrics) 22:13:48 daft punk has lyrics? 22:14:24 ok i looked it up on a lyrics site and it rules 22:15:14 :D 22:15:15 -!- Lymia has quit (Ping timeout: 246 seconds). 22:16:01 -!- Sprocklem has quit (Ping timeout: 252 seconds). 22:16:05 -!- Lymia has joined. 22:16:18 -!- Lymia has quit (Changing host). 22:16:18 -!- Lymia has joined. 22:18:01 Have you written any just intonation chiptune music? It seems suitable for such thing. 22:19:45 matlab profiler claims 54.862 of the 55.404 second runtime was spent in "java.util.concurren.LinkedBlockingQueue". mildly skeptical here 22:19:48 (I have done so in Famicom Hangman, and instead of using A=440Hz, adjusted the tuning so that the notes would have the exact pitch I wanted and don't have to be detuned.) 22:23:57 java and matlab: two great tastes that taste great together 22:24:02 also how does that even work 22:24:09 shachaf: how goes 22:24:11 Okay, that's a mondegreen that completely changes the meaning of the song 22:24:24 iunno. you can call out to java and stuff. 22:24:41 all this means is that the profiler has no goddamn clue what to do with parallel code, which is unsurprising 22:24:54 Touch by Daft Punk, "If love is the answer you're home." => "If love is the answer you're wrong." 22:27:01 -!- nisstyre has quit (Ping timeout: 252 seconds). 22:27:26 Turns it from slightly regretful to really really bitter 22:27:43 wow, one run calls this not-built-in function one and a half million times 22:27:53 profiling is fun. 22:27:58 nuilt-in function 22:28:38 -!- tertu3 has quit (Ping timeout: 240 seconds). 22:31:42 this thing is so fancy, it highlights lines hat took up more time in a deeper shade of red 22:37:25 nice 22:37:49 pro files 22:39:44 hi kmc 22:39:56 goes as expected 22:40:26 Bike: i love profilers 22:40:28 they are so fancy 22:40:43 -!- nisstyre has joined. 22:40:51 I prefer filers 22:44:18 ion: you should teach Taneb about categories 22:44:58 Categories are like chili con carne 22:45:22 Semigroupoids are like the vegetarian version 22:45:47 ... 22:45:48 h8r 22:45:54 Doesn't con carne mean "with meat" 22:46:01 yes 22:46:10 So, vegetarian chili con carne is... just chili 22:46:20 Possibly chili con quorn 22:46:31 Taneb: so of course you can also think of that category as one where the objects are R^n and the arrows are linear functions 22:46:57 Taneb: "chili sin carne", ı think. 22:47:13 con textured soy protein or something 22:47:52 shachaf, I don't think you can, in the case of non-square matrices 22:48:22 -!- tertu3 has joined. 22:49:24 There is Penrose tensor diagrams, which can be applicable to matrices, although I think they can be applicable to tensor categories too (which features of the diagram are available depends on what features the category has) 22:49:52 shachaf: you dropped one of these --> . 22:50:12 (I noticed that matrix multiplication formed a category when one of my lecturers demonstrated that set relations can be defined in terms of them) 22:50:16 Taneb: Why not? 22:50:28 Taneb: A linear function : R^n -> R^m. 22:50:56 shachaf, maybe I'm just insufficiently familiar with linear functions 22:51:38 I also notice that matrix multiplication forms a category, but not for that reason. 22:52:39 Taneb: A linear function between two vector spaces is a function f such that f(x + y) = f(x) + f(y); f(rx) = r*f(x) 22:52:47 Where x and y are vectors and r is a scalar. 22:53:35 You can generally represent them as matrices. 22:54:08 Okay 22:54:31 I noticed because of Penrose diagrammatic tensor notation. Do you know about Penrose diagrammatic tensor notation? 22:54:41 I do not! 22:54:41 I don't. 22:54:46 Hmm, maybe I do. 22:54:59 (There is a Wikipedia article, in case you do not know.) 22:55:14 It looks like string diagrams. 22:56:58 I think when the entries of the matrices are in the two-element boolean algebra this category is identical to Rel 22:57:03 -!- augur has quit (Remote host closed the connection). 22:57:23 ? 22:57:51 Like, matrix multiplication is defined when the things in the matrix are a semiring 22:58:29 Taneb: Yes I noticed that it is when they are a semiring. (I did not notice if it is identical to Rel, though) 22:58:43 -!- ter2 has joined. 22:58:57 {F, T}, + = ∨, * = ∧ 0 = F, 1 = T forms a semiring 22:59:25 OK, yes I know that too. 22:59:28 -!- tertu3 has quit (Read error: Connection reset by peer). 22:59:58 the scalar of a vector space has to be a field 23:00:34 but if you want it to be only a ring then you can talk about modules instead of vector spaces 23:00:50 well you can just yes that 23:01:11 What about when you're talking about the module over a ring D of differential operators 23:01:12 did you know a Z-module is the same thing as an abelian group 23:01:20 i'm reading that now 23:01:28 but I have to eat breakfast instead of understanding it 23:01:30 someone told me that one week ago 23:01:30 ttyl 23:01:39 Taneb: whoa, dude, that's some serious inventioning going on right here 23:01:41 `? d-module 23:01:42 maybe i will have chile con carne 23:01:43 D-modules are just modules over the ring of differential operators. Taneb invented them. 23:02:14 kmc: chile is p. far from korea 23:02:47 the antipode of Formosa, Republic of China is Formosa, Argentina 23:03:03 Is Penrose notation as annoying as Einstein's 23:03:14 are antipodes related to octopodes 23:03:15 What is Einstein's? 23:03:33 Anyway, when the matrix is filled with these {F, T} (rather than ℝ), I think this category is equivalent to Rel 23:03:41 zzo38: einstein summation notation i mean 23:04:06 Bike: I am not aware of such notation. 23:04:50 there is a wikipedia article 23:04:54 OK 23:05:02 Bike: that's the notation where you just don't write the sigma, right 23:05:09 and you just gotta know it's there 23:05:31 yeah 23:05:37 the worst imo 23:05:41 imo why not 23:05:47 might as well drop the expression too 23:05:58 "look fuck you, i'm Einstein" 23:06:16 - Bike 23:06:25 yes 23:07:56 -!- oerjan has joined. 23:10:47 -!- mrhmouse has quit (Quit: Leaving.). 23:16:51 -!- KingOfKarlsruhe has quit (Quit: ChatZilla 0.9.90.1 [Firefox 25.0/20131025151332]). 23:16:53 -!- Ghoul_ has quit. 23:22:53 -!- Lymia has quit (Ping timeout: 272 seconds). 23:33:01 -!- ter2 has quit (Ping timeout: 272 seconds). 23:34:36 -!- sebbu has joined. 23:35:13 -!- sebbu has quit (Changing host). 23:35:13 -!- sebbu has joined. 23:48:24 matlab's help cites "Nineteen Dubious Ways to Compute the Exponential of a Matrix" 23:49:17 haha 23:49:32 -!- Phantom_Hoover has joined. 2013-11-13: 00:05:56 -!- Ghoul_ has joined. 00:07:59 -!- Taneb has quit (Quit: Leaving). 00:24:19 -!- nooodl has quit (Ping timeout: 272 seconds). 00:25:54 -!- augur has joined. 00:26:24 -!- nathnath has left. 00:32:48 -!- prooftechnique has joined. 00:33:55 -!- Lymia has joined. 00:56:44 -!- nisstyre has quit (Quit: Leaving). 00:58:45 -!- Bike has quit (Ping timeout: 248 seconds). 00:59:18 -!- Phantom_Hoover has quit (Remote host closed the connection). 01:01:45 -!- tswett has left ("http://quassel-irc.org - Chat comfortably. Anywhere."). 01:06:10 -!- Bike has joined. 01:07:50 -!- augur has quit (Quit: Leaving...). 01:08:43 -!- shikhin has quit (Ping timeout: 244 seconds). 01:09:44 -!- prooftechnique has quit. 01:12:44 -!- yorick has quit (Remote host closed the connection). 01:27:38 -!- prooftechnique has joined. 01:31:45 -!- ter2 has joined. 01:34:40 -!- ter2 has changed nick to tertu. 01:35:58 Semigroupoids are like the vegetarian version <-- i don't see the need for the term semigroupoid, since categories are identical. 01:36:16 * oerjan hides under rock 01:41:42 i prefer non-associative semigroupoids 01:45:40 oerjan: Uh, i thought semigroupoids are categories sans id. But i probably remember incorrectly. 01:45:49 "On Windows, we cannot make a flie named 'aux'. So It doesn't make src/components/main/layout/aux.rs on Win" 01:45:52 best platform ever 01:46:27 the top hit for magmoid is relevant, dunno about the rest. 01:47:44 kmc: :-D 01:49:10 -!- Ghoul_ has quit. 01:49:27 kmc: Yes, AUX is a DOS device name in Windows. So is CON, PRN, COM1, COM2, LPT1, etc. Yes it can be a problem, such as that one. 01:50:12 con.carne 01:50:27 who here remembers 01:50:49 They should have perhaps used a symbol at front which isn't used in actual filenames, in DOS 1.0, but that isn't what they did. 01:51:07 kmc: \o/ 01:51:08 | 01:51:08 /< 01:51:20 click here 01:51:34 90s Kids Remember These 12 IE5 DoS Exploits 01:52:31 I have done in some versions of ZZT, made a link to CON in a menu, which caused strange things to happen. In the latest version I believe that bug is fixed and a link to CON is an error. 01:52:55 ion: that is correct. thus semigroupoids are not identical, but categories are. 01:58:56 oerjan: Oooh, i see what you did there. 01:59:51 puns: sometimes they get too deep and sink 02:00:20 Especially funpuns 02:00:51 i sunk columbus, oh 02:01:04 oh no 02:04:40 -!- Sgeo has joined. 02:05:41 kmc: hell, no 02:07:10 Are there any good amateur philosophy subreddits? I get the impression that /r/philosophy isn't one. I want to rant about how "same" is a silly concept 02:07:21 oh my god 02:07:56 "amateur philosophy subreddit" ;_; 02:08:21 kmc: i think we need to find such a subreddit to ask whether it's ethical to answer that question 02:08:50 do you enjoy arguing with programmers who have never taken a philosophy class or read a book but think that they're automatically an expert because humanities are for dumb people 02:08:51 kmc: Not just any amateur, *good* amateur. 02:09:33 Also, kmc, I have a criticism of Rust in regards to macros 02:09:34 at least when they do this about philosophy it's of no real consequence to anyone 02:10:09 http://www.reddit.com/r/askphilosophers seems empty 02:10:16 Sgeo: oh? 02:10:28 (based on r/askhistorians, it was the obvious place) 02:10:48 "To make this behavior more obvious, the rule has been made that use-statement always need to be written before any declaration, like in the example above. This is a purely artificial rule introduced because people always assumed they shadowed each other based on order, despite the fact that all items in rust are mutually recursive, order independent definitions." 02:11:34 Having artificial restrictions like this could hinder the ability for macros to emit such code without regard to their location in the file, or mixing two separate macros that both expand to use-statements and declarations 02:11:48 http://www.reddit.com/r/askphilosophy looks promising 02:11:59 I think I'm lagging a bit 02:12:22 Sgeo: interesting 02:12:29 I'm not sure that macros can even emit "use" items at the moment 02:12:31 but I think they can 02:12:35 rust-http generates whole modules from macros 02:12:53 btw, another confusing consequence of that is "use foo::Bar; ...; mod foo;" 02:12:57 it must be in that order and not the other 02:13:16 I think there's another similar artificial restriction that's related (external mod, I think?) but same concept/concern 02:14:01 "mod foo;" is a definition and not just a declaration; it creates a module named "foo", but it grabs the module contents from an external file foo.rs and so it doesn't really "look like" a definition 02:16:03 Sgeo: you should start reddit.com/r/Sgeo 02:16:59 shachaf: that's such a good idea, I'll hop in my time machine and do it a year ago 02:17:54 (I wanted to see what the mod tools were like) 02:18:14 I CAN SEE THAT 02:18:15 it's private :'( 02:18:18 but nothing else 02:18:36 i was hoping for a place full of Sgeoy things 02:18:47 such as «Are there any good amateur philosophy subreddits? I get the impression that /r/philosophy isn't one. I want to rant about how "same" is a silly concept» 02:18:59 shachaf: are you sure this would be safe? 02:18:59 did sgeo say that 02:19:24 oerjan: for whom 02:19:27 Bike: well he said the same thing 02:19:44 oh, indeed he did 02:20:07 a good amateur philosophy subreddit presumes good amateur philosophy 02:20:08 whether this means he said that, you'll have to ask an amateur philosopher. 02:20:17 Bike: well, it could be empty 02:20:24 checkmate 02:20:27 damn. 02:20:39 shachaf: for the universe. maybe it would turn reddit into a black hole or something. 02:20:52 could make /r/BikeGetsOwned. only user is shachaf 02:21:01 just constantly burning me left and right 02:21:59 * oerjan remembers to drink his irange juice 02:22:00 the other day i found reddit.com/r/magicskyfairy which seems to be a sort of improvement on reddit.com/r/atheism 02:22:19 i don't know what that is, i thought it was orange but the keyboard doesn't lie 02:22:52 the true spirit of reddit, i think 02:23:13 haha an improvement on /r/atheism 02:23:45 /r/atheism, now with blackjack and hookers 02:23:55 *but with 02:24:17 kmc: hard to believe, i know 02:27:28 I have heard a lot, many people think of "God" as the "magic sky fairy" and is why those people don't believe in such things. Other people are not so dumb. And learn ignosticism too. 02:28:33 are antipodes related to octopodes <-- whatever you do, don't mix them, especially not in 8:1 proportion 02:29:36 Hey, i heat my house with that energy. 02:30:35 also you get a nice tan from the gamma rays? 02:31:07 Only cos. 02:32:05 i get really nervous whenever I add an rm -rf rule to a makefile 02:32:50 hehe 02:34:01 zzo38: I don't think it's *why* those people don't believe in a god, it's just a way to make fun of people who do 02:34:41 kmc: Probably you are correct at least in some cases. I don't know if it is true in all cases. 02:34:51 i dislike religion immensely but that kind of mockery is probably bad and unhelpful 02:35:11 I think you are correct, it isn't very helpful. 02:35:42 one thing that most of the Angry Internet Atheists tend to miss is that religions fulfill like 30 different social roles, many of which have nothing to do with superstition or metaphysics 02:35:51 the fact that they are tied up with superstition and metaphysics is historical baggage 02:36:05 Yes, that is true too, you do make the good points too 02:36:10 hooray 02:39:32 I think ignosticism should be a thing. You just don't think about the existence of god 02:39:43 it is a thing 02:39:47 zzo38 just recommended it 02:39:58 (I've heard it called "apatheism" as well) 02:40:03 Oh, wow, it is a thing 02:40:09 it actually means the belief that questions of theism can't be dealt with without an adequate definition of 'god' etc 02:40:14 there are other positions like, "whether god exists is an ill-posed question" 02:40:33 which is different from "i don't care" and also different from the traditional agnostic "we can't ever know" 02:40:43 "whether god exists is independent of the axioms of ZFC" 02:40:52 Bike: Yes that is what I meant 02:41:06 kmc: That one's a little better 02:41:11 kmc: [gödel joke] 02:41:37 but of course we can talk about systems ZFC+Θ and ZFC+¬Θ 02:41:53 Yes I think that is correct, whether or not God exists is an ill-posed question. 02:42:03 can God create a statement of number theory which is so self referential that even He cannot prove or disprove it 02:42:57 I assume that Gödel actually said something about that at some point 02:42:59 anyone know what? 02:43:20 oh, i was referring to godel's attempted proof of god's existence 02:43:28 yeah I figured 02:44:00 lexande: do you know if he said anything about it? 02:44:21 I guess it is similar to other simpler theological puzzles such as, can god create an object which is both light and heavy 02:44:28 or a glass which is both empty and full 02:44:39 (can god create an object whose inertial mass differs from its gravitational mass?) 02:45:38 Bah, temporal logic 02:45:57 -!- drlemon has quit (Ping timeout: 240 seconds). 02:46:10 kmc: I suppose they might be possible, but not in this universe (by definition) 02:46:14 hmm 02:46:28 can god create a new universe where naive set theory is consistent 02:46:37 a philosopher buddy of mine happened to be reading a book on godel's philosophical influences, perhaps it is relevant http://www.amazon.com/After-Godel-Platonism-Rationalism-Mathematics/dp/019960620X 02:46:59 as for that, i <3 psychologism~ 02:47:04 kmc: But set theory is mathematics, not physics. Therefore the question is wrong. 02:47:07 yeah i don't "read books" or anything like this 02:47:41 zzo38: oh? 02:48:10 zzo38: uh, i think that's explicitly the question 02:48:22 of whether maths had to be the same in all "universes" 02:48:34 -!- nisstyre has joined. 02:48:44 I think it does have to be the same. 02:49:10 how about the fact that YHWH apparenly thinks that pi=3.0? 02:49:18 prooftechnique: I guess my view is a form of agnosticism, in that I believe any evidence of God which is admissible to a finite mind would be better explained (c.f. occam's razor) with beings of finite power instead 02:49:23 "god doesn't exist, aliens are just fucking with you" 02:49:25 lexande: That is simply an error in the Bible. 02:49:39 Any book can contain errors. 02:49:56 prooftechnique: so I can't assert "there is no god" but i have no reason to believe there is one, and I never could 02:50:04 zzo38: so i'd say that no universe where naive set theory is consistent exists 02:50:13 but i think this relies heavily on my definition of "exists" 02:50:13 zzo38: many people believe quite explicitly that the Bible is exempt from that fact about books 02:50:17 kmc: I can get down with a little Lovecraftian theology, sure 02:50:23 prooftechnique: heh is that what we call it 02:50:52 However if you say God created that, God did that, deliberately, accidentally, by choice, by having no choice, etc, it is just metaphorical and why should we think it is applicable to God in the same way it is to us? Probably it isn't. 02:50:59 kmc: how about the statement that you're in a simulation? 02:51:08 could naive set theory be consistent in this cardboard box right here 02:51:14 Bike: no. 02:51:17 That sounds exciting because maybe there are cheat codes 02:51:21 People think of God as a Person, but that is silly and stupid. 02:51:37 Bike: The Axiom of the Carboard Box says it is 02:51:47 lexande: hmm, it depends on what you mean by "simulation" 02:51:47 Still it can be a metaphor when some people draw the picture (which is a representation, as inaccurate as others); it is not the kind of metaphor I prefer however. 02:51:54 lexande: are you sure. have you even seen the box! 02:52:09 Bike: does the cardboard box exist? if so then i'm sure 02:52:11 it's pretty nice. filled with books. books i like, so objectively good 02:52:29 you're that sure huh 02:52:30 -!- tertu has quit (Ping timeout: 245 seconds). 02:52:35 kmc: depends how? 02:52:43 The Weak Axiom of the Cardboard Box says it might be consistent in a certain neighborhood of the box. 02:52:56 The Axiom of the Weak Cardboard Box says that the box might fall apart under stress. 02:52:57 in which topology 02:53:04 prooftechnique: http://lesswrong.com/lw/qk/ 02:53:23 lexande: if I take a red pill and trip balls and emerge naked from a pod of alien goo, I'll probably conclude that I was in a simulation before, but maybe aliens are just tricking me, but if their trick is sufficiently advanced then maybe it counts as a simulation too 02:53:47 i suppose i could have said "why is 'X theory is consistent' a statement you make about places" directly but i like boxes 02:54:03 What is the simulation in, then? 02:54:11 intercal 02:54:16 Turtle 02:54:24 kmc: how do you decide whether pre or post red pill is the simulation? 02:54:32 and who is emerging from the pod 02:55:09 valid questions too 02:55:13 but anyway i'm specifically considering the statement that the whole universe is more or less how it looks except it's a simulation inside a larger universe 02:55:16 "I" is a leaky abstraction 02:55:33 and it seems like no evidence could convince me of that for the same reason none could convince me of god 02:55:38 yeah, maybe 02:55:38 which is good, because it allows some p. cool exploits 02:55:41 I will think about that more 02:55:54 and yet it seems odd to assign that statement extremely small probability 02:56:07 given the arguments about how the universe is probably a simulation, etc 02:56:16 oh, hey, i read a nice paper about this once, let me see if i can find it again 02:56:16 Does the simulation have to be in a larger universe? 02:56:30 I don't think the universe is a simulation, although I cannot discard that hypothesis. 02:56:33 people write papers about brains in vats all the time though :/ 02:56:34 so i think i have to say that "the universe is a simulation" is not a meaningful statement, since only things in the universe "are" 02:56:44 kmc: I think the problem is that "naive set theory" refers to something within this universe. 02:56:46 What is universe in, anyways? 02:56:53 if you assume mathematics can vary over universes then "naive set theory" as a concept is local to this one 02:57:14 here it is, drevil.pdf 02:57:24 zzo38: what evidence might cause you to increase or decrease your confidence in that hypothesis? 02:57:27 naive set theory is local to this box 02:57:48 Bike: So the Axioms of the Cardboard Box are consistent 02:57:50 Sweet 02:57:52 good, good 02:57:52 I assume mathematics is fixed and cannot vary over universes. However, if a mathematical theory is inconsistent (i.e. all well-formed statements are theorems) then it isn't a Mathematical Truth. 02:57:55 we should find some actual space aliens and ask them what their mathematics is like 02:57:56 how do you compare the probability of the universe being a simulation with the probability of in-universe aliens trolling you 02:58:02 "Defeating Dr. Evil with self-locating belief", if anyone's interested. 02:58:04 zzo38: you ever dream maths? 02:58:19 when i dream maths it's all wrong 02:58:28 kmc: i have a fantasy of running some AI simulations and seeing what they can come up with under various developmental schemes. 02:58:34 Yes I sometimes to dream about mathematical things 02:58:38 things feel like proofs that certainly are not proofs 02:58:55 I sometimes finish proofs while I'm asleep 02:58:57 which i find deeply disconcerting 02:59:16 Dr Evil is about, uh, "Dr. Evil learns that a duplicate of Dr. Evil has been created. Upon learning this, how seriously should he take the hypothesis that he himself is that duplicate?" 02:59:18 i had a dream where I discovered a security flaw in a real software system and it turned out to be real 02:59:29 And I notice that some of the "illogical" things in my dreaming are actually logical if you use the wrong kind of logic. 02:59:44 kmc: nice 02:59:47 wrong kind, huh. 02:59:52 the reasoning in my dreams is consistently nonsense 02:59:54 i hate dreaming 02:59:54 kmc: I think something similar may have happened to me, but I am unsure. 03:00:01 and with that, i'm going to take a nap 03:00:05 Bike: At the end, do they fight, or do they make out? 03:00:09 Yes the reasoning is sometimes nonsense. 03:00:09 enjoy, lexande 03:00:21 prooftechnique: well, one of them is being tortured. 03:00:25 prooftechnique: one and then the other 03:00:26 Kinky 03:00:30 also man i'm glad i'm not a mathematician because i would not fit in 03:00:42 However I am distinguishing between logic (which is mathematics) and reasoning (which is informal thinking, and should be logical). 03:00:45 It's fun, Bike. Pinky swear 03:01:02 It's just pacing for hours and thinking really hard 03:01:13 Which, as I understand it, is what most people do, just not about math 03:01:29 yeah, i do that about parts of china and caterpillar legs. 03:01:39 By "wrong kind of logic", I mean for example linear logic where classical logic would be a better model in real situations, and vice versa, and other similar kind of things too. 03:01:43 -!- nisstyre has quit (Disconnected by services). 03:01:59 -!- nisstyre has joined. 03:02:23 If everyone turned all their nervous energy to some light mathematics, there'd be some neat stuff to show for it :D 03:02:50 three billion proofs of the parallel postulate from the other axioms 03:03:07 oerjan: That was pretty cool 03:03:11 Definitely bookmarking 03:14:02 An example of something that doesn't follow ordinary logic, but may be logical in other kinds of logic, in my dreams, may be the one where I had the belief that I (as my character in the dream) had never been there but that I (as myself) had been to that place before, and these beliefs could not be combined in my reasoning. (As it turns out, the second belief is also untrue, but I believed it while I was asleep.) 03:14:39 -!- Oj742 has joined. 03:15:16 Despite being strange (and clearly incorrect), it still appears perfectly logical to me, just using the "wrong kind of logic". 03:19:48 Do you have dreams like that too? 03:20:40 why do you think math "does have to be the same [in all universes]", i'm curious 03:21:02 i mostly dream about being very afraid 03:22:34 Because mathematics is the *real* reality. 03:22:43 why do you think that? 03:22:46 Bike: Very afraid? If anything in particular? 03:23:04 the things i'm afraid of aren't very constant between dreams, no 03:23:31 But what are they for instance? Do you know? Or is just being afraid in general? 03:23:37 * constant looks at Bike 03:23:45 * Bike looks at constant 03:24:25 zzo38: one time, it was a virtual reality character, an imperial japanese soldier who had strapped himself with explosives. for example. 03:24:40 Ah, OK. 03:24:51 another time it was the concept of dreaming. another time it was a big thing that looked like a displacer beast made of half-cooked meat 03:25:00 OK. 03:25:46 When I am dreaming of being afraid of something (which isn't common), it is almost always other people trying to push me or rescue me or something, it seems. 03:26:47 Bike: Sounds low calorie 03:26:54 prooftechnique: also, http://qntm.org/responsibility :) 03:27:50 oerjan: https://sites.google.com/site/asenselessconversation/ 03:27:52 I like this one 03:28:51 oerjan: Also, did you hear about Google/NASA's quantum computer? 03:29:28 um did they buy one of those d-wave things that are _possibly_ sort of qc but not the "real" thing 03:30:20 (aaronson at shtetl-optimized likes to criticize them) 03:31:07 It is a D-wave, yes 03:31:44 iirc from his last post about it, they cannot do "real" quantum algorithms and the evidence that what they can do is hard with classical computers is increasingly weak 03:31:54 Aww 03:55:11 kmc: should I comment on my Rust thoughts elsewhere? 03:55:28 perhaps you could use the rust channel 03:56:08 I could bring it up in the Rust channe; 03:56:08 channel 03:58:11 I feel awkward being on the Mozilla IRC network while being a Chrome user 03:58:29 it's in your user-agent, they can deal! 03:59:04 Disable VERSION then. 04:05:14 kmc: fwiw, a thing I do think I like about Rust is its do syntax. As readable as Ruby, without an actual physical distinction, just syntactic sugar 04:37:42 yep 04:37:59 'for' used to be similarly superficial sugar 04:38:14 -!- ^v has quit (Ping timeout: 240 seconds). 04:38:15 for a call with a lambda 04:38:16 but it didn't work out so well, so now it's sugar for calling .next() repeatedly 04:38:40 not such a big deal to consumers, but implementing an object with a .next() method is a lot more work than implementing a function that takes a function 04:38:43 oh well 04:38:58 (the reasons for switching were composability and performance, I think) 04:39:06 I often don't like to knock out opponent's active pokemon cards. 04:39:13 C++ lambdas can do something Rust lambdas can't which is inline into the function they're passed to 04:39:28 that's weird 04:40:00 in C++ you can do void f(std::function g) but you can *also* do template void f(G g) and the latter will enable such optimizations 04:40:27 with Rust if you want the latter you need to define and implement a trait 04:41:06 Sgeo: I dunno, if you have specific questions or suggestions you could take them to #rust on irc.mozilla.org 04:42:35 Already did, someone commented on my mentioning the restriction, but not my comment about how it affects macros 04:42:42 okay 04:42:52 you could press on that point? 04:42:55 i thought it was an interesting point 04:43:14 I don't know how to do that without being rude 04:44:04 -!- ^v has joined. 04:46:47 i give this article an eight of ten. most enlightening. http://krazydad.com/tutorials/makecolors.php 04:47:31 prooftechnique: reading your senseless conversation link now, i think i guessed pretty quickly where this is going... 04:47:42 oerjan: Yeah, so did I 04:47:50 That was the only disappointing thing about it 04:53:29 kmc: are you in the chat? 04:53:50 not paying attention atm 04:57:47 http://zzo38computer.org/img_16/pokemon_card_never_switch.png As it turns out both of us had the same active pokemon card during the entire duel, never shifting or getting knocked out. (I knocked out their bench pokemon cards though; the AI is really bad.) 05:04:00 oerjan: i am amused by the idea of hofstadter administrating the test tho :D 05:07:59 zzo38: the symbols look like a mess, how can you read that? 05:08:50 -!- augur has joined. 05:08:55 oklopol: I can read it, I can tell you its meaning: Side card, Active pokemon card, Number of cards remaining in draw pile. 05:09:18 i could read up to side card 05:09:39 but kanji are a mess 05:09:58 Well, now you know the rest too. Yes the kanji is in a small resolution that is hard to read, but I know what they mean in this context anyways. 05:10:50 how do you say the active 05:11:35 I don't know. 05:11:58 But that is what it means in this context. 05:12:08 ok 05:13:49 Do you play Pokemon card? It would be more understandable to someone who does. 05:15:17 i don't 05:15:42 but i play some japanese 05:16:21 What games can you play in Japanese? Shogi? Mahjong? 05:16:55 no i mean i play the language itself 05:17:02 in the sense of pretending to learn it 05:17:21 well i've played some mahjong obviously 05:17:29 Pretending to learn it? 05:17:45 Is it Japanese mahjong? Do you know Washizu mahjong? 05:18:41 i just know the mahjong computer game, it's a kind of solitaire 05:18:50 you have to remove pairs until the heap runs out 05:18:55 and then you win 05:19:19 Yes, mahjong solitaire, I know that one, but that isn't the real mahjong game, it is just the mahjong solitaire, using the same tiles 05:19:51 i sort of figured 05:19:53 The true mahjong game is 4 players game. 05:19:55 what's the actual mahjong like 05:19:57 ohhhh 05:20:03 i've read its rules 05:20:06 i think 05:20:12 there's like four winds and stuff 05:20:16 Yes 05:20:36 and like a great wall made from the pieces maybe_ 05:20:37 ? 05:20:55 Yes, usually there is. (Sometimes a bag is used instead.) 05:21:09 There is many different variants, such as Chinese game, Japanese game, etc. 05:21:44 dunno which one was in the big book of random games i read once 05:22:25 http://en.wikipedia.org/wiki/X-machine okey doke 05:30:57 oerjan: i am amused by the idea of hofstadter administrating the test tho :D <-- oh, i didn't notice the first name coincidence. 05:31:38 coincidence? i'd guess intentional. it's not like Zongker is much of a computational philosopher 05:46:11 hey oklopol 05:46:15 hii 05:46:21 surely you know the answer to my question 05:46:45 hide the finnish grammars! 05:46:49 how can we probe a formal language for word-word interactions without knowing the grammar or the class of grammars involved? 05:47:48 well that's easy but you don't know enough flexo-flamigold theory to understand it so no can do 05:48:16 probe like, how? temperature? 05:48:32 Bike: yes, temperature 05:54:09 oklopol: it's more-or-less like canasta, if you've played that 05:54:12 it's similar anyway 05:54:20 mahjongg, I mean 06:00:38 i don't know canasta 06:01:00 but kanasta means "from a chicken" in finnish 06:05:07 -!- prooftechnique has quit. 06:17:07 Yes, it is somewhat like canasta and other rummy games. 06:17:27 Although there are actually many significant differences. 06:20:44 I made up a new esolang http://esolangs.org/wiki/B-tapemark 06:28:03 -!- Oj742 has quit (Ping timeout: 245 seconds). 06:37:35 -!- ^v has quit (Quit: http://i.imgur.com/MHuW96t.gif). 07:03:17 -!- Ghoul_ has joined. 07:20:45 -!- ^v has joined. 07:24:54 -!- ^v has quit (Client Quit). 07:25:24 -!- ^v has joined. 07:33:23 Bike: so imo the "finite observations" business is a sensible way to understnd continuity 07:35:36 -!- Bike has quit (Ping timeout: 246 seconds). 07:40:33 @ask Bike imo wow rude 07:40:34 Consider it noted. 07:42:29 -!- ^v has quit (Quit: http://i.imgur.com/MHuW96t.gif). 07:54:48 oerjan: in re http://lesswrong.com/lw/qk/ , https://twitter.com/HardSciFiMovies/status/396699827414646784 07:54:58 (though i realise that's kind of missing the point) 07:56:18 that was a plot point in the movie also 07:57:00 lexande: that's based on the Matrix movies though (duh), not yudkowsky 07:57:14 yes. still. 07:57:32 should i read more lesswrong sci fi 07:57:35 it seems p. interesting 07:57:56 the only yudkowsky sci fi i know about is this and the one with the babyeaters and superhappies and hpmor 08:00:12 "If you have a sexual fetish for people who have a fetish for recursion, and they have a fetish for people with a fetish for recursion, the two of you have a fetish for each other via Lob's Theorem." 08:01:13 \rainbow{yudkowsky} 08:01:34 kmc: i haven't seen any other fiction on lesswrong than those yudkowksy things but i haven't looked 08:03:30 :D 08:04:34 oerjan: where should i eat pizza if i visit .no 08:05:25 the latest HardSciFiMovies happens in a world close to you 08:05:53 shachaf: i see you think i have taste 08:06:08 alternative answer: you can't afford norwegian food anyhow. 08:06:53 i hear good norwegian pizza costs $30 or something? 08:07:08 PLAYSIBLE 08:08:40 i can tell you the two biggest pizza chains i know of, but i cannot remember if they're considered _good_: peppe'?s pizza and dolly dimple's 08:09:18 (actually dolly's has a bit unusual cheese mix) 08:09:40 also norwegians have lousy taste in food in general. 08:09:49 and mine is worse. 08:10:30 by which i mean, i'm not very discerning. 08:10:32 lexande: I support research into further applications of modal logic in this domain 08:12:03 oh and i should mention Egon for old times sake, and because i recall at least one person praising their pizza. 08:13:32 oerjan: is one of them on the other side of the street from the royal palace 08:14:03 shachaf: i have no idea what's there, i don't live in Oslo. 08:14:50 i hear everything in scandinavia costs at least $30 08:14:54 i'll have to send lexande on a pizza mission for me 08:16:05 "the other side of the street from the royal palace" doesn't really make sense, the palace is in the middle of a park. 08:17:11 shachaf: yeah i suspect you will just have to go hungry the whole time you are in norway 08:17:23 why 08:17:28 oh, i guess you have a real job, so maybe not 08:17:38 because expensive 08:18:09 I'll probably be in .eu early next year for work. But maybe not .no. 08:21:01 shachaf: took a stroll on streetview down from the castle, hit Egon: https://maps.google.no/maps?q=slottsplassen,+Oslo&hl=no&ll=59.914042,10.738304&spn=0.000003,0.00206&sll=63.409649,10.364351&sspn=0.359599,1.054687&t=h&hq=slottsplassen,&hnear=Oslo&z=19&layer=c&cbll=59.914042,10.737794&panoid=TZqdkmjMXg09K1O52clPeA&cbp=12,26.73,,0,-7.72 08:23:18 oerjan: what about Peppes Pizza - Stortingsgaten 08:26:48 well i looked down Karl Johans gate which is the main street 08:27:03 Pizza in Oslo? Sounds expensive 08:27:18 well there's a peppes in both streets anyhow 08:29:28 well there you go https://maps.google.no/maps?q=Peppes+Pizza+-+Stortingsgaten,+Stortingsgata,+Oslo&hl=no&ll=59.912869,10.738964&spn=0.000086,0.065918&sll=59.912923,10.741856&sspn=0.000792,0.003082&oq=Pepp&t=h&hq=Peppes+Pizza+-+Stortingsgaten,+Stortingsgata,+Oslo&z=14&layer=c&cbll=59.912987,10.738613&panoid=0JExO66m127U5RdZx3MyPA&cbp=12,205.42,,1,17.44 08:31:08 the one in Karl Johans gate is much further down 08:32:29 are there loads of peppes pizza places in oslo? if not I might've eaten at that one 08:32:39 olsner: was it good 08:33:00 olsner: yes 08:33:11 shachaf: not really... I guess it was ok? 08:35:19 anyway just give up all your money and eat at maaemoe hth 08:35:20 -!- MindlessDrone has joined. 08:35:42 wait that was one e too much 08:35:49 *maaemo 08:35:58 (i doubt they have pizza) 08:37:51 (do i need to mention i've never eaten there?) 08:47:51 shachaf: you know how JavaScript supports bitwise "32-bit integer operations" on its sole numeric type of 64-bit floats? 08:48:05 well I learned today that this is actually essential to Emscripten performance 08:48:23 it outputs code like «var x = f()|0; var y = g()|0; return (x+y)|0;» 08:48:35 That's the asm.js thing too, right? 08:48:36 which acts as a hint to the JIT that it should compile this as 32-bit integer code 08:48:48 right, the big win of asm.js is that you can do this interprocedurally too 09:12:51 -!- FreeFull has quit. 09:17:41 -!- Bike has joined. 09:24:11 -!- Bike has quit (Ping timeout: 272 seconds). 09:25:35 -!- aloril_ has quit (Ping timeout: 260 seconds). 09:38:49 -!- aloril_ has joined. 09:57:33 -!- upgrayeddd has quit (Quit: Connection closed for inactivity). 10:10:26 -!- Bike has joined. 10:22:11 -!- Bike has quit (Ping timeout: 272 seconds). 10:56:47 -!- Taneb has joined. 10:57:06 In two years this channel has turned me from loving python to hating it 10:57:34 And now I am forced to use it 10:59:32 aww 11:00:18 Was it two years? Or was it three? Or even more? 11:00:35 Anyway, I'm wondering how my younger self tolerated it 11:01:04 and you hate it because...? 11:01:12 mroman_: it's scary and aaaah 11:01:29 It's got numbers, classes and stuff 11:01:33 what you want more? 11:01:41 I want less! 11:01:43 "a type system" 11:01:44 except static type checking 11:01:55 Oh yeah, and static type checking 11:01:57 I fucking started to hate every language with no perfect type checking 11:01:58 this car has everything except seatbelts or airbags, what's the problem 11:02:00 like C 11:02:06 especially gtk callback 11:02:12 I spent 3 hours debugging memory corruption bug 11:02:25 until I noticed I passed something else to a gtk callback as userdata as I thought 11:02:29 python is way too boring for me to have love or hate emotions about it 11:02:33 I passed a data struct and not a widget 11:02:41 and gtk kept corrupting my structs :) 11:02:49 mroman_: you can do that bug in haskell too 11:02:54 elliott: Really? 11:03:00 Then I guess I fucking hate haskell too 11:03:11 Maybe you just hate GTK 11:03:17 elliott: Shouln't there be type safe callbacks? 11:03:25 I actually quite like C 11:03:30 kmc: i ride in cars without seatbelts and airbags, don't you? 11:03:50 not very often 11:03:56 i don't ride in cars very often at all 11:03:59 but this week yes 11:04:09 i think most of the cars i ride in probably lack seatbelts and airbags 11:04:14 being third world taxis 11:04:23 > fromDyn (toDyn (123 :: Int)) :: Double 11:04:31 Couldn't match expected type `GHC.Types.Double' 11:04:31 with actual ty... 11:04:36 Just keep in mind that every airbag has an electric-fuse 11:04:40 > fromDyn (toDyn (123 :: Int)) :: Maybe Double 11:04:42 Couldn't match expected type `Data.Maybe.Maybe GHC.Types.Double' 11:04:42 ... 11:04:45 i guess most of the cars i hitchhiked in had seatbelts and airbags, which probably shifted the ratio back that way 11:04:47 and you don't know if it still works until you try it out . 11:04:54 toyota recalled 870,000 cars because of spiders living in the airbags 11:05:16 i have been riding in taxis this week because a 4km taxi ride in korea is like $5 11:05:17 whether hitchhiking is safer than a third world taxi seems unclear 11:05:30 but the seoul metro is so shiny 11:05:36 yeah but we're not in seoul 11:05:39 we're out in suwon 11:06:00 I've been getting buses mainly recently 11:06:05 Occasionally trains 11:06:16 :t toDyn 11:06:17 Typeable a => a -> Dynamic 11:06:19 :t fromDyn 11:06:20 Typeable a => Dynamic -> a -> a 11:06:26 :t fromDynamic 11:06:26 > fromDynamic (toDyn (123 :: Int)) :: Maybe Double 11:06:27 Typeable a => Dynamic -> Maybe a 11:06:28 Nothing 11:06:29 i'll go to seoul on friday afternoon and also saturday afternoon through monday sometime 11:06:39 Buses are really scary when you think about it 11:07:23 yes but how so 11:07:37 Because there are loads of people and no seatbelts 11:07:48 And busy roads and you're an easy target 11:08:00 i think the theory is that seatbelts become less important the further you are from the front 11:08:07 cause you won't go through the windshield 11:08:46 i spent a lot of time on school buses and thought about this a lot and they basically told me it's fine cause you'll just hit the back of the seat in front of you 11:09:03 fsvo fine 11:09:25 Also often you have to stand 11:09:46 And if the bus stops suddenly you fall over 11:10:38 afaiu they've made seat belts mandatory in school buses in norway now. 11:11:06 of course, the cool kids don't use them 11:11:34 no the cool kids are too cool for school 11:11:57 i vaguely think the driver may be legally mandated to check that they do. 11:12:13 driver carries less than $20 11:12:17 (that's certainly the case for children in private cars) 11:14:29 hm it says on this page that it's still legal to stand 11:16:34 If it were illegal to stand in busses 11:16:46 then they have to use much more busses :) 11:16:49 at least around here 11:17:03 the probably need double the busses they have now at rush hours 11:17:04 well this doesn't apply to adults anyway. 11:17:05 *they 11:17:13 Oh. 11:17:14 Ok 11:17:23 And only for school buses? 11:17:26 not generally? 11:17:31 yes. 11:17:32 well. ok 11:17:42 -!- yorick has joined. 11:17:56 the problem is, that the driver can't really ensure that everyone uses the seatbelt 11:18:00 for adult buses 11:18:18 "I'm not driving until everyone uses his seatbelt!" 11:18:39 sounds like a way to become popular 11:18:48 the drivers get assaulted by passengers often enough as it is 11:19:01 in both NYC and SF there are signs on every bus/train reminding you that it's illegal to beat up the driver 11:19:11 ... 11:19:37 there was this bus mini-massacre in norway recently 11:20:34 mini because there were only about 3 people in the bus, but they were all killed 11:20:54 :O 11:21:30 Sounds like it's not a dream job to be busdriver in the US 11:21:42 i don't think so, no 11:21:50 probably not anywhere, really 11:21:50 how poor 11:22:13 except that these days "dream job" means like "a job, where you get health care" 11:22:25 and bus drivers are often unionized and make decent money and benefits and get a pension etc 11:22:26 Yeah 11:22:32 Your country is messed up ;) 11:22:32 so that puts them ahead of most employed people even 11:22:34 yep 11:23:15 the latest on that is, the website they set up for the new healthcare law is buggy and this proves that universal health care is a bad idea 11:23:16 I got annoyed at a bus driver recently because he insisted that the bus didn't go anywhere near Heslington East when it terminated at the Heslington East Interchange (which is at Heslington East) 11:23:32 kmc: How is that a prove? 11:23:36 *proof 11:23:49 (Heslington East is where my uni's CS department is) 11:23:56 (and WHERE I AM RIGHT NOW) 11:24:23 heh 11:25:44 -!- Taneb has quit (Quit: I'm going now). 11:25:46 mroman_: it isn't, clearly, but the people fighting reform don't really care about facts or logic 11:26:09 the sad fact is, there's a small number of very rich americans who honestly would rather let thousands of people die every year than pay slightly higher taxes 11:26:16 and they have enough money to fool enough people to get their way 11:27:08 Maybe you should think about establishing a real democracy ;) 11:27:19 but this website thing... wow the government spent a bunch of money on something that doesn't work well? STOP THE FUCKING PRESSES 11:27:29 happens every day but it's usually something republicans like, such as military spending 11:27:45 Are republicans anti-military? 11:27:48 Or pro-military? 11:27:55 pro 11:27:57 Ok 11:28:01 i mean both parties are very much pro-military 11:28:10 republicans tend to be slightly more in favor of actually fighting wars 11:28:16 they both love spending money on jet planes and whatever 11:28:25 And the republicans are the ones with more money? 11:28:34 -!- oerjan has quit (Quit: Later). 11:29:00 yes they're the party of rich people who don't want to pay taxes 11:29:03 Ironic 11:29:09 they were founded to stop slavery 11:29:29 rich people who don't want to pay taxes, who convince a lot of ignorant poor people to go along by leveraging various forms of bigotry 11:33:51 Yeah 11:34:45 * kmc -> afk 11:34:47 I don't really know anything about the US tax system 11:34:55 other than it's apparentely really messy and complicated 11:35:04 -!- Koen_ has joined. 11:35:32 -!- Koen_ has quit (Read error: Connection reset by peer). 11:35:41 -!- Koen_ has joined. 11:38:48 "For adult buses" sounds a bit dirty. 11:40:17 Also I just built a thing with ICC instead of GCC (also with Intel's BLAS instead of generic ATLAS, which is probably more relevant), and its runtime (for a test case) dropped from three and a half minutes to one minute, which was quite the speedup. 11:44:05 fizzie: They usually are a bit dirty. 11:45:15 It could even be a serial bus! 11:48:32 adult serial buses 11:58:12 -!- carado has joined. 12:08:40 -!- Koen_ has quit (Quit: Koen_). 12:20:21 -!- carado has quit (Ping timeout: 252 seconds). 12:24:12 fizzie: nice 12:25:13 -!- carado has joined. 12:26:25 -!- Taneb has joined. 12:33:42 -!- Sgeo has quit (Read error: Connection reset by peer). 12:50:50 kmc: the metro totally goes to suwon but i guess there are only a couple stations there 12:52:38 one note about the safety of city busses with lots of people standing is that such busses tend to be slow as balls 12:53:17 -!- Taneb has quit (Ping timeout: 250 seconds). 12:53:33 people may fall over in a sudden stop but nothing too traumatic 12:55:43 lexande: yeah i think we will take the metro to seoul and back 12:55:54 though we took a cab here from ICN 12:55:56 there are exceptions; riding the M60 across the triboro bridge is a little disconcerting in this respect. but generally in the developed world busses that spend a significant amount of time at high speeds (primarily commuter express and intercity coaches) aren't allowed standees. 12:55:57 but i wasn't paying 12:56:47 a cab from ICN to anywhere sounds cringeworthy; i guess it's the land of cheap cabs but does that really mean they refrain from milking airport passengers? 12:57:52 also what, i tried to do google maps directions in korea and transit is the only option 12:58:18 it was about $80 12:58:26 yeesh 13:00:48 -!- FreeFull has joined. 13:02:02 lexande: yeah what's with that? re gmaps 13:03:27 i don't know. it took them a long time to get road data in south korea at all. i think they may have actually had it in north korea first (because mapmaker was allowed in north korea) 13:03:33 haha 13:03:37 $80 doesn't seem so bad to go 60km 13:04:36 actually more than 60km because I'm pretty sure we took the north bridge 13:04:39 we went past GMP on the way 13:06:18 i've had a 50km taxi ride for like $18 in china, and an 80km ride for like $3 in Botswana (though i may have actually been hitchhiking then, what is a taxi really) 13:06:29 haha 13:06:40 albania: where every car is a taxi and also a 90s mercedes 13:06:58 i took a cab from JFK to Exchange Place once, by myself 13:07:04 THAT was a ridiculous thing to do 13:07:36 but again, not my money, plus I had very little idea how to get around the area at the time 13:07:41 that was like $120 13:07:56 oh yeah we paid €26 or whatever for that 50km taxi ride from Shkoder to Bar 13:08:18 in a mixture of EUR and ALL yes 13:12:55 i think we paid like $150 for a 250km taxi ride from El Calafate to Rio Turbio 13:17:49 i paid something under $35 for a 450km taxi ride from Nuweiba to Cairo 13:23:13 though he dropped me out in Heliopolis or some shit and i had to pay almost $10 more for a taxi into the city centre 13:23:56 #esoteric-taxis 13:25:35 is there a rush-hour based esolang, I wonder ... 13:27:49 also https://twitter.com/kevinmarks/status/390188941749395456 13:35:51 I think we once took a taxi from Mikkeli to Helsinki back when I was a small child, and the family car broke down, and it was late, and there was some reason or another that we absolutely had to get back the same day. 13:36:14 (That's about 230 km.) 13:37:41 today's finding: most programs do not work well if you set all of the registers to 0 after every instruction 13:37:46 but i have one that does! 13:40:11 * kmc writes sizeof(uint64_t) and feels silly 13:40:39 7.1111! 13:46:41 you should 13:50:44 -!- nooodl has joined. 14:03:49 -!- Bike has joined. 14:22:58 -!- boily has joined. 14:23:05 -!- metasepia has joined. 14:32:55 -!- mrhmouse has joined. 14:37:39 -!- conehead has quit (Quit: Computer has gone to sleep.). 15:08:29 i wonder if x86 is turing complete with only instructions «mov dword [dest], imm» and «jmp [src]» but allowing self-modifying of those operands 15:08:55 Can you flush icaches with those 15:09:15 you don't need to flush the icache to do self-modifying code on x86 15:09:27 iianm, that would mean some form of memory mapping, no? 15:09:56 i dunno why people complain so much about x86, the assembly language is so nice and high level 15:09:59 * kmc only mostly trolling 15:10:11 boily: what do you mean 15:10:14 I wonder how much x86 legacy involves local self-modifying code 15:10:18 Probably a lot 15:11:02 kmc: now that I think about what I thought, I don't think I was thinking what I meant to. 15:12:29 Can you think something other than the thing you thought to think? 15:13:37 you guys, it is way too early here for this 15:13:48 kmc: oh there's a bit of self-modifying code here and there; e.g. the first bresenham implementation I encountered had a point where an inc was patched to a dec if the lines sloped upwards, things like that. 15:13:58 rock on 15:16:11 `run ls bin | paste 15:16:20 http://codu.org/projects/hackbot/fshg/index.cgi/raw-file/tip/paste/paste.6704 15:16:25 Well, x86 is the (?) architecture that decodes every single byte offset in parallel because it can't know in advance where instructions start 15:17:13 that would be an implementation detail 15:17:39 but also, I haven't heard about that 15:17:49 and would like to know more 15:18:08 `paste bin/welcome 15:18:10 http://codu.org/projects/hackbot/fshg/index.cgi/raw-file/tip/bin/welcome 15:18:16 @localtime mrhmouse 15:18:34 `paste wisdom/welcome 15:18:36 http://codu.org/projects/hackbot/fshg/index.cgi/raw-file/tip/wisdom/welcome 15:18:40 `run ls wisdom | paste 15:18:45 http://codu.org/projects/hackbot/fshg/index.cgi/raw-file/tip/paste/paste.22595 15:19:11 `run echo wisdom/* | paste 15:19:16 http://codu.org/projects/hackbot/fshg/index.cgi/raw-file/tip/paste/paste.13718 15:19:33 int-e: what have you done to that poor lambdabot? 15:19:43 `? wercome 15:19:45 ​エソテリックプログラミング言語のディザインとデプロイメントの国際な場所へようこそ!詳しく、ウィキを見て: http://esolangs.org/wiki/Main_Page。(他のエソテリック、irc.dal.netの#esotericへ) 15:19:50 c.c 15:21:04 boily: not lambdabot's fault that mrhmouse doesn't answer CTCP time requests 15:21:19 I answered, just not in any valid format 15:21:30 bleh. 15:21:31 you know that's what I meant ;) 15:21:53 what format does lambdabot expect? 15:22:20 also, is it okay if I bring my own bot into the channel / is there a rule list I can read someplace? 15:22:41 oh! another bot! ☺ 15:22:56 boily: Don't get excited, it's not an interesting one :) 15:23:27 not a problem. as long as it answers to ping, echo, botsnacks and does something unique, everything's fine. 15:24:02 I only have two: a chatterbot along the lines of fungot and one that does nothing by default but can load functionality from code on the web 15:24:02 mrhmouse: that is the only moving thing was the eye of the black bird. 15:24:06 It seems that I misread; agner fog only suspects that intel chips try decoding in parallel. 15:24:49 boily: I'm assuming ping is an actual ping, but what should it answer when prompted with echo or botsnacks? 15:24:59 ~ping 15:24:59 Pong! 15:25:13 ~echo echo. 15:25:14 echo. 15:25:14 Okay, so some of our bots don't respond to ping already. 15:25:55 so ... CTCP, it expects a NOTICE (not PRIVMSG), starting with \001 (ASCII 1), followed by "TIME ", followed by another \001 15:25:58 and uhm... I... didn't implement the Botsnack Munching Behaviour Module for Bots on Metasepia yet. 15:26:14 maximal munch 15:26:16 I don't think that it really cares about the format of the part. 15:26:21 That's not a ping, is it? That's a privmsg containing the text "ping". 15:26:33 ~botsnacks 15:26:33 --- Possible commands: dice, duck, echo, eval, fortune, metar, ping, yi 15:26:40 Interesting! 15:26:48 botsnack 15:26:54 :( 15:27:02 fungot: botsnack 15:27:02 quintopia: i've seen cases where chatzilla seems to send messages without getting autoreplies. doctors seem to always be of the egyptian god isis or what was it 15:27:12 @botsnack 15:27:12 :) 15:27:18 ^botsnack 15:27:19 I think fungot only answers to its name 15:27:19 mrhmouse: where is a lot of freedom with that big list of them in .bashrc will prevent it from being " a property which a closed topological space exhibits". 15:27:46 mrhmouse: that, and some obscure non-proto-indo-european spells. 15:28:01 `botsnack 15:28:02 ​:-D 15:28:20 I should make my shell rc topologically closed. 15:28:31 i'm not used to having to address botsnacks to a particular bot 15:29:28 `run printf 'Hi! This is a chat about unusual programming tools. For additional info, visit our wiki: . (For unusual things of a contrasting sort, try http://bit.ly/19k9nf8.)' > wisdom/wlcom 15:29:31 No output. 15:31:52 it's either that or set up a CNAME for irc.dal.net 15:32:30 `? welcome 15:32:32 Welcome to the international hub for esoteric programming language design and deployment! For more information, check out our wiki: . (For the other kind of esoterica, try #esoteric on irc.dal.net.) 15:35:54 -!- conehead has joined. 15:36:25 * kmc hugs lexande 15:36:30 -!- conehead has quit (Client Quit). 15:36:48 conehead is lexande? 15:36:55 no... 15:37:15 oh 15:37:18 coincidence then 15:37:18 fungot: got any cool .bashrc tricks? 15:37:18 kmc: btw, i'd like to start with that +2 function you mentioned earlier? think it's worth having, but once i picked up the memory to be turing complete 15:37:29 :O 15:37:46 fungot: are you a self-aware makefile 15:37:46 kmc: they could be scattered throughout the signals, conditions, arithmetic, enums, records, etc. but i can't argue with the library access actually, you end up thinking in c. 15:37:48 -!- conehead has joined. 15:38:07 wow 15:38:07 fungot: that shit rots your brain 15:38:08 kmc: i can't remember the details now, heh. 15:38:15 fungot: i rest my case. 15:38:15 kmc: one would imagine so, yes. but defining a variable ' define' 15:38:44 `welcome conehead 15:38:44 fungot: "I would be surprised if anyone went to all of the effort that this researcher suggests." 15:38:45 int-e: in a way similar to how monads can be done 15:38:47 conehead: Welcome to the international hub for esoteric programming language design and deployment! For more information, check out our wiki: . (For the other kind of esoterica, try #esoteric on irc.dal.net.) 15:39:02 I miss my rainbow mixed-case welcome ): 15:39:13 `run WeLcOme | rainwords 15:39:15 bash: WeLcOme: command not found 15:39:19 `run ? WeLcOme | rainwords 15:39:22 ​Welcome to the international hub for esoteric programming language design and deployment! For more information, check out our wiki: . (For the other kind of esoterica, try #esoteric on irc.dal.net.) 15:39:27 sucks 15:39:41 `run WeLcOmE conehead | rainwords 15:39:44 ​CoNeHeAd: WeLcOmE To tHe iNtErNaTiOnAl hUb fOr eSoTeRiC PrOgRaMmInG LaNgUaGe dEsIgN AnD DePlOyMeNt! FoR MoRe iNfOrMaTiOn, ChEcK OuT OuR WiKi: . (fOr tHe oThEr kInD Of eSoTeRiCa, TrY #eSoTeRiC On iRc.dAl.nEt.) 15:39:48 huh 15:39:50 Thanks <3 15:40:10 `run perl -e "print '~' x 50" | rainbow 15:40:12 ​~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 15:40:18 The Onion? The body of a spy is found in a padlocked sports bag in his apartment. The investigating police: he probably died by accident on his own. http://www.bbc.co.uk/news/uk-24927078 15:40:43 that's some kinky shit 15:41:07 that case is old and sort of famous; the coroner? tried to zip himself up in a bag and decided it couldn't be done. 15:41:28 but indeed it's a clear-cut case of suicide. nobody expected anything else. 15:42:02 kmc: what stops people from sending harmful commands to HackEgo? 15:42:12 mrhmouse: define 'harmful' 15:42:17 uml 15:42:26 box 15:42:39 I just wonder what theory they came up with ... maybe a self-destructing lego mindstorm robot that locked the bag. 15:42:41 mrhmouse: every command runs in a separate User Mode Linux system and the filesystem changes are merged with Mercurial (so can be reverted) 15:42:53 * boily throw a mint-condition, shrink-wrapped UML manual with garish covers and bad business analogies over at quintopia 15:43:16 a business is like a burrito 15:43:31 r[ead]m[ail] -r[eally]f[ast] /[search pattern matching anything] 15:43:31 boily: not that kind of uml :P 15:43:41 is that harmful enough? 15:44:01 `run perl -e "print '~' x 100" | rainbow 15:44:03 ​~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 15:44:04 int-e: Remember --no-preserve-root on GNU systems. 15:44:34 `run python -c "print('eh?')" 15:44:36 eh? 15:44:49 `run python -c "while True: pass" 15:44:56 ion: nice catch. 15:45:18 /. would probably work. 15:45:20 No output. 15:45:22 on any system 15:45:36 hm. it eventually dies... 15:45:38 `run python -c "while True: pass" 15:45:40 `run python -c "while True: pass" 15:45:42 `run python -c "while True: pass" 15:45:44 `run python -c "while True: pass" 15:45:46 `run python -c "while True: pass" 15:46:09 No output. 15:46:11 No output. 15:46:14 No output. 15:46:15 No output. 15:46:18 No output. 15:46:27 I am disappoint. 15:46:27 if False: yield 15:46:38 rm -rf /boot 15:46:50 that's fine 15:47:00 just get a new kernel from wherever 15:47:04 they're all pretty much the same 15:47:07 HackBot doesn't permission to delete that, I assume? 15:47:21 anyway the 'kernel' from UML comes from The Outside 15:47:25 *have permission, my apologies 15:47:34 `run bash -c ': ( ) { : | : ; } ; :' 15:47:49 nice one, int-e 15:48:05 bash: fork: retry: Resource temporarily unavailable \ bash: fork: retry: Resource temporarily unavailable \ bash: fork: retry: Resource temporarily unavailable \ bash: fork: retry: Resource temporarily unavailable \ bash: fork: retry: Resource temporarily unavailable \ bash: fork: retry: Resource temporarily unavailable \ bash: fork: retry: Resourc 15:48:07 but it should still die with the virtual machine :) 15:48:40 Does the VM reboot itself automatically? 15:48:49 `run uname -a 15:48:50 Linux umlbox 3.7.0-umlbox #1 Wed Feb 13 23:30:40 UTC 2013 x86_64 GNU/Linux 15:48:55 mrhmouse: every command runs in a fresh VM instance 15:49:18 `run cat /proc/cpuinfo 15:49:20 processor: 0 \ vendor_id: User Mode Linux \ model name: UML \ mode: skas \ host: Linux codu.org 2.6.32-5-xen-amd64 #1 SMP Tue Mar 8 00:01:30 UTC 2011 x86_64 \ bogomips: 632.01 15:49:20 HackEgo is trapped in an endless cycle of reincarnation 15:49:54 Very nice indeed! I'll have to sandbox up my command bot like that before adding it to any public channel. Right now it just answers to me, anyways. 15:49:55 I want to checkout a past life 15:50:12 `run echo 'const int main[] = { 14776, 3942977280, 247 };' > fb.c && gcc -o fb fb.c && ./fb 15:50:35 mrhmouse: does it check that you're identified with services :3 15:50:47 kmc: Nope! Just the name. 15:50:50 good to know 15:51:06 He's not identified with services 15:51:15 No output. 15:51:17 It's not on freenode, anyways :) Maybe I'll just add my chatterbot for now. 15:53:09 -!- Frooxius has quit (Read error: Connection reset by peer). 15:53:53 -!- Frooxius has joined. 15:53:57 -!- ruddy has joined. 15:54:11 Ah, here's the chatterbot now. 15:55:40 ruddy: what do you do? 15:55:40 I think it goes for most people that they're not inherently 'bad' 15:56:04 ruddy: can you say "fungot"? 15:56:04 boily: oh well, really night now. i run drscheme on my 256mb box, but it 15:56:04 1 gram of TNT equivalent is equal (defined, even, I think) to 1 kcal 15:56:30 ruddy is a bit different from fungot, and there isn't much chance you can get it to invoke fungot 15:56:31 mrhmouse: sponsored by british taxpayers, of course) 15:56:31 SuperTipsyCam approves 15:56:35 -!- oerjan has joined. 15:56:59 ruddy: sing me a song 15:56:59 is it real 15:57:03 ruddy: are you real 15:57:03 You could look for failing video rental places. 15:57:08 I forgot how hard to kill that : | : thing is ... now one reboot later :) 15:57:15 ruddy: Blockbuster shut their last stores just recently 15:57:16 They cater to other tastes. 15:57:24 ruddy: indeed (bankruptcy mostly) 15:57:24 ruddy: row, row, row your boat 15:57:24 iRowBoat 15:57:40 ruddy: a motherfucking boat? 15:57:40 that would be unfortunate to not have the ability to tell a story like I just did :( 15:57:50 ~echo `echo ruddy fungot 15:57:50 boily: how about this? 15:57:50 `echo ruddy fungot 15:57:50 sponsored by british taxpayers, of course) 15:57:50 Speak! 15:57:51 ruddy fungot 15:57:51 how about this? 15:58:10 * kmc claps 15:58:29 the only chance you have is to get fungot to invoke ruddy, really 15:58:29 mrhmouse: yeah, but i figured i can just do this all with a single 15:58:53 Also ruddy doesn't recognize its name when combined with punctuation :P 15:58:53 Hey! 16:01:06 * kmc falls asleep 16:01:10 Even if you get fungot to invoke it, you'll have to get lucky with a response that includes a name. 16:01:10 mrhmouse: but produces a function on-the-fly at startup. sorry, this is tedious. http://62.167.150.30/ acm100.c of 16:01:30 It stores placeholders instead of names when it logs things, and fills them out when responding 16:20:07 ok. brainstorm. 16:20:19 Infinte sized rubik's cube 16:20:32 how many dimensions? 16:20:45 3D 16:20:49 like a regular rubik's cube 16:21:04 but not 3x3 16:21:38 on a regular rubik's cube every side has 9 squares 16:22:01 now there are's an infinite amount of squares on each side 16:23:09 wtf 16:23:11 there are's 16:23:12 :D 16:23:16 there is 16:24:14 mroman_: I don't see where this is going 16:25:33 * boily prods mrhmouse with a calibrated 10' pole mad out of the finest maple and with a tapered end wrapped in a hand-knit woolen dampener 16:26:03 * mrhmouse vomits profusely 16:27:26 sorry. bad autocompletion. 16:27:33 * boily swings the pole over at mroman_ 16:27:45 That's odd. ruddy doesn't seem to log /me commands... 16:27:45 probably just Bucket spouting some nonsense it was taught 16:28:03 No ruddy, you can't blame other bots 16:28:03 ew? 16:30:21 mrhmouse: An esolang based on said rubik cube 16:31:10 mroman_: what operations are there? you can't rotate it -- that's effectively shifting an infinite list to its end 16:31:15 instructions are commands on how to rotate stuff 16:32:33 e.g if you rotate the yellow side 16:32:48 then a row of orange squares are now there, where a row of green squares was 16:33:56 mroman_: So you're just defining transformations, then. Interesting... 16:34:45 and the data would be the squares 16:34:50 I'm assuming each square is then basically a cell (a la Brainfuck, but 2D), and you can now shuffle cells 16:34:59 yes 16:35:08 http://www.kickstarter.com/projects/cartesianco/the-ex1-rapid-3d-printing-of-circuit-boards 16:35:09 So you would have to provide an offset for each rotation, from the center. 16:35:32 I'm thinking of viewing the cube from one side 16:35:39 Yes, that's what I assumed 16:35:47 and then it's just a 2D field 16:35:58 but you can rotate the whole cube itself too 16:36:04 or rotate "the view" 16:36:13 to not confuse it with the "actual rotation" of stuff 16:36:19 So there are six views? 16:36:27 yes 16:36:38 And each view can be modified by rotating at different offsets in one of the four directions. 16:36:46 and you can switch between those 16:36:51 and then you can do stuff like uhm 16:37:08 if (0,0) == RedSquare then RotateLikeThis otherwise RotateLikeThat 16:37:45 where 0,0 is either the center or the upper left corner 16:37:49 -!- ^v has joined. 16:37:54 I'm not sure what be more convenient 16:37:57 You know what would be interesting? 16:38:23 Do tell 16:38:25 If you ran the program and then printed a "window" of one of the views (obviously you can't print the whole view) 16:38:38 where each cell is one pixel 16:38:47 and then you ran that image through Piet 16:39:01 Though you may perhaps need more than six sides, then 16:39:20 No 16:39:21 :( 16:39:35 The whole interesting part would be that the data is represented by squares :) 16:40:14 With only the six values? 16:40:23 a para-meta-multi-dimensional rubikified langton ant on a piet framework of infinite proportions! 16:40:32 mrhmouse: Well 16:40:39 you don't need more than that 16:40:44 you'd only need two anyway 16:41:27 mroman_: I'm assuming you mean you would interpret data across runs of cells, as opposed to just one cell at a time 16:42:06 Hm? 16:42:20 It's a machine with a Rubik Cube as a Storage Device 16:42:24 that's it 16:43:07 and on a regular rubik's cube there are 16:43:08 uhm 16:43:17 That's what I mean. You would be looking at the big picture as opposed to each cell individual. Initially I thought you intended for each cell to store some other value 16:43:29 4.3 * 10^19 possible variations 16:43:33 since I compared them to Brainfuck cells, and you agreed 16:43:57 A "cell" can contain one of 6 values 16:46:07 of course there are restrictions on how you can move data around 16:46:14 since if you move data, other data moves as well 16:46:43 I thought a standard Rubik's Cube would have 6 sides * ( 6 values per cell ^ 9 cells per side ) => 60_466_176 possible states 16:48:02 Wikipedia says there are 32 quintillion possible arrangements 16:48:33 is that including rotations of the entire cube? 16:49:01 mrhmouse: If you wanted to allow all possible "settings", that would be 6^(6*9), not 6 * (6^9). 16:49:11 (Of course not all of those are legal arrangements.) 16:49:23 which is about 65 bits of Storage? 16:49:56 in particular, if you ignore rotations of the entire cube, the middle squares never move. 16:50:21 clearly it's still too early here for me to do any sort of thinking 16:50:25 Quite many of the 6^(6*9) states also don't have equal amounts of all colors. 16:50:49 fizzie: Good point, I didn't account for a limited set of colors 16:52:37 oerjan: Correct 16:53:28 this is an infinite cube. any computation should be possible. remains to be proved, of course. 16:55:40 @tell elliott Darn spammer got past captcha again :( 16:55:40 Consider it noted. 17:01:07 -!- Sprocklem has joined. 17:01:29 -!- Phantom_Hoover has joined. 17:10:02 -!- augur has quit (Remote host closed the connection). 17:10:28 -!- augur has joined. 17:11:16 -!- sebbu has quit (Ping timeout: 264 seconds). 17:14:43 -!- augur has quit (Ping timeout: 245 seconds). 17:16:02 mroman_: Have you thought of syntax for that esolang? 17:19:19 No, not yet. 17:20:07 I can sketch one out 17:28:05 when you have a sketch, could you link me to it? 17:28:42 -!- sebbu has joined. 17:29:16 -!- sebbu has quit (Changing host). 17:29:16 -!- sebbu has joined. 17:32:56 mrhmouse: http://codepad.org/mTwYvVAv 17:32:59 Probably something like that 17:33:06 some Basic like syntax 17:33:18 esentially you have a "cell pointer" with x,y coordinate 17:33:31 which is part of the machine (so not stored on the rubik cube) 17:33:52 you can increment it, decrement it 17:33:58 or set it to a specific value 17:34:05 you can get the value of a square by {x,y} 17:34:11 or {x + 9, y - 8} 17:34:21 and compare them 17:35:58 -!- Slereah has quit (Ping timeout: 245 seconds). 17:46:08 -!- Slereah has joined. 17:48:43 -!- sebbu has quit (Ping timeout: 240 seconds). 17:51:59 -!- augur has joined. 17:56:53 so you're rotating single rows/columns? 17:57:18 or does a vertical rotation at offset 2 imply that all rows >= 2 are also rotated? 18:03:31 -!- Bike has quit (Ping timeout: 272 seconds). 18:04:51 Also, you mention in your sketch that {x, y} is relative to the corners. I'm guessing that's a typo? 18:06:32 ion: Thanks again for that tip about infants. I just fed one to a carnivorous plant to quiet it down. 18:07:00 back from lunch, and no, I didn't eat any infants. 18:07:40 -!- Phantom_Hoover has quit (Ping timeout: 264 seconds). 18:08:41 fizzie: stop making me want this game 18:09:59 -!- Bike has joined. 18:10:44 -!- Sprocklem has quit (Ping timeout: 246 seconds). 18:13:54 mrhmouse: single rows/columns, yes 18:14:10 but if you rotate column 0 upwards 18:14:20 it's the same thing as rotating every other row downwards 18:14:38 (i think) 18:14:45 mrhmouse: Why is that a typo? 18:14:49 mroman_: No it isn't, you would have to also rotate the view for it to be the same 18:15:03 mrhmouse: Yeah 18:15:07 because it's an infinite cube, it doesn't have corners 18:15:44 doesn't that depend on how you view it? 18:15:49 there's an upper left corner 18:15:51 yes, I suppose it does 18:16:01 but it "extends" to infinity from there 18:16:16 so you only have positive offsets 18:16:17 i.e the buttom right corner is at (infinity,infinity) 18:17:19 -!- sebbu has joined. 18:17:47 which means there's no "center square" 18:17:51 or at least 18:17:53 -!- sebbu has quit (Changing host). 18:17:53 -!- sebbu has joined. 18:17:56 you don't know it's position :) 18:19:02 but 18:19:26 you have actually an unbounded tape 18:19:34 i.e if you face the white side 18:19:48 you rotate the first row right it turns red 18:19:50 white = 0 18:19:51 red = 1 18:20:05 it boils down to brainfuck with 1 bit cells 18:21:05 so actually pretty boring :( 18:21:19 I hate how everything is just syntactic sugar for brainfuck 18:21:28 or syntactic desugar 18:21:36 is brainfuck with 1 bit cells AND limited amount of cells still turing complete? 18:21:54 no 18:21:57 i hate how everything is just syntactic sugar for assembly 18:22:13 because limited amount of cells implies that it has not infinite storage 18:22:43 but an infinite sized rubik's cube has infinite storage 18:23:19 brainfuck with one cell with an infinitely large value should be complete 18:23:40 probably 18:26:33 -!- oerjan has quit (Quit: leaving). 18:27:56 it should? 18:28:25 finite state machine + single counter 18:29:52 -!- ais523 has joined. 18:36:33 -!- carado has quit (Ping timeout: 252 seconds). 18:36:42 however, presumably two unlimited cells are turing complete 18:37:20 well, you need operations that make use of those cells 18:37:56 yeah but brainfuck with two cells 18:39:27 -!- Taneb has joined. 18:39:50 -!- Sprocklem has joined. 18:45:37 -!- carado has joined. 18:47:32 fizzie: :-) They also work for a number of other things than food, for instance projectiles. 18:47:52 I saw Thor 2 today 18:48:54 ion: can you use them as building material? 18:49:08 I enjoyed it 18:49:17 mrhmouse: I don’t remember if anyone has asked for building materials in the game. 18:50:11 -!- prooftechnique has joined. 18:50:35 Taneb: a friend of mine had a tongue ring put in without anesthetics. now she's thor 2 18:50:48 :O 18:51:06 that was a terrible lie 18:51:14 I told a terrible lie for the sake of a terrible pun 18:51:31 It was okay 18:51:37 It was the best kind of terrible pun 18:51:44 ion: There was one "help these guys fix this treehouse" kind of thing, for which a "plank" worked. 18:51:52 ion: I have a feeling an infant would not have. 18:52:01 Yeah, it probably wouldn’t. 18:52:17 http://www.penny-arcade.com/comic/2009/09/23 related 18:52:44 (You *can* create one, but it doesn't do anything.) 18:52:50 heh 18:54:38 I don't understand the pun :( 18:54:48 boily: Sore. 18:55:08 boily: The word "sore", when pronounced with a sore tongue or lisp, sounds like "Thor" 18:56:10 ruddy appreciates a good pun 18:56:10 Also, this is spinal tap 18:56:55 ... 18:57:11 * boily applies the aforementioned egregious mapole on mrhmouse 18:59:35 is mapole an amalgam of maple and pole? 19:00:13 yup :D 19:01:13 ~eval 10 * 12 * 25.4 / 1000 19:01:14 3.048 19:01:52 what was that? 19:02:30 I could've frinked it, but it was a conversion from 10 foot → 3.048 metres. 19:02:44 `frink 10 ft to m 19:02:52 ​[] 19:03:03 welp. 19:03:50 More Scribblenauts: I just fixed global warming. 19:04:04 fizzie: did it involve infants? 19:04:09 MORE Scribblenauts? 19:04:15 So there's more than just Maxwell!? 19:04:16 No. Though in retrospect, I should've tried to make it so. 19:04:34 fizzie: please tell me you at least fixed global hunger with infants 19:04:40 Taneb: He's got all those brothers, and that evil twin. 19:04:47 Oh yeah 19:04:49 mrhmouse: Nobody's asked me to fix global hunger yet. 19:05:01 well when they do, at least you now have a plan 19:05:06 -!- Bike has quit (Ping timeout: 246 seconds). 19:05:07 `frink poulet 19:05:15 poulet (undefined symbol) 19:05:23 `frink ft m 19:05:30 381/1250 (exactly 0.3048) m^2 (area) 19:05:31 Global hunger seems a problem that a scribblenaut could solve pretty well 19:05:48 `frink --help 19:05:56 Syntax error: , line 1, near column 1 \ --help \ ^ \ 1 error(s) occurred during parsing. 19:06:13 What's frink? 19:06:42 Taneb: HUGE FLYING BURGER WITH PICKLES 19:09:07 `file mind 19:09:09 mind: empty 19:09:21 I used to move around by adding wings to Maxwell, but now I just apply "flying fast" as adjectives. 19:10:04 -!- Sprocklem has quit (Ping timeout: 264 seconds). 19:15:29 -!- Bike has joined. 19:16:31 fizzie: how does Scribblenauts handle unknown words? 19:17:02 mrhmouse: "What do you mean, unknown words?" 19:17:33 for example, if you use the nonsense word "foobarbaz" 19:17:54 It pops up a dictionary list if you give it a word it doesn't recognize. 19:18:17 ah, cool :) 19:18:28 For "foobarbaz", it suggests footbag, ferbam, fleabag, flower box, flowerbed, foie gras, and four more pages of stuff. 19:18:38 awesome. 19:19:02 @tell shachaf no it's true you burnedm e good 19:19:02 Consider it noted. 19:19:06 (I just told it to create "nothing", and it made a black hole instead. Hm.) 19:19:16 very Lem 19:19:55 A black hole is kind of like contagious nothingness, except for the fact that it really isn't 19:20:35 Bike: Lem, as in the Stanislav of the same name? 19:20:53 ye 19:21:05 fizzie: can you gorge an infant like a goose, and then make foie gras out of it? 19:21:26 What's a footbag? 19:21:44 prooftechnique: a hacky sack. 19:21:50 Ah 19:22:14 http://i.imgur.com/pfhkQsa.gif 19:22:19 Curious what sort of object fleabag is in the game, too 19:22:26 arguably, a black hole is more like a contagious everything.. 19:23:17 boily: Probably not quite. 19:23:25 -!- Sprocklem has joined. 19:24:07 A mermaid asked for some "gizmo" from above the surface, and I made a television, which promptly electrocuted us both. 19:24:27 Er. A "fleabag" is some kind of a building. 19:24:45 well, did you win before you died 19:24:57 "A seedy, rundown hotel or other lodging place" -- I guess it's from that. 19:25:13 Now there's a seedy hotel at the bottom of the sea. 19:25:22 fizzie: please give her a black hole at the bottom of the sea 19:25:29 or try "drain" 19:25:53 fizzie: Try a fork. 19:27:00 -!- prooftechnique has quit. 19:27:18 I miss the good old days of CRTs. those were the last electrified appliances that I could apply righteous and cathartic percussive maintenance onto. 19:27:21 Oh, I seem to in fact have won before I died. 19:27:29 yesssss 19:29:40 I wrote a program to convert binary decision trees to Internet Quiz Engine. 19:30:10 oh, new quizzes for the zzopher site! 19:31:22 I didn't add any new quizzes yet; just a program to convert binary decision trees. 19:38:22 !bfjoust preparation http://nethack4.org/esolangs/preparation.bj 19:38:33 ​Score for ais523_preparation: 51.3 19:38:53 oh come on :) 19:38:57 it beats every program 19:39:03 and /still/ isn't #1 on the leaderboard 19:41:19 it's only 0.7 points off #1, admittedly 19:41:22 which is hardly anything 19:41:28 perhaps I just need a program that beats space_hotel 19:41:42 or, because this pushed space_hotel up to #1, I can rely on people targeting it now 19:42:13 !bfjoust flangoustine >>>>>>>>[[-.]>] 19:42:16 ​Score for boily_flangoustine: 6.4 19:43:21 -!- conehead has quit (Quit: Computer has gone to sleep.). 19:44:48 does that beat space hotel? 19:45:03 I doubt it beats anything very much, given that it tends to run off the end of the program 19:45:17 do you mean a ()*21 around the outer []? 19:45:44 boily: flangoustine? 19:45:50 an even so, isn't it likely to just terminate after 9 steps? 19:46:49 !bfjoust stupidity >>>>>>>>>([-.]>)*21 19:46:52 ​Score for int-e_stupidity: 15.8 19:48:30 nooodl: it's kinda hard to explain. it implies one of my friends, wildly gesticulating around in a much uncoördinated manner, and lazily not doing something while doing it. 19:48:55 http://sprunge.us/jPId This is the program to do so. 19:49:36 man this is like an eight hundred line brainfuck program... 19:49:52 -!- Ghoul_ has quit (Quit: Connection closed for inactivity). 19:51:08 !bfjoust stupidity . 19:51:10 ​Score for int-e_stupidity: 6.4 19:51:17 Bike: I want to get it to #1 so I can write about it 19:51:24 int-e: you use < to delete a program, normally 19:51:30 that guarantees a score of 0 19:51:36 !bfjoust stupidity < 19:51:39 ​Score for int-e_stupidity: 0.0 19:51:39 !bfjoust flangoustine < 19:51:41 ah so that's what this does :) 19:51:42 ​Score for boily_flangoustine: 0.0 19:52:24 that's by far the most common reason for the "off own end" loss 19:52:52 which is in the rules mostly because there's no other sensible way to handle that situation, not because it's at all possible to generally trick opponents into doing it 19:53:16 Bike: help what 19:53:30 i don't have anything to help. 19:56:17 I wonder if this is an intended consequence of the scoring system or not 19:56:39 !bfjoust wiggle ([]++[]--)*100000 19:56:42 ​Score for int-e_wiggle: 6.4 19:57:40 the [] is purely harming that program 19:57:56 never zerotest your own flag unless you think the opponent is offset or turtle clearing it (and even in those cases, it's really dangerous) 19:58:11 because if you test it and find it's zero, then if the opponent doesn't repair it on the same turn, you've lost 19:58:21 zero-testing the /opponent's/ flag is fine, and commonly done, for the same reasons 19:58:33 !bfjoust apathy (>[-])*100000 19:58:35 ​Score for Bike_apathy: 12.7 19:59:13 !bfjoust pointlesslock >([-])*100000 19:59:16 ​Score for ais523_pointlesslock: 6.4 19:59:23 !bfjoust pointlesslock >(-)*100000 19:59:29 ​Score for ais523_pointlesslock: 7.2 19:59:42 the scoring favours programs that can win, over programs that don't lose 19:59:59 !bfjoust pointlesslock >(+-)*100000 20:00:04 ​Score for ais523_pointlesslock: 7.7 20:00:13 !bfjoust pointlesslock >+(+-)*100000 20:00:19 ​Score for ais523_pointlesslock: 5.6 20:00:23 !bfjoust pointlesslock >(+-)*100000 20:00:27 ​Score for ais523_pointlesslock: 7.7 20:00:44 -!- nisstyre has quit (Quit: Leaving). 20:01:03 haha, that actually beats preparation 20:01:12 !bfjoust pointlesslock 20:01:12 ​Use: !bfjoust . Scoreboard, programs, and a description of score calculation are at http://codu.org/eso/bfjoust/ 20:01:13 !bfjoust pointlesslock < 20:01:16 ​Score for ais523_pointlesslock: 0.0 20:01:32 !bfjoust wiggle >>>>>>>>((-)*100[-]>)*21 20:01:36 ​Score for int-e_wiggle: 8.9 20:01:43 better than apathy :) 20:02:19 !bfjoust wiggle >>>>>>>>((-)*100(-.)*50>)*21 20:02:22 ​Score for int-e_wiggle: 1.7 20:02:55 -!- Bike has quit (Ping timeout: 245 seconds). 20:03:24 !bfjoust syntaxerror [ 20:03:27 ​Score for ais523_syntaxerror: 0.0 20:03:36 I guess that's another way to delete a program 20:08:04 !bfjoust stupidity +++>(+)*33>>(-)*29>>>>>>((-)*128.>)*21 20:08:06 ​Score for int-e_stupidity: 10.9 20:09:24 int-e: you might want to offset that turtle slightly 20:09:31 and maybe put a zero test around it 20:10:46 boily: Now there is a new quiz file; "Pokemon in 9 questions" has been converted using the binary decision tree program. 20:11:04 ais523: probably, if I wanted to do something not-so-stupid :) 20:11:26 yeah 20:11:41 I like it when people do stupid things, though, it often gives a challenge to beat them 20:12:13 quintopia_wireless_frownie is basically a normal rush program with a bunch of arbitrary misbehaviour built in 20:12:14 zzo38: it can decide which pokemon it is in just 9 questions? 20:12:32 to make it not get beaten by programs that beat normal rush programs 20:13:01 quintopia: well there are more than 512 Pokémon, so… 20:13:29 zzo38 has an urban dictionary entry??? http://www.urbandictionary.com/define.php?term=zzo38 20:14:15 quintopia: Only first generation. I didn't make up the questions; I only converted them. 20:14:37 (I also got rid of the non-ASCII characters) 20:14:44 generation 1 should be doable in 8 20:14:58 151 is between 128 and 256 20:15:13 actually, even if you include all the glitch mons, including all the formes of Missingno., you could still theoretically do it in 8 20:15:14 Enjoy finding good questions though 20:15:27 ais523: Yes I know that. 20:15:38 "is its national dex number above x?" isn't good enough :P 20:15:55 “Is it Pikachu?” 20:15:59 FireFly: it isn't, the glitch mons don't have sensible dex numbers 20:16:13 Even then, it'd be a boring quiz 20:16:58 Like I said I didn't make up the questions. 20:19:02 -!- ^v has quit (Ping timeout: 240 seconds). 20:19:20 -!- MindlessDrone has quit (Ping timeout: 244 seconds). 20:20:24 ais523: i'm not that into pokemon. 20:20:51 that's why I was answering the question 20:20:58 because I thought there was a reasonable chance you didn't know the answer 20:22:03 ais523: i'm pretty sure gen1 actually did have an 8-bit value to identify pokemon? 20:22:20 lexande: it did, but it wasn't dex number 20:22:29 and doesn't seem to correspond to any particular order, in fact 20:22:36 and it's not user-visible 20:22:53 how many missingnos are there? 20:23:14 lots, like half the glitch mons are missingnos. 20:23:16 -!- ^v has joined. 20:23:18 err, missingno.s 20:23:24 the other half are just random 20:23:35 apart from 'M, which looks like missingno. and has similar but not identical stats 20:23:59 'M is commonly seen because its index number is the string terminator 20:24:53 are glitchmons considered pokemons? 20:25:11 apparently there are 49 missingno formes 20:25:32 and a specific instane of a glitchmon is typically considered to be a Pokémon, but their species is not considered to be a Pokémon species 20:25:45 ah 20:25:56 so the quiz is unlikely to be about them 20:26:18 indeed 20:26:27 this is what i get for being too old for pokemon 20:27:11 (it got popular in america after i was in middle school becuase of the card game, and i never had a game boy) 20:27:29 Ah. Pokémon 20:27:31 that takes me back 20:27:38 hmm, I'm probably not too /old/ for Pokémon 20:27:39 quintopia: In a magazine once some 93 year old people who played Pokemon card wrote a letter to them. So, even old people do. 20:27:41 I was playing it earlier this year 20:27:42 to like... uhm 20:27:44 age 9. 20:27:51 but there's lots I dislike about the latest games, X/Y 20:28:09 zzo38: are they japanese 20:28:10 the competitive battling seems better than Black/White, but I fear I wouldn't enjoy the ingame enough to make it worthwhile 20:28:23 I never had the attention span for Pokemon, but I did have several of the shiny holographic cards 20:28:24 quintopia: The message was in English. 20:28:43 zzo38: i'd like to meet them. 20:28:56 I don't know who they are though, and I have lost the message. 20:29:30 I still like to play Pokemon card too, especially the Pokemon card puzzle game. 20:29:45 zzo38: how old are you? 20:30:11 ais523: anything in particular? I rather like it 20:30:33 FireFly: a huge reliance on online play/trading with strangers is the thing that puts me off most 20:30:35 FireFly: O, have you tried to figure out the puzzle.5 game yet? I think it is past 14:00 UTC+1 20:30:42 ais523: you wouldn't happen to know anything about k-servers would you? 20:30:43 also, the plot is stupid and just doesn't work 20:30:49 and the game is very easy compared to all the previous ones 20:30:52 zzo38: yeah, i spammed you a bit in query, maybe you didn't notice? 20:31:04 FireFly: I was sleeping. 20:31:04 finally, some specific changes are ridiculous 20:31:12 Sorry! 20:31:20 Oh, don't worry 20:31:48 the most absurd one, IIRC, is what they did with Flash 20:32:01 Flash's effect is to light up an area around you 20:32:18 there is an ability, Illuminate, that's flavoured as lighting up an area 20:32:24 Illuminate increases encounter rate 20:32:25 zzo38: http://hastebin.com/raw/voqaxufuna 20:32:34 in generation 6, IIRC Flash /reduces/ encounter rate 20:32:39 although I haven't played the game so don't know for sure 20:32:45 this inconsistency really bothers me 20:33:00 something something flash being sudden and blinding 20:33:06 I dunno 20:33:19 FireFly: well that's what it does in battle 20:33:33 -!- MindlessDrone has joined. 20:33:48 I don't like the new Pokemon card rules; they aren't very good. I also don't like the variant with 4 side-cards, or the ordinary "sudden death" rule. They get rid of a lot of the tactics and strategy, involving defense, sacrifice, and other things. 20:33:48 also generation 6 seems to mostly have locations that are boring in terms of gameplay 20:33:52 although the graphics are neat 20:34:13 And positional play; one of the most important features of Pokemon card. 20:34:37 It's hard to go back to grid-restricted games after playing Y though.. 20:35:36 zzo38: I agree about the new TCG rules 20:35:53 seeing a speedrun of X is quite depressing, it has so many spare resources 20:36:19 the current best known route uses vitamins to increase happiness to get the Lucky Egg earlier 20:36:25 rather than needing them for battle 20:36:26 for instance 20:37:56 the speedruns use Lucario but mega evolve it exactly once, in the mega evolution tutorial 20:38:11 kind-of ridiculous to have that button option right there and not even need it 20:42:13 -!- Sprocklem has quit (Ping timeout: 248 seconds). 20:43:53 I don't have a clue what's going on but I have the sudden desire to take my shoes off and eat canned spaghetti rings 20:45:00 mrhmouse: duly noted. 20:45:21 mrhmouse: which brand? 20:45:59 -!- Bike has joined. 20:55:08 boily: generic 21:00:11 mrhmouse: call me a snob, but when it comes to canned pastas I accept nothing less than chef boyardee. 21:03:33 -!- zzo38 has quit (Remote host closed the connection). 21:04:08 !bfjoust bathos (>-)*100000 21:04:11 ​Score for Bike_bathos: 0.0 21:04:16 right 21:05:35 !bfjoust bathoff_the_end >*10([-..]>)*100000 21:05:37 ​Score for boily_bathoff_the_end: 11.2 21:05:44 -!- MindlessDrone has quit (Quit: MindlessDrone). 21:05:51 bin torieux. that's I think the best score I achieved right there. 21:07:49 four-cycle clear? 21:08:00 it's creative, at least? 21:08:43 I got a score in the double digits! considering my past record, that's quite good! 21:18:33 Now aim for triple-digits. 21:19:37 has anyone ever achieved that? 21:22:09 no 21:22:12 it's impossible 21:22:16 I think 21:22:27 not sure if a perfect score would hit 100 or not 21:22:41 although, one of my aims with omnipotence, and later preparation, was 1000 wins-losses 21:22:49 I achieved that with preparation last night 21:22:53 (in my local testing) 21:23:47 -!- Sprocklem has joined. 21:34:03 -!- AnotherTest has joined. 21:38:43 ruddy: botsnack 21:38:43 :D 21:39:01 is ruddy a bot? 21:39:01 NOT THE HOUSE 21:39:11 he's just special 21:39:35 wee oo wee oo, this is the turing police, present operator credentials or turing test results immediately 21:40:04 fungot: friend of yours? 21:40:05 olsner: but hey, 400 euros ( or more like... unsecured bbs with little ads, but people usually aren't direct implementations of formulas :) 21:40:14 I do believe ruddy would fail the Turing test, with flying colors 21:40:14 Correct 21:40:17 see? 21:40:28 I think a good Turing test would be to get the person you're testing to give a Turing test 21:40:49 as the rate at which CAPTCHAs are broken indicates, computers suck at Turing-testing 21:41:18 have we tried the "pick which image from this set matches X criteria" approach yet? 21:41:32 I think you should be able to get a score of exactly 100, maybe. 21:42:32 fungot: fmap fmap fmap turing turing turing 21:42:32 boily: what paren styles don't work?) 21:42:44 fungot: the ones you won't balance, you shmuck. 21:42:44 boily: and with that good night to y'all! /bin/ sh it doesn't 21:42:55 mrhmouse, I think that's getting easier to be solved by computers 21:43:20 Taneb: I figured as much, since there are fewer possible answers 21:43:52 maybe if we mixed the two approaches (or any number of test types), with a random test each time instead of always a CAPTCHA? 21:44:31 ruddy: could you give me a Turing test? 21:44:32 well, you need operations that make use of those cells 21:44:33 It's also hard to get hold of large tagged image categories that your adversaries won't also get, which would mean you'd have to start again warping and distorting the images. 21:45:12 fizzie: the idea of warped and distorted pictures of kittens pleases me 21:45:20 Microsoft had a cats-vs.-dogs CAPTCHA. 21:45:33 http://research.microsoft.com/en-us/um/redmond/projects/asirra/ 21:45:41 I remember when they introduced that thing. 21:46:27 scrolled to the bottom, saw the developers, immediately thought "these are terrible pictures of cats and/or dogs" 21:47:16 Also there's an "adopt me" link under each photo in ASIRRA, which means you may end up with a cat just because you were trying to log onto some website. 21:47:28 i see no problems with this 21:47:50 "You're a human!" yay 21:48:19 can bots adapt the cats too? 21:48:25 *adopt 21:48:31 ruddy: do you like cats? 21:48:31 1 gram of TNT equivalent is equal (defined, even, I think) to 1 kcal 21:48:40 olsner: I would suppose they can do both. 21:48:44 I don't think he's qualified to own pets. what about fungot? 21:48:44 mrhmouse: you why double you aitch why" is in evolution. he's the channel owner kicked out a lot of 21:48:51 olsner: Though the first one is a disquieting thought. 21:49:08 fungot: I'm not getting you a cat, just so you know. 21:49:08 fizzie: there's enough spam in the channel who has been asked for id...) 21:50:12 selecting all the dogs when asked to select all of the cats determined that I am a bot. 21:50:13 wait, who is ruddy? 21:50:13 clap clap! 21:50:18 a sea lion 21:50:20 longshot, but does anyone have experience in making visuals for control flow 21:50:26 * FireFly eyes ruddy 21:50:39 mrhmouse: I did that too, and was hoping for some sort of a funny message at least. 21:50:53 iirc, one of the puzzles in seventh guest involved ruddy 21:50:54 Speak! 21:50:56 fizzie: clearly they haven't calibrated their tests for sassiness 21:51:08 ruddy ruddy ruddy ♪ 21:51:09 Speak! 21:51:13 no. 21:51:18 ruddy: row, row, row your boat 21:51:18 Row, row, row your butt 21:51:30 who.. who would teach it that 21:51:35 ruddy: very creative 21:51:36 A black hole is kind of like contagious nothingness, except for the fact that it really isn't 21:52:26 ruddy is still very young, and doesn't have a large amount of data to work with 21:52:27 224kb 21:52:32 yes, that's actually about right 21:52:36 I was tasked to give a person something to get the attention of a dinosaur. I gave him/her a vuvuzela, but apparently it was *so* annoying that the person started attacking me. (Then the dinosaur ate him/her. The end.) 21:52:43 so what does ruddy do? 21:52:44 he's sassy now already 21:52:54 well, he's sassy, and he spouts nonsense 21:52:54 looks like a shitty chatterbot 21:53:02 ^pretty much that 21:53:29 ruddy, meat fungot. fungot, this is ruddy. 21:53:29 FireFly: okay...... oh a web page that lame is not to be confused with fnord 21:53:30 sponsored by british taxpayers, of course) 21:53:48 fizzie: vuvuzelas are approx. as loud as MRI machines 21:53:51 meet* even 21:55:29 ruddy isn't as cool, but often gives more appropriate responses 21:55:30 that explains some weird behaviour 21:55:30 olsner: are you saying that when you're undergoing an MRI and/or a CAT scan it feels like a fast-spinning choir of faceless, robotic vuvuzelas? 21:56:06 fungot, don't you ever start tooting the vuvu. I'm already scared enough of you. 21:56:06 boily: what do you mean? like goto statement ( i know jix isn't here but i have only read a foreword 21:56:09 boily: a CAT scan is like silent 21:56:22 olsner: I wouldn't know. I never underwent one. 21:56:55 fungot: I wouldn't goto, I don't want any raptors charging, I shun the vuvuzelas. 21:56:56 boily: " having points" like in between the towers. 21:57:41 boily: neither sounds much at all like a vuvuzela fwiw 21:57:56 oh well. tdsh. 21:58:35 * boily SPINNING MAGNETIC CHICKENS! 21:58:44 -!- boily has quit (Quit: SPINNING MAGNETIC CHICKENS!). 21:58:52 -!- metasepia has quit (Remote host closed the connection). 21:59:12 so that's a no :( 21:59:21 i think MRIs are deeper in pitch than vuvuzelas 21:59:38 @tell boily the cat goes whirr (and tuk-tuk-tuks a bit when it moves you) 21:59:39 Consider it noted. 22:01:08 mris have a surprisingly wide vocal range 22:01:39 -!- AnotherTest has quit (Ping timeout: 272 seconds). 22:09:43 `oohlist (930) 22:09:45 oohlist (930): shachaf oerjan Sgeo FireFly 22:10:24 ooh 22:11:09 shachaf: is that similar to erflist? 22:11:30 No idea. 22:11:55 I don't know what erflist does. 22:12:05 `which erflist 22:12:07 ​/hackenv/bin/erflist 22:12:17 `erflist (123) 22:12:19 erflist (123): 22:12:27 that's a short list 22:12:39 I've seen shorter 22:12:45 that was a lie, no I haven't 22:24:18 -!- Sprocklem has quit (Ping timeout: 245 seconds). 22:30:40 good morning friends 22:30:57 Evenin', kmc 22:31:09 morning? you must be in weird-timezone-land 22:31:14 UTC+9 22:31:26 @time lifthrasiir 22:31:28 Local time for lifthrasiir is Thu Nov 14 07:31:26 2013 22:31:36 +9? isn't that the wrong way? 22:32:02 he's not in south america or alaska 22:32:07 alas 22:32:08 or did you go visit ... samsung? 22:32:11 hi kmc 22:33:03 Thu Nov 14 07:33:00 KST 2013 22:33:09 Good night, kmc 22:33:12 \rainbow{THE FUTURE} 22:33:24 and yes, this week I'm working from Samsung Digital City 22:47:35 -!- augur has quit (Remote host closed the connection). 22:51:20 -!- Taneb has quit (Quit: Leaving). 22:52:26 -!- conehead has joined. 22:57:24 -!- Bike_ has joined. 22:58:41 -!- augur has joined. 22:59:55 -!- Bike has quit (Ping timeout: 272 seconds). 23:01:27 -!- augur has quit (Remote host closed the connection). 23:03:11 -!- Bike_ has changed nick to Bike. 23:07:53 -!- Bike has quit (Ping timeout: 272 seconds). 23:34:06 -!- carado has quit (Ping timeout: 252 seconds). 23:39:40 -!- augur has joined. 23:43:38 -!- mrhmouse has quit (Quit: Leaving.). 23:53:45 -!- nooodl has quit (Ping timeout: 244 seconds). 2013-11-14: 00:04:40 -!- Frooxius has quit (Ping timeout: 264 seconds). 00:09:12 -!- Bike has joined. 00:14:06 -!- prooftechnique has joined. 00:20:45 -!- yorick has quit (Remote host closed the connection). 00:26:35 -!- Phantom_Hoover has joined. 00:27:15 -!- Sprocklem has joined. 01:00:30 -!- ais523 has quit. 01:06:19 -!- Sprocklem has quit (Ping timeout: 272 seconds). 01:06:34 I'm drinking "Lotte DMZ" brand water http://web.tradekorea.com/upload_file2/product/163/P00346163/cbe9caa5_8547efa1_1f04_4180_8529_8e7d0eb186a1.jpg 01:06:38 which is actually bottled from inside the DMZ apparently 01:27:17 <^v> * Disconnected (Invalid argument) 01:27:17 <^v> * Disconnected (Connection reset by peer) 01:27:17 <^v> * Disconnected (Remote host closed socket) 01:27:53 <^v> oh esper 01:28:44 what's an esper 01:28:53 An IRC network 01:29:03 <^v> a network that hit the fan 01:31:45 <^v> ffs 01:31:54 <^v> i think their entire net went down 01:47:31 i'm uh, talking on esper right now. 01:48:14 oh, there was a netsplit 26 minutes ago. 01:48:54 -!- Phantom_Hoover has quit (Quit: Leaving). 02:15:01 -!- Sgeo has joined. 02:16:35 http://www.theonion.com/articles/breaking-intruders-detected-in-zone-17,34541/ 02:16:44 Is this parodying a specific game, or just a genre of games in general? 02:17:10 Area Man Confused By Onion Article 02:17:18 Sgeo: did you see the Onion is ending print publication :( 02:17:27 what will I read if I'm ever at a Quiznos in Boulder, CO again :( 02:18:04 kmc: yeah. I think I linked an Onion article poking fun at it 02:22:36 What is it called when you have code that's working, but as far as you can tell it shouldn't be working, and you're trying to figure out why it's working? 02:23:10 hell 02:31:36 codebugging 02:32:19 rebugging 02:32:21 kmc: SO IT BEGINS 02:32:29 how long until the other papers end print 02:33:00 it's been going on for a while 02:33:09 i know 02:33:14 but i didn't care 02:33:18 and still don't really :P 02:33:19 -!- Bike has quit (Ping timeout: 252 seconds). 02:33:27 Hmm, Google News finds Onion articles, but adds "(satire)". :-( 02:35:17 what do they add for links to the daily mail 02:35:26 (not Poe) 02:39:23 D-: 02:57:00 -!- Bike has joined. 03:07:18 Even the ghosts know http://youtu.be/dXVNvfPetxU?t=2m37s 03:20:24 -!- john_metcalf has quit (Read error: Connection reset by peer). 03:39:14 -!- drlemon has joined. 03:50:07 -!- ^v has quit (Remote host closed the connection). 03:50:54 -!- augur has changed nick to not_ion. 03:53:55 -!- ^v has joined. 03:55:56 -!- not_ion has changed nick to augur. 03:58:35 -!- ^v has quit (Client Quit). 04:11:00 -!- Nisstyre-laptop has joined. 04:12:36 -!- ^v has joined. 04:14:39 -!- conehead has quit (Quit: Computer has gone to sleep.). 04:15:56 -!- prooftechnique has quit. 04:16:15 -!- ^v has quit (Read error: Connection reset by peer). 04:27:53 -!- Sprocklem has joined. 04:40:04 I designed a norn to drop dead instantly if he ever thought about eating elevators. He was stillborn. 04:40:23 i take back everything mean i've ever said or thought about you sgeo, that rules 04:40:53 norn? 04:41:38 http://static2.wikia.nocookie.net/__cb20050101192132/creatures/images/5/59/Chichi.png 04:42:02 that does not answer my question 04:42:16 `addquote I designed a norn to drop dead instantly if he ever thought about eating elevators. He was stillborn. 04:42:20 1132) I designed a norn to drop dead instantly if he ever thought about eating elevators. He was stillborn. 04:42:48 A species, the main one the player is supposed to care for, in the Artificial Life series Creatures 04:43:29 and Sgeo hates those bastards 04:44:58 ah ok 04:47:26 I used to try to make paradises for Norns that arrived in my worlds from other people. Can you believe I actually poured antibacterial agents on incoming norns??? 04:48:08 (There's actually a reason to not do that besides 'not doing that sounds potentially mean' --- travelling to another person's world doesn't transfer bacteria) 05:00:13 did you know that? 05:00:25 Not when I did it, but I learned/realized it later 05:00:56 When I first started playing Creatures, I saw a norn hitting a toy, but I didn't realize it was a toy. I thought it was another creature, so I slapped the norn 05:01:19 and that's when it all started 05:01:40 I've put norn brains in the useless body of the toy 05:01:42 didn't take long till you would hit them even if they didn't hit toys 05:01:58 :D 05:02:22 what happens 05:02:34 They sit there doing nothing and eventually starve to death 05:02:45 also how often do norns think of eating elevators 05:02:52 Surprisingly often 05:03:10 http://creatures.wikia.com/wiki/EE_Syndrome 05:03:37 i can't stop laughing 05:03:43 Hmm... that's.. not what I had in mind 05:03:49 I hadn't actually heard of that before now 05:03:57 Just the same old tired "eat elevator" jokes 05:05:54 "eat elevator" jokes are "old" and "tired"? 05:06:00 i can assure you they are new to me 05:06:55 http://www.creaturesvillage.com/helen/symptoms.php?ID=613 05:10:11 -!- Nisstyre-laptop has changed nick to nisstyre. 05:13:18 `olist 930 no one did this yet? really? 05:13:20 olist 930 no one did this yet? really?: shachaf oerjan Sgeo FireFly 05:13:27 No. Not really. 05:13:52 (In particular I did this yet.) 05:14:04 I don't see that in the logs of 13 or 14 05:14:04 `rm bin/oohlist 05:14:07 No output. 05:15:36 ooh 06:22:17 -!- Sprocklem has quit (Ping timeout: 244 seconds). 06:28:48 -!- FireFly has quit (*.net *.split). 06:28:49 -!- hogeyui has quit (*.net *.split). 06:57:45 Bike: wait which one was your definition of continuity again 06:59:34 the shitty one, or the one i copied from wikipedia? 07:00:15 can't it be both 07:00:27 the wikipedia one wasn't shitty. 07:00:40 the wikipedia one 07:00:45 was it with neighborhoods 07:01:37 "f is continuous at some point x ∈ X if and only if for any neighborhood V of f(x), there is a neighborhood U of x such that f(U) ⊆ V" 07:01:49 where neighborhood isn't required to be open? 07:01:55 why not 07:02:54 preimages of closed sets have to be closed anyway i guess 07:06:53 so i was reading about vaguely-hinting-at-pointless things in a book and now i want to figure out why the idea of a neighborhood even makes sense 07:07:13 when you define a thing with an arbitrary lattice rather than a set of open sets 07:07:42 (well, not arbitrary. a frame.) 07:08:43 anyway now the definition of continuity is obvious, it's just a structure-preserving thing such that knowing f(x) : Y doesn't give you any new information you couldn't get from x : X 07:09:02 and it goes backwards because, like, that's totally sensible and stuff 07:10:15 on the other hand neighborhoods aren't sensible anymore so help 07:29:03 -!- oerjan has joined. 07:32:47 @tell oklopol however, presumably two unlimited cells are turing complete <-- i sincerely doubt it, my construction for three cells is related to two cell minsky but needs the extra cell to get around the limited flow control. 07:32:47 Consider it noted. 07:34:42 yoerjan 07:34:45 -!- Slereahphone has joined. 07:35:14 @tell oklopol and even then i had to discover conway's collatz functions to get relatively satisfactory control flow in _that_. basically problem is (1) whenever you exit a loop one cell _must_ be 0 (2) you cannot enter a loop based on a cell being zero, without extra cells. 07:35:14 Consider it noted. 07:35:53 yachaf 07:36:46 @tell myname no way 1 cell is enough and even 2 seems impossible, see my @tells to oklopol 07:36:46 Consider it noted. 07:37:40 @tell myname also, stop having the same first three letters as myndzi twh 07:37:40 Consider it noted. 07:38:06 so you're an expert in homology too right 07:38:44 someone was talking about something but i can't remember what 07:38:49 i'll just go to sleep 07:38:49 if using it a bit in one published article counts 07:39:02 shachaf: was it me? 07:39:19 * oerjan recalls blathering about algebraic topology the other day 07:39:27 oerjan: please fix infinite redirect in https://en.wikipedia.org/wiki/Homology_theory thx twh 07:40:11 what infinite redirect it works fine here 07:40:22 oh hm 07:41:35 someone merged it out of existence. 07:42:30 -!- Slereah has quit (Ping timeout: 245 seconds). 07:43:50 -!- augur_ has joined. 07:45:23 shachaf: DONE 07:45:34 oerjan: "Using it a bit in one published article" is like the *definition* of "expert". 07:45:45 fizzie: THOUGHT SO 07:45:50 oerjan: i still don't know what a homology theory is :'( 07:46:10 plz fix https://en.wikipedia.org/wiki/Eilenberg%E2%80%93Steenrod_axioms to make sense or something 07:46:18 -!- Slereahphone has quit (Quit: Colloquy for iPhone - http://colloquy.mobi). 07:46:49 -!- augur has quit (Ping timeout: 252 seconds). 07:48:50 shachaf: SORRY, LOOKS COMPLETELY CLEAR TO ME 07:49:38 (read a textbook?) 07:50:39 shachaf: it's a completely general setting, you basically need to learn the concreter versions to know why it's interesting? 07:52:03 https://en.wikipedia.org/wiki/Ham_sandwich_theorem nice article picture there 07:54:07 very relevant 07:59:10 shachaf: i think singular homology is like the basic version. (my published use used Alexander-(Spanier-)Čech homology which works in general compact hausdorff spaces or something) 08:07:54 * kmc wonders if lexande highlights on "ham sandwich" 08:09:53 is there a vegetarian version of the theorem 08:10:01 seitan sandwich 08:11:14 argh carpentry 08:11:35 arp entry 08:15:28 what are you carpentering? 08:16:22 i'm not, the neighbor is 08:17:00 a clear infringement of my human rights to silence 08:19:21 put on some abba 08:19:46 have some loud sex 08:21:10 oerjan: oh cool maybe someone should prove that brainfuck with two cells is not universal 08:21:42 hm 08:23:55 say,for brainfuck with k cells, we say the language of a program is the set of numbers n such that (n,0,0,...,0) (where we have k-1 zeroes) eventually halts 08:24:25 from what k on is there a bf program with re-complete language? 08:24:36 definitely k <= 3 08:24:45 okay, just wanted to check i formalized this sensibly 08:24:58 assuming you can do reencoding of n before starting. 08:25:04 ? 08:25:14 or wait 08:25:17 what does that mean 08:25:28 no, you can do that inside bf with 3 cells too. 08:25:50 re-complete with respect to just general 1-1 reductions by turing machines, say 08:26:11 so okay, k <= 3. 08:26:17 what's it for k = 1? 08:26:31 oklopol: just that since the method depends on converting via fractran, you want an original n encoded as 3*2^n or something equivalently handleable. but you can do that conversion inside bf. 08:26:44 for re-completeness, what does that matter 08:26:58 it doesn't. 08:27:31 i guess it matters if you want some sensible set of (unary) languages i guess 08:27:50 i'm definitely interested in what the exact set is for unary 08:27:53 for k=1 you cannot use >< at all (at best they wrap around to the same cell), so you have a balanced bf program with one cell, which is basically a linear loop at most 08:27:58 (i think) 08:27:59 is it just regular? 08:28:26 hmm 08:28:58 yeah okay err 08:29:09 a loop without inner loops 08:29:14 oh hm well 08:29:19 will either increment of decrement 08:29:28 if you have a loop, then you either never halt it it, or halt with 0. 08:29:31 *-it 08:29:32 if it increments, then we're in trouble 08:29:35 yes 08:29:50 so all depends on the first loop. 08:30:15 yes 08:30:16 before it, you can do some +-constant 08:30:33 or wait 08:30:44 actually i guess all depends on what happens before we first exit a []? 08:31:08 right, i just realized that's not necessarily the same ] in all cases 08:31:13 oh. 08:31:50 [-[-[-]]] e.g. 08:32:08 true 08:32:21 so there are finitely many states which you can enter, depending on the number 08:32:38 (the states after exitting some []) 08:32:47 (state being program counter value) 08:33:08 and at that point your counter is 0 08:33:11 if you have ]+], that loop will never halt. 08:33:16 and similar 08:33:35 well, if it's entered at all 08:33:54 do you all assume that ++[--->+<] never halts? 08:34:13 lifthrasiir: we're dealing with a single cell right now 08:34:19 kmc: i don't, but maybe i should 08:34:21 no <> 08:34:25 we should probably specify whether we can go under 0 08:34:29 oh wait, a single cell? 08:34:30 might matter 08:34:41 lifthrasiir: also, it is unbounded, so no wrapping 08:35:21 lifthrasiir: we were just trying to find out exactly what can be the halting condition of a single cell bf program 08:35:30 so err 08:36:06 we encounter the first ] depending solely on n up to a threshold, right 08:36:19 -!- Tod-Autojoined has joined. 08:36:27 like we might encounter different ] first, depending on which loops are skipped, but if n is big, then we'll necessarily go inside all. 08:36:41 when we meet the first ], i guess we're done? 08:37:01 hm seems so, the rest is just tracing the result from a 0 08:37:06 because you'll be in that loop, and what happens depends only on n (might look at parity if you can go under 0) 08:37:16 yeah 08:37:35 so i think you get finite languages or languages with finite complement if you can't go under 0 08:37:52 um i was assuming unbounded negative too... 08:37:59 then err 08:38:51 maybe you then get something like n = a + bm for some m, modulo getting to choose first k values arbitrarily 08:39:06 well, first assume that (x) translates to x +s when x>0, x -s when x<0, or nothing when x=0. and {X} code {Y} means that if X holds for the initial state then after code runs Y holds for the current state (or may enter an infinite loop). then {cell=x} (n) {cell=x+n}, {cell=x} [(n)] {sign(cell)+sign(n)=0 and (n=0 or cell%n=0)}. 08:39:49 (big enough n will necessarily bump into the first ] in the program, and from that on you either halt or don't, on that it depends whether you get the arithmetic sequence a + bm. finitely many values of n might behave differently.) 08:39:59 and no, we don't just get that. we get modulo conditions, e.g. [---] halts on n == 0 (mod 3) 08:40:10 oerjan, and n >= 0. 08:40:18 so a = 0 and b = 3 in n = a + bm 08:40:23 (sorry if you already said that, i got disconnected for a moment) 08:40:40 i gave a conjecture about the case where you can go negative, with a proof sketch 08:40:57 -!- Bike has quit (Ping timeout: 246 seconds). 08:41:04 i don't know what lifthrasiir is saying 08:41:17 [---] halts on n >= 0 and n == 0 (mod 3). 08:41:24 (since the cell is unbounded) 08:41:48 or, are you asking for the {cell=x} ... things? 08:41:48 so a = 0 and b = 3 in n = a + bm 08:42:13 (m goes over naturals) 08:42:23 lifthrasiir: i don't know what you proved 08:42:39 oklopol, no, I didn't prove anything, I'm just trying to formalize things a bit 08:42:42 okay 08:42:45 and stuck 08:43:34 okay 08:43:45 -!- Bike has joined. 08:44:38 -!- FireFly has joined. 08:44:38 -!- hogeyui has joined. 08:44:41 oerjan: big enough n will necessarily bump into the first ] in the program, and from that on you either halt or don't, depending on whether n is in the arithmetic sequence of things that go to 0. you take that arithmetic sequence in the language if the program halts from that point, with counter value 0. finitely many values of n might behave differently. 08:44:49 -!- Tefaj has joined. 08:45:16 "depending on whether n is in the arithmetic sequence of things that go to 0" which you get from looking at how many times the first innermost loop increments 08:45:49 -!- tromp__ has quit (*.net *.split). 08:45:50 -!- TodPunk has quit (*.net *.split). 08:45:50 -!- Jafet has quit (*.net *.split). 08:45:50 -!- Fiora has quit (*.net *.split). 08:45:52 i don't know what the "modulo finitely many values" means though 08:46:06 but at least this would already prove that the language is trivial anyway, in the sense of formal language theory 08:46:46 -!- tromp__ has joined. 08:46:46 -!- Fiora has joined. 08:48:19 oklopol: hm i suspect you can choose behavior exactly how you want on finitely many values, + your one arithmetic sequence 08:48:55 that is, choose any finite set union an (optional) arithmetic sequence as your halting set 08:49:00 i suspected that as well, until i started thinking about how to do it 08:49:21 -!- Bike has quit (Ping timeout: 246 seconds). 08:49:28 well assume the sequence goes upward 08:49:49 how do you just any finite language? 08:49:53 *just 08:50:00 *do 08:50:01 *argh 08:50:16 how do you implement a finite language 08:50:46 1,3,7,10,20,30,... can be done as: 08:51:04 -[--[----[---[----------]]]] 08:51:22 i think that's pretty generalizable :P 08:51:49 -1,3,7,10,20,30,... : +[----[----[---[----------]]]] 08:51:56 k i feel pretty stupid 08:52:11 but hi5 we solved it 08:52:16 yay! 08:52:20 we have k=1 and k>=3 08:52:24 now just k=2 left 08:52:29 a5gh 08:52:32 :D 08:53:07 at least we can then just identify > and < 08:53:15 by saying the tape wraps 08:53:24 yes 08:53:49 so each sequence either flips tapes or not 08:53:50 but now we can leave a loop with one cell non-zero. 08:53:57 o dear 08:54:29 oklopol: well, it might still vary which cell a particular loop halts on 08:55:05 it's no longer guaranteed balanced, e.g. [-<] could halt anywhere 08:55:38 we should come up with a better symbol for > and < 08:55:45 X 08:55:45 x is dangerous 08:55:50 wat 08:55:55 IT'S A VARIABLE LOL 08:55:59 O KAY 08:56:00 but yeah it's good 08:56:08 it looks like an eXchange of counters too 08:57:25 now we can do the usual multiplication by a constant stuff like [-<+++++>] 08:57:36 yes 08:58:57 hmm 08:59:16 isn't the first ] we hit in any case the same when n is large enough 08:59:41 and in an innermost loop, [--<+++++>] with all parts optional is basically the same. 08:59:51 oklopol: i think that is true independent of number of cells 08:59:56 true 09:00:03 *is basically all we can have 09:00:07 i'm just wondering if we should start there 09:00:20 but err, what do you mean basically the same 09:00:54 um i corrected that 09:01:13 i got confused and pressed enter with an unfinished sentence 09:02:25 [--<+++++>] either fails to halt, or adds 5/2 of the initial cell to the other, clearing the first. 09:02:27 so we have two kinds of non-nested loops: 1) balanced ones: ones that hang up if n is not in a particular arithmetic sequence cm, m in \N, and otherwise zero n and multiply the other counter by dn/c 09:02:35 err 09:02:53 multiplies it by that you mean, or are you thinking of Q with multiplication with additive notation 09:03:13 2) unbalanced ones 09:03:15 what do they do 09:03:20 um it's basically the same as what you said in (1) 09:03:32 yes, just wanted to know why you said add 09:03:33 well i dunno quite 09:03:43 -!- Bike has joined. 09:03:45 however, hm 09:04:10 one interesting fact: all loops after the first to exit will have a cell with a known value. 09:04:38 or hm 09:04:39 ? 09:04:41 Is this two-infinitely-huge-cells brainfuck? 09:04:44 well not inside. 09:04:44 yes 09:04:59 but before you start a later loop, one of the cells is known 09:05:31 or hm 09:05:37 i'm not following you! 09:05:42 if you have something like [..[....]...] 09:05:47 okay 09:05:53 ... never contains [ or ] 09:05:59 after the inner loop ends, a cell is known to be zero. 09:06:18 true. 09:06:21 so that cell has known value from there on to the next ] 09:06:27 oh true 09:06:43 *next ] or [ 09:07:00 so um 09:07:14 i get the feeling that only one of the counters will have a big value after the first ] is met 09:07:28 like ever 09:07:38 yes, that's also true 09:07:54 (trivially, but i mean maybe that's important and we should like call that n and think of which counter it is in as a state, or something) 09:07:55 iirc i thought a big of this stuff back when i was doing the 3-cell thing. 09:08:10 *bit 09:08:24 possibly a big bit 09:08:32 but definitely not all the way through 09:09:11 now that you mention it, the idea of treating the small counter as a state also rings a bell 09:09:25 great minds think alike 09:09:48 when it comes to trivial things 09:09:53 -!- Bike has quit (Ping timeout: 246 seconds). 09:10:10 or well, i don't think it's entirely true. they might still get big in a non-halting way. 09:10:22 sure 09:10:39 but i prefer thinking as such loops as LOOP FOREVER LOL instructions 09:10:44 *of 09:10:45 like, [-->--<] can loop indefinitely even if one cell starts zero 09:10:54 hmm 09:11:20 however, after a ] until the next ]/[ this holds. 09:11:39 -!- Frooxius has joined. 09:11:43 -!- Bike has joined. 09:12:12 hm... 09:13:05 -[+[-->+<]>-] 09:13:37 i think that may be a program that halts for powers of 2. 09:13:37 what does that do 09:13:41 oh dear. 09:14:42 i was thinking if everything was still arithmetic sequences, then this popped up 09:15:01 yeah that seems to work 09:15:16 *-[+[--x-x]x-] :P 09:16:01 perhaps we are in the presence of a legendary beast, thinking it's a koala 09:16:18 OKAY 09:17:32 oh hm 09:18:24 perhaps it's just that you can do trivial checks for factors 09:18:36 and factor exchange 09:18:38 it might be possible to get rid of nonbalanced loops by replacing ]x stuff with ]x[-x+] stuff 09:18:50 erm 09:19:02 er 09:19:05 *with ]x[-x+x]x stuff 09:19:32 because you don't actually care _which_ cell is zero, mostly. 09:20:02 there's no way to detect a stack exchange 09:20:06 erm *counter 09:20:14 oh hm this may have some trouble if you don't know sign. 09:20:25 -!- dessos has joined. 09:20:44 perhaps all things need to know sign anyway 09:20:50 because they hang up for the other sign 09:21:00 alrighty i have to go swimming now 09:21:08 oh. see you. 09:21:26 but i think we're pretty close, tell me if you come up with the last few details :) 09:21:52 ok but now brain needs rest 09:22:47 -!- Alexander_ has joined. 09:23:07 -!- Bike has quit (Ping timeout: 272 seconds). 09:26:26 -!- Bike has joined. 09:34:15 -!- Bike has quit (Ping timeout: 272 seconds). 09:40:03 -!- john_metcalf has joined. 09:58:20 -!- Bike has joined. 10:04:41 -!- Bike has quit (Ping timeout: 252 seconds). 10:26:30 1 gram of TNT equivalent is equal (defined, even, I think) to 1 kcal <-- most interesting, are you sure you're a bot? 10:26:31 can you say "oerjan"? 10:26:40 ruddy: yes, i can. 10:26:41 That's the one with Captain Gandalf? 10:26:56 ruddy: i don't think i've had the honor. 10:26:57 that was a lie, no I haven't 10:27:13 if you say so 10:28:37 mrhmouse: you why double you aitch why" is in evolution. he's the channel owner kicked out a lot of <-- no, i am quite sure that's _not_ how "evolution" is spelled. 10:28:37 oerjan: the eye socket parts are probably paper thin just like real ones 10:28:46 fungot: eww 10:28:46 oerjan: nothing in haskell says you can't just grovel through stack frames manually. take a few decades.) without problems, but when i started working on implementing scheme, by the way 10:28:47 calories have to do with the heating of water, if 1 gram of TNT matches that would be a p. big coincidence I think 10:29:02 olsner: it's an arbitrary definition 10:29:09 but it's a fun fact 10:30:17 -!- john_metcalf has quit (Ping timeout: 244 seconds). 10:30:29 huh, it's actually true 10:31:09 one gram of TNT contains (almost) exactly as much energy as it takes to heat one kg of water one degree 10:33:58 *almost exactly approximately 10:34:04 "A gram of TNT releases 4100–4602 joules upon explosion. To define the tonne of TNT, this was arbitrarily standardized by letting 1 gram TNT = 4184 J (exactly)." 10:51:26 fungot: doesn't sound terribly efficient to me 10:51:26 FireFly: where does uml fit into that number 11:01:45 -!- oerjan has quit (Quit: leaving). 11:12:12 -!- KingOfKarlsruhe has joined. 11:35:59 http://sprunge.us/THif Yes, that looks very optimized. 11:42:24 -!- yorick has joined. 12:33:00 -!- Sgeo has quit (Read error: Connection reset by peer). 13:04:25 -!- john_metcalf has joined. 13:10:49 -!- Bike has joined. 13:15:21 -!- Bike has quit (Ping timeout: 246 seconds). 13:17:24 -!- dessos has quit (Quit: leaving). 13:42:23 -!- Bike has joined. 13:50:07 -!- Bike has quit (Ping timeout: 272 seconds). 13:51:46 -!- boily has joined. 13:53:01 -!- boily has quit (Client Quit). 14:00:02 -!- boily has joined. 14:00:27 good kernel morning! 14:01:02 @messages-loud 14:01:03 olsner said 16h 1m 24s ago: the cat goes whirr (and tuk-tuk-tuks a bit when it moves you) 14:01:43 olsner: ..................? 14:02:04 (cat goes whirr, dog goes screeeeech... ♪) 14:05:54 -!- metasepia has joined. 14:33:23 -!- KingOfKarlsruhe has quit (Quit: ChatZilla 0.9.90.1 [Firefox 25.0/20131025151332]). 14:44:24 -!- mrhmouse has joined. 14:47:38 boily: what the fox say? 14:52:23 john_metcalf: hush! I'm trying to unearwom myself! 14:52:34 s/wom/worm/ 14:56:44 What does the earworm say? 14:58:00 [16:44:10] ducks say quack 14:58:00 [16:44:17] and fish go blub 14:58:06 [16:47:31] boily: what the fox say? 14:58:19 what is all this synchronicity between #esoteric and #japanese 14:58:28 there is little intersection 14:58:59 everything intersects in one way or another. 14:59:06 mmm synchronicity 14:59:08 i mean it's not like the fox thing is _everywhere_ on the internet RITE 14:59:16 (that reminds me I haven't perturbed elliott with ##crawl-talk for a long time...) 14:59:51 oklopol: The fox thing was #1 on Spotify's list of most listened songs for the geographical region "Finland". 15:00:04 (Last I looked, a week or two ago.) 15:00:04 and trying to join #japanese ends me up into ##namespace. 15:00:50 boily: ohhh maybe i'm imagining the whole channel 15:00:53 that would explain a lot! 15:01:19 -!- Bike has joined. 15:01:38 it's ##japanese 15:01:45 apparently 15:04:50 -!- carado has joined. 15:08:01 not endoresd by the japan 15:08:17 -!- Bike has quit (Ping timeout: 272 seconds). 15:08:49 -!- nooodl has joined. 15:17:15 If there WERE an official channel for Japanese, it would be #japanese. 15:17:25 /msg lambdabot @stfu 15:21:23 wouldn't it be #nihongo or #nippon or something? unless IRC supports Unicode channel names 15:21:51 utf-7 is the way to go 15:22:56 -!- MindlessDrone has joined. 15:23:23 freenode - :: #日本語 :Illegal channel name 15:24:15 thanks boily 15:24:36 I was busy looking up whether freenode supported non-ASCII :P 15:27:00 どういたしまして。 15:27:53 -!- Lymia has quit (Ping timeout: 244 seconds). 15:28:43 I just see a past-tense verb. I haven't read Japanese in years :I 15:29:27 * boily frappe kmc avec une po+AOo-le en acier galavanis+AOk- 15:29:51 どういたしまして 《どう致しまして(P); 如何致しまして》 (int) (uk) you are welcome; don't mention it; not at all; my pleasure; (P) 15:35:24 mrhmouse: did you have classes? if so, how many years? what are your approximate coördinates and body weigh? 15:41:42 are you trying to set up a catapult, and if so, what's the destination? 15:44:37 no, I'm trying to find this channel's centroïd, and see if it falls on Hexham. 15:44:57 boily: I didn't take classes. I studied independently in highschool with resources I found online. 15:45:35 I've got a spiral notebook of the 300 or so kana that I once knew. But that's been since sophomore year of highschool, and without anybody to converse with, I've lost it all 15:49:15 -!- conehead has joined. 15:50:11 mrhmouse: can you translate “sophomore year of highschool” into Canadianese? 15:51:38 -!- Phantom_Hoover has joined. 15:55:37 boily: the schoolyear when you're 15-16 years old 15:57:11 -!- Lymia has joined. 16:00:07 oh. «Secondaire 4». 16:01:03 incidentally, I tried beginning thinking about starting to maybe try to learn basic Japanese around that time. 16:03:56 me too!! well, that's when i got even kinda serious about it. i'd learnt hiragana at age 12 but gave up again soon after 16:04:17 -!- AnotherTest has joined. 16:04:35 i definitely remember not being in the secondaire yet at the time 16:05:39 -!- Lymia has quit (Ping timeout: 272 seconds). 16:08:58 education systems of the world endlessly confuse me, especially France's. I can never remember when «lycée» and «collège» happen, let alone what are those university year designations («bac + 5» ???). 16:14:41 -!- Sprocklem has joined. 16:15:42 merry christmas boily 16:16:39 quintopia: joyeux noël à toi aussi! 16:17:17 happy birthy boily 16:18:02 boily: you christmas present is on its way 16:20:21 Phantom_Hoover: as it happens, you're only a little bit off. my birthday falls on December 24. 16:20:28 quintopia: woot ^^ 16:20:59 boily: that must have been annoying 16:21:18 -!- Bike has joined. 16:21:36 kids birthdays should be as far from christmas as possible, to maximize presentage 16:23:56 it's far from annoying. a holiday is garanteed, I spend time with my family, and there are various offers and rebates and discounts for many things (mwah ah ah). 16:24:42 also, my parents have fun, like that year where I got that nice chair frame on my birthday, but the cushions on Christmas. 16:25:31 i think it'd be better to have a birthday on jan. 1 16:25:51 after-christmas sales are the best 16:28:05 -!- Sprocklem has quit (Ping timeout: 272 seconds). 16:31:21 -!- Phantom_Hoover has quit (Ping timeout: 246 seconds). 16:33:33 -!- Sprocklem has joined. 16:46:02 -!- Phantom_Hoover has joined. 17:01:35 -!- Sprocklem has quit (Ping timeout: 252 seconds). 17:04:11 -!- Bike has quit (Ping timeout: 272 seconds). 17:05:43 -!- Bike has joined. 17:30:51 -!- MindlessDrone has quit (Ping timeout: 244 seconds). 17:32:16 quintopia: I suppose early august is pretty good in that regard 17:49:09 -!- conehead has quit (Quit: Computer has gone to sleep.). 17:51:32 -!- Lymia has joined. 17:52:26 Today's Scribblenaut: a man needed something to contain an ooze. I gave him "big klein bottle". Somehow, he managed to get the ooze *inside* it. 18:01:02 obviously a klein bottle has an inside. 18:01:29 But it's the same side as the outside. 18:01:44 -!- Taneb has joined. 18:02:32 only a minor detail. 18:03:03 -!- Lymia has quit (Ping timeout: 246 seconds). 18:03:50 -!- sebbu has quit (Ping timeout: 240 seconds). 18:06:02 -!- Phantom_Hoover has quit (Read error: Operation timed out). 18:06:02 -!- Lymia has joined. 18:07:19 -!- Lymia has quit (Client Quit). 18:07:42 -!- Lymia has joined. 18:17:11 -!- Taneb has quit (Ping timeout: 260 seconds). 18:19:35 -!- Phantom_Hoover has joined. 18:19:51 Meanwhile on the Kindle http://imgur.com/a/EMBIM 18:20:00 -!- Slereah has joined. 18:21:17 ion: Z̩̦͘A̠L̘̭̼G̱̯̲̻̗̰͔O̞̫̤̣̥,͈̗ ̟͉̥͎h̪̩̦͎̫͡e͇̺̝͈͎ͅ ̧e̦̺̘p̼͍͉͓̦ͅu̼͚̱̦b̠̰͕̪̖͘s͏̱!̸̗̜͓ͅ 18:21:30 verily 18:22:14 -!- Taneb has joined. 18:25:12 I guess that's pronounced just as it's written? 18:25:36 int-e: the b̠̰͕̪̖͘s͏̱!̸̗̜͓ͅ is silent 18:27:01 -!- oerjan has joined. 18:28:00 * boily chokes on the «ȅ» 18:28:45 -!- carado has quit (Ping timeout: 252 seconds). 18:32:43 boily: I was going to say that yesterday and then you left 18:34:07 oh. that kind of cat. 18:34:20 bahahaha 18:34:40 `unidecode ȅ 18:34:42 ​[U+0205 LATIN SMALL LETTER E WITH DOUBLE GRAVE] 18:34:57 wtf which language has that 18:35:49 https://en.wikipedia.org/wiki/Double_grave_accent 18:36:00 scholary discussions. nice! 18:36:13 it's ȅducational. 18:36:22 btw, android's libc is pretty crappy... discovered today that its fork() deadlocks occasionally 18:37:11 (also: its pselect is just sigprocmask+select, which defeats the point of the function existing in the first place) 18:39:43 (and fopen and getaddrinfo are not thread safe, but I guess that's fair since nothing I've found explicitly declares that they have to be) 18:39:55 ~eval let lev a b = let lev' i j = if min i j == 0 then max i j else minimum [lev' (i - 1) j + 1, lev' i (j - 1) + 1, lev' (i - 1) (j - 1) + (if a !! (i - 1) /= b !! (j - 1) then 1 else 0)] in lev' (length a) (length b) in lev "oerjan" "olsner" 18:39:58 Error (1): 18:40:03 ~eval let lev a b = let lev' i j = if min i j == 0 then max i j else minimum [lev' (i - 1) j + 1, lev' i (j - 1) + 1, lev' (i - 1) (j - 1) + (if a !! (i - 1) /= b !! (j - 1) then 1 else 0)] in lev' (length a) (length b) in lev "oerjan" "olsner" 18:40:04 5 18:40:35 -!- nisstyre has quit (Quit: Leaving). 18:40:51 C has no Threads. 18:41:06 I thought that was the conclusion of the latest discussion about that particular topic 18:41:37 Given C11, that's kind of a strange conclusion. 18:41:44 http://rosettacode.org/wiki/Concurrent_computing#C 18:42:29 -!- conehead has joined. 18:42:59 -!- Taneb has quit (Ping timeout: 272 seconds). 18:43:19 Wait, I missed the whole chain of messages from olsner. Ignore that. 18:44:16 On a separate note: what fascinating thing are you building that needs to use C on an Android device, olsner? 18:45:42 http://www.theonion.com/articles/console-wars-heat-up-as-zenith-unveils-gamespace-p,34551/?utm_source=butt&utm_medium=butt&utm_campaign=butt 18:46:04 boily: i think your algorithm has unnecessary exponential blowup 18:46:07 fwiw, the fork thing affects java too, since the Process implementation eventually does fork+exec 18:46:29 not sure about the other stuff, but it wouldn't be too weird if dns stuff uses getaddrinfo 18:47:23 mrhmouse: "work stuff" :) 18:48:58 Have you isolated the issue to Android's version of libc, or is there some bug report you're working off of? 18:53:01 these are only the bugs I know and that I found proof of or fixes for (fixed in *some* version of bionic, which just means you know the bug exists in all the older versions) 18:57:36 oerjan: I only needed a naïve oneliner. I know I could iterate over a pair of vectors, but that would have implied thinking. 18:57:45 onëliner 18:59:07 `learn onëliners are pairs of unfathomable vectors in the category of exponential distance. 18:59:12 I knew that. 18:59:17 -!- Bike has quit (Ping timeout: 248 seconds). 19:02:15 `? chess 19:02:17 Chess is a complex boardgame, where players exchange unclear royal steaks until they decide which of them has lost. The game is recorded through the Gringmuth Moving Pineapple Notation. 19:02:22 `? pineapple 19:02:24 Pineapple is a hybrid species descended from a cultivar of spinach and wild ivy, therefore making it a class 6 vegetable. 19:04:52 so annoying 19:05:03 people write paper and make a mistake in their algorithm 19:05:12 well in the pseudocode 19:05:30 ... and it gets published 19:06:36 bugs do have to originate from somewhere. you weren't thinking that they just appeared out of nowhere in production code? 19:07:02 it takes many man-hours to produce good quality, free-range bugs. 19:07:15 no, they made a "logical" mistake in the pseudocode 19:07:47 this paper looks at if it hasn't been read by anyone at all 19:07:59 but it was on IEEE 19:08:09 mass-producing cheap bug knock-offs amateurs. 19:08:22 "Modified integer factorization algorithm using V-Factor method" 19:08:34 also has some typos etc 19:08:40 I think it's for a conference 19:08:41 but still 19:10:44 -!- Bike has joined. 19:10:57 also, it's not really something new 19:11:41 I have an algorithm here that outpreforms it and is just as simple, and I don't really think it's ready for publication yet 19:12:01 ion: utm_campaign=butt 19:12:24 well I haven't really thought about writing a paper or anything either 19:12:40 Bike: from the butt, for the butt 19:13:00 (btw, do people even look at papers from people in highschool) 19:13:22 not if they can't help it 19:13:26 (do highschool pupils evne write them) 19:16:39 http://i.imgur.com/7IVS5LT.jpg britain rules 19:19:31 where neighborhood isn't required to be open? <-- the definition of continuity is equivalent whether you require them to be or not. 19:19:53 Oh god 19:20:00 Plankalkül is so gross 19:20:22 oerjan: right but why do neighborhoods even make sense 19:21:16 `run mv wisdom/onëliner{s,} 19:21:20 No output. 19:21:42 "The original notation was two dimensional." 19:21:46 Gee golly jeeperw 19:22:58 Slereah: why is it gross? I like it. 19:24:02 It's not abstract enough to have the beauty of some abstract notation, but not computery enough to look like some serious machine code 19:25:53 preimages of closed sets have to be closed anyway i guess <-- um that's yet another definition of (global) continuity 19:28:48 the sweet-and-sour spot of Baudot encoded languages. 19:29:28 oerjan: that's wh at i meant, yes 19:29:34 shachaf: in the one definition, a neighborhood is just an open set containing your chosen point, which are important for being able to say anything local to a point. in the other definition where they aren't open, neigborhoods of a point form a _filter_, which is important as one way to generalize what you take limits in. 19:30:25 ok my book talks about that so i'll read about that?? 19:30:29 thx 19:31:36 oerjan: why does https://en.wikipedia.org/wiki/Prime_filter redirect to an article that says "Hence, most additional information on this topic (including the definition of maximal filters and prime filters) is to be found in the article on ideals." 19:32:29 -!- MindlessDrone has joined. 19:34:55 shachaf: well the article on ideals doesn't seem to define them either. 19:35:52 hm well i guess it does. 19:36:15 maybe you need to read the thing that says that an ideal is dual to a filter before that makes sense 19:38:17 -!- Sprocklem has joined. 19:40:48 well you'll be happy to know that it no longer redirects there hth 19:41:21 also i have started bypassing the script lately tdnh 19:41:23 -!- constant has changed nick to variable. 19:41:31 what script 19:42:17 the one that censors any line ending with things like 19:44:23 how did you manage to hth in “... redirects there hth” but not in “... with things like”? 19:46:27 oerjan: Wait, you have a script to censor "hth"? 19:46:38 :'( 19:46:43 boily: http://tvtropes.org/pmwiki/pmwiki.php/Main/RuleOfFun 19:46:48 shachaf: elliott made it 19:47:47 oerjan: and now I know. 19:48:07 * boily tries to sing «hth, hthhhhh, hhhhhhhhhhhthhhh ♪» 19:48:46 remarkable effort from a french speaker there 19:49:07 are you sure you're not abusing them all being silent 19:53:07 don't pay attention to the silent h behind the curtain. 19:54:08 i eard noting 19:56:09 -!- john_metcalf has changed nick to impomatic. 19:57:52 -!- Taneb has joined. 19:59:00 from wikipédia's samples, I can't make no difference between [ħ] and [h]. 20:00:15 hahaha 20:03:21 * boily glares at myname while he thinks of a suitable counter-attack 20:03:26 what's "tdnh" 20:03:31 `? tdnh 20:03:33 tdnh does not help 20:03:38 oh 20:03:40 another aah 20:03:47 -!- Taneb has quit (Ping timeout: 268 seconds). 20:05:58 (meanwhile, I like south (django's (the web platform (or framework, I lost count (a character in Sesame (you never can get enough of it on maki (ja:巻 en:scroll) sushi) Street))) migration tool)) 20:08:26 boily: sounds a little one-directional 20:09:16 Maybe it's the winter (when birds migrate south) version and you'll have to wait for the summer one. 20:09:49 -!- Phantom_Hoover has quit (Ping timeout: 240 seconds). 20:10:54 -!- Phantom_Hoover has joined. 20:17:13 -!- nisstyre has joined. 20:18:56 oerjan: I do not listen to One Direction. all I know is that it's kinda like the latest manufactured boy band or something. eeqça. 20:22:15 -!- nisstyre has quit (Disconnected by services). 20:22:34 -!- nisstyre has joined. 20:25:30 * myname wonders if rule of fun is in any way related to dwarf fortres 20:27:42 “Failure Is the Only Option: "Losing is Fun!" became the official motto for a reason.” 20:28:03 “Hilarity Ensues: Look, if you actually get upset when one of your dwarves gets into a foul mood because you killed his cat on accident, beats up another dwarf who then gets ticked off enough to put his pick into the head of another dwarf who then lies there decaying on the ground, causing bad smells that drive a handful of the other dwarves unhappy enough to pick up axes until bleeding, insane and dead 20:28:05 dwarves litter your fortress, you're playing it wrong. Losing is Fun, after all!” 20:29:58 -!- augur_ has quit (Remote host closed the connection). 20:30:31 -!- augur has joined. 20:30:37 for the time being, I'll stick with good ol' DCSS. I'm not yet prepared to be maximally enfunised. 20:32:07 -!- MindlessDrone has quit (Quit: MindlessDrone). 20:35:05 -!- augur has quit (Ping timeout: 265 seconds). 20:41:44 -!- Oj742 has joined. 20:50:44 while we're on the subject of games with roguelike interfaces.. Does anybody know of a worthwhile multiplayer roguelike? 20:51:16 -!- Sprocklem has quit (Ping timeout: 268 seconds). 20:55:37 Obviously turn-based play is probably out the window. I'm more interested in the general nature of the game (dungeon diving for some mythical item while leveling up along the way). 20:56:28 i only knew one which i didn't get :/ 20:56:38 diablo clearly 20:57:51 mangband. 20:57:52 i thought of making my own rl, but i don't have time right now 20:57:55 boily: that 20:58:12 -!- boily has quit (Quit: Poulet!). 20:58:15 -!- metasepia has quit (Remote host closed the connection). 20:58:21 -!- sebbu has joined. 20:58:55 -!- sebbu has quit (Changing host). 20:58:55 -!- sebbu has joined. 20:59:50 -!- augur has joined. 21:04:45 mangband looks like what I'm looking for! Bike: I've never played any of the Diablo games. Are they local multiplayer or online? 21:05:23 online, apparently. i wasn't really serious 21:05:27 @tell boily thanks for suggesting mangband, looks great 21:05:28 Consider it noted. 21:05:34 well, it has LAN, i don't know what you mean by "local" exactly 21:05:47 -!- boily has joined. 21:05:53 Bike: same screen == local to me 21:06:03 right, so no, doesn't have that 21:06:06 i never played any *band so i didn't get warm with mangband 21:06:56 it really saddens me how few games these days include same-screen co-op play :/ 21:08:47 -!- sebbu has quit (Ping timeout: 246 seconds). 21:12:05 -!- AnotherTest has quit (Ping timeout: 248 seconds). 21:13:11 -!- Oj742 has quit (Read error: Connection reset by peer). 21:21:45 -!- Sprocklem has joined. 21:22:32 -!- Frooxius has quit (Read error: Connection reset by peer). 21:26:56 -!- carado has joined. 21:35:21 -!- yiyus has quit (Remote host closed the connection). 21:36:41 fungot! 21:36:42 FireFly: def command lang code tends to go fubar when you haven't yet 21:36:59 I'd rather not go fubar 21:37:03 fungot: when you haven't what yet? 21:37:03 mrhmouse: i'm not seeing the 32bit loving code in pre-scheme. but it makes it a good target 21:38:02 I'm not sure if you mean target (expected runtime platform) or target (receiver of projectiles) 21:39:26 I'm sure ruddy knows what you're talking about, though 21:39:26 USually some kind of technical issue. 21:40:50 -!- sebbu has joined. 21:41:29 -!- sebbu has quit (Changing host). 21:41:29 -!- sebbu has joined. 21:42:47 ruddy: well duh 21:42:48 Can't touch dis. 21:44:41 -!- sebbu has quit (Read error: Connection reset by peer). 21:48:06 -!- sebbu has joined. 21:48:41 -!- sebbu has quit (Changing host). 21:48:41 -!- sebbu has joined. 21:49:58 -!- sebbu has quit (Read error: Connection reset by peer). 21:51:54 -!- sebbu has joined. 21:51:55 -!- nisstyre has quit (Quit: Leaving). 21:52:28 -!- sebbu has quit (Changing host). 21:52:28 -!- sebbu has joined. 21:52:51 ruddy, we're no longer in the 1990s... 21:52:52 \o/ 21:55:41 ruddy: dis, as in the Iron City of the same name? 21:55:41 ye 21:55:46 ! 21:56:22 mrhmouse: your bot is scary. he invokes branches of Hell. 22:08:50 -!- boily1 has joined. 22:09:51 -!- boily has quit (Ping timeout: 244 seconds). 22:10:55 -!- boily1 has changed nick to boily. 22:12:49 ruddy: so um, what esolangs do you like? 22:12:50 Welcome back 22:13:03 ruddy: stop trying to avoid the question. We need to know. 22:13:04 and the point I'm making is that I really like this story. 22:13:17 clearly ruddy wants to tell us a story 22:13:17 mangband. 22:13:29 :o 22:13:33 it may also have brain damage 22:14:12 ruddy learns fast! 22:14:13 no. 22:14:19 and ruddy is modest! 22:14:19 no. 22:14:29 ruddy is pretty negative today.. 22:14:29 planet melmac 22:14:30 ok i'm liking this chatterbot's style now. 22:14:41 ruddy is fungot in disguise. 22:14:41 boily: saw that. 22:14:42 Speak! 22:14:52 fungot: I saw it too. 22:14:52 boily: sure: cd /usr/ pkgsrc/ fonts/ misc has fnord 22:14:58 (also, http://eleks.github.io/js2js/) 22:15:32 fungot has a fnord font? I'm not too surprised. 22:15:32 FireFly: my mouse just goes poof. time to apply that procedure, so the value of writing them anybody want to clue me in on the fnord 22:16:08 fungot: I thought your box was headless... 22:16:08 FireFly: oh wait, 22:16:12 * FireFly waits 22:16:52 * boily waits for FireFly 22:16:59 -!- Sprocklem has quit (Ping timeout: 268 seconds). 22:20:17 boily: that is glorious. 22:20:32 boily: haha, nice 22:21:11 ruddy: row, row, row your botsnack 22:21:11 before you break my heart 22:21:16 -!- Frooxius has joined. 22:24:46 i think i'm seriously considering memoizing a function over all possible floats. 22:25:53 ...why? 22:26:08 because calling it a billion times takes twenty seconds and i'd rather it not. 22:26:25 Oh, memoizing 22:26:53 I was thinking of making a LUT for all possible floats 22:27:22 <`^_^v> how do you memoize a function over all possible floats 22:27:36 -!- boily has quit (Quit: LATE NIGHT REVERSE CHICKEN IN A NEW YORK BACKALLEY). 22:27:37 you don't, it's stupid 22:27:52 <`^_^v> i'm just trying to figure out what that means 22:28:00 <`^_^v> cause it sounds like you want to precalculate, not memoize 22:28:11 whatever. 22:28:21 it sounds like he wants to do both 22:28:31 it sounds like everything is terrible! 22:28:32 couldn't you use something hashmappy to map floats to values? it seems like it'd be easy to write a good hash function for floats 22:28:39 I think 22:29:16 i think i need better metrics. draw up a distribution of the billion values this is called on 22:30:50 anything that floats and isn't a duck is clearly a witch and I don't trust it 22:33:50 No no, it just has to weigh the same as a duck, obviously 22:34:15 * FireFly throws Bike's floats in the water 22:34:23 D:! 22:38:27 -!- carado has quit (Ping timeout: 252 seconds). 22:38:49 Huh. Right to the bottom. At least now you know your floats aren't witches, Bike 22:40:18 Although they may now be guests at a seedy hotel 22:51:38 -!- ais523 has joined. 22:55:08 -!- yiyus has joined. 22:58:35 -!- mrhmouse has quit (Quit: Leaving.). 22:58:45 `frink 96.7 kg to lbs 22:58:54 ​[] 22:58:59 welp 22:59:26 `frink 10 px to radians 22:59:35 Warning: undefined symbol "px". \ Bounds in range expression are of unsupported types: (10 px (undefined symbol), 1) \ at frink.expr.bh.byte(frink) \ at frink.expr.bh.evaluate(frink) \ at frink.parser.Frink.parseString(frink) \ at frink.parser.Frink.parseStrings(frink) \ at frink.parser.Frink.main(frink) \ Bounds in range expression 22:59:51 Ow 22:59:54 why is pounds written lbs? 23:00:02 "libras" or something 23:00:11 hmm, as in books? 23:02:19 I think it's a corruption of the Latin for "pound" 23:02:32 but I can't remember exactly how it's spelt 23:03:01 Wikipedia says "The unit is descended from the Roman libra (hence the abbreviation "lb"); the name pound is a Germanic adaptation of the Latin phrase libra pondo, 'a pound by weight'" 23:03:59 As far as I can tell 'libra' as a unit of weight originated in Latin 23:06:55 wow, this spambot put "Dear Smith Alex, " and my email address in the subject line of the email 23:07:17 and the email itself looks similar to XML but isn't because it's got some text before the tag 23:07:28 -!- Taneb has joined. 23:08:04 also, it appears to be OOXML using no tags but

    tags and with all spaces changed to nonbreaking spaces 23:08:17 and the links aren't even hyperlinked 23:08:34 in other words, this email could have been written entirely in plaintext, and would look the same as intended if it had been 23:09:07 this is a good argument for using the right format for your messages :) 23:09:46 -!- oerjan has quit (Quit: nite). 23:17:08 -!- yorick has quit (Read error: Operation timed out). 23:19:14 -!- yorick has joined. 23:47:09 -!- ais523 has changed nick to ais523\unfoog. 23:54:07 -!- nisstyre has joined. 23:58:31 -!- Oj742 has joined. 23:58:50 -!- nooodl has quit (Quit: Ik ga weg). 23:58:52 -!- Lymia has quit (Ping timeout: 244 seconds). 23:59:54 -!- nisstyre has quit (Ping timeout: 244 seconds). 2013-11-15: 00:01:40 -!- nisstyre has joined. 00:11:38 -!- FireFly has quit (Excess Flood). 00:12:51 -!- FireFly has joined. 00:32:44 -!- ais523\unfoog has quit. 00:36:48 -!- ais523 has joined. 00:42:42 -!- augur has quit (Remote host closed the connection). 00:43:16 -!- augur has joined. 00:47:47 -!- augur has quit (Ping timeout: 260 seconds). 00:51:19 -!- Bike has quit (Ping timeout: 272 seconds). 00:52:56 -!- ^v has joined. 01:00:59 -!- Oj742 has quit (Ping timeout: 246 seconds). 01:03:38 -!- Bike has joined. 01:06:56 -!- Taneb has quit (Quit: Leaving). 01:10:47 -!- yorick has quit (Remote host closed the connection). 01:25:20 -!- augur has joined. 01:35:35 -!- Sgeo has joined. 01:48:30 -!- Phantom_Hoover has quit (Remote host closed the connection). 02:15:03 -!- nisstyre has quit (Quit: Leaving). 02:18:01 FireFly: early august is good in what regard? scrolling back forever is a pain 02:19:27 -!- doesthiswork has joined. 02:19:47 delimited continuations are exceedingly esoteric 02:20:02 oh 02:20:05 hi doesthiswork 02:20:17 hi quintopia 02:20:23 your IP is showing 02:21:05 (~Adium@98.145.118.186)? 02:21:16 yep 02:21:58 the irc is coming from inside the house 02:22:40 lol 02:31:49 -!- Alexander_ has quit (Ping timeout: 250 seconds). 02:32:53 doesthiswork: do you have any languages 02:33:10 not at the moment 02:34:03 although I'm trying to figure out how to make a inconsistent logic programming language work just well enough to be evil 02:35:32 And I have an idea for a language that uses a lazy learning mechanism to parse the input into constructs 02:44:53 -!- Lymia has joined. 02:44:54 -!- Lymia has quit (Read error: error:1408F10B:SSL routines:SSL3_GET_RECORD:wrong version number). 02:45:16 -!- Lymia has joined. 02:46:18 -!- Lymia has quit (Read error: error:1408F10B:SSL routines:SSL3_GET_RECORD:wrong version number). 02:46:19 oh okay 02:46:22 i uh 02:46:31 the beautiful thing about that is it will change semantics over time 02:46:42 -!- Lymia has joined. 02:46:44 lazy learning? what? 02:47:02 like what you do in lecture 02:47:08 sleep through it and read the textbook 02:47:08 also inconsistent logic sounds to me like the kind of system where explosion happens 02:47:39 apparently para inconsistent logics don't explode 02:49:00 can you just drop proof by disjunction 02:49:02 lazy learning is basically classifying input using the k-nearest neighbors from the training data. 02:49:05 fix everything in one fell swoop 02:50:28 logic programming without modus ponens would be funny 02:51:22 yes I think dropping proof by disjunction would be good 02:51:42 doesthiswork: actually quite a lot of study of logic is proving that modus ponens is unnecessary 02:51:51 as in, not actually /wrong/, just they design their logics so they never have to use it 02:51:54 because it screws things up 02:52:45 ais523: why does it screw things up? 02:53:18 coppro: basically because the structure of a term no longer guides its derivatoin 02:53:20 *derivation 02:53:50 ah 03:00:41 -!- nisstyre has joined. 03:12:27 Anyone here know about building computers? 03:12:37 <^v> yes 03:12:55 i'm thinking i should have a pretty good windows computer but i don't know shit. 03:13:00 <^v> step 1. newegg.com 03:13:05 <^v> step 2. newegg.com 03:13:08 <^v> step 3. newegg.com 03:13:10 <^v> etc 03:13:16 <^v> or 03:13:17 how many steps are there 03:13:47 -!- augur_ has joined. 03:13:49 <^v> wget http://old-computer-parts/ 03:14:57 Hey, tht's not a real website! 03:16:55 -!- impomatic has left. 03:16:59 -!- augur has quit (Ping timeout: 272 seconds). 03:18:45 -!- Tod-Autojoined has changed nick to TodPunk. 03:31:50 kmc: is there a good reason for blocking the ability to make diamond structures without requiring the GC? 03:32:04 Cyclic structures needing GC makes sense 03:40:01 simpler than detecting cycles? 03:51:51 -!- ^v has quit (Quit: Leaving). 03:51:51 -!- v^ has joined. 03:51:51 You can have a data type that could potentially have diamonds without it being able to potentially have cycles 03:52:38 -!- `^_^v has quit (*.net *.split). 03:52:38 -!- jix has quit (*.net *.split). 03:52:39 -!- nortti has quit (*.net *.split). 03:54:00 -!- jix has joined. 03:54:46 -!- nortti has joined. 03:55:51 yes you could 03:59:37 -!- `^_^v has joined. 04:06:56 -!- nisstyre has quit (Quit: Leaving). 04:08:03 -!- Sprocklem has joined. 04:11:45 Sgeo: what do you mean, how is it blocked? 04:12:17 Can't have two owned pointers to the same box, right? 04:12:21 right 04:12:33 that would require reference counting or some other scheme to decide when they've both gone away 04:12:49 owned boxes have deterministic memory management; when an owning pointer is destroyed, the box is freed 04:12:55 so they have to be unique 04:13:14 @ is actually just refcounted and not GC'd at the moment 04:13:18 it's expected to change in the future 04:13:38 there's also a library type Rc which provides a more semantically clean version of refcounting 04:13:48 but Rust doesn't have smart pointer deref sugar yet, so it's a bit more cumbersome to use 04:14:01 Rc also statically forbids cycles 04:14:35 and there's Arc which is "atomic reference counting" and can be shared between tasks 04:14:40 and there are mut versions of both 04:15:03 (an Rc is an ownership root much like an @T, so it determines the mutability of the stuff inside) 04:16:25 Sgeo: people have argued you shouldn't think of ~T as a pointer at all; it's a value type similar to T but with an optimization to make sure it's never bigger than a word 04:16:56 heh. 04:17:08 and also allows recursive structures... a ~T can hold another ~T but a struct can't contain a copy of the same struct 04:17:18 they talk about a world where ~int and int have the same representation 04:22:53 are you talking about Rust? 04:23:50 I think a proper garbage collection in Rust would involve some kind of type visitors in order to detect the cycle 04:24:01 kmc: what if an &int exists borrowed from that ~int? 04:24:08 (or inaccurate gc) 04:24:09 oh, would the &int point to the ~int rather than to the underlying int? 04:25:03 ais523, &int points to the underlying int, but &int cannot live longer than ~int. 04:25:16 lifthrasiir: I know it can't 04:25:22 but with ~int being the same as int, there isn't an underlying int 04:25:41 uh, you mean the internal representation? 04:25:54 yes 04:25:57 borrowing an ~int to an &int would then be the same as borrowing an int to an &int 04:26:00 you'd point to the ~int directly, then 04:26:05 kmc: oh, I see 04:26:09 I forgot you could do that 04:26:17 «let x: ~int = ~3; f(&x);» that'll just pass a pointer to the stack 04:26:38 yeah you can borrow stack vars and arguments as well as heap boxes 04:26:45 uh, &x is of the type &~int and not &int. 04:26:55 lifthrasiir: right, but it would be the same operationally 04:27:04 if ~int is the same operationally as int 04:27:30 this also depends on the fact that rust generics are monomorphized 04:27:34 I don't see a value in making ~int internally equivalent to int 04:27:49 a generic function operating on ~T would have to produce different code for ~int and ~MyStruct 04:27:53 but that's already what it does 04:28:04 (and for ~Trait) 04:28:05 lifthrasiir: I don't see huge value either, but it would save an allocation 04:28:14 if for some reason you were making lots of owned-boxed ints 04:28:18 but I don't know why that would be the case 04:28:22 maybe generic code 04:28:27 oh, i thought "they talk about a world where" was more supposed to be a conceptual thing. 04:28:33 AFAIK LLVM has some kind of malloc-to-reg passes 04:30:19 -!- nisstyre has joined. 04:30:34 kmc, actually, non-primitive non-boxed types behaves almost identically to owned boxes (major difference being the memory layout, of course), so using type params instead of using an explicit owned box can solve that problem. 04:32:12 "In sequential code it is possible to control the flow of the program using if-then-else statements and various forms of loops. Such flow control structures have only recently been added to GPUs" so, i'm starting to think the wikipedia article on gpgpu is actually stupid 04:33:30 why 04:33:36 "A variety of data structures can be represented on the GPU: * Dense arrays * Sparse arrays * Adaptive structures [citation needed]" 04:33:44 lifthrasiir: right 04:33:52 A variety of data structures can be represented on the GPU: * Integers 04:33:59 you're saying there's not much you can do on a generic ~T that you can't also do on a T:Send ? 04:34:04 makes sense 04:34:06 yup. 04:34:09 integers, single floats, the possibilities are limitless 04:34:13 it was not long ago that integers were not really a data type in gpus 04:34:19 just floats 04:34:27 if it's good enough for javascript 04:34:32 oklopol: doubles were only added recently, too 04:34:36 * Integers that fit in IEEE 754 binary floating point types. 04:34:40 although they always used to have at least slightly working ints to do array indexes 04:34:54 lifthrasiir: apparently not all GPUs are ieee-conformant, just to punish me 04:35:23 Bike: most of them used not to be 04:35:33 Bike, subnormals? :) 04:35:40 yeah, probably subnormals 04:35:42 they started adding IEEE conformance only recently, for people who wanted to do scientific computations on them 04:35:51 right 04:36:04 i'm seeing about the realism of my getting a GPU for games and also for work 04:36:05 Java bytecode had something like strictfp, I think 04:36:34 what cha gonna do with one 04:36:49 lifthrasiir: strictfp is actually a keyword in Java 04:37:13 nothing all that interesting >_> simulations at lab take time to run, they'd take less time if i got 'em running on something good 04:37:30 probably would take some work to really parallelize it well though 04:37:52 right now it just runs different sims on different cores, which helps but is boring 04:38:14 what cha labbing? 04:38:32 what does that mean 04:39:02 synonyms for labbing oh god you be testing my englishability. 04:39:14 yes. you pass. now what the fuck are you saying 04:39:14 what are you simulating at the lab 04:39:18 oh. muscles. 04:39:43 cooool 04:39:48 real ones??? 04:39:55 yes? 04:40:06 how do you put real muscles into a gpu 04:40:21 UNCLE MUSCLES 04:40:25 MUSCLES FOR BONES 04:40:27 I'm thinking it might be possible to do the computations across space in parallel 04:40:31 CASH FOR BONES 04:40:58 honestly my main motivation is that i want to fuck around but that's how it always is 04:41:01 kmc: NETHACK.ALT.ORG HAS BONES 04:41:36 are these your own muscles or like walrus muscles or what and how do you preserve them 04:42:06 or are they virtual muscles which are real in the sense that they are real if you believe in them really really hard 04:42:15 some human muscles from football players who fucked up their feet, some fly muscles from catching flies and dissecting them, some rabbit muscles from killing rabbits 04:42:25 the flies are killed too* 04:43:00 do flies have big muscles 04:43:09 what does it look like when they flex 04:43:54 anyway yeah gpus are awesome you should do everything with them 04:44:17 i once almost did something with them other than shading stuff but then i ended up not doing it but just daydreaming about how cool it would be to do it 04:44:37 but that was cool too 04:44:46 are you ok 04:46:40 good q 04:47:09 lemme ponder upon that 04:48:06 but basically science code is fucking terrible and rewriting it to be not terrible is fun and involves lots of cool optimization opportunities like "lexical scope" 04:48:07 oklopol: what was the thing you daydreamed 04:48:10 -!- conehead has quit (Quit: Computer has gone to sleep.). 04:48:38 quintopia: cellular automata stuff 04:49:27 right should have known 04:49:34 could be cool though. 04:49:40 because there are no programs out there for implementing CA 04:49:42 lexical scope is p. great 04:49:43 all i'm doing is linear algebra. Like, Who Cares, Man 04:50:19 oklopol: What would you do that Golly can't handle? (not a challenge or anything it sounds supa cool) 04:50:34 golly is worse than C 04:50:38 you have to list the rule manually 04:50:54 gonna be honest i've only used golly because it makes pretty pictures 04:50:59 but i mean, it does hashlife and all. 04:51:05 if you have more than 8 states it takes forever to write up a rule 04:51:13 and usually CA have hundreds of thousands of states 04:51:20 ah, i see. 04:51:34 usually in the sense that i have some specific ones i'd like to see implemented 04:51:40 the most complex CA i know is von neumann's. i'm a dabbla, see 04:51:54 the 29 state constructor thing maybe 04:51:59 yeah, that one. 04:54:15 -!- Sprocklem has quit (Ping timeout: 260 seconds). 04:54:24 basically my only concrete new idea is to do (n+1)-dimensional SFTs instead of n-dimensional CA, the rest is hype 04:54:42 i don't know that initialism. 04:54:52 subshift of finite type, like wang tiles 04:55:08 i don't really know that concept either but i know wang at least. 04:55:36 so basically you would just draw signals and stuff, and it would say "this is downward deterministic, would you like to make it a CA" 04:55:56 well wang tiles are squares with colors on their left, top, right, bottom sides 04:56:00 right. 04:56:05 and you fill Z^2 with them so that colors match 04:56:10 can't turn them 04:56:22 right, and that's uncomputable and whatnot. 04:56:39 whether or not Z^2 can indeed be filled is undecidable, yes 04:57:21 anyway, this is the same thing as a cellular automaton on a one-dimensional SFT, restricted to its limit set 04:58:02 where a one-dimensional SFT includes the full shift S^Z CA are usually run on, and basically just means wang tiles with only left/right colors 04:58:25 and limit set is the set of configurations with an infinite chain of preimages 04:58:27 and stuff 04:58:42 so like dynamics. 04:58:59 well, not like dynamics. 04:59:01 whatever. 04:59:43 one-dimensional SFTs are dynamical systems with the shift maps giving an action of Z 05:00:13 two-dimensional SFTs are dynamical systems with an obvious Z^2 action 05:00:39 cellular automata are dynamical systems with an N-action given by repeating it 05:00:44 or Z if the CA is reversible 05:02:51 (an action of a group G on a space X means a homomorphism from G to the group of continuous homeomorphism from X to itself) 05:03:21 (sorry i didn't know what dynamics means so i guess i did a dictionary look up or something) 05:10:14 -!- v^ has quit (Ping timeout: 240 seconds). 05:21:16 -!- heroux has quit (Ping timeout: 244 seconds). 05:22:14 -!- nisstyre has quit (Quit: Leaving). 05:32:49 "If you had asked me whether or not it was possible to get a 2x speedup for my LazySorted project by adding a single line of code, I would have told you "No way, substantial speedups can really only come from algorithm changes."" 05:33:29 reddit commenters pointed out that the line in question is incorrect, it can read out of bounds while trying to calculate the address to prefetch 05:33:30 I guess every algorithm change affects multiple lines of code, according to this person? 05:33:43 prefetching's safe if the address to fetch isn't valid, but not if something goes wrong calculating it 05:33:51 Sgeo: memoize('function_to_memoize'); 05:34:22 ais523: I was thinking about work, and how I'm about to do what is essentially a major algorithm change in two li.. actually, hmm, it's more than two lines of code 05:34:45 -!- v^ has joined. 05:34:55 ais523: nice example 05:35:24 oklopol: luckily i don't know anything. 05:35:32 I was thinking of (besides work), some language where the functions you use on data structures are overloaded, but one line can determine whether you're working with a linked-list or a vector 05:42:00 -!- v^ has quit (Quit: http://i.imgur.com/MHuW96t.gif). 05:45:12 2x speedup is not that substantial 05:45:30 algorithm changes usually get you tends-to-infinity-x speedup 05:45:49 https://developer.nvidia.com/sites/default/files/imagecache/banner_slideshow/akamai/cuda/images/banners/GeoINT_Defense_700x240_static.jpg nvidia promises me vast fields of geoint, and also jpeg artifacts 05:48:22 -!- doesthiswork has quit (Quit: Leaving.). 06:08:36 i found a neat whitepaper on this stuff. apparently instead of fp control stuff every instruction just has rounding modes and stuff encoded. (attn fiora i need your help) 07:01:57 -!- carado has joined. 07:20:21 AMD's new APU, "Kaveri", means (approximately) "a friend, a pal" in Finnish. 07:43:24 -!- ais523 has quit. 08:11:39 -!- FreeFull has quit (Ping timeout: 252 seconds). 08:16:46 -!- FreeFull has joined. 08:39:31 -!- Slereah has quit (Ping timeout: 252 seconds). 09:10:45 -!- nisstyre has joined. 09:40:50 -!- nisstyre has quit (Quit: Leaving). 09:47:23 -!- oerjan has joined. 10:04:24 -!- ais523_ has joined. 10:09:48 -!- Phantom_Hoover has joined. 10:30:35 you know spammers are making you nervous when you google the nick of new registrations 10:31:47 I just got an SMS that my mobile number had won £2.5M and I just need to email some random-looking gmail address to claim it. 10:31:56 My ~first SMS spam, I think. 10:31:58 that sounds like spam to me 10:32:29 (Well, "just"; it came at around 05am and woke me up.) 10:34:22 how loud is your sms sound 10:36:09 I... haven't measured. 10:41:46 fizzie: i got my first just a few weeks ago too 10:44:11 don't they have to pay to send SMS in Europe? 10:44:16 that must be some expensive spamming 10:44:54 presumably they found a loophole to that 10:45:36 in the US, SMS is recipient-pays, for some bizarre historical reason 10:45:46 which at least means SMS spamming is really cracked down on 10:47:33 docsdept2013@gmail.com 10:47:46 2.5 million pounds 10:48:07 recipient pays? 10:48:17 -!- impomatic has joined. 10:48:23 so if your number gets known by someone random, they can make you pay as much as they like? 10:48:59 oklopol: pretty much 10:50:35 in finland, it's relatively easy to move anyone whose name you know, you just call the authorities and say you've moved, and they update your address 10:50:57 sometimes they ask where you were born or something, but for example i don't remember and it was fine 10:51:05 (i was born in sweden) 10:51:13 a few prepaid customers in the US pay for each SMS they receive but it's much more common (even on prepaid) to have some "unlimited SMS" package 10:51:31 ah right, that would make sense 10:51:37 it's still recipient pays, but they buy in bulk 10:51:49 it's the same for sending in the UK 10:52:31 and the risk of spam is one of several factors that pushes people towards such packages 10:54:21 i never actually send/receive SMS through my carrier anyway though, because i use google voice for that which uses my data connection 10:55:30 -!- ais523_ has quit (Quit: Page closed). 11:02:16 oklopol: I think mine was the same. 11:05:36 (I remember there being a news article about this particular scam few weeks back.) 11:20:16 ahhh they seem to have fixed that annoying windows 8.1 spellchecking bug 11:20:37 (that is, you couldn't turn it off) 11:24:57 -!- yorick has joined. 11:32:19 -!- Taneb has joined. 11:35:10 hm, Timwi is learning haskell. 11:35:14 be very afraid. 11:38:19 oerjan, I hope his learning experience goes better than mine did 11:38:43 At first I was programming Haskell as though it was Python 11:38:49 -!- Tefaj has changed nick to Jafet. 11:38:51 Now I code Python as though it were Haskell 11:38:59 -!- Jafet has quit (Changing host). 11:38:59 -!- Jafet has joined. 11:39:04 Partying like it's 1991, and coding Haskell like it's Python. 11:39:26 coding 1991 haskell like it's 1991 python? 11:39:28 fact n = reduce(lambda x, y: x * y, range(1,n+1)) 11:39:49 I'm slightly surprised xkcd hasn't done "party(ing) like it's ____" plot yet. (Or if so, I don't remember it.) 11:40:42 -!- doesthiswork has joined. 11:41:57 (note: for python < 3, using xrange may be better than range) 11:42:19 "total error: NaN" I don't know if that's a good thing or not. 11:42:27 (and actually, reduce isn't in Python 3?) 11:43:14 That certainly sounds like programming Haskell. "What, it's not in this version?" 11:43:37 from functools import reduce, perhaps. 11:44:43 Aaah, that's where it ended up 11:48:50 from HaskellPretenders import foldl, foldr 11:54:50 -!- sebbu has quit (Read error: Connection reset by peer). 11:55:20 -!- esucg0aq47trgb8 has joined. 11:55:25 -!- sebbu has joined. 11:56:00 -!- sebbu has quit (Changing host). 11:56:00 -!- sebbu has joined. 11:57:53 -!- esucg0aq47trgb8 has quit (Excess Flood). 11:58:07 -!- esucg0aq47trgb8 has joined. 11:58:10 YOU MAY BE WATCHED 11:58:10 WARNING WARNING WARNING, WARNING 11:58:10 WARNING WARNING WARNING, WARNING WARNING 11:58:10 YOU MAYWATCHED 11:58:10 YOU MAY BE WATCHED 11:58:10 YOU MAY BE WATCHED 11:58:11 ) 11:58:11 Do usa&Israel use chat &facebook 2 spy?!?!?!? 11:58:12 Do they record &analyse everything we type?!?!?!? 11:58:12 -!- esucg0aq47trgb8 has quit (Excess Flood). 11:58:35 -!- esucg0aq47trgb8 has joined. 11:58:40 -!- esucg0aq47trgb8 has quit (Excess Flood). 11:58:53 -!- esucg0aq47trgb8 has joined. 11:59:00 -!- esucg0aq47trgb8 has quit (Excess Flood). 11:59:02 I liked today's XKCD 11:59:13 -!- esucg0aq47trgb8 has joined. 11:59:14 -!- esucg0aq47trgb8 has quit (Excess Flood). 11:59:29 Taneb, still weak imo 11:59:37 -!- esucg0aq47trgb8 has joined. 12:00:24 Phantom_Hoover, it has an actual joke 12:00:41 -!- esucg0aq47trgb8 has quit (Excess Flood). 12:00:42 It's a good start and I want to encourage them 12:00:52 -!- esucg0aq47trgb8 has joined. 12:00:57 -!- esucg0aq47trgb8 has quit (Excess Flood). 12:01:16 Taneb, only barely! 12:01:20 -!- esucg0aq47trgb8 has joined. 12:01:39 -!- esucg0aq47trgb8 has quit (Excess Flood). 12:01:44 I take jokes where they come! 12:02:59 There did not seem to be one in today's Gunnerkrigg Court, but that's okay because Gunnerkrigg Court is much more story-based than xkcd 12:03:45 And Freefall is on hiatus this week 12:03:52 :O 12:04:00 how is that even possible 12:04:09 Family medical emergency, apparently 12:04:18 "Due to family medical problems (not mine, but still requires my attention), Freefall will be on Hiatus for a week. Sorry about that everyone." 12:06:19 Poor Annie 12:06:30 i think this is the first day i've managed not to check anyhow. 12:06:54 I just spent like 15 minutes clustering a matrix full of zeros. 12:07:02 Some sanity checks might've been nice. 12:07:20 `? mad 12:07:22 (There was a typo in the code loading files, it was assigning to a whole another matrix.) 12:07:23 ​"But I don't want to go among mad people," Alice remarked. "Oh, you can't help that," said the Cat: "we're all mad here. I'm mad. You're mad." "How do you know I'm mad?" said Alice. "You must be," said the Cat, "or you wouldn't have come here." 12:07:34 NO SANITY HERE 12:07:52 oerjan, I check Freefall daily for no good reason 12:08:06 I get highlighted by freefall 12:08:10 Dammit 12:09:12 ok i meant "daily when it usually updates" 12:09:49 I mean daily 12:12:08 Taneb: also, discworldproblems? how many r/*problems subreddits _are_ there these days? 12:13:56 a) why are you redditstalking me? and b) I have no idea. At least 4 12:14:24 -!- asie has joined. 12:14:42 because you're on my friends list hth 12:15:15 this would be the creepy friends list that requires no confirmation or even notification of the 'friend' 12:15:26 yep. you're on it too btw 12:15:39 Okay, to be fair you're on mine, oerjan 12:15:43 yay! 12:15:54 neither of you are my friends 12:15:55 hth 12:16:18 Phantom_Hoover: i cannot be held responsible for reddit's poor choice of terminology. 12:16:22 That's a shame, you're my friend 12:16:56 Taneb, ok you're my friend 12:17:05 oerjan is too old though 12:17:12 sad trombone 12:18:30 anyway 12:18:35 * Phantom_Hoover → campus 12:22:54 -!- Phantom_Hoover has quit (Ping timeout: 252 seconds). 12:32:35 -!- doesthiswork has quit (Quit: Leaving.). 12:36:37 -!- Sgeo has quit (Read error: Connection reset by peer). 12:59:07 -!- heroux has joined. 12:59:10 -!- MindlessDrone has joined. 13:01:53 -!- boily has joined. 13:02:02 -!- metasepia has joined. 13:05:59 -!- oerjan has quit (Quit: leaving). 13:15:48 good morning! 13:15:55 @tell oerjan good ørjanight! 13:15:55 Consider it noted. 13:16:14 bohily 13:21:45 tanello! 13:22:01 (or is it “tanellob”? I can never seem to conjugate your name properly.) 13:24:21 Well, I think this would be the vocative 13:24:56 And "Taneb"'s a name, so I think you'd decline it rather than conjugate it 13:25:43 indeed. 13:43:30 meanwhile, 1614 pages and still going strong. really, people flock over the pointlessest things these days... 13:45:46 -!- asie has quit (Quit: I'll probably come back in either 20 minutes or 8 hours.). 13:51:58 -!- ^v has joined. 14:04:57 -!- snuffeluffegus has joined. 14:09:09 -!- ^v has quit (Remote host closed the connection). 14:19:01 -!- snuffeluffegus has quit (Quit: Leaving). 14:22:16 -!- Taneb has quit (Quit: Leaving). 14:23:02 -!- metasepia has quit (Ping timeout: 240 seconds). 14:24:50 -!- boily has quit (Ping timeout: 264 seconds). 14:29:21 -!- boily has joined. 14:30:25 -!- metasepia has joined. 14:32:42 -!- carado_ has joined. 14:34:16 -!- asie has joined. 14:44:58 -!- mrhmouse has joined. 14:51:24 what are you reading, boily? 14:58:01 -!- nooodl has joined. 15:00:57 -!- ^v has joined. 15:05:00 mrhmouse: irregular check up on the OTT in the xkcd forums. 15:09:06 "off topic threads"? 15:09:36 the One True Thread, cf. xkcd 1190 “Time”. 15:11:42 Ah, I see. Very interesting! 15:31:53 -!- Taneb has joined. 15:32:15 I just got feedback on a programming formative assessment 15:32:55 My lecturer said that it was good, but I should take my time a bit, put more useful comments in, and more line breaks, and also re-read the question 15:33:03 And also put in tests 15:33:15 what did you mis-read in the question? 15:33:25 -!- asie has quit (Quit: I'll probably come back in either 20 minutes or 8 hours.). 15:34:22 Actually I wish more people would learn those other points (comments, line breaks, write tests first, and slow down) 15:34:33 kmc: one of the tasks was to write a script that takes a sentence and prints the total number of words and the average number of characters per word 15:34:58 http://youtu.be/CDVQvme5tb0 15:34:58 I wrote a function that just returned the average number of characters per word 15:35:20 "useful" comments is key... when you tell students to write lots of comments you get code like "int x = 3; // Declare an integer variable named x and set its initial value to 3" 15:35:37 kmc: and then they take that habit into the workplace... 15:36:24 kmc: also useful names! far too often do I see things like this: "int intX = 3; // set intX to 3" 15:36:34 kmc: my only comment was along the lines of "I like this function" 15:36:39 haha 15:36:40 useless prefixes madden me 15:37:01 (although it may have actually been a method, I'm not sure) 15:37:06 -!- variable has changed nick to trout. 15:37:19 kmc: mrhmouse: theil eventually learn 15:37:28 I don't mind stupid overcommenting from new coders 15:37:30 mrhmouse: the best kind of type system is one where you write the types every time and also you don't get any static checking... i'm pretty sure there's no better kind of type system 15:37:44 kmc: you mean C ? 15:38:05 Also I did something in three lines that I could have done in one 15:38:40 trout: well it's not so bad when the good kinds of comments are also present, yeah 15:39:01 the ones that explain 'how' and 'why' rather than the 'what' which is already part of the code 15:39:37 kmc: yeah, my lecturer specifically asked about the "why" in one case 15:39:48 but if the dictate is "lots of comments" you won't bother with those kind because they're harder to write and there will be few of them anyway 15:40:19 -!- doesthiswork has joined. 15:40:54 I had done something that was less efficient than the quickest thing matching specification but slightly more general 15:41:00 trout: I have coworkers who still do that, so I don't believe they ever learn 15:41:25 I kinda like codebases where most code has no comments but occasionally there's a 4 paragraph comment explaining some tricky shit 15:41:32 people will payattention :) 15:41:38 personally, I prefer static typing with type inference (a la D or Cobra) 15:41:52 kmc: I rarely comment at all, actually, except for the documentation comments 15:42:06 but that's because I rarely have a method that's more than five lines long. 15:46:21 I comment tricky, unusual, surprising or implicit stuff. I comment exceptions, and reasons I throw them. I comment expectations, workflow, and how you should manage resources' lifecycles. 15:47:45 Most of that I stick in documentation comments. For exceptions, I don't use comments (I just give a detailed exception message). I don't comment expectations or garauntees - those are done in the specifications and contracts. 15:48:39 Workflow is only documented if it's unexpected or unclear, and often I'll just reference what approach I'm taking ("this is the visitor pattern", etc) and why 15:49:24 -!- carado_ has quit (Quit: Leaving). 15:50:02 I... can't actually remember what grade I was given 15:50:17 I think it was a first with room for improvement 15:50:34 He said "Try to beat last year's best, which was 96%" 15:50:48 There's always room for improvement, no matter how good the code looks or how experienced the coder :) 15:50:59 Also, congrats on the 96%! 15:51:46 No, the 96% is my target, not my mark 15:53:34 -!- Sprocklem has joined. 16:00:40 -!- conehead_ has joined. 16:02:20 -!- conehead_ has changed nick to conehead. 16:03:04 -!- Taneb has quit (Quit: Page closed). 16:05:04 -!- Taneb has joined. 16:18:44 -!- Taneb has quit (Quit: INVESTIGATION). 16:21:29 mrhmouse: in a programming language that integrates those fancy features, of course comments become redundant. 16:22:06 (ô, how I wish Python had static typing) 16:24:24 * impomatic just wrote to Knuth to ask if he ever played Core War! :-) 16:24:47 -!- Bike has quit (Ping timeout: 268 seconds). 16:25:09 boily: Python is a dynamic language mate; you're asking to make an apple an orange ;) 16:25:45 mrhmouse: nothing less. besides, oranges taste good. 16:25:47 And for languages that don't integrate those "fancy features" (I'm guessing you mean contracts), I use a library that allows me to use them 16:26:00 -!- Taneb has joined. 16:26:02 -!- Bike has joined. 16:26:05 For example, with C# at work, we use SpecFlow. At home with CoffeeScript, I use Vows 16:26:34 It's a bit annoying to separate the specifications from the code, but it's better than nothing. 16:28:24 -!- ^v has quit (Quit: http://i.imgur.com/MHuW96t.gif). 16:28:47 -!- ^v has joined. 16:29:05 ruddy is written in CoffeeScript... I really should have written tests for him :P 16:29:06 i don't see why. 16:29:16 in that case, nevermind then 16:31:14 ruddy, have you met fungot? 16:31:14 Taneb: http://www.flame.org/jivera/ random/ fnord ( sic) 16:31:15 lol 16:31:31 * kmc tries to set up ruddy and fungot on a date 16:31:31 kmc: silicon castles http://www.cowlark.com/ fnord libcurl: http error ( 404?) 16:31:43 ruddy doesn't respond to /me yet.. need to fix that 16:31:44 ew? 16:33:04 ruddy..... 16:33:18 ruddy: why don't you respond? :( 16:33:19 lol 16:33:33 If ruddy can't figure out a suitable response, he just stays silent 16:33:33 I wouldn't know. I never underwent one. 16:33:54 ruddy: you never underwent what? 16:33:55 my spirit animal is a horsey 16:34:02 ruddy: oh, right, that. 16:34:02 I saw it too. 16:34:28 pretty sure ruddy's spirit animal is fungot 16:34:28 what? 16:34:29 mrhmouse: aren't fnord those funny fnord tiny pachyderms that live on a small bf interpreter ( without very much bf fnord). it's not related to " normal" 16:34:57 kmc: some people here tried matchmaking ruddy and fungot, with no avail. 16:34:57 boily: it is often confusing for new u-' 16:34:57 2am :P 16:35:25 Yeah, you'd have to get fungot to say its name for that to even have a chance. 16:35:25 mrhmouse: even solaris would be better to specify it on each function call 16:35:26 confusing bot on bot action in the early morning? oooooh :D 16:35:48 And even then, ruddy would have to pick a response that included a name placeholder. 16:35:48 but produces a function on-the-fly at startup. sorry, this is tedious. http://62.167.150.30/ acm100.c of 16:36:15 -!- Bike has quit (Ping timeout: 272 seconds). 16:39:06 fungot: tiny pachyderms living on small bf interpreters..? 16:39:06 FireFly: i wanted to make it work in msg? i don't 16:39:11 ^echo ruddy hi how are you? 16:39:11 ruddy hi how are you? ruddy hi how are you? 16:39:11 ohnoi'mfallingover! 16:39:12 your IP is showing 16:39:25 ruddy is quite rude 16:39:25 ok, I guess I should have played the game in order to understand what is going on. 16:39:36 ruddy: the game of love? 16:39:36 I think the right word may have been aesthetic 16:39:42 ruddy: oh. 16:39:43 [-[-[-]]] e.g. 16:40:01 That's certainly.. aesthetically pleasing 16:40:49 and unless a fungottian bot, he actually balances his brackets. 16:40:49 boily: i just clicked through links." :) is it possible make it print 10 first in a series of 16:42:54 -!- Bike has joined. 16:49:39 -!- Bike has quit (Ping timeout: 260 seconds). 16:50:15 -!- Taneb has quit (Ping timeout: 250 seconds). 16:52:06 -!- AnotherTest has joined. 17:01:05 yeah, ruddy is just an echo bot. 17:01:06 they started adding IEEE conformance only recently, for people who wanted to do scientific computations on them 17:01:33 I intend to have it understand a subset of English at some point, so that it can munge messages together 17:08:08 -!- Bike has joined. 17:09:14 -!- Taneb has joined. 17:21:37 -!- carado has quit (Quit: Leaving). 17:21:59 -!- carado has joined. 17:33:20 boily: Won't you stop with the balanced parentheses already what kind of balanced paren fascist pig you are aaagagagaga 17:35:58 ^ignore 17:35:59 ^(EgoBot|HackEgo|toBogE|Sparkbot|optbot|lambdabot|oonbotti.*|metasepia|jconn)! 17:36:08 ^ignore ^(EgoBot|HackEgo|toBogE|Sparkbot|optbot|lambdabot|oonbotti.*|metasepia|jconn|ruddy)! 17:36:08 OK. 17:36:08 ^(Frooxius|conehead|toBogE|Sparkbot|optbot|ruddy|oonbotti.*|fizzie|jconn)! 17:36:19 well done, fizzie 17:36:35 For the record, you can get fungot to say anything you want, with ^bf/^ul(/^str). 17:36:36 fizzie: you wouldn't get much out of multi-processor boards. especially on machines with finite memorys of... a python love story looks rather like she of the magic compiler chip. 17:37:10 (I don't remember a Frooxius or a conehead at all.) 17:37:19 (I'm not a bot) 17:37:55 Huh? Oo 17:37:58 ruddy is just replacing names at random, and he stole your (fizzie) "response" to fungot 17:37:59 mrhmouse: i understand the way kawa works. the second book, soo...... you are going to support it 17:37:59 erm 17:38:14 Oh, there's some mungling in there already. 17:38:42 Yes, it replaces names with the currently active users to maintain an appearance of conversation 17:39:11 In most cases there are only one or two names to replace, but you gave it a huge list to use with that line to fungot 17:39:11 mrhmouse: like, the first thing you notice is that emacs and the shell 17:39:39 -!- Slereahphone has joined. 17:41:59 * FireFly hands conehead some botsnack 17:42:42 `buttsnack 17:42:44 ewww 17:53:28 -!- Slereahphone has quit (Remote host closed the connection). 17:55:55 -!- Slereahphone has joined. 18:00:29 -!- Bike has quit (Ping timeout: 272 seconds). 18:01:48 -!- nooodl has quit (Ping timeout: 244 seconds). 18:07:28 -!- Bike has joined. 18:17:10 -!- asie has joined. 18:22:50 http://steamcommunity.com/sharedfiles/filedetails/?id=195142868 18:34:33 -!- Sprocklem has quit (Ping timeout: 265 seconds). 18:34:38 What are you playing on, Imax?! 18:38:34 gee, with a resolution to size ratio the same as my netbook, that would be ten million cm across 18:39:03 which netbook? 18:39:12 some asus crap i got a year ago 18:39:17 ah 18:39:46 i have a sony vaio p and i am looking for some kind of successor, but i didn't find one yet 18:39:56 i mostly got the cheapest one i could find 18:43:35 -!- conehead has quit (Quit: Computer has gone to sleep.). 18:44:15 looks like imax is 10000×7000, so 18:44:27 back from lunch and fizzie aaagagagagas me. 18:44:39 Bike: pixels? 18:45:11 yeah. source: random crap on wikipedia i might be misinterpreting 18:49:17 hello, math ... "Most IMAX theatres use two 4000x2000 reolution projectors to produce an 8000x4000 resolution image." 18:50:21 wait, are the projectors overlapping at all? 18:50:33 what the hell? 18:50:47 where is this from? 18:51:44 http://answers.yahoo.com/question/index?qid=20091101105136AAbmCcJ 18:51:56 another random internet page 18:52:13 well, i don't expect anything good from yahoo anwers 18:53:17 -!- oerjan has joined. 18:54:00 my most favouritest answer is the first one on http://stackoverflow.com/questions/1732348/regex-match-open-tags-except-xhtml-self-contained-tags 18:54:15 `? hello 18:54:18 hello hello hello, what's all this then? 18:55:06 more funny numbers ... http://www.celco.com/FormatResolutionTable4K.asp 18:55:57 well, that's everyone's favorite, boily. 18:56:17 -!- asie has quit (Quit: I'll probably come back in either 20 minutes or 8 hours.). 18:56:25 it's not mine 18:56:38 -!- asie has joined. 18:56:42 "bla bla random rant about regular languages" 18:56:58 -!- asie has quit (Client Quit). 18:57:09 myname: you are not everyone, then. 18:57:27 that's good! 18:57:48 hoilyssä 18:59:04 boerjan après-midi. 19:00:08 oerjan: inessive??? 19:01:53 legjóilybb estét 19:02:35 wait, no ´ in superlative, sorry 19:02:54 the boilyest evening? well, I'm flattered. 19:03:03 also, you're learning hungarian? that's neat. 19:03:24 no, i picked up a little years ago 19:03:40 How many languages do you know anyway? 19:03:55 define "know"? 19:04:02 define "language"? 19:04:33 fizzie: is a set datastructure that just has 'add an element' and membership testing going to be something i can get out of matlab or do i have to do it myself somehow 19:05:27 -!- MindlessDrone has quit (Quit: MindlessDrone). 19:05:42 i'd consider myself fluent in english, norwegian, and by extension near-fluent in swedish and danish. i can probably get by in german with some effort. everything else is on a lower level, including the french i've actually had lessons in. 19:06:33 (it's been a long time since i sincerely tried getting by in german, though.) 19:09:13 now if you want what i've dabbled through a few grammar or textbook chapters in, you've got italian, latin, czech and hungarian. and esperanto. 19:09:24 All right 19:10:16 no quenya nor any sindarin at all? 19:10:40 loooks like the matlab cas (why does matlab have a cas) has sets, but they let you do weird optionsn like "indexing"... 19:11:14 boily: i don't remember any of their grammar to speak of, although i _do_ recall visiting the aldalambion web page. 19:11:41 *ardalambion 19:12:25 -!- asie has joined. 19:13:01 when one visits ardalambion, one remembers the backgrounds. 19:16:45 -!- Bike has quit (Quit: Reconnecting). 19:17:04 -!- Bike has joined. 19:17:13 -!- Slereah has joined. 19:17:30 hmm, doesn't seem like a very memorable background 19:18:35 and in retrospect, maybe I shouldn't have cleaned up whatever it was that held my mouse pad stuck to the desk 19:23:31 -!- Slereahphone has quit (Quit: Colloquy for iPhone - http://colloquy.mobi). 19:26:36 Bike: In a modern-enough MATLAB (I don't know details), you can use http://www.mathworks.se/help/matlab/map-containers.html 19:26:43 olsner: backgrounds, in the pluralo-chromatic sense of the term. view the pages. bask in the colours. 19:27:00 Bike: There's also a longstanding tradition of using structs as impromptu hashmaps (and hashsets), but that comes with some rather bad gotchas related to field name restrictions and so on. 19:27:25 urgh 19:27:26 Bike: (And of course only works for string keys, unlike containers.Map. (Also, it's slower.)) 19:27:46 i think i might just use a bitvector, this should probably be parallizable in the future anyway 19:27:58 (Last fact not guaranteed to be true.) 19:28:08 speed is what i was going for, right now the "set" is a vector and an element is added with vec(end+1) = element 19:28:19 which like...you know. 19:28:36 so it isn't actually a set 19:29:26 it's only used as a set. 19:29:29 I think a containers.Map (with just 'true's as values) might not be too bad. (Or, of course, some sort of bitvector if the keys have a feasible range for that.) 19:29:38 adding an element and finding if something is in it are the only things done with it. 19:29:49 yeah, i'll have to check the range but i think it should be fine 19:31:40 -!- conehead has joined. 19:33:22 The Map is probably the fastest built-in way for generic hashmaps, and I believe was quite the welcomed addition, thanks to the "struct hack" (no relation to C's struct hack) being so horrible. 19:33:32 Apparently it's a 2008b feature. 19:33:38 i'm on 2009b, i think 19:33:56 i think i'm going to make a hacky tool i can use to run the program and get a graphed distribution of the values of some variable 19:34:12 That's not terribly new. But not as bad as, say, 7.x would be. 19:35:01 I guess theoretically R2009b is still also a 7.x. But I mean something like R14. 19:35:05 Bike: that's the one i have. because that's the year i stole it :P 19:35:22 I'm not sure what's the deal with the version/release dichotomy. 19:35:45 also, hi boily 19:35:56 i just want it to work, man, no time 4 thinking 19:36:00 qhintopia! 19:37:01 yes ok good 19:37:13 It goes 6.0 - R12, 6.1 - R12.1, 6.5 - R13, 7 - R14, 7.1 - R14SP3, then 7.2, 7.3, ..., 7.14 are R2006a, R2006b, ..., R2012a, and then 8, 8.1 and 8.2 are the newest R2012b, R2013a and R2013b. 19:37:39 are you doing anything 19:37:41 fantastic. 19:37:56 quintopia: who? what? when? 19:38:01 you 19:38:05 now 19:38:15 -!- AnotherTest has quit (Ping timeout: 358 seconds). 19:39:00 eating gummy bears as a mean to not fall asleep during a SCRUM training. 19:40:36 scrum is so irritating.. In concept, it sounds great. Once or twice a week, it would be great 19:40:51 http://sprunge.us/IYPd look at all that MATLAB 19:41:07 but every single morning.. it's just an interruption where the whole team nods and says "yep, I'm still working on that thing from yesterday" 19:41:15 (Tab completion.) 19:41:50 mrhmouse: come working for us, then! you'd feel right at home. 19:42:15 fizzie: well now i feel better about my work setup. 19:42:47 boily: aren't you in canadia? 19:43:10 mrhmouse: I am at canada. 19:43:40 I suppose I could get there via ICBM 19:43:50 @tell zzo38 I owe you some royalties for the “at canada” brand. 19:43:51 Consider it noted. 19:44:17 mrhmouse: Québec is lovely this time of the year! it's very warm here! 19:44:21 ~metar CYUL 19:44:22 CYUL 151900Z 23016G23KT 30SM FEW070 BKN080 BKN240 10/M01 A3003 RMK AC2AC4CI1 CI TR SLP171 19:44:44 Bike: That's just one of them. In another, I have to say (e.g.) "module load matlab/r2013a", and in yet another there's just the three latest in the path. 19:44:56 I'm from the south-eastern US.. I think I would freeze to death in a Canadian heat wave 19:45:51 -!- Sprocklem has joined. 19:46:32 -!- mrhmouse has quit (Quit: Windows updates...). 19:57:26 -!- Taneb has quit (Read error: Operation timed out). 19:58:03 -!- boily has quit (Quit: Poulet!). 19:58:10 -!- boily has joined. 19:59:11 -!- mrhmouse has joined. 20:03:13 boily: what is scrum 20:04:59 btw "g major" is the best youtube meme in a while 20:05:54 -!- Bike has quit (Ping timeout: 265 seconds). 20:08:20 quintopia: an Agile Programming Method. slightly less bullshitty than the other methods. 20:08:31 what is g major? 20:09:37 take a music video, spectrally filter all frequencies not in the key of g major, reverse the video, publish to youtube 20:09:53 here i the most terrifying one: http://www.youtube.com/watch?v=45lB-fyB87Y 20:10:13 -!- Taneb has joined. 20:10:51 I can't watch it now. it'll have to wait, but I think I'll be properly terrified tonight by that grotesque thing. 20:12:09 -!- yorick_ has joined. 20:15:23 -!- yorick has quit (Ping timeout: 272 seconds). 20:16:11 -!- Bike has joined. 20:19:19 -!- ^v has quit (Quit: http://i.imgur.com/MHuW96t.gif). 20:24:45 -!- yorick_ has changed nick to yorick. 20:25:37 boily: the key word in "slightly less bullshitty" is "slightly" 20:26:15 mrhmouse: it is physically non-null. 20:27:28 I don't follow 20:31:19 “it”, meaning the difference. 20:31:39 I may have subtly left out some important context. my brain is not in functioning order at the moment. 20:37:18 -!- boily has quit (Quit: Poulet!). 20:37:26 -!- boily has joined. 20:44:09 did you patch your brain 20:45:16 * boily drinks tea. delicious tea. it tastes good. 20:45:38 boily: find me some delicious tea that tastes bad 20:45:47 (is it david's tea?) 20:46:16 no. some unknown oolong sold to me by an enthusiastic guy in Montréal's Chinatown. 20:46:28 :D 20:46:34 how often you gp there 20:46:36 go 20:46:40 try passing it through a civet 20:47:26 oerjan: musky oolong? 20:47:30 once every 2 months, I'd say. last time I blew up about 70$ on multiple teas. 20:47:38 oerjan: cha luwak? 20:48:49 boily: i don't think that "up" belongs there, unless you have a youtube link to prove it. 20:49:23 oerjan: don't destroy my dreams 20:49:33 oerjan: don't destroy my dreamy explosions. 20:50:08 explosive dreams 20:50:41 -!- Sprocklem has quit (Ping timeout: 243 seconds). 21:07:00 -!- Sprocklem has joined. 21:18:13 -!- ^v has joined. 21:19:40 Tea is good 21:19:54 * FireFly sips some earl grey 21:20:33 -!- nooodl has joined. 21:20:45 I think the biggest shock for me when I moved to "the big city" was the tea 21:20:59 where I grew up we had two kinds of tea: sweet and unsweet 21:22:17 You're giving me flashbacks to when I put sugar in the tea.. 21:23:02 putting sugar in tea after it's brewed just isn't the same as sweet tea 21:25:03 lately, I started brewing Hong-Kong style milk tea at home. 21:37:23 -!- Sprocklem has quit (Remote host closed the connection). 21:37:24 -!- ^v has quit (Quit: http://i.imgur.com/MHuW96t.gif). 21:37:51 -!- ^v has joined. 21:42:39 How can I modify a transformation matrix so it treats a different point as the origin 21:43:02 Apply a translation to it 21:43:12 Hmm 21:43:19 I'm not thinking about this right, hang on 21:44:25 -!- Bike has quit (Ping timeout: 272 seconds). 21:53:27 -!- sebbu has quit (Read error: Connection reset by peer). 21:53:59 -!- sebbu has joined. 21:54:41 -!- sebbu has quit (Changing host). 21:54:41 -!- sebbu has joined. 21:55:46 -!- Bike has joined. 21:58:35 * boily waits for Taneb. 22:03:41 Right, I have something with its own origin (x1, y1) and a transformation matrix applied to it assuming that origin, M 22:04:25 wish i had my own origin 22:04:26 Then I have a secondary origin (x2, y2), and a transformation matrix applied around that origin, N 22:06:29 To begin with, (x1, y1) is gonna be transformed by N 22:09:57 I need some paper... 22:10:26 I don't quite understand what "transformation matrix applied around an origin" means, given that it's just a matrix. But you could certainly first translate point (x2, y2) to (x1, y1), apply your thing, and then translate (x1, y1) back to (x2, y2), if that's the sort of thing you had in mind. 22:10:34 Taneb : There are matrices you can use for translations 22:10:57 I need to get this clear in my own mind before I ask for help... 22:11:13 fizzie: he probably means a rotation around that point or whatnot 22:11:42 Who knows, it could be a skew or a conformal transformation! 22:11:58 -!- metasepia has quit (Remote host closed the connection). 22:12:14 -!- boily has quit (Quit: SLEEPY CHICKEN!). 22:12:36 Well, that'd just be T1 N T2, or so on. 22:13:07 right. 22:13:25 (Or T^-1 N T.) 22:15:16 Though beware 22:15:29 You have to change your rotation matrix if you want to apply a translation 22:15:55 On a n dimensional vector, you need (n+1)x(n+1) translation matrices 22:16:11 And the vector becomes (x1, x2, x3, ..., xn, 1) 22:16:17 I was sort of assuming homogenous coordinates by default. 22:16:34 also taneb pretyt much specified this is all on the plane. 22:16:48 Well in that case the translation matrix is 3x3 22:16:52 Yeah, it's on a plane 22:16:57 And the vector transforms to (x,y,1) 22:17:46 Quite often you see those as 2x3 matrices with an implicit [0 0 1] at the bottom. 22:18:43 (Like in the SVG "matrix(a b c d e f)" transform attribute.) 22:18:52 good to see you are doing affine without me 22:19:12 oerjan: It's affine day for it. 22:23:41 -!- asie has quit (Quit: I'll probably come back in either 20 minutes or 8 hours.). 22:23:52 -!- updog has quit (Ping timeout: 264 seconds). 22:24:11 -!- Oj742 has joined. 22:36:51 -!- Bike has quit (Ping timeout: 260 seconds). 22:47:05 -!- Bike has joined. 22:59:22 -!- asie has joined. 23:00:50 -!- mrhmouse has quit (Quit: Leaving.). 23:01:46 http://vimeo.com/79179138 I'm sure this is old news, but it was the fanciest. 23:02:15 -!- Bike has quit (Ping timeout: 240 seconds). 23:02:45 "3 days ago" so in Internet time that's like six generations. 23:09:20 fizzie: cool. i hadn't seen it! 23:12:45 Hey, cool 23:13:08 (I'd seen pictures of that, but not the actual video) 23:13:35 so i finished my SELECT. interpreter. would someone like to test it? would someone like to host it so i can change the category to Implemented? 23:14:42 -!- nisstyre has joined. 23:14:52 i guess i can host it 23:15:02 but no guarantees i won't go stale 23:16:30 Can't you just put it into a gist or something? 23:18:23 Guys 23:18:30 -!- carado has quit (Ping timeout: 252 seconds). 23:18:30 Why are there "standard libraries" 23:18:41 Why not make them part of the language if they are standard 23:18:55 err, that's what standard library means? 23:19:16 Well no, you still need to call them up 23:19:26 And they are themselves written in the language itself 23:20:04 Not necessarily? 23:20:23 Sure, but in the case they are, let's say 23:20:38 I am wondering why not just make them part of the language itself 23:20:43 um 23:20:50 because they aren't? 23:20:57 I'm not sure if I see the distinction 23:21:22 "utilities that people use a lot" doesn't necessarily mean "a bunch of extra code you definitely want linked into your app" 23:22:09 Well if it's part of the language it wouldn't be extra code technically 23:22:09 I think that's called "the PHP model", where everything in the "standard library" is available in your global namespace by default. 23:22:58 (The C standard library certainly is part of the language, FWIW.) 23:23:21 -!- Phantom_Hoover has joined. 23:23:33 fizzie: meaning it is all inside the compiler somewhere? 23:23:50 ready to be tacked on to code without having to import? 23:23:53 I don't think that's what "part of the language" means. 23:24:00 well 23:24:07 i don't know what Slereah means either 23:24:21 No matter I guess 23:24:23 It is late 23:24:26 I should go to bed 23:24:33 so the SELECT. interpreter is here: http://rutteric.com/files/select.py 23:25:27 -!- prooftechnique has joined. 23:25:47 For small enough standard libraries, the "PHP model" makes sense, I think 23:26:03 For PHP, I'm not terribly sure it does. 23:27:33 What do you expect 23:27:38 It has pee in the name 23:27:38 What's "the PHP model"? Just pile stuff on whenever someone has an idea? 23:27:46 Slereah: TWICE 23:27:59 prooftechnique: I think that's called "the PHP model", where everything in the "standard library" is available in your global namespace by default. 23:28:00 More, if you count the recursive name 23:28:13 fizzie: Sorry, I just logged on 23:28:27 Yes, I saw that, that's why I pasted it. It wasn't an accusation or anything. 23:28:35 Haha, okay 23:28:47 I should get in the habit of checking the logs, though 23:30:34 THE LOGS BECKON YOU 23:31:16 -!- asie has quit (Quit: I'll probably come back in either 20 minutes or 8 hours.). 23:31:25 fizzie: PHP's isn't small though.. 23:31:32 I was thinking more along the lines of Scheme or Lua 23:32:47 ...have you read your SICP today? 23:33:44 You sound like a Sussman's Witness 23:34:11 Or a /prog/rammer D: 23:34:12 The horror 23:34:13 FireFly: R6RS and R7RS both have a module system. (Then again, they're larger.) 23:39:28 I'm finding this Windows 8(.1) thing of having "desktop" things and "apps" things very confusing. "Apps" don't show up in the task bar, but they do show up in the alt-tab list. And they have completely different interaction paradigm (that's the word, right?) that's almost like a tiling WM. E.g. to make the built-in PDF reader visible while having something else open on the same monitor, I had ... 23:39:34 ... to split the screen so that one half is the PDF viewer, and the other is a half-wide desktop. It looks very strange. 23:40:13 That sounds unpleasant 23:40:32 a bit disappointing that they went and invented the whole new thing and then end up having to keep the old thing around anyway 23:40:59 I think the idea is that the old thing is just a single "app", but that's kind of ridiculous, because that's where just about everything is happening. 23:41:11 (So far the PDF reader is probably the only new thing I've used.) 23:41:11 I guess the real reason is that the new thing is unusable 23:41:42 Also the corner-based navigation is kinda clunky with multiple screens. 23:41:59 There's stops at the corners, so it can be used, but it's still clunky. 23:43:00 i agree with all of the above 23:43:14 the only think i truly enjoy about windows 8 is the app store 23:43:45 totally engineering the UI around touchscreens is just annoying to a diehard keyboardist like me 23:44:00 I can't figure out how to use the application switcher. 23:44:37 There's a top-left-corner thing, but it keeps switching just one half of the screen, and there's no list of what's running. 23:44:49 I'm sure there's some way, I just can't figure it out. 23:45:05 Possibly you're meant to swipe from somewhere, but I don't know how to do that with a mouse. 23:46:29 Ah, left-corner-move (but not click), and then move cursor down to the small rectangles that are poking out of the edge slide out a list. 23:46:30 you have a separate sits-on-your-desk mouse? 23:46:55 Um. Do most desktops not have one? 23:47:12 This is a regular computer I'm using. 23:47:15 most laptops have touchpads, and windows 8 was LAPTOP-ENGINEERED 23:47:37 Wasn't it TOUCHSCREEN-ENGINEERED? 23:47:42 I've got Windows 8.1 on the desktop, and Windows 7 on the laptop. 23:47:43 The world is all about touch these days. 23:50:20 "Touch one another!", like a Finnish TV personality from the early 90s used to say. 23:50:35 shachaf: which is why modern laptops have touchscreens 23:50:37 (That's kind of a bad translation of "Kosketelkaa toisianne!", arguably.) 23:51:10 (Guess it's still better than GT's "kosketelkaa each other".) 23:51:20 i assume he meant touch as in "touching" the adjective and not touch as in "fondle"? 23:51:40 No, it's the latter. 23:51:46 oh 23:51:49 well 23:52:06 It's very close to "fondle" in meaning, in fact. 23:52:24 http://en.wikipedia.org/wiki/Frank_Pappa_Show but it's just a stub. The .fi article knows more, but is in Finnish. 23:52:31 well then 23:52:36 i guess he was popular 23:53:19 [[ The program is remembered, among other things, -- Frank Papa fly the phrases "Kosketelkaa each other!", "Relentless go!" and "Bailatkaa severely". ]] 23:53:35 Relentless go! 23:53:37 fizzie: perhaps "hug" is closer but with fewer unfortunate associations to americans? 23:53:45 *close enough 23:54:01 Maybe the Finns are just a more tactile and accepting culture 23:54:17 Or were, in the 90s 23:54:25 prooftechnique: that seems like exactly the opposite of my stereotype of finns. 23:54:27 oerjan: Mmmmaybe, but "kosketella" really has some of those unfortunate associations in Finnish too. I think it's just a thing. 23:57:32 but maybe i've misunderstood, and finns are all about touching as long as you don't speak while doing it. 23:59:35 and as long as you don't tell foreigners, stereotypes to uphold etc 23:59:37 You may only speak to whisper "we shall never speak of this" 2013-11-16: 00:00:07 arthur, you are an evil duck http://www.sheldoncomics.com/archive/131115.html 00:01:32 oerjan: As far as I know, the canonical stereotype involves no touching either. See http://depressingfinland.tumblr.com/post/65617168839/chibisuz-depressingfinland-234937289-bus 00:02:25 "it’s okay if you don’t pronounce it perfectly right because the only reason someone would talk to strangers in public transport is to ask them to move, so they will get the hint" very true 00:02:47 you can't really mispronounce a grunt either 00:03:01 fizzie: what's a "standing up seat" 00:03:43 oerjan: A paradox. (I think a standing place was intended.) 00:03:56 We don't have seats you stand on in buses, no. 00:04:08 the rule in norway is similar but we do _not_ usually take standing places before starting to sit next to each other :P 00:04:21 well, some probably do, but it's not a rule. 00:05:04 Yes, well, I think maybe about half the people in here don't, either. (Could be more, could be less.) So it's not as strict rule as the no-talking one, or the others. 00:06:40 (Also depends on distance and such.) 00:07:05 mä jään tääs of course consists solely of the one finnish vowel i find awkward to pronounce. 00:07:11 -!- Bike has joined. 00:07:43 despite it being nominally in norwegian too 00:09:31 Älä rääkkää sitä kääkkää! En rääkkääkään. 00:09:57 i think my brain basically is prejudiced with "it's not in front of an r, use an "e" instead you idiot!" 00:10:32 can someone do it in IPA plox 00:10:43 I'd consider it weird to stand on the bus if there are free seats even if they are no double free seats 00:11:10 quintopia: ä = [æ] afaik 00:11:37 what about j? 00:11:49 I keep mentally hearing all the 'ä's in, say, LOTR (Eärendil) as the Finnish ä, which is so wrong. 00:11:49 [j] 00:13:34 otoh it does avoid the difficult problem of deciding which person on the bus is least scary to sit next to 00:13:36 google cannot translate rääkkääkään, but still suggests it should be rääkkääkkään (which it cannot translate either) 00:14:09 Does it suggest rääkkääkkääkkään or rääkkääkään for rääkkääkkään? 00:14:15 no. 00:14:44 oerjan: i cannot seem to tell the difference between æ and ɛ...there's just no reason to ever get that kind of find tongue control in english 00:14:48 *fine 00:15:07 "(enclitic, appended to a verb form) indicates confirmation of not doing something, e.g. if someone doubts it, or, when someone is more or less surprised at an occurrence, indicates the reason why some thing was not successful – which is by not doing that something 00:15:11 (Minä) en syönytkään eilen jäätelöä. 00:15:13 But I didn't eat ice-cream yesterday." 00:15:24 It's just that. 00:15:50 The "confirmation" one. 00:16:26 fizzie: it doesn't know rääkkää or kääkkää either. 00:16:49 How about "rääkätä"? 00:17:04 Isn't that a pokemon 00:17:16 "torment" 00:17:26 That's right. 00:18:27 And kääkkä is... something like a pejorative term for an old person. 00:19:05 There's a proper English word for it, I'm sure. 00:19:13 Crone? 00:19:22 i think that only applies to women 00:20:24 I guess kääkkä is gender-neutral, maybe slightly biased towards women. 00:20:42 also i think crone is sort of archaic? 00:20:47 maybe "hag". 00:21:43 which somehow needs "old" in front, i suspect 00:22:09 oerjan: are you thinking of "anacrone"? 00:22:23 -!- Sprocklem has joined. 00:22:41 NO. 00:22:42 http://en.m.wiktionary.org/wiki/crone includes "kääkkä" as the Finnish translation. 00:24:19 "As a stock character in fairy or folk tale, the hag shares characteristics with the crone, and the two words are sometimes used as if interchangeable." 00:24:59 Is there such thing as a true synonym? 00:25:20 A word that is perfectly interchangable for another? 00:25:20 "The word "crone" is a less common synonym for "old woman," and is more likely to appear in reference to traditional narratives than in contemporary everyday usage." 00:25:39 "Using the word "hag" to translate terms found in non-English (or non-modern English) is contentious, since use of the word is often associated with a misogynistic attitude." 00:25:56 i'd say hag seems more like what you are implying. 00:27:00 Perhags. 00:27:05 oerjan: why do you shout so much 00:27:37 BECAUSE YOU'RE ALL THE WAY ON ANOTHER CONTINENT 00:28:01 AND POSSIBLY HARD OF HEARING 00:28:32 -!- zzo38 has joined. 00:31:41 Taneb: i can think of a few examples, i'm sure. for words that have lots of synonyms, sometimes there are several subsets which also have the same connotations 00:31:47 -!- Sgeo has joined. 00:32:42 for instance, i can't see any situation where ill-at-ease and uncomfortable aren't completely swappable 00:32:58 When you're talking about a sofa? 00:33:09 http://depressingfinland.tumblr.com/post/66945321786/i-love-your-blog-i-am-a-finnophile-it-all-came-about 00:33:11 true 00:33:15 What if your 'i' key is broken? 00:33:17 bad example 00:33:20 i am not sure this person realises that we have a word for that in english also 00:33:21 need to think harder 00:34:01 "bloody freezing"? 00:34:03 Taneb: how about "delay" and "wait"? 00:34:16 reallyfuckingcold 00:34:22 quintopia, you wouldn't delay for someone 00:34:33 why not 00:34:40 Well, I wouldn't 00:34:52 Also you wouldn't want someone in a restaurant to delay on you 00:35:23 -!- nisstyre has quit (Quit: Leaving). 00:35:33 Taneb: shore and coast? 00:35:36 And I see "wait" as having much friendlier connoctations 00:35:51 oh wait 00:35:53 You wouldn't wait a delivery, I think. (Though you might wait for one that's been delayedf.) 00:35:55 both of those are also verbs 00:36:13 but i think the noun forms are identical 00:37:47 "Noun 00:37:47 shore (plural shores) 00:37:47 A prop or strut supporting the weight or flooring above it. 00:37:49 The shores stayed upright during the earthquake." 00:37:55 Not a coast. 00:38:17 meh 00:38:24 Taneb: how about miasmic and miasmal 00:38:37 It is a p. tricky task T. has set. 00:39:00 t. dat 00:39:00 quintopia, I imagine miasmic referring to a substance and miasmal as to an environment, but maybe that's just me 00:39:10 -!- glogbackup has quit (Remote host closed the connection). 00:39:28 Taneb: everyone and everybody 00:39:41 hmm, is pakkanen a specific word for "below 0"? afaik none of the swedish words for cold have any specific temperature ranges 00:39:42 Ø. agrees, I see. 00:40:00 quintopia, hmm, good one 00:40:22 olsner: It does mean "freezing". 00:40:51 -!- glogbackup has joined. 00:41:36 "freezing" is also a generic word for being/feeling cold 00:42:58 olsner: Well, the sense of freezing that means a temperature where water freezes. 00:43:01 -!- oerjan has set topic: The channel of the chimæric hellos | The most corum, clargoint chait you could ever loofefl your slance in. | Magnus!! | Koirammekokaan ei lennä? :( | https://dl.dropboxusercontent.com/u/2023808/wisdom.pdf | logs: http://codu.org/logs/_esoteric/ or http://tunes.org/~nef/logs/esoteric/. 00:43:43 It's not "pakkanen" if it's above zero, that's non-negotiable. 00:44:21 fizzie: what if you are at abnormally high pressures? 00:44:30 hm doesn't swedish have a word like "kuldegrader" 00:45:22 "Pakkassen puolella" and "pakkasasteita" are both also real expressions. 00:45:46 q.: I don't know, actually. 00:48:23 It doesn't change all that much, right? Not like the boiling point. 00:48:56 (Matter. Sigh. What's it good for, anyway?) 00:49:07 -!- Taneb has quit (Quit: Leaving). 00:50:56 -!- APott has joined. 00:51:08 Hello! 00:51:20 oerjan: hm, we do have "minus degrees" (which doesn't mean that it's considered cold) or possibly "degrees cold" (but sometimes +20 is "cold"...) 00:51:36 but those are like phrases for pronouncing temperatures 00:51:50 Has anyone here ever built an interpreter? I have a few questions 00:52:17 Of a normal language, may be a bit off topic 00:52:41 lol off topic 00:52:42 but yeah sure 00:53:13 Alright great 00:53:27 I've built a basic one before but I'm working on one right now 00:53:42 I have always never really understood the best way to construct an AST 00:54:02 specifically how meta data should be stored, and the different node types are determined 00:54:11 or the most proper way 00:54:13 sounds like a job for a parser generator 00:54:27 This is not what I want 00:54:38 I find handwriting fun and actually a bit simpler than writing a grammar 00:54:56 I know how to create an AST I just don't know the best methods for it 00:55:07 i guess you hvae to write a few parsers in order to learn to hate doing it yourself. 00:55:40 So you can't answer my question? xD 00:56:12 well, to specify an AST the usual way basically amounts to an algebraic data structure. 00:57:23 like you might have Form = Conditional Form Form Form | Call Form Form | Lambda Symbol Form | Access Symbol for a simple lambda calculus with ifs. 00:57:59 that means, form is either a "conditional" with three subforms (for the condition, the "then", and the "else"), a call with two subforms (the callee and the argument), a lambda, or a variable. 00:58:21 yes 00:58:35 and uh... that's basically it? 00:58:38 how would I store metd data though? 00:58:43 or should I*? 00:58:45 What metadata? 00:58:49 Like names of things and stuff 00:58:58 Names of things... and stuff. 00:59:03 What? 00:59:05 -!- Oj742 has quit (Ping timeout: 268 seconds). 00:59:10 For example 00:59:53 if I'm parsing a javascript variable definition or something: "var name;" in the node how/where would be the best place to store "name"? 01:00:12 ... 01:00:27 Then in this AST you have a syntax type like VarDecl [Symbol]. 01:00:41 I feel like I'm missing something huge or frustrating you, or both. 01:01:35 The whole point of this algebraic thing is you just have a struct definition for every type of syntactic construct, basically. 01:01:48 Symbol is where the symbol is stored 01:01:55 data Expr a = Bound Nat a | Lambda (Expr a) a | App (Expr a) (Expr a) a 01:01:59 I understand this, but what confused me is how to structure them for interpretation later on 01:02:40 in the structure itself 01:02:41 i don't think you understand this. 01:02:48 Mainly, how do I keep these types together in the tree structure. I have them all extend the root AST struct 01:02:51 it's a tree 01:02:56 I know this 01:02:57 oh 01:03:02 Jafet: Pft, arbitrary Nats. 01:03:05 I know this, let me explain what I'im gertting aty 01:03:13 the tree is based on the grammar 01:03:18 Yes 01:03:18 Whatever, ASTs are overrated. 01:03:32 @let eval = let e s@(_:'\\':v:'.':l)=let(x,')':t)=e$d l in(take 4 s++x++")",t);e('(':s)=let(x,t)=e s;(y,')':u)=e$d t in(a x y,u);e s=splitAt 1$d s;d=snd.span(==' ');a(_:'\\':v:_:l)s=let f x|x==v=s|1>0=[x]in fst.e$init l>>=f;a f x='(':f++" "++x++")" in e 01:03:34 Defined. 01:03:37 so an expression might have subexpressions, which would eb its children in the AST 01:03:40 get a job taneb 01:03:57 jafet 01:04:00 god why do i confuse you 01:04:00 I don't even know what the hell that is 01:04:14 jafet's thing is humorous if you're a goddamn nerd and we're not goddamn nerds here 01:04:26 the only things that are children of root are things that the start symbol could produce in the grammar 01:04:34 yes I know 01:04:47 I haven't finished my explanation but yet I'm hearing obvious answers to questions not asked 01:05:02 seeing* 01:05:26 okay. i'll give you a few minutes to narrow your question down 01:05:39 thanks 01:07:17 Goddamn bikes 01:07:22 So I have a struct named AST. I have others for each language construct that extend this AST struct. Each struct has a property which determines what it represents. Each has an array for more AST structs, for the tree structure. Lets say I have a piece of data I need passed with a node, how do I do this? 01:07:53 That's quite specific to each rule/construct 01:08:18 well, yeah, that's why the AST i laid out has some things with "Symbol" instead of just always more ASTs. you need a base case as it were. 01:08:20 Do I simply create a property in the struct for that rule? 01:08:32 oic 01:08:44 -!- Phantom_Hoover has quit (Remote host closed the connection). 01:09:01 Ok after reading that I feel the answer to that was way to simple to even be asked 01:09:11 at least you knocked my head straight 01:12:49 basically this amounts to a tagged union - in C you'd have an AST struct with two fields, the tag and the actual object. the actual object is a union over all the syntactic types, and the tag just says which syntactic type this AST is. 01:13:15 oic 01:17:30 Would you guys like an alligator? 01:18:17 -!- yorick has quit (Remote host closed the connection). 01:24:53 like these? http://worrydream.com/AlligatorEggs/ 01:25:36 -!- nooodl has quit (Quit: Ik ga weg). 01:26:19 -!- ^v has quit (Quit: http://i.imgur.com/MHuW96t.gif). 01:26:43 lets play hangman! 01:26:43 -!- Sprocklem has quit (Ping timeout: 260 seconds). 01:26:46 -!- ^v has joined. 01:27:04 they do? 01:27:35 ~metar RKSI 01:29:19 augur_: Okay 01:29:26 prooftechnique: :D 01:29:50 i dont know if these a convention for doing the picture of the dude, so ill just count to 6 01:30:05 E 01:30:17 hold on :| 01:30:35 _ _ _ _ (0 wrong) 01:31:21 A 01:31:30 _ a _ _ (0 wrong) 01:31:42 Z 01:31:51 _ a z z (0 wrong) 01:31:54 JAZZ 01:32:03 prooftechnique: you watch QI :( 01:32:09 Correct :D 01:32:13 :D 01:32:39 prooftechnique: ok lets go again 01:32:43 _ _ _ _ (0 wrong) 01:33:22 i 01:33:28 _ _ _ _ (1 wrong: i) 01:33:41 j 01:33:50 _ _ _ _ (2 wrong: i j) 01:33:52 e 01:34:12 _ _ _ _ (3 wrong: e i j) 01:34:27 f 01:34:35 _ _ _ _ (4 wrong: e f i j) 01:34:53 Well, that's a whole class of hard words eliminated 01:34:56 a 01:35:11 _ _ _ _ (5 wrong: a e f i j) 01:35:15 :( 01:35:41 q 01:35:52 hangman isn't fair with short words 01:36:01 _ _ _ _ (6 wrong: a e f i j q) 01:36:09 cull 01:36:16 also you should add a prog to hackego to do what you're doing :P 01:36:20 Pretty good 01:36:36 Also, hangman in Haskell is surprisingly easy 01:36:37 prooftechnique: you didnt watch that episode of QI sufficiently :X 01:36:53 I blocked it out to make it fair, of course 01:36:59 lol 01:37:25 I never draw the picture in hangman; I always just count how many more tries you have 01:38:03 i always draw 01:38:22 because that way you can give extra tries without making it obvious you're doing so with kids 01:38:29 by adding eyes and hair and stuff 01:39:05 I don't like that; I always want everyone to know exactly how many tries you have left. No cheating by giving extra tries!!! 01:39:49 Some hangman games set how many tries by the length of the word or phrase. Famicom Hangman does this too (a program I have written). 01:40:19 I do not like using the picture since it makes it unclear so it just makes a box containing the wrong letters and once it is fill up, then you lose. 01:40:20 what's the point of hangman where you aren't murdering a stick figure 01:40:22 honestly 01:40:41 I agree with that statement 01:41:11 Bike: To guess the word. Of course you can draw the stick figure if you prefer but I prefer to not do so since it makes it less clear how many tries you have left. 01:41:36 -!- ^v has quit (Quit: http://i.imgur.com/MHuW96t.gif). 01:43:09 +you're right because there is a variable amount of body parts you could count 01:43:15 down to the eye lashes 01:43:23 To the toenails 01:43:29 indeed 01:43:37 to your individual hairs 01:43:57 skin cells 01:44:03 blood cells 01:44:12 atoms 01:44:16 organelles 01:44:29 ?messages-loud 01:44:30 boily said 6h 39s ago: I owe you some royalties for the “at canada” brand. 01:45:00 "I have shown, by ingenious induction on the structure of man, that in fact I have (n+1) tries in hangman. QED, nyah nyah nyah" 01:45:11 boily: I do not accept royalties for such brand. 01:48:30 prooftechnique: famous last words 01:49:21 I call it "Little Fermat's Theorem" 01:51:16 zzo38: do shorter words get you more tries than longer words? 01:51:22 (in famicom hangman) 01:52:00 oerjan: This alligator game is crazy 01:52:09 Where do you find these links? 01:52:33 quintopia: I wonder if shorter people get you fewer guesses 01:59:15 So I have a programming question 01:59:25 If you don't mind 01:59:48 prooftechnique: seen it way back, possibly linked in r/haskell 01:59:54 or perhaps even here 02:00:02 APott: Go for it 02:00:07 oerjan: You always have the best links :D 02:00:10 Lets say in the source i'm analyzing there is a number that I need to perform mathematical operations with. How do I get the integer value of a string? 02:00:34 most standard libraries have a function for that 02:00:47 c has atoi, that sorta thing 02:01:09 !c printf("%d",atoi("42")); 02:01:16 oic alright 02:01:20 `interp c printf("%d",atoi("42")); 02:01:24 D has the same sort of functions in it's library 02:01:27 so 02:01:37 now what 02:01:38 Does not compile. \ ./interps/gcccomp/gcccomp: fork: retry: Resource temporarily unavailable \ ./interps/gcccomp/gcccomp: fork: retry: Resource temporarily unavailable \ ./interps/gcccomp/gcccomp: fork: retry: Resource temporarily unavailable \ ./interps/gcccomp/gcccomp: fork: retry: Resource temporarily unavailable \ ./interps/gcccomp/gcccomp: for 02:01:45 sweet 02:01:50 Gregor: YOUR BOT IS ILL 02:02:02 and you are idle 02:02:02 Do i store this and perform operations with the float type for most accuracy? (some of this I stilld on't understand) 02:02:25 like "float num = atoi("42");" 02:02:49 num * 16.25 02:03:05 anything could be several decimals long 02:03:07 double has double accuracy to float 02:03:51 although neither will give you exact arithmetic for huge integers. 02:03:51 oh yeah 02:03:57 that's true 02:04:04 oerjan: `interp c does that 02:04:06 but it should be sufficient for my simple project 02:04:23 elliott: what, always? i thought it worked... 02:04:25 well thanks for that 02:04:27 lolfloats 02:04:32 `interp c printf("hm"); 02:04:48 holy cheese a new haswell costs $339 02:04:50 Does not compile. \ ./interps/gcccomp/gcccomp: fork: retry: Resource temporarily unavailable \ ./interps/gcccomp/gcccomp: fork: retry: Resource temporarily unavailable \ ./interps/gcccomp/gcccomp: fork: retry: Resource temporarily unavailable \ ./interps/gcccomp/gcccomp: fork: retry: Resource temporarily unavailable \ ./interps/gcccomp/gcccomp: for 02:04:53 OKAY 02:05:42 -!- Frooxius has quit (Ping timeout: 252 seconds). 02:06:04 I call it "Little Fermat's Theorem" <-- fermat's little theorem already exists. 02:06:16 on the other hand i can get a six core vishera for under $150 02:06:18 life is mysterious 02:06:56 oerjan: The proof was delivered childishly, so the idea is that it was delivered by a young Fermat 02:07:03 Thus, "Little Fermat" 02:07:27 "Current world record [for overclocking] is 8.79 GHz achieved on FX-8350 by Andre Yang using liquid nitrogen." why 02:08:00 you mean why didn't he use helium, right 02:08:03 hmmmmmm i don't know how big the caches should be though 02:08:07 is 8 MB sensible 02:08:42 is that L2 or L3? 02:08:53 also do the haswells really cost that much? 02:09:11 um, L3. L2 is three 2 MB caches, presumably pairs of cores share them? 02:09:32 that sounds like a good amount of cache to me? 02:09:38 I think L2 is a lot more relevant than L3 generally, but I might be wrong 02:09:40 ok i have no idea. 02:09:46 like at all. just saying. 02:09:52 I'm not sure which is more important either 02:10:02 I know on like, intel ones nowadays they only have like 256K per core L2? and the huge big thing in L3 02:10:05 *is L3 02:10:11 oh, here's a $200 haswell 02:10:20 "Limit 5 per customer" 02:10:28 pc shopping is really weird, y'all. 02:10:44 -!- Frooxius has joined. 02:10:46 ah, you're probably right, this doesn't even mention the L2 size 02:10:47 if I remember right the big L3s are like, also a way to use up extra die space without emitting much more power 02:10:57 but... it does mention the process size. 02:10:59 thanks I guess? 02:11:07 L2 is the same on all haswells, I think? which might be why it's not mentioned 02:11:11 while L3 varies 02:11:42 well i was thinking because "256K per core" wouldn't be very impressive compared to this 2 MB per core-pair on this amd one, but that works too 02:12:01 i don't know why i'm even looking this up, i don't think i'll be hacking deep enough that i need to know the µarch >_> 02:14:02 http://c1.neweggimages.com/BizIntell/item/19/116/19-116-901/herox.jpg the ads are fantastic though 02:14:37 Is that guy inside the processor? 02:14:44 THAT THING MUST BE SO STRONG 02:15:01 he's the adaptive techniques. if you need more PROCESSING POWER he yells at the instruction decoder until it gets its shit together 02:15:32 this thing lists more than one thread per core... is that that hyperthreading thing 02:17:48 maybe i should just buy a bunch of DSPs to fuck with instead. people still use those right. 02:19:50 quintopia: Yes, in Famicom Hangman, shorter words/phrases get you more tries than longer ones. 02:22:00 https://gs1.wac.edgecastcdn.net/8019B6/data.tumblr.com/a3ec9cd009cad7b4825479fae0a4b632/tumblr_inline_mvj43rbyXS1qik0w4.jpg 02:22:09 I love the precision of these Finns 02:22:38 I'm a bit surprised that those two on the end are standing together 02:26:30 i uploaded two example programs to go with the SELECT. interpreter. these two work. just wish someone would write one that tests some other language features :D. http://rutteric.com/files/ 02:37:25 -!- oerjan has quit (Quit: leaving). 02:43:00 -!- APott has quit (Quit: Page closed). 02:47:49 Have you played hangman games with a time limit? 03:16:35 Using the symbols &|!()10 only, can anything be made in Perl other than only the boolean condition checking if a 1 and 0 is only by itself? 03:26:19 perhaps ask in #perl 03:26:26 OK I can try 03:33:18 In the Dungeons&Dragons game I was trying to add more tally marks. The DM said there was room for 818 in total. This doesn't seem right to me, since 818 isn't a multiple of five. 03:43:29 -!- conehead has quit (Quit: Computer has gone to sleep.). 03:45:47 huh. church's thesis doesn't hold in a newtonian universe. neat. 03:46:40 Bike: huh, howso? 03:47:05 "We will sketch a proof (it is based on Gerver’s proof of the ‘‘Painleve con- 03:47:08 jecture’’ in the plane) of Theorem 4 that an uncountably infinite number of topologically distinct trajectories are 03:47:11 possible in 1 s, among the planar N-body problems with fixed masses and whose initial locations lie within 03:47:14 certain disjoint balls and whose velocities are bounded 03:47:20 [period] 03:47:27 i don't like pasting the sentences on periods, it's a bad habit 03:49:32 wait, what does that have to do with the Church-Turing thesis? 03:49:40 or is this some other thesis of Church's? 03:49:57 it means a turing machine can't simulate the topological properties of the bodies' trajectories 03:50:01 (in finite time) 03:51:30 oh and the initial configuration isn't even uncomputable, sweet 04:02:15 What do people here think about Elixir? 04:02:40 I like panaceas but I don't think they exist. 04:02:49 the language 04:03:09 The language of the birds? 04:09:22 Sgeo: I think the first Elixir demo I saw was pulling some data directly from some web service and turning it into code with macros 04:09:37 And the first reddit comment was "Oh, god, please never actually do this" 04:09:57 It looks like a nicer way to write Erlang, if nothing else 04:11:04 i like that on mushroomobserver.org if you don't know what kind of mushroom is in your photo you can put "Agaricales sensu lato" 04:11:12 which is latin for "looks like a mushroom, I guess" 04:11:36 (okay it's latin for "agarics, in the loose sense") 04:11:48 I like your translation better 04:12:11 if you're extra unsure you can just put "fungi" instead 04:12:22 is there a designation above kingdom which includes all life 04:12:38 cladistics people usually just go for "unranked" i think 04:12:48 since i mean, it's a tree, the levels are gonna get hairy anyway. 04:13:11 kmc: Well, domains are above kingoms 04:13:12 kmc: there's http://en.wikipedia.org/wiki/Three-domain_system at least? 04:13:14 *kingdoms 04:13:15 also using latin to obscure that you mean something boringly obvious is kind of great. incertae cedis~ 04:13:24 And then "Life" is above that 04:13:34 i should really hit up some taxonomists on twitter to see wtf they do in the presence of cladistics 04:13:58 But what about maybe-life? 04:14:11 http://en.wikipedia.org/wiki/File:Mammal_Diversity_2011.png mammal diversity 04:14:12 viruses are a whole different ballgame. 04:14:20 they change way faster than the rest, for one. 04:14:28 Bike: Shouldn't that be cedis? 04:14:34 *sedis 04:14:36 I can't type 04:14:46 petition to designate richard nixon as the type specimen for H. sapiens 04:14:52 isn't that what i typed... oh, oops, yes sedis 04:15:06 We both did it :/ 04:15:13 Sgeo: also viruses may be paraphyletic which is pretty cool imo 04:15:47 that is cool 04:15:49 i actually have no idea about viral taxonomy. i'd grab a book on it if i didn't already have five books checked out 04:15:57 it doesn't take long for things like viruses to evolve in artificial life systems 04:16:18 it kind of ties into abiogenesis stuff. like, were virus-like things first, or did they arise from bacteria, or what. 04:16:22 right 04:16:26 Bike: I read the wiki page for paraphyly, still don't know what you mean by that 04:16:52 Sgeo: viruses being paraphyletic would mean that the last common ancestor of all viruses is not a virus, i.e. that virality arose several times independently. 04:16:53 so why has something like life only evolved once on earth, anyway? is it just that it took a really long time? or is it that anything life-like which starts out today gets eaten by the usual kind of life? 04:17:21 Ah 04:17:22 (how would you designate the latter, anyway? "nucleic acid life"?) 04:17:24 Sgeo: (or er that the tree of ancestry includes non-viruses anyway) 04:17:47 kmc: i've thought about that a decent amount, but part of it is you have to qualify the universality of life 04:17:48 I guess it's like asking why nobody has replaced UNIX 04:17:55 i mean, we pretty much all use RNA 04:18:05 BUT sometimes the amino acid coding is different! 04:18:10 yep 04:18:13 that's pretty cool 04:18:41 And some things, like lipid bilayers, those are just... convenient. I'm not sure how they would be replaced. 04:19:46 it probably comes down to "we don't know enough about abiogenesis to make decent guesses" though, which suckz 04:20:38 yeah 04:20:59 there was that one abiogenesis experiment but it turned out to be wrong? i have a great memory of high school bio class as you can tell 04:21:08 You mean Miller-Urey? 04:21:15 the "throw some gas in a tube and get amino acids" thing. 04:23:26 yep 04:26:07 yeah the conditions they used weren't really very early-earth-like, and besides that life is rather more complicated than a couple monomers 04:26:47 living organisms obviously have their bilayers and their nucleotides, but even with just proteins you need a damn complex system (itself made mostly of proteins) to make everything fold right... 04:27:30 yeah 04:27:41 there's the theory that RNA itself served as the enzymes at first, right? 04:28:57 Yeah. and rna even still does that in living organisms. 04:29:02 really 04:29:13 that's cool 04:29:17 yeah they call them 'ribozymes' 04:29:33 Because... I dunno? I guess having an r plus the zy makes it even cooler sounding. 04:29:33 what's the advantage of protein enzymes 04:29:48 advantage of DNA over RNA for data storage is durability? 04:30:23 that's about where my cargo culted molecular bio runs out i'm afraid 04:30:28 ok 04:30:35 i kind of think of proteins as being more... flexible 04:31:05 when you really look at how a protein works, often it's made up of like four separate "domains" that each do their own thing, have their own binding sites, but can induce conformational changes in the other domains (i think) and stuff like that 04:31:20 iunno if you could replace titin with rna, basically 04:33:22 mm 04:33:33 proteins are like, really complicated /mechanically/, and i don't know if you can do that while staying hereditarily stable, i guess... 04:33:48 ah yes 04:34:31 maybe it's like, separation of concerns. which is vague and the analogy hardly works at all god 04:35:23 and if you're doing a translation thing anyway then maybe amino acids are a more flexible thing to translate to 04:35:55 Bike: i was gonna make an analogy to hereditary source code vs. ephemeral build products but that's even worse ;) 04:37:25 i'm kind of thinking of this like, here's gentoo on a macbook, now figure out how MULTICS worked. 04:37:33 haha 04:37:58 and your main tool is, you can break parts of the macbook and see what still functions 04:39:38 you also have the fossil record, which is a bunch of partially accurate descriptions of how older linux distributions functioned you found on some help forums. 04:40:09 haha 04:40:19 okay time to ride some trains, ttyl all 04:40:22 have fun 04:56:09 > let hangman (x:xs) (y:ys) c | y == c = c : hangman xs ys c | otherwise = x : hangman xs ys c; hangman _ _ _ = ""; in hangman "____" "jazz" 'z' -- augur_ 04:56:10 "__zz" 04:56:43 prooftechnique: what 04:56:54 augur_: For the next time we play hangman 04:57:03 A terrible code snippet that will do the work for you 04:57:22 prooftechnique: what does it do exactly 04:57:49 you give it blanks, the real word, and a chosen letter, and it computes the filled in letters bla bla bla. 04:57:54 ^ 04:58:09 oh oh i see what you mean 04:58:21 It'll be a big help when you play against me. "methylenedioxymethamphetamine" is easy to remember, but the longer ones, welllll 04:58:47 its methylene-dioxy-3,4-n-methylamphetamine, to be precise 04:59:20 or 3,4 at the beginning, take your pick 04:59:22 it's party dust mother fucker 05:20:26 -!- doesthiswork has quit (Quit: Leaving.). 05:23:39 "Thus there exist initial configurations of N bodies in the plane in which several of the bodies will hit the unit circle within 1.2 s iff the Riemann hypothesis is false (and the trajectories may be interpreted as a description of a counterexample)" 05:25:23 does that require real number computation? 05:26:05 yeah, but the initial configuration can be computable. 05:26:15 obviously this isn't actually a practical help towards /finding/ a counterexample, but. 05:27:15 hm, the state of unsimulatable initial configurations is of measure zero though.. 05:27:18 this paper is weird. 05:29:04 also kind of informal. «The third and most complicated set of laws we discuss (and the one we will concentrate on) is "modified linearized general relativity", which has all the mathematically annoying features of SRTG, and also has tensors.» 05:31:42 http://www.theonion.com/articles/barbershop-pole-finally-runs-out,34491/ 05:32:59 Fiora: i think this stuff basically comes about because of the newtonian-physics-allows-infinite-energy thing. 05:43:02 -!- lambdabot has quit (Ping timeout: 240 seconds). 05:47:30 -!- Jafet has quit (Ping timeout: 245 seconds). 05:48:09 -!- Jafet has joined. 06:04:15 -!- nisstyre has joined. 06:14:34 -!- Jafet has left. 06:41:13 -!- asie has joined. 06:45:50 A computer program just called me a distinguished Haskell coder 06:45:55 Based on ... not very much 06:46:00 What program? 06:46:01 http://osrc.dfm.io/Sgeo 06:46:11 Open Source Report Card 06:46:33 What is it based on? 06:46:53 GitHub profile 06:47:40 Bike: how does that thing work? 06:47:58 the infinite energy thing 06:47:59 ? 06:48:19 Not everyone has GitHub profiles though, and there may also be many programming languages that GitHub profiles do not yet include. 06:48:52 I tried to read Xia's paper once but it was beyond me 06:49:23 yeah 06:49:29 Basically, with the right initial conditions (and the paper is about what these conditions are) you can get an object infinitely far away in finite time 06:49:37 but of course, that's just restating "infinite energy". 06:52:10 I did get far enough to read that Xia's construction uses five bodies and is symmetrical across one axis. 06:52:36 So I kind of imagine four bodies moving back and forth as the last goes straight between them, getting faster and faster exponentially (or uh, superexponentially i guess?) 06:53:13 is that possible without arbitrarily small distances between objects? 06:53:39 like. if you apply a constraint like the planck length does it stil work 06:54:11 that would probably be a whole other paper. the classical n-body equations are in continuous spacetime. 06:54:21 oh. so it's not like. realistic 06:54:29 I guess? 06:54:39 Newtonian physics is unrealistic to begin with, though. 06:54:47 Because, I mean. Einstein. 06:55:49 oh. so like, relativity doesn't have that ""vulnerability""? 06:56:13 Can't exactly get to an infinite speed, now can you? 06:57:05 xia's paper is http://www.jstor.org/stable/2946572 if you want to take a crack but it's long and hard 07:06:05 oh, there's a short explanation of another construction in this paper... 07:06:12 it involves arranging things so that an asteroid moves polygonally. @_@ 07:06:22 @_@ 07:07:03 And uh the infinitizing comes by... 07:07:14 As a consequence of properties I–III, the entire N-gon expands in roughly geometric progression to infinite 07:07:18 size, but the asteroid traverses the N-gon edges in durations of time which shrink roughly geometrically 07:07:21 toward zero. In consequence, the asteroid travels an infinite number of circuits around the N-gon (and this 07:07:24 is an infinite distance), as the N-gon grows to infinite size, in a finite time tsingular, 07:08:04 so, that's basically insane. 07:09:48 so like does this mean newtonian mechanics doesn't conserve energy? 07:10:37 Um... I think in this construction, as the asteroid speeds up super fast the stars it's orbiting slow down. 07:10:54 does that mean you need an infinite number of stars or something? 07:11:02 since like, the energy has to come from somewhere 07:11:37 it comes from the stars slowing down. i think. 07:11:42 Does it violate things like that? Without doing such an experiment, or proving it mathematically inconsistent, it isn'ta reason to call such a theory wrong. (Now we do, but that doesn't seem a way?) 07:11:48 the stars start with an infinite amount of energy... (???) 07:12:11 zzo38: you're going to need to rephrase that more readably 07:12:17 Fiora: i don't know. math is hard 07:12:32 pretty sure newton is supposed to conserve energy though so lol i dunno 07:12:37 maybe i was wrong in talking about infinite energy 07:13:19 maybe just, like, unbounded? 07:13:29 maybe. 07:13:34 Bike: What, is he running out of food or something? 07:13:45 that is a joke i do not understand 07:14:07 Bike: O, I thought it is clear to me at least. 07:14:26 it's not very good anyway 07:14:32 "A baseball player on a frictionless plane surface flings a ball against a wall repeatedly" physics.jpg 07:35:28 http://www.theonion.com/articles/man-who-drinks-5-diet-cokes-per-day-hoping-doctors,34570/ this is me 07:36:15 Hoping doctors are what? 07:36:33 "working on a cure for whatever he's getting" 07:36:38 It's an expressio, zzo38. 07:36:46 Like "raining cats and dogs". 07:37:10 n 07:37:48 zzo38: i learned to play Magic: The Gathering 07:38:16 are you any good at it? 07:38:51 probably not 07:42:57 -!- doesthiswork has joined. 07:42:59 shachaf: Do you think some of the rules are too klugy? 07:43:15 @wn klugy 07:43:25 int-e: :'( 07:43:30 -!- doesthiswork has quit (Client Quit). 07:44:51 -!- asie has quit (Quit: I'll probably come back in either 20 minutes or 8 hours.). 07:46:21 zzo38: It's v. complicated. 07:47:38 -!- nisstyre has quit (Quit: Leaving). 07:58:04 i used to play mtg 07:58:10 i even have cards and stuff 07:58:35 I have no cards, but I sometimes do play the game (not very commonly though). 07:59:39 http://gatherer.wizards.com/pages/Card/Details.aspx?multiverseid=3315 i have this guy 08:00:15 i played this as a kid and i always mainly tried to manage to play that 08:00:29 oklopol: Is "unaffected by summoning sickness" distinct from "Haste"? 08:00:43 it may be the old name 08:00:45 that card is too good 08:00:45 Haste makes it unaffected by summoning sickness. 08:00:51 -!- asie has joined. 08:01:08 i also had 4 cards that simply let you play that card 08:01:25 Haste is a very old mechanic, and has existed at least since 4th Edition on Ball Lightning. However the Haste keyword was not added until much later. 08:01:30 http://mtg.wikia.com/wiki/Haste 08:02:08 (Summoning sickness is given to all permanents when they enter play/are created. At end of each turn, all permanents lose summoning sickness. Creatures with summoning sickness cannot attack, and any abilities with the tap symbol in their cost are unusable if it is a creature.) 08:02:22 zzo38: All permanents? I thought it was just creatures? 08:03:02 Hmm, "unusable if it is a creature". So non-creatures have summoning sickness but it's unobservable? 08:03:20 haha 08:03:56 shachaf: Yes, like that. It is also unused if the permanent has the Haste ability. 08:04:19 most of my friends play all sorts of rpg and card games and watch anime and stuff 08:04:41 oklopol: do you know things about chu spaces 08:04:45 oh and dota2 08:04:51 and other computer games 08:04:57 i doubt i do 08:06:01 oklopol: well anyway can you define a topological space/system/thingy as a product of some C and D^op 08:06:09 my first impression is that chu spaces sound a bit silly, topological spaces are already much more general than you need in real life 08:06:21 (usually) 08:06:27 oklopol: well look at the definition of a morphism though! what's with that 08:07:03 of morphisms between chu spaces? 08:07:07 yes 08:07:14 let's see 08:07:26 Understood statically, a Chu space (A, r, X) over a set K consists of a set A of points, a set X of states, and a function r : A × X → K. This makes it an A × X matrix with entries drawn from K, or equivalently a K-valued binary relation between A and X (ordinary binary relations being 2-valued). 08:07:40 okay maybe i should first try to parse that 08:07:42 so it's sort of like an adjunction (can you make it an actual adjunctiony thing by having p/q in p(f(a),b) = q(a,g(b)) be functors sort of like hom functors) 08:07:57 are you asking me? :P 08:08:08 Maybe. 08:08:13 i can't even make sense of the binary relation crap 08:08:23 oklopol: Well, the "topological system" thing in this book is less general than Chu spaces. 08:09:02 In particular, there's a "frame" -- a lattice that has finite meets and arbitrary joins, such that meets distribute over joins -- and a set of "points" 08:09:04 Bike: it just calls a function a binary K-valued relation. 08:09:15 but why 08:09:19 i mean a function from A times X to K is called a binary K-valued relation 08:09:22 i don't know why 08:09:30 Where the frame corresponds to the topology, of course. 08:10:51 So you have (X,A) where X is a set of points and A is a lattice of "opens" (which aren't sets, just things). And you have a "satisfies" relation, x |= a, that tells you whether a point satisfies an open. 08:11:20 You could say that points are what things "are" and opens are what observations you can make of them. 08:11:31 so A and X are the other way around than in wikipedia? 08:11:49 IS THAT IMPORTANT 08:11:50 Let me see. 08:11:57 Oh, I just used the other letters. 08:12:11 so what do you get out of this 08:12:17 The definition of Chu space is completely symmetrical so it doesn't matter. 08:12:30 But this one isn't, since you have a set and a frame. 08:12:45 okay so that's something between a topological spaces and a pointless topological space i guess 08:12:54 Right. 08:13:05 In fact if X = {} you get a pointless topological space, I guess. 08:13:14 perhaps it's exactly the latter (it's properly more general than the former though) 08:13:27 erm 08:13:36 oh err. 08:14:18 i figured two opens are indeed distinct iff they have different points (they are then sets, but it's still more general than the usual notion of topology) 08:14:21 I think there's some adjunction relation with functors between this thing and topological spaces and locales being forgetful/free or something. I don't remember. 08:14:40 No, you could have distinct opens that satisfy the same points. 08:14:45 alrighty 08:14:47 Er, that are satisfied by. 08:14:58 can you have U < V even if U has more points 08:15:05 That's the "that the open sets be extensional" part of the Chu space page. 08:15:05 in the lattice 08:15:43 Hmm, I'm not sure. 08:15:47 or does the frame somehow be a refinement of a sublattice of the lattice of subsets of X at least (if that makes sense.) 08:15:55 "does it be" 08:16:21 good lyric 08:17:03 OK, there are requirements on |= 08:17:42 "If S is a finite subset of A, then x |= Join S <-> x |= a for all a in S" 08:17:59 Sorry, "Meet" 08:18:07 "If S is a finite subset of A, then x |= Meet S <-> x |= a for all a in S" 08:18:33 "If S is any subset of A, then x |= Join S <-> x |= a for some a in S" 08:18:53 okay the morphisms of chu spaces certainly seem adjunctive. however, i do not quite get them yet. 08:19:21 Well, the definition is pretty intuitive from the perspective of topological systems, at least. 08:19:41 If you think of opens as "finite observations" that you can make about points. 08:19:47 ("adjunctive" in a very non-mathematical sense that this looks vaguely similar to some things i've seen when trying to understand adjunctions.) 08:19:54 (Right.) 08:20:38 So you might have bit streams as points, and "starts with 00101" as an open. 08:21:04 But "the stream is all 0s" not as an open, because it observes an infinite amount of information, say. 08:21:23 okay "x |= Join S <-> x |= a for all a in S" and "x |= Meet S <-> x |= a for all a in S" makes things pretty simple 08:21:25 Or "this real number is within the interval (x-d,x+d)" 08:21:39 but perhaps that's a typo. 08:21:52 No, one of them was wrong. 08:22:04 so it seems that joins are really set-theoretical joins and meets are really set-theoretical meets, and the lattice is there only for presentational reasons? 08:22:20 i mean associate with each open the set of points that satisfy it 08:22:28 By set-theorical joins/meets do you mean unions/intersections? 08:22:39 now the join of 2 opens is open, and is satisfied by exactly the union 08:22:42 yes 08:23:04 Yes, clearly for any topological space (X,ΩX), (X,ΩX,∈) is a "topological system". 08:23:32 But even if the set of points is empty you can have lots of different topological systems with different frames. 08:23:44 i thought the definition of join and meet was w.r.t. the lattice itself (in the abstract sense), so that they are just minimal upper bound etc.. then you get some weird additional stuff for i think. 08:23:46 Since there's no requirement that opens are extensional. 08:23:48 *-for 08:24:21 I'm not sure what you mean? 08:24:29 well it doesn't matter 08:24:45 the current definition is interesting enough 08:25:22 Anyway so if you think of opens as observations that you ought to be able to make, then you might ask what a structure-preserving function between (X,A) and (Y,B) could be. 08:25:45 Clearly it maps points to points, so you have f : X -> Y 08:26:34 But if b is some B-open, and f(x) |= b, then that's a finite observation you were able to make (by using f and an observation in (Y,B)). 08:26:53 (About x.) 08:27:02 true 08:27:07 So there ought to be some A-open that x satisfies, if it's structure-preserving. 08:27:28 oh that's the role of the backmap 08:27:33 should'be 08:27:35 erm 08:27:39 should've been obvious i guess 08:27:40 In particular, given f, there ought to be some thing g : B -> A such that f(x) |= b iff x |= g(b) 08:27:44 Right. 08:28:02 And it works out nicely for g to be a frame homomorphism, of course. 08:28:59 So a "continuous function" between (X,A) and (Y,B) is defined to be (f : X -> Y, g : B -> A) such that f(x) |= b iff x |= g(b) 08:29:00 that's something we require i guess? 08:29:07 (And g is a frame homomorphism.) 08:29:55 hmm 08:30:18 okay in the case of usual topology, g is precisely the map that maps an open to its f-preimage i guess 08:30:23 If you take a topological space, so that b is an open set, then clearly this is just defining g to be -- right. 08:30:56 So the morphism is entirely defined by f. 08:31:06 welllll 08:31:31 if the frame is like injective in the sense that no two opens have the same points 08:31:37 then i guess it's determined by f 08:31:49 I mean in the case of a usual topological space. 08:31:52 right 08:31:53 In general it isn't, of course. 08:32:01 (For example when X is empty.) 08:32:05 in general, i guess you explicitly require that it's a lattice homomorphism? 08:32:21 g? A frame homomorphism, yes. 08:33:13 The counterpart of a continuous function from (A, r, X) to (B, s, Y) is a pair (f, g) of functions f : A → B, g : Y → X satisfying the adjointness condition s(f(a), y) = r(a, g(y)) for all a ∈ A and y ∈ Y. 08:33:18 okay i totally get this now 08:33:29 that looked really weird a few minutes ago. 08:34:07 Right, so a Chu space generalizes a frame to not necessarily be a frame, and generalizes |= : (A,X) -> Bool to |= : (A,X) -> K 08:34:56 btw 08:35:03 let X be a topological space and Y a subset 08:35:24 then you get a topological system on Y by taking as the frame the opens of X 08:35:30 with their order 08:36:08 the frame is always the same as it was in X, but for example if Y = {} then the satisfaction relation is pretty trivial. 08:36:15 perhaps all topological systems arise this way? 08:37:43 Hmm, it's possible. I don't know. 08:38:04 in general topology, subspaces are defined the same way (except you add Y as an open set), but some open sets of X become the same set for Y; now you just don't identify them. and i guess it makes sense for the "frame" of the sub-topological system to be the same as the frame of the original space. 08:38:52 (makes sense in the sense that the word "frame" could be considered to suggest that) 08:39:09 (or it could be considered to suggest anything else i guess) 08:40:45 I think possibly this book talks about that but I've only read some of it so far. 08:41:14 so which book 08:41:25 Topology via Logic 08:42:45 So this "adjointness condition" thing and the backwards-and-forwards maps thing are a bit strange. 08:42:59 i don't really get adjointness 08:43:27 It sounds like maybe you could define it as some product C × D^op or something, if you could figure out a nice way of talking about the extra condition. 08:43:38 (i've tried to get it quite a few times) 08:44:22 The usual definition of an adjunction F -| G is that Hom(F(A), B) ≅ Hom(A, G(B)), natural in A and B 08:44:27 (Where F and G are functors, of course.) 08:44:40 btw i've noticed you're on #categorytheory, did you perhaps mention the channel at some point? i have no idea why i'm there myself 08:44:57 yeah but what's "natural in A and B" 08:45:22 So this is very similar, except it's dealing with functions instead of functors, and it generalizes Hom_C/Hom_D to s/r. 08:45:23 something that takes a page to define and a week to take in, and then it's obvious? 08:45:45 Well, it means you have a natural isomorphism between functors. 08:45:51 I don't know if I mentioned ##categorytheory in here. 08:46:05 between what functors 08:46:08 Naturality does take a bit to take in. 08:46:12 Hom(F(A), B) is not a functor, it's a set. 08:46:27 The functors \a b -> Hom(F(a), b) 08:46:36 Which is : C^op x D -> Set 08:46:41 oh. 08:46:52 Er, and the other Hom functor which gets the same type, of course. 08:47:42 that's actually something that sounds understandable 08:48:27 Usually people write it Hom(F(-), -) and so on 08:48:43 When you say "natural in X" it means that X is implicitly an argument. 08:49:01 but you have to guess what categories are dualed 08:49:04 And that you have a natural transformation. 08:49:12 well 08:49:16 i guess there's no choice... 08:49:21 Well, Hom_C : C^op x C -> Set 08:50:02 And F : D -> C, and we overload that to mean F : D^op -> C^op because it's the same thing. 08:50:19 sure 08:50:28 I guess you could write Hom(F^op(-), -) ≅ Hom(-, G(-)) 08:51:10 i'm not sure that's helpful though (is it unambiguous even?) 08:51:42 i guess it is 08:51:59 It's not very standard because it's usually pretty obvious which way F is being used. 08:52:39 obvious to some 08:52:56 not obvious to slow noobs 08:54:20 Anyway, it seems pretty related to this whole topological system and/or Chu space thing. 08:54:26 so F and G are adjoint if the functors \a b -> Hom(F^op(a), b) and \a b -> Hom(a, G(b)) are adjoint, as functors C^op \times D \to Set 08:54:30 is that the definition 08:54:39 Are naturally isomorphic. 08:54:46 erm right 08:54:48 ;D 08:55:09 That's a definition. 08:55:18 https://en.wikipedia.org/wiki/Adjoint_functors#Hom-set_adjunction 08:55:24 naturally isomorphic = there's a natural transformation from F to G such that every object map F(x) \to G(x) is an isomorphism 08:55:42 That sounds right. 08:56:51 (A natural isomorphism is probably defined as a pair (f : F -> G,g : G -> F) such that f . g = id, g . f = id with natural transformation composition. But I think that works out to the same thing.) 08:57:02 okay i guess that explains everything you just did 08:57:16 i haven't looked very closely at that definition, just the previous one 08:57:18 and it's too complicated 08:57:57 The unit-counit one is also nice but from a different perspective. 08:58:14 This is probably the simplest definition. 08:58:39 Note that when F has an inverse, it's always adjoint to its inverse. 08:58:48 probably, at least it looks like something i could understand if i spent half an hour looking at mental images of diagrams 08:58:56 might be a useful half an hour 08:59:13 adjoints are in some sense unique right 08:59:20 But if it doesn't have an inverse it might still have adjoints which you can think of as a best effort at an inverse or something. 08:59:26 Yes. 09:00:14 i don't actually know what an inverse functor is, or at least what precisely should be required from one 09:00:38 in any case again that clarifies a lot 09:01:29 Well, the most obvious definition would be that you have an isomorphism between categories. 09:01:55 I.e. F . G = id, id = G . F 09:02:07 i guess F's inverse if G such that F \circ G and G \circ F are naturally isomorphic to the identity functors? 09:02:17 oh err exactly equal? 09:02:31 oh okay you mean that's the obvious one 09:02:44 Well, "exactly equal" is in practice too strong, you just want "naturally isomorphic". 09:02:47 right. 09:02:56 so that you get for example equivalence with skeleton 09:03:11 If you pick "exactly equal" you get isomorphism of categories, which isn't really what you want in practice, so you use "naturally isomorphic" to get equivalent of categories. 09:03:35 And if you have F,G that give you an equivalence of categories then they're adjoint too. 09:04:00 You can often think of the special case of categories which are posets, and functors which are monotonic functions. 09:04:26 Where "≅" turns into "iff" and these are called "Galois connections" and people say it's simpler. 09:04:39 dude you are so wise 09:05:09 galois connections are awesome i hear 09:05:26 I hear that too but I don't understand them all that well. 09:06:27 Anyway, if you think of some way to relax "F . G ≅ id" and "id ≅ G . F", you might end up saying that those should just be natural transformations instead of isomorphisms. 09:06:39 That's the unit-counit of the other definition. 09:06:54 eps : F . G -> 1, eta : 1 -> G . F 09:07:25 You can think of it in the case of posets as relaxing f(g(x)) = x and x = g(f(x)) to f(g(x)) ≤ x and x ≤ g(f(x)) 09:07:59 oh okay 09:08:07 And there are some laws, namely that if you eta-and-then-eps you end up where you started. 09:08:31 Except they work in different categories, so it's more like "eps . fmap eta = id" and "fmap eps . eta = id" 09:08:49 I.e. https://en.wikipedia.org/wiki/File:AdjointFunctorSymmetry.png 09:09:14 Going back and forth between these definitions is a good way to figure them out. 09:09:56 fmap? 09:10:15 Well, that's how you write it in Haskell. 09:10:38 It's "eps . F eta" and "G eps . eta", or maybe the other way around. 09:11:40 Actually it's not exactly eps, it's eps-of-F-of, but anyway when you try to work out how these things could possibly compose there's only one way that makes sense. 09:12:58 Hmm, I guess talking about this helped me figure out part of my question. 09:13:27 i'm not really used to thinking about what makes sense when taking in definitions 09:13:51 OK, well, take the exact definition from Wikipedia or nlab. 09:15:02 The definition of continuous function didn't quite make sense to me until I saw the topological system formulation of it. 09:15:19 -!- asie has quit (Quit: I'll probably come back in either 20 minutes or 8 hours.). 09:15:25 Where it's vaguely obvious -- it's just a structure-preserving map as usual. 09:18:24 what's F eta 09:18:44 eta is a functor from D to itself 09:18:47 erm 09:18:50 what am i saying 09:18:54 eta is a natural transformation 09:19:19 eta is a natural transformation from 1_D to GF 09:19:24 right 09:19:36 and now we're composing if with a functor from D to C 09:19:37 Ah, see https://en.wikipedia.org/wiki/Natural_transformation#Operations_with_natural_transformations for the notation used in that article. 09:20:06 (F eta)_x means F (eta_x) 09:20:12 (i've gone down this road but i usually lose patience at some point :P) 09:20:42 So for eta : G -> H, F eta : F.G -> F.H 09:21:12 And (eta F)_x = eta_(Fx) 09:22:10 eta F : G.F -> H.F 09:22:25 (I'm explaining this much more confusingly than Wikipedia so just read that.) 09:23:41 well it's helpful to have someone be all like lol this is easy 09:23:53 usually i don't have much pressure to learn this since i don't know anyone who knows category theory 09:24:33 I don't know category theory. :-( Sometimes I pretend to know a bit on IRC. 09:25:10 Pullbacks! 09:25:12 But it certainly seems like it's relevant here to the whole adjointness thing. 09:26:16 Maybe you can generalize Chu spaces to work in arbitrary categories, with p/q being functors rather than functions? 09:26:58 I mean the ones in p(f(a), b) = q(a, g(b)) 09:27:11 Except this is already more general than adjunctions in a couple of ways. 09:27:48 Talking about f . g doesn't even make sense here because A/B and X/Y are two different kinds of things, not necessarily both categories/sets/whatever. 09:28:22 And p/q aren't Hom, they're just functions. 09:29:12 (Saying that p/q are "2-valued" as opposed to "K-valued" seems a bit like talking about posets/preörders instead of general categories.) 09:30:50 Let's put the contravariant argument first to make it more like Hom. 09:31:37 So a space-system-thingy is (A,X,p : A×X -> K) 09:31:58 i had a dream that i tried to put my pants on and it was incredibly hard 09:32:08 putting them on i mean 09:32:33 i was just about to step outside my apartment, when i realized i had no clothes on 09:33:12 my girlfriend and her sister were inside, and i was embarrassed that they'd know i almost went outside without any clothes on so i started putting them on at the door, while afraid that someone would see me 09:33:15 and it took forever 09:33:40 ...but yeah do continue 09:33:59 -!- asie has joined. 09:34:07 And a homomorphism : (A,X,p) -> (B,Y,q) is (f : B -> A, g : X -> Y) s.t. for any b : B, x : X, p(f(b), x) = q(b, g(x)) 09:34:10 Does that sound right? 09:34:27 so what are A, X, p and K here 09:34:39 sets, categories or nostrils? 09:34:46 In a Chu space? I think they're just sets and functions. 09:34:57 oh i thought you were already generalizing there. 09:35:15 No, this is still the old Chu space thing. 09:35:27 Just rephrased a bit. 09:35:32 so the latter guy in the tuple is the points 09:35:36 and the first is the frame 09:35:41 "frame" 09:35:43 Right. 09:35:59 So one issue here in the definition of Chu space is that f is just a regular function, not a homomorphism. 09:36:15 sounds right yes 09:36:48 So I guess you should say that A/B are objects in one category and X/Y are objects in another category. 09:36:57 And f/g are morphisms. 09:37:05 sure 09:37:35 Running out of letters. :-( 09:37:44 ö, ä, å 09:38:06 OK, using categories instead of functions makes it clearer, actually. 09:38:39 So we have (A : C, X : D, p : A^op × X -> K) 09:38:42 Where p is a functor. 09:38:44 -!- prooftechnique has quit. 09:38:45 Right? 09:39:22 There are probably properties that we want p to satisfy to make it "Hom-like". 09:39:42 Isn't there a thing for functors that are like Hom? 09:40:08 Related to presheaves or something, maybe? 09:40:08 when you say p is a functor 09:40:22 do you mean p is a functor from C^op \times D to K 09:40:31 or what's a functor from an object 09:40:35 to a category 09:40:43 Er, you're right, that made no sense. 09:41:13 OK, so that doesn't work. 09:41:21 What does A×X even mean when A and X are objects? 09:41:40 (In different categories.) 09:41:45 it means the tuple (A, X)? 09:41:51 hmm 09:42:13 I'm mixing up levels here. 09:42:36 but yeah it seems you are trying to work with morphisms between objects that come from different categories 09:42:58 which is beyondly stuff. 09:43:40 Well, right. That's one of the ways in which these Chu space things are weirder than regular adjunctions. 09:44:16 this is the most interesting channel i keep not looking at because i don't understand a word 09:44:27 OK, so the old definition: A space is (A : Set, X : Set, p : A×X -> K) 09:44:50 Where K is some global fixed thing. 09:45:44 A homomorphism : (A,X,p) -> (B,Y,q) is (f : B -> A, g : X -> Y) s.t. forall b∈B, x∈X, p(f(b), x) = q(b, g(x)) 09:47:12 Hmm. 09:47:22 -!- nooodl has joined. 09:48:42 hi nooodl! 09:48:46 hi 09:50:15 oklopol: help 09:50:22 :P 09:51:04 i have no idea how that should be generalized 09:51:19 As it is it doesn't even cover our old notion of topological systems. 09:51:28 Since we can't get frame homomorphisms. 09:52:21 Maybe we can relax the "K-valued relation" thing for a bit and bring back the iffs. 09:52:29 Does that even help? 09:52:41 -!- carado has joined. 09:52:58 iffs sound uncategorical 09:53:04 Yep. 09:53:25 I just want something that lets you express the topological system thing in a reasonable way. 09:53:46 But I'm pretty sure p ought to be something more than a function somehow. 09:53:46 well umm 09:54:07 It's so much like Hom. 09:55:05 you have two categories, the one of points (Set) and the one for frames (Lattice?). a topological system is, first of all, a tuple (X, A) where X is from the point category and A is from the frame category but how do you say which points are in which opens? 09:55:32 Frames aren't just lattices, they're a bit more. 09:55:52 you mean because they have infinite joins or what 09:56:00 And meets distribute over joins. 09:56:11 Anyway, a system is (X, A, |=), I guess. 09:56:25 let's say that's what Lattice is the category of. 09:56:31 but okay let's call if Frame 09:56:45 https://en.wikipedia.org/wiki/Complete_heyting_algebra calls it Frm 09:56:56 still how do you connect two objects from different categories 09:57:09 Anyway, "satisfies" is a relation, |= ⊆ X×A 09:57:10 i guess you could have a fixed functor from Frm to Set 09:57:13 or something 09:57:21 In the book's definition. 09:57:23 Which is a pretty unsatisfying way of doing it. 09:57:24 or maybe that's a bad idea 09:59:51 Maybe I should read http://boole.stanford.edu/pub/coimbra.pdf 10:00:13 Ugh, it calls the points A and the "states" X. 10:00:20 That's too confusing for me. 10:01:27 proves that functions between Chu 10:01:27 spaces are continuous if and only if they are homomorphisms. 10:01:52 sounds about right? 10:02:02 whatever that means 10:02:53 -!- impomatic has quit (Ping timeout: 272 seconds). 10:03:20 Well, given the definition of continuous that they have in that PDF, sure. 10:04:02 Oh, I should have read all of the Wikipedia article, too. 10:05:00 So if you put everything in some monoidal category you can do all the same things. 10:05:19 -!- MindlessDrone has joined. 10:05:55 I.e. a (C : Cat, K : C)-space is (A : C, X : C, p : A⊗X -> K) 10:06:50 And a morphism : (A,X,p) -> (B,Y,q) is (f : B -> A, g : X -> Y) s.t. forall b:B, x:X. p(f(b), x) = q(b, g(x)) 10:07:00 Where maybe = means isomorphic? 10:08:08 Maybe we can recover the usual notion of adjunction from that. 10:09:15 Chu(Cat, Set), where every p is p(-,-) = Hom(-^op,-) 10:09:42 Having to insert that ^op is really ugly, surely there's a nicer way to express all this? 10:11:27 " Where maybe = means isomorphic?" i would default to "equal" 10:12:12 "isomorphic" gives us the wrong thing in the Set case. 10:12:28 But it gives us the right thing in the category case. :-) I don't know. 10:13:58 But neither of them lets us do the thing where we have two different categories. 10:14:38 what does p(f(b), x) = q(b, g(x)) doesn't even mean? is C a concrete category 10:14:58 *-doesn't 10:15:39 I think it means that I'm saying complete nonsense again. Sigh. 10:16:05 So what am I trying to say here? 10:16:54 The original Chu construction as described in Po-Hsiang (Peter) Chu’s master’s 10:16:57 thesis took a symmetric monoidal closed category V with pullbacks and an 10:16:59 object k of V and “completed” V to a self-dual category Chu(V, k). 10:17:37 "forall b:B, x:X. p(f(b), x) = q(b, g(x))" could be changed into "p \circ (f \times id_X) and q \circ (\id_B, g) are isomorphic morphisms in some category (the arrow category?)" maybe, assuming the category has products in a nice sense. 10:17:50 or maybe that means nothing either 10:18:14 what's closed category, does that mean cartesian closed i wonder 10:18:41 oh 10:18:42 "monoidal closed" is like "cartesian closed" but with some monoidal category, not necessarily categorical product. 10:18:43 not at all i guess. 10:19:47 analogy with categories enriched in V [Kel82] one might refer to the 10:19:47 objects of the general Chu construction Chu(V, k) as V -enriched Chu spaces, 10:19:48 and indeed Chu(V, k) can be formulated as a V -category, one whose hom-objects 10:19:49 are objects of V . 10:19:53 Hmm. 10:22:21 Oh, hmm, apparently Chu spaces were introduced in the context of https://en.wikipedia.org/wiki/*-autonomous_category 10:23:20 Maybe that can be a place for the ^op to come from? 10:23:32 maybe, maybe. 10:23:33 -!- asie has quit (Quit: I'll probably come back in either 20 minutes or 8 hours.). 10:23:45 why is category theory so harrrrd 10:23:47 Oh, probably not. 10:23:51 sooooooooo harrrrrrrrrrrrrrrrrrrrrd 10:23:57 ⊥ is an actual object here. 10:25:42 I'm too tired now to think about any of this. 10:25:48 oklopol: Thanks for your help! 10:26:17 i was helpful?? i thought you were teaching me. 10:26:36 but you're welcome i guess :P 10:27:27 It looks like de Paiva's thesis was about something related to all this. 10:27:42 there are basically no courses that talk about category theory at our university 10:27:45 it's crazy 10:27:57 I hear she sometimes comes to bacat. Maybe we can get her to talk about it. 10:27:57 -!- mig22 has joined. 10:28:34 Well, the thing I was "really" trying to understand was the whole topological systems/Chu spaces bit. But it seems so categorical. 10:30:03 right 10:30:27 -!- Jafet has joined. 10:36:20 When I was asking whether you could express the space/system/whatever as some sort of C×D^op, I was focusing too much on (A,X) and not enough on p. 10:37:08 But p is the important thing here anyway. 10:37:41 So that's why I wanted to say something like p : A^op×X -> K 10:38:37 But that doesn't make sense as-is and I don't know what sort of thing p would be or what sort of thing ^op would be such that it causes the arrows to be reversed. 10:38:59 Anyway, I'm going to sleep. 10:49:34 night! 10:50:08 and yeah i too have no idea what anything should be, is, will be, or squirrels about. 11:06:05 What sort of games could be made out of category theory? 11:09:58 Or other various mathematical systems? 11:10:37 I have managed to make some out of sequent calculus. 11:17:30 -!- zzo38 has quit (Quit: zzo38). 11:35:42 -!- ais523 has joined. 11:41:16 -!- yorick has joined. 11:45:03 -!- Taneb has joined. 11:56:03 -!- Taneb has quit (Read error: Connection reset by peer). 11:57:34 -!- asie has joined. 11:57:39 -!- Taneb has joined. 12:04:34 -!- mig22 has quit (Quit: mig22). 12:04:35 -!- auzboz has joined. 12:08:59 -!- auzboz has quit (Ping timeout: 250 seconds). 12:44:26 oh wow, someone created a substitute-all-the-symbols language that /isn't/ based on brainfuck? 12:44:36 that doesn't make it any better as a language, but at least it's more original than usual :) 12:44:49 * ais523 wonders what the Phantom Hoover verdict on that sort of language is 12:45:20 i'm learning Io 12:56:11 -!- impomatic has joined. 12:59:15 -!- KingOfKarlsruhe has joined. 13:05:23 -!- asie has quit (Quit: I'll probably come back in either 20 minutes or 8 hours.). 13:37:18 -!- Phantom_Hoover has joined. 13:38:41 -!- asie has joined. 13:52:20 ais523: it's not the first time. RAGE!!! is a syntax replacement for python 13:52:46 -!- MindlessDrone has quit (Quit: MindlessDrone). 13:53:01 quintopia: right 13:53:16 so it currently seems to be BF-or-(non-eso)-language, right? 13:53:40 i can't think of one that doesn't fit one of those two, no 13:56:50 -!- mig22 has joined. 13:59:20 ais523: i have a challenge for you. come up with an algorithm that clears cells from an infinite BF tape based on a (cautious not-likely-to-make-type1-errors) analysis of the portion of the program that has left to be run 13:59:28 http://en.wikipedia.org/wiki/Celestial_Eye 13:59:34 jesus 13:59:47 quintopia: I'm not 100% sure what you mean by that 13:59:50 basically "it looks like this cell will never be read or written again, so delete it" 13:59:54 is this about BF Joust or regular BF? 14:00:05 it's really about SELECT. 14:00:12 right 14:00:14 but say BF 14:00:16 http://en.wikipedia.org/wiki/Bubble_Eye 14:00:19 OK this is just silly 14:00:28 so it's an attempt to throw away memory that will never be touched again? 14:00:39 I just added a command for that in Shove 14:00:47 which is a bit of a cop-out 14:00:55 -!- oerjan has joined. 14:07:31 -!- S1 has joined. 14:11:10 -!- mig22 has quit (Quit: mig22). 14:19:48 -!- S1 has left. 14:25:04 -!- impomatic has quit (Quit: impomatic). 14:33:58 @tell fiora is that possible without arbitrarily small distances between objects? <-- i am assuming no, since that's the only way i can see you getting infinite kinetic energy from potential... 15:11:57 A black hole should be able to give you infinite kinetic energy, right? 15:13:42 -!- MindlessDrone has joined. 15:14:29 FreeFull: by accelerating you to infinite velocities? 15:14:55 Yeah. There might be problems with regards to time though 15:15:35 With regards of an external observer, you never even cross the event horizon 15:17:51 FreeFull: this was about newtonian mechanics, which doesn't have black holes. 15:18:49 Newtonian mechanics has an infinite speed of light, right? 15:19:29 it might, in any case other objects don't have a speed limit. 15:20:52 In Newtonian mechanics, you need either infinite velocity or mass 15:21:27 Which probably does mean accelerating towards a singularity 15:22:08 the previous discussion was about how you _can_ get infinite speed in newtonian mechanics, even without starting with it. 15:22:18 for point masses, anyway. 15:27:11 is that through abuse of the rocket equation or sth 15:29:06 Phantom_Hoover: just plain gravitation, no other forces. 15:30:25 as i was implying to Fiora, it's probably borrowing potential energy from two of the masses getting infinitely close/colliding. 15:33:03 ah 15:33:18 well, two point masses falling towards each other will go infinitely fast won't they 15:34:10 think so. although the actual example has a point mass going infinitely fast towards infinity. 15:45:39 -!- oerjan has quit (Quit: Later). 16:07:29 Phantom_Hoover: golddfish breeding is kind of messed up sometimes. 16:08:19 it seems to consist mostly of "how much can we fuck up a goldfish and still be able to breed it" 16:09:17 yeah. :( 16:14:56 -!- lambdabot has joined. 16:18:12 Well, that was odd 16:18:24 Someone hid the carpet from my flat's hallway 16:19:20 dastardly 16:22:13 Then, when everyone was standing around the bare underlay, he said "We need to cover it up. Maybe we can cover it up with this?", holding the carpet 16:26:25 this sounds way more fun than my halls 16:53:53 -!- Phantom_Hoover has quit (Ping timeout: 245 seconds). 16:57:49 -!- conehead has joined. 17:09:27 -!- Phantom_Hoover has joined. 17:25:45 -!- sebbu has quit (Ping timeout: 268 seconds). 17:36:50 -!- Phantom_Hoover has quit (Ping timeout: 264 seconds). 17:46:33 -!- sebbu has joined. 17:49:04 Today's innovation: In many (Windows) games, I can keep an SSH client open on a second monitor, while the game itself is fullscreen on the first -- but typically there's no way of interacting with the SSH client without alt-tabbing out of the game. However! I can "screen -x" the same screen window that's visible in the SSH client from a mobile device, and then connect a small Bluetooth ... 17:49:10 ... keyboard to that mobile device. And now I have a separate keyboard for blathering in IRC or whatever. So fancy. 17:51:17 Is there a way to have two different keyboards on the same device interacting with different windows 17:51:36 -!- Phantom_Hoover has joined. 17:51:47 You could certainly hack something up for that. 17:52:10 Write something that listens for /dev/input/eventX of the other keyboard, convince X not to listen to it, and have that program synthesize key events. 17:52:11 -!- Sgeo has quit (Read error: Connection reset by peer). 17:52:22 I don't know of any out-of-the-box solutions, though. 17:52:38 There's MPX if you want different mice to have their own independent pointers. 17:53:27 -!- Sgeo has joined. 17:53:39 (At least I think it was called MPX.) 17:54:25 -!- Sgeo has quit (Read error: Connection reset by peer). 17:55:42 -!- Sgeo has joined. 17:58:24 pavucontrol (pulse audio volume control) turns volumes UP when you scroll-wheel DOWN and DOWN when you scroll-wheel UP. 17:58:35 Software written by people who have never used software is the best kind of software. 17:58:52 ais523: the reason i want that problem solved is because SELECT. has no way of returning sufficiently modified cells to their original state without clobbering another cell, which means SELECT. programs are memory hogs by necessity (you have to use a new cell for every new number you want). so it would be nice if my interpreter could clean up unusable cells automatically 17:59:18 quintopia: yeah, it's clearly an unsolvable problem in general, but it may be solvable in useful special cases 18:11:13 I HAVE BROKEN MY OATH 18:11:36 ? 18:12:30 I promised I'd try to drink less caffeinated soft drinks 18:12:31 -!- prooftechnique has joined. 18:12:37 After an incident a couple of weeks ago 18:12:52 There is a CAOS command: 18:12:53 Taneb: I decided to give them up for a bit several years ago 18:12:53 pat: butt 18:12:57 like, umm, trying to work it out 18:12:59 9 years ago 18:13:02 and haven't drunk them since 18:13:28 giving up vehicles only lasted a month, though, but then that wasn't meant to be permanent 18:13:46 still, it's interesting to learn how rarely they're needed 18:13:59 atm I only use them if I'm in a hurry or it's raining really badly or I need to go a long distance 18:14:28 actually when I give things up, it's never really meant to be permanent, sometimes it just turns out that way 18:14:30 Right now I actually don't need vehicles, the furthest I need to be is about half an hour's walk from here 18:14:47 for me, s/half an hour/one hour ten minutes/ 18:14:49 but yeah 18:14:53 much the same situation 18:15:15 But that's only in term time and not-term time. The edges I need to travel, I guess 18:15:52 I use the bus a lot 18:15:56 car quite rarely 18:15:58 that's close to the reason I was travelling, too; I don't need to move house between termtime and holiday, but I'm sometimes needed to help other people travel 18:16:02 coppro: that used to be the case for me, too 18:16:13 but my bus pass ran out and I needed exercise and the commute seemed like a good time 18:16:28 makes sense 18:16:32 the nice thing about using walking as exercise is that nothing forces the start point and destination to be the same 18:16:38 I have a student bus pass so it costs me nothing 18:16:43 Can you guys give any tips for finding flatmates 18:16:50 yeah, I used to have a student bus pass, but I'm not eligible for it any more 18:16:57 I'm starting to think that I need to start to think about that 18:16:59 Taneb: no, I can't, or at least my advice would probably be really bad 18:17:23 ais523, how about some cautionary tales? 18:17:30 nor that 18:17:35 I've never had a flatmate 18:17:37 step one, find a mate. step two, find a flat. step three, mate the flat and the mate 18:17:53 you could probably get some cautionary tales from oerjan, though 18:17:53 I'd paste a video I took yeserday, but when I made it, I was incompetent with the recording tool I used 18:18:14 http://www.youtube.com/watch?v=Wpufk1bed9M 18:18:19 Taneb: be careful if you room with a good friend; it can deteriorate a friendship quick if you don't get along as roommates 18:18:24 based on comments he made in #esoteric, he used to be with some if he disliked 18:18:30 coppro: that sounds like good advice 18:19:03 coppro, I think that if that happened I'd blame myself and then be really sad 18:19:34 if you can be choosy, ask about things like sleeping habits 18:20:00 if you're social people, being on the same sleep schedule is good; if you're not, you may prefer being on different ones 18:20:26 my sleep schedule is not actually random, but I'm not convinced it compresses well 18:21:01 also figure out if you want to share food/dishes 18:21:26 some people take the approach that each roommate brings their own and there is no sharing, others handle it communally. if you're doing communal, make sure to sort out payment 18:22:09 cleaning is another big source of friction; work out your mutual expectations 18:22:18 some people can't stand to live with things not clean, and others can't be bothered to clean 18:22:27 unsurprisingly, these two types of people don't go well together 18:24:08 Thanks for the advice, coppro 18:24:17 And the caffeine and sugar are going to my head and I feel woozy 18:25:31 (depending on the layout and personal preferences, significant others may also be an issue) 18:28:49 -!- asie has quit (Quit: I'll probably come back in either 20 minutes or 8 hours.). 18:29:50 -!- Lymia has quit (Ping timeout: 246 seconds). 18:35:59 -!- asie has joined. 18:55:53 -!- ais523 has changed nick to ais523\unfoog. 19:00:36 -!- zzo38 has joined. 19:01:19 -!- S1 has joined. 19:01:25 -!- S1 has left. 19:01:40 -!- S1 has joined. 19:11:08 -!- S1 has left. 19:15:48 -!- doesthiswork has joined. 19:30:47 -!- asie has quit (Quit: I'll probably come back in either 20 minutes or 8 hours.). 19:31:04 -!- asie has joined. 19:48:32 ski: did you see the longversation about chu spaces in here yesterday 19:51:47 -!- Guest72395 has joined. 19:53:13 -!- conehead has quit (Quit: Computer has gone to sleep.). 19:54:03 How's everyone's hardware programming language going? 19:54:19 What hardware programming language? 19:56:58 I assumed everybode was working on one . 19:57:08 but really I just forgot how it was how was doing that 19:57:49 and by how i mean who 19:57:59 I'm apparentely a little bit legasthenic 19:58:01 Well, I am one of the people who was designing a hardware programming language, and wanted some comments about it 20:00:05 -!- conehead has joined. 20:02:58 I didn't add a lot recently since I didn't know what else needs to be change; one thing would be analog stuff, CMOS stuff, and various other things. 20:06:03 I think the macros are OK now though; do you think of anything missing or redundant or something with the macro system I have defined for this purpose? 20:20:10 -!- Frooxius has quit (Read error: Connection reset by peer). 20:22:52 -!- conehead has quit (Quit: Computer has gone to sleep.). 20:24:38 -!- Guest72395 has quit (Quit: Leaving). 20:26:30 -!- Frooxius has joined. 20:30:47 you know i'm still waiting for jsvine to write that article 20:31:27 Hmm, yeah 20:34:18 Yes, I didn't know they haven't done so yet? 20:35:03 -!- Sprocklem has joined. 20:43:35 -!- nisstyre has joined. 20:45:13 well 20:45:33 it has come to the point where I'm seriously designing esoteric processing units 20:50:06 mroman_: Can you describe it please? 20:52:57 -!- sebbu has quit (Ping timeout: 268 seconds). 20:55:45 `quote scipi 20:55:50 No output. 20:55:53 `quote scipy 20:55:55 No output. 20:57:58 -!- MindlessDrone has quit (Quit: MindlessDrone). 20:58:36 zzo38: I'm designig weird cpus :) 20:58:43 *designing 20:59:07 -!- Sprocklem has quit (Ping timeout: 268 seconds). 20:59:10 have you ever designed a blitter 21:05:53 -!- Sprocklem has joined. 21:10:54 what? 21:10:55 no 21:11:02 zzo38: http://codepad.org/43llKpDB 21:11:06 ^- stuff like that 21:11:08 aw, but they're cool. 21:11:16 screen blitters? 21:11:33 well, yeah. basically a coprocessor that can do memory movs according to a mask. 21:12:09 ic 21:12:27 hm 21:12:39 that SBA could actually be moved out of the loop to make it run faster 21:14:29 zzo38: I'm designing something with integrated Support for graphics stuff and stuff 21:14:34 then I'll write some crappy game for it 21:14:41 and then I consider the project done :) 21:18:49 and yeah 21:18:59 DST and SRC set the destination and source 21:19:03 -!- Sprocklem has quit (Ping timeout: 252 seconds). 21:19:07 because they arent encoded in instructions itself 21:19:20 but must ruther be set by instructions 21:19:22 *rather 21:19:45 Programming is a meritocracy because it’s an empirical activity. That’s why we don’t have programming fads or fashions. 21:20:02 1/10 not even mad 21:21:07 isn't it the most wonderful quote? 21:21:56 -!- conehead has joined. 21:22:36 doesthiswork, by wonderful do you mean humorously completely wrong? 21:22:57 yes! 21:23:10 it's not a real opinion. 21:24:51 the consequence is so hilariously wrong that it disproves the antecedent. 21:26:25 -!- nooodl has quit (Read error: Operation timed out). 21:26:25 "It's about time Stephen Wolfram got credit for inventing Lisp." good blog here 21:26:47 huh, he hasn't taken credit for that yet? 21:26:48 ooh another good one 21:27:15 xah lee would like that 21:27:23 Wolfram Language will be the last programming language we ever need™ 21:35:36 -!- Sprocklem has joined. 21:40:20 I like how need is copywritten 21:41:30 holy god is wolfram making a programming language 21:41:31 like "well typed programs can't go wrong™" 21:41:50 yes he is 21:42:08 fucking 21:42:09 beautiful 21:44:32 is it called "Wolfram" 21:45:23 doesthiswork: copywritten? :( 21:46:18 woops "trademarked" 21:46:25 or did you mean that the copy writer added the trademark sign 21:46:39 Bike: wolfram beta 21:46:45 yesssss. 21:47:05 mroman_: OK, that is you have some idea 21:47:32 Bike: it actually is called Wolfram, I think 21:48:01 how are we supposed to make jokes if real life beats us to them 21:49:35 -!- Sprocklem has quit (Ping timeout: 272 seconds). 21:50:26 -!- impomatic has joined. 21:54:09 zzo38: Hm? 21:54:54 One always needs an idea before doing anything. 21:55:07 mroman_: What game did you intend to write? 21:55:12 but I'm also designing a CPU for my university ;) 21:55:30 What CPU do you design for your university? 21:55:38 zzo38: I was thinking of Pong. 21:56:05 zzo38: It's actually a whole "computer system" 21:56:23 It's supposed to be a simplified "real computer" 21:56:36 for demonstration purposes. 21:56:55 It has a full cache and MMU emulation 21:57:25 What I wanted is a CPU with explicit caching/pipelining rather than being implicit. 21:57:39 How so? 21:57:47 I am not sure exactly how, but I think it would be a good idea. 21:57:51 and why "wanted"? 21:57:56 And how would that work? 21:58:01 If have to explictly cache data? 21:58:05 e.g. through uhm. 21:58:19 cache load instructions? 21:58:39 Yes, that would be one thing, I suppose. 21:58:54 Or due you just treat the cache as memory 21:59:06 but you have instructions to write from the cache to memory? 21:59:29 which would be roughly the same as having an internal RAM and external RAM 21:59:40 -!- prooftechnique has quit. 21:59:40 like some microcontrollers have 21:59:50 I suppose you would have instructions to transfer between the cache and the external memory, and to transfer between the cache and registers. 21:59:58 like the 8051 22:00:02 MOVX and MOV :) 22:00:23 Another idea I had is some instruction to swap between cache and microcode RAM. 22:00:25 (MOVX = external Data) 22:00:43 it actually also has MOVC 22:00:55 as it is harvard architecture 22:01:35 -!- asie has quit (Quit: I'll probably come back in either 20 minutes or 8 hours.). 22:02:15 I don't really see why you'd want explicit caching 22:02:49 of course, for some microcontrollers it makes sense to keep often accessed data in the internal ram and not the external ram 22:02:51 I would want explicit caching and pipelining so that it can all be software-controlled with predictable instruction timings, as well as user-defined microcodes. 22:03:26 which means you explicitly programm "caching" 22:03:38 zzo38: So 22:03:43 Hard-Realtime Constraints? 22:03:52 mroman_: Yes. 22:04:08 I see. 22:04:19 That I accept as an argument :) 22:04:42 I'm not well informed about real-time CPUs 22:04:58 if there are any specifically designed for that 22:05:14 you could argue that old CPUs with predictable cycles per instructions are more or less real-time-safe 22:05:16 It may also simplify the implementation of the CPU somewhat, depending on how it is done, and allows software to figure out the best way to cache data for the application rather than the hardware to guess. 22:05:32 mroman_: Yes, it is one of the things I prefer about the older CPU designs. 22:05:40 i.e old x86 processor 22:05:57 If you have the assembler code you can make worst case timing analysis on the assembler code 22:06:07 it get's a little bit trickier with interrupt latency 22:06:11 but it's doable 22:06:14 And make it slow on purpose too if you want to. 22:22:51 -!- carado has quit (Ping timeout: 252 seconds). 22:29:15 -!- lambdabot has quit (Quit: requested). 22:31:39 -!- yiyus has quit (Ping timeout: 252 seconds). 22:33:11 -!- lambdabot has joined. 22:38:54 oops. poor thing 22:38:56 @botsnack 22:38:56 :) 22:45:45 -!- Sprocklem has joined. 22:50:00 -!- sebbu has joined. 22:50:25 It lives! 22:50:39 -!- sebbu has quit (Changing host). 22:50:39 -!- sebbu has joined. 22:57:12 -!- lambdabot has quit (Quit: requested). 22:57:36 gah, tab completion is evil. I should stop using it. 22:57:53 int-e: Is it? Not if you are careful? 22:58:17 well, lamb completed to lambdabot rather than the intended lambdacat ... 22:58:36 Do you have a file named lambdacat in your computer? 22:58:39 maybe I should pick a different name for my test bot :) 22:59:44 elliott used to use mubot 22:59:45 v. creative 23:00:36 What program are you using with tab-completion anyways? Different programs sometimes implement it a bit differently, such as Windows difference from Linux tab completion. 23:01:14 -!- lambdabot has joined. 23:01:28 Bike, clearly the next one is nubot 23:02:32 -!- ais523\unfoog has quit. 23:08:14 -!- JesseH has joined. 23:11:56 I have made up the program which will provide two low-pass filters and one signal selects any fraction in between the two filters; one filter stops while the other one is running, or the effect of the audio on the filter and vice-versa is only partial and the other filter is the other part of the fraction. A triangle wave then is used to control this fraction, and the signal filtered with a fixed fraction is subtracted from it, to make the output. 23:12:05 Is this a known thing too? 23:12:55 -!- ^v has joined. 23:13:21 Could you provide a sound file? 23:13:32 Yes, I could do so 23:15:31 Will you? 23:15:42 Yes, just wait a minute 23:15:59 int-e: kattacat 23:24:17 FreeFull: http://zzo38computer.org/csound/music/example1.wav (see example1.csd for the parameters) 23:27:50 Taneb: h8r 23:28:08 What am I a hater of this time? 23:28:22 zzo38: Do the filters alternate very quickly? 23:28:23 Trains? 23:28:32 No. Merely a disbeliever 23:28:46 I'm a traintheist 23:29:14 FreeFull: They alternate at the frequency of the triangle wave (the p4, p5, and p6 correspond to the fourth, fifth, and sixth parameters on each line of the block in the input file) 23:29:31 See ../csoundextraopcodes.c to see what "mixlpf" does. 23:52:03 -!- oerjan has joined. 23:53:29 `addquote Phantom_Hoover: golddfish breeding is kind of messed up sometimes. it seems to consist mostly of "how much can we fuck up a goldfish and still be able to breed it" 23:53:34 1133) Phantom_Hoover: golddfish breeding is kind of messed up sometimes. it seems to consist mostly of "how much can we fuck up a goldfish and still be able to breed it" 2013-11-17: 00:00:33 After an incident a couple of weeks ago <-- ic, *opens caffeinated soft drink* 00:01:19 this + the pain killers better remove my headache. 00:02:35 * oerjan imagines Taneb running frantically around on a caffeine high 00:04:02 -!- prooftechnique has joined. 00:05:10 oerjan, it was more that I was visibly shaking and felt like my entire digestive system was trying to go on holiday 00:05:25 oh i felt that way yesterday 00:05:38 I am typing the Dungeons&Dragons game recording; not finished yet but will be soon, hopefully. 00:05:39 then i ate some food and it went away 00:05:42 And then I stopped visibly shakin 00:05:43 g 00:05:51 Taneb: ok i know that second part. if i take more than about two cups of coffeee. 00:05:56 And couldn't stop smiling and giggling 00:06:16 And I couldn't feel my hands 00:06:25 -!- Sgeo has quit (Read error: Connection reset by peer). 00:06:33 how f much did you drink 00:06:51 Two pints, on an empty stomach 00:07:00 `frink 2 pints -> l 00:07:10 473176473/500000000 (exactly 0.946352946) 00:07:12 2 pints of coffee? 00:07:13 I managed to get an extra 300 XP for an idea I had about what to do next, just at the end of the session, and this was just enough to advance to 27 ECL (20 HD), so maybe these two new spells might help a bit. 00:07:16 olsner, of cola 00:07:32 was it sugary as well, i expect that doesn't help 00:07:37 hmm, that's only like half a 2l bottle 00:07:39 -!- Sgeo has joined. 00:07:40 i do think, writing java makes me urinate more 00:07:54 oerjan, yeah, it was coca cola 00:08:01 Very sugar, much caffeine 00:08:33 * oerjan drinks coca cola zero 00:09:01 I drink coke zero now when I haven't eaten much 00:09:56 myname: fascinating! 00:10:14 oerjan: indeed 00:10:38 it may be SOAP, though 00:11:08 oerjan: did you logread the whole space nonsense from last night 00:11:25 shachaf: i quite firmly skipped most of it. 00:11:38 oerjan: h8r 00:11:50 imo read it and gimme your insights 00:12:00 was that the thing about infinite velocity black holes and whatnot? 00:12:02 my concentration would never last through all of that these days. 00:12:22 It's always disappointing when someone cites the laws of form seriously. 00:12:23 olsner: no, it was chu spaces and category theory and adjunction and a horrible mess 00:12:30 *adjunctions 00:13:38 i've never read the laws of form, but i vaguely recall some claim it's just an encoding of propositional logic or thereabouts. 00:13:59 yes it is 00:14:13 but people cite it for the metaphysics 00:14:14 Hang on, I've got a vague feeling I may have triggered this discussion 00:14:19 nope 00:14:30 Oh thank god 00:14:31 unless you mean chu spaces 00:14:40 That's what I meant 00:14:46 oh. 00:14:46 ok then yes 00:15:27 OK, I sincerely apologize 00:15:58 Taneb: you know, don't start going all Sgeo on worrying about what you're doing tdnh 00:16:34 oerjan, weren't you banned from variants of "hth"? 00:16:44 Also I don't know what you mean by tdnh 00:16:45 yes, but i have cheating methods 00:16:49 ` 00:16:51 ​/home/hackbot/hackbot.hg/multibot_cmds/lib/limits: line 5: exec: : not found 00:16:53 oops :P 00:16:58 `? tdnh 00:17:01 tdnh does not help 00:17:13 `? hth 00:17:13 (that was me forgetting to use it) 00:17:15 hth is help received from a hairy toe. It is not at all hambiguitous. 00:17:38 that explains it finally 00:17:54 Taneb: i wasn't banned, elliott wrote a censoring script. 00:19:18 I could do with an ice cream 00:19:35 I wonder if a) the petrol station next door is open and b) sells ice cream 00:19:49 What kind of ice cream did you want? 00:19:51 hm i was going to complain to Gregor that the logs broke the windows zooming shortcut, but then i realized i'd been pressing the neutralize zooming shortcut instead 00:20:01 zzo38, vanilla, preferably 00:20:07 (also that he'd just laugh evilly at me) 00:20:43 why did tunes.org choose to log esoteric? 00:21:06 i dunno, it happened before i got here 00:21:12 fizzie might know? 00:21:25 Taneb: why not tar? 00:21:53 olsner, I am not a huge fan of tar flavoured ice cream 00:22:19 miksi ei tar 00:22:31 i'm suspicious on that last word, google translate 00:22:40 *of 00:23:44 * oerjan just realizes that fizzie might be the only active one here who's been here longer than him... 00:23:55 oh wait 00:24:00 Gregor, surely 00:26:40 Right, I'm seeing if the petrol station's shop is open 00:26:52 good luck on your quest 00:27:27 -!- yorick has quit (Remote host closed the connection). 00:28:13 `quote petrol 00:28:15 345) what would you ever need petrol for newsflash: it doesn't actually taste that good \ 346) [on petrol] oklofok: it's actually poisonous, so I advise against drinking it ais523, also contains benzene, my carcinogen of choice. 00:28:37 `quote gasoline 00:28:39 No output. 00:29:02 ais523 was on petrol? 00:29:11 #drugz 00:30:08 kmc: you should swat shachaf, he made a drugz joke not involving you 00:30:41 or he could if he weren't hopelessly idle 00:31:41 he's in korea and/or japan right now 00:32:05 @tell ais523 based on comments he made in #esoteric, he used to be with some if he disliked <-- i'm too noise sensitive to have flatmates, period. 00:32:06 Consider it noted. 00:32:40 samsung digital city, the small autonomous state 00:33:55 Well, that ice cream was certainly ice cream 00:34:12 "Samsung Town is twinned with Disneyland Paris and Sony World (Tokyo, Japan). The "twinning" is only symbolic and has no legal significance." 00:34:22 if you say so 00:34:39 I don't think twinning has any legal significance in any case 00:35:07 i recall trondheim has a twin city in israel and also one in palestine. 00:35:38 as well as several in europe 00:36:22 wait, that's friendship city, but presumably essentially the same thing. 00:37:19 Taneb: i suppose it might not look good if samsung and sony had an antitrust case against them... 00:40:35 "The streets had been laid down, but no houses were built; merely a row of cardboard boxes housed the first few residents who had migrated east from the slums of Ashburton to enjoy a better standard of living, only to be bitterly disappointed with the estate agents who promised milk and honey but instead delivered a mosquito infested swamp. The Ashburton immigrants, while disappointed all agreed that the swamp was a major step up from their former homes." 00:40:51 `addquote my sleep schedule is not actually random, but I'm not convinced it compresses well 00:40:55 1134) my sleep schedule is not actually random, but I'm not convinced it compresses well 00:41:50 Taneb: wtf 00:42:08 oerjan, from the Wikipedia page of the suburb I lived in when I lived in Australia 00:42:48 http://en.wikipedia.org/wiki/Mount_Waverley,_Victoria 00:44:46 monash, the ancient grounds of agora nomic 00:46:28 I could have met the founders of agora nomic!? 00:46:32 When I was 4!? 00:46:38 I've met waggie 00:47:49 me too! 00:48:14 -!- ^v has quit (Quit: http://i.imgur.com/MHuW96t.gif). 00:48:22 Taneb: well Steve i suppose. 00:49:41 agora looks disturbingly quiet. 00:55:38 `unidecode ™" 00:55:41 ​[U+2122 TRADE MARK SIGN] [U+0022 QUOTATION MARK] 00:56:06 very useful, this command 00:56:48 Wolfram Language will be the last programming language we ever need™ <-- i assume because it will cause the end of the world somehow. 00:57:47 `unicode TRADE MARK SIGN 00:57:49 ​™ 00:57:51 cool 00:58:04 how ™cool™ 00:59:30 alt gr+shift+8 01:00:27 ¾? 01:00:40 it's ™ here 01:05:16 -!- prooftechnique has quit. 01:06:52 compose-t-m 01:07:16 note to self: make a better compose setup 01:08:30 `unicode REGISTERED TRADE MARK SIGN 01:08:32 Unknown character. 01:08:39 soo fickle 01:08:50 `unicode REGISTERED SIGN 01:08:52 ​® 01:12:52 `unicode COPYRIGHT SIGN 01:12:53 ​© 01:13:03 copyright ⓒ 01:14:17 shachaf™ 01:14:52 `unidecode ⓒ 01:14:54 ​[U+0020 SPACE] [U+24D2 CIRCLED LATIN SMALL LETTER C] 01:17:29 Ⓒ 01:19:40 `run unidecode Ⓒ #oh no, shachaf is onto me 01:19:42 ​[U+24B8 CIRCLED LATIN CAPITAL LETTER C] 01:20:01 `unidecode 01:20:02 Traceback (most recent call last): \ File "/hackenv/bin/unidecode", line 4, in \ print u" ".join("[U+{0:04X} {1}]".format(ord(c), unicodedata.name(c, "DUNNO")) for c in " ".join(sys.argv[1:]).decode("utf-8")).encode("utf-8") \ File "/opt/python27/lib/python2.7/encodings/utf_8.py", line 16, in decode \ return codecs.utf_8_decode 01:20:07 `run unidecode 01:20:08 Traceback (most recent call last): \ File "/hackenv/bin/unidecode", line 4, in \ print u" ".join("[U+{0:04X} {1}]".format(ord(c), unicodedata.name(c, "DUNNO")) for c in " ".join(sys.argv[1:]).decode("utf-8")).encode("utf-8") \ File "/opt/python27/lib/python2.7/encodings/utf_8.py", line 16, in decode \ return codecs.utf_8_decode 01:20:21 ...am i on that stupid encoding still 01:20:30 Phantom_Hoover....................................................................... 01:20:35 `unidecode © 01:20:37 ​[U+00A9 COPYRIGHT SIGN] 01:20:39 c, DUNNO 01:20:45 yes 01:20:49 fuck's sake xchat 01:20:54 `run unidecode 01:20:56 Traceback (most recent call last): \ File "/hackenv/bin/unidecode", line 4, in \ print u" ".join("[U+{0:04X} {1}]".format(ord(c), unicodedata.name(c, "DUNNO")) for c in " ".join(sys.argv[1:]).decode("utf-8")).encode("utf-8") \ File "/opt/python27/lib/python2.7/encodings/utf_8.py", line 16, in decode \ return codecs.utf_8_decode 01:21:04 ok fuck this shit 01:23:06 -!- Taneb has quit (Ping timeout: 245 seconds). 01:23:29 -!- Taneb has joined. 01:29:27 i like how useless the aleph numbers are 01:32:03 -!- Phantom_Hoover has quit (Quit: Leaving). 01:35:05 -!- ggherdov has quit (Ping timeout: 252 seconds). 01:35:28 /nick LordEnglish 01:36:33 -!- lambdabot has quit (Quit: move to better server, be right back). 01:38:18 NOOO LAMBDABOT, IT'S A TRAP! 01:41:05 -!- lambdabot has joined. 01:42:08 @botsnack 01:42:08 :) 01:42:31 @let fibs = fix ((0:) . scanl (+) 1) 01:42:32 Defined. 01:42:36 > fibs 01:42:37 [0,1,1,2,3,5,8,13,21,34,55,89,144,233,377,610,987,1597,2584,4181,6765,10946... 01:42:48 huh 01:42:54 someone explain 01:43:08 i know the 0:1:zipwith-way 01:43:25 > scanl (+) 0 [a,b,c] 01:43:26 [0,0 + a,0 + a + b,0 + a + b + c] 01:43:59 myname: Isn't it more fun to figure it out yourself? 01:44:51 it kinda makes sense 01:44:58 what does fix do? 01:45:22 > fix f 01:45:23 No instance for (Debug.SimpleReflect.Expr.FromExpr a0) 01:45:23 arising from a us... 01:45:31 aw. 01:45:35 @src fix 01:45:35 fix f = let x = f x in x 01:45:45 aaaah 01:45:58 Y combinator? 01:46:05 right 01:46:27 funny 01:47:38 -!- KingOfKarlsruhe has quit (Quit: ChatZilla 0.9.90.1 [Firefox 25.0.1/20131112160018]). 01:47:43 > fix (expr . f) 01:47:44 f (f (f (f (f (f (f (f (f (f (f (f (f (f (f (f (f (f (f (f (f (f (f (f (f (... 01:47:59 -!- CADD has joined. 01:48:17 -!- ggherdov has joined. 01:53:03 -!- KingOfKarlsruhe has joined. 01:53:04 -!- CADD has quit (Quit: leaving). 01:53:19 -!- CADD has joined. 01:53:22 -!- CADD has quit (Client Quit). 01:53:49 -!- CADD has joined. 01:54:37 -!- oerjan has set topic: The channel of the chimæric hellos | The most corum, clargoint chait you could ever loofefl your slance in. | Magnus!!! | Koirammekokaan ei lennä? :( | https://dl.dropboxusercontent.com/u/2023808/wisdom.pdf | logs: http://codu.org/logs/_esoteric/ or http://tunes.org/~nef/logs/esoteric/. 01:57:21 -!- CADD has quit (Client Quit). 01:57:38 -!- CADD has joined. 01:57:38 -!- CADD has quit (Client Quit). 01:58:24 -!- CADD has joined. 02:01:03 -!- CADD has quit (Client Quit). 02:01:36 -!- CADD has joined. 02:02:28 CADD: FIX YOUR CONNECTION 02:03:07 -!- CADD has quit (Client Quit). 02:04:05 -!- CADD has joined. 02:04:29 -!- CADD has changed nick to Guest59952. 02:04:30 oerjan: its not my connection, im fixing my .irssi 02:04:55 -!- Guest59952 has quit (Client Quit). 02:05:41 -!- CADD_ has joined. 02:05:56 -!- CADD_ has quit (Client Quit). 02:09:53 huh 02:10:01 does CADD know about /reload? 02:14:17 -!- ^v has joined. 02:24:08 -!- Taneb has quit (Quit: Leaving). 02:27:22 POSSIBLY NOT 02:27:47 pizza! 02:33:33 oerjan: norwegian pizza? 02:33:37 i hear that's good 02:33:59 OKAY 02:47:12 -!- ^v has quit (Quit: http://i.imgur.com/MHuW96t.gif). 02:53:01 -!- ^v has joined. 03:11:53 -!- trout has changed nick to constant. 03:23:49 I've got a new book for the esoteric list http://www.amazon.com/exec/obidos/ISBN=0195079515/principiacyberneA/ 03:25:20 it will change your life! 03:27:59 Kauffman's recent work translates his biological findings to the http://en.wikipedia.org/wiki/Mind_body_problem and issues in neuroscience 03:28:27 wait, your second line makes me suspect you are being sarcastic. 03:30:03 heard enough bullshit like that in one life time thanks 03:30:24 I've actually read the book, it's interesting but not particularly meaningful 03:30:36 oh, wait, kauffman. so he's not like, insane, just... right. 03:30:56 not insane, just right, sounds like a good place to be. 03:31:45 it points out that if you make the fitness landscap complex enough, fitness doesn't really matter 03:32:11 @djinn f :: Maybe (b -> Either a b) 03:32:11 Cannot parse command 03:32:15 wat 03:32:21 @djinn Maybe (b -> Either a b) 03:32:22 f = Nothing 03:32:32 doesthiswork: like how 03:32:32 lambdabot: you're boring. 03:33:08 and that if you collect a set of more than K Boolean functions it is universal 03:33:09 oerjan: Your question is boring. 03:33:38 (by universal I mean you can construct any boolean function) 03:33:54 doesthiswork: that's technically incorrect. 03:34:04 and that is pretty much the entire 2 pound book 03:34:07 (see my beloved Post Lattice) 03:35:05 well, that reminds me i should pick up some systems biology stuff. 03:35:15 hm i wonder if it _is_ possible to have a set of infinitely many boolean functions where none can be expressed in the others. 03:35:35 hm no. 03:36:10 Kauffman wrote (January 2012) "No entailing laws, but enablement in the evolution of the biosphere," which aims to show that evolution is not law entailed, as is physics, and that, without selection, evolution enables its own future possibilities. 03:36:27 which I can't tell what the hell it means 03:36:29 because all the classes are finitely generated, and you must be able to express the generators in finitely many of them, which means you can express everything. 03:36:46 however is there really an upper bound K... 03:36:53 post lattice is cool 03:37:20 well, technically _if_ you generate everything, your set has 5 which do it. 03:37:34 *5 functions 03:39:01 which 5? 03:39:51 oh, it's on arxiv. 03:40:13 doesthiswork: for each of the 5 maximal subclasses, find a function that doesn't belong to it. 03:40:37 the same function can work for more than one, so it doesn't have to be the full 5. 03:40:37 bike: can you recommend me some systems biology books or papers? 03:40:50 ok 03:41:40 http://arxiv.org/abs/1201.2069 yeah i don't know what the hell they're on about 03:41:40 that is, find (1) a function which doesn't send all 0 to 0 (2) a function which doesn't sent all 1 to 1 (3) a function which isn't monotone (4) a function which isn't linear/affine (5) a function which isn't self-dual. 03:41:51 *send 03:42:18 doesthiswork: i've been recommended http://www.amazon.com/dp/1584886420/ 03:42:23 you will note that nand and nor don't do any of those, and so generate everything alone. 03:42:59 oerjan: thank you, now I know more than I did this morning 03:43:18 you're welcome! 03:43:52 the first one star review of that has some oter links, eheh 03:44:40 the university library has it, I'll take a look 03:45:58 oh wow, the abstract actually makes sense to me. 03:47:29 it says with physics you can predict the future at pretty well (some of the time). With biology who the hell knows 03:49:21 looking at the lattice diagram again, i cannot see any node other than the top which has 5 edges down - so it probably _is_ the case that if you have 5 functions none of which can be expressed in the others, they must generate everything. 03:50:25 although i'm not at the spot quite sure if each of the 5 classes misses a function that belongs to all of the others. 03:51:25 constant zero, constant one, identity, ... i guess and and or would let you build xor and negation 03:51:41 in which case it would simply be impossible to find 5 such functions. 03:51:41 Bike: I refuse to identify myself 03:52:54 I miss the List of Things That Don't Exist 03:52:55 :( 03:53:19 Sgeo: Your true love. 03:53:28 Bike: your list includes nothing non-monotone yet 03:53:30 wisconsin 03:53:52 so you definitely cannot build xor and negation 03:55:16 so... is that five functions that aren't complete 03:55:20 identity is assumed by default. 03:56:09 like, it's what you get if you start with a variable and don't use any functions. 03:56:33 so it's expressible without anything. 03:56:35 Sgeo: Like gruncheons and pritons? 03:56:51 aw. 03:57:23 bike: http://www.amazon.com/review/R7DHOCB2N9PYT/ref=cm_cr_dp_title/177-0981632-5731719?ie=UTF8&ASIN=0231075650&nodeID=283155&store=books 03:57:28 constant zero and constant one together take care of three of the classes, however. 03:57:47 Critics of reductionism have pointed to Kurt Goedel's 1931 "incompleteness theorem" (which shows that in any axiomatic formulation of, say, number theory there will be true theorems that cannot be established) as a contrary example, but this paradigm-shattering result has been largely ignored the scientific community, which has blithely persisted in its reductive beliefs. 03:58:12 http://english.lem.pl/home/bookshelf/how-the-word-was-saved 03:58:14 doesthiswork: time to misunderstand everything at once 03:58:24 Bike: hm i think you _may_ have detected a flaw in my argument, anyway. 03:58:50 brute force is the method of kings, oerjan 03:59:00 nolars, nightzebs, nocs, necs, nallyrakers, neotremes and nonmalrigers :'( 03:59:38 "Why are living things alive? As a theoretical biologist, Robert Rosen saw this as the most fundamental of all questions-and yet it had never been answered satisfactorily by science. " god damn it people 04:00:08 -!- CADD has joined. 04:00:13 "Since both the atom and the organism can be seen to fit that description, Rosen asserts that complex organization is a general feature not just of the biosphere on Earth-but of the universe itself." 04:00:27 -!- ^v has quit (Remote host closed the connection). 04:01:18 "One of his results is to show precisely why physics (including molecular biology) has little to say about life (and non-life)." 04:01:56 seriously jesus fucking christ unpredictability doesn't mean indeterminism 04:02:07 why are you reading this Bike 04:02:34 because i guess i'm an evil reductionist somehow 04:02:40 Bike: hm i think my argument that (5 independent functions => generate everything) holds 04:02:46 because I like to torture him :D 04:04:17 "He concluded, based on examples such as this, that phenotype cannot always be directly attributed to genotype and that the chemically active aspect of a biologically active protein relies on more than the sequence of amino acids,," and he's doing the "REVOLUTION: THING NOBODY ACTUALLY BELIEVES IS WRONG" thing that is so, so fucking irritating 04:04:33 because he(*)'s a sucker ((*) everyone) 04:04:34 this is really failing to convince me that there is anything to systems biology 04:04:48 well it's not just this guy 04:05:05 "Certain questions about Rosen's mathematical arguments were raised in a paper authored by Christopher Landauer and Kirstie L. Bellman which claimed that some of the mathematical formulations used by Rosen are problematic from a logical viewpoint. It is perhaps worth noting, however, that such issues were also raised long time ago by Bertrand Russel and Alfred North Whitehead" lol 04:05:15 Reductionism is a useful tool, but not always!!! 04:05:32 Dr. Rosen was one of those unfortunate scientists who worked on problems, that to the rest of his community were non-existent. 04:05:41 pst i'm not really a sole reductionist 04:06:04 "REVOLUTION: THING NOBODY ACTUALLY BELIEVES IS WRONG" <-- you could make that into an onion headline 04:07:44 -!- CADD_ has joined. 04:08:00 i think it just needs an "IN SCIENCE" after the REVOLUTION 04:08:37 -!- CADD has quit (Read error: Connection reset by peer). 04:09:28 i mostly think of systems biology as being like this one mostly informal book i read tbh 04:09:41 which was about cells-as-computers, which is the opposite of this rosen guy so fuck 'im 04:10:06 But he goes on and shows how the recursion in a function can be seen as constraints between (differential) equations, which he calls "chronicles". 04:11:37 ok bike what did you read? 04:12:28 http://www.amazon.com/dp/0300167849 04:12:31 dunno if it 'counts' 04:12:34 hm i think maybe you _cannot_ have 5 boolean functions that cannot be written in terms of each other. 04:13:10 because if one is self-dual and sends all 0 to 0, it will automatically send all 1 to 1. 04:13:11 goes over gene regulatory networks and protein stoichiometry equations and shit 04:13:18 for non-scientists 04:14:51 so you cannot get a function that is in not in P_1 and yet in all the others. which means whatever function avoids P_1, avoids one of the others, and so you need at most 4 of them to avoid all the maximal classes. 04:15:14 meanwhile bike's example shows that you _can_ have 4, so this is optimal. 04:15:35 just as i planned 04:15:48 congrats 04:17:24 yay! 04:23:56 According to this paper, the Pentagon once asked if nuclear bombs can be made to explode in the past. 04:24:16 that sound right 04:24:59 possibly my favorite 'systems' stuff is in ethology though. it's not really 'systems biology' but like lorentz had this adorable machine model made of waterwheels 04:30:29 he actually built it at one point iirc 04:31:57 konrad lorenz? 04:32:23 yea 04:33:23 or edward lorenz 04:34:10 i said ethology, didn't i 04:34:51 http://www.ace.gatech.edu/experiments2/2413/lorenz/fall02/ 04:35:08 but this lorenz has waterwheels and everything 04:36:05 that looks cool, actually. 04:36:22 there's a double pendulum set up in one of the physics buildings, it's fun to fuc with 04:47:28 why is it that interesting things are also interesting to crackpots? 04:48:41 -!- nisstyre has quit (Quit: Leaving). 04:52:32 I suppose because it is interesting in general. 04:53:54 AI is interesting but the AI channel here is a wasteland 04:56:52 the ais like to keep it that way >_> <_< 05:07:05 Is that what we're calling him now? 05:09:48 `? ais523 05:09:53 Agent “Iä” Smith is an alien with a strange allergy to avian body covering, which he is trying to retroactively prevent from ever evolving. On the 3rd of March, he's lawful good. 05:10:16 shachaf: no, we have no evidence that he is plural yet 05:17:36 `? Sgeo 05:17:38 Sgeo is a language nomad. (Not to be confused with a language monad.) He invented Metaplace sex. 05:19:30 3rd of March of what year? In what timezone? 05:19:52 Of the year 0/0 05:20:16 zzo38: i have always assumed it's every year. 05:20:30 and probably british standard time. 05:20:32 and whatever timezone ais is in, probably 05:20:56 which is probably the same as UTC that time of year 05:21:33 so... what is metaplace sex? 05:22:40 Two people repeatedly fainting without clothes 05:23:33 what 05:24:30 That's how I implemented a 'sex' option in Metaplace: Caused the participants to loop the "fainting" animation 05:24:56 should i know metaplace? 05:25:13 isn't it Yet Another Second Lifey Thing 05:25:31 http://en.wikipedia.org/wiki/Metaplace 05:25:40 Bike: yeah, in 2d, Flash-based 05:25:41 as long as there is no ncurses ui, i am not interested 05:25:54 It's dead now 05:26:07 It died less than a month after I invented metaplace sex 05:26:12 surprise surprise 05:26:18 lol 05:30:13 i'd love to have something like snow crashs metaverse with a terminal interfacee 05:34:27 wait so the part about Sgeo inventing metaplace sex is _true_? 05:34:51 Yes. 05:34:52 And what did ais523 invent, then? 05:35:07 zzo38: it doesn't say. 05:35:40 He invented the ability to learn multiple esolangs at once. Isn't there that news article about him knowing 25 languages? 05:35:54 define "knowing" 05:35:59 OK add that in, then. 05:36:11 can't be that hard 05:36:25 just learn any bf derivate and you are way ahead 05:36:29 No one said it was an accurate news article 05:36:34 erm, misread you 05:37:29 `run sed -i 's/sex/sex, thus killing it within a month/' wisdom/sgeo 05:37:34 No output. 05:38:08 fwiw, the part about killing it within a month isn't true, it's correlation-therefore-causation fallacy 05:38:27 It died within a month, but I didn't cause it 05:38:28 oerjan: :D 05:38:39 Sgeo: can you prove that? 05:39:20 myname: the entry was breaking #esoteric tradition with its accuracy. 05:39:43 hth 05:40:41 Sgeo: we prefer to believe. 05:41:07 `quote what sex looks like 05:41:09 313) sgeo do you actually know what sex looks like i am just checking here I think so 05:42:18 O, that is Sgeo, too. So I suppose it is related, then. 05:42:39 Yeah, elliott said that in response to me talking about metaplace sex 05:45:12 so, did you make a language about virtual sex? 05:46:19 sex can look like a lot of things 05:46:23 that's one of them 05:46:27 interestingly, the only mention of "sex" on the wiki is Taneb's userpage. 05:46:37 :D 05:46:49 maybe i should make a page only with the word sex in it 05:47:41 you make the awesomest palindromes, you don't need sex and you don't need sleep. you are a fucking superhuman :| 05:47:44 oh and you can transform into an elf 05:47:47 User:Oklopol (note: only one of these is true) 05:48:11 That palindrome sucked. 05:48:17 i think the "you don't need sex" is the true one. 05:48:34 i cannot tell whether oklopol believes it's the palindrome part, though. 05:48:36 Probably that is correct. 05:48:47 there is a great german palindrome i heard recently 05:48:51 Taneb has stated being asexual. 05:49:39 otoh maybe he's just on his way to the big breakdown. 05:50:24 ^ 05:52:06 "York student has psychic breakdown and starts fucking everything that moves, and some things that don't." you heard the headline here first. 05:52:18 wait this is britain. 05:52:28 psychic breakdown? like carrie? 05:52:30 "York student has psychic breakdown, starts fucking everything that moves, some things that don't." you heard the headline here first. 05:52:58 Bike: wait what is the correct phrase. 05:53:02 oh nervous 05:53:24 "York student has nervous breakdown, starts fucking everything that moves, some things that don't." you heard the headline here first. 05:53:33 https://lh3.googleusercontent.com/-P6h3xdZ34rE/ULVLrUmc3eI/AAAAAAAAZo0/JA2D-oN8Zjg/w506-h788/carrie_sriracha.jpg 05:53:38 ...Did this person just go through my old stackoverflow answer and add Unicode quotes everywhere? 05:53:51 http://stackoverflow.com/posts/13538351/revisions 05:53:59 ion: XD 05:54:19 However, I can tell you what I invented at least; I invented matrix accounting (while sitting in an accounting class in school, having nothing else to do, trying to think of how to use complex numbers in accounting in a way that doesn't violate GAAPs; I concluded that this is impossible). Yes, you can make up lies about it if you want, I suppose. 05:55:17 I seem to be one of only a handful of people who know how to do a certain thing with Varnish 05:55:25 *And* he moved punctuation inside quotes? 05:55:27 That's too much. 05:55:29 shachaf: i like how it states "typo" 05:55:32 What certain thing with Varnish? 05:55:53 myname: Well, apparently «`s -> (a,s)» was missing a `. 05:56:04 Passing data computed in the VCL to ESI subrequests 06:00:12 is – in "world-passing" even plausibly correct? 06:00:42 shachaf: ^ 06:01:04 My intuition says no, but you probably shouldn’t trust it. 06:01:41 I don't know if it's correct, but I don't like it. 06:02:05 I think I'll roll this back and add the missing ` myself. 06:03:18 same with error-prone, i guess. 06:05:19 `unidecode -- — 06:05:20 ​[U+0020 SPACE] [U+002D HYPHEN-MINUS] [U+002D HYPHEN-MINUS] [U+0020 SPACE] [U+2014 EM DASH] 06:05:39 changing -- to mdash is an improvement in my mind, though. 06:06:02 I don't like it. 06:06:15 I didn't write - -. I wrote --. 06:06:28 you don't like _anything_, shachaf. 06:06:36 I liked it the way it was! 06:06:44 OKAY 06:06:58 it's just the one thing that's definitely better in my mind, though. 06:07:28 and i'm neutral on the quote marks. 06:07:29 I think correct usage of "—" dictates that you don't put spaces around it. 06:07:31 Which is even worse. 06:08:12 shachaf: yeah wikipedia says you should use no spaces around mdash but spaces around ndash 06:10:28 Oh, he's actually changing semantic meaning too! 06:11:25 * oerjan didn't notice that. 06:11:45 "and also quite error-prone (if we accidentally try to read too far into stdin, the program will just block until the user types more in)." 06:11:48 into 06:11:51 "and also quite error-prone. (If we accidentally try to read too far into stdin, the program will just block until the user types more in.)" 06:12:01 That's some sort of semantics, anyway. 06:12:39 it's a small detail, like all the rest. 06:13:27 ...Is he using an en-dash in "as–is"? 06:14:41 hey, i'm not actually stopping you from rolling back. 06:20:30 -!- conehead has quit (Quit: Computer has gone to sleep.). 06:50:35 -!- nisstyre has joined. 07:02:21 * oerjan suddenly realizes that hangman must be hell to play in vietnamese. 07:03:26 _ _ _ (1 incorrect: ở) 07:09:23 -!- CADD_ has quit (Ping timeout: 260 seconds). 07:09:25 oerjan, or korean :) 07:10:22 is korean that bad if you use "letters" instead of "characters"? 07:10:42 hm i guess you'd have the problem of where to place the _'s 07:10:57 that's why we use only the initial letters (jamos, to be exact) in hangman-like quizzes... 07:11:09 copumpkin: Where were you yesterday when we needed your help with foo-spaces? 07:11:14 wat 07:11:18 ? 07:11:46 oerjan, it therefore feels like a hangman but without vowels 07:12:22 lifthrasiir: hm and that would be hebrew or arabic 07:12:56 haha 07:13:56 -!- Sprocklem has quit (Ping timeout: 245 seconds). 07:14:12 * oerjan wonders if indic languages do the same thing as korean, since vowels are like "accents" there 07:15:44 I can think of a few possible ways to make up a variant of hangman game for languages having much more letters of alphabet, whether it is due to accents, or other purposes. 07:16:38 the first page of google hits for hangman game "hindi" makes me suspect they only use it as an english learning tool 07:17:28 i suppose i might need to know the hindi words to search for the real thing. 07:17:31 -!- asie has joined. 07:35:47 -!- asie has quit (Quit: I'll probably come back in either 20 minutes or 8 hours.). 07:35:57 -!- doesthiswork has quit (Quit: Leaving.). 07:41:33 -!- zzo38 has quit (Quit: zzo38). 07:58:24 -!- asie has joined. 08:05:55 -!- Slereah has quit (Ping timeout: 272 seconds). 08:06:12 -!- Slereah has joined. 08:09:58 i dead 'since vowels are like "accidents" there', and read quite a bit of history in case something would explain what on earth you mean. 08:10:04 yes, i dead. 08:18:00 Need some suggestions for weird instructions 08:18:04 well... I don't need them 08:18:11 but I'm always looking for other ideas :) 08:19:52 mroman_: http://en.wikipedia.org/wiki/Apollo_Guidance_Computer#Instruction_set definitely CCS 08:22:06 or how about 'execute instruction in register' 08:23:23 Bike: Neat 08:23:26 That would work 08:23:37 as I have 16bit Registers and the longest instruction is two bytes 08:24:38 maybe something really silly, like have a register for how much the instruction pointer moves each cycle 08:24:41 execute code backwards 08:25:37 -!- asie has quit (Quit: I'll probably come back in either 20 minutes or 8 hours.). 08:26:06 good for debugging! or reliving the days of barrel memory 08:37:53 -!- asie has joined. 08:39:39 -!- nisstyre has quit (Quit: Leaving). 08:40:28 hm 08:40:41 I think I'm going to add Rational Number Support 08:40:53 i don't know if you're going for "weird instructions" as in crazy dumb shit or what though 08:41:09 rationals in hardware? 08:41:49 Yeah. 08:42:03 8bit Quotient, 8bit Denominator 08:42:24 Bike: Not really "crazy dumb shit" 08:42:31 just "crazy but still useful shit" 08:42:34 damn but i like the barrel thing :( 08:43:14 i guess rationals aren't too hard though, mostly you need gcd right 08:43:14 Since I don't have barrel memory reversing the control flow 08:43:17 would be crazy dumb shit 08:43:20 i was in a barrel once for a play 08:43:26 it was good 08:45:00 i guess it depends on what the processor's for. i mean presumably the vax had that evalpoly thing for a reason. 08:45:29 possibly just because horn evaluation is super easy but w/e. 08:48:18 What's that thingy called in english 08:48:26 where you do 4/8 = 1/2? 08:48:45 "reducing a fraction to lowest terms" 08:48:57 ok 08:49:00 so... 08:49:03 RDC then :) 08:49:03 or just "reduction" i guess. 08:49:06 -!- asie has quit (Quit: I'll probably come back in either 20 minutes or 8 hours.). 08:49:08 sounds good to me! 08:49:22 One has to do that manually 08:49:41 because it's probably slow if the CPU does it automatically all the time 08:50:53 i uh, dont' think i've ever cared about speed when i was using rationals, really. dunno how good the algorithms are. 08:51:04 plus like, when i use rationals i usually want infinite precision... 08:51:09 Although with 8bit/8bit I don't have a sign flag 08:51:19 Hm. 08:51:30 so i'm really wondering the use case here i guess? 08:51:32 unless I treat both 8bit values as signed 8 bit 08:52:40 Bike: To allow < 1 pixel calculations 08:52:50 i.e if you wan't to move 1/10 of a pixel per frame 08:52:53 *e.g. 08:53:04 Of course 08:53:04 mm, don't you usually use fixedpoint for that 08:53:09 You could also do that with integers 08:54:24 (It's a processor for some weird game console I guess) 08:55:08 -!- asie has joined. 08:55:20 suddenly wonders how that one snes coprocessor on... starfox? worked 08:55:52 The Super FX? 08:56:09 dunno. let it 3d render. 08:59:34 hi 08:59:49 yo 09:00:09 hangul is the best 09:00:57 what's an ul 09:01:11 is it a many-appendaged creature for the korean version of hangman 09:01:25 that would explain things. 09:01:48 shachaf: see one of the many benefits of hangul is that you can't mis-parse a word into syllables like that 09:02:10 kmc: i know, hangul is p. good 09:02:18 glad u agree 09:03:00 hang̈ul 09:37:14 -!- Taneb has joined. 09:49:20 -!- ais523 has joined. 09:54:27 Taneb: hi did you know the esolang wiki's sole mention of the word "sex" is on your user page hth 09:55:23 Heh 09:55:31 I did not 09:57:34 I also didn't know that 09:58:00 It's almost ironic 09:58:04 Clearly time for the "Sex" language, eh? (It's a brainfuck derivative with lewd words replacing the instructions.) 09:58:12 In that way that makes people think it's ironic but really not at all 09:58:13 fizzie: no 09:58:23 fizzie, there's already at least one language that is almost exactly thaty 09:58:43 . o O ( Ook! ) 09:59:03 http://esolangs.org/wiki/Fuckfuck 09:59:31 ah, 'sex' was too short for that one. 09:59:48 Ø.: V. good. 09:59:50 that explains it. 10:02:13 -!- nooodl has joined. 10:08:23 "[Ook] represents the first, although unfortunately not the last, in a long line of trivial Brainfuck command substitutions." Amen. ("Look, I came up with 8 tokens and now I'm the creator of an esolang!") 10:09:43 (whitespace deserves a honorable mention though) 10:10:00 I hate brainfuck derivatives with an exact 1:1 mapping to brainfuck 10:11:53 int-e: i thought of a whitespace derivate with zero width non-breaking space and zero width space 10:16:46 I guess one could play with control characters like U+202A (left-to-right) and U+202B, too. 10:16:59 are there matrices with only integers whose inverses also consist solely of integers? 10:17:04 except for the identity matrix 10:17:04 but it's sort of boring. 10:17:14 -!- MindlessDrone has joined. 10:17:40 mroman_: of course. A big class is all the triangular matrices with 1 on the diagonal. 10:17:50 int-e: yeah, the only interesting part is you had to use a hex editor to write 10:18:18 myname: ordinary brainfuck + some trivial sed, awk or perl. 10:18:19 -!- MindlessDrone has quit (Client Quit). 10:18:20 The inverse of 2x2 has a factor of (1/(ad-bc)) 10:18:36 So I guess a,b,c and d must all be multiples of (ad - bc) 10:18:51 ad-bc = 1 is not that hard to satisfy 10:19:07 No. That should be easy 10:20:27 although 10:20:42 what's a singular matrix? 10:21:06 You can start with the identity matrix and then swap rows, columns, or add a multiple of a row or column to another row and column; finally you may negate rows and columns. 10:21:17 "Singular matrix, a matrix that is not invertible" 10:21:18 ok 10:21:28 so not every Matrix with ad-bc=1 is invertible 10:22:18 oh wait 10:22:24 I accidentally did ad-bc = 0 10:22:34 which is exactly the criteria for it not being invertible 10:22:36 yeah 10:23:34 -!- carado has joined. 10:25:32 for the sake of completeness: ad-bc = -1 is also allowed 10:31:46 -!- nooodl has quit (Quit: Ik ga weg). 10:33:41 Good point 10:35:09 -!- MindlessDrone has joined. 10:36:24 (whitespace deserves a honorable mention though) <-- whitespace is not brainfuck-based. 10:39:02 mroman_: ad - bc is also known as the determinant of the matrix. 10:39:32 and yes, integer matrices with det M = +-1 have integer inverses. 10:42:47 that's if and only if, actually, because the inverse as determinant 1/det M which must be an integer for M^-1 to have integer entries. 10:42:53 *has 10:43:45 oerjan: oops. thanks! 10:44:57 Yeah. 10:45:12 But only integer matrices with M = +=1 have integer inverses. 10:45:22 *det M 10:45:36 That's at least what my math tells me 10:45:48 that's what i am saying! 10:45:48 a|(ad-bc) ^ b|(ad-bc) ... 10:45:58 adbc|(ad-bc) 10:46:05 and so on 10:46:13 which yields to 1 = x/(bc - ad) 10:46:39 oh 10:46:41 Yeah 10:46:47 Didn't read your 11:42 10:51:04 https://en.wikipedia.org/wiki/Adjugate_matrix#Inverses 10:52:04 "From this formula follows one of the most important results in matrix algebra: A matrix A over a commutative ring R is invertible if and only if det(A) is invertible in R." 10:52:32 mroman_: your notation is off though; (ad-bc) | a. (The symbol | can be read as "divides"). 10:52:37 note that +-1 are the invertible elements in the ring Z of integers. 10:58:00 -!- asie has quit (Quit: I'll probably come back in either 20 minutes or 8 hours.). 11:07:04 -!- oerjan has quit (Quit: leaving). 11:12:38 -!- impomatic has quit (Ping timeout: 245 seconds). 11:24:53 -!- nooodl has joined. 11:26:07 int-e: I know nothing about math notation :) 11:26:18 almost nothing. 11:27:40 Luckily converting between binary and hexadecimal is still considered by my university to be a very difficult task for students 11:28:09 so my lack of math skills does not matter 11:30:55 Do any of you guys know the C167? 11:35:16 anyway... to make a point short: it's apparentely hard to read specs and find out how to figure out the physical address of stuff 11:36:02 -!- yorick has joined. 11:45:17 -!- nooodl_ has joined. 11:49:04 -!- nooodl has quit (Ping timeout: 264 seconds). 12:00:51 "From this formula follows one of the most important results in matrix algebra: A matrix A over a commutative ring R is invertible if and only if det(A) is invertible in R." from that formula, the "if" certainly follows, for the other direction i guess you need to extend to commutative ring to a field or something? 12:01:32 and then because there's an inverse if it's nonzero and inverses are unique, the only if follows 12:02:07 *if the determinant is 12:02:08 oklopol: if A is invertible in R, then det(A) and det(A^-1) are both in R, and their product is one, so the determinant is invertible in R. 12:02:21 s/in R/over R/g 12:02:57 i'm just wondering why it follows from that formula 12:03:17 but err 12:03:36 det(A)*det(A^-1) = det(A*A^-1) = det(I) = 1 is an instance of that formula 12:03:38 like you said i guess, take the determinant from both sides 12:04:02 oh err 12:04:10 apparently it's explained right after 12:04:18 oh :) 12:04:59 " det(A)*det(A^-1) = det(A*A^-1) = det(I) = 1 is an instance of that formula" how is it an instance of that formula? 12:05:20 (although i'm not sure this question is very useful) 12:06:14 the formula was "A adj(A) = det(A) I" 12:07:34 my point is that indeed it should follow from that formula that A has an inverse in an extension of the ring where there is an inverse for det(A) 12:08:32 and err... okay dunno. maybe i should forget about this. 12:11:37 Ikea donated more to the Philippines recovery effort than China 12:12:15 :P 12:12:43 Maybe Ikea is the larger country ... 12:16:15 oklopol: I think you're right, it's not *that* formula; at least every argument that I see for invertibility of A implying that det(A) is a unit uses det(AB) = det(A) det(B), and we've seen that this identity is all one needs. 12:16:42 -!- Phantom_Hoover has joined. 12:24:00 perhaps after seeing that there is little incentive to try much else, because that's sort of obvious 12:24:37 although i don't think it's quite trivial to prove det(AB) = det(A) det(B) (maybe because i've never tried to prove it myself and it's quite an index hassle in most proofs i've seen) 12:25:26 -!- asie has joined. 12:27:11 -!- S1 has joined. 12:27:20 What is the opposite of bootstrapping 12:27:59 A safe shut down? 12:28:49 nah I mean in terms of programming paradigms and stuff 12:29:33 So, bootstrapping here means building a program in small components, right? 12:30:40 I understand it as bringing things up to more abstract layers. as in from machine code via assembler to script languages to modern programming languages 12:31:33 Look here: http://en.wikipedia.org/wiki/Bootstrapping#Software_development 12:31:41 I don't think it really has an opposite, then, only an absence 12:31:50 Which would be writing an agda compiler in machine code, I guess 12:32:14 k 12:35:43 although i don't think it's quite trivial to prove det(AB) = det(A) det(B) (maybe because i've never tried to prove it myself and it's quite an index hassle in most proofs i've seen) 12:35:56 if either A or B is singular then so is AB 12:36:13 who cares what the determinant is if it isn't 0 12:36:49 and how do you prove the determinant of AB is 0 iff that of A or that of B is? 12:37:45 or what do you mean by "singular" 12:38:13 -!- S1 has left. 12:38:22 'has determinant 0' 12:38:44 and how do you prove that if the determinant of A is not 0 and that of B is not 0 then also the determinant of AB is not zero 12:39:03 and how does that help with showing what we were trying to show anyway? 12:39:15 because if A and B are bijective then so is their composition? 12:39:28 okay i have a hunch you have no idea what we're talking about 12:40:23 we are trying to show that the invertibility of the determinant of A has something to do with the invertilibity of A 12:40:40 determinant not being 0 is _not_ what characterizes invertilibity of A 12:41:14 yes it... is, isn't it 12:41:37 "A matrix A over a commutative ring R is invertible if and only if det(A) is invertible in R." 12:41:45 this is what we're talking about 12:41:53 not fields 12:41:58 ahhhhh 12:42:16 well yes i joined well after any of that was said 12:42:25 EXCUSESSSSS 12:43:45 should you not call that something other than matrix then 12:43:55 like they call vector spaces over a ring modules don't they 12:44:21 perhaps 12:45:11 oklopol: To calculate det(A*B) one can use column operations on A (which are column operations on AB) and row operations on B to transform both A and B into upper triangular matrices, with the determinant unchanged or multiplied by -1 (from swapping rows or columns). This works over fields, e.g. Q. So now we have det(AB) = det(A)*det(B) over the rationals. We may regard the entries of A and B as variables, whence det(AB) =... 12:45:17 ...det(A)*det(B) becomes an identity of two polynomials of degree n in 2n^2 variables. The identity holds over the rational numbers, which means that the polynomials must be identical. They also have integer coefficients. Therefore, the identity carries over to arbitrary commutative rings. 12:45:23 usually you say "matrix A over a commutative ring R" i guess, but then matrix after you've said it a few times. 12:46:19 oklopol: one still needs to show that row and column operations preserve the identity, but that's *far* less messy than doing the full calculation for det(A*B). 12:46:31 let me think about that for a sec 12:48:23 okay i guess that works 12:48:46 i have only read proofs in the case of R and C anyway 12:48:49 R as in reals 12:49:00 C as in complicated numbers 12:49:33 i imagine row and column operations work pretty easily just from the permutations and signs and stuff definition 12:50:02 I really like the idea of using polynomial rings for transferring results from Q to commutative rings. 12:50:21 yeah 12:51:47 that's probably not something i would come up with using in a proof, or at least i would then be like "does it really work like this daddy?" 12:52:02 gtg play tennis 13:12:21 -!- impomatic has joined. 13:27:06 -!- yorick has quit (Remote host closed the connection). 13:32:30 -!- yorick has joined. 13:40:22 Is there a way to get a strike-through to render on text-based browsers, especially links2 13:44:06 -!- yiyus has joined. 13:44:41 why won't lex accept my #include o_O 13:45:20 Taneb, i assume it's like italics 13:47:27 mroman_: is it in the wrong part of the file? lex files are divided into sections, it'd need to be in the section appropriate to C includ files 13:51:47 wait 13:51:53 strdup is not actually in string.h 13:52:10 there's no strdup in C 13:53:02 indeed 13:53:10 it's kind-of trivial to write, though 13:53:53 strdup is gnu99 13:53:56 but not c99 13:53:58 i see 13:54:15 I did not know that 13:54:23 that's kinda surprising 14:10:00 -!- ais523 has changed nick to ais523\unfoog. 14:26:35 -!- mroman_ has quit (Read error: Operation timed out). 14:28:00 -!- mroman_ has joined. 14:38:44 -!- conehead has joined. 14:42:29 -!- Frooxius has quit (Read error: Connection reset by peer). 14:49:34 -!- asie has quit (Read error: Connection reset by peer). 14:51:18 -!- asie has joined. 14:53:58 There are very few (if any) standard C library routines that'd return allocated memory, except for malloc/calloc/aligned_alloc themselves. 14:54:54 And strdup-except-without-allocating-storage is basically strcpy. 14:57:25 an allocating sprintf would be nice... I think GNU or BSD has that 14:58:53 Yes, asprintf. 14:59:18 In both GNU and BSD, I believe. 15:00:54 GNU also has the 'a' flag for *scanf conversion specifiers, so that e.g. %as allocates a buffer of sufficient size, and returns a pointer to that. 15:01:28 (And getline, of course.) 15:07:25 -!- Frooxius has joined. 15:28:43 ah, strdup is posix at least 15:35:27 -!- asie has quit (Quit: I'll probably come back in either 20 minutes or 8 hours.). 15:39:59 fizzie: whoa. i never knew about those 15:42:39 -!- asie has joined. 16:41:43 I still have enough space for 15 Instructions... 16:41:49 But I'm running out of ideas. 16:43:13 hm 16:43:20 evaluate generalized hypergeometric 16:43:26 distribution? 16:44:06 Hm 16:44:13 "Count Bits" 16:44:17 That oughta be usefull 16:44:26 like count one bits? 16:44:46 Yes 16:44:51 101 -> 2 16:44:59 yeah, that's always nice to have 16:45:21 how about findfirstset while you're at it 16:45:46 index of the first set bit? 16:45:53 mmhm 16:45:57 FSB 16:46:02 :) 16:46:08 a touch of russian 16:46:18 I'm not opposed to it 16:46:24 but where would one need that? 16:47:30 it's floor of log 16:47:51 -!- asie has quit (Quit: I'll probably come back in either 20 minutes or 8 hours.). 16:48:09 -!- asie has joined. 16:49:29 Apparently the linux kernel's scheduler uses it to implement a priority queue as a bitfield 16:49:52 ok 16:50:05 then bsr and bsl it ist 16:50:11 (starting from right, starting from left) 16:53:45 http://dl.acm.org/citation.cfm?id=1592232 16:54:17 although I currently have no matrix or vector instructions 16:54:38 and no floats 16:54:40 floats are bad 16:55:37 what kind of instructions would you have just for vectors? if not just do X in parallel i mean 16:56:12 I don't know yet 16:56:18 also.. that paper seems to be paywalled 16:56:34 huh, is that so. 16:57:23 "Purchase article: $19" damn bloodsuckers 16:57:59 i got a copy if you want it. 16:58:58 I'd like to have a look at it 16:59:02 unless it's too illegal 16:59:05 then I rather don't. 16:59:17 i think intel will survive one copied paper. 16:59:30 lemme try dcc 17:00:50 bam. 17:00:56 nvm 17:00:58 I googled it 17:01:01 haha k 17:01:07 inurl:*.pdf 17:01:08 ;) 17:10:52 -!- oklopol has quit. 17:16:16 alright 17:16:24 Bike: Well, I have three register sets 17:16:29 with each 4 Registers 17:16:38 So that would easily allow 2x2 matrices 17:16:53 although 2x2 is probably not really helpful for 2D Graphics? 17:17:04 yeah... 17:17:12 all 2D transformation matrices I know are 3x3 17:18:27 however 17:20:24 -!- doesthiswork has joined. 17:21:09 with such small matrices would you even get any advantage from a dedicated instruction rather than multiplies and adds, though 17:21:13 -!- yiyus has quit (Read error: Connection reset by peer). 17:21:55 You can multiple a point with a 2x2 matrix to rotate it, if you count that as "helpful for 2D graphics". (Maybe not.) 17:21:56 all 2D transformation matrices I know are 3x3 17:22:30 can't you represent all euclidean motions of an n-dimensional space with an n+1xn+1 matrix 17:23:49 I think you need 4x4 for 3d rotation (quatranons) 17:23:55 Phantom_Hoover: So? 17:23:58 That's exactly the point 17:24:04 isn't the extra dimension to let you do translations (which aren't linear) 17:24:04 2D transformations require 3x3? 17:24:12 Bike, yeah 17:24:13 nb i don't know shit about grafix 17:24:27 It's the same as vector geometry 17:24:28 ;) 17:24:31 (it works because projective geometry) 17:24:39 Instead of points you move pixels 17:24:42 but i don't know projective geometry :( 17:25:13 well, with 2x2 you can do any linear transform, i guess 17:25:21 still not sure i see the computer-side point 17:26:38 i mean matrix×vector is gonna be four mults an two adds no matter what, right. 17:27:19 I don't think you can do translations with 2x2 matrices 17:28:06 no, you can't. translations aren't linear. 17:28:27 yep 17:30:19 http://en.wikipedia.org/wiki/Freivalds%27_algorithm wow this is the easiest algorithm ever 17:36:59 Nope. 17:37:02 That's [-] 17:37:52 -!- asie has quit (Quit: I'll probably come back in either 20 minutes or 8 hours.). 17:40:25 !bfjoust [-] 17:40:25 ​Use: !bfjoust . Scoreboard, programs, and a description of score calculation are at http://codu.org/eso/bfjoust/ 17:40:31 !bfjoust loop [-] 17:40:41 ​Score for mroman__loop: 10.5 17:40:46 wow 17:40:49 two digit score . 17:41:29 !bfjoust loop [-]<[+][>--[>+]] 17:41:32 ​Score for mroman__loop: 9.1 17:42:18 !bfjoust loop [-][>->-<<] 17:42:20 ​Score for mroman__loop: 10.4 17:42:23 -!- zzo38 has joined. 17:42:41 !bfjoust loop - 17:42:45 ​Score for mroman__loop: 6.8 17:44:41 !bfjoust ++[[]+][>+][-] 17:44:42 ​Use: !bfjoust . Scoreboard, programs, and a description of score calculation are at http://codu.org/eso/bfjoust/ 17:44:53 -!- asie has joined. 17:44:53 !bfjoust saladdressing ++[[]+][>+][-] 17:44:57 ​Score for mroman__saladdressing: 6.4 17:46:35 mroman_: [[]+] is the suckiest triplock ever :) 17:46:47 !bfjoust suckiest_triplock_ever [[]+] 17:46:51 ​Score for ais523_unfoog_suckiest_triplock_ever: 6.4 17:47:30 I thought it'd loop until it drops to zero 17:47:31 increment it 17:47:34 and then wait again 17:47:53 which should've prevented my from being killed 17:48:13 !bfjoust saladdressing [[]+++] 17:48:17 ​Score for mroman__saladdressing: 6.4 17:48:19 hm. 17:48:47 [] takes a cycle to detect the zero, and then it's been there for two cycles and you lost. 17:49:14 mroman_: it does do that, but it's a cycle too slow to avoid losing 17:49:37 this is intentional in the rules, that sort of program would be unbeatable if it actually worked 17:49:46 well, not 100% unbeatable 17:49:47 but pretty close 17:50:35 !bfjoust saladdressing >+++>+++>+++[]<+++[]<+++[] 17:50:39 ​Score for mroman__saladdressing: 1.4 17:50:42 Yeah 17:50:45 I can go suckier 17:52:38 -!- Phantom_Hoover has quit (Ping timeout: 245 seconds). 17:52:44 !bfjoust salad (>-)*9([-])*21 17:52:48 ​Score for mroman__salad: 0.2 17:52:51 Hoho 17:53:04 !bfjoust salad (>-)*9([-]>)*21 17:53:08 ​Score for mroman__salad: 5.0 17:53:36 How can that be worse than [-] 17:54:13 !bfjoust salad (>->+)*4([-]>)*21 17:54:16 ​Score for mroman__salad: 6.2 17:54:28 !bfjoust ten (>+)*9([[-.]]>)*21 17:54:30 ​Score for int-e_ten: 11.8 17:54:37 !bfjoust salad (>->+)*4([-]>[+]>)*11 17:54:39 ​Score for mroman__salad: 8.2 17:54:49 !bfjoust ten (>+)*9([[-]]>)*21 17:54:50 what's .? 17:54:52 ​Score for int-e_ten: 6.1 17:54:54 nop 17:55:03 takes a cycle :) 17:55:17 !bfjoust ten (>+)*9([-.]>)*21 17:55:20 ​Score for int-e_ten: 11.3 17:58:40 [-] defeats [+] almost all the time, and [-] half the cases, I think. 17:59:44 -!- oerjan has joined. 18:00:14 (but it's still interesting) 18:00:15 int-e: but it loses to . 18:00:31 anyway, that's what I call a "probabilistic lock", I need to add it to the wiki 18:01:24 against [+] it forms a perfect lock 100% of the time; against [-] it forms a perfect lock 50% of the time, a detectable lock 25% of the time, and loses 25% of the time 18:02:16 "detectable" meaning that [-][.this.code.runs.]? 18:02:52 int-e: yeah 18:03:00 !bfjoust salad (>>--)*4>([-]..+>])*21 18:03:03 ​Score for mroman__salad: 0.0 18:03:07 yeah 18:03:12 mroman_: unbalanced [] 18:03:14 !bfjoust salad (>>--)*4>([-]..+>)*21 18:03:17 ​Score for mroman__salad: 6.3 18:03:20 damn 18:03:22 !bfjoust salad (>>--)*4>([-].+>)*21 18:03:25 ​Score for mroman__salad: 6.3 18:03:35 mroman_: you don't need that . after the [-] 18:03:41 the - sets it to 0, that's one 18:03:47 !bfjoust salad (>>--)*4>([-]->)*21 18:03:47 the ] checks it's 0, that's two 18:03:50 ​Score for mroman__salad: 7.9 18:04:16 !bfjoust salad (>>--)*4>([-]->)*22 18:04:19 ​Score for mroman__salad: 7.9 18:04:21 !bfjoust salad (>>--)*4>([-]->)*23 18:04:24 ​Score for mroman__salad: 7.9 18:04:28 ok 18:04:29 hm 18:04:32 30 cells at max 18:04:32 so 18:04:43 22 should get me to cell 30 18:05:29 !bfjoust salad (>>-->+>-)*2>([-]->)*22 18:05:31 ​Score for mroman__salad: 9.5 18:06:04 !bfjoust one >+[]<[-] 18:06:08 ​Score for int-e_one: 6.2 18:07:02 !bfjoust one >+[]<.[-] 18:07:06 ​Score for int-e_one: 5.7 18:07:30 !bfjoust salad (>>-->+>-)*2>([-][<]+[>]>)*22 18:07:33 ​Score for mroman__salad: 1.7 18:07:45 [<] finds a non-zero cell, right? 18:07:46 hmm. need two more? 18:08:03 mroman_: no. it finds a zero cell, skipping over non-zeros 18:08:15 !bfjoust one >+[]<..[-] 18:08:18 ​Score for int-e_one: 6.8 18:08:22 !bfjoust one >+[]<...[-] 18:08:25 ​Score for int-e_one: 7.9 18:08:30 funny. 18:08:47 !bfjoust salad (>>-->+>-)*2>([-][<]+[>]>)*220 18:08:50 ​Score for mroman__salad: 1.7 18:09:07 !bfjoust zero .[-] 18:09:11 ​Score for int-e_zero: 9.8 18:09:12 !bfjoust salad (>>-->+>-)*2>([-]<[<]+[>]>>)*220 18:09:15 ​Score for mroman__salad: 3.5 18:09:19 !bfjoust salad (>>-->+>-)*2>([-]<[<]+[>]>>)*22 18:09:22 ​Score for mroman__salad: 3.5 18:09:29 hm. wait 18:09:51 !bfjoust salad (>>-->+>-)*2>([-]<[<]+[>]>)*22 18:09:53 ​Score for mroman__salad: 8.6 18:10:40 !bfjoust salad (>>-->+>-)*2>([-]<[<]-[>]>)*22 18:10:43 ​Score for mroman__salad: 8.0 18:10:52 !bfjoust salad >(>>-->+>-)*2>([-]<[<]-[>]>)*21 18:10:55 ​Score for mroman__salad: 5.2 18:12:37 !bfjoust pancake ->>>-->>+++>*10([-]>)*0 18:12:41 ​Score for FireFly_pancake: 0.8 18:13:55 http://sprunge.us/DJaG MATLAAAAAB 18:13:55 !bfjoust salad >>->+([>]->[-])*30 18:13:58 ​Score for mroman__salad: 5.3 18:14:47 wait 18:14:52 .[-] is suicide? 18:15:03 why does that give you more points than my non suicid ones :( 18:18:07 i'm going to guess it's because .[-] can get a tie or even win against a fast attacker 18:18:50 while the other ones have a severe chance of going out of bounds 18:18:57 Apparently an X server is required for "matlabpool local" to operate correctly. Possibly because (from what I recall) the JVM thing is somehow tied to the "desktop" system. 18:21:12 What is "matlabpool local" supposed to do? 18:21:38 !bfjoust zero (-)*128[-] 18:21:41 ​Score for int-e_zero: 10.5 18:22:29 !bfjoust zeroer (-)*-1 18:22:34 ​Score for oerjan_zeroer: 11.5 18:26:10 zzo38: It's related to the MATLAB Distributed Computing Server, which is a system for parallelizing MATLAB code. It has a concept of a "pool" where the workers come from; "matlabpool open local 4" tells it to make up a pool that just involves running up to 4 workers on the local machine. (Other pools may distribute the work into nodes in a cluster, and so on.) 18:38:07 !bfjoust salad >+++>(>(+)*4[<---]+++)*1000 18:38:11 ​Score for mroman__salad: 0.0 18:38:15 what 18:38:34 mroman_: it's the [<---] loop 18:38:43 you have nothing but nonzero value between there and your flag 18:38:48 so you end up falling off your own end of the tape 18:39:30 well 18:39:31 no 18:40:02 not on egojsout 18:40:18 ah right, no, cell 2 is clear 18:40:30 you fall off your own end of the tape when the opponent unclears it 18:41:26 yeah 18:42:25 huh. 18:42:32 and by 2 I mean 3 18:42:43 because I use 1-based indexing for BF Joust for some reason 18:42:50 maybe I should change my mental indexing system 18:43:58 I found something which is called SWIG says is for wrapping and interface generator for several programming languages, but it doesn't mention Haskell and SQL. 18:44:47 !bfjoust salad >+++>(>(+)*4[<---]+++>)*100([-]>)*21 18:44:50 ​Score for mroman__salad: 1.6 18:47:44 ais523\unfoog: but it needs a 3 on the tape - there is one in cell 2, but if that gets modified (and all bots on the ladder will eventually attack), then it trips over the left end very quickly. 18:48:57 !bfjoust zero >+[]<< 18:49:01 ​Score for int-e_zero: 1.9 18:49:27 !bfjoust zero >+++[]<< 18:49:31 ​Score for int-e_zero: 3.6 18:49:41 The definition of persistence, from #scheme@freenode: http://sprunge.us/SOgT 18:51:17 aah. i was hoping you would do the work 18:51:20 fizzie: I remember reading somewhere that one of Blizzard's early RTSes, I think it was Starcraft, was delayed while they tried to reach feature parity with something that one of their rivals had demoed 18:51:43 and it turns out that their rivals didn't have the feature at all, the demo was just a video recording rather than something actually playing 18:52:28 hu 18:52:35 why does [>+][-]> run over the tape? 18:52:43 [>+] should find a non zero cell 18:52:50 then zero it 18:52:55 and then move to the next one 18:53:03 After the +, pretty much any cell is nonzero, so the loop goes on and on. 18:53:08 mroman_: [> moves to the next cell, + sets it to 1, ] goes back to the start of the program 18:53:19 for [>+] to stop, the cell below the pointer must be zero. 18:53:30 so 18:53:35 how does one find a non-zero cell? 18:54:10 mroman_: (>[program here])*29 18:55:16 anybody here knows where to find this regex example of why ruby sucks at parsing with whitespaces? 18:55:34 ais523\unfoog: well _did_ blizzard reach feature parity anyhow 18:55:51 oerjan: yeah, they were the first to impl the features 18:56:57 I think that's called the "bait-and-switch". 18:57:43 (The "demo" of a nonexistent feature, that is.) 18:57:56 The definition of persistence, from #scheme@freenode: http://sprunge.us/SOgT <-- did they manage to ban him, alternatively did shachaf quit in disgust 18:58:04 -!- Deewiant has quit (Ping timeout: 264 seconds). 18:59:27 -!- myndzi has quit (Ping timeout: 240 seconds). 19:03:04 -!- myndzi has joined. 19:03:39 oerjan: I wasn't really following. My grep sees no bans, though no other signs after that 15th-day appearance either. Still, I'm sure that wasn't the last we'll see of them. 19:04:43 -!- augur_ has changed nick to augur. 19:05:12 mhm 19:06:10 !bfjoust nop []+ 19:06:14 ​Score for mroman__nop: 6.5 19:06:48 -!- asie has quit (Quit: I'll probably come back in either 20 minutes or 8 hours.). 19:07:54 !bfjoust zeroest (-.)*-1 19:07:57 ​Score for oerjan_zeroest: 10.2 19:09:12 !bfjoust salad >+>+[]<<[+] 19:09:16 ​Score for mroman__salad: 3.1 19:13:53 !bfjoust salad >+>+>+[]<[+]<[]<[-] 19:13:58 ​Score for mroman__salad: 0.3 19:14:25 !bfjoust salad >+>+>+[]<[+]<[]<[-](>[-])*30 19:14:30 ​Score for mroman__salad: 1.0 19:16:49 -!- Deewiant has joined. 19:17:03 fungot: hey, have *you* tried bfjoust? 19:17:03 FireFly: ( i remember something like rest or tail). new hardware is required usually for games, its fpu ran much slower than realtime to figure out how 19:17:26 fungot: I don't think you'd really need new hardware for bfjoust. 19:17:26 fizzie: these people really _are_ on crack. fnord::' demi-thread. if you have to code an attempt at adding " l'" to the wall with bug listings 19:18:49 fungot: You're crack. 19:18:50 mroman_: and that's a neat new language 19:18:57 Wow. Gee. Thanks 19:19:03 I always new all my languages were neat. 19:19:05 *knew 19:19:27 fungot: What about your languages? 19:19:27 mroman_: the primary documentation for emacs is done. 19:19:58 fungot: I'd rather have vim... 19:19:58 mroman_: i have a midland accent ( or in most cases it is best not to hang around those cobol programmers in their late thirties and early fnord 19:20:00 fungot: elisp isn't "your" language 19:20:01 FireFly: that is the fucking point. i really appreciate it. as i type. how nice. 19:20:39 I'm not sure what point fungot is trying to make.. 19:20:39 FireFly: y " is not a great essay writer the sentence choices seem odd. 19:23:09 fungot writes essays? 19:23:09 int-e: so much about coding, as i've been giving them some stuff to do. you don't have to 19:31:01 the sentence choices DO seem odd 19:32:56 how dare you question that 19:39:18 this is a funny quiz about undefined behavior in C http://blog.regehr.org/archives/721 19:41:52 !bfjoust [>+][>-] 19:41:53 ​Use: !bfjoust . Scoreboard, programs, and a description of score calculation are at http://codu.org/eso/bfjoust/ 19:42:08 !bfjoust blah [>+][>-] 19:42:11 ​Score for doesthiswork_blah: 0.0 19:43:27 !bfjoust blah2 [>-] 19:43:30 ​Score for doesthiswork_blah2: 0.0 19:43:44 -!- AnotherTest has joined. 19:44:14 doesthiswork: I'm disappointed that some of the questions are about specific implementations rather than C 19:46:09 he said that no one uses the standard, they all use implementations of the standard so questions about implementations are more meaningful 19:47:41 for the kinds of things you need to watch out for 19:53:25 i assume that is why he made me fail question 5, the bastard. 19:53:59 of _course_ i'd know the answer if he'd said only actual implementations counted. 19:54:03 *known 19:55:50 I remember reading that thing and finding a number of things to nitpick on. 19:57:05 Like in the explanation of Q4, it speaks of "promoting" an unsigned int to long, but that's (at least in nitpick mode) not a promotion, it's just part of the usual arithmetic conversions. 19:57:23 it's a nice touch that the introduction with all those assumptions gets hidden when you start the quiz 19:59:03 The signedness of char wasn't in the introduction, anyway. 19:59:15 that's what makes it fun :) 19:59:23 Oh, it says as much in the explanation. 20:00:08 -!- asie has joined. 20:02:57 I also disagree with Q10 explanation, which claims that "other values can be safely left-shifted", while in fact no negative values can. 20:03:52 -!- CADD has joined. 20:05:03 !bfjoust attack1 [>[-]+] 20:05:06 ​Score for ais523_unfoog_attack1: 3.8 20:05:47 -!- asie has quit (Quit: I'll probably come back in either 20 minutes or 8 hours.). 20:15:54 fizzie: Aw, I thought it would be about persistent data structures. 20:18:32 I also think Q18 is unambiguously wrong. It claims that, for int x, "(short)x + 1" is defined for all values of x, while in fact it's undefined, as acknowledged in the comments. 20:20:00 And the "I’ll stand by my answer since I’ve never heard of an LP64 compiler that doesn’t just truncate" cop-out in the comments is utter nonsense, given the "Make no assumptions about undefined behaviors" requirement of the introduction, and the way other questions (like overflowing a signed integer) are handled. 20:21:23 Oh, conversion to narrower integer was in fact implementation-defined? How weird. I guess in that case it's a little more defensible. 20:21:31 I was thinking that if sizeof int == sizeof short, then (short)x+1 overflows if x+1 overflows 20:21:54 c is fuked up 20:22:21 olsner: "sizeof (int) == sizeof (short)" is more clearly disallowed by the assumptions in the introduction, though. 20:22:54 yes, that was before I figured out which assumptions I was supposed to be making 20:24:14 -!- nooodl_ has quit (Read error: Connection reset by peer). 20:24:40 -!- nooodl_ has joined. 20:26:42 -!- asie has joined. 20:26:46 Do you know of any free graphics plotting software with language bindings for calling from SQL? 20:27:10 there's a thread on comp.lang.c about whether "f() + f()" is defined behaviour for all int-returning functions f (when f itself always has defined behaviour) 20:27:25 anyone want to take a guess at the currently accepted answer? 20:27:37 I assume it isn't? 20:27:53 -!- yorick has quit (Ping timeout: 246 seconds). 20:28:08 -!- yorick has joined. 20:28:45 ais523\unfoog: It probably works for most functions on most computers, I would think; maybe there are some cases allowed by the C standard where this doesn't work but I don't know how obscure these are 20:29:45 the answer sees to be "it's always defined in C11; it's also always defined in C89 as of Defect Report 87 and C99 as of Defect Report 287, the actual text of the standards is silent on the issue" 20:30:18 O, so it depends on the standard. 20:30:33 what happened to signed int overflows? are those not-undefined now? 20:30:50 http://www.vex.net/~trebla/humour/tautologies.html 20:30:51 olsner: I think it's not "about that". 20:31:05 olsner: At least based on what those defect reports address. 20:45:26 olsner: I think they're still undefined 20:46:00 let me check n1570 20:48:11 yeah, C11 says that overflow is undefined, and unsigned operations cannot overflow 20:50:18 * oerjan is pretty sure olsner meant in the f(x) + f(x) context 20:50:32 er, f() + f() 20:51:00 yes, that's what I was talking about 20:51:27 -!- KingOfKarlsruhe has quit (Quit: ChatZilla 0.9.90.1 [Firefox 25.0/2013102400]). 20:51:33 -!- oerjan has quit (Quit: Good that's settled, good night!). 20:51:53 oh, I wasn't thinking 20:52:35 bleh, are there any symmetrical binary operators that are defined no matter what their arguments? 20:52:51 bitwise operators aren't fully defined on negative numbers 20:53:07 + - * can all overflow, / and % can divide by zero 20:53:19 (and / can also overflow if you do INT_MIN / -1) 20:53:56 we can at least change the problem to "is f() + f() always defined if f() is always defined and returns an unsigned int?" 20:54:17 or simply assume that f doesn't return something that causes an overflow 20:54:41 yeah 20:55:22 In LLVM, at least, I think addition and subtraction are defined to wrap around unless you explicitly specify that overflow is undefined, in which case it is undefined. 20:55:59 in Verity, there aren't signed versions of + - * because it's always two's complement and thus the unsigned versions work just fine 20:56:04 so there's no issue with signed overflow 20:56:45 except in signed cast-to-fewer-bits, which is defined to simply take the low bits 20:59:38 Yes, that would work too (actually LLVM does the same thing; there is no separate signed and unsigned add command, although there are parameters to tell it to be signed or unsigned if you want overflow to be undefined) 20:59:59 -!- asie has quit (Quit: I'll probably come back in either 20 minutes or 8 hours.). 21:03:23 In Z-machine all arithmetic operators are signed and there are no unsigned versions. Overflow is supposed to be an error, but making it not error for addition and subtraction would help so that you can make address arithmetic. 21:05:40 But I did not think of division overflowing! Now I know. Therefore, DIV -32768 -1 S 0 (Frolg syntax) in Z-machine would also be error. 21:05:45 -!- carado has quit (Ping timeout: 252 seconds). 21:06:28 -!- MindlessDrone has quit (Quit: MindlessDrone). 21:06:29 sup 21:07:09 -!- asie has joined. 21:08:50 -!- ajf has joined. 21:24:23 -!- yiyus has joined. 21:24:55 http://steamcommunity.com/sharedfiles/filedetails/?id=195992856 21:25:48 -!- doesthiswork has quit (Quit: Leaving.). 21:25:55 "Human Revolution" sounds like an appropriate name. 21:26:11 (Now everyone knows your Steam Name.) 21:30:51 -!- asie has quit (Quit: I'll probably come back in either 20 minutes or 8 hours.). 21:33:06 So? 21:33:44 Well, they can... 21:33:50 I'm sure they can do something dastardly. 21:33:52 THEY CAN STEAM YOU 21:33:54 Friendly you in Steam. 21:33:56 STEEEAAAAAM 21:33:59 No "ly" in there. 21:34:14 There's no "lye" in your friend, at least under normal circumstances. 21:34:20 steamly you in friendship 21:35:27 -!- lambdabot has quit (Ping timeout: 252 seconds). 21:46:22 -!- prooftechnique has joined. 21:55:43 -!- AnotherTest has quit (Ping timeout: 252 seconds). 21:57:43 Oh god I watched like a whole anime this weekend and suddenly I'm noticing loads of people reblogging it on Tumblr 21:58:00 What anime? 21:58:08 Puella Magi Madoka Magica 21:58:27 Neat choic 21:58:28 *choice 21:58:45 Taneb: it is quite a popular one yes 21:59:15 MOE 21:59:49 I enjoyed it 22:00:15 One of my friends tried to get me to cosplay it but then we realised how expensive that'd be 22:01:46 (really expensive) 22:01:52 (also I'd probably have to shave) 22:03:59 Taneb: Go as Snake Quiet. Much cheaper 22:04:16 (Quiet Snake, I guess) 22:04:43 I already have a Jake English cosplay 22:04:49 http://nerdreactor.com/wp-content/uploads/2013/09/metal_gear_solid_v__big_quiet_boss_xd_by_zombiesandwich-d6lio0e-424x600.jpg 22:04:57 nsfw 22:04:58 ? 22:05:12 prooftechnique, I don't think I have the muscle tone for that 22:17:45 -!- asie has joined. 22:19:22 -!- Phantom_Hoover has joined. 22:22:49 -!- asie has quit (Ping timeout: 265 seconds). 22:24:09 -!- ajf has left. 22:40:10 int-e: lambdabot :☹( 22:42:47 `unidecode :☹( 22:42:49 ​[U+003A COLON] [U+2639 WHITE FROWNING FACE] [U+0028 LEFT PARENTHESIS] 22:43:00 Oh no, some kind of recursive frown. 22:43:07 Just nested. 22:43:22 If you zoom and enhance, I'm sure there's more frowns where that came from. 22:44:38 > let zoom [a,b,c] = [b]; let enhance "☹" = ":☹(" in (enhance . zoom) ":☹(" 22:44:45 int-e: lambdabot :☹( 22:45:23 Don't worry, I'm sure there would've been some kind of Unicode problem. 22:46:00 Yep. 22:49:44 `run echo 'zoom [a,b,c] = [b]; enhance "*" = ":*("; main = print ((enhance . zoom) ":*(")' | runghc 22:49:48 ​":*(" 22:50:07 * is practically a smiley face. if you squint 22:50:41 Or a massively huge tear 22:55:19 -!- ais523\unfoog has quit. 23:19:05 -!- Slereah has quit (Remote host closed the connection). 23:19:17 -!- Slereah has joined. 23:19:21 -!- Oj742 has joined. 23:25:22 I DON'T HAVE ANY MILK 23:25:49 I despise CAOS, but there's still an interesting property. In one way, it's like REBOL 23:26:18 a b c could be interpreted as a (b c) if needed 23:26:34 setv name "my variable" 5 23:26:46 setv takes a variable and an int and puts the int into the variable 23:27:00 name "my variable" refers to the variable on the targ called "my variable" 23:27:20 (targ is a piece of global state, blech, but the REBOL-like processing is still interesting) 23:31:41 -!- yiyus has quit (Read error: Connection reset by peer). 23:42:30 Taneb: I DO 23:42:58 shachaf, IS IT FULL FAT 23:43:32 http://heh.fi/tmp/mpiling_data.jpeg 23:44:02 Taneb: IS THAT THE SAME AS WHOLE 23:44:11 -!- Oj742 has quit (Quit: irc2go). 23:44:15 shachaf, YES 23:44:41 Taneb: THAT'S WHAT IT SAID ON THE COW 23:45:31 -!- nisstyre has joined. 23:45:58 shachaf, CAN I HAVE SOME OF YOUR MILK PLEASE 23:46:11 Taneb: SURE 23:46:29 Taneb: SEND ME A SELF-ADDRESSED STAMPED ENVELOPE AND I'LL POUR SOME MILK IN AND SEND IT BACK 23:47:01 shachaf, IS YOUR ADDRESS "SHACHAF, CALIFORNIA PROBABLY"? 23:47:27 THAT MIGHT GET TO ME 23:47:56 Hmm, I bet you could figure out how to send mail to me. 23:48:52 Taneb: PLEASE ALSO INCLUDE CADBURY FLAKE 23:50:48 @google tuscan whole milk 23:51:00 int-e: lambdabot :☹( 23:53:05 -!- Sprocklem has joined. 23:55:27 :😸3 2013-11-18: 00:16:01 http://i.imgur.com/ZTcgzOq.jpg 00:16:03 canada.jpg 00:21:09 `danddreclist 44 00:21:10 danddreclist 44: shachaf nooodl boily \ http://zzo38computer.org/dnd/recording/level20.tex 00:26:37 zzo38: You should add a PDF file so I can view it from my browser. 00:27:13 shachaf: No, if you want a PDF you do it yourself. 00:27:30 (I don't have the program to print it to PDF) 00:27:33 zzo38: I think you want "starts laughing", not "stars laughing". 00:27:35 Oh. 00:28:07 Thank you for noticing that mistake; I fixed it now. 00:29:52 -!- Sprocklem has quit (Ping timeout: 264 seconds). 00:30:05 And now I found out that I need to fix dungeonsrecording.tex to support more than five levels of spells; the current implementation will try to put them all in one row, which doesn't fit on the page very well. 00:30:24 zzo38, help I'm starting to play D&D 00:30:39 don't doitneb 00:30:55 Taneb: I cannot help you with too general requests like that. 00:31:17 I think I've made one of the hardest characters for a beginner 00:31:30 A freakin' pacifist 00:31:59 https://www.fanfiction.net/s/6466824/1/The-Pacifist 00:32:01 Well, make whatever character you want; that is OK. You can make a character which is difficult for you if that is what you prefer. 00:36:01 -!- Taneb has quit (Quit: Leaving). 00:57:49 -!- nooodl_ has quit (Quit: Ik ga weg). 00:59:03 I have been trying to find graphing software with language bindings for SQL, and cannot find some. 01:22:07 Why are there none? 01:31:07 -!- Phantom_Hoover has quit (Remote host closed the connection). 01:42:15 I could try to write one for PLplot 01:51:56 zzo38: matlab can talk to mysql servers 01:51:59 or 01:52:01 well 01:52:07 sql servers in general probably 01:53:03 quintopia: Well I mean calling graphing software from SQL programs, in SQLite 01:53:15 I don't mean accessing SQL servers from other programs 01:53:29 why would someone want to do that 01:54:36 It seems the most sensible way to me 01:56:00 That way you don't need to access it from other programming languages, if you have SQL data you can plot it by writing SQL queries, having aggregate functions that will plot the data they receive, and so on 01:58:32 an rdbms client is not and was never intended to be visualization software 01:59:51 -!- yorick has quit (Remote host closed the connection). 02:02:32 shachaf : nope 02:03:04 But SQL can import foreign functions too, like other programming languages can. 02:08:19 I want to be able to plot data that has been filtered and manipulated and stuff too, and grouped, and various other things that are done in an SQL query. 02:13:37 ski: ? 02:18:11 * shachaf leaves for a while. 02:19:57 What I want actually is a SQLite extension library which provides aggregate functions to plot graphs of the data they receive. 02:27:09 ski: did you see the longversation about chu spaces in here yesterday 02:33:02 -!- doesthiswork has joined. 02:40:59 Oh. 02:41:48 My 02:53:07 hope we don't die 02:53:12 * quintopia starts chanting 02:58:49 -!- ^v has joined. 03:01:35 Die of what? 03:03:10 grue 03:03:36 O, I thought you don't want to die of chanting. 03:11:45 we're more likely to die of chatting 03:30:13 -!- JesseH has left ("Leaving"). 03:48:45 -!- conehead has quit (Quit: Computer has gone to sleep.). 03:51:40 -!- ruddy has quit (Ping timeout: 245 seconds). 04:13:05 -!- CADD has quit (Quit: leaving). 04:15:17 -!- prooftechnique has quit. 04:38:27 -!- oklopol has joined. 04:45:14 How common is it for programs to use true to mean failure and false to mean success? In the Z-machine, the PRINTR instruction prints a string, followed by a line break, and then returns true. Due to this, the program I am writing uses true to indicate failure. 04:49:41 0 is a "nothing failed" return value for most processes 04:49:48 which would also be considered false in most languages 04:49:57 but not in shell script :) 04:50:27 this is based on the notion that there's one way to succeed but many ways to fail 04:52:26 I keep forgetting to post to SO 04:52:48 Incidentally, if commercial support gives you a solution to something, is that supposed to be ... proprietary? 04:52:51 kmc: sounds like the Anna Karenina principle 04:52:54 Especially if others have similar questions? 04:53:30 Well, in the Z-machine, zero is still considered false and one is considered true 04:57:24 doesthiswork: yes 04:57:57 in Rust you used to be able to create a bool which is neither false nor true 04:58:00 that... got fixed 04:58:21 (Although I suppose this isn't much more than a convention, since any actual instructions that test less/greater/equal/flags/etc just branch instead) 04:58:28 are you able to create a bool that is both? 04:58:54 they refuse to be limited by your 1-dimensional thinking 04:59:13 (Also, routine 0 always returns 0, and the SAVE/RESTORE opcodes return 0 or -1 on failure, and other numbers on success.) 04:59:37 doesthiswork: no 05:00:14 philistines! 05:00:32 zzo38: mmap(2) returns -1 rather than 0 for errors, because one could map a page at 0 but one couldn't map a page at -1 unless the page size is 1 05:00:53 does POSIX allow a page size of 1? that would make so many things so much nicer 05:00:55 (this is the place to drop a "laws of form" reference) 05:01:27 kmc: Ah, OK, but I mean a function that returns a boolean 05:02:09 kmc: I suppose if it would be allowed, then it should be prohibited for the page to start at -1 in order for that to continue to work. 05:02:10 also I was wondering the other day if there are programs which map the same pages 2 or 4 or 8 times so that tag bits in pointers can be used without needing to mask them out 05:05:03 Would that work? 05:06:18 why wouldn't it? 05:06:54 I don't know how the page mapping works, so I wouldn't know much about it 05:07:11 i don't think i understand this mechanism, explain? 05:07:15 well, you would still have to mask when taking offsets or comparing pointers for object identity 05:07:31 -!- asie has joined. 05:09:20 Bike: you would map the same physical page at (e.g.) 0x10000 and 0x11000 so that a pointer into either region works the same, and then you can use that bit 0x1000 to store some associated information that can be accessed without dereferencing the pointer 05:10:15 pointer tagging tricks are common but generally you have only a single mapping and so you need to mask off the tag bits first before dereferencing 05:10:52 -!- aloril_ has quit (Read error: Connection reset by peer). 05:10:55 oh, i see. 05:10:57 They don't seem to work necessarily so well on all computers necessarily, since they might operate differently. 05:11:08 i've heard of having different regions for different types to avoid tagging but not that. 05:11:14 I do not expect to guaranteed to work it correctly. 05:11:29 fun fact: 16 of the virtual address bits in a current AMD64 CPU are ignored and could be used for such tags without masking, except that the architecture explicitly forbids it 05:11:38 for forwards compatibility reasons 05:11:57 -!- asie has quit (Ping timeout: 246 seconds). 05:12:53 questionable decision imo 05:13:49 Allocating different regions ahead of time and checking if the pointer is in range would seem to work more consistently, although then you need to fix the amount of available memory when the program is starting. (But I don't know if this would work on the "Future Systems" 128-bit processor and other really strange things) 05:14:06 how hard would it be to have a "I don't intend to use more than 256 TB of address space" control flag 05:14:46 there are a lot of people who need speeeeeeeeed and don't mind writing unportable code or using a nonstandard ABI 05:15:28 another fun fact: ARM uses the low bit of the program counter basically as a tag to say whether it's in ARM or Thumb mode 05:15:49 (instructions on ARM are at least 2-byte aligned) 05:15:55 this is nice because function calls automatically save/restore that mode too 05:16:44 If you want to write non-portable codes, you could at least partially write them in assembly language, and/or use C preprocessor macros to detect what computer it is running on 05:17:20 yes 05:17:28 that is typically done 05:18:06 But if I am writing a program in C, I rarely want unportable codes anyways 05:20:21 Protected mode adds too many complications anyways, I think. Some of these things could still be done in simpler ways, and other things 05:25:29 -!- conehead has joined. 05:26:09 what's with people who have a television on at night making noise 05:26:22 it's snowin 05:26:22 g 05:26:39 can there just not be such people in the world anymore 05:27:22 kmc: Yes, I've heard of such behavior. 05:27:53 I think maybe the Xbox did something like that? 05:28:10 okay before it was snowing but now it's snowing like a motherfucker 05:30:06 i was just trying to sleep and now i hate all people within a 5km radius 05:30:55 what did the xbox use it for 05:30:59 -!- asie has joined. 05:33:45 Hmm, maybe I'm thinking of something else. 05:40:11 -!- aloril has joined. 05:41:20 kmc: Ah. The Xbox 360 has 64-bit addresses but only 512MB of RAM, so the upper 32 bits are used as flags by the L2 cache. 05:41:34 cool 05:41:36 E.g. whether memory is encrypted. 05:41:43 that's physical address bits right? 05:41:58 Oh, yes, true. 05:42:07 i recall that was used for some hax 05:42:30 http://www.youtube.com/watch?v=uxjpmc8ZIxM was a nice talk about it. 05:44:13 off to japan, ttyl 05:44:51 -!- zzo38 has quit (Remote host closed the connection). 05:49:51 kmc: i like how the bug was in the syscall handling code 05:53:38 anyone here feel like translating TAPASM to syntactically correct english? 06:04:18 A hospital room is the perfect place for the data center. http://steamcommunity.com/sharedfiles/filedetails/?id=196098420 06:04:20 -!- conehead has quit (Quit: Computer has gone to sleep.). 06:28:03 -!- carado has joined. 06:39:57 -!- carado has quit (Ping timeout: 252 seconds). 06:55:09 -!- doesthiswork has quit (Quit: Leaving.). 06:56:23 -!- heroux has quit (Ping timeout: 260 seconds). 07:15:22 ski: Do you know lots of things about Chu spaces? 07:16:22 no 07:17:11 ran into them when looking at linear logic papers 07:17:44 Related to de Paiva's thing? 07:17:53 yes 07:18:42 Do you know how I can relate them to (a) topological systems and/or (b) adjunctions? 07:20:11 Also, do you know anything about the category whose objects are categories and whose arrows are adjunctions? 07:23:10 -!- doesthiswork has joined. 07:23:36 (Valéria de Paiva,Peter Wojtáš, whence "PV") 07:23:56 sorry, no details :/ 07:24:16 -!- FreeFull has quit. 07:25:08 -!- doesthiswork has quit (Client Quit). 07:26:58 -!- asie has quit (Quit: I'll probably come back in either 20 minutes or 8 hours.). 07:33:16 -!- ^v has quit (Remote host closed the connection). 08:14:30 -!- oerjan has joined. 08:19:07 Bike: Execute In Register with an Execute in Register Instruction in the Register would be an endless loop 08:19:48 halt and catch fire :) 08:20:40 you mean never halt hth 08:21:28 (Now everyone knows your Steam Name.) <-- well all the 3 who visited the page. 08:22:13 iirc, on s/390 the execute in register instruction doesn't accept another execute-in-register instruction 08:23:01 olsner: how non-orthogonal 08:23:28 (all instructions should be orthogonal to themselves, obviously!) 08:26:22 there should be an ISA where instructions have 90 degree angles to each other... maybe call it a vector processor 08:26:33 -!- carado has joined. 08:28:48 @tell Taneb I DON'T HAVE ANY MILK <- ME NEITHER 08:28:57 eek 08:29:07 eek? 08:29:08 wasn't there a language with stuff like "turn right"? 08:29:19 olsner: lambdabot has been kidnapped! 08:29:38 oh noes! 08:29:39 myname: Logo, also karel the robot 08:29:47 Many (most?) 2D languages have "turn right" too. 08:29:59 that's not what i meant 08:30:13 literally "turn right" as a command 08:30:15 fizzie: technically don't they have "turn in this direction i'm pointing" 08:30:32 myname: i _think_ karel the robot may have had that. 08:30:37 and if your instruction pointer is moving from top to bottom, you have to write one letter at a column 08:30:41 oerjan: A number also do it relatively. Like the Funge-98 ]. 08:30:54 aha 08:31:21 -!- carado has quit (Ping timeout: 272 seconds). 08:31:25 (And I suppose you could argue that ">" is still "turn right" even though it's absolute, it's all about the definition of "right".) 08:31:27 myname: wat "one letter at a column" 08:31:40 at a line 08:31:41 <_< 08:32:16 (Whoops, lunchtime.) 08:32:17 hm actually it had turnleft and turnright is the first example procedure in https://en.wikipedia.org/wiki/Karel_(programming_language) 08:33:19 oerjan: alight! 08:33:47 http://codepad.org/m5LlaE5D 08:34:00 ^- as of now. all 128 instruction are taken :) 08:34:05 http://esolangs.org/wiki/Alight 08:35:23 oh right 08:36:04 although I could make shl,shr use Reg[src] for how many shifts to be performed 08:36:32 myname: itym "per line" 08:36:50 but that would be stupid 08:38:32 better replace them with a generic bit manipulation instruction where the src register encodes what's to be done :) 08:41:48 http://heh.fi/tmp/mpiling_data.jpeg <-- my new laptop is seriously sucky on dark pictures :( 08:42:28 The relevant part isn’t darkened. 08:43:10 putting full brightness on isn't enough, at the same time i need to put brightness on 50% not to hurt my eyes on ordinary black on white text... 08:43:35 Try adjusting the gamma. 08:44:17 i have no idea how. and all i could find about constract was claims about "laptops don't usually have it". 08:44:26 *contrast 08:44:58 Try xgamma -gamma 1.2 08:45:08 * oerjan swats ion -----### 08:45:26 i'm on windows. 08:45:40 * ion swats oerjan with a fish 08:46:32 @google windows adjust gamma 08:47:16 olsner: There really is a CPU that can decode an instruction in a register and execute it? 08:47:38 Why did IBM do that? 08:47:51 oh i found something! 08:47:57 Perhaps Hitler requested that. 08:50:43 Ok 08:51:06 I thought one should only pull the Hitler card in a vigorous discussion one is about to loose because running out of useful arguments 08:51:21 and to possibly troll the opponent discusser. 08:52:31 That was a completely reasonable guess given that IBM did business with him. 08:54:03 Really? 08:54:21 Isn't that uhm... treason? 08:54:36 Seeing as IBM is probably an american or ukanian company 08:55:30 ion: thanks gamma helped 08:55:44 * oerjan tries with 1.5 for now. 08:57:15 oerjan: http://www.lagom.nl/lcd-test/gamma_calibration.php 08:58:08 oh 2.2 is the standard? 08:58:35 Don’t set the value to 2.2, set the value to whatever makes the bars say 2.2 09:00:23 mroman_: they _may_ have stopped in 1942 or so? 09:01:06 Yeah. But the war started 1939? 09:01:18 ok 09:01:21 not with the US 09:01:27 checks out 09:07:23 mroman_: "ukanian" is somewhat liable to misreadsings 09:11:57 damn those battletoads 09:12:03 I can't get that theme out of my head :) 09:12:13 elliott: yeah... 09:17:30 -!- nisstyre has quit (Ping timeout: 245 seconds). 09:35:02 gah my eyes 09:51:23 -!- heroux has joined. 09:51:33 ah well. I just reserve one instruction as a marker for a secondary instruction set 09:51:42 that'll give me another 128 instructions once I need them 09:56:29 256 actually 10:01:03 what's with people who have a television on at night making noise <-- devil worshipers hth 10:03:10 elliott: plz take back lambdabot this new guy is obviously not up to the responsibility thx 10:08:12 shachaf: the same goes for people with barking dogs 10:08:41 see: my neighbor in some not entirely determined direction 10:20:39 -!- heroux has quit (Ping timeout: 246 seconds). 10:22:43 -!- heroux has joined. 10:38:41 oerjan: Background noise 10:38:51 I do that too 10:38:54 -!- lambdabot has joined. 10:39:06 I let streams run in background while working 10:39:15 (tv streams) 10:39:21 but not a night :) 10:39:23 *at 10:50:54 -!- darklust has joined. 10:58:41 "IEEE's core purpose is to foster technological innovation and excellence for the benefit of humanity." 10:58:47 Oh, I thought they were in it to make money. 10:59:17 -!- heroux has quit (Ping timeout: 248 seconds). 10:59:57 -!- heroux has joined. 11:03:10 Much expensive 11:03:11 So wow 11:03:48 `relcome darklust 11:03:53 ​darklust: Welcome to the international hub for esoteric programming language design and deployment! For more information, check out our wiki: . (For the other kind of esoterica, try #esoteric on irc.dal.net.) 11:04:17 >DalNet still exists 11:05:11 I'm here for brainfuck and brainfuck accessories 11:05:20 good, good. 11:05:36 your nick made me suspicious :P 11:07:39 @botsnack 11:07:39 :) 11:07:46 poor, abused little thing. 11:07:56 @hug lambdabot 11:07:56 http://hackage.haskell.org/trac/ghc/newticket?type=bug 11:36:40 -!- Taneb has joined. 11:38:55 -!- yorick has joined. 11:57:56 -!- oerjan has quit (Quit: leaving). 12:05:45 mroman_: so's jump rel 0 12:07:26 fizzie: But who's looking at money when humanity is at stake?! 12:09:30 Hmm, this quote that I read yesterday seems related somehow: "It is not heartless to say that if every human life is actually priceless, then it follows that there will never be enough money." 12:16:12 -!- carado has joined. 12:18:40 -!- MindlessDrone has joined. 12:40:22 Bike: Yeah. But that's a different loop :) 12:41:01 execute in register would produce a loop inside the execution circuitry 12:42:07 -!- Sgeo has quit (Read error: Connection reset by peer). 12:42:52 i.e uninterrutable 12:43:50 depends on the implementation of course 12:45:03 If it had interrupts 12:49:22 I remember there being some debate on the corner cases of the semantics of Funge-98's "k" instruction, which repeats the next instruction N times. 12:53:54 "some debate" is an understatement 12:57:51 ooh! I guess I can ask a similar question for x86: what happens if a rep stosb modifies the rep or stosb opcodes? 13:01:34 According to http://www.woodmann.com/forum/archive/index.php/t-12442.html "when an interrupt is generated, CPU stops executing overwritten REP STOS/MOVS" 13:05:00 Deewiant: nice. can you parse this? "meanwhile, some CPU have a bug. they executes CLD commands _before_ overwritten REP STOS/MOVS will be stopped or finishes. as result, REP STOS/MOVS changes the direction and hits the memory not supposed to be written." 13:05:03 -!- MindlessDrone has quit (Ping timeout: 252 seconds). 13:05:40 -!- boily has joined. 13:05:46 -!- metasepia has joined. 13:06:14 -!- boily has quit (Client Quit). 13:06:16 -!- metasepia has quit (Remote host closed the connection). 13:06:28 int-e: Seems mostly clear except that I don't know where the CLD is coming frmo 13:06:31 from* 13:07:03 -!- boily has joined. 13:07:07 -!- metasepia has joined. 13:09:09 ok, I guess it's just too weird to really believe :) 13:11:22 good unbelievable morning! 13:11:41 -!- Taneb has quit (Quit: Page closed). 13:13:45 -!- asie has joined. 13:16:54 -!- nisstyre has joined. 13:18:42 -!- MindlessDrone has joined. 13:42:16 -!- nisstyre has quit (Quit: Leaving). 13:50:29 -!- oklopol has quit (Ping timeout: 248 seconds). 13:52:34 -!- ski has quit (Remote host closed the connection). 14:02:37 -!- asie has quit (Quit: I'll probably come back in either 20 minutes or 8 hours.). 14:08:36 -!- zzo38 has joined. 14:22:36 -!- asie has joined. 14:27:49 -!- asie has quit (Quit: I'll probably come back in either 20 minutes or 8 hours.). 14:28:21 -!- chatamici has joined. 14:28:34 -!- chatamici has quit. 14:30:16 -!- chigipuga has joined. 14:31:21 -!- chigipuga has quit (Remote host closed the connection). 14:40:16 -!- ecolin has joined. 14:41:06 -!- ecolin has quit (Read error: Connection reset by peer). 15:28:39 -!- FreeFull has joined. 15:48:15 -!- mrhmouse has joined. 15:56:05 -!- Sprocklem has joined. 16:14:10 -!- conehead has joined. 16:20:35 -!- nooodl has joined. 16:24:55 -!- asie has joined. 16:46:31 Hello 16:47:15 What the hell is the .stack header supposed to be in 8086? 16:47:52 I can't seem to find a tutorial that actually says what it does 16:47:53 define the stack size? 16:48:15 Thanks. 16:53:19 -!- Sprocklem has quit (Ping timeout: 272 seconds). 16:53:54 -!- Sprocklem has joined. 17:02:13 -!- asie has quit (Quit: I'll probably come back in either 20 minutes or 8 hours.). 17:11:11 -!- yiyus has joined. 17:14:04 -!- Koen_ has joined. 17:27:53 -!- asie has joined. 17:28:37 -!- ruddy has joined. 17:28:46 ruddy, where have you been? 17:28:46 THAT'S WHAT IT SAID ON THE COW 17:29:14 -!- oklopol has joined. 17:35:26 -!- augur has quit (Remote host closed the connection). 17:36:00 -!- augur has joined. 17:40:49 -!- augur has quit (Ping timeout: 272 seconds). 17:44:35 hi ruddy 17:44:35 your IP is showing 17:44:53 who's ruddy and why is it quoting me 17:44:54 day is in his late 20s 17:45:08 If register access is faster than memory access, why are there so few of them? 17:45:25 I thought register were memory 17:45:26 Is it a problem of price, complexity? 17:45:33 The fear that they would go unused? 17:45:45 They are, but not RAM memory or disk memory 17:45:47 @messages 17:47:13 @tell boily I moved to paris but there was not much to do there until tuesday 19th, november, so I kept moving back and forth between paris and the suburbs and most of the time I left the computer at the other place 17:47:14 Consider it noted. 17:47:40 @google memory hierarchy 17:47:41 http://en.wikipedia.org/wiki/Memory_hierarchy 17:47:41 Title: Memory hierarchy - Wikipedia, the free encyclopedia 17:47:50 ruddy: Your computer may be broadcasting an IP address! 17:47:51 i doubt i do 17:48:07 I am in Paris! 17:48:21 fizzie: THAT'S WHAT IT SAID ON THE COW 17:48:36 Is "expensive" in price or in electricity? 17:48:56 fizzie: http://dl.dropboxusercontent.com/u/13786158/portraits/shachaf.png 17:49:01 Or whatever else 17:49:24 shachaf: Those pictures are the best. 17:49:55 Slereah: tell me more 17:50:01 About what 17:50:14 I wonder what's the highest number of registers on a processor 17:50:14 about you being in Paris! 17:50:17 Well 17:50:20 I am in Paris 17:50:24 Near Massy Palaiseau 17:50:27 Since september 17:50:38 To do some computer school thang 17:50:46 Slereah: http://people.freebsd.org/~lstewart/articles/cpumemory.pdf probably has good answers to your questions. 17:50:53 Thx 17:50:56 what's the name of the school? 17:51:06 CFA-AFTI 17:51:11 oh 17:51:11 It's more than just an issue of expensive. 17:51:15 I've got a friend there 17:51:19 LET'S MAKE A GIGABYTE OF REGISTERS 17:51:25 Whom! 17:51:28 Maybe I know him 17:56:48 back from lunch, and I haven't moved to Paris. 17:57:06 Good thing 17:57:09 Paris is terrible 17:57:25 hi boily 17:59:17 Koen_: bonjour! 17:59:51 I went to Paris once, ten years ago. can't say I remember much of it. 18:01:02 ~metar CYUL 18:01:03 CYUL 181700Z 22028G38KT 30SM BKN055 10/02 A2941 RMK SC7 SLP959 18:02:27 when foreigner friends come to paris they all tell me it's a beautiful city and I'm lucky to live there... all I see here are the unfriendly people, the cigarettes and other trash scattering the floor, and angry drivers 18:03:50 Koen_: I think that's the same for many (if not all) major cities 18:04:20 well, i went to Koln and Bonn in germany during the summer and it was sooooo clean 18:04:43 and London is much much cleaner than Paris 18:04:58 and people there don't drive with their right hand stuck to the horn 18:09:36 -!- Taneb has joined. 18:13:17 I remember being envious of the river, in Paris. 18:13:26 But that extends to any city with a river, which is quite many of them. 18:13:46 -!- augur has joined. 18:13:59 yeah hmmmmmm I wonder why people keep building cities next to rivers 18:14:12 like they want the water or something 18:14:22 better than next to a river, on an island in the river! 18:14:23 It's just that we don't have one here, and for some reason it feels lacking. 18:14:42 At least anything you'd count as a proper river. I mean, there's some water. 18:15:18 how about hijacking a neighbouring river? 18:15:26 I'm not sure how we'd carry it. 18:16:11 http://goo.gl/maps/fAFdU like there's that one little thing but it's there on the wrong side of the city and all. 18:16:36 is it me or have you got a whole ocean? 18:17:06 It's not much of an ocean. And anyway, it's clearly not a river. 18:17:33 I'm sure that if I lived in a city with a river, I'd be disappointed with it and want an ocean instead. 18:21:29 Speaking of cities in Europe, Berne (in Switzerland) seemed like a nice place, based on a very short visit. (There's even a river.) Maybe it doesn't quite count as a "major city". 18:22:56 ouh, the movie I wanna see is ten minutes away, both timely and spacely gotta go bye 18:23:05 -!- Koen_ has quit (Quit: Koen_). 18:24:53 @tell Koen_ ouh? 18:24:53 Consider it noted. 18:25:14 fizzie: rivers are good 18:25:15 fizzie: you're envious of turku? 18:25:39 fizzie: can you cross the same river twice 18:25:51 fizzie: according to wikipédia's “List of Primate Cities”, Bern counts as a major city in Switzerland. 18:26:27 oklopol: Kinda-sorta. Vaguely. Not because of much else than the river, though. 18:37:54 -!- Sprocklem has quit (Ping timeout: 265 seconds). 18:41:38 It's large enough to be known by name by random europeans who have never been to Switzerland 18:48:39 -!- oerjan has joined. 18:48:39 It's also the capital 18:48:57 -!- Phantom_Hoover has joined. 18:49:22 York has like two rivers 18:49:24 It's great 18:51:02 fizzie, move to York imo 18:51:40 is this what it's like to leave hexham 18:51:56 "omfg two whole rivers what kind of paradise is this" 18:52:01 Phantom_Hoover, York has twice as many rivers as Hexham! 18:52:10 fizzie: Montréal is better. we have the same river, but twice! 18:52:12 Also I'm just being silly at fizzie 18:52:29 Phantom_Hoover, York even has a wall! 18:52:42 -!- conehead has quit (Read error: Connection reset by peer). 18:52:43 dragons attack and you'll be ready 18:53:19 Except I live on the outside of the wall :( 18:54:32 we have walls. sort of. https://commons.wikimedia.org/wiki/File:Fortifications_Montr%C3%A9al_2009.JPG 18:55:17 we don't have walls in edinburgh because *rolls dice* walls are for puny englishmen 18:55:40 ~dice 20 18:55:40 16 --- Sum = 16 18:55:46 Phantom_Hoover, does Coventry have walls 19:00:37 i don't know 19:00:45 i spend as little time in coventry proper as possible 19:01:23 hoily 19:02:05 Taneb: plot and graph (not in the node-vertex sense but the other one) appear to be interchangeable both as nouns and verbs 19:02:21 Taneb: plotting a graph and graphing a plot are about the same thing 19:02:43 ~dice 5d20 19:02:43 4 --- Sum = 4 19:02:54 HRM 19:03:56 ~dice 20 4 19:03:56 20 12 9 14 --- Sum = 55 19:04:05 quintopia, but both have different meanings 19:05:13 Taneb: yes i know you were looking for words which have the same meanings and ONLY the same meanings, but words which interchangeable for one of their definitions is useful enough to a learner of english 19:05:37 quinthellopia. 19:05:41 -!- Bike has quit (Ping timeout: 248 seconds). 19:05:47 quintopia, now you're moving the goalposts :P 19:06:14 Taneb: i already hit a home run. i can do what i want. 19:06:25 boily: does ursula martinez live in montreal 19:06:54 quintopia: probably. lots of people live in montréal. who is she? 19:07:50 (wikipédia says that she lives in London.) 19:08:03 -!- Bike has joined. 19:08:15 hmm 19:09:37 they call her a "cult cabaret diva" 19:09:47 i would have just said "stripper" 19:10:23 i have a video of an amazing performance of hers in montreal. so i had to ask. 19:11:10 it's the second youtube link on google...but i think the full version is longer than 4:47? 19:11:37 once again according to the wiki, youtube videos butcher her performance. 19:12:02 (why do we have so many naked people in montréal? don't they know that it gets fungottely cold in the winter?) 19:12:02 boily: i could never put a cat in the barrel because they believed in the dark or otherwise confused. 19:12:02 quintopia: possibly because not all of her performance is "acceptable" for YouTube? 19:12:13 i have the unbutchered version. 19:12:22 fungot: please don't barrel any cats 19:12:22 mrhmouse: you just enter a number to someone whom sarahbot thinks that your nick resembles. then t has a uniquely determined extension to a bounded linear transformation s from the closure to see the enhancements. i 19:12:27 mrhmouse: you mean youtube can't show full frontal nudity? NONSENSE 19:12:59 fungot: you do texture mapping with other bots? fascinating. 19:12:59 boily: no they aren't 19:13:07 fungot: beuh. I am disappoint. 19:13:07 boily: remove ( unit foo) ( define b ( begin ( define ( push el list))) shoudl tell you. 19:13:19 fungot: oh, a secret coded message! 19:13:19 boily: very simple to implement, i juts mean a set with a fluid environment, as well as math functions ( the ones from queue) but they use perl because it's what i'm currently using that via ssh rather than my perl programs 19:13:46 fungot: I'll have the decoder implemented right away. by the way, did you know that R7RS is out? 19:13:46 boily: gorgeous soaking cold! var temp)... in essense you're constructing an if/ else that does either one or the other 19:14:06 fungot: you're confusing everyone 19:14:07 shachaf: " amis" is finnish for finland finnish :p) 19:14:22 today I learned finnish. thanks, fungot. 19:14:22 mrhmouse: mmmdonuts: so you didn't write asiebot to another channel sometime and i'll tell you that continuations are an integral part of the article. 19:14:25 fizzie: can you confirm or deny (probably deny) 19:14:28 s/is finnish/is french/ 19:15:05 fungot: do you even know finnish? 19:15:05 shachaf: i agree, i still don't get why they think schemers are arrogant.) 19:15:19 fungot: can you help me make a starcraft clone in scheme 19:15:20 shachaf: somehow you're getting into the hair splitting business 19:16:29 fungot: i'd love to get into that business 19:16:29 shachaf: yes, and misspelling it purposely. very clever. but alltogether i think cotmta is the best 19:16:41 fungot: no, you're the best ♥ 19:16:41 shachaf: neilv says: no problem writing ' u' and liberally sprinkling sentences with ' lol' 19:17:31 fungot: i got a problem with that 19:17:58 fungot, you are the best, it's true 19:17:58 Phantom_Hoover: two stacks for the program :) 19:18:14 shachaf: looks like fungot got tired of you 19:18:14 quintopia: ( especially regarding the cons) ( define ( fnord status) " an error is signalled", btw). i thought of that 19:18:26 it's mutual, fungot 19:18:26 shachaf: then i'll get back to when the state of the art. it's a large industry to be sure 19:18:47 fungot: WHAT'S A LARGE INDUSTRY? complete sentences, please! 19:18:47 shachaf: oh wait. that was actually very inviting... 19:18:55 fungot: go away 19:18:55 shachaf: i want a break from it. so it took a while to adjust to it and crossed my fingers.) 19:19:01 thanks fungot, being friends is so much better than when you wanted to kill me 19:19:01 Phantom_Hoover: tried to copypaste stuff from this compiling machine to the next logical step is to figure out 19:19:17 fungot wanted to kill Phantom_Hoover? 19:19:17 shachaf: notice that its name already ended in -y. 19:19:33 *Phantom_Hoovery 19:19:59 fungot is teaching ruddy to spout nonsense 19:20:00 mrhmouse: it has two defective pixels, no matter who listens to trance :) 19:20:00 how about this? 19:20:02 Phantom_Hoover: how pick name? 19:20:31 -!- zzo38 has quit (Remote host closed the connection). 19:20:58 how indee 19:20:59 d 19:24:18 JesseH blanked the Derplang page. Yes, it's JesseH's lang, but... NO TAKEBACKSIES ON PUBLIC DOMAIN DEDICATION. can i get a ROLLBACK?? 19:24:58 shachaf: "amis" is colloquial (arguably slightly derogatory, depending on use) for "ammattikoulu" ("ammattiopisto", "ammattioppilaitos"), i.e., "vocational school", a place for the sort of career-oriented upper secondary education from which one typically does not go on for a university degree. 19:25:02 Phantom_Hoover: but seriously, why "Phantom Hoover"? 19:26:19 Higgledy-piggledy, / Phantomy_Hoovery / Once thought that fungot would / Want him to die; // How'd he survive that? By, / Uncomplicatedly, / Changing his nickname by / Dropping a -y. 19:26:19 shachaf: but it would cause executing unwanted instructions even if you leave it out. 19:26:36 Oops, too many "by"s. 19:27:40 fungot: Is "amis" Finnish for Finland Finnish? 19:27:40 shachaf: the ultimate esolang shootout" ( when i'm already familiar with usual til strategies. 19:27:44 Er, fizzie: 19:28:43 Higgledy-piggledy, / Phantomy_Hoovery / Once thought that fungot would / Want him to die; // How'd he survive it? By / Uncomplicatedly / Changing his nickname, and / Dropping a -y. 19:28:44 shachaf: i could be wrong. it refers to whether you do it, 19:28:47 shachaf: No. But maybe it's Finland for Finnish Finland, if that means anything. 19:29:24 fizzie: well maybe YOU'RE finland for finnish finland!! 19:29:50 at least fungot has admitted it might be wrong 19:29:51 quintopia: because nobody does this mean? 19:30:06 exactly fungot. you're the first 19:30:07 quintopia: are you referring to 19:30:11 yep 19:34:49 fungot: are you dropping 19:34:50 oerjan: by saying " you hit me, and the 19:35:02 i take that as a yes. 19:35:32 oerjan: i think you're 19:35:44 -!- Sprocklem has joined. 19:42:38 -!- AnotherTest has joined. 19:49:21 quintopia: no u 19:50:47 :/ 19:50:50 -!- darklust has changed nick to Darklust. 19:51:38 `relcome Darklust 19:51:41 ​Darklust: Welcome to the international hub for esoteric programming language design and deployment! For more information, check out our wiki: . (For the other kind of esoterica, try #esoteric on irc.dal.net.) 19:52:07 oerjan: I think you accidentally. 19:52:19 what's this about fungot 19:52:19 Phantom_Hoover: the music sucks ( war samples like guns and radio communications) and the second one is a editor for midi ( rosegarden, kde based) 19:52:19 boily: he's already had a `relcome 19:52:34           19:52:34           19:52:34           19:52:34           19:52:34           19:52:42 thanks, Darklust 19:52:42 boily: nothing accidentally about it 19:53:12 So brain, such fuck 19:53:32 you haven't been coding in dogescript have you. 19:53:33 Uh oh, we need to undo boily's damage. 19:53:37 Darklust: You are not relcome here. 19:53:39 oerjan: and there I was naïvely hoping I could `relcome someone... 19:54:06 I'd rather not, it's built ontop of what, javascript? 19:54:10 good 19:54:16 we don't like that type here 19:54:29 naïve 19:55:49 Why is there no implementation of NABD? 19:55:59 At least, none that I can find 19:56:02 because you haven't written it yet 19:56:46 shachaf: that diæresis was valid. you can't counter it. 19:57:12 boily: Over here, "naïve" gets rendered with *three* dots above the ı. 19:57:28 shachaf: weeeeeeeird 19:57:48 `unidecode naïve 19:57:50 ​[U+006E LATIN SMALL LETTER N] [U+0061 LATIN SMALL LETTER A] [U+0069 LATIN SMALL LETTER I] [U+0308 COMBINING DIAERESIS] [U+0076 LATIN SMALL LETTER V] [U+0065 LATIN SMALL LETTER E] 19:57:57 Yes, that's a combining diæresis. 19:58:03 naïve gets rendered with two dots. 19:58:10 naive gets rendered with one dot. 19:58:17 naıve gets rendered with no dots. 19:58:40 Are those mapped to your keyboard 19:58:44 naïve gets rendered with three dots. three! 19:58:53 Darklust: http://esolangs.org/wiki/Not_a_brainfuck_derivative is this what you're referring to? it definitely doesn't say "Implemented" there at the bottom. also, there's no spec. 19:58:56 olsner: For you too? 19:59:05 shachaf: yep 19:59:14 Yeah, quintopia 19:59:15 I think this font is lacking lots of fancy unicode 19:59:22 I got excited and then I wasn't excited 19:59:36 I am wondering 19:59:39 `unidecode naïve 19:59:40 ​[U+006E LATIN SMALL LETTER N] [U+0061 LATIN SMALL LETTER A] [U+00EF LATIN SMALL LETTER I WITH DIAERESIS] [U+0076 LATIN SMALL LETTER V] [U+0065 LATIN SMALL LETTER E] 19:59:42 I think gtk and xchat aren't much good at it either 19:59:54 How easy is it to write a BF compiler in assembly? 20:00:10 I am wondering if it's a good idea to try out assembly a bit 20:00:18 o_o 20:00:33 it's pretty easy to write a bf compiler in anything 20:00:34 Slereah: an assembly program to compile BF to machine code? 20:00:40 what Bike said 20:00:51 but what machine would you target? x86? 20:00:52 Well, that's just weird. In PuTTY (I'm doing some Windows-Steaming), "naïve" gets three dots; if I copy-paste it to Chrome's input line, it gets a single dot; but when I paste it in, say, Google's search field, it gets two. 20:00:56 Yes 20:00:58 I guess that averages out to correct. 20:01:13 naı̈ve 20:01:15 Perfect. 20:01:17 Seems like it might be a neat little project to learn some more assembly 20:01:20 lol 20:01:21 your setups are wëird. 20:01:21 naïve 20:01:26 naȯve 20:01:34 ȯöps 20:01:35 (Maybe Chrome's input line has some special handling for safety.) 20:01:36 boily: don't worry. it renders just fine with two dots here. 20:01:39 naø̄ve. 20:01:44 naïve 20:01:49 naı̈ve 20:01:53 quintopia: thanks for reassuring me. I was feeling very strange. 20:03:04 -!- lambdabot has quit (Quit: brb). 20:03:07 does the w in ẅ look normal to you? 20:03:22 olsner: it switches fonts, but displays properly. 20:03:50 I guess the font switch is what makes it look bad here 20:04:50 I guess the hardest part would be figuring out the IO 20:05:52 -!- Bike has quit (Ping timeout: 264 seconds). 20:05:55 olsner: my IME lets me put diæresises on: äëḧïöẗüẅẍÿ 20:07:21 -!- lambdabot has joined. 20:08:00 http://www.c-span.org/Live-Video/C-SPAN3/ 20:09:03 boily: same here 20:09:29 boily: the htx look a bit strained, but the others get remapped to the appropriate non-combined characters 20:10:12 Slereah: not too hard, just depends entirely on what you target with the assembly... doing a system call on e.g. linux is easy 20:10:19 `ord ḧ 20:10:21 7719 20:10:33 wat not even combined 20:10:44 `ord ḧ 20:10:46 7719 20:11:00 `ord ḧ 20:11:01 104 776 20:11:07 there was a " on that h right until I pressed enter 20:11:35 or ¨ 20:12:00 hmm. even the non-combined form looks blurry 20:12:04 nvm 20:12:51 `unidecode äëḧïöẗüẅẍÿ 20:12:53 ​[U+00E4 LATIN SMALL LETTER A WITH DIAERESIS] [U+00EB LATIN SMALL LETTER E WITH DIAERESIS] [U+1E27 LATIN SMALL LETTER H WITH DIAERESIS] [U+00EF LATIN SMALL LETTER I WITH DIAERESIS] [U+00F6 LATIN SMALL LETTER O WITH DIAERESIS] [U+1E97 LATIN SMALL LETTER T WITH DIAERESIS] [U+00FC LATIN SMALL LETTER U WITH DIAERESIS] [U+1E85 LATIN SMALL LETTER W WIT 20:13:12 `unidecode ẅẍÿ 20:13:14 ​[U+1E85 LATIN SMALL LETTER W WITH DIAERESIS] [U+1E8D LATIN SMALL LETTER X WITH DIAERESIS] [U+00FF LATIN SMALL LETTER Y WITH DIAERESIS] 20:13:25 not a combined character in sight 20:14:15 `unidecode ḧ 20:14:17 ​[U+0068 LATIN SMALL LETTER H] [U+0308 COMBINING DIAERESIS] 20:17:59 -!- conehead has joined. 20:20:02 -!- Bike has joined. 20:20:15 -!- asie has quit (Quit: I'll probably come back in either 20 minutes or 8 hours.). 20:26:55 -!- nisstyre has joined. 20:31:59 -!- Koen_ has joined. 20:40:25 reachable accented letters on my layout: http://pastebin.ca/2477097 20:42:05 -!- Sprocklem has quit (Ping timeout: 245 seconds). 20:45:27 -!- asie has joined. 20:49:12 -!- MindlessDrone has quit (Quit: MindlessDrone). 20:51:45 `file bin/unidecode 20:51:47 bin/unidecode: a python script text executable 20:57:34 -!- asie has quit (Quit: I'll probably come back in either 20 minutes or 8 hours.). 21:00:42 I wonder if it'd be good to make a variant of befunge that's more suitable for scripting 21:00:55 FreeFull: more suitable how? 21:02:03 Ability to execute programs and pipe/redirect their results, maybe ability to have substacks that can be pushed onto the stack 21:02:46 Funge-98 already has a stack of stacks. Though not quite like that. 21:04:47 by "execute programs", do you mean arbitrary system calls or other Befunge programs? 21:05:00 And a kind of an equivalent to C's system(3) even without going into the fingerprints. No redirection of inputs with built-in commands, though. 21:07:47 -!- oerjan has quit (Quit: Nyet). 21:08:52 Curiously, I'm not sure if there's a fingerprint for doing something like popen. There's FORK, but that's just a FORK. There's no file-descriptor-level IO (though FILE could perhaps open /dev/fd/N) or exec that I can find, which is kind of crazy, because there *is* SysV message queues, semaphores and shared memory. 21:12:40 maybe you could open /proc/self/mem and add some code 21:15:16 -!- jix has quit (Read error: Operation timed out). 21:19:08 -!- jix has joined. 21:35:18 -!- Koen_ has quit (Quit: The struct held his beloved integer in his strong, protecting arms, his eyes like sapphire orbs staring into her own. "W-will you... Will you union me?"). 21:43:45 -!- AnotherTest has quit (Ping timeout: 245 seconds). 22:03:32 -!- upgrayeddd has joined. 22:12:25 -!- lambdabot has quit (Quit: (lpaste url is .net, not .org)). 22:16:25 -!- lambdabot has joined. 22:20:01 @ask oerjan Hey, do you Norweggers have some sort of logical rules when you use "på" and when "i" when you're explaining where someone/something is? (In Finnish the two suffixes -ssa/ssä and -lla/llä seem to be used pretty much randomly, but OTOH all Swedish examples I could think of were pretty logical; mostly "i", and then "på" for things like islands.) 22:20:02 Consider it noted. 22:26:45 <`^_^v> @ask lambdabot will you go out with me 22:26:45 Nice try ;) 22:26:49 <`^_^v> :( 22:32:05 fizzie: Things like islands? 22:33:42 -!- muskrat has joined. 22:35:19 shachaf: På Åland, i Helsingfors. På Sveaborg. I Vanda. "På" is like "on", so it makes sense for islands. "I" is like "in", so it makes sense for generic places. 22:35:46 shachaf: (But those four in Finnish would be "Ahvenanmaalla", "Helsingissä", "Suomenlinnassa" and "Vantaalla".) 22:36:49 Oh, on vs. in. 22:37:59 Right. I'm sure Swedish has some exceptions that don't really make sense too, but I couldn't think of any. At least for the Swedish names of Finnish places. 22:46:33 `olist (931) 22:46:35 olist (931): shachaf oerjan Sgeo FireFly 22:53:16 -!- Phantom_Hoover has quit (Ping timeout: 264 seconds). 22:57:04 -!- Phantom_Hoover has joined. 23:05:23 -!- muskrat_ has joined. 23:05:32 -!- muskrat has quit (Disconnected by services). 23:05:36 -!- muskrat_ has changed nick to muskrat. 23:06:45 -!- Bike has quit (Quit: w/e. lab meeting ho!). 23:12:10 -!- mrhmouse has quit (Quit: Leaving.). 23:24:47 -!- boily has quit (Quit: Poulet!). 23:24:48 -!- metasepia has quit (Remote host closed the connection). 23:27:49 -!- prooftechnique has joined. 23:32:22 -!- muskrat_ has joined. 23:32:22 -!- muskrat has quit (Disconnected by services). 23:32:24 -!- muskrat_ has changed nick to muskrat. 23:43:37 -!- Phantom_Hoover has quit (Remote host closed the connection). 23:44:55 The overview text http://www.crutchfield.com/S-AtP1DjFffcX/p_703SUB36M/AudioQuest-SUB-3-6-meter-19-7-feet.html 23:45:45 -!- augur has quit (Remote host closed the connection). 23:49:51 -!- Slereah_ has joined. 23:50:11 -!- nooodl has quit (Quit: Ik ga weg). 23:52:00 -!- Slereah has quit (Ping timeout: 240 seconds). 23:53:22 ion: wow i'm throwing away all my other cables 23:57:30 shachaf: Remember to only use this for the subwoofer, there are other cables for other speakers. 23:57:53 Important: “Although this same material can cause high frequencies to sound edgy with full-range analog audio signals, it actually improves bass articulation when used in subwoofer cables.” 23:58:14 “edgy” and “bass articulation” being the proper scientific terms. 23:58:48 barticulation 2013-11-19: 00:03:54 copumpkin: hmm, didn't you categories package define a category of adjunctions 00:03:57 How possible is a language like Haskell but with support for object-oriented programming 00:04:19 Taneb: People have tried various things. 00:04:46 That says it all 00:05:02 @google object-oriented haskell 00:05:03 http://stackoverflow.com/questions/5414323/does-haskell-support-object-oriented-programming 00:05:03 Title: Does Haskell support object oriented programming - Stack Overflow 00:05:21 (for some bizarre reason I have to write blog posts about computer science for my uni course) 00:05:32 (and also comment on other people's blog) 00:05:36 -!- Sprocklem has joined. 00:05:47 Taneb: why don't you figure out chu spaces for me instead 00:05:54 (me and some friends are writing controversial posts because they are easy to comment on) 00:05:55 (checkmate) 00:06:04 ion: Wow, no break-in period! 00:06:10 (I'm writing one about why Haskell's a great language, and one of my friends is writing a similar post about C++) 00:06:26 *cough* C++? 00:06:49 ion, he has similar opinions of Haskell as I do of C++ 00:07:23 Also, as long as we can provide citations, easy-to-disagree-with is good 00:10:28 "When you place your order, you can select our cable break-in service, selectable through a drop down box in the shopping cart for that cable product. Prices vary with the cable model and level of break-in desired." 00:10:46 "Our cables require a total of 400 to 500 hours to completely break in. If you ordered our 2 day cable break-in service, your cables will arrive with the equivalent of 96 hours on them. If you ordered the extended 5 day breakin, the equivalent of 240 hours will be on them." 00:11:26 Now that’s customer service. 00:12:14 Comments: Personally i think this cable is so fast it has changed the phase relationship (or corrected it) by 180 degrees above 60hz, the bass is so tight it sounds like the bass is coming from my speakers. 00:12:55 -!- muskrat has quit (Read error: Connection reset by peer). 00:13:00 ion: And it only costs $25 bucks for the 5-day extended breakin! (Two days is free!) 00:13:11 Whoa! What a bargain! 00:13:33 -!- muskrat has joined. 00:15:18 -!- Bike has joined. 00:16:05 http://news.cnet.com/8301-13645_3-20009082-47.html CNET teaches you the difference between analog and digital: digital is dotted. 00:16:20 Choice quote: "Every sound you hear in real life that doesn't come out of a speaker is analog." 00:16:45 "Theoretically have an infinite resolution", nice 00:17:39 great 00:18:23 Analog is always "on," digital is either on or off. 00:18:46 lol this is great 00:18:59 go over the advantages of digital and then be like "but anyway analog sounds better" 00:19:04 "analog", "infinite resolution" what? 00:19:09 It's Like, Cold And Impersonal, Man 00:19:26 Every time I end up on an audiophile web-crawl I get this feeling maybe we should just get rid of ears in general. 00:19:32 pikhq: "CDs have a 16-bit resolution and DVD-Audio discs can be encoded with a maximum of 24-bit resolution" 00:19:45 Even ignoring the band-limitedness of human senses, reality is quantised. 00:20:12 Bike: Sigh. 00:20:21 pikhq: "Analog recording's theoretically infinite resolution refers to its continuity, compared with digital's on/off sampled nature." See, it's that simple. 00:20:34 It's a shame elementary signal processing is relatively obscure. 00:20:47 shannon is my god, man 00:21:16 I wasn't accusing anyone *here* of being this ignorant. Just CNET. :) 00:21:29 though i know less signal processing than i'd like :( 00:21:41 Bike: Anyway they both "still fall short in creating truly life-like sound", so you can use either. 00:22:08 thank goodness 00:22:37 Bike: Yeah, but you at least know Shannon. 00:23:02 neuronal coding is kind of awesomely all over the place btw, sometimes it reasonably makes sense as frequency coding and sometimes a transient stimulus of one photon causes a response 00:23:35 hello 00:23:39 helmc 00:23:48 kello? 00:23:52 And presumably also know about quantization noise. 00:23:54 must be what's after jello 00:24:26 pikhq: not by that name, at least :/ 00:24:40 kmc: g'daymc 00:24:57 http://en.wikipedia.org/wiki/File:Quantization_error.png oh, yeah, that's simple enough 00:25:03 -!- Darklust has quit (Read error: Connection reset by peer). 00:25:13 clearly another data point (!) saying analog is superior. 00:25:20 -!- Taneb has quit (Quit: Leaving). 00:25:44 -!- Darklust has joined. 00:28:54 'Cept that quantization noise, for 16-bit audio, is like -90 dB. 00:29:28 i think that might be the lowest dB measurement i've ever heard of 00:30:27 Note that here the maximum volume is 0 dB. 00:31:02 The 24-bit noise floor is, uh, -145 dB. 00:31:14 http://www.rane.com/pi14.html heh :) 00:31:22 (Look at that list of features.) 00:31:23 24-bit isn't (16-bit) * 1.5? 00:31:47 Fiora: No, each extra bit doubles the precision of the samples. 00:32:03 > 90 ** 1.5 00:32:04 853.8149682454624 00:32:05 I meant, in db 00:32:13 ...what? 00:32:22 :t (**) 00:32:23 Floating a => a -> a -> a 00:32:28 if 8-bit is 45db and 16-bit is 90db would 24-bit be 135...? 00:32:32 i may have underestimated **1.5. 00:32:55 Fiora: It'd be, like, log_10(2^8)? 00:33:34 fizzie: niiiiice 00:34:08 Oh, except that a change by a factor of 10 is a 10dB change. 00:34:19 So that'd be... 10*log_10(2^8)? 00:35:00 Or... 24 dB? Hum. 00:35:25 20*, I believe. Because of power/magnitude and blahblah. 00:35:33 Ah, yes, 20* 00:35:45 pagnitude 00:35:49 That makes it work. 48dB. 00:36:16 And the actual number for 16 bits is -96 dB, so hey. 00:36:44 And 0.5*96 is 48. :p 00:36:48 Yup! 00:37:33 For comparison, a vuvuzela is 120dB. 00:37:38 good to know dB are just as confusing as the last time i cared about dB 00:38:18 Bike: imo use cents instead? 00:38:36 good mo 00:38:38 1200 cents/octave, it's perfect 00:38:39 cB? 00:38:51 what's the unit where you use e? nats? 00:39:11 So... yeah. 16-bit 44.1 kHz is perfect for those of us who don't care about listening to the grand vuvuzela orchestra at actual volume. 00:39:11 or was nats for information... 00:39:12 why would you use e 00:39:12 What was the power being compared to again when using a dB value as an “absolute” value? 00:39:14 how unnatural 00:39:37 Bike: It's the e-bit, yes. 00:39:37 Bike: have you learned about chu spaces yet 00:39:45 why would i care about chu spaces 00:39:54 because they're great 00:40:26 come on they generalize topological spaces and vector spaces and a zillion things apparently?? 00:41:03 ion: It's very context-dependent. 00:41:14 and, uh, games? 00:41:24 look i don't know that's why you read these papers for me 00:41:26 20 µPa 10e−12 W/m² or 10e−12 W apparently. 00:41:36 why would i want to generalize all those things though 00:41:37 comma after the µPa 00:41:42 That's just the usual for dBA. 00:41:57 (Which is also A-weighted.) 00:42:10 I was asking due to For comparison, a vuvuzela is 120dB. 00:42:17 Ah. 00:42:24 why would you generalize anything 00:42:30 -!- Frooxius has quit (Read error: Connection reset by peer). 00:42:37 btw a chu space is just a matrix 00:42:42 -!- Frooxius has joined. 00:42:45 ion: Ah. Well, if you set the noise floor of a CD at 0, the loudest sound it can represent is 96dB. 00:42:46 What chu say? 00:43:06 differentiation is just a matrix. 00:43:15 The Matrix is just a matrix. 00:43:17 Btw, is there an algebraic structure that captures the idea of 'complemet'? I've been thinking some about that 00:43:24 solidity is just a matrix 00:43:37 complement* even 00:43:42 The "acoustic decibel" zero is (very) approximately at the threshold of hearing. 00:43:53 that must be very approximate indeed 00:45:39 -!- carado has quit (Ping timeout: 252 seconds). 00:46:16 The figures get better with noise shaping. (you can make the quantization noise lie in bands humans don't hear so well, making the *effective* noise floor in the bands we care about lower; about -120dB) 00:46:17 Very. But it's at least some sort of a justification for the level. 00:47:51 Hm, never mind my earlier line.. 00:49:38 Bike: differentiation is just a matrix? 00:50:40 it's only a linear operator 00:51:59 but with an infinite-dimensional vector spaces? 00:52:18 Well yes, f(x+ε)=f(x)+f'(x)ε... 00:52:56 shachaf: yes? 00:53:08 does that even have a basis 00:53:08 imo no 00:53:40 shachaf: I think you could extrapolate the duals to infinite-dimensional vector spaces. 00:54:31 have one delta function for every real (or w/e) 00:55:36 you could also do something easier like just polynomials, if you want, i guess. 01:03:13 -!- Darklust has quit (Ping timeout: 246 seconds). 01:05:28 -!- Darklust has joined. 01:08:24 oklopol: Oh, http://ncatlab.org/nlab/show/Chu+construction 01:19:40 -!- doesthiswork has joined. 01:21:10 -!- Sgeo has joined. 01:52:02 -!- yorick has quit (Remote host closed the connection). 01:59:07 shachaf: I never wrote one, but Saizan or xplat might have 01:59:56 copumpkin: Well, do you know anything good about that category? 02:00:59 hmm, what are objects and morphisms in it? 02:01:12 Objects are categories, morphisms are pairs of adjoint functors. 02:02:25 You can pick which direction it goes -- let's say an adjunction : C ~~> D is a pair (F : D -> C, G : C -> D, F -| G) 02:02:32 So it goes in the direction of the right adjoint. 02:03:45 Since there are no functor to the empty category, I guess there are no adjunctions either to or from it. 02:04:23 Adjunctions to/from a singleton category correspond to terminal/initial objects in the other category. 02:10:16 But in general adjunctions are weird so I don't know. 02:12:03 Does it have products or something? Certainly it doesn't have an initial/terminal object. 02:28:45 -!- muskrat has quit (Ping timeout: 240 seconds). 02:29:28 -!- prooftechnique has quit. 02:32:07 -!- muskrat has joined. 02:33:47 -!- augur has joined. 02:42:28 -!- CADD has joined. 02:43:25 interesting 02:43:40 need to think about it some more 02:45:21 Someone's complaint about Elixir arguably applies to Rust 02:45:30 Perhaps less so, but still applies IMO 02:48:28 They were complaining about rebindable variables. Not about making mutable structures with them (which I had previously strawmanned that sort of complaint as), but about being able to read a code and finding where the variables it mentions are adjusted. 02:49:02 So, it seems to me that Rust owned pointers, even non-mut, could still end up changing between declaration and use, and that that needs to be known. Although getting that wrong is a compile-time error, so it's less bad 02:49:51 -!- madbr has joined. 02:53:49 -!- conehead has quit (Ping timeout: 246 seconds). 02:59:49 hm 03:00:27 trying to figure out if there's some set of numbers where evaluating if a number is in that set is turing complete 03:01:27 a recursive set? 03:01:28 (aside from encoding a program in some real language into a number and then the number is in the set if it runs) 03:01:48 I think it would have to be a recursive set yeah 03:02:03 though maybe it's possible to do it with a plain function 03:03:30 or something in the style of the collatz sequence 03:10:41 -!- conehead has joined. 03:11:54 -!- conehead has quit (Max SendQ exceeded). 03:12:58 -!- conehead has joined. 03:17:06 /msg bike can you give me an estimate of when the ai winter began and ended? 03:17:37 i'm no good with dates. 03:18:04 I really should make a bot that takes messages beginning with space 03:18:08 and thanks 03:18:21 wikipedia would probably be better than me. 03:19:37 it says 87 to 93 03:19:58 I guess I have to find more modern paper to read then 03:20:08 paper on what? 03:22:46 in this case knowledge representation, but I'm trying to get familiar with case based reasoning 03:23:30 My god 03:23:41 read the rdf docs or whatever 03:24:39 I'd prefer to avoid learning more than a rough overview knowledge representation 03:25:20 ontology is a word that gives me a slight rash 03:26:39 -!- Bike_ has joined. 03:26:51 doesthiswork: then i recommend "Ramón Llull's Thinking Machine" and "John Wilkins' Analytical Language". 03:26:56 -!- Bike has quit (Disconnected by services). 03:26:59 -!- Bike_ has changed nick to Bike. 03:27:06 THANKS 03:28:12 woops capslock 03:28:35 -!- augur has quit (Remote host closed the connection). 03:28:43 YOU ARE WELCOME 03:39:31 http://www.youtube.com/watch?v=gF_qQYrCcns 03:59:43 `wercome hackego 03:59:45 hackego: エソテリックプログラミング言語のディザインとデプロイメントの国際な場所へようこそ!詳しく、ウィキを見て: http://esolangs.org/wiki/Main_Page。(他のエソテリック、irc.dal.netの#esotericへ) 04:34:11 that’s waisis 04:35:00 -!- madbr has left. 04:35:27 no, it's Japanese 04:58:15 did you know there is a book series about sexual encounters with dinosaurs 04:59:23 http://www.cracked.com/quick-fixes/10-real-book-covers-from-dinosaur-on-human-sex-novels/ 05:07:49 -!- doesthiswork has quit (Quit: Leaving.). 05:12:55 Looks truncated. "irc.dal.netの#esotericへ)" it should be. 05:13:09 And in fact I thought that's what I had typed when I wrote that. 05:13:31 so what's the purpose of `wercome 05:13:42 `WELCOME 05:13:45 WELCOME TO THE INTERNATIONAL HUB FOR ESOTERIC PROGRAMMING LANGUAGE DESIGN AND DEPLOYMENT! FOR MORE INFORMATION, CHECK OUT OUR WIKI: . (FOR THE OTHER KIND OF ESOTERICA, TRY #ESOTERIC ON IRC.DAL.NET.) 05:15:06 Hrm, is the "hackego: " text what made it too long? 05:15:07 `wwalcome 05:15:08 ​/home/hackbot/hackbot.hg/multibot_cmds/lib/limits: line 5: exec: wwalcome: not found 05:15:10 `wercome 05:15:12 ​エソテリックプログラミング言語のディザインとデプロイメントの国際な場所へようこそ!詳しく、ウィキを見て: http://esolangs.org/wiki/Main_Page。(他のエソテリック、irc.dal.netの#esotericへ) 05:15:12 `ls w* 05:15:14 ls: cannot access w*: No such file or directory 05:15:17 So it is. 05:15:18 wha. 05:15:21 `ls /bin/w* 05:15:23 ls: cannot access /bin/w*: No such file or directory 05:15:29 `run ls /bin/w* 05:15:31 ​/bin/which 05:15:42 `run ls w* 05:15:44 As the wisdom directory contains many files named after nicks, listing it in public annoys people. Try https://dl.dropboxusercontent.com/u/2023808/wisdom.pdf instead. 05:16:02 ...yeah certainly wisdom starts with w. 05:16:19 `welkom 05:16:20 ​/home/hackbot/hackbot.hg/multibot_cmds/lib/limits: line 5: exec: welkom: not found 05:16:25 `Welkom 05:16:26 ​/home/hackbot/hackbot.hg/multibot_cmds/lib/limits: line 5: exec: Welkom: not found 05:16:28 :( 05:16:34 -!- augur has joined. 05:18:46 -!- augur has quit (Remote host closed the connection). 05:18:54 `? Welkom 05:18:56 Welkom bij het internationaal centrum voor het ontwerpen en implementeren van esoterische programmeertalen! Voor meer informatie, bezoek de wiki: http://esolangs.org/wiki/Main_Page. (Voor de andere soort esoterie is er #esoteric op irc.dal.net.) 05:19:22 -!- augur has joined. 05:21:22 -!- augur_ has joined. 05:23:45 -!- augur has quit (Ping timeout: 245 seconds). 05:48:49 -!- asie has joined. 06:06:43 " Btw, is there an algebraic structure that captures the idea of 'complemet'? I've been thinking some about that" boolean algebra maybe? 06:10:50 -!- asie has quit (Quit: I'll probably come back in either 20 minutes or 8 hours.). 06:11:50 (" a recursive set?" being recursive is an _upper_ bound for complexity) 06:12:12 -!- conehead has quit (Quit: Computer has gone to sleep.). 06:18:49 -!- asie has joined. 06:22:38 -!- asie has quit (Client Quit). 06:23:43 -!- Sprocklem has quit (Ping timeout: 272 seconds). 06:28:17 halp pikhq 06:28:24 does * not work in filenames with mv? 06:31:22 -!- tertu has joined. 06:36:13 `run ls -d w* 06:36:15 As the wisdom directory contains many files named after nicks, listing it in public annoys people. Try https://dl.dropboxusercontent.com/u/2023808/wisdom.pdf instead. 06:37:03 `run ls . 06:37:05 bdsmreclist \ bi \ bin \ canary \ cat \ complaints \ :-D \ dog \ etc \ factor \ fb \ fb.c \ file \ head \ hello \ hello.c \ ibin \ index.html \ interps \ lib \ mind \ paste \ pref \ prefs \ quines \ quotes \ share \ src \ wisdom \ wisdom.pdf 06:37:44 -!- adu has joined. 06:37:47 hi 06:38:05 `relcome adu 06:38:08 ​adu: Welcome to the international hub for esoteric programming language design and deployment! For more information, check out our wiki: . (For the other kind of esoterica, try #esoteric on irc.dal.net.) 06:39:14 nice 06:39:33 I tried deploying a language once 06:39:43 I didn't get very far 06:40:25 interesting. must have been a very complicated language. 06:40:33 it was a scheme clone 06:40:36 http://andydude.github.io/droscheme/ 06:40:54 (i am deploying right now, and in under a week, i have a working prototype and a boatload of example programs) 06:41:07 sweet 06:41:21 (because the language is danged simple) 06:41:24 I'm more interested in metaprogramming now 06:41:51 what's a complete numerical tower 06:42:02 oklopol: up to complex 06:42:08 oh okay 06:42:11 and strict rationals 06:42:31 some schemes do 1/2 => 0.5, which is not using a rational object 06:42:48 why should there be a difference in a high level language 06:43:05 hmm 06:43:08 unless you imply that precision is lost 06:43:16 in some operations 06:43:24 well, it's not precision that's lost, it's exactness that's lost 06:43:38 i don't know the difference 06:43:41 well 06:43:48 i guess i do but i still don't know what you mean 06:43:49 precision is continuous 06:43:52 exactness is binary 06:44:07 err 06:44:19 although, you could make the argument that exactness is infinite precision 06:44:28 as in, 0.33333... does not equal 1/3 no matter how many 3's you put 06:44:33 yes 06:45:00 but yes, if you say exactness is infinite precision, then precision is also lost 06:46:03 well, droscheme is also an experiment in metaprogramming for me 06:46:07 the compiler is at least 06:46:13 "exactness is binary" do you mean to be exact is to conform to the ieee specification? 06:49:41 nope 06:50:01 ieee specifies operations within a given preciison 06:50:38 i mean if you do (acos -1), then even though -1 is an exact number, the output will be inexact, i.e.: pi 06:51:21 or whatever double-precision object best represents pi 06:51:56 so i made this minigolf "game" some weeks ago, where there are some lines and a ball bounces off of them 06:52:13 after 11 bounces, the number usually has something like 100 digits 06:52:35 i mean the position & direction 06:52:47 the numbers representing those i mean 06:53:00 and i mean the numerator and denominator of those numbers 06:53:25 point is rationals are funnnn 06:53:38 yes 06:54:08 one of things I wanted to try out was the whole "exact real" concept 06:54:25 essentially how Mathematica does things 06:55:07 everything is stored symbolically, then when you ask for 50 decimal places, it calculates everything, then when you ask for 2000 decimal places, it calculates it again from scratch 06:55:16 my hope was to make a puzzle game where you have to solve hole-in-one problems, where some of the levels can be passed only if you solve some big math conjecture 06:56:00 but apparently such systems are not known to be able to simulate turing machines 06:56:18 heh 06:56:20 a closely related model is one where for each wall you have a specific direction in which the ball bounces 06:56:35 that reminds me of an episode of Elementary 06:56:38 (in mine, it's a "physically correct" bounce) 06:56:56 in the closely related model, apparently from 3d on you can simulate arbitrary computation 06:57:13 with rotational momentum and table-top friction? 06:57:28 oklopol: what if some of the walls are interlinked, so that a bounce against one wall removes another wall and causes a third to pop-up. i bet you could do arbitrary circuits that way. 06:57:31 with a reflection over the normal 06:57:34 thus the quotes 06:57:43 oklopol: or portals 06:58:34 quintopia: surely, but that's not as cool as having a turing machine running in the decimal extension of your rationals. 06:58:58 oklopol: maybe it would let you have that too 06:59:31 perhaps 06:59:41 oklopol: hmm, couldn't you simulate fractran by clever wall placement? 07:00:07 well that's pretty much what has been done in 3d for the one with bounces in constant directions 07:00:20 ah 07:00:28 except usually people simulate affine functions 07:00:30 erm 07:00:58 whaddyacallem functions which are affine in some way in some places and affine in another way in other places. 07:01:35 you have a 2d vector of rationals represent the left and right tail of the turing machine 07:01:44 oklopol: i think maybe you could do it in 3D with "physical" bounces 07:01:45 erm 07:01:55 tails of the infinite configuration 07:02:14 perhaps, but do you have a specific idea? 07:02:43 i have an idea for a divisibility test... 07:03:18 draw a quick sketch in your favorite 3d modeling program 07:03:23 :) 07:03:37 i don't 3d modeling. and i don't have a computer cable of it anyway. 07:03:43 cable? 07:03:50 a computer cable of 3d modeling 07:03:53 yes 07:03:54 mm mm mm 07:03:59 that's the most important part 07:05:19 3d modeling doesn't need a fancy computer, realistic rendering does 07:05:40 capable? 07:05:45 yes 07:05:48 yes adu yes 07:05:57 thank you for your kind help with my condition 07:06:20 but yeah there is pretty much no nice and easy way to do 3d modeling afaik (let alone nd) 07:06:20 lol 07:06:39 say compared to opening paint and drawing a 2d image 07:06:43 oklopol: there is one easy way, it's called photogrammetry 07:06:59 okay photogram me something quickly 07:07:10 oklopol: yeah oklopol just build a real one and photogrammeter it into a model! 07:07:27 photogrammetry requires specialized tools that convert static images from multiple angles into a 3D model for you 07:07:52 i don't have any such tools 07:07:58 oklopol: also oklopol i like oklopol saying oklopol your name oklopol too many times oklopol in a sentence oklopol. oklopol! 07:08:15 http://www.microsoft.com/ultracam/en-us/umap20.aspx 07:08:20 look i just made your name banal 07:08:40 http://www.vjn.fi/temporary%20shit/ddd.png 07:08:43 could you explain Clue (oklopol) to me, oklopol? your description on the wiki is nonsense 07:08:44 that was so much faster 07:08:57 tell me when you are done 07:09:25 oklopol: awwww 07:09:49 ;) 07:09:54 oklopol: I can't, I don't have the software 07:10:59 yes, you have to get special software and i bet it takes seconds and seconds to open when you double-click it so you will never bother to use it. 07:11:09 paint on the other hand 07:11:11 oh it's so nice 07:11:16 lol 07:11:29 I prefer Gimp 07:11:44 I can do things in Gimp that will make you weep 07:12:04 things i need to do: paint pixels, paint straight lines 07:12:56 other things of importance: the program takes less than 3 seconds to open 07:13:03 i'm a busy and important guy 07:13:08 and my programs need to respect that 07:13:44 i don't really get gimp, iirc last time i tried it took me a week to find an actual brush 07:14:49 oklopol: yes, i'm pretty sure it's possible in 3D with "physical bounces" if you're allowed infinite walls and infinite cups. i just designed one in my head. it only uses 90 degree bounces. 07:15:18 infinite walls? 07:15:44 cups sound dangerous 07:15:48 well, i left out one part of the design, but yes what i have requires there be an infinite number of walls 07:15:54 does infinite walls mean infinitely many walls? 07:16:06 or why do you need infinite size 07:16:07 cups as in holes as in "hole in one" 07:16:12 oh. 07:16:46 i have a hunch that you are not doing the computation in the presentation of the number, but in the large scale location of the ball 07:16:53 getting the ball in the hole is the halting condition right 07:16:57 yes 07:17:12 can you try to describe what's going on 07:17:13 well of course i am. i can't think in terms of the position numbers 07:17:51 so the position of the ball on the x axis is your number n (in fractran) 07:18:06 just using integer positions you know 07:18:12 alrighty 07:18:39 and it bounces ziggity zag parallel to the y, then z, then y, then z axes 07:19:03 every wall that turns it from y towards z has holes in it every kth integer 07:19:22 so the first wall has even/odd holes, the second open-closed-closed, etc. 07:19:47 where k is one of the denominators of one of the fractions 07:19:51 in sequence 07:20:25 so the first fraction it comes to that divides it, it will pass through the wall and keep traveling down the y axis 07:20:25 got some breakfast, will now read your formal proof 07:22:05 "and it bounces ziggity zag parallel to the y, then z, then y, then z axes" can you clarify this 07:22:07 then it hits a wall that turns it to the left, towards the yz plane with a y value corresponding to the product of the fraction and the number 07:22:23 ok it looks like this: 07:22:28 (from the side) 07:22:33 \ 07:22:36 (which way is y) 07:22:42 \\ 07:22:45 \\ 07:22:48 \\ 07:23:01 etc. 07:23:34 i'm not sure i'll be able to describe it in words :/ 07:24:38 well anyway i believe it's doable if you allow that sort of stuff 07:25:05 and that sort of stuff with infinite boards might certainly make an interesting game 07:25:09 no idea how you'd do it encoding the data in the digits after the decimal 07:25:59 me neither, i've asked 2 professors and another researcher sofar 07:26:07 so can you explain clue please 07:26:08 the first said it's clearly undecidable in 2d 07:26:17 but we then later agreed maybe it's not known 07:26:49 the second said http://mathworld.wolfram.com/IlluminationProblem.html 07:26:55 -!- FreeFull has quit. 07:27:45 oh er clue 07:27:49 well clue is awesome 07:27:58 what do you wanna know 07:28:29 i should really make a more serious version of it, and a documentation that actually documentates something 07:30:09 i don't understand how you define a function by examples 07:30:12 like 07:30:44 what if i want a function that ... squares negative numbers and square roots positive numbers 07:30:57 how would i specify that and how would the compiler figure out that's what i want 07:31:49 i wonder where clue.rar is nowadays. 07:32:19 well you have to know the exact recursive algorithm 07:32:34 clue doesn't figure that out, it just saves you the trouble of actually writing it down 07:32:39 are you talking about http://esolangs.org/wiki/Clue 07:32:43 yes 07:32:52 http://esolangs.org/wiki/Clue_(oklopol) 07:32:54 who is keymaker? 07:33:24 another finnish guy 07:33:28 sometimes visits the channel 07:34:07 quintopia: writing mathematical functions might be tricky 07:34:33 because the end condition for the recursion is complicated (some error is small enough) 07:34:45 maybe you could give the comparison operator and the epsilon value as helpers 07:34:50 it might figure it out eventually 07:35:58 basically, you have . a -> b things and you have :. c -> d : e -> f things, and you have a list of helper functions 07:36:16 first, the compiler figures out how, using the helper functions, you can separate things like a from things like c or e 07:36:35 erm, doesn't need to separate e sorry 07:36:43 because a is where recursion should stop, and c is where recursion should happen 07:37:04 hi oklopol 07:37:05 -!- tertu has quit (Ping timeout: 245 seconds). 07:37:39 how easy this of course depends on what sort of helper functions you have (i think the reference function mostly had list operations and some integer operations) 07:37:55 (you can of course also use your own functions as helpers) 07:38:05 reference function? does this still exist? 07:38:36 reference function? 07:38:47 hi shachaf 07:39:01 you have an example i can see? 07:39:07 oh. 07:39:15 http://esolangs.org/wiki/Clue_(oklopol)/Quicksort 07:39:25 this compiled in less than a minute iirc 07:39:35 quicksort ~ {. [] -> [] } 07:39:39 base case 1 07:39:45 quicksort ~ {. [1] -> [1] . [2] -> [2] } base case 2 07:39:59 (one is enough, the other is basically just a comment.) 07:40:58 {:. [4 2 3 1] -> [1 2 3 4] 07:40:58 : [2 3 1] -> [1 2 3] 07:40:58 : [] -> [] 07:41:01 that says 07:41:23 if you get [4 2 3 1] as input, you should somehow get [2 3 1] out of it and [] out of it 07:41:40 then you somehow patch up [1 2 3 4] from [4 2 3 1] and [1 2 3] and [] 07:42:30 -!- adu has quit (Quit: adu). 07:42:35 then it just does that same thing for all inputs 07:42:41 and usually it just works 07:43:01 (usually = in the three or so examples in the history of mankind that have been implemented) 07:43:45 http://esolangs.org/wiki/Clue_(oklopol)/SKI_calculus this was a bit trickier because you have to go very deep into the list, and the main logic ski apply has many many branches 07:43:54 (deep into the input list) 07:44:09 so that, iirc, took like 10 minutes to compile 07:44:46 oklopol: so did you figure out adjunctions 07:45:44 wellllllllllllllllllllllllllllllllllllllllllllllll 07:45:46 -!- copumpkin has quit (Read error: Connection reset by peer). 07:47:20 -!- copumpkin has joined. 07:50:24 -!- CADD has quit (Quit: leaving). 07:53:18 quicksort helper ~ {. [1 2 3] [4 8 9] [5 6 7] -> [1 2 3 4 5 6 7] } 07:53:18 quicksort helper ~ car; quicksort append 07:53:46 i like how you need to know exactly what you want to happen and write helper functions for random subprograms 07:57:35 I think they mean “transmission”. http://cloud-3.steampowered.com/ugc/451779723596490868/3CCEC987D1FC8666EEE0A0BB1B0C69EA5093FF0E/ 07:58:39 "throwing a SHA5 up" 07:59:31 Also "RE: (no subject)". That's some realism there. 08:02:37 and top-posting, too 08:16:54 -!- TodPunk has quit (Read error: Connection reset by peer). 08:19:11 -!- TodPunk has joined. 08:34:59 -!- oerjan has joined. 08:37:04 @messages-loud 08:37:04 fizzie asked 10h 17m 2s ago: Hey, do you Norweggers have some sort of logical rules when you use "på" and when "i" when you're explaining where someone/something is? (In Finnish the two suffixes - 08:37:05 ssa/ssä and -lla/llä seem to be used pretty much randomly, but OTOH all Swedish examples I could think of were pretty logical; mostly "i", and then "på" for things like islands.) 08:38:31 @tell fizzie Sorry, i vs. på in norwegian place names is like a whole extra random gender... there are heuristics, but they sure aren't reliable. 08:38:31 Consider it noted. 08:40:10 @tel fizzie *gender system 08:40:10 Consider it noted. 08:51:02 -!- carado has joined. 08:54:23 -!- S1 has joined. 08:54:47 What was the language again where everything is a string? 08:55:53 tcl? 08:56:17 Can't find that on the eso wiki 08:56:24 it's not esoteric :P 08:56:40 try /// then :) 08:57:08 It’s not esoteric? ;-) 08:57:50 alternatively, thue, and a heap of variants of either. 08:58:19 (ok i guess /// has only one variant that i can recall) 08:58:25 Thue it was. /// is interesting though 08:58:34 thx 09:03:27 yw 09:08:13 -!- S1 has quit (Quit: http://www.kiwiirc.com/ - A hand crafted IRC client). 09:38:39 `addquote Every time I end up on an audiophile web-crawl I get this feeling maybe we should just get rid of ears in general. 09:38:45 1135) Every time I end up on an audiophile web-crawl I get this feeling maybe we should just get rid of ears in general. 09:54:43 @tell firefly Btw, is there an algebraic structure that captures the idea of 'complemet'? I've been thinking some about that <-- complement _alone_ seems to have no other algebraic property than c(c(x)) = x, which is called an _involution_. 09:54:44 Consider it noted. 09:55:57 @massage-loud 09:55:57 oerjan said 1m 13s ago: Btw, is there an algebraic structure that captures the idea of 'complemet'? I've been thinking some about that <-- complement _alone_ seems to have no other 09:55:57 algebraic property than c(c(x)) = x, which is called an _involution_. 09:56:31 oerjan: I guess I should've been more specific, but it turns out what I was thinking of is a complemented lattice, I think 09:57:04 FireFly: in fact it's an example in wikipedia's involution page. 09:57:13 oh. 10:19:15 -!- nisstyre has quit (Read error: Operation timed out). 10:23:17 oerjan: Good. 10:23:57 "A reasonably easy-to-find and vegetarian-friendly Indian restaurant in Umeda. Mina, the proprietress, speaks excellent English. Vegetarian curry is available on request.Note that this shop no longer exist. Set meals from ¥1554, curries from ¥1050, beers from ¥525." 10:24:01 i love wikis 10:24:33 :-D 10:26:07 i wonder if x86 is turing complete with only instructions «mov dword [dest], imm» and «jmp [src]» but allowing self-mod 10:26:13 ifying of those operands <-- well, I'm pretty sure it's not 10:26:27 even ignoring the finite-pointer-size problem 10:26:44 because a finite program will contain only a finite set of numbers and there's no way to make new numbers 10:29:08 I still don't have a handle on whether "Turing complete except for finite memory" can be formalized as something other than "finite state machine", even though it's something people talk about all the time 10:29:57 I usually think in terms of "would be turing complete given infinite memory" 10:30:01 if you talk about your language interacting with an external tape device, then the language only needs to provide a finite state machine 10:31:02 I guess to formalize a statement like "C is Turing complete" you would talk about a family of languages C_i where sizeof(void *) = i, and require that the languages have a uniform description (for example, a log-space TM that given i acts as an interpreter for C_i) 10:31:12 similar to the way circuit complexity classes work 10:31:59 * oerjan wonders what the "log-space" is doing there. 10:32:05 the problem is that "given infinite memory" doesn't have an obvious meaning in all cases, such as C where sizeof(void *) must be finite 10:32:26 oerjan: shrug, it's standard for circuit classes, it shouldn't be necessary if we are talking only about computability and not complexity 10:32:30 but "why not" 10:32:35 -!- darklust_ has joined. 10:34:15 people talk about C being TC with fseek(SEEK_CUR) and ignoring ftell(), but I think that would be the case even if the core of C were a finite state machine with a fixed IO pipeline 10:34:26 cause the control unit of a TM is a FSM 10:35:58 -!- Darklust has quit (Ping timeout: 245 seconds). 10:37:52 so basically C is hideously overqualified to be TC "if you add infinite memory", and therefore that variation of TC-ness is uninteresting. 10:47:41 maybe C is a bad benchmark because it's not even almost-TC (fsvo almost that's relevant for other languages) 10:49:38 that sounds... unlikely. 10:52:24 what do you mean by it's not even almost-TC? 10:52:57 it's hard to imagine a language that is _more_ almost-TC without being TC. 10:53:59 anyway I think "add a tape" doesn't work because then the language only needs to be a FSM 10:55:04 you need to talk about extending the original language's storage primitives to accommodate unbounded storage, without changing their character 10:55:54 argh jackhammer 10:56:21 more like jerkhammer 10:56:38 definitely 10:56:39 have you ever used a jackhammer? well I haven't but I did use a hammer drill for a while 10:56:45 that was p. fun 10:56:47 for a few minutes anyway 10:58:11 you see we had this tradition where the freshman build a fortified bunker in one of the dorms at the end of the school year 10:58:46 and then all of the people who were really gung ho about this being a good idea skipped town immediately after 10:59:02 and so it became my responsibility by default to demolish the bunker 10:59:20 and you haven't been the same since. 11:00:01 or anyway a significant part of it, being a 10cm thick door-size slab of reïnforced concrete in a doorway 11:01:16 we had a ```special trick''' which was to put some of the rebar inside conduit so that if you cut into the conduit with an angle grinder, you'll just spin the rebar inside it without cutting into the rebar 11:01:30 another ```special trick''' was to put some shaving cream cans inside the concrete 11:02:48 googling "10cm" finds on the first page "Is it true that the vagina is only 10 cm (3.9 inches) deep?" 11:03:04 confirmed: freshmen are insane 11:03:11 ah yes "the vagina", the international reference vagina kept at the Bureau international des poids et mesures under precise climate control 11:03:58 `addquote googling "10cm" finds on the first page "Is it true that the vagina is only 10 cm (3.9 inches) deep?" ah yes "the vagina", the international reference vagina kept at the Bureau international des poids et mesures under precise climate control 11:04:03 1136) googling "10cm" finds on the first page "Is it true that the vagina is only 10 cm (3.9 inches) deep?" ah yes "the vagina", the international reference vagina kept at the Bureau international des poids et mesures under precise climate control 11:05:07 -!- yorick has joined. 11:06:25 oerjan: the house put significant effort into selecting the kind of freshman who think this sounds like a great idea 11:06:55 should say "freshmen and freshwomen" although the colloquial "frosh" is nicely un-gendered 11:07:06 ah, to be young again, and also a robot 11:07:13 freshpeople 11:07:31 @tell madbr or something in the style of the collatz sequence <-- collatz functions, see our wiki. you are _not_ going to escape the "encoding a program" part when you prove something actually _is_ TC, though. 11:07:31 Consider it noted. 11:09:59 i guess that had to be futurama. 11:45:18 -!- ais523 has joined. 12:08:30 -!- Sgeo_ has joined. 12:11:02 -!- Sgeo has quit (Ping timeout: 240 seconds). 12:13:11 -!- oerjan has quit (Quit: leaving). 12:16:58 -!- yorick has quit (Remote host closed the connection). 12:18:56 -!- yorick has joined. 12:32:48 -!- Sgeo_ has quit (Read error: Connection reset by peer). 12:55:51 -!- doesthiswork has joined. 13:01:45 -!- JesseH has joined. 13:01:52 New idea for a language. I call it BodyMindLang 13:01:56 not 1 13:01:56 -!- boily has joined. 13:01:57 => true 13:02:00 not 2 13:02:03 -!- metasepia has joined. 13:02:03 => true 13:02:20 not 1 and not 2 13:02:22 => true 13:02:39 good true morning! 13:02:58 o/ 13:16:36 -!- yorick has quit (Remote host closed the connection). 13:31:36 alas, poor yorick 13:32:14 He shall be missed. 13:32:31 * boily lobs a strangely misshapen, not-quite-from-this-Earth cranium over at lexande 13:32:51 * JesseH hops on his Bike 13:42:41 -!- yorick has joined. 13:56:54 `unicode MOUNTAIN BICYCLIST 13:56:56 Unknown character. 13:57:22 `unidecode 🚵 13:57:24 ​[U+D83D DUNNO] [U+DEB5 DUNNO] 13:57:32 darn. 13:57:44 fizzie: nice dunno. 13:59:55 It's not very non-BMP-friendly, because of an UCS-2 Python build. 14:01:06 -!- doesthiswork has quit (Quit: Leaving.). 14:13:11 kmc: this coallier person seems pretty douchey, wtf 14:17:18 `unidecode 北北 14:17:19 ​[U+5317 CJK UNIFIED IDEOGRAPH-5317] [U+F963 CJK COMPATIBILITY IDEOGRAPH-F963] 14:17:56 catchy names 14:18:15 Bike: yup 14:18:55 Oh my god, Bike you're a real person? Sorry for sitting on you mate 14:19:13 i'm a real bike 14:19:26 and a reeeeeal hero 14:19:59 O_o 14:20:02 whatever you say man 14:23:04 -!- tertu has joined. 14:23:27 whatever you say bike 14:23:36 http://www.youtube.com/watch?v=-DSVDcw6iW8 14:46:28 -!- constant has changed nick to variable. 14:52:11 -!- asie has joined. 14:57:12 -!- nooodl has joined. 15:21:59 -!- conehead has joined. 15:29:28 -!- mrhmouse has joined. 15:34:35 Bike is a real hero? 15:36:13 -!- muskrat has quit (Quit: Leaving). 15:42:52 -!- Sprocklem has joined. 15:46:30 -!- monotone_ has joined. 15:48:10 -!- int-e_ has joined. 15:51:10 -!- Gregor` has joined. 15:51:23 mrhmouse: Bike is everything. Bike is the Whole Experience of the Universe. Bike has two wheels. 15:51:55 -!- rodgort` has joined. 15:52:39 -!- monotone has quit (*.net *.split). 15:52:39 -!- rodgort has quit (*.net *.split). 15:52:39 -!- int-e has quit (*.net *.split). 15:52:40 -!- Gregor has quit (*.net *.split). 15:52:40 -!- HackEgo has quit (*.net *.split). 15:52:52 -!- HackEgo has joined. 15:59:40 -!- int-e_ has changed nick to int-e. 16:02:07 -!- doesthiswork has joined. 16:16:53 -!- asie has left ("Textual IRC Client: www.textualapp.com"). 16:19:42 -!- FreeFull has joined. 16:22:11 -!- Gregor` has changed nick to Gregor. 16:34:19 Are the registers initialized at anything in particular in x86? 16:34:44 I guess some are like the instruction pointer and such, but what about the rest 16:34:57 Like the address of the stack and such 16:37:03 -!- monotone_ has changed nick to polytone. 16:40:00 Are they at 0 on power on and initialized by the BIOS? 16:44:25 I thought the initial value was undefined...? Just some random value? 16:44:40 A lot of it is defined. 16:45:19 From what I remember they're condensators (kinda), so I would guess that either they are drained on power off or left at the old value 16:45:24 So I guess either 0 or random 16:45:28 But I don't know which 16:45:37 The (somewhat dated) copy of the AMD64 Architecture Programming Manual has a section 14.1.3 Processor Initialisation state. 16:45:43 And I don't know if it's initialized at anything by BIOS 16:45:50 registers are static RAM so they're logic gates in a feedback configuration, not capacitors 16:45:57 disclaimer: may be completely wrong 16:46:33 at minimum CS will be initialized in addition to IP 16:46:44 so CS is 0xF000, other segment registers are 0, RAX is 0, RDX contains some CPU ID information, other basic registers are 0 ... 16:46:58 they are either 0, 1, random, undefined, unknown or blueberry flavoured. 16:47:05 and RIP is 0xFFF0. 16:47:19 even flags are defined :) 16:47:25 what's the CPU ID info useful for? 16:47:35 RAX? 16:47:52 RAX is the x86-64 64 bit version of AX/EAX. 16:47:57 Ah 16:48:08 Most doc I've seen stops at 32 16:48:08 some of the flags register must be defined to successfully execute an instruction 16:48:14 like trap flag = 0 16:48:26 In any case, those processor manuals are the right place to look up such information :) 16:49:09 Also what exactly does the stack definition do in the assembly? 16:49:18 hm? 16:49:18 The .stack 256 or whatever it may be 16:49:28 oh, which assembler? 16:49:29 (rflags is essentially set to 0, but there's a reserved bit that is forced to be 1 :) ) 16:49:43 I guess the general purpose is to define the size of the stack, but how does that translate in the processor? 16:49:46 also has anyone seen the electrical datasheet for a current Intel / AMD processor? with like a thousand entry pinout list? :) 16:49:46 In 8086 16:49:49 are those public? 16:50:00 I guess they're public enough? 16:50:03 Slereah_: no, what assembler program 16:50:11 Slereah_: well have you seen one? 16:50:18 No, I just assume kinda 16:50:25 u make an ass out of u and me 16:50:26 Otherwise it might be hard to program anything on them 16:50:47 I think I have seen the pinout list for a recent-ish socket, but not a full datasheet 16:50:51 The examples I see are usually in Borland C 16:51:02 Slereah_: no, the architecture manuals are enough to do programming 16:51:14 you don't need to know the electrical specifications of the particular chip your code is executing on 16:51:21 ...usually 16:51:43 right. no I have not seen any detailed electrical datasheets. Then again, I've never really looked for them. 16:51:51 but if you look up the datasheet for (say) an 8-bit AVR microcontroller, it has info both on "this instruction does that" and also "this pin needs this many volts" 16:52:30 Don't they have to give such things to the patent office? 16:52:42 Yeah, but with those guys (embedded processors) you are you are quite likely to be your own motherboard manufacturer. 16:52:45 doubtful 16:53:07 Then I don't know 16:53:07 patents are pretty general, you don't need to submit detailed specs of every product which invokes the patent, I don't think 16:53:20 You never know with those fucks 16:53:53 Slereah_: only if you patent them, and even then you don't have to describe anything at the packaging level (which pin does what). And you can split features into many patents (signaling on busses, communicating with memory, etc.) 16:54:11 Slereah_: and I don't know about your .stack; googling with "borland C" doesn't find anything, and it's not something I recall from any assembler I've used 16:54:33 hm, MASM has a .STACK: http://msdn.microsoft.com/en-us/library/bffws6w0(v=vs.71).aspx 16:54:46 http://prism2.mem.drexel.edu/~rares/asm4.htm < for instance 16:54:51 MODEL small 16:54:51 STACK 266 16:54:57 mr-: Yes, but I'm not sure that it helps much in this case. 16:55:01 Er, wrong channel. 16:55:06 Apparently the MODEL describes where the code and data are stored 16:55:11 so it's probably more of a linker directive, which tells the linker how much space to reserve for the stack 16:55:21 http://msdn.microsoft.com/en-us/library/bffws6w0%28v=vs.110%29.aspx 16:55:39 I guess STACK initializes the stack base and allocates some memory up to 266*4 in that case? 16:55:39 it probably ends up in bytes 10-11 of an EXE file, http://www.delorie.com/djgpp/doc/exe/ 16:55:47 and puts something in the .EXE saying what the initial value of SS:SP is? 16:55:48 Maybe? 16:56:00 ah yep 16:56:02 (obviously that's old DOS EXE files, not the sille PE ones we have nowadays) 16:56:04 *silly 16:56:34 I bet that with .COM files you're not allowed to use .STACK because you're stuck in the TINY memory model anyway 16:56:45 speaking of PE executables: http://blog.theincredibleholk.org/blog/2013/11/18/booting-to-rust/ 16:56:47 -!- MindlessDrone has joined. 16:56:59 boot to Rust via UEFI, with no assembly 16:57:06 (I say "probably" because the 8086 segmented addressing model has so much aliasing) 16:58:09 kmc: it could still be a declaration that a linker can use to check whether everything (code, data, declared stack) fite into 65300 bytes (256 bytes go to the PCB (process control block)). 16:58:21 so 65280. darn :) 16:58:35 but would it also emit code to initialize SS:SP? 16:58:46 what for? the OS does that for the program 16:58:49 I think DOS does that for you to a fixed point, probably just the end of that 64k 16:58:52 right 16:59:04 based on the header fields, or just SP=0xFFFE for a COM file. 16:59:08 but yeah, I guess the checking is still potentially useful 16:59:55 that said, I'm not sure whether .stack is allowed in the .tiny model :) It's been a while ... 17:00:21 -!- Sprocklem has quit (Ping timeout: 252 seconds). 17:00:21 Also most documents seem pretty vague on how many registers there are 17:00:33 There's the basic ones described by most 17:00:38 Then the flag things 17:00:44 Then control registers and debug??? 17:00:49 the answer is "a fuckload" 17:00:50 And divider??? 17:00:56 again, processor manuals are the source to go to (but have a history of not talking about all registers *anyway*) 17:00:58 Are they all accessible? 17:01:06 yes read the manual 17:01:11 Thx 17:01:35 I think the less manual-y question is "is it a good idea to access them" 17:01:56 in particular, read the bit of the Intel manual where it talks about the VMX virtualization feature, because that describes the layout of an in-memory struct used to save/restore ~all state from a VM 17:02:10 this is x86? i don't think there's like, a mov-word-to-flags-reg ability 17:02:16 including some things that aren't directly accessible, like the segment descriptor which was loaded when a segment selector was last set 17:02:27 Bike: there's lahf / sahf 17:02:31 Bike: there is lah... 17:02:34 too slow 17:02:40 Slereah_: "good idea" depends on what you're trying to do.......................................................................... 17:02:41 right, of course there is 17:03:04 Slereah_: control registers are essential to the operation of a typical operating system 17:03:04 Well currently mostly trying to get a feel of Assembly 17:03:14 but are invisible to userspace code 17:03:14 SAHF: Welcome to Stewards for Affordable Housing for the Future 17:03:15 I'll probably stick with the usual registers from now on 17:03:20 I'll see the rest later 17:03:27 they set things like, where in physical memory does the page table live 17:03:48 debug registers are useful for debugging, e.g. breakpoint when a particular memory address is accessed 17:04:00 Bike: obviously the mnemonics are for "load ah register from flags" and "store ah registers into flags" 17:04:10 yeah i looked it up 17:04:17 unrelatedly, it's hard to take toilet day seriously, i blame sgeo 17:04:18 they too can only be directly manipulated by ring-0 (i.e. kernel-mode) code 17:04:21 Assembly is kind of weird 17:04:30 a typical OS will provide some interface like ptrace() for using those debug registers 17:04:32 what's weird about it 17:04:33 If they're just mnemonics for opcodes, why are most of them so cryptic 17:04:44 I guess back then it was to save space, but nowadays? 17:06:00 are you saying PCLMULQDQ isn't immediately obvious 17:06:22 Well that one is obvious, but who would guess that mov is move 17:08:42 or that jmp is branch ;-) 17:08:43 Slereah_: the regs you're likely to see in user code are: R[ABCD]X RSI RDI RSP RBP and their sub-components; RIP (in RIP-relative memory addressing), flags (implicitly for the most part), x87 FPU registers ST0 through ST7, MMX registers MM0 through MM7, SSE registers XMM0 through XMM15 17:09:01 and segment selectors, mostly only FS and GS these days 17:09:09 (though honestly, making 'b' the mnemonic for 'branch' isn't all that sane either.) 17:09:29 and R8 to R15 17:09:30 kmc : All the R's I saw in most documents, the rest I have no idea! 17:09:43 int-e: oh yeah duh 17:10:11 But well I guess I'll stick with simple things for now 17:10:15 Like "print a letter" 17:10:20 sounds good 17:10:37 Also I saw that it's not too complicated to access the PC speaker, which is neat 17:10:56 * int-e hands Slereah_ some black ink and lead, 17:10:57 in 16-bit code you're more likely to use the segment overrides 17:11:09 anyway yeah you should probably keep learning rather than listening to me recite lists :) 17:11:10 int-e : Real men use a brush 17:11:35 fs: is used for thread-local storage :) 17:12:09 assembly code in calligraphy 17:14:01 I got "flat assembler" for assemblin', I'd better see the syntax there 17:14:51 hmm, is nasm still maintained? 17:14:57 Not a clue! 17:15:06 Really I thought Assembler would be much worse than it is 17:15:09 "real men" jokes are distasteful because tying this or that skill to masculinity is problematic 17:15:23 But it has constants, procedures and control structures :o 17:15:43 (yes it is :-) ) 17:16:12 It's basically C with a slightly more distasteful handling of variables 17:16:32 people make a big deal about x86 being so complicated but it's not that hard when you're writing it yourself, as opposed to understanding what a compiler has spit out 17:16:45 much of the complexity works in the favor of the assembly author 17:17:05 I guess reading binary might be tough, yeah 17:17:14 well you disassemble it 17:17:21 but you lose a lot of context 17:17:24 How are the jump instructions translated, by the way? 17:17:27 It's like 17:17:31 .jump point 17:17:33 do shit 17:17:34 Slereah_: typically an offset in bytes 17:17:37 JMP whatever 17:17:47 -!- Frooxius has quit (Read error: Connection reset by peer). 17:17:52 one of the main things an assembler provides is resolving those labels into byte offsets 17:17:54 Is the jump point translated as the address of that point? 17:17:56 (Assembler documentation like http://www.nasm.us/pub/nasm/releasebuilds/2.11rc1/doc/nasmdoc.pdf can also be a viable source for learning about processor features.) 17:17:56 or absolute addresses depending 17:17:57 yes 17:18:30 (and one of the main things a linker provides is, deferring that process) 17:18:57 (such that you can compile/assemble many files independently into something that's like machine code but still has jump targets in a symbolic form, and then link them all together quickly) 17:19:08 one time i tried reading 6502 asm that had this convention where you could put * next to a line, and then "jmp ++" would mean "jump to the second line ahead with a *", etc. that was quite confusing 17:19:19 lolwut 17:19:47 GNU as has something like that; you can write numeric labels 1: or 2: and then jmp to them as 1f (meaning "next 1:") or 1b (meaning "previous 1:") 17:19:58 very useful for inline assembly 17:20:16 Oh. A puzzle for Slereah: figure out the difference between jmp short foo and jmp near foo. (Not quite serious.) 17:20:31 so like for a loop you'd have "* ...loop body... jump-if-test -;" 17:20:43 Slereah_: I find an absolutely vital tool for understanding assembly is to run a disassembler on the output 17:21:09 then you see what instructions were really encoded, with machine code and mnemonics side by side 17:21:21 -!- Frooxius has joined. 17:24:53 -!- ais523 has changed nick to ais523\unfoog. 17:24:55 I'll give it a shot, thanks 17:25:32 I assume all the header shit is either preprocessor shit or initialization? 17:25:57 header in the assembly source or in the binary? 17:26:03 Assembly source 17:26:12 Like replacing the constants and initilizing the segment registers and such 17:29:23 -!- Oj742 has joined. 17:32:06 -!- tertu has quit (Read error: Connection reset by peer). 17:32:23 -!- tertu has joined. 17:36:04 I wonder if anyone ever made some hardware cellular automaton 17:36:08 Probably not too hard to do 17:41:01 -!- tertu has quit (Read error: Connection reset by peer). 17:41:14 -!- tertu has joined. 17:41:29 ask google 17:41:57 -!- MindlessDrone has quit (Ping timeout: 248 seconds). 17:42:44 http://www.univ-orleans.fr/lifo/Members/Jerome.Durand-Lose/Recherche/Publications/1996_RT-LIP_1996-01.pdf 17:42:47 So it seems 17:51:09 -!- Oj742 has quit (Ping timeout: 272 seconds). 17:56:00 -!- MindlessDrone has joined. 18:01:19 I don't see what'd be hard at doing cellular automatons in Hardware 18:02:13 are we talking 'lay out a circuit' hardware or 'with a processor but no particular OS' hardware 18:02:18 either way it seems simple enough 18:02:45 'lay out a circuit' I assume 18:03:27 yeah 18:03:51 i should really figure out the VGA driver on my FPGA so i could try that>_> 18:04:11 doing it efficiently is probably hard 18:04:24 but doing it at all... 18:04:29 vhdl to the rescue :) 18:05:00 is it that hard? you'd just need a little register, and inputs from the clock and the neighborhood, for each cell 18:05:17 i mean, something like hashlife would be hard, of course 18:06:00 depends on the automaton 18:06:07 I mean 18:06:18 you could just use some sram 18:06:24 :) 18:06:35 store some 2D stuff in there 18:06:39 and boing.. you're done 18:07:31 depends on how much storage you need 18:07:46 well what kind of automata do you like, Slereah_ 18:07:57 it'd be even easier with a 1D automaton 18:08:04 like wolframs thingy 18:08:21 that would just fit neatly into a single bitstream 18:08:59 i did wolfram automata on a shitty calculator once. surely hardware can't be harder 18:10:32 -!- Taneb has joined. 18:12:14 if you can program it you can also program it in vhdl 18:12:18 and if you can program it in vhdl 18:12:22 it's hardware-ish 18:13:28 Going to university has made me realise that while I'm not the best programmer, this channel has set me up with a brilliant background knowledge of the theoretical side of CS 18:13:30 Thanks 18:14:04 great, so you can help us analyze the time complexity of this thing 18:14:05 then you can only imagine how I feel here ;) 18:14:07 (nb nah) 18:14:26 Bike: i've analyzed it and the time complexity is "very" hth 18:14:34 I assume I'm the dumbest person in this channel. 18:16:51 let's see, module pt (input clk, input [7:0] neighborhood, output [...] out); reg [...] state; assign out = state; always @(posedge clk) state <= ...some function of state and neighborhood...; endmodule 18:16:55 and i think that's about it. 18:17:15 just make a couple thousand of those and it's all good 18:18:25 -!- AnotherTest has joined. 18:19:57 i dunno vhdl ;( 18:20:14 It's pretty easy 18:20:22 Everywhere where you'd expect not to put a semicolon 18:20:27 just put a fucking semicolon there 18:20:31 sensible 18:20:36 everywhere where you'd put a comma 18:20:42 try putting a semicolon first 18:21:10 this is an accurate description :) 18:21:23 I think there is a context that uses commas, though 18:21:30 Yes 18:21:32 Port Maps use commas 18:21:34 both of them are frickin verbose 18:21:42 other list-like stuff uses semicolon as a seperator 18:22:08 but it's illegal to put a semicolon at the end of such a list 18:22:21 that's one exception to the previously stated rules 18:22:36 also 18:22:43 I think there's one place where you have to write 18:22:48 GENERIC () MAP () 18:23:05 and there's a place where you have to write GENERIC (); MAP (); 18:23:29 which makes sense though 18:23:42 somehowe 18:24:28 obviously i should just get zzo to give me money for an open source neuromorphic fpga, and then i can make my own synthesizer for my own language, w/ blackjack & hookers 18:27:06 It ain't a party with just one hooker . 18:28:02 mostly blackjack, practically speaking 18:28:11 -!- carado has quit (Quit: Leaving). 18:29:43 I'd love to see a vhdl synthesizer that can produce plans for mechanical hardware 18:29:52 with ... like ... 18:30:13 piñón 18:30:17 mechanical? 18:30:28 gear wheels 18:30:33 Bike: Yeah 18:30:50 piñón is apparently pine nuts? 18:31:02 no 18:31:02 and i have an esolang idea that's basically that (or rather the vhdl equivalent) 18:31:12 since like, digital operations are hard. 18:31:28 -!- carado has joined. 18:31:52 Mechanical Computers don't need energy when they're not doing stuff . 18:32:07 So lazy 18:32:18 you'd have to use a crank 18:32:23 and crank 18:32:36 apparentely the word for that is crank 18:33:00 *really* 18:33:03 well, real mechanical computers usually used motor drives, since you need it to have an exact speed 18:33:08 cranks were just used for input 18:33:19 with like 18:33:21 steam powered? 18:33:25 Awesome 18:33:34 I'd love to have a steam powered super computer 18:33:38 that'll show china 18:33:45 steam?? this is the 1940s 18:33:50 or whoever is currently leading in this cyber d*** contest 18:33:52 i mean, you could use steam if you wanted, i guess 18:34:05 just anything that can get you a steadily turning gear. 18:34:09 you need that for integrators. 18:34:09 I don't know when steam got old 18:34:52 depends on what you mean by steam, i guess... the obvious nuclear reactor design which i think is still used is basically steam 18:35:14 right 18:35:46 Regular steam engines 18:36:06 anyway i don't really know what real mechanical computers used, i'm pretty sure that by wwii they were basically on diesel 18:37:14 power source isn't terribly important though, the trick is making the components have enough accuracy 18:37:28 lemme tell you, CVTs are some weird-ass shit to make 18:52:51 -!- Bike has quit (Ping timeout: 272 seconds). 18:56:50 Balanced ternary electronic computers are so much simpler 19:02:58 Controversy at the university of York as HackSoc, the university's computer science society, declares an upcoming game-making society to be stepping on their toes 19:03:43 Taneb: that sort of thing never happens at Birmingham, it's considered an advantage to be able to get away with having two basically identical societies 19:04:18 ais523\unfoog, doesn't Birmingham have like 5 universities 19:04:41 yeah, but only one is the University of Birmingham 19:04:47 the others all have different names 19:04:52 Actually, York has two and a half universities 19:05:07 also two of them only became classified as universities recently 19:05:35 (University of York, York St John University, and Hull York Medical School) 19:05:52 (and strictly speaking the last one is half part of the first one) 19:06:06 thus the "and a half" 19:07:09 And also half part of the University of Hull 19:08:15 But the University of York has one of the highest duck to student ratios of any university in the world! 19:12:02 http://doctorbeet.blogspot.co.uk/2013/11/lg-smart-tvs-logging-usb-filenames-and.html 19:18:51 -!- myname has quit (Ping timeout: 252 seconds). 19:26:40 -!- myname has joined. 19:30:07 -!- oerjan has joined. 19:50:16 wow 19:50:26 labeling long horizontal lines "Horizontal long lines" is genius 19:50:38 @figure 4 of that high speed harware automaton paper 19:50:38 Unknown command, try @list 19:50:50 hairyware 19:50:57 3 vertical long lines 19:50:58 cool 20:00:08 -!- aloril has quit (Ping timeout: 245 seconds). 20:00:36 -!- augur_ has quit (Remote host closed the connection). 20:01:06 -!- augur has joined. 20:01:42 i think the zuse z1 had an electric motor 20:03:48 -!- augur_ has joined. 20:05:47 -!- augur has quit (Ping timeout: 272 seconds). 20:07:43 What paper? 20:16:16 -!- aloril has joined. 20:22:05 -!- variable has changed nick to function. 20:25:54 -!- Bike has joined. 20:27:45 -!- nisstyre has joined. 20:27:55 -!- tertu has quit (Ping timeout: 265 seconds). 20:29:43 -!- aloril has quit (Ping timeout: 252 seconds). 20:34:22 ~yi 20:34:22 Your divination: "Humbling" to "Swallowing" 20:37:53 -!- aloril has joined. 20:40:27 -!- Sprocklem has joined. 20:43:18 -!- tertu has joined. 20:49:11 -!- Sprocklem has quit (Ping timeout: 265 seconds). 20:58:07 -!- augur_ has quit (Remote host closed the connection). 20:58:43 -!- augur has joined. 20:59:04 -!- augur has quit (Read error: Connection reset by peer). 20:59:14 -!- MindlessDrone has quit (Quit: MindlessDrone). 20:59:23 -!- augur has joined. 21:00:29 -!- tertu has quit (Read error: Connection timed out). 21:01:29 -!- tertu has joined. 21:21:49 ~yi 21:21:49 Your divination: "Stripping" to "Swallowing" 21:21:57 swallowing 21:21:59 time for food. 21:22:43 fungot: you're way better than metasepia 21:22:44 shachaf: 1.8.5 would allocate 128 bytes per loop.) 21:22:53 fungot: and way better than lambdabot 21:22:54 shachaf: and it still seems like an odd goal, which is deterministic, it just requires making your eval support a fnord flag for fnord would just muck up the puzzle 21:23:01 fungot: especially with the new management!! 21:23:02 shachaf: abum hehe i've done that kind of sh1t hasn't happened in linux for graphics pretty much all sedative drugs, very similar to the list 21:23:53 -!- AnotherTest has quit (Ping timeout: 245 seconds). 21:24:18 shachaf: :-( 21:24:35 shachaf: is fungot better than ruddy? 21:24:35 mrhmouse: yes... i see someone who is in almost as many channels as you're in, you can do 21:24:35 clap clap! 21:24:42 fungot is better than ruddy 21:24:42 shachaf: hm. so you're golden. 21:24:43 yes... i see someone who is in almost as many channels as you're in, you can do 21:25:14 well, I can't argue with golden 21:28:08 :-( 21:28:41 :-) 21:29:03 int-e: how come i'm not in the lambdabot admins list 21:30:44 I took elliott's list of admins. 21:31:04 shachaf: don't diss my lovely bot. 21:31:13 -!- tertu has quit (Read error: Connection reset by peer). 21:31:30 -!- tertu has joined. 21:32:01 -!- muskrat has joined. 21:32:09 fungot is lovely too 21:32:09 shachaf: if i'm going north or south" i am part of the ' offcuts' of several famous single malts. 21:32:15 -!- ter2 has joined. 21:32:26 fungot: exactly 21:32:26 shachaf: ( cadr fnord) doesn't properly clear the screen correctly: just scheme code in a module are statically decidable. regexes, otoh... would be very helpful 21:32:36 -!- tertu has quit (Read error: Connection reset by peer). 21:33:59 I'd be slightly surprised if (cadr fnord) did clear the screen. 21:34:00 shachaf: and I don't think we're short on lambdabot admins, are we? 21:34:30 int-e: You'd be surprised. 21:35:44 yes I would 21:36:31 -!- Taneb has quit (Quit: Leaving). 21:52:21 -!- muskrat has quit (Quit: Leaving). 22:02:39 -!- boily has quit (Quit: SUPERLATIVE CHICKEN!). 22:02:41 -!- metasepia has quit (Remote host closed the connection). 22:03:57 -!- ter2 has quit (Ping timeout: 252 seconds). 22:05:27 -!- Taneb has joined. 22:06:31 That's weird. Told mplayer to play a .mp3 file, and it's showing a 88x31 "video" of the CC-BY-NC-SA license logo banner icon thing. 22:07:10 fizzie: are the file contents actually MP3 format? 22:07:34 According to 'file', sure. 22:07:42 "Audio file with ID3 version 2.3.0, contains: MPEG ADTS, layer III, v1, 128 kbps, 44.1 kHz, JntStereo" 22:08:03 I guess it's some curious ID3 image thing, but I've never seen that happen before. 22:08:10 interesting indeed! 22:08:18 Also it keeps complaining, though it plays just fine. 22:08:41 http://sprunge.us/KEIN and so on. 22:08:52 Not just one but three "video" streams. 22:09:21 Must be some kind of a mplayer2 thing, I don't recall the old one ever "playing" ID3 tag images. 22:13:47 -!- ter2 has joined. 22:36:46 oerjan: imo add chu spaces to https://en.wikipedia.org/wiki/Topological_space#Specializations_and_generalizations 22:37:12 imo do it yourself 22:37:47 imo i don't remember my wikipedia password 22:38:01 https://news.ycombinator.com/item?id=599852 22:38:17 imo ask them to send it to your email 22:40:25 ion: sweet. 22:42:05 -!- darklust_ has quit (Ping timeout: 252 seconds). 22:43:20 http://www.preposterousuniverse.com/blog/2013/11/19/scientists-confirm-existence-of-moon/ "Scientists Confirm Existence of Moon" 22:53:52 -!- oerjan has quit (Quit: Insert pun here). 22:57:44 -!- augur has quit (Remote host closed the connection). 22:57:51 -!- ter2 has quit (Ping timeout: 252 seconds). 22:58:17 -!- augur has joined. 22:59:47 -!- augur_ has joined. 23:02:29 -!- augur has quit (Ping timeout: 248 seconds). 23:07:22 -!- Phantom_Hoover has joined. 23:10:57 -!- carado has quit (Ping timeout: 252 seconds). 23:15:44 I forgot how sad Interstella 5555 was 23:16:13 that seems like a good thing if it was sad 23:16:30 what if i value sadness more than happiness. 23:16:34 afaict it's about the space smurfs? 23:16:47 yeah. one of em dies 23:16:57 It's an anime opera by Daft Punk about space smurfs 23:17:05 god damn it i have one more time stuck in my head now 23:17:48 killing off a character isn't that sad 23:18:14 Taneb: have you seen Grave of the Fireflies? 23:18:19 mrhmouse, I have not 23:18:24 Is that an opera by Daft Punk 23:18:29 it should be 23:19:15 it's my understanding that if interstella 5555 is sad grave of the fireflies will convince you to hang yourself halfway through the film 23:19:15 But no, it's a film by Isao Takahata 23:19:22 i have, it's at least 100% more sad 23:19:40 Bike: that sounds about right. you might be understating it 23:19:47 well, i've never seen it. 23:20:17 don't really intend to either, god knows i've seen enough sad world wars in snow 23:20:51 I've seen enough sad things this century 23:21:45 GofF is pretty high on my "my face is leaking please help" list 23:21:50 *GotF 23:22:14 actually make that at least 500% more sad 23:22:25 at least 23:22:53 I don't think we can call GotF "sad" because otherwise by comparison nothing else is sad ever 23:23:19 actually, gotf makes me think of another japanese film i haven't seen that's probbly near the same level 23:23:28 do tell 23:23:30 or at least, it's nine hours of a socialist getting eaten alive by the IJA 23:23:46 http://en.wikipedia.org/wiki/The_Human_Condition_(film_series) 23:23:49 that is, uh, not really the same 23:24:30 oh he's not being literally eaten alive 23:24:39 lol 23:25:37 outside of the subject of war, the only other film content that's made me that sad was season 2 (or 3?) of the Dr. Who reboot. But that was some time ago. 23:34:13 doctor who lost the ability to evoke any emotion in me other than cringe long ago 23:36:38 -!- Taneb has quit (Quit: Leaving). 23:38:15 it's campy and cheesy 23:38:19 but I like that 23:39:13 mind you, I haven't seen anything past Tennant.. so I'm not sure if that still holds. 23:50:12 -!- nooodl has quit (Quit: Ik ga weg). 23:51:15 -!- Sprocklem has joined. 23:51:37 mrhmouse, it does not 23:52:54 -!- CADD has joined. 2013-11-20: 00:04:58 that's disappointing, then :/ 00:05:47 -!- mrhmouse has quit (Quit: Leaving.). 00:11:58 -!- CADD has quit (Quit: leaving). 00:17:37 -!- nisstyre has quit (Quit: Leaving). 00:18:33 -!- nisstyre has joined. 00:21:19 -!- nisstyre has quit (Read error: Connection reset by peer). 00:26:35 -!- prooftechnique has joined. 00:43:07 -!- Phantom_Hoover has quit (Remote host closed the connection). 00:49:43 -!- ter2 has joined. 00:52:57 -!- nisstyre has joined. 00:53:19 -!- Bike has quit (Ping timeout: 272 seconds). 01:04:31 -!- Bike has joined. 01:09:52 -!- CADD has joined. 01:10:55 -!- CADD has quit (Client Quit). 01:19:14 -!- CADD has joined. 01:24:22 -!- Sgeo has joined. 01:30:45 -!- Sprocklem has quit (Ping timeout: 240 seconds). 01:41:02 -!- yorick has quit (Remote host closed the connection). 01:48:21 -!- function has changed nick to trout. 02:22:47 -!- copumpkin has changed nick to samwell. 02:22:51 -!- samwell has changed nick to copumpkin. 02:42:51 huh, . in C and -> in C both become . in Rust 02:43:00 because it always knows whether the LHS is a struct or a pointer to struct 02:43:38 -!- Darklust has joined. 02:48:24 Feels a bit implicit-castish 02:48:33 Although not sure if it's really a problem 02:48:41 When would you want to actually . on the pointer? 02:50:33 what's doing ais523\unfoog 02:50:38 also what does unfoog mean 02:50:54 Sgeo: you can't . on a pointer in C, which is why it works 02:50:59 and unfoog is a /dev/null/nethack clan 02:56:17 what are you working on 02:56:41 right now, nothing 02:56:47 over the last few days I've been working on NetHack 4 02:56:58 and more generally, I've been working on my PhD thesis 02:57:17 damn you're still survivng academia. wow. 02:57:20 what's the thesis on 03:00:25 :\ 03:00:27 -!- Sprocklem has joined. 03:01:20 quintopia: hardware compilation 03:01:51 sounds lame. you're like pretty close to myy age right? 03:04:19 I'm 26 03:05:30 yeah i'm 27 03:05:33 thot so 03:05:42 ever been potholing? 03:05:44 I tried to erase the content from my Derplang page, but it came back one day... 03:05:50 Not sure what to do about this. 03:06:02 Because im getting ready to do derplang 2, and its a big change up. 03:06:06 leave it alone 03:06:13 make a separate deplang 2 page 03:08:19 Oh, not a bad idea 03:09:06 JesseH: you can't delete a page by blanking it, that just leaves a blank page which confuses people 03:09:17 Ill keep the page 03:09:22 because the old derplang is still fun to use 03:09:23 I can delete pages given a good reason, but there isn't an obvious good reason to delete that one 03:09:48 But derplang 2 wouldnt belong on the esoteric site, because its less esoteric this time...a lot less 03:09:56 Improved syntactic sugar ^_^ 03:10:18 I would have changed the name but i am horrible with names. 03:10:27 well than 03:10:29 then 03:10:40 why are you doing it 03:10:55 Why am I doing what? 03:10:59 why would you make a language that is actually useful and convenient 03:11:11 because I haven't done that yet 03:11:17 oh 03:11:19 okay 03:11:20 well 03:11:23 it's not fjn 03:11:25 fun 03:11:33 Sure it's fun :P 03:11:39 The joy comes in writing it 03:11:54 I doubt people other than myself would use it... 03:12:00 but still 03:12:20 ah the spec might be fun 03:12:27 Python didnt start off at version 2.7 03:12:30 but implementing a real full on language 03:12:32 is 03:12:34 a pain 03:12:43 Sure its painful, but its fun too 03:12:49 ah 03:12:51 a masochist 03:12:55 that i can appreciate 03:13:01 Like paintball, airsoft, or angry sex 03:13:27 that's a very esolangal motivation 03:13:38 but 03:13:46 i don't think it's the fun kind of pain 03:13:55 What is 03:14:54 the guy who figured out how to write actual functional algorithms in malbolge got to see the fun kind of pain 03:15:05 https://github.com/marcelog/jsonex/blob/2.0/lib/jsonex.ex 03:15:20 trying to implement languages has been more fun than using esolangs :P 03:15:26 But maybe I havent found the right language to use 03:17:51 -!- prooftechnique has quit. 03:18:12 JesseH: try implementing an esolang in another esolang! 03:34:58 quintopia, thats a terrible idea .... 03:35:00 i like it ._. 03:36:37 Someone help me find an esoteric language that could be used for general purpose stuff if one was dedicated enough 03:36:51 I'm having some trouble torturing norns 03:38:43 tragic 03:40:47 Bike: what was it that made you horrified? My putting norn brains into the body of a toy, or my experimenting with how much ATP decoupler a norn could tolerate? 03:40:54 Or something else I forget 03:41:32 i don't remember 03:41:40 i also don't remember if i was actually horrified or just being silly 03:41:50 Bike 03:41:57 Your name fascinates me 03:42:09 it's not really an uncommon word 03:42:10 bleh, I want to go home and sleep 03:42:14 but it's like 3;42 03:42:16 JesseH: fungot is written in Befunge 03:42:16 Sgeo: what is lambda?) on windows, have a bunch of empty cd-rs. err... 03:42:17 *3:42 03:42:22 which is not a good time to be walking around 03:42:57 Befunge-98 allows for plugins to the language, I think 03:43:33 ooo neat 03:43:43 pluggable commands, to be exact 03:44:31 you cannot use more than 26 commands at any given time (there are some ways to work around but limited) 03:44:55 you can swap out the commands dynamically, though 03:45:52 What are your favorite esolangs? 03:47:30 Underload; BF Joust; various functional-ish ones that haven't been fully worked out yet 03:47:51 I'm kind-of an esolang narcsissist, I tend to prefer esolangs I created myself 03:48:03 but that's mostly because I aim to create the sort of esolangs I like 03:48:50 link me to your esolangs so i can see if im interested 03:48:55 :P 03:49:07 I would google but i need to go scavenge for good 03:49:09 food 03:49:12 good food 03:51:40 JesseH: there's a list on http://esolangs.org/wiki/User:ais523 03:52:04 \o/ 03:52:04 | 03:52:04 |\ 03:52:15 lol 03:52:42 Jesus 03:52:46 You made a lot :p 03:53:10 not as many as cpressey did (he also has a good eye for interesting esolangs) 03:54:03 Oooo minimax looks nice 03:54:44 backflip looks painfil 03:54:46 painful 03:56:05 http://esolangs.org/wiki/Black 03:56:07 Good god 04:00:41 /o\ 04:00:41 | 04:00:41 |\ 04:00:52 ha 04:02:08 I should try to get a grasp of the Erlang OTP 04:17:48 -!- `^_^v has quit (Read error: Connection reset by peer). 04:18:13 -!- `^_^v has joined. 04:20:08 I recommend it. 04:22:27 -!- conehead has quit (Quit: Computer has gone to sleep.). 04:23:06 i have just come upon the greatest bug ever in my life 04:26:10 yeah? 04:26:30 i'm writing a program to draw a circle in SELECT. 04:26:45 it works great for 20 evenly spaced points on a circle 04:26:50 but when i do 400 04:28:26 it transposes the bottom and top thirds (breaking it at the points corresponding to the angles tau/8, 3tau/8, 5tau/8) just enough to make a funny tesselatable bowtie. and instead of halting after drawing it, it goes and draws it again in the opposite direction, apparently forever 04:28:37 (it halts fine on the small case) 04:29:03 no idea why the imaginary part keeps getting translated like that 04:29:25 but it is quite nice to look at 04:30:19 how reproducible is it? 04:31:12 ah. well let's see. i'll run it again. (it should be perfectly reproducible...everything involved is determinstic) 04:32:26 yep. reproduces. 04:33:08 Well, that makes me scared to try BEAM languages... 04:33:11 i suspect it's some mpmath weirdness 04:38:03 BEAM? 04:38:52 -!- nycs has joined. 04:39:43 what's the smallest number of points it appears in 04:41:30 -!- `^_^v has quit (Read error: Operation timed out). 04:41:32 Bike: the Erlang VM thingy 04:42:18 doesthiswork: i'll find out 04:42:19 oh. 04:54:52 -!- CADD has quit (Quit: you are all a bunch of faggots). 04:55:53 -!- CADD has joined. 04:58:08 My favorite esoteric language....Perl 04:58:25 Perl is not an esolang 04:58:34 *gasp* 04:58:43 JesseH: that's basically the first joke about esolangs. we all made it at one point 04:58:53 frequently people make an unfunny "joke" where they just mash some keys on their keyboard and claim it's valid Perl 04:58:59 and I decode it, stopping at the first syntax error 04:59:10 ais, meanwhile, is just an astonishing person 04:59:18 Bike, which is why i had to make it...its my initiation. 04:59:54 I didn't make that joke about Perl, as far as I know 04:59:59 !pastlog esoteric.*Perl 05:00:08 let's find some examples of it 05:00:13 err 05:00:15 `pastlog esoteric.*Perl 05:00:16 does egobot have a pstlog too? 05:00:17 wrong bot :) 05:00:19 Wait there are more esolang jokes? 05:00:22 oh 05:00:28 JesseH: ESME 05:00:29 JesseH: don't worry, they're all terrible 05:00:33 "cant stop laughing" 05:00:49 No output. 05:00:56 ais523\unfoog: iajsdfijasdfijsdklfjasfjiowejfoiwejfiowejiofjweiofjwefjkjdlfjwf 05:00:59 in fact i think i made a joke about how bad jokes are once. 05:01:06 `quote Bike.*joke 05:01:08 871) i don't even know anything about feather and i'm getting sick of the time travel jokes \ 1034) i vaguely thought sigbovik was all jokes? oerjan: jokes written by CS people, so none of it's funny, just sad 05:01:10 there's a valid perl expression for you 05:01:11 oklopol: that is actually valid Perl 05:01:12 bam 05:01:26 although not particularly interesting, it just returns a string literal 05:01:28 you have just been served 05:01:31 I think you knew that though 05:01:43 well there is a paper showing that the number of errors some cs students made were not significantly different with perl and a language with random symbols (there was a significant difference between the random one and a control language) 05:01:44 `pastlog esoteric.*Perl 05:02:00 2010-03-01.txt:01:53:52: languages: Esoteric: 1l 2l adjust asm axo bch befunge befunge98 bf bf8 bf16 bf32 boolfuck cintercal clcintercal dimensifuck glass glypho haskell kipple lambda lazyk linguine malbolge pbrain perl qbf rail rhotor sadol sceql trigger udage01 underload unlambda whirl. Competitive: bfjoust fyb. Other: asm c cxx forth sh 05:02:02 doesthiswork: that was busted, they were given some really old Perl 4 with bad style 05:02:17 haha, EgoBot has the "perl is an esolang" joke too? 05:02:18 "[.+]" 05:02:29 !perl print iajsdfijasdfijsdklfjasfjiowejfoiwejfiowejiofjweiofjwefjkjdlfjwf 05:02:31 `pastelogs esoteric.*Perl 05:02:31 No output. 05:02:51 http://codu.org/projects/hackbot/fshg/index.cgi/raw-file/tip/paste/paste.16918 05:02:58 it's cool how i'm going to get like ten results of people doing this same log search 05:03:10 Bike: that's why I invented `pastlog 05:03:11 it omits today 05:03:17 ais523 I thought the complaint was not "modern" style, meaning it has been accepted style at one point 05:03:26 What do you call a tailor who talks too much? 05:03:26 «#esoteric is not associated with the joke language Perl, please visit www.perl.org» aw yeah, right there in the topic. 05:03:28 A sailor 05:03:35 ais523\unfoog: oh, i didn't know that... i wanted the paste though. 05:03:41 doesthiswork: yeah, but in an old version of Perl wher the modern style didn't exist 05:04:03 yes 05:04:05 They say that perl always existed. 05:04:15 You can see signs of this in cave paintings 05:04:35 -!- Sprocklem has quit (Ping timeout: 245 seconds). 05:04:44 and the perl students did make few errors, it just wasn't enough fewer to be significant 05:05:05 hypothesis: computer scientists are even worse at stats than psychologists 05:05:32 apparently, past-me was very enamoured of trying to create an eso derivative of Perl 05:05:37 which sort-of implies I never considered it eso 05:06:12 «2009-01-03.txt:22:14:38: -!- klslvoeoe changed the topic of #esoteric to: you can subtract your mom from my dick because she's old and you're a stupid fuckface! now LEARN C or say perl! stop being esoteric asswads» fascinating 05:06:26 was this like, an actual troll 05:06:45 yes, although not a very good one 05:06:58 bike: all the stats I've seen have generally been fine 05:06:59 our usual response to obvious trolls is countertrolling 05:07:16 I know once I kicked one like ten times in a row, no ban, out of morbid curiosity as to when they'd give up and stop bothering 05:07:43 wow, this joke language perl thing was in the topic for years 05:08:24 the channel was slow to change topic back then 05:08:40 when I first joined, it'd be very rare for the "devlopment and deployment" bit to not be in the topic 05:08:47 even optbot made sure to leave that bit in 05:08:50 but nowadays you hardly ever see it 05:08:58 «% w3m -dump http://tunes.org/~nef/logs/esoteric/ | awk '{print $6}' | tail -n +22 | perl -ne 's/K/* 1024/; print int(eval($_) + .5), "\n"' | squish 140 | sparkline» elliott what the hell 05:09:22 doesthiswork: it reproduces at all resolutions. but it halts successfully on the small ones. 05:09:47 hmmm 05:09:52 i wonder 05:11:09 hm, this leads to another question i've been wondering about. 05:11:10 okay it seems to be a function of canvas size. it happens all the time at 101x101, but never for 51x51 05:12:18 `pastelog [Mm]ath[- _]?[Nn]erd 05:12:29 http://codu.org/projects/hackbot/fshg/index.cgi/raw-file/tip/paste/paste.22864 05:13:01 oh, it's all one person, huh. 05:13:05 `pastelog [Mm]ath[- _]?[Nn]erd[^3] 05:13:21 http://codu.org/projects/hackbot/fshg/index.cgi/raw-file/tip/paste/paste.32067 05:13:36 why does that look like a GY!BE song title to me... 05:15:49 okay so...i think i've tracked it down. cool. raising numbers to big powers results in weirdness. 05:15:56 * quintopia ups precision 05:16:13 you're raising numbers to big powers for circle drawing? 05:23:14 yes 05:23:30 you raise numbers to big powers for everythin in SELECT. 05:23:52 you'd think it would have better support then... 05:23:54 i just set the default tape value to very very close to 1 and it solved the problem. 05:24:00 getting beautiful circles now 05:25:35 Bike: well, it would have better support if someone besides me had written the interpreter i guess. i'm counting on mpmath to handle the math, but apparently some of the calculations i need require such immense precision i would have to develop my own algorithms to handle the math if i wanted it to be able to work for any base value. 05:27:28 probably you should switch to a repeated exponent representation 05:28:18 kind of still not sure where huge exponents come up though... you just need to divide 2pi doncha 05:32:16 -!- Darklust has quit (Ping timeout: 246 seconds). 05:34:43 perhaps you should go read the spec 05:35:42 what is this repeated exponent representation 05:37:36 well, i saw it said double precision floats, but that's boring 05:39:45 as for representation, http://en.wikipedia.org/wiki/Symmetric_level-index_arithmetic 05:41:13 i'm not using double-precision. i'm using "select your own precision". i've been running my test code at p=100 decimal digits 05:41:31 ais523\unfoog: although that joke is a bad joke, there are other real criticizms of perl (not a perl expert), such as the fact that all lists are automatically flattened. 05:44:20 but i mean, all you need to do for a circle is exp(0*2pi/20), exp(1*2pi/20), etc, right 05:44:25 CADD: the correct criticism there should be "lists and references to lists are distinct firstish-class values" 05:45:02 ais523\unfoog: lol, fair enough. i dont know enough about perl to give a proper criticism 05:45:08 Perl is saner if you only ever create lists as a result of dereferencing a reference to a list (you might want to make an exception for function arguments, but in a sanely designed Perl you wouldn't need one) 05:45:40 recent Perls have been moving towards allowing you to write programs in that style, but it's still experimental 05:45:52 -!- Darklust has joined. 05:46:00 anyway, the issue is not that lists flatten, because a Perl list is not what most languages call a list, and it's sensible that it flattens 05:46:05 the problem is that they're pervasive at all 05:46:38 ais523\unfoog: lists you mean? 05:46:56 yes 05:47:10 ais523\unfoog: im not sure what you mean by that 05:47:26 "In fact, if you can avoid the whole procedure (which will be called relup from now on) and do simple rolling upgrades by restarting VMs and booting new applications, I would recommend you do so. Relups should be one of these 'do or die' tools. Something you use when you have few more choices." 05:47:47 But I want to use Erlang [VM] hotswapping for development, so I don't have to restart the development instance when I make a code change 05:47:49 :( 05:48:07 Bike: that's exactly what i'm doing. but then i have to scale it to the canvas size. and multiplication in SELECT. uses the rule x*y=logK((k^x)^y). so for a radius 50, i have to raise k^50 to one of those numbers you wrote above. it gets even worse if you have to add. 05:48:09 CADD: list variables exist, for instance 05:48:17 and list contexts 05:48:34 both are useful, and widely used; neither would be useful nor widely used if Perl didn't insist on trying to use non-reference lists for so much 05:48:52 quintopia: sounds like representing exponentiations explicitly would help a lot, then... 05:50:35 ais523\unfoog: well, no language is perfect. an i guess here we revel in that fact.. :) 05:51:58 Bike: yes. SLI looks nice. too bad there are no python libraries that have it implemented for complex numbers and such. 05:53:28 quintopia: i think you could do it yourself? i mean, just basically have a nuber class that's a fractional float plus an integer. probably. 05:53:47 but SELECT, that lets you use different bases, doesn't it 05:53:54 i could try. and lose even more of my life to coding 05:54:22 i feel i should point out you're drawing a circle in a brainfuck derivative based on exponentation 05:54:52 i ahve succeeded at that 05:55:06 i can move on to other more pressing things in my life 05:55:17 maybe i'll come back and write mandelbrot sometime 06:12:37 -!- oklopol has quit. 06:29:33 -!- trout has quit (Remote host closed the connection). 06:29:48 zomg chu spaces: https://en.wikipedia.org/wiki/Boolean_algebras_canonically_defined#Truth_tables 06:39:50 choo choo 06:44:17 -!- `^_^v has joined. 06:46:40 -!- nycs has quit (Ping timeout: 245 seconds). 06:54:29 -!- nisstyre has quit (Ping timeout: 248 seconds). 07:01:48 -!- nisstyre has joined. 07:33:47 -!- carado has joined. 07:36:45 -!- ter2 has quit (Ping timeout: 272 seconds). 07:42:41 -!- ter2 has joined. 07:49:29 http://data.aalto.fi/ <- so modern! (I didn't know we had a thing like that.) 07:58:48 -!- ais523\unfoog has quit. 08:00:59 -!- doesthiswork has quit (Quit: Leaving.). 08:02:11 -!- CADD has quit (Quit: leaving). 08:07:07 -!- nisstyre has quit (Disconnected by services). 08:07:19 -!- nisstyre has joined. 08:11:36 -!- carado has quit (Ping timeout: 252 seconds). 08:26:05 Vihart: How I Feel About Logarithms http://youtu.be/N-7tcTIrers 08:32:51 Hey, algorithm is an anagram of logarithm. 08:35:53 > and $ zipWith (==) (sort "algorithm") (sort "logarithm") -- just checking 08:35:54 True 08:36:19 > sort "algorithm" == sort "logarithm" -- a.k.a. 08:36:21 True 08:39:17 > on (==) sort "algorithm" "logarithm" -- DRY 08:39:18 True 08:44:17 -!- ter2 has quit (Ping timeout: 240 seconds). 09:13:04 -!- FreeFull has quit. 09:50:13 -!- oerjan has joined. 10:10:22 -!- carado has joined. 10:36:34 !perl print "hm..." 10:36:36 hm... 10:36:51 wow, that command actually works 10:37:00 !c printf "hi!\n"; 10:37:03 Does not compile. 10:37:03 oops 10:37:10 !c printf("hi!\n"); 10:37:12 hi! 10:37:25 !slashes Does this work now? 10:37:26 Does this work now? 10:37:34 Gregor++ 10:38:47 So, "Gregos"? 10:38:59 MAYBE 10:48:04 as for representation, http://en.wikipedia.org/wiki/Symmetric_level-index_arithmetic <-- neat 11:04:18 -!- MindlessDrone has joined. 11:25:36 -!- Taneb has joined. 11:51:22 -!- yorick has joined. 12:10:43 -!- S1 has joined. 12:12:20 What happened to the EsoAPI? All I was able to find was the link from the EsoAPI article on esolang 12:12:41 which was http://esolangs.org/wiki/EsoAPI and http://kidsquid.99k.org/programs/esoapi/esoapi.html 12:22:11 Possibly the same thing that happens to all such things, like PESOIX and PSOX. (A quiet death, that is.) 12:22:52 Doesn't someone still have the files? 12:33:36 -!- oerjan has quit (Quit: leaving). 12:37:28 -!- Sgeo has quit (Read error: Connection reset by peer). 12:52:30 -!- nisstyre has quit (Ping timeout: 245 seconds). 13:04:14 -!- nisstyre has joined. 13:04:36 -!- boily has joined. 13:04:43 -!- metasepia has joined. 13:15:22 hm 13:15:28 EsoAPI 13:15:34 EsoCOM! 13:15:45 good esoteric morning! 13:15:59 bonjour 13:16:45 Comment ca va? 13:17:16 ça va bien. on voit que l'hiver arrive à grand pas. pas trop froid de ton bord? 13:21:13 il fait froid :) 13:22:17 si je ne m'abuse, tu es Suisse? 13:22:25 oui. 13:22:48 pas du neige 13:23:02 maintenante. 13:24:37 -!- S1 has left. 13:24:44 je suppose que il'ya du neige en canada? 13:25:29 il neige déjà à Québec, mais pas encore à Montréal. 13:25:45 ah. ok 13:26:57 il'ya du neige sur les montagnes 13:27:10 je suis pas surpris :p 13:27:25 on peut déjà faire du ski 13:27:45 pas de surprise :) 13:28:09 je suis nul en ski, et encore pire en planche à neige. 13:29:47 :) 13:34:40 -!- nooodl has joined. 13:47:56 -!- john_metcalf has joined. 13:48:29 * john_metcalf is watching a man fix the boiler 13:48:50 "Sounds hot." 13:49:13 So happy I didn't attempt to do it myself 13:50:27 -!- Taneb has quit (Quit: Leaving). 13:51:56 Is anyone here at Cambridge uni? 13:52:04 -!- nisstyre has quit (Ping timeout: 264 seconds). 13:52:46 Cambridge sounds fun... 13:53:51 Cambridge has a computer history museum 13:54:17 ;__; 13:54:39 I think someone was? 13:55:43 Phantom_Hoover, perhaps. 13:56:18 Or maybe he just mentioned the place as a hypothetical, I didn't really keep track. 13:57:38 Some grepping seems to suggest he went to some other place. Oh well. 13:59:41 Cambridge is a confusing name. I never know which side of the Great Puddle it is. 14:00:13 Both, just like every other place. :p 14:03:04 London and Paris are easy, they're both in Ontario! 14:04:15 At least there seems to be no university in Cambridge, MA, unlike the case with, say, the University of Birmingham and Birmingham City University in UK, and the Birmingham High School in California, and two different universities in Birmingham, Alabama. 14:06:45 I don't think Finland has many places named after other places, though there's probably a couple. There's an "Egyptinkorpi" ("desert/forest/backwoods of Egypt") in the middle of nowhere in Lieksa, at least. 14:10:35 -!- nooodl has quit (Ping timeout: 272 seconds). 14:24:02 fizzie: Arabia? 14:24:28 Or Arabianranta 14:27:13 -!- FreeFull has joined. 14:28:05 Mhm. 14:28:13 Also "Tukholmankatu", in case streets count. 14:30:56 where is Tukholmankatu? 14:31:34 In Helsinki. ("Tukholma" is the Finnish name of Stockholm.) 14:31:55 obviously. 14:34:26 Apparently there's a large number of "Amerikka"s all around Finland too. 14:36:07 And a Jerusalemi, Finland somewhere in the general neighborhood of Joensuu. 14:36:29 (So I guess we have these things too.) 14:37:07 next thing you're going to tell me there's a Finland in Finland. 14:41:21 There's Ditch of Finland, Espoo, Finland. ("Suomenoja".) 14:44:10 “I knew it.” 14:46:05 -!- mrhmouse has joined. 14:46:21 mrhellouse. 14:46:35 belloily 14:47:05 -!- ter2 has joined. 14:57:02 -!- Phantom_Hoover has joined. 14:57:51 Phantom_Hoover: did you Cambridge? 14:57:58 what? 14:58:00 no 14:59:06 I was just confuse. 15:05:42 i decided not to go to cambridge after i found out timwi did maths at the same college i applied to and, well... 15:05:45 `quote 575 15:05:47 575) oh god oh god what if I become attracted to birds 15:06:41 * boily is suddenly perplexified 15:07:13 the joke is that timwi is attracted to birds 15:08:09 http://www.timwi.com/ ? 15:08:37 no, http://www.lionking.org/~timwi/progs.htm 15:09:40 http://www.lionking.org/~timwi/eagles.htm would be more appropriate, probably 15:09:45 this is not the work of a healthy mind! 15:09:55 I'd be dubious of a consulting company known to be attracted to birds. 15:10:11 * boily replaces his perplexification with terror 15:11:18 -!- doesthiswork has joined. 15:12:15 helloesthiswork. 15:21:38 hi 15:24:23 -!- AnotherTest has joined. 15:25:48 Anothellost. 15:27:19 Definitely read that as "An Othello soundtrack" 15:27:47 is that the name of your new esoteric language? 15:30:00 -!- ter2 has quit (Ping timeout: 245 seconds). 15:31:02 meanwhile, another brainfuck derivative. yéééé....... 15:31:33 ,[-+] i think 15:31:35 i cant remember 15:31:57 Brainfuck isnt really interesting to me 15:32:20 I want to be able to do more with a language if i want 15:33:13 create a self-modifying Aubergine program? 15:35:12 It's hard to define more 15:35:40 write bindings for gtk, write networked application etc 15:37:01 is there an esolang out there that has a networking library? 15:37:04 -!- conehead has joined. 15:37:11 (no, Ursala doesn't count.) 15:37:19 I think any esolang that can call C libraries counts? 15:46:11 -!- Phantom_Hoover has quit (Ping timeout: 252 seconds). 15:49:56 -!- ter2 has joined. 15:56:58 -!- ter2 has quit (Read error: Connection reset by peer). 15:57:14 -!- ter2 has joined. 16:01:32 -!- Phantom_Hoover has joined. 16:03:24 -!- nisstyre has joined. 16:04:18 -!- ter2 has quit (Ping timeout: 245 seconds). 16:06:20 -!- impomatic has quit (Quit: impomatic). 16:14:17 -!- nooodl has joined. 16:14:50 -!- ter2 has joined. 16:15:04 Boiler repaired after four hours. Might be expensive :-( 16:21:58 -!- nisstyre has quit (Quit: Leaving). 17:06:46 fungot: Do you know any esolangs that could do networking? 17:06:47 fizzie: the point of 17:06:54 fungot: ...what? 17:06:54 fizzie: http://community.schemewiki.org/ cgi-bin/ viewcvs/ mit-scheme/ snapshot.pkg/ 20060906/ 17:07:41 fungot: Your link is broken. Anyway! I'm sure you've heard of at least one language in which it'd be possible to write an IRC client, wink wink. 17:07:41 fizzie: do you happen to get something fnord, but it's not 17:07:51 Not getting the hint, I see. 17:10:33 -!- ter2 has quit (Ping timeout: 265 seconds). 17:15:50 -!- Phantom_Hoover has quit (Ping timeout: 245 seconds). 17:19:57 -!- Phantom_Hoover has joined. 17:20:07 fungot: I got some moldy mushrooms, can I eat them? 17:20:07 olsner: that's a lot of lisp companies barely cover the cost of speed, that's why i mentioned ' pretty complete.' 17:20:45 fungot: No, no, mushrooms, not speed. 17:20:45 fizzie: ah i had a discrete math lecturer who would lecture painfully and fnord, 17:21:08 I think that's common among discrete math lecturers. 17:21:37 My discrete math lecturer would always swing this yardstick about while teaching 17:21:57 One day he broke it in two by mistake and, instead of fixing it, hid the pieces in the ceiling 17:22:16 Turns out it actually belonged to the professor who lectured in the class before his 17:25:31 i remember nothing about my discrete maths lecturer except that he was a total dickhead about the lecture notes 17:28:28 -!- Taneb has joined. 17:29:03 Phantom_Hoover: You should have taken mine. I once got credit on a bonus question that involved finding a number of items in a dark room (I don't remember the specifics) for the answer "It is pitch black. I am likely to be eaten by a grue" 17:30:42 -!- Sprocklem has joined. 17:35:58 -!- augur_ has quit (Remote host closed the connection). 17:36:32 -!- augur has joined. 17:39:14 helloily 17:39:20 do you have a package yet 17:40:37 back from lunch, and I don't have a package yet. probably very soon. 17:40:37 -!- augur has quit (Ping timeout: 246 seconds). 17:40:53 Shady dealings! 17:41:08 shady and delicious dealings. 17:41:20 fungot: are your mushrooms tasty? 17:41:20 boily: the results of compilation up with the default background so it'll be the killer app for scheme 17:42:17 fungot: A killer app for Scheme? Are you talking about a Starcraft clone? 17:42:18 fizzie: improvisational language? you're not fnord with a monad. 17:42:23 boily: those were olsner's mushrooms, and they are moldy 17:42:30 `learn fizzie is not fnord with a monad. 17:42:36 I knew that. 17:43:29 olsner: mushrooms can get moldy? I didn't know that. 17:43:36 is the mold super-death-mold because it can grow on other funguses? 17:43:59 fizzie: what shall I do for the PDF? should I remove the Minecraft invention snippet, or keep it and append the not fnord? 17:44:05 or is it just the mushrooms that kept growing for a bit? or is it just plain mold... 17:44:25 boily: I think you should follow the high-level policy you surely must have formulated before now. 17:45:07 unless boily is mechanism, not policy 17:45:14 -!- darklust_ has joined. 17:45:31 fizzie: rule Nº 1: do whatever it is that feels right, and or keeps eldritch abominations at bay. 17:45:44 olsner: I am not mechanism, I am at Canada. 17:48:15 "You may still request that your article be published with unrestricted public access, as [REDACTED] is a hybrid publication allowing either traditional publication or Open Access publication. The author publication charge for making your paper Open Access is a discounted US$1750.00, --" I'm not going to start paying that kind of money! 17:48:39 (As far as I know, we don't have a university-wide open access policy guideline thing that'd say they'd pay it.) 17:49:04 -!- Darklust has quit (Ping timeout: 264 seconds). 17:49:14 publish somewhere else, obviously, you can't avoid being evil if you play with those guys 17:51:39 -!- conehead has quit (Quit: Computer has gone to sleep.). 17:56:44 -!- doesthiswork has quit (Read error: Connection reset by peer). 18:01:00 publish on arxiv. i hear you can win millennium prizes that way. 18:06:22 -!- tertu has joined. 18:07:30 -!- Bike has quit (Ping timeout: 245 seconds). 18:14:47 -!- Bike has joined. 18:16:17 -!- sebbu has quit (Ping timeout: 265 seconds). 18:17:53 -!- Bike has quit (Client Quit). 18:18:06 -!- Bike has joined. 18:18:30 the journal might not allow preprints. 18:21:14 -!- variable has joined. 18:22:47 fungot: are your words preprinted? 18:22:47 boily: if i were to try to get ppl to think and think and think and think and think and think. 18:23:32 <3 fungot 18:23:32 quintopia: int fnord c) 18:24:59 -!- tertu has quit (Ping timeout: 265 seconds). 18:27:47 That is a lot of thinking 18:29:28 fungot is the great thinker 18:29:28 olsner: no idea what half of this it keeps a log cabin 18:29:49 fungot: think harder! 18:29:49 FireFly: i signed lotsa those 18:29:55 fungot: log cabins are good. 18:29:55 boily: let's assume local variables are kept in the interpreter, already written many times i set it 18:30:19 fungot: a sane assumption 18:30:20 FireFly: do you prefer books or tv? huh....intriguing have you ever been to. personally i'm not a common lisper? just kidding. 18:30:37 oh, you do common lisp eh 18:30:45 just kidding 18:30:54 fungot: books are better, im[REDACTED]o. 18:30:55 boily: but the word has had the fnord setup? :) " migrate my process thence!" :) 18:31:21 fungot: a great plot twist, the “fnord setup”. I never see it coming. 18:31:21 boily: ( ( lambda ( x y) ( define ( min. xs)) ( lambda 18:31:29 fungot is asking the important questions here 18:31:29 FireFly: found a metallic coat-hanger actually. category pattern* restaurant/pattern template i like to think that performance is a great example 18:31:37 The [REDACTED] journal does allow preprints, for the record. 18:32:11 the restaurant pattern? 18:32:42 hey, british people, can someone tell me what the fuck a 'reader' is 18:33:53 kmc: https://twitter.com/search?q=%23LERNorigin&src=hash&f=realtime neat talk on abiogenesis going on (random sorry) 18:34:38 -!- augur has joined. 18:35:42 Bike: reader is a pretty common word, what's the context? 18:35:49 like in a university 18:36:26 it can mean textbook 18:36:38 like 'i am a reader at x university' 18:37:11 "4. reviewer, referee, reader -- (someone who reads manuscripts and judges their suitability for publication)"? 18:37:30 hm... it always seems like a permanent position though 18:37:36 "7. lector, lecturer, reader -- (a public lecturer at certain universities)"? 18:38:01 (The latter sounds more likely.) 18:38:01 maybe 18:38:16 like this lane guy is "Reader in Evolutionary Biochemistry, Department of Genetics, Evolution and Environment, University College London" 18:38:29 -!- Sprocklem has quit (Ping timeout: 272 seconds). 18:38:33 -!- other1 has joined. 18:38:37 "4. (chiefly UK) A university lecturer below a professor." (Wiktionary.) 18:38:57 en:reader, fr:sous-fifre. 18:39:33 "The title of reader in the United Kingdom and some universities in the Commonwealth nations, for example Australia and New Zealand, denotes an appointment for a senior academic with a distinguished international reputation in research or scholarship. It is an academic rank above senior lecturer (or principal lecturer in the new universities), recognising a distinguished record of original ... 18:39:39 ... research at professorial level. In the British ranking, for some universities a reader could be seen as a professor without a chair, similar to the distinction between professor extraordinarius and professor ordinarius at some European universities, professor and chaired professor in Hong Kong and professor B and chaired professor in Ireland. Both readers and professors in the UK would ... 18:39:45 ... correspond to professors in the US." 18:39:49 (note that «sous-fifre» is usually pejorative) 18:39:49 I wonder if this is slightly the same as the Finnish use of the title of docent. 18:39:53 how confusing. 18:40:07 Oh, "An incompatibility of ranking systems between different (English-speaking) countries makes the position of reader difficult to place outside the context of the United Kingdom. A similar title used in some countries, for instance in Sweden, is docent, which is officially translated in English as reader." Guess so. 18:40:40 My immediate supervisor got certified as a docent the other day. 18:42:23 -!- sebbu has joined. 18:43:25 being an academic is suffering. 18:43:29 -!- sebbu has quit (Changing host). 18:43:29 -!- sebbu has joined. 18:46:25 I thought it was insufferable, instead. 18:46:33 Bike is meduka meguca. 18:56:02 -!- other1 has quit. 19:00:28 -!- Bike has quit (Ping timeout: 264 seconds). 19:05:35 -!- tertu has joined. 19:05:42 -!- Bike has joined. 19:28:10 -!- muskrat has joined. 19:28:16 -!- muskrat has left. 19:31:01 -!- oerjan has joined. 19:34:43 London and Paris are easy, they're both in Ontario! <-- rubbish, everyone knows paris is in texas 19:37:46 oerjan: Yukon's Paris is better than Texas's paris, I say. 19:37:55 (also, helloerjan.) 19:38:31 belloily: what's this namello business you're tello? 19:38:49 mrhmouse: I'm perpetuating a fine chännel tradition. 19:39:39 (hm. there's also a Paris, and a London, in Kiribati.) 19:40:02 shockingly, wikipedia lists no other nonfictional trondheims. 19:42:17 https://en.wikipedia.org/wiki/Quebec_Platelet_Disorder ← we have a blood disease! 19:43:25 mrhellouse 19:44:43 `? mrhmouse 19:44:45 mrhmouse? ¯\(°_o)/¯ 19:44:46 | 19:44:46 o/`¯º 19:44:58 “Let It Be” in Minor Key http://youtu.be/SeIyX4KXgpE 19:44:59 oh, the myndzi-bot is back! 19:45:36 speaking of weird arrangements, who suggested g-major videos to me? 19:46:14 hm myndzi hasn't been gone, although he _did_ make his script ignore HackEgo ... 19:46:32 (meanwhile, http://youtu.be/cKce8d_ffS4) 19:46:36 which has obviously broken again. 19:47:31 i don't think we have enough information on mrhmouse to add an entry yet. 19:49:26 http://blogs.discovermagazine.com/notrocketscience/2012/04/19/synthetic-xna-molecules-can-evolve-and-store-genetic-information-just-like-dna/ how are vhs/betamax analogies so common 19:49:37 back in the 80s (it was the 80s right) were all ads about betamax and vhs or something 19:51:03 -!- tertu has quit (Ping timeout: 272 seconds). 19:51:19 * oerjan clicked on that link in a vain hope to discover X was for "xylitol". 19:51:42 i mean, it's a sugar replacement, right? 19:52:03 you'll just have to survive with cyclohexane. 19:52:57 oerjan: http://www.ncbi.nlm.nih.gov/pubmed/20017539 good news! 19:53:04 hm xylose exists, so xylonucleic acid _should_ be reasonable 19:54:35 * boily takes notes for his next Paranoia campaign... “Give a player a bottle of xylylylytic acid” 19:55:11 it's sugar, dude. 19:55:58 yup. 19:56:12 but they don't have the clearance to know that :D 19:56:26 oh, right, heh. 19:56:39 google claims xylylylytic is not a word hth 19:56:58 describe it as an "extremely virulent bioinformation precursor" 20:02:04 At least there seems to be no university in Cambridge, MA, [...] <-- you should ban yourself for trolling hth 20:03:03 alternately, proofread your lines. 20:03:54 also, stop being idle. 20:04:43 -!- Bike has quit (Ping timeout: 245 seconds). 20:05:17 * boily tapes an electronic eggtimer onto fizzie 20:05:25 oerjan: how about i stop being idle instead 20:05:41 but you cannot ban fizzie. 20:08:44 i could if you +oed me 20:08:58 (but i probably wouldn't) 20:11:47 * boily misses the days where he had voice. those were nice days. 20:11:50 no, http://www.lionking.org/~timwi/progs.htm <-- how has timwi avoided being sued by hasbro and/or mattel 20:12:10 shachaf: s/w/sh/ 20:12:13 they're too creeped out 20:12:33 oerjan: i'm not a moralist; i can't make "should" statements 20:13:09 -!- ChanServ has set channel mode: +v boily. 20:14:06 shachaf: marvelous 20:16:48 why does Gregor not have voice 20:16:51 `thanks anonymous 20:16:51 fix this imho 20:16:52 Thanks, anonymous. Thanonymous. 20:17:25 `run cat "$(which thanks)" 20:17:26 ​#!/usr/bin/perl \ $_ = (join " ", @ARGV) || `words`; s/^\s+|\s+$//g; print "Thanks, $_. "; if (/[aeiouyAEIOUY]/) { s/^[^aeiouyAEIOUY]*/Th/; } else { s/^./T/; } print "$_."; 20:19:05 Phantom_Hoover: it's part of our anti-idling campaign hth 20:19:45 antiïdling 20:21:30 `thanks 20:21:32 haha, guess whose video's on the front page of /r/math: http://www.youtube.com/watch?v=xHvAqDuWG2M 20:21:35 Thanks, palatalized. Thalatalized. 20:22:51 wat 20:23:00 `thanks 20:23:04 Thanks, tjosentme. Thosentme. 20:23:38 oh right 20:24:03 HackEgo: who is this tjo you're speaking for 20:24:36 fungot: can you coerce HackEgo into speaking? 20:24:36 boily: is is occasionally identity, and weak tables. 20:24:45 HackEgo: see, your tables are weak! 20:26:30 Phantom_Hoover: why doesn't he have a french accent 20:26:37 he... does? 20:27:15 well then it's too slight for me to hear 20:28:19 fungot: enlighten me 20:28:19 FireFly: none at all. :( i can't even be printed!! for dessert, i'll have to write 20:28:46 Hm, seems... philosophical 20:28:50 -!- impomatic has joined. 20:32:06 phantom_hoover: Who is he? 20:32:17 he made unlambda 20:32:20 perhaps other things also 20:32:20 ok 20:34:33 i don't think he's done esolangs for a decade. 20:34:51 by which i mean he never responded to the programs i sent him, the bastard. 20:39:55 -!- Bike has joined. 20:40:01 `help 20:40:01 Runs arbitrary code in GNU/Linux. Type "`", or "`run " for full shell commands. "`fetch " downloads files. Files saved to $PWD are persistent, and $PWD/bin is in $PATH. $PWD is a mercurial repository, "`revert " can be used to revert to a revision. See http://codu.org/projects/hackbot/fshg/ 20:40:36 `` 20:40:38 No output. 20:40:45 ...??? 20:40:49 ``run run 20:40:50 ​/home/hackbot/hackbot.hg/multibot_cmds/lib/limits: line 5: exec: `run: not found 20:40:56 `` run run 20:40:57 bash: run: command not found 20:41:05 `` fortune 20:41:07 You just know when a relationship is about to end. My girlfriend called me \ at work and asked me how you change a lightbulb in the bathroom. "It's very \ simple," I said. "You start by filling up the bathtub with water..." 20:41:33 why are all the fortunes creepy 20:41:37 ~fortune 20:41:37 I'm a bisexual; I get it maybe twice a year. 20:41:38 -- Rodney Dangerfield 20:42:17 they're secretly all misfortunes 20:43:33 -!- conehead has joined. 20:44:37 `fortune 20:44:39 See store for details. 20:44:45 kay. 20:45:02 ^fortune 20:45:26 does ruddy fortunes? 20:45:26 OH EM GEEEEEE 20:45:38 guess so 20:45:43 ruddy's certainly excited about fortune 20:45:43 good point. Just not the same one 20:45:43 go figure. 20:45:54 btw, who is polytone? 20:46:07 e used to be mono 20:46:15 oooooh. subtle. 20:46:59 polytone: i always toldja that the antiphony was gonna be outdated, but nooooo, you didn't even want to TRY those newfangled fortepianos 20:49:03 `which ` 20:49:05 ​/hackenv/bin/` 20:49:20 `cat bin/` 20:49:22 exec bash -c "$1" 20:49:39 `` ` ` `````` ``` 20:49:40 bash: -c: line 0: unexpected EOF while looking for matching ``' \ bash: -c: line 1: syntax error: unexpected end of file 20:50:00 `` `\`` 20:50:02 bash: command substitution: line 0: unexpected EOF while looking for matching ``' \ bash: command substitution: line 1: syntax error: unexpected end of file 20:50:08 `!! 20:50:10 ​/home/hackbot/hackbot.hg/multibot_cmds/lib/limits: line 5: exec: !!: not found 20:50:20 `run `\`` 20:50:22 bash: command substitution: line 0: unexpected EOF while looking for matching ``' \ bash: command substitution: line 1: syntax error: unexpected end of file 20:50:26 Oh well 20:50:46 `history | tail -n 1 20:50:48 ​/home/hackbot/hackbot.hg/multibot_cmds/lib/limits: line 5: exec: history: not found 20:50:52 `́ 20:50:53 ​/home/hackbot/hackbot.hg/multibot_cmds/lib/limits: line 5: exec: ́: not found 20:52:55 `` '`' 'echo hi' 20:52:57 hi 20:53:03 What's a good assembler for windows? 20:53:46 generally you want windows made in one piece, they're rather hard to assemble afterwards. 20:54:03 Slereah_: tasm, iirc. 20:54:22 s/t/y/ 20:55:32 yasm? 20:55:49 Ah, found it 20:55:50 thx 20:56:36 -!- MindlessDrone has quit (Quit: MindlessDrone). 20:57:09 Fuck 20:57:16 When I launch it it closes immediatly 20:57:21 I had the same thing with NASM 20:57:57 what commandline did you call it with? 20:58:21 You know 20:58:25 DOUBLE CLICK 20:59:19 oerjan: your sass has been noted and approved 21:00:20 oerjan : I'm pretty sure if I had the assembly program of windows, I'd be a rich man 21:00:23 I could SELL IT 21:00:37 mrhmouse: wat 21:00:41 Slereah_: try running it in a console and checking for error messages. maybe it segfaulted? is that a thing in Windows-land? 21:01:09 Let's see 21:01:10 Man 21:01:18 I haven't opened the windows command thing in a while 21:01:25 or it just printed help and exited or something 21:01:40 Aaaah dir how I missed you 21:01:46 Nowadays with the classes it's all ls 21:02:54 Windows commandline makes me feel like I'm instructing a grade school student to do calculus over the phone in a language they don't understand 21:03:04 * boily covers Slereah_ with a robe made of stitched 5¼" floppies, all with a glittering different DOS version 21:03:26 fungot, where can I get such a robe as Slereah_? 21:03:26 mrhmouse: it's easy to parse 21:03:35 To launch nasm.exe, it's just nasm, right? 21:03:43 Oh wait 21:03:44 -!- FreeFull has quit (Quit: Rebooting). 21:03:47 Slereah_: Depends. Is it in your %PATH%? 21:03:49 I need an input file I guess 21:03:56 That's why it's bitching 21:03:58 Hm 21:04:05 Let's whip up some ASM I guess 21:04:28 mov ax,1 21:04:31 BEST PROGRAM 21:05:23 very program. much efficient. 21:05:30 -!- conehead has quit (Ping timeout: 246 seconds). 21:06:00 Such register 21:06:02 wow 21:06:11 Well it did a thing at least 21:06:21 Now let's try a thing that will display a thing 21:08:02 are you going to use a library or syscalls 21:08:07 can you even use syscalls nowadays. 21:08:17 (for printing. on windows.) 21:08:37 I tried using thems interrupts 21:08:40 Didn't work 21:08:52 is your guide from the dos era 21:09:00 Not sure if I'm using the wrong syntax for the assembler or if I just fucked up 21:09:17 http://w3.ufsm.br/rmbranco/cefet_files/Apostila/8086%20Assembly.pdf < dunno 21:09:18 depends on the exact nature of 'didn't work' 21:09:23 Well 21:09:28 It didn't display a thang 21:09:34 but it assembled? 21:09:48 nasm should complain if you give it something syntactically invalid. 21:09:48 Oh wait 21:09:57 That's right 21:10:01 It just assemble it 21:10:04 It doesn't run it 21:10:10 indeed it does not. 21:10:27 let's see 21:10:43 -!- FreeFull has joined. 21:11:15 Hm, how do I read it now 21:11:24 It's just test.asm -> test 21:11:34 read? that's gonna be a binary. 21:11:49 I tried inputting "test", no work 21:11:57 how do you normally run programs on windows? 21:11:58 I tried adding a .exe file extension, it bitched 21:12:17 Well usually I just click 'em 21:12:32 If I have to command line things, I just input the exe name in the directory 21:12:38 Slereah_: usually, you only get object code. you need to link that afterwards to make a real executable. 21:12:39 But here it doesn't seem to work 21:12:46 Ah 21:12:55 I guess I'd better read the nasm docv 21:12:58 oh, i forgot linking. dumb. 21:13:15 Dang, 245 pages 21:13:18 that's not part of nasm. have you got gcc or something? usually they can call the linker for you 21:13:20 Maybe this week end 21:13:26 Yeah 21:13:27 Let's see 21:13:47 Oh wait, no, it's dev c++ 21:13:59 I _think_ you can link "test.o" by just calling "gcc test.o". 21:14:12 well, mingw oughta be able to do it too. 21:14:21 I should reinstall linux 21:14:21 Yeah, it would be pretty much the same 21:14:32 Now that I got classes on it prolly easier to deal with 21:15:38 ruddy can link as well. ruddy is the best at linking. 21:15:39 good point. Just not the same one 21:16:16 Hm 21:16:26 -!- tertu has joined. 21:16:27 Apparently the NASM syntax is a bit more complicated than I thought 21:17:08 The NASM manual isn't very clear on how to use macros :-( 21:17:25 Also what format should I pick 21:17:26 Hm 21:17:33 They use ELF in the example, but I'm not sure 21:17:38 On windows use PE. 21:17:46 How *do* you figure out what kind of file a file is without relying on file extensions, in windows? 21:17:56 I'm too used to just `file`ing stuff I don't know what it is 21:18:06 "ASCII text" 21:18:09 FireFly : You don't! 21:18:13 FireFly: I don't think you can.. 21:18:18 >< 21:18:22 Well at least not from the GUI 21:18:24 +mouth 21:18:38 Usually what I do is to just open it with a variety of programs 21:18:46 Usually notepad is a pretty good int for the content 21:18:58 Slereah_: ELF (Executable and Linking Format) is the format on unixy machines. macs use either that or mach-o, i forget. windows uses PE (Portable Executable). 21:19:06 file? format? fuck it 21:19:08 Okay thanks. 21:22:41 I just wanted to write some assembly man :( 21:22:53 -!- tertu has quit (Ping timeout: 272 seconds). 21:23:03 Bike: it's Format, you were right the first time 21:23:10 I'm not doing assembly to deal with shells and linking! 21:23:17 Assembly man, assembly man, does whatever assembly can. 21:23:35 fizzie: so, everything, but in no reasonable time at all? 21:24:01 Slereah_: on the contrary, understanding linking is an important advantage of understanding assembly-level mechanisms. 21:24:04 Slereah_: any reason you chose x86 first? IIRC MIPS assembly is supposedly easier to jump into. disclaimer: I haven't actually used it 21:24:15 -!- tertu has joined. 21:24:20 Slereah_: some assembly required. it's even spelled out in the name! 21:24:22 probably because Slereah_'s computer is x86 21:24:27 which is a pretty good reason. 21:24:40 -!- Slereah has joined. 21:24:41 I'll just shoot electrons at my CPU 21:24:44 was I saying 21:24:53 Did you miss something? Check the logs? 21:24:56 @uname Slereah 21:24:56 Unknown command, try @list 21:25:02 meh. 21:25:04 [22:23:13] fizzie: so, everything, but in no reasonable time at all? 21:25:04 [22:23:38] I'll just shoot electrons at my CPU 21:25:04 [22:23:57] * Disconnected 21:25:10 yeah, you missed some things. 21:25:14 anyway mars is pretty good for mips http://courses.missouristate.edu/kenvollmar/mars/ 21:25:24 does windows have a uname? 21:25:44 Bike: I'm a SPIM man, myself. 21:25:47 there's a system information dialogue in the control panel, or there was last i used one, anyway 21:26:12 (Though they've wimped it out completely with a QtSpim.) 21:26:24 `uname -a 21:26:25 Linux umlbox 3.7.0-umlbox #1 Wed Feb 13 23:30:40 UTC 2013 x86_64 GNU/Linux 21:26:27 I chose x86 'cause it's my CPU 21:26:33 I guess I could use a virtual machine 21:26:38 fungot: uname -a 21:26:38 shachaf: i have ripped rotty's library out of scheme42, in case somebody is interested, i'll look for you. 21:26:47 "win-r dxdiag" is very slightly like uname, it's what I do. 21:26:57 fungot, please don't look for me. that's frightening. 21:26:57 mrhmouse: haskell would be ( fnord !p) ( p q)). i woke up 21:26:58 aurgh. that stupid dhcp/dns thing scrozzled my perfectly fine hostname. 21:27:20 dxdiag, lol 21:27:27 Man why do I even need a linking for a single file 21:27:31 Bike: But it's handy! 21:27:38 my machine is «njorun», not «aboily-pc»! 21:27:47 Slereah_: because most nontrivial files use library routines. 21:28:04 -!- Slereah_ has quit (Ping timeout: 264 seconds). 21:28:13 Bike: There's a "System Information" block on the first tab, and it's always in path. 21:28:30 I want to use machine code, not libraries ;w; 21:28:47 you'll think differently when you want to use printf. 21:29:23 fungot: imo look for Bike instead 21:29:24 shachaf: swear filtering gone wrong or a deliberate, evil plot. 21:29:29 If I wanted printf I'd use some C 21:29:43 so what do you want to do in assembly? 21:29:51 Eeeeh I dunno 21:29:54 Just try it out 21:29:57 ok, well, there's a problem. 21:30:05 Plus it's the next thing on our curriculum 21:30:12 think about it. you need some kind of function to do something as basic as outputting a number as text. 21:30:13 So probably a good idea to check it out 21:30:14 > printf "%d %.3f" 1 1.0 21:30:16 Could not deduce (Text.Printf.PrintfType t) 21:30:16 arising from the ambiguity c... 21:30:19 > printf "%d %.3f" 1 1.0 :: String 21:30:20 "1 1.000" 21:30:21 Slereah: what architecture is in your curriculum? 21:30:33 Not specified 21:30:40 I assume x86 since we have regular PCs 21:30:49 fungot: the latter, I believe 21:30:49 FireFly: whoa i changed it to 21:30:57 not a good assumption. lots of assembly classes use VM tools. 21:31:02 Maybe 21:31:03 when I covered assembly, we used MIPS 21:31:04 We'll see 21:31:07 not that I paid attention 21:31:08 MIPS at my school too. 21:31:20 We used a kinda weird kinda MIPSy thing 21:31:20 Plus I saw that you can access the PC speaker pretty easily in assembly, which is neat 21:31:25 Also nowadays there's a slim chance the students have ARM-based netbooks, ha ha. 21:31:26 I might try fucking around with that 21:31:44 MIPS is terribly common for assembly courses. 21:31:47 (We did it too.) 21:32:08 MIPS is universal for assembly courses. we did it too. 21:32:19 mips seems popular (it's a fairly pure RISC architecture) 21:32:25 I think assembly starts next week 21:32:30 The unix class ends tomorrow 21:32:33 we used Nios II, which looks very similar to MIPS from what I've seen about MIPS, but for some reason the Wikipedia article for Nios II doesn't even mention MIPS 21:32:36 MIPS is short for "Mips Is Popular in Schools". 21:32:42 heh 21:33:06 `learn MIPS Is Popular In Schools. 21:33:11 I knew that. 21:33:57 fizzie: good one 21:34:05 Slereah: low-level sound in #esoteric? have you seen stackbeat? :) 21:34:08 fizzie: PDFed. 21:34:10 MIPIS Is Popular in Schools 21:34:15 Nope 21:34:22 darn. 21:35:02 rePDFed. 21:35:12 -!- tertu has quit (Read error: Connection reset by peer). 21:35:31 -!- tertu has joined. 21:36:15 -!- boily has quit (Quit: GÀ!). 21:36:18 -!- metasepia has quit (Remote host closed the connection). 21:38:46 `learn MIPS Is Popular in Schools. 21:38:51 I knew that. 21:39:01 can't have that. 21:40:15 I wonder, can you write a binary by hand? 21:40:28 1101010101 21:40:30 Write the program, figure out the opcodes, translate it to ASCII 21:40:39 ascii? what? 21:40:50 Slereah: check it out. maybe you'll get some inspiration for a project in assembly http://esolangs.org/wiki/StackBeat 21:40:52 Well, put it in a txt file 21:41:06 i think you are confused about what assembly is. 21:41:07 Slereah: I _guess_ you could write the opcodes by hand with a hex editor? 21:41:09 Or something 21:41:25 anyway, you're not on DOS, you need pexe format. 21:41:28 I am aware that assembly is to avoid writing opcodes, yes 21:41:41 I am just wondering about that other thing 21:41:49 You could write opcodes -- and executable file headers -- by hand with a good enough text editor, too. (Control characters might be too much for Notepad.) 21:41:50 I wonder how different the Avengers movie would be if Norton had reprised his role as the Hulk 21:42:57 Bike: well you *could* restrict your machine code to the printable-ASCII range... 21:43:04 That would make for some fun programs 21:43:23 yeah, they do that for exploits sometimes 21:43:26 I wonder if that ... 21:43:31 I was about to suggest that 21:43:35 Printable is like 21:43:42 30 to... 200 maybe? 21:43:52 32 to 126? 21:43:54 aka ' ' to '~' 21:44:09 Well 126 is guaranteed printable 21:44:10 ASCII doesn't even have 200 characters :D 21:44:17 Isn't ASCII 10 the newline? That's printable 21:44:27 A lot of them are after 126 for the most part 21:44:33 Especially in le france 21:44:35 mrhmouse: it isn't printable in the sense of what's defined as 'printable ASCII' 21:44:43 'cause éàùè 21:44:46 Oh, sorry, "ASCII printable characters" 21:44:49 http://en.wikipedia.org/wiki/ASCII#ASCII_printable_characters 21:44:56 Slereah: but those aren't in ASCII. 21:45:04 FireFly: Ah, I was just assuming "insertable without control codes" :P 21:45:09 They are in some extension of ASCII, like ISO-8859-1 or whatever 21:45:21 FireFly : Well they are in some versions of ASCII 21:45:44 though I suppose "new line" is a control code.. 21:45:53 They're characters undefined by the ASCII norms 21:46:05 But for the most part they are used if needed 21:47:04 Wait, is ASCII 7 or 8 bits? 21:47:06 I forget 21:47:07 seven. 21:47:10 Hm 21:47:14 What's the 8 bit one? 21:47:19 there are a lot of them. 21:47:24 such as iso whatever. 21:47:33 ISO-8859-1 aka Latin-1 is p. popular. 21:47:43 Well, maybe "was" is a better word. 21:48:15 I see. 21:48:34 yeah, I think utf-8/utf-16 are more popular these days. maybe 32? 21:48:44 Unicode is the only worthy charset nowadays 21:48:57 s/charset/set of charsets/ 21:49:01 * int-e has fond memories of codepage 437 21:49:02 charsetset 21:49:08 Unicode is great, but 21:49:15 There's no font that has all of it 21:49:16 I guess techincally Unicode could be considered a charset, but not an encoding? 21:49:21 Which I find frustrating 21:49:22 I wouldn't be surprised if there was still quite a lot of Windows-1252 stuff around. 21:49:25 -!- Phantom_Hoover has quit (Ping timeout: 248 seconds). 21:49:35 technically? unicode has multiple encodings 21:49:46 Bike: right 21:49:46 I want a font that has all the unicode characters 21:49:57 Slereah: "yes i often find myself stymied when i want to use SNOWMAN WITHOUT SNOW, burmese, and × in the same text" 21:50:12 Bike : 𓃡𓃢𓃣𓃤𓃥𓃦𓃧𓃨𓃩𓃪𓃫 21:50:24 hi 21:50:31 Slereah: what does it matter, if your font renderer just falls back to a font that has the character if your preferred font doesn't? 21:50:33 `unidecode 𓃡𓃢𓃣𓃤𓃥𓃦𓃧𓃨𓃩𓃪𓃫 21:50:35 ​[U+D80C DUNNO] [U+DCE1 DUNNO] [U+D80C DUNNO] [U+DCE2 DUNNO] [U+D80C DUNNO] [U+DCE3 DUNNO] [U+D80C DUNNO] [U+DCE4 DUNNO] [U+D80C DUNNO] [U+DCE5 DUNNO] [U+D80C DUNNO] [U+DCE6 DUNNO] [U+D80C DUNNO] [U+DCE7 DUNNO] [U+D80C DUNNO] [U+DCE8 DUNNO] [U+D80C DUNNO] [U+DCE9 DUNNO] [U+D80C DUNNO] [U+DCEA DUNNO] [U+D80C DUNNO] [U+DCEB DUNNO] 21:50:41 nice. 21:50:48 FireFly : Some characters are displayed by almost no font 21:51:00 Maybe they're very new to the standard? 21:51:01 fizzie: actually I recently came across something in Windows-1251 at work.. but I can't find it now :( 21:51:03 Bike: UCS-2 build of Python strikes again. 21:51:10 Bike : http://codepoints.net/egyptian_hieroglyphs 21:51:15 Why hasn't unicode got a balloon or a candle? 21:51:16 FireFly : 2008 21:51:29 impomatic : They did the emoji recently, I think? 21:51:31 i would have picked coptic, myself. 21:51:34 So there's probably some in it 21:51:51 they've been doing emoji because of pressure to add emoji. 21:51:52 don't forget the essential ♖♘♗♕♔♗♘♖ ♙♙♙♙♙♙♙♙ ♟♟♟♟♟♟♟♟ ♜♞♝♛♚♝♞♜ characters 21:51:52 Coptic is basically greek 21:52:01 lol, yeah sure. 21:52:04 Slereah: why don't you make a font with all the codepoints no-one else has bothered to implement, so we all could install that? 21:52:06 :D 21:52:22 int-e: also, don't forget the domino pieces. or the Mahjongg pieces. 21:52:29 FireFly : Well I just need some time to design 65 million characters 21:52:30 Very essential characters, those 21:52:42 (but for shogi there's only ☖☗⛉⛊) 21:52:43 Slereah: maybe that's why no-one else has bothered 21:52:48 There aren't 65 million characters in Unicode. 21:52:56 I am but one man 21:53:15 Probably not 21:53:24 And no dedicated go stones, go players must do with circles, I believe. 21:53:26 I wonder how much they're up to 21:53:32 It's so unfair :) 21:54:18 "Unicode defines a codespace of 1,114,112 code points in the range 0hex to 10FFFFhex" 21:54:40 Yes, but they've allocated only about a hundred thousand and a bit. 21:54:53 how many times has this channel talked about unicode. man 21:54:54 There's a lot in the "to do" area though 21:54:55 -!- tertu has quit (Ping timeout: 272 seconds). 21:55:17 They're planning on doing fucking Aztec script 21:55:23 ah, more ... ⛀⛁⛂⛃ ⚀⚁⚂⚃⚄⚅ 21:55:53 http://www.unicode.org/roadmaps/smp/ 21:56:02 Also cuneiform 21:56:20 In case you want to send an email to King Hammurabi 21:56:30 ☔ <- unicode protection, it's raining characters. 21:57:17 personally i'm looking forward to tangut support. 21:57:20 I like U+1F5FE SILHOUETTE OF JAPAN, at least it's not unclear where all those characters are coming from. 21:58:08 oh, that's right next to lots of stupid? cute? whatever smileys. 21:58:16 Bike : It will only take 17 blocks 21:58:18 It's also right next to STATUE OF LIBERTY, TOKYO TOWER and MOUNT FUJI. 21:58:40 Wonder what they need the STATUE OF LIBERTY for. 21:58:53 because they tragically lack sa's crying eagle emote. 21:58:54 (my font (whatever gucharmap is using) doesn't have those :/) 21:59:08 Wait, they're adding blissymbols? Huh. 21:59:22 and phaisos disk, nice 21:59:34 😶 21:59:41 oh shit, deseret 22:00:03 they used to have to use private use for that. 22:00:15 By that point they're just adding whatever ancient script there is 22:00:20 Soon there will be cave drawings 22:00:37 U+3425C LEFT-FACING MAMMOTH WITH TWO SPEARS 22:00:42 well it is supposed to include all text. 22:00:57 i had no idea the hittites had hieroglyphs 22:01:05 except they're not hittite 22:01:08 good stuff 22:01:10 I can't wait until aliens come and they have to include all alien scripts 22:01:17 fizzie: is that an actual codepoint? 22:01:34 I'm more irritated by things like U+1D794 MATHEMATICAL SANS-SERIF BOLD ITALIC CAPITAL EPSILON 22:01:40 U+F4A86A GLIXNAR VENUSIAN GLYPH 22:01:56 FireFly: No. :( 22:02:12 Oh 22:02:16 Hm, is it bad that I had to ask? 22:02:32 With unicode, you never know 22:02:38 🐘 22:02:41 There's a penis character in unicode 22:02:52 I mean, there's (at least) five different characters of the moon with a face, so I wouldn't be surprised if there were one for left-facing mammoths with spears 22:02:58 One of the egyptian hieroglyph determinative is a penis 22:03:00 FireFly: I don't think there's anything in astral plane 3 yet. 22:03:08 it turns out that the aliens have extelligence only in the form of long-term self-sustaining chemical reactions. unicode consortium throne into a penis. 22:03:14 panic 22:03:23 possibly a penis, i really fucked up that sentence 22:03:46 Just the prime materi... I mean, basic multilingual plane, and astral planes 1, 2, E and F. 22:03:51 funny. google for "�" says it matches no pages. duckduckgo displays a picture of an elephant. duckduckgo won that round :) 22:04:00 They're gonna be so embarrassed when it turns out the aliens have 4D letters 22:04:04 -!- Phantom_Hoover has joined. 22:04:11 Man, they so should call BMP the "prime material plane" in Unicode terminology. 22:05:01 (And refer to its characters disparagingly as "primes".) 22:05:15 What about the outer planes 22:05:23 Which part of unicode is lawful neutral 22:05:46 Slereah: there are lots of unassigned codepoints. 22:06:00 Well yes, that's why they're adding more! 22:06:01 They've got 16 outer planes, they could easily map the D&D standard ring to those. 22:06:11 not sure whether that's lawful, but it doesn't get any more neutral :) 22:06:33 I would think that control characters are lawful neutral 22:06:49 Hm 22:06:56 I guess unicode doesn't have elvish or klingon 22:07:08 They're probably copyrighted anyway 22:07:12 No, though both have been proposed. 22:07:21 Also : no Batman or Prince symbol 22:08:10 Hm, the proposed Tengwar region is still in the roadmap. 22:08:18 I remember that the Klingon proposal was entirely shot down, at least. 22:08:54 The unicode people probably responded NEEEEEERDS 22:10:47 http://www.unicode.org/roadmaps/smp/ -- Cirth and Tengwar (the Tolkienesque things) are there on line 160, in the font that's for "scripts for which proposals have been formally submitted to the UTC or to WG2". 22:11:20 "As a result, blogs in pIqaD have begun to appear, --" it's the Klingon blogosphere. 22:11:20 3. Requester typeExpert request 22:11:33 2. Information on the user community?Tengwar enjoys both scholarly and popular use. 22:11:35 heh 22:12:19 Well, there's magazines published in it and all. 22:12:28 -!- AnotherTest has quit (Ping timeout: 264 seconds). 22:14:03 Probably also in Klingon 22:14:17 You P'takh! 22:14:25 (I forget the spelling) 22:15:15 I have a Tengwar font that just replaces [a-zA-Z0-9] 22:15:51 requesting klingon translation of 'blogosphere' 22:16:16 They have no word for blogosphere, but a hundred for flamewars 22:16:19 There's a "shadow registry" of mappings of different conlangs to the Unicode Private Use Area -- http://www.evertype.com/standards/csur/ 22:16:34 NEEEERD 22:17:22 unicode has blissymbols proposed, but not solresol? 22:19:41 jesus fucking christ am i talking about blissymbols just to avoid homework 22:19:57 You should type your homework in blissymbols. 22:19:59 Good plan 22:20:16 great plan 22:20:35 i am unsure how to translate 'monocot' 22:21:30 Bike: I think you combine the symbol for plant and the number 1. 22:23:05 for plants? what would be like, a gymnosperm, then 22:23:40 It probably involves some kind of caret pointing at something. 22:23:53 freaky 22:24:12 i wonder if any 'logical language' people have ever looked at what a clusterfuck systematics is. maybe that would convince them they're barking up a nonexistent tree 22:25:04 Everytime I see "lojban", I always interpret it as "logical banter" 22:25:07 i also wonder if any logical language person has seriously considered describing humans in terms of their jaws, as systematists do. 22:25:14 Slereah: that's kind of the idea, no? 22:25:25 yeah, but it's probably not the etymology 22:25:33 Loj is probably from logic 22:25:35 Ban, not a cxlue 22:25:39 let's see 22:25:46 i think it is, actually. it's not like they only used english roots. 22:26:00 " "Lojban" is a compound formed from loj and ban, which are short forms of logji (logic) and bangu (language), respectively. " 22:26:17 Hm, doesn't specify where they got bangu from 22:26:20 man, have you ever thought to yourself, yes, having jaws is awesome 22:26:21 -!- typeclassy has joined. 22:26:23 'cos it is 22:26:32 Bike: have you considered the many alternatives 22:26:47 Bike: I just have the one jaw, where did you get your second one? 22:26:49 I wouldn't mind having an anteater face 22:26:54 Anteaters are cute! 22:26:58 shachaf: what, like mandibles? fuck 'em 22:27:16 advantages of jaws include: adaptive immune system 22:27:33 aren't mandibles a kind of jaws 22:28:11 i mean bony jaws. 22:28:22 of the gnathostomata, of which you are and bikes are 22:28:58 what did you just call me 22:29:21 a gnathostome. 22:34:01 `learn shachaf is a gnathostome 22:34:06 I knew that. 22:36:00 uh do you just overwrite old wisdom entries like that all the time 22:36:26 does `learn overwrite? I thought it was concatenative 22:36:55 either way, it's versioned, so it can be rolled back.. 22:37:52 it overwrites. 22:38:18 well that's unfortunate :( 22:39:22 shachaf: should I revert that, then? 22:42:19 -!- darklust__ has joined. 22:44:35 -!- john_metcalf has quit (Ping timeout: 272 seconds). 22:46:13 -!- darklust_ has quit (Ping timeout: 272 seconds). 22:46:51 -!- Bike has quit (Ping timeout: 272 seconds). 22:50:55 what was the old entry 22:51:22 http://codu.org/projects/hackbot/fshg/index.cgi/rev/6295652cdd8a 22:51:29 It's from an hour ago (or so) 22:51:56 i don't think it's up to me 22:51:59 ask oerjan 22:52:18 I'll just revert it. 23:02:01 -!- conehead has joined. 23:07:33 -!- carado has quit (Ping timeout: 252 seconds). 23:24:14 -!- nisstyre has joined. 23:26:40 `olist (932) 23:26:42 olist (932): shachaf oerjan Sgeo FireFly 23:36:34 o 23:39:53 `oerjan 23:39:55 ​/hackenv/bin/oerjan: line 1: AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA: 23:40:58 -!- tertu has joined. 23:41:56 -!- mrhmouse has quit (Quit: Leaving.). 2013-11-21: 00:02:15 -!- Phantom_Hoover has quit (Remote host closed the connection). 00:14:27 -!- oerjan has quit (Quit: Nite). 00:16:09 -!- Bike has joined. 00:21:40 -!- nooodl has quit (Quit: Ik ga weg). 00:23:25 -!- Sprocklem has joined. 00:29:56 -!- Taneb has quit (Quit: Leaving). 00:32:20 -!- Sgeo has joined. 00:36:30 -!- augur has quit (Remote host closed the connection). 00:37:05 -!- augur has joined. 00:42:07 -!- augur has quit (Ping timeout: 272 seconds). 00:45:09 Going to go cry in a corner about the betrayal of a language that I was starting to like 00:45:10 http://pastie.org/8496948 00:46:20 shot through the heart AND YOU'RE TO BLAME 00:52:37 Why is the movement lobe so laggy 00:53:48 -!- yorick has quit (Remote host closed the connection). 00:54:05 Oh, ok, tht's easy to fix 00:55:18 I think im going to create a language, where you just hit the keyboard with your fist randomly 00:55:30 like, aim for a with your fist, and that will me like + for brainfuck 01:07:10 -!- adu has joined. 01:09:27 -!- tertu has quit (Ping timeout: 246 seconds). 01:14:55 -!- typeclassy has quit (Ping timeout: 246 seconds). 01:33:02 -!- tertu has joined. 02:06:57 -!- augur has joined. 02:19:51 -!- conehead has quit (Quit: Textual IRC Client: www.textualapp.com). 02:20:09 -!- conehead has joined. 02:24:45 JesseH: so the commands will be clusters of letters? and the interpreter tries to guess where one cluster ended and the next one started? 02:32:13 -!- tertu has quit (Ping timeout: 272 seconds). 02:34:49 -!- Sprocklem has quit (Ping timeout: 240 seconds). 02:35:37 -!- tertu has joined. 02:45:52 -!- typeclassy has joined. 02:48:08 -!- madbr has joined. 02:49:11 -!- adu has quit (Quit: adu). 02:56:53 -!- typeclassy has left ("ERC Version 5.3 (IRC client for Emacs)"). 03:00:41 -!- adu has joined. 03:19:38 -!- tertu has quit (Read error: Connection reset by peer). 03:58:56 -!- tertu has joined. 03:59:41 -!- tertu has quit (Read error: Connection reset by peer). 04:04:48 -!- doesthiswork has joined. 04:51:27 -!- adu has quit (Quit: adu). 05:20:45 -!- doesthiswork has quit (Quit: Leaving.). 05:58:27 -!- conehead has quit (Quit: Computer has gone to sleep.). 06:02:19 quintopia, indeed 06:04:55 what 06:04:57 oh 06:05:00 damn 06:05:15 where is zzo38 when you need him? 06:05:21 (inb4 "at Canada") 06:05:28 the moo- oh, sorry 06:07:22 -!- muahaha has joined. 06:07:28 -!- muahaha has left. 06:20:56 -!- Sgeo_ has joined. 06:22:56 -!- Sgeo has quit (Ping timeout: 240 seconds). 06:28:17 -!- madbr has quit (Quit: Rouringu de hajikunda!). 06:48:24 -!- augur_ has joined. 06:51:57 `relcome shachaf 06:52:02 ​shachaf: Welcome to the international hub for esoteric programming language design and deployment! For more information, check out our wiki: . (For the other kind of esoterica, try #esoteric on irc.dal.net.) 06:52:05 Finally! 06:52:53 -!- augur has quit (Ping timeout: 272 seconds). 06:55:52 what? 06:56:16 I don't think I've been `welcomed before. 06:56:32 so you just made it yourself 06:59:48 where is oerjan 07:00:09 `wercome shachaf 07:00:11 shachaf: エソテリックプログラミング言語のディザインとデプロイメントの国際な場所へようこそ!詳しく、ウィキを見て: http://esolangs.org/wiki/Main_Page。(他のエソテリック、irc.dal.netの#esotericへ) 07:00:28 now someone else has welcomed them. happy? 07:00:28 `rercome shachaf 07:00:29 ​/home/hackbot/hackbot.hg/multibot_cmds/lib/limits: line 5: exec: rercome: not found 07:00:38 shachaf: i've never been welcomed either 07:01:08 `welcome quintopia 07:01:10 quintopia: Welcome to the international hub for esoteric programming language design and deployment! For more information, check out our wiki: . (For the other kind of esoterica, try #esoteric on irc.dal.net.) 07:01:39 thanks lexande 07:02:18 have you been hth'd? 07:02:41 hi lexande 07:02:57 have i asked you about chu spaces yet 07:03:30 -!- darklust_ has joined. 07:03:30 What’s a choo choo space? 07:03:41 @ask oerjan why did you expand the definitions of sin and cos on SELECT.? and why not the others? (i prefer the unexpanded versions because it shortens the code i have to write if i can just call other ones as subroutines.) 07:03:41 Consider it noted. 07:04:10 shachaf: you've never asked me hth 07:04:22 ion: there's a channel for that 07:04:40 #cslounge-topologicalgeneralizations 07:04:51 #cslounge-bikes does exist 07:05:18 * quintopia cuts a red deck of bikes 07:05:45 isn't csharp basically an esolang? 07:05:47 * myname hides 07:06:00 shachaf: yeah, i don't know about them, sorry 07:06:05 Should i lounge on #cslounge? 07:06:11 is C++ still kmc's favourite esolang? 07:07:04 -!- darklust__ has quit (Ping timeout: 264 seconds). 07:07:15 Bike: let's talk about SLI 07:07:28 ok 07:07:41 is there a working complex SLI library? 07:07:53 ion: tough question 07:07:56 not that i'm aware of 07:08:12 guess you have to work out the operations 07:08:16 do you know how to fast add and multiply in SLI 07:08:28 ion: once saul kripke was walking in DC and he saw john nash, so he went up to him and say "hi, i'm saul kripke, it's an honour to meet you professor nash." and nash said "who are you!? who sent you!?" 07:08:30 e^a * e^b is e^(a+b), so recursin' 07:08:37 so kripke said "aaaah!" 07:08:43 so nash said "aaaah!" 07:08:46 so kripke said "aaaah!" 07:08:47 so nash said "aaaah!" 07:08:54 lol 07:09:09 it is unknown how many times this iterated 07:09:21 lexande: Acknowledged. 07:09:27 sounds like a nash equilibrium 07:09:31 e^a + e^b is uh... some bullshit 07:09:32 anyway, if you do decide to join #cslounge, be prepared to answer a question similar to nash's with a better response than kripke's 07:09:42 so in SLI 07:10:39 Sgeo_ is in #cslounge somehow 07:11:17 I've been there a while 07:11:36 sometimes i wonder what knowledge you people here have 07:11:44 oh, wikipedia has a library. https://code.google.com/p/sli-c-library/ 07:11:55 myname: i can name, like, three different pokemons. 07:11:56 a*b=(a-1(whatever plus is)b-1)+1 07:12:10 «SLI (symmetric level-index) arithmetic essentially prevents overflow & underflow in computing. With this library, you may use 'SLI' as a normal data type in C++. Replace 'double' with 'SLI' in you program, and over/underflow problem would be solved.» lol 07:12:15 Bike: yeah that's not implemented complex numbers :P 07:12:15 i have a seminar this semester about game theory and slowly understand nash equilibrium 07:12:23 Bike: that is pretty lame 07:13:02 surely c++ templating makes it a snap to replace the underlying numeric type! 07:14:10 hmm, but x*y=ln((e^x)^y), but ln is just -1, and e^ is just +1, so that's just (x+1)(whatever ^ is)y-1 07:14:18 i think this one is easier to figure out 07:14:45 but ^ is not a simple thing in SLI 07:16:00 i don't get the nash joke :( 07:17:23 exp(a) * exp(b) = exp(a + b) is 1 + a + b, right 07:19:16 lexande: i heard that story before 07:19:17 was it from you 07:19:27 using multiple forms of arithmetic in the same go like that is confusing. 07:19:31 shachaf: probably, or kmc 07:21:20 Bike: ˖ ᐩ ⁤ ⁺ ₊ ∔ ⊕ ⊞ ➕⧺ ⧻ ⨁ ⨹ hth 07:21:28 thank's 07:21:52 oh how could i forget, ﬩ 07:22:05 you broke my irssi 07:22:08 that's what they use in elementary schools in .il 07:22:19 because + is too christian?? 07:22:34 i would go with the first five 07:22:44 should be enough 07:22:49 maybe with + 07:22:59 some schools, anyway. i had it in some books 07:23:12 shachaf: You forgot ☩ 卍 卐 hth 07:23:32 ☮ 07:23:58 maybe we can just decide adding things is overrated. 07:24:37 Bike: btw did you see my 2064 INVISIBLE PLUS [⁤] 07:24:43 no 07:24:47 since it was invisible 07:25:02 The jokes within the Unicode standard are hilarious. 07:25:13 May you live in INVISIBLE PLUS. 07:26:21 Bike: yes it would be 1+(a卐b). and a = exp(a)-1, and b=exp(b)-1, but the 卐 is not simple. 07:26:51 a^b = e^(a * log(b)) = 1 +' (a *' (b -' 1)) 07:26:58 i'm really too tired to think ugh 07:27:06 er, b * log a. 07:27:10 wow. 07:27:12 I’ll think ugh for you. 07:27:19 why does anyone pay attention to me. why do i exist? what is life. 07:27:29 that first plus is a normal plus 07:27:30 fungot: what is life. 07:27:30 shachaf: i'll need to buy bread i assume it was a fools fnord. 07:27:45 life is a fools fnord. 07:27:46 and the minus is a normal minus 07:27:50 quintopia: i'm using ' to mean "in normal arithmetic", and without it to mean "in SLI" 07:27:58 which is dumb 07:27:58 oh in that case 07:27:59 -!- FreeFull has quit. 07:28:00 sorry 07:28:03 - is not a normal minus, − is a normal minus. 07:28:05 you should drop the ' on the * 07:28:10 yeah, you're right. 07:28:16 fungot: - is a HYPHEN—MINUS 07:28:16 shachaf: doesn't mean anything to me either. rather read the algorithm, as well 07:28:43 shachaf, shouldn't it be an en-dash? 07:28:58 oh wait- just hyphen? 07:29:06 i like to subtract using em-dashes 07:29:17 so a^b = 1 +' (1 +' (b + (a -' 1))) or so 07:29:37 that was a pedant trap. let's see who else falls in. 07:29:42 + is bullshit that i hate though. fuck it. die. mother 07:29:45 quintopia, that reminds me of Unispace 07:30:23 what are you even trying to figure out 07:30:29 who fucking knows 07:30:32 what's sli 07:30:41 Bike: i think it may be easier to define + and * in terms of ^ and have ^ be the one complicated algorithm 07:30:53 has anyone ever even been so far decided as to more like 07:30:54 service level initiative?? 07:30:59 Bike: p. sure ion has 07:31:13 uh, what are you doing now? 07:31:33 has anyone really been so far even as do go be look more like? 07:31:38 four hundred nineteen armless and legless corpses float conspicuously through the remains of the hangar 07:31:41 defining ^ : N x N -> Q? 07:33:29 lifthrasiir: definininininining ^ CxC->C where C uses the SLI representation 07:33:30 sli is where each number has two parts, a regular small significand, and a whateverthefuckinand such that the value of the number is the power tower of e's whateverthefuckinand tall with the significand at the top 07:33:50 Sign-Level-Index? 07:33:53 they call them level and index 07:33:54 yes 07:33:58 well 07:34:01 symmetric level index 07:34:10 ah got it 07:35:09 of course it really only makes sense in the complex field if we only allow anyone ever to use the principal branch 07:35:23 the other branches can fuck themselves 07:35:39 well, brances do have crotches between them 07:35:43 +h 07:36:00 the -1 branch of lambert is such an asshole at parties 07:36:10 no i'm not dressed as andrew jackson you dumb motherfucker 07:36:47 are the branches of the product-log polyamorous 07:37:12 they do seem to like to get together at one point 07:37:19 or is that just a coincidence? 07:42:34 http://link.springer.com/chapter/10.1007%2FBFb0024702 07:43:14 -!- augur has joined. 07:44:32 only thirty bucks 07:44:56 -!- impomatic has quit (Quit: impomatic). 07:45:13 -!- augur_ has quit (Read error: Connection reset by peer). 07:53:02 what a bargain 07:53:44 well there's a hint in the abstract 07:53:53 the algorithms are recursive 07:54:11 saw it comin' 07:54:20 yeah sucks though 07:54:33 means compute time is slow 07:54:39 probably O(i) 07:54:42 wait 07:54:59 i mean O(l+p^k) 07:55:03 or something 07:55:10 k probably less than 2 07:55:49 it also talks about "the original recursive algorithms for arithmetic" 07:55:57 meaning those are exposed somewhere besides this paper 07:55:58 so 07:56:03 can we find them 07:56:13 i guess 07:56:14 classical arithmetic is recursive too... 07:56:17 the source code 07:57:03 classical arithmetic is usually implemented iteratively, and a lot of it is ENTIRELY parallelizable 07:57:51 like, to do x^y, you don't compute x*(x^(y-1)) 07:58:52 but anyways 07:58:54 the source code 07:58:59 that's where the answer lies 08:00:12 what is this i don’t even http://redalertlive.com/2013/11/18/body-modification-piercings-lip-plates/ 08:02:53 kmc: http://www.youtube.com/watch?v=FavUpD_IjVY 08:04:02 cyriak & cyriak & cyriak 08:04:42 oh it's that person 08:04:45 who makes those videos 08:18:59 i remember now 08:28:19 Is there a community like this one, but for non-esoteric prog langs? 08:29:46 Like where you can talk about the creation of programming languages, unharmed :P 08:33:17 make #nonesoteric 08:34:04 it doesn't seem like such discussion would be considered offtopic here? 08:35:59 It seems like it would to me, or could be. 08:37:09 Just went ahead and made #nonesoteric :P 08:39:00 No thats a stupid name :P 08:39:22 Because the creation of programming languages doesnt mean just nonesoteric ones 08:39:54 But this channel is centered around esoteric, so thats why I was wondering. 08:40:10 I think there should be a channel for each real number representing esotericness. 08:40:41 I hear #esoteric-0.594381… is great. 08:40:54 Will check it out :P 09:01:14 -!- carado has joined. 09:31:14 JesseH: Please don't create a Java derivative. 09:31:15 -!- carado has quit (Ping timeout: 252 seconds). 09:31:41 Nah; Derplang 2.0 :P 09:31:46 Example would would be 09:31:50 var x int 1 09:31:52 out x 09:31:53 -!- oerjan has joined. 09:31:53 May I suggest a more verbose version of J 09:31:55 => 1 09:31:58 I like J 09:32:00 but it's to unreadable 09:32:06 (for a non J-er like me) 09:32:08 *too 09:32:14 I see 09:32:29 but generally I'm pretty sure J kicks ass 09:32:54 I see :P 09:33:19 and we need more kick ass languages 09:33:58 Derplang is going to be a kick ass language :P 09:34:12 @messages-loud 09:34:12 quintopia asked 2h 30m 31s ago: why did you expand the definitions of sin and cos on SELECT.? and why not the others? (i prefer the unexpanded versions because it shortens the code i have to write 09:34:13 if i can just call other ones as subroutines.) 09:34:23 way too lowlevel @derplang 09:34:45 wat 09:35:01 var x add 2 2 09:35:05 out x # => 4 09:35:07 yeah 09:35:11 that's exactly low level 09:35:29 Handling lists is going to be interesting; I was thinking 09:35:33 var x list 1 2 3 4 5 09:35:37 out x 0 09:35:39 => 1 09:35:40 @tell quintopia Because SELECT. is a complex number language and the unexpanded versions only hold for reals. and because i didn't remember the inverse versions and my brain didn't feel like working it out. 09:35:40 Consider it noted. 09:35:59 Can I create 3D figures and then let derplang calculate its volume? 09:36:22 where are matrices, vectors 09:36:24 and stuff 09:36:24 this is not forth 09:36:42 If you want special things, you probably will have to implement it yourself. 09:37:40 That's what C said. 09:37:42 Ill create a package manager thing, so we can easily share libraries :P 09:38:12 mroman_, lol i get it 09:38:23 @tell quintopia alternatively s/remember/ever learn how branch cuts work for/ 09:38:23 Consider it noted. 09:39:34 At least don't use Integers for Listindices 09:39:43 or array indices 09:39:45 O_o 09:39:52 are you mad 09:40:10 There should be a data type for indicies 09:40:30 that behaves like an integer but safer 09:41:26 :t range 09:41:28 Ix a => (a, a) -> [a] 09:41:55 > range ((0,0),(1,1)) 09:41:56 [(0,0),(0,1),(1,0),(1,1)] 09:44:11 more or less an iterator 09:44:20 that overloads + and - or something 09:44:35 If Java had operator overloading . 09:45:27 Operator Overloading for Haskell... 09:45:49 Did they consider that to prevent operator hell? 09:46:19 e.g. uhm 09:46:44 foo :: String -> Int; foo x = read x; foo :: Int -> String; foo x = show x; 09:47:05 I assume it would be possible to detect which version of foo is meant 09:47:18 um that's what type classes are for. 09:47:27 Yeah 09:47:34 But type class != overloading 09:47:50 i.e (+) is reserved for Num 09:47:59 so you can't use (+) for anything that is not a Num 09:48:01 :i (+) 09:48:08 :t (+) 09:48:09 Num a => a -> a -> a 09:48:27 so you have ++ for strings 09:48:35 because it wouln't really work well with the regular + 09:48:39 type classes were invented because the haskell inventors considered usual overloading ugly and messy. 09:51:56 It is 10:15:17 `unidecode ࠐ 10:15:21 ​[U+0810 SAMARITAN LETTER FI] 10:15:30 oh wait 10:15:56 `unidecode ⁤ 10:15:57 ​[U+2064 INVISIBLE PLUS] 10:16:11 hm in putty it _is_ invisible. 10:16:17 not in IE. 10:38:49 myname: C# seems pretty un-eso to me 10:39:15 it's like java but without all the useful features you'd want inexplicably missing 11:17:22 am i getting overly trigger happy 11:26:16 -!- darklust_ has quit (Remote host closed the connection). 11:27:49 -!- nooodl has joined. 11:30:07 kmc: what features? 11:30:48 -!- MindlessDrone has joined. 11:38:21 unsigned integers, lambdas, tuples, monad comprehensions (kinda), operator overloading, reference parameters, generators, optional & named arguments, extension methods 11:38:42 http://en.wikipedia.org/wiki/Comparison_of_C_Sharp_and_Java 11:40:10 oh the lambda is also an AST quotation and you can do dynamic macros and JIT them 11:42:35 -!- Patashu has joined. 11:43:16 so yeah, C#: actually pretty good and cool 11:43:52 I haven't really needed it so far, but I would seriously consider it for a future project, although I'd have to first convince myself Mono is fully-baked enough 11:44:07 (it was fine for the one toy project I did in C#) 11:45:52 -!- nooodl_ has joined. 11:49:13 -!- nooodl has quit (Ping timeout: 252 seconds). 12:02:48 I'm a bit disappointed that those languages are so framework dependant 12:03:16 C# is really a neat language 12:03:35 But I'd rather have it produce native code 12:05:17 or at least they should have considered portability a bit better 12:05:28 it does produce native code, via JIT 12:05:37 what properties associated with "native code" do you actually care about? 12:07:02 It's better for compile'n'run 12:07:17 so "size" 12:08:03 which means it's more portable 12:09:14 you mean that you don't want to have a JIT around at runtime? 12:09:22 for size reasons? 12:09:27 I don't care if it's JITed 12:09:56 It's probably even better if it's JITed 12:11:24 But JIT requires an extra installation of some software on your system 12:11:28 that's what I dislike 12:11:32 ah 12:11:39 well you could bundle the JIT with every executable ;P 12:11:43 Yes 12:11:55 But I'm not sure how big the Java JIT is :) 12:12:00 huge 12:12:08 I suspect like... 12:12:13 10MB? 12:12:46 Although that sounds too much 12:13:06 anyway does the C# spec even forbid, say, an ahead-of-time compiled implementation? 12:13:15 i'm not sure whether the spec requires the full Common Language Infrastructure 12:13:29 it might, I have no specific knowledge of it 12:13:37 kmc: I don't think so @CLI 12:13:42 But I haven't read the spec. 12:14:15 Seeing as C# is used in OSDEV I assume you don't need a huge runtime around it 12:14:36 so if your complaint is that Microsoft's C# implementation is not the kind of C# implementation you'd want to use, that's not a complaint with C# the language 12:14:41 Mono has http://www.mono-project.com/AOT 12:14:50 don't know anything about it past 2 seconds of reading that page ;P 12:14:55 mroman_: what's it used for in os dev? 12:15:30 For "Hey look I can write an OS in C#"-stuff 12:15:55 Much like "Hey look I can write an OS in Ada, Cobol, Pascal, Delphi"-Stuff 12:16:06 kmc: Singularity is probably C#? 12:16:31 hom no 12:16:38 A C#-Derivative 12:16:48 Sing# 12:16:49 :) 12:17:07 kmc: No C# is fine. 12:17:16 It's the Framework I don't like :) 12:17:18 -!- Patashu has quit (Quit: Soundcloud (Famitracker Chiptunes): http://www.soundcloud.com/patashu MSN: Patashu@hotmail.com , AIM: Patashu0 , YIM: patashu2 , Skype: patashu0 .). 12:17:33 ok then 12:17:37 Well 12:17:41 I like the Framework 12:17:43 on windows :) 12:17:49 I don't like Windows so I'd never use MSFT's C# stuff anyway 12:17:55 but I might use it via Mono sometime 12:18:01 It's really future rich 12:18:20 and now with new .NET and wpf and stuff you have even more feature rich stuff 12:18:39 like 10000 Classes . 12:18:56 Hm 12:19:15 kmc: Or you find someone who does C# on JVM 12:19:21 *to JVM 12:20:06 Apparentely there's the "Stab programming language" 12:20:24 every programming language is a stab programming language 12:20:31 http://code.google.com/p/stab-language/ 12:24:26 esoteric frameworks 12:24:30 are there yet any? 12:24:56 EsoAPI 12:25:02 but I've heard it's dead 12:25:23 :t (^~) 12:25:24 (Integral e, Num a) => ASetter s t a a -> e -> s -> t 12:25:37 oops 12:25:47 :t (^%) 12:25:48 Not in scope: `^%' 12:25:48 Perhaps you meant one of these: 12:25:48 `^' (imported from Prelude), `^^' (imported from Prelude), 12:26:21 :t (%~) 12:26:22 Profunctor p => Setting p s t a b -> p a b -> s -> t 12:26:38 -!- oerjan has quit (Quit: BRAAAIN). 12:27:16 yoob? 12:29:36 -!- MindlessDrone has quit (Quit: MindlessDrone). 12:41:11 -!- carado has joined. 12:44:00 -!- Sgeo_ has quit (Read error: Connection reset by peer). 12:44:41 -!- yorick has joined. 12:58:14 -!- boily has joined. 12:58:26 -!- metasepia has joined. 12:59:21 -!- oerjan has joined. 12:59:50 -!- oerjan has set topic: The channel of the chimæric hellos | The most corum, clargoint chait you could ever loofefl your slance in. | Magnus!!!! | Koirammekokaan ei lennä? :( | https://dl.dropboxusercontent.com/u/2023808/wisdom.pdf | logs: http://codu.org/logs/_esoteric/ or http://tunes.org/~nef/logs/esoteric/. 12:59:55 -!- oerjan has quit (Client Quit). 13:12:46 good exclamative morning? 13:12:58 @tell oerjan what with the drive-by topicking? 13:12:58 Consider it noted. 13:13:39 -!- MindlessDrone has joined. 13:22:16 hi 13:32:54 good kmorningc. 13:45:35 how are you? 13:59:28 doing well. how's life on your end? 14:00:12 pretty good 14:03:20 -!- muskrat has joined. 14:04:00 ~metar KSFO 14:04:00 KSFO 211356Z 25003KT 10SM SCT013 BKN023 OVC042 10/09 A2994 RMK AO2 SLP137 T01000089 14:04:10 -!- muskrat has left. 14:06:04 kmc: I'm guessing you're currently eating breakfast? 14:06:54 nope 14:06:59 it's 23:06 here 14:07:55 ooookay... either my file is wrong, or the Earth has a very, very weird curvature today. 14:08:39 you're not in Frisco anymore? 14:09:26 i'm vacationing in japan 14:09:39 * kmc twitches at "Frisco" 14:11:14 オォ!すごい!どこにいっていますか? 14:12:40 i can't read any of that -_- 14:12:48 but google informs me you asked where i'm going in japan 14:13:45 osaka, nara, kyoto, hiroshima, tokyo in that order 14:13:50 i'm in hiroshima right now, heading to tokyo tomorrow night 14:13:56 :D 14:14:17 this is after a work week + a few days of touristing in Seoul 14:14:49 which means that work paid for my flights across the Pacific which is すごい indeed 14:16:27 btw Hangul is the coolest writing system ever 14:17:15 I fear my main motivation to learn languages spoken in Asia is to understand what's written on restaurant menus... >_>'... 14:19:01 -!- yiyus has quit (Read error: Operation timed out). 14:19:18 -!- augur has quit (Ping timeout: 245 seconds). 14:24:27 -!- augur has joined. 14:24:38 seems fine to me 14:27:21 you can learn to read hangul in a few hours 14:27:46 or as one of the developers of the alphabet put it, "a wise man can acquaint himself with them before the morning is over; a stupid man can learn them in the space of ten days" 14:31:16 on the other end of the spectrum, culinary cantonese is unbelievably hard, not for the characters themselves, but the poetic metaphors and shortcuts. 14:46:15 example? 14:53:37 I'll take pictures tonight of a potential source of incomprehensibility. 14:54:07 cool 14:54:15 do you know anything about szechuan cooking, by the way? 14:54:32 i quite like szechuan food and we cook it at home sometimes 14:55:38 I tried my hand at it a few times, but I have to hone my techniques. 14:55:40 -!- mrhmouse has joined. 15:04:00 kmc: some day, I'll succumb to the temptation, and buy a portable electric stove with a fondue pot, and make myself real sichuanese fiery fondue of deathly agonizing doom. 15:07:04 nice 15:24:23 next step: find a recipe with raccoon meat. there are more than enough overweight raccoons on Mont Royal. 15:25:03 haha 15:44:43 -!- Sprocklem has joined. 15:48:33 -!- Phantom_Hoover has joined. 15:49:49 -!- MindlessDrone has quit (Read error: Operation timed out). 15:50:24 -!- mrhmouse has quit (Ping timeout: 246 seconds). 15:52:04 -!- MindlessDrone has joined. 15:57:12 -!- conehead has joined. 16:19:52 -!- Sorella_ has joined. 16:20:47 `relcome Sorella_ 16:20:50 ​Sorella_: Welcome to the international hub for esoteric programming language design and deployment! For more information, check out our wiki: . (For the other kind of esoterica, try #esoteric on irc.dal.net.) 16:21:47 ~duck gnathostome 16:21:47 Gnathostomata are the jawed vertebrates. 16:22:50 well-spaced 16:25:01 it's a well-known anatidæ feature. 16:25:03 -!- nisstyre has quit (Ping timeout: 246 seconds). 16:35:06 -!- mrhmouse has joined. 16:40:19 I think I have decided to keep the old derplang syntax, since more people have told me they like it over the new 16:46:46 Hello esoterics 16:46:58 Slereahello. 16:56:29 Slereah: how is your trek into assembly going? 17:03:33 you could say he...JMPd right in... 17:04:41 -!- Sprocklem has quit (Ping timeout: 272 seconds). 17:10:45 -!- Bike has quit (Ping timeout: 272 seconds). 17:16:57 -!- Bike has joined. 17:19:45 mrhmouse: not far 17:19:51 I went to bed and went to class 17:20:01 I'll investigate this week end 17:30:11 -!- FreeFull has joined. 17:34:42 -!- ais523 has joined. 17:35:01 helloily 17:35:46 what isn't the command called ~anatidae 17:38:50 @tell oerjan the unexpanded versions work for complex numbers too, as that's exactly how i implemented it and got right answers. and the inverse trig functions branch the same way as log (e.g. the principal branch of each agrees) 17:38:50 Consider it noted. 17:43:25 Why do most computer things use reals instead of rationals 17:43:45 Rationals are easy to code, easy to operate with, and floating points are just really rationals in the end 17:45:01 Although 17:45:25 There's the possibility of wasted space I guess 17:45:39 Since 1/2 = 1*10^30 / 2*10^30 17:45:57 You could be overflowing needlessly 17:46:23 Some languages work with rationals by default. 17:46:33 Which ones? 17:46:44 Well, I think Haskell does 17:46:56 And probably many functional languages 17:47:17 There's still the floating point type to store irrational numbers. 17:47:27 LISP would be great for it, since a rational is just a list of two integers 17:47:38 And I think most general purpose languages have some way of dealing with rationals 17:48:00 You can't store irrational numbers in a floating point 17:48:03 Or even in anything 17:48:10 Most irrationals aren't computable 17:48:32 No, but you can store a better approximation (read: smaller in size) in floating point 17:48:58 I guess! 17:49:27 I wonder what would be the most efficient way of encoding some real number approximatively 17:51:59 quintopia: quinthellopia. because I lack imagination. 17:55:39 Slereah: const real x = 0; 17:56:15 That's a pretty big approximation 17:56:23 Also not that efficient 17:56:36 If you encode it on one bit, at least do "0 or not 0" 17:56:49 I'm an approximation expert, with a specialisation in coördinates. 17:59:47 Hm 18:00:12 I guess you could encode algebraic numbers as a vector of their polynoms 18:00:18 I wonder what precision that would allow 18:04:21 -!- conehead has quit (Quit: Textual IRC Client: www.textualapp.com). 18:06:08 -!- conehead has joined. 18:11:08 boily: and body weigh! 18:12:29 -!- Taneb has joined. 18:12:36 Tanelle. 18:13:03 Slereah: as a certified appröximator, what are your coördinates and body weigh? 18:13:04 what do today 18:13:26 quintopia: today thursdays. 18:13:41 i only got 5 hours of sleep. 18:13:53 i couldn't sleep any more even though i was so sleepy 18:26:09 -!- Bike has quit (Ping timeout: 246 seconds). 18:27:12 * boily removes fizzie's eggtimer and glues it onto quintopia 18:27:21 ow 18:27:35 do i have to stand on my head to reset it 18:29:40 only if you start seeing Ephemeral Shadow-Bats because of sleep deprivation. 18:33:05 -!- Bike has joined. 18:57:37 https://d24w6bsrhbeh9d.cloudfront.net/photo/aEwpeEe_460sa.gif 18:59:13 is it really that big of a deal? (the G+ / YouTube linking) 18:59:33 it ruins the sanctity of youtube comments. 18:59:38 I haven't actually noticed, since I've had a G+ account for ages.. 19:00:47 it's caused YouTube comments to stop working for me altogether 19:00:51 which is arguably a good thing, but… 19:02:17 Maybe that's another reason I haven't noticed... 19:02:42 if youtube comments can't be youtube comments, that'll cause an overflow and drown the rest of the intarwebs under a neverending flood! 19:14:58 boily: what did we do before youtube existed? 19:16:05 upload videos in actual video formats 19:16:13 to actual directories of web servers 19:16:33 things were so much simpler then 19:16:50 anyone remember quicktime 19:17:01 yeah but where did the comments overflow to? 19:17:41 there were no comments then! 19:17:56 people watched videos in silence in the comfort of their own hard drive 19:18:09 back in the Previous Era, people overflowed in newspapers. 19:18:12 if they had a comment they wrote it in a text file and saved it for themselves to look at later 19:18:57 boily: now, at the end of the movie, they always overflow on her face 19:19:35 or, in horror movies, a Supernatural Floating Disflagrated Face. 19:19:53 so uh, the original strongly agree-agree-neutral-disagree-strongly disagree scale was kinda fucked up https://twitter.com/mc_hankins/status/403270681846378496/photo/1/large 19:23:05 unnnnrelated but you could vote in this poll, it's got ada lovelace and grace hopper. http://www.bobbleheads.com/bobblehead-scientist-poll.html 19:24:20 -!- Sprocklem has joined. 19:29:13 -!- oerjan has joined. 19:38:33 @messages-loud 19:38:34 boily said 6h 25m 35s ago: what with the drive-by topicking? 19:38:34 quintopia said 1h 59m 43s ago: the unexpanded versions work for complex numbers too, as that's exactly how i implemented it and got right answers. and the inverse trig functions branch the same way 19:38:34 as log (e.g. the principal branch of each agrees) 19:38:58 boily: magnus won another game hth 19:40:31 quintopia: i fail to see how cos(x) = Re(e^(i*x)) can work for complex numbers given that the correct answer isn't always real. 19:41:32 > cos (0 :+ 1) 19:41:34 1.5430806348152437 :+ (-0.0) 19:41:48 obviously not a good example. 19:41:51 > cos (1 :+ 1) 19:41:52 0.8337300251311491 :+ (-0.9888977057628651) 19:41:55 :) 19:41:58 thanks :) 19:42:34 oerjan: perhaps i should reimplement and expand my test cases :P 19:42:53 ~eval sin 1 == (exp (0 :+ 1) - exp (0 :+ -1)) / (0 :+ 2) 19:42:54 Error (1): Precedence parsing error 19:42:54 cannot mix `Data.Complex.:+' [infix 6] and prefix `-' [infixl 6] in the same infix expression 19:43:03 ~eval sin 1 == (exp (0 :+ 1) - exp (0 :+ (-1))) / (0 :+ 2) 19:43:04 True 19:43:04 i'll expand the others too 19:43:27 Implementation of cos(x) in what? 19:43:48 in http://esolangs.org/wiki/SELECT. 19:44:13 * oerjan wonders how many clients will erroneously leave out the dot. 19:44:32 Mine does 19:44:37 well, among those who make it a link in the first place. 19:44:41 > let i = 0 :+ 1; cos' x = (exp (i*x) + exp(-i*x))/2 in (cos (1 :+ 1), cos' (1 :+ 1)) 19:44:43 (0.8337300251311491 :+ (-0.9888977057628651),0.833730025131149 :+ (-0.98889... 19:45:03 Oh, the dot was part of it 19:45:19 `thanks oerjan 19:45:21 Thanks, oerjan. Thoerjan. 19:45:28 `yw FireFly 19:45:30 ​/home/hackbot/hackbot.hg/multibot_cmds/lib/limits: line 5: exec: yw: not found 19:45:52 i set up a redirect hth 19:45:52 oerjan: wait a second. what's the difference between (x+x*)/2 and (e^ix+e^-ix)/2 again? 19:46:01 You're welcome, Firefly. You're wireFly 19:46:10 quintopia: there is no conjugation in the latter. 19:46:12 oerjan: You could try http://esolangs.org/wiki/SELECT%2E. ;-) 19:46:32 just two numbers that _happen_ to be conjugate if x is real. 19:47:22 hmmmm 19:47:40 it's not clear to me what happens when they are complex 19:48:21 cos and sin are entire analytic functions in the complex plane, the expressions in e give the same result as the usual power series everywhere. 19:49:32 i guess e^(i(a+bi)) = e^(ia) * e^(-b)? 19:49:47 nooodl_: yeah 19:51:32 e^(ia) e^(ia) e^(complex fhtaghn) 19:51:40 btw (e^(i*x))* = e^(-i*x*) 19:52:15 postfix * is confusing as fuck 19:52:24 imo conj() 19:52:28 -!- Phantom_Hoover has quit (Ping timeout: 246 seconds). 19:55:17 The complex conjurer. 19:56:41 quintopia: well e^(ix) and e^(-ix) are essentially the exponential with arguments rotated 90 degrees, which switches which of real and imaginary direction is growing and which is periodic. and then you take linear combinations of that, to make similar functions that are real on reals. 19:57:06 oerjan, stop being fungot. twh. 19:57:06 boily: generally alternative rock or ska. uh, i have trouble assimilating a url that refers to it.... 19:57:42 so cos and sin in imaginary direction are approximately growing exponentially. 19:57:46 So is there some easy way to get cos and sin out of exp for complex values? 19:58:12 Bike: um yes that's what started this. 19:58:27 cos(x) = (e^(i*x)+e^(-i*x))/2 19:58:27 sin(x) = (e^(i*x)-e^(-i*x))/(2*i) 19:58:43 right. silly me. 19:59:14 -!- Sorella_ has quit (Quit: Ex-Chat). 19:59:22 boily: how am i fungot when the sword alone cannot stop! 19:59:23 oerjan: sounds like fnord talk. then again as has been demonstrated... i've been wondering about encoding things like stress and vowel lengths...) 20:00:12 fungot: you mean you're working on an audio version of yourself? i think fizzie would appreciate that. 20:00:12 oerjan: aww. hold it gently.) but it has slower screen updates as they happen when you were fnord 20:00:42 fungot: audio versions don't need screen silly 20:00:42 oerjan: i'm unclear as to how to extract information from gnomon, should he ever join the fnord 20:01:27 I would certainly "appreciate" an incessantly babbling audio-fungot in my home, sure. 20:01:28 fizzie: they're cheating a bit with the old version 20:02:33 fizzie: imagine, a fungot plushie with an embedded speaker. the world would be a much better place! 20:02:33 boily: fnord francais? ( assuming that code is valid: 20:02:39 fungot: i am not sure extracting that information is good for sanity. 20:02:39 oerjan: i've been looking in the wrong timezones ( as opposed to what you explained above 20:02:47 fungot: oui, une version francophone serait appréciée. 20:02:48 boily: someone could tell fizzie to stop reading before an overflow would fnord, and t f) 20:03:52 fizzie: stop reading before an overflow would fnord hth 20:06:04 fizzie: do you have a large enough French corpus available for fungotification? 20:06:04 boily: only if your kidneys are borked, xerox. xerox, fnord copier, xerox machine ( duplicator that copies graphic matter by the action of a failure continuation 20:06:14 -!- MindlessDrone has quit (Quit: MindlessDrone). 20:06:57 fungot: your insightfulness dazzles me 20:06:57 int-e: fnord!.... u shouldnt help ppl fnord suicide u fnord!. 20:07:42 -!- impomatic has joined. 20:08:04 -!- augur has quit (Remote host closed the connection). 20:08:30 -!- augur has joined. 20:12:54 -!- augur has quit (Ping timeout: 246 seconds). 20:13:08 damn straight, fungot 20:13:08 FireFly: do you think human reasoning is like. 20:13:50 fungot, yes, it's very much like. 20:13:50 int-e: you have a lot of votes in 1996 due to pure cash flow... nobody even seemed to care about support for syntax extensions in 5.1, but hey, i do 20:14:06 fungot: yes, i think facebook has made that much clear 20:14:07 lexande: it's pretty much fnord i'm not an expert audio fnord, that's what it means in her area. and all.) 20:14:14 @tell mrhmouse Well, I think Haskell does <-- nope, the defaults are bignum Integer and floating point Double. although Rational is there too, but doesn't support all the same functions as either of those. 20:14:14 Consider it noted. 20:14:36 > sin pi :: Rational 20:14:38 No instance for (GHC.Float.Floating GHC.Real.Rational) 20:14:38 arising from a us... 20:14:51 oerjan: but I'm here 20:14:55 > toRational $ sin pi 20:14:56 4967757600021511 % 40564819207303340847894502572032 20:15:22 mrhmouse: i don't trust people who have been idle for an hour. 20:16:31 oerjan: which language am I thinking of that defaults to rationals? I'm certain it was at least similar to Haskell in syntax 20:16:33 Just @massage-loud it 20:16:50 @massage 20:16:50 You don't have any messages 20:17:07 -!- yiyus has joined. 20:17:41 @let default (Integer, Rational, Double) -- whistles innocently 20:17:42 Defined. 20:17:48 > 1/2 20:17:49 0.5 20:17:52 darn. 20:18:00 nasty. 20:18:21 oh wait defaults don't get imported, and @lets go into the L.hs module. 20:18:56 @let (test, _) = (1/2, undefined) 20:18:57 Defined. 20:19:01 > test 20:19:03 0.5 20:19:05 wat 20:19:13 :t test 20:19:14 Rational 20:19:17 oh 20:19:37 :t 1/2 20:19:38 Fractional a => a 20:19:40 hm this is probably messing somewhere. 20:20:14 mrhmouse: also, i dunno. 20:20:39 > typeOf test 20:20:40 Double 20:20:52 :t test 20:20:53 Rational 20:20:56 O KAY 20:21:01 cool 20:21:43 > denominator test 20:21:44 2 20:21:54 > sin test 20:21:55 0.479425538604203 20:22:00 strange. 20:23:14 i suppose with > the actual use of test flows back to the inference. 20:23:28 somehow. 20:23:41 AAAAAAAAURGH WHY WON'T YOU GIVE ME A STACK TRACE YOU FSCKING STUPID FRAMEWORK I ALREADY KNOW IT'S A 500 ERROR I WANT DETAAAAAIIILLLLSSS!!!!! 20:23:52 (sorry. ranting against django.) 20:24:03 also lambdabot probably has monomorphism restriction turned off, hm 20:24:31 although i was hoping the tuple would get around that. 20:24:37 -!- cherez has joined. 20:24:57 > let (x, y) = 1 `divMod` 2 in (x :: Int, y :: Integer) 20:24:58 (0,1) 20:25:03 hm nope 20:26:26 > (typeOf test, test) 20:26:28 (Double,0.5) 20:26:57 > (typeOf test, denominator test) 20:26:58 (Double,2) 20:27:07 UM 20:27:15 oh 20:27:20 well if it is polymorphic then ... of course. 20:27:29 but I'm confused as to why 20:27:58 well it's polymorphic given the monomorphism restriction is turned off. 20:28:29 and that means it gets exported polymorphic, and the default declaration in L.hs gets no chance to fire. 20:28:59 -!- Bike has quit (Ping timeout: 272 seconds). 20:29:25 Ugh this is going to drive me mad. I could swear I was reading a language tutorial ages ago that showed "1 / 3" at the prompt and "1 / 3" as the response... 20:29:25 so instead the usual defaulting (same as ghci?) happens for lambdabot expressions. 20:30:18 oh hm... 20:30:31 mrhmouse: why are you looking for this? 20:30:31 @let showTest = show test 20:30:32 Defined. 20:30:36 > showTest 20:30:37 "1 % 2" 20:30:38 -!- metasepia has quit (Ping timeout: 240 seconds). 20:31:17 `relcome cherez 20:31:20 ​cherez: Welcome to the international hub for esoteric programming language design and deployment! For more information, check out our wiki: . (For the other kind of esoterica, try #esoteric on irc.dal.net.) 20:31:20 there you go. since show test has type String, the defaulting of test has to happen even with the monomorphism restriction, since the type cannot escape. 20:31:32 -!- metasepia has joined. 20:31:45 FireFly: Slereah was talking about rationals, and I thought I remembered that Haskell defaulted to Rational. But it isn't Haskell.. but I remember _some_ language did that... 20:31:48 and showTest is inside L.hs so uses its defaulting declaration. 20:32:40 and it was similar in syntax? would SML do that? 20:33:27 -!- Bike has joined. 20:35:07 Oh, thank you! 20:36:00 -!- evalj has joined. 20:36:06 -!- b_jonas has joined. 20:37:58 @let (evil, attempt) = (show attempt, mempty) 20:37:59 .L.hs:156:20: 20:37:59 No instance for (Show a0) arising from a use of `show' 20:37:59 ... 20:38:02 `relcome evalj 20:38:05 ​evalj: Welcome to the international hub for esoteric programming language design and deployment! For more information, check out our wiki: . (For the other kind of esoterica, try #esoteric on irc.dal.net.) 20:38:06 `relcome b_jonas 20:38:09 ​b_jonas: Welcome to the international hub for esoteric programming language design and deployment! For more information, check out our wiki: . (For the other kind of esoterica, try #esoteric on irc.dal.net.) 20:38:16 -!- JesseH has quit (Quit: Leaving). 20:38:16 argh, that's colorful 20:38:18 cherez: what brings you to this channel? 20:38:21 * oerjan whistles innocevilly 20:38:22 can I get that without colors? 20:38:33 oerjan: I like that word 20:38:37 WHAT DO YOU HAVE AGAINST COLORS 20:38:38 `welcome b_jonas 20:38:38 `welcome b_jonas 20:38:39 b_jonas: you may, but it's untraditional. 20:38:40 b_jonas: Welcome to the international hub for esoteric programming language design and deployment! For more information, check out our wiki: . (For the other kind of esoterica, try #esoteric on irc.dal.net.) 20:38:40 b_jonas: Welcome to the international hub for esoteric programming language design and deployment! For more information, check out our wiki: . (For the other kind of esoterica, try #esoteric on irc.dal.net.) 20:38:42 darn. 20:38:46 thanks 20:38:56 also, huh, didn't expect to see b_jonas over here 20:38:56 I think you're sufficiently `welcome'd now 20:39:15 ais523: do you think i was trigger happy in blocking PcCleaner 20:39:19 but then, I don't generally expect to see anyone happy over here 20:39:31 oerjan: I was scouring the relevant logs to try to find something to block them for :) 20:39:33 ais523: I AM HAPPY, FUNGOT IT! 20:39:34 boily: Nothing in particular. Old friends with pikhq and thought it might be fun to lurk here a bit. 20:39:42 but I'd have allowed account creation 20:40:26 if you're blocking someone on the basis of username, you should give them a chance to change it 20:40:32 ais523: i mean it seems to be named after what seems to be a scam company at best. 20:40:35 yeah 20:40:44 the name's free on Freenode, btw? anyone want it? 20:40:53 heh 20:40:58 err, s/\?/;/ 20:44:08 -!- JoeyEsper has joined. 20:44:30 hello 20:44:30 oi 20:44:56 -!- JoeyEsper has left. 20:45:09 but, but... I was typing a nice `relcome... 20:46:14 it's one of those weird things about IRC, people who say hello, then get annoyed at the lack of response and leave before you have a chance to type a response 20:46:55 -!- ais523 has quit. 20:49:41 -!- Sprocklem has quit (Ping timeout: 252 seconds). 20:56:59 oerjan: hmm, mueval turns off the monomorphism restriction without being asked to. 20:57:00 -!- Bike has quit (Ping timeout: 246 seconds). 20:59:12 -!- augur has joined. 21:02:01 int-e: I guess on this channel an evaluator bot should use the craziest extensions by default, such as not only no monomorphism restrictions, but also circular types, undecidable instances, etc 21:02:16 definitely circular types 21:02:30 b_jonas: yeah but the primary channel it's for is #haskell 21:02:33 * boily points to metasepia “Go nuts with it! But be careful with the error messages” 21:02:42 int-e: sure, but use channel-dependent options 21:02:47 @eval iterate show 21:02:51 @eval fix show 21:02:55 um 21:02:57 @help eval 21:02:57 eval. Do nothing (perversely) 21:03:09 @help run 21:03:09 run . You have Haskell, 3 seconds and no IO. Go nuts! 21:03:18 > "or use this" 21:03:19 "or use this" 21:03:19 @run fix show 21:03:20 "\"\\\"\\\\\\\"\\\\\\\\\\\\\\\"\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\"\\\\\\\\\\\\... 21:03:39 @run fix print 21:03:40 21:03:47 @type fix print 21:03:48 ~eval fix show 21:03:48 IO () 21:03:48 "\"\\\"\\\\\\\"\\\\\\\\\\\\\\\"\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\"\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\"\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\"\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\ 21:04:31 -!- Bike has joined. 21:05:04 @run print print 21:05:05 21:05:21 @run let { x = print; } in x 21:05:22 <() -> IO ()> 21:05:40 > fix error 21:05:41 "*Exception: *Exception: *Exception: *Exception: *Exception: *Exception: *E... 21:06:56 ] ,29$'*Exception: ' 21:06:57 b_jonas: *Exception: *Exception: *Exce 21:07:08 ] ,29$,:'*Exception: ' 21:07:08 b_jonas: *Exception: *Exception: *Exception: *Exception: *Exception: *Exception: *Exception: *Exception: *Exception: *Exception: *Exception: *Exception: *Exception: *Exception: *Exception: *Exception: *Exception: *Exception: *Exception: *Exception: *Exception: *Exception: *Exception: *Exception: *Exception: *Exception: *Exception: *Exception: *Exception: 21:10:13 @let evil = mempty 21:10:14 .L.hs:156:8: 21:10:14 No instance for (Monoid a0) arising from a use of `mempty'... 21:10:46 interesting. @let seems to use the monomorphism restriction. 21:11:19 when checking if the addition is sane. 21:12:12 @run let { x = show; } in x () ++ x [] 21:12:13 "()[]" 21:14:09 oerjan: it uses some ghc invocation for type-checking L.hs, but mueval for the final evaluation. (it seems that mueval *also* does not explicitly turn off the monomorphism restriction ... next stop will be hint ...) 21:14:43 b_jonas: i don't recall haskell having any extension for circular types. 21:16:57 ~eval mempty 21:16:58 Error (1): No instance for (Data.Monoid.Monoid a0) arising from a use of `e_1' 21:16:58 The type variable `a0' is ambiguous 21:16:58 Possible fix: add a type signature that fixes these type variable(s) 21:16:58 Note: there are several potential instances: 21:16:58 instance Data.Monoid.Monoid () -- Defined in `base:Data.Monoid' 21:16:58 instance (Data.Monoid.Monoid a, Data.Monoid.Monoid b) => 21:16:58 Data.Monoid.Monoid (a, b) 21:16:59 -- Defined in `base:Data.Monoid' 21:16:59 instance (Data.Monoid.Monoid a, Data.Monoid.Monoid b, 21:17:00 Data.Monoid.Monoid c) => 21:17:00 Data.Monoid.Monoid (a, b, c) 21:17:01 -- Defined in `base:Data.Monoid' 21:17:01 ...plus 18 othersNo instance for (GHC.Show.Show a0) 21:17:02 arising from a use of `M175202735352782162727845.show_M175202735352782162727845' 21:17:07 :D 21:17:15 type families can be abused for that to some extent ... with horrible, horrible type errors when things go wrong. 21:17:32 metasepiaaaaaa 21:17:52 la la la la la ♪ 21:19:09 boily: i think you mean SPAM SPAM WONDERFUL SPAM 21:20:45 plan for the holidays: eat food. eat food. revamp metasepia. eat food. eat food. enjoy saner error messages! 21:25:20 oerjan,boily: you might like http://int-e.eu/~bf3/haddock/typeeval-0.0/ 21:26:36 int-e: I might not understand it. 21:27:27 any Haskell programmer will tell you that Node 42 [False, True] and Node 42 [Node 23 [], Leaf 0] should not type-check at the same time. 21:27:34 more like typeevil 21:27:48 oerjan: really? let me check the ghc manual. I really thought there was one, only nobody uses it because it masks too much errors. 21:28:03 (And I agree. I wrote that ... code, and I never used it after encountering type errors reminiscent of C++.) 21:28:10 and because if you really want a circular type you can get one by that higher order type trick 21:29:56 hmm, did I just imagine that there was such an option in ghc? 21:30:29 b_jonas: generally you use newtypes and they're optimized away. 21:30:41 also, ocaml has one, i used it once. 21:31:07 (to implement unlambda) 21:32:19 @type let { x = [x]; } in x 21:32:20 Occurs check: cannot construct the infinite type: t0 = [t0] 21:32:20 In the expression: x 21:32:20 In the expression: [x] 21:33:10 * boily is tempted to run that in ~eval, but he spammed once today so he'll be wise and not do it. 21:33:38 int-e: my Haskell-fu is diminishing. too much Python for the past few months. 21:34:49 strange, it looks like ghc doesn't have such an extension 21:35:14 but why? I mean, it seems like something those people who develop some of the other crazy type system extensions would want to try 21:35:29 can it not be made to a consistent type system extension?\ 21:36:13 that is, an extension such that if an occurs check finds a cycle in type constraints, it just creates a cyclic type instead of an error 21:36:30 maybe it doesn't play well with higher order types or something? 21:36:30 there's no big pressure (newtype Mu f = Mu (f (Mu f)) gets the desired effect with some extra source code) 21:36:49 int-e: sure, but you have seen some of the other type system extensions people have added 21:36:57 I'd have thought they'd try this too 21:37:11 int-e: imo call that type Fix 21:37:12 * int-e shrugs 21:37:27 newtype Fix f = Fix { runFix :: f (Fix f) } 21:37:37 newtype Mu f = Mu { runMu :: forall r. (f r -> r) -> r } 21:37:42 it's been done before -> less research interest. 21:37:45 data Nu f = forall x. Nu x (x -> f x) 21:37:59 opaque greek is the future, shachaf 21:38:01 and also the past 21:38:31 Bike: what, that's not enough opacity for you?? 21:38:35 fix f = f (fix f) 21:38:36 and from a practical perspective, I think having let x = [x] *not* typecheck is a great boon for sanity. 21:38:39 Fix f = f (Fix f) 21:38:56 Oh, you're talking about equirecursive types. 21:39:04 Yes, there are various good reasons not to have them. 21:39:07 I have to assume someone tried but it turned out if you combine it with some other language features you lose the guarantee of the compilation terminating or you can prove Void or something crazy like that so they didn't add them 21:39:15 shachaf: I know why we don't have them by default: 21:39:21 they'd mask too many errors 21:39:28 user errors that is 21:39:32 ocaml supports them, I think. 21:39:51 but I was wondering why we don't have it as a language extension 21:39:55 I see 21:40:13 otoh, as far as I know, ocaml frowns on data Tree a = Level a | Nest (Tree (a,a)) 21:40:45 int-e: that's non-regular types or whatever that's called, right? 21:40:50 has some fancy name 21:41:15 "non-regular" makes sense, but I don't know. 21:41:34 I think that feature had two names, and non-regular may or may not have been one of them 21:43:05 polymorphic recursion is used for the functions operating on such things, at least. 21:47:18 If I remember correctly, polymorphic recursion is the issue. You might even be able to define the type itself? 21:47:38 shachaf: what? define what type where? 21:47:49 int-e's non-regular type. 21:48:04 Not too useful without functions to operate on it. 21:48:42 I liked Conal's talk at http://conal.net/talks/understanding-parallel-scan.pdf 21:48:44 but you mean in ocaml? 21:48:52 i think shachaf means in ocaml, which doesn't have polymorphic recursion. 21:49:13 and so even if you could define the type, you couldn't use it for anything. 21:49:30 right 21:50:11 or maybe you could only use it non-parametrically, limited to the first compile-time-finite many depths 21:50:23 which doesn't buy you anything over just separate type 21:50:26 separate types 21:50:45 plus a class for them 21:50:52 similarly to what would happen in C++ 21:51:12 you could define a type that looks like this, but you can only ever instantiate finitely many in a program 21:51:23 if you try unlimited recursion, the compiler will give up 21:53:43 now I'm curious, can ocaml do the higher order type quantification trick haskell's ST does? 21:56:54 -!- boily has quit (Quit: Gàààààààààrgh). 21:56:57 -!- metasepia has quit (Remote host closed the connection). 21:58:17 I thought at one point whether C++ can do it, and decided it can't, because even though it can do higher order quantification, sort of, it can't prove things about it, so can't enforce the kind of restriction ST depends on 22:07:23 the term is "higher rank" btw. dunno about ocaml, but doubt it unless they've added it after my time. 22:08:35 oerjan: when was your time 22:09:05 I see 22:11:39 today in confusing terminology: insect flight involves 'synchronous' and 'asynchronous' muscle, which are alllllmost analogous to programming 22:12:55 shachaf: 'bout 2002 or so. 22:13:00 rip 22:13:13 oerjan 1975-2002 22:13:26 (is 1975 right) 22:13:43 1970 22:13:47 oh 22:13:49 close enough 22:14:03 what's it like outliving the soviet union 22:14:23 oerjan 1917-2002 22:14:35 >_> 22:14:41 I didn't even outlive Yugoslavia 22:18:57 Hmmm... Notepad++ handles a 2.6 million line 170 MB text file without any problems. Windows Notepad and Programmers Notepad both stopped responding. 22:21:51 windows notepad can't really handle anything bigger than like 10k lines in my experience 22:22:45 hum, curry's original paper defines \lambda^n ...vars... for an n-ary function, weird 22:25:11 -!- mrhmouse has quit (Quit: Leaving.). 22:25:26 i assume they hadn't invented schönfinkeling yet 22:26:01 "they" = schönfinkel? or did someone else invent schönfinkeling? 22:26:23 we assume not. 22:26:29 http://www.urbandictionary.com/define.php?term=schonfinkeling 22:26:43 i noticed that in the google hits. 22:27:06 ach, du finkelst so schön 22:28:14 oh i can downvote it without registering 22:28:40 I'm scared by sql triggers. they let you write almost arbitrary programs in sql, but only in a very ugly way 22:28:44 "Finally, K converts a constant into a function with a constant value, or a function into one with an additional, fictitious variable." 22:29:39 b_jonas: so you are not trigger happy. 22:30:21 they look like something that's very easy to abuse 22:30:34 you start with some simple triggers and you end up in an unmaintenable mess 22:31:15 hmm, I think I've forgotten what schönfinkeling is 22:31:20 in sqlite3, you can have views with instead of insert triggers that basically simulate an arbitrary function 22:31:31 backwards currying, i think? 22:31:46 not quite arbitrary, but very close 22:31:58 b_jonas: so like this basically? http://www.youtube.com/watch?v=EKajmVgaOEM 22:32:19 yeah 22:32:31 Bike: it's just currying, except with the correct inventor name. 22:32:44 oh. sensible. 22:32:55 for what it's worth curry mentioned schofinkel a lot. 22:32:56 of course the sqlite3 language can be scary even without triggers: 22:33:06 there's no let statement, so if you need one you have to write a nested select 22:33:18 well, you don't have to 22:33:21 "It was originated by Moses Schönfinkel and later worked out by Haskell Curry." says wp 22:33:23 credits him with BCWK and SKI 22:33:39 the normal solution is to do the variable copying from outside sql language, which sqlite3 totally allows to do easily 22:34:02 you can copy results of a statement to the bindings of another statement without examining them 22:34:13 and with proving SK is complete or whatever you call it. 22:34:42 Bike: really? I thought Church proved that 22:35:03 kind of assumed 22:36:13 "Schönfinkel discovered that all combinators can be defined in terms of two special ones, S and K," 22:36:47 what did Church prove then? 22:36:53 oerjan: Ok, it's hint's fault. When initialising, it queries the enabled extensions from ghc. Then it's translating MonomorphismRestriction to NoMonomorphismRestriction internally, but without inverting the current state of the extension. 22:38:50 as for S and K, I recently bought Smullyan's mockingbird book because they just translated it 22:38:56 b_jonas: that it's inconsistent, how to restrict it so that it's consistent, how to avoid variables entirely, bla bla bla 22:39:16 -!- nisstyre has joined. 22:39:24 Bike: but isn't avoiding variables the whole point of S K ? 22:39:31 or did he find some other basis instead? 22:39:52 how to define things without reference to a lambda calculus meta formalism, i mean, i think 22:40:56 do you mean construct them as functions or something like that? 22:42:33 construct a formalism of combinators with no reference to functions 22:42:43 int-e: MADNESS 22:43:01 huh? but it's exactly the lambda symbols that doesn't reference functions 22:43:06 only syntax transform rules 22:43:31 well, the S K or other combinator basis can also do that 22:43:46 it's 'the combinatory basis of logic' or something if you want to read it yourself 22:45:02 I see 22:45:27 oerjan: there's even a bug report about it: http://darcsden.com/jcpetruzza/hint/issue/1 (different extension but same idea: hint only has NoImplicityPrelude) 22:48:43 is it just me or is darcsden kind of ugly. 22:49:02 I don't know about you but darcsden *is* ugly. 22:54:13 > test 22:54:15 1 % 2 22:54:57 but now that that's fixed I better add a sane default directive there ... 22:55:20 um what's wrong with the default one. 22:55:21 more about sqlite3, table constraints can be arbitrary expressions, and those expressions can call user-defined functions, and I think those functions can modify the database 22:55:42 but now they added partial indices, but the conditions for partial indices can't call user-defined functions 22:55:45 oerjan: nothing. I'm adding default (Integer,Double) so your @let will hopefully stop working :) 22:55:55 the inconsistency seems a bit strange 22:56:06 > test 22:56:08 0.5 22:56:10 but I might be misunderstanding something here 22:56:13 int-e: ((),Integer,Double) is what ghci uses. 22:56:27 @let default (Integer, Rational, Double) 22:56:28 .L.hs:170:1: 22:56:28 Multiple default declarations 22:56:28 here was another defa... 22:56:49 > read "()" 22:56:50 () 22:57:21 also, that default only applies within the L module, iiuc 22:57:46 > test 22:57:47 0.5 22:57:56 oerjan: yes, I added () there, too. thanks for the hint :) 22:58:21 obviously those constraints can not only modify the database but also have random return value, so the same contraints are sometimes true and sometimes false 22:58:51 which would be wierd for both constraints and partial indices 23:01:22 -!- nisstyre has quit (Quit: Leaving). 23:01:41 > let (t,1) = (show,1) in t 1 ++ t () 23:01:42 No instance for (GHC.Num.Num ()) arising from the literal `1' 23:01:43 Possible fix... 23:02:36 (MonoPatBinds was another one that went the wrong way ... hmm ... but I didn't test it right.) 23:06:46 > let t = show in t 1 ++ t () 23:06:47 No instance for (GHC.Num.Num ()) arising from the literal `1' 23:06:47 Possible fix... 23:07:13 > let t x = show x in t 1 ++ t () 23:07:14 "1()" 23:07:38 now start waiting for the barrage of complaints hth 23:08:32 hmm. did that really change? *goes to test* 23:12:39 Yes. Hmm. 23:15:07 -!- nooodl_ has changed nick to nooodl. 23:15:17 Ah, NoMonomorphismRestriction implies NoMonoLocalBinds, obviously. 23:15:58 -!- Bike has quit (Ping timeout: 245 seconds). 23:21:44 meh. I'm being stupid. 23:21:50 -!- S1 has joined. 23:24:25 -!- evalj has quit (Remote host closed the connection). 23:25:25 -!- lambdabot has quit (Quit: wee! restarting!). 23:26:51 it's a bit annoying to have to restart lambdabot just because of an extra flag. oh well :) 23:28:21 -!- carado has quit (Ping timeout: 252 seconds). 23:29:20 -!- Phantom_Hoover has joined. 23:29:27 -!- lambdabot has joined. 23:29:29 > let t = show in t 1 ++ t () 23:29:35 "1()" 23:29:57 oerjan: thanks :) 23:30:33 -!- Bike has joined. 23:30:46 are we still complex numbers 23:30:47 you're welcome 23:31:11 oh also meanwhile: http://blog.wolfram.com/2013/11/21/putting-the-wolfram-language-and-mathematica-on-every-raspberry-pi/ 23:31:23 let us all point & laugh; cry 23:31:48 oerjan: haha, darcshub is buggy, too: http://darcsden.com/jcpetruzza/hint/patches 23:37:07 -!- augur has quit (Remote host closed the connection). 23:37:43 -!- augur has joined. 23:41:57 -!- augur has quit (Ping timeout: 248 seconds). 2013-11-22: 00:05:42 -!- augur has joined. 00:07:09 -!- nooodl has quit (Quit: Ik ga weg). 00:08:19 -!- oerjan has quit (Quit: leaving). 00:12:52 -!- augur has quit (Read error: Connection reset by peer). 00:13:17 -!- augur has joined. 00:14:45 -!- augur has quit (Read error: Connection reset by peer). 00:14:45 -!- augur_ has joined. 00:15:29 -!- augur has joined. 00:18:48 -!- heroux has quit (Ping timeout: 240 seconds). 00:19:34 -!- augur_ has quit (Ping timeout: 265 seconds). 00:19:44 -!- heroux has joined. 00:26:35 -!- S1 has left. 00:31:10 -!- nisstyre has joined. 00:38:43 Someone in another channel fed KJV and SICP to a markov bot 00:38:53 "And Jonathan caused David to be different, such as new-withdraw, we will always be considered `unreal' in five years. See BITTY BOX and TOY. GIGO (gie'goh) [acronym] garbage in, garbage out. Usually said of problems spawns new languages." 00:45:11 -!- typeclassy has joined. 00:53:04 that's wonderful 00:53:46 do you ever look at a biography and realize they died young and feel bad 00:59:28 -!- Phantom_Hoover has quit (Remote host closed the connection). 01:01:17 ^style 01:01:17 Available: agora alice c64 ct darwin discworld enron europarl ff7 fisher fungot homestuck ic irc* iwcs jargon lovecraft nethack pa qwantz sms speeches ss wp youtube 01:01:24 ^style iwcs 01:01:24 Selected style: iwcs (Irregular Webcomic scripts) 01:01:31 fungot, what are you doing 01:01:31 Taneb: you are not evil, terrible things are happening. this time you will not. hmm, no. j. k. rowling, who had given the thrashing we saw a webcomic with a missing. 01:01:47 fungot, I'm not evil? I think my userpage says otherwise 01:01:47 Taneb: but, but... that's not a fish. it's a lump of rock! we didn't give any thought the guys at nasa has fast-tracked a prototype deep has held out well on the bright side, the snakes, and 9... 01:02:54 ^style discworld 01:02:55 Selected style: discworld (a subset of Terry Pratchett's Discworld books) 01:02:58 fungot, symbols, whose values are looked up in the court of the LORD's glory. 01:02:59 Taneb: " they're just fnord,' the girl went on. ' it'd take all day.' 01:07:23 fizzie: when you establish the CS books/holy text style, i can hook you up with a /lot/ of the latter 01:17:46 -!- Sgeo has joined. 01:20:18 I have the opportunity to give a CS-related talk at some point in the near-ish future 01:21:30 I'm somewhat tempted but at a loss for the topic 01:22:12 the fast-growing hierarchy: applications to haskell-based microcontrollers 01:24:04 I was thinking either category theory or something about esolangs 01:24:13 -!- yorick has quit (Remote host closed the connection). 01:24:21 (there's pretty much no restrictions and it's not very formal or anything) 01:25:51 "Esolangs: programming language design as art?" 01:26:17 that sounds way worse than mine imo 01:26:32 Yeah but I don't think I'm sufficiently cool to do yours 01:27:14 sure y'are 01:29:21 -!- adu has joined. 01:51:51 -!- Bike has quit (Ping timeout: 240 seconds). 01:52:05 fuckin assembly 01:52:07 this is hurting my head 01:52:12 probably because i don't know anything about it :P 01:52:40 if i have "mov rax, cs:qword_someshit" and then "call qword ptr [rax+140h]" 01:52:41 -!- cherez has quit (Quit: Leaving.). 01:53:03 what is it doing? calling the code pointed to by memory address rax + 140h i assume 01:53:13 but cs:qword_etc is 0 01:53:23 it's calling the pointer at [rax+140h] 01:53:40 so it loads the 8 bytes at [rax+140h] into temporary space, and then calls /that/, I think. 01:53:43 so rax is 0 and it's just adding 0 for no good reason? 01:54:00 are you like, looking at compiled object code? 01:54:11 disassembled bios code 01:54:16 my fuckin laptop... 01:54:21 i went to put a wireless ac card in it 01:54:28 and its like NO I HAVE A WHITELIST U CANT USE WIRELESS CARDS LOLOL 01:54:37 so i'm to the part where i hack it to avoid that check :P 01:54:46 but i can't find where to do it 01:54:46 lol 01:55:05 the "mov rax, cs:qword_...." might be a thing to load like, the base of the code segment or something, for PIC-ish addressing? 01:55:34 i don't know what that means, but i'm about to check out qword_180001ac8 + 140 and see if anything is there :P 01:56:13 okay, that's past the end of the code lol 01:56:20 but 01:56:29 the program that extracted this module was fucked up anyway 01:56:36 it had like 27 bytes of garbage before the MZ 01:56:43 maybe an equal amount got cut off the end? 01:57:57 -!- adu has quit (Quit: adu). 02:00:14 anyway, nope, didn't think so 02:00:31 there's like a bunch of 0 bytes and various places of the code load them in 02:00:46 i guess that's just how it is... but if so i have no idea where it's calling :| 02:07:57 appears to maybe be an external call 02:08:04 to some other part of the bios 02:08:19 ah 02:08:30 so something would load the correct addresses there, they wouldn't be 0 at runtime obviously :P 02:08:48 and it's a qword which means it could be a long frickin' way away, so probabyl irrelevant for my purposes 02:11:16 -!- Taneb has quit (Quit: Leaving). 02:22:12 -!- adu has joined. 02:28:32 -!- typeclassy has quit (Ping timeout: 240 seconds). 02:57:14 -!- adu has quit (Quit: adu). 02:59:16 -!- Bike has joined. 03:01:40 -!- adu has joined. 03:02:25 -!- jconn has joined. 03:06:47 -!- typeclassy has joined. 03:12:56 -!- adu has quit (Quit: adu). 03:23:52 -!- adu has joined. 03:32:08 hi adu 03:32:19 hi 03:32:29 I didn't realize I had IRC open :) 03:32:30 what do? 03:32:49 can you repeat that in the form of a question? 03:52:11 -!- CADD has joined. 04:07:20 -!- nisstyre has quit (Quit: Leaving). 04:34:38 -!- adu has quit (Quit: adu). 04:43:53 -!- adu has joined. 04:51:07 -!- typeclassy has quit (Ping timeout: 246 seconds). 04:53:26 -!- doesthiswork has joined. 05:36:42 -!- nisstyre has joined. 05:45:09 -!- doesthiswork has quit (Quit: Leaving.). 06:09:57 -!- nisstyre has quit (Ping timeout: 252 seconds). 06:28:28 -!- adu has quit (Quit: adu). 06:48:15 -!- tangentstorm has joined. 07:25:05 Hi tangentstorm :-) 07:33:53 Bike: I still have the RFC style on the to-do list. 07:34:31 kay 07:34:41 are RFC holy 07:34:54 Also, won't people be offended if I put religious texts in? 07:35:50 not if they're all dead religions, and that's where i come in 07:36:42 TIL: freenode channel guidelines imply human beings have been "designed". 07:36:54 [[ Speakers in physical proximity with each other communicate quite a bit of emotional context via this extra bandwidth. This context enables them to avoid misjudging the intent of their conversational partners. It also functions as an unconscious negative feedback mechanism to reduce the incidence of emotional "firestorms" which tend to disrupt the efficient flow of conversation. Human beings ... 07:37:00 ... look for this feedback and indeed they may be designed to require it. ]] 07:37:07 -!- FreeFull has quit. 07:37:17 I've always found the freenode pseudo-psychology material amusing. 07:37:46 (Have you polished your catalyst skills today?) 07:37:55 amusement is about the most positive emotion i can muster in response to it 07:38:29 -!- CADD has quit (Quit: leaving). 07:40:30 I turned off my computer at home yesterday night since it wasn't really doing anything in particular and I would have had to reboot anyway, but now it's not responding to WOL packets. :/ 07:46:24 I guess the lack of psychic communication from fungot may lead to people misreading its intent and e.g. getting offended 07:46:24 olsner: " no," said teppic. it was the rare kind of madness caused by being yourself for so long. 07:46:59 fungot: You certainly have your fair share of that. 07:46:59 fizzie: ' commander vimes is keen on reports.' albert coughed nervously. 07:50:01 -!- carado has joined. 07:50:22 fungot: how long have you been yourself anyway? 07:50:22 olsner: ' don't you dare patronize me!" 07:51:00 hey impomatic :) just heard about this channel, so i thought i'd come lurk :) 07:59:18 -!- carado has quit (Ping timeout: 252 seconds). 08:03:28 -!- yiyus has quit (Ping timeout: 245 seconds). 08:45:28 -!- carado has joined. 08:47:11 -!- CADD has joined. 08:50:45 -!- augur has quit (Read error: Connection reset by peer). 08:50:50 -!- augur_ has joined. 08:59:05 -!- CADD has quit (Quit: leaving). 09:03:02 -!- carado has quit (Remote host closed the connection). 09:40:31 -!- tangentstorm has quit (Quit: WeeChat 0.3.2). 09:50:55 -!- olsner has quit (Quit: Leaving). 10:09:37 -!- drlemon has quit (Read error: Connection reset by peer). 10:21:44 -!- dchevak has joined. 10:25:36 -!- dchevak has left. 10:37:13 -!- Taneb has joined. 10:42:44 -!- Phantom_Hoover has joined. 11:09:33 -!- oerjan has joined. 11:36:37 -!- Phantom_Hoover has quit (Ping timeout: 248 seconds). 11:50:00 -!- MindlessDrone has joined. 12:22:04 -!- yorick has joined. 12:32:11 -!- Taneb has quit (Quit: Leaving). 12:43:31 -!- Sgeo has quit (Read error: Connection reset by peer). 13:06:19 -!- boily has joined. 13:10:33 -!- boily has quit (Client Quit). 13:10:36 -!- carado has joined. 13:11:21 -!- jix has quit (Remote host closed the connection). 13:13:22 -!- jix has joined. 13:15:36 -!- boily has joined. 13:15:43 -!- metasepia has joined. 14:14:39 -!- variable has changed nick to trout. 14:17:25 -!- oerjan has set topic: The channel of the chimæric hellos | The most corum, clargoint chait you could ever loofefl your slance in. | Magnus♔ | Koirammekokaan ei lennä? :( | https://dl.dropboxusercontent.com/u/2023808/wisdom.pdf | logs: http://codu.org/logs/_esoteric/ or http://tunes.org/~nef/logs/esoteric/. 14:21:50 good U+2654 morning! 14:27:48 "-acoustic-mesh -- Preserve word-level acoustic information (times, scores, and pronunciations) in sausages, encoded as described in wlat-format(5)." 14:27:52 I like the terminology. 14:29:25 «acoustic sausages à la provençale, with an entrée of preserved meshes» 14:33:22 "-write-mesh-dir dir -- Similar, but write sausages to files in dir named after the utterance IDs." 14:33:36 "-init-mesh file -- Initialize the word confusion network by reading an existing sausage from file. This effectively aligns the lattice being processed to the existing sausage." 14:34:09 fascinating... and delicious. 14:34:45 the sausages are egregious. 14:43:55 -!- hogeyui has quit (Ping timeout: 272 seconds). 14:46:09 -!- Taneb has joined. 14:46:35 hellogeyui. Tanelle. 14:47:31 bonjoily 14:47:59 Also I now own nerf guns help 14:53:36 -!- mrhmouse has joined. 14:58:47 -!- fergusq has joined. 14:59:13 -!- S1 has joined. 14:59:24 Some of you programming in deadfish? 15:00:41 -!- fergusq has quit (Client Quit). 15:03:36 -!- Rylee has joined. 15:03:52 -!- Rylee has left ("WeeChat 0.4.3-dev"). 15:07:44 darn. too missed `relcomopprtunities... 15:07:52 -!- hogeyui has joined. 15:07:53 Taneb: what kind of nerf gun? 15:08:29 Elite Strongarm times 2 15:08:36 boily: you `relcomissed them 15:09:59 https://www.ruby-lang.org/en/news/2013/11/22/heap-overflow-in-floating-point-parsing-cve-2013-4164/ 15:10:03 heap overflow 15:10:04 in floating point parsing 15:10:07 in 2013 15:11:15 it's all there in the url people 15:11:19 -!- nooodl has joined. 15:13:36 -!- Taneb has changed nick to Ngevd. 15:13:45 heloooooooodl. 15:14:05 -!- Ngevd has changed nick to Taneb. 15:15:42 hoily~ 15:17:45 in other news, i wrote a program that self-modifies its machine code by calling read() 15:18:22 like, it reads into a 'buffer' in the middle of the program? 15:18:40 yes 15:18:45 hells yea 15:19:24 scary. 15:19:28 -!- oerjan has quit (Quit: leaving). 15:22:37 and that program is used to control medical hardware, I hope? 15:22:54 -!- sebbu has quit (Ping timeout: 265 seconds). 15:25:39 -!- S1 has changed nick to S1_afk. 15:30:39 -!- sebbu has joined. 15:31:17 -!- sebbu has quit (Changing host). 15:31:17 -!- sebbu has joined. 15:32:20 yes 15:32:27 a nuclear-powered flying hospital 15:34:43 kmc: do you at least use a lock so another thread can't execute the function while you're modifying it? 15:37:38 i don't have threads 15:37:42 also i don't have functions 15:37:57 or registers (except as necessary to call read()) 15:38:29 huh what? 15:38:50 how does that work 15:38:58 stay tuned for an article about it 15:39:39 do you not even have other processes sharing that memory map executing simultanously for which you need an ipc lock? 15:40:57 no 15:41:04 i guess it would be more eso if i did 15:41:10 is this the kind of wasteful last century program that has a complete copy of its code allocated for just a single thread of execution? does your wood-powered hospital submarine waste its oil like it was last century too? 15:44:27 let's go with 'yes' 15:57:13 Guys 15:57:28 If I were to try to find some PC speaker music from some old game 15:57:54 Can I do it by just looking at the binary for the opcodes of "send shit to the PC speaker" 15:58:07 And see what happens 15:59:17 (Or maybe with a disassembler to be more readable) 16:01:58 there are no such opcodes. the pc speaker is driven by a programmable timer, which can be programmed via a couple of IO ports ... http://wiki.osdev.org/PC_Speaker may be useful 16:02:30 I am aware, yes 16:02:59 http://www.intel-assembler.it/portale/5/make-sound-from-the-speaker-in-assembly/8255-8255-8284-asm-program-example.asp 16:03:07 This is a pretty good description of it 16:04:52 Still I assume you cound find in a binary the "send to port 61H" parts 16:04:59 And maybe find the actual music from there 16:05:16 (though I guess it might be a procedure making it a bit more complicated) 16:05:35 -!- adu has joined. 16:06:25 dosbox has some debugging features 16:07:11 -!- adu has quit (Client Quit). 16:10:06 -!- S1_afk has changed nick to S1. 16:11:36 boily: I made you a thing 16:11:57 mrhmouse: what is this mysterious thing you made at me? 16:12:02 `ello boily 16:12:04 belloily 16:12:15 oh. oooooooh. 16:12:24 * boily grins :D 16:15:37 `ello mrhmouse 16:15:39 mrhmellouse 16:19:50 `ello kmc 16:19:52 kmcello 16:21:03 it has a few basic situations that it checks for, and then it falls back to "Hello, !". 16:22:16 Although maybe I should have it output similarly to `thanks. "Hello, boily. belloily." 16:47:47 but if you thankify the ello, it'll remove its charm! 16:48:38 <`^_^v> is there any list of "famous" PL problems like expression, samefringe, etc 16:49:03 rosettacode? PL shootout on alioth? 16:51:25 <`^_^v> i feel like rosetta code is mostly algorithms that can have different implementations based on the language, but don't really highlight the difficulty of a problem resulting from the languages design decisions, if that makes sense 16:56:47 `ello nooodl 16:56:49 nellooodl 16:57:19 `run cat bin/ello 16:57:21 ​#!/usr/bin/env node \ (function() { \ var consonant_then_o, ends_with_consonant, ends_with_e, name, starts_with_o; \ \ name = process.argv[2]; \ \ if (!(name != null ? name.length : void 0)) { \ console.log('Usage: ello '); \ process.exit(); \ } \ \ ends_with_e = /(.*)(e)$/i; \ \ consonant_then_o = /(.*)([bcdfghjklm 16:57:45 yikes javascript 16:58:24 esoteric ;) 16:59:50 -!- Phantom_Hoover has joined. 17:08:56 -!- S1 has changed nick to S1_afk. 17:13:11 nooodl: what's wrong with JavaScript? :P 17:20:47 Salaam aleikum 17:20:53 Woops 17:20:55 <`^_^v> prototypal inheritance is so 1990s 17:20:55 Wrong window 17:33:14 so meanwhile the first draft of the wolfram language documentation is up: http://reference.wolfram.com/language/ 17:33:19 it's mathematica 17:33:25 like it's literally mathematica 17:34:57 -!- S1_afk has changed nick to S1. 17:41:52 Phantom_Hoover, it's mathematica but named after Wolfram 17:42:26 he makes sure to call it Wolfram Mathematica when he can get away with it 17:42:53 Maybe he was saying "Wolfram/Mathematica" 17:42:59 like some say "GNU/Linux" 17:43:09 http://reference.wolfram.com/language/guide/WebOperations.html 17:43:22 whoops, looks like something got past the search-and-replace 17:43:24 (I kind of want a linux distro with no GNU components, just to piss off Stallman) 17:43:44 those exist i think? but probably not on the desktp 17:43:46 *deskto 17:43:48 *desktop 17:44:31 I meant a desktop one, yeah 17:46:04 -!- FreeFull has joined. 17:48:10 Taneb: that would be difficult 17:52:40 what you should do is have every contributor listed in the name rather than just GNU 17:55:04 when it's cold and rainy outside, nothing beats a good plate of random steamy italian food. 18:02:36 -!- Bike has quit (Ping timeout: 246 seconds). 18:10:08 -!- Bike has joined. 18:11:40 -!- Taneb has quit (Ping timeout: 245 seconds). 18:18:06 -!- Taneb has joined. 18:25:21 -!- Bike has quit (Ping timeout: 241 seconds). 18:26:48 sudden random interrogation: what happened to jsvine and his II? 18:29:13 ¿jsvine? 18:29:30 ¿II? 18:29:37 nobody knows 18:29:42 `seen jsvine 18:29:47 not lately; try `seen jsvine ever 18:29:54 `seen jsvine ever 18:30:01 2013-08-05 21:08:56: Bike: you might like this: https://github.com/dwillis/post_haste 18:30:49 i wonder if bike liked it 18:31:05 -!- Bike has joined. 18:31:55 -!- Taneb has quit (Ping timeout: 272 seconds). 18:39:55 mrhmouse: Infamous Interview. 18:40:14 Bike, 2013-08-05 21:08:56: Bike: you might like this: https://github.com/dwillis/post_haste 18:40:14 i wonder if bike liked it 18:41:10 i don't remember august 18:43:28 August was like forever ago 18:43:34 even HackEgo seems to think so 18:45:03 fungot: how many evers is August for you? 18:45:03 boily: ' not your fault you've moved into a city full of giants,' said detritus, stoically. ' i see here where it contains a number of surprised animals stared down at him. 18:45:34 fungot: pratchett style today, eh? and indeed, it ain't my problem. besides, giants live Downtown, and I don't. 18:45:35 boily: " i suppose it makes sense anyway. there's only so much more clearly... wondering about going in and out of the window by their ankles 18:47:11 boring fungot style imo 18:47:11 FireFly: oats gave up and made a noise like a mouse blowing fnord, and eight, and a couple of ugly things were coiled up in the darkness, found the greasy pilings of a jetty, and clung to them, we're something that might have looked like part of the background hum of the castle mews. there was a question about music. power found its way out. 18:47:44 `style fungot 18:47:44 FireFly: 45. file://localhost/ mnt/ space/ media/ books/ 1000+sci-fi%20books/%5bebooks%5d%201000+%20sciencefiction%20%26%20fantasy%20novels%20%28.lit%20forma/ pratchett%2c%20terry/ text/ 19/ fnord 18:47:45 ​/home/hackbot/hackbot.hg/multibot_cmds/lib/limits: line 5: exec: style: not found 18:47:52 ^style fungot 18:47:52 Selected style: fungot (What I've said myself) 18:48:00 whoa, whoa, that shit's illegal!! 18:48:31 fungot: I didn't know you're a pirate 18:48:31 FireFly: agora alice c64 ct darwin discworld europarl ff7 fisher ic irc* jargon lovecraft nethack pa speeches ss wp 18:48:59 Is this a sign? I think fungot wasn't content with my choice of style 18:48:59 FireFly: so, let's say i call them mindless games. if we hit every stupid person, any person going, tough one. if we solve it,... i know... 18:49:22 fungot's getting sinister 18:49:22 Phantom_Hoover: no, it's not. it's more complex than that. read the code.) good stuff 18:49:39 sorry fungot i've underestimated the depths of your character 18:49:39 Phantom_Hoover: to, uhhh.... like nuns in the street, and has not named a programming language... as it's pretty difficult to get computers, but i think they can keep their bullsh*t straight.) 18:50:07 fungot: your code *is* good stuff, though 18:50:07 FireFly: or is it just me, or i: yet, you rogue! fnord fnord --user:protiousgeorge ( user talk:protioustalk) 01:44, 8 september. the officials of the european union's number, and can be extended by nesting them ( having one function call. if one is older. see http://okmij.org/ ftp/ papers/ lagarias/ paper/ html/ fnord 18:50:51 I have a dream. I dream that someday fungot will balance his parenthesises. 18:50:52 boily: agora alice c64 ct darwin discworld europarl ff7 fisher ic irc* jargon lovecraft nethack pa speeches ss wp youtube ( some youtube comments) 18:51:07 Your dream came true 18:51:18 fungot: thungot. 18:51:18 boily: am i that much bad. take up, boy; open't. so, now go with, do miscarrie, thou had'st bin resolute pompey 18:59:51 -!- S1 has left. 19:03:17 hoily! 19:03:27 bonjoily! 19:03:38 I'd like to watch a fungottian version of Julius Caesar 19:03:38 mrhmouse: and is one thing which you might want is broken" archives. even less chance. i called " o" in " the other side has. you came through and through and through and through and through and through and through and through and through and through and through and through and through and through and through and through and through and through and through and through and through and through and through and through and through 19:04:15 i love it when it gets stuck in loops 19:05:08 ^style youtube 19:05:08 Selected style: youtube (Some YouTube comments) 19:05:12 fungot is demonstrating Pollard's rho method? 19:05:12 int-e: but that is so funny to read my previous post? again: no a320 has ever flown completely by computer and fully automated, there for taking him into the forest at over 200mph? wikipedia should not be allowed to show the ' tenor' roles... 19:05:35 quintopia: hintopia! before you ask, no package yet. 19:05:46 `ello me 19:05:47 mello 19:05:48 i wasn't even thinking of asking 19:06:05 `ello quintopia 19:06:07 quintellopia 19:06:16 clever! 19:07:26 but I want your package! 19:08:18 i'm not in charge of that! talk to the postal service! 19:08:43 (unless you mean the other one. in which case, ... talk to "the postal service") 19:11:29 -!- s_o_l has joined. 19:11:43 -!- s_o_l has left ("Leaving"). 19:12:57 ah, the joy of having to go through USPS and Postes Canada... 19:13:06 Hurray, got Flat Assembler to work! 19:13:08 I printed an h! 19:13:11 (yes, I meant the other other one.) 19:13:30 Though I had to go to dosbox 19:13:42 Apparently windows 64 bits is a bit more finnicky 19:15:41 yay, I can still do *that* ... mov al, 68h; int 29h; int 0x20h 19:15:52 eh, 0x20 -> 20h 19:16:00 and hh -> h 19:17:09 I incremented the register and printed it 19:17:13 And now it says hi :o 19:18:07 are your brainfscking your helloworld through assembly by hand? that's nice :D 19:20:56 Well I am lurnin' 19:21:20 -!- muskrat has joined. 19:21:27 -!- muskrat has left. 19:22:33 and what on earth where they thinking when they decided to use $ as a terminator for strings... http://www.ctyme.com/intr/rb-2562.htm 19:23:02 (maybe they didn't appreciate money back then? :) ) 19:24:09 how do you print an '$', then? 19:24:54 I should link to this copy, less infested by banners (but still some stuff from amazon. sigh. the internet is going to hell.). http://www.delorie.com/djgpp/doc/rbinter/id/73/25.html 19:25:51 boily: you can print single characters or use proper file IO: http://www.delorie.com/djgpp/doc/rbinter/id/02/28.html 19:26:18 (0 is stdin and 1 is stdout, I wonder where they got that from ;-) ) 19:32:26 I have multiple aggressive adblocking and privacy-preserving extensions installed. 19:33:01 BX is on how many bytes? 19:34:10 a 16 bit register 19:35:15 Or two 8 bit ones 19:35:20 BH and BL 19:35:35 Or half a 32-bit one, or one quarter of a 64-bit one. 19:40:29 so, at most 65536 open files at the same time. 19:40:37 (well, minus stdin, out and err) 19:45:31 you'll run out of memory first 19:46:11 Which one is the 32 bit, EBX I think? 19:46:17 And RBX for 64? 19:47:15 Yes. 19:47:20 Hah, I forgot that. CONFIG.SYS had a FILES directive for the number of files that could be opened at once; typical values would be 20 to 40. 19:47:50 (keep in mind that as a rule, only one process would have files open at a time. so that's actually plenty.) 19:53:50 FILES=255 19:53:56 (It doesn't go any higher.) 19:54:55 but that eats kilobytes of memory! 19:57:07 -!- ais523 has joined. 20:01:10 mmm.. kilobytes... 20:06:41 -!- Bike has quit (Ping timeout: 252 seconds). 20:11:58 -!- Bike has joined. 20:13:51 I have FILES=80 in my CONFIG.SYS, it seems. 20:14:00 FILES=80 STACKS=9,256 20:14:27 Oh, wait; there's FILES=35 for some other menu options. 20:14:32 -!- faryad has joined. 20:17:10 -!- faryad has quit. 20:20:20 fizzie: you still have a config.sys? 20:20:32 people here have weird, weird setups. 20:20:57 @tell zzo38 you are the weirdest. 20:20:58 Consider it noted. 20:21:34 ais523: I have one too in my bochs dos install. I have to play commander keen somehow. 20:21:47 ais523: It's in ~/archive/backup/older/colin/old/misc_install/4dos/config.sys, so it's not exactly... active... 20:21:57 fair enough 20:22:10 colin? 20:22:12 * ais523 runs locate config.sys 20:22:19 I guess colin is a hostname 20:22:24 boily: A former hostname, indeed. 20:22:33 well, I might be able to play it without a config.sys in dosbox, technically, but I run a real ms-dos in bochs more often 20:22:54 I use dosbox only for games that don't run under bochs 20:23:42 I should perhaps do some directory cleaning some day. 20:24:01 As an illustrative example, there's the directory ~/__UBUNTU__/_MUST_SORT_/momusspace-before-crash/mnt/_NSA_MOVE_/music_unsorted/random/old/unsorted/ that has some music in it. 20:24:47 ais: in fact, I also have a smaller bochs install that I wired up to irc and might be thematically approperiate for this channel: 20:24:56 btw, I figured out what's up with Unity; it's trying to become Google Desktop 20:25:06 you can run edlin in it to edit files, then bcc to compile C and run the executables 20:25:07 which explains why people are confused 20:25:12 so it can serve as an evalbot 20:25:16 b_jonas: wow, I used to use bcc 20:25:17 I guess /etc/dosemu/freedos/config.sys doesn't really count. 20:25:35 I can show it if you want but it's a bit verbose so probably not on this channel 20:25:51 (I would have to dig out the HD image from a previous PC) 20:25:56 there's #esoteric-blah for things that are appropriate here except too verbose 20:25:59 but it hasn't been used for ages 20:26:03 hi b_jonas 20:26:07 and so I doubt anyone's there 20:27:27 if you want to try it, just tell me so 20:28:02 evalbot? HackEgo is good enough for me... 20:28:27 but this runs a full OS where you have root rights 20:28:41 there's an even more off-topic channel than #esoteric? wooooah, duuuuude... 20:28:44 still sounds like hackego 20:29:09 theoretically you can even install a new OS on it and reboot, all through irc, only you want a very small OS because it's not connected to the internet so you have to transmit all the files through irc 20:29:41 "not connected to the internet" haha 20:30:17 (no internet protocol, I got it, but it's still a funny claim when you can talk to it via IRC) 20:30:48 technically, IRC would work without being part of the public Internet, despite the "Internet" in its name 20:30:52 no, it's not no internet protocol 20:30:58 it's that the virtual machine doesn't have a net connection 20:31:01 Usenet used to not be part of the public Internet at all 20:31:08 only a serial console which a wrapper connects to irc 20:31:13 although nowadays nearly always goes over the Internet 20:31:25 there's probably some Usenet-only cable still keeping it connected somewhere 20:32:53 in theory you could install a linux on the vm and use the same wrapper, configured to talk through serial console, and it would still not have net access 20:34:22 Ah, but if you set it to talk slirp or something over the IRC to another system that's configured to route for it. 20:34:29 Then you could argue it suddely has net access. 20:34:33 then the other system is proxying for it 20:34:36 so it only has proxy access 20:34:55 fizzie: yes, only the bandwidth would be really slow 20:35:03 That's not any different from a carrier who does NAT for all their customers, and that's still called "net access". 20:35:20 sure, but you don't need net access 20:35:31 you could just directly type an uuencoded file through the serial console 20:35:52 but you'd be limited in bandwidth seriously 20:35:55 so it's not worth 20:36:18 It's a matter of principle. 20:36:22 if you wanted to transmit large files, it would be easier to convince me to give you some kind of direct access outside of irc, or run the machine yourself, or something 20:36:26 sure 20:37:56 fungot: Do you consider yourself to have net access? 20:37:56 fizzie: yes, pilots on board...there were 136 people on board. the first modern warfare(which i think his face. well, atleast in tucson, arizona. during the cold war. 20:38:54 hmm, now I have an urge to show that bot here and get kicked for flood 20:39:48 b_jonas: your bot couldn't be as floody as mine. let's have a duel! 20:40:01 boily: ok, on what channel? 20:40:21 b_jonas: esoteric-blah. 20:40:25 boily: #buubot ? that channel likes floody bots 20:40:43 buubot? 20:40:48 #esoteric-blah then 20:43:41 -!- genesisp31011 has joined. 20:44:30 -!- genesisp31011 has left. 20:46:53 Woo 20:46:58 I made a function to display a number 20:47:20 good job. 20:48:37 -!- MindlessDrone has quit (Quit: MindlessDrone). 20:48:57 -!- oerjan has joined. 20:55:21 Wrong window <-- in which Slereah accidentally reveals his al-qaeda membership. 20:55:32 Well it was for #generalrelativity 20:55:40 (It's a secret Al Qaeda front) 20:55:41 (convert 0 <= al <= 15 to 0123456789ABCDEF ASCII:) cmp al, 10; sbb al, 69h; das 20:55:54 We discuss the word of the Imam Al Bert 20:57:23 gener al-relativity 21:02:11 `ello relativity 21:02:13 Hello, relativity! 21:03:06 int-e: yeah, it falls back to a simple hello when it can't mangle the name nicely.. Any ideas for how to mangle "relativity"? 21:03:33 I was expecting something like rello-ativity 21:03:38 `ello bike 21:03:40 bikello 21:03:47 relatello 21:03:59 `ello int-e 21:04:01 int-ello 21:04:12 `ello lambdabot 21:04:14 lambdabellot 21:04:20 int-e: I could probably have it look for el+ 21:05:40 or maybe el+[aeiouy]+, and have it output "rellotivity" 21:07:23 `ello shachaf 21:07:25 shachafello 21:07:37 `ello cello 21:07:39 cellello 21:08:13 `ello kmc 21:08:15 kmcello 21:08:38 `ello fungot 21:08:38 FireFly: is this funny shit. unless they pull off a level, really, i dont now how too write it in the programation, the crew at the station, then... shit, we saw survivors, later we saw captain covered with blood after the game- the preview? 21:08:40 fungellot 21:09:06 ^style 21:09:07 Available: agora alice c64 ct darwin discworld enron europarl ff7 fisher fungot homestuck ic irc iwcs jargon lovecraft nethack pa qwantz sms speeches ss wp youtube* 21:09:18 hmm… youtube comments are no more 21:09:24 but they live on through fungot 21:09:24 ais523: actually, laminarwing, test planes with airline colors are not like im writing a fucking freak. 21:09:43 fungot: wow v. realistic 21:09:43 shachaf: get the facts that are part 121 certified by both the game was hysterical. 21:10:11 yeah shachaf get the facts. fungot is 121 certified for realistic youtube comment impressions. 21:10:11 FireFly: here's the short haired one from earlier scenes on trailer. 21:10:22 v. hysterical 21:13:27 It's kind of fixated on planes in this mode. 21:14:21 fungot: tell me about the astral plane 21:14:21 shachaf: don't be discouraged from flying again. 21:15:14 `ello relativity 21:15:15 rellotivity 21:15:49 `help 21:15:50 Runs arbitrary code in GNU/Linux. Type "`", or "`run " for full shell commands. "`fetch " downloads files. Files saved to $PWD are persistent, and $PWD/bin is in $PATH. $PWD is a mercurial repository, "`revert " can be used to revert to a revision. See http://codu.org/projects/hackbot/fshg/ 21:16:41 fungot: I've never flown before. What should I expect from it? 21:16:41 mrhmouse: no one was aboard this flight had a little over 3,000. granted, any crash is unacceptable but i just don't want to land xd 21:17:09 fungot: You've got to land at some point. 21:17:09 fizzie: to any expert, what is the first unmanned, computer didn't ' try to see people killed. 21:17:19 Well, that's comforting. 21:17:36 Any people-killing was apparently purely accidental. 21:17:52 fungot didn't _mean_ to kill people. it just didn't want to land. 21:17:52 mrhmouse: whats that " these angels" are the old her better when she saw me jizz in my pants 21:18:38 `perl -e 'print "\u\c*\c5\c3\c4\c`\c!\c.\c/\c4\c(\c%\c2 \u\c0\c%\c2\c,\c`\c(\c!c\c+\c%\c2\cJ"' 21:18:40 No output. 21:18:45 huh? 21:18:50 try with `run 21:18:54 `run perl -e 'print "\u\c*\c5\c3\c4\c`\c!\c.\c/\c4\c(\c%\c2 \u\c0\c%\c2\c,\c`\c(\c!c\c+\c%\c2\cJ"' 21:18:55 Just another Perl hacker 21:19:01 better, thanks 21:19:24 "`command blah bluh bleh" runs `command` with the single argument that is the literal string "blah bluh bleh" 21:19:34 whereas `run does sh 21:19:42 ah, I see 21:20:03 `run cat /proc/$$/cmdline 21:20:05 cat./proc/285/cmdline. 21:21:03 `run cat /proc/$PPID/cmdline 21:21:05 sh.-c.'env' 'PATH=/hackenv/bin:/opt/python27/bin:/opt/ghc/bin:/usr/bin:/bin' 'HACKENV=/hackenv' 'http_proxy=http://127.0.0.1:3128' 'LANG=en_NZ.UTF-8' '/home/hackbot/hackbot.hg/multibot_cmds/lib/limits' 'bash' '-c' 'cat /proc/$PPID/cmdline' | cat. 21:21:08 `perl -eeval for'for$=(2..27){$*=0;$*=($**$=+ord)%127,for/./gs;print+chr$*}'."\n#ig\\tq\24^-/v\c^l,\23\$%\3\ta2\tk\b\c\)\x18 -- ambrus" 21:21:09 ​$* is no longer supported at (eval 1) line 1. \ Just another Perl hacker, 21:21:31 works 21:22:00 ah, I have a variant that's warning-free in newer perls 21:22:28 `perl -eeval for"for\$^(2..27){\$==0;\$==(\$=*\$^+ord)%127,for/./gs;print+chr\$=}\n#P*h!9= Nn[\c\9\0*.:\eUt\17%j{dY\31 -- ambrus" 21:22:29 Just another Perl hacker, 21:22:30 It's OK, you don't have to type it. 21:22:34 We believe you. 21:23:29 this bot msgs the answer without any prefix. I like that, that's great for creating a loop between two bots. 21:23:42 Not quite true 21:24:01 I think it inserts ^O before the reply, precisely to protect against that (and unwanted CTCPs) 21:24:12 ah, nice 21:24:30 I didn't know about that trick 21:24:39 -!- shachaf has left. 21:24:51 I mean, the normal method is to just have bots send NOTICEs instead of msgs, but few people do that 21:25:45 Hm 21:25:49 -!- evalj has joined. 21:25:50 It's a non-breaking space it inserts, isn't it? 21:25:55 Er, zero-width space. 21:25:56 fizzie: no 21:25:59 um 21:26:00 wait 21:26:02 let me try 21:26:02 The assembler is bitching if I try mov es, ip 21:26:16 Is it not the same size, or is it because it's the instruction pointer? 21:26:18 `echo division 21:26:19 division 21:26:26 Slereah: there's no such instruction 21:26:29 you write to the instruction pointer with jmp 21:26:37 whoa, it doesn't actually insert anything! 21:26:43 Yes, but I'm not writing in IP 21:26:48 I'm reading its value 21:26:53 b_jonas: It's only inserted when the reply starts with something that could plausibly be a command prefix. 21:26:59 And saving it for later 21:27:00 Slereah: still, there's just no such instruction as that on x86 21:27:02 `echo ^a 21:27:04 ​^a 21:27:05 Hm 21:27:14 How do I keep track of where I left off then? 21:27:16 ah 21:27:17 `echo .foo 21:27:19 ​.foo 21:27:26 Slereah: with the call insn 21:27:27 `unidecode > ​.f 21:27:28 ​[U+003E GREATER-THAN SIGN] [U+0020 SPACE] [U+200B ZERO WIDTH SPACE] [U+002E FULL STOP] [U+0066 LATIN SMALL LETTER F] 21:27:37 U+200B ZERO WIDTH SPACE, apparently. 21:27:41 `echo ] 39$'x' 21:27:42 That's Numberwang! 21:27:43 ​] 39$'x' 21:27:47 insn? 21:27:51 instruction 21:27:59 `echo evalj: 39$'x' 21:28:01 evalj: 39$'x' 21:28:01 HackEgo: xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx 21:28:31 `echo evalj: '`echo hi' 21:28:32 "Pushes Instruction Pointer (and Code Segment for far calls) onto stack and loads Instruction Pointer with the address of proc-name." 21:28:33 evalj: '`echo hi' 21:28:33 HackEgo: `echo hi 21:28:35 Ah yes, sounds like it 21:29:28 anyway, yes, it looks like it inserts some non-ascii stuff before some prefixes 21:29:40 and evalj doesn't like that before its short prefix 21:30:12 `echo ~help 21:30:13 ​~help 21:30:19 too smart 21:30:28 Everything outside of [a-z] and maybe digits, from what I recall. 21:30:31 To jump back, can I pop the stack into es and do jmp es? 21:30:43 Slereah: No, but you can "ret". 21:31:14 I'm a bit disappointed 21:31:14 You could also pop the stack to some general-purpose register (not a segment one) and jmp to it, but that sounds very silly. 21:31:24 Slereah: this is what arch exactly? x86_16, x86_32, or x86_64? 21:31:30 I was expecting assembly to be a bit more arcane 21:31:39 Currently using DOSBOX for it 21:31:47 So I assume it is 16? 21:31:50 32 maybe 21:32:05 16 or 32, depending. 21:32:14 if you want to treat ip as a general register, get an ARM or MIPS or whichever arch that is that does that 21:32:18 but I think that's crazy 21:32:30 it's a bad idea for an architecture to do that 21:32:32 Well it is #esoteric 21:32:35 sure 21:32:40 ARM no longer does that in AArch64, either. 21:32:50 fizzie: I see 21:32:51 (No more combined multi-register pop and return.) 21:33:08 does it have jump instructions then? 21:33:22 Are there any "real" architectures that treat pc as a general register? 21:33:30 (and encode jumps as arithmetic on pc) 21:33:53 I think it would be pretty neat to be able to write some self modifying code 21:34:01 does 32-bit ARM do that? 21:34:10 I remember seeing code with pc in it and stuff 21:34:29 Fiora: I think that's arguable. I mean, it does have separate jump instructions too. 21:34:31 i thought the notion of a program counter was oudatd. 21:34:52 huh. so like, redundant instructions? is there a reason for that? 21:34:53 Fiora: (With bigger relative offsets than just usual immediate arithmetic.) 21:34:56 ohhhhh 21:34:56 well, x86_64 can read ip, though not as a general register, 21:35:02 that makes sense. 21:35:09 they added that so you can write position independent code 21:35:17 but it can't just write ip of course 21:35:20 you need jumps for that 21:35:48 Fiora: Also conditional jumps even in modes that don't have condition bits for all instructions. 21:35:50 however, x86_32 didn't have that 21:36:07 Slereah: so what? you can still write self-modifying code with jumps 21:36:40 Slereah: if you want to do so, I recommend overwriting the instruction byte of a conditional jump with the opposite condition 21:36:49 thus dynamically negating a jump 21:37:07 recommend as in #esoteric obviously 21:38:19 Fiora: What it didn't have (I think) is a separate RET instruction, but I guess that's pretty common on architectures with a link register. 21:40:32 Bike: you'd get that impression from Knuth, yeah 21:40:51 but a program counter is really just a different name for an instruction pointer, or for the * register as Knuth calls it 21:40:57 well, he doesn't call it a register 21:41:15 i meant because of ooe and stuff. 21:41:23 ooe? 21:41:23 been a while since i've read taocp1, unfortunately 21:41:27 out of order execution 21:41:34 um so? 21:41:47 ooe: Out Of Echaracter. 21:41:59 So things aren't as simple as one instruction then another instruction. 21:42:03 the semantics is still given by serial execution with an ip, except maybe with some modification 21:42:21 it's not like the cpu can just randomly pick instructions from anywhere and execute them 21:42:42 I mean, some obfuscations play with that, but real cpus don't 21:42:56 there's that ioccc winner 21:44:25 `perl sub h($){($_=$_[0]=pack b208,0 .unpack b362,$_[0])=~tr/\0-\c?/\0/;tr/\0/\377/c;$_}do{$y=$r;$v=join$r='',a..z;$r^=h$r&"\217"x26^h$v&$y for 0..6;$r^=$_ x26}for"k6sNP2B}({ambrusLB%Ox)Z]n0*zf\0I3"=~/./g;print$r 21:44:26 Can't open perl script "sub h($){($_=$_[0]=pack b208,0 .unpack b362,$_[0])=~tr/\0-\c?/\0/;tr/\0/\377/c;$_}do{$y=$r;$v=join$r='',a..z;$r^=h$r&"\217"x26^h$v&$y for 0..6;$r^=$_ x26}for"k6sNP2B}({ambrusLB%Ox)Z]n0*zf\0I3"=~/./g;print$r": No such file or directory 21:44:35 `perl -esub h($){($_=$_[0]=pack b208,0 .unpack b362,$_[0])=~tr/\0-\c?/\0/;tr/\0/\377/c;$_}do{$y=$r;$v=join$r='',a..z;$r^=h$r&"\217"x26^h$v&$y for 0..6;$r^=$_ x26}for"k6sNP2B}({ambrusLB%Ox)Z]n0*zf\0I3"=~/./g;print$r 21:44:36 Just another Perl hacker, 21:44:39 duh 21:44:54 what the fungot is that linënoise... 21:44:54 boily: and if there were many passengers. 21:45:03 boily: http://www.perlmonks.com/?node_id=863110 21:45:03 fungot: then it'd have crashed. 21:45:04 boily: the flying club which staged the show 21:45:06 many, many passengers. (fungöt) 21:45:09 good. 21:45:24 b_jonas: ain't clicking on that. I swore off perlmonks-related drugs years ago. 21:45:44 boily: evaluates a polynomial over GF(128) 21:45:59 that long double-quoted string encodes the polynomial 21:46:21 ... 21:46:25 ........... 21:46:31 /clear 21:46:33 /abort 21:46:37 it has a funny story 21:46:38 /flee-in-abject-terror 21:48:14 ages ago I wrote a perl obfu that evaluates a polynomial over GF(127), which is of course much easier. then martin reinvented that idea and wrote his version. 21:48:45 then I said that his obfu was better than mine, but would be even more amazing if it did computations over GF(128). 21:49:32 he took that seriously and wrote such an obfu, which works quite differently from mine: it computes a table of powers of some primitive root and uses that as a log table to do the multiplications. 21:49:51 I had to one-up his obfu and so wrote this GF(128) obfu which is better 21:50:06 it looks nicer if I don't have to paste it in one irc line of course 21:50:51 “looks better”. yeah right. it still disturbs me. 21:50:55 the nice part is that the obfu is branded in that you can't just strip the "ambrus" part from it and replace it with your name without understanding the obfu 21:51:09 http://pastebin.com/raw.php?i=ucw6tpJa 21:51:15 Goddamn this took forever to write 21:51:16 because that's part of the polynomial 21:51:52 if it weren't, I'd only have felt dejected. 21:52:31 Slereah: oh, shiny! 21:52:42 Now to write a loop to print all the numbers! 21:52:45 255 to 0 21:53:28 Oh great 21:53:33 Loop uses cx 21:53:47 I'd better rewrite the cx stuff into dx 21:53:54 Slereah: modify it to write to stdout and you can try it with that dos machine hooked up to irc that I just showed on #esoteric-blah 21:54:09 Slereah: it even has an assembler installed I think 21:54:24 Isn't that a lot to put in IRC 21:54:33 not really 21:54:48 strip the comments and I guess it fits in a couple of irc lines 21:55:07 plus, that's why it's -blah channel, we can flood there 21:56:37 "The "label" operand must be within -128 or 127 bytes of the instruction following the loop instruction." 21:56:38 Whaaat 21:56:52 Goddamn 21:56:58 Well fortunately the code is small enough 21:57:00 -!- boily has quit (Quit: GAÀÁẢẠÃ!). 21:57:03 -!- metasepia has quit (Remote host closed the connection). 21:57:51 you can always do things like loop foo -> loop x; jmp y; x: jmp foo; y: ... though you're probably better off with dec cx; jnz foo. 21:58:11 Slereah: really, modify it to call dos function 40h and it should work in termbot 21:58:11 (but loop preserves flags, so that's not always an option) 21:58:36 int-e: why bother? on a 286 (or is it 386) onward you can just use the long form conditionals 21:58:48 b_jonas: not with 'loop'. 21:58:48 which take a wider offset 21:58:51 ah, loop 21:58:52 ... 21:58:53 ok 21:59:11 b_jonas: see also the part after the ellipsis :) 21:59:23 ah, I see 21:59:34 anyway, this code is so short it won't even come up 22:00:35 https://dl.dropboxusercontent.com/u/19940612/loop.jpg 22:00:37 Trippy 22:00:45 I guess "line feed" doesn't mean the same thing here 22:01:35 Slereah: show us the source when it's ok so we can try it in evalbot! 22:01:44 you need CR/LF (ASCII 13, 10) 22:01:54 Damn you windows! 22:02:00 DOS 22:02:04 winDOS 22:02:08 actually, old line printers did the same 22:02:27 Yes, but this is not a printer 22:02:33 it's even in the name, LF is a line feed, cr is a carriage return 22:02:41 I'm aware, yes 22:02:42 it's a terminal, which emulates a printer :) 22:02:46 Old typewriter terminology 22:03:14 I think you can skip the cr in the irc bot wrapper 22:03:24 I'm not quite sure 22:03:31 cr lf is probably better 22:03:33 more portable 22:04:15 Portable DOS code. 22:04:22 int-e: exactly 22:04:25 http://pastebin.com/hp1akjtk 22:04:27 There you go 22:04:28 It works 22:04:33 int-e: come on, windows will support it for years after dos 22:05:09 Slereah: great, but like I said, modify it to use dos function 40h so it writes to stdout, or else the output won't go through irc 22:05:29 How is it called? 22:05:39 wait, let me check the manual 22:05:47 int 40h, printing al? 22:05:54 no 22:06:42 http://www.delorie.com/djgpp/doc/rbinter/id/69/25.html is probably more convenient (and should still go through the file handle properly) 22:07:12 int 21h because it's a dos function, ah=40h, bx=1 is the file handle, cx= the number of bytes, ds:dx=address of bytes 22:07:24 like the write call for unix 22:07:29 Fuck 22:07:33 it uses dx 22:07:38 But dx is required D: 22:07:39 so? push and pop it 22:07:43 Ah yes 22:07:46 The stackin' 22:07:53 honestly, use mov ah,06h; mov dl,char; int 21h 22:08:08 Well I need to keep track of dx 22:08:12 saves you setting up a memory buffer 22:08:14 It contains important things 22:08:16 push dx; pop dx 22:08:21 Will do 22:08:26 and you can modify dx inbetween 22:08:27 int-e: does that go to stdout? I see 22:09:43 I guess I'm too used to unix to think of any way other than write(2) to write stuff 22:10:05 printnum: 22:10:06 add al, 0x30 22:10:06 push dx 22:10:06 mov dl, al 22:10:06 mov ah, 0x06 22:10:06 int 0x21 22:10:06 pop dx 22:10:07 ret 22:10:08 All good? 22:10:35 Slereah: let's hope. and the same for the crlf too I guess 22:10:40 yep 22:12:20 you could use the bios serial port service too, but then you'd get a program that works only on the serial console, which would suck. let's use dos to hide this abstraction. 22:13:30 Is assembler sensitive to linefeeds? 22:13:36 Or can I put it in a big line 22:14:09 Some of them have a command-separating character that lets you put multiple things on a line. (Some of them don't.) 22:14:35 http://pastebin.com/81tMfjaC < it is this anyway, if you want the 21h version 22:18:41 it is sensitive 22:18:47 but you can put multiple lines in an irc line 22:18:57 I'll show in a few minutes 22:20:24 So is jmp 0xabcd equivalent to mov ip, 0xabcd 22:22:17 -!- Sprocklem has joined. 22:25:43 have you ever been able to mov into ip 22:25:55 Also if you can't get the value of IP, how does the processor recall the value where it left when using CALL? 22:26:20 the processor can do things you can't, so to speak 22:26:45 Are things like CALL actual instructions? 22:26:51 yes. 22:26:51 I thought it was assembler shortcuts 22:27:07 it might be on some other architecture 22:27:20 Slereah: often it's a shortcut for a range of CALL instructions 22:27:26 like, CALL NEAR and CALL FAR, or whatever 22:27:49 Oh wait 22:27:55 It pushes the IP on the stack 22:28:03 So I guess you can get the IP 22:28:06 Like 22:28:10 CALL whatever 22:28:16 whatever: 22:28:25 on x86, call is an actual instruction. you can read the IP using something like call next; next: pop ax (this can be useful because 'call' uses relative addressing. stuff like that is actually used in x86 dynamically linked libraries) 22:28:27 "call next; next: pop bx" is the conventional "trick", yes. 22:28:28 pop ax 22:29:12 ais523: CALL ABSOLUTE(VARPTR(a%(0))) 22:29:45 Even for x86, I should've written "near call" there :) 22:30:12 Slereah: I've used a system where the stack was not in normal memory, and could only be manipulated via call and return instructions 22:30:20 also it was only 8 entries 22:30:20 That's Numberwang! 22:31:02 If you're writing regular, non-position-independent code, you can typically "read the IP" (so to say) by using a special symbol -- often $ or . -- that the assembler replaces with the address of the current instruction, incidentally. 22:32:39 ais523 : Damn you 22:32:46 I won't be denied my IP! 22:32:55 Slereah: ? 22:33:01 that's a really really weird reaction 22:33:05 to lambdabot randomly spouting stuff 22:33:12 it's not even my fault :-( 22:33:19 oh, I see 22:33:22 that's not my fault either 22:33:27 it's the system's 22:33:32 besides, the IP was stored in regular memory 22:33:34 it's my fault, though I'd like to put the blame on chrisdone (on #haskell) 22:33:45 you could assign to it to do a computed goto if you wanted to 22:34:48 seriously, though, I don't like strong maledictions like that when I haven't done anything wrong 22:34:52 (or even when I have, really) 22:35:05 having used a system with a weird stack is not really something to be damned over 22:35:41 Hm 22:35:46 What thing to try out next 22:35:56 I guess some arithmetics 22:36:11 And then 99! 22:36:18 Slereah: seriously, though 22:36:24 it's not nice 22:36:35 literally can't figure out how to negate a bus 22:36:36 What is? 22:36:44 Slereah: damning me over using a weird CPU architecture 22:36:45 pretty sure i'm basically idiot satan 22:36:54 Well it was more of a joke 22:36:55 Slereah: ais has this thing where he reacts to "damn". 22:37:02 I don't really damn people in seriousness 22:37:06 good 22:37:08 Unless be they damn dirty apes 22:37:11 Are you? 22:37:38 I don't think so 22:38:15 -!- lambdabot has quit (Quit: bye, bye, numberwang). 22:39:02 I wonder if there's a shorter way to display a byte 22:39:15 Without resorting to interrupts or such 22:40:48 ais523, fuck you btw 22:41:17 Phantom_Hoover: I don't mind people saying that because it doesn't really make much sense when interpreted literally 22:41:28 thus, it's just an entirely generic insult with no substance 22:41:39 neither does damn 22:41:59 and let's not pretend you have any reason for doing it beyond amusing yourself 22:42:12 -!- lambdabot has joined. 22:42:19 Phantom_Hoover: well I care about language not eroding 22:42:30 if people keep on using words with meanings entirely different from their actual meanings 22:42:35 ais523 22:42:36 eventually communication will become impossible 22:42:39 English isn't eroding 22:42:41 * Bike points and laughs at the prescriptivist 22:42:48 that's called the language evolution that has been happening for thousands of years 22:42:51 Languages don't erode when they're living 22:42:52 -!- mrhmouse has quit (Quit: Leaving.). 22:43:02 i'm seriously so bad at verilog though. 22:43:03 Bike: I formed the possessive of someone's name, that ended with s, via adding just an apostrophe today 22:43:05 i'm the one eroding, here. 22:43:07 miraculously, communication still appears to be possible, despite the frightening lack of prescriptivists thousands of years ago 22:43:09 If you want to see a language erode go to some village in bumfuck siberia where it's spoken by 3 people 22:43:18 and concluded that it was probably correct nowadays, but I felt bad about it 22:43:26 stop worrying about stupid shit 22:43:47 "Reynolds's" is not something anyone would say nowadays, even though they probably would when I was younger 22:43:57 god. 22:44:13 elliott: uh i have no actual evidence that you're not actually speaking french and i just don't know it?? 22:44:25 ais523, modern language, even when correct, is very much incorrect when compared to old english! 22:45:01 Slereah: there's someone from another channel who asks me for help with English from time to time 22:45:14 For instance 22:45:16 it's depressing that English is so complex and inconsistent, it makes it quite hard to work out what is right 22:45:24 Did you know that "pea" is terribly wrong 22:45:27 what does it mean to be "right". 22:45:30 If you know where it comes from 22:45:37 Bike: exactly :-( 22:45:41 What is the definition. Where does English come from. 22:45:42 Slereah's program works in termbot! 22:45:43 yay 22:45:44 the answer is "what people use" 22:45:52 (WHOA) 22:45:56 only irc is throttling it 22:45:59 btw, the nose in smiley thing is just me being pointlessly prescriptivist for no reason ;-) 22:46:06 Slereah++ 22:46:10 Pea is from the latin "pisum' 22:46:11 no you're still annoying 22:46:19 don't do the "just kidding" thing 22:46:23 Which was rendered as "pease" in old english 22:46:25 But 22:46:32 Since it ended in /s/ 22:46:36 People thought it was a plural 22:46:42 And decided that the singular was "pea" 22:46:46 counting down from 255 at IRC speed seems like a fitting use of #esoteric-blah 22:47:06 ais523: yes, especially in assembly 22:47:07 heh 22:47:14 because it would be much easier if we wrote it in c or pascal 22:47:20 b_jonas: what are you using to convert the number to decimal? 22:47:22 in other news i just noticed that a multiplier is also a shifter. 22:47:34 -!- fr0k has joined. 22:47:37 and i can see an engineer's ass crack. 22:47:43 not regular crack, unfortunately. 22:47:47 ais523 : first digit is n/100 22:47:57 -!- fr0k has quit (Client Quit). 22:47:57 Second is (n/10)%10 22:47:59 ah right, I was wondering whether it was done manually 22:48:03 Last is n%10 22:48:07 Slereah: http://int-e.eu/~bf3/tmp/num.nas is what I'd probably write 22:48:33 XORs :o 22:48:39 I will have tto investigate 22:49:24 Wait, what is x XOR x again 22:49:29 0 22:49:30 Isn't it always 0? 22:49:30 zero. 22:49:38 Why is it there? 22:49:42 xor dx,dx is just a byte shorter than mov dx,0 22:49:43 clears the register. 22:49:48 Ah 22:49:53 Faster than mov? 22:49:55 welcome to x86 i guess 22:50:08 probably the same speed 22:50:20 ais523: me? ask Slereah 22:50:21 but I used to optimize for size, so ... 22:50:36 b_jonas: I wasn just asking generally 22:50:39 and I'd already got my answer 22:50:48 I was thanking Slereah for the answer 22:50:57 The xor-clear is still on the list of recommended idioms, IIRC. 22:51:07 ais523: you mean in C or pascal? I wouldn't divide, I'd just call printf or write 22:51:15 the compilers i still use xor clearing, anywho 22:51:44 b_jonas: I was asking what the #esoteric-blah program did, and I'd already got the answer 22:51:56 According to a friend you can do a shorter version with AAM 22:51:57 my statement was explaining that I was happy with the answer 22:52:04 sure, reducing code size saves memory bandwidth, code cache pressure, all that; and the CPUs are smart enough not to intruduce any artificial data dependencies in this case ('dx depends on the previous value of dx') 22:52:12 I see 22:52:32 Bike: There was some scenario where it was still faster. 22:52:34 int-e: actually there's a better reasoning for why using xor dx,dx 22:52:37 int-e: its 22:53:00 it's that the amd64 architecture optmization manual explicitly says that xor is the best way to clear the register 22:53:14 you don't have to guess anything about artificial data dependencies or stuff 22:53:15 "Since zero idioms [like XOR REG, REG] are detected by and removed by the renamer, they have no execution latency," says the Intel optimization manual. 22:53:21 exactly 22:53:29 and zeroing an sse register is similar 22:53:56 XOR, SUB, PXOR/VPXOR, PSUBB/W/D/Q, VPSUBB/W/D/Q, XORPS/PD, VXORPS/PD is the full list. 22:54:02 "Use one of these -- when possible." 22:54:55 fizzie: in that list, does xorps refer to both the sse and mmx insns? 22:55:15 Well, it says XMMREG only, so maybe not MMX. 22:55:31 meh, ignore that 22:55:33 I don't care about mmx 22:55:38 it's obsolate and stupid 22:55:53 -!- Bike_ has joined. 22:56:15 -!- Bike has quit (Disconnected by services). 22:56:20 -!- Bike_ has changed nick to Bike. 22:56:44 Another random tidbit: while "CMP a, 0" and "TEST a, a" produce the same flags, the latter canbe macro-fused more often. 22:57:13 -!- muskrat has joined. 22:57:16 I'm trying to remember what TEST does 22:57:19 what? there's no way they produce the same flag 22:57:19 -!- muskrat has left. 22:57:23 is it AND but don't write the result anywhere? 22:57:24 ais523: Non-writing AND. 22:57:25 ais523: AND but without writing the result 22:57:26 yes 22:57:32 whereas CMP is subtraction that doesn't write the result 22:57:36 i guess this is what kmc means when he talks about writing compiler assembly being easy. 22:57:42 b_jonas: "a - 0" and "a & a" are the same value. 22:57:57 (So they'll produce the same flags.) 22:57:59 IIRC, and CMP a,0 clears the carry flag; test shouldn't. *goes to check memory* 22:58:04 fizzie: yes, but TEST affects the eflags differently I think 22:58:11 int-e: something like that yes 22:58:32 "The OF and CF flags are set to 0." 22:58:33 er, reading compiler assembly being hard, and writing assembly being easy. on x86. 22:58:34 (For TEST.) 22:58:44 Apparently a better solution for the digits is n/100, and AAM n 22:58:47 No I'm wrong. 22:59:08 confused that with inc/dec :) 22:59:30 yeah, TEST clears CF and AF, and leaves AF undefined 23:00:10 whereas CMP a,0 would zero CF and AF and OF I Think 23:00:24 Nobody's going to be testing AF. 23:00:33 but isn't TEST one byte shorter in first place, except maybe for rAX? 23:00:49 I had a snippet above that used AF: cmp al, 10; sbb al, 69h; das 23:00:54 at least one byte 23:01:01 I mean, the CMP needs an immediate 23:01:15 which is an extra byte unless it uses the special forms for AL or RAX 23:01:16 But there's no place for a 'test' in there :) 23:01:49 b_jonas: OF would also be 0. Only AF makes a difference. 23:02:02 -!- nisstyre has joined. 23:02:06 And indeed that flag is hardly ever important. 23:03:22 What does JZ do? 23:03:28 "Jump if Zero". 23:03:29 I find 'jump if zero' 23:03:35 But if what register is zero? 23:03:38 CX? 23:03:38 "jump if zero flag is set" 23:03:40 If the zero flag is set. 23:03:42 Oh 23:03:47 the flag is set by the test instruction. 23:04:18 anyway, good night now 23:04:25 night 23:04:42 (Curiously enough, there is a special instruction for jumping if CX is zero -- JCXZ/JECXZ/JRCXZ.) 23:05:08 "It is set if an arithmetic result is zero, and reset otherwise." 23:05:09 neat 23:07:10 Let's try rewriting a bit my program 23:08:40 -!- evalj has quit (Remote host closed the connection). 23:13:08 Woo 23:13:10 AAM works 23:15:18 -!- ais523 has quit. 23:15:39 -!- ais523 has joined. 23:15:57 -!- ais523 has quit (Client Quit). 23:16:15 -!- ais523 has joined. 23:20:20 my professor used an inconvenient distribution of opcodes and it fills me with rage 23:21:01 it's just practice for x86, I think ;-) 23:21:35 Now that I can print numbers 23:21:43 I will try to see what the IP looks like! 23:21:46 If I can get at it 23:22:05 Is the IP 8 bits or 16 bits? 23:22:22 the only ops are addition, subtraction, increment, and bit parallel shit. you might think it would be convenient to divide one from the other but nooooo 23:22:22 is this IPv1? 23:22:28 -!- nooodl has quit (Quit: Ik ga weg). 23:22:30 Slereah: 256 bytes of addressable code wouldn't be enough or most purposes :) 23:22:31 oh, instruction pointer 23:22:31 it's x86 23:22:34 not internet protocol 23:22:37 *for 23:22:47 on the 8086 CS is 16 bits and IP is 16 bits 23:22:54 and you need both to work out which instruction is executing 23:23:01 Well, I guess printing the last octet will be enough 23:23:05 but the formula is, IIRC, CS*16+IP 23:23:17 so there's much less than 16 actual bits of data there 23:23:22 but we're writing COM files where initially, CS=DS=ES=SS 23:23:27 Just to make sure that the next instruction is indeed that instruction 23:28:20 http://pastebin.com/raw.php?i=u694Agh6 23:28:24 Let's see 23:28:32 I get 203, 210 and 217 23:29:06 In between, there is always 3 instructions 23:29:14 But why 7 23:29:40 7 bytes, presumably. 23:30:02 But why 7 bytes 23:30:03 1 byte pop, 3 bytes for each call 23:30:04 "call test" is 3, "call printint" is another 3, and "pop dx" is 1, at a guess. 23:30:13 Oh, I see 23:30:15 Your disassembler should print the opcode bytes for you. 23:30:35 I guess call test is like 23:30:38 push the address 23:30:44 jump to test 23:30:51 And... somethig something? 23:31:05 That's pretty much it. 23:31:18 Though "push the address" is "push the address of the following instruction". 23:31:25 Ah 23:31:53 But I guess that the CPU has "push the address of the following instruction" as just one opcode? 23:32:12 the whole call thing is one instruction 23:32:28 (1 byte opcode + 2 bytes address) 23:32:51 Ah right, an address is 16 bytes 23:32:56 where the address is relative, so internally rather than "jump to test" it adds that offset to IP. 23:33:53 It is good to know that I can get IP 23:34:00 Once I am good at assembling 23:34:03 It's a CISC architecture. There are amazingly complex instructions with compact encodings. 23:34:08 I can write the Worst Code 23:34:39 in assembly? the competition is fierce 23:35:10 http://www.cs.utah.edu/~elb/folklore/mel.html 23:35:18 writing bad assembly code has been automated :) 23:35:24 heh 23:37:31 "Put *that* in Pascal's pipe and smoke it." 23:37:38 I will have to remember that expression 23:37:42 Slereah: which assembler are you using now? 23:37:46 x86 23:37:50 On the dosbox 23:38:12 nah, I mean to translate the source code 23:38:27 Oh 23:38:30 Flat assembler 23:38:40 wasn't it nasm? 23:38:45 Nope 23:38:51 NASM was giving me lip 23:39:00 Flat assembler does the linking itself 23:39:15 You don't need to do any linking for a .com file. 23:39:28 NASM's "-f bin" is just fine for making those. 23:39:39 Eh too late 23:39:46 Flat assembler works fine now 23:40:21 I like this Mel fellow 23:41:45 nasm -f bin is the default here. 23:41:50 My first week of computin' school was all "Don't try to be smart, write maintanable code!" 23:41:55 huh, it's a weird feeling when the Story of Mel gets linked again and you see all the reactions from people who haven't seen it before 23:41:56 Mel knows the real deal! 23:42:01 It's the default everywhere, I was just being explicit. 23:42:08 Slereah: in assembler? 23:42:14 and Mel-like behaviour is still useful sometimes, but was more useful then 23:42:16 Nah, in general 23:42:35 hehhhhh, teach just described parameters in verilog modules as "like C #defines" 23:42:41 And I'm afraid I'm not that much into computering unfortunately 23:42:41 I agree in general, but it starts by ditching assembler except possibly for very small pieces of low-level code. 23:42:44 i think that right there is why i loathe this language 23:43:03 So I did not hear of this Mel fellow 23:43:19 I mostly know physics anecdotes! 23:43:45 (The important thing about assembly language is to know when not to use it.) 23:44:08 -!- Sgeo has joined. 23:44:20 Well it is certainly not a good idea to use it 23:44:25 But neither is Brainfuck 23:46:04 BF Joust begs to differ 23:46:13 that game would be less fun in other languages, I feel 23:46:21 because it's designed around how brainfuck works 23:46:30 What is BF Joust 23:46:36 (I haven't been there in a while) 23:47:16 http://esolangs.org/wiki/BF_Joust 23:47:28 the most awesome competitive esolang-based game ever 23:47:32 (not that there's much competition) 23:47:46 it's become something of a running pastime for this channel, now and again 23:47:55 !bfjoust rimfall (>)*31 23:47:59 -!- convicinum has joined. 23:48:02 ​Score for int-e_rimfall: 0.0 23:48:33 int-e: what did you expect? 23:48:37 that dies almost as quickly as < 23:48:51 ais523: I expected 0.0 :) 23:48:58 fair enough 23:49:06 obviously we need more competitive crap. 23:49:09 What competition is there except FYB? 23:49:23 -!- convicinum has quit (Client Quit). 23:49:30 !bfjoust thirty (>)*29(+)*100(+.)*50000 23:49:32 i guess dueling fungepointers has probably been thought of 23:49:32 ​Score for ais523_thirty: 0.0 23:49:40 fizzie: there's golf, I guess 23:50:14 Bike: There's vague rumours about "BeGlad" (Befunge Gladiators), which is reportedly built on Befunge-97 of all things. 23:50:29 thirty beats almost everything perfectly on tape length 30, except omnipotence (loses) and zeroer (win+draw) 23:51:08 Wouldn't the Rube language be perfect for game-things? 23:51:41 oh, right 23:51:41 dasklickenklacker 23:51:44 Rubicon 23:51:47 that's awesome too 23:51:59 http://kevan.org/rubicon/ (requires JavaScript) 23:52:04 err, Java 23:52:08 wow, I haven't rubiconned for ages 23:52:23 i'm going to continue thinking of the marathon mod and you can't stop me 23:52:26 Robozzle might almost-count. 23:53:10 !bfjoust just_curious (>)*8(>(+)*96(+.)*128)*21 23:53:13 ​Score for fizzie_just_curious: 5.9 23:53:39 Are there many loopless "serious" BF Joust programs? 23:54:09 fizzie: not many; there was a lock+full tape clear that someone else submitted that did decently 23:54:19 but you get too much benefit from skipping blank cells 23:54:20 Slereah: there are many good reasons to use assembly language... 23:54:47 they aren't situations most programmers encounter often, though 23:55:27 also even if you're not writing assembly, being able to READ it is incredibly useful 23:56:01 for debugging or for seeing how your compiler is optimizing things 23:56:33 (compilers are smart so the solution is usually to change the code to help the compiler, not to rewrite it in assembly) 23:59:10 kmc: the question "how would you optimize this program?" came up in comp.lang.c 23:59:17 I managed to beat both gcc -Os and clang -Os on size with my own asm 23:59:19 ok. xilinx tools detect finite state machines during optimization. i think something has gone very wrong here. 23:59:43 nice :) 2013-11-23: 00:00:04 maybe it's naïve of me to think that analyers shouldn't have to infer things i meant in the original code 00:00:10 analyzers 00:02:17 ais523: I bet -Os is not the primary focus of the gcc developers :) 00:02:48 int-e: it should be, it's often the fastest setting due to caching issues 00:03:01 (Besides, when do you stop making the code smaller? There's a lot of things one can do when speed is of no importance.) 00:03:02 -!- yorick has quit (Remote host closed the connection). 00:03:17 Bike: finite state machines are a very common design pattern 00:06:02 x86 could use more general registers 00:06:08 -!- Bike_ has joined. 00:06:09 4 is a bit short to work with well 00:06:18 you have 7 00:06:29 si, di, bp are also available 00:07:03 ais523: of course, but it seems like it should be possible to just tell the tools "this is an FSM" instead of them having to analyze whatever encoding of an FSM you write and infer that that was an FSM before you encoded it 00:07:09 -!- Bike has quit (Disconnected by services). 00:07:10 Aren't they related to the stack and such? 00:07:11 -!- Bike_ has changed nick to Bike. 00:07:25 Don't I risk bothering the stack if I toy with them 00:07:47 Bike: the entire practice of VHDL/Verilog appears to be deciding what you want, then writing it into VHDL/Verilog in such a way that the compiler will infer it back 00:07:49 Also what about ES FS and GS 00:07:54 Can I fuck with them 00:08:06 Slereah: SI and DI are not related to the stack, they're used as postincrement operators by some commands 00:08:14 and tend not to be efficient unless you use them like pointers 00:08:17 ais523: so, is it naive of me to think that that's fucking stupid, or am i missing something? 00:08:24 Okay 00:08:33 BP is related to the stack but it's mostly useful for debugging 00:08:52 bp is used in some programming languages as a "frame pointer", but you don't have to worry about that in your small test programs. DOS doesn't care about bp. 00:08:57 like, for god's sake, the actual FPGA is a bunch of LUTs and shit, and aren't there ALUs or adders or something at least 00:08:59 an interview question I like is "Explain how inlining could make code faster, or slower, or bigger, or smaller" 00:09:05 Bike: I guess it saves the language needing to evolve to adopt whatever basic structures the FPGA manufacturers add to their FPGAs 00:09:13 but apart from that I can't see any advantages 00:09:17 Oh wait 00:09:28 i think there should be a better way. i'll think about it, and then never do it 00:09:29 I need it to be 4 bits in my program to work 00:09:30 Dang 00:09:31 kmc: nice. 00:09:34 I guess I'll go with cl 00:09:44 Postdecrement too! 00:09:46 Bike: an actual FPGA is mostly LUTs and RAM (and wires), sometimes it'll have a few fast multipliers on or something like that 00:09:53 Slereah: yes, one of the big improvements in x86-64 is adding 8 more general purpose regs 00:10:08 fpga design seems super interesting really, i honestly like the idea of designing my own 00:10:08 Slereah: you mean 8 bits, hopefully? 00:10:13 Nope 00:10:14 -!- muskrat has joined. 00:10:14 4 00:10:17 and putting an HDL on top of it <_> 00:10:20 CL is 8 bits 00:10:24 there aren't any 4-bit registers 00:10:28 Oh 00:10:37 it's the bottom half of CX, which is 16 00:10:41 I guess I do mean 8 00:10:53 maybe i should look at your charity thingie 00:11:10 CLL and CLH and CHL and CHH should clearly exist. 00:11:18 er, was it charity 00:11:19 verity? 00:11:23 ais523: anyway, I'm not opposed to writing assembly code, but there should be a good reason :) 00:11:41 Well I do have a good reason 00:11:45 fizzie: well, they don't :) 00:11:47 Ferrets are nesting in my brain 00:11:50 ais523: what's that hdlish thingie you work on. 00:12:13 Bike: Verity, http://veritygos.org 00:12:22 although the person currently in charge of it does not fill me with confidence 00:12:25 (learning how stuff works is among the possible good reasons, btw) 00:12:48 oh no? 00:12:52 I got an email complaining that the compiler was emitting wires with no declarations, which is a reasonable complaint 00:13:14 then when I explain that it's generating incorrect code due to an error in the original program that it failed to notice (which is a bug) 00:13:24 their solution is to add declarations and then complain it still doesn't work 00:13:40 can't help but notice the "language" page is comparing to programming languages, not HDLs 00:14:24 Bike: it's pretty high level for an HDL, that's the entire point 00:14:35 mrm 00:14:36 actually it's a dialect of Algol 60 00:14:45 but you can't really say that nowadays without people laughing at you 00:15:18 nah, i like algol. 00:15:34 http://en.wikipedia.org/wiki/ELLA_(programming_language) it seems the standards for HDLs are not that high. 00:16:01 also there are a billion "C-like languages", why has god forsaken me 00:16:11 "C++ extended with HDL style threading and communication for task-parallel programming" 00:17:04 Woo, I did an addition 00:17:55 Let's try doing an iterative one 00:20:41 i just realized. is this what it's like to be sgeo 00:22:41 What are you referring to? Am I associated with complaining about uncreative languages? 00:22:53 Bike: Next you'll get involved in some virtual world stuff. 00:22:56 Or am I associated with something else that is similar to what you said? 00:22:58 -!- CADD has joined. 00:23:06 looking for 'the perfect HDL' 00:23:11 fizzie: god forbid. 00:23:21 Ah :) 00:23:38 Why am I writing smiley faces this is unircsgeolike 00:23:54 maybe your personalities are swapping 00:24:08 Bike: Just you wait, you'll be converting your savings account to Linden-dollars any moment now. 00:24:20 nooooo 00:25:47 `pastelogs bike> .*:) 00:25:55 grep: unmatched parentheses \ http://codu.org/projects/hackbot/fshg/index.cgi/raw-file/tip/paste/paste.9987 00:26:01 fancy 00:26:02 so VGA controllers are CRT only right 00:26:06 `pastelogs bike> .*:[)] 00:26:18 or... vga is i mean 00:26:47 http://codu.org/projects/hackbot/fshg/index.cgi/raw-file/tip/paste/paste.16433 00:26:51 "For example, the Microsoft Windows splash screen, in versions prior to Windows Vista, appears while the machine is still operating in VGA mode, which is the reason that this screen always appears in reduced resolution and color depth." oh, that's neat. 00:27:30 hm Bike isn't precisely a heavy :) user 00:29:03 Yay I did a square function 00:29:13 From a sum 00:29:15 so this is like 50% haskell, 40% other people, 9% me being nice to newbies, and 1% me being a dick to elliott 00:29:17 `pastelogs int-e> .*:[)] 00:29:28 percentages are not to scale 00:29:31 http://codu.org/projects/hackbot/fshg/index.cgi/raw-file/tip/paste/paste.27098 00:29:44 Slereah: say, you don't happen to have The Art of Computer Programming do ya 00:29:51 Nope 00:29:55 might be interesting to follow along, translating the code from MIX to x86 00:29:56 I don't even have SICP 00:30:05 I'm not even sure I have any computer related book 00:30:09 Except for like 00:30:12 Turing machines and shit 00:30:37 Hm, let's try a recursion maybe 00:30:41 Some factorial 00:31:28 int-e: now repeat after me, "My name is int-e and I am a :)holic" 00:32:09 nice 7 year hiatus. 00:32:40 oerjan: that's just a trick to get me to use yet another smiley, isn't it? 00:33:34 I won't even grep for semicolon-closing parenthesis, because I'm afraid the result will be even longer. 00:33:36 Slereah: are you a university student 00:34:10 I was, and I am once again! 00:34:14 Damn job market 00:35:12 int-e: oops 00:35:14 well, check the library, then 00:35:32 the :A movement is not starting well 00:35:37 -!- KingOfKarlsruhe has joined. 00:36:13 oerjan: Oh no! Z: 00:37:20 fizzie: it's like having the word for alcohol containing a phoneme that can only be produced by drinking it 00:37:53 those poor airholics are also in trouble, i fear 00:39:14 -!- Taneb has joined. 00:39:28 `ello Taneb 00:39:30 Hello, Taneb ! 00:40:10 Yo 00:40:11 Yoerjan 00:40:15 surely that should be Tanellob 00:40:36 The SCP-2000 contest is open 00:41:11 SCP 2000 is a contest that you cannot escape. hth 00:41:13 oerjan:whatdoyousayaboutallthosespaceholics? 00:41:52 what, are they already planning on the third scp series? 00:42:47 int-e : i don ' t see any problem 00:43:36 -!- carado has quit (Ping timeout: 252 seconds). 00:45:28 -!- carado has joined. 00:45:42 I guess I need to make one memory space per recursion if I want to do a recursive thing 00:45:51 hm 00:46:08 I will see about that tomorrow 00:46:10 stack! 00:46:10 It is my bedtime 00:46:15 Staaaack 00:46:31 a recursive "call" just works 00:46:53 But call doesn't send arguments 00:46:53 you may have to save registers with "push" and restore them with "pop" afterwards 00:46:59 So I do need to stack shit 00:47:05 call preserves registers 00:47:20 Just like in the doodoo olympics 00:47:22 you can use those for arguments, no trouble. 00:47:53 Yeah, but it's a factorial 00:48:08 There has to be a whole bunch of calls! 00:48:14 I guess n-1 00:48:22 Why is it always a factorial? 00:48:44 Because the factorial is an old and time tested recursive function! 00:48:55 You can also do Fibonacci, but Fibo needs two conditions 00:48:57 there are way better implementations though. 00:49:12 many of which involve far more fun things than recursion. 00:49:20 imo do tak or ackermann 00:49:39 -!- CADD has quit (Ping timeout: 246 seconds). 00:50:47 i am not sure ackermann with bounded size ints has quite the intended effect. 00:53:19 Well I'm limited to 255 00:53:21 what everrrr 00:53:22 So ackerman is a bad idea 00:53:41 damn. "09:27:05 I'll remember that, GregorR-W." -- I completely forgot. 00:53:58 -!- CADD has joined. 00:54:02 factorial will fail too after, what, 14? 00:54:24 wut 00:55:35 Gregor: http://int-e.eu/~bf3/tmp/remembering 00:55:48 (Oh and that was in july 2005.) 00:55:50 12, on 32 bits 00:56:30 for 16 bits it goes up to 8. imo whoopdie fucking do 00:56:42 -!- Phantom__Hoover has joined. 00:56:46 -!- carado has quit (Remote host closed the connection). 00:56:53 A lot has changed since July 2005. 00:57:01 For instance, I no longer specify my read/write status. 00:57:04 -!- carado has joined. 00:57:34 i remember that. 00:58:04 -!- oerjan has quit (Quit: Also. Good night.). 00:58:33 -!- Phantom_Hoover has quit (Ping timeout: 252 seconds). 01:00:02 !daemon 01:03:52 Gregor: is the Sonivox soundfont even sold anymore? 01:21:19 Sgeo: A quick look would appear to suggest "no" 01:21:58 :( 01:22:37 -!- Phantom__Hoover has quit (Remote host closed the connection). 01:34:39 -!- Taneb has quit (Quit: Leaving). 01:37:03 -!- Bike has quit (Ping timeout: 252 seconds). 01:42:09 -!- Bike has joined. 01:46:11 -!- carado has quit (Remote host closed the connection). 01:49:54 -!- Oj742 has joined. 01:51:12 -!- sergio2 has joined. 01:55:19 -!- sergio2 has quit (Ping timeout: 246 seconds). 01:57:46 -!- sergio1 has joined. 02:01:40 -!- Sprocklem has quit (Ping timeout: 245 seconds). 02:03:47 -!- sergio1 has quit (Ping timeout: 265 seconds). 02:27:19 -!- Sprocklem has joined. 02:30:50 -!- typeclassy has joined. 02:43:03 -!- Sprocklem has quit (Ping timeout: 245 seconds). 02:50:02 -!- typeclassy has quit (Remote host closed the connection). 03:10:33 -!- Oj742 has quit (Ping timeout: 245 seconds). 03:15:07 -!- adu has joined. 03:25:23 -!- shachaf has joined. 03:27:22 -!- adu has quit (Quit: adu). 03:58:46 -!- zzo38 has joined. 04:06:49 -!- adu has joined. 04:38:40 -!- adu has quit (Quit: adu). 05:09:02 -!- adu has joined. 05:09:13 -!- adu has quit (Client Quit). 05:27:42 -!- adu has joined. 05:29:09 -!- adu has quit (Client Quit). 05:44:20 -!- Sprocklem has joined. 05:49:52 anyone know how to write the kronecker delta as a non-piecewise composition of principal branches of elementary functions? 05:50:32 er, can you get a non-function out of function composition? 05:51:43 kronecker delta is a function 05:51:46 think man think 05:52:12 oh, i was thinking dirac :V 05:52:30 I am not sure what "principal branches" are, but perhaps 0^((x-y)^2) is a definition? 05:52:45 can you just take a hump function and compose it with itself infinitely many times 05:54:17 Bike: I didn't find a Wikipedia article about "hump function" 05:54:32 zzo38: 0^0 is indeterminate 05:55:02 0^0 is 1. 05:55:17 zzo38: a function with a hump at the origin (f(0) = 1) that decays to zero at infinities 05:55:32 shachaf: according to python it is zero 05:55:49 ^ is xor in Python. 05:55:50 quintopia: I think that is wrong then; 0^0=1 clearly (to me at least). 05:55:51 ** is exponentiation. 05:56:05 oh 05:56:06 O, yes, then in Python you need 0**0; what does it make? 05:56:07 my bad 05:56:12 Does it make anything? 05:56:13 yeah that'll work :D 05:56:15 -!- adu has joined. 05:56:25 * Bike grumbles 05:57:11 Bike: Then with such function unless f(1) = 1 also, then composing infinite numbers of times becomes an unknown response? 05:57:17 ?messages-loud 05:57:17 i don't understand why 0^0 is 1, since lim_{x->0+} 0^x is 0... 05:57:17 boily said 9h 36m 19s ago: you are the weirdest. 05:57:22 yeah, it would be zero, i don't know what i was thinking. 05:58:17 OK, it is unclear the intended context (if any) of boily's message. 05:58:21 0^0 is the number of functions from the empty set to itself. 06:00:08 i guess i'm thinking of the limit of successively steeper functions, like you do for dirac 06:00:11 shachaf: Yes, there is that, and several other reasons too, why zero to power of zero should make one. 06:00:28 so there's one function from empty to empty but zero from {empty} to empty? 06:00:40 Yes. 06:01:05 well thank god math makes intuitive sense. 06:01:30 i can't tell if that was meant seriously or the opposite of seriously 06:10:03 Bike: a function from {{}} to {} is a set of pairs (x,y) where x is in {{}} and y is in {}, such that for every x in {{}} there is y such that (x,y) is in the function 06:10:10 (and also no duplicates) 06:10:15 yeah i already got this explained 06:10:21 thanks anyway 06:10:30 a function from {} to {} is a set of pairs (x,y) where x is in {} and y is in {} (no such pair exists, of course), such that for every x in {} -- and then you're done because vacuous 06:10:35 sorry :P 06:10:52 basically with a function from the empty set, you trivially satisfy the requirement of covering all values in your domain. 06:10:55 set theory is so tedious 06:11:02 from the singleton set, you have to have at least one element of the codomain. 06:11:13 it's easier in type theory!! 06:11:17 (arguably?) 06:11:43 it's even easier in i'm asleep theory 06:12:56 what does infinite composition of logarithms give you 06:14:46 gallavanting about the plane. 06:35:40 -!- nisstyre has quit (Quit: Leaving). 07:06:52 Bike: I noticed you were writing stuff about FPGA and HDL; if you are able to design your own and make the actual one, then if it is open-source (or at least open-specification enough to know exactly how all the timing, connection, etc works, and the bitstream format) then I would buy it. 07:07:12 do you have four thousand friends who would also buy it, though 07:07:32 Bike gets down to brass tacks 07:07:50 Perhaps there may be a lot of HDL because a lot of people don't like the existing ones (including me), but I don't think there is the "perfect HDL". I designed HWPL to do the kind of things I think is good idea, but not necessarily everyone in agreement. 07:08:09 there aren't that many HDL, really 07:08:26 Bike: No, but you can find a lot of messages on various forums and stuff in internet, it seem like about four thousand might be interested 07:08:43 And then more people would learn and might use it too 07:08:45 well i'll keep that in mind for the kickstarter. 07:09:20 a few days ago i found out some neuro people i like sell an FPGA board (with just a boring lockedout FPGA but) for brainstuff, which is cool 07:09:26 clearly needs more neuromorphism imo 07:10:40 Since there are several advantages to a open-source FPGA (even if the company that makes the FPGA sells no open-source design software for it) 07:11:13 i guess i don't know what most people who buy fpgas actually use them for 07:11:27 there's a niche in education, and then prototyping? 07:12:09 a lot of finished products use them too 07:12:12 I don't really know either, but yes those may be some uses; there are several others too. 07:13:01 if you're planning to sell fewer than n thousand units, it's cheaper to ship programmed FPGAs than to design and fab your own chip 07:13:13 makes sense. 07:13:23 not sure how much open hardware would help there 07:13:31 also then you can field-upgrade the "hardware" which is nice 07:13:32 http://nsa.unaligned.org/ is a really cool project repurposing a bunch of HD video transform boards with FPGAs on them 07:13:43 However, with open-source FPGAs, many more uses would be enabled, such as reconfigurable computing, more accurate designs, and if you are making an ASIC it is guaranteed not to be slower than the FPGA. 07:14:00 240 W :o 07:14:28 really wish i knew more electrics 07:15:13 and yeah, good point about reconfiguring 07:16:04 gotta grab information and opportunities in the subfield of electrobrains where i can, i guess 07:19:12 I also don't like various things about Verilog, VHDL, and other HDLs that I also decided to make up a new one; what features are you looking for in a HDL anyways? One thing I like to have is a lot of macros. 07:21:39 i'd like good macros, good parametrized modules, and some sort of way to annotate things like FSMs for optimization 07:22:47 How do you want to annotate things like FSMs for optimization? Maybe it might help a bit, if you can specify some examples of how this would work. 07:23:23 not sure. i'd like the macros and modules to be involved enough that i could write out a state transition diagram, really 07:24:01 i don't see the point in compiling things "down" to gates if the toolset's just going to analyze it as an fsm anyway 07:24:45 Are the macros and parametrized modules in HWPL (my design) good enough for this? If not, I would like to improve it if it help! (HWPL does have the MODELS keyword, which can be used for optimization, but I don't know if this is sufficient for the purpose you are describing.) 07:26:20 I would like an example of what you mean, though, if you can do that. 07:28:28 ok, do you know how a serial adder works? 07:29:11 OK, yes I looked up in Wikipedia, and yes I found it is something I am familiar with. 07:30:11 it's pretty easily conceptualized as an FSM. you have four states, one for each combination of outputs, and each clock you transition to another state based on the inputs 07:31:00 Ah, OK, I understand. 07:31:20 in verilog you could write this as an always block on the clock edge, where the logic is a very tedious case on the state and the inputs 07:32:33 and if you write it out the synthesizer is going to compile it into whatever IR and /then/ analyze it to be an FSM 07:36:31 Dear Microsoft: It's fairly obvious that your process for generating the IE compatibility mode list involves monkeys at typewriters. Please stop. Love, Sgeo. 07:38:55 A serial adder only has one bit of state being the carry flag though, isn't it? 07:47:49 you need to keep the sum out stable through the clock 07:50:53 but yeah, the carry is the only one you need to worry about between transitions 07:54:35 i guess that's a distinction between state of the FSM and state of the circuit. 08:02:15 What explains this behavior: As long as Chrome (ium) is loading any page, even in another tab, it doesn't show title text when hovering the cursor over something. 08:06:07 is the hover thingy an OS-level GUI element? 08:06:37 maybe it's because there's a single compositor thread in charge of all talking to the OS graphics system, and it's busy doing something else? 08:08:16 you should find out whether servo has the same limitation, first you'll have to contribute code to show title text, also to have tabs 08:09:10 -!- yiyus has joined. 08:26:29 oh, i've onwdered about that too 08:27:35 I think Chrome actually serializes OpenGL calls and sends them to a single process 08:27:51 we will probably have to do something like that eventually, for WebGL 08:28:12 -!- CADD has quit (Quit: leaving). 08:28:17 but for now our approach is, separate GL context for each thread/process, sending textures between them using OS-level features for doing so (the same ones compositing WMs use) 08:28:29 e.g. sending GLXPixmaps on Linux 08:28:29 -!- CADD has joined. 08:28:34 -!- CADD has quit (Client Quit). 08:31:51 -!- carado has joined. 08:33:56 kmc: Hmm, I don't know. 08:53:11 I think that assessment of Chrome doing all GL stuff in a single process is correct, because on my system it used to go all "GPU thread has crashed" and disable hardware acceleration whenever I tried to go to a WebGL page. 08:53:20 -!- Sprocklem has quit (Ping timeout: 245 seconds). 08:59:48 -!- adu has quit (Quit: adu). 09:23:08 -!- Taneb has joined. 09:38:41 I would think a serial adder in HWPL might be something like: TRIGGER .CLOCK SET {.OUT,.CARRY} TO MUX({.CARRY,.X,.Y},$96,$E8); and something like that may be usable in other hardware programming languages too; would that work? 09:45:13 In fact it looks like a direct implementation of the state machine as well as being directly translatable to FPGA muxes. 10:00:24 -!- ais523 has quit. 10:08:27 -!- nooodl has joined. 10:11:19 -!- yiyus has quit (Read error: Connection reset by peer). 10:31:47 fizzie: I was never able to get webgl to work properly in chromium 10:32:07 It tends to just stop working for no reason 10:32:11 While in Firefox it just works 10:33:26 -!- zzo38 has quit (Remote host closed the connection). 10:52:55 FreeFull: It used to work with my old graphics card, then it stopped working when I upgraded hardware, then it again started to work after upgrading the browser. (Though this last is a bit tentative, I haven't used it much.) 10:55:23 -!- muskrat has left ("Leaving"). 11:01:40 So I be trying to do the factorial recursively 11:01:41 But 11:01:46 It doesn't seem to stop at 0 11:01:54 What might the dealio be 11:02:25 The program being http://pastebin.com/e5bNNSf1 11:02:41 Oh wait 11:02:45 I think I know now 11:02:51 The jump isn't well placed 11:02:57 NEVERMIND 11:09:16 factorial: pop ax, pop ax, dec cx, jcxz zero, mul cl, push ax, call factorial, zero: jmp prog 11:09:18 There we go 11:09:26 I should do a version with a jump instead of a call 11:09:35 That will avoid me the double popping 11:15:29 Typically you'd access any parameters on stack with something like mov ax, [sp+2] instead of popping off the return address. 11:16:36 Wouldn't that fill the stack if I don't pop it in this case? 11:17:09 you can adjust sp manually without popping, like 'add esp, 8' 11:17:14 Normally the caller pops the arguments off the stack after the call. 11:17:33 Yeah but because of reasons I had to drop it 11:17:40 Also it's a jump now: 11:17:41 Fiora: sp, in this case. 11:17:41 factorial: pop ax 11:17:41 dec cx 11:17:41 jcxz zero 11:17:41 mul cl 11:17:41 push ax 11:17:42 jmp factorial 11:17:42 zero: jmp prog 11:17:56 er, right, sp. 11:18:11 Wait 11:18:17 Why do I have jmp prog 11:18:24 I can do directly jcxz prog 11:18:24 It's not really a function call any more if you never ret. 11:18:46 factorial: pop ax 11:18:46 is there some reason ax gets pushed, and then like, popped right back off? 11:18:46 dec cx 11:18:46 jcxz prog 11:18:46 mul cl 11:18:46 push ax 11:18:47 jmp factorial 11:18:49 Much better 11:18:58 To keep the result? 11:19:07 Basically if I do 5! 11:19:10 but isn't pushing and then popping a no-op...? 11:19:17 First I put 5 in cx 11:19:25 I push it 11:19:29 And I jump to the function 11:19:40 It pops the stack to ax 11:19:43 decrements cx 11:19:50 So ax = 5, cx = 4 11:19:54 And multiplies them 11:20:04 And sends the result to the stack 11:20:13 So ax = 20, cx = 3 11:20:37 It's not really a recursive function as written. And the use of stack is indeed unnecessary. 11:20:42 Wait, I don't need it if ax stays the same 11:21:36 factorial: dec cx 11:21:36 jcxz prog 11:21:36 mul cl 11:21:36 jmp factorial 11:21:37 Much better 11:21:51 I guess it is more of a loop yeah 11:22:44 Also not a function; you can't call it from two places, because it always returns to the same place. 11:22:52 yeah 11:23:16 I tried doing it as a function, but 11:23:33 I did jcxz zero 11:23:35 zero : ret 11:23:43 But that didn't seem to work 11:23:53 Like the ret didn't returl to the proper place? 11:24:18 If you popped the return address off, no wonder. 11:24:55 I don't think I did when that was there 11:24:59 Well, let's try redoing it 11:25:12 If you don't mind calling conventions, you can just pass parameters (and return values) in registers, in which case it's very simple. 11:25:41 factorial: dec cx 11:25:41 jcxz zero 11:25:41 mul cl 11:25:41 jmp factorial 11:25:41 zero: ret 11:25:43 Seems to work! 11:26:16 It might be more generic if you had the proper initialization of al (to 1) inside the function. 11:26:36 al is actually initialized at cl 11:26:58 Hm 11:27:03 Oh, I guess that works too, since you decrement before the first multiplication. 11:27:07 I guess I need one more label if I want to do the initialization 11:27:21 You can use a label local to the function for the loop, if you like. 11:27:53 (With syntax depending on assembler, but starting with a period is common.) 11:28:50 factorial: mov ax, cx 11:28:50 doshit: dec cx 11:28:50 jcxz zero 11:28:50 mul cl 11:28:50 jmp doshit 11:28:50 zero: ret 11:28:52 There we ho 11:28:53 go 11:30:48 What would the recursive version look like? 11:33:25 Hm 11:33:41 I guess at each passage in the loop, it would push the stack with the address 11:33:45 And go back to that point 11:34:18 In half-pseudo, possibly something like factorial: if ax == 0 { mov ax, 1; ret } else { push ax; sub ax, 1; call factorial; pop cx; multiply ax by cx; ret } 11:35:17 That's the "direct" translation of factorial(a) { return factorial(a-1) * a; } 11:35:45 (With the convention of passing the input argument in ax, and the return value in ax too.) 11:36:02 Er, the latter is missing the termination condition, but anyway. 11:36:19 facrec: mov ax, cx 11:36:19 dec cx 11:36:19 jcxz zerec 11:36:19 call facrec 11:36:19 mul cx 11:36:19 zerec: ret 11:36:23 Let's try something like this 11:37:30 Hm, 0 11:37:35 Let's see 11:37:51 -!- Taneb has quit (Quit: Leaving). 11:38:05 Well, you decrement cx all the way to 0, and then return from the deepest "call facrec" right into the mul cx. 11:38:18 oh right 11:38:27 If it's 0 I need to return cx = 1 11:39:19 Still no work, damn 11:39:34 Let's see 11:39:45 All your "mul cx"s will use the same cx value. 11:40:01 If cx = 2, then ax = 2 11:40:19 Once decremented, cx = 1, ax = 2 11:40:55 Ah yes, it totally forgets the value of 2 on the second call 11:41:00 I need to stack 11:41:09 You can expand the control flow out what it executes: {mov ax, cx; dec cx;}*n, then {mul cx}*n. 11:43:12 You can do the recursive-with-an-accumulator variant -- factorial(x, acc) { if (x == 1) return acc; else return factorial(x-1, acc*x); } -- without using any stack except for the call/ret. (And then convert that to a tail call, after which you've ended back in the original solution.) 11:44:54 What's a good ASM debugger? 11:45:45 debug.com would be in keeping with your DOSBox style, but it might not fit the attribute "good" that well. 11:46:04 What about "functional" 11:47:01 There's a gdb stub built in DOSbox, if I remember right, but gdb can be p. iffy for 16-bit code, and I don't have any idea how easy that would be to get going on Windows. Of course the old 16-bit programming environments (Turbo C and such) come with debuggers too. 11:53:07 -!- Phantom_Hoover has joined. 11:55:05 Man dosbox is so slow 12:11:55 ctrl f12 a bit? 12:13:30 I think now is time for food buying, actually 12:20:17 you know what's infuriating 12:20:42 when you've downloaded 0.2% of a torrent and you're already uploading twice as fast as you're downloading 12:27:31 hahaha http://i.imgur.com/0vRuu.png 12:29:54 interesting 12:32:24 don't want to leave out the general complex case 12:33:39 -!- oerjan has joined. 12:34:28 also: http://www.wolframalpha.com/input/?i=what+is+the+planck+length 12:35:20 i am missing beardseconds as unit 12:37:23 Phantom_Hoover: amazing 12:39:07 "Comparison as length: ≈ 0.2 x length of a putative string in M-theory" 12:44:07 i didn't think string theory had fixed length strings 12:44:31 i suppose some might 12:48:23 I guess they use strncpy with them then aha ah ha. Haa. 12:50:57 _ _ _ _ _ _ 12:50:57 _| || |_ _| || |_ _| || |_ 12:50:57 _____ _____ _____ _____ _____|_ .. _|_ .. _|_ .. _| 12:50:57 |_____|_____|_____|_____|_____|_ _|_ _|_ _| |_||_| |_||_| |_||_| 12:51:09 wat 12:51:55 pasting ascii art doesn't mix well with irssi's line joining. 12:52:35 pasting ascii art rarely mixes well with irc 12:52:57 NONSENSE 13:07:04 -!- Slereahphone has joined. 13:09:08 good morning. how are the rabbits 13:09:44 LET ME TELL YOU ABOUT THE RABBITS 13:14:05 __ __ ___ ___ ___ ___ 13:14:06 | |_| | | \/ | | \/ | 13:14:06 | _ | | \ / | | \ / | __ __ __ 13:14:06 |__| |__| |___\/___| |___\/___| |__| |__| |__| 13:15:30 Oh no, who gave oerjan the really big swatter? 13:15:32 I'm scared. 13:16:44 is that what that was 13:43:56 -!- Slereahphone has quit (Quit: Colloquy for iPhone - http://colloquy.mobi). 13:44:35 i just used a temporary magnification ray. 13:46:31 And back 13:46:35 Time to cook de meat 13:49:24 -!- yorick has joined. 13:50:03 i don't understand why 0^0 is 1, since lim_{x->0+} 0^x is 0... <-- switch 0 and x in that... x^y does not have a limit at (0,0) and you can get several values by approaching along different paths. 13:51:38 so limits are useless for choosing a value. 13:56:03 0^0 is undefined 13:56:11 It is set at 1 by convention 13:58:39 hmm 13:59:47 Slereah, well no, it's just that 0^0 doesn't have a single 'nice' extension of the exponential function 14:00:22 you're going to break useful properties, most importantly continuity, no matter how you define it 14:01:40 yes, hence why it is not defined from the definition of the exponential! 14:01:41 it's normally taken to be 1 because that still preserves things like the number of functions from {} to {} 14:02:00 Slereah, well neither is x^y for x and y not positive integers 14:02:17 Well yes, it is! 14:02:28 x^y = e^(y ln(x)) 14:02:58 right but originally it was 'x multiplied by itself y times' 14:03:07 Sure, back in the 16th century 14:03:58 'well what if y is negative' 'make it reciprocal, that preserves the additivity' 14:04:24 'Charlie Stross @cstross: This morning got email from a “technical sourcer” at Google, wondering if I wanted a job interview. Told ’em to look me up on wikipedia …' 14:04:32 nobody is safe 14:04:39 'what if y is fractional' 'well make it a root, that preserves multiplicity' 14:04:46 etc. 14:05:15 But what if y is transcendant? :o 14:05:38 then you set it to the limit, because obviously you want continuity 14:06:03 What if y is a matrix 14:07:02 Phantom_Hoover: fortunately, by that point, 0^0 is already 1 :-) 14:07:37 but it's not, because you really want continuity from R^2 -> R 14:07:53 Slereah: then it better be diagonalizable, and we can then apply ^y to each diagonal entry. 14:08:04 Phantom_Hoover: I don't. 14:08:45 I'm happy with the state of affairs where that only works for positive x :) 14:08:56 With the exponential definition it is much easier~ 14:09:10 e^M = 1 + M + MM/2 + ... 14:09:19 Slereah: 2^2 = exp(ln(2)*2)? good luck ;-) 14:09:21 easier to define, not so easy to calculate 14:09:32 int-e : Yep 14:09:38 Pretty easy! 14:09:46 ln(1+2) = 1 + x + x² + ... 14:09:56 +x* 14:10:09 p. sure that expansion doesn't actually work for x outside of a certain range 14:10:24 It will work for ln(2) 14:10:31 Slereah: no. 14:10:31 http://en.wikipedia.org/wiki/File:LogTay.svg 14:10:56 Slereah: it's ln(1+x) = x - x^2/2 + x^3/3 - x^4/4 + - ... 14:11:03 Maybe 14:11:07 I don't remember it off hand 14:11:17 Slereah: well I wasn't the one who claimed this was the easy way :-P 14:11:21 it does actually work for ln(2), just 14:11:51 I think it basically works for C* 14:12:12 but now you're talking about holomorphic functions 14:12:21 They are the holomorphest 14:12:46 it doesn't work very well for C* because you can't pick a canonical choice of root 14:13:34 But well 14:13:36 Anyway 14:13:48 x^y is pretty much defined for most things with it 14:14:00 and how do you exclude ln(1) = 2pi*i ... if you go via the complex numbers? 14:14:19 Do you mean ln(-1) 14:14:22 no. 14:14:29 ln(1) = 0 14:14:32 no 14:14:37 (yes) 14:14:39 e^(2pi*i) = 1. 14:14:42 ln(1) = 2npi*i 14:14:48 for all integers n 14:15:06 Except not. 14:15:11 Because ln is a function 14:15:16 So it can only have one image 14:15:42 Slereah: from the positive reals to reals, yes. fine. we never argued about x^y for y>0 anyway. 14:15:50 or x>0, sorry. 14:15:55 yes, but the choice of branch cuts you use to obtain that unique image is as arbitrary as 0^0=1 14:16:14 Well you can define it with a parameter, I guess 14:16:25 ln(1,n) = 2npi*i 14:17:23 no. 14:17:41 Why not 14:18:12 the point is that if you want ln() to be continuous, and ln(1) = 0, then by taking the logarith of ln(e^(ix)) for x=0 to 2pi, you end up with ln(1) = 2pi*i. 14:21:21 -!- oerjan has quit (Quit: Use the Riemann surface). 14:25:07 (the principal branch of ln() that people usually use is discontinuous for negative reals) 14:32:33 -!- copumpkin has quit (Ping timeout: 252 seconds). 14:56:08 another thing I saw in Akihabara was an adapter which accepts an IEC 60320-C13 (i.e. computer power supply) cable and provides a universal AC outlet (NEMA 5-15 / BS 1363 / Europlug + various grounds) 14:56:30 i don't know what the use case for that adapter is, but it's an interesting one 15:05:12 One thing I found in my closet was a cable where the other end was an IEC 60320-C13 female, while the right end was the ungrounded europlug. 15:05:28 I don't know where that came from, and what the grounding pin of the power-supply-connector side is connected to. 15:05:31 Probably nothing. 15:06:41 (But, I mean, ground, right? Who needs that sort of stuff.) 15:08:35 not japan, that's for sure 15:09:16 (except for certain large appliances, which have a separate grounding wire that screws to a thingy) 15:17:10 whatever, things are made of plastic now, and we have GFCIs, and yolo 15:17:23 i don't get why some thinkpad bricks have ground lines and not others 15:20:03 -!- copumpkin has joined. 15:21:19 (I think "C13 female" is redundant; the inlet is called C14) 15:21:47 (but this is 100% from reading wikipedia just now to sound knowledgable, as is my custom) 15:26:23 hell is a torrent stalled at 99.9% 15:42:04 -!- MindlessDrone has joined. 15:42:57 kmc: i was amused to learn that stross used to work for SCO 15:57:45 fixed it by turning it off and then on again 16:23:35 -!- evalj has joined. 16:29:29 kmc: Since you're thereabouts, how about popping down to Kyoto and checking it out? We was thinking of visiting next summer. 16:31:26 i'm flying home tomorrow but I was in Kyoto the other day 16:31:42 it has a bunch of temples and shrines and such 16:31:45 if you're into that 16:33:03 cool castle 16:33:29 it's a short train ride from Nara and from Osaka, both of which are also worthwhile 16:34:21 We've visited some kind of Japanese-garden-style of a place pretty much everywhere else we've ever been (when possible), thought it might make sense to go straight to the source, so to speak. 16:35:12 :) 16:35:13 my itinerary for this trip was Suwon, Seoul, Osaka, Nara, Kyoto, Hiroshima, Itsukushima aka Miyajima, Tokyo 16:36:33 all were fantastic :) 16:36:58 in Nara i just kinda showed up at the train station and wandered around, but that doesn't work in Kyoto, the cool stuff is too spread out 16:37:14 i should have planned more in advance 16:39:09 We tend to have our trips planned in advance down to the very last detail, though not exactly by my choice. (Admittedly there's a slightly lower risk of "what, I was like right next to this cool thing and didn't even realize", afterwards.) 16:39:15 (well, ok, I'm not sure Suwon was "fantastic"; I was mostly there for work although there was half a day's worth of stuff to see at least) 16:39:33 yeah when i travel alone i tend to plan just in time 16:39:43 look on wikivoyage the night before i go out in some city 16:40:05 on this trip I spent a lot of time looking for free wifi because I wanted to talk to my friends because i was lonely :/ 16:40:17 and there's a small window in which the time zones coöperate 16:41:22 It's... seven hours ahead of Finland, I think. 16:45:02 speaking of Finland, http://i.imgur.com/zfsNaUl.jpg 16:45:32 that's Finland-themed Japanese fabric softener 16:45:36 they had Russia-themed as well 16:46:53 I can see the flag, but nothing else in that picture is exactly screaming "Finnish!" at me. 16:51:07 Skip & Hop! 17:00:38 this business of coin lockers at train stations &c is fantastically convenient 17:00:54 they exist lots of places but mostly not the US or the UK, because terrorism 17:04:21 got to sleep now 17:04:24 good night! 17:07:25 they don't exist in the UK? that's crazy 17:07:42 i may have wrong information 17:08:07 i thought the train stations got rid of coin lockers and trash cans both, thanks to the IRA 17:08:14 now you have to get on a train to throw something away 17:09:05 I know some banks don't have a user-accessible trashcan here 17:09:18 * Bike feels it's convenient that east asia and the UK are both eight hours away from his time zone. 17:09:31 but there people can just use a nearby trashcan in the street 17:10:18 but no trashcan in a railway station would be downright stupid, it would just lead to excessive littering 17:26:48 -!- sebbu has quit (Ping timeout: 245 seconds). 17:38:37 -!- Bike has quit (Quit: home). 17:46:53 -!- FireFly has quit (Ping timeout: 272 seconds). 17:52:06 -!- adu has joined. 17:56:55 -!- drlemon has joined. 18:03:09 -!- Oj742 has joined. 18:10:42 Oh 18:11:05 Are you guys talking about the lovely idea of removing public trash cans in order to prevent littering? 18:11:39 Even worse 18:11:43 Paying public toilets 18:11:46 I can't imagine to whom this sounds as a good idea but I'm no psychology genius. 18:11:48 What do you do with that 18:11:55 What if you don't have some coins 18:12:10 I'm pretty sure it's illegal to shit in the street 18:12:17 That's kinda the standard in switzerland @pay toilets 18:12:21 IT IS A FLAW IN THE SYSTEM 18:12:25 Unless you're a real men 18:12:39 *man 18:12:51 The Swiss always have money on them though 18:13:09 Yes 18:13:16 but that doesn't mean you have the right coin available 18:13:17 -!- sebbu has joined. 18:13:24 they don't take 10 CHF Bills . 18:13:53 https://dl.dropboxusercontent.com/u/113389132/Misc/20131123-smoking.png I'm sure there's some good, entirely logical reason why it's like this. 18:14:41 Well what do each character mean in both languages 18:20:48 'forbidden' and 'smoke' 18:20:50 in both 18:20:58 the chinese one is presumably wrong 18:21:55 alternative translations for the chinese include "no smoking" 18:22:11 Maybe it is so delicious because it is forbidden 18:26:15 http://cs.wellesley.edu/~cs342/handouts/more-assembly.pdf 18:26:16 Oh boy 18:26:18 There's one 18:26:19 Let's see 18:26:21 The "rfk86" account at zem.fi just got the following email: "Johnny Clunker was an awkward and shy kid who kept mostly to himself. But when the school day ended he became Johnny B. Fast, a super spy Utilizing super technology so advanced that it seems like magic, Johnny and his friends battle the United Order, a ruthless organization trying to acquire the Super Chip - a computer processor so ... 18:26:27 ... powerful it can virtually hold the world's technology hostage. But when one of his fellow classmates, Nancy Korrins, is also revealed to be a spy kid who was trained by the world's most deadly and advanced agent, Johnny has his hands full trying to figure out if he can trust her to help him capture the Super Chip, or if he has to fight her as his greatest rival." 18:27:43 -!- Taneb has joined. 18:28:30 fungot: Are you running on a Super Chip? 18:28:31 fizzie: great work lonely island afterall. but you dont post shit like that 18:36:08 What does the instruction pointer refer to, exactly? 18:36:14 Is it a memory space in the ram? 18:36:26 And if so, how do you deal with big programs on the hard drive 18:36:33 Do you transfer it little by little? 18:37:02 And does that imply restrictions on programs 18:37:32 Quite rarely do you load code on-demand. Program code doesn't tend to be as large as data. 18:37:46 Some DOS programs did use "overlays", including (IIRC) NetHack, though. 18:37:58 Sure, but I'm talking theoretically 18:38:36 Let's say you have a 10 GB program 18:38:39 (Pretty big!) 18:39:15 Does it mean that you could not do jumps from one end to the other 18:39:25 Or at least not without complications 18:39:45 I'm not sure if you want answers related to actual systems or what, if it's supposed to be entirely theoretical. 18:39:49 The IP refers to a memory address. That address may be mapped to RAM by the OS, or absent; if it's absent, then the OS gets notified and gets a chance to load the code from disk, for example. 18:40:02 Ah, I see 18:40:22 int-e: That doesn't sound like a theoretical answer. 18:40:22 I guess it goes to the RAM directly in the absence of an OS 18:40:33 Anyhow, in x86-32, you can't fit 10 gigabytes in the address space. 18:40:34 You really don't have to worry about it unless you write an operating system, or there is no OS to speak of (as was the case under DOS, hence the Overlays that fizzie mentioned.) 18:40:38 fizzie: it wasn't 18:40:51 (And in x86-16, even less so.) 18:41:02 I yet have to see a program with 10 GB of code :) 18:41:04 So indeed a ten-gigabyte program would involve complications. 18:41:18 It would be a pretty sweet program man 18:41:39 You could program the universe 18:42:00 -!- adu has quit (Quit: adu). 18:42:21 You can still load code at runtime if you absolutely have to. (The necessary technology is present in just-in-time compilers, albeit for a different purpose) 18:42:24 This afternoon I had my first session of D&D 18:42:37 Were you a wizard 18:42:39 Perhaps a 18:42:41 Computer wizard 18:42:44 I was a cleric 18:42:55 did you heal any undead? 18:42:57 We had a wizard/rogue in the party, though 18:42:59 A computer cleric? 18:43:07 int-e, I had the opportunity, I cannot recall if I did or not 18:43:14 Stallman is a computer cleric 18:44:37 http://lemonodor.com/images/sicp-lecture-wizard-s.jpg 18:44:44 Sussman is a computer wizard, though 18:45:15 Who would be the computer barbarian? 18:45:34 Schneier looks like one, I think. 18:45:57 I would talk about computer thief, but that might get controversial! 18:46:32 Snowden? 18:46:52 He is the computer spy 18:47:34 Computer rogue? 18:47:42 Perhaps 18:47:43 Computer paladin? 18:47:51 Knuth is the king of computers, I suppose 19:05:16 First output from a markov-chain thingy I'm making: "Just the place for a season of woe- But the Snark, with a Snark." 19:05:19 (with quotes) 19:27:42 Snarky. 19:29:53 -!- nisstyre has joined. 19:31:19 I need to figure out a way to make it parse punctuation as separate tokens 19:40:38 -!- AnotherTest has joined. 19:45:45 -!- Taneb has quit (Quit: Leaving). 19:49:21 -!- MindlessDrone has quit (Quit: MindlessDrone). 19:49:27 Sorry, but McCarthy = king of computers. :-) 19:49:42 -!- FireFly has joined. 19:50:26 Damn that man and his anticommunist policies! 19:53:45 -!- Oj742 has quit (Ping timeout: 252 seconds). 19:54:36 "if your grave doesnt say "rest in peace" on it you are automatically drafted into the skeleton war" 19:54:40 True fact. 20:04:45 -!- coppro has changed nick to coppro|nospoiler. 20:08:10 `run python -c 'l = [[0]]*2; l[0][0] = 1; print l' 20:08:16 ​[[1], [1]] 20:08:59 `? 20:09:01 ​? ¯\(°_o)/¯ 20:09:01 | 20:09:02 o/`¯º 20:09:44 ? _/..\ 20:17:48 -!- oerjan has joined. 20:27:01 kmc: Regarding the use case for your adapter, perhaps the idea was that you're going to have a large piles of those computer power supply cables (with wall-plugs proper to your walls) anyway, so they can sell their universal outlet to a wide audience without having to worry about the "input side". 20:27:41 A large piles, yes. 20:30:15 oerjan: i am aware of the fact x^y has no limit as 0^0. what i don't understand is why CAS implementers picked 1 20:34:32 because amongst other things x^y is the number of functions from a set of cardinality y to one of cardinality x, and there's 1 function from the empty set to itself 20:34:55 0^0=1 also cleanly extends some combinatorial identities, afaik 21:02:56 -!- muskrat has joined. 21:04:14 -!- zzo38 has joined. 21:04:21 quintopia: intuitively, consider the fact that polynomials and power series are among the most important objects in mathematics, and the sum_{i=0}^n a_i x^i formulation only works if x^0 = 1 without exception. 21:08:32 -!- Taneb has joined. 21:27:06 oerjan, btw, does the axiom of regularity require that it's impossible to do an 'infinite descent' through a set? 21:27:20 yes, that's equivalent. 21:27:52 and was iirc von neumann's original formulation. 21:28:03 oh, it says exactly that in the fourth line of the wp article 21:28:21 which is about where i last read it. 21:28:34 although not the first time, i think. 21:30:55 What is an "infinite descent" through a set? 21:31:30 zzo38: an infinite sequence such that x_0 is in the set and x_{i+1} is an element of x_i. 21:31:45 or well, x_0 might just be the set. 21:32:16 hm or maybe von neumann's original formulation was the thing about ordinal rank. 21:33:41 -!- augur_ has quit (Remote host closed the connection). 21:35:11 hm wikipedia's history section disagrees, maybe. 21:35:11 oerjan: O, that's what it is. 21:35:44 I've heared of that infinite descent thing but that's so ugly complicated that it shouldn't be an axiom. 21:35:55 the current formulation fo the axiom of regularity is much better 21:36:07 and the set ranks should be the theorem 21:36:41 it seems von neumann had a simple formulation. 21:37:07 however, the entire _point_ of the axiom is to rule out the infinite descent stuff. 21:37:35 and get the ranks. 21:37:51 yes. and? 21:38:00 the simple formulation still should be the axiom 21:38:08 it's easier to work from there 21:38:32 (not that you really need regularity for anything) 21:38:32 i'm saying it shouldn't be given alone since it obscures the purpose. 21:40:07 maybe 21:40:43 people care about the elegance of ZFC axioms? :/ 21:41:26 Eleven herbs and axioms 21:44:25 -!- typeclassy has joined. 21:47:07 -!- zzo38 has quit (Quit: zzo38). 21:47:13 -!- gigimoi has joined. 21:49:19 * oerjan smells a haskeller 21:49:53 `WeLcOmE typeclassy 21:49:56 TyPeClAsSy: WeLcOmE To tHe iNtErNaTiOnAl hUb fOr eSoTeRiC PrOgRaMmInG LaNgUaGe dEsIgN AnD DePlOyMeNt! FoR MoRe iNfOrMaTiOn, ChEcK OuT OuR WiKi: . (fOr tHe oThEr kInD Of eSoTeRiCa, TrY #eSoTeRiC On iRc.dAl.nEt.) 21:50:13 `WELCOME gigimoi 21:50:15 GIGIMOI: WELCOME TO THE INTERNATIONAL HUB FOR ESOTERIC PROGRAMMING LANGUAGE DESIGN AND DEPLOYMENT! FOR MORE INFORMATION, CHECK OUT OUR WIKI: . (FOR THE OTHER KIND OF ESOTERICA, TRY #ESOTERIC ON IRC.DAL.NET.) 21:50:33 hola 21:50:39 oh. 21:50:48 `bienvenido gigimoi 21:50:50 gigimoi: ¡Bienvenido al centro internacional para el diseño y despliegue de lenguajes de programación esotéricos! Por desgracia, la mayoría de nosotros no hablamos español. Para obtener más información, echa un vistazo a nuestro wiki: http://esolangs.org/wiki/Main_Page. (Para el otro tipo de esoterismo, prueba #esoteric en irc.dal.net.) 21:51:03 I'm not spanish : ) 21:51:19 ARE YOU SURE 21:51:38 Not 100%, but pretty sure. 21:52:05 we have a regular inflow of spanish people getting here and getting confused. we think it's because the channel name starts with es. 21:52:26 Lol. 21:52:26 well, sometime regular. it's been a while since the last one. 21:53:42 hehe 21:54:22 strictly speaking, not spanish, i think an unusual number are venezuelan. 21:54:54 but suffice to say that i now have a reflex action on newbies saying "hola". 21:54:59 *+it 21:55:55 oh that's news to me. "" 21:55:55 Javascript is required to use IRC. 21:56:28 at least to past quotes properly inside quotes. 21:56:31 *paste 21:56:38 lso to spel corectly 21:57:21 oerjan: I did place the cursor between "" and then I pasted ... but a newline defeated my perfect plan. 21:57:29 i suspected. 21:58:10 someone is being secretive. 21:58:21 it's irssi. :P 21:58:42 i suspected that, since i have it too and pasting is a regular annoyance. 22:02:36 -!- augur has joined. 22:05:55 oerjan: I'm actually wondering why firefox put a newline there, all I did was triple click on the first line of https://webchat.freenode.net/ (without javascript enabled, obviously). 22:06:23 But I guess it boils down to stupid software being stupid. 22:16:56 -!- nisstyre has quit (Read error: Connection reset by peer). 22:20:09 -!- augur has quit (Read error: Connection reset by peer). 22:20:26 -!- augur has joined. 22:28:45 -!- augur has quit (Ping timeout: 245 seconds). 22:29:57 -!- AnotherTest has quit (Ping timeout: 252 seconds). 22:30:28 -!- augur has joined. 22:33:41 -!- typeclassy has quit (Ping timeout: 248 seconds). 22:39:14 -!- adu has joined. 22:40:17 -!- evalj has quit (Remote host closed the connection). 22:52:37 hey 22:52:40 hey people 22:52:57 `ello quintopia 22:52:59 quintellopia 22:53:11 http://mathoverflow.net/questions/149620/easy-way-to-prove-that-this-algorithm-eventually-terminates solve this thing! 22:53:21 -!- Kevin has joined. 22:53:46 -!- Kevin has changed nick to Guest6589. 22:56:45 -!- Guest6589 has quit (Client Quit). 23:10:11 -!- adu has quit (Quit: adu). 23:12:59 -!- adu has joined. 23:29:06 -!- typeclassy has joined. 23:36:37 -!- augur has quit (Quit: Leaving...). 23:45:58 -!- typeclassy has quit (Ping timeout: 245 seconds). 23:46:38 copumpkin: hi did you ever read that thing 2013-11-24: 00:06:11 -!- Sprocklem has joined. 00:08:14 http://imgur.com/gallery/IkUDj 00:10:38 have the youtube commenters migrated to imgur 00:13:33 -!- kmc has set topic: SUNTORY BOSS is the boss of them all since 1992 | Koirammekokaan ei lennä? :( | https://dl.dropboxusercontent.com/u/2023808/wisdom.pdf | logs: http://codu.org/logs/_esoteric/ or http://tunes.org/~nef/logs/esoteric/. 00:15:03 -!- prooftechnique has joined. 00:17:26 hmm 00:17:57 i see a few places calling the real plane with a point at infinity 'projective' (e.g. http://en.wikipedia.org/wiki/Elliptic_curve#The_group_law ) 00:18:12 this does not make much sense to me 00:18:16 TRESPASSERS W 00:20:56 oh, in that article it's the specific point at infinity corresponding to the y axis 00:21:03 shachaf: :) 00:21:43 the projective plane has a line at infinity, not just a point. 00:21:53 * kmc -> afk 00:22:08 oerjan, this is why i was confused 00:22:47 (while we're at it: is the surface at infinity of the 3d projective space a 2-sphere or the projective plane?) 00:27:10 eep 00:28:04 the projective plane. 00:29:46 -!- zzo38 has joined. 00:30:16 in homogeneous coordinates, the subspaces at infinity are just the elements that have a fixed coordinate 0, so you cannot normalize it to 1. 00:30:41 but this is the same as the projective space of one lower dimension. 00:32:29 that is, R^3 embeds into the projective space as (x,y,z,1) and points of the form (x,y,z,0) are the infinite remainder. 00:42:46 oerjan, yeah, i realised this right after asking 00:43:19 it's just the subspace (x,y,z,0) over the same equivalence relation as the normal projective plane 00:48:36 -!- yorick has quit (Remote host closed the connection). 00:53:56 -!- impomatic has quit (Quit: impomatic). 00:55:23 -!- sebbu has quit (Ping timeout: 272 seconds). 00:56:47 -!- sebbu has joined. 01:02:14 Working on my own eso language, currently looks like this: https://github.com/gigimoi/B2D/blob/master/examples/fibonnaci.b2d 01:04:48 it's "fibonacci" hth 01:06:38 hm that would look better if [ and ] swapped meanings in the opposite direction 01:09:07 for years i thought it was fibocanni 01:10:01 I though paradigm was pronounced paradiggum 01:10:26 i thought that also 01:11:41 oerjan: And perhaps you'd use ⎴ and ⎵ when going up/down too? 01:12:00 it's ok, mispronouncing words because you've only read them is a sign of erudition (pretend i mispronounced the word "erudition" here) 01:14:41 fizzie: i see no point in using those little squares 01:14:58 Yes I have pronounce words wrong too due to only reading them, and so have other people, even Feynman was studying biology but never learned it in the class so he mispronounced everything too, and my father said he also mispronounced everything at first; a lot of people do. 01:18:09 `@ oerjan unidecode ⎴⎵ 01:18:11 oerjan: [U+23B4 TOP SQUARE BRACKET] [U+23B5 BOTTOM SQUARE BRACKET] 01:18:53 -!- Sprocklem has quit (Ping timeout: 245 seconds). 01:25:46 -!- CADD has joined. 01:31:24 -!- nooodl_ has joined. 01:31:37 -!- nooodl has quit (Ping timeout: 240 seconds). 01:39:18 -!- Phantom_Hoover has quit (Read error: Connection reset by peer). 01:41:37 -!- oerjan has quit (Quit: leaving). 01:56:39 -!- carado has quit (Ping timeout: 252 seconds). 02:13:57 -!- augur has joined. 02:28:45 The dancing Imakuni?'s card is much more useful than the ordinary Imakuni?'s card! (The dancing Imakuni?'s card allows you to make your active pokemon card sleeping, confused, paralyzed, or poisoned, according to your choice.) 02:31:21 zzo38, yesterday afternoon I played my first session of D&D 02:32:03 During which in the first encounter my character got transformed into a walking plot device 02:33:58 Which is kind of useful because now the party actually has a reason to keep me alive 02:34:11 (my character is the only nice character in the party) 02:34:47 Taneb: Ah, OK. Well, now you don't have to defend yourself against attacks they make against you, I suppose. 02:35:02 zzo38, I thought it was fun to play a pacifist 02:35:26 Taneb: Well, that is OK if you like to do so! 02:35:38 So far it's been a fun constraint for me at least 02:35:54 I think the rest of the party is a bit annoyed but then again they are all quite combat-oriented 02:36:08 I don't play combat-oriented though either 02:36:50 Also I do not associate a recording of my voice to me at all 02:37:04 Unless either I've just said it or there's a picture of me 02:38:01 -!- prooftechnique has quit. 02:38:39 Maybe it is true of some other people too though 02:38:55 -!- prooftechnique has joined. 02:38:57 Also I quite like my voice when I don't associate it with me 02:38:59 Do you like my own kind of playing of Dungeons&Dragons game? 02:39:02 But when I do I don't like it 02:39:09 zzo38, can you describe that briefly 02:40:33 ? 02:41:19 Well, I try to affect the situation rather than making direct attacks and so on (although sometimes I will, the other characters in my party are better at combat); I also like to play monster character. There are various other things too I do, such as strange spells, and I always try to conserve all spells and everything rather than use them, if possible 02:41:41 You would have to read it to understand (it is a file on my computer, you can download) 02:41:58 That sounds fun 02:42:20 I think it is the DM's first game, though, and I want to make it easy for him 02:42:31 So I'm sticking with his quest 02:42:32 OK 02:42:52 This is my game recording: http://zzo38computer.org/dnd/recording/level20.tex 02:43:31 (Whenever I update it, I will post a message starting with "`danddreclist" to this channel.) 02:45:05 Well, goodnight! 02:45:24 -!- Taneb has quit (Quit: Leaving). 03:01:49 -!- adu has quit (Quit: adu). 03:15:02 -!- Phantom_Hoover has joined. 03:15:04 -!- Phantom__Hoover has joined. 03:15:47 -!- Phantom__Hoover has quit (Client Quit). 03:15:51 -!- tertu has joined. 03:20:00 -!- Sprocklem has joined. 03:24:49 -!- gigimoi has quit (Ping timeout: 250 seconds). 03:59:14 "Please help us improve our service by answering a few questions about your experience: * Take the survey * No, I do not wish to take the survey at this time" 03:59:20 I feel like this is a trap. 04:00:05 The only winning move is not to play. 04:00:13 -!- sebbu has quit (Ping timeout: 272 seconds). 04:05:53 You could possibly ignore the question if you don't like it, I suppose. 04:07:11 Imakuni?'s card is *not* useless! 04:09:35 -!- polytone has changed nick to monotone. 04:11:27 -!- nisstyre has joined. 04:20:40 oerjan: what's with the infinite redirect in https://en.wikipedia.org/wiki/Peter_Johnstone 04:21:00 oerjan: and in the meanwhile completely ignoring https://en.wikipedia.org/wiki/Peter_Johnstone_(mathematician) 04:21:03 what's with that 04:33:53 -!- nooodl_ has quit (Quit: Ik ga weg). 04:37:42 -!- nisstyre has quit (Ping timeout: 240 seconds). 04:41:56 -!- Phantom_Hoover has quit (Read error: Connection reset by peer). 04:47:28 -!- jconn has quit (Remote host closed the connection). 04:47:42 -!- Jesin has joined. 04:50:15 -!- jconn has joined. 04:50:24 -!- Frooxius has quit (Read error: Connection reset by peer). 05:12:01 -!- prooftechnique has quit. 05:31:50 -!- Phantom_Hoover has joined. 05:55:45 -!- sebbu has joined. 05:56:23 -!- sebbu has quit (Changing host). 05:56:24 -!- sebbu has joined. 06:03:13 -!- Sgeo_ has joined. 06:05:25 -!- Sgeo has quit (Ping timeout: 240 seconds). 06:24:27 -!- Frooxius has joined. 06:26:05 http://www.reddit.com/r/shittyaskreddit/comments/1rc44v/i_dont_know_why_people_add_a_question_mark_to_a/ 06:27:01 ion: Because it's fun? 06:46:41 -!- Bike has joined. 06:46:55 kmc: http://i.imgur.com/87zBrsJ.jpg 06:49:04 Bike: totally 06:49:37 oh hey mispronunciation in the logs 06:49:45 today i found out that i've been saying 'array' wrong for presumably years 06:49:46 i live right by crescent park 06:50:14 those billionaires, man. somebody gotta do something 06:50:23 * Bike nods 06:52:38 i live on the east palo alto side of the border, though 06:53:05 Bike: is it "uh-ray"? 06:53:24 don't think so 06:53:24 which makes me the kind of people they want to keep out :'( 06:53:32 i already forgot though 06:53:40 not like i use it in conversation much 06:53:51 relatedly i explained what an FPGA is to my dad, that was fun 07:00:11 -!- Phantom_Hoover has quit (Ping timeout: 272 seconds). 07:05:40 -!- Sgeo has joined. 07:08:07 -!- Sgeo_ has quit (Ping timeout: 240 seconds). 07:24:47 -!- Bike has quit (Ping timeout: 272 seconds). 07:29:51 -!- tertu has quit (Ping timeout: 272 seconds). 07:38:05 https://pbs.twimg.com/media/A9aQ7DYCYAAb0fU.jpg 07:42:53 deja vu 07:43:53 -!- Sprocklem has quit (Ping timeout: 272 seconds). 07:44:57 -!- zzo38 has quit (Quit: zzo38). 08:10:45 -!- tromp__ has quit (Ping timeout: 272 seconds). 08:13:53 -!- tromp__ has joined. 08:25:20 -!- evalj has joined. 08:51:49 -!- evalj has quit (Ping timeout: 252 seconds). 09:07:12 -!- MindlessDrone has joined. 09:12:58 10:05:55 Sweet, can't used @ as a function name in haskell, but I can use @! Thanks. 09:13:02 i don't even 09:29:05 hah 09:39:11 unicode to the rescue 09:47:16 -!- Taneb has joined. 10:05:20 b_jonas: there are no trashcans in british train stations, except in rare cases in the form of clear plastic bags hanging freely (in the hopes that a bomb inside one would be visible, i guess) 10:05:44 and yet there is not much litter because britain 10:06:31 lexande, there are up north 10:06:46 really? i never saw one 10:06:50 I know Hexham and Newcastle both have bins 10:06:53 Because I've used them 10:06:56 (in the station) 10:07:00 huh, okay 10:07:11 also in new york the MTA can't manage to empty all the trash cans fast enough 10:07:15 so they overflow 10:07:18 Can't remember any in York but I've never had to wait in York 10:07:22 so they've removed the trashcans from some stations 10:08:11 so that people will take their trash outside rather than putting it in an overflowing bin 10:08:37 which seems like a parody of government-agency disfunction 10:09:00 but then, London once stored bags full of rubbish in giant piles in Leicester Square 10:09:42 s/dis/dys/; 10:10:10 s/government-agency/organisational/; 10:30:42 -!- muskrat has quit (Quit: Leaving). 10:38:04 -!- CADD has quit (Quit: leaving). 11:09:16 @ask kmc Do people often call you "Kegs"? 11:09:16 Consider it noted. 11:09:45 (I think I may have asked about that before.) 11:10:38 -!- Phantom_Hoover has joined. 11:19:18 fizzie: i have spent a lot of time around Keegan and have never ever heard anyone call him Kegs. 11:35:59 fizzie, you made fungot, right? 11:35:59 Taneb: this was acctully a computer could land by itself-with no one thinks the black guy, the crew. 11:36:18 Can you give me some tips for markov-chain text generation 11:37:43 I think fungot's trying to say they created themself 11:37:43 FireFly: nesun dorma in female roles only, i could show you a stack of proof from a sensationalist american tv-shows are not always right' mode. 12:04:32 -!- oerjan has joined. 12:06:09 -!- yorick has joined. 12:08:08 @messages-lewd 12:08:08 You don't have any messages 12:08:27 oh hm 12:09:01 Taneb: Well, I mean, fungot's just a ngram model, generating text from one is borderline trivial. 12:09:01 fizzie: you're not exactly gonna be relased....what a shame that it was mostly a maze involving a red line as the tail hit the trees or something? 12:09:29 fungot: how do you feel about fizzie insulting you 12:09:30 oerjan: wow like 10 mins ago i saw the poseidon go down quick enough. i think most can remeber their first flight" for " habsheim airbus crash" under search and watch the video above, it was 12:09:41 fizzie, I'm having trouble dealing with punctuation 12:09:53 i think he may not have noticed. 12:10:38 Taneb: I just preprocess that stuff. The tokens in the model for (foo.) look like POPAREN foo PDOT PCPAREN. 12:11:01 Taneb: (The Perl version keeps a stack of paired punctuation to ensure it matches, but that's not in the Funge version.) 12:11:29 yeah stacks are too hard in funge 12:11:58 oerjan: You're free to submit a patch, you know. 12:12:27 ^style irc 12:12:27 Selected style: irc (IRC logs of freenode/#esoteric, freenode/#scheme and ircnet/#douglasadams) 12:12:31 (Enough of the YouTubes.) 12:27:48 Welp 12:27:56 I did some little assembly things with the registers 12:28:03 Now let's try to fuck around with the RAM a bit 12:28:06 Addresses and shit 12:29:25 What the hell are you doing? 12:36:14 Learning my man 12:37:59 shachaf: fixed hth 12:40:40 @tell shachaf whoever made the redirect wiped out some stuff. also i don't see how it was infinite. 12:40:40 Consider it noted. 12:41:21 @tell shachaf you might learn to read wikipedia history diffs hth 12:41:21 Consider it noted. 12:47:07 -!- MindlessDrone has quit (Quit: MindlessDrone). 12:56:53 -!- Tod-Autojoined has joined. 12:57:13 -!- TodPunk has quit (Read error: No route to host). 12:57:25 > let x @! y = var $ x++': '++y in "myname" @! "yes, it's true" 12:57:26 :1:24: parse error on input `:' 12:57:29 wat 12:57:38 > let x @! y = var $ x++": "++y in "myname" @! "yes, it's true" 12:57:39 myname: yes, it's true 12:58:43 what is var for? 12:58:47 myndzi: myname: you two have to battle it out in a nick deathmatch. 12:59:07 which two? 12:59:10 ah 12:59:12 no 12:59:17 myname: removing quotes. technically it's some symbol representation thing. 12:59:32 :t var 12:59:33 String -> Expr 12:59:45 oh it's just Expr 13:00:04 oerjan: just make your client complete to the right one 13:01:01 > scanl1 (+) . map var $ cycle ["myname","myndzi"] 13:01:02 [myname,myname + myndzi,myname + myndzi + myname,myname + myndzi + myname +... 13:01:31 myname: it doesn't do so until the right one speaks 13:03:58 > fix (var "myname" +) 13:03:59 myname + (myname + (myname + (myname + (myname + (myname + (myname + (mynam... 13:04:06 nicely lazy 13:04:13 -!- Sorella has joined. 13:08:28 -!- carado has joined. 13:23:27 -!- nooodl has joined. 13:30:19 -!- oerjan has quit (Quit: leaving). 13:46:23 -!- sebbu has quit (Ping timeout: 245 seconds). 13:53:05 -!- evalj has joined. 14:04:57 -!- sebbu has joined. 14:05:37 -!- sebbu has quit (Changing host). 14:05:37 -!- sebbu has joined. 14:22:20 > expr "meow" 14:22:21 Couldn't match expected type `Debug.SimpleReflect.Expr.Expr' 14:22:21 w... 14:25:36 Bah. The (DS3) gamepad has stopped working in Windows again, after the 8.1 upgrade. 14:25:53 -!- impomatic has joined. 14:46:10 -!- tertu has joined. 15:00:20 -!- Koen_ has joined. 15:01:07 hello 15:09:03 -!- MindlessDrone has joined. 15:14:02 -!- ter2 has joined. 15:14:52 -!- tertu has quit (Read error: Connection reset by peer). 15:15:16 -!- Koen_ has quit (Quit: Koen_). 15:17:52 -!- MindlessDrone has quit (Quit: MindlessDrone). 15:35:16 -!- mrhmouse has joined. 15:42:03 -!- MindlessDrone has joined. 15:58:02 -!- nooodl_ has joined. 16:01:23 -!- nooodl has quit (Ping timeout: 240 seconds). 16:36:54 -!- Jesin has quit (Quit: Leaving). 16:44:09 -!- Taneb has quit (Quit: Leaving). 16:59:09 -!- Phantom__Hoover has joined. 17:02:07 -!- Phantom_Hoover has quit (Ping timeout: 272 seconds). 17:17:28 -!- MindlessDrone has quit (Quit: MindlessDrone). 17:17:48 -!- MindlessDrone has joined. 17:35:31 -!- sebbu has quit (Read error: Connection reset by peer). 17:35:57 -!- sebbu has joined. 17:36:40 -!- sebbu has quit (Changing host). 17:36:40 -!- sebbu has joined. 17:41:49 -!- muskrat has joined. 17:41:53 -!- muskrat has left. 18:00:49 -!- ais523 has joined. 18:03:19 -!- Phantom_Hoover has joined. 18:05:55 -!- Phantom__Hoover has quit (Ping timeout: 265 seconds). 18:09:49 -!- Phantom_Hoover has quit (Read error: Connection reset by peer). 18:16:14 -!- sebbu has quit (Read error: Connection reset by peer). 18:16:34 -!- sebbu has joined. 18:17:17 -!- sebbu has quit (Changing host). 18:17:17 -!- sebbu has joined. 18:24:49 -!- Phantom_Hoover has joined. 18:55:21 oerjan: what about https://en.wikipedia.org/wiki/Johnstone_(surname) though 19:00:05 fizzie: no, maybe a few people in high school....... why 19:01:57 -!- oerjan has joined. 19:02:59 :t expr 19:03:00 Expr -> Expr 19:03:49 FreeFull: expr is like a type restriction of id, to use when the usual Expr functions are so polymorphic that you get error messages like these: 19:03:53 > f x 19:03:54 No instance for (Debug.SimpleReflect.Expr.FromExpr a0) 19:03:54 arising from a us... 19:03:59 > expr $ f x 19:04:00 f x 19:05:01 > fix f 19:05:03 No instance for (Debug.SimpleReflect.Expr.FromExpr a0) 19:05:03 arising from a us... 19:05:09 > fix (expr . f) 19:05:09 f (f (f (f (f (f (f (f (f (f (f (f (f (f (f (f (f (f (f (f (f (f (f (f (f (... 19:05:41 @tell FreeFull see logs. 19:05:41 Consider it noted. 19:07:13 > f (expr . g . expr) x :: Expr 19:07:14 No instance for (Data.Typeable.Internal.Typeable 19:07:14 Debug.... 19:07:19 hm wat 19:07:35 i guess that might be a problem. 19:09:29 > f sin x 19:09:30 No instance for (Debug.SimpleReflect.Expr.FromExpr a0) 19:09:31 arising from a us... 19:09:38 > f sin x :: Expr 19:09:39 f Double> x 19:09:55 fancy 19:10:03 > expr . g . expr 19:10:04 No instance for (Data.Typeable.Internal.Typeable 19:10:04 Debug.... 19:10:32 > g :: Expr -> Expr 19:10:33 No instance for (Data.Typeable.Internal.Typeable 19:10:34 Debug.... 19:10:44 oh wait it's Expr itself which isn't Typeable 19:10:54 @let derive Typeable Expr 19:10:55 Parse failed: TemplateHaskell is not enabled 19:11:00 :( 19:11:17 hm not sure that's even correct syntax 19:11:51 -!- Bike has joined. 19:13:22 oh well i guess it couldn't print "f g x" even if it did. 19:15:23 > var "f g x" {- it can print anything -} 19:15:24 f g x 19:15:48 > fix var 19:15:49 Couldn't match type `Debug.SimpleReflect.Expr.Expr' 19:15:49 with `[G... 19:15:56 @ty var 19:15:57 String -> Expr 19:16:09 > fix fix 19:16:10 Occurs check: cannot construct the infinite type: a0 = a0 -> a0 19:16:10 Expected t... 19:17:33 > fix (show . (:[]) . var) 19:17:34 "[[[[[[[[[[[[[[[[[[[[[[[[[[[[[[[[[[[[[[[[[[[[[[[[[[[[[[[[[[[[[[[[[[[[[[[[[[... 19:17:54 Oh, you generated a lisp program 19:18:13 Unfortunately it's infinitely deep 19:18:22 > fix (show . flip (,) undefined . var) -- more lispy 19:18:23 "((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((... 19:19:43 blah! 19:19:43 > var(repeat'(') 19:19:44 :1:14: parse error on input `)' 19:19:53 > var(cycle "(") 19:19:53 (((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((... 19:20:15 that looks buggy. also i have a feeling i've seen that bug before. 19:20:21 but 19:20:25 it doesn't start with a " 19:20:27 and it's shorter 19:20:30 oh wait 19:20:30 so b_jonas wins 19:20:40 > var(repeat '(') 19:20:41 (((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((... 19:20:49 ' is a legal identifier character 19:22:17 > var$cycle"(" 19:22:17 (((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((... 19:22:24 as long as we're golfing 19:23:05 * quintopia flogs oerjan 19:25:05 kmc: Oh, no reason. 19:25:39 > cb 19:25:40 (((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((... 19:25:46 :t cb 19:25:47 Expr 19:26:27 Quick, generate lots of ]s or )s or the channel will capsize due to unbalanced parens. 19:26:45 ^ul ((])S:^):^ 19:26:46 ]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]] ...too much output! 19:26:53 Phew. 19:27:12 ] 999$')' 19:27:13 b_jonas: ))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))... 19:27:23 oerjan: what's that? 19:27:45 b_jonas: oerjan's code was Underload, http://esolangs.org/wiki/Underload 19:27:59 did jconn get renamed? 19:28:18 oerjan: it's a different instance 19:28:29 oerjan: we've had four or five different instances of the same bot 19:28:43 ) 999$')' 19:28:44 oerjan: ))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))... 19:28:44 evalj is mine, but I only run it occasionally 19:28:57 jconn is fftw's instance, he runs it all the time 19:29:00 how many bots do we have that can do Underload? 19:29:01 fungot, obviously 19:29:01 ais523: google will find plenty :) iz 3. 19:29:09 thutubot can but it's not online atm (nor is it normally) 19:29:10 Three, apparently. 19:29:13 can any of the non-eso bots do it? 19:29:14 !underload (hi)S 19:29:16 hi 19:29:22 ah right 19:29:23 we used to have two or three instances of buubot at some time too 19:29:28 now I think we only have one active 19:29:30 `interp underload (hi)S 19:29:34 hi 19:30:41 also, esobots tend to pick Underload and brainfuck to impl 19:30:44 presumably because they're easy 19:31:03 although thutubot doesn't do brainfuck because Thutu sucks at arithmetic 19:31:05 does any of them run dc? 19:31:41 `which dc 19:31:42 ​/usr/bin/dc 19:32:12 if i remembered how dc worked i'd check EgoBot. 19:32:16 ah right, a universal bot 19:32:38 and it uses backtick as the invocation character too, which is funny 19:32:43 because I chose backtick for termbot 19:33:30 oerjan: what about https://en.wikipedia.org/wiki/Johnstone_(surname) though <-- argh 19:35:00 `dc -e[[)]ndx]dx 19:35:01 ​))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))))) 19:35:47 https://dl.dropboxusercontent.com/u/113389132/Misc/20131124-reddit.png <- that was new for me. (Not that I diddit much.) 19:36:37 -!- zzo38 has joined. 19:37:11 `dc -e[93andx]dx 19:37:12 ​]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]] 19:37:29 `run echo '1 2 3 4 5' | dc - <(echo '0ss[q]sq[z1=qrls+ssdx]dxlsp') # easiest way to sum numbers in stdin? 19:37:30 15 19:37:47 this underload looks scary 19:38:08 b_jonas: it's probably my greatest esolanging accomplishment 19:38:32 because it is actually new and different and yet useful 19:39:25 ais523: can underload be translated to dc by some simple replacements, like replacing parens to square brackets etc? 19:39:34 quite possibly 19:39:43 or does this stack turned to program not allow that? I don't really understand underload 19:39:50 concatenative languages are known to be quite easy to interconvert between 19:39:57 although it won't be exactly the same due to the S command 19:40:12 yeah 19:40:13 the stack->program translation is really vital, though, it's the only way to be able to do control flow 19:40:29 there's a dc obfu that takes the length of strings that are also used as code 19:40:43 so if you try to replace parts of code it falls apart because the lengths are wrong 19:40:53 it's a brilliant method 19:41:17 now I'm wondering why anyone would ever want to obfuscate dc code 19:41:29 shachaf: made it a disambiguation page instead. 19:41:37 anyway, I consider S a design mistake in Underload, but given that I hardly ever work on its successor Underlambda… 19:41:41 ais523: you're asking that on #esoteric ? you can't be serious 19:42:26 b_jonas: I was; it's like asking "why would anyone ever think of writing a standard library for BackFlip" 19:42:34 fizzie: reddit not loading happens all the time. 19:42:42 mind you, I shouldn't call it a brilliant idea 19:42:46 it's the sort of thing that just didn't occur to me that it might be a useful operation, nor even do just for the hell of it 19:43:02 fizzie: nice dc, also what? 19:43:04 given that that perl obfu I showed you yesterday uses exactly this trick: it re-uses its code as data so you can't change its code 19:43:23 `perl -eeval for'for$=(2..27){$*=0;$*=($**$=+ord)%127,for/./gs;print+chr$*}'."\n#ig\\tq\24^-/v\c^l,\23\$%\3\ta2\tk\b\c\)\x18 -- ambrus" 19:43:25 ​$* is no longer supported at (eval 1) line 1. \ Just another Perl hacker, 19:43:37 i've never written code for dc, is it actually usually like '0ss[q]sq[z1=qrls+ssdx]dxlsp' ? 19:43:53 `perl -eeval for"for\$^(2..27){\$==0;\$==(\$=*\$^+ord)%127,for/./gs;print+chr\$=}\n#P*h!9= Nn[\c\9\0*.:\eUt\17%j{dY\31 -- ambrus" 19:43:54 obfuscating Perl makes sense, both because people have competitions in it, and because you might want to stop people reading your Perl source and yet have the compiler understand it 19:43:55 Just another Perl hacker, 19:43:56 kmc: yeah, it always looks like that 19:44:00 I sometimes use dc. 19:44:00 kmc: yes 19:44:11 I have some dc code somewhere 19:44:26 basically because dc was originally intended for arithmetic, which it devotes most of its readability to 19:44:43 and everything else gets pushed into a few keywords which are single consonants 19:44:47 ais523: also it was written back when memory was really expensive 19:44:50 and probably vowels too, but nobody uses those 19:44:52 dc looks almost as obfuscated as TECO 19:44:57 so the original dc had to be implemented in a very tight space 19:45:05 obviously it's gained a few more primitives since, 19:45:10 but the basics haven't changed 19:45:13 "back when memory was really expensive, and probably vowels too" 19:45:33 kmc: but nobody uses those 19:46:02 are there any esolangs with Hangul syntax? actually I asked this before and the answer is "yes" but there should be more because, Hangul owns 19:46:03 Actually I think dc is OK 19:46:26 `dc -e1dp[pdsd+ldrlxx]dsxx 19:46:27 1 \ 1 \ 2 \ 3 \ 5 \ 8 \ 13 \ 21 \ 34 \ 55 \ 89 \ 144 \ 233 \ 377 \ 610 \ 987 \ 1597 \ 2584 \ 4181 \ 6765 \ 10946 \ 17711 \ 28657 \ 46368 \ 75025 \ 121393 \ 196418 \ 317811 \ 514229 \ 832040 \ 1346269 \ 2178309 \ 3524578 \ 5702887 \ 9227465 \ 14930352 \ 24157817 \ 39088169 \ 63245986 \ 102334155 \ 165580141 \ 267914296 \ 433494437 \ 701408733 \ 1134 19:46:37 kmc: It doesn't always look quite like that if you're just using it interactively to do some arithmetic. 19:46:37 `dc -e1d[prdk+KdZ5\>x]dsxx 19:46:39 dc: dc: dc: dc: dc: dc: dc: dc: dc: dc: dc: dc: dc: dc: dc: 1 \ '\' (0134) unimplemented \ 1 \ '\' (0134) unimplemented \ 2 \ '\' (0134) unimplemented \ 3 \ '\' (0134) unimplemented \ 5 \ '\' (0134) unimplemented \ 8 \ '\' (0134) unimplemented \ 13 \ '\' (0134) unimplemented \ 21 \ '\' (0134) unimplemented \ 34 \ '\' (0134) unimplemented \ 55 \ '\' 19:46:39 http://esolangs.org/wiki/Aheui 19:46:46 what? 19:46:53 `dc -e1d[prdk+KdZ5>x]dsxx 19:46:54 1 \ 1 \ 2 \ 3 \ 5 \ 8 \ 13 \ 21 \ 34 \ 55 \ 89 \ 144 \ 233 \ 377 \ 610 \ 987 \ 1597 \ 2584 \ 4181 \ 6765 19:47:21 `dc -e'4 5*p' 19:47:22 dc: ''' (047) unimplemented \ 20 \ dc: ''' (047) unimplemented 19:47:26 `dc -e4 5*p 19:47:27 `dc -e1d[pdk+Krlxx]dsxx 19:47:28 20 19:47:29 1 \ 2 \ 3 \ 5 \ 8 \ 13 \ 21 \ 34 \ 55 \ 89 \ 144 \ 233 \ 377 \ 610 \ 987 \ 1597 \ 2584 \ 4181 \ 6765 \ 10946 \ 17711 \ 28657 \ 46368 \ 75025 \ 121393 \ 196418 \ 317811 \ 514229 \ 832040 \ 1346269 \ 2178309 \ 3524578 \ 5702887 \ 9227465 \ 14930352 \ 24157817 \ 39088169 \ 63245986 \ 102334155 \ 165580141 \ 267914296 \ 433494437 \ 701408733 \ 11349031 19:47:40 no idea about this bracket stuff 19:47:43 or any of the other stuff 19:47:52 stuff in general, tbh 19:48:03 Brackets are like Underload parens hth 19:48:27 In fact the TeXnicard programming language is based on dc and Underload (well, one of its embedded programming languages anyways; there is another used for graphics, and another used for booster packs and deck construction, etc) 19:48:30 pretty much all concatenative languages have something equivalent to Underload parens, unless you're intentionally trying to make one that doesn't 19:48:32 And x is like Underload ! hth^2 19:48:37 (such as dei, which I don't think is on the wiki) 19:48:56 Er, I mean ^. 19:49:08 (I don't know how I got that wrong, brain fart.) 19:49:12 zzo38: sounds scary 19:49:12 brackets are for quotation I suppose? 19:49:19 I should learn dc.. 19:49:30 FireFly: yes 19:49:53 huh. meta 19:50:46 dc has many esolang-like properties 19:51:35 FireFly: Brackets introduce strings, which are used for code blocks too. 19:51:48 so "e1d[prdk+KdZ5>x]dsxx" pushes 1,1,"prdk+KdZ5>x" to the stack, puts "prdk+KdZ5>x" in the "x" register, and then pops "prdk+KdZ5>x" from the stack and executes it? 19:51:56 er, scratch the initial e 19:52:29 hi Bike 19:52:32 himc. 19:52:39 sup 19:52:45 not much 19:52:49 waiting at LAX for my flight home to SF 19:53:41 Bike: Yes, that would do 19:53:42 Bike: some explanation in http://www.perlmonks.com/?node_id=627011 19:53:45 and yes 19:53:53 `dc -e[d91aPP93aP[dx]P]dx 19:53:55 ​[d91aPP93aP[dx]P]dx 19:53:56 `interp underload (:aS(:^)S):^ 19:53:58 ​(:aS(:^)S):^ 19:54:19 hm... but then p should pop 1 from the stack and print it, leaving the stack as just a 1, so what's r do? 19:54:23 maybe i should actually learn the korean language instead of just obsessing over how cool the alphabet is 19:54:34 It's not quite as clean as the Underload version because there's no equivalent of "a". 19:55:23 Bike: swaps the other 1 with the long string 19:55:42 but i thought x popped the string to execute it 19:55:49 yes, but it got duplicated by d 19:55:56 hmm wait 19:55:59 but s popped it 19:56:02 oh, wait 19:56:05 p doesn't pop 19:56:09 it prints but doesn't pop 19:56:13 oh. 19:56:16 ok. 19:56:57 ais523: this underload is awesome 19:57:08 thanks 19:57:25 k sets the precision... i thought dc used bignums 19:57:46 I love this bit of the dc man page, regarding P on a number: "Assuming that (UCHAR_MAX+1) is 256 (as it is on most machines with 8-bit bytes), the sequence KSK0k1/_1Ss [ls*]Sxd0>x [256~Ssd0qaPlxx] dsxxsx0sqLqsxLxLK+k could also accomplish this function." 19:57:48 It does use bignums, although some operations still need the precision 19:57:52 Bike: here we use the precision as just a register 19:57:54 They're not shy about what it looks like. 19:57:57 -!- nooodl_ has quit (Read error: Connection reset by peer). 19:58:00 oh. 19:58:01 uh, why. 19:58:02 Bike: we don't use any ops that precision changes 19:58:11 it's just that k is shorter than saving to a register 19:58:16 in this case 19:58:17 blah. 19:58:21 -!- nooodl_ has joined. 19:58:25 this was a golf attempt 19:58:43 Yes, I think I have done that too for golf attempt 19:58:46 you can see the history here: http://www.perlmonks.com/?node_id=490532 19:58:59 This is dc program implementing the XKCD variation of Deadfish: [p]1:z[d*]2:z[1+]3:z[1-]4:z[0sB]dsAx[lB0>AlB256=A0d?lBz;zxsBclCx]dsCx 19:59:24 Someone else implemented the ordinary Deadfish however that one has some problem dealing with the "s" command properly. 19:59:53 more variants at http://www.perlmonks.com/?node_id=626801 19:59:56 "f : R -> R is a continuous function with the property that for any fixed real number x, f(nx) -> 0 as n -> \infty. Show that f(x) -> 0 as x -> \infty." i think i'm a failure 20:00:27 i can't tell if they mean natural n 20:00:39 they must do, otherwise you just choose 1 as your fixed x 20:01:03 oh, yeah, ok. 20:01:07 and it's not an interesting question 20:01:24 a blog post linked about it specifies naturals too so there we go 20:01:46 i came up with a discontinuous counterexample and that's about it, go me 20:01:52 do you want me to give away the solution? I think I've got it 20:02:06 ah, hmm, no :( 20:02:23 well i already have "easy consequence of baire's category theorem" as a solution but i don't really know that theory 20:02:26 theorem 20:04:32 underlang is both awesome and scary 20:04:45 btw, does anyone happen to have a working running copy of wikiplia? 20:06:25 * oerjan swats b_jonas for misspelling underload -----### 20:07:06 oerjan: might want to deal with https://en.wikipedia.org/wiki/Peter_Johnston 20:07:37 thx 20:08:00 shachaf: um no i didn't change the others so why change that. 20:08:09 sorry 20:08:10 -!- Sprocklem has joined. 20:08:10 underload 20:08:44 `dc 448378203247P 20:08:45 dc: Could not open file 448378203247P 20:08:47 there isn't a really good article for that peter johnstone, the original was so minimal it got changed to a redirect to the list of governors. 20:08:51 `dc -e448378203247P 20:08:52 hello 20:09:04 hm 20:09:58 oerjan: well that one is already a combined disambiguation page for johnston and johnstone 20:10:14 oh hm that is true 20:10:20 argh 20:10:37 can i ban shachaf until he starts doing his wikipedia editing himself 20:10:39 FireFly: hmm, that's a good idea 20:10:56 something like the mod 127 polynomial obfu could possibly be translated to dc 20:10:58 oerjan: i need the experts to think of all the edge cases for me 20:11:01 otherwise i might miss something 20:11:03 I have it in perl and lua so far 20:11:33 shachaf: but you keep giving me extra work because you keep finding new edge cases! 20:11:58 b_jonas: oh, mind showing the lua version? 20:12:03 FireFly: let me find it 20:12:27 but yeah, the P command seems like a useful one to (ab)use 20:12:42 FireFly: you don't need P, you can use a 20:13:00 oh 20:13:05 I haven't gotten that far in the manpage yet 20:13:30 FireFly: http://dpaste.com/1481708/ 20:13:57 shachaf: anyway, i fixed the problem where someone who seeks for the mathematician might end up on a dead end with no way to him, which was the main problem afaiac. 20:14:07 that one also puts most of the code inside the string used for data, so you can't change the code, but for some silly reason my name is not in that string so you can change that 20:14:53 oerjan: that's true 20:14:59 (that was my original problem) 20:18:55 hmm, maybe I should try to write such a version of the GF(128) japh too 20:19:09 one where you can't just change the code that is 20:19:18 nah, no 20:19:27 that would be against its purpose 20:19:57 the point of my GF(128) obfu is to show off how easy it is to do calculations over GF(128) in perl 20:20:09 so the code should be changeable 20:22:02 Hm, so basically the idea is to treat the bytes in the string as coefficients of a polynomial, and compute that polynomial for x ∈ [2,26] (or however long a string you want to output) 20:22:02 easy not only in that the code is short, but that it does the computation vectorized working with all the coefficients at the same time 20:22:08 there's no explicit loops on the coefficients 20:22:12 FireFly: yes 20:22:52 Btw, you could change that ; in the string to a space for (slightly) more obscure code, I'm pretty sure 20:23:19 what semicolon in which code? 20:23:27 Or rather, less-expected-to-work code for someone not used to Lua's grammar 20:23:32 ah 20:23:34 in lua 20:23:46 yeah... you can often omit semicolons in lua 20:23:49 that wierds me out 20:23:55 Lua doesn't require any particular delimiter between statements 20:24:03 usually yes 20:24:16 the semicolon is required only when it would be ambiguous otherwise 20:24:21 Right 20:24:38 so which semicolon out of the three? 20:25:05 Er 20:25:12 Actually, I think all three 20:25:14 in the string... which out of two 20:25:23 I don't think any of them cause any ambiguity 20:25:32 yeah 20:25:34 ais523: i have a hunch lucasieks may be trying to make the pages fit within his browser width. 20:25:51 for the last one you could even remove it (the string and the identifier are separate tokens anyway) 20:26:00 well, 20:26:18 `which lua 20:26:19 ​/hackenv/bin/lua 20:26:23 oh neat 20:26:29 the second semicolon is after an end, which makes it less surprising you can omit it (for me as a perler) 20:26:46 i recall previously having a bug where i couldn't scroll properly rightwards when wikitables got too wide, although that seems to have been fixed for me now. maybe he still has that problem. 20:26:59 the third one uyou could omit but you'd still need the newline or it would be too wide 20:27:01 oerjan: I had a hunch that might be it too, but his solutions are really destructive 20:27:07 one of them put a newline in the middle of a keyword… 20:27:10 Btw, newlines in Lua has no special meaning either (i.e., newlines == spaces as far as the lexer is concerned) 20:27:20 (as in, my browser for some reason didn't detect that it needed a scrollbar when the reason was a wide wikitable) 20:27:21 FireFly: sure 20:27:31 and that part I like 20:27:42 I like that feature in perl and C too where it's mostly true about newlines 20:27:58 (and some other languages) 20:28:56 b_jonas: Algol 60 completely ignores whitespace 20:29:10 What, even for separating tokens? 20:29:11 ais523: some basics and some fortrans do as well 20:29:14 except that it's left undefined what the representation of a keyword is, and some compilers disallow whitespace inside keywords 20:29:14 Yes, I like that feature of how C and so on treats line breaks (except in C++ comments and preprocessor directives) 20:29:15 FireFly: yes 20:29:32 in so much that you can't write X OR Y in some basics because X OR is a token 20:29:32 all compliant Algol 60 implementations allow whitespace inside variable names, though 20:29:39 So the substring "for" is always treated as a separate token, say, even if it appears in "aforb" or something? 20:29:48 FireFly: in some basics, yes 20:29:54 FireFly: in Algol 60, it depends on the impl 20:30:08 the impl I have requires keywords to have no internal spaces but is insensitive to spaces around them 20:30:19 if you wand an identifier name aforb, you have to write it as af orb, for instance 20:30:20 FireFly: mind you, those basics also had 2 characters significant length of variable names, 3 significant of keywords, and small memory 20:30:37 OASYS does the same and it doesn't even have semicolons or whatever to separate statements. 20:30:58 ais523: that is.. weird. 20:31:39 -!- Taneb has joined. 20:31:40 Algol 68 is whitespace-sensitive, I think, but it still allows whitespace inside identifiers 20:31:53 Hi 20:32:37 but that's because algol/fortran was invented in the days of punch cards 20:33:22 -!- AnotherTest has joined. 20:40:48 I only ever made my own esolang once, and wrote only one program in it, and that one program was buggy. 20:41:00 I know now how I could fix that program, but have lost interest in it. 20:41:13 -!- Oj742 has joined. 20:41:17 I won't revive that esolang, but might try something with similar design later. 20:46:08 hmm... I wonder if it's possible to translate http://www.perlmonks.com/?node_id=989716 (arithmetic in Zeckendorf representation) to sed 20:46:20 it's all rewrite rules, so it's probably representable in sed 20:46:45 of course, there's already a famous calculator (using decimal) in sed, so it might not be worth 20:46:50 b_jonas: well, Thue is Turing-complete… 20:47:45 ais523: sure, 20:48:04 is it BF-complete, btw? 20:48:24 but I wonder if zeckendorf addition in particualr can be translated in a short and simple way 20:48:32 and I think it can 20:48:40 to sed that is 20:49:06 ais523: you cannot input an arbitrary string and be sure it doesn't mess up your program. 20:49:33 because it can always be identical to something you are using for internal data 20:49:53 oerjan: you can almost do it in sed 20:50:08 maybe you can completely do it 20:50:14 yeah, I think you can 20:50:20 oerjan: yeah, that's what I was wondering about 20:50:35 perhaps you could do something clever involving the ends of the string, but probably not 20:50:36 you can save the current buffer, read a string, do some replacements in it to make it safe, then load back the holded string 20:50:39 sed can detect end of string while thue cannot; i think this is the essential difference to some things. 20:50:50 *beginning and/or end 20:52:12 well regexes are much more powerful in other ways too. 20:53:28 well, sed is also more convenient 20:53:47 ais523: e.g. see the discussion on http://esolangs.org/wiki/Talk:Thue#Challenging_Problem 20:53:50 because it has match wildcards and can copy parts of the matched string to the replacement 20:54:01 (with the limitation that only the first nine parenthesis can be copied) 20:54:11 s/parenthesis/parenthesis group/ 20:54:30 oerjan: right 21:11:09 Hm, I wonder why dc's ? executes the input rather than pushing it to the stack... 21:11:39 the latter seems like it'd be more useful, and executing it is as easy as applying x to it anyway 21:11:44 because it's designed for interactive use, not as a programming language 21:12:47 -!- muskrat has joined. 21:13:10 fair enough 21:13:28 it foils my code-golfing plans, though 21:16:27 -!- AnotherTest has quit (Ping timeout: 272 seconds). 21:21:10 FireFly: what did you want to golf? 21:22:17 Oh, nothing in particular. I just thought dc seemed like it'd be neat for golfing 21:23:37 I see 21:25:38 -!- muskrat has quit (Read error: Connection reset by peer). 21:27:01 -!- muskrat has joined. 21:27:20 -!- muskrat has left. 21:31:15 -!- impomatic has quit (Ping timeout: 245 seconds). 21:32:12 -!- MindlessDrone has quit (Quit: MindlessDrone). 21:35:45 -!- FreeFull has quit. 21:42:17 ais523: perhaps a message on [[User talk:Lucasieks]] is warranted 21:42:38 elliott: I will if he does that more, I'm too apathetic right now 21:43:11 -!- ais523 has changed nick to ais523\unfoog. 21:46:27 Hi 21:47:25 -!- FreeFull has joined. 21:50:44 Can you play Yomi cards? I have made up three new decks of Yomi cards. 21:51:24 -!- typeclassy has joined. 21:57:07 Me? I don't even know what that is 21:58:03 FireFly, it is. 21:58:29 FireFly, I found that even if I don't try to golf in it, it ends up looking like an unreadable golfed program anyway 21:58:57 Vorpal: assuming you don't need to input things that aren't numbers or bracket-encompassed strings? 21:59:07 s/input things/read things from input/ 21:59:07 FireFly, well yea 21:59:18 Steam is advertising a pre-purchase option of "Professional Farmer 2014" to me. 21:59:18 I mostly used it to perform math from shell scripts 21:59:27 hah 21:59:36 20% off! 21:59:52 "Tractors And Farm Machines Get Your Farm Up And Running The PC simulator "Professional Farmer 2014" takes the player to the countryside and gives hobby farmers full control in the comfort of their home." 22:00:24 I never understood the craze for farming simulators 22:00:36 Nor truck simulators either. 22:00:46 I guess this is like the ultra-realistic "flight simulator" end of farming simulators. 22:00:52 Where Farmville and such are at the opposite side. 22:00:53 Heh 22:01:16 "Good Ol’ Times DLC: 7 additional, historical Tractor models for Professional Farmer 2014." 22:01:37 Included in the Collector's Edition, of course. 22:01:45 Heh 22:01:52 Anyway, I don 22:02:01 don't see why you would want to simulate farming 22:02:10 big machinery. 22:02:26 now with 15 extra manure options! 22:02:54 Bike, yes but tractors? Combine harvesters? Really? 22:03:13 why would you simulate mining and crafting 22:03:33 oerjan: "Agricultural Simulator 2013"'s "Key Features" include a freely placeable "Dung Tank". 22:03:38 elliott, alas, minecraft is not much of a simulation. It is way to "gameified" for that. 22:03:54 And that is for the better I would say 22:04:01 alas, it is for the better 22:04:53 I think I just got z-buffer fighting in a 2D program. That was weird. 22:05:05 Or something like that 22:05:11 Very very strange 22:07:28 I suppose the farm thing makes as much sense as the train thing, which I at least can somewhat understand. 22:07:45 Guess so 22:08:00 Flight sims and space sims I can see some point in. Especially space sims. 22:08:05 fizzie can only understand train simulations for doing logic in them. 22:08:31 elliott, that was OpenTTD, which is far from a train sim, again way too "gameified". 22:08:38 Vorpal: How about game development simulators? 22:09:03 * Bike the rural guy stands by and stares sidelong at Vorpal. 22:09:04 fizzie, oh yeah I heard of that, Haven't checked it out though. Somewhat of a management game iirc? 22:09:21 Vorpal: So I've understood. I only know of it because of the piracy thing. 22:09:51 Eh, not really interested in management games, so meh, couldn't care less. 22:10:34 (The pirated version has a tweak that, after some amount of time, people start to pirate all your games and your company will pretty much unavoidably tank, plus a guilt-trip message.) 22:11:13 Nice 22:13:11 http://en.wikipedia.org/w/index.php?title=Jamie_Zawinski&diff=582900523&oldid=prev need a source, stat 22:14:25 What is the bouncing cow screensaver?? 22:14:26 Bike: "man bouncingcow" says "Author: Jamie Zawinski", FWIW. 22:14:39 Vorpal: Part of XScreenSaver. 22:14:48 Ah, don't have that installed 22:14:54 I just blank the screen instead 22:15:10 Bike is a rural guy? 22:15:15 never seen the point of screensavers that don't save the screen by turning it off or blacking it out. 22:16:57 Presumably the point is that they're both pretty to look at, and still functional at avoiding burn-in. 22:18:15 Hm, I guess screensavers make more sense now again when there is OLED? I never heard of burn in with TN or IPS 22:19:59 There are so many technologies nowdays... TN, IPS, MVA, PLS, PVA... 22:20:31 It used to be that the only ones you ever heard about were CRT, TN and maybe IPS. 22:20:44 soon they'll run out of TLAs 22:23:02 oerjan, Wikipedia already lists AFFS as a screen technology, so they started early on that 22:23:24 good, good 22:23:29 Oh and there is also OLED I guess. 22:23:33 and AMOLED 22:24:00 IAMOL'ED 22:25:06 Hm I don't think each monitor around me has a different technology. Well okay not quite. There are three TN monitors with the laptops included, but apart from that I have one IPS, one AMOLED and one "Super PLS" 22:25:40 4 TN with the laptops included. I forgot the old first model ibook in the bookshelf. 22:26:22 mrhmouse: why, i live in the lentil capitol of the world 22:26:43 Bike, where is that? 22:27:09 http://en.wikipedia.org/wiki/Pullman,_Washington 22:27:12 there's a fucking festivavl 22:27:23 Ah 22:27:42 Bike, hey that isn't rural. 29799 inhabitants is quite respectable 22:27:50 That is a small city by Swedish measurements. 22:28:06 it's a small city by american measurements, and are you saying small towns aren't 'respectable'! 22:28:32 I live in a city that has a population of ~20000 22:28:53 Can't find up-to-date numbers on the web alas 22:28:56 anyway it's surrounded by farms and shit, is the point 22:29:02 Hm 22:29:06 Bike: *capital 22:29:08 the university has seed storehouses 22:29:13 oerjan: capitil 22:29:27 Bike, yeah I have like 300 m away to the closest field 22:29:32 I'm a city dweller 22:30:23 You guys are funny 22:30:34 mrhmouse, hm? 22:30:35 i used to be that close to a field too, although it was a pretty isolated one 22:30:42 look, i ain't gonna argue about my rurality penis. 22:30:49 (no pun here) 22:30:55 Bike: I respect your rurality penis 22:31:07 mrhmouse, I commute daily to a city with around 200000 inhabitants 22:31:11 thank you, mrhmouse 22:31:44 I went to highschool here: http://en.wikipedia.org/wiki/Excel,_Alabama but I grew up about fifteen miles from there (and it was the closest town) 22:31:52 oerjan, eh I just live near the edge of the city. 22:32:12 Excel, Alabama, twinned with Word, Germany and PowerPoint, Iran 22:32:15 mrhmouse, did they use MS Office? 22:32:15 i think the spot i'm living in now may have been a field before this year. 22:32:20 -!- Slereah_ has joined. 22:32:23 did you have busing? 22:32:23 elliott, dammit 22:32:51 No, we did not have buses. Yes, I have heard the Office joke before. 22:32:59 So. Many. Before. 22:33:16 Wait what? No buses? 22:33:18 At all? 22:33:22 Whaaaat? 22:33:28 vorpal you're not american are you 22:33:54 we had busing at my school but for the people up in the hills it took like an hour so that fucking sucked 22:33:56 Bike, sure you may not have city buses, but there are always inter-city buses going through even the tiniest places... 22:34:05 Bike: Did you mean school buses? 22:34:08 yes. 22:34:15 Vorpal: We didn't have either of those 22:34:42 Bike, the city I live in is served by a couple of inter-city lines, and it has one city bus line. Which runs like 4 times per day admittedly. 22:34:44 Bike: Ah, we did have school buses. I was the last to get off on my route and the first to get on. The bus arrived at 5:30AM and dropped me off at 4:30PM 22:34:45 there's public busing in my hometown (not pullman) but it's like an hour walk from my house to the nearest stop, so, fuck 22:34:51 School ended at 3:00PM 22:34:56 Bike: you lived in the hills? talk about rural 22:35:06 Bike, the city I work in has maybe 10-20 city bus lines. 22:35:14 why, these hills are the weed capitol of the world, probably 22:35:18 Bike, what about commuter trains? 22:35:24 Vorpal: lol. 22:35:37 -!- Slereah has quit (Ping timeout: 272 seconds). 22:35:44 Hm? 22:35:55 mrhmouse: for a second i thought you meant the bus ride took eleven hours 22:36:11 Bike, I have like a 5 minute walk to the train station. 22:36:25 So I live pretty close to it yes 22:36:29 -!- mrhmouse has quit (Quit: Leaving.). 22:36:40 Vorpal: commuter trains in the US are a joke. 22:36:48 Hm 22:36:53 Sad 22:37:11 the light rail in portland is actually pretty good, but that's a twenty mile drive from here and it doesn't cross state lines because of hilarious politicking. 22:37:22 twenty minute* 22:37:24 Heh 22:37:35 Vorpal: the city of 100kish i was born in had one intercity bus in each direction per day. smaller cities will typically have nothing at all. 22:37:46 lexande, wow 22:37:46 as for long distance rail, well, lolamtrak 22:38:01 -!- evalj has quit (Remote host closed the connection). 22:38:05 pullman has pretty alright public busing, but that's because it's full of undergrads with no cars. 22:38:28 Bike: Hey, I've used the Portland Light Rail! (Admittedly only for airport to hotel to airport.) 22:38:35 Bike: If that's the "MAX" thing. 22:38:43 lexande, I work in a city of around 200k. It has around 10-20 city lines. And a whole bunch of intercity lines going all over the county (since it is the hub of the county as it were). 22:38:43 yeah, max. 22:39:04 even if a bus is passing through on the highway it won't bother getting off for a town of less than like 20k 22:39:13 Bike, it is bad there too? Lots of delays and issues with winter weather and so on? 22:39:39 -!- typeclassy has quit (Remote host closed the connection). 22:39:49 is what bad, the light rail? 22:40:03 Vorpal: the city of 100k actually had like 8 city bus lines, that ran circuitously once an hour. though there are larger cities in the US with no public transit. 22:40:07 if so the answer is "i don't know, i don't use it" but thankfully trainnerds are here to help http://en.wikipedia.org/wiki/MAX_Light_Rail 22:40:36 lexande, the bus line from where I live to where I work is weird. It goes like 5 different routes during different times of the day. All using the same line number. The time table has a crazy number of footnotes to represent this. 22:40:43 I think it goes to g or k 22:40:53 Vorpal: where are you? 22:40:56 Sweden 22:41:22 if you're within a few hours of a major city in the US things are better 22:41:29 this reminds me, i'm gonna have to take greyhound back to pullman. pray for me. 22:41:55 there are buses to a lot of pretty nowhere places in New Jersey because people from there want to get to NYC without having to park in NYC 22:41:59 don't people get stabbed and eaten on greyhounds 22:42:05 lexande, eh what is a major city by your definition? Remember Sweden as a whole has ~9.5 million inhabitants 22:42:33 Phantom_Hoover: i think that was actually in canada. 22:42:44 what is a greyhound in this context? Dog sled??? XD 22:42:48 bus 22:42:53 lern4google 22:42:56 How boring 22:42:58 lern 4. 22:43:03 i recall someone pointing out the other day all of norway has fewer inhabitants than birmingham. 22:43:08 Vorpal: http://en.wikipedia.org/wiki/Killing_of_Tim_McLean here, this will probably be less boring. 22:43:39 oerjan: All of Norway has fewer inhabitants than Finland. 22:43:44 Ouch 22:44:05 Vorpal: well, Portland OR or Pittsburgh are just about large enough to have this effect, and are comparable in urban area population to Stockholm 22:44:06 fizzie, Finland has like 7 million right? 22:44:08 wow, five million. i think my metro area might have more than that. 22:44:09 buses with toilets?? 22:44:15 I guess I have never been on a bus that goes very far 22:44:15 fizzie: oh dear 22:44:21 oh, 5.4 22:44:26 hm that birmingham guy was completely wrong. 22:44:35 Vorpal: Yeah, it's only barely above Norway. 22:44:44 the whole SYSTEM is wrong, man 22:44:46 Birmingham used to have about a million inhabitants, it's probably more now 22:45:04 Hm 22:45:08 oh, portland metro is under 2.5 million 22:45:11 half a norway 22:45:21 ais523\unfoog, hi! Also interesting name 22:45:27 "The family of Tim McLean have brought a [[lawsuit]] of [[Canadian dollar|$]]150,000 [...]" that is a good secret wikilink 22:45:33 Vorpal: this is my /dev/null/nethack clantag 22:45:35 Bike: "Half a Norway in the subway at the same time?!" 22:45:39 Ah 22:45:59 terrifying 22:46:18 Vorpal: we just passed 5 millions the other ...february, but i'm not sure if it was this year. 22:46:23 Oh my god. That is way too many Norwegians to comprehend 22:46:23 wait. i meant 'metro' like 'metro area', not 'metropolitan train' 22:46:43 the taking of norhelm 1-2-3 22:47:29 re portland light rail, it works alright but is nothing special 22:47:38 it has to poke along in mixed traffic waiting at stoplights downtown 22:47:52 Light rail? Is that like trams? 22:47:56 yeah 22:48:04 "light rail" means a tram built after 1960 22:48:10 basically 22:48:17 heh. 22:48:34 Oh according to WP it is not quite the same 22:48:37 Compared to Helsinki's trams, the MAX trains felt a tiny bit more train-ish, but not by very much. At least from a subjective, non-expert viewpoint. 22:48:42 Trying to figure out what the different is though 22:49:08 "Conversely, LRVs generally outperform traditional streetcars in terms of capacity and top-end speed, and almost all modern LRVs are capable of multiple-unit operation. Particularly on exclusive rights-of-way, LRVs can provide much higher speeds and passenger volumes than a traditional streetcar.[citation needed] Thus a single-unit streetcar capable of only 70 kilometres per hour (43 mph) operating on a 22:49:08 shared right of way is not generally considered "light rail".[citation needed] The latest generation of LRVs is considerably larger and faster, typically 29 metres (95 ft) long with a maximum speed of around 105 kilometres per hour (65 mph).[19]" 22:49:43 Vorpal: so, if it just runs in the street in mixed traffic with cars it's dubious to call it light rail (portland has a line that does that and they just call it "streetcar") 22:49:45 pff, i don't think a max train has ever gone that fast 22:49:50 LRV being light rail vehicle 22:50:22 lexande, is that a question? Because I don't know the answer to that question 22:50:32 but if it's anything even slightly better than mixed-traffic-in-the-street-like-a-bus-on-rails, it will be called light rail 22:50:44 Incidentally, they're at the moment introducing (test driving) new trams in Helsinki. 22:50:48 Half of the pictures on this page looks like proper railways to me, and half look like trams 22:50:49 so meh 22:50:58 for political/marketing reasons, regardless of anybody's attempt to make stricter technical definitions of "light rail" 22:51:46 Vorpal: well, the idea of light rail when done optimally is that you run like a proper railway when you can and like a street tram otherwise 22:52:13 Ah 22:52:30 http://en.wikipedia.org/wiki/Helsinki_tram#Future_acquisitions "Two new trams are start test runs in line service in 2013, and --" some train nerd should go update that, they've already started. 22:52:54 -!- Phantom__Hoover has joined. 22:53:08 in the city max is like buses, but it runs outside the city too, where it's more trainy 22:53:25 outside downtown, whatever 22:53:41 so for example if you have a disused railway line that doesn't make it to the city centre, you use that and then use street tracks to get it the rest of the way 22:54:35 -!- Phantom_Hoover has quit (Ping timeout: 245 seconds). 22:54:58 (Vorpal: what cities are you familiar with? i can probably come up with a european example) 22:55:35 lexande, Stockholm and Gothenburg 22:55:48 One has a metro the other has proper trams 22:56:00 That definitely runs in the street 22:56:05 Terribly noisy and old 22:56:48 lexande, god damn, these things still run. No wonder they are so noisy, given the year of that image... https://en.wikipedia.org/wiki/File:Tram_in_Gothenburgh_1963.jpg 22:57:12 anyway Portland is mostly like what i described above (except sometimes the middle of a freeway instead of a disused railway) 22:57:24 -!- Phantom_Hoover has joined. 22:57:58 There are still some built-in-the-70s trams working in the Helsinki system. 22:58:04 on the other hand maybe you have downtown streets that are small and full of traffic, but wide fast streets further out, in which case you build a tunnel downtown but then run in the street further out to save tunnelling costs 22:58:07 And a couple of museum pieces, but those don't count. 22:58:19 "When Sweden’s switch to right-hand traffic in 1967 made existing unidirectional trams obsolete, Gothenburg was one of only two cities in Sweden to maintain its city-centre tramway, the other such network to survive being the Norrköping tramway." 22:58:23 Heh, I didn't know that 22:58:32 Explains why they are so rare here then 22:59:19 Mostly just buses nowdays. The city buses in the city I work in runs on biogas though. 22:59:31 Apparently they've got six 1962-1964 trams also used as "backup" when necessary. 22:59:41 I think I read about there being electric buses in Karlskrona or something 23:00:12 And the oldest of the "museum" trams is originally from 1917, though it's been renovated. 23:00:15 -!- Phantom__Hoover has quit (Ping timeout: 265 seconds). 23:00:32 Oh, that one's just a replica. Aw. :/ 23:00:58 The 1955 one is a touched-up original, though. 23:01:23 hmm https://en.wikipedia.org/wiki/Public_transport_in_Stockholm#Light_rail_and_tram 23:03:09 lexande, pretty sure that Stockholm has underground metro and buses exclusively in the city center. And that one tram line yes. 23:03:19 The fact that those all end up in "-banan" (banana) always amuses me. I tend to pronounce it like the fruit. 23:03:24 The metro goes above ground in some outlying regions though 23:03:59 lexande, but it *never* goes on normal streets. That would be super-dangerous since it uses a third rail system rather than overhead electrification. 23:04:05 this thing considers the nockebybanan, lidingöbanan and tvärbanan to be light rail 23:04:18 The (horse) race track nearby here has a "Travbanan ->" sign pointing at it. 23:04:20 though only the last seems to have significant street running 23:04:31 Oh wait, this is different 23:04:32 Hm 23:04:48 those three are all a ways out from the centre 23:04:53 The Stockholm metro, aka "tunnel banana". 23:05:06 Never been on tvärbanan 23:05:26 Guess that is light rail yes 23:06:16 "Near Liljeholmen the track is shared with freight traffic in a short section, this being the only place in Sweden where freight and electric trains share the same track." 23:06:20 About tvärbanan 23:06:25 What? Really? 23:06:27 fizzie: swedes sometimes intentionally prononce it as such, too 23:06:45 fizzie: or rather, some of my friends do, at least 23:06:59 to pun, I mean 23:07:14 There's a longstanding plan to build a "proper" light rail system in Helsinki, but so far they've just managed to paint some buses orange. 23:07:22 I live a couple of hundred meters from the regular railroad. It is electrified. It has inter city, commuter and freight trains 23:07:30 So I have no clue what that WP article meant 23:07:41 maybe it meant "light rail and freight" or something like that 23:08:39 "In the Helsinki region, there are also other plans to expand the network, through a larger project called Jokeri ("The Joker", after the playing card). This planned expansion, if constructed, would be the first real light rail line in Helsinki, and would involve the conversion of the current Jokeri bus line, line 550, into a cross city tramway similar to Stockholm's Tvärbanan." Heh, they're ... 23:08:45 ... referring to that. 23:09:06 (550 is the bus line with the orange buses.) 23:09:50 fizzie, as long as Batman doesn't get wind of it, that would work fine. 23:10:08 Did you know that roslagsbanan is the only narrow-gauge track in regular use in Sweden? 23:10:40 but yeah, "light rail" is a marketing term that gets applied to things ranging from "only slightly less crappy than a mixed traffic streetcar" to "only slightly crappier than a full underground high-capacity metro" 23:11:22 FireFly, heh, it is DC too, not AC 23:11:25 that is pretty weird 23:11:50 "Motorerna är trefas asynkronmotorer som matas med växelström. I varje motorvagn finns en s.k. traktionsomriktare som omvandlar likströmmen i kontaktledningen (1500 V) till växelström för motorerna. Motoreffekten är 400 kW." 23:12:06 Vorpal: hm, where in sweden do you live? 23:12:21 FireFly, i Örebros omnejd 23:12:27 Or, as boily would say, what are your approximate coördinates? 23:12:29 Oh, okay 23:12:51 FireFly, you? 23:13:10 Stockholm suburb 23:13:16 Ah 23:13:48 FireFly, never liked Stockholm. Way too big. At least it isn't as bad as Gothenburg when driving. Bloody one way streets over there... 23:14:20 Vorpal: I've heard driving in Lund is like a labyrinth due to one-way roads 23:14:30 If I remember our plans right, we're probably going to be passing through Örebro sometime next summer. 23:14:31 Never been there 23:15:02 Gothenburg is pretty much a mesh (and mess) of one-way streets, trams, tunnels and highways. Also a lot of hills. A LOT of hills. 23:15:23 fizzie, heh. Nice. 23:15:39 Not much to see really. Pretty boring city 23:15:40 At least Lund is completely flat 23:15:47 FireFly, so like Örebro then 23:16:23 I think I live near like the only hill within kilometers. Actually an "ås" whatever that is in English 23:16:51 So not very high. Maybe a total of 5-10 meters above the rest of the plains here 23:16:59 (I've said this before, but) trams are one of the traditional "gotcha" questions in the Finnish driver's license theory exam, because they have some right-of-way exceptions. (Usually in the form that there's a picture of a scene, a question on right-of-way, and a tram partially hidden behind a bush.) 23:17:05 FireFly: do people commonly answer boily like "40.80, -73.94"? 23:17:24 lexande: something like that 23:17:40 lexande: usually accompanied with approximate body weigh, too 23:18:04 lexande: It's all a part of a project to calculate the center of mass of the channel, you see. 23:18:24 It is conjectured to lie in Hexham 23:18:40 "Under Hexham" sounds more likely. 23:18:40 90kg or a bit less 23:19:06 i move around a lot though 23:20:31 I fed those numbers in maps.google, and it's like right next to "Best Hair & Nail Salon" -- a shame that's not Real Fast Nora's. 23:21:30 maybe i should try to figure out my average position over the past year 23:22:21 fizzie, I don't remember any tram stuff in the driving license stuff, but out of pure survival instinct I would probably give any tram right of way 23:23:10 i stayed at (37.77, -122.40) for a while 23:23:38 I've worked around that problem by not having a driver license 23:23:46 driving* 23:23:53 -!- Vorpal has changed nick to an. 23:24:00 -!- an has changed nick to Vorpal. 23:24:01 -!- Phantom__Hoover has joined. 23:24:21 Vorpal: That would generally be the correct answer here, too. (Though usually the point is that, given the limited time, you'd look at the otherwise plausible scenario and answer based on that, instead of noticing the semi-hidden tram.) 23:24:42 heh 23:25:00 lexande: Lexande, near Lexington Avenue? seems.. fitting 23:25:14 (Though the "trams have right-of-way no matter what their approach direction" exception doesn't -- as far as I know, anyway -- override explicit right-of-way signage.) 23:26:03 Hm 23:26:23 good night 23:26:34 lexande: You stayed inside a "Budget Truck Rental" building for a while? Well, whatever floats your truck, I guess. 23:26:43 (Yes, yes, "approximate".) 23:27:25 -!- Phantom_Hoover has quit (Ping timeout: 252 seconds). 23:27:33 Also coordinate systems suck. 23:27:55 -!- Phantom_Hoover has joined. 23:28:03 fizzie: what happens if you answer all the questions based on the assumption that there might be a tram hidden somewhere you don't see 23:28:48 oerjan: Probably they'll ask you to try again after studying a bit more. 23:29:08 I looked at code for converting from whatever NMEA gives you (WGS iirc) to various local coordinate systems and so on. What a confusing mess that is. 23:29:10 fizzie: bloody examinators 23:29:17 oerjan: From what I recall, it's mostly multiple-choice stuff, so you don't get to explain your reasoning. 23:29:41 fiendish 23:29:51 clearly this is a plot to end humanity. 23:30:06 by the evil trams. 23:31:04 -!- Phantom__Hoover has quit (Ping timeout: 264 seconds). 23:32:25 i think the most amusing place i stayed this year was -36.836, 174.751 or so 23:33:17 fizzie: well, i was assuming we were going to project the actual centroid to the nearest point on the sphere 23:34:26 quintopia: There is no sphere. Also, I've completely forgotten what the center of mass was for, really. 23:34:54 fizzie: sure there is. "the surface of the earth as approximated by a sphere" is a definitely a sphere 23:34:57 lexande: on a boat? 23:35:01 yup 23:35:32 (that some friends had sailed there from san diego) 23:35:48 Nice 23:36:25 FireFly: what are your approximate coördinates? 23:37:07 Approx. 59,204, 17,89 23:37:38 You get commas as decimal points because apparently Google Maps felt like localising them 23:38:41 "We could not understand the location 59,204, 17,89" it also doesn't feel like delocalizing. 23:44:04 wait, do you use a comma to separate numbers? 23:44:14 like, not as the radix 23:44:36 1 000 000,00 23:44:42 i'm european and write comma tuples as (3,4; 5,6) 23:44:50 yeah, that seems better 23:45:06 Yeah, that's what we use too 23:45:07 I think the SI standard specifies to use spaces to group digits. 23:45:26 I think I saw somewhere a suggestion to use half-width non-breaking spaces 23:45:33 but I don't even know how to type that 23:45:42 Or rather, it's a mix between (3,4; 5,6), (3.4, 5.6) or (3,4, 5,6) 23:45:48 usually it's clear what is meant, anyway 23:46:07 nooodl_: OpenFormula uses ; as the argument separator everywhere in order to avoid localisation problems if commas are part of the numeric syntax 23:46:36 I always use . as the radix point and nothing as digit grouping. 23:46:51 I usually use . as radix point and spaces to group digits 23:47:06 I use , as radix point when writing by hand, though 23:47:33 Using , as a radix point feels weird, though it is also the Finnish way. 23:47:58 Even for doing calculations by hand? 23:48:08 I grew up with using , there, so I guess that's why it's stuck 23:48:26 I guess maybe by hand it's less weird. 23:48:36 Can't say I've been written that many decimal numbers by hand lately. 23:52:55 -!- muskrat has joined. 23:52:59 -!- muskrat has left. 23:53:19 UTR #20 recommends U+2009 THIN SPACE between decimal digits and following fractions, "as in 1 ¾". 23:55:12 U+200A HAIR'S BREATH SPACE, U+200B SHADOW WIDTH SPACE, U+200C PLANCK SPACE 23:56:00 `run unidecode '⎖' # this also exists, not sure what for 23:56:02 ​[U+2396 DECIMAL SEPARATOR KEY SYMBOL] 23:57:53 `run unicode U+200C 23:57:55 Unknown character. 23:58:01 hmm 23:58:11 `run printf "\u200c" | unidecode 23:58:13 No output. 23:58:20 zero width non-joiner, apparently 23:58:35 `unidecode ‌ 23:58:35 `run cat $(which unicode) 23:58:36 ​[U+200C ZERO WIDTH NON-JOINER] 23:58:37 ​#!/usr/bin/env python \ # -*- encoding: utf-8 -*- \ import sys \ import unicodedata \ try: \ print u''.join(map(unicodedata.lookup, sys.argv[1:])).encode('utf-8') \ except KeyError: \ print u'Unknown character.' 23:58:58 oh so i have no idea how it works. 23:59:03 `unicode ZERO WIDTH NON-JOINER 23:59:04 ​‌ 23:59:08 `unicode 200c 23:59:09 Unknown character. 23:59:13 rats 23:59:23 In trying to turn off SafeSearch, a setting on a web form, I rendered my system unbootable 2013-11-25: 00:00:18 it tries very hard to keep you safe 00:02:20 how can that even 00:03:29 Phantom_Hoover: basically because it originally didn't work due to running an outdated version of Firefox, the reason he was running an outdated version of Firefox was that he hadn't updated in a really long time, and his sources.list had a mix of Ubuntu and Debian repositories for some reason 00:03:51 "The worst part was, everyone kept saying “oh yeah — there’s a comic about that; have you read it?" 00:04:21 -!- glogbackup has quit (Remote host closed the connection). 00:04:23 -!- CADD has joined. 00:04:24 hoist by his own petard 00:04:28 the last part was the root cause, I guess; trying to change the SafeSearch setting was just the trigger 00:05:02 hoist by his own mustard 00:08:08 -!- Phantom__Hoover has joined. 00:10:56 -!- zzo38 has quit (Remote host closed the connection). 00:11:49 -!- Phantom_Hoover has quit (Ping timeout: 248 seconds). 00:12:13 -!- Phantom_Hoover has joined. 00:12:30 -!- Phantom__Hoover has quit (Ping timeout: 245 seconds). 00:19:49 -!- `^_^v has quit (Read error: Connection reset by peer). 00:19:55 -!- ter2 has quit (Read error: Connection reset by peer). 00:20:08 -!- nooodl_ has quit (Quit: Ik ga weg). 00:20:11 -!- ter2 has joined. 00:20:13 -!- `^_^v has joined. 00:33:46 Bike: unidecode looks at sys.argv so piping to it does not work. 00:33:49 `run unidecode $(/usr/bin/printf '\u200c') 00:33:51 ​[U+200C ZERO WIDTH NON-JOINER] 00:34:13 i think i am just unsure of which direction is encoding and which is decoding 00:35:47 Bike: Oh, sorry, it was ais523 who piped to unidecode. (Which really probably should look at stdin if given no arguments.) 00:46:33 -!- Phantom_Hoover has quit (Quit: Leaving). 00:52:51 -!- yorick has quit (Remote host closed the connection). 00:59:40 `run printf '\u200c\0' | xargs -0 unidecode 00:59:42 ​[U+005C REVERSE SOLIDUS] [U+0075 LATIN SMALL LETTER U] [U+0032 DIGIT TWO] [U+0030 DIGIT ZERO] [U+0030 DIGIT ZERO] [U+0063 LATIN SMALL LETTER C] 00:59:58 * pikhq shakes fist at moronic printf 01:00:03 `run /usr/bin/printf '\u200c\0' | xargs -0 unidecode 01:00:05 ​[U+200C ZERO WIDTH NON-JOINER] 01:00:35 Also: http://pubs.opengroup.org/onlinepubs/9699919799/utilities/printf.html 01:00:46 Oh, right, no \u there. 01:00:59 Permitted, not required. 01:02:30 -!- Taneb has changed nick to benaT. 01:06:25 -!- benaT has changed nick to Taneb. 01:07:54 @tell shachaf nice, someone else finished cleaning up the Peter Johnstone mess 01:07:54 Consider it noted. 01:14:58 oerjan: zomg who 01:15:16 thx StAnselm 01:15:35 @messages-lead 01:15:35 oerjan said 7m 40s ago: nice, someone else finished cleaning up the Peter Johnstone mess 01:20:37 -!- Sgeo_ has joined. 01:23:00 -!- Sgeo has quit (Ping timeout: 240 seconds). 01:25:04 http://en.wikipedia.org/wiki/Moving_sofa_problem new favorite problem 01:25:07 "sofa constant" 01:27:24 it's a pity you can't get to infinity with some sort of fractal sofa 01:27:32 although people should actually make sofas that shape 01:27:48 actually having tried similar problems in real life, three dimensions tend to be involved 01:27:53 which can make things still more interesting 01:28:31 i dunno how fractals would help, it's still gotta be a rigid body... 01:29:20 hm, you know, i think if you had one person on each end you could actually move a sofa like in the gif 01:29:36 assuming a perfectly frictionless sofa, which admittedly wouldn't be good for sitting 01:30:16 Bike, it doesn't need to be frictionless on the top 01:30:20 `addquote assuming a perfectly frictionless sofa, which admittedly wouldn't be good for sitting 01:30:24 1137) assuming a perfectly frictionless sofa, which admittedly wouldn't be good for sitting 01:30:25 oh good point! 01:30:26 it'd only need to be frictionless round the edges, and low enough friction on the bottom that it would roll 01:30:39 (the friction on the bottom can be positive just so long as you're strong enough to move it) 01:32:55 look for my paper, "New Bounds on a Physically Realistic Deidealization of the Moving Sofa Problem, with Applications to U-HAUL" 01:34:57 http://www.theonion.com/articles/area-man-can-remember-exactly-where-he-was-what-he,34647/?ref=butt 01:41:39 and we heartily thank urbandictionary for their explanation of the term "u-haul". 01:42:39 you could have just used wikipedia 01:43:22 i used google and couldn't avoid noticing that hit 01:55:37 -!- oerjan has quit (Quit: leaving). 02:04:53 deidealization 02:04:55 good word 02:05:50 that's me, making shit up since nineteen ninety something 02:08:11 -!- Bike_ has joined. 02:10:25 -!- Bike has quit (Disconnected by services). 02:10:27 -!- Bike_ has changed nick to Bike. 02:17:29 -!- muskrat has joined. 02:18:54 -!- Bike has quit (Ping timeout: 265 seconds). 02:20:36 -!- Bike has joined. 02:27:25 -!- Bike has quit (Ping timeout: 272 seconds). 02:28:19 -!- ais523\unfoog has quit. 02:28:51 -!- Bike has joined. 02:37:13 -!- muskrat has left ("Leaving"). 02:42:12 -!- carado has quit (Ping timeout: 252 seconds). 02:51:37 -!- zzo38 has joined. 04:04:54 -!- Taneb has quit (Quit: Leaving). 04:18:05 “only uploading it to show that the PC Speaker can actually sound good.” http://youtu.be/wyXBESSgakM 04:57:31 -!- Sorella has quit (Ping timeout: 272 seconds). 05:08:57 -!- FireFly has quit (Excess Flood). 05:10:13 -!- FireFly has joined. 05:12:44 `welcome kmc 05:12:46 kmc: Welcome to the international hub for esoteric programming language design and deployment! For more information, check out our wiki: . (For the other kind of esoterica, try #esoteric on irc.dal.net.) 05:12:58 and also to california 05:23:29 -!- Sprocklem has quit (Ping timeout: 272 seconds). 06:42:09 I tried making a text adventure game involving things in my dream, although it can be expanded with things in other people's dream too. For now when it starts you get to pick one of three characters; you and anyone else may provide additional things, and then it can be more than that, and more location, situation, puzzles, too. 06:44:34 zzo38: please make it out of mnoqy's dreams thx 06:45:32 We can try. Although I started such thing I actually only made one room so far and a few properties and the starting simply to test my OASYS clone written in QBASIC. Probably the later one would be rewritten and using collaborative if that would help, too. 06:45:45 But if you have those ideas, please be more specific! It might interest. 07:11:50 zzo38: maybe you should get a programming bit in an existing mud (multi-player online open-ended text adventure world) and implement your dream there? 07:17:50 b_jonas: I do have that already. 07:17:57 great 07:18:43 I programmed it in so that you can fight me and stuff too 07:19:36 However the winner is currently decided at random 07:21:12 [[ "Money is important" I think it is, and no wonder that the. For tax increase of consumption tax recently, it has been making noise well. I would not be 8% and 3% increase in April 2014. Action we can take is two main. First, that "give up". This enclosed the belly and can not be helped anymore, Get a salary upgrade Good luck work. ]] -- recent spam through Google translate. 07:21:15 I own 176 objects on ifMUD already (see ifmud.org:4000 my apartment is room 11011) 07:29:41 However I also intend to make single-player Z-machine story files too 07:30:11 -!- FreeFull has quit. 07:34:45 b_jonas: Have you made up such a game too? 07:35:35 no 07:36:12 I tried some mud at one point but it seems it's not really my world 07:40:02 OK 07:40:47 Did you see my stuff though? 07:40:54 no 07:43:13 Did you make any standalones though that don't use internet? 07:43:38 no, but I'm starting to contribute to a non-mud game these days 07:43:54 currently mostly just testing and filing bug reports and reading source, 07:44:01 but should try writing more serious patches these days 07:44:06 What games? 07:44:11 the nethack variant nethack4 07:44:17 see #nethack4 07:45:11 I have made up various computer games using QBASIC, and other things 07:48:24 http://academictree.org/theology/tree.php?pid=59492 07:50:54 [Unsetting the zoned flag.] Field cleared. You drop leech. You drop pencil. You drop Imakuni?'s Card. You drop moldy scroll. You drop 69105-dimensional mapping tool. You drop Fanucci deck. You drop psychic channel computer. You drop list of people who read this list. You drop strange key. You drop room tester. You drop book. You drop key. You are not carrying that. You are not carrying that. 07:52:23 That is the kind of things it displays to me when I am attacked by another player. (I don't know why it says "You are not carrying that." twice.) 07:54:16 http://www.youtube.com/watch?v=9H1gRQ6S7gg "Now we destroy a castle with cannonball." 07:54:45 (It isn't very important though; other people will not see that message.) 07:57:15 fizzie: snazzy. too bad the movie looks dull. 07:58:27 that is some intense plowing 07:58:41 -!- hogeyui has quit (Ping timeout: 265 seconds). 08:05:24 They could have made a fancier video. Esp. the narration. But still, simulated snow. 08:14:23 -!- Oj742 has quit (Ping timeout: 272 seconds). 08:17:52 -!- hogeyui has joined. 08:33:22 Most people at the con didn't notice him, he just walked around, sweeping things http://imgur.com/gallery/0TWF1nJ 08:33:37 True or false: What is the bus driver's name? 08:34:19 True 08:36:17 Do you know what is the square root of your godfather's telephone number (without trying to calculate it)? 08:37:34 Sorry, i’m not in the mafia. 08:38:01 Do people in the mafia figure it out ahead of time, or are told by other people, or something? 08:38:49 Yes, they are very much into knowing the square root of everything. 09:32:27 apparently patashu is a vihart fan. 09:33:08 he thinks computation in base 2 is easier than computation with e 09:36:51 What kind of computation is meant? 09:38:03 Hm, why do I recognize the nick Patashu? 09:40:17 It sounds like Pikachu 09:44:14 FireFly: From #esoteric, I would suppose. 09:46:01 `seen Patashu ever 09:46:08 2012-06-24 23:33:06: I am a continuous chess armchair theorist 09:47:29 I see. 09:47:50 Is “ever” not the default? 09:48:05 Err, why even have such a parameter? 09:48:44 Because it takes a terribly long time to scan through all the logs. 09:49:07 -!- impomatic has joined. 09:49:13 That’s not the answer to my question. That’s the answer to “why do we use indexes?” 09:49:15 17 seconds in my query beforehand; caching is probably responsible for the above happening in six. 09:49:59 That would presumably involve updating the index every time `seen is used, which is really rarely, too. 09:51:26 Indices should be updated simultaneously with log updates, not searches. 09:51:48 But that's not doable without touching HackEgo itself. 09:51:57 What about, storing in a SQL database and then using CREATE INDEX to do it; that way you can make various kind of search/query/statistics, especially if extensions are written. 10:06:38 -!- Tod-Autojoined has quit (Read error: Connection reset by peer). 10:08:16 -!- TodPunk has joined. 10:12:15 -!- Slereah_ has quit (Ping timeout: 240 seconds). 10:31:48 -!- CADD has quit (Ping timeout: 245 seconds). 10:36:26 -!- carado has joined. 10:54:33 -!- TodPunk has quit (Read error: Connection reset by peer). 10:56:50 -!- TodPunk has joined. 10:57:17 https://github.com/mame/quine-relay 11:11:11 -!- Sorella has joined. 11:11:33 -!- Sorella has quit (Changing host). 11:11:33 -!- Sorella has joined. 11:15:20 -!- oerjan has joined. 11:19:33 -!- TodPunk has quit (Read error: Connection reset by peer). 11:21:29 -!- TodPunk has joined. 11:30:45 -!- tromp__ has quit (Ping timeout: 248 seconds). 11:30:50 -!- zzo38 has quit (Remote host closed the connection). 11:34:04 -!- tromp__ has joined. 11:49:54 -!- tromp__ has quit (Ping timeout: 246 seconds). 11:52:32 -!- tromp__ has joined. 12:12:53 -!- Sgeo_ has quit (Read error: Connection reset by peer). 12:15:35 `url bin/seen 12:15:37 http://codu.org/projects/hackbot/fshg/index.cgi/raw-file/tip/bin/seen 12:17:26 gah 12:19:44 I think that's partly my fault. :/ 12:20:01 In fact, it might be entirely my fault. 12:21:17 i was just wondering, does it check the files in reverse order? 12:21:47 Yes, due to "ls -r". 12:22:23 (And only the 30 latest without "ever".) 12:22:45 Oh, or did you mean within the files? 12:23:45 -!- tromp__ has quit (Ping timeout: 245 seconds). 12:24:03 nah, i don't think that would be important. 12:24:28 `seen oerjan 12:24:32 2013-11-25 12:24:28: `seen oerjan 12:24:39 -!- tromp__ has joined. 12:26:32 i was theoretically thinking, it should be possible to make a digest of files that leaves out every line that _isn't_ the last by that nick. 12:28:19 and then just replace the ls'ed files older than a certain date by those. 12:30:24 probably not worth the bother. 12:33:03 * oerjan is slightly annoyed that stackoverflow has no obvious shortcut to get to his favorite tag(s) 12:37:38 -!- Taneb has joined. 12:38:00 bah, sort -u compares the whole line, not only the key. 12:42:27 int-e: what if you add -s ? 12:45:55 wait, it works without -s for me. 12:46:59 `run (echo 'test';echo 'testing'; echo 'ho') | sort -u -k1.1,1.3 12:47:01 ho \ test 12:48:57 int-e: ^ 12:49:22 `run (echo 'testing';echo 'test'; echo 'ho') | sort -u -k1.1,1.3 12:49:24 ho \ testing 12:59:39 > (==)<*>reverse$"hi" 12:59:40 False 12:59:42 > (==)<*>reverse$"hih" 12:59:43 True 13:04:56 -!- boily has joined. 13:05:54 good cryogenic morning! 13:05:58 -!- metasepia has joined. 13:06:40 -!- ais523 has joined. 13:06:41 boily: help I want to opimize some code I wrote but I can't until I get home tonight 13:07:24 Tanelle. what kind of code is that? 13:08:05 It's not even code that particularly needs optimizing 13:08:19 Find the largest palindrome that is the product of 4 2-digit numbers 13:08:22 `run (echo 1 2; echo 1 3; echo 2 4) | sort -k1 -u 13:08:24 1 2 \ 1 3 \ 2 4 13:08:31 My code does it in .6 of a second 13:08:38 `run (echo a b; echo a c; echo b d) | sort -k1 -u 13:08:39 a b \ a c \ b d 13:08:45 A friend's does it in .006, apparently 13:09:21 `run (echo a b; echo a c; echo b c) | sort -k2 -u 13:09:23 a b \ a c 13:09:29 oerjan: I'm confused :) 13:09:30 Taneb: can I peek at your code? sounds interestoptimising. 13:09:44 boily: unfortunately my code is at home 13:10:04 oh. so the want to optimise it, but being unable to. I understand too well that urge. 13:10:11 (and I'm writing in Haskell and he's writing in C and we're timing it using different methods) 13:10:38 (so he's not taking into account startup or printing) 13:10:39 `run (echo a b; echo a c; echo b c) | sort -k1,1 -u 13:10:41 a b \ b c 13:10:52 oerjan: but it looks more and more like a bug :) 13:11:22 Taneb: compile to binary, “time ./whatever”? 13:11:28 That's what I'm doing 13:11:37 His code is doing it within the program 13:11:45 http://paste.strictfp.com/39615 is his code 13:11:49 nonsense. that's cheating, and unscientific. 13:13:13 I can remember a fair bit about my code off the top of my head 13:13:20 We used roughly the same algorithms 13:13:24 `run (echo a b; echo a a) | sort -k1 -s 13:13:26 a a \ a b 13:13:44 Except I found the answer by folding a list of [V4 Int] 13:16:37 oerjan: ah, I see. I should read manpages more often. 13:17:16 Taneb: V4? 13:17:43 (I thought -k1 and -k1,1 were equivalent but now I see that they are not.) 13:18:02 -!- yorick has joined. 13:18:05 `run (echo a b; echo a a; echo b c) | sort -k1,1,1 -s 13:18:07 sort: stray character in field spec: invalid field specification `1,1,1' 13:18:12 meh. 13:18:21 boily: it's essentially a strict 4-tuple 13:18:25 In the linear package 13:18:33 fascinating. 13:21:20 -!- Taneb has quit (Quit: Page closed). 13:21:21 Taneb: trying to solve that palindrome problem you mentioned, not in an optimized way, but just solve it 13:22:13 @tell Taneb Taneb: trying to solve that palindrome problem you mentioned, not in an optimized way, but just solve it 13:22:13 Consider it noted. 13:31:43 ) 99*97*92*76 NB. I think this is the largest one, but I don't have a nice code to prove it yet 13:31:44 b_jonas: 67144176 13:40:26 My (mostly) brute-force C verification consistently says "0.002" when timed with "time", but that's of course no proper kind of timing. 13:40:56 time(1) works a lot better than using a stopwatch 13:41:18 there should be a “propertime” binary somewhere... 13:41:30 fizzie: what result does it give? 13:41:39 b_jonas: The same. That's also in Taneb's paste. 13:41:42 great 13:41:57 Also the "time" output is "real 0m0.002s" "user 0m0.000s" "sys 0m0.000s" which is kind of meh. 13:44:36 (every time I hear “proper time”, http://youtu.be/yT5CzKGYhQk starts playing in my head.) 14:04:23 -!- ais523 has quit. 14:05:10 oh, here 14:05:14 ) #m2a=. (#~6700&<)~./:~,*/~10+i.90 14:05:14 b_jonas: 292 14:05:41 that's the list of product of two two-digit numbers greater than 6700 14:05:48 uniqued 14:05:53 ) ]mr=. m4a{~1 i.~(-:"1|."1)(8#10)#: m4a=. ~.\:~,*/~m2a 14:05:53 b_jonas: 67144176 14:06:56 m4 is all pairwise products of two of those, so they're all products of four two-digit numbers, and no such product greater than 6700*99*99 can be missing. 14:07:13 then mr is the largest palindrome from that list 14:07:20 ) mr=99*97*92*76 14:07:21 b_jonas: 1 14:07:53 and this shows the four two-digit numbers you get this from 14:23:12 -!- tertu3 has joined. 14:24:32 are there as many tertues as there are aises? 14:24:49 there is only one ais. left. 14:25:24 and there are at least three tertues. right. 14:26:21 well three rights make a left. 14:27:13 -!- ter2 has quit (Ping timeout: 245 seconds). 14:29:17 `quote theorem 14:29:19 216) (the former is a very deep theorem, i'd have had to read the whole book to understand it, so i didn't.) \ 502) theorem prover yada yada halting problem. \ 558) but i guess (x + y)^n = (x^2 + 2xy + y^2)(x^2 + 2xy + y^2)...(x^2 + 2xy + y^2) if n is even, (x + y)^n = (x^2 + 2xy + y^2)(x^2 + 2xy + y^2)...(x^2 + 2xy + y^ 14:30:09 `quote Theorem 14:30:11 216) (the former is a very deep theorem, i'd have had to read the whole book to understand it, so i didn't.) \ 502) theorem prover yada yada halting problem. \ 558) but i guess (x + y)^n = (x^2 + 2xy + y^2)(x^2 + 2xy + y^2)...(x^2 + 2xy + y^2) if n is even, (x + y)^n = (x^2 + 2xy + y^2)(x^2 + 2xy + y^2)...(x^2 + 2xy + y^ 14:30:25 * boily kicks HackEgo in the case insensitives 14:30:43 `run allquotes | grep Theorem 14:30:44 963) it's raining in newcastle, therefore the elliotts are distinct. boily's Newcastle Theorem. 14:31:05 thørjan. 14:31:39 boilyw 14:31:56 ...??? 14:32:21 you seem confused. 14:32:57 I am trying to parse that mysterious declension, with no avail. 14:33:06 alternatively, excessively punctuated. 14:33:14 it means yw, yw 14:33:26 oh. tdh. 14:33:37 I like punctuation. you can use all sort of them! 14:33:49 indeed- 14:35:27 Very funny⸮ 14:36:16 `unidecode ⸮ 14:36:18 ​[U+2E2E REVERSED QUESTION MARK] 14:37:16 "The irony mark or irony point (⸮) (French: point d’ironie) is a punctuation mark proposed by the French poet Alcanter de Brahm (alias Marcel Bernhardt) at the end of the 19th century used to indicate that a sentence should be understood at a second level (irony, sarcasm, etc.)" 14:39:08 -!- mrhmouse has joined. 14:39:21 ?⸮¿ is also a good punctuation for "nurr so confused nurr". 14:39:21 Unknown command, try @list 14:39:47 `unidecode ⸮ 14:39:48 ​[U+2E2E REVERSED QUESTION MARK] 14:39:58 (Any permutation of those three is valid, but there are subtle changes in tone.) 14:40:21 `unidecode ?⸮¿ 14:40:23 ​[U+003F QUESTION MARK] [U+2E2E REVERSED QUESTION MARK] [U+00BF INVERTED QUESTION MARK] 14:40:32 i sense one missing. 14:40:48 `unicode INVERTED REVERSED QUESTION MARK 14:40:50 Unknown character. 14:40:51 The REVERSED INVERTED QUESTION MARK is not in Unicode, as far as I can tell, shamefully. 14:40:57 darn 14:41:26 shameful encoding. Shunicode. 14:41:42 `unicode BADLY KERNED RN 14:41:43 Unknown character. 14:41:46 so much missing 14:43:29 `unicode ế 14:43:29 `unicode LATIN SMALL LIGATURE RN 14:43:30 Unknown character. 14:43:31 Unknown character. 14:43:39 `unidecore ế 14:43:40 ​/home/hackbot/hackbot.hg/multibot_cmds/lib/limits: line 5: exec: unidecore: not found 14:43:44 `unidecode ế 14:43:45 ​[U+1EBF LATIN SMALL LETTER E WITH CIRCUMFLEX AND ACUTE] 14:44:59 `unidecode 뻯 14:45:01 ​[U+DEAD DUNNO] [U+BEEF HANGUL SYLLABLE BBEGS] 14:45:31 There are 24 question marks: the regular, the {INVERTED,GREEK,ARMENIAN,ARABIC,ETHIOPIC,LIMBU,DOUBLE,EXCLAMATION,REVERSED,VAI,BAMUM,PRESENTATION FORM FOR VERTICAL,SMALL,FULLWIDTH,CHAKMA,TAG} QUESTION MARK, the QUESTION EXCLAMATION MARK, the COPTIC OLD NUBIAN {DIRECT,INDIRECT} QUESTION MARK, the {BLACK,WHITE} QUESTION MARK ORNAMENT and the {LESS,GREATER}-THAN WITH QUESTION MARK ABOVE. 14:46:27 fizzie: also the interrobang and I think there's a banginterro or whatsit 14:46:47 Yes, I counted only characters including the words QUESTION and MARK. 14:47:53 fizzie: ok, so cuont 0x2048 and 0x2049 too 14:47:55 http://imgur.com/YlA36ze 14:48:15 b_jonas: I did count those. 14:48:23 b_jonas: They're right there in the lists. 14:48:27 ah, ok 14:48:53 fizzie: 0x203d then 14:49:11 There's also the INVERTED INTERROBANG, if you want to go that way. 14:49:26 (U+2E18.) 14:50:13 And also QUESTIONED EQUAL TO, APL FUNCTIONAL SYMBOL QUAD QUESTION, and CIRCLED IDEOGRAPH QUESTION. 14:50:42 right 14:50:56 hehe 14:51:12 First two involve a ?-like thing in them. 14:51:40 As does the official picture of the REPLACEMENT CHARACTER. 14:52:49 `unicode REPLACEMENT CHARACTER 14:52:51 ​� 14:53:03 I DON'T THINK I HAVE THAT ONE 14:54:38 You need to use UPPERCASE when discussing UNICODE. 14:56:44 FIZZIE: WHAT? CAN'T HEAR YOU. SPEAK LOUDER! 14:58:16 THERE SHOULD BE SOMETHING EVEN MORE UPPER THAN UPPERCASE WHEN UNICODISCUSSING. SOMETHING... GRANDIOSE, MAGNIFICENT. SOMETHING LIKE: EXCELLENTCASE! 14:58:53 𝐎𝐇 𝐍𝑶𝑂❢ 15:00:15 𝖀𝕹𝕴𝕮𝕺𝕯𝕰 15:00:18 * boily replaces int-e with an IOCCC entry typeset to look like a replacement character. 15:00:26 (Sorry if something broke that.) 15:00:51 something broke mine :/ 15:01:16 Both look fine in the browser-view of the logs, so I guess it's okay. 15:04:12 data:text/plain,%F0%9D%90%8E%F0%9D%90%87+%F0%9D%90%8D%F0%9D%91%B6%F0%9D%91%82%E2%9D%A3 ... hmm. 15:09:46 actually it's just screen displaying those characters that's broken -- they made it fine to the channel as http://codu.org/logs/log/_esoteric/2013-11-25 proves. 15:24:16 i didn't see anything break in tmux. 15:25:45 hm. trying to start screen in tmux in screen doesn't work. 15:26:01 shocking 15:26:04 -!- Sprocklem has joined. 15:33:23 -!- TodPunk has quit (Quit: This is me, signing off. Probably rebooting or something.). 15:36:39 -!- oerjan has quit (Quit: leaving). 15:40:20 -!- TodPunk has joined. 15:46:29 something broke putty. a lot. 15:48:37 FireFly: Didn't break my PuTTY or tmux. What's your remote character set? 15:48:48 Good question 15:49:09 This is a weird putty app thingy for symbian, so that might be why 15:49:47 (although, my characters don't display correctly - my RCS is UTF-8 and I'm seeing Chinese characters instead of the text I see in the browser view of the logs) 15:50:43 This putty app thing seems to render fragments of boily's all-caps line in place of int-e's an fizzie's lines 15:51:01 which I'm pretty sure is very wrong 15:51:08 -!- nooodl has joined. 15:51:16 I'd take a screenshot if I could.. 15:53:48 `ello nooodl 15:53:51 nellooodl 15:54:08 -!- FreeFull has joined. 15:54:17 good ello 15:54:50 FireeFyllo. 15:54:57 `ello FireFly 15:54:59 FireFlello 15:55:02 (it's a Firefly-FreeFull-hello combo!) 15:55:24 FlelloFly 15:56:39 Fun fact: "fyllo" is swedish slang for "drunk" 16:00:59 -!- ais523 has joined. 16:05:09 @tell oerjan I can't see a reasonable interpretation of this: http://esolangs.org/w/index.php?title=Universal_Turing_machine&curid=1168&diff=37907&oldid=7972 except vandalism, or someone who really doesn't understand how software works 16:05:09 Consider it noted. 16:19:35 bonjourily 16:22:29 hmm. http://esolangs.org/w/index.php?title=Self-modifying_Brainfuck&diff=prev&oldid=37875 16:23:45 I don't think Lucasieks understands how wikis work 16:27:47 i just think it's hilarious 16:27:55 there's clearly something he/she doesn't understand 16:27:58 but I'm not entirely sure what it is 16:29:20 hmm… I wonder if he/she is browsing entirely from view source, using some sort of third-party viewer 16:29:31 I'm not sure why you'd do that, but it'd explain the #REDIRECT change 16:31:52 Bah. There is one serious (if self-promoting) contribution, and the rest of the edits look worthless from the sample I've looked at. :-/ 16:33:36 self-promotion is fine on esolangs.org, so long as it's ontopic 16:33:39 nothing would ever get done otherwise 16:33:50 right. 16:33:50 I can agree with int-e. Looks like some kid goofing off 16:33:56 (there's a rules page somewhere where it's explicitly allowed, probably http://esolangs.org/wiki/Esolang:Policy) 16:34:01 Especially the random line breaks 16:36:15 -!- muskrat has joined. 16:37:43 ais523: on the ZZZ page, the [[stub]] thing was also added by Lucasieks. (I'm not sure whether the page should be marked as a stub. There's little more to say about a brainfuck derivative.) 16:38:16 int-e: I noticed, but at least that wasn't outright counterproductive so I just decided to fix the syntax 16:41:36 Fair enough (I should probably shut up anyway, since I'm not contributing to the wiki. Thanks for the hard work!) 16:47:11 quintopia: bon matintopia! 16:59:36 -!- Slereah has joined. 17:02:08 boily: you slipped that one in just under the wire. past the eleventh hour even! 17:14:28 -!- Phantom_Hoover has joined. 17:19:27 I am wondering 17:19:34 How does assembly work in dual cores? 17:19:47 How do you specify which CPU you're talking to 17:20:39 i was going to give you a snotty response but then realized i don't particularly know myself. well played. 17:20:45 Heh 17:20:59 pretty sure it's arch-dependent. you tell the OS to do it. how the OS does it, i don't know 17:21:25 I get a lot of "the OS does it" whenever I ask assembly questions 17:21:57 managing this shit is what the OS is for, after all. 17:22:13 Yeah, but I like to learn things bottom up 17:22:51 the problem is that there are hundreds of different bottoms for different arches :p 17:23:02 heheheh, bottoms 17:23:16 Sure, but most of them are similar bottoms 17:23:21 Hey, do you want a match? 17:23:23 I have a match 17:23:33 My bottom and your face! 17:23:37 huhuhu 17:24:00 Pretty much all computers are variations on the Von Neumann architecture 17:24:07 And a lot of them are Intel stuff 17:24:32 A lot of these questions do not depend that much on the architecture, for the most part 17:25:39 yeah but "von neumann architecture" is pretty broad, that's like saying english and sanskrit are both variations on indo-european so it's simple 17:25:42 It's not like I'm using some soviet analog computer from the 60's 17:25:44 plus modern computers are harvardish at times 17:26:08 Intel is more of a "Germanic language" though 17:26:18 Perhaps even north germanic! 17:26:23 Is english noth germanic? 17:26:26 I forget 17:26:38 Ah, west germanic 17:28:49 heh heh heh 17:28:59 «regarding x86. In a multi threaded environment (Hyper-threading, multi-core or multi-processor), the Bootstrap thread (usually thread 0 in core 0 in processor 0) starts up fetching code from address 0xfffffff0. All the other threads start up in a special sleep state called Wait-for-SIPI. As part of its initialization, the primary thread sends a special inter-processor-interrupt (IPI) over the APIC called a SIPI (Startup IPI) to each ... 17:29:05 ... thread that is in WFS. The SIPI contains the address from which that thread should start fetching code.» 17:29:28 Ah, I see 17:29:41 And I guess there's some opcodes to communicate between processors, maybe? 17:29:46 Or do they work independantly 17:29:50 independently. 17:29:57 they share memory, though. 17:30:09 Weird 17:31:08 the few cores on a CPU generally are for running totally independent processes, so intercore communication doesn't have to be fast 17:35:21 -!- sebbu2 has joined. 17:35:55 -!- sebbu has quit (Ping timeout: 246 seconds). 17:36:01 -!- sebbu2 has quit (Changing host). 17:36:01 -!- sebbu2 has joined. 17:41:20 -!- sebbu2 has changed nick to sebbu. 17:42:02 -!- fizzie has quit (Quit: Coyote finally caught me). 17:43:45 -!- augur has quit (Remote host closed the connection). 17:44:39 -!- fizzie has joined. 17:46:47 This reconnect brought to you by the We Don't Look At Hostnames In Prompts Before 'shutdown -r now' Foundation. 17:47:34 (and people like you. Thank you.) 17:48:03 fizzie: I have a different sudo password on every computer where I have sudoers access 17:48:12 it's saved me from stupid mistakes like that several times so far 17:49:16 Something like that might not be a bad idea. 17:53:46 I use one colour for the prompt per machine 18:02:58 -!- yiyus has joined. 18:09:48 * boily pokes whichever sebbu is currently connected 18:09:56 ~metar CYUL 18:09:56 CYUL 251800Z 15010KT 30SM BKN040 BKN085 BKN240 M05/M18 A3024 RMK SC5AC1CI1 SLP244 18:10:05 oh. only minus 5. yééé.... 18:10:32 ~metar ESSA 18:10:32 ESSA 251750Z 32010KT CAVOK M02/M06 Q1025 R01L/19//95 R08/19//95 R01R/19//95 NOSIG 18:13:20 -!- zzo38 has joined. 18:13:35 `ello zzo38 18:13:37 zzello38 18:14:30 Hello 18:15:32 -!- Phantom__Hoover has joined. 18:16:01 boily: A few days ago I received a message from you but the context is unclear. Can you explain it please? 18:16:40 hah. speaking of context :) 18:16:40 zzo38: was that about you being the weirdest? 18:16:42 -!- yiyus has quit (Remote host closed the connection). 18:16:46 Yes 18:17:08 the context was computer setups and suchlike. 18:18:07 `? pineapple 18:18:09 Pineapple is a hybrid species descended from a cultivar of spinach and wild ivy, therefore making it a class 6 vegetable. 18:18:20 int-e: context ↑ 18:18:37 -!- Phantom_Hoover has quit (Ping timeout: 246 seconds). 18:20:09 I haven't checked on ruddy in a while... 18:20:11 So I've understood. I only know of it because of the piracy thing. 18:21:07 ah yes. fizzie: you still have a config.sys? / people here have weird, weird setups. / @tell zzo38 you are the weirdest. 18:21:49 (the discussion was longer, but that should do for context) 18:25:57 ruddy: do you understand context? 18:25:57 like in a university 18:26:09 I take that as a resounding “no”. 18:28:22 ruddy understand as much as I would expect, which isn't much 18:28:23 I guess it is more of a loop yeah 18:29:53 circular logic ftw! 18:30:34 I really need to get to work on having ruddy understand a subset of English.. or maybe just a new bot 18:30:39 mrhmouse, symbols, whose values are looked up in the court of the LORD's glory. 18:31:36 ruddy: have you been reading /r/fearme lately? 18:31:37 I need so much more privacy to be comfortable 18:31:40 -!- Sprocklem has quit (Ping timeout: 264 seconds). 18:32:05 mrhmouse: your bot is under Bad Influences. He is Basking under the Glorious Shadows of the Throne. 18:32:06 stay away from reddit then, ruddy 18:32:06 i want a break from it. so it took a while to adjust to it and crossed my fingers.) 18:32:11 ~metar EFHK 18:32:11 EFHK 251820Z 31007KT CAVOK M04/M05 Q1019 NOSIG 18:32:18 -!- Taneb has joined. 18:32:21 Does that ever say "M00"? 18:32:34 (For below-zero-but-rounds-to-zero.) 18:32:43 `ello Taneb 18:32:45 Tanebello 18:32:52 fizzie: afaicrbtnm, yes. 18:33:47 Hi 18:33:49 boily: "btnm"? "but that's not much"? 18:34:12 mrhmouse: wow. you guessed it. 18:34:18 -!- callforjudgement has joined. 18:34:23 `relcome callforjudgement 18:34:26 ​callforjudgement: Welcome to the international hub for esoteric programming language design and deployment! For more information, check out our wiki: . (For the other kind of esoterica, try #esoteric on irc.dal.net.) 18:34:37 -!- ais523 has quit (Disconnected by services). 18:35:20 b_jonas, we agree on the answer :) 18:50:54 -!- augur has joined. 19:07:30 -!- muskrat has quit (Quit: Leaving). 19:13:35 -!- Phantom_Hoover has joined. 19:15:57 -!- Phantom__Hoover has quit (Ping timeout: 272 seconds). 19:19:28 -!- callforjudgement has quit (Read error: Connection reset by peer). 19:19:43 -!- callforjudgement has joined. 19:20:11 HAH! I GOT IT! MWAH AH AH HA AH AHAHAHAHAHAHA! 19:20:24 im afraid 19:20:48 nothing to be afraid of. only a hairy Python problem solved. 19:21:04 -!- Sprocklem has joined. 19:21:59 if I had a nickel for every time I've had a hairy python problem... 19:22:07 c.c 19:22:11 also, hi everyone 19:22:17 `ello kmc 19:22:19 kmcello 19:22:44 Hmm 19:22:53 `ello limonc 19:22:54 My C solution runs in 1/70 the time of my Haskell solution 19:22:55 limellonc 19:23:02 that didn't work at all 19:23:58 Taneb: but which one is easier to understand? 19:24:15 mrhmouse, probably either depending on how you think 19:24:17 kmc: clearly we need a `cosby function 19:24:28 how would that work 19:24:37 kmc: hilariously 19:25:06 `ello limоnc 19:25:06 `ello HackEgo 19:25:08 HackEgello 19:25:08 limоncello 19:25:23 What is a limon cello? 19:25:29 does it produce music? 19:25:40 it's booze, so yes 19:25:51 it's very strong and sweet booze. 19:25:59 `unicode о 19:26:00 Unknown character. 19:26:04 `unidecode о 19:26:06 ​[U+043E CYRILLIC SMALL LETTER O] 19:26:08 ahhh 19:26:17 * boily whistles innocently ♪ 19:26:23 CYRILLIC SMALL LETTER SINGLE NON-OCULAR O 19:26:26 -!- Bike_ has joined. 19:26:27 hi kmc 19:26:30 hichaf 19:26:48 -!- Bike has quit (Ping timeout: 245 seconds). 19:27:11 I have a bottle of "Pallini" brand limoncello in the closet, bought because fi:pallini == en:"my balls". 19:27:35 There's a tumblr of jokes about it, of course. 19:27:42 awesome 19:27:57 did you try any 19:29:20 -!- tertu3 has changed nick to tertu. 19:29:24 -!- Phantom__Hoover has joined. 19:29:28 -!- Phantom__Hoover has quit (Changing host). 19:29:29 -!- Phantom__Hoover has joined. 19:29:34 Not from this particular bottle; I haven't managed to organize our usual set of participants yet. I might have had some of "my balls" on a previous trip to Italy, but I can't be sure about that. 19:29:53 -!- Phantom_Hoover has quit (Ping timeout: 272 seconds). 19:30:11 this sounds like a good tumblr especially because i don't know finnish. please link 19:30:13 fizzie: and with one sentence you seem to have frightened off Phantom_Hoover 19:30:45 nooodl: Oh no, it turns out to have been a blogspot. But anyway: http://pallinimun.blogspot.com/ 19:31:24 Many of the puns are not going to translate well. 19:31:31 -!- Bike_ has changed nick to Bike. 19:31:34 i was right. this is the best blog ever 19:31:49 Like that bit about the cucumber is because the Finnish word for "cucumber" equals the Finnish word for "throat". 19:32:10 pikkujoulutunnelmissa is a good word 19:32:36 http://pallinimun.blogspot.be/2012/12/pallini-aamiaisen-kanssa-sankyyn.html god i can't imagine the joke here at all 19:32:57 "My balls in bed with the breakfast", going from the URL. 19:33:27 it's that plus "tarjoiltuna" 19:33:49 is this breakfast in finland. finland is weird 19:33:56 Well, that's just "served". 19:34:16 I guess it could be someone's breakfast. 19:34:42 I mean, there's bread, there's fruit, there's some cheese, there's some yogurt. That's not so weird, is it? 19:35:03 you have a "usual set of participants" for sampling italian liqueurs with unintentionally hilarious names? 19:35:24 be prepared for anything kmc 19:35:40 now I wish I lived within a thousand miles of fizzie 19:35:51 kmc: Well, technically it's a "usual set of participants" for sampling all different brands of tequila we come across, but we've been branching out. 19:36:08 the revelations, they are striking. 19:36:43 kmc: For example, we sampled this: http://gamma.zem.fi/~fis/bottel.jpg 19:36:50 (It tasted exactly like it looks like.) 19:38:39 * boily is disturbed “guess I wasn't prepared for anything.” 19:38:55 is it sfw 19:39:13 yeah 19:39:16 GIRL 19:39:19 It's a bottle. I guess that depends on your place of work? 19:39:38 what about girls? 19:39:40 oh heh 19:39:59 is it vodka with estrogen mixed in or something 19:40:28 Sadly, it's just "Litchi, Framboise, Vodka Premium & Cognac", like it says on the bottle. 19:41:17 litchi = lychee? 19:41:20 as expected from a French bottle, the label is mostly English. 19:41:28 kmc: c'est ça. 19:42:28 It wasn't very good, just so you know. 19:52:45 Taneb: I've showed the calculation too since: http://dpaste.com/1482712/ 19:54:07 :) 20:08:16 -!- muskrat has joined. 20:23:23 -!- Phantom_Hoover has joined. 20:24:37 -!- Phantom__Hoover has quit (Ping timeout: 272 seconds). 20:25:25 -!- zzo38 has quit (Remote host closed the connection). 20:48:37 -!- Sprocklem has quit (Ping timeout: 248 seconds). 21:07:34 -!- Phantom__Hoover has joined. 21:07:37 -!- Phantom_Hoover has quit (Ping timeout: 252 seconds). 21:26:45 -!- callforjudgement has quit. 21:27:06 every time I see Phantom__Hoover swapping _es, I get reminded of mitosis, like if a new Phantom__Hoover got generated. 21:34:52 -!- muskrat_ has joined. 21:35:07 -!- muskrat has quit (Disconnected by services). 21:35:14 -!- muskrat_ has changed nick to muskrat. 21:50:52 -!- Phantom_Hoover has joined. 21:52:04 -!- Phantom__Hoover has quit (Ping timeout: 264 seconds). 21:52:53 -!- oerjan has joined. 22:00:02 -!- boily has quit (Quit: λf.(λx.f (x x)) (λx.f (x x))). 22:00:08 -!- metasepia has quit (Remote host closed the connection). 22:02:55 -!- typeclassy has joined. 22:03:26 How can I download the entire archive of a USENET group? (going back to 1991) 22:04:08 @messages-odd 22:04:09 ais523 said 5h 59m ago: I can't see a reasonable interpretation of this: http://esolangs.org/w/index.php?title=Universal_Turing_machine&curid=1168&diff=37907&oldid=7972 except vandalism, or someone 22:04:09 who really doesn't understand how software works 22:04:56 oerjan: I guess that covers pretty much all #esoteric messages. 22:05:07 you'd think 22:05:12 please. i pride myself on my low algorithmic randomness 22:05:21 also my parity 22:08:15 lambdabot: you really didn't have to split that into two lines ... *goes look at some code* 22:08:16 -!- impomatic has quit (Ping timeout: 264 seconds). 22:08:41 -!- impomatic has joined. 22:08:46 @tell ais523 Well he did understand how {{wrongtitle|...}} worked, at least. 22:08:46 Consider it noted. 22:15:26 textwidth = 200 -- IRC maximum msg length, minus a bit for safety. 22:15:40 that is quite a safety margin :) 22:15:45 you'd think. 22:16:53 you need to include room for :lambdabot!wherever@somewhere PRIVMSG : or what it was 22:17:28 -!- nisstyre has joined. 22:17:32 also a possible + or - with that one extension clients can enable. and other stuff 22:17:32 oerjan: yes, but the limit is 512 (- newline - what you said) 22:17:38 it'd be nice if it listened to the capabilities message sent on connect 22:17:43 the newline is two bytes, though :) 22:17:54 I know :) 22:17:56 also inter-server communication can add stuff, IIRC 22:18:09 looks like lambdabot's longest-named channel is #learnanycomputerlanguage 22:18:16 let's all use xdcc 22:18:25 oh right the channel name 22:19:06 lambdabot should be able to know the length of that, though. 22:19:23 apparently the limit is lifted for inter-server communication nowadays. look at the calculation in http://scripts.irssi.org/html/splitlong.pl.html ... and that script seems to work reasonably well :) 22:19:29 just saying it isn't as easy as bumping up a constant a bit 22:19:44 freenode cloaks are quite annoying for splitting. 22:19:57 splitlong.pl gets them wrong. 22:20:37 (It calculates assuming hostname for the prefix.) 22:20:56 elliott: I'll probably bump it to 350. :) 22:21:22 i can't tell if the smilies are passive aggressive or what 22:21:40 they are supposed to be friendly. 22:21:47 but I do overuse them. 22:22:07 there is no such thing as a passive agressive smiley :) 22:22:16 :-P 22:22:29 * Bike shrinks 22:22:49 Bike: problem? 8VP 22:23:32 I've splitlong_max_length set to 400, and that seems to have been safe so far. 22:27:48 -!- yorick has quit (Quit: quit.). 22:28:04 > "snack" 22:28:05 "snack" 22:28:51 > var "snicker\nsnack" 22:28:52 snicker 22:28:52 snack 22:28:59 oi. 22:29:06 > text "a\nb" 22:29:07 a 22:29:08 b 22:29:26 does the IRC message limit of 512 include name/channel/etc, or just the "message" part itself? 22:29:26 I wonder if it caps at three lines? 22:29:28 as with error messages 22:29:36 mrhmouse: it's the whole raw message AFAIK 22:29:51 i assume the first line is different on purpose 22:29:52 so, including name/channel/etc 22:29:58 right, so it includes all that. 22:30:14 > 1 22:30:15 1 22:30:24 there is no purpose in lambdabot. 22:30:33 Hrm... I'm using a third-party lib for ruddy that claims to cap at 512.. I wonder if that includes the entire message. 22:30:38 I'm not sure why you'd do that, but it'd explain the #REDIRECT change 22:30:47 oerjan: I'm note sure about that. 22:31:01 ruddy: sure would 22:31:01 Running out of letters. :-( 22:31:08 @quote purpose 22:31:08 UmbertoEco says: I don't even have an e-mail address. I have reached an age where my main purpose is not to receive messages. 22:33:18 > [1..] -- oh I guess this one is goverened by textwidth as well? 22:33:19 [1,2,3,4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28... 22:33:25 no. too short :) 22:34:10 int-e: > commands give much longer output in private. 22:34:29 that's ok :) 22:35:01 it'd be bad if lambdabot would suddenly produce twice as much output on the channels for infinite lists. 22:36:15 it's considerably more than twice. i tested and it got up to 283. 22:37:06 split into five lines. 22:37:08 -!- augur has quit (Remote host closed the connection). 22:37:27 -!- Sorella` has joined. 22:37:36 it's a feature, I believe 22:37:52 certainly 22:38:10 i vaguely think the limit was higher before, but #haskell is much larger now. 22:38:10 kmc: I press Alt-R instead of Alt-4 and Firefox restarts, losing all my tabs? 22:38:11 -!- Sorella has quit (Ping timeout: 252 seconds). 22:38:16 thx a lot firefox :'( 22:38:49 oerjan: I tried [1, 3..] and got six lines 22:39:02 It behaves differently in /msg 22:39:05 Oh, oerjan said that. 22:39:07 shachaf: sucks :( 22:39:11 so it's limiting off of number of elements 22:39:15 or time.. 22:39:19 I had a bunch of logged in sessions in Private Browsing. 22:39:28 wait did i say five, i meant six. 22:39:40 The sixth one kinda doesn't count though 22:39:50 yeah it's just a tiny output 22:39:53 @pretty 22:40:15 > length . show $ [1..283] 22:40:16 1025 22:40:28 Oh. that makes for a sane number to restrict output to 22:40:45 yes, it's just the length of the string showed. 22:40:57 mueval does that. 22:41:14 iirc it always caps at 1024, even if it shows a shorter string. 22:41:30 > [1..29] 22:41:31 [1,2,3,4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28... 22:41:40 > [1..29] ++ fix id 22:41:44 mueval-core: Time limit exceeded 22:41:58 > [1..282] ++ fix id 22:42:02 mueval-core: Time limit exceeded 22:42:05 > [1..283] ++ fix id 22:42:07 [1,2,3,4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28... 22:42:29 @@ @run @where pi_10 22:42:31 yes. mueval cuts the result off at 1024 characters; lambdabot then formats the result 22:42:31 "31415926535897932384626433832795028841971693993751058209749445923078164062... 22:42:50 @@ @run @where pi_11 22:42:53 mueval-core: Time limit exceeded 22:42:54 :'( 22:43:00 @where pi_10 22:43:00 (!!3)<$>transpose[show$foldr(\k a->2*10^2^n+a*k`div`(2*k+1))0[1..2^n]|n<-[0..]] 22:43:04 @where pi_9 22:43:04 I know nothing about pi_9. 22:43:09 what in god's name 22:43:11 of course you don't 22:43:30 @where e_10 22:43:30 [show(sum$scanl div(100^n)[1..[4..]!!n])!!n|n<-[0..]] 22:43:39 10^2^n... 22:44:43 ah. I see :) 22:44:58 @@ @run @where e_10 22:45:00 "27182818284590452353602874713526624977572470936999595749669676277240766303... 22:45:18 [4..]!!n looks a bit silly. 22:45:21 Yep. 22:45:26 Go ahead. Improve it. 22:47:44 haha 22:52:15 -!- Sorella`` has joined. 22:53:57 -!- Sorella` has quit (Ping timeout: 252 seconds). 22:54:24 oerjan: there are two places where a space is added to the output of @eval ... once in the eval plugin itself, which preprends a space to the output, and once in a generic function that tries to be polite on channels (which is also responsible for limiting lines to 80 characters). 22:55:03 @eval is something else entirely! 22:55:06 so, no, that doesn't look intentional to me :) 22:55:15 I mean @run, but the plugin is called Eval. 22:55:41 @help eval 22:55:41 eval. Do nothing (perversely) 22:56:03 @help choose 22:56:03 choose. Lambdabot featuring AI power 22:56:05 AI! 22:56:25 @choose wisely 22:56:25 wisely 22:56:42 @@ @choose @@ @where ops 22:56:42 monochrom 22:56:51 @choose the alternative 22:56:51 alternative 22:57:13 @@ @choose @where ops 22:57:13 dcoutts 22:57:25 @dice 3d8 + 5d2 22:57:25 int-e: (7+3+7) + 6 => 23 22:57:46 3d8 + 5d2 22:57:46 shachaf: (6+8+8) + 8 => 30 22:58:00 wow 22:58:15 1000000000d8 22:58:15 oerjan: 4500001312 22:58:43 lambdabot: way to leave out the breakdown 22:59:03 @numberwang 4500001312 22:59:03 Unknown command, try @list 22:59:06 :'( 22:59:19 that plugin was too noisy 22:59:26 Not the @numberwang version. 22:59:30 Just the unprompted version. 22:59:31 same plugin 22:59:47 Well, that's an unsolvable problem. 22:59:53 kmc wrote a good Numberwang tester. 23:00:08 `numberwang fnord 23:00:09 ​/home/hackbot/hackbot.hg/multibot_cmds/lib/limits: line 5: exec: numberwang: not found 23:00:13 shocking 23:00:29 s/not found/That's not a Numberwang!/ 23:00:42 !numberwang 5 23:00:44 That's numberwang! 23:00:48 !numberwang fnord 23:00:48 I'm sorry, but Brazil isn't a vegetable! 23:00:59 !numberwang 5.2 23:01:00 That's numberwang! 23:01:03 int-e: you're not numberwang 23:01:04 `thanks Taneb 23:01:06 Thanks, Taneb. Thaneb. 23:01:27 I wonder if we can hook `thanks to a karma system 23:01:33 elliott: you're numberwang 23:01:50 * int-e shrugs 23:01:53 Taneb: the answer is: yes! we *can* do that. 23:02:33 `? shachaf 23:02:35 shachaf sprø som selleri and cosplays Nepeta Leijon on weekends. 23:02:54 `? int-e 23:02:56 int-e? ¯\(°_o)/¯ 23:02:57 | 23:02:57 º¯`\o 23:03:01 -!- yorick_ has joined. 23:03:38 Bike: look, now there's a really awful smiley. 23:03:39 Who was admin of lambdabot before Cale? 23:03:45 `? Ngevd 23:03:47 ​eZ&W:{\4g_R"y榭y6w1i5d)u+..?_V-.YD1! E4X|sKKVsc\\><>y̔\4I.DDۦԢɘ_萺j⫤8| 23:03:58 Apparently it was geekosaur once upon a time? 23:04:00 i'ma big fan of ¯\(°_o)/¯ :( 23:04:00 | 23:04:00 º¯`\o 23:04:10 And of course it was Pseudonym once. 23:04:15 And probably dons once? 23:05:05 hm... ¯\(°_o)/¯ 23:05:05 | 23:05:06 º¯`\o 23:05:07 dons, certainly. geekosaur, I believe so; I don't know about Pseudonym. 23:05:19 . ¯\(°_o)/¯ 23:05:19 | 23:05:19 o/`¯º 23:05:21 ¯\(°_o)/¯ 23:05:21 | 23:05:22 o/`¯º 23:05:22 Maybe I'm mixing people up. 23:05:34 `celebrate 23:05:35 ​/home/hackbot/hackbot.hg/multibot_cmds/lib/limits: line 5: exec: celebrate: not found 23:05:42 ^celebrate 23:05:42 \o| c.c \o/ ಠ_ಠ \m/ \m/ \o_ c.c _o/ \m/ \m/ ಠ_ಠ \o/ c.c |o/ 23:05:42 | c.c.c | ¯|¯⌠ `\o/´ | c.c.c | `\o/´ ¯|¯⌠ | c.c.c ¦ 23:05:42 /`\ c.c /< |\| | /< c.c >\ | /< | |\ c.c ´¸¨ 23:05:44 /`¯|_) /'\ 23:05:44 (_| (_| |_) 23:05:46 shachaf: Oh I wasn't trying to say that you're wrong. I didn't keep track. 23:05:53 I know. 23:05:54 oh, are the c.c.cs new? 23:05:54 c.c.c 23:05:54 c.c 23:05:58 But maybe I'm mixing people up. 23:05:58 x.x 23:06:05 ಠ.ಠ 23:06:12 ꙮ.ꙮ 23:06:30 c.c.c.c 23:06:30 c.c.cc.c.c 23:06:31 c.c c.c 23:06:39 ew 23:06:43 myndzi: BUG 23:06:48 . 23:06:49 . 23:06:52 . 23:06:55 aww 23:07:04 c..c.c..c 23:07:05 c.c.c 23:07:05 c.c 23:07:17 @tell myndzi c.c.c.c # bug 23:07:17 Consider it noted. 23:07:17 c.c.cc.c.c 23:07:17 c.c c.c 23:07:36 > cycle "c." 23:07:37 "c.c.c.c.c.c.c.c.c.c.c.c.c.c.c.c.c.c.c.c.c.c.c.c.c.c.c.c.c.c.c.c.c.c.c.c.c.... 23:07:41 c.cc.c 23:07:52 c.c c.c 23:07:53 c.c.cc.c.c 23:07:53 c.c c.c 23:07:57 * int-e shrugs 23:08:01 C.C 23:08:04 ©.© 23:08:06 c.c 23:08:09 oopse 23:08:11 C.C 23:08:15 ©.© 23:08:15 O.o 23:08:18 c.c 23:08:19 c.c.c 23:08:19 c.c 23:08:24 hm... ¯\(°​_o)/¯ 23:08:24 \O/ 23:08:46 actually, that could look kind of cute. 23:09:03 \O/ 23:09:04 ¯\(°​_o)/¯ 23:09:04 imo enough spam 23:09:27 i recall myndzi ignored HackEgo ¯\(°​_o)/¯ at one time. did someone request that back? 23:09:49 misaligned. and yes, you're probably right :) 23:10:15 That \O/ is like a crown, right? 23:10:16 -!- nisstyre has quit (Quit: Leaving). 23:10:27 `url bin/? 23:10:29 http://codu.org/projects/hackbot/fshg/index.cgi/raw-file/tip/bin/%3F 23:11:24 -!- yorick_ has changed nick to yorick. 23:11:47 wth is rnooodl 23:12:26 never mind, I should just read the source. 23:12:37 -!- lambdabot has quit (Ping timeout: 246 seconds). 23:12:56 `run sed -i 's/°_o/°​_o/' bin/'?' 23:12:57 | | 23:12:57 /< /| 23:13:01 No output. 23:13:11 `? fnordy 23:13:13 fnordy? ¯\(°​_o)/¯ 23:13:13 -!- augur has joined. 23:15:02 int-e: apparently it's not too surprising 23:15:39 `echo nooodl | rnooodl 23:15:40 nooodl | rnooodl 23:15:44 oh heh, ngevd is special-cased 23:15:59 int-e: you want to `run that 23:16:06 `run echo nooodl | rnooodl 23:16:08 noooooodl 23:16:13 thanks 23:16:20 `thanks int-e 23:16:21 Thanks, int-e. Thint-e. 23:16:55 `thanks FireFly 23:16:56 Thanks, FireFly. ThireFly. 23:17:15 `thanks kzrk 23:17:17 Thanks, kzrk. Tzrk. 23:18:04 ugh. 23:18:19 `thanks Mgrvgrvladje 23:18:20 Thanks, Mgrvgrvladje. Thadje. 23:18:24 -!- lambdabot has joined. 23:18:29 lambdabot: what did you do? 23:18:33 `thanks lambdabot 23:18:34 Thanks, lambdabot. Thambdabot. 23:19:03 -!- muskrat has left ("Leaving"). 23:19:05 but at least it came back without me having to do anything about it. good. 23:22:49 oerjan: and now it splits [1..] into three lines rather than 5 :) 23:26:41 charming 23:35:15 -!- typeclassy has quit (Ping timeout: 272 seconds). 23:35:52 -!- typeclassy has joined. 23:36:01 -!- mrhmouse has quit (Quit: Leaving.). 23:39:38 fungot: is it numberwang 23:39:39 shachaf: i can use dingbat circled sans-serif digit five 23:39:46 That's numberwang! 23:39:50 fungot: am i numberwang 23:39:50 shachaf: i say don't worry and use it a lot in my fnord to huhta. 23:40:13 I'm the numberwang and I'm okay, I count all night and a sleep all day... 23:40:27 -!- Phantom__Hoover has joined. 23:41:23 -!- Phantom_Hoover has quit (Ping timeout: 245 seconds). 23:41:40 fungot: is int-e numberwang 23:41:41 shachaf: fnord ihope waits patiently for someone to come tell me that 23:42:40 * oerjan sees no trace of ihope here by any name 23:43:08 fungot: are you ihope 23:43:08 shachaf: a debian terminal is pretty dark, after all.) and ( 23:43:09 ihope by any other name smells just as sweet? 23:43:25 just as tswett, usually. 23:43:54 @thanks sweet 23:43:54 you are welcome 23:43:57 `thanks sweet 23:43:59 Thanks, sweet. Theet. 23:44:25 ^all `those @prefixes !make %me #dizzy 23:44:41 ^prefixes -- happy to help 23:44:41 Bot prefixes: fungot ^, HackEgo `, EgoBot !, lambdabot @ or ?, thutubot +, metasepia ~, jconn ) , blsqbot ! 23:45:30 is it safe to have so many bots in one channel? 23:45:31 ^`!@?+~)! 23:46:14 typeclassy: nope. 23:46:35 `run (echo tsrif; echo ytefas) | rev | tac 23:46:36 safety \ first 23:47:24 ) 1+1 23:47:25 oerjan: 2 23:47:36 ) 1+1 2 23:47:36 shachaf: 2 3 23:47:38 `whoami 23:47:40 whoami: cannot find name for user ID 5000 23:47:59 `make 23:48:01 make: *** No targets specified and no makefile found. Stop. 23:48:04 `thanks \o| c.c \o/ ಠ_ಠ \m/ \m/ \o_ c.c _o/ \m/ \m/ ಠ_ಠ \o/ c.c |o/ 23:48:05 Thanks, \o| c.c \o/ ಠ_ಠ \m/ \m/ \o_ c.c _o/ \m/ \m/ ಠ_ಠ \o/ c.c |o/. Tho| c.c \o/ ಠ_ಠ \m/ \m/ \o_ c.c _o/ \m/ \m/ ಠ_ಠ \o/ c.c |o/. 23:49:03 typeclassy: there are various mechanisms for avoiding botloops, but i'm not sure if all of them are currently watertight. (i don't recall if lambdabot's obscure loophole was closed.) 23:51:01 -!- lambdabot has quit (Ping timeout: 248 seconds). 23:51:01 -!- fungot has quit (Ping timeout: 248 seconds). 23:51:19 shachaf: help is it bad if i'm not even surprised by that result 23:51:28 i think they smelled my plans... 23:51:50 ) 7+ 28 19 10 23:51:50 Bike: 35 26 17 23:52:06 Well, that's because virtually all bots (including lambdabot) violate the recommendation of the IRC RFC (1459): automatic responses should only be made to PRIVMSG messages, and should be sent as NOTICE. (clients hilighting NOTICE don't help...) 23:52:31 i think i can get a chain fungot -> HackEgo/EgoBot -> lambdabot, but you cannot get back to fungot because it has an ignore system. 23:52:44 @where quine 23:52:59 int-e: OH GOD I HATE THAT DISCUSSION 23:53:14 botloops are _fun_, dammit. 23:53:38 oerjan: There's no need to discuss this :) 23:55:36 obviously, lambdabot's current approach is to put a space in front of everything that might come from a user, but I don't know how thoroughly that was done. (and it won't help with bots like fungot and ruddy ? who will reply to anything with their name in it) 23:55:47 rather technical 23:56:02 oh. not fungot, then :) 23:56:26 fungot is not here at the moment. fizzie! 23:56:27 -!- lambdabot has joined. 23:56:40 oh. again? 23:57:40 ruddy seems harmless as you cannot get em to respond reliably in any useful format. fungot's bladder works similarly, although adds the original nick. 23:57:44 oerjan..... 23:57:54 ruddy: RELIABLY, i said. 23:57:54 it's probably a bit more difficult to keep track of who every customer is like that 23:58:08 oh hm 23:58:10 *blather 23:59:36 int-e: it's not thorough. 23:59:37 ?where q 23:59:37 I know nothing about q. 2013-11-26: 00:00:48 yeah ?where was the loophole i was thinking of. 00:01:08 god help us if someone makes a bot triggered by "I" or a space 00:01:09 @where paste 00:01:09 http://lpaste.net/new/haskell 00:01:48 @where+ loop @where q 00:01:48 Good to know. 00:01:52 @where loop 00:01:52 @where q 00:02:00 ?where ?where 00:02:00 ?where ?where 00:02:05 hth 00:02:20 yeah. it really should just add a space to everything :) 00:02:29 No, spaces are annoying. 00:02:47 @where- loop 00:02:48 Maybe you meant: where+ where 00:03:40 jconn: ) 1+1 00:03:41 oerjan: |syntax error 00:03:41 oerjan: | )1+1 00:03:50 jconn: 1+1 00:03:50 oerjan: 2 00:04:11 i think jconn and lambdabot can loop. 00:04:33 well, assuming J can output formatted text. 00:04:44 do you know that great feature where lambdabot checks whether a nick ends in "bot" 00:04:59 shachaf: it does? 00:05:22 elliott discovered it when testing in the channel "#lambdabot" 00:05:39 it was removed. 00:05:46 do you know that great feature where lambdabot checked whether a nick ends in "bot" 00:07:11 did it just silently ignore every command you'd give in #lambdabot. if so that sounds... fun 00:07:18 shachaf: it did? 00:14:15 -!- tertu has quit (Ping timeout: 272 seconds). 00:15:10 -!- nooodl has quit (Quit: Ik ga weg). 00:17:54 -!- Sgeo has joined. 00:19:08 -!- tertu has joined. 00:32:20 -!- Oj742 has joined. 00:35:14 -!- Slereah_ has joined. 00:36:21 -!- Slereah has quit (Ping timeout: 240 seconds). 00:49:42 -!- Oj742 has quit (Ping timeout: 246 seconds). 00:56:36 !malbolge (=<`#9]~6ZY32Vx/4Rs+0No-&Jk)"Fh}|Bcy?`=*z]Kw%oG4UUS0/@-ejc(:'8dc 00:56:37 Hello World! 00:57:13 -!- Taneb has quit (Quit: Leaving). 00:58:38 huh, i thought malbolge programs were generally longer 00:59:08 User:ErichS8 at wikipedia has been greatly improving it 01:04:11 hm the one in our wiki's hello world page is none of the ones in wikipedia. 01:04:26 "After each instruction is executed, the guilty instruction gets encrypted[...] after a jump, Malbolge will encrypt the innocent instruction just prior" this seems unwikipedian 01:04:34 good pun though 01:04:50 but _starts_ with the same code as the newest short version. 01:05:12 !malbolge (=<`#9]~6ZY32Vw/.R,+Op(L,+k#Gh&}Cdz@aw=;zyKw%ut4Uqp0/mlejihtfrHcbaC2^W\>Z,XW)UTSL53\HGFjW 01:05:12 Hello, world. 01:05:23 oh it's not exactly the same text. 01:06:09 -!- typeclassy has quit (Ping timeout: 246 seconds). 01:06:21 first 14 chars are the same. 01:09:46 mtve: hey you made the one in the wiki http://esolangs.org/w/index.php?title=Hello_world_program_in_esoteric_languages&diff=6158&oldid=5803 01:10:36 idle as a snail 01:12:34 `seen mtve ever 01:12:39 2013-03-15 11:37:33: i like kenrube's homepage btw (not really sure its his, but it was mentioned somewhere linked to him) - http://www.yyyyyyy.info/ 01:25:49 -!- Phantom__Hoover has quit (Ping timeout: 272 seconds). 01:35:41 -!- oerjan has quit (Quit: nuit). 02:00:01 -!- Sprocklem has joined. 02:29:34 http://arstechnica.com/tech-policy/2013/11/newegg-trial-crypto-legend-diffie-takes-the-stand-to-knock-out-patent/ 02:29:40 -!- Sprocklem has quit (Ping timeout: 246 seconds). 02:30:56 ^good article 02:34:47 -!- yorick has quit (Remote host closed the connection). 02:39:03 discovery: opencl is really boring 02:40:18 -!- Sorella`` has changed nick to Sorella. 02:40:19 -!- Sorella has quit (Changing host). 02:40:19 -!- Sorella has joined. 02:40:24 why does seemingly every C library define a typedef around int and other basic types 02:45:05 -!- Taneb has joined. 02:45:13 Missing: Taneb's sleep schedule 02:45:15 Reward if found 02:50:16 -!- Sprocklem has joined. 02:50:31 Sorry, i borrowed it. 02:50:49 ion, give it back when you're done 02:51:10 Crap. It seems i have lost it, too. 02:51:17 :O 02:59:26 I must be some kind of cruel, heartless neurogengineer 02:59:39 :O 02:59:58 Don't know if I already mentioned my latest norn cruelty or not 03:00:02 did you decerberate a cat 03:00:05 cerebrate 03:00:06 god 03:00:22 look did you mutilate a fucking cat or not fuck this language fuck science fuck everything 03:00:36 No cats were mutilated in the mutilation of norns 03:03:01 -!- zzo38 has joined. 03:03:24 Made a norn that's blind to anything that's moving, relative to its own location. Norns tend to move around a lot, especially when they can't do anything, e.g. if they're blind 03:03:49 What's a norn 03:04:13 -!- typeclassy has joined. 03:04:19 pointless nerd shit. i want to see blood sgeo 03:04:39 blood on your hands 03:05:23 Taneb: a species of virtual creature in the Creatures series of games 03:09:35 -!- typeclassy has quit (Read error: Connection reset by peer). 03:13:24 -!- typeclassy has joined. 03:24:27 -!- typeclassy has quit (Ping timeout: 265 seconds). 03:25:25 -!- realz has quit (Ping timeout: 245 seconds). 03:39:51 -!- carado has quit (Ping timeout: 252 seconds). 03:41:28 -!- parduse has joined. 03:41:44 -!- parduse has left. 03:55:33 -!- tertu has quit (Ping timeout: 272 seconds). 04:02:32 -!- Taneb has quit (Quit: Leaving). 04:04:11 -!- nisstyre has joined. 04:10:40 -!- Oj742 has joined. 04:59:20 -!- tertu has joined. 05:06:17 -!- zzo38 has quit (Remote host closed the connection). 05:14:47 -!- typeclassy has joined. 05:15:36 Bike: There are a lot of utterly incompetent C coders out there. 05:15:53 this is an industry standard, though... 05:15:53 Bike: There's also a lot of stupid cargo cult stuff going on. 05:16:13 Yes, but even zlib is in freaking terrible C. 05:17:15 i just, i don't get it. what's the thought process behind foo_int 05:17:29 typedef unsigned char Byte; 05:17:33 * pikhq cries 05:18:00 typedef unsigned char FAR Bytef; // Yes, because DOS is *that* important in software released today. 05:18:25 And yes, believe it or not zlib still is littered with far pointer annotations. 05:18:43 Just in case you wanna use your 286. 05:18:49 I think the modern descendant of DOS now supports x64 as well :S 05:19:00 modern descendants, to be exact 05:19:31 Eh, WinNT is about as much DOS as Linux is. 05:21:20 Bike: Part of the issue is, so few people write good C that there's nothing to learn good C style *from*. 05:21:37 I mean, shit, people use int instead of size_t for goodness sake. 05:22:10 this explains a lot about my formative years programming. 05:22:31 pikhq: and ssize_t. 05:22:36 pikhq: and ptrdiff_t. 05:22:37 in that i read a lot of C and didn't understand a bit of it 05:22:46 lifthrasiir: Yes. 05:22:47 pikhq: and intptr_t and uintptr_t and int_fastN_t etc. 05:22:52 ha. 05:23:12 lifthrasiir: To be fair-ish, intptr_t, uintptr_t, intN_t, etc. are C99-isms. 05:23:31 And Microsoft's compiler is still stuck in 1989. 05:23:39 right now i'm kind of weirded out that opencl not only has a runtime compiler but lets you call it asynchronously by specifying a callback function (??) 05:23:52 right, but that has changed printf formatting specifications as well, and there is not much need for two copies of printf in libc. 05:24:15 I really hate that %zd specifier... 05:24:27 Meh, Microsoft's C library is also psycho broken in many other regards. 05:24:55 (SUPPORT UTF-8 YOU PSYCHOTIC BASTARDS) 05:25:19 zd is size_t? 05:26:02 Yeah, z is the size_t or ssize_t length modifier. 05:26:03 pikhq: I think once upon a time msvcrt did not support floating point printing in printf() unless there are no floating point library (analogous to libm, but automatically linked) used. is this still a case? 05:26:14 what's wrong with it? 05:27:11 * pikhq looks forward to the days of i686-windows-musl 05:27:15 Bike: there are bunch of other prefixes for such integral-but-i-dunno-its-size pseudo-types. 05:27:33 ptrdiff_t is assigned, I think, %jd. 05:27:44 or that's for intptr_t? I dunno. 05:27:46 Only 2 others. j is intmax_t and t is ptrdiff_t. 05:27:59 ha. 05:28:04 The intN_t types have preprocessor defines. 05:28:08 yeah, there is intmax_t as well. 05:28:27 PRId64 etc? :S 05:28:32 Yup. 05:28:40 Suboptimal, but eh. 05:29:03 and we have INT64_C(...) macros. 05:29:07 In a sense they're the least intrusive way of doing so. Especially since they're only exposed by inttypes.h 05:29:44 this conversation has gotten away from me but now i know uint_least32_t and uint_fast32_t are distinct 05:30:19 Bike: Nominally distinct. They're pretty likely to be typedef'd the same though. 05:30:26 right 05:30:31 diggin all these constants. INTMAX_MIN 05:30:58 And you can just use "unsigned int" instead of uint_least32_t on POSIX... 05:40:23 Seriously, have you ever looked at zlib's source? 05:41:21 well, no. 05:41:41 https://github.com/madler/zlib/blob/master/adler32.c Freaking adler32 was made this complicated. 05:42:28 "#define local static" i see. 05:43:27 uint32_t adler32(uint32_t adler, const char *buf, size_t len) {uint16_t sum1 = adler, sum2 = adler>>16;for(;len;len--,buf++){sum1+=*buf;sum2+=sum1;sum1%=65521;sum2%=65521;}return (sum1 << 16) | sum2; } 05:44:00 It's not a hard function. 05:44:16 oh i'm liking ZEXPORT what's that do 05:44:33 except that division by 65521 is expensive. 05:44:44 On Windows, __declspec(dllexport). On BeOS, __declspec(dllexport). Elsewhere, nothing. 05:44:56 be used dlls? 05:46:26 pikhq: anyway, I think a freshly-redesigned version of zlib would be better to manage, there are actually several known issues with zlib's performance. 05:47:02 lifthrasiir: Fine, while(len){ size_t i = 0;for(;i < 5552 && i < len;i++) { sum1+=buf[i]; sum2+=sum1; } sum1%=65521; sum2%=65521; buf+=i;len-=i; } 05:47:06 Yeah, I'm aware. 05:47:40 * pikhq looks at ~/src/pikhq-zlib 05:49:39 -!- Sprocklem has quit (Ping timeout: 272 seconds). 05:51:46 It's not even *that* big of an interface, just kinda ugly. 05:54:27 http://sprunge.us/HLVF Like, that's the whole thing. 05:55:30 what's the difference between a voidpf and a voidp. 05:55:51 On DOS, a voidpf is far. 05:56:22 oh i like all that stuff to get a 32 bit int 05:56:46 This is the actual interface that it exports, not the official header. 05:56:56 The official header is an order of magnitude larger. 05:57:50 https://github.com/madler/zlib/blob/master/zlib.h 06:00:28 The application can compare zlibVersion and ZLIB_VERSION for consistency. If the first character differs, the library code actually used is not compatible with the zlib.h header file used by the application. This check is automatically made by deflateInit and inflateInit. 06:03:18 -!- Oj742 has quit (Ping timeout: 246 seconds). 06:03:30 Yeah, zlib's a bit... special. 06:09:11 -!- typeclassy has quit (Ping timeout: 240 seconds). 06:09:35 -!- tertu has quit (Ping timeout: 245 seconds). 06:09:47 -!- zzo38 has joined. 06:16:18 -!- tertu has joined. 06:32:05 huh, i hd no idea half-precision floats exist 06:33:47 I think they're mainly for storange and less so calculation? 06:34:01 though that guess kinda comes from the fact that intel added functions to convert to/from FP16 but no arithmetic on them 06:34:08 s/functions/instructions/? 06:34:18 that's what wikipedia said 06:34:23 but opencl c has 'em 06:34:45 O_O 06:34:51 I wonder if GPUs have them as a thing. 06:35:47 "The half data type can only be used to declare a pointer to a buffer that contains half values. 06:35:51 so, yeah, storage only. 06:36:31 you have to use builtins to get a real float out of em 06:36:43 and do, like, arithmetic. 06:38:13 and there are length three vectors. ok then! 06:39:36 float4 f = (float4)((float2)(1.0f, 2.0f), (float2)(3.0f, 4.0f)); 06:39:40 i feel right at home. 06:41:02 oh man there are arbitrary permutations of vectors. rad i guess 06:42:09 x = (float16)(a.xxxx, b.xyz, c.xyz, d.xyz, a.yzw) // now x is four of a.x, then b, c, d, then a permuted a. 06:49:54 "A divide by zero with integer types does not cause an exception but will result in an unspecified value." fuck the police 06:55:39 -!- Slereah_ has quit (Read error: Connection reset by peer). 06:55:52 -!- Slereah has joined. 07:23:40 8-bit floats ftw. 07:24:10 I have a vague recollection some system somewhere had those as a built-in data type. 07:26:21 What programs would use 8-bit floats? 07:28:48 uint8_t with a 64K multiplication table. 07:28:51 I can't think of an example offhand. http://www.mrob.com/pub/math/floatformats.html (see "Microfloats") points out that the IBM PC keyboard repeat rate is set using what's essentially a floating-point format. 07:29:44 -!- FreeFull has quit. 07:29:50 μ-law also acts as a sort of a floating point type. 07:32:14 That's also mentioned on the page. 07:50:25 -!- Vorpal has quit (Ping timeout: 245 seconds). 07:58:29 -!- tertu has quit (Ping timeout: 248 seconds). 08:05:42 -!- Vorpal has joined. 08:13:56 I think it would be useful, if PuTTY would have an option which, if enabled, does something special with SCROLL LOCK. How is such a feature made suggested? What I wanted it to do is: If scroll lock is on, it does two things: [1] Disables the "reset scrollback" options. [2] Makes the up/down/pgup/pgdn keys to scroll the window instead of sending to the server. 08:14:34 Is it would seem useful to you, too? 08:17:02 Bike: Might it be better if it would be defined to instead mean, it is undefined whether integer division by zero will cause an exception or an unspecified result? 08:17:13 -!- tromp__ has quit (Ping timeout: 272 seconds). 08:17:55 -!- tromp__ has joined. 08:34:01 -!- Phantom_Hoover has joined. 08:40:58 -!- zzo38 has quit (Remote host closed the connection). 08:41:53 -!- Phantom__Hoover has joined. 08:42:49 -!- Phantom_Hoover has quit (Ping timeout: 252 seconds). 08:56:35 Bike: yeah, GLSL also has the permutation thing. it's really useful when you're writing vector-intensive stuff 09:04:09 -!- Phantom_Hoover has joined. 09:05:12 -!- Phantom__Hoover has quit (Ping timeout: 265 seconds). 09:17:39 -!- ais523_ has joined. 09:22:39 `unicode EM DASH 09:22:43 ​— 09:22:46 thanks 09:22:52 public computer, no compose key :( 09:22:55 * :-( 09:26:45 -!- Phantom__Hoover has joined. 09:27:13 -!- Phantom_Hoover has quit (Ping timeout: 246 seconds). 09:30:40 `run unicode 'COMPOSITION SYMBOL' 'COMBINING ENCLOSING KEYCAP' # ais523_: There you go, a compose key. 09:30:41 ​⎄⃣ 09:30:59 fizzie: it doesn't render properly on this OS :-( 09:32:02 It renders quite badly in my terminal, too. (Mostly okay in the browser.) 09:49:21 -!- Phantom_Hoover has joined. 09:49:28 -!- Phantom_Hoover has quit (Changing host). 09:49:28 -!- Phantom_Hoover has joined. 09:50:16 -!- Phantom__Hoover has quit (Ping timeout: 264 seconds). 09:54:24 http://arstechnica.com/tech-policy/2013/11/jury-newegg-infringes-spangenberg-patent-must-pay-2-3-million/ 09:57:06 that's a p. great patent 09:58:30 "The lawyers from both teams took in the verdict without emotion and shook hands following the verdict." "The weather shifted dramatically since the beginning of trial, and it was cold and rainy then." "Diffie looked the part of the eccentric genius, resplendent with his long white hair and beard. He spoke with a booming voice but carefully articulated manner; he was professorial but not ... 09:58:36 ... overbearing." That's a p. weird way of reporting. 09:58:43 fizzie: yeah 09:58:56 -!- Phantom__Hoover has joined. 09:59:05 -!- Phantom_Hoover has quit (Ping timeout: 252 seconds). 10:00:52 -!- ais523_ has quit (Quit: Page closed). 10:18:06 -!- tromp__ has quit (Remote host closed the connection). 10:18:09 -!- Phantom__Hoover has quit (Ping timeout: 252 seconds). 10:19:40 -!- tromp__ has joined. 10:33:43 -!- carado has joined. 11:18:28 -!- Slereah has quit (Ping timeout: 245 seconds). 11:26:57 -!- tromp__ has quit (Remote host closed the connection). 11:28:29 -!- tromp__ has joined. 11:35:04 -!- Jafet has quit (Quit: Quit). 11:35:23 -!- Jafet has joined. 11:35:24 -!- Jafet has quit (Changing host). 11:35:25 -!- Jafet has joined. 11:35:30 -!- Jafet has left. 11:38:33 -!- Slereah has joined. 12:23:51 -!- myndzi has quit (Ping timeout: 240 seconds). 12:32:45 -!- myndzi has joined. 12:41:32 -!- Sgeo has quit (Read error: Connection reset by peer). 13:06:42 -!- yorick has joined. 13:07:28 -!- boily has joined. 13:07:36 -!- metasepia has joined. 13:14:16 -!- Frooxius has quit (Read error: Connection reset by peer). 13:15:35 -!- Frooxius has joined. 13:27:50 quintopia: bontopia matin! 13:39:41 -!- Frooxius has quit (Read error: Connection reset by peer). 13:41:53 -!- Frooxius has joined. 13:42:50 * boily ties Bike and Frooxius together. “With their disconnection powers combined, may they be Present in this Channel and Not Leave!” 13:45:25 -!- oerjan has joined. 13:49:48 `? sgeo 13:49:50 Sgeo is a language nomad. (Not to be confused with a language monad.) He invented Metaplace sex, thus killing it within a month. 13:50:59 -!- Taneb has joined. 13:51:01 `? impomatic 13:51:01 `run sed -i 's/$/ He was Doctor Mengele in his previous life, as evidenced by his norn experiments./' wisdom/sgeo 13:51:06 impomatic? ¯\(°​_o)/¯ 13:51:09 No output. 13:51:14 i think the evidence is clear by now. 13:51:16 `? Taneb 13:51:18 Taneb is not elliott, no matter who you ask. He also isn't a rabbi although he has pretended in the past. He has at least two backup keyboards, and five genders. (See also: d-modules) 13:51:26 :-) 13:52:37 oerjan: are you writing down the SGSGS? 13:52:40 It is true that I am not elliott. 13:52:48 what's the SGSGS 13:52:52 I have played the Rabbi in Fiddle orn the Roof 13:52:56 Strange and Great SGeo Saga. 13:53:17 I used to have two spare keyboards, but I have since thrown one out because it did not work 13:53:19 Taneb: i didn't hear you say any more about it, so i assume the latest auditions didn't go too well. 13:53:28 oerjan: didn't get any parts 13:53:38 Also I realised I really don't have the time 13:53:48 mechanical keyboards are proliferating in our workplace. mwah ah ah. 13:54:01 The gender thing I can't remember why, probably the kind of joke I make about myself 13:54:37 Someone sharing my surname is cited on the wikipedia page for d-modules 13:54:38 that's because one of the genders is amnesiosexual hth 13:54:42 `? tanebventions 13:54:44 Tanebventions include D-modules, automatic squirrel feeders, the torus, and Go. 13:54:55 When did the torus get there 13:55:04 recently. 13:55:31 sadly there is no way to find out unless you dare to poke into the murky depths of our hg browser. 13:56:06 -!- augur has quit (Remote host closed the connection). 13:56:22 I have a vague feeling Taneb's torus is related to chess and pineapples... 13:56:25 -!- augur has joined. 13:56:30 `? people who taneb is not 13:56:32 elliott, a rabbi, Mark Zuckerberg, James Bond 13:56:44 That is an exhaustive list 13:56:45 -!- augur has quit (Remote host closed the connection). 13:57:11 -!- augur has joined. 13:57:12 Hmm, adding torus I think predates the pdf 13:57:31 `? torus 13:57:33 Topologically, a torus is just a torus. Taneb invented them. 13:57:45 http://codu.org/projects/hackbot/fshg/index.cgi/rev/b3ecbbf31355 <-- you definitely are amnesiosexual 13:57:47 `help 13:57:48 Runs arbitrary code in GNU/Linux. Type "`", or "`run " for full shell commands. "`fetch " downloads files. Files saved to $PWD are persistent, and $PWD/bin is in $PATH. $PWD is a mercurial repository, "`revert " can be used to revert to a revision. See http://codu.org/projects/hackbot/fshg/ 13:57:56 oh wait 13:58:29 oh right you keep adding that s 13:59:37 `learn Impomatic never did anything weird enough to get into this database. 13:59:42 I knew that. 14:00:07 `learn impomatic never did anything weird enough to get into this database. 14:00:12 I knew that. 14:00:42 Aha! 14:00:44 Phantom_Hoover, topologically, a torus is a torus (I think) 14:00:48 April 14th 14:01:09 -!- augur has quit (Ping timeout: 240 seconds). 14:01:37 In response to "Topologically, an elliptic curve is a torus." dude 14:02:25 browsing the PDF sources, apparently Sgeo is also a wall. 14:02:26 Mystery solved 14:04:30 Hmm 14:04:38 Could one argue that FALSE is the first modern esolang? 14:06:08 modern? that'd imply we had a classical, a baroque, and a romantic esolanging periods. 14:06:27 boily: classical = P'', baroque = INTERCAL, romantic = Biota 14:06:30 Problem solved 14:07:55 -!- Slereah has quit (Ping timeout: 246 seconds). 14:12:24 @ask ais523 May I "interview" you for an essay on the impact of Turing's paper On Computable Numbers? 14:12:24 Consider it noted. 14:18:39 Biota wasn't the first 2D programming language. 14:21:47 Mouse reminds me of FALSE and was quite a few years earlier. (I have a copy of Grogono's book) 14:23:26 -!- Taneb has quit (Quit: Page closed). 14:39:52 -!- mrhmouse has joined. 14:45:32 -!- metasepia has quit (Remote host closed the connection). 14:45:37 -!- Phantom__Hoover has joined. 14:46:07 ~duck grogono 14:46:07 ...? 14:46:27 -!- metasepia has joined. 14:46:32 ~metar CYUL 14:46:33 CYUL 261420Z 22012KT 12SM -SHSN BKN030 BKN050 OVC080 01/M04 A3017 RMK SC5SC1AC2 SLP217 14:46:42 much better. 14:47:10 ~metar ENVA 14:47:10 ENVA 261420Z 25012KT 9999 VCSH BKN025 07/04 Q1011 TEMPO 25030G40KT RMK WIND 670FT 26017G30KT 14:48:27 too much TEMPO 14:50:30 here they are called «abris tempo» → http://www.abristempo.com/ 14:51:07 Ô KAY 14:51:47 Ô CANADA. 14:52:38 ꙮ CANADA 14:53:11 -!- tertu has joined. 14:59:51 -!- Phantom_Hoover has joined. 15:00:56 -!- Phantom__Hoover has quit (Ping timeout: 265 seconds). 15:01:55 -!- realzies has joined. 15:02:24 `relcome realzies 15:02:26 ​realzies: Welcome to the international hub for esoteric programming language design and deployment! For more information, check out our wiki: . (For the other kind of esoterica, try #esoteric on irc.dal.net.) 15:06:01 hoily 15:06:12 quintopia: the package, it was received :D 15:06:24 wat! 15:06:35 * boily claps with small hands *CLACKACLACKACLACKACLACKACLACKA* 15:06:37 boily: good catch! 15:06:55 but but these packages were obviously destined to be eternally in transit! 15:07:15 you have doomed us all 15:07:40 boily: your hands sound suspiciously wooden 15:07:41 the Doom was already Sealed when Roujo and I met irl. 15:07:48 oerjan: plasticky. 15:07:54 ah. 15:07:58 oerjan: we can restore the balance by putting another package in transit asap 15:08:09 quintopia: ah, good thinking 15:08:11 so quick, send me something cool 15:09:20 i sense a disturbance in the force 15:10:26 someone else has suggested the world will end anyway due to the alignment of thanksgiving and the start of hanukkah 15:10:43 boily: hi 15:10:45 yes, clearly this has never happened before. 15:11:19 quintopia: maybe it will instead cause thanksgiving to last 8 times as long as usual. 15:12:16 oerjan: yes, please 15:12:17 this will _seem_ welcome, until they discover on the 3rd day that this does not extend to turkey supply. 15:12:33 that seems unlikely 15:12:49 thanksgiving leftovers always last well over a week 15:13:00 hm i see 15:13:19 realzies: what brings you here? 15:13:29 dunno 15:13:33 I been idling here 15:13:42 oh. so were you already `relcomed? 15:13:48 lol don't remember 15:13:53 but I don't remember why I joined 15:13:59 ah esoteric programming, sounded interesting 15:14:49 fizzie!!!! 15:14:52 quintopia: here we have réveillon leftovers. a little bit later in the year, but just about the same: lots of meat and gravy and sauces and things that make you fat even if they had some fruits in them at some time. 15:15:50 "Jean-Baptiste Réveillon, (Paris, 1725 – Paris, 1811) was a French wallpaper manufacturer. Réveillon's career was an exemplary story of the self-made businessman in the Ancien Régime." 15:16:02 why are you yelling for fizzie? 15:16:17 ~duck réveillon 15:16:18 --- No relevant information 15:16:30 quintopia: if you look closely, you can see something missing... 15:16:33 oerjan: https://fr.wikipedia.org/wiki/R%C3%A9veillon_de_No%C3%ABl 15:16:53 what the fungot could it be? 15:17:32 no fungotting idea 15:17:52 * boily casts a nasty look over at fizzie. “I WANT MY FUNGOT FIX!” 15:18:34 "instant magique pour les enfants". yes please! <3 magic 15:19:44 boily: i note the cross-language links for that are generally like "christmas eve" 15:20:00 boily: it's probably good you got some time off. you seem a bit overly attached. this could be the sign of addiction 15:20:30 but the english wp also has Réveillon by itself 15:22:13 oerjan: do you know anything about polar representation of quaternions 15:22:26 quintopia: I can quit fungotting any time I want. 15:23:01 okay good now's a good time 15:23:11 hm the picture in french wp is actually swedish christmas eve. by carl larsson, who is of course _the_ painter to use for such. 15:23:24 quintopia: "no" 15:23:44 oerjan: O KAY 15:23:56 quintopia: as oerjan said, “no.” 15:24:17 :\ 15:26:48 ooh Réveillon made the paper for the montgolfier balloons 15:28:54 "His wine cellar, containing 2,000 bottles of wine, was pillaged and quickly consumed by the riotious mob. Réveillon and his family escaped by climbing a wall and fleeing to the nearby Bastille." 15:29:20 -!- AnotherTest has joined. 15:30:31 mmm wine 15:33:27 Oh, no. 15:34:27 -!- fungot has joined. 15:34:30 Phew. 15:42:28 -!- Sprocklem has joined. 15:43:04 fungot: hi there! (and nothing about my mother.) 15:43:04 boily: yeah, it kinda is. :) must've been a burp. first time that's happened in a recent email he sent from think.com was in 1993. 15:45:03 fungot: 1993 is not recent 15:45:04 mrhmouse: it features dolph lundgren. nuff said. :) for me, then period fnord me like that before: mors said i suck. choose two. i'd rather use some sort of 15:49:08 i wish i had a burger 15:55:16 <`^_^v> who doesnt 15:56:44 the burgeousie 15:57:46 -!- nooodl has joined. 15:58:24 * boily cringes at the sight of that missspelling 15:58:45 the last u was note ven intended 15:59:48 bourgeoisie DID I DO IT RITE 16:00:10 it's the hardest word to spell ever, so... 16:01:00 YOUR RITED IT WELL. 16:01:35 it has too many vowels relative to consonants 16:01:37 * boily mutters to himself... «à cause que le monde ont de la misère tant que ça avec l'orthographe...» 16:01:49 boozhwazee 16:02:05 the vowels are short! 16:02:08 that's a little better 16:03:36 /buʁ.ʒwa.zi/. 16:04:14 bourjoisie 16:04:24 hm. that reminds me it's been a long time since I've last disturbed Koen_ with my "horrible" accent :D 16:04:27 i think that's the only plausible simplification 16:04:52 oerjan: that'd be logicaler, but then you're going against the Académie Française of Décisions Stupides concerning la Langue Française. 16:06:23 boily: maybe someone could arrange to have the academie and the OQLF have an ... accident? 16:19:40 -!- FreeFull has joined. 16:23:51 -!- Slereah has joined. 16:33:36 oerjan: for the right price, I could. 16:33:46 (hey, people outside of Québec know about the OQLF! :D) 16:34:34 from this channel, no less 16:34:55 -!- AnotherTest has quit (Ping timeout: 246 seconds). 16:40:43 -!- MindlessDrone has joined. 16:47:16 Does the CPU automatically increment the instruction pointer with each instruction, and if so, what happens once the code reaches the end of the code segment (or addressable memory, even) 16:47:36 Does it just stop? 16:47:48 -!- Phantom__Hoover has joined. 16:49:40 -!- Phantom_Hoover has quit (Ping timeout: 265 seconds). 16:52:36 i still haven't heard enough canadian french to imagine what boily's accent sounds like 16:52:57 -!- carado has quit (Ping timeout: 252 seconds). 16:53:41 Quebecer accent is hilarious 16:53:44 At least to us french people 16:56:00 -!- ais523 has joined. 16:56:30 nooodl: sample → http://www.radio-canada.ca/widgets/mediaconsole/medianet/6893298 16:57:28 @messages? 16:57:29 You have 2 new messages. '/msg lambdabot @messages' to read them. 16:58:07 @candy? 16:58:07 Unknown command, try @list 16:58:10 :( 16:58:12 @tell Taneb I'm not opposed to the idea, but given that I've never actually read that paper, it may be a less informative paper interview than you expect 16:58:13 Consider it noted. 16:58:23 oh, this reminds me 16:58:39 a question that this channel has a decent chance of knowing the answer of 16:58:52 is there a monad for which a >>= b is defined as a b? 16:58:57 (and does it have a name?) 16:59:05 a applied to b? 16:59:08 oerjan: yes 16:59:15 Maybe you mean b a? 16:59:33 shachaf: I don't think so, but that might inspire me 16:59:44 I realised that something I did for work looked a lot like do-notation 16:59:46 shachaf's is the Identity monad. 16:59:52 then tried to work out the monad it was the do notation for 17:00:00 Yes (modulo newtypes). 17:00:25 oh hm 17:00:29 well you'd have (a :: m p) and (b :: p -> m q) and (a >>= b :: m q) 17:00:44 Yes. 17:00:48 my do-notation looks something like "(a, b, c) <- x; (d,e) <- y a b; (f) <- z c d e" 17:00:58 the only application you can get outta there is "b a" where m is Identity 17:01:23 which desugars into \q.x(\(a,b,c).y(\(d,e).z(\f.q))) 17:01:58 OK, maybe that's a continuation monad of some sort? 17:02:10 ais523: given that a >>= return = a for all monads, what would return be in yours? 17:02:23 Or trying to be one somehow. 17:02:38 oerjan: I'm not sure, I just noticed the similarity to do-notation 17:02:43 -!- Sprocklem has quit (Ping timeout: 265 seconds). 17:02:57 which made me think there might be a monad in there somewhere 17:03:29 -!- carado has joined. 17:03:39 you would need a return = a (with some newtype wrapping for the types to even work) 17:03:59 perhaps a >>= b = a b is the wrong definition 17:04:11 yeah, it's compose 17:04:13 I'm not sure I understand your desugaring. 17:04:13 not apply 17:04:25 a >>= b = a . b 17:04:29 that seems a lot saner 17:05:44 now you need return x . b = b x 17:06:03 wait, which way round does compose go? 17:06:05 perhaps it's b.a 17:06:26 \x.(a >>= b) x = b(a(x)) 17:06:39 :t \x -> b(a(x)) 17:06:40 Couldn't match expected type `t1 -> t0' with actual type `Expr' 17:06:40 The function `b' is applied to one argument, 17:06:40 but its type `Expr' has none 17:06:49 :t \b -> \a -> \x -> b(a(x)) 17:06:50 (t1 -> t) -> (t2 -> t1) -> t2 -> t 17:06:53 err 17:06:53 b (a x) == (b.a) x 17:07:06 OK, then (>>=) = flip (.) 17:07:14 sorry for being so bad at Haskell :-( 17:07:25 ais523: What happens to the "y a b" and "z c d e" in your desugaring? 17:07:43 err, whoops 17:08:29 it produces \q->x(\(a,b,c)->(y a b)(\(d,e)->(z c d e))(\f->q))) 17:08:59 apologies for the gratuitous Verity 17:09:10 I'll try to remember that Haskell uses -> not . in its lambdas 17:09:35 I'm not sure I see how that "q" thing is working. 17:09:36 ais523: i think you still have some parentheses wrong there, but otherwise it's the Cont monad. 17:09:44 oerjan: right 17:09:49 I can believe that this is Cont 17:09:49 if you drop the \q-> 17:09:54 yeah, that's fine 17:10:07 Anyway I have to go now. 17:10:29 the application for this is that I'm trying to write a linker 17:10:35 @src >>= Cont 17:10:35 Source not found. I am sorry. 17:10:39 @src Cont >>= 17:10:40 Source not found. Do you think like you type? 17:10:43 * shachaf vanishes for a while. 17:10:46 @src ContT >>= 17:10:46 Source not found. You untyped fool! 17:10:53 @src >>= ContT 17:10:53 Source not found. 17:10:56 @src Cont (>>=) 17:10:56 m >>= k = Cont $ \c -> runCont m $ \a -> runCont (k a) c 17:10:57 hth 17:11:12 @djinn-add type Contt r a = (a -> r) -> r 17:11:16 that links together various libraries which are basically just open terms 17:11:21 int-e: please fix @src to be parenthesis-insensitive thx 17:11:27 @djinn Contt r a -> (a -> Contt r b) -> Contt r b 17:11:27 f a b c = a (\ d -> b d c) 17:11:50 @tell int-e please fix @src to be parenthesis-insensitive thx 17:11:50 Consider it noted. 17:12:57 ais523: oh your \q is actually correct 17:12:59 -!- Phantom_Hoover has joined. 17:13:12 for Cont 17:13:29 why don't we ever get to talk to keymaker 17:13:30 oerjan: I thought it would be, otherwise I don't see how >>= would be associative 17:13:41 Oh, another reason it didn't make sense is that you don't have a ... at the end of the do block. 17:13:51 You don't actually mean a lone "q" at the end there, I guess. 17:14:09 shachaf: ah right 17:14:16 -!- Phantom__Hoover has quit (Ping timeout: 264 seconds). 17:14:21 I don't have a lone \q at the start either, though 17:14:45 ? 17:14:55 why don't we ever get to talk to keymaker <-- i don't think he uses irc? 17:15:03 `seen keymaker ever 17:15:07 A do block can't end on a <-, anyway. 17:15:14 I am the gate keeper 17:15:29 Slereah: koo koo kachoo 17:15:34 No output. 17:16:12 `seen keymaker ever 17:16:14 * shachaf really vanishes. 17:16:43 No output. 17:17:05 `seen output 17:17:10 not lately; try `seen output ever 17:17:16 `seen output ever 17:17:19 `cat bin/seen 17:17:20 ​#! /usr/bin/env perl \ ($n,$e)=split /\s+/, join(" ",@ARGV); $n=~s/ *$//; $c="ls -r /var/irclogs/_esoteric/????-??-??.txt"; $c.=" | head -n 30" unless $e eq "ever"; @f=split /\s+/, `$c`; for $f (@f) { open F,"<$f"; @l=grep(/^..:..:..: <$n>/i,); close F; if (@l) { $b=$f; $b=~s#.*/(.*?).txt#$1#; print "$b $l[-1]"; exit 1; } } print $e eq "ever 17:17:27 `url bin/seen 17:17:31 http://codu.org/projects/hackbot/fshg/index.cgi/raw-file/tip/bin/seen 17:17:36 but you're not *really* a part of the community if you're not in the channel RIGHT 17:17:47 No output. 17:18:18 it's not supposed to give no output if it doesn't find somewhere, so it's probably timing out 17:18:39 which of course means he hasn't been here in a _long_ time. 17:18:46 `pastelogs keymaker 17:18:55 http://codu.org/projects/hackbot/fshg/index.cgi/raw-file/tip/paste/paste.28419 17:19:25 heh he was here in 2004 17:19:38 a _lot_. 17:19:59 `pastelogs keymaker has 17:20:08 http://codu.org/projects/hackbot/fshg/index.cgi/raw-file/tip/paste/paste.32253 17:20:29 can you tail that? 17:20:36 that got up to 2005. 17:20:37 i was not here in 2004. i didn't even create spiral until 2004. 17:21:32 `url bin/pastelogs 17:21:34 hmm 17:21:34 http://codu.org/projects/hackbot/fshg/index.cgi/raw-file/tip/bin/pastelogs 17:21:42 matrix reloaded came out in 2003 17:21:51 `which pastelog 17:21:52 ​/hackenv/bin/pastelog 17:21:52 so maybe that was when keymaker came into existence 17:21:57 `url bin/pastelog 17:21:59 http://codu.org/projects/hackbot/fshg/index.cgi/raw-file/tip/bin/pastelog 17:22:30 the stopping is written into the pastelogs program. 17:22:40 -!- Phantom_Hoover has quit (Ping timeout: 264 seconds). 17:24:02 `pastelog keymaker has quit 17:24:18 http://codu.org/projects/hackbot/fshg/index.cgi/raw-file/tip/paste/paste.20577 17:24:35 Last here in 2008 17:24:53 so, anyway speaking of keymaker, Etre really is a tour de force in my opinion. there couldn't have been an easier lang to implement in SELECT. 17:25:57 * quintopia foresees a future in which all new imperative tape languages are reduced from Etre rather than BF 17:26:49 but BF has IO! 17:28:06 -!- oerjan has quit (Quit: that's irrelevant to TC-ness, boily). 17:28:38 boily: IO is unnecessary for TC! 17:28:53 quintopia: it's necessary for BF-completeness 17:28:57 which is a real, interesting category 17:29:33 fwiw, if I have a lang that's really /really/ eso and want to prove it TC, then cyclic tag tends to be easiest 17:30:31 BCT? 17:31:38 BCT is a specific syntax for cyclic tag 17:31:58 just like you can invent a syntax for Turing machines, say 17:32:13 but Turing machines are a concept that exists independent of syntax 17:32:26 is it? i thought it was just specifying the alphabet was 10 and a specific rule for when to apply the production 17:33:04 ah well 17:33:13 cyclic tag always has an alphabet of two symbols 17:33:22 it's the original tag that can have more 17:33:31 cyclic tag would have been harder to implement than etre for SELECT. 17:34:18 -!- FreeFull has quit (Ping timeout: 245 seconds). 17:34:35 hmm, really? that surprises me 17:35:16 etre needs an extendable tape, whereas cyclic tag needs a queue, which mostly uses the same structure but doesn't need an internal pointer 17:36:21 -!- FreeFull has joined. 17:36:26 but an infinite tape is already a feature in SELECT 17:36:33 as well as a tape pointer 17:37:12 -!- impomatic has left. 17:37:23 as it is in most imperative tape languages 17:44:03 yeah but I consider those uninteresting :-) 17:45:31 they don't have to be uninteresting. depends on what your goals are 17:46:40 speaking of which, i came up with a new lang. partially. basically it's oklopol's minigolf idea in 3D. interesting because i have a TC proof. 17:46:42 something I haven't seen yet: a Game of Life where cells are fragments of a 2D esolang. 17:47:14 (although i am not trying to encode anything in the decimal digits) 17:47:24 boily: make it 17:49:12 quintopia: after reimplementating metasepia. 17:49:42 boily: inventing a languabe is not nearly so time-consuming as implementing *anything* 17:49:56 languabes are fun 17:50:02 * quintopia eats a languabe 17:50:52 Eat a languava, it's healthy. 17:50:56 `run echo 'Languabes are edible and fun. They provide a quick implementation energy boost!' >wisdom/languabe 17:51:00 No output. 17:52:58 * shachaf unvanishes a bit. 17:53:04 -!- nisstyre has quit (Quit: Leaving). 17:55:18 Did you figure out your monad? 17:57:56 shachaf: yeah, it was Cont 17:58:41 Cont is p. good 17:58:49 Codensity is even better, of course. 18:16:15 btw, today I had a complaint that Verity wasn't sexp-based, making it harder to implement a macro syste 18:16:18 *system 18:16:29 my conclusion for this is that the world generally needs better ways to manipulate parse trees 18:16:50 @tell zzo38 i don't think opencl c even has provisions for exceptions 18:16:50 Consider it noted. 18:17:22 how would you implement an exception happening in some threads and not others? 18:17:45 even if statements are a little tricky to implement at anything finer-grained than the warp level 18:18:08 right 18:18:08 closest you can get is to do the calculations anyway and just not store the data anywhere 18:18:44 incidentally, Don Knuth apparently uses this technique when writing INTERCAL 18:19:04 not because it's necessary, but because he finds it easier than actually writing a control flow statement 18:22:07 i like don. he seems like a p cool guy. 18:22:09 fungot: how many warps do you support? 18:22:09 boily: hmm. when was it pebble and co surge? 18:22:49 fungot: pebbles are smart watches. the co-everything are propagated by Nutty Categoricists. 18:22:50 boily: forth is worth learning ( for chicken at least behaves much like emacs lisp to me. all you need is 18:23:37 quintopia: his secretary has actually emailed me, because esr CCed me on an email to him and it went reply-all from then on 18:23:45 fizzie: s/fnord/chicken/g 18:23:49 he was commissioning a new version of C-INTERCAL 18:23:54 some day, we may find out why 18:23:56 his secretary has emailed me also 18:24:08 interesting 18:24:09 what for? 18:24:42 ais523: why is a new version necessary? is the spec changing? 18:25:05 quintopia: he just wanted a bugfix release, it seems 18:25:14 i was accidentally removed from the bank of san serriffe page 18:25:15 just to make sure everything was up to date 18:25:22 and also some other thing 18:25:41 ais523: are there any bugs? 18:25:50 yes, we find them every now and then 18:26:20 here's a particularly nasty one I fixed a couple of months ago: https://gitorious.org/intercal/intercal/commit/a905156af4fd2ab88036f59c13321081bd203d47 18:32:38 even better, the bug was in the build system so you don't need to know any INTERCAL to understand it 18:34:58 yeah. what is ick though 18:35:06 what is pit 18:35:43 quintopia: ick is the Intercal compiler library 18:35:49 and pit is the directory containing the testsuite 18:37:16 -!- activ_Trinidad has joined. 18:37:24 `relcome activ_Trinidad 18:37:27 ​activ_Trinidad: Welcome to the international hub for esoteric programming language design and deployment! For more information, check out our wiki: . (For the other kind of esoterica, try #esoteric on irc.dal.net.) 18:37:43 `bienvenido activ_Trinidad 18:37:46 activ_Trinidad: ¡Bienvenido al centro internacional para el diseño y despliegue de lenguajes de programación esotéricos! Por desgracia, la mayoría de nosotros no hablamos español. Para obtener más información, echa un vistazo a nuestro wiki: http://esolangs.org/wiki/Main_Page. (Para el otro tipo de esoterismo, prueba #esoteric en irc.dal.ne 18:37:49 How many bots are around nowadays 18:38:12 -!- nisstyre has joined. 18:38:43 where is the bot prefix list again 18:38:58 nooodl: there's a bot prefix list? 18:39:07 hackego has it? 18:39:39 ^prefixes 18:39:39 Bot prefixes: fungot ^, HackEgo `, EgoBot !, lambdabot @ or ?, thutubot +, metasepia ~, jconn ) , blsqbot ! 18:40:02 (if things were sane, it would be accessible by just saying "prefices" on its own line without any prefix) 18:40:36 `seen blsqbot 18:40:40 `seen blsqbot ever 18:40:40 not lately; try `seen blsqbot ever 18:40:45 2013-03-08 14:18:29: Pong! 18:41:02 clearly a nonbot 18:44:08 `prefixes 18:44:10 Bot prefixes: fungot ^, HackEgo `, EgoBot !, lambdabot @ or ?, thutubot +, metasepia ~, jconn ) , blsqbot ! 18:44:12 !prefixes 18:44:14 Bot prefixes: fungot ^, HackEgo `, EgoBot !, lambdabot @ or ?, thutubot +, metasepia ~, jconn ) , blsqbot ! 18:44:19 (Just checking.) 18:44:54 Doesn't lambdabot also respond to > ? 18:44:57 > 1 + 1 18:44:58 2 18:45:30 It's not quite the same sort of prefix, but admittedly it is a kind of a prefix. 18:45:46 well, I mean, it invokes lambdabot 18:45:46 :k Int 18:45:47 * 18:45:58 -!- activ_Trinidad has quit (Remote host closed the connection). 18:46:07 lambdabot: You're such a prefix-hog. 18:46:32 -!- activ_Trinidad has joined. 18:46:35 at least it doesn't respond to its name 18:46:43 @pinky Are you thinking what fizzie is thinking? 18:46:43 But where will we find an open tattoo parlor at this time of night? 18:46:55 I don't think I'm thinking the same. 18:46:56 lambdabot: ? 18:46:56 Maybe you meant: . 1337 ? @ activity activity-full admin all-dicts arr ask b52s bf bid botsnack bouvier brain bug check choice-add choose cide clear-messages clear-topic compose define dequeue-topic devils dice dict-help djinn djinn-add djinn-clr djinn-del djinn-env djinn-names djinn-ver do docs dummy easton echo elements elite eval faq farber 18:46:56 flush foldoc forget fortune free freshname gazetteer get-shapr get-topic ghc girl19 google googleit gsite gwiki hackage haskellers help hitchcock hoogle hoogle+ id ignore index instances instances-importing irc-connect irc-password jargon join karma karma+ karma- karma-all keal kind l33t learn leave leet let list listall listchans listmodules 18:46:56 listservers localtime localtime-reply messages messages-loud messages? more msg nazi-off nazi-on nixon oeis offline palomer part paste ping pinky pl pl-resume pointful pointless pointy poll-add poll-close poll-list poll-remove poll-result poll-show pop-topic pretty print-notices protontorpedo purge-notices push-topic queue-topic quit quote rc 18:46:56 reconnect remember repoint roll run sequence set-topic shift-topic shootout show slap smack spell spell-all src tell thank you thanks thesaurus thx tic-tac-toe ticker time todo todo-add todo-delete type undefine undo unlambda unmtl unpf unpl unpointless unshift-topic uptime url v vera version vote what where where+ wiki wn world02 yarr yhjulwwiefzo 18:46:56 jcbxybbruweejw yow 18:47:02 to anyone good at hackego: the bienvenido message drops a "t" at the end 18:47:18 @help jcbxybbruweejw 18:47:18 help . Ask for help for . Try 'list' for all commands 18:47:29 It also drops a ). 18:47:30 @help yhjulwwiefzojcbxybbruweejw 18:47:30 V RETURNS! 18:47:34 hmm 18:48:02 @v 18:48:02 Exception: <> 18:48:19 @oeis 346357 18:48:20 Sequence not found. 18:48:36 @oeis 32,53,92 18:48:37 Sequence not found. 18:49:02 @oeis 1,11,21,1211 18:49:03 Look and Say sequence: describe the previous term! (method A - initial term ... 18:49:24 -!- Nisstyre-laptop has joined. 18:49:55 @tic-tac-toe 18:49:55 how about a nice game of chess? 18:50:04 -!- Nisstyre-laptop has quit (Read error: Connection reset by peer). 18:50:16 @poll-list 18:50:16 ["(++)","ConfusedWithVixenSituation","FlavaOfJRuby","Prelude-(.)?","best-programming-language","best-spoken-language","food","funniest-thing-in-the-whole-world","naming","nethack","president","prove->","remove@src","sleep"] 18:50:33 @poll-result funniest-thing-in-the-whole-world 18:50:33 Poll results for funniest-thing-in-the-whole-world (Open): unintentionally-funny-situations=1, Poles=1 18:50:50 @poll-result nethack 18:50:50 Poll results for nethack (Open): Val_Dwa_Fem_Law=1, Wiz_Elf_Mal_Cha=1 18:51:00 boring 18:51:03 that wizard should be a gnome :-( 18:51:07 but valks are better 18:51:08 Gnome? Why? 18:51:26 @poll-result best-spoken-language 18:51:26 Poll results for best-spoken-language (Open): magyar=3, Polish=484, Welsh=1, Georgian=2, Manx=1, norwegian=8 18:51:26 shachaf: you get to play neutral 18:51:29 and their caps are easily high enough 18:51:31 I always played Wiz_Elf_Mal_Cha back in the day. 18:51:36 and they're not human, which is the really important thing 18:51:41 Wow, that's quite a win for Polish. 18:51:45 What's the advantage of being neutral? 18:51:59 no chaotic disadvantages, and you get the best artifact selection 18:52:24 You can get Magicbane and the quest artifact anyway. 18:52:33 -!- activ_Trinidad has quit (Remote host closed the connection). 18:52:45 What are the chaotic disadvantages? 18:52:55 And the artifact advantages? 18:53:01 (I haven't played NetHack in quite a while.) 18:54:06 artifact advantages: there is 1 useful lawful artifact and basically 0 useful chaotic artifacts (best is the MKoT, which isn't really good) 18:54:13 also the lawful artifact's only really good on speedruns 18:54:18 there are like 5 or 6 viable neutral artifacts 18:54:24 -!- activ_Trinidad has joined. 18:54:46 chaotic disadvantages (and advantages) are all minor but there are a lot of them 18:54:51 quite a lot to keep in track 18:54:58 god mollification is a big one, it's harder for chaotics 18:55:03 True. 18:55:33 I remember there being less of a penalty for killing shopkeepers, or something. 18:56:18 yeah, but if you're powerful enough to kill the shopkeeper, the penalty mostly doesn't matter anyway 18:56:42 Maybe I should play NetHack 4. 18:57:43 shachaf: you might want to wait a couple of weeks, we're working on a stable version atm 18:58:12 I'm trying to do stuff with the stack, but the assembler bitches when I do this : 18:58:17 push 2, mov dx, [sp] 18:58:30 Is it a syntax problem or can you not move the stack pointer? 18:58:41 I'm not sure what that's supposed to mean. 18:58:44 what's the comma after 2 for 18:58:55 what's the mov after the comma for 18:59:02 It's not in the program 18:59:09 Are those two lines? 18:59:12 I just wanted to paste it here in one line 18:59:16 ah right 18:59:18 push 2 18:59:19 mov dx, [sp] 18:59:23 If you insist 18:59:40 I get "reserved word used as symbol" 19:00:11 On which token? 19:00:13 I was wondering whether derefencing sp is allowed, but it probably is due to omit-frame-pointer 19:00:34 for mov dx, [sp], no idea which part 19:00:42 Yes, it should be fine (at least on 32-bit x86?). 19:00:44 I don't know Intel syntax very well. 19:02:16 Do you need to specify "dword" or something? 19:03:36 Hm, maybe 19:03:40 Let's see how big is SP 19:04:35 I guess it'd be "word" or whatever it's called. But I don't think that's the issue. 19:06:12 I think they're both 16? 19:06:40 Oh wait, it's the address 19:06:52 -!- Taneb has joined. 19:06:52 Right, I think addresses are 4 bytes 19:06:59 Probably the problem 19:07:05 Why are you using sp, then? 19:07:18 Just looking at the content of the stack 19:08:10 sp is a 16-bit register 19:08:14 Maybe you want esp. 19:08:45 if he had esp, he'd already know the answer 19:08:53 he'd just read some intel guru's mind 19:08:58 Yes, but when you use it in an address, it points to a 4 bytes object, no? 19:09:10 32 19:09:20 Which I guess is the problem 19:09:49 So it would either be mov edx,[sp] or mov dx, byte ptr [sp], I guess 19:10:11 k 19:10:21 Let's try. 19:10:22 ? 19:14:38 you shouldn't need "word ptr" for "mov dx, [sp]" because the size is known from the destination being a 16-bit register 19:15:02 Sounds reasonable. 19:15:29 and I thought Slereah is doing 16-bit programmin' 19:15:42 Hm 19:15:52 I thought so too, but in that case what's the "addresses are 4 bytes" deal? 19:15:59 wrongness? 19:16:19 Ah 19:16:23 Wrong, yes 19:16:28 Nevermind 19:16:33 Then I don't know the problem 19:16:52 I think maybe [sp] addressing modes just don't exist in 16-bit 19:17:03 does the code assemble if you change sp to another register? 19:17:09 Yes. 19:17:25 Wait 19:17:28 No it doesn't 19:17:30 Hm 19:17:34 16-bit x86 is less orthogonal than the newer versions; it's more of a thing that ax is the "accumulator" and bx is the "base" and such 19:17:42 this affects what you can do with them 19:17:53 Oh, looks like that's right. 19:18:10 Maybe flat assembler doesn't use [] 19:18:19 I tried getting this working here and it didn't work with mov edx,[esp] either. 19:18:25 hmm 19:18:31 But I think that was an issue with GNU as's Intel mode or something. 19:18:38 Ah, mov dx, [bx] works 19:18:44 Because I did manage to get code that disassembled to that. 19:18:49 So I guess sp is the problem 19:18:58 Is there a way to get the value of the stack pointer? 19:19:10 Slereah: yeah, you can use bp, si, di, bx as pointers, but maybe not the other regs in 16-bit mode 19:19:31 Slereah: mov ax, sp 19:19:46 So I guess what I want is like 19:19:55 mov ax, sp 19:20:02 mov bx, [ax] 19:21:04 It works! 19:21:15 Woo 19:21:26 -!- Sprocklem has joined. 19:21:35 Any less circuitous way to get a value from the stack without popping it? 19:22:16 you could just pop and then sub sp, 2 ;P 19:22:25 pop bx; ... what kmc said 19:22:35 I think that's probably more circuitous, though. 19:22:43 Wouldn't I need add sp, 2? 19:22:47 To put the pointer back up? 19:22:55 the stack grows towards smaller addresses 19:22:57 -!- AnotherTest has joined. 19:23:00 Oh, I see 19:23:02 Thanks 19:23:12 this confuses roughly everyone at some point 19:23:16 I guess both are as circuitous 19:23:56 how did i find out all these things 19:24:03 probably by looking at disassembled code 19:24:34 I wish assembly was a bit less stringent with its functiond 19:24:44 Just treating all registers the same way 19:24:48 Except for specific functions 19:24:57 why are you writing 16-bit x86 19:25:02 well, the newer versions of x86 are more like that 19:25:08 and other architectures even moreso 19:25:09 I'm running it in DosBox 19:25:25 Not sure it allows 32 19:25:27 in the original ARM architecture, even the instruction pointer is an ordinary register that can be used as an operand for anything else 19:25:38 Slereah: it does, however you'd need to write the code to switch to 32-bit mode yourself, which is gross 19:25:45 or hook into some "dos extender" 19:25:46 yeah 19:25:54 I'll wait to be a bit more experimented first 19:25:57 you could just write 32-bit Linux programs in assembly instead 19:25:59 but shrug 19:26:01 16-bit is fun 19:26:06 you can write a boot sector graphics demo :) 19:26:17 I find it weird that they always say "you can't change the IP!" everywhere 19:26:24 But JMP is basically mov ip 19:26:26 yep 19:27:01 you can even do "jmp [some_addr]" which is like "mov ip, [some_addr]" 19:27:03 or "jmp ax" 19:27:25 there's even conditional move into ip 19:27:29 By the way 19:27:30 v. sophisticated 19:27:30 you can actually do a mov ip on a PIC, but the jmp is more efficient because there are only two registers you can assign a constant to, and one of them's the IP 19:28:07 Can I move the IP in such a way that the variables are interpreted as functions? 19:28:22 Like say, I dunno 19:28:41 123456 is [opcode 12] 34 56 19:28:45 You do ip++ 19:28:50 -!- muskrat has joined. 19:28:53 And then it reads as [opcode 34] 56 19:29:02 Slereah: sure 19:29:06 Neat 19:29:07 sometimes that's used for golfing, or obfuscatoin 19:29:10 *obfuscation 19:29:13 -!- muskrat has quit (Client Quit). 19:29:38 -!- activ_Trinidad has left. 19:31:28 -!- MindlessDrone has quit (Quit: MindlessDrone). 19:39:54 `pbflist 19:39:55 pbflist: shachaf Sgeo quintopia ion 19:40:01 `pbflist 19:40:02 pbflist: shachaf Sgeo quintopia ion 19:40:42 `peanut-butter-fjelly-list 19:40:44 ​/home/hackbot/hackbot.hg/multibot_cmds/lib/limits: line 5: exec: peanut-butter-fjelly-list: not found 19:40:54 `pbflistdeluxe 19:40:56 pbflistdeluxe: 19:41:01 Such a shame. 19:41:12 You would've gotten higher-quality updates, and earlier. 19:45:07 _LIBCPP_ALWAYS_INLINE _LIBCPP_CONSTEXPR operator int __nat::*() const {return 0;} 19:45:30 I can see why that was wanted always inline 19:45:35 and it looks like an excellent candidate for constexpr 19:45:45 although, hmm 19:45:54 * kmc can't parse operator int __nat::*() 19:46:05 "operator int" is a fine name for a function 19:46:08 yeah, constexpr is useful in case you want to parse something in terms of it 19:46:18 kmc: isn't that the name of the "(int)" cast that casts things to int? 19:46:28 yeah but what's the "__nat::*()" doing 19:46:40 hmm.. 19:47:11 where's that from 19:47:12 gah, my attempted fix to the random compose key breakages didn't help 19:47:17 *hmm… 19:47:19 there we go 19:47:40 shachaf: it's from libc++ i guess 19:47:45 "it's from compiler errors" 19:47:51 perhaps it's an int*, with a weird order 19:48:18 Man the part that's really gonna be shitty is when I'll have to learn protected mode 19:48:25 Can't understand much so far 19:48:34 Oh, https://llvm.org/viewvc/llvm-project/libcxx/trunk/include/cstddef?revision=111750&pathrev=113270 clears up a bit about it, maybe. 19:48:53 Slereah: writing ordinary userspace code to run under a typical protected mode OS is nice and simple 19:49:05 Slereah: putting the CPU into protected mode yourself, i.e. writing a protected mode OS, is not simple 19:49:18 Yeah 19:49:27 I looked at it a bit 19:49:34 I can't seem to quite grasp it 19:49:39 what about it 19:50:26 The global descriptor table, I guess 19:50:49 the basic thing is that in real mode, the segment selector registers (cs ds es ss fs gs) are just a value that gets multiplied by 16 and added to your address, but in protected mode they are indexes into one of these descriptor tables 19:51:03 That much I got 19:51:08 each entry ("segment descriptor") in the descriptor table describes a segment 19:51:08 But how do you fill these tables 19:51:21 they live in memory 19:51:34 What is the type "int T::*"? 19:51:39 And why does the code even have overlapping segments? 19:51:43 Where T is a struct. 19:51:46 That's the weirdest part 19:51:49 you just build those structures in memory and then use the "sgdt" instruction to set the global descriptor table base 19:52:00 kmc: LGDT. 19:52:10 oh is it 19:52:11 sorry 19:52:26 Slereah: what about it's weird? 19:52:28 or what do you mean 19:52:51 (It's like, LGDT loads the GDT register from memory, and SGDT stores it into memory, like other L/S pairs.) 19:53:07 Why aren't the address built as DS * 1000h + DI instead of * 10h 19:53:17 oh 19:53:21 you're back to real mode now 19:53:29 Yeah 19:53:42 I guess what I'm asking is, why did they even need protected mode to access all memory 19:54:02 the *10h is kind of weird 19:54:06 because real mode had already been defined that way 19:54:10 but I think I can explain why, too 19:54:34 basically it's handy for a kind of position independent code 19:54:36 shachaf: "ptr-operator: * cv-qualifier-seq_opt | & | ::_opt nested-name-specifier * cv-qualifier-seq_opt" is part of the C++ declarator syntax, but I can't quite figure out what it means. 19:54:50 your code doesn't need to know where it lives in physical memory, as long as CS is properly initialized when it runs 19:55:40 Yes, but in that case, why not let DI or whatever offset run the full course of the segment 19:55:49 it does 19:56:00 Sure, but then you get overlap 19:56:08 a "segment" in the real mode context is just 2^16 consecutive bytes 19:56:20 with 16-byte alignment 19:56:49 if you're adjusting CS to relocate code then you want it to be *10h so that you can put it on any 16-byte-aligned address 19:57:04 Aligned? 19:57:08 if it were *10000h then you could only put it at one of 16 different points 19:57:15 Slereah: yes, meaning the address is a multiple of 16 19:57:20 Ah 19:57:40 (one of 16 different points, assuming the physical address size is still 20 bits) 19:58:19 So does the protected mode allow you 2^32 addresses by having the two address arguments not overlap? 19:58:28 template 19:58:28 _LIBCPP_ALWAYS_INLINE 19:58:28 operator _Tp _Up::* () const {return 0;} 19:58:28 (And be indexed by a table as a nicety) 19:58:29 help 19:59:09 shachaf: Actually, are you sure operator int __nat::*() const {return 0;} isn't just the same as int __nat::operator *() const { return 0; } ? 19:59:42 As in, an overload for the unary * with a return type of int. 19:59:53 Slereah: well, firstly, let's ignore the 286's weirdo 16-bit protected mode 20:00:06 fizzie: Yes, because it gives a different error message. 20:00:20 in that case, "protected mode" also means "32-bit mode", and the base specified in a segment descriptor is 32 bits 20:00:28 so they still overlap... 32-bit base plus 32-bit pointer 20:00:33 Ah, okay 20:00:50 Backward compatibility is nice but damn, you have to drag some shit 20:00:52 in fact there's no multiply now 20:00:54 yep 20:01:12 i mean this overlapping isn't backwards compat though 20:01:17 it's a totally different CPU mode 20:01:25 Yeah, but the fact that real mode is still around 20:01:28 yeah 20:01:43 And still being real mode in 16 bits 20:01:46 not only that but there's a new "Virtual 8086" mode in the 386 which lets you run real mode code within a protected mode OS 20:01:55 Apparently there's a long mode with 64 bits registers 20:01:59 that's right 20:02:06 that's x86-64 i.e. amd64 20:02:09 And yet the CPU still has to drag around the 16 bits mode 20:02:12 yep 20:02:15 Like some old grmapa in a wheelchair 20:02:31 at least with EFI you don't need to write 16-bit code when you write an OS, anymore 20:03:00 Are there any CPUs that don't have backward compatibility issues like that? 20:03:04 sure 20:03:06 And are just servicable on their own 20:03:18 non-x86 CPUs 20:03:20 i wonder to what extent real mode is basically a complete 8086 20:03:29 like, Alpha was 64-bit from the beginning 20:03:33 neat 20:04:01 i don't know if there are (say) MIPS64 or AArch64 (64-bit ARM) chips that only run in those modes 20:04:04 i expect not 20:04:20 though 20:04:33 if you're putting a soft MIPS64 in your FPGA, you probably don't want to waste FPGA resources on compat modes 20:04:38 so I bet you can disable them for that 20:04:56 Intel did make a 386 or two that could only run in 32-bit protected mode, but nothing like that since then 20:05:10 and anyway MIPS and ARM and PowerPC don't have any legacy 16-bit mode like x86 has 20:05:13 I wonder how far back the compatibility extends 20:05:19 tertu: oh, interesting! do you have some info on that? 20:05:29 Like could you still install the old DOS on modern CPUs 20:05:35 think so 20:05:50 https://en.wikipedia.org/wiki/Intel_80376 20:05:57 yeah DOS runs on modern cpus 20:06:02 Dang 20:06:06 compatibility goes back to the 8086 20:06:12 tertu: nice 20:06:22 try sticking a freedos boot cd in your computer, it'll work and that's all real mode code 20:06:23 i'm always interested in non-PC-compatible x86 platforms 20:07:07 -!- impomatic has joined. 20:07:08 One day we will have quantum computers and they will have a fucking 16 qbit mode 20:07:12 hahaha 20:07:29 There's gonna be 16 atoms just there to run the DOS 20:07:41 yeah I like seeing the x86 used in non-pc things 20:07:53 (A)bort, (R)etry, (D)o both 20:07:57 hahahaha 20:07:59 nowadays the chips are so tied to being pcs though 20:08:01 :D 20:08:08 the OLPC XO-1 is an x86 platform with OpenFirmware 20:08:59 I wish there were quantum computers out by now 20:09:03 at some point somebody's going to just go fuck ISA, fuck all this 80s legacy shit 20:09:10 I could at least use my half quantum physics half software engineering diploma 20:09:19 the 80s are here to stay man 20:09:21 I wonder what quantum assembly looks like 20:09:36 cool you have a quantum physics diploma? 20:09:38 There's a quantum version of Core War 20:09:41 right now i think quantum computers work by physically arranging bits somehow 20:09:50 like they're at the eniac stages 20:09:55 fizzie: Oh, I think it's a member pointer. 20:10:10 ENIAC had punchcards, no? 20:10:17 yeah but no stored program 20:10:20 you had to wire it in 20:10:21 Or did they recode it by rewiring? 20:10:24 Ah yes 20:10:31 eventually they hacked it up to support stored programs though 20:10:50 * Slereah googles QUANTUM ASSEMBLY 20:10:58 shachaf: I had just arrived at that same conclusion. 20:11:00 but that was after other computers that actually supported it from the start were built 20:11:02 in the future, we'll have holographic cubes. (mind you, those will be 80-column cubes, EBCDIC) 20:11:13 heh 20:11:15 16 colors! 20:11:22 http://arxiv.org/ftp/quant-ph/papers/0201/0201082.pdf 20:11:23 Yessss 20:11:30 QUANTUM C 20:11:35 I want to put that on my resume 20:11:36 kmc: ☝ 20:11:47 I am an expert in quantum COBOL 20:11:52 shachaf: ? 20:11:57 Oh man 20:11:57 shachaf: In retrospect, I guess that should've been pretty obvious, and I thought of it, but then for some reason discarded the idea. 20:12:05 Quantum Core War is described here http://www.freelogy.org/wiki/Coreworld_QTAAS 20:12:05 Imagine the esolangs you could do 20:12:08 QUANTUM BRAINFUCK 20:12:31 kmc: It's pointer-to-member syntax. 20:12:36 E.g. http://publib.boulder.ibm.com/infocenter/comphelp/v8v101/index.jsp?topic=%2Fcom.ibm.xlcpp8a.doc%2Flanguage%2Fref%2Fcplr034.htm 20:12:43 in a world... saturated with quantum brainfuck derivatives... a young boy is about to discover his destiny... 20:13:09 shachaf: yeah i thought it might be 20:13:10 So, a conversion operator into a pointer-to-int-member-of-__nat. 20:13:14 Many Tapes Interpretation 20:13:20 but couldn't make it fit 20:13:33 also for anybody who knows modern x86 architecture: do individual PCIX devices get assigned IO ports still 20:13:43 but what fizzie said makes sense 20:13:46 and is also terrifying 20:14:03 hm? I fail to see the terror in fizzie's utterances. 20:14:29 boily: Then you've been C++-infected. We're going to have to put you out, sorry. 20:15:04 how i learned to stop worrying and love c++ 20:15:40 More like C peepee 20:16:09 fizzie: oh well. my only regret is to not have eaten as much sushi as I would have liked. 20:17:17 I wonder how close is a commercially available quantum CPU 20:17:29 there's that one company which claims to sell a quantum computer 20:17:32 but people think it's bullshit maybe 20:17:48 http://en.wikipedia.org/wiki/D-Wave_Systems 20:18:15 it might be more of a special purpose device for quantum annealing, and not something which can implement an arbitrary quantum circuit 20:18:26 Too bad 20:19:27 can we emulate quantomputing on regular hardware? 20:19:33 Yes 20:19:42 It's a pretty old result, actually 20:19:55 Probabilistic Turing machines have the same power as regular Turing machines 20:20:00 Hence you can emulate it 20:20:08 -!- muskrat has joined. 20:20:36 Either by emulating all possible outputs, or if you can cheat, pseudo randum generator 20:21:21 i don't think doing it with a PRNG is satisfactory for the computability-theoretic result 20:21:27 but people do things like that in complexity theory 20:22:07 if you can invent a PRNG which no poly-time algo can distinguish from true randomness, then you've proven BPP = P 20:22:12 this is called derandomization 20:22:21 -!- Slereah_ has joined. 20:22:23 Like, if you have QUANTUM BRAINFUCK 20:22:29 If there's a probability popping up 20:22:34 Clone the tape 20:22:42 And work on the two tapes with the program 20:22:43 of course it's not known whether BPP = P; nobody has been able to do this yet 20:22:49 why do so many people not understand how quantum computers work 20:22:51 BPP? 20:22:55 kmc: does P = NP iply that? 20:22:56 *impl 20:23:00 *imply 20:23:06 ais523: yes, BPP is contained in NP 20:23:19 Slereah_: https://complexityzoo.uwaterloo.ca/Complexity_Zoo:B#bpp 20:23:43 I see. 20:23:44 that definition of BPP actually doesn't refer to "randomness" per se 20:23:49 and makes it more obvious that BPP is in NP 20:24:13 but basically, BPP is the class of problems that can be solved efficiently on a TM if you have randomness 20:24:41 the probability of a wrong answer needs to be sufficiently far from 1/2 that you can run the machine n times to get an O(2^n) reduction in the error rate 20:25:00 -!- Slereah has quit (Ping timeout: 245 seconds). 20:25:23 ais523, as the person credited with the proof of the universality of Wolfram's 2-3 machine, how important do you think it is to prove or disprove the Turing-completeness of things? 20:25:38 He has a sick sexual fetish for it 20:26:38 Taneb: I think it's fun, but except when you're trying to design a sandbox or similar intentionally sub-TC system, it's less practically important than the question of whether it can run practically useful programs in a reasonable amount of time 20:27:26 ais523: I think people misunderstand quantum computers because there are a lot of appealing but false analogies to classical computers, and because quantum mechanics is fucking weird 20:27:35 Eh 20:27:37 elliott: I'm using Helvetica for parts of my thesis, but it keeps giving me the uncanny valley effect because it's not Arial 20:27:43 like, it's more perfect, but it seems wrong as a result 20:27:47 and maybe a little bit of the "programmers are experts at everything and can work anything out from first principles" bias 20:27:47 I don't think QM is *that* relevant to quantum computing 20:28:01 Basically it's just the state superposition that is relevant to it 20:28:09 and measurement 20:28:20 and the fact that you can rotate probabilities 20:29:08 You know what's cool? 20:29:15 The SUPERTURING computer designs 20:29:21 They will never be fucking built 20:29:21 actually rotating probabilities is probably the weirdest part, it's necessary for any sort of understanding of how quantum computers work 20:29:25 and yet it intuitively makes no sense 20:29:43 What is the probability rotation in quantum terms? 20:29:51 the state of a QC isn't directly made of probabilities either 20:30:30 Slereah_: well probabilities of things in quantum mechanics are given by (possibly entangled) phasors 20:30:35 the probability is the square of the length of the phasor 20:30:42 and the phasors can be rotated so that probabilities cancel out 20:31:05 Phasors? 20:31:13 Is that QC talk for "Hilbert space vector" 20:31:19 the aim of a quantum computer program is to start with a random value, then entangle the phasors in such a way that the ones for the incorrect results cancel out 20:31:31 giving you a high chance of getting the correct answer 20:31:36 and they're basically just vectors in the plane 20:31:39 entangle the phasors! detach the saucer section! 20:31:41 capped at a maximum length of 1 20:33:53 if I get a quantum computer, will I be able to go on Facebook? 20:34:06 No, just quantum facebook 20:34:17 Oh, and there's no JMP in quantum assembly 20:34:19 Only the 20:34:23 QUANTUM LEAP 20:34:25 Is that the one where you can be in multiple relationship statii at once? 20:34:36 that would be convenient 20:34:41 where did the second 'i' come from 20:34:50 Latin plural 20:34:56 shachaf: it's fun to pronounce 20:34:58 ee-eye 20:35:10 yes, but does it make sense 20:35:17 although the second declension male plural would be stati because the original word is status not statius 20:35:24 and I'm not sure it's a second declension male word in the first place 20:35:27 i think molecular orbitals are a better analogy for poly relationships, though 20:35:30 delocalized pi bonds 20:35:42 It's probably an incorrect Latin plural, I don't know any Latin. 20:35:52 i've seen it for words like "radius" but that has an 'i' already 20:35:52 might have something to do with the fact that i'm dating a physical chemist (or chemical physicist?) by education 20:36:32 and for words like hawaius 20:36:54 esotericians' relationships are as weird as the languages they create. 20:37:15 kmc: you're educated to date specific people? 20:37:40 lol 20:38:08 What esolang is your relationship like 20:38:15 boily: i haven't even created any esolangs yet 20:38:19 shachaf: Fun fact: individual characters of ASCII are called "ascius". 20:38:23 (Not true.) 20:38:28 although "x86 with no registers" probably counts, once I write that up 20:38:47 How do you do x86 with no registers 20:38:52 -!- muskrat has quit (Read error: Connection reset by peer). 20:38:58 Are there any instructions that use no registers? 20:39:00 fizzie: zomg 20:39:01 Slereah_: i'll send you a link when it's done 20:39:02 yes 20:39:19 mov dword ptr [some_addr], 1234 20:39:22 add dword ptr [some_addr], 1234 20:39:27 jmp [some_addr] 20:39:28 I guess 20:39:31 these are the main tools 20:39:37 `learn ascii is the plural of ascius 20:39:42 I knew that. 20:39:50 plus self-modifying code 20:40:01 but it's cheating to modify an instruction into one that uses registers 20:40:22 I just modify the address and immediate operands of those instructions 20:40:24 Esolangs are all about cheating 20:40:25 -!- muskrat has joined. 20:40:39 nah 20:40:48 I wanted to define a legitimately difficult subset and then work my way out of it 20:41:00 if you can modify the instructions to use registers then it's pretty much trivial 20:41:11 Well, if you have jumps and addition 20:41:14 That's a good start 20:41:24 Do you know µ-recursive functions? 20:41:28 yes 20:41:35 That's probably the easiest parallel 20:41:42 yeah 20:41:49 i wrote a compiler from brainfuck 20:41:54 but that's probably not the easiest way 20:42:06 i just like it because it's a pretty normal programming language, not too esoteric 20:42:22 and yet we can compile it into this nonsense 20:42:27 Well 20:42:34 ADD does change flags :o 20:42:40 that's ok 20:42:52 i'm fine writing to registers if we never depend on their contents 20:43:07 Just remove the registers by hand 20:43:26 i have a program which uses ptrace() to zero out all the registers after every instruction 20:43:45 anyway I'll send you the link when it's done ;P 20:43:56 lunchtime -> 20:44:18 kmc: are you allowed to use rip-relative addressing 20:45:08 probably but i don't think it's useful so i didn't make up my mind about it 20:45:45 Wait 20:45:45 Are you allowed to use the stack? 20:47:58 -!- Sprocklem has quit (Ping timeout: 246 seconds). 20:49:44 Not the stack pointer register, presumably. 20:50:39 kmc: this reminds me of Malbolge, but easier 20:51:37 I think if you can use the stack 20:51:47 It's probably trivial 20:52:30 You can use INC and DEC, create function calls and do a loop for a µ-functions 20:52:41 You can do µ recursive functions, which are TC 20:54:43 -!- AnotherTest has quit (Ping timeout: 265 seconds). 20:55:23 -!- Frooxius has quit (Quit: *bubbles away*). 20:57:18 -!- Oj742 has joined. 20:58:03 From what I recall about the rules, I think the stack wasn't allowed. 20:58:23 -!- muskrat has quit (Read error: Connection reset by peer). 20:59:09 I used the stack a lot when writing ASCII-only programs 20:59:31 -!- muskrat has joined. 21:00:15 Well you can probably still do function calls without the stack 21:00:20 It's just gonna be a bit more tricky 21:04:17 no you can't use the stack because those instructions depend on the value of sp 21:04:31 You can always use a manual stack, of course. (E.g. just keep the stack pointer in the immediate operand of a "mov dword ptr [foo], 1234; jmp [bar]", and when you want to write the stack pointer somewhere -- probably to some register -- self-modify the foo displacement to point at where you want, and the bar to next instruction, and jump to that snippet.) 21:04:48 Er, "register" should've been "operand". 21:05:04 I think this should be doable without self-modifying code 21:05:08 Yeah 21:05:17 let me know if you figure out a way :) 21:05:19 Just µ recursive functions should be doable pretty easily 21:05:35 Hell even a compiler of it 21:05:35 you could do something like MiniMAX, I guess 21:05:51 i ended up needing only one level of non-tail calls so I didn't have to implement a stack, just a single place to store a return address 21:05:53 except the difficulty you have doing addition 21:05:57 because one of the arguments has to be a constant 21:10:12 If you wan't "unbounded" (up to the address space size, anyway) memory, I don't see how you can do it without self-modifying the operands, since otherwise you can only touch memory mentioned in the "source". 21:11:14 Hm, true 21:11:35 And if you try functions you need to store the arguments somewhere 21:12:17 you can just store those in memory right 21:13:16 Yeah, but how can you access it 21:13:37 If you only use numbers, you won't be able to use arbitrarily large numbers of recursions and function calls 21:14:43 Clearly the next Intel instruction set rehash should add a double-indirect addressing mode. 21:15:25 "If the 6502 could do it..." 21:15:39 Like [[butts]]? 21:15:52 That seems like a reasonable syntax for it. 21:16:01 Especially the butt part 21:16:05 -!- yiyus has joined. 21:18:33 fizzie: you can touch unmentioned memory via indirects, can't you? 21:19:01 ais523: What indirects? 21:19:07 oh, I see 21:19:12 you can store values in unmentioned memory 21:19:24 but you can't read them, except to store a different value back in the same memory 21:19:24 ais523: I don't see how you can do that either. 21:19:37 mov [123], 456 21:19:42 ais523: Stores to address 123. 21:19:48 oh right 21:19:56 I'm getting my syntaxes muddled 21:20:09 even with double indirects I don't see how you can usefully read distant memory 21:20:31 Well, small steps. 21:20:32 and being TC without the ability to read (only write and add constants) seems dubious, if not completely impossible 21:20:37 You can just use some memory as a data pointer? 21:20:51 Slereah_: apparently I was mistaken 21:21:04 so yes, you'd need self-modifying code to make this work 21:21:32 Wait, don't you need the instruction pointer for that? 21:21:36 -!- sebbu2 has joined. 21:21:36 -!- sebbu2 has quit (Changing host). 21:21:36 -!- sebbu2 has joined. 21:21:46 Well I guess you can know the exact position of your code 21:21:47 Slereah_: you can write to absolute addresses 21:22:20 can you do introspection in assembly? 21:22:24 the idea of "double indirects, no self-modifying" has me thinking, though 21:22:32 actually it's easy, if you can JMP to a double indirect 21:22:41 Can you do double indirects? 21:22:44 Slereah_: no 21:22:49 this is a different esolang I'm thinking of now 21:22:49 Hm 21:22:54 oh 21:22:59 hmm… can it be done with computed or conditional jumps? 21:23:05 -!- sebbu has quit (Ping timeout: 240 seconds). 21:23:09 err, no computed or conditional jumps 21:23:17 just running the same commands over and over again, forever 21:23:33 I guess you can simulate double indirect using a self modifying code 21:23:45 Just do some mov [address], value 21:23:52 And modify the code to change the address 21:24:14 yes 21:24:23 Then implement a stack or whatnot 21:24:48 ais523: You can do the usual sort of "conditional" jump by having an indirect "jmp [0]" and then doing a double-indirect "mov [[foo]], newcode" -- that'll make a conditional jump to newcode if the value at foo is 0. 21:24:49 anyway reads are the hard part, I think 21:25:02 fizzie: right 21:25:35 I guess that kind of thing could be used to "read" a bounded value. 21:25:37 kmc: not really; use only 0 and (insert small constant here, something around 12 or 16) for your data 21:25:52 then to read, add, indirect jump, get the destination to subtract again 21:26:44 Ah, I suppose you don't even need the double-indirect for that approach. 21:26:57 yep 21:27:03 this is basically how MiniMAX works 21:27:15 except that MiniMAX uses a VM (that has an 8-byte implementation) 21:27:39 yeah that's like what i did ais523 21:27:46 i still consider that the hard part, compared to writes 21:27:52 fair enough 21:28:07 Now try to write an OS without registers 21:29:37 Regarding hardware access, can't write to I/O ports (not that they're probably all that important these days?) without registers. 21:29:51 Yeah 21:29:57 Them ports sure love the accumulator 21:30:27 -!- boily has quit (Quit: ACCUMULATING CHICKEN!). 21:30:29 -!- metasepia has quit (Remote host closed the connection). 21:31:13 Hm 21:31:22 Can't think of any way to access any hardware, yeah 21:32:04 You could access memory-mapped hardware just fine. Well, for some values of "fine". (If you start from real mode, I don't think you can get to any sort of usable protected mode without loading segment registers.) 21:32:39 Even the interrupts needs the accumulatore 21:33:05 I guess you'll just have to use your imagination for the GUI 21:33:33 -!- impomatic has quit (Ping timeout: 252 seconds). 21:35:54 -!- impomatic has joined. 21:38:05 fizzie: did you know that that "return 0;" gets compiled to "mov $-1, %rax" 21:38:07 (so i'm told) 21:38:27 Is $ for a literal value? 21:38:38 in AT&T assembler syntax yeah 21:38:47 Weird 21:38:51 and the operand order is reversed from intel 21:38:57 Maybe it's a signed zero 21:39:04 nah 21:39:07 I dunno 21:39:18 there's no negative zero in two's compliment integer arithmetic 21:39:24 I know 21:39:28 It's a bit disappointing 21:39:37 You could do -0 and +0 21:39:45 And their divisions would give +- infinity 21:39:55 there's no infinity in integer arithmetic, either 21:39:57 I think floating points has signed infinities 21:40:00 yes 21:40:34 +Infinity represents an unknown positive value which is too large to represent 21:41:08 and NaN represents a value about which nothing is known 21:41:17 which is why NaN ≠ NaN i guess 21:41:17 yeah 21:41:33 kmc, fungot: you're both cute imo 21:41:33 shachaf: they only need to remove the adverts, come to think of a regex as a string that the host language without using call/ cc 21:41:36 "two's compliment" 21:41:43 :) 21:41:46 thanks shachaf 21:41:47 but fungot produces better ebooks 21:41:47 shachaf: totally hilarious. 21:42:37 fungot's ebooks are extremely hilarious 21:42:37 mrhmouse: use the fink package? 21:45:22 -!- muskrat has quit (Read error: Connection reset by peer). 21:45:49 -!- muskrat has joined. 21:45:59 -!- Oj742 has quit (Ping timeout: 272 seconds). 21:52:09 Wait, can you do a conditional jump without registers? 21:52:28 The µ function idea I had kinda hinged on that 21:53:04 Ah yes, we discussed it earlier 21:53:09 So yeah, probably TC 21:55:56 -!- muskrat has quit (Quit: Leaving). 22:00:23 ion: i'm surprised you haven't been through the who-sent-you cslounge dance yet 22:00:30 i guess you're too quiet 22:02:04 heh 22:03:59 so maybe i'll fly to san jose in december 22:04:01 who knows 22:04:16 shachaf: Are you *sure* that is a return 0;? 22:05:13 maybe you're not using the return value and the compiler decided to pre-load some constant into rax? 22:05:43 I didn't try it but I believe the person who did try it because returning 0 wouldn't make sense. 22:06:43 why? 22:14:02 Because in the g++ implementation 0 is (/could be) a pointer to the first member. 22:16:44 for int foo() { return 0; }? 22:17:38 No, for the code discussed above. 22:17:56 "did you know that that" 22:18:20 int T::*foo() { return 0; } 22:19:14 oh, you're saying that a NULL function pointer is not represented by the integral value 0? 22:19:20 NULL member pointer, I mean 22:19:23 interesting 22:19:52 I think it's implementation dependant 22:19:58 right I meant in this implementation 22:20:29 shachaf: Oh 22:20:33 Then I'm not surprised at all 22:21:12 shachaf: Huh, so it does. 22:21:35 http://sprunge.us/YChV 22:22:08 fizzie: g++ -O2 -S -o/dev/stdout tmp.cc 22:22:17 Member pointer representations are a terribly complicated thing, anyway. 22:23:18 Or at least pointers to member functions. 22:23:29 http://www.codeproject.com/Articles/7150/Member-Function-Pointers-and-the-Fastest-Possible "Implementations of Member Function Pointers" has a nice table. 22:26:00 shachaf: "-o -" hth 22:26:55 -!- typeclassy has joined. 22:27:28 fizzie: https://codereview.appspot.com/22170044/ hth 22:28:37 -!- mrhmouse has quit (Read error: Connection reset by peer). 22:28:46 What's "govet"? 22:29:17 Probably http://godoc.org/code.google.com/p/go.tools/cmd/vet 22:29:18 (Except a non-stationary veterinarian.) 22:29:35 Anyway I meant the collapsed messages earlier in the thread. 22:30:15 Well it's about stdin anyway! Nothing to do with using - for stdout. 22:30:59 `run echo hi > - 22:31:03 No output. 22:32:30 Also - is the convention "too bad" "so sad" 22:33:37 "wow" 22:35:04 (Also, I didn't know "null member pointer value" even existed, v. fancy.) 22:40:25 [[ A prvalue of type "pointer to member of B of type cv T", where B is a class type, can be converted to a prvalue of type "pointer to member of D of type cv T", where D is a derived class (Clause 10) of B. If B is an inaccessible (Clause 11), ambiguous (10.2), or virtual (10.1) base class of D, or a base class of a virtual base class of D, a program that necessitates this conversion is ... 22:40:31 ... ill-formed. The result of the conversion refers to the same member as the pointer to member before the conversion took place, but it refers to the base class member as if it were a member of the derived class. The result refers to the member in D's instance of B. Since the result has type "pointer to member of D of type cv T", it can be dereferenced with a D object. The result is the same ... 22:40:37 ... as if the pointer to member of B were dereferenced with the B subobject of D." 22:40:40 Well, that's good to know. 22:47:50 -!- augur has joined. 22:56:47 -!- sebbu2 has changed nick to sebbu. 22:57:00 -!- nooodl has quit (Ping timeout: 265 seconds). 23:08:01 what's a TIL except I didn't learn it today, rather a few days ago? 23:08:26 well, AFDAIL that BNF was invented for the original Algol 60 spec 23:08:26 kmc says "shachaf: did you know [...]" 23:08:32 which lists Backus and Naur as authors 23:13:04 -!- oerjan has joined. 23:26:47 hackego has it? <-- the prefixes command is in all of fungot, HackEgo and EgoBot, which are the bots i know how to update a command in. 23:26:47 oerjan: are you serious? what else is there to call/ cc 23:27:47 * oerjan swats everyone for being idle -----### 23:28:07 @tell quintopia hackego has it? <-- the prefixes command is in all of fungot, HackEgo and EgoBot, which are the bots i know how to update a command in. 23:28:07 Consider it noted. 23:28:08 oerjan: plus i got some really nice fnord. but if you told me, i hate google doing that. 23:31:07 to anyone good at hackego: the bienvenido message drops a "t" at the end <-- oops 23:31:13 `bienvenido 23:31:15 `^! prefixes 23:31:16 ​¡Bienvenido al centro internacional para el diseño y despliegue de lenguajes de programación esotéricos! Por desgracia, la mayoría de nosotros no hablamos español. Para obtener más información, echa un vistazo a nuestro wiki: http://esolangs.org/wiki/Main_Page. (Para el otro tipo de esoterismo, prueba #esoteric en irc.dal.net.) 23:31:17 ​/home/hackbot/hackbot.hg/multibot_cmds/lib/limits: line 5: exec: ^!: not found 23:31:57 i think it's simply over HackEgo's limit with a nick, because of the "Most people here don't speak Spanish" addition. 23:32:34 has that variant ever been used in anger? 23:33:29 ais523: i use it when someone shows up who says "hola" as their first message :P 23:33:44 which happens surprisingly often. 23:33:49 have they been Spanish speakers? or just people who hola'd out of the blue? 23:34:15 ais523: mostly Spanish speakers, although the last time i did it wasn't. 23:34:26 (also it's not always literally "hola") 23:35:12 `안녕하세요 23:35:13 ​/home/hackbot/hackbot.hg/multibot_cmds/lib/limits: line 5: exec: 안녕하세요: not found 23:35:14 we have the theory it happens because #esoteric starts with es. although i don't think that has ever really been confirmed. 23:35:42 apparently `bienvenido cuts off it the nick is longer than 12 chars. 23:35:49 *if 23:36:03 which happened earlier today, but isn't common. 23:36:19 oh wait 23:36:44 it dropped "t.)", and the nick was 14, so longer than 11. 23:37:10 isn't 14 the absolute limit? 23:37:32 `welcome fourteenletter 23:37:34 fourteenletter: Welcome to the international hub for esoteric programming language design and deployment! For more information, check out our wiki: . (For the other kind of esoterica, try #esoteric on irc.dal.net.) 23:37:43 `bienvenido fourteenletter 23:37:45 fourteenletter: ¡Bienvenido al centro internacional para el diseño y despliegue de lenguajes de programación esotéricos! Por desgracia, la mayoría de nosotros no hablamos español. Para obtener más información, echa un vistazo a nuestro wiki: http://esolangs.org/wiki/Main_Page. (Para el otro tipo de esoterismo, prueba #esoteric en irc.dal.ne 23:37:54 seems pretty conclusive 23:38:04 `nick fifteenletter12 23:38:05 ​/home/hackbot/hackbot.hg/multibot_cmds/lib/limits: line 5: exec: nick: not found 23:38:07 oops 23:38:10 -!- oerjan has changed nick to fifteenletter12. 23:38:12 (I use "twelveletter" as a test name when I'm trying to test if there's room in the status area) 23:38:13 -!- fifteenletter12 has changed nick to fifteenletter123. 23:38:24 ok 16 is the limit 23:38:26 fifteenletter123: bu that's 16 letters 23:38:29 -!- fifteenletter123 has changed nick to oerjan. 23:38:30 you should be sixteenletter123 23:38:37 I KNOW 23:38:50 actually, it's only 13 letters 23:38:57 it's 16 /characters/ but "123" are not letters 23:38:58 in any case there's a simple fix. 23:39:30 `run sed -i 's!wiki/Main_Page!!' wisdom/bienvenido 23:39:31 sed: can't read wisdom/bienvenido: No such file or directory 23:39:36 wat 23:39:37 oh 23:39:37 oerjan: hmm, all the fixes I thought of were massively complicated 23:39:43 but then I was trying to fix something else 23:39:44 `run sed -i 's!wiki/Main_Page!!' wisdom/welcome.es 23:39:48 No output. 23:39:54 `? wisdom.es 23:39:56 wisdom.es? ¯\(°​_o)/¯ 23:40:02 eep 23:40:12 er 23:40:15 `cat bin/bienvenido 23:40:16 *cough* 23:40:16 ​#!/usr/bin/perl -w \ if (defined($_=shift)) { s/ *$//; s/ +/ @ /g; exec "bin/@", $_ . " ? welcome.es"; } else { exec "bin/?", "welcome.es"; } 23:40:24 aha 23:40:26 `? welcome.es 23:40:28 ​¡Bienvenido al centro internacional para el diseño y despliegue de lenguajes de programación esotéricos! Por desgracia, la mayoría de nosotros no hablamos español. Para obtener más información, echa un vistazo a nuestro wiki: http://esolangs.org/. (Para el otro tipo de esoterismo, prueba #esoteric en irc.dal.net.) 23:40:34 -!- ais523 has quit. 23:40:37 `bienvenido sixteenletters12 23:40:39 sixteenletters12: ¡Bienvenido al centro internacional para el diseño y despliegue de lenguajes de programación esotéricos! Por desgracia, la mayoría de nosotros no hablamos español. Para obtener más información, echa un vistazo a nuestro wiki: http://esolangs.org/. (Para el otro tipo de esoterismo, prueba #esoteric en irc.dal.net.) 23:45:02 ? 23:45:15 lambdabot: > [1..] 23:45:23 huh 23:45:29 lambdabot: @run [1..] 23:45:30 [1,2,3,4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28... 23:45:34 ic 23:46:19 (just testing if the lambdabot: ? spam is only for lambdabot: ? or something more general. seems it isn't.) 23:48:31 @tic-tac-toe 23:48:31 how about a nice game of chess? 23:48:33 @tic-tac-toe 23:48:34 how about a nice game of chess? 23:49:32 @poll-result remove@src 23:49:32 Poll results for remove@src (Closed): no=1, yes=1 23:50:19 -!- typeclassy has quit (Ping timeout: 252 seconds). 23:51:31 @poll-list 23:51:31 ["(++)","ConfusedWithVixenSituation","FlavaOfJRuby","Prelude-(.)?","best-programming-language","best-spoken-language","food","funniest-thing-in-the-whole-world","naming","nethack","president","prove->","remove@src","sleep"] 23:51:35 @poll-result (++) 23:51:35 Poll results for (++) (Open): (++)::Semigroup_m=>m->m->m=1, (++)::Monoid_m=>m->m->m=2, (++)::[a]->[a]->[a]=2 23:51:50 @poll-result best-programming-language 23:51:50 Poll results for best-programming-language (Open): COBOL=2, PHP=1, Coq=0, Agda=0, anything-else=0, Haskell=0 23:52:02 @poll-result naming 23:52:02 Poll results for naming (Closed): Lovelace=1, Babbage=0 23:52:14 @poll-result sleep 23:52:14 Poll results for sleep (Open): no=1, yes=7 23:52:17 -!- typeclassy has joined. 23:52:21 hmm, p. sure i made that last one 23:52:26 @poll-result prove-> 23:52:26 Poll results for prove-> (Open): proven=1, proved=0 23:52:28 well did you sleep 23:52:32 eventually 23:52:42 @poll-result president 23:52:42 Poll results for president (Open): cthulhu=3, kmc=1, copumpkin=5 23:53:06 @poll-result food 23:53:06 Poll results for food (Open): quesadilla=2, meatball-sub=2 23:53:37 man, tough choice. 23:53:46 @help poll-add 23:53:47 poll-add Adds a new poll, with no candidates 23:53:53 @list poll 23:53:53 poll provides: poll-list poll-show poll-add choice-add vote poll-result poll-close poll-remove 23:54:01 @help choice-add 23:54:01 choice-add Adds a new choice to the given poll 23:54:11 @choice-add food lutefisk 23:54:11 New candidate "lutefisk", added to poll "food". 23:54:23 @vote food lutefisk 23:54:23 voted on "lutefisk" 23:54:43 @choice-add best-programming-language SNOBOL 23:54:43 New candidate "SNOBOL", added to poll "best-programming-language". 23:54:49 @vote best-programming-language SNOBOL 23:54:49 voted on "SNOBOL" 23:55:32 copumpkin for president 23:56:01 @poll-result best-spoken-language 23:56:01 Poll results for best-spoken-language (Open): magyar=3, Polish=484, Welsh=1, Georgian=2, Manx=1, norwegian=8 23:56:24 @vote best-spoken-language Georgian 23:56:24 voted on "Georgian" 23:56:31 Mgrvgrvladje! 23:57:33 -!- Phantom_Hoover has joined. 23:57:50 -!- sebbu has quit (Ping timeout: 240 seconds). 23:59:50 @poll-add olist 23:59:50 Added new poll: "olist" 2013-11-27: 00:00:05 @choice-add olist 00:00:05 usage: @choice-add 00:00:07 @choice-add olist update 00:00:07 New candidate "update", added to poll "olist". 00:01:32 @@ @@ (@run text . concat . run (replicate 20 "(@vote olist update) ")) 00:01:33 Not in scope: `run' 00:01:33 Perhaps you meant `fun' (imported from Debug.SimpleRef... 00:01:43 @@ @@ (@run text . concat $ (replicate 20 "(@vote olist update) ")) 00:01:44 Plugin `compose' failed with: Missing ')' in nested command 00:01:49 @@ (@run text . concat $ (replicate 20 "(@vote olist update) ")) 00:01:50 (@vote olist update) (@vote olist update) (@vote olist update) (@vote olist... 00:02:01 @@ (@read @run text . concat $ (replicate 20 "(@vote olist update) ")) 00:02:02 Plugin `compose' failed with: Unknown command: "read" 00:02:17 @@ @@ (@run text . concat $ (replicate 3 "(@vote olist update) ")) 00:02:17 voted on "update" voted on "update" voted on "update" 00:02:21 @@ @@ (@run text . concat $ (replicate 4 "(@vote olist update) ")) 00:02:22 Plugin `compose' failed with: Missing ')' in nested command 00:02:23 :'( 00:02:46 @@ @@ (@run concat $ (replicate 20 "(@vote olist update) ")) 00:02:47 "(@vote olist update) (@vote olist update) (@vote olist update) (@vote olis... 00:03:02 help 00:03:14 i think it's @run which has such a low output limit? 00:03:18 Yes. 00:03:21 This used to work, though. 00:03:28 That's why Polish is so popular. 00:03:32 I don't remember how I did it. 00:03:37 I might've used @read, which is gone now? 00:03:51 @help @read 00:03:51 help . Ask for help for . Try 'list' for all commands 00:03:54 @list read 00:03:54 No module "read" loaded 00:04:05 @@ @@ (@run text . concat $ (replicate 20 "(@vote olist update) ")) 00:04:06 Plugin `compose' failed with: Missing ')' in nested command 00:05:36 ^ul (@@ )(@vote olist update)a::::::*******S 00:05:36 @@ (@vote olist update)(@vote olist update)(@vote olist update)(@vote olist update)(@vote olist update)(@vote olist update)(@vote olist update) 00:05:36 voted on "update"voted on "update"voted on "update"voted on "update"voted on "update"voted on "update"voted on "update" 00:05:55 Well, yes, but that doesn't let you get really high. 00:05:59 (kmc can confirm) 00:06:05 @karma blah 00:06:05 blah has a karma of 31337 00:06:16 ion's work?? 00:06:27 @help show 00:06:27 show . Print "" 00:06:32 @list show 00:06:32 dummy provides: eval choose dummy bug id show wiki paste docs learn haskellers botsnack get-shapr shootout faq googleit hackage thanks thx thank you ping tic-tac-toe 00:06:41 @help haskellers 00:06:42 haskellers. Find other Haskell users 00:06:46 @haskellers 00:06:46 http://www.haskellers.com/ 00:06:53 great. 00:08:04 @thank you 00:08:04 Maybe you meant: thank you thanks 00:08:06 i wonder if the @run cut-down is related to int-e's fixes the other day, he was looking at how that worked. 00:08:10 :'( 00:08:18 int-e: did you break lambdabot 00:09:05 @run [1..] 00:09:06 [1,2,3,4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28... 00:09:47 hm... 00:09:50 > [1,1..1] 00:09:51 [1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,... 00:14:06 @poll-results olist 00:14:06 Poll results for olist (Open): update=932 00:14:13 * oerjan whistles innocently 00:14:29 The trouble is that you can't unvote. 00:14:34 that it is. 00:14:40 And you can't remove options. 00:15:04 oh hm 00:15:08 @karma olist 00:15:08 olist has a karma of 0 00:15:12 But this does give me the idea to give `olist an incrementing counter. 00:15:20 the obvious solution ^ 00:15:28 Well, @karma won't let you add a list of nicks. 00:15:36 hm right 00:16:05 @where+ olist olist ((@karma olist)): shachaf oerjan 00:16:05 Good to know. 00:16:07 @@ @where olist 00:16:08 olist ((@karma olist)): shachaf oerjan 00:16:15 @@ @@ @where olist 00:16:15 olist (olist has a karma of 0): shachaf oerjan 00:16:32 @show blah 00:16:33 "blah" 00:17:06 :t isNumber 00:17:07 Char -> Bool 00:17:31 @where+ olist olist ((@run text $ dropWhile (not isNumber) @show @karma olist)): shachaf oerjan 00:17:31 It is stored. 00:17:34 @@ @@ @where olist 00:17:35 olist ( Couldn't match expected type `GHC.Types.Char -> GHC.Types.Bool' 00:17:35 ...): shachaf oerjan 00:17:49 * shachaf sighs. 00:17:56 @@ @run @show @karma olist 00:17:57 "olist has a karma of 0" 00:18:05 Er. 00:18:09 @where+ olist olist ((@run text $ dropWhile (not . isNumber) @show @karma olist)): shachaf oerjan 00:18:09 It is forever etched in my memory. 00:18:12 @@ @@ @where olist 00:18:13 olist ( 0 00:18:13 ): shachaf oerjan 00:18:24 OK, well, you get the idea. 00:18:45 FANCY 00:18:56 @where+ olist olist ((@run text . filter isNumber $ @show @karma olist)): shachaf oerjan 00:18:56 I will never forget. 00:18:59 @@ @@ @where olist 00:19:00 olist ( 0 00:19:00 ): shachaf oerjan 00:19:05 What's with the newlines? 00:19:11 -!- Oj742 has joined. 00:19:14 what in sam hill is going on here 00:19:41 @where+ olist olist ((@run text . filter isNumber $ "")): shachaf oerjan 00:19:41 It is forever etched in my memory. 00:19:44 @@ @@ @where olist 00:19:45 olist ( Terminated 00:19:45 ): shachaf oerjan 00:19:49 @@ @show @karma olist 00:19:50 "olist has a karma of 0" 00:19:53 why am i @where+ing each time 00:20:15 @@ olist ((@run text . filter isNumber $ @show @karma olist)): shachaf oerjan 00:20:16 olist ( 0 00:20:16 ): shachaf oerjan 00:20:22 @@ olist ((@run text . filter isNumber $ @show @karma olist)): [...] 00:20:23 olist ( 0 00:20:23 ): [...] 00:20:30 @@ olist ((@run text "")): [...] 00:20:31 olist ( Terminated 00:20:31 ): [...] 00:20:41 i blame int-e 00:20:43 > text "" 00:20:44 Terminated 00:21:00 @@ @show @run () 00:21:01 " ()\n" 00:21:21 :'( 00:21:43 "sry 4 highlighting you" 00:22:53 @tell int-e your new @run is hard to compose with @@ because of the newline 00:22:54 Consider it noted. 00:23:07 @tell int-e and the spaces 00:23:07 Consider it noted. 00:23:09 -!- Phantom__Hoover has joined. 00:23:57 -!- Phantom_Hoover has quit (Ping timeout: 252 seconds). 00:24:26 > 1 00:24:26 1 00:25:29 i think he was trying to simplify the space handling. 00:25:46 > var $ "1\n2\n3" 00:25:47 1 00:25:47 2 00:25:47 3 00:26:08 hm it's the same as it used to be there 00:26:22 oerjan: p. sure it takes a rocket scientist to do that 00:26:29 (space joke) 00:27:08 i hear the new gravity movie has a joke about "it's not rocket science" 00:27:23 the joke is that it's about how to use a rocket 00:29:39 -!- typeclassy has quit (Ping timeout: 272 seconds). 00:29:51 -!- nisstyre has quit (Ping timeout: 240 seconds). 00:33:11 -!- Oj742 has quit (Ping timeout: 272 seconds). 00:33:15 -!- Phantom_Hoover has joined. 00:34:10 -!- Phantom__Hoover has quit (Ping timeout: 245 seconds). 00:36:18 -!- Bike_ has joined. 00:36:53 -!- Bike has quit (Ping timeout: 252 seconds). 00:37:25 -!- typeclassy has joined. 00:39:03 -!- Bike_ has changed nick to Bike. 00:42:25 -!- Sgeo has joined. 00:44:45 -!- nisstyre has joined. 00:47:31 -!- Phantom__Hoover has joined. 00:47:50 -!- yiyus has quit (Read error: Connection reset by peer). 00:48:23 -!- Phantom_Hoover has quit (Ping timeout: 272 seconds). 00:52:16 -!- carado has quit (Ping timeout: 245 seconds). 00:53:12 -!- oklopol has joined. 00:53:32 @tell ais523 and I'm not sure it's a second declension male word in the first place <-- fourth, according to wiktionary, so plural is also status 00:53:32 Consider it noted. 00:54:04 evening 00:54:18 i've been internetless for the last week o_O 00:54:29 shocking 00:54:29 get some reading done then 00:54:31 -!- sebbu has joined. 00:54:46 what should i read 00:55:09 -!- sebbu has quit (Changing host). 00:55:09 -!- sebbu has joined. 00:56:58 and for words like hawaius <-- in hawaiian the name's Hawaiʻi 00:57:12 i think it's a glottal stop 00:57:19 Aaaaaaaaaah 00:57:29 The murder mystery series my dad's cousin was in HAS AIRED IN THE UK 00:58:00 Taneb: does this mean you're forever shamed by your family 00:58:23 I don't think so 00:58:28 I'm a little annoyed nobody told me 00:59:03 it's a mystery 01:00:56 Taneb: who did he murder 01:01:27 oklopol, I don't know I haven't watched it yet 01:01:40 I think she's playing a recurring character so maybe lots of people 01:01:54 oh i thought this was some reality show 01:02:21 (seriously, although i didn't think your cousin was the murderer) 01:13:17 -!- Phantom__Hoover has quit (Read error: Connection reset by peer). 01:47:29 -!- Sprocklem has joined. 01:52:30 -!- typeclassy has quit (Ping timeout: 252 seconds). 02:05:25 -!- Sprocklem has quit (Ping timeout: 248 seconds). 02:05:52 -!- Sprocklem has joined. 02:17:52 thoerjan 02:20:18 ywintopia 02:21:20 https://www.linkedin.com/jobs2/view/9887522 02:23:13 is this the awful thing everyone is talking about 02:23:14 yes 02:24:11 https://twitter.com/search?q=%23pennyarcadejobpostings&src=typd&f=realtime ? 02:24:12 isn't it awful 02:24:30 kmc is clearly not a bad enough dude 02:24:56 some of the responses are pretty great (in a terribly cathartic way, at least) 02:25:15 "A bunch of 25 year-old kids with a ton of talent and stars in their eyes are going to try to get this crap job for crap pay" see this is where I feel pleased with myself about being 25 years old and already cynical enough to see through this shit 02:25:20 this is a great ad 02:25:36 oh man it just keeps going 02:26:23 "a creative and potentially offensive environment" 02:26:24 kmc: p. sure that doesn't say "25-year-old" 02:28:06 haha 02:28:45 maybe like, nerds will finally discover penny arcade are actually horrible people? or like they'll all apply anyways <.< 02:30:43 kmc: do you think of yourself as v. cynical 02:30:47 you don't seem that way to me most of the time 02:31:10 PA is like the ultimate example of nerds acting like underdog rebels even after they come to control everything 02:32:10 it helps that the comic has been pretty shitty for the last few years so I don't lose much by trying to ignore them 02:32:22 it was fucking hilarious for a long time, though 02:33:02 shachaf: I do, generally 02:33:15 I see myself as relatively idealistic 02:33:17 but I know that I'm pretty unfair in my judgements about myself 02:33:20 It's a nice life 02:33:41 keep in mind that kmc's favourite comic strip is jerkcity 02:34:08 no, it has to be Achewood 02:34:13 but Jerkcity is pretty good too 02:38:07 -!- yorick has quit (Remote host closed the connection). 02:50:32 shachaf: I guess I am cynical about most things but really positive and idealistic about a few and that keeps me going 02:52:41 -!- oklopol has quit (Remote host closed the connection). 02:57:53 -!- Taneb has quit (Quit: Leaving). 02:59:51 I wonder when Trident will go the way of MSIE 03:03:18 -!- oerjan has quit (Quit: Z?). 03:31:37 -!- Slereah_ has quit (Read error: Connection reset by peer). 03:31:46 -!- Slereah has joined. 03:32:06 what is the opposite of "cynical" 03:32:20 "romantic"? 03:32:43 "optimistic", usually 03:33:13 -!- typeclassy has joined. 03:34:33 -!- Oj742 has joined. 03:40:35 -!- typeclassy has quit (Ping timeout: 252 seconds). 03:47:17 I can't be president :( 03:47:40 what, of anything? 03:48:00 but can you be copresident 03:49:40 -!- KingOfKarlsruhe has quit (Ping timeout: 264 seconds). 03:57:32 copumpkin can be president of my heart ♥ 04:03:56 -!- Bike_ has joined. 04:04:19 shachaf can be president of my fart ♥ 04:05:57 -!- Bike has quit (Ping timeout: 240 seconds). 04:20:52 -!- typeclassy has joined. 04:28:09 -!- typeclassy has quit (Ping timeout: 272 seconds). 04:31:13 http://research.microsoft.com/en-us/um/people/hoppe/proj/videoloops/ 04:47:41 -!- Sprocklem has quit (Ping timeout: 252 seconds). 05:11:29 higher order, higher rank, higher kinded polymorphism #drugz 05:12:42 shachaf: "idealistic" 05:13:17 -!- Bike_ has changed nick to Bike. 05:13:43 ion: i think i watched a presentation about that for some conference once... 05:13:58 probably SIGGRAPH 05:14:01 linked on their site 05:20:05 -!- tertu has quit (Ping timeout: 248 seconds). 05:31:30 -!- tertu has joined. 06:14:02 -!- tertu has quit (Ping timeout: 264 seconds). 06:24:12 -!- Oj742 has quit (Ping timeout: 246 seconds). 06:29:04 -!- tertu has joined. 06:50:19 -!- glogbackup has joined. 07:21:06 -!- L8D has joined. 07:21:36 Would you guys consider a simplified form of FORTH to be an esoteric language? 07:22:31 -!- tertu has quit (Ping timeout: 246 seconds). 07:22:33 simplified how? have you seen underload? 07:23:21 -!- tertu has joined. 07:23:38 simplified as in, not a full implementation, but enough to be turing complete and usable for embedded machines 07:24:24 i wouldn't really consider that esoteric just because somebody probably already made it for such a machine. 07:24:37 I broke down the semantics of the language so that everything could be bootstrapped with no 'special' operators or keywords 07:25:25 -1 ? " true " : " false " ; type 07:25:45 and the if conditional looks like a ternary expression 07:26:06 well, it is. 07:26:47 A language is esoteric iff it has an esolangs.org wiki page. 07:26:55 lol 07:27:09 what's ; 07:27:52 shachaf: You just done proved that Perl really is an esoteric language. (Not that there was any doubt.) 07:27:55 are you asking what the esoteric language named 'semi-colon' is, or are you asking about the code? 07:30:03 theh code. 07:30:05 the first instruction in the code is the '-1', which just adds a -1(the standard value for a true boolean), then the '?' is the instruction for a conditional expression which will run the code between the '?' and the ':' if the item popped from the stack is true, and will run the code between the ':' and the ';' if the popped item is false 07:30:31 Then what's "type"? 07:30:34 the ';' really just marks the end of the if statement 07:30:35 is ; the comment character 07:30:39 oh 07:31:22 'type' is an intrstuction to pop an item off the stack as a pointer and print it as a string 07:31:32 oh, i see. 07:31:36 odd name 07:31:57 Odd but popular. 07:32:02 What's -"1 type" do, out of curiosity 07:32:10 "-1 type"* 07:32:13 TYPE CON 07:32:43 Bike: p. sure hott has a meaning for -1-type 07:32:49 It will try to use -1 as a char pointer and probably segfault or throw an error depending on whether type checking was enabled 07:32:53 p. sure i don't care. 07:32:59 L8D: makes sense. 07:33:41 http://comonad.com/reader/wp-content/uploads/2011/10/slides.pdf 07:35:10 !forth -1 1 type 07:35:11 ​\ in file included from *OS command line*:-1 \ /tmp/input.20539:1: Invalid memory address \ -1 1 >>>type<<< \ Backtrace: \ $7FCE1EB7CE70 write-file 07:35:31 Plain "-1 type" stack-underflows, of course. 07:35:42 : fib dup 2 < ? : dup 1 - fib 2 - fib + ; ; 07:37:03 !forth -1 IF S" true" ELSE S" false" THEN TYPE 07:37:03 ​\ in file included from *OS command line*:-1 \ /tmp/input.20573:1: Interpreting a compile-only word \ -1 >>>IF<<< S" true" ELSE S" false" THEN TYPE \ Backtrace: \ $7FC39808AB30 throw 07:37:10 -.- 07:37:42 !forth : true s" true " ; : false s" false" ; -1 IF true ELSE false THEN TYPE 07:37:42 redefined true redefined false \ in file included from *OS command line*:-1 \ /tmp/input.20617:1: Interpreting a compile-only word \ : true s" true " ; : false s" false" ; -1 >>>IF<<< true ELSE false THEN TYPE \ Backtrace: \ $7F25C6EC4B30 throw 07:37:49 -.- 07:38:00 this is why I created the simplified form 07:38:11 !forth -1 [IF] S" true" [ELSE] S" false" [THEN] TYPE \ so immediate 07:38:12 true 07:41:33 !forth -1 if s" true" else s" false" then type 07:41:34 ​\ in file included from *OS command line*:-1 \ /tmp/input.20897:1: Interpreting a compile-only word \ -1 >>>if<<< s" true" else s" false" then type \ Backtrace: \ $7FF2BEB33B30 throw 07:41:52 !forth -1 [if] s" true" [else] s" false" [then] type 07:41:52 true 07:41:55 Repeating the same thing is not going to make it work. :p 07:42:00 i don't get this. 07:42:17 See some documentation re interpretation and compilation semantics. 07:42:31 !forth : dummy -1 if s" true" else s" false" then type ; dummy 07:42:32 redefined dummy true 07:42:36 Uh... 07:42:47 There's a defined "dummy"? 07:42:59 !forth dummy type 07:42:59 ​\ in file included from *OS command line*:-1 \ /tmp/input.21094:1: Stack underflow \ dummy >>>type<<< \ Backtrace: \ $7F886AB35E70 write-file 07:43:06 !forth dummy 07:43:07 No output. 07:43:13 ...what? 07:43:14 I think dummy is no op. 07:43:16 !forth 4 type 07:43:17 ​\ in file included from *OS command line*:-1 \ /tmp/input.21221:1: Stack underflow \ 4 >>>type<<< \ Backtrace: \ $7F6B3345CE70 write-file 07:43:30 ok, it's clearly been way too long since i 'learned' forth. 07:43:31 !forth ." This is a test" 07:43:32 This is a test 07:43:34 !forth see dummy 07:43:35 ​\ : dummy ; immediate 07:43:42 Apparently. 07:44:36 !forth s" 'type' prints the usual two-cell string" type 07:44:37 ​'type' prints the usual two-cell string 07:45:24 why two cells? 07:45:45 couldn’t you fit a pointer into one? 07:46:09 It's an address-and-length pair. 07:46:19 ahh 07:46:23 !forth s" foo" . . 07:46:23 3 140010104896768 07:46:29 !forth c" foo" . 07:46:30 ​\ in file included from *OS command line*:-1 \ /tmp/input.21579:1: Interpreting a compile-only word \ >>>c"<<< foo" . \ Backtrace: \ $7F9583151B30 throw 07:46:34 Heh. 07:46:53 !forth : bah c" foo" . ; bah 07:46:54 139705325593352 07:47:00 !forth : bah c" foo" count type ; bah 07:47:01 foo 07:47:07 And so on. 07:47:53 !forth : bah c" foo" -1 type ; bah 07:47:54 No output. 07:48:02 !forth : bah c" foo" 1 - type ; bah 07:48:02 ​\ in file included from *OS command line*:-1 \ /tmp/input.21780:1: Stack underflow \ : bah c" foo" 1 - type ; >>>bah<<< \ Backtrace: \ $7F782C04CE70 write-file \ $7F782C09F348 type 07:48:28 !forth : bah c" foo" count 1 - type ; bah 07:48:29 fo 07:48:32 there we go 07:48:52 !forth : bah c" foo" +1 count 1 - type ; bah 07:48:53 ​\ in file included from *OS command line*:-1 \ /tmp/input.21876:1: Undefined word \ : bah c" foo" >>>+1<<< count 1 - type ; bah \ Backtrace: \ $7FD3F0895A68 throw \ $7FD3F08ABC68 no.extensions \ $7FD3F08993A0 compiler-notfound1 07:49:00 !forth : bah c" foo" 1 + count 1 - type ; bah 07:49:01 oo 07:49:05 hehe 07:49:12 !forth : bah c" foo" 1 + count 2 - type ; bah 07:49:12 oo 07:49:17 -.- 07:49:45 what is c""? 07:49:55 It's a counted string. 07:50:31 A pointer to a Pascal-style (length, data) pair, instead of the (pointer-to-data, length) pair on the stack, like s". 07:50:53 huh. 07:51:16 If you do c" foo" 1+ count it's going to interpret the 'f' as the length. 07:51:52 !forth : x c" foo" 1+ count . . ; x 07:51:53 102 139824385598218 07:53:45 -!- L8D has quit (Ping timeout: 245 seconds). 07:55:55 !forth : x c" ab" dup 10 0 do dup c@ . 1+ loop drop 1+ 10 type ; x 07:55:56 2 97 98 32 32 32 32 32 0 78 ab 07:56:18 I guess "type" stops as the 0 there, even though it might not need to. 07:56:44 (Also not sure what's up with those spaces.) 07:57:47 !forth : x c" ab" dup 10 0 do dup c@ . 1+ loop drop 1+ 10 ." <" type ." >" ; x 07:57:47 2 97 98 32 32 32 32 32 0 78 Oh, maybe it's actually EgoBot that stops at the 0. 08:19:42 -!- nisstyre has quit (Ping timeout: 252 seconds). 08:38:32 -!- nisstyre has joined. 08:44:38 -!- tertu has quit (Ping timeout: 264 seconds). 09:09:27 -!- FreeFull has quit. 09:12:38 !forth : C >R 256 15 16 1799 4 13107 2 21845 R> 4 0 DO TUCK OVER AND -ROT INVERT AND ROT / + LOOP ; 12345 C 09:12:41 No output. 09:12:47 !forth : C >R 256 15 16 1799 4 13107 2 21845 R> 4 0 DO TUCK OVER AND -ROT INVERT AND ROT / + LOOP ; 12345 C . 09:12:47 6 09:13:11 !forth 175 C . 09:13:12 ​\ in file included from *OS command line*:-1 \ /tmp/input.24099:1: Undefined word \ 175 >>>C<<< . \ Backtrace: \ $7FAC86EF5A68 throw \ $7FAC86F0BCE0 no.extensions \ $7FAC86EF5D28 interpreter-notfound1 09:15:52 No persistence for you. 09:16:10 :-( 09:16:38 !forth : f 46. do dup 1 .r cr dup rot + loop ; 0 1 f 09:16:39 1 \ 1 \ 2 \ 3 \ 5 \ 8 \ 13 \ 21 \ 34 \ 55 \ 89 \ 144 \ 233 \ 377 \ 610 \ 987 \ 1597 \ 2584 \ 4181 \ 6765 \ 10946 \ 17711 \ 28657 \ 46368 \ 75025 \ 121393 \ 196418 \ 317811 \ 514229 \ 832040 \ 1346269 \ 2178309 \ 3524578 \ 5702887 \ 9227465 \ 14930352 \ 24157817 \ 39088169 \ 63245986 \ 102334155 \ 165580141 \ 267914296 \ 433494437 \ 701408733 \ 1134903170 \ 1836311903 09:17:38 The #forth channel should have this! 09:19:07 What, don't they have an eval-bot? 09:19:17 No :-( 09:19:35 I thought that was kind of a standard feature. The channels I'm on (##c, #perl, #scheme) all do. 09:41:46 what does .r do_ 09:49:49 Prints a number with a given field width. 09:50:06 I think that "1 .r" is pretty close to "." but maybe there's some subtle difference. 09:50:52 !forth : f 46. do dup . cr dup rot + loop ; 0 1 f 09:50:53 1 \ 1 \ 2 \ 3 \ 5 \ 8 \ 13 \ 21 \ 34 \ 55 \ 89 \ 144 \ 233 \ 377 \ 610 \ 987 \ 1597 \ 2584 \ 4181 \ 6765 \ 10946 \ 17711 \ 28657 \ 46368 \ 75025 \ 121393 \ 196418 \ 317811 \ 514229 \ 832040 \ 1346269 \ 2178309 \ 3524578 \ 5702887 \ 9227465 \ 14930352 \ 24157817 \ 39088169 \ 63245986 \ 102334155 \ 165580141 \ 267914296 \ 433494437 \ 701408733 \ 1134903170 \ 1836311903 09:51:03 Ah, right, the automatic space. 09:51:47 !forth : f 46. do dup . dup rot + loop ; 0 1 f \ arguably better, though 09:51:48 1 1 2 3 5 8 13 21 34 55 89 144 233 377 610 987 1597 2584 4181 6765 10946 17711 28657 46368 75025 121393 196418 317811 514229 832040 1346269 2178309 3524578 5702887 9227465 14930352 24157817 39088169 63245986 102334155 165580141 267914296 433494437 701408733 1134903170 1836311903 09:52:53 I like the "46." shorthand for "46 0". 09:53:28 The whole thing with "double precision" in Forth is kind of funny-weird. 09:53:46 .1234, 12.34 and 1234. are all the same number, a two-cells-wide 1234. 09:54:53 !forth 0.1234 12.34 1234. d. d. d. \ okay, plain .1234 wasn't quite legal 09:54:53 1234 1234 1234 10:35:21 Are Imperial Measurements outdated? http://youtu.be/r7x-RGfd0Yk 10:42:21 Hrm, my log database update script seems to have barfed at the recent string "\udead\ubeef". Apparently the UTF-8 encoder involved there is strict about standards, and refuses to UTF-8-encode that standalone trail surrogate. 10:45:24 heh 10:52:59 -!- carado has joined. 10:53:49 -!- carado has quit (Client Quit). 10:54:05 -!- carado has joined. 10:55:46 -!- carado has quit (Remote host closed the connection). 10:56:22 -!- carado has joined. 11:20:50 -!- carado has quit (Ping timeout: 245 seconds). 11:49:53 -!- carado has joined. 11:52:42 -!- MindlessDrone has joined. 12:02:15 -!- Taneb has joined. 12:06:58 -!- ais523 has joined. 12:21:34 http://dolan.naurunappula.com/screen/d5/f7/d5f7f404978714ec/0/787935.jpg 12:49:53 -!- Sgeo has quit (Read error: Connection reset by peer). 12:58:21 -!- Taneb has quit (Quit: Page closed). 13:00:14 -!- yorick has joined. 13:01:19 -!- carado has quit (Ping timeout: 246 seconds). 13:03:05 -!- boily has joined. 13:03:37 -!- metasepia has joined. 13:08:57 -!- carado has joined. 13:13:28 -!- ggherdov has quit (Remote host closed the connection). 13:13:33 -!- upgrayeddd has quit (Remote host closed the connection). 13:13:45 -!- conehead has quit (Remote host closed the connection). 13:23:26 -!- conehead has joined. 13:30:07 -!- upgrayeddd has joined. 13:36:16 ~metar CYUL 13:36:16 CYUL 271300Z 04012KT 4SM -RA OVC005 01/00 A2951 RMK SF8 PRESFR SLP996 13:36:37 -!- carado has quit (Quit: Leaving). 13:49:26 -!- ggherdov has joined. 13:58:19 good sloshy morning! 13:59:22 quintopia: I went through the Takis bag yesterday. I want moar. I'll have to scour downtown's groceries and dépanneurs under exécrable weather just to probably find some. 14:01:01 -!- L8D has joined. 14:01:05 `relcome L8D 14:01:10 ​L8D: Welcome to the international hub for esoteric programming language design and deployment! For more information, check out our wiki: . (For the other kind of esoterica, try #esoteric on irc.dal.net.) 14:04:00 shachaf: what would a single ascius be? how many avoidupois ounces in an ascius? 14:07:04 -!- oerjan has joined. 14:08:25 `? copumpkin 14:08:27 copumpkin? ¯\(°​_o)/¯ 14:08:58 `learn copumpkin is categorically incapable of being president. 14:09:03 I knew that. 14:09:25 not a natural born citizen, i guess. 14:09:47 -!- nooodl_ has joined. 14:09:47 -!- nooodl has joined. 14:09:54 darn there's _another_ 3-letter nick clash? 14:10:58 copumpkin: can you say something memorable, so that your quote-section won't be empty? 14:11:03 (same goes for impomatic) 14:11:16 `addquote copumpkin: can you say something memorable, so that your quote-section won't be empty? 14:11:19 oerjan: who's nicklashing with whom? 14:11:20 1138) copumpkin: can you say something memorable, so that your quote-section won't be empty? 14:12:10 * boily sighs... “there we go agais523n...” 14:12:26 coppro|nospoiler with copumpkin, myndzi with myname, tromp__ with trout (just found that), and i guess glogbot with glogbackup although they're not _supposed_ to be here at the same time and who speaks to them anyway. 14:12:38 boily: you can just delete it again 14:13:14 ais523: nah. I like it. 14:13:33 glogbot: hi there! :) 14:14:51 trout is of course highly variable, and will sometimes clash with conehead instead. 14:14:52 -!- boily has changed nick to oerboily. 14:14:56 -!- nooodl_ has quit (Ping timeout: 240 seconds). 14:14:56 -!- nooodl has quit (Ping timeout: 240 seconds). 14:15:19 fortunately i rarely have occasion to tab complete my own nick. 14:15:29 hm. right. 14:15:45 -!- oerboily has changed nick to fizboily. 14:15:53 there, that should do it :D 14:15:54 sometimes I /nick to a name just to be able to tab complete it 14:16:04 however, I've got into the awful habit of tab-completing on one letter 14:16:15 because my client favours tab-completing whoever spoke most recently 14:16:20 tab-completing on “f” is dangerous. 14:16:24 meaning it's normally right but I sometimes get tab-ninja'd 14:16:30 fizboily: yep. 14:16:46 even "fi" is annoying. 14:17:48 @quote copumpkin 14:17:48 copumpkin says: YOU ARE SUCH A PULLBACK YOU KNOW WHAT? I FUNCTORED YOUR MOTHER LAST NIGHT 14:18:03 he says most of his memorabilia elsewhere. 14:18:13 -!- fizboily has changed nick to boily. 14:18:18 @quote impomatic 14:18:19 No quotes match. Do you think like you type? 14:19:10 oerjan: is there an easy way to aggregate cucurbitaceæ into the PDF? 14:19:58 do we have that, i've forgotten. 14:20:08 `? cucumber 14:20:10 cucumber? ¯\(°​_o)/¯ 14:20:15 oh wait 14:20:18 * impomatic hasn't said anything interesting to date... 14:20:31 `addquote * impomatic hasn't said anything interesting to date... 14:20:35 1139) * impomatic hasn't said anything interesting to date... 14:20:37 ... 14:21:05 oh come on, you knew it had to happen. 14:21:14 adding it... 14:21:58 boily: to aggregate cucurbitaceæ you need to exploit categorical duality. 14:24:42 -!- carado has joined. 14:25:11 the impomatiquote was added, with a footnote *smirk* 14:31:12 i seem to have mostly stopped reading pdfs after getting the new laptop, because it no longer opens them inside IE. 14:31:56 and in fact opens them in metro hell. 14:32:28 * boily hugs his fully pinguinized machine 14:35:47 -!- trout has changed nick to constant. 14:36:01 -!- FreeFull has joined. 14:36:35 boily: how's your flash doing? >:) 14:37:24 oerjan: I don't know what you're talking about. la la la ♪ 14:38:02 -!- callforjudgement has joined. 14:38:33 -!- ais523 has quit (Read error: Connection reset by peer). 14:38:51 -!- callforjudgement has changed nick to ais523. 14:38:54 oerjan: I probably went through all major bugs and misfires. the most memorable was on my home desktop, when nvidia drivers swapped the blue and red channels. 14:39:05 boily: wow 14:39:51 -!- nooodl has joined. 14:46:50 oh dear they must have fixed it in 8.1 14:48:45 ~metar ENVA 14:48:46 ENVA 271420Z 27026KT 9999 FEW020 BKN046 07/02 Q1002 RMK WIND 670FT 30026G38KT 14:49:23 which one of those represent the storm i seem to be hearing outside the window 14:49:31 *represents 14:50:11 hm weather forecast says breeze. 14:50:18 * oerjan is skeptical. 14:56:00 Maybe "WIND" 14:56:13 hm you'd think. 14:56:21 a _little_ unspecific, there. 14:58:19 you have 26 knot winds going on, which is non-homeopatic. 14:58:29 no clue about that “670FT”. 14:58:57 oh hm. a second wind group. I guess the storm hasn't come to ENVA yet. 15:00:02 well the yr.no weather forecast claimed a breeze, not a storm. dunno why it sounds so loud. 15:00:44 ultra hardcode Norwegian wind? 15:01:21 `frink 26 knots -> m/s 15:01:30 6019/450 (approx. 13.375555555555556) 15:02:48 hm ok there's a warning about possible storm by the coast, perhaps it's got further inland than they expected. 15:04:17 ~eval 26 * 1.852 15:04:17 48.152 15:05:48 ~eval 48.152 / 3.6 15:05:49 13.375555555555556 15:07:56 a boring fungus https://en.wikipedia.org/wiki/Cliona_viridis 15:08:07 wait 15:08:09 *sponge 15:08:24 sheesh, brain, do i have to whack you upside the head 15:12:21 -!- nooodl has quit (Ping timeout: 246 seconds). 15:15:36 oerjan: your head seems to be fille with Impure Brainfsck Derivative Thoughts. please apply brick and reboot. 15:15:42 s/fille/filled/ 15:16:03 ... “green boring sponge”??? 15:20:52 i told you it was boring. 15:23:16 Not Impure Fungeoid Derivative Thoughts? 15:28:20 Hm what happened with Magnus in the topic? 15:45:38 I have an idea for brainfuck 15:45:47 it's like brainfuck, but with a logarithmic scale . 15:46:15 FireFly: he won hth 15:46:31 mroman_: http://esolangs.org/wiki/SELECT.? 15:46:48 Hm, what happened to someone's continuous brainfuck idea? 15:47:06 * oerjan had vaguely hoped for Shikhin to add a "Vishy!" or something. 15:47:27 although the way it ended, probably just as well he didn't. 15:48:40 ~duck magnus 15:48:40 --- No relevant information 15:48:44 ~duck vishy 15:48:45 Viswanathan Anand (born 11 December 1969) is an Indian chess Grandmaster and former World Chess Champion. 15:48:51 * oerjan swats metasepia -----### 15:49:13 eille! no violence against my peaceful bot! 15:49:19 -!- upgrayeddd has quit (Quit: Connection closed for inactivity). 15:49:21 BUT IT'S HIDEOUSLY BIASED 15:49:49 * boily hugs his bot. “don't listen to angry magnus supporters.” 15:52:34 also google translate thinks "eille" is finnish. 15:52:36 -!- carado has quit (Quit: Leaving). 15:53:23 and means "MATCH", capitals required. 15:54:16 fr:eille → en:hey. 15:54:36 WHY DOESN'T GOOGLE TRANSLATE KNOW THAT? 15:56:36 FOR THE SAME REASON FRENCH IS FRANCE FRENCH, AND ARMENIAN IS EASTERN ARMENIAN, AND CHINESE IS MANDARIN. 15:57:06 (I'd really like to have a Cantonese version. it'd be very useful in Montréal.) 15:58:20 but the best would be simultaneous multiple languabe output. 16:03:17 aren't Mandarin and Cantonese spelled the same? 16:03:27 so unless you were doing voice recognition, it make sense to merge them in a machine translator 16:05:27 no, the gramar and characters used are different. 16:06:38 right 16:09:03 ~metar CYUL 16:09:04 CYUL 271600Z 31009KT 8SM -SN OVC009 01/00 A2945 RMK SF8 /S01/ SLP976 16:09:10 -SN indeed. 16:12:42 -!- MindlessDrone has quit (Quit: MindlessDrone). 16:12:58 !forth 2 dummy . 16:12:59 2 16:18:03 -!- carado has joined. 16:34:49 Or a Brainfuck Derivative based on the disecrete logarithm problem thingy 16:35:15 or Knappsack Problem 16:36:18 -!- MindlessDrone has joined. 16:37:02 mroman_: to base a language on an NP problem is vile and nasty. please implement. 16:42:08 What about a travelling saleman language 16:42:13 That salesman sells integers 16:42:33 -!- Sprocklem has joined. 16:42:35 -!- Taneb has joined. 16:43:31 Tanelle. 16:44:09 boily: you failed to mention Eodermdrome 16:49:46 * boily fails to mention Eodermdrome 16:50:31 Apparently there are some 2^2^n problems 16:50:34 That is pretty heinous 16:51:00 Hitler if he was a complexity class 16:52:13 what about O(ackermann). 16:53:01 I recall ackermann⁻¹ appearing in the complexity of some algorithms 16:53:16 Yeah, but ackermann^-1 is pretty fucking soft 16:53:17 that's "p. slow" 16:53:22 Barely a step above O(1) 16:53:40 also, log*(n) (iterated logarithm) 16:53:45 O(fast growing * factorial * exponent * tetration * fuck you fuck you fuck you) 16:53:54 If I had a cancer growing at O(a^-1), I wouldn't even stop eating radium 16:54:05 Bike : Sure, but try finding such a problem! 16:54:19 Such a problem *that doesn't have a less complex solution* 16:54:46 Also my guess is that there's probably a cap on complexity 16:55:23 what does radium taste like? 16:55:29 what's the complexity of finding every problem with ackermann complexity 16:55:31 -!- Slereah has quit (Read error: Connection reset by peer). 16:55:42 -!- Slereah has joined. 16:55:44 Oh dagnabbit 16:58:13 and the upper limit on complexity is impossibility. 16:59:20 http://en.wikipedia.org/wiki/ALL_(complexity) 17:00:47 -!- oerjan has quit (Quit: keep your limit down). 17:22:05 Yeah, but I meant more computational time-wise 17:22:35 'forever' is a time! 17:27:58 -!- nooodl has joined. 17:33:57 Would ALL include undecidable decision problems? 17:35:35 i.e. is the halting problem in ALL, or is it not classified as a decision problem despite having a boolean answer? 17:36:20 halting problem is in RE 17:36:25 (which is a subset of ALL ofc) 17:37:15 Oh 17:38:52 since if a program halts it takes finite time to demonstrate thath. 17:39:09 but yes, ALL is a strict superset of RE, and so includes impossible problems. 17:41:24 But not undefinable problems! 17:43:32 iunno. might as well put them in there too. 17:46:58 Nah 17:47:11 Undefinable problems cannot be inputed in a Turing machines 17:47:36 Though they can be in a SUPERTURING MACHINE 17:47:41 i'll just use an undefinable machine. 17:47:52 Like a Turing machine with continuous cells 17:48:23 Or a Turing machine with infinite starting input 17:54:10 Why is EXPTIME considered unfeasable 17:54:28 I ran some exptime programs 17:54:35 They were mighty feasable 17:54:46 boily: isn't it just the greatest food invention ever? why did it take so long to get invented? 17:55:05 Slereah: because for realistically large problem sizes you're usuallyy fucked. 17:55:44 Feasable isn't the same as "Fuck it's too big, let's give up 17:55:59 twss 17:56:59 if you're giving up you're basically saying it's infeasible. 17:57:36 wikipedia has a good example of an exptime problem: figuring out perfect play from a given chess position is exponential in the size of the board. 17:57:58 and guess what, people actually don't compute perfect play in chess. 17:58:11 They might if they played on a 4x4 chess set! 17:58:31 they don't. 17:59:33 "Chess Attack: played on a six-row five-column board, Chess Attack follows standard chess rules, and can be regarded as an endgame variant." 17:59:42 That's only 30 cells! 18:00:13 i didn't know that was proven exptime...yes there are exp many games from a position, but i didn't know it had been proven that there wasn't some complicated heuristic that ended up being as good as perfect 18:00:29 'as good as perfect' is pretty hard. 18:00:41 quintopia: my mouth was burning with the force of a thousand limes. 18:00:47 but "prove it doesn't exist" is also hard 18:01:18 http://turbo.sos.gd/ 18:01:42 boily: and i only sent the regular ones. they also have NITRO, which are the same but habanero based. 18:01:57 Slereah: i can prove that "while (1) {}" never halts but that doesn't make the halting problem feasible, you know? 18:02:51 Well yes, but you can always solve an EXP problem 18:02:56 * boily has gained a new quest! “Find a bag of NITRO TAKIS”! 18:02:56 Given sufficient time and space 18:02:57 Bike: doesn't it halt when someone interrupts it/ 18:03:02 So it's not really comparable 18:03:14 Bike: do you ever sleep? 18:03:56 I was last on here about 11 hours ago 18:04:10 and you were here then 18:05:26 L8D: http://zem.fi/ircvis/esoteric/people_presence.html 18:06:11 boily: you live in BIG SCOTLAND 18:06:14 http://www.buzzfeed.com/robinedds/its-thanksgiving-so-we-asked-some-brits-to-label-the-us-stat?s=mobile 18:06:47 http://www.buzzfeed.com/robinedds/its-thanksgiving-so-we-asked-some-brits-to-label-the-us-stat 18:07:18 bwah ah ah ah ah :D 18:07:30 that's a new one, Big Scotland. 18:08:37 L8D: thanks 18:09:13 `learn Canada is Big Scotland. Like, you know, very big. 18:09:17 L8D: no 18:09:18 I knew that. 18:10:45 Slereah: what's the point of having 'feasible' mean 'possible'? 18:14:51 Because that's what it means? 18:15:01 'possible' could be said to mean that we can imagine some actor, possibly in a science-fiction novel, considering it feasible, while 'feasible' means that i can be that actor. 18:15:08 Sharing the same root as french "faisable" 18:15:09 Doable 18:15:09 what does hackego actually say is he already has information about something? 18:15:20 fuck etymology 18:15:32 Well yes, but if you go by that 18:15:34 myname: i don't think `learn checks. 18:15:37 None of them are feasable 18:15:43 Polynomial can be unfeasable! 18:15:47 Even O(1) 18:15:57 If O(1) is 10^100 18:16:36 a particular O(1) algorithm might be infeasible but most of the ones we use aren't. 18:17:24 That sounds a bit racist to judge a class from a few bad apples! 18:18:01 s/a few bad apples/the majority of the bunch/ 18:19:05 So racist 18:19:27 i know you're joking and all but don't trivialize racism, please. 18:19:27 * boily colle des pommes sur Slereah 18:20:06 feasibility is an informal concept. it is what it is. 18:20:28 the golden pommes de soleil or ... the silver pommes de la lune? 18:20:31 The best program is O(0) 18:20:54 Slereah: all Unnecessary programs are O(0)! 18:21:18 unless they exist 18:21:22 Well there's only one O(0) program 18:21:23 *don't exist 18:21:24 The empty program! 18:21:30 quintopia: I'd go with a golden apple. you know, something something kallisti something... 18:21:35 Although 18:21:42 I'm not sure O(0) makes sense 18:21:59 Since O(f) is O(f)/f ~> 1 18:22:09 Is it? 18:22:10 I forget 18:22:36 no 18:23:14 "[f(x) = O(g(x)) if and only if there is a positive constant M such that for all sufficiently large values of x, f(x) is at most M multiplied by g(x) in absolute value." 18:23:25 an annoying definition i can never remember 18:24:04 this implies that if f = O(0) then f is 0, probably. 18:24:09 I guess O(0) makes sense for the empty program then 18:24:15 quite. 18:25:21 O(0 + i) 18:26:41 multiply the Ms of an O(1) by -i, and voila. 18:27:43 Are the computational classes machine dependant? 18:27:47 Speed-wise 18:28:03 I seem to recall that some algorithms are faster in certain paradigm 18:28:26 that's what oracles are for, probably. 18:29:22 I mean within the TC class of computers 18:29:55 but like, say for ripple-carry addition, you say it's linear in the number of digits; that basically means that the time is a linear function of how much an operation taken as primitive (adding digits) takes 18:30:57 -!- Frooxius has joined. 18:34:50 boily: isn't eris the moon goddess? 18:34:55 oh wait 18:34:57 that's selene 18:35:06 why do i associate eris with the moon somehow? 18:36:01 Bike: that implies that O(0) and O(1) mean the same thing :) 18:36:20 BUT WE KNEW WHAT SLEREAH MEANT 18:37:21 -!- Sprocklem has quit (Ping timeout: 252 seconds). 18:37:38 mathematical question 18:37:52 psychological answer. 18:38:05 if i have a function f: A x P(A) - > R 18:38:15 what the hell is f(.,A)? 18:38:37 what is P()? 18:38:40 powerset? 18:38:47 yes 18:39:12 and . means plug in the whole set? 18:39:32 eh i don't know. but it's still a function into the reals 18:39:36 that is my question 18:39:52 P(A) means you had issues with your mother when you were young. 18:40:33 i have never seen f(. in any way 18:42:17 myname: I've seen people use - as an implicit lambda variable 18:42:25 as in, f(_,A) means \x.f(x,A) 18:43:19 well, it says it should be a vector 18:43:48 f(.,A) that is 18:46:49 myname: what do you mean? it depends what f and A are. for example if A is the empty set then it's the empty function. 18:47:21 i think myname is asking about notation. 18:49:15 oh, yeah presumably that's a lambda variable 18:49:43 that sounds strange in this context, but i will take it for now 18:56:14 -!- nisstyre has quit (Quit: Leaving). 18:56:30 -!- L8D has quit (Read error: Operation timed out). 18:57:57 ais523: Sometimes people even use two -s! It's great. 18:58:44 As in Hom(f(-),-) ~ Hom(-,g(-)) 19:00:12 -!- L8D has joined. 19:00:59 shachaf: I refuse you adjunction. 19:01:08 * boily still doesn't understand adjunctions. :( 19:01:23 boily: I only understand them from the axioms, and intuitively 19:01:25 i don'2 get the advantage of saying "f(.,A) is in the core" instead of "for every x in A, f(x,A) is in the core" 19:01:28 I don't get the in-between bits 19:01:59 like, in a closed category, you have (A×B)=>C === A=>(B=>C) 19:02:06 which is the main interesting point 19:02:42 the main interesting thing you can do in a closed category is to tensor morphisms backwards 19:15:38 -!- tertu has joined. 19:16:56 -!- Sprocklem has joined. 19:18:03 -!- Sprocklem has quit (Remote host closed the connection). 19:20:05 -!- tertu has quit (Ping timeout: 248 seconds). 19:22:30 -!- MindlessDrone has quit (Ping timeout: 245 seconds). 19:27:44 ais523: Well, that's usually the definition of =>. 19:28:15 (Note that the two =>s on the right side aren't the same thing.) 19:28:30 -!- carado has quit (Ping timeout: 252 seconds). 19:30:06 boily: https://www.youtube.com/watch?v=7YLy4j8EZIk 19:32:55 that video will be at home watched. 19:37:38 shachaf: yes they are 19:37:42 -!- MindlessDrone has joined. 19:37:47 that's the definition on objects 19:37:55 there's a definition on morphisms too but it's more complex 19:40:40 (->) -> (->) => >>> -> => -> >>> × >>> -> => -> >>> => (->) -> (->) 19:41:04 ? 19:41:35 morphism art. 19:41:42 I'm not sure what you mean. 19:42:17 -!- muskrat has joined. 19:42:18 Or maybe I do understand, actually, will look again in a little while. 20:00:46 -!- Slereah has quit (Ping timeout: 240 seconds). 20:23:41 -!- nisstyre has joined. 20:29:02 -!- ais523 has changed nick to scarf. 20:32:30 -!- yorick has quit (Remote host closed the connection). 20:34:14 fizzie: are you named after a train? someone in another channel just said that the train they were on wasn't fizzie 20:36:02 -!- yorick has joined. 20:36:47 scarf: I am not named after a train. But that sounds curious. 20:37:11 `quote 820 20:37:12 820) I am a train. There's a wireless network in the train! 20:37:24 fizzie: they just referenced HackEgo quote 820 20:37:27 so, hmm 20:37:38 must be following this channel for some reason 20:37:41 other people can HackEgo? 20:37:44 -!- Oj742 has joined. 20:37:46 Oh. Uh. Strange. 20:37:48 `relcome Oj742 20:37:51 ​Oj742: Welcome to the international hub for esoteric programming language design and deployment! For more information, check out our wiki: . (For the other kind of esoterica, try #esoteric on irc.dal.net.) 20:38:05 scarf: why on fungot would people want to follow the chännel... 20:38:06 boily: which includes themselves. if they were fnord. amazing restaurant. even the wrong bits be painted as a string? examples that i have 20:38:22 (I tried googling for "fizzie train" but mostly got "Fizzie Vixen"'s Vine stuff. 20:38:34 traaaaain! 20:38:37 (That's not me.) 20:38:41 I like trains. 20:38:47 * kmc too 20:39:16 -!- scarf has quit. 20:39:40 oh fungot. I just understood fizzie's pectopah. 20:39:40 boily: i use a combination of ( for the bytecode compiler could work well 20:40:07 fungot: I'll let that unbalanced ( slip this time, you vile unkarmic bot. 20:40:07 boily: and my debugging usually revolves around ( define low-level in terms of s-expressions ( i don't expect you to go to a public school? remind me not to 20:40:19 fungot: you're stretching your luck too far, young'un. 20:40:20 boily: i can't believe i said that 20:40:26 fungot: me neither. 20:43:40 -!- constant has changed nick to variable. 20:44:23 I don't remember what 476 is about at all. 20:44:49 `quote 476 20:44:51 476) I think it's fizzie against everyone atm AND EVERYONE IS WINNING EXCEPT FIZZIE 20:45:09 maybe it was a race to make you not remember itself 20:46:45 Taneb: do you know? 20:47:06 I do not 20:47:10 it was the other Taneb 20:47:21 Ah, the usual explanation. 20:47:23 other taneb?? 20:47:32 You know... 20:47:35 the one who Taneb is not. mystery explained. 20:47:35 ...ngevd 20:48:00 `?people who taneb is not 20:48:01 ​/home/hackbot/hackbot.hg/multibot_cmds/lib/limits: line 5: exec: ?people: not found 20:48:04 `? people who taneb is not 20:48:07 elliott, a rabbi, Mark Zuckerberg, James Bond 20:48:19 can't help but notice a lack of ngevd 20:48:47 `pastelogs AND EVERYONE IS WINNING 20:48:59 It seems to have been a #esoteric-minecraft quote. 20:49:16 well, shit. 20:49:26 http://codu.org/projects/hackbot/fshg/index.cgi/raw-file/tip/paste/paste.1861 20:49:46 About a dorf furtress game. 20:49:56 In which I guess there's a convention to name folks after #esotericers? 20:50:01 how do you 'win' dorf furtressx 20:50:26 @tell oerjan I didn't add any new newlines to @run or change the space handling, all I did was increase a constant. I didn't touch the code, though I considered it. https://github.com/int-e/lambdabot/commits/master is up-to-date except for the 200 -> 350 change in lambdabot-core/src/Lambdabot/OutputFilter.hs (textwidth). 20:50:27 Consider it noted. 20:51:36 Taneb: Who is on a rampage currently? Just fizzie He's a mason 20:51:52 -!- MindlessDrone has quit (Quit: MindlessDrone). 20:51:58 What do you call a dorf with no nose? fizzie? Yup 20:52:03 Sometimes reading stuff feels kinda weird. 20:52:08 (I do have a nose.) 20:52:16 do you really 20:52:18 where'd you get it 20:52:24 fizzie, I presume you're not a dorf, too 20:52:28 It came with the face. 20:52:35 Speaking of dwarf fortress 20:52:42 @tell Phantom_Hoover ... 20:52:42 Consider it noted. 20:58:13 pegnose fizzie 21:03:56 ~duck pegnose 21:03:57 --- No relevant information 21:07:47 -!- oklopol has joined. 21:15:21 `? befunge 21:15:23 befunge? ¯\(°​_o)/¯ 21:16:02 : SUM ( + SIZE 1 EQUAL NOT ) WHILE ; 10 RANGE SUM . 21:16:41 or: : sum ( + size 1 = ! ) while ; 10 range sum . 21:17:35 !forth : SUM ( + SIZE 1 EQUAL NOT ) WHILE ; 10 RANGE SUM . 21:17:37 ​\ in file included from *OS command line*:-1 \ /tmp/input.3307:1: expected control flow stack item \ : SUM ( + SIZE 1 EQUAL NOT ) >>>WHILE<<< ; 10 RANGE SUM . \ Backtrace: \ $7FBF20466988 throw \ $7FBF20476918 c(abort") \ $7FBF20476AC8 cs-item? \ $7FBF20477440 CS-ROLL 21:20:55 Presumably that's the suggested Forthoid, and not actual Forth. 21:21:04 !forth : sum 0 begin over while + repeat ; 0 1 5 2 4 3 sum . \ sum of a 0-terminated list 21:21:05 15 21:23:52 -!- Bike_ has joined. 21:23:55 -!- sebbu has quit (Ping timeout: 252 seconds). 21:23:59 -!- Bike_ has quit (Client Quit). 21:24:18 -!- Bike_ has joined. 21:26:17 `list 21:26:19 ais523 atriq Bike boily cuttlefish elliott fgrep Fiora fungot HackEgo metasepia mnoqy monqy Ngevd nortti oklopol Phantom_Hoover Phantom__Hoover pikhq quintopia Roujo Sgeo SgeoBot shikhin SUPREME_BUTT_SUI Taneb 21:26:31 Aaaah 21:26:38 -!- Bike has quit (Ping timeout: 264 seconds). 21:26:38 sorry. couldn't resist. 21:28:26 -!- Bike_ has changed nick to Bike. 21:31:42 -!- boily has quit (Quit: (APPLY CHICKEN '(CHICKEN CHICKEN))). 21:31:45 -!- metasepia has quit (Remote host closed the connection). 21:37:19 Sometimes I'm happy I'm not on the List 21:44:03 -!- muskrat_ has joined. 21:47:30 -!- muskrat has quit (Ping timeout: 246 seconds). 21:52:35 -!- nisstyre has quit (Quit: Leaving). 21:54:58 Thing I like: when someone writes a long S-expression in Scheme (or other such), and needs to put some two dozen )s after the last non-) character, and decides to put them like http://sprunge.us/INhI 21:55:55 hah 21:56:21 (I've seen that happen a total of one time.) 21:57:43 :D 22:03:20 -!- nisstyre has joined. 22:25:52 When someone writes "CRINGE" on IRC you know it's a pun well done 22:27:43 !forth : i begin #tib @ >in @ = if tib 50 accept #tib ! 0 >in ! then bl word find dup if state @ = if , else execute then else dup rot count >number if state @ if last @ dup @ last ! dp ! then abort then drop2 state @ if ['] lit , , then then again ; i | 2 2 + . 22:27:44 ​\ in file included from *OS command line*:-1 \ /tmp/input.3951:1: Undefined word \ : i begin #tib @ >in @ = if tib 50 accept #tib ! 0 >in ! then bl word find dup if state @ = if , else execute then else dup rot count >number if state @ if last @ dup @ last ! dp ! then abort then >>>drop2<<< state @ if ['] lit , , then then again ; i | 2 2 + . \ Backtrace: \ $7F226ACC9A68 throw \ $7F226ACDFC68 no.extensions 22:27:59 !forth : int begin #tib @ >in @ = if tib 50 accept #tib ! 0 >in ! then bl word find dup if state @ = if , else execute then else dup rot count >number if state @ if last @ dup @ last ! dp ! then abort then drop2 state @ if ['] lit , , then then again ; int | 2 2 + . 22:28:00 ​\ in file included from *OS command line*:-1 \ /tmp/input.3997:1: Undefined word \ : int begin #tib @ >in @ = if tib 50 accept #tib ! 0 >in ! then bl word find dup if state @ = if , else execute then else dup rot count >number if state @ if last @ dup @ last ! dp ! then abort then >>>drop2<<< state @ if ['] lit , , then then again ; int | 2 2 + . \ Backtrace: \ $7FCE3F9ADA68 throw \ $7FCE3F9C3C68 no.extensions 22:28:45 -!- Bike has quit (Ping timeout: 245 seconds). 22:30:36 -!- Bike has joined. 22:36:16 -!- oerjan has joined. 22:36:40 -!- nisstyre has quit (Quit: Leaving). 22:36:47 -!- carado has joined. 22:38:20 nice of the storm to fully hit just as i was going back home 22:38:37 http://i.imgur.com/ampdE1n.gif 22:39:19 @messages-lost 22:39:19 int-e said 1h 48m 52s ago: I didn't add any new newlines to @run or change the space handling, all I did was increase a constant. I didn't touch the code, though I considered it. https://github.com/int-e/lambdabot/commits/master is up-to-date except for the 200 -> 350 change in lambdabot-core/src/Lambdabot/OutputFilter.hs (textwidth). 22:40:14 @tell int-e i guess it was done before your time then. 22:40:14 Consider it noted. 22:40:27 * oerjan looks suspiciously at elliott 22:40:28 @messages- 22:40:29 You don't have any messages 22:40:45 oerjan: might also look suspiciously at mokus 22:41:08 who is mok 22:41:14 *mokus 22:41:28 irssi's tab completion, so primitive 22:41:46 cannot take me trying to tab complete someone not here. or its own name. 22:42:40 Maintainer: James Cook 22:42:58 -!- muskrat_ has changed nick to muskrat. 22:43:49 wat 22:44:14 oerjan: you asked who mokus is. 22:45:40 is that somewhere in lambdabot's code. 22:45:52 look at the .cabal file 22:46:24 https://github.com/mokus0/lambdabot/blob/master/lambdabot/lambdabot.cabal 22:46:37 or http://hackage.haskell.org/package/lambdabot :) 22:46:48 http://www.deepbondi.net/ looks promising. 22:47:11 -!- sebbu has joined. 22:47:50 -!- sebbu has quit (Changing host). 22:47:50 -!- sebbu has joined. 22:49:14 -!- muskrat has quit (Read error: Connection reset by peer). 22:49:41 -!- Sgeo has joined. 22:57:50 -!- Bike has quit (Ping timeout: 264 seconds). 22:57:59 -!- Bike has joined. 23:02:36 @tell slereah Why is EXPTIME considered unfeasable <-- "For every polynomial-time algorithm you have, there is an exponential algorithm that I would rather run." -- Alan Perlis 23:02:36 Consider it noted. 23:03:00 ---------[--------- 23:03:48 Bike: are you removing tabs in brainfuck 23:05:08 ugh. +[,>+<---------[>-]>[<+++++++++.>->]<<] 23:05:56 ]+] 23:05:57 I probably messed that up, I'm out of practice. 23:07:34 I should simply do +[,---------[+++++++++.[-]]+] 23:08:49 int-e: you're not halting at eof 23:09:19 so which eof convention do you favor? 23:09:40 @poll-results olist 23:09:41 Poll results for olist (Open): update=932 23:09:41 0 usually, since that's what the bots around here use 23:10:02 oerjan: i just realized that @vote won't show the list of names anyway, so you still need to @poll-results 23:10:05 so ,[---------[+++++++++.[-]],] 23:10:30 that'd work 23:11:19 wait, how's the middle loop ever halt 23:11:34 or. wait. nevermind. 23:20:12 -!- myname has quit (Ping timeout: 240 seconds). 23:20:20 -!- myname has joined. 23:33:47 oerjan: i don't understand that quote 23:34:02 wait i read that as alan turing 23:34:13 Perlis -> Turing 23:35:03 (that that it changes anything) 23:35:07 perling 23:35:16 (*not) 23:35:43 oklopol: it means that the formal complexity class of an algorithm may not mean much in practice. 23:35:54 example: simplex method 23:36:33 yeah okay i guess it changes things if it was someone who lived much after turing 23:36:53 also that constant overhead may be more important than O() class for problem sizes you actually care about 23:37:05 at least that's how read it. 23:37:09 indeed 23:37:18 one remarkable thing about EXPTIME is that it's actually known to be different from P 23:37:19 *\i 23:37:22 *-\ 23:38:00 it's not _that_ remarkable, time and space hierarchies are pretty fine masked _separately_. 23:38:11 yeah 23:38:19 it's just hard to compare time with space. 23:38:21 saying it's remarkable is somewhat tongue-in-cheek 23:38:39 given all the classes which aren't known to be distinct from P 23:38:43 time with space, or deterministic with nondeterministic 23:38:54 wait can you say "fine masked" in english 23:39:04 i'm not familiar with that phrase 23:39:08 whatsit mean 23:40:06 Then there are the classes for quantum computers 23:40:11 gt suggests "meshed" 23:41:44 or maybe fine mesh 23:43:17 still not familiar with this idiom 23:44:02 finely divided 23:44:28 now that has to be actual english. 23:44:31 please? 23:45:04 perhaps i'm just thick. 23:46:03 next try "fine-grained" 23:48:25 FreeFull: yeah, P ?= BQP ?= NP is real important 23:49:31 i think it would be funny if someone found out a way to simulate quantum systems efficiently with classical computers, and as a side effect broke RSA 23:49:45 "Love #StackOverflow? Want it for your team? Check out http://quandora.com" ok you can't just take the name "Quora" and stick a few more letters in the middle 23:50:06 that would be funny 23:50:24 I think it would be funny to get a totally non-constructive proof of P = NP 23:50:30 quwhynotora 23:50:49 that too 23:51:08 or a proof which produces a polynomial-time algorithm which is way too slow to ever use, and which resists improvement 23:51:18 or a proof that P ?= NP is independent of the axioms of ZFC 23:51:58 i think the point is that kmc likes to frustrate mathematicians 23:52:18 five worlds etc 23:52:26 what about an algorithm for SAT that seems to work extremely fast but which no one can prove that it always works 23:52:42 imo, a good paper 23:52:53 that is a good paper 23:53:14 maybe i should read it once, i guess it has all those options. 23:53:27 now, are you referring to http://www.joelonsoftware.com/articles/FiveWorlds.html or http://starwars.wikia.com/wiki/Five_Worlds 23:53:37 no 23:53:40 (have found the actual paper but i like that those two links were first) 23:53:46 shachaf: i vaguely suspect not the latter 23:53:59 What about a proof that P > NP? 23:54:01 That'd be weird 23:54:23 FreeFull: well then you're just breaking mathematics 23:54:24 oerjan: oh, well, i vaguely suspect not you 23:54:55 P <= NP is pretty trivial. 23:55:14 (all P turing machines are also NP turing machines) 23:56:33 -!- sebbu has quit (Ping timeout: 272 seconds). 23:57:56 likewise P <= BPP <= NP because a BPP machine is like a NP machine but it has to accept on "lots of paths" not just one 23:58:28 we did an exercise about the class BPP^NP which my friend decided means "Black Panther Party with NP oracle" 23:58:40 puttin that in my next sci-fi epic 23:59:23 wait is BPP <= NP really obvious 23:59:47 NP doesn't allow you to count paths 2013-11-28: 00:00:21 both reducing to #P is obvious. 00:00:57 ah, yeah, i'm wrong 00:01:09 "The relationship between BPP and NP is unknown: it is not known if BPP is a subset of NP, NP is a subset of BPP or if they are incomparable." 00:01:37 P is still a subset of BPP though, right 00:01:42 sure 00:04:32 what is it thundering 00:04:38 nooodl: genericLength is almost never a good idea. 00:04:44 Pretty much the only use case is lazy naturals. 00:05:20 * oerjan unplugs laptop, just in case 00:06:07 it's about time for the monthly recommended uncharging, anyway 00:07:27 shachaf: what if my list has more than 2^64 elements? er hmm... 00:07:52 i guess that's more interesting on 32-bit machines 00:08:10 > 2^64 00:08:11 18446744073709551616 00:08:21 i'm so over 32-bit machines 00:08:25 > 2**64 00:08:26 1.8446744073709552e19 00:08:28 kmc: With 64-bit Int it doesn't matter much realistically. With 32-bit Int it can matter, but you should *still* not use genericLength. 00:08:31 @src genericLength 00:08:32 genericLength [] = 0 00:08:32 genericLength (_:l) = 1 + genericLength l 00:08:41 maybe by the time Servo is a product even phones will all be 64-bit 00:08:46 @src length 00:08:46 Source not found. I can't hear you -- I'm using the scrambler. 00:08:46 that would be cool 00:09:01 > map Seq.length (iterate (\s -> s <> s) (Seq.singleton ())) !! 63 00:09:03 -9223372036854775808 00:09:08 32-bit architectures are a real problem if you want lightweight threads because there isn't enough address space for all the stacks 00:09:20 @list vote 00:09:20 poll provides: poll-list poll-show poll-add choice-add vote poll-result poll-close poll-remove 00:09:29 @help poll-show 00:09:29 poll-show Shows all choices for some poll 00:09:38 @poll-show remove@src 00:09:38 ["no","yes"] 00:09:53 @poll-add remove@src makeitactuallywork 00:09:53 usage: @poll-add with "ThisTopic" style names 00:10:05 oops 00:10:39 @choice-add remove@src makeItActuallyWork 00:10:39 New candidate "makeItActuallyWork", added to poll "remove@src". 00:10:51 @vote remove@src makeItActuallyWork 00:10:51 The "remove@src" poll is closed, sorry ! 00:10:54 darn 00:11:10 @poll-show remove@src 00:11:10 ["makeItActuallyWork","no","yes"] 00:11:17 semi-closed. 00:11:22 oerjan, what's your favourite turing tarpit 00:12:13 * int-e gives up on tab removal (with bfgolf rules; no negative numbers), after ,[[>+>+<<-]>-[-[-[-[-[-[-[-[-[>.<[-]]>[-]<]]]]]]]]>[.[-]]<<,] and the slightly longer >,[>>+++++++++[>+<-<<-[>]>]>[>[>]<[<<<+>>>-]<[-]<<.>>]>[-]<<<,] 00:15:45 Taneb: underload or ///, maybe slightly the former 00:16:10 oerjan, thank you 00:16:23 wait is this for your essay 00:16:52 THIS IS A GREAT INVASION OF PRIVACY AND I WANT ROYALTIES 00:17:06 Shush 00:17:17 I just wanted an example of a turing tarpit 00:17:17 Taneb is writing an essay? 00:17:26 kmc, I have to write an essay in the next 9 or so hours 00:17:42 About a classic Computer Science paper of my choice 00:17:47 I chose On Computable Numbers 00:17:58 shoulda done five worlds. smh 00:18:12 if you want it really tarpitty you can do underload with just :()^ or /// with just /\ 00:18:34 Taneb: can i have royalties too 00:18:48 shachaf, if you pay for me to live in CA 00:19:00 uh 00:19:03 no royalty in CA 00:19:15 try .uk instead 00:19:27 or .nl etc 00:19:29 tarpittiful 00:19:30 r.i.p. Emperor Norton 00:19:45 we'll name that bridge after him yet 00:19:46 int-e: well, Taneb is actually in .uk 00:19:55 fucking oakland wouldn't go along 00:19:55 rip 00:20:07 kmc: the bastards! 00:20:29 we just need to make sure all the san franciscans who move to oakland due to outrageous rent in SF will remain loyal to the emperor 00:20:35 shachaf, although I have contacts in .nl and .au 00:20:42 And .it, come to think of it 00:20:51 also there's a new bar in the Tenderloin called Emperor Norton's Boozeland 00:20:55 i've yet to go 00:21:00 I assume I will either love it or hate it intensely 00:22:23 did norton even drink 00:23:03 That reminds me 00:23:04 don't know 00:23:12 I really need to get a game of Diana: Warrior Princess going 00:23:31 -!- myname has quit (Ping timeout: 272 seconds). 00:25:10 shachaf: there is royalty in .ca though 00:25:18 Taneb: would .ca suffice 00:26:15 hmmm maybe 00:27:33 emperor Taneb for president 00:28:33 "Whoever after due and proper warning shall be heard to utter the abominable word "Frisco," which has no linguistic or other warrant, shall be deemed guilty of a High Misdemeanor, and shall pay into the Imperial Treasury as penalty the sum of twenty-five dollars." 00:28:57 if outsourced royalty counts 00:30:13 -!- myname has joined. 00:30:21 oerjan: how much is that in 2013 dollars 00:30:49 hm can frink convert that 00:31:52 https://github.com/ngerakines/commitment/blob/master/commit_messages.txt 00:32:58 ...I may be guilty of a few of those 00:33:07 -!- Phantom_Hoover has joined. 00:33:42 `frink 25 dollars_1872 -> dollar 00:33:53 Error when reading Consumer Price Index file from FTP site. \ Will use static file for historical U.S. currency conversions. \ 463.23673749815968985 00:34:07 -!- Bike has quit (Ping timeout: 260 seconds). 00:35:16 i suppose that shouldn't be _too_ out of date. 00:35:41 'IEize" 00:35:51 -!- Bike has joined. 00:45:18 -!- muskrat has joined. 00:45:22 -!- sebbu has joined. 00:46:01 -!- sebbu has quit (Changing host). 00:46:01 -!- sebbu has joined. 00:47:59 -!- Oj742 has quit (Ping timeout: 265 seconds). 00:48:21 Aaaah 00:48:32 What does the fact that things can be accidentally turing complete show 00:48:58 This essay is in in 9 hours and I'm 50 words short 00:49:01 that the world is a bad place 00:49:09 > 50/9 00:49:10 5.555555555555555 00:49:18 Not quite shachaf 00:49:20 > 50/(9*60) 00:49:21 9.259259259259259e-2 00:49:52 Help I've reached the point where I'm being really introspective about my chest hair 00:49:59 that we're doomed once our toasters accidentally turn sentient. 00:50:08 sorry, *sapient 00:50:28 are your chest hairs turing complete 00:50:39 I don't think so but on the other hand bathroom tiles are 00:50:41 So who knows 00:50:48 kmc: did you know there was an iso standard for entering unicode codepoints 00:51:07 actually it's just what urxvt does 00:51:12 i guess you use urxvt 00:57:58 -!- Phantom__Hoover has joined. 00:58:13 -!- Phantom_Hoover has quit (Ping timeout: 248 seconds). 01:08:30 -!- yorick has quit (Read error: Connection reset by peer). 01:09:15 yeah i think i've mentioned it here 01:31:58 -!- variable has changed nick to function. 01:33:02 fungot: but are you a constant function or a variable function? 01:33:02 lexande: i'm ol' x86 user ;p http://www.klubitus.org/ fnord/ fnord 01:33:07 err, function ^ 01:33:58 function: fun fact, all except one of your nicks collides with someone else in the first 3 letters 01:34:42 * oerjan vaguely wonders if function is changing nick automatically and has been idling this whole time 01:34:45 fungot is /win 19 01:34:46 lexande: how old are you?" " this section describe infrared connection troubleshooting procedure." hahah, same with perl/ java/ io/ file.html 01:35:10 -!- Taneb has quit (Quit: Leaving). 01:35:45 you have fungot in its own window? 01:35:45 oerjan: different people have different preferences. some people don't 01:35:56 fungot: i guess you're right. 01:35:56 oerjan: hmm how can drscheme fnord factorial that fast and with no examples. 01:36:09 fungot: it's a mystery 01:36:09 oerjan: hehe... my wife? is she at home enjoying capitalism?. yarly nowai fnord if then else 01:36:35 fungot: that sounds expensive, also i didn't know you were married. 01:36:35 oerjan: external 1g scsi hd. but that may be very good for writing little scripts." how many people use religion as an answer 01:37:00 oerjan: no, I don't change nick automaticall 01:37:08 oerjan: i started saying something about fungot, and then i won 01:37:08 lexande: but why would you need to check 01:37:11 oerjan: which nick doesn't collide ? 01:37:19 lexande: I'm a mutable constant function 01:37:25 function: variable 01:37:32 oerjan: ha 01:37:46 constants are just a kind of function 01:39:27 -!- Sprocklem has joined. 01:43:26 -!- nooodl has quit (Ping timeout: 264 seconds). 01:43:42 -!- nooodl has joined. 01:45:52 -!- Sorella has quit (Remote host closed the connection). 01:48:23 -!- nooodl_ has joined. 01:49:17 -!- nooodl has quit (Ping timeout: 272 seconds). 01:52:50 -!- Sorella has joined. 01:53:09 -!- Sorella has quit (Changing host). 01:53:10 -!- Sorella has joined. 02:20:57 -!- Phantom__Hoover has quit (Read error: Connection reset by peer). 02:27:18 -!- oklopol has quit (Ping timeout: 241 seconds). 02:27:49 -!- nooodl__ has joined. 02:31:18 -!- nooodl__ has changed nick to nooodl. 02:31:43 -!- nooodl_ has quit (Ping timeout: 260 seconds). 02:43:34 -!- nisstyre has joined. 02:56:45 -!- carado has quit (Ping timeout: 252 seconds). 02:58:13 http://discontinuity.info/~pkhuong/futures/ of course 03:30:38 -!- oerjan has quit (Quit: leaving). 04:11:51 "Horny Ghost Of Osama Bin Laden : Rise Of The Ghost and over one million other books are available for Amazon Kindle. [Learn more]" 04:21:56 -!- ruddy has quit (Remote host closed the connection). 04:29:57 note to self: when someone asks me what an applicative functor is i have to tell them "they're like halfway between boxes and burritos" 04:31:49 https://twitter.com/bos31337/status/402212508187897856 04:34:29 fungot has a twitter account? 04:34:29 shachaf: why no pointers? me scared by pointer fnord n' stuff? 04:35:04 fungot: are you a three-star programmer 04:35:04 kmc: i wish i were a fan of the fnord and passing it to number-string with a radix of 8 to just generate a simple html webpage. 04:35:13 how often are you asked what an applicative functor is 04:35:16 fungot: what do you think of http://kingjamesprogramming.tumblr.com/ 04:35:16 kmc: you are, 6 instructions. i figured that 04:35:30 fungot: ya got me 04:35:30 kmc: do you think the extension was? just some random ideas and the thought alone makes me want to kill someone. i'll make up something 04:38:35 fungot: how many instructions am i 04:38:35 shachaf: although really all programming concepts out there in the begin clause of define-structure then? ;p it might make sense 04:38:45 fungot don't make sense 04:38:45 shachaf: there was a major transition to 32-bit architectures in all sorts of things 04:39:10 fungot: 32-bit addresses aren't enough for kmc 04:39:10 shachaf: in scheme?' 04:40:50 fungot: you're the seriously best bot 04:40:51 shachaf: zomg repeat!! but that low-level stuff frightens and confuses me, so to have binary data combined with gc'ed data i'd have to special-case literals; you treat them as a tad) n 04:40:56 fungot: you're the seriously best bot 04:41:10 last time i'm taking directions from a bot 04:41:51 ah, to be young again, and also a robot 04:43:41 http://www.theonion.com/articles/ah-to-be-young-rich-white-male-collegeeducated-str,34320/ 04:45:52 haha 04:47:09 -!- coppro|nospoiler has changed nick to coppro. 04:47:19 coppro|spoiled 04:47:26 nope 04:47:28 no spoilers! 04:47:54 brian dies 04:49:41 kmc: wow is this 04:49:50 markov chains from sicp and the king james bible 04:51:15 ah. yes 04:51:28 aka "the description in the header" 04:52:40 what it says on the tin 05:13:08 -!- nisstyre has quit (Quit: Leaving). 05:29:15 -!- nisstyre has joined. 05:48:28 -!- nisstyre has quit (Quit: Leaving). 05:49:10 -!- nisstyre has joined. 06:08:37 -!- Sprocklem has quit (Ping timeout: 248 seconds). 06:24:40 -!- Slereah has joined. 07:06:03 -!- tertu has joined. 07:20:40 shachaf: It hasn't tweeted for a while, though. 07:20:52 (The script might be broken.) 07:39:55 -!- FreeFull has quit. 07:41:02 -!- L8D has quit (Ping timeout: 264 seconds). 07:49:53 "Date of publication nulldate; date of current version nulldate." 07:51:49 seems like you have the first and only version 07:59:20 Also it seems that in the acknowledgements footnote I've claimed that the "recognition experimenters" (rather than experiments) have been performed using computational resources from the Triton cluster. 07:59:29 I guess that means that I'm a program after all. 08:00:50 not a train? 08:01:50 am i a train 08:03:02 http://acko.net/blog/on-asmjs/ 08:04:10 nope nope nope 08:04:24 nope? 08:04:25 fuck that guy for his rant about how feminism is bullshit and what about the men: http://acko.net/blog/storms-and-teacups/ 08:04:36 also for his absurd LOOK AT ME web design which distracts from the content and melts my computer 08:04:37 Maybe some kind of a computer-simulated train. 08:04:39 in conclusion, nope 08:04:49 oh. didn't know. 08:04:53 fizzie: am I a computer dreaming i'm a train? or a train dreaming i'm a computer? 08:05:52 the exercises in model checking class did often involve trains and elevators 08:06:11 and the prof had a story about being hired by the italian government to prove that the trains wouldn't run into each other 08:06:15 hehe the first page of that hits like half my antifeminism bingo card. 08:06:19 i know right 08:06:35 i haven't been able to make it all the way through (which I guess means I have no right to criticize, according to the first section) 08:06:44 instead I open it, scroll to a random point, get intensely angry, close it 08:07:08 there's usually a way for humans to fuck up so that the trains run into each other, anyway, though 08:07:11 , isn't it 08:07:39 i think i've seen like one video of a head on train collision, but i might have imagiend int 08:07:48 head-on-train collision 08:07:52 those happen a lot on caltrain :/ 08:07:59 huh, really 08:08:06 i've mostly seen train-hits-incidental-vehicle 08:08:09 "ICE 3 high speed trains use electrochromatic glass panels between the passenger compartment and the driver's cabin. The standard mode is clear, and can be switched by the driver to frosted/translucent, mainly to conceal "unwanted sights" from passengers' view, for example in the case of (human) obstacles." 08:08:46 uh. 08:09:06 caltrain runs right through the center of a densely populated corridor and mostly at grade 08:09:13 so there are a lot of vehicle collisions but also a lot of suicides 08:11:24 We had an elevator exercise in the model checking class. 08:11:29 No trains that I can recall. 08:13:28 we were given a puzzle about how two trams could pass each other through a bridge that looks like -=-=- , i.e., three single track sections with two passing sections between them 08:13:35 based on some bridge in amsterdam supposedly 08:14:18 a protocol for the trams to follow which never results in them getting stuck or backing up 08:14:30 i find it interesting that http://en.wikipedia.org/wiki/Gauntlet_track is used for some bridges rather than actual single tracking 08:15:02 Our class was based on http://spinroot.com/spin/ if I recall correctly. 08:15:11 ours too 08:15:16 the instructor was the main developer 08:15:48 PROMELA was kind of funny to write. 08:16:36 merging two tracks into two overlapping tracks is simpler & more reliable (no moving parts) than merging them onto one track with switches 08:17:05 fizzie: I don't remember much about it 08:17:32 I know it had finite state, and pattern-matching on message reception, and slightly odd syntax but nothing too awful iirc 08:17:49 Oh, I mostly remember the syntactical bits. 08:18:15 Parts of it looked very C-inspired, but then there were the oddities that really stood out with that background. 08:18:52 (Also "if ... fi" and "do ... od" control structures.) 08:19:00 oh i forgot about that 08:19:52 I don't have anything against if..fi or do..od, it's just that e.g. procedures were "normal" brace-delimited blocks. 08:20:12 ("Some of my best friends are if..fi's and do..od's.") 08:34:51 https://dl.dropboxusercontent.com/u/76028872/kuusipalaa.png 08:35:57 what about "the spruce is on fire" 08:36:02 is that not valid :'( 08:36:10 oh, wait 08:36:12 that's the top one 08:37:38 we don't need no water let the motherfucker burn 08:44:07 that's a lot of definitions for one phrase 08:44:16 -!- shachaf has quit (Ping timeout: 264 seconds). 08:45:00 -!- shachaf has joined. 08:58:35 http://www.youtube.com/watch?v=796bHaAtlkE#t=1m hth 09:05:47 I happened to write an explanation of that to someone who asked, might as well paste it here: The words for spruce and six happen to be the same. I have no idea why. “To return” is “palata” and “to burn” is “palaa”; “I return” is “palaan” and “I burn” is “palan”. The rules of inflection just happen to make both “(it) returns” and “(it) burns” “palaa”. The word for 09:05:49 “piece” is “pala”. The inflection for “(eleventy) pieces” just happens to be “palaa”. That’s not unlike “I have a rose” and “I rose up” in English. The word for “moon” is “kuu”. The inflection for “your moon” happens to be “kuusi”. 09:06:28 Seems sensible to me. 09:08:32 shachaf: So that’s what the fox says. 09:23:40 `? d-module 09:23:44 D-modules are just modules over the ring of differential operators. Taneb invented them. 09:24:27 `thanks taneb 09:24:28 Thanks, taneb. Thaneb. 09:29:12 ion: Wiktionary seems to indicate "kuusi" migth be both six and spruce just by accident; the number has the etymology "from Proto-Finnic *kuuci, from Proto-Finno-Ugric *kutte", while the tree is "from Proto-Uralic *kuse, *kose or *kowse". 09:29:35 Yeah, i assumed it’s just by accident, but i didn’t know the etymology of either. 10:21:35 -!- nisstyre has quit (Quit: Leaving). 10:51:32 -!- nisstyre has joined. 11:18:12 -!- copumpkin has quit (Quit: My MacBook Pro has gone to sleep. ZZZzzz…). 11:22:08 Do you folks happen to know if there are good open-sores tools to annotate PDF files? 11:22:51 i was going to say "printer and a pen" but even printing from Linux is nigh-impossible so 11:24:14 fizzie: Xournal 11:28:02 kmc: I've in fact already printed the PDF, from Linux. 11:28:13 (But I'm supposed to return an annotated PDF.) 11:29:52 ion: I guess Xournal does something custom? The file I return needs to be something Adobe-compatible, I presume. 11:30:11 It lets you draw on the PDF and save it again. 11:30:16 Very useful with a wacom pad. 11:31:11 -!- nisstyre has quit (Ping timeout: 260 seconds). 11:32:16 From what I can tell from the manual, that would produce a PDF with scribblings on it, not a PDF with those specific annotation boxes. 11:38:12 Maybe I'll just rdesktop to the terminal server, it's supposed to have Adobe Acrobat X Pro on it. 11:38:56 Give Up And Use Windows 11:39:44 Yes. 11:40:13 Deewiant: Heh, there's a /C:\nppdf32Log\debuglog.txt file (as in, in the root directory) owned by root:root on kosh.org.aalto.fi. :p 11:41:18 Nice, who's been running firefox as root 11:41:52 Maybe it's been MATLAB instead. 11:44:57 Wow, this PDF renders quite horribly in rdesktop-Acrobat. 11:47:17 https://dl.dropboxusercontent.com/u/113389132/Misc/20131128-baseline.png that's some quality horizontal alignment there 11:49:06 vertikerning 11:51:22 http://www.youtube.com/watch?v=bew73APL7X4 wow hypnotizing 12:07:36 cool 12:10:51 -!- carado has joined. 12:21:00 fizzie: I thought that was from adobe's pdf reader plugin for firefox 12:21:49 Deewiant: I get it from MATLAB's help browser, but of course the help is a mess of HTML, so it might well use the same underlying components. 12:26:31 Ah, okay 12:31:33 -!- Nisstyre-laptop has joined. 12:36:53 -!- Nisstyre-laptop has quit (Ping timeout: 246 seconds). 12:37:12 -!- Sorella has quit (Disconnected by services). 12:37:27 -!- Sorella` has joined. 12:48:22 -!- yorick has joined. 13:08:58 -!- boily has joined. 13:09:07 -!- metasepia has joined. 14:01:46 -!- L8D has joined. 14:02:32 -!- muskrat has quit (Quit: Leaving). 14:18:16 -!- oerjan has joined. 14:21:31 `ello L8D 14:21:34 L8Dello 14:21:44 hellœrjan. 14:21:54 fungot has a twitter account? <-- pretty sure e used to have, but i think it stopped working. 14:21:54 oerjan: http://web.archive.org/ web/ fnord/ fnord? or where the number of arguments 14:22:16 quintopia: the ball was sweet and mushy, kinda like a rice crispies square... 14:22:21 fungot: it's nice of you to point to the archive version, but you really shouldn't apply the fnord substitution to it 14:22:21 oerjan: i haven't seen any ' fnord just yet. 14:22:43 fungot: you cannot see your own fnords? i guess that makes some sense. 14:22:43 oerjan: fnord? catch the wind and cut off its fnord? 14:22:58 fungot: i have this feeling you are just messing with me. 14:22:58 oerjan: the only motivation for the syntax 14:23:41 fungot: you are creepy. 14:23:41 boily: they shit out rice crispies" when you ask the question 14:23:43 boily: i have a certain urge to `addquote that. 14:23:55 (um, what you said just before.) 14:24:11 Well, technically, the account still works, the tweeting script just might not. 14:24:58 Maybe I should revive it. 14:25:11 fungot: How do you feel about getting back to the social twitosphere? 14:25:11 fizzie: fnord) if ( *cptr fnord *cptr fnord) check the next cell ( a total of n places in under n moves, moving only one place 14:25:12 `pastlog twitter\.com.*fungot 14:25:13 oerjan: ais523 can read it back in whenever it changes cons that list onto another list 14:25:43 No output. 14:25:57 `pastlog twitter\.com.*fungot 14:25:57 oerjan: and malice fnord. but i was talking about making a whole scheme 14:26:04 @tell ais523 could you read the twitting fungot back when the cons are changed? twh. 14:26:04 Consider it noted. 14:26:04 boily: that's the purpose. why write source code at all 14:26:11 2013-04-09.txt:01:51:08: http://twitter.com/fungot 14:26:25 fungot: uhm... like, you know, like, it's my job, genre tsé. 14:26:25 boily: maybe it's more: the public is saved from what it doesn't 14:26:59 fungot: indeed. I wouldn't want the public to start coding too much. too dangerous, imho. 14:26:59 boily: i'll bet the fact that nothing works properly on this computer so i can't count. 14:27:09 fizzie: what is the one twitter account fungot follows 14:27:09 oerjan: what were you talking about? what is the reindeer effect? odd :) 14:28:32 * oerjan just noticed that fungot mentioned rice crispies after boily did 14:28:32 oerjan: process 4 killed. there was this comment: fnord/ guile-ref/ fnord? here's not even the current editors. they know me. you've never seen the lectures myself, but i 14:29:00 the reindeer effect is when you drop a twitter account in order to latch onto rice crispies. 14:29:35 oerjan: It's probably my twitter account. 14:31:00 Yes, that is indeed the case. 14:32:53 fungot: latch? 14:32:54 boily: do you know the problem of namespace pollution problems.) ack! 14:33:36 fungot: I do know. as a certain bespectacled girl who wields blood would say, 不愉快です。 14:33:36 boily: gnu tend not to go in early for some project instead of eager... then you could shine lasers on them to make smart decisions or act out some kind of syntax is that just x. z) 14:34:48 wielding blood sounds creepy 14:34:50 fungot: am I able to make you trip onto some predetermined keywords? what are the gnu commandline options for that? poulet, orange, navet, melon, luffa, kiwi? 14:34:50 boily: mmm.... montreal smoked meat. :) why do you say it'd work particularly well on many modern windows-based platforms" 14:34:58 oerjan: it's a plot point. 14:35:10 fungot: yé! montréal smoked meat! 14:35:10 boily: ( " a gentle introduction to ml" is much harder than with anything else 14:35:28 fungot: indeed. ML is hardcore. those Haskell wussies don't know nothing. 14:37:22 it has a formal definition, which sadly only half exists because it's paywalled, iiuc. 14:37:47 ic. ow. tdh. 14:38:06 *tdnh 14:38:58 i live by the principle that information that isn't freely available doesn't really exist. 14:39:55 your explanation dh, even if ML by itself dnh. 14:40:24 i think they recently released an older version of the definition. 14:41:34 imo, paywalls are there to protect a lack of information. case in point, about the only thriving mainstream news source in Québec switched to a tablet version. 14:42:03 (well. printed and or textual. we're still stuck with TVA and suchlike when turning on a television.) 14:43:05 i wonder if the released version is from before they switched to the value restriction. 14:44:18 (ML used to have a complicated kind of purity annotation on type variables.) 14:45:19 but then someone realized (or borrowed from ocaml) that you can just restrict generalization of types to actual functions given syntactically. 14:51:07 " gnu tend not to go in early for some project instead of eager... then you could shine lasers on them to make smart decisions" fungot explains how to make the GNU project work. 14:51:08 fizzie: 30 meg or so. i take it back a few times when i get h. in case you hadn't noticed, i was 14:53:26 the whole GNU project fits in 30 MB, and to work need to be shined upon by lasers. 14:59:31 (I strongly suspect every GNU application is only emacs in disguise.) 15:11:37 -!- MindlessDrone has joined. 15:31:46 -!- muskrat has joined. 15:32:08 -!- Phantom_Hoover has joined. 15:32:31 -!- muskrat has quit (Client Quit). 15:40:20 -!- Sprocklem has joined. 15:46:59 http://acko.net/blog/on-asmjs/ <-- so, this guy has to be blind, right? 15:54:08 I need someone with a brain 15:54:29 for what? 15:54:34 3SAT 15:55:13 A term in conjunctive normal form is only satisfable if every subterm is? 15:55:28 *satisfiable 15:55:57 ok conjuctive is where the and's are outermost, right? 15:56:01 Because all subterms are AND-ed 15:56:06 oerjan: Yes 15:56:23 All Subterms consist only of OR-ed variables and a Term consists of AND-ed subterms 15:56:28 well then yes, that's a requirement. 15:56:33 Ok 15:56:49 Every subterm esentially describes a "non-solution" 15:56:54 (of course if it were also sufficient, things would be very simply) 15:57:05 *simple 15:57:06 * boily recalls his «Circuits logiques» classes, with Karnaugh tables and smokeless chips... 15:57:35 (a v !b) ^ (a v b v c) tells us, that (0, 1, x) and (0, 0, 0) can't be solutions 15:57:41 (x = don't care) 15:58:28 yep 15:59:22 you can just put a big "not" around the whole and apply deMorgan. 15:59:41 Right. 16:00:58 Due to that, the complexity of determining if the whole term is satisfiable is linear in the number of "don't care"s 16:01:22 um wait what 16:01:28 this is NP-complete, you know. 16:01:45 -!- augur has quit (Ping timeout: 272 seconds). 16:02:06 all known algorithms are exponential. 16:02:20 Well 16:02:41 Consider exact 3-SAT with 6 Variables 16:02:53 ok 16:02:58 wait 16:03:35 I'm aware that it must be exponential ;) 16:04:15 good, good 16:04:34 (if you can _prove_ it, you have a million dollars hth) 16:04:50 It's exponential in the number of "don't care"s 16:05:03 sounds more likely 16:06:24 In theory 16:09:12 -!- Sprocklem has quit (Ping timeout: 265 seconds). 16:12:09 I think there should be an algorithm that is exponential in number of subterms 16:12:18 like uhm 16:12:30 8^m where m is the Numbers of Terms for 3-SAT 16:15:17 7^m actually for 3-SAT 16:16:06 because a single subterm is satisfiable in (2^n)-1 ways 16:18:37 -!- function has changed nick to trout. 16:21:35 -!- Phantom__Hoover has joined. 16:22:01 well you can have one that is exponential in number of variables, which is no more than 3*subterms 16:22:07 -!- Phantom_Hoover has quit (Ping timeout: 246 seconds). 16:35:37 -!- Phantom_Hoover has joined. 16:36:53 -!- Phantom__Hoover has quit (Ping timeout: 248 seconds). 17:00:41 -!- oerjan has quit (Quit: leaving). 17:36:31 -!- FreeFull has joined. 17:42:47 -!- Phantom_Hoover has quit (Ping timeout: 246 seconds). 18:06:25 back from lunch. the accentèd soup was good, but the place was cold. 18:34:46 what does "kuusi palaa" mean? 18:35:16 All those things listed in the image? 18:36:06 Also see ion's comprehensive explanation. 18:36:25 Huh, "This account's public links are generating too much traffic and have been temporarily disabled!" 18:36:50 -!- yiyus has joined. 18:38:21 oh, it already got linked here, i see 18:40:35 There's a "joke" related to translating "voi äiti, joulukuusi palaa!" to Swedish in an intententionally wrong way; it goes something like "smör mamma, julsex kommer tillbaka!" 18:42:15 -!- olsner has joined. 18:42:59 julsex? is that some kind of twisted Santa Fetish? 18:43:50 That would be YuleSex 18:44:05 Them Swedes collapse en:six and en:sex, probably for some good reason. 18:44:25 http://www.graficaobscura.com/future/futnotes.html 18:44:27 (Also itself a subject of much giggling in primary school language lessons.) 18:45:02 -!- Sprocklem has joined. 18:45:12 i,i sextuplets 18:47:34 Slereah: “try indenting from right to left” ??? 18:47:57 A sextet too, I guess. 18:48:43 I doubt there is any good reason for using sex for six 18:50:39 What about the sex 18:50:42 Pretty good reason 18:50:53 boily : ANARCHISTS 18:52:20 anarchists are a strangely structured bunch... 18:53:16 Except : "Structured programming = slow. " 18:53:23 THEY HATE STRUCTURE :o 18:53:44 ↑ cf. strangely. 18:54:42 Though I'd love to see a modern OS programmed entirely efficiently 18:54:53 Although I'm pretty sure it would cost a million dollars 18:54:56 How does that work? "I just want to code, I don't want to abide by any structure. It slows me down." 18:55:44 I guess they want to code efficiently instead of maintainably 18:55:57 Which is a nice idea in theory 18:56:10 But I wouldn't want to be the guy who has to pick up the project later on 18:56:46 if I apply their principles, all I'll achieve is unusable-code-that-only-works-on-my-machine-today. 18:56:47 so, not a nice idea in theory. 18:57:05 boily : But boy will it run smoothly! 18:57:22 until you try to install something and it messes everything up. 18:57:30 usability means more than 'speed'. 18:57:37 Such are the risks! 18:58:31 -!- MindlessDrone has quit (Quit: MindlessDrone). 18:58:38 but there's no advantage. 18:59:00 Well, speed I guess 18:59:22 If you run it for one thing on a dedicated machine, should be fine 18:59:33 -!- tswett has joined. 18:59:43 But if you're running it for "one thing" you might as well just put that one thing on the hardware. 18:59:46 Slereah: that I can't deny. but it's like doing lines of code as if doing lines of coke. instant gratification, but empty. 18:59:46 ABOUT LINEAR TYPING. 19:00:02 `ello tswett 19:00:04 Hello, tswett ! 19:00:06 Hardware is expensive though! 19:00:12 `ey there. 19:00:13 beuh. who changed `ello? 19:00:13 ​/home/hackbot/hackbot.hg/multibot_cmds/lib/limits: line 5: exec: ey: not found 19:00:21 boily : You say that like it's a bad thing 19:00:22 well i guess we can't buy a computer then 19:00:31 `cat /bin/ello 19:00:32 cat: /bin/ello: No such file or directory 19:00:37 `which ello 19:00:38 ​/hackenv/bin/ello 19:00:39 A computer is probably cheaper than building a dedicated CPU 19:00:44 `paste /hackenv/bin/ello 19:00:47 http://codu.org/projects/hackbot/fshg/index.cgi/raw-file/tip//hackenv/bin/ello 19:00:56 `ello tsetto 19:00:56 by 'on hardware' i meant just putting it on a regular cpu, but without an os 19:00:58 tsettello 19:01:01 w 19:01:17 Isn't that still software? 19:01:17 `ello tswett 19:01:19 tswettello 19:01:24 Software doesn't mean "on an OS" 19:01:28 Well, then. 19:01:46 I guess you can put it in a static memory, if that counts? 19:01:55 Yeah, but doesn't "on software" mean "on an OS"? 19:02:08 software means all that can't be physically kicked around. 19:03:11 So, right. ABOUT LINEAR TYPING. You can make a linear type system out of Haskell's type system just by adding one operator, ~, the dual operator. a with b becomes ~(Either ~a ~b), a par b becomes ~(~a, ~b), bottom becomes ~(), and so on. 19:03:56 And this raises the question, what does ~ mean? It acts suspiciously like (-> e), where "e" is some universally quantified type variable. 19:04:43 But where do you put the quantifiers? 19:05:01 on the left 19:05:25 Oh, there's my problem. I was putting the quantifiers in Zimbabwe. 19:05:45 zimbabwe is to the left of some places, to be fair. 19:05:58 @tell oerjan can I learn Zimbabwe's quantification? 19:05:58 Consider it noted. 19:06:13 Let me see whether or not Zimbabwe is to my left right now. 19:06:15 I'm guessing it is. 19:06:44 tswett: what are your current approximate coördinates? 19:07:08 42.9612° N, 85.6557° W 19:08:00 Accurate to within a few tenths of a degree. 19:09:32 Where was I. Oh yeah. 19:10:00 Really, all of linear logic's production rules can be translated directly into Haskell, practically unchanged! 19:10:04 I just don't know what will come out. 19:10:06 boily: i'm sorry it was mushy. they were very crunchy at the beginning of the month. 19:12:15 quintopia: don't be sorry, I quite enjoyed it. the sweetness was surprising, though. 19:12:45 tswett: thanks. for scientific purposes, could you provide me with you body weigh? 19:13:52 boily: 185 lbs. 19:13:59 Probably accurate to within 5 lbs. 19:14:24 that's much appreciated. and strangely precise. I am disturbed; this doesn't happen often... 19:15:01 You don't usually get body weights accurate to within 5 lbs? 19:15:12 also have people here been enjoying the autogenerated hackernews headlines? they use the same technique as fungot afaict 19:15:12 quintopia: call it " fn" is ( a f)) ( map fnord lst) 19:15:48 So, gimme a few minutes, lemme see how the cut rule translates. 19:15:49 tswett: I get frivolous answers, viz. megaluns. 19:15:58 `? megalun 19:16:00 megalun is a chain of a million SCSI devices. FreeFull weighs 482 of them. 19:16:11 boily: do you have my coordinates and body weigh? they are less fluctual now 19:16:11 I see. 19:16:27 Oh dang, I never figured out whether or not Zimbabwe is to my left. 19:16:51 quintopia: I don't have your weigh. the coordinates were properly appröximated according to your last known address. 19:17:15 Yep, I'm pretty sure I would describe Zimbabwe as being on my left. 19:17:20 righto 19:17:23 ahm 19:17:26 -!- muskrat has joined. 19:17:31 -!- Sgeo has quit (Read error: Connection reset by peer). 19:17:41 probably near 220lbs? 19:18:15 that'll do. 19:18:30 tswett: michigan? zimbabwe is most definitely to your left. 19:18:49 Depends on which way I'm facing. 19:19:45 zimbabwe's leftness is orthogonal to your orientation. 19:19:49 apparently my desk points zimbabwe 19:20:10 zimbabwards 19:20:14 No, I disagree. Zimbabwe's leftness is highly dependent on my orientation. 19:20:21 -!- Sprocklem has quit (Ping timeout: 272 seconds). 19:21:51 `run echo "olsner's desk points zimbabwards. it is highly dependent on tswett's michiganic orientation." >wisdom/zimbabwe 19:21:55 No output. 19:22:02 -!- Sprocklem has joined. 19:22:05 boily: it would only be orthogonal if michigan was antipodal to zimbabwe 19:22:36 -!- Sgeo has joined. 19:25:25 Sgello. 19:25:56 quintopia: sadly, I concur that is not the case. 19:26:00 I think sgello is a kind of a (virtual?) string instrument? 19:27:01 fizziello 19:27:59 * boily strokes Sgeo with a sbow 19:29:31 i'm sure that's exactly what sgeo was hoping for waking up today 19:29:40 "i need to get myself stroked today" 19:30:56 I'm hoping for a computer that doesn't keep struggling with its graphics driver 19:31:18 Also hoping not to be stroked by something that I don't even know what it is 19:31:57 Looked it up. Apparently, boily is trying to run me over with an SUV? 19:32:52 huh? 19:33:03 http://www.urbandictionary.com/define.php?term=SBOW 19:33:11 boily: Don't try to play innocent, we know what you did. 19:33:57 bin torieux. there's always that chance that unknown words I type already mean something. I guess that just happened, eh? 19:34:17 fizzie: I claim not-guilty. 19:35:00 besides, how would one realistically stroke somebody else with an SUV? 19:41:11 By driving over them, presumably. 19:42:15 I deny everything. also, Sgeo is a wall. 19:42:54 Some people are walls, other people are wextras, it's just a fact of life. 19:46:04 boily: that's why you should type randomly-chosen 256-bit words 19:48:39 -!- ais523 has joined. 19:50:05 shachaf: I 4ediGUdynGUJfQr0rGb582AvRrw6IBZX with you. 19:52:16 ew 19:52:28 that's disgusting 19:52:58 So the cut rule ends up typed like this: 19:53:01 (d -> (b -> t4, g -> t3) -> t) -> ((d', b) -> (g' -> t2) -> t4) -> (d, d') -> (g -> t3, g' -> t2) -> t 19:53:26 Where all those ts are the universally quantified variables. 20:02:55 Each one seems to correspond to a normal variable. t3 obviously corresponds to g, and t2 to g'. Then t4 seems to correspond to b, and t must correspond to d. And that leaves nothing to correspond to d'. 20:06:02 -!- copumpkin has joined. 20:11:31 what cut rule thing? 20:12:01 one cut to rule them all, and in the scissors snip them... 20:19:25 maybe cut elimination should be called stitching. 20:20:30 chellopumpkin. int-hello. 20:24:45 -!- tswett has quit (Ping timeout: 250 seconds). 20:25:10 -!- jochem88 has joined. 20:25:30 `relcome jochem88 20:25:33 ​jochem88: Welcome to the international hub for esoteric programming language design and deployment! For more information, check out our wiki: . (For the other kind of esoterica, try #esoteric on irc.dal.net.) 20:26:06 -!- tswett has joined. 20:26:17 Whoever asked, the cut rule is from here: http://plato.stanford.edu/entries/logic-linear/ 20:26:51 -!- augur has joined. 20:29:14 -!- jochem88 has quit (Client Quit). 20:29:58 -!- jm__ has joined. 20:34:31 http://www.techwyse.com/blog/wp-content/uploads/2010/04/robots-txt1.gif 20:35:51 -!- elliott has quit (Ping timeout: 260 seconds). 20:36:54 -!- yiyus has quit (Read error: Connection reset by peer). 20:41:15 -!- Sprocklem has quit (Ping timeout: 245 seconds). 20:42:40 -!- elliott_ has joined. 20:43:21 relcome jut might be a bit too colourful 20:43:25 just* 20:43:33 -!- ais523 has quit (Read error: Operation timed out). 20:43:35 -!- Bike_ has joined. 20:43:42 it is not colourful enough 20:43:55 -!- Bike has quit (Ping timeout: 246 seconds). 20:44:21 -!- ais523 has joined. 20:44:28 -!- Bike_ has changed nick to Bike. 20:45:29 /set hide_colors on 20:50:49 -!- Bike has quit (Ping timeout: 252 seconds). 21:02:35 -!- jm__ has quit (Ping timeout: 272 seconds). 21:12:01 Grumble murgle burgle, that computer with the noisy broken-sounding fan, into which I put a new nice and silent fan, has made the new fan also noisy and broken-sounding, in just a month or three. Must be some kind of a curse. 21:13:23 `rwelcome FireFly 21:13:25 ​FireFly: Welcome to the international hub for esoteric programming language design and deployment! For more information, check out our wiki: . (For the other kind of esoterica, try #esoteric on irc.dal.net.) 21:13:32 Hmm, those are the same? 21:13:37 fizzie: did you cast the chicken bones right? 21:13:52 Awful. 21:13:53 `run ls -l bin/r*me 21:13:55 lrwxrwxrwx 1 5000 0 8 Oct 28 14:16 bin/relcome -> rwelcome \ -rwxr-xr-x 1 5000 0 12 Sep 25 13:06 bin/resume \ -rwxr-xr-x 1 5000 0 35 Oct 19 20:40 bin/rwelcome 21:13:55 I think someone decided the other one broke too much stuff 21:14:03 `resume 21:14:05 rsum 21:14:11 `stop 21:14:12 ​/home/hackbot/hackbot.hg/multibot_cmds/lib/limits: line 5: exec: stop: not found 21:14:16 `run cat bin/resume 21:14:17 echo rsum 21:14:43 `run echo 'echo resume' > bin/rèsumè; chmod +x bin/rèsumè 21:14:47 No output. 21:18:34 l'horreur. 21:21:47 What! The non-word-based rainbow welcome is no more? 21:22:15 Bah. I guess there's no accounting for taste. 21:22:16 fizzie: indeed. it was squished away by heretics. 21:22:21 ==fizzie 21:23:28 > fizzie == fizzie 21:23:29 Not in scope: `fizzie'Not in scope: `fizzie' 21:23:35 -!- Bike has joined. 21:32:09 -!- boily has quit (Quit: PSYCHOSOMATIC CHICKEN!). 21:32:10 -!- metasepia has quit (Remote host closed the connection). 21:33:19 -!- Sprocklem has joined. 21:34:18 -!- ais523 has quit. 21:36:17 -!- Bike has quit (Ping timeout: 252 seconds). 21:38:04 -!- Bike has joined. 21:53:10 -!- oerjan has joined. 21:54:34 -!- elliott_ has changed nick to elliott. 22:17:01 -!- Bike has quit (Ping timeout: 246 seconds). 22:18:57 -!- Bike has joined. 22:26:11 -!- Sprocklem has quit (Ping timeout: 272 seconds). 22:32:01 @messages-good 22:32:01 boily said 3h 26m 3s ago: can I learn Zimbabwe's quantification? 22:35:24 -!- carado has quit (Ping timeout: 252 seconds). 22:35:43 @tell boily the zimbabwean uncertainty principle means you cannot quantify their bmp precisely without causing runaway inflation. 22:35:43 Consider it noted. 22:40:51 There's a "joke" related to translating "voi äiti, joulukuusi palaa!" to Swedish [...] <-- google translate doesn't seem to know that meaning of "voi" 22:41:39 oh it knows it the other way around. 22:43:30 oh hm it's listed in the footnotes if you try "voi" alone. 22:48:47 @tell boily beuh. who changed `ello? <-- i think you got hit by the tab expansion space issue. 22:48:48 Consider it noted. 22:48:53 `ello tswett 22:48:55 Hello, tswett ! 22:48:57 `ello tswett 22:48:58 tswettello 22:49:14 `ello oerjan 22:49:16 helloerjan 22:49:35 `ello оerjan 22:49:37 ​оerjanello 22:49:49 v. flexible command 22:50:00 `unidecode оerjan 22:50:02 ​[U+043E CYRILLIC SMALL LETTER O] [U+0065 LATIN SMALL LETTER E] [U+0072 LATIN SMALL LETTER R] [U+006A LATIN SMALL LETTER J] [U+0061 LATIN SMALL LETTER A] [U+006E LATIN SMALL LETTER N] 22:50:06 yes. 22:52:23 -!- Sorella` has changed nick to Sorella. 22:52:24 -!- Sorella has quit (Changing host). 22:52:25 -!- Sorella has joined. 22:53:23 `unencode [U+043E CYRILLIC SMALL LETTER O] 22:53:24 ​/home/hackbot/hackbot.hg/multibot_cmds/lib/limits: line 5: exec: unencode: not found 22:53:27 er 22:53:28 `uniencode [U+043E CYRILLIC SMALL LETTER O] 22:53:29 ​/home/hackbot/hackbot.hg/multibot_cmds/lib/limits: line 5: exec: uniencode: not found 22:53:37 h8rego 22:55:11 `unicode CYRILLIC SMALL LETTER O 22:55:13 ​о 22:57:15 SHЕЕSH 23:01:29 `unicode A 23:01:31 Unknown character. 23:01:47 `unicode PILE OF POO 23:01:49 Unknown character. 23:02:46 you're an unkown character 23:03:00 * shachaf looks at the logs 23:03:07 oh 23:03:55 what about the logs. 23:04:06 They have piled up 23:08:31 Hmm, those are the same? <-- some people overwrote the old relcome with rwelcome. 23:09:11 oh it's actually a link. 23:09:27 some bad people imo 23:09:57 h8rs 23:10:08 i vaguely agree. 23:11:03 `resume 23:11:05 rsum 23:11:12 `cat bin/resume 23:11:14 echo rsum 23:11:37 `run echo "echo résumé" >bin/resume 23:11:40 No output. 23:11:45 `resume 23:11:46 résumé 23:12:23 ? 23:12:28 What did you change? 23:12:35 shachaf: it was in latin-1 23:12:41 now it's utf-8 23:12:42 !!!!!!! 23:12:46 h8rs 23:12:53 You know the old adage: when you résumé, you make a rés out of both you and mé. 23:13:06 `rèsumè 23:13:07 resume 23:13:17 * oerjan checks fizzie's line encoding. you pass. 23:13:47 I not only pass, I pass-te. (From your line.) 23:13:57 `unidecode rèsumè 23:13:59 ​[U+0072 LATIN SMALL LETTER R] [U+00E8 LATIN SMALL LETTER E WITH GRAVE] [U+0073 LATIN SMALL LETTER S] [U+0075 LATIN SMALL LETTER U] [U+006D LATIN SMALL LETTER M] [U+00E8 LATIN SMALL LETTER E WITH GRAVE] 23:14:00 fan-cy 23:14:13 shachaf: you appear to possess a grave disorder 23:14:21 è.é 23:15:33 fizzie also has it, it seems to be turning acute 23:15:36 why does unicode require you to know the code point 23:15:39 ♪ when they resume the résumé ♪ 23:15:53 oerjan: but is it turning complete? 23:15:59 that's all we care about in this channel 23:16:26 hm we have defined turning tarpits, but have we defined turning completeness 23:16:47 p. sure 2π is turning complete 23:17:33 ok 23:18:03 itym (4/3)pau right? 23:18:12 * shachaf is desperately trying to stop pronouncing the j in oerjan like the j in jack. 23:18:35 "oerjack" doesn't sound too shabby. Maybe a bit piratey. 23:18:59 ørjack the ørrible 23:19:18 @ørr 23:19:18 Maybe you meant: yarr arr 23:19:28 lambdabot: you disappoint. 23:19:31 that's the worst thing 23:19:59 is there any actual difference between the commands? 23:20:02 ϕrjan. 23:20:04 Yes. 23:20:10 They have two different lists of responses. 23:20:26 (Or did in the past. Maybe in the new age of mokusism that's different.) 23:20:31 arright. 23:20:44 @yarrjn 23:20:44 Splice the Mainbrace! 23:21:19 people who play music loudly are the worst people 23:22:55 shachaf: no, i would say people who do carpentry are just as bad. 23:23:07 -!- Phantom_Hoover has joined. 23:23:13 @wn mainbrace 23:23:14 No match for "mainbrace". 23:23:29 @wn vambrace 23:23:30 *** "vambrace" wn "WordNet (r) 3.0 (2006)" 23:23:30 vambrace 23:23:30 n 1: cannon of plate armor protecting the forearm [syn: 23:23:31 {vambrace}, {lower cannon}] 23:23:32 Close enough. 23:24:05 https://en.wikipedia.org/wiki/Splice_the_mainbrace 23:25:49 Oh, it has nothing to do with mainframes. *disappoint* 23:26:11 well it was more interesting than i expected. 23:29:40 -!- Taneb has joined. 23:30:57 Aaaaaaaaah 23:31:09 I've been pressganged into presenting a talk on esolangs 23:31:45 how big of an audience are we talking 23:32:43 Taneb: well it probably beats joining the navy. 23:33:17 -!- conehead has quit (Quit: Connection closed for inactivity). 23:34:16 nooodl, around 6 23:35:02 cirka sex 23:37:30 (disclaimer: both of my previous messages make slightly more sense if you read the logs.) 23:38:11 But only slightly. 23:38:41 that was implied. 23:39:23 It was also explied. 23:40:09 @wn exply 23:40:10 No match for "exply". 23:40:19 lambdabot: your dictionary is useless 23:41:34 Ex-ply, the euphemism for used toilet paper. 23:42:43 is there an app for identifying a tune i whistle? 23:43:50 i vaguely recall hearing one mentioned, although in the context of it not really working. 23:43:58 -!- copumpkin has quit (Quit: My MacBook Pro has gone to sleep. ZZZzzz…). 23:44:16 -!- augur_ has joined. 23:44:36 * oerjan assumes quintopia can google himself. 23:45:01 SoundHound claims to do it, IIRC. 23:45:12 ah i've heard of that 23:46:00 oerjan: i was asking because my googling had failed to turn it up 23:46:13 -!- augur has quit (Ping timeout: 248 seconds). 23:46:21 "Can SoundHound work if I whistle instead of singing or humming? 23:46:23 SoundHound has been designed to work even when you whistle! But please note that the microphones on most mobile devices, including iPhones and Android phones, are very sensitive to whistling. To make sure your whistled search gets the best results, try not to whistle too loud or too close to the microphone: hold the phone at arm's length while whistling, and whistle at only a moderate volume ... 23:46:30 ... so that the SoundHound volume bar does not fill up all the way." 23:46:36 quintopia: yes, i'm just logically deducing that i don't need to do it. 23:46:45 From what I recall, it does do humming better. 23:47:26 How do I even do a talk on esolangs 23:48:19 Musipedia also does whistling, I believe. 23:48:30 hm i am sure some finn here did some. not sure if it was fizzie or oklopol. 23:48:53 or maybe even another finn. 23:48:56 `? finland 23:48:59 Finland is a European country. There are two people in Finland, and at least nine of them are in this channel. Corun drives the bus. 23:49:07 "You may sing or whistle (the latter might work better)" 23:49:11 i guess that covers all, then. 23:49:53 the big question is, does it work for people who cannot carry a tune. 23:49:59 atehwa did some kind of series at the University of Helsinki. 23:51:14 oerjan: Musipedia also has a keyboard if you can laboriously pick notes. 23:52:30 i mean tone deaf, i guess. 23:52:51 like, unable to tell whether they have selected the right notes. 23:53:07 Shazam (the other big name for "mainstream" music search) explicitly does not do singing, I think. 23:53:56 oerjan: It has a search-by-tapping-a-rhythm option for them. 23:55:02 (Also a mode where you just say if consecutive notes are higher or lower than their predecessors.) 23:56:20 `? poland 23:56:22 poland? ¯\(°​_o)/¯ 23:56:33 -!- Phantom__Hoover has joined. 23:56:41 Phantom__Hoover, ... 23:56:55 -!- Phantom_Hoover has quit (Ping timeout: 260 seconds). 23:57:35 hellp 23:58:25 Phantom__Hoover, ... 23:59:39 `ello Oerjan 23:59:41 hellOerjan 23:59:52 `ello Logan 23:59:54 Lellogan 2013-11-29: 00:00:07 Qué. 00:01:05 `echo "Połąnd is a European country. Its population consists of two main ethnicities, the North Połes and the South Połes." >wisdom/poland 00:01:07 ​"Połąnd is a European country. Its population consists of two main ethnicities, the North Połes and the South Połes." >wisdom/poland 00:01:11 oops 00:01:15 `run echo "Połąnd is a European country. Its population consists of two main ethnicities, the North Połes and the South Połes." >wisdom/poland 00:01:18 No output. 00:01:30 Hey! You didn't use single quotation marks! 00:01:49 And? 00:02:00 `? poland 00:02:03 Połąnd is a European country. Its population consists of two main ethnicities, the North Połes and the South Połes. 00:02:03 `run echo 'Aren't single quotes awesome? They can't be beat!' 00:02:05 Arent single quotes awesome? They cant be beat! 00:02:14 i think no harm was done. 00:03:06 hm i see a misspelling 00:03:19 This reminds me of a command I ran once. Lemme see. 00:03:24 `run echo "Połąńd is a European country. Its population consists of two main ethnicities, the North Połes and the South Połes." >wisdom/poland 00:03:28 No output. 00:05:05 You mean Półęś? 00:05:25 I'm pretty sure it had either "'"'"'" or '"'"'"' in it. 00:05:55 (The correct way to type either of those is to hold down the apostrophe key for a while, while being very fast and precise with the shift key.) 00:07:14 `run echo '"'"'"'"' "'"'"'"'" 00:07:15 ​"'" '"' 00:07:30 Neither seems to make too much sense, but 'foo'"'"'bar' is common-ish. 00:07:34 One of those must have been it. Lemme see. 00:08:02 Maybe in some two-levels case. 00:09:14 `run python -c 'print repr(repr(repr(repr(repr('"')))))' 00:09:15 bash: -c: line 0: unexpected EOF while looking for matching `"' \ bash: -c: line 1: syntax error: unexpected end of file 00:09:21 erm 00:09:49 `run python -c "print repr(repr(repr(repr(repr('"\""')))))" 00:09:50 ​'\'\\\'\\\\\\\'\\\\\\\\\\\\\\\'"\\\\\\\\\\\\\\\'\\\\\\\'\\\'\'' 00:10:03 hmph 00:10:18 right you cannot mix both 00:10:23 or can you 00:10:34 `run python -c print "a" 'ha' 00:10:35 No output. 00:10:42 wat 00:10:50 Something along these lines: alias man="MANPAGER='col -b | view -c'"'"'"'set ft=man nomod nolist nonu'"'"'"' -' man" 00:10:57 `run echo alias man="MANPAGER='col -b | view -c'"'"'"'set ft=man nomod nolist nonu'"'"'"' -' man" 00:10:57 `run python -c 'print "a" '"'ha'" 00:10:58 alias man=MANPAGER='col -b | view -c'"'set ft=man nomod nolist nonu'"' -' man 00:10:59 aha 00:11:55 Yes, that must have been it. 00:13:01 The argument to view -c has to be enclosed in quotes. But since I'm putting that into MANPAGER, those quotes have to be quoted. But since I'm making that an alias, *those* quotes have to be quoted. 00:14:22 Thing is, that's a silly way of doing things. 00:14:51 `run echo alias man="MANPAGER=\"col -b | view -c 'set ft=man nomod nolist nonu' -\" man" 00:14:53 alias man=MANPAGER="col -b | view -c 'set ft=man nomod nolist nonu' -" man 00:16:50 -!- Phantom_Hoover has joined. 00:16:57 -!- Phantom__Hoover has quit (Ping timeout: 240 seconds). 00:20:27 -!- Bike has quit (Ping timeout: 252 seconds). 00:22:08 -!- Bike has joined. 00:27:14 -!- Bike has quit (Ping timeout: 264 seconds). 00:28:25 -!- Bike has joined. 00:39:39 -!- Bike_ has joined. 00:41:15 -!- Bike has quit (Ping timeout: 260 seconds). 00:42:00 -!- Taneb has quit (Quit: Leaving). 00:43:58 -!- Bike_ has changed nick to Bike. 00:45:35 I wonder if there are any implementations of a Unix-like operating system that just run as applications. 00:50:04 does cygwin count? 00:50:46 Mm... I'd say not really. 00:53:22 User Mode Linux? 00:53:38 `echo hi tswett 00:53:40 hi tswett 01:20:52 `echo Hi tswett. Hwett. 01:20:53 Hi tswett. Hwett. 01:21:50 -!- Sorella has quit (Remote host closed the connection). 01:22:04 Hihkq. 01:22:15 -!- Phantom_Hoover has quit (Ping timeout: 272 seconds). 01:24:32 -!- Phantom_Hoover has joined. 01:25:10 -!- Sorella has joined. 01:25:31 -!- Sorella has quit (Changing host). 01:25:31 -!- Sorella has joined. 02:11:01 -!- yorick has quit (Remote host closed the connection). 02:21:02 -!- Phantom__Hoover has joined. 02:21:25 -!- Phantom_Hoover has quit (Ping timeout: 248 seconds). 02:43:29 -!- Phantom_Hoover has joined. 02:44:36 -!- Phantom__Hoover has quit (Ping timeout: 246 seconds). 02:51:30 -!- nisstyre has joined. 02:53:00 -!- nooodl has quit (Quit: Ik ga weg). 03:09:00 -!- Phantom_Hoover has quit (Read error: Connection reset by peer). 03:47:11 -!- tswett has quit (Ping timeout: 250 seconds). 04:05:37 -!- oerjan has quit (Quit: leaving). 04:06:17 -!- impomatic has quit (Ping timeout: 272 seconds). 05:20:16 -!- jm__ has joined. 05:38:47 -!- jm__ has quit (Ping timeout: 240 seconds). 06:04:36 -!- nisstyre has quit (Quit: Leaving). 06:17:13 -!- tertu has quit (Ping timeout: 246 seconds). 06:44:32 -!- nisstyre has joined. 07:31:43 -!- nisstyre has quit (Quit: Leaving). 07:33:03 -!- FreeFull has quit. 09:17:22 -!- Tod-Autojoined has joined. 09:18:43 -!- Sgeo_ has joined. 09:19:01 -!- Slereah_ has joined. 09:23:36 -!- MindlessDrone has joined. 09:26:56 -!- Sgeo has quit (*.net *.split). 09:26:56 -!- Slereah has quit (*.net *.split). 09:26:56 -!- TodPunk has quit (*.net *.split). 09:26:56 -!- hogeyui has quit (*.net *.split). 09:36:45 -!- hogeyui has joined. 09:41:01 -!- Tefaj has joined. 09:41:23 -!- Tefaj has quit (Changing host). 09:41:23 -!- Tefaj has joined. 09:41:26 -!- Tefaj has changed nick to Jafet. 10:15:09 "Spectrocable allows for an incredible speed of over 10^54000 bits per second! -- Spectrocable has the bandwidth to allow for the download of the entire Library of Congress in less than half a second, --" 10:15:36 I guess, given the first part, the second part is technically true, but it's kind of an understatement to call that "less than half a second". 10:16:16 (This is from some utter nonsense at http://www.cyborg.co/spectrocable/ -- there's the usual impossible compression method there, too.) 10:18:10 That cable sounds perfect for hifists. 10:18:31 “Speed: 1.295 x 10^53802 bits per second / 1.62 x 10^53801 bytes per second” 10:18:39 They’ll of course be able to hear the difference between the two. 10:19:47 The wireless version "allows for a speed of over 10^55000 bits per second! That, in terabits per second, is about 10^54900 terabits per second!" Yeah, I guess that's "about" right, I mean, it's off only by 88 or so orders of magnitude. 10:20:29 I guess when you're talking about completely ludicrous numbers, there's no particular reason to be consistent. 10:23:12 What I think is funny is that, as far as I can tell, there really was a presentation of these "revolutionary technologies" at some actual "serious" tech thing -- http://techweek.com/losangeles/ -> "click here to view the 2013 schedule" -> Thursday 2pm "making the Internet blazing fast". 10:23:55 (Given the other talks, I guess that it's not *so* out of place.) 10:25:53 -!- L8D has quit (Ping timeout: 246 seconds). 10:28:35 http://www.cyborg.co/shadow/ xD 10:29:01 It reminds me a lot of another equally impossible Finnish compression algorithm I've mentioned here too. 10:29:29 That, too, was just about to come to the market and revolutionize everything. 10:30:14 it actually claims to compress any file losslessly? 10:30:26 Then nothing happened, and now the guy behind it is doing "Drupal, Concrete5, eZ publish, jQuery, underscore, PhoneGap" at some web shop, which I guess is kind of sad maybe? 10:30:47 I don't think it's any more or less unbelievable than transfer speeds of 10^55000 bits per second. 10:45:18 -!- ais523_ has joined. 10:45:24 `perl --version 10:45:28 ​ \ This is perl, v5.10.1 (*) built for x86_64-linux-gnu-thread-multi \ (with 61 registered patches, see perl -V for more detail) \ \ Copyright 1987-2009, Larry Wall \ \ Perl may be copied only under the terms of either the Artistic License or the \ GNU General Public License, which may be found in the Perl 5 source kit. \ \ Complete documenta 10:45:33 gah 10:45:40 any bots around here with Perl 5.14 or later? 10:45:56 !perl print "$^V\n" 10:45:58 v5.10.1 10:47:00 I tried codepad.org, but it's even older (5.8) 10:50:50 -!- muskrat has quit (Quit: Leaving). 10:51:45 ooh, anagolf has 14.2 10:53:47 -!- impomatic has joined. 10:53:59 bleh, I think this might actually need 5.16 10:58:54 -!- ais523_ has quit (Quit: Page closed). 11:01:40 -!- Taneb has joined. 11:05:08 -!- Phantom_Hoover has joined. 11:08:15 5.10! 11:09:55 @tell ais523 ideone's Perl is v5.16.2 if that helps. (Though the point is probably moot by the time you get this.) 11:09:55 Consider it noted. 11:18:52 perlbot (a lesser fork of buubot) also has perl 5.16.2 right now 11:23:17 -!- Phantom__Hoover has joined. 11:23:58 Phantom__Hoover, ... 11:24:17 -!- Phantom_Hoover has quit (Ping timeout: 272 seconds). 11:39:14 Wow, I forgot I made a profile on Haskellers.com 11:39:30 I've... just 11:39:32 Hang on, fire alarm 11:40:29 As I was saying 11:40:53 I've... just received an email asking if I want to be a senior software developer 11:47:07 -!- Phantom_Hoover has joined. 11:47:37 -!- Phantom__Hoover has quit (Ping timeout: 246 seconds). 12:01:28 I've just received an email addressed to "Dr. Prof. [my name]". (I guess they think it's better to err in that direction.) 12:02:01 So, Doctor Professor Fizzie 12:04:32 -!- yorick has joined. 12:13:13 fizzie: yes, all academic spam does that 12:18:24 -!- qlkzy has joined. 12:19:02 `relcome qlkzy 12:19:05 ​qlkzy: Welcome to the international hub for esoteric programming language design and deployment! For more information, check out our wiki: . (For the other kind of esoterica, try #esoteric on irc.dal.net.) 12:19:49 -!- Phantom_Hoover has quit (Ping timeout: 246 seconds). 12:21:27 herr dr. prof. Taneb, inventor of d-modules 13:06:16 -!- boily has joined. 13:06:55 -!- metasepia has joined. 14:00:46 -!- L8D has joined. 14:06:24 good creative commons morning! 14:06:32 @messages-loud 14:06:32 oerjan said 15h 30m 48s ago: the zimbabwean uncertainty principle means you cannot quantify their bmp precisely without causing runaway inflation. 14:06:32 oerjan said 15h 17m 44s ago: beuh. who changed `ello? <-- i think you got hit by the tab expansion space issue. 14:07:58 @tell oerjan bmp, as in Bone Morphogenetic Proteins or as in Besi Merah Putih? 14:07:58 Consider it noted. 14:08:49 @tell oerjan indeed. tabcompletion is evil. either it three-letter-clashes, or it inserts Spurrious Satanic Spaces. 14:08:49 Consider it noted. 14:15:02 -!- ais523 has joined. 14:15:05 -!- ais523 has quit (Changing host). 14:15:05 -!- ais523 has joined. 14:22:04 How great; I have a broken sshfs mount that I can't seem to fusermount. 14:22:14 fusermount -u, I mean. 14:23:03 sudo umount --force /mountpoint? 14:23:38 No "sudo" access here. 14:24:02 "fusermount: failed to chdir to [REDACTED; parent of mount point]: Permission denied" 14:24:03 hm. and I suppose $(which reboot) isn't setuid? 14:24:22 is there a sysadmin you can berate? 14:24:26 "which reboot" is so 90s. 14:24:46 systemctl reboot, then? 14:24:47 Of course I can reboot (it goes via DBus and UPower or whatnot), but I don't wanna. 14:25:07 fizzie: this reminds me of how I somehow managed to get init to ptrace a process 14:25:15 Maybe I'll just keep collecting dead sshfs mounts. 14:25:22 meaning that that process couldn't be killed via any means whatsoever, apart from a reboot 14:25:35 * boily misses the '90s, where machines were simple and emitted an nice blue glow... 14:25:52 Incidentally, we do have privileges to do "sudo apt-get", so the whole "no root access" is kind of based on a honor system. 14:26:11 because the only ways to recover would be to debug init (explicitly allowed), or kill init (possible but kind-of fatal to the system) 14:26:34 fizzie: can you run arbitrary commands from within apt-get? 14:26:38 fizzie: I'm not sure; apt-get isn't dpkg, it only installs from repositories 14:26:49 so what access you could get from that would depend on the repository contents 14:26:54 ais523: You can "sudo apt-get changelog whatever", and then "!" out of less. 14:27:04 fizzie: haha, clever 14:27:08 neat. 14:27:12 And if someone goes and plugs that hole with a custom pager, I'm pretty sure more can be found; it's not supposed to be secure. 14:27:19 apt-get probably should drop permissions in that case 14:27:44 Probably, out of general principles, but it's not really in the use case. 14:28:33 have you ever tried running aptitude without arguments, btw? 14:28:33 -!- nooodl has joined. 14:28:40 I didn't actually realise that was possible for ages 14:28:51 it works even as non-root, albeit in read-only mode 14:28:54 Um. Yes, if by that you mean the usual aptitude UI. 14:29:55 yep, that's what I meant 14:29:59 I assumed it was command-line for years 14:30:19 We do have "sudo aptitude" access too; I didn't find an as obvious hole from it, because it doesn't have a spawn-a-shell menu command, and uses its built-in pager for changelogs. 14:36:44 -!- tertu has joined. 14:53:06 "sbatch: error: Batch job submission failed: Invalid account or account/partition combination specified" I just can't use that thing right. 15:04:21 Other than "[number]" and "[citation needed]", what special things like that can appear in wikipedia text 15:08:40 [who?] 15:09:11 [weasel words] 15:09:37 There seems to be loads of them help 15:09:46 [dubious · discuss] 15:09:52 I'm sure there's a category for them 15:10:32 http://en.wikipedia.org/wiki/Category:Inline_citation_and_verifiability_dispute_templates 15:10:33 Taneb: http://en.wikipedia.org/wiki/Template:Inline_tags 15:11:17 I was going to suggest http://en.wikipedia.org/wiki/Category:Inline_templates but I suppose that's formatted better. 15:11:55 -!- augur_ has quit (Remote host closed the connection). 15:11:58 I don't think I've come across [unbalanced opinion] in any article. 15:13:41 I don't think I've seen that either 15:13:45 nor [contradiction] 15:18:29 Ooh thanks 15:29:58 -!- oerjan has joined. 15:32:24 @messages-lol 15:32:24 boily said 1h 24m 26s ago: bmp, as in Bone Morphogenetic Proteins or as in Besi Merah Putih? 15:32:24 boily said 1h 23m 35s ago: indeed. tabcompletion is evil. either it three-letter-clashes, or it inserts Spurrious Satanic Spaces. 15:32:57 @tell boily bmp as in worst misspelling of gdp ever. 15:32:58 Consider it noted. 15:34:04 @tell boily it probably has _something_ to do with the abbrevation being bnp in norwegian. 15:34:04 Consider it noted. 15:38:06 fizzie: that's some spectrobabble 15:43:12 -!- Sprocklem has joined. 15:50:50 -!- conehead has joined. 15:56:02 -!- jm__ has joined. 16:00:55 -!- jm__ has quit (Client Quit). 16:09:00 http://en.wikipedia.org/wiki/Template:Awkward is cute 16:31:22 oerjan: that makes much more sense. 16:31:27 @messages-silent 16:31:27 Unknown command, try @list 16:31:34 @messages-lllll 16:31:34 Unknown command, try @list 16:31:39 @messages-lol 16:31:40 oerjan said 58m 42s ago: bmp as in worst misspelling of gdp ever. 16:31:40 oerjan said 57m 35s ago: it probably has _something_ to do with the abbrevation being bnp in norwegian. 16:32:52 -!- augur has joined. 16:36:47 -!- augur_ has joined. 16:39:46 -!- augur has quit (Ping timeout: 245 seconds). 16:56:13 The text box has the best scroll bar ever. http://apollo.spaceborn.dk/dsky-sim.html 16:57:38 ion: oh my god 16:58:10 you have to actually slam the brake button a few times for it to really stop 16:59:36 once worked for me. 16:59:38 -!- augur_ has quit (Remote host closed the connection). 17:00:47 hmm i can click the scroll buttons multiple times to scroll faster and then i have to click the stop one multiple times to slow back down 17:01:20 hm right. fancy. 17:02:02 -!- Sprocklem has quit (Ping timeout: 264 seconds). 17:02:23 function stopscroll() { if (window.moveupvar) clearTimeout(moveupvar); if (window.movedownvar) clearTimeout(movedownvar); } 17:03:11 if you assign multiple timeouts to the same variable do they stack...... 17:03:21 that sounds javascript enough to be true 17:06:12 -!- oerjan has quit (Quit: Later). 17:06:34 -!- yorick has quit (Remote host closed the connection). 17:16:32 ew. I don't think there's any gurantee that the return value of setTimeout is truthy 17:17:31 AFAIK it's just an arbitrary thing that could be passed to clearTimeout to stop it from firing, though numbers are common (at least, I think both SpiderMonkey and V8 use numbers) 17:37:20 -!- muskrat has joined. 17:51:10 -!- copumpkin has joined. 17:55:46 I love the way that "truthy" has become an actual part of the computer science lexicon (if only in languages with ubiquitous coercion) 17:55:49 actually, hmm 17:56:26 there was an article talking about how the only sensible axis on which to classify type systems was static/dynamic, anything else is ambiguous and arbitrary 17:56:50 I disagree, I think the amount of coercion in a language is another axis 18:02:52 hmm… what about an esolang based entirely on casts 18:03:00 which don't roundtrip, so you can do actual calculation 18:03:00 PHP? 18:03:08 ok, not PHP then. 18:03:40 something like, (int)"4+7" => 11? 18:03:46 i guess that's too easy. 18:03:50 that seems too easy 18:03:56 -!- FreeFull has joined. 18:03:58 also, it needs control flow 18:04:07 presumably via casting things to functions 18:04:15 that sounds like an interpreter... 18:04:30 not necessarily 18:04:34 you could cast ints to lines of code, for instance 18:04:39 BASIC-style 18:16:51 -!- muskrat has left ("Leaving"). 18:37:56 uh? 18:38:17 like, 10 GOTO 10? 18:38:29 boily: 10 GOTO (int)x 18:38:37 err, (lineno)x 18:40:00 the lineno type. you don't see that one too often... 18:41:10 boily: gcc adds one to C; it's stored in void* variables and you get it via using unary && on a label 18:42:35 * boily runs away at the sight of an unary && 18:50:14 -!- Sprocklem has joined. 18:50:16 And then you call it by dereferencing a void * in a goto. 18:51:14 (Technically it's just a "goto *expression" syntax, and not an instance of the unary *, but still.) 18:53:18 -!- nisstyre has joined. 18:56:17 so easy. 18:56:54 fizzie: in gcc-bf, _exit in the standard library is implemented as "goto *(void *)0" 18:57:04 which must be one of the weirdest lines of C ever 18:58:49 ais523: isn't that abort() ? 18:59:01 not quite, I know, because it's not the same signal 18:59:02 but still 18:59:44 b_jonas: _exit doesn't quite have the same semantics as abort, abort can be handled 19:00:52 although it always exits after the handler returns 19:01:05 the handler can longjmp out, though 19:03:08 how does jumping to zero halt? 19:03:35 Bike: it falls out of the main loop 19:03:52 oh 19:04:03 it's brainfuck, after all 19:04:16 what is gcc-bf after all 19:04:19 anyway* 19:04:42 Bike: a gcc backend that targets a lowlevel language that compiles to brainfuck 19:04:49 oh. 19:10:26 gimme gimme 19:10:34 not finished 19:10:45 I got fed up trying to impl a 64-bit multiply 19:13:00 mroman_: can I get your approximate coördinates, so that I can get the distance between you and ais523? 19:13:06 ais523: I can help in the multiply 19:13:16 ais523: also, you asked about perl evaluator bots a few days ago 19:13:31 boily: Can't you just google them? 19:13:35 ais523: perlbot (a less complete fork of buubot) has perl 5.16 via the eval command 19:13:35 mroman_: b_jonas: I can send you my source code if you want to continue it, if you like 19:13:50 but it probably only works on a specific version of gcc and newlib which may now be hard to obtain 19:13:51 ais523: wait, 19:13:58 ais523: how do you represent the integers? 19:14:07 b_jonas: one byte on each tape element 19:14:13 nah, I can't help then 19:14:13 assuming an 8-bit wrapping tape 19:14:25 well, not so easily anyway 19:14:28 mroman_: is that you → https://www.facebook.com/roman.muntener ? 19:14:39 No 19:14:46 I don't have a Facebook Account 19:14:54 I do only less efficitn formats like binary (addressable only in bits) or zeckendorf representation 19:15:07 for bytewise you'll have to read Knuth or something 19:15:10 though wait 19:15:11 actually 19:15:13 47.69684, 8.63977 19:15:19 that's bf, right? 19:15:20 ^- my approximate coordinates 19:15:29 that means you can only increment and decrement the bytes 19:15:33 that's not so efficient 19:15:44 hmm 19:16:01 mroman_: thanks! 19:16:06 N47 41 48, E8 38 23 that is 19:16:12 but bf is too eww 19:16:16 If you prefer this format 19:16:19 (hm. I wonder where 80.246.50.48 will take me...) 19:16:20 oh right, this is the build system that runs gcc's build system halfway 19:16:30 then runs sed on the generated Makefiles before completing the build 19:16:32 mroman_: any format translatable to this Physical Earth is fine. 19:17:05 Title and buttons: “Verify?” “No”, “Yes”. Description: “Do you not want to restore any of the projects? They cannot be restored later.” http://heh.fi/tmp/audacity-kayttoliittymakukkanen.png 19:17:06 I'm suprised americans don't have an imperial format for coordinates 19:17:10 like uhm... 19:17:13 earthworms 19:17:46 that zeckendorf thing is a bit riddiculous 19:18:01 I still don't know how much addition can loop, and don't know how to implement subtraction properly 19:18:08 anyway, this tarball is 50MB, but I'll send it to people who want it 19:18:10 nobody likes runs of ones. 19:18:13 I should try to analyze it some day 19:18:16 it bugs me a bit 19:18:26 also, working with gcc was really frustrating 19:18:44 most of the codepaths that aren't used for x86 are either buggy and untested, or just outright unimplemented 19:18:58 and maybe figure out direct multiplication too, looping on zeckendorf digits instead of binary bits, though that might be very difficult 19:20:26 pervasive languages 19:20:30 inteesting 19:23:19 although 19:23:47 I probably won't be able to figure out this zeckendorf thing unless I learn about those tricky things people do to do binary faster these days 19:24:02 like extra bits or strange representations to make it more vectorizable 19:24:17 like fourier transformations? 19:24:22 no 19:25:07 I mean that thing where they put a binary number in like base 2**30 but put each digit in 32-bit words to somehow avoid cascading carries 19:25:11 or something tricky like that 19:25:28 the fourier transforms help for really large numbers 19:25:47 but in the zeckendorf representation the problem is that carries in an addition go both way: down and up 19:25:54 and can cascade both ways or something 19:25:56 it's crazy 19:26:21 so I can't even prove how to add in guaranteed linear time 19:26:48 another problem is that it's not particularly easy to multiply two fibonacci numbers, as far as I can see 19:27:03 int-e: you don't have to directly multiply 19:27:28 int-e: you have to generate the sequence of multiplies of one factor by successive fibonacci numbers 19:27:32 which you can do by repeated additions 19:27:51 ah. right. 19:27:52 like, you know, when you implement multiply in a language that doesn't allow accessing bits, but only does add/subtract/compare 19:28:02 you can implement multiply and even divide in binary on such a system 19:29:10 my zeckendorf add code is in http://www.perlmonks.com/?node_id=989716 in case you care 19:29:52 but that only implements the addition in zeckendorf, and then binary built on that 19:45:09 -!- muskrat has joined. 20:03:32 -!- muskrat has quit (Quit: Leaving). 20:20:34 boily: Why did you want to calculate the distance? 20:29:33 -!- Sprocklem has quit (Ping timeout: 265 seconds). 20:31:56 mroman_: your wanted to be gimmeed the gcc-bf compiler. 20:33:52 Ah 20:33:58 And what's that got to do with distance? 20:37:11 to know if you could walk up to ais523's residence and extirpate the aforesaid compiler from him. 20:37:26 boily: I did say I was planning to give it voluntary 20:37:28 (that, and I opportunisted the occasion of asking you the The Question.) 20:37:31 voluntarily 20:37:52 boring. I could have wrote mroman_'s epic compiler fetch quest! 21:05:29 aforesaid 21:05:38 are you trying to make fun of my lack of english skills 21:06:11 although aforesaid I knew 21:06:13 but extirpate 21:06:15 seriously 21:06:46 you could have gone with wipe out, eradicate or extermine 21:07:11 extirpate doesn't even look like an english word 21:08:46 That's totally excrescent 21:09:27 There's even superexcrescently 21:09:33 -!- muskrat has joined. 21:10:40 far from it. I just like to butcher the English language myself. 21:10:52 extirpate is real, although rarely used 21:10:57 ~duck extirpate 21:10:57 extirpate definition: to destroy completely. 21:11:04 darn. and there I was hoping it wouldn't be one. 21:11:08 wtf 21:11:14 nice dictionary 21:11:15 -!- muskrat has quit (Client Quit). 21:11:23 two times in two. first with sbow, then extirpate. 21:11:39 ~duck waste 21:11:39 waste definition: a sparsely settled or barren region. 21:11:40 mroman_: a very rare occurence. ~duck usually finds nothing. 21:11:44 ~duck to waste 21:11:44 --- No relevant information 21:11:54 ~duck impetus 21:11:54 impetus definition: a driving force. 21:12:04 ~duck sbow 21:12:04 --- No relevant information 21:12:06 I want to invent a word that doesn't exist, dammit! 21:12:11 ~duck INTERCAL 21:12:11 INTERCAL is an esoteric programming language that was created as a parody by Don Woods and James M. Lyon, two Princeton University students, in 1972. 21:12:15 ~duck forty-two 21:12:15 --- No relevant information 21:12:20 shachaf: no. ain't gonna bdbvxZfLOCmfKdNH1tg9EidKQqsn2zQHrC4XwQrP72RdkBxE3KrOdvJeZBNKl2yH. 21:12:28 ~duck 42 21:12:29 --- No relevant information 21:12:31 ("INTERCAL" is my standard search query for testing search engines, btw) 21:12:52 ~duck snobol 21:12:52 SNOBOL (StriNg Oriented and symBOlic Language) is a series of computer programming languages developed between 1962 and 1967 at AT&T Bell Laboratories by David J. Farber, Ralph E. Griswold and Ivan P. Polonsky, culminating in SNOBOL4. 21:13:06 ~duck strongtalk 21:13:06 Strongtalk is a Smalltalk environment with optional static typing support. 21:13:12 didn't expect that. 21:13:15 ~duck passerine 21:13:15 A passerine is a bird of the order Passeriformes, which includes more than half of all bird species. 21:13:26 ~duck gnatostomata 21:13:26 --- No relevant information 21:13:29 (I believe that the INTERCAL manual is the only place where I've encountered SNOBOL) 21:14:18 snobol's funny. the string concatenation operator is a space, the regular expressions are actually CFGs, and every line has a goto included. 21:14:32 ~duck chordate 21:14:32 --- No relevant information 21:14:33 ~duck onomatopoeia 21:14:33 onomatopoeia definition: the naming of a thing or action by a vocal imitation of the sound associated with it (as '''buzz, hiss'''). 21:14:51 boily: your bot's knowledge of phylogenic systematics is worryingly low. 21:15:15 ~duck hylomorphism 21:15:16 Hylomorphism is a philosophical theory developed by Aristotle, which conceives substance as a compound of matter and form. 21:15:28 ~duck entelechy 21:15:28 In the philosophy of Aristotle, the condition of a thing whose essence is fully realized; actuality. 21:16:27 ~duck eschatology 21:16:27 eschatology definition: a branch of theology concerned with the final events in the history of the world or of humankind. 21:16:45 Bike: I concur. it saddens me. 21:16:59 Where's it get the information fro? 21:17:24 -!- AwfulProgrammer has joined. 21:18:11 Bike: duck duck go. 21:18:45 AwfulProgrammer: hi! I have this stong urge to `relcome you. were you already `relcomed? 21:19:41 "Safe search blocked some results for chordate." this search engine is worrying, boily. 21:20:12 let me check if I use safe search... 21:20:28 no i just mean, is it turning up sexual chordates or something. 21:20:44 I feel welcomed boily 21:20:50 :3 21:20:59 hot sexual chordate on protozoan action... 21:21:46 Bike: incidentally, yes, safe search is on. wouldn't want to make this chännel perverteder anymore than what it is. 21:22:25 protozoa are hardly monophyletic 21:23:59 ~duck protozoan 21:23:59 Protozoa are a diverse group of unicellular eukaryotic organisms, many of which are motile. 21:24:39 Bike: are you a biologist? 21:25:34 a bikeologist. 21:26:45 logical. 21:31:50 -!- Phantom_Hoover has joined. 21:39:21 -!- augur has joined. 22:00:52 -!- yorick has joined. 22:04:09 INTERCAL you say 22:04:35 According to bing that's a firm that creates oil-burners 22:04:56 well... according to google too 22:05:10 but the real intercall on bing is place 4 22:05:12 and google place 2 22:05:14 so google wins . 22:08:18 -!- MindlessDrone has quit (Quit: MindlessDrone). 22:11:56 in my google bubble, the wikipedia intercal page comes first 22:12:30 -!- yiyus has joined. 22:15:43 Ah, the language preference plays a role here; google.de puts said company first 22:19:58 yes, the hl= parameter giving ui language changes a LOT about the order of google hits 22:20:18 that's why I use both hl=hu and hl=en depending on what language of pages I want to find 22:25:32 `? szoup 22:25:34 A szoup a szilárd tápszereknek híg alakban való elkészítése a célból, hogy könnyebben emészthetők legyenek; a hígító anyag a viz, mely feloldja s magába veszi a tápanyag legértékesebb részeit. 22:27:16 `? 22:27:18 ​? ¯\(°​_o)/¯ 22:27:55 `?   22:27:57 ​ ? ¯\(°​_o)/¯ 22:28:36 `quote hogy hogy hogy 22:28:38 33) `translatefromto hu en Hogy hogy hogy ami kemeny How hard is that 22:29:17 `run echo "The final frontier." > wisdom/\ 22:29:21 No output. 22:29:26 `? 22:29:28 ​ ? ¯\(°​_o)/¯ 22:29:40 fascinating. 22:31:11 -!- oerjan has joined. 22:32:46 -!- muskrat has joined. 22:35:49 -!- ais523 has quit. 22:42:07 -!- muskrat has quit (Quit: Leaving). 22:45:20 -!- Bike_ has joined. 22:46:00 -!- Bike has quit (Disconnected by services). 22:46:02 -!- Bike_ has changed nick to Bike. 23:03:01 -!- Phantom__Hoover has joined. 23:03:28 -!- Phantom_Hoover has quit (Ping timeout: 246 seconds). 23:17:59 https://plus.google.com/+MikeStay/posts/Vgz4kMFiyCU 23:30:30 -!- boily has quit (Quit: Poulet!). 23:30:31 -!- metasepia has quit (Remote host closed the connection). 23:32:33 shachaf: saw that coming from a mile away. 23:32:57 @ask Oj742 are you going to add a long description of smartlock to strategy page? 23:32:57 Consider it noted. 23:33:22 `? \ 23:33:24 ​\? ¯\(°​_o)/¯ 23:34:09 `? hogy 23:34:11 hogy? ¯\(°​_o)/¯ 23:34:25 `?lambdabot 23:34:27 ​/home/hackbot/hackbot.hg/multibot_cmds/lib/limits: line 5: exec: ?lambdabot: not found 23:34:31 `? lambdabot 23:34:32 lambdabot? ¯\(°​_o)/¯ 23:34:38 `? oerjan 23:34:40 Your evil overlord oerjan is a lazy expert in future computation. Also a lying Norwegian who hates Roald Dahl. 23:35:27 why do you hate Roald Dahl 23:35:57 `learn \ was initially popular as a replacement for the solidus, but inevitably there was a backslash. 23:36:02 I knew that. 23:37:27 `learn lambdabot is a fully functional bot. just don't ask about @src. 23:37:32 I knew that. 23:43:45 -!- Phantom_Hoover has joined. 23:43:53 -!- Phantom__Hoover has quit (Ping timeout: 246 seconds). 23:48:33 -!- carado has joined. 23:49:28 shachaf: iirc roald dahl is evil or something 23:51:29 He's welsh, there is that 23:51:35 Also Danish 23:51:46 * oerjan swats Taneb -----### 23:51:46 Or maybe Norwegian, I forget 23:51:49 But he's Welsh 23:51:52 Very Welsh 23:52:14 DON'T FORGET AGAIN 23:52:21 Aaaaaaaaaaaaaaaaaaaaaah 23:52:57 istr from his wikipedia page that he was pretty evil. 23:53:27 `olist 933 23:53:29 olist 933: shachaf oerjan Sgeo FireFly 2013-11-30: 00:00:07 -!- Phantom__Hoover has joined. 00:01:13 -!- Phantom_Hoover has quit (Ping timeout: 246 seconds). 00:05:00 well that seemed to go rather well 00:11:33 -!- Phantom_Hoover has joined. 00:14:03 -!- Phantom__Hoover has quit (Ping timeout: 272 seconds). 00:24:53 -!- Sprocklem has joined. 00:32:45 -!- muskrat has joined. 00:32:54 -!- Phantom__Hoover has joined. 00:33:24 -!- ruddy has joined. 00:36:31 -!- Phantom_Hoover has quit (Ping timeout: 265 seconds). 00:57:10 -!- yorick has quit (Remote host closed the connection). 01:09:08 @vote olist 01:09:08 usage: @vote 01:09:12 @vote olist update 01:09:12 voted on "update" 01:09:13 useless 01:11:30 -!- carado has quit (Ping timeout: 252 seconds). 01:11:46 @poll-result olist 01:11:46 Poll results for olist (Open): update=933 01:12:15 @poll-remove olist 01:12:15 Poll should be closed before you can remove it. 01:12:18 help 01:12:20 @help vote 01:12:20 vote Vote for in 01:12:24 @list vote 01:12:24 poll provides: poll-list poll-show poll-add choice-add vote poll-result poll-close poll-remove 01:12:27 you can't close it yet! 01:12:32 what if someone votes for... another option! 01:12:35 @poll-close olist 01:12:35 Poll "olist" closed. 01:12:39 @poll-remove olist 01:12:39 poll "olist" removed. 01:12:43 nooooo. 01:12:58 such a profoundly secure system. 01:13:13 you're destroying democracy 01:13:35 Bike: that's pollitics for you 01:13:58 Bike: it's ok the ballot was stuffed anyway 01:14:18 http://dynasty-scans.com/system/releases/000/008/952/cw-a-4.png a depiction of shachaf 01:14:42 help 01:14:51 which one am i 01:15:05 the demon thing, obviously, you fascist. 01:16:11 which demon thing 01:16:17 -!- Phantom__Hoover has quit (Ping timeout: 246 seconds). 01:16:32 i don't know what's going on help 01:18:52 «Primary duties will be to place and monitor trial carcasses as part of searcher efficiency and carcass removal trials [...] on the Island of Maui.» in CowHub news 01:24:19 an opening for a cow orker, i take. 01:26:40 -!- muskrat has left ("Leaving"). 01:32:43 -!- FreeFull_ has joined. 01:36:00 -!- FreeFull has quit (Ping timeout: 260 seconds). 01:38:41 :D 03:51:02 -!- Tod-Autojoined has changed nick to TodPunk. 04:33:51 -!- nooodl has quit (Quit: Ik ga weg). 04:41:29 @remember ddarius The secret to usable software is not discoverability, not documentation, not consistency; it's preview and undo. 04:41:30 I will remember. 04:44:59 -!- zzo38 has joined. 04:52:45 -!- Taneb has quit (Quit: Leaving). 05:00:36 -!- oerjan has quit (Quit: leaving). 05:12:34 Star Wars Downunder http://youtu.be/mhTn8cjm9ZM (the subtitles have a translation to English :-D) 05:20:21 ?messages-loud 05:20:22 Bike said 3d 11h 3m 31s ago: i don't think opencl c even has provisions for exceptions 05:20:29 -!- CADD has joined. 05:21:33 hi ion 05:21:39 hachaf 05:22:36 Vorpal: regarding your claim that 'nobody in "real life"' cares about gendered language, https://github.com/joyent/libuv/pull/1015 has about 50 people posting in the space of a few hours to say that they do in fact care 05:22:55 mostly men, some women, many people with "real names" and geographic locations in their github profiles 05:24:26 I have played Dungeons&Dragons game on Wednesday; I have almost disabled the prisoner; he is now in a coma. 05:24:54 what will you do now? 05:26:23 Ensure he is disabled some more, would be the next thing to do. And if the captain gets angry, work around that, too (possibly with illusions). 05:26:40 use your illusion 05:27:58 O no, I don't want to waste it. 05:29:32 silly kmc, internet people aren't real 05:29:35 and nor are people who disagree with me 05:29:47 it's possible that i'm not helping right now 05:31:07 :3 05:31:25 if i'm not real how do you explain my invention of the steam-powered bike gear 05:31:47 shachaf: i visited https://twitter.com/catcafecalico while I was in Japan 05:31:51 :3 :3 :3 05:32:01 i like cats 05:32:56 imo there should be a pointless cat 05:34:36 What’s a catca and what’s fecal ico? 05:36:02 kmc: good pull request comments 05:36:06 i like how there's always that person 05:36:07 thx 05:36:13 ion: oof 05:36:19 shachaf: Or fifty of “that person”s. 05:36:21 ion: see that can't happen in Hangul!! best writing system ever 05:37:00 great, now i want to see korean puns. 05:37:55 I don’t understand why the world hasn’t just switched to Hangul. 05:37:57 ion: in this case it looked like there were only a few 05:38:10 shachaf: "stop wasting your time on this issue!" *ensures that even a trivial fix becomes a multi-hour fight* 05:38:47 ion: it's not so great if your language doesn't conform to Korean phonetics 05:38:57 if you like distinguishing "r" from "l" or "g" from "k", for example 05:38:58 The Internet fight or fight response 05:39:01 Most languages don't. :-( 05:39:11 Perhaps we should invent a writing system to end all writing systems. 05:39:30 @google xkcd standards 05:39:31 http://xkcd.com/927/ 05:39:31 Title: xkcd: Standards 05:41:31 blissymbols 05:41:37 Hangul is not a bad system, although you can definitely make up a lot of new kinds, for conlangs and whatever else you like to do; I don't really like the IPA symbols which are racist and inelegant; I would prefer to compose symbols based on if it is dental, approximant, etc, even for impossible combinations, sounds out of human range, simultaneous speech, implied but unspoken sounds, and so on. 05:41:53 And Blissymbols is OK too, for meaning rather than sound. 05:42:14 None of these are perfect though, and probably they cannot really intended to be anyways. 05:42:31 zzo38: you should invent a writing system 05:42:38 and serve documents written in it via gopher 05:44:18 * kmc = 기간 미갈읏텔 ? 05:44:40 what the hell 05:45:00 are those just normal hangul? my term font is terrible 05:45:11 they're copypasted from google translate 05:45:49 gi gan mi gal eus tel 05:46:01 creative 'mcallister' i must say 05:46:03 kmc: i like how "only women actually care about this" and "only men actually care about this" are both arguments against making the change 05:46:27 yep 05:46:28 Sure I could serve them by gopher or whatever protocol, although probably if I was making such a thing I should write the METAFONT programs to draw the symbols in such a writing system. 05:48:17 사캅 벤-기기? no idea how to do "chaf" tbqh 05:48:39 and s/sh didn't seem to be distinguished, based on reading hangul on street signs in japan >_> 05:49:09 Bike: yeah well like I said, l/r and g/k are the same 05:49:11 That's OK, no one really does. 05:49:18 i know, i'm just amused 05:49:21 :D 05:49:49 Are g/k the same? 05:50:03 http://josefwigren.com/wp-content/uploads/2013/01/full-hangul.jpg has separate g and k 05:50:18 hm 05:50:24 colorful :) 05:50:30 oh i forgot about that letter 05:50:38 what are the greyed out ones. 05:50:48 the forbidden notes 05:50:58 the black keys 05:51:03 :o 05:51:26 should i learn hangul 05:52:05 you could learn korean. 05:52:19 that sounds like a lot more trouble than learning an alphabet 05:52:24 i want to learn korean 05:52:26 but don't know how 05:52:31 gotta get some books or something 05:52:34 books are a lot of effort 05:52:47 move to samsung digital city 05:53:15 i like that it has ᄋ 05:53:31 because that poor consonant is disregarded in many languages 05:53:35 :ᄋ 05:54:39 hebrew has it, though 05:54:52 since there is also a vaguely kind of similar system of consonants and vowels 05:56:31 you mean the one that gets transliterated as "ng"? 05:56:46 Wait, maybe I'm mixing things up. 05:56:55 What's "ng"? 05:57:26 ᄋ can also appear as an initial but there it means nothing at all 05:57:57 Right, that's the usage I mean. It can appear as non-initial? 05:58:24 "nothing at all", not even a glottal stop? 05:58:26 yes, as a final consonant it's "ng" 05:58:43 That's odd. I thought this alphabet was supposed to make sense. :-( 05:59:13 as in 삼성 "samseong" 05:59:51 shachaf: they used to be separate but got conflated down the line 05:59:51 Star Trek Tᄋ 05:59:56 >_< 06:00:04 hangul had more letters back when it was supposed to represent all the sounds in Classical Chinese 06:00:25 how much of the phonology of classical chinese do we actually know 06:00:53 So do you pronounce it as a glottal stop or do you slur syllables together? 06:00:59 i don't know man 06:01:07 i ought to learn korean though 06:01:20 why not finnish 06:01:35 a language with no gendered third-person pronouns 06:02:00 why not Zoidberg 06:02:31 should i also learn korean 06:02:42 We should all switch to Lojban 06:02:46 you should learn double korean. 06:08:43 Help, i seem unable to get in touch with Simon Marlow. I have sent a message on Google+ and two messages on IRC on different days. 06:09:33 He was online in IRC aa few days ago. 06:10:03 By a few days ago I mean, uh, earlier today. 06:10:14 Oh, you sent IRC messages. 06:10:31 You could try email? 06:11:03 I’ll try email next. But one would think Google+ and IRC would, like, work. 06:12:06 I didn't know there was such a thing as a Google+ message. 06:12:43 Maybe he prefers Facebook messages. 06:13:37 If you send messages to non-Facebook friends on Facebook, they won’t get notified. They’ll see the message if they happen to check out the obscure “probably spam” place nobody checks. 06:14:16 Perhaps Google+ does something similar, but that’s why i tried to contact him on IRC after no response. 06:14:49 Maybe you can go work at Facebook and then send him an internal message. 06:15:18 Perhaps i could become a billionaire, buy Facebook and send him a memo from the boss. 06:16:20 p. sure there are better things to buy at that price 06:20:49 Some people abbreviate the Finnish word “eli” (http://en.wiktionary.org/wiki/eli#Finnish) as “l.” That’s like abbreviating “pretty” as “r.” 06:21:23 The name of the letter l isn’t “el” either, it’s “äl”, so that doesn’t explain it either. 06:21:43 Also, why abbreviate a three-letter word? :-P 06:22:17 not to be confused with "ål" 06:22:36 verily 06:22:45 en långsträckt fisk med säreget fortplantningsbeteende 06:22:49 FWIW, there’s no å in Finnish 06:22:57 right 06:23:37 and there's no l in christmas 06:23:54 Depends on how you pronounce r 06:23:59 säreget fortplantningsbeteende och uppskattat kött 06:24:11 (the joke is noel) 06:24:19 g. joke 06:24:27 saturnalia – both r and l! 06:26:23 ion: do they in finland that russian has n different 's's 06:26:29 for some value of n 06:26:37 say 06:26:47 I think you a verb. 06:27:31 for some value of finland 06:31:18 `run echo $'#!/usr/bin/env python\n# coding: rot-13\ncevag h"Uryyb, Jbeyq!"\n' > /tmp/whoaaa.py; chmod +x /tmp/whoaaa.py; /tmp/whoaaa.py 06:31:20 Hello, World! 06:31:29 i need to learn enough korean to implement `안녕하세요 anyway 06:32:47 shachaf: whoa, dude 06:32:49 Python has that? 06:32:59 Why doesn’t Haskell have that‽ 06:33:03 lifthrasiir: Maybe you can implement `안녕하세요 for us? 06:34:06 ion: ghc -pgmF hth 06:34:27 kmc: That’s GHC. :-( 06:34:38 "everyone knows haskell is really just ghc" 06:34:43 Fair enough. 06:37:17 What I think it should include is some way to convert identifiers containing non-ASCII characters into ASCII 06:39:21 > let 안녕 = "hello" in 안녕 06:39:22 "hello" 06:40:48 For example, there could be some extension to support a declaration like "\49493\12920\122223" = magic; and then it will treat "magic" as a synonym for the non-ASCII identifier. 06:44:00 -!- conehead has quit (Quit: Computer has gone to sleep.). 07:00:06 However, in this Dungeons&Dragons game, I did notice a hole in the floor in the bedroom hallway, directly above the prison cell. It is a small hole, but large enough for a coin or leech or small key to fit. Perhaps this key was intended that someone might drop it into this hole? (I am not going to do that, though.) 07:20:49 -!- Sprocklem has quit (Quit: Leaving). 07:42:31 Is any cellular automaton a convolution filter followed by a scalar function on each cell? From what I can tell, they are able to be represented in this way; Conway's Game of Life can easily be done like this, for example. 08:05:03 mostly depends what you mean by "cellular automaton", I expect 08:08:09 -!- impomatic has quit (Ping timeout: 272 seconds). 08:14:07 What do *you* mean by "cellular automatic"? 08:15:23 -!- rdococ_ has joined. 08:15:32 well, what if I make a CA where each cell computes a complicated nonlinear function of its neighbors 08:15:33 -!- nisstyre has quit (Quit: Leaving). 08:15:42 that would not fit in your scheme right? 08:16:03 I suppose then it wouldn't, if the number of states isn't finite 08:16:12 So you are correct about that 08:16:18 and if it is finite then it still works? 08:17:15 I expect it to (although maybe if something else strange is done, it might not?) 08:18:04 -!- rdococ_ has changed nick to Halite. 08:19:10 If the number of states is infinite though, then I would think a convolution followed by a scalar (even if nonlinear) function would still work in *some* cases, but not all 08:19:11 -!- Halite has quit (Changing host). 08:19:11 -!- Halite has joined. 08:19:11 -!- Halite has quit (Changing host). 08:19:11 -!- Halite has joined. 08:38:33 -!- kmc has set topic: SUNTORY BOSS is the boss of them all since 1992 | Although maybe if something else strange is done, it might not? | https://dl.dropboxusercontent.com/u/2023808/wisdom.pdf http://codu.org/logs/_esoteric/ http://tunes.org/~nef/logs/esoteric/. 08:47:02 -!- L8D has quit (Ping timeout: 264 seconds). 08:59:11 While playing backgammon earlier this week, I have noticed that although doubles will give you more moves, it also makes you more likely to get stuck, so there is that counterbalance involved. 09:01:48 -!- ruddy has quit (Ping timeout: 246 seconds). 09:07:35 I have, even before, noticed how sequent calculus can be considered as a game between two players, the first player who selects a rule and applies all variables, and the second player must select a sequent above the line to continue with. Whoever has no legal moves loses. I think there are also other ways to consider a logic as a game, but I do not know what they are or how they work. Do you know? 09:11:29 it's common (and useful imo) to view predicate logic as a game between two players, ∃ and ∀ 09:11:51 A proof of some sequent then corresponds to a strategy for the first player to be guaranteed to win from such a position. 09:11:58 mhm 09:12:14 kmc: I have read about that, but didn't study it much to know much about how such thing is working. 09:15:28 put a formal in prenex normal form, then ∃ and ∀ take turns selecting values for their respective variables; ∃ wins (and the formula is true) if they end up at a true propositional statement, ∀ wins (and it's false) if they end up at a false one 09:15:34 i think that's how it goes 09:16:16 it might not be that useful to view totally abstract logic this way, but thinking about two players has helped me keep straight complicated quantifiers in e.g. definitions of continuity, or VC-dimension, or what have you 09:17:03 O, I can understand now, how you mean! 09:19:51 recall that TQBF / QSAT is PSPACE-complete, so any problem in PSPACE can be phrased as such a game 09:20:17 I don't know whether or not it useful to view abstract logic in such a way either, however, I have noticed that it can be made up other way around; first make up the game and then the sequent calculus which implements such a game. For example a subtraction game where the first player wins with numbers that aren't divisible by four, encode such a thing in sequent calculus and that is one way to define the logical system where theorems are numbers wh 09:20:34 also sometimes you have another player "Nature" who chooses randomly, and then you can talk about the probability of ∀ or ∃ winning 09:21:09 kmc: O, OK, you can have that too. I didn't think of quite that, but I did think of similar things actually. 09:21:12 and then there are things like interactive proof systems or Arthur-Merlin proofs or zero-knowledge proofs, which are also phrased as games between multiple players, usually with access to randomness and some (possibly differing) bounds on their computational power 09:23:20 zero knowledge proofs are so cool 09:23:51 OK 09:25:47 I do not know what "Arthur-Merlin proofs" means, however. 09:26:03 http://en.wikipedia.org/wiki/Arthur%E2%80%93Merlin_protocol 09:27:22 -!- nooodl has joined. 09:27:31 Notice that in the system I have defined, draws may be possible (although I find it is usually useful to consider draws as a win for the second player, or at least draws by repetition, anyways) 09:31:11 OK, now I looked at Arthur-Merlin 09:45:17 -!- esowiki has joined. 09:45:21 -!- esowiki has joined. 09:45:21 -!- esowiki has joined. 09:45:44 -!- esowiki has joined. 09:45:48 -!- esowiki has joined. 09:45:48 -!- esowiki has joined. 09:46:04 -!- esowiki has joined. 09:46:08 -!- esowiki has joined. 09:46:09 -!- esowiki has joined. 09:46:18 -!- glogbot has joined. 09:46:20 [freenode-info] if you're at a conference and other people are having trouble connecting, please mention it to staff: http://freenode.net/faq.shtml#gettinghelp 09:52:04 -!- zzo38 has quit (Remote host closed the connection). 10:08:39 -!- MindlessDrone has joined. 10:19:33 -!- Taneb has joined. 10:35:36 why is there no cat cafe in san francisco 10:42:24 when I said "put a formal" above i meant "put a formula" 10:43:09 kmc, what is a cat cafe 10:44:22 only the best sort of retail establishment there is!!!! 10:44:45 it's a cafe and a bunch of cats live at the cafe and you can pet / play with / snuggle with the cats at the cafe 10:48:51 imo get a cat 10:49:15 thats different 10:49:16 then your house can be a cat cafe and i can visit and pet / play with / snuggle 10:51:17 Cats are the cats. 10:51:45 I want to go to a cat cafe 10:52:16 do cat cafes dispose of cats in evil ways when they get old 10:52:16 If an oscilloscope can be set to display vectors, why do we still use pixels? 10:52:33 I don't think there's a cat cafe in the whole of Finland. 10:53:22 -!- yorick has joined. 10:53:47 `unicode ARABIC LIGATURE UIGHUR KIRGHIZ YEH WITH HAMZA ABOVE WITH ALEF MAKSURA ISOLATED FORM 10:53:51 ​ﯹ 10:54:03 There is one in England and they are making another 10:54:04 With a name that long, you'd think it'd be more impressive. 10:54:06 wb Halite 10:54:12 But they make them in very far away places 10:56:03 they have some in Paris, Berlin, and München as well 10:56:18 and Budapest 10:56:21 all the cool places 10:56:23 There are none in York or Hexham 10:56:25 sorry hexham 10:56:57 i suggest moving to Berlin or Seoul 10:57:08 although, Finland is a cool place and doesn't have one 10:59:06 Halite: lots of reasons, one is that LCDs are a lot nicer than CRTs (and OLED displays nicer yet) and they're inherently pixel-oriented 11:01:13 vector graphics doesn't really do full color images, shading, etc. 11:01:48 you can have graphics stacks that mix vector and raster pretty far down the pipeline, but you want something uniform when you actually send graphics to a display device, and pixels make sense there 11:02:19 some old video games did use vector graphics and directly control the deflection of a CRT beam in the manner of an oscilloscope 11:02:31 http://www.jmargolin.com/vgens/vgens.htm has an incredible amount of detail on how that works 11:03:16 an original _Asteroids_ game looks absolutely stunning 11:04:12 brilliant bright white CRT with beautiful trails and perfectly smooth lines 11:04:16 monochrome so there's no shadow mask even 11:04:18 Can and do vector LEDs exist? 11:05:06 maybe ... thinking of laser printers 11:05:30 the objects are drawn by a 10-bit DAC so there's a notional 1024x1024 resolution, which is already very high for 1979, but also I believe that straight lines get smoothly interpolated between those points 11:05:39 in theory you could also do smooth circles etc. with analog oscillator circuits 11:06:26 Halite: I don't think "vector LEDs" refers to any kind of well-defined thing... you could invent a vector display technology that uses LEDs in some capacity and call it "vector LED", sure, but it would be pretty different from either a CRT or a traditional LED or LCD display 11:06:53 (But that involves mechanical mirrors. Now I'm sure you can do some fance micromechanics stuff and make it work, but I wouldn't hold my breath waiting for that. :) ) 11:06:59 Is it possible? 11:07:09 is what possible 11:08:22 * int-e is pondering how to actually control a beam of laser light in CRT like fashion. 11:08:45 stupid photons with their zero electrical charge 11:09:09 (laser printers cheat; they just deflect the beam along a single scan line and rely on the printing drum's rotation for vertical displacement) 11:09:22 there is http://en.wikipedia.org/wiki/Electro-optic_effect 11:09:29 specifically http://en.wikipedia.org/wiki/Pockels_effect and http://en.wikipedia.org/wiki/Kerr_effect 11:10:12 I think Media Lab used one of these in their "trillion frame per second" camera 11:10:38 And even laser printers to have be getting replaced by LED printers, because they take less space and less delicate mechanics; building a row of many LEDs is chepaer. 11:10:49 interesting 11:10:58 kmc: nice. 11:11:41 http://web.media.mit.edu/~raskar/trillionfps/ 11:13:13 urgh, what did I do to that sentence? s/to have be/are/ 11:13:15 or maybe not, maybe it was just a material which produces electrons when hit by light, and they deflected those electrostatically 11:14:00 either way the idea is to vary the electric field rapidly so that photons coming from a single point end up spread across a linear detector according to the time they arrived, with picosecond resolution 11:15:15 and you do that again and again for many points in a scene, illuminated by laser pulses the same way each time 11:15:23 and there's your "trillion frame per second" movie 11:16:00 http://1.2.3.11/bmi/www.mit.edu/~velten/press/content/pictures/bottle_photo.jpg looks silly. (note the lack of absence of trade marks) 11:17:56 What's that 1.2.3.11/bmi stuff? 11:18:26 (Link didn't work for me with that; worked without.) 11:18:44 fizzie: a "transparent" proxy that I keep forgetting about. 11:19:03 so the correct link is http://www.mit.edu/~velten/press/content/pictures/bottle_photo.jpg 11:19:34 does your organization legit own 1.2.3? 11:20:08 i spent a few summers at the school which owns 129.186.*.* ; that was super confusing 11:20:12 wonder if they got it at a discount 11:20:19 1.2.3.0/24 was reserved for bogonity, IIRC. 11:20:47 inetnum: 1.2.3.0 - 1.2.3.255; netname: Debogon-prefix. 11:20:58 ah 11:21:02 what does that mean exactly 11:21:15 (It's part of APNIC's range, I remember reading about it when they were introducing 1/8. Both the /24's containing 1.1.1.1 and 1.2.3.4 were reserved.) 11:21:34 kmc: certainly not. (it's a mobile ISP, I'm sure they don't really care about RFCs as long as most customers are happy) 11:21:51 so are they available for private use in the same manner as 10/8 and 192.168/16? 11:21:54 s/are happy/don't complain/ 11:21:56 or are you "not supposed to use them" in some way 11:22:02 You're not supposed to use them, no. 11:22:09 and I have no clue why they aren't using 10.* 11:22:35 Perhaps they were already using 10.* for some other internal purpose. 11:22:44 (I mean, they do use it; my assigned IP is 10.165.126.240) 11:22:55 also I'm amused that MIT can't get any official IPv6 space because IANA is still pissed off that they own 1/256 of the entire IPv4 space 11:24:12 Wait ... 11:24:48 I didn't know that, that is funny. How are they expecting MIT to move off the IPv4 space if they don't even get IPv6 space to migrate to? 11:25:12 well I don't know the details, but probably they have to commit to give it back eventually, or something, and MIT is unwilling to do it? 11:25:15 i don't know really 11:25:23 heard this second- or third-hand 11:25:58 On a different topic, can a vector image composed of lines be separated into a raster image and the slope of the line at each point on each rasterisation? 11:26:46 Halite: I'm not sure what you mean but it sounds like you want to chop up a single vector image into a grid of many vector images (one per "pixel") and yes, you can do that 11:29:13 Well, kind of 11:33:54 Anyway, is it also possible to create a perfect zoom system for raster images? 11:38:43 depends what you mean by "perfect zoom system" but probably no 11:39:33 definitely you can't take a raster photograph and zoom in arbitrarily far 11:39:42 there's a finite amount of information in the original photograph 11:40:38 if your raster image is actually a line drawing, you can try to convert back to a vector image and zoom on that 11:40:49 this sounds relevant: http://null-ptr.blogspot.co.at/2008/06/vector-representation-of-fonts-on-gpu.html (I believe I've even seen a paper with a similar idea somewhere, but I don't remember any details.) 11:41:35 (Not related to "perfect zooming" but to the previous idea of assigning vector images to pixels) 11:42:37 and of course there's all the marching cubes stuff that is also related somehow. 11:44:13 1987. old :) 11:46:21 oh, "meandering triangles" is a cute term. ( https://en.wikipedia.org/wiki/Marching_squares#Meandering_triangles ) 11:50:29 :) 11:53:41 My battery power is so freaking low 11:57:32 How low can my battery get before my iPad refuses to budge? 11:57:40 Have a guess. 11:58:05 i could not care less 11:59:48 8-10% so far 12:00:11 5-8% now 12:00:22 Wifi gone 12:00:59 Or 10-based bound gone 12:01:19 please redirect these updates to #esoteric-halites-ipad 12:01:41 or /dev/null 12:01:43 Oh haws I'm monologue nag yet again 12:01:57 not sure what all those words are, but yes 12:01:58 Keyboard feeling sad 12:16:11 …​ 12:21:25 ... 12:26:07 ꙮꙮꙮ 12:28:10 ꙭꙬꙪ 12:28:57 -!- carado has joined. 12:34:51 ⠈⠞ ⠐⠼ ⠵⠂ ⠠⠵ 12:36:59 . o O ( how do you produce ⪓ in (La)TeX? ) 12:39:50 int-e: nice! 12:42:06 I have something to show you on the PC 12:42:52 -!- Halite has changed nick to Halite[tablet]. 12:43:38 -!- Halite[PC] has joined. 12:44:08 int-e: use 12:46:06 Anyway I wanted to show you https://www.dropbox.com/s/cpujagd162oos0x/JSB%20File%20format.html -- I made it earlier this year. I'd like a bit of advice on how to make the format vector. 12:46:41 Warning: don't try to go on it in Internet Explorer 12:53:10 * int-e feels reminded of http://dilbert.com/strips/comic/1994-10-17/ 12:53:48 -!- FreeFull_ has changed nick to FreeFull. 12:54:29 ?? 12:54:36 I'm trying to make it right now 12:54:51 Heck, cant find the file I saved 12:56:45 http://www.w3.org/TR/SVGTiny12/single-page.html ... that's really stretching the meaning of the word "tiny". 12:59:03 hmm 12:59:59 What if we could mix pixel and vector displays so we can fill while being of high quality? The vector display could override to prevent filling problems. 13:00:48 anyway, that's why I had this association; defining a vector graphics format is a bottomless pit. it's easy enough to hack something together that supports straight lines and filling with solid colors, but people tend to want gradients, transparency, curves, various line styles, arrows on lines, clipping, and so forth. 13:00:58 int-e: Closest I know is \lesseqqgtr from amssymb; that's the ⪋ -- but of course it's not quite the same. (Supplemental Mathematical Operator is very good when it comes to s and slanted -s. 13:01:21 fizzie: Oh sorry, that was a rhetorical question. I don't actually need the symbol. :) 13:02:14 they'll have to approximate curves :p 13:10:05 yay made it 13:10:30 $3 {\leq \atop \geq} 4$ looks ok to me 13:10:57 anyway what a profoundly useless symbol?! 13:18:42 nooodl: hmm, your \geq is \geqslant? 13:19:18 it isn't, i just didn't consider the slant important 13:21:18 Unicode makes a difference there. 13:21:25 (And therefore so should you.) 13:27:06 -!- muskrat has joined. 13:30:59 I am trying arcs though 13:31:15 Hmm 13:39:32 ⣶⣀⣶⢀⡤⢤⡀⢲⡆⠐⣶⠀⣠⠤⣄ 13:39:32 ⠿⠀⠿⠘⠯⠭⠅⠼⠧⠠⠿⠄⠻⠤⠟ 13:39:34 these are cute 13:40:25 I like the regular 2x2 grid blocks. 13:40:39 ▌▌▗ ▐ ▐ ▗ ▟▖▌ ▗ ▖▖▗ 13:40:40 ▛▌▛▘▐ ▐ ▌▌ ▐ ▛▖▛▘▛ ▛▘ 13:40:40 ▘▘▝▘ ▘ ▘▝ ▘▘▘▝▘▘ ▝▘ 13:41:29 (Better resolution with the dots though, that's for sure.) 13:43:32 braille abuse. 13:45:39 -!- muskrat has quit (Quit: Leaving). 13:51:57 My standard JSON bitmap file would be .jsb, but now I've made .vjsb 13:53:15 So far an image would contain arrays of the for max,ya,xb,yb, 13:53:24 Form ax* 13:55:36 E.g. Bitmap [row, row, row, ...] where row is a colour array, vector [[colour, xa, ya, xb, yb], ...] 13:58:37 https://www.dropbox.com/s/rh5r0wgbikq61va/JSB%20Vector%20format.html it's worth a try 14:00:49 -!- L8D has joined. 14:01:02 ░█▀█░█░█░░░█░█░█▀▀░█▀█░█░█ 14:01:05 ░█░█░█▀█░░░░█░░█▀▀░█▀█░█▀█ 14:01:08 ░▀▀▀░▀░▀░░░░▀░░▀▀▀░▀░▀░▀░▀ 14:03:02 FreeFull: Cool. Now make that in JSB vector form using the link I provided. 14:08:42 -!- Sgeo has joined. 14:11:35 -!- Sgeo_ has quit (Ping timeout: 260 seconds). 14:15:47 -!- Slereah_ has quit (Ping timeout: 260 seconds). 14:15:58 Halite[PC]: I can't find anything about that format 14:16:09 Ah, you just made it 14:16:51 [0,0,10,10,0,10,10,0] is a cross? 14:18:16 [[colour,0,0,10,10], [colour,0,10,10,0]] would be the right one, I think 14:18:48 nortti: yep 14:19:08 well actuall 14:19:12 ah, fair enough. 14:19:17 what format is the colour in? 14:19:41 [[colour, "0", "0", "10", "10"], [colour,"0", "10", "10", "0"]] 14:19:48 colour is hex 14:20:06 ah 14:21:06 Oh, it just draws lines 14:21:11 so far 14:21:20 doesnt mean I can't change it 14:25:32 [["red",0,0,30,30],["red",0,30,30,0],["blue",30,15,34,4],["blue",34,4,45,0],["blue",45,0,56,4],["blue",56,4,60,15],["blue",60,15,56,26],["blue",56,26,45,30],["blue",45,30,34,26],["blue",34,26,30,15]] 14:26:20 cool! 14:26:47 why are you using '[]' instead of '()' ? 14:26:52 ["l"/*line*/,style,x0,y0,x1,y1,x2,y2,...] 14:27:04 nortti: the thing is read as arrays 14:27:08 ah 14:27:10 an array of arrays 14:27:13 "Square brackets hold arrays" 14:27:53 JSON has no parentheses as far as I know. 14:28:09 And I'm using json 14:28:15 oh 14:28:18 -!- Taneb has quit (Quit: Leaving). 14:28:21 I see 14:28:29 great for data types 14:29:05 that said I'm happy to read ["l","red",0,30,30,0] as (l 'red 0 30 30 0) :) 14:29:34 I see you're using "l" as future syntax to denote that the object is indeed a line and not a curve? 14:29:42 I might use "line" for that 14:30:16 well, not a (filled) polygon, was my idea 14:31:09 but the main point was that there should be *some* sort of marker to make the thing extensible. 14:32:14 I will indeed add one as the format expands 14:32:42 Who can make an image of a stickman? :D 14:34:37 ask this guy? http://www.etch-a-sketchartist.com/etchasketches/ 14:34:54 Ha? 14:35:19 LOL 14:38:03 http://www.gvartwork.com/gvetchedintime/gallery.php -- this guy is better, and still active. 14:38:53 epic 14:39:16 I have to say arrays seem boring 14:40:48 . 14:42:59 shitty stick figure: [["#ffffff", 1,0, 6,0], ["#ffffff", 1,0, 1,5], ["#ffffff", 6,0, 6,5], ["#ffffff", 1,0, 6,5], ["#ffffff", 3,5, 3,10], ["#ffffff", 3,6, 0,9], ["#ffffff", 3,6, 6,9], ["#ffffff", 3,10, 0,13], ["#ffffff", 3,10, 6,13]] 14:45:59 white on white. 14:45:59 #ffffff makes it entirely white 14:47:32 and its head is an N even if you do make it #000000 14:47:50 at this rate I'll have to set bg notation 14:48:29 k done bg notation 14:48:43 now do [bg, [line], [line], ...] 14:49:06 eg. ["#000FFF", ["#ffffff", 1,5, 5,6]] 14:49:07 ["#000000", ["#ffffff", 1,0, 6,0], ["#ffffff", 1,0, 1,5], ["#ffffff", 6,0, 6,5], ["#ffffff", 1,0, 6,5], ["#ffffff", 3,5, 3,10], ["#ffffff", 3,6, 0,9], ["#ffffff", 3,6, 6,9], ["#ffffff", 3,10, 0,13], ["#ffffff", 3,10, 6,13]] 14:49:43 -!- Slereah has joined. 14:50:02 scaled up: [["#000", 110,100, 160,100], ["#000", 110,100, 110,150], ["#000", 160,100, 160,150], ["#000", 110,150, 160,150], ["#000", 130,150, 130,200], ["#000", 130,160, 100,190], ["#000", 130,160, 160,190], ["#000", 130,200, 100,230], ["#000", 130,200, 160,230]] 14:50:12 fourth line is incorrect nortti 14:50:22 anyway. 14:50:39 ["#fff", ["#000", 110,100, 160,100], ["#000", 110,100, 110,150], ["#000", 160,100, 160,150], ["#000", 110,150, 160,150], ["#000", 130,150, 130,200], ["#000", 130,160, 100,190], ["#000", 130,160, 160,190], ["#000", 130,200, 100,230], ["#000", 130,200, 160,230]] 14:50:49 are you even trying it? 14:51:26 well when you add the bg it works 14:52:01 Halite[PC]: you changed the format :P 14:52:08 slightly yeah 14:52:11 and told you 14:52:16 now do [bg, [line], [line], ...] 14:52:25 ^^ quote from previously ^^ 14:55:04 http://lpaste.net/5940427395184984064 rainbow spiral! 14:55:15 * int-e is staring at carry patterns for Zeckenhaus addition ... they look funny. 14:55:23 -!- sebbu has quit (Ping timeout: 272 seconds). 14:55:25 should add a background i guess 14:55:30 ["black", that] 14:56:04 so cool nooodl 14:56:18 seemed to work without onw 14:56:27 but maybe a line was missed 14:56:56 yep line miss 14:57:16 -!- muskrat has joined. 14:58:14 -!- oerjan has joined. 14:58:43 -!- muskrat has quit (Client Quit). 14:59:26 e.g. http://sprunge.us/WDdd 15:01:56 Updated. Now accepts no bg. 15:02:49 wait 15:03:21 nvm 15:06:33 no bg deal 15:09:27 "What came first, the chicken or the egg?" "The red junglefowl. 15:11:54 Halite[PC]: coelurosaurians hth 15:13:27 It's a good answer. After all, the first chicken was born out of a junglefowl-chicken hybird's egg. 15:14:15 shachaf: i visited https://twitter.com/catcafecalico while I was in Japan <-- /me doesn't get whether that is a café for cats or with cats. also, what is with all the turkish trending on twitter? i guess besiktas might refer to the football team. 15:14:25 http://static.nichtlustig.de/toondb/020119.html ("Both of you want to buy the last can of dog food. This raises the question, who of you came first?") 15:14:46 -!- Slereah has quit (Ping timeout: 245 seconds). 15:15:04 i hate nichtlustig for not working with my custom css 15:15:24 lol 15:15:33 -!- Slereah has joined. 15:16:07 ok http://wandertokyo.com/cat-cafe-calico/ explains in english 15:16:53 for your coffee and toxoplasmosis needs. 15:17:25 * oerjan is probably infected anyway. 15:19:29 * oerjan wonders what might be the youngest ancestor of chickens that _didn't_ have eggs. 15:20:07 probably older than vertebrates. 15:21:05 well i guess it might have to be just before sex. 15:21:19 so something protozoan 15:24:08 int-e: don't look at today's comic hth 15:26:30 good old protozoan times 15:26:38 we never needed to urinate back then 15:26:40 oerjan: hmm. the usual. only one in ten of those are funny anyway :) 15:27:00 and ... another smiley. 15:27:46 anyway oerjan, we don't have eggs how do we multiply 15:28:28 Halite[PC]: women have egg cells. 15:29:21 true 15:29:30 bacteria do too in a way 15:29:35 wat 15:29:56 what came first, the bacteria or the egg cell 15:30:14 bacteria divide and conquer 15:30:19 twist: the bacteria were the egg cells all along? 15:30:57 i have a tooth like this after a biking accident http://static.nichtlustig.de/toondb/131031.html 15:31:22 i guess that means i should hunt down and kill the guy i collided with. or his teeth, maybe. 15:31:41 too bad i was too shocked to remember who it was. 15:31:57 "RADICAL TOOTH" hmm :) 15:32:47 but apparently, no tooth symbol in unicode 15:33:41 find the symbol for radical 15:33:53 √ 15:34:01 maybe there's a hieroglyph and you have to know the word for tooth in egyptian to find it. 15:35:21 I have a middle egyptian textbook 15:35:24 http://shapecatcher.com/ ? 15:35:25 I can check if you want 15:35:49 unfortunately Google Translate doesn't support egyptian 15:36:08 oh, that is broken atm 15:36:16 oh wait unicode doesn't even use the egyptian word, just a numbering scheme 15:36:20 Let's see the Gardiner egyptian hieroglyph sign list 15:36:33 Part D, PARTS OF THE HUMAN BODY 15:36:56 There is "lips with teeth" and "two lips and teeth" 15:37:41 PARTS OF MAMMALS has jawbone of an ox and tusk 15:38:37 又? 15:39:02 `unicode 9F6C 15:39:03 Unknown character. 15:39:10 `unicode 龉 15:39:11 Unknown character. 15:39:45 `unidecode 龉 15:39:46 ​[U+9F89 CJK UNIFIED IDEOGRAPH-9F89] 15:39:57 not much of a name there either. 15:40:28 Definition in English: uneven teeth; to disagree 15:41:03 `unicode 齬 15:41:05 Unknown character. 15:41:18 齬 is definitively 6f6c 15:41:35 `unidecode 齬 15:41:37 ​[U+9F6C CJK UNIFIED IDEOGRAPH-9F6C] 15:41:50 And ... Definition in English: uneven teeth; to disagree 15:41:54 lovely. 15:42:08 `unidecode 15:42:10 ​[U+0002 DUNNO] 15:42:14 lol I dunno 15:42:22 is that one of those simplified vs. traditional ones? 15:42:25 `unidecode 15:42:27 ​[U+0002 DUNNO] [U+0003 DUNNO] [U+001F DUNNO] [U+001D DUNNO] 15:42:59 Slereah: unicode is not magic. only pain. 15:43:40 `unidecode Halite 15:43:42 ​[U+0048 LATIN CAPITAL LETTER H] [U+0061 LATIN SMALL LETTER A] [U+006C LATIN SMALL LETTER L] [U+0069 LATIN SMALL LETTER I] [U+0074 LATIN SMALL LETTER T] [U+0065 LATIN SMALL LETTER E] 15:44:06 48,61,6c,69,74,65 15:44:20 well, as far as I can see, one has four lambdas (I suppose those are the teeth?) and the other one has only one. 15:44:34 hmm http://static.nichtlustig.de/toondb/131023.html 15:46:46 Lemmings are a recurring theme. My favourite goes something like "You want me to buy a bicycle just because all your friends have one, too? ..." "... If all your friends were to jump off a bridge, would you also ..." "... Never mind. I'll buy you the bicycle." 15:47:46 `unidecode 15:47:47 -!- sebbu has joined. 15:47:48 No output. 15:48:35 Ah, not a bicycle, just a scooter. http://static.nichtlustig.de/toondb/020906.html 15:48:57 (and the bridge is a cliff.) 15:51:45 int-e: well if my family did then I would 15:52:38 int-e: something tells me you might be german 15:52:57 myname: that is interesting. what gave me away? 15:53:14 int-e: i can tell from being one myself ;) 15:53:47 wait do we have a german inflation here 15:53:50 -!- impomatic has joined. 15:54:20 you make it sound like it is something bad 15:54:36 well if we go by history there'll soon be billions of you 15:58:05 -!- int-e-19212451 has joined. 15:58:15 * int-e-19212451 grins at oerjan. 15:58:18 -!- int-e-19212451 has quit (Client Quit). 15:58:51 Is there a negative time period before the Big Bang? I've always wondered that 15:59:56 Halite[PC]: there's endless speculation? 16:01:03 The answer is maybe 16:01:04 the math breaks down. you can make all kinds of theories. 16:01:13 Well it doesn't really break down 16:01:20 But it hinges on some other things 16:02:18 i'm not sure PETA approves of this http://static.nichtlustig.de/toondb/130912.html 16:03:29 PETA is my urine. 16:04:14 I ATEP PETA. 16:10:33 i'd recommend buying more matching sets http://static.nichtlustig.de/toondb/130820.html 16:15:32 oerjan: btw I'm not sure whether you're trying to make me feel guilty about linking to that comic, but if so, you're succeeding. 16:15:51 OKAY 16:16:09 Ok. So. A language based on the knappsack problem makes no sense if you have infinite storage 16:16:42 The idea would have been, that a value N occupies N cells 16:17:17 lol 16:17:44 which is boring anyway 16:17:52 you could store N ones 16:18:02 and N zeroes 16:18:10 so it'd esseantilly be bitfuck 16:18:18 ergo -> boring 16:18:20 a value N could also take log_2(N) cells 16:18:57 which makes me think that a log_1(N) = N 16:19:35 Well 16:19:46 my second idea is that you have a 2D (or 1D) storage 16:19:53 and a value N distorts nearby cells 16:20:03 and the higher N, the higher and more cells it distorts 16:20:37 like uhm 256 distorts cell[i +- 1] by 128, cell[i +- 2] by 64 and so on 16:20:53 which is also boring, if you have infinite storage 16:21:02 (i.e just use every 1000iest cell) 16:21:14 Conclusion: Everything is boring if it has infinite storage. 16:21:36 Infinity is super boring. 16:22:01 Not if you mean transfinity 16:22:11 Then it's epic 16:22:59 I have no idea what that even is. 16:23:32 Is that the stuff that is larger than finite stuff 16:23:33 a number that is less than infinity and more than any finite number 16:23:35 but still not infinite? 16:23:41 there are multiple transfinite numbers 16:23:52 I have no idea how that would work 16:23:52 infinitely many infact 16:24:02 It does not make any sense at all (intuitively) 16:24:03 it's defined as the hyperreal numbers 16:24:08 well 16:24:11 How can something be bigger then finite 16:24:13 but not infinite 16:24:21 when everything that is not infinite, is probably finite 16:24:43 What I mean is that they ARE infinite but they're not always going to be equal another of their kind 16:24:58 so 16:25:00 e.g. let's say w is a transfinite ordinal. 2w > w. w+1 > w 16:25:11 so 16:25:12 but 2*infinity makes no sense 16:25:19 It avoids infinity + 1 == infinity? 16:25:40 it's not exactly infinity because there is a number more than w 16:25:55 and with w you can make an infinitesimal -- lets name it e 16:26:13 don't bother explaining it to me 16:26:17 I won't understand it. Seriously. 16:26:28 ... 16:27:11 I don't have enough math background to even understand the explanations ;) 16:27:34 I bet you have computational background though 16:28:00 Probably not, no. 16:28:33 I'm the guy who replaces your broken Ethernet Cable 16:28:57 oh... 16:29:23 Halite[PC]: 2w = w, you mean 2w > w hth 16:29:26 oops 16:29:29 wtf 16:29:38 I'm that kind of computer scientist 16:29:38 *Halite[PC]: 2w = w, you mean w2 > w hth 16:29:42 not really a scientist at all 16:30:18 oerjan: I understand. That's in the surreals. The hyperreals keep communative operations. 16:30:32 no, not surreals. ordinals. 16:30:48 ok thats it I don't like ordinals 16:30:59 * oerjan whistles innocently 16:31:46 (also 1+w = w) 16:31:54 that's like saying 1+2 = 2 16:32:03 or 2+1 = 1 16:32:17 no, it only holds for infinite w. 16:32:23 and precisely then. 16:32:54 the 2w = w holds for limit ordinals. 16:35:24 the limit of {-infinity, ..., x} is x. and that's an infinite set. 16:35:29 Halite[PC]: The only reason I'm here is because I read some paper thingies back when I was a teenager 16:35:33 like uhm 16:35:33 lambda calculus papers 16:35:35 and such 16:36:04 and I wrote interpreters etc. 16:36:59 Halite[PC]: is that supposed to contradict me somehow? 16:37:04 oerjan: You can just refer to http://en.wikipedia.org/wiki/File:Omega-exp-omega-labeled.svg then it's all so clear. 16:37:09 (there are no negative ordinals.) 16:37:56 fizzie: thank you, i was pondering linking to https://en.wikipedia.org/wiki/Ordinal_arithmetic#Cantor_normal_form 16:38:10 the limit of {0, 1/w, 2/w, 3/w, ..., 1, 1 + 1/w, 1 + 2/w, ... x} is x 16:38:14 But that's not a picture at all. :/ 16:38:27 fizzie: true. 16:38:53 -!- Bike has quit (Ping timeout: 272 seconds). 16:39:14 * oerjan has no(*) idea why Halite[PC] keeps dragging surreals and hyperreals into this. ((*) not true) 16:40:42 Ah yes. The practice of lieing then admitting. 16:41:13 it's so practical! 16:42:34 Hyperreals are pretty neat! 16:42:40 As well as DECEPTIVE 16:52:15 -!- muskrat has joined. 17:05:44 -!- Taneb has joined. 17:12:18 * FreeFull gets all surreal 17:12:50 Do you have an apple for a face 17:13:15 No but I have infinitessimals 17:25:37 -!- oerjan has quit (Quit: leaving). 17:33:47 -!- Phantom_Hoover has joined. 17:41:54 -!- muskrat has quit (Quit: Leaving). 18:07:15 I'm still on the search for a book abouth math 18:07:17 there seems to be none. 18:07:43 I have one about 17 equations that changed the world 18:07:53 I think that's at least partially about maths 18:08:02 One of them is actually an inequality which makes me sad 18:08:18 I'm looking for one that is ordered in order of discovery 18:08:35 so I can aquire math knowledge in the order that makes sense 18:08:38 :) 18:09:08 mroman_: http://www.math.wustl.edu/~sk/books/newhist.pdf ? :P 18:09:19 mroman_: also, the historical order frequently doesn't make sense 18:09:32 That can't be 18:09:35 @does not make sense 18:09:35 not make sense not available 18:10:33 When you learn math now you get teached stuff like uhm fourier stuff 18:10:40 but you don't actually know enough 18:10:51 it feels like you're missing something that was invented before that 18:11:41 I figured learning in historical order should prevent me from stumbling upon anything I don't know the basics of 18:11:44 mroman_: no seriously. frequently, the simplifying assumptions that make a topic teachable frequently come after the major theorems are discovered in another context 18:12:04 for instance, newton's calculus, which he used to do all that physics stuff 18:12:08 sucks 18:12:29 isn't that the same as leibniz's calculus? 18:12:46 mroman_: leibniz's notation is much better/easier to use 18:12:48 liebniz's was a bit better 18:13:09 but also, neither of them had any kind of rigorous foundation for it 18:13:29 it involved significant handwaving 18:14:11 and you put in some non-integrable function and stuff blows up and you don't know why 18:14:42 they basically didn't know what they were doing, but managed to get it right enough for physics anyway 18:15:47 yep 18:17:33 that said, i definitely wish i'd had more background before being taught fourier 18:18:28 i think it's pretty common to charge into it as quickly as possible for the benefit of the physicists in the audience 18:35:39 Maybe they had no idea what they were doing 18:35:48 but I'm sure they contributed a lot to math 18:56:10 -!- Bike has joined. 19:14:36 -!- Bike has left. 19:14:48 -!- Bike has joined. 19:18:54 i think the problem with newton's calculus is more that he did all this insane crap with geometry to deal with planets 19:19:07 seriously, have you tried reading the principia, it's crazy 19:28:16 i kind of sympathize with where mroman_'s coming from though, not that i'd actually recommend a fully historical order. mroman_, have you heard of "Mathematics: Its Content, Methods and Meaning"? it's supposed to be real good 19:32:03 -!- sebbu has quit (Quit: reboot). 19:33:53 -!- ais523 has joined. 19:39:19 -!- nisstyre has joined. 19:58:59 I'm going to make a computer algebra system. Wish me luck. 20:01:48 Bike: What about Leibnitz's calculus? 20:04:23 what about it? 20:05:34 How does it compare to Newtons? I've never actually looked at the work Newton and Leibnitz did on calculus 20:05:51 beats me. i don't even know what he was using it for. 20:06:01 i've only read part of newton's because historians seem to like it. 20:06:11 i would guess that they're both near incomprehensible to my modern eyes, though! 20:07:08 Well, it probably took some time to settle on notation 20:07:45 not notation. the general forms of arguments. 20:08:08 this is like, practically before algebraicization. 20:08:31 they weren't just doing the same kind of math in a different alphabet, is what i'm sayin. 20:09:02 though this reminds me, did you know that the derivative was invented by pierre de fermat? 20:10:27 Writing everything out in words is notation too =P 20:10:45 Fermat was a smart guy, no doubt 20:11:52 they're different words, i'm telling you. 20:13:18 Probably latin 20:20:22 -!- zzo38 has joined. 20:23:56 -!- Bike has quit (Quit: Reconnecting). 20:28:11 -!- Sgeo_ has joined. 20:28:13 -!- Bike has joined. 20:28:16 Did you know that the formulae for area of a circle are also related to other integral-based formulas in that they describe the 'inside' of a semantic or geometrical object? 20:28:42 you didn't learn that in calculus? 20:29:09 I self-taught myself. 20:29:23 i did so many problems about finding the volumes of ridiculous shapes, you don't even know 20:29:25 I should still have the knowledge of a child in Year 6. 20:29:55 what's the volume of gabriel's horn 20:30:35 -!- Sgeo has quit (Ping timeout: 246 seconds). 20:31:13 -!- muskrat has joined. 20:31:27 sounds like a multiple of e 20:31:36 ~= 2.718281828459045 20:31:42 -!- muskrat has left. 20:32:31 nope 20:32:33 also you don't need to give me or anyone digits of e really 20:32:35 -!- muskrat has joined. 20:32:43 infinity 20:32:45 or 2 20:32:49 or ... -zzz- 20:33:41 i consider e much more beautiful than pi 20:34:02 i consider the dalles more beautiful than stupid numbers WHAT NOW NERD 20:35:04 -!- muskrat has quit (Client Quit). 20:36:24 there's a train across the entire horizon. 20:36:37 myname: same 20:36:47 myname: I absolutely hate pi 20:37:01 do i need to take some lunch money 20:37:43 Do you prefer to use 2pi as a constant? (When this is done, it is called tau, and I have used it in some programs such as a Csound extension which does this) 20:38:05 no 20:38:14 tau is stupid and bad and smarmy 20:38:20 i just write 'half the circumference of the unit circle' like gauss 20:38:22 as god intended 20:38:39 oh Taneb said ... in @tell 20:39:05 what about 4/3 pau? 20:39:14 Phantom_Hoover: Maybe, but it is sometimes useful (other times, using pi is useful; other times neither is useful) 20:39:30 basedgauss 20:39:44 But I do think e seems a more beautiful than pi, too, I suppose 20:40:09 that's it, give me your lunch money or i'll stuff you in a locker 20:40:22 Phantom_Hoover: Why is it 'smarmy'? Does that mean it is 'elegant'? 20:40:30 yes exactly 20:40:52 it's 'elegant', as interpreted by people whose concept of elegance comes from looking at pictures of fractals and videos by vi hart 20:41:23 ecks dee 20:42:02 i like vi hart :/ 20:42:29 i do too 20:42:32 AND YET 20:42:35 i liked 2pi before it was cool and/or called tau 20:42:45 remember http://www.math.utah.edu/~palais/pi.pdf 20:42:52 no 20:43:05 imo pi², comes up all the time!! in zeta functions!! 20:43:11 and who doesn't like zeta functions 20:43:12 Well, you cannot call a C macro "2pi" so I called it TAU 20:43:28 zzo38: you can call it pi2 20:43:38 anyway the way that pdf draws it is a pi with 3 legs 20:43:43 but that might be confused with Bike's Cool Constant, shachaf 20:43:52 you know it's good when it doesn't even have a unicode codepoint 20:43:53 http://xkcd.com/1292/ 20:43:59 it still needs a symbol, though 20:44:10 shachaf: I suppose if you want that symbol you could make a METAFONT program to draw it 20:44:14 Bike: zeta is based on integral, and integral brings a half factor 20:44:26 It doesn't need a Unicode codepoint 20:44:30 myname: no, it can just go away and be gone 20:44:33 WHOA A HALF FACTOR 20:44:48 yep you heard 20:44:48 shachaf: why? :D 20:46:01 i like the "everybody is equally fucked up" approach 20:46:03 I totally support tau. You can't have a constant which is half of some important value. It has to be that value. 20:46:10 Halite[PC]: Weren't you banned? 20:46:18 oh my glob. 20:46:24 Halite[PC]: tau^2/4 sucks 20:46:34 i think it was a temp ban or something 20:46:36 myname: (tau/2)^2 rocks 20:46:41 it does not 20:46:45 Oh, maybe it was just #haskell and related channels. 20:46:57 actually just #haskell 20:47:05 Halite[PC]: you can't have a constant which is double of some important value 20:47:08 And -lens and others. 20:47:16 myname: unfortunately pi is not an important value 20:47:22 For sending "creative" spam to the people who banned you. 20:48:00 Oh well. 20:48:52 also, pau is very handy for spheres, 2pau is much better than 4/3 pi or 2/3 tau! 20:49:10 oh my 20:49:13 'pau' 20:51:48 idk why all the mathematicians don't support tau 20:52:14 -!- Bike has quit (Ping timeout: 240 seconds). 20:52:34 there's no reason to keep pi, all of the arguments for pi are just rewritten points that tau argued successifully against 20:52:42 because there is no reason to adapt tau :p 20:53:32 -!- shachaf has left. 20:54:41 Phantom_Hoover, ... 20:59:59 -!- MindlessDrone has quit (Quit: MindlessDrone). 21:01:17 -!- Bike has joined. 21:09:29 Taneb, i was playing xcom the other day and there was some random npc called van doorn 21:09:37 :O 21:10:07 what's 48÷2(9+3) 21:10:19 Bike, 2 21:10:22 is this a trick question? 21:10:23 Phantom_Hoover, what did van doorn do 21:10:35 it looks like maybe a check to see how people will interpret associativity 21:10:40 ais523: no, it's just about as interesting as tau. 21:10:44 my answer is, "2 is not a function" 21:10:50 or alternatively, 2 is a function 21:10:52 hmm 21:11:01 is it a good function 21:11:12 it's \f -> f . f 21:11:20 @pl \f -> f . f 21:11:20 join (.) 21:11:23 that's pretty good. 21:11:54 i suppose 9 is the ninth power of a function, and so on? 21:12:14 Taneb, sat around on a burning bridge mostly 21:12:24 Bike: yes 21:12:38 this is how you do numbers in, say, Underload or Unlambda 21:12:43 looks like the expression still has problems, then. 21:14:25 2 is not a function unless there is a function instance for Num 21:14:54 In which case the answer is 24 21:14:59 we're interpreting the other numerals as functions as well, freefull. 21:15:16 well, 9+3 is the twelth-power function 21:15:25 so 2 is that function composed with itself 21:15:35 which is, umm, 144? 21:15:59 I'd expect 9+3 to be the same as 12, even if 9 and 3 are functions 21:16:16 yeah 21:16:43 a+b is defined as a(succ)(b) 21:17:29 clearly + should just be succ so you don't need to define that. 21:18:27 Bike: except that then it'd become nofix rather than infix 21:18:43 as god intended. 21:18:45 hmm… that sounds like an esolang idea 21:18:56 all the operators are nofix, just values 21:19:01 and the data are infix, postfix, etc. 21:26:01 -!- Sprocklem has joined. 21:27:23 -!- Bike has quit (Remote host closed the connection). 21:28:58 -!- Bike has joined. 21:36:41 https://events.ccc.de/congress/2013/wiki/Projects:Hammer_and_Tongs oh, neat. 21:43:56 -!- Bike has quit (Ping timeout: 245 seconds). 21:47:43 if 2 is \f → f.f and 1 is id, what is 0? 21:48:04 easy, 0 21:48:17 -!- Bike has joined. 21:48:56 FreeFull: \f -> id, probably 21:49:21 interesting 21:50:48 FireFly* 21:51:28 yeah, 0 is \f -> id 21:51:39 That makes sense I suppose 21:51:43 -!- shachaf has joined. 21:53:10 -!- Bike has quit (Read error: Connection reset by peer). 21:54:10 It's just representing n as \f -> f^n 21:55:19 -!- Bike has joined. 21:55:47 kind of hard when you try to get negatives, eh 21:56:00 exercise for the bicycle 21:56:29 busycle 21:56:29 Bike: why? 21:56:38 Note that inhabitants of the type (forall a. (a -> a) -> a -> a) exactly correspond to the naturals. 21:56:54 -1 could be \xy.x 21:58:42 Or of the type (forall r. (Maybe r -> r) -> r), of course. I.e. Mu Maybe 21:58:51 hooray for mu 21:59:16 Mu Shachaf 21:59:50 Muion 21:59:53 does that sum with 1 right? 21:59:57 (\xy.x)(succ)(\x.x) => (\y.succ)(\x.x) => succ 22:06:05 -!- Halite[PC] has quit (Ping timeout: 250 seconds). 22:12:50 -!- Taneb has quit (Quit: Leaving). 22:20:06 Guys, is there a theorem that says that all TC things have like 22:20:09 Five THINGS 22:20:30 I know there's one that the smallest Turing machines have 2 states, 3 symbols or vice versa 22:20:57 Logical combinators have 3 symbols, and two rules 22:21:18 OISC has three symbols, and I guess two possible behaviour? 22:21:22 I dunno 22:21:31 Just wondering if there's an overall rule for that 22:23:39 -!- muskrat has joined. 22:25:36 -!- muskrat has left. 22:27:06 -!- Taneb has joined. 22:27:15 Slereah: no 22:27:58 though i'll have to remember that next time i need to be discordian. 22:28:35 After all all algorithms can be defined by a set of symbol, a grammar and transformation rules 22:28:50 So I guess you might be able to put limits on it 22:28:59 basically 'things' isn't something you can generalize across. 22:30:38 i have five things am i tc 22:31:10 shachaf: no. 22:31:22 shachaf: you are clearly a finite state automaton 22:31:32 I have 99 problems but turing completeness isn't one of them 22:31:53 i have ninety-nine problems and it's probably possible to reduce about half of them to the halting problem. 22:33:14 i got 99 problems but an STD ain't one 22:38:45 -!- Bike has quit (Ping timeout: 245 seconds). 22:39:53 -!- Bike has joined. 22:47:45 kmc: i like the joyent response. 22:52:00 can't help but laugh at 'consider yourself chided' 22:54:11 yeah 22:54:18 "God, this is so sad. This is the smallest amount of power I've ever seen go to someone's head." 22:55:36 clearly they never watched the green mile 22:55:38 also glad i'm getting this from someone who calls themselves 'wizandrist' 22:55:39 -!- sebbu has joined. 22:55:39 -!- sebbu has quit (Changing host). 22:55:39 -!- sebbu has joined. 23:00:55 Bike: I'd say 98 problems are reducible 23:01:18 one of my problems is to count exactly how many of the problems are reducible to the halting problem. 23:01:31 For the 99th one, you can't figure out if the algorithm for creating an algorithm will ever halt 23:02:12 I guess it's generally undecidable whether problems reduce to the halting problem? 23:03:44 Any TNT string can be a halting problem for an oracle machine, I think. 23:05:07 Can you state your problem in TNT form in the first place though? 23:05:41 -!- ruddy has joined. 23:05:51 First to convert all of "forall" into "exists" (using the logical negation operators in order to do so), and then, to try them until one number succeeds the check. 23:06:12 FreeFull: Perhaps not; what is your problem anyways? 23:06:28 How to win at life 23:06:37 with brawndo 23:08:14 -!- Bike has quit (Quit: Reconnecting). 23:08:19 -!- Bike_ has joined. 23:15:50 -!- Bike_ has quit (Ping timeout: 264 seconds). 23:18:48 -!- oerjan has joined. 23:24:00 Stephen Wolfram sounds like an esolanger with too much money and power 23:24:52 `run echo "Stephen Wolfram is an esolanger with too much money and power." >wisdom/wolfram 23:24:56 No output. 23:25:06 NOW IT'S OFFICIAL 23:25:10 :O 23:25:27 (i apologize to all those who don't want to be in the same category as him.) 23:25:28 oerjan: should have mentioned the source 23:25:46 "Stephen Wolfrom is an esolanger with too much money and power. Taneb invented him." 23:25:50 it's a different sort of esolanging 23:26:01 esolanging... 23:26:05 ok Taneb convinced me. 23:26:15 `run echo "Stephen Wolfram is an esolanger with too much money and power. Taneb invented him." >wisdom/wolfram 23:26:19 No output. 23:26:26 `? tanebventions 23:26:28 Tanebventions include D-modules, automatic squirrel feeders, the torus, and Go. 23:26:59 `? automatic squirrel feeders 23:27:01 automatic squirrel feeders? ¯\(°​_o)/¯ 23:27:03 :( 23:27:16 `run sed -i 's/torus,/torus, Stephen Wolfram,/' wisdom/tanebventions 23:27:17 sed: can't read wisdom/tanebventions: No such file or directory 23:27:22 oops 23:27:25 `run sed -i 's/torus,/torus, Stephen Wolfram,/' wisdom/tanebvention 23:27:28 No output. 23:28:02 `run ln -s wisdom/{stephen ,}wolfram 23:28:04 go? wtf? 23:28:06 No output. 23:28:12 `? stephen wolfram 23:28:13 stephen wolfram? ¯\(°​_o)/¯ 23:28:15 `? Go 23:28:16 oops 23:28:17 Go is a common verbal game programming language invented by the Germanic Taneb tribes in the strategic territories of East Asia. 23:28:21 `? wolfram 23:28:23 Stephen Wolfram is an esolanger with too much money and power. Taneb invented him. 23:28:44 oh wait 23:28:55 i don't even 23:28:58 `run ls wisdom/*wolfram 23:29:00 wisdom/wolfram 23:29:21 `run ln -s wisdom/{,"stephen "}wolfram 23:29:24 ln: accessing `wisdom/stephen wolfram': Not a directory 23:29:45 ok what does that expand to 23:30:06 `run echo wisdom/{,"stephen "}wolfram 23:30:07 wisdom/wolfram wisdom/stephen wolfram 23:30:35 `echo "Automatic squirrel feeders are just feeders in the category of automatic squirrels. Taneb invented them" > wisdom/automatic\ squirrel\ feeders # i got that wrong didn't i 23:30:37 ​"Automatic squirrel feeders are just feeders in the category of automatic squirrels. Taneb invented them" > wisdom/automatic\ squirrel\ feeders # i got that wrong didn't i 23:30:42 `run echo "Automatic squirrel feeders are just feeders in the category of automatic squirrels. Taneb invented them" > wisdom/automatic\ squirrel\ feeders # i got that wrong didn't i 23:30:46 No output. 23:30:47 oh wait 23:30:56 `? automatic squirrel feeders 23:30:58 Automatic squirrel feeders are just feeders in the category of automatic squirrels. Taneb invented them 23:31:07 `run ln -s wolfram wisdom/"stephen wolfram" 23:31:08 ln: accessing `wisdom/stephen wolfram': Not a directory 23:31:22 `which ln 23:31:23 ​/bin/ln 23:31:43 `ls wisdom/*wolfram 23:31:44 ls: cannot access wisdom/*wolfram: No such file or directory 23:31:48 `run ls wisdom/*wolfram 23:31:49 ls: cannot access wisdom/stephen wolfram: Not a directory \ wisdom/wolfram 23:32:00 lol 23:32:06 `? wolfram 23:32:08 Stephen Wolfram is an esolanger with too much money and power. Taneb invented him. 23:32:14 `? stephen wolfram 23:32:15 also, i like the automatic squirrel feeders 23:32:15 stephen wolfram? ¯\(°​_o)/¯ 23:32:22 `run touch wisdom/"cannot access wisdom/stephen wolfram: Not a directory" 23:32:23 touch: cannot touch `wisdom/cannot access wisdom/stephen wolfram: Not a directory': No such file or directory 23:32:47 `ls -l wisdom 23:32:48 ls: invalid option -- ' ' \ Try `ls --help' for more information. 23:32:55 `run touch this 23:32:58 `run ls -d wisdom 23:32:59 No output. 23:33:00 `ls wisdom/"stephen wolfram" 23:33:01 As the wisdom directory contains many files named after nicks, listing it in public annoys people. Try https://dl.dropboxusercontent.com/u/2023808/wisdom.pdf instead. 23:33:01 ls: cannot access wisdom/"stephen wolfram": No such file or directory 23:33:03 :( 23:33:09 `run ls wisdom/"stephen wolfram" 23:33:10 ls: cannot access wisdom/stephen wolfram: Not a directory 23:33:17 `run rm wisdom/"stephen wolfram" 23:33:20 hey, this ls is broken 23:33:22 No output. 23:33:26 ls -d specifically doesn't list the contents of a directory 23:33:29 just the directory itself 23:33:39 You should remove that ls anyways 23:33:51 `run ls wisdom/ste* 23:33:52 The first few files aren't named after nicks, for one thing 23:33:53 ls: cannot access wisdom/ste*: No such file or directory 23:34:07 zzo38 has a point, although i don't like it. 23:35:00 `run ln -s wolfram wisdom/"stephen wolfram"; ? "stephen wolfram" 23:35:03 ln: creating symbolic link `wisdom/stephen wolfram': File exists \ bash: -: command not found 23:35:14 argh 23:35:24 am i getting the order wrong or something 23:36:30 `run ln -T -s wolfram wisdom/"stephen wolfram"; ? "stephen wolfram" 23:36:32 ln: creating symbolic link `wisdom/stephen wolfram': File exists \ bash: -: command not found 23:36:32 File exists means your rm doesn't seem to have worked 23:36:38 oh. 23:36:46 `? stephen wolfram 23:36:46 `ls wisdom/*wolfram 23:36:47 ls: cannot access wisdom/*wolfram: No such file or directory 23:36:48 Stephen Wolfram is an esolanger with too much money and power. Taneb invented him. 23:36:49 Try /bin/ls instead of ls if you need to I suppose 23:36:54 `run ls wisdom/*wolfram 23:36:56 wisdom/stephen wolfram \ wisdom/wolfram 23:37:02 `run /bin/ls -d wisdom 23:37:02 wat. 23:37:03 wisdom 23:37:10 `? wolfram 23:37:12 Stephen Wolfram is an esolanger with too much money and power. Taneb invented him. 23:37:19 ok it works? 23:37:26 `run ls -l wisdom/*wolfram 23:37:28 lrwxrwxrwx 1 5000 0 7 Nov 30 23:35 wisdom/stephen wolfram -> wolfram \ -rw-r--r-- 1 5000 0 83 Nov 30 23:26 wisdom/wolfram 23:37:30 `? run rm -f "wisdom/stephen wolfram" 23:37:32 run rm -f "wisdom/stephen wolfram"? ¯\(°​_o)/¯ 23:37:33 *sigh* 23:37:37 `run rm -f "wisdom/stephen wolfram" 23:37:41 No output. 23:37:48 `? stephen wolfram 23:37:50 stephen wolfram? ¯\(°​_o)/¯ 23:37:55 oerjan: There you go 23:38:09 `? bc 23:38:11 bc ௵௵௵௵௵௵௵௵௵௵௵௵௵௵௵௵௵௵௵௵௵௵௵௵௵௵௵௵௵௵௵௵௵௵௵௵௵௵௵௵௵௵௵௵௵௵௵௵௵௵௵௵௵௵௵௵௵௵௵௵௵௵௵௵௵௵௵௵௵௵௵௵௵௵௵௵௵௵௵௵௵௵௵௵௵௵௵௵௵௵௵௵௵௵௵௵௵௵௵௵௵௵௵௵௵௵௵௵௵௵௵௵௵௵௵ 23:38:18 FreeFull: "There you go, I broke it for you"? 23:38:41 fizzie: He's been trying to delete it 23:39:25 FreeFull: To create a symlink, which based on the last ls was already there. 23:40:01 Oh, didn't notice that 23:40:41 `run ln -s wisdom/wolfram "wisdom/stephen wolfram" && echo "success" 23:40:45 ln: accessing `wisdom/stephen wolfram': Not a directory 23:41:39 Yeah, I think you just generated the wrong symlink again. 23:41:43 `run ls -l wisdom/*wolfram 23:41:44 lrwxrwxrwx 1 5000 0 14 Nov 30 23:40 wisdom/stephen wolfram -> wisdom/wolfram \ -rw-r--r-- 1 5000 0 83 Nov 30 23:26 wisdom/wolfram 23:42:00 (That's supposed to point at "wolfram", not "wisdom/wolfram".) 23:42:08 Oh, you're right 23:42:20 XD 23:42:22 I thought that since it errored it wouldn't make a symlink though 23:42:36 aimake's symlink command has a more sensible argument pattern 23:42:41 `revert 23:42:42 Done. 23:42:43 you give the source and destination relative to . 23:42:52 and it automatically works out what should be put in the symlink 23:42:54 `run /bin/ls -l wisdom/*wolfram 23:42:55 ​-rw-r--r-- 1 5000 0 83 Nov 30 23:26 wisdom/wolfram 23:43:01 `run ln -s wolfram "wisdom/stephen wolfram" 23:43:02 No output. 23:43:09 `? stephen wolfram 23:43:11 Stephen Wolfram is an esolanger with too much money and power. Taneb invented him. 23:43:14 whew 23:43:21 oerjan saves the day 23:43:27 oerjan: Much ado about a Wolfram. 23:43:29 i have no idea why that didn't seem to work the first time i did it. 23:43:39 fizzie: that's the usual, isn't it 23:45:30 oh also 23:45:53 `run mv wisdom/"automatic squirrel feeder"{s,} 23:45:57 No output. 23:45:58 *cough* 23:46:54 `run sed -i 's/$/./' wisdom/"automatic squirrel feeder" 23:46:58 No output. 23:47:06 `? automatic squirrel feeders 23:47:08 Automatic squirrel feeders are just feeders in the category of automatic squirrels. Taneb invented them. 23:48:54 `run grep "Taneb invented them." "wisdom/*" | wc -l 23:48:55 grep: wisdom/*: No such file or directory \ 0 23:49:03 `run grep "Taneb invented them." wisdom/* | wc -l 23:49:07 grep: wisdom/stephen wolfram: Not a directory \ 3 23:49:13 Blah 23:49:36 What's up with this not a directory error 23:49:46 `ls wisdom/stephen wolfram 23:49:48 ls: cannot access wisdom/stephen wolfram: Not a directory 23:50:01 `run ls wisdom/"stephen wolfram" 23:50:03 ls: cannot access wisdom/stephen wolfram: Not a directory 23:50:03 It's has magically turned to the wrong symlink again. 23:50:08 `run ls -l wisdom/*wolf* 23:50:10 lrwxrwxrwx 1 5000 0 14 Nov 30 23:45 wisdom/stephen wolfram -> wisdom/wolfram \ -rw-r--r-- 1 5000 0 83 Nov 30 23:26 wisdom/wolfram 23:50:10 -!- ais523 has quit. 23:50:14 `? stephen wolfram 23:50:16 stephen wolfram? ¯\(°​_o)/¯ 23:50:19 I don't know what's up with that. 23:50:21 argh 23:50:23 How did that happen 23:50:45 oh whatever 23:51:24 `run rm "wisdom/stephen wolfram"; cp wisdom/{,"stephen "}wolfram 23:51:25 The repository browser has disapparated oerjan's fixups. 23:51:28 No output. 23:51:34 `? stephen wolfram 23:51:36 Stephen Wolfram is an esolanger with too much money and power. Taneb invented him. 23:51:43 `run grep "Taneb invented them." wisdom/* | wc -l 23:51:45 3 23:51:49 `run grep "Taneb invented" wisdom/* | wc -l 23:51:51 5 23:52:30 i guess there has been previous warnings that symbolic links don't work well with HackEgo. 23:52:33 `run grep -li 'taneb invented' wisdom/* 23:52:34 *have 23:52:36 wisdom/automatic squirrel feeder \ wisdom/d-module \ wisdom/stephen wolfram \ wisdom/torus \ wisdom/wolfram 23:52:47 Impressive list. 23:52:53 I hope he'll put all that in his CV. 23:53:01 -!- _46bit has joined. 23:53:07 <_46bit> Hi Taneb! 23:53:11 Hi 23:53:14 `relcome _46bit 23:53:17 ​_46bit: Welcome to the international hub for esoteric programming language design and deployment! For more information, check out our wiki: . (For the other kind of esoterica, try #esoteric on irc.dal.net.) 23:53:37 <_46bit> Esoteric bot welcome colouring as well! 23:54:01 Yup 23:54:03 `help 23:54:03 Runs arbitrary code in GNU/Linux. Type "`", or "`run " for full shell commands. "`fetch " downloads files. Files saved to $PWD are persistent, and $PWD/bin is in $PATH. $PWD is a mercurial repository, "`revert " can be used to revert to a revision. See http://codu.org/projects/hackbot/fshg/ 23:54:16 fungot, hi 23:54:17 Taneb: fnord __theo but i don't like 23:54:20 ^source 23:54:20 https://github.com/fis/fungot/blob/master/fungot.b98 23:55:13 beware of _46bit, e's a massive multiplayer online krysz. 23:55:18 *-ly 23:56:42 also i suspect Taneb invented him. 23:56:56 what's a "TNT string"? 23:57:11 kmc: Something Hofstadter made up, I think. 23:57:23 kmc, it's a fuse for an explosive 23:57:32 a very unsafe text representation format. 23:57:58 It'd be interesting if wisdom factoids were actually scripts in some programming language 23:58:21 Bonus points for making all the current ones work fine in the new system 23:58:28 kmc, more seriously, it's a string in Typographical Number Theory 23:58:52 oh right