00:00:31 -!- CodingBat has quit.
00:08:30 -!- tromp has joined.
00:20:11 -!- augur has quit (Ping timeout: 246 seconds).
00:22:28 -!- yorick has quit (Remote host closed the connection).
00:51:35 -!- augur has joined.
00:59:58 -!- augur_ has joined.
01:00:33 -!- mhi^ has quit (Quit: Lost terminal).
01:03:14 -!- augur has quit (Ping timeout: 246 seconds).
01:19:04 -!- tromp has quit (Remote host closed the connection).
01:19:37 -!- tromp has joined.
01:20:42 -!- Phantom_Hoover has quit (Ping timeout: 240 seconds).
01:23:54 -!- tromp has quit (Ping timeout: 240 seconds).
01:25:32 <ion> http://docs.oracle.com/javase/8/docs/api/java/util/function/package-summary.html
01:39:26 -!- ^v has quit (Read error: Connection reset by peer).
01:39:54 -!- ^v has joined.
01:43:40 -!- edwardk has joined.
01:55:23 -!- ^v has quit (Read error: Connection reset by peer).
01:55:50 -!- ^v has joined.
01:57:30 -!- nisstyre has joined.
02:04:46 -!- Sorella has quit (Quit: It is tiem!).
02:25:39 -!- glogbackup has joined.
02:40:32 -!- ^v has quit (Ping timeout: 252 seconds).
03:01:20 -!- ^v has joined.
03:06:03 -!- edwardk has quit (Quit: Computer has gone to sleep.).
03:06:07 -!- nisstyre has quit (Quit: WeeChat 0.4.3).
03:59:31 -!- edwardk has joined.
04:05:43 <Sgeo> http://docs.oracle.com/javase/8/docs/api/java/util/function/Supplier.html
04:05:45 <Sgeo> How functional.
04:06:15 <Sgeo> (ok, so it makes perfect sense in any impure language)
04:07:22 <kmc> is Java 8 out yet?
04:08:15 <kmc> java has lambda now
04:08:51 <kmc> truly the future is upon us
04:09:17 <Bike> "The CheckPerson interface is a functional interface. A functional interface is any interface that contains only one abstract method. (A functional interface may contain one or more default methods or static methods.) Because a functional interface contains only one abstract method, you can omit the name of that method when you implement it." incredible imo
04:12:12 <Bike> roster.stream().filter(p -> p.getGender() == Person.Sex.MALE && p.getAge() >= 18 && p.getAge() <= 25).map(p -> p.getEmailAddress()).forEach(email -> System.out.println(email));
04:12:24 <Bike> love me some dot chains
04:13:35 <Sgeo> Without syntax support there tends to be difficulty interleaving multiple sources in a non-ugly (syntactically) way, what does that look like here?
04:15:16 <Bike> "local variables referenced from a lambda expression must be final or effectively final" weak
04:16:37 <Bike> i'm pretty excited to find out if "effectively final" is supposed to be reliable
04:18:46 -!- ter2 has joined.
04:27:16 -!- kwertii has quit (Quit: kwertii).
04:37:59 -!- password2 has joined.
04:39:38 -!- adu has joined.
04:40:08 -!- ter2 has changed nick to tertu.
04:40:12 -!- tromp has joined.
05:06:09 -!- ^v has quit (Read error: Connection reset by peer).
05:06:37 -!- ^v has joined.
05:19:19 -!- `^_^v has quit (Ping timeout: 252 seconds).
05:25:49 -!- tertu has quit (Ping timeout: 252 seconds).
05:39:20 -!- ^v has quit (Read error: Connection reset by peer).
05:39:48 -!- ^v has joined.
05:52:01 -!- FreeFull has quit.
06:00:31 <kmc> does that mean mutability inference
06:02:20 <Bike> couldn't find a solid definition before i got bored
06:02:33 <Bike> basically "it could be declared final no problem"
06:06:23 -!- ^v has quit (Quit: http://i.imgur.com/DrFFzea.png).
06:13:23 <shachaf> if i used Sgeo as a verb would people understand what i mean
06:17:23 <quintopia> something to do with every language beingc close to perfect but no cigar
06:36:49 -!- adu has quit (Quit: adu).
06:46:13 -!- augur_ has quit (Read error: Connection reset by peer).
06:46:40 -!- augur has joined.
06:49:35 <fizzie> "A local variable or a method, constructor, lambda, or exception parameter is effectively final if it is not declared final but it never occurs as the left hand operand of an assignment operator (§15.26) or as the operand of a prefix or postfix increment or decrement operator (§15.14, §15.15)."
06:50:06 <fizzie> "In addition, a local variable whose declaration lacks an initializer is effectively final if all of the following are true: * It is not declared final. * Whenever it occurs as the left-hand operand of an assignment operator, it is definitely unassigned and not definitely assigned before the assignment; that is, it is definitely unassigned and not definitely assigned after the right-hand ...
06:50:12 <fizzie> ... operand of the assignment (§16 (Definite Assignment)). * It never occurs as the operand of a prefix or postfix increment or decrement operator."
06:50:15 <fizzie> In case you were wondering.
06:51:42 <fizzie> The definition (npi) of definite assingment is unfortunately too long to quote.
06:52:04 <Bike> very exciting.
06:52:20 -!- oerjan has joined.
06:52:44 <quintopia> i'll be in your country in two days!
06:53:35 <oerjan> AAAAAAAAAAAAAAAAAAAAAAAAA
06:54:48 <quintopia> i might even have to eat your food
06:57:02 <shachaf> double letters are my nemesis
06:57:28 <quintopia> i will be avoiding it though, since i hear it costs half a day's dsalary to get dinner
06:58:26 <oerjan> and here i was wondering if it was still season for skreimølje
06:58:59 * oerjan also realizes he hasn't eaten it himself in a long time
06:59:39 <oerjan> shachaf: are you being stalked by the evil ZZ?
07:00:39 -!- `^_^v has joined.
07:00:57 <oerjan> `addquote <kmc> i came back here and misread my own statement as "fancy C++ mushrooms"
07:00:58 <HackEgo> 1191) <kmc> i came back here and misread my own statement as "fancy C++ mushrooms"
07:03:44 <ion> The reverse of ierks
07:04:34 <oerjan> it's cod, except not just any cod, but the best kind
07:08:56 -!- augur has quit (Read error: Connection reset by peer).
07:09:15 <ion> I should try it some time.
07:09:25 -!- augur has joined.
07:17:09 -!- tromp__ has joined.
07:19:29 -!- tromp has quit (Ping timeout: 246 seconds).
07:22:19 <Sgeo> Wait, it shouldn't even be possible to write a forall f. (Functor f) => f a -> a
07:25:12 <oerjan> Sgeo: consider f = Const b
07:25:41 <Sgeo> shouldn't be = isn't
07:25:48 <Sgeo> So how do I deal with this:
07:25:54 <Sgeo> > class Walk p => Settable p where
07:25:54 <Sgeo> > mapping :: Functor f => p a b -> p (f a) (f b)
07:25:56 <lambdabot> from the context (GHC.Base.Functor f)
07:25:56 <lambdabot> it :: GHC.Base.Functor f => p a b -> p (f a) (f b)
07:26:20 <oerjan> also, can you use ~ on non-* kinds
07:26:45 <Sgeo> So, how would I dimap on the result of that mapping?
07:26:58 <Sgeo> It looks like I would have to write a (Functor f) => f a -> a
07:27:18 <Sgeo> Well, if I wanted another p a b
07:28:01 <oerjan> Sgeo: um that's a class it's not supposed to be implementable for all p is it?
07:28:38 <oerjan> for (->) it would be the usual fmap, no?
07:28:43 <Sgeo> Not asking for a fully general implementation, just trying to see how to use it to implement a... setter, I think
07:29:03 <shachaf> actually, never mind, don't answer that
07:29:06 <Sgeo> I think I may be pattern matching the dimap on usage of whatever a bit excessively
07:29:17 <Sgeo> \f g -> dimap blah blah . first'
07:32:13 <Sgeo> How do I make class definitions in lambdabot?
07:32:36 <Sgeo> Or maybe I do need the walk instance, which I don't understand yet
07:36:03 <oerjan> Sgeo: with @let class ...
07:43:03 <oerjan> also, happy International Workers' Day, you filthy capitalist americans!
08:00:47 <oerjan> i find your calendar to be off https://en.wikipedia.org/wiki/National_Hug_Day
08:01:39 <shachaf> i'm referring to international hug day, obviously
08:01:59 <oerjan> stupid wikipedia redirects hug day to that.
08:02:23 <shachaf> imo linux should support hug pages
08:03:12 <oerjan> machines cannot hug. right fungot?
08:03:12 <fungot> oerjan: there now ensued a mighty fnord and foaming in the noisome pits; the awful formula which had yielded such nameless fnord the message in ordinary english. i boarded it and looked vainly about for the light fnord as i was pushed slowly and inexorably toward the
08:03:14 <kmc> every day is hug day
08:03:35 <oerjan> see, fungot cares nothing for hugs.
08:03:35 <fungot> oerjan: they now slid along at great speed, once passing and fnord another galley of kindred form, but generally it would produce no effect at all, but floated easily in the blue harbour, and watched at the head of the glen. someone telephoned the news to others and gather such troops as might be necessary.
08:03:36 <kmc> oerjan: http://pbfcomics.com/115/
08:03:42 <lexande> shachaf: international free hugs day is reportedly july 5 this year
08:03:52 <lexande> maybe your day is for nonfree hugs
08:03:59 <lexande> but that doesn't seem great
08:04:08 <kmc> free as in hugs
08:05:06 <shachaf> free hugs were invented when somebody left adjoint where a mathematician could find it
08:06:03 <shachaf> anyway, today is hug day, ok
08:06:12 <shachaf> i'm at least as reliable on this matter as wikipedia
08:07:17 <lexande> i feel like this day is pretty heavily booked already
08:07:48 <lexande> what with generic-month-change-thigns and maypoles and international workers and outdoor fucking starts today
08:08:49 <shachaf> oh, right, it's pay-rent-day or something
08:13:51 <kmc> mailman reminder day
08:18:09 <Taneb> Happy shachaf hug day
08:18:21 <kmc> every day is kmc hug day
08:18:38 <Taneb> kmc, is every day hug kmc?
08:18:49 -!- Taneb has left ("Leaving").
08:18:53 -!- Taneb has joined.
08:18:58 <Taneb> I did not mean to part
08:19:05 <Taneb> As I was going to say
08:19:19 <Taneb> Then I'm sorry I haven't hugged you on any hug kmc day so far, kmc!
08:19:31 * kmc hugs Taneb
08:23:32 <shachaf> Taneb: when you come to bayhac we can have a special hugs group where we refuse to use ghc and also we hug people
08:23:50 <shachaf> kmc probably won't be there though i heard he was invited or something
08:24:13 <Taneb> Unfortunately it will be a long time before I can bayhac
08:24:18 <Taneb> I am slightly on the wrong continent
08:24:28 <Taneb> And too much a student to be able to afford things
08:36:01 <coppro> you guys should meet halfway in waterloo
08:47:56 -!- drlemon has quit (Ping timeout: 252 seconds).
08:52:45 -!- MindlessDrone has joined.
09:01:53 -!- trout has quit (Quit: I found 1 in /dev/zero).
09:03:20 <shachaf> ion: What were the restrictions on .fi domains, again?
09:03:34 <shachaf> Two-letter domains were generally reserved?
09:04:15 <ion> shachaf: https://domain.fi/info/en/index/hakeminen/kukavoihakea.html
09:05:47 <ion> shachaf: Yes. The last time i looked, a domain consisting of some arbitrary digit and some arbitrary letter was free. I ended up picking heh.fi.
09:06:31 <shachaf> I thought of using that pattern but I'm not so sure.
09:09:57 -!- password2 has quit (Ping timeout: 245 seconds).
09:11:47 <ion> s6.fi is free.
09:12:21 <shachaf> (But previously I tried to register a reserved domain name and it showed up as "free" and failed after taking my payment.)
09:12:36 <shachaf> (Which was refunded to my account as registrar credit. But still.)
09:14:30 <shachaf> s6 is slightly difficult to pronounce.
09:15:37 -!- password2 has joined.
09:15:43 <nortti> alternatively, /æsku:si/
09:16:46 <ion> or /æsku:s/ in spoken Finnish
09:17:04 <shachaf> imo swedish would also be valid
09:19:11 -!- variable has joined.
09:19:11 -!- variable has quit (Changing host).
09:19:11 -!- variable has joined.
09:23:13 <shachaf> 6f might be another option...
09:23:44 <shachaf> Probably starting with a digit is a bad idea.
09:34:30 -!- Phantom_Hoover has joined.
09:40:18 <shachaf> What's with low-contrast UI design?
09:41:13 <oerjan> shachaf: it's so we know who to put against the wall when the revolution comes hth
09:54:30 <int-e> shachaf: it's for people who buy modern displays and still set them to 100% contrast, 100% brightness.
09:56:29 <int-e> (I've never heard of low contrast UI design before.)
09:56:38 -!- coppro has quit (Ping timeout: 240 seconds).
09:57:44 -!- coppro has joined.
10:14:46 -!- boily has joined.
10:15:45 -!- conehead has quit (Quit: Computer has gone to sleep).
10:24:17 -!- nucular has joined.
10:24:17 -!- nucular has quit (Changing host).
10:24:18 -!- nucular has joined.
10:39:07 -!- password2 has quit (Ping timeout: 245 seconds).
10:52:30 -!- password2 has joined.
10:57:27 -!- oerjan has quit (Quit: leaving).
11:02:12 -!- boily has quit (Quit: DISSOLVED CHICKEN).
11:24:58 <Taneb> Good afternoon, #esoteric
11:25:21 <b_jonas> enjoying the long weekend, if you have one?
11:26:03 <olsner> I stupidly didn't take tomorrow off, so it's a very short weekend today
11:26:20 <Taneb> I don't believe I have much time off at all
11:26:35 <Taneb> Although right now I don't seem to have much time on, either
11:40:00 <Taneb> Why is this weekend special?
11:45:53 <Taneb> Whoa, there's going to be a zoo opening in my university to relieve exam stress
11:46:50 <Slereah> Then you can watch animals in prison
11:49:29 -!- idris-ircslave has quit (Ping timeout: 255 seconds).
11:50:55 -!- Melvar has quit (Ping timeout: 252 seconds).
11:52:30 -!- yorick has joined.
11:55:36 -!- Melvar has joined.
11:56:58 <Phantom_Hoover> you could go and do this: http://www.youtube.com/watch?v=ZQ12DDe4ag0&t=42s
12:27:49 <impomatic> Someone here is interested in the history of computer viruses, but I can't remember who...
12:28:06 <impomatic> So I'll just leave this here :-) http://corewar.co.uk/creeper.htm
12:29:10 <nortti> at least the one did not explode
12:30:19 -!- Patashu has joined.
12:33:37 <Slereah> impomatic : I like how it seems to be written on a receipt
12:33:37 <impomatic> No, nothing like that. Most users wouldn't even be away it had visited.
12:35:28 <Slereah> I remember reading a PhD thesis written in the 60's
12:35:45 <Slereah> Reading quantum mechanics on typewriter isn't fun
12:35:56 <impomatic> nortti: I'm rubbish at multitasking! Results in typos, talking nonsense, etc :-D
12:38:21 -!- Sgeo has quit (Read error: Connection reset by peer).
12:40:26 <Taneb> I should write more things on typewriter
12:41:42 <nortti> are replacement "ink tapes" still available?
12:43:59 <Slereah> The NSA will steal your ribbons
12:44:16 <nortti> wasn't that just with electric ones?
12:44:39 <Taneb> No, just with the mechanical ones
12:48:44 <Taneb> I mean, the electricity scares the NSA away
12:51:24 -!- drdanmaku has quit (Quit: Connection closed for inactivity).
12:52:24 -!- tromp__ has quit (Remote host closed the connection).
13:06:04 -!- tertu has joined.
13:12:50 -!- Phantom_Hoover has quit (Ping timeout: 276 seconds).
13:15:39 <impomatic> http://es.wikipedia.org/wiki/Reaper_(antivirus) is one the most inaccurate pages I've seen on Wikipedia! 21 errors in 24 sentences.
13:16:11 -!- Slereah_ has joined.
13:16:23 <impomatic> I would fix it, but my Spanish isn't up to scratch.
13:19:24 <Jafet> "En este suceso esta inspirado el enemigo final de la serie de anime Digimon Tamers" vital facts
13:19:35 -!- Slereah has quit (Ping timeout: 240 seconds).
13:19:43 <Jafet> http://math.stackexchange.com/a/261036 "int 1/(x+1) dx = int 1/x + 1/1 dx = int 1/x dx + int 1/1 dx = log x + log 1 = log (x+1) + C"
13:26:57 <b_jonas> Jafet: http://www.xkcd.com/759/
13:27:13 -!- AnotherTest has joined.
13:28:51 -!- nooodl has joined.
13:31:02 -!- tertu has quit (Ping timeout: 276 seconds).
13:33:32 <Taneb> I wonder how long ago the minecraft side-channel was actually used
13:34:01 <nortti> what minecraft side-channel?
13:34:33 <Taneb> We used to have our own minecraft server!
13:42:44 -!- Sprocklem has quit (Ping timeout: 276 seconds).
13:53:27 -!- tertu has joined.
14:17:59 -!- Patashu has quit (Ping timeout: 254 seconds).
14:26:18 -!- Sprocklem has joined.
14:44:32 -!- `^_^v has quit (Ping timeout: 255 seconds).
14:47:29 -!- `^_^v has joined.
15:12:59 -!- Sorella has joined.
15:16:59 -!- tertu has quit (Disconnected by services).
15:16:59 -!- ter2 has joined.
15:18:23 <Taneb> I'm going to ramble about data structures for a bit
15:18:33 <Taneb> I've had a bit of caffeine and sugar so this may not make sense
15:19:29 <Taneb> (by a bit of sugar, I mean it says on the bottle that in 250ml there's 29% of the RDA for an average adult)
15:19:42 <Taneb> (I've had about 7 times that)
15:20:28 -!- ter2 has quit (Read error: Connection reset by peer).
15:20:53 <Taneb> Anyway, I want to have some sort of queue
15:21:04 <Taneb> But I also want to be able to move things to the back of the queue?
15:21:06 -!- ter2 has joined.
15:22:23 -!- nucular_ has joined.
15:22:31 <Taneb> Well, it's less of a queue and more of a "everything has an associated time"
15:22:50 -!- nucular has quit (Ping timeout: 276 seconds).
15:24:45 <olsner> and the queue is sorted by the associated time? sounds like a priority queue
15:25:31 <olsner> but some of those are not great at removing/re-queueing items but rather made for popping the head of the queue
15:29:15 -!- drdanmaku has joined.
15:34:38 <ion> http://en.wikipedia.org/wiki/Surstr%C3%B6mming | http://youtu.be/m-wQhSuf6mM?t=1m50s
15:36:21 -!- edwardk has quit (Quit: Computer has gone to sleep.).
15:39:21 <Taneb> I was going to ramble more but then I played QWOP for a bit
15:45:43 -!- tertu3 has joined.
15:47:54 -!- ter2 has quit (Ping timeout: 240 seconds).
15:54:59 -!- ^v has joined.
15:57:50 -!- tertu3 has quit (Ping timeout: 246 seconds).
16:06:38 <impomatic> Does anyone know what my gf is talking about?
16:07:33 <impomatic> 100000 individual videos on Youtube uploaded over the last two year, all showing a shape and a colour. She said it's part of a code?
16:12:13 <impomatic> This http://www.bbc.co.uk/news/technology-27238332 - weird
16:20:00 -!- ^v has quit (Read error: Connection reset by peer).
16:20:34 -!- ^v has joined.
16:22:55 -!- ^v has quit (Read error: Connection reset by peer).
16:23:22 -!- ^v has joined.
16:34:46 -!- augur has quit (Quit: Leaving...).
16:43:10 -!- kallisti has joined.
16:44:07 <kallisti> would anyone happen to be familiar with openGL and also good design practices in C#?
16:44:30 <kallisti> I'm not really sure where else I would find someone to get advice from
16:45:00 <nortti> didn't you change your nick to spirity?
16:46:07 -!- kallisti has quit (Disconnected by services).
16:46:13 -!- kallisti has joined.
16:47:06 <kallisti> basically I'm creating a class that wraps an openGL buffer objects
16:48:08 <kallisti> so most operations on buffers in openGL require that you bind a buffer as active
16:50:13 <kallisti> so I have a VertexBuffer Bind method that takes an Action<BoundVertexBuffer> callback. BoundVertexBuffer is a (public) nested type inside VertexBuffer that exposes OpenGL calls which require a bound buffer
16:51:02 <kallisti> supposedly public nested types are bad practice, but I'm not really seeing the drawback of using one here.
16:51:04 -!- CodingBat has joined.
16:51:47 <kmc> why are they bad?
16:52:13 <kallisti> I don't know man. That's why I'm using it. :P
16:52:25 <kallisti> I was hoping someone could convince me that they're bad or show me a different way.
16:52:30 <kmc> do what thou wilt shall be the whole of the law
16:53:42 <kallisti> OpenGL has to be the most confusing thing I've ever attempted to use.
16:55:40 -!- nucular_ has changed nick to nucular.
16:55:59 -!- nucular has quit (Changing host).
16:55:59 -!- nucular has joined.
16:57:56 -!- edwardk has joined.
17:00:08 -!- Phantom_Hoover has joined.
17:01:26 -!- ^v has quit (Read error: Connection reset by peer).
17:01:55 -!- ^v has joined.
17:15:56 -!- variable has quit (Quit: I found 1 in /dev/zero).
17:23:03 -!- CodingBat has quit (Quit: Page closed).
17:31:02 -!- variable has joined.
17:33:42 -!- Sprocklem has quit (Ping timeout: 245 seconds).
17:41:49 -!- Sprocklem has joined.
18:03:49 -!- FreeFull has joined.
18:16:23 -!- Phantom_Hoover has quit (Ping timeout: 276 seconds).
18:19:51 -!- Sprocklem has quit (Ping timeout: 252 seconds).
18:33:51 -!- Phantom_Hoover has joined.
18:40:02 <fizzie> Huh, I just looked out of the window and https://dl.dropboxusercontent.com/u/113389132/Misc/20140501-sunset.jpg
18:42:31 <fizzie> It's probably compensating for the day being quite rainy.
18:46:58 -!- Phantom_Hoover has quit (Ping timeout: 240 seconds).
19:01:44 -!- Phantom_Hoover has joined.
19:52:09 -!- conehead has joined.
20:00:30 -!- Sprocklem has joined.
20:04:54 -!- MindlessDrone has quit (Quit: MindlessDrone).
20:22:24 -!- impomatic has quit (Read error: Connection reset by peer).
20:30:21 -!- Bicyclidine has joined.
20:30:22 -!- AnotherTest has quit (Ping timeout: 245 seconds).
20:37:26 <HackEgo> [wiki] [[User talk:Lucasieks]] M http://esolangs.org/w/index.php?diff=39431&oldid=37909 * Lucasieks * (-491) Replaced content with "Talk with me clicking on ' ''add topic'' '."
20:54:44 -!- impomatic has joined.
21:01:12 -!- Patashu has joined.
21:16:22 -!- nisstyre has joined.
21:18:26 -!- Patashu has quit (Disconnected by services).
21:18:26 -!- Patashu_ has joined.
21:20:06 -!- tertu3 has joined.
21:22:56 -!- Sprocklem has quit (Ping timeout: 276 seconds).
21:27:11 -!- Patashu_ has quit (Ping timeout: 246 seconds).
21:37:08 -!- nucular has quit (Quit: Switching to phone).
21:57:52 -!- edwardk has quit (Ping timeout: 245 seconds).
21:58:44 -!- oerjan has joined.
22:04:15 -!- tertu3 has quit (Ping timeout: 252 seconds).
22:13:00 -!- CodingBat has joined.
22:36:05 -!- boily has joined.
22:38:48 <lambdabot> oerjan asked 2d 22h 45m 4s ago: <boily> `` echo 'A mathematimu is a quantum of mathematics. If you observe it, its codepoint can change.' >wisdom/mathematimu <-- WHY DID I EVEN BOTHER TO MAKE `learn UNDERSTAND ARTICLES
22:39:12 <boily> oerjan: hellørjan. because I am dumb.
22:39:45 <boily> (also, I mistrust any sign of intelligence and practicality coming from the Silicon World. yes, fungot, I'm looking at you.)
22:39:45 <fungot> boily: of my frantic ascent of the slope whose presiding demon beckoned to me with pale faces when they saw the slim, deceptively fnord figure with its yellow hair and blue eyes, who are you?' a very strange person, believed to have been.
22:40:16 <fowl> f-ngot needs a couple seconds delay
22:40:20 <boily> fungot: my figure isn't that fnordish, you know. I've been training! also, I'm boily.
22:40:20 <fungot> boily: published in march 1924 in weird tales, vol. fnord, 44, fnord: arkham house, fnord
22:40:52 <fowl> ive always wanted an irc bot to sit in #(programming language channel) and ask questions that have been asked before
22:41:48 <Jafet> Like a reverse-robot9000?
22:42:30 <boily> you could always start with #haskell, and periodically post “have you read <insert monad tutorial>?”
22:43:45 <oerjan> sounds like a way to get banned.
22:45:25 <boily> have you heard of the work of our Lord Brainfuck-Derivative?
22:46:15 <elliott> no, you can't get banned from #haskell for being unhelpful
22:46:24 -!- augur has joined.
22:46:27 <oerjan> boily: see http://dev.stephendiehl.com/hask/#eightfold-path-to-monad-satori
22:47:28 <Jafet> Look on the bright side, you'll get some humans banned as well.
22:47:48 <elliott> I mean, if I was in charge...
23:03:48 <boily> hm. still hearing opera singing coming over from the next apartment. I really wonder who the lady is...
23:07:31 -!- yorick has quit (Read error: Connection reset by peer).
23:08:03 -!- metasepia has joined.
23:08:08 <boily> JE VEUX QU'IL FASSE CHAUD, TAB*****!
23:08:24 <boily> at least it stopped raining today.
23:08:29 <metasepia> CYUL 012300Z 22016KT 15SM FEW025 SCT090 BKN120 14/08 A2963 RMK CU1AC4AC1 CU TR SLP033 DENSITY ALT 300FT
23:09:36 <quintopia> i see metasepia still doesnt know how to translate metar to english :P
23:10:57 -!- variable has quit (Quit: I found 1 in /dev/zero).
23:11:02 <boily> la la la my bot isn't vaporware it transcends mere unimplementation la la la ♪
23:11:05 <quintopia> remind me what units that temp is in
23:11:11 <oerjan> boily: it was snowing here today hth
23:11:24 <boily> quintopia: Celsius.
23:11:28 <metasepia> ENVA 012250Z 28015KT 9999 VCSH FEW010CB SCT014 SCT024 03/01 Q1020 RMK WIND 670FT 29014KT
23:11:41 <boily> oerjan: yes, but you live in a country that Exists. I don't have that luxury here.
23:11:55 <boily> quintopia: it's an optical illusion.
23:14:47 -!- CodingBat has quit (Quit: Page closed).
23:15:50 <boily> hm... that's a tough one...
23:19:56 -!- Eritzap has joined.
23:20:43 -!- Sgeo has joined.
23:21:11 <boily> Eritzap: did you ever go to Iceland?
23:22:03 <oerjan> i had an air transit there once
23:23:03 <oerjan> Eritzap: boily likes to confuse people, also it was mentioned just before you joined.
23:23:48 <boily> ~duck stroopwaffeln
23:23:56 * oerjan smells a belgian (it's the waffles)
23:24:21 <metasepia> A stroopwafel (English translation: syrup waffle, treacle waffle, or caramel waffle; lit "syrup waffle") is a waffle made from two thin layers of baked dough with a caramel-like syrup filling in the middle.
23:24:41 <boily> by the look of it, it sounds delicious.
23:25:04 <oerjan> hm those aren't belgian
23:26:23 <oerjan> hm en.wikipedia has an article on rømmegrøt but not rømmevaffel
23:26:55 <Eritzap> I can tell they aren't Belgian waffles, and I know my subject, I AM Belgian :U
23:29:25 -!- Sprocklem has joined.
23:29:35 <boily> Eritzap: vlaming or wallon?
23:30:43 -!- oerjan has set topic: The increasingly French speaking channel | PSA: fizzie is running the wiki now, contact him for any problems | https://dl.dropboxusercontent.com/u/2023808/wisdom.pdf http://codu.org/logs/_esoteric/ http://tunes.org/~nef/logs/esoteric/.
23:30:58 <oerjan> maybe that should have been in french
23:31:13 <oerjan> Eritzap: well you just increased it by one
23:31:30 <oerjan> and boily keeps swearing in quebecois thinking we don't understand
23:31:49 <boily> ah tiens, c'est vrai qu'on est rendus avec plusieurs belges...
23:32:16 <boily> (I REALLY need to bring back Roujo in the chännel. we're being out-frenchcanadianed.)
23:32:35 <quintopia> boily: i could try to send you some if you can't buy them there
23:33:14 <boily> quintopia: well, I think I think I could find some places over here that should sell them, but I expect them to be waaaaay overpriced.
23:33:57 <Eritzap> I'm used to type and read english on the internet, so french is a bit unusual for me
23:33:59 <quintopia> well i'd have to find them myself first
23:34:52 <nooodl> Eritzap: that's a very belgian thing
23:35:09 <boily> quintopia: want me to send you something québécois on the way?
23:35:36 -!- edwardk has joined.
23:36:19 <quintopia> can you send cuddles in the mail? the day that is possible, whoever does it will be rich
23:36:37 <nooodl> are cuddles particularly québécois
23:37:22 -!- variable has joined.
23:40:28 <oerjan> it's just a letter off from curdles
23:40:39 * boily is raking his brain over trying to find something québécois, but not too heavy...
23:45:29 -!- tertu3 has joined.
23:46:17 <Eritzap> and I found out computing additions using only logarithms and powers are impracticable
23:48:47 <boily> Eritzap: did you take a look at SELECT.? → http://esolangs.org/wiki/SELECT
23:49:24 <quintopia> good job including the . in the name
23:49:36 <quintopia> boily: it doesnt have to be quebecois
23:49:54 -!- Bicyclidine has quit (Quit: leaving).
23:50:46 <boily> quintopia: Canadian, then.
23:53:56 <boily> http://en.wikipedia.org/wiki/File:Nem_chua.jpg ?
23:55:39 <quintopia> looks like it will definitely survive the postal system
23:57:01 <boily> we once tried mailing yak cheese from China. it didn't work.
23:57:31 <quintopia> now you gave me a craving for yak butter tea :(
23:57:35 <Eritzap> boily: well that's interesting
23:57:52 <quintopia> why can't they live in a normal part of the world.
23:58:51 <boily> I tried YBT. it was. it was...
23:58:55 * boily shudders in abject terror
23:59:48 * boily goes and fixes himself a stiff gin tonic...
00:01:57 <oerjan> i'd like to remind haskellers here and especially edwardk that you can write {-# LANGUAGE Extension1, Extension2, Extension3, ... #-} hth
00:03:53 <boily> (what? neoballs can't be sold in Canada/USA anymore? but I bought some last month!)
00:05:31 -!- nisstyre has quit (Quit: WeeChat 0.4.3).
00:05:33 <Sgeo> oerjan: I've been starting to get the impression that people consider that ugly
00:07:04 <Sgeo> I don't know if that's the case, or if people really did forget that that's possible
00:07:20 <Sgeo> I'm jjust basing it on how common one extension per LANGUAGE pragma seems to be
00:07:39 -!- ^v has quit (Quit: http://i.imgur.com/DrFFzea.png).
00:08:05 -!- ^v has joined.
00:15:26 <edwardk> oerjan: I deliberately don't
00:15:43 <edwardk> that way when I grep -r LANGUAGE src I can take all the results, sort and uniq them
00:16:02 <edwardk> if they are smashed together that becomes awk-ward
00:16:20 <copumpkin> and how else would you make a nice ascending chain?
00:16:35 <edwardk> but the reason was more to do with 'other-extensions:' for cabal
00:16:55 <HackEgo> [wiki] [[User:Homfrog]] http://esolangs.org/w/index.php?diff=39432&oldid=37002 * Homfrog * (-44)
00:19:09 <edwardk> oerjan: i tend to sort them by length
00:20:01 <boily> MyExtensionIsLongerThanYoursSoTheres
00:30:19 -!- Phantom_Hoover has quit (Ping timeout: 265 seconds).
00:38:48 <kmc> is there any deep reason that K_4 is planar and K_5 isn't?
00:39:05 <kmc> I remember reading that for a torus there are hundreds of forbidden minors and the exact set isn't known (or wasn't at the time)
00:40:41 * Bike googles. kuratowski's theorem? eh what do i know
00:41:14 -!- tertu3 has quit (Ping timeout: 255 seconds).
00:43:22 -!- tertu3 has joined.
00:46:15 <boily> what the fungot is a torus forbidden mirror?
00:46:15 <fungot> boily: after two more quarries the inhabited part of inquanok seemed to end the business, but i felt that i had no knowledge of what legrasse had learned of simon or jedediah orne of salem. with these men he was often at the ward home to be present when the detectives arrived. allen's destruction or imprisonment or curwen's if one might regard the tacit claim to reincarnation as valid he felt must be accomplished at any cost. a
01:01:20 -!- tertu3 has quit (Ping timeout: 276 seconds).
01:02:59 -!- _1_Shingeki3 has joined.
01:03:17 -!- _1_Shingeki3 has left.
01:05:14 <oerjan> minor, boily, not mirror
01:07:54 <kmc> if a graph contains any of these graphs as a minor, it can't be embedded in a torus without edges crossing
01:08:20 <kmc> H is called a minor of the graph G if H can be formed from G by deleting edges and vertices and by contracting edges
01:08:47 <kmc> it's minors not subgraphs because (for example) K_5 is not planar, but clearly it doesn't become any more planar if you stick a node in the middle of each edge
01:09:41 <boily> oerjan: this devastates me.
01:10:00 <boily> I shall quit and drown my sorrows in a dreamless sleep.
01:10:12 -!- boily has quit (Quit: TOROÏDAL CHICKEN).
01:10:16 -!- metasepia has quit (Remote host closed the connection).
01:25:54 -!- password2 has quit (Ping timeout: 265 seconds).
01:34:44 -!- tromp has joined.
01:54:07 -!- conehead has quit (Quit: Computer has gone to sleep).
01:55:24 -!- tertu3 has joined.
01:56:05 <HackEgo> sansisesocoin ntchalcoin tomoufcoin scricoin baktecoin piralcoin sephcoin iincommodacoin braktivecoin tricoin brelumcoin luigcoin revicoin elpicoin excelumcoin wherimcoin brococoin suzcoin bankcoin etartricoin
01:56:09 -!- tertu3 has quit (Read error: Connection reset by peer).
01:59:27 -!- Eritzap has quit (Quit: Page closed).
02:00:46 -!- Froox has joined.
02:04:32 -!- Frooxius has quit (Ping timeout: 245 seconds).
02:06:36 <Bike> who here is an expert in biophysical applications of computational fluid dynamics
02:08:46 <kmc> fungot: are you an expert in biophysical applications of computational fluid dynamics
02:08:46 <fungot> kmc: his name with fnord fervour fnord. it was very
02:09:33 -!- Froox has quit (Read error: Connection reset by peer).
02:12:42 -!- Frooxius has joined.
02:32:12 -!- oerjan has quit (Quit: leaving).
02:34:38 -!- clog has quit (Ping timeout: 255 seconds).
02:42:52 -!- fizzie has quit (Ping timeout: 245 seconds).
02:50:04 -!- fizzie has joined.
02:57:29 -!- fungot has quit (Ping timeout: 252 seconds).
03:09:22 -!- MoALTz_ has joined.
03:11:57 <kmc> Bike: what kind of biowhatsit are you doing
03:12:59 <Bike> i was looking at https://github.com/openworm/Smoothed-Particle-Hydrodynamics
03:13:17 -!- MoALTz has quit (Ping timeout: 276 seconds).
03:14:42 <kmc> Fork C. elegans on GitHub!
03:15:25 <kmc> https://www.kickstarter.com/projects/openworm/openworm-a-digital-organism-in-your-browser
03:15:45 <Bike> unfortunately it's low on details of how it actually does contraction, which is a bit irritating since the contraction simulation in my own lab is way, way, way different and i'm not sure how
03:16:24 <Bike> probably i'll have to ask on the......... mailing list
03:19:14 <Bike> well i mean, i am sure how it's different. i don't know how to explain this. the methods are incredibly divergent
03:20:03 -!- fizzie has quit (Ping timeout: 252 seconds).
03:20:39 <kmc> kind of tripping out on the idea that there's a kickstarter where the reward is an uploaded organism
03:21:33 <Bike> i wonder how 'uploaded' it is. the connectome is obviously stable but i wonder where they get membrane parameters
03:22:24 <kmc> you mean for an initial state of the nervous system?
03:23:22 <kmc> i wonder what happens when you simulate inputs that are physically impossible
03:23:34 <kmc> hallucinating, disembodied worms in your web browser
03:24:01 <kmc> I guess if they are disembodied then they are hallucinating by definition. in a manner of speaking
03:24:18 <Bike> "We have captured the full 3D morphology of the C. elegans connectome in NeuroML format, and we are currently working to integrate electro-physiology. " hm, so i guess they haven't yet
03:24:48 <Bike> includes the initial state and also the transitions, probably. membrane physics is hard :D
03:25:34 <Bike> was talking with my boss's old boss today and he said modern physics is insufficient to model cells in enough detail
03:28:09 <Bike> cytoplasm violates too many convenient assumptions~
03:29:47 <Bike> i mean, i don't know how particle physics is going, you could probably like, run the standard model
03:29:52 <Bike> "not very efficient"
03:30:36 <kmc> just need a quantum computer
03:32:04 -!- adu has joined.
03:33:16 <Bike> let's see, one myosin molecule is probably, iunno, 50 kDa or some shit, so that's like a hundred thousand particles to simulate. and then a fibril's gonna have a few hundred of those
03:36:47 <Bike> how well do quantum computers do at physics sims, anywho
03:45:25 <kmc> supposedly they are good for simulating quantum mechanics
03:46:29 <Bike> http://www.sciencemag.org/content/273/5278/1073.abstract good abstract
03:46:54 <Bike> son of a fuck i don't have Science access for 96? fuck
03:48:23 <Bike> http://link.springer.com/article/10.1007%2FBF02650179 hm i'll have to read this later
03:48:38 <kmc> son of a fuck
03:52:52 -!- Bike has quit (Quit: should focus a bit).
03:58:48 <adu> have any of you heard of Funge-98?
03:59:13 <kmc> i would ask fungot but he left :(
03:59:52 <adu> I admire Funge-98 for it's audacity to think outside the box :)
04:02:57 -!- tertu has joined.
04:04:40 <myname> well, most multidimensional languages do that
04:04:53 <kmc> think outside the box and inside the torus?
04:05:35 <adu> any programming language that requires topological reasoning is fine by me.
04:05:55 <kmc> oh, we're in french now? ♫ debout, les damnés de la terre ♫
04:06:05 <kmc> adu: you might like homotopy type theory
04:06:55 <fowl> adu, you sounded like a jehovas witness for befunge98 just then lol
04:07:17 <fowl> have you heard the good word of multidimensional programming?
04:08:04 <myname> as a matter of fact, we currently have a project for building a compiler for rail
04:15:50 -!- adu has quit (Quit: adu).
04:16:47 -!- adu has joined.
04:17:04 <adu> myname: what kind of rail?
04:17:48 -!- Sorella has quit (Quit: It is tiem!).
04:17:57 <myname> http://esolangs.org/wiki/Rail that kind
04:21:18 <adu> myname: hmm
04:21:47 -!- adu has quit (Quit: adu).
04:25:04 <Sgeo> "It works dammit! Leave me alone!
04:25:05 <Sgeo> causes heart bleed 2.0"
04:25:10 <Sgeo> "But that didn't work"
04:25:15 <Sgeo> "It did what it was supposed to, and it did some more as well."
04:25:32 <Sgeo> Also http://www.reddit.com/r/programming/comments/24g6al/i_have_officially_failed_at_programming/ch76623
04:26:03 <kmc> we have arrived too late to play in the bleeding heart show
04:34:27 -!- clog has joined.
04:35:47 -!- nisstyre has joined.
04:37:00 <HackEgo> brakoncoin miniuscoin jehintcoin codecoin twischedrungcoin boemiccoin scalcoin befalcoin bredcoin chocoin adderitcoin waker)coin minuocoin proof!coin hitecoin concrcoin wulgarthubicoin whiccoin mincocoin axocoin
04:48:14 -!- nooodl has quit (Quit: Ik ga weg).
04:48:50 -!- tertu has quit (Ping timeout: 276 seconds).
04:52:08 -!- Bike has joined.
04:53:17 <Bike> darn, adu's gone, i was going to recommend Practical CS that needs topologishit
05:03:33 -!- fizziev has joined.
05:04:27 <fizziev> The one day I'm switching ISPs is of course when someone comes in with the best excuse for fungot promotion.
05:05:32 <myname> it is like "dude, did you hear about brainfuck????"
05:08:57 -!- conehead has joined.
05:50:48 -!- FreeFull has quit.
05:55:36 -!- aloril has quit (Ping timeout: 265 seconds).
06:08:56 -!- aloril has joined.
06:13:01 -!- MoALTz_ has quit (Quit: bbl).
06:30:02 -!- ^v has quit (Read error: Connection reset by peer).
06:31:23 -!- drdanmaku has quit (Quit: Connection closed for inactivity).
07:03:26 <Bike> There are campaigns to get governments to use open-source software, aren't there?
07:10:07 -!- fizzie has joined.
07:23:14 -!- variable has changed nick to function.
07:29:09 <Bike> i'm wondering cos i looked up a government program and it advises uninstalling IE8 in favor of IE7
07:41:10 -!- slereah has joined.
07:52:42 -!- impomatic has quit (Ping timeout: 240 seconds).
08:03:26 -!- nisstyre has quit (Quit: WeeChat 0.4.3).
08:22:26 -!- Sprocklem_ has joined.
08:25:07 -!- edwardk_ has joined.
08:26:50 -!- atriq has joined.
08:27:15 -!- password2 has joined.
08:27:29 -!- Patashu has joined.
08:28:36 -!- shachaf_ has joined.
08:29:11 -!- mroman_ has joined.
08:30:05 -!- heroux_ has joined.
08:30:26 -!- lexande_ has joined.
08:31:47 -!- Gracenotes_ has joined.
08:31:54 -!- variable has joined.
08:34:39 -!- augur has quit (*.net *.split).
08:34:39 -!- Melvar has quit (*.net *.split).
08:34:40 -!- heroux has quit (*.net *.split).
08:34:41 -!- mroman has quit (*.net *.split).
08:34:41 -!- Gracenotes has quit (*.net *.split).
08:34:47 -!- heroux_ has changed nick to heroux.
08:34:54 -!- aloril has quit (*.net *.split).
08:34:54 -!- function has quit (*.net *.split).
08:34:54 -!- edwardk has quit (*.net *.split).
08:34:54 -!- Sprocklem has quit (*.net *.split).
08:34:55 -!- shachaf has quit (*.net *.split).
08:34:55 -!- Taneb has quit (*.net *.split).
08:34:56 -!- lexande has quit (*.net *.split).
08:36:41 -!- lexande_ has changed nick to lexande.
08:36:57 -!- aloril has joined.
08:49:18 -!- fizziev has quit (Quit: leaving).
08:53:23 -!- augur has joined.
08:53:23 -!- Melvar has joined.
08:54:04 -!- skarn has joined.
08:55:42 -!- password2_ has joined.
08:56:51 -!- scoff has changed nick to dudejzkisfail.
08:57:26 -!- dudejzkisfail has left ("Leaving").
08:58:01 -!- password2 has quit (Ping timeout: 252 seconds).
09:08:22 -!- atriq has changed nick to Taneb.
09:19:45 -!- Patashu_ has joined.
09:19:45 -!- Patashu has quit (Disconnected by services).
10:15:34 <HackEgo> [wiki] [[If(j)invert()if(l)change()if(q)input()if(t)output(x);]] N http://esolangs.org/w/index.php?oldid=39433 * Lucasieks * (+878) Created page with "==INTERPRETER== Especifications: J - invert the bit pointed L - invert the pointer Q - input and put in the pointer T - output the pointer Interpreter in c: int[] mem..."
10:16:24 <HackEgo> [wiki] [[Talk:If(j)invert()if(l)change()if(q)input()if(t)output(x);]] N http://esolangs.org/w/index.php?oldid=39434 * Lucasieks * (+25) Created page with "This need some additions."
10:17:51 <HackEgo> [wiki] [[If(j)invert()if(l)change()if(q)input()if(t)output(x);]] M http://esolangs.org/w/index.php?diff=39435&oldid=39433 * Lucasieks * (+51) /* SAMPLES */
10:18:59 -!- boily has joined.
10:21:03 <HackEgo> [wiki] [[User:Lucasieks]] M http://esolangs.org/w/index.php?diff=39436&oldid=37889 * Lucasieks * (+2)
10:25:23 <HackEgo> [wiki] [[Joke language list]] M http://esolangs.org/w/index.php?diff=39437&oldid=39420 * Lucasieks * (+60)
10:26:25 -!- conehead has quit (Remote host closed the connection).
11:02:04 -!- yorick has joined.
11:10:10 -!- boily has quit (Quit: ´´´´´´´´).
11:21:34 <HackEgo> [wiki] [[Symbols]] M http://esolangs.org/w/index.php?diff=39438&oldid=39429 * Lucasieks * (+13)
11:21:47 <HackEgo> [wiki] [[Symbols]] M http://esolangs.org/w/index.php?diff=39439&oldid=39438 * Lucasieks * (-1)
11:34:51 <HackEgo> [wiki] [[ND]] N http://esolangs.org/w/index.php?oldid=39440 * Lucasieks * (+196) Created page with "nD is a project to create one language for each dimension. ==1D== It is a line. ==2D== 2D space. ==3D== How to represent in a 2D space? ''This is a WIP, we need help to f..."
11:37:42 <HackEgo> [wiki] [[Talk:ND]] N http://esolangs.org/w/index.php?oldid=39441 * Lucasieks * (+102) Created page with "<!-- PLEASE DONT EDIT HERE CLICK ON ADD TOPIC ABOVE --> ''Click on 'add topic' above to add an topic''"
11:37:43 -!- mhi^ has joined.
11:38:34 <HackEgo> [wiki] [[Talk:ND]] http://esolangs.org/w/index.php?diff=39442&oldid=39441 * Lucasieks * (+17) /* new */ new section
11:39:05 <HackEgo> [wiki] [[Talk:ND]] M http://esolangs.org/w/index.php?diff=39443&oldid=39442 * Lucasieks * (-8) /* new */
11:41:23 <HackEgo> [wiki] [[Talk:ND]] M http://esolangs.org/w/index.php?diff=39444&oldid=39443 * Lucasieks * (+106) /* 1 */
11:41:31 -!- KingOfKarlsruhe has joined.
11:43:51 <HackEgo> [wiki] [[Talk:ND]] http://esolangs.org/w/index.php?diff=39445&oldid=39444 * Lucasieks * (+89) /* 2D */ new section
11:44:08 <HackEgo> [wiki] [[Talk:ND]] M http://esolangs.org/w/index.php?diff=39446&oldid=39445 * Lucasieks * (-1)
11:45:59 <HackEgo> [wiki] [[Talk:ND]] http://esolangs.org/w/index.php?diff=39447&oldid=39446 * Lucasieks * (+91) /* 3D */ new section
11:50:42 <HackEgo> [wiki] [[Works in progress]] M http://esolangs.org/w/index.php?diff=39448&oldid=38457 * Lucasieks * (+68)
11:51:02 -!- nooodl has joined.
11:53:42 <HackEgo> [wiki] [[Tubes]] M http://esolangs.org/w/index.php?diff=39449&oldid=17768 * Lucasieks * (+17)
11:57:26 <HackEgo> [wiki] [[Main Page]] M http://esolangs.org/w/index.php?diff=39450&oldid=37905 * Lucasieks * (+17)
11:58:09 <HackEgo> [wiki] [[Main Page]] M http://esolangs.org/w/index.php?diff=39451&oldid=39450 * Lucasieks * (+10)
12:30:33 -!- Sgeo has quit (Read error: Connection reset by peer).
12:40:08 -!- Sorella has joined.
12:53:01 -!- tromp has quit (Remote host closed the connection).
12:53:38 -!- tromp has joined.
12:58:17 -!- tromp has quit (Ping timeout: 276 seconds).
13:25:03 -!- augur has quit (Quit: Leaving...).
13:42:46 -!- nucular has joined.
13:42:46 -!- nucular has quit (Changing host).
13:42:46 -!- nucular has joined.
13:46:13 -!- Patashu_ has quit (Ping timeout: 245 seconds).
13:49:54 -!- Sprocklem_ has quit (Ping timeout: 240 seconds).
14:08:37 -!- augur has joined.
14:12:44 -!- MindlessDrone has joined.
14:24:22 -!- variable has changed nick to constant.
14:29:25 -!- nooodl_ has joined.
14:33:50 -!- nooodl has quit (Ping timeout: 276 seconds).
14:34:19 -!- Sprocklem has joined.
14:37:04 -!- Eritzap has joined.
14:38:18 <HackEgo> [wiki] [[Main Page]] http://esolangs.org/w/index.php?diff=39452&oldid=39451 * Ehird * (-27) revert appearance-breaking change
14:39:02 -!- KingOfKarlsruhe has left.
14:39:14 -!- nooodl_ has changed nick to nooodl.
14:40:35 -!- ^v has joined.
14:41:48 <HackEgo> [wiki] [[User talk:Lucasieks]] http://esolangs.org/w/index.php?diff=39453&oldid=39431 * Ehird * (+1034) restore thread + comment
14:50:14 -!- AnotherTest has joined.
14:54:41 <elliott> fizzie: http://esolangs.org/forum/forum/ should be http://esolangs.org/forum/
14:56:25 -!- Patashu has joined.
15:03:59 -!- idris-ircslave has joined.
15:12:05 <Bike> /forum/ just links to /forum/forum/, though
15:19:20 -!- slereah has quit (Remote host closed the connection).
15:30:27 -!- edwardk_ has quit (Quit: Computer has gone to sleep.).
15:38:25 -!- Patashu_ has joined.
15:38:25 -!- Patashu has quit (Disconnected by services).
15:56:35 -!- drdanmaku has joined.
15:57:13 -!- tromp has joined.
16:01:37 -!- tromp has quit (Ping timeout: 250 seconds).
16:04:20 -!- Sprocklem has quit (Quit: Math test).
16:07:15 <fizzie> I don't know how it ended up nested like that.
16:19:08 -!- Phantom_Hoover has joined.
16:27:38 -!- Eritzap has quit (Quit: Page closed).
16:43:07 -!- yorick has quit (Remote host closed the connection).
16:56:44 -!- FreeFull has joined.
17:07:29 -!- edwardk has joined.
17:10:59 -!- edwardk has quit (Read error: Connection reset by peer).
17:11:28 -!- edwardk has joined.
17:15:27 -!- MoALTz has joined.
17:20:03 -!- MoALTz has quit (Ping timeout: 250 seconds).
17:28:20 -!- MoALTz has joined.
17:29:46 -!- shachaf_ has changed nick to shachaf.
17:29:56 -!- shachaf has quit (Changing host).
17:29:57 -!- shachaf has joined.
17:33:37 -!- Sprocklem has joined.
17:39:27 <fizzie> On the other hand, we bought a teapot.
17:40:46 -!- Bike_ has joined.
17:40:52 -!- Bike_ has changed nick to Bicyclidine.
17:41:51 -!- edwardk has quit (Read error: Connection reset by peer).
17:42:12 -!- edwardk has joined.
17:49:50 -!- fungot has joined.
18:19:45 <Slereah_> You could make a bong out of it
18:19:53 -!- Sprocklem has quit (Quit: Class).
18:20:06 <Bicyclidine> perhaps bonghits could help me make a bong out of it
18:21:08 -!- Eritzap has joined.
18:23:43 <fizzie> I'm not sure how bongable it is.
18:23:50 <fizzie> Though I guess you can make one out of just about anything.
18:24:39 <fizzie> This one was in the hotel room, and it looked nice and useful, and they had one for sale in the reception.
18:24:57 -!- edwardk has quit (Read error: Connection reset by peer).
18:25:21 -!- edwardk has joined.
18:25:59 <fizzie> https://dl.dropboxusercontent.com/u/113389132/Misc/20140502-teapot.jpg
18:26:20 <fizzie> (There's the kind of a wire mesh tea-holder thing in the top hole.)
18:28:11 -!- Phantom_Hoover has quit (Ping timeout: 252 seconds).
18:43:31 -!- nisstyre has joined.
18:49:58 -!- password2_ has quit (Ping timeout: 240 seconds).
18:57:59 -!- edwardk has quit (Ping timeout: 250 seconds).
19:07:05 -!- not^v has joined.
19:10:27 -!- ^v has quit (Ping timeout: 252 seconds).
19:27:15 -!- Eritzap has quit (Quit: Page closed).
19:55:41 <douglass_> you can boil water in that to reconstitute cup of noodle or such
19:56:01 <douglass_> since it appears to also be a kettle
19:58:03 <myname> https://twitter.com/michaeljhudson/status/462103006410858496/photo/1/large xD
19:58:13 -!- Sprocklem has joined.
19:59:23 -!- john_metcalf has joined.
19:59:44 <kmc> is that a Microsoft product or just branded swag
20:01:19 <olsner> nothing wrong with products having several uses
20:02:29 <myname> the question is: where do you get 4 spherical usb covers
20:02:30 <kmc> those exposed ports will be a problem though
20:02:37 <fizzie> It's iron, I don't know if it's really a kettle too.
20:03:51 <olsner> fizzie: you mean it's a purely decorational teapot?
20:04:21 <fizzie> No, I mean, I think the officially designated way is to pour hot water in it.
20:04:25 <myname> as far as i know, you can use them, but they are far from practical
20:04:40 <fizzie> Rather than putting it on a stove or some such.
20:04:48 <myname> those pots tend to get pretty hot
20:05:17 <fizzie> I guess since it doesn't seem to have any parts that are not cast iron, you could use a pole and put it on an open fire or something.
20:05:29 <kmc> the mixing of conversations here is amusincg
20:05:38 <fizzie> The handle didn't seem to get especially hot, anyway.
20:06:05 <fizzie> But the hotel had a regular whatchamacallit, water-boil-o-mater.
20:06:08 <kmc> anyway yes, things that go in your butt should not have exposed ports
20:06:15 <kmc> sex toys are the killer app for inductive charging
20:06:48 <kmc> what's unclear about that statement
20:07:36 <myname> i wouldn't say "unclear"
20:07:45 <olsner> hmm, I wonder if they could be inductively charged/powered while in use too, should be theoretically possible I guess
20:08:18 <olsner> otoh, cords are pretty great compared to uncharged batteries
20:09:15 <kmc> not so much for insertable items though :P
20:10:58 -!- MindlessDrone has quit (Quit: MindlessDrone).
20:11:05 <douglass_> I've used a metal teapot like that and it was fine. Didn't boil the water in it but I don't see why that wouldn't work. Cast iron is actually a very poor conductor of heat (as metals go).
20:11:48 <olsner> I'd guess it's good enough to burn your hand
20:12:16 <kmc> there should be a version of the We-Vibe that's powered by the, er, natural mechanical action of using it
20:13:10 <douglass_> I didn't burn my hand on the handle, but it's not like using a potholder is terribly impractical.
20:13:17 <myname> as a more serious side note: i do think they should do that for smartphones
20:13:35 <olsner> would it charge fast enough?
20:14:24 <kmc> almost certainly not
20:14:36 <myname> probably not, but it could expend the time between charging
20:14:52 <Bicyclidine> presumably you'd use a thermal charger instead, for one
20:15:09 <myname> no reason to not do both
20:15:35 <Bicyclidine> i don't think phones touch the skin enough for a self-winder to be practical.
20:15:43 <Bicyclidine> as much as the idea of a phone with a mainspring amuses me
20:15:56 <myname> Bicyclidine: you never played ingress, do you?
20:16:09 -!- conehead has joined.
20:17:56 <olsner> is it like more real than reality?
20:18:26 <myname> also: if you don't dislike anime, watch dennou coil
20:21:06 <Bicyclidine> https://pbs.twimg.com/profile_images/3683374135/c637bfc5e4055c9d3a6d007aa1297b24_400x400.jpeg no, i am the big anime fan
20:22:27 <kmc> can't find a teardown to get the battery capacity :/
20:47:30 <fungot> olsner: bloody hell. i totally missed it. :)
21:15:07 <Taneb> Oh dear god, the guy who played Anakin in Episode I of Star Wars is 5 years older than me
21:15:10 -!- Bicyclidine has quit (Ping timeout: 240 seconds).
21:16:00 -!- nortti has changed nick to lawspeaker.
21:16:11 <HackEgo> [wiki] [[Powerlist]] N http://esolangs.org/w/index.php?oldid=39454 * CodingBat * (+19915) Created the article
21:16:21 -!- lawspeaker has changed nick to nortti.
21:16:52 -!- Sprocklem has quit (Quit: Leaving).
21:19:03 -!- edwardk has joined.
21:19:54 -!- yorick has joined.
21:24:05 -!- AnotherTest has quit (Ping timeout: 252 seconds).
21:36:17 -!- sebbu has quit (Ping timeout: 264 seconds).
21:36:56 -!- edwardk has quit (Read error: Connection reset by peer).
21:38:02 -!- sebbu has joined.
21:38:40 -!- sebbu has quit (Changing host).
21:38:40 -!- sebbu has joined.
21:41:51 -!- nucular has quit (Quit: Excess Food).
21:59:07 <Bike> so, for ssl stuff, explicit_bzero is a function that the compiler refuses to optimize out, right? would a regular bzero be optimized out if, like, the variable goes out of scope after the call?
22:00:38 <nortti> depends on the smartness of the compiler but smart enough one would
22:01:30 <elliott> Bike: explicit_bzero is openbsd-specific
22:01:49 <Bike> well yes, but the idea of it, which ssl had independently of bsd for instance
22:02:28 <olsner> so is that a real problem that everyone else ignores or are the bsd people just a bit crazy?
22:02:55 <elliott> the BSD people aren't the only ones who do it, I don't think.
22:04:15 <Bike> kqueue.org/blog/2012/03/05/memory-allocator-security-revisited/ right, so C is impossible
22:04:43 -!- Phantom_Hoover has joined.
22:05:36 <olsner> hmm, nicely broken page, everything except the quoted code is blank
22:07:22 <fizzie> I had to reload it for that to go away.
22:08:08 <olsner> yeah that worked for me too
22:10:46 -!- edwardk has joined.
22:11:42 <HackEgo> [wiki] [[Powerlist]] http://esolangs.org/w/index.php?diff=39455&oldid=39454 * CodingBat * (+1487) Added categories and a proof of Turing-completeness
22:18:25 -!- edwardk has quit (Quit: Computer has gone to sleep.).
22:18:39 -!- Eritzap has joined.
22:20:17 -!- Sprocklem has joined.
22:22:39 -!- MoALTz_ has joined.
22:25:41 -!- MoALTz has quit (Ping timeout: 252 seconds).
22:34:44 -!- edwardk has joined.
22:47:08 -!- boily has joined.
22:54:46 <fungot> \o| c.c \o/ ಠ_ಠ \m/ \m/ \o_ c.c _o/ \m/ \m/ ಠ_ಠ \o/ c.c |o/
22:54:46 <myndzi> | c.c.c | ¯|¯⌠ `\o/´ | c.c.c | `\o/´ ¯|¯⌠ | c.c.c |
22:54:46 <myndzi> /´\ c.c /< >\| | /`\ c.c /< | |\| >\ c.c /<
22:55:52 <boily> (strangely, you're still the only one I address in the vocative case.)
22:56:06 <Taneb> (I need to get some sleep)
22:56:40 <Taneb> I wonder if myndzi works on PM
22:57:12 <Taneb> Doesn't seem like it :(
22:57:36 <boily> myndzi: please correct this outrageous and egregious bug asap twh kthxbye.
23:01:39 <Taneb> boily, have fun in Canadaland or wherever the hell you are
23:06:52 <boily> @tell Taneb I always am at Canada, modulo some rare lapses spent on other continents.
23:17:29 <boily> I already went to the US. multiple times. on my own volition.
23:17:40 <Sprocklem> boily: "I always am at Canada ... other continents."
23:18:09 <Sprocklem> boily: Canada's a country, not a continent
23:18:29 <kmc> good to know
23:18:39 <boily> I only transit through the US. except when I was younger and we family-vacationed on the East Coast.
23:18:51 -!- tromp has joined.
23:23:21 -!- tromp has quit (Ping timeout: 252 seconds).
23:28:35 -!- Sgeo has joined.
23:33:50 -!- mhi^ has quit (Quit: Lost terminal).
23:44:05 <kmc> where on the east coast?
23:48:16 <boily> Connecticut, Massachusetts, New York, Boston, Washington DC., Baltimore (nice aquarium by the way). Michigan too, but that's not quite eastcoastian.
23:48:27 <kmc> never saw the b'more aquarium
23:48:38 <kmc> boston has a pretty good one, but the best part was closed when I went :/
23:48:54 <boily> there's an aquarium in boston and nobody told me? aaaaargh!
23:49:30 <boily> I like aquariums. they have interesting floating things that move.
23:49:38 <kmc> osaka has a nice one
23:49:49 <boily> I went to the ōsaka one :D
23:50:46 <kmc> the monterey bay aquarium is supposed to be one of the best, and it's not too far from where I live
23:50:49 <kmc> I could bike there in two days
23:52:21 -!- yorick has quit (Remote host closed the connection).
23:52:38 <boily> you are tempting me with scenic places.
23:53:10 <lexande> boily: clearly there's an aquarium in boston, since it has a subway station named after it
23:55:09 <boily> I don't think I ever used Boston's subway.
23:57:03 <boily> but according to the plan, I can get from Honoré-Beaugrand over to Lechmere through the Green Line Extension to Canada.
00:01:59 -!- Eritzap has quit (Quit: Page closed).
00:10:11 <Phantom_Hoover> i remember reading that somewhere and being mildly sceptical but i've never been able to find another mention of it
00:12:01 <kmc> pointless cosmology
00:13:55 <boily> I picture the Universe as having the shape of a grain of cottage cheese.
00:14:03 <boily> a very large grain.
00:14:28 <kmc> All energy flows according to the whims of the Great Magnet. What a fool I was to defy him.
00:16:18 -!- Eritzap has joined.
00:16:41 <boily> kmc: it's a quote by hunter s thompson???
00:16:58 <Phantom_Hoover> i thought i was writing that in the kerbal space program channel
00:17:17 <kmc> kerbal space drugs
00:22:12 -!- Phantom_Hoover has quit (Quit: Leaving).
00:41:28 -!- nisstyre has quit (Quit: WeeChat 0.4.3).
00:41:58 -!- Eritzap has quit (Quit: Page closed).
00:49:13 -!- Patashu has joined.
00:50:12 <HackEgo> [wiki] [[Language list]] M http://esolangs.org/w/index.php?diff=39456&oldid=39421 * CodingBat * (+16) Added Powerlist
00:51:58 -!- Patashu_ has quit (Ping timeout: 240 seconds).
00:58:16 <boily> I hate it when I seem to be reading some comments on reddit for the first time, and then a wild orange arrow appears, attached to a six month old comment.
00:58:35 * boily mapoles his memory back into working condition
01:02:37 <olsner> the key to making good use of your memory is to forget such stuff you have no use for
01:03:30 <boily> oh. so... forgetting reddit comments is a good thing?
01:04:17 * boily mapoles himself up the head a few more times, just to be sure and drive the point home. «c'est pour... ow!... mon bien!»
01:04:54 <kmc> I hate it when I seem to be reading some comments on reddit
01:07:10 <boily> hmpfh! phillistines...
01:14:16 -!- not^v has quit (Quit: http://i.imgur.com/DrFFzea.png).
01:14:42 -!- ^v has joined.
01:15:59 -!- tromp has joined.
01:16:46 -!- edwardk has quit (Quit: Computer has gone to sleep.).
01:28:30 -!- not^v has joined.
01:29:31 -!- ^v has quit (Read error: Connection reset by peer).
01:58:17 -!- boily has quit (Quit: CHALLENGING CHICKEN).
02:06:42 -!- Sorella has quit (Quit: It is tiem!).
02:12:18 <HackEgo> resocoin umbercoin codecoin millcoin msgcoin hydrivarmycoin liccoin iincecoin brainvigatacoin quiercoin jgdcoin fadrompcoin hevercoin alcedcoin 960096coin ometcoin *coin cuylicoin blacrcoin mazacoin
02:18:29 -!- ^v has joined.
02:18:35 -!- not^v has quit (Read error: Connection reset by peer).
02:24:56 -!- pdurbin has quit (Ping timeout: 252 seconds).
02:25:01 -!- nisstyre has joined.
02:30:03 -!- nooodl_ has joined.
02:30:48 -!- nooodl has quit (Disconnected by services).
02:30:50 -!- nooodl_ has changed nick to nooodl.
02:32:38 -!- ^v has quit (Ping timeout: 252 seconds).
02:33:34 -!- ^v has joined.
02:49:29 -!- BlueProtoman has joined.
03:02:06 -!- ludmilaa has joined.
03:02:28 -!- Frooxius has quit (Ping timeout: 245 seconds).
03:02:53 -!- ludmilaa has left.
03:15:55 <Bike> i'm reading a paper and realized it's the first time i've heard of parallel quantum computing, which is kinda weird
03:27:19 -!- nooodl has quit (Ping timeout: 276 seconds).
04:05:16 -!- nycs has joined.
04:06:05 -!- `^_^v has quit (Ping timeout: 246 seconds).
04:15:48 -!- drdanmaku has quit (Ping timeout: 245 seconds).
04:15:54 -!- ggherdov_ has quit (Ping timeout: 240 seconds).
04:18:47 -!- ^v has quit (Ping timeout: 252 seconds).
04:35:13 -!- drdanmaku has joined.
04:39:16 -!- Phantom_Hoover has joined.
04:51:20 -!- ggherdov_ has joined.
04:56:25 -!- MoALTz__ has joined.
04:59:38 -!- MoALTz_ has quit (Ping timeout: 276 seconds).
05:21:18 -!- tromp has quit (Remote host closed the connection).
05:21:51 -!- tromp has joined.
05:25:54 -!- tromp has quit (Ping timeout: 240 seconds).
05:30:01 -!- nisstyre has quit (Quit: WeeChat 0.4.3).
05:32:00 -!- nisstyre has joined.
05:48:21 <HackEgo> [wiki] [[List of ideas]] http://esolangs.org/w/index.php?diff=39457&oldid=38995 * 69.123.94.202 * (+29) /* Physics */
06:00:39 -!- Slereah_ has quit (Read error: Connection reset by peer).
06:00:59 -!- Slereah_ has joined.
06:03:34 -!- Phantom_Hoover has quit (Ping timeout: 240 seconds).
06:11:25 -!- password2_ has joined.
06:16:13 -!- Sprocklem has quit (Ping timeout: 245 seconds).
06:22:50 -!- Sprocklem has joined.
06:28:52 <Bike> http://www.nature.com/nature/journal/v435/n7039/full/nature03484.html biology needs raytracers now~
06:44:11 <shachaf> elliott: How do you feel about lenses these days?
06:54:18 -!- BlueProtoman has quit (Ping timeout: 240 seconds).
06:57:22 <shachaf> Taneb: can you write a function :: forall k s t a b. (forall p. Profunctor p => (forall f x y. k f -> p x y -> p (f x) (f y)) -> p a b -> p s t) -> (exists f. k f)
06:57:39 <shachaf> you're all about lenses these days, right
07:00:30 <kmc> write a lens combinator which is analogous to the advanced cnidarian optics in the bio paper Bike linked
07:03:16 <Taneb> shachaf, I can't even make that typecheck and you've given me the signature
07:03:18 <Bike> how can i use coq to show that box jelly lenses allow more visual acuity than is actually possible due to the retinal distance
07:04:41 <Bike> i wonder if there's some sense in which proofs in the sciences are generally simpler than ones in mathematics, since the main practical issue is designing and running experiments
07:31:33 -!- MindlessDrone has joined.
07:33:03 -!- nisstyre has quit (Quit: WeeChat 0.4.3).
07:36:55 -!- password2_ has changed nick to password2.
07:58:17 -!- JZTech102 has joined.
08:04:18 -!- JZTech101 has quit (*.net *.split).
08:04:23 -!- Melvar has quit (*.net *.split).
08:04:25 -!- nycs has quit (*.net *.split).
08:04:26 -!- impomatic has quit (*.net *.split).
08:04:27 -!- Taneb has quit (*.net *.split).
08:04:30 -!- maurer has quit (*.net *.split).
08:04:32 -!- jix has quit (*.net *.split).
08:04:33 -!- nortti has quit (*.net *.split).
08:04:33 -!- elliott has quit (*.net *.split).
08:04:34 -!- int-e has quit (*.net *.split).
08:04:35 -!- drdanmaku has quit (*.net *.split).
08:04:37 -!- FreeFull has quit (*.net *.split).
08:04:39 -!- shachaf has quit (*.net *.split).
08:04:40 -!- glogbackup has quit (*.net *.split).
08:04:42 -!- rodgort has quit (*.net *.split).
08:04:42 -!- erdic has quit (*.net *.split).
08:04:42 -!- skarn has quit (*.net *.split).
08:04:43 -!- jhj1 has quit (*.net *.split).
08:04:43 -!- myname has quit (*.net *.split).
08:06:09 -!- Melvar has joined.
08:06:53 -!- nycs has joined.
08:06:53 -!- Taneb has joined.
08:06:53 -!- maurer has joined.
08:06:53 -!- jix has joined.
08:06:53 -!- nortti has joined.
08:06:53 -!- elliott has joined.
08:06:53 -!- int-e has joined.
08:08:49 -!- oerjan has joined.
08:11:56 -!- drdanmaku has joined.
08:11:56 -!- FreeFull has joined.
08:11:56 -!- skarn has joined.
08:11:56 -!- shachaf has joined.
08:11:56 -!- glogbackup has joined.
08:11:56 -!- rodgort has joined.
08:11:56 -!- erdic has joined.
08:11:56 -!- jhj1 has joined.
08:11:56 -!- myname has joined.
08:17:20 <oerjan> <myname> https://twitter.com/michaeljhudson/status/462103006410858496/photo/1/large xD <-- ok what is wrong with that or am i not getting a reference.
08:20:06 <fowl> it looks like cloaca beads
08:20:24 * fowl just pooped a little
08:21:29 <myname> https://www.youtube.com/watch?v=_ThkQTo8-jI
08:23:49 <oerjan> i find it interesting that google suggests "cloaca beads" but shows up no relevant hits
08:25:05 <myname> you are not doing safe search, do you?
08:25:06 <oerjan> in fact putting it in quotes doesn't help.
08:25:16 <shachaf> You know the thing where you have two representations of something, where one is a collection of arguments and the other is a polymorphic result after applying one argument?
08:25:20 <oerjan> i don't think that applies to _text_
08:25:21 <shachaf> E.g. Yoneda and CoYoneda, Mu and Nu.
08:25:39 <Taneb> oerjan, it really does
08:26:12 <shachaf> Density and Codensity (only in one direction each)
08:26:18 <oerjan> also i definitely don't have safe search on.
08:26:40 <fowl> i forget u mammals have anuses instead of cloaca
08:27:15 <oerjan> oh it's fowl being foul
08:47:07 <oerjan> <Phantom_Hoover> is it true that gravity probe b was pointless? <-- i also read that by the time they got any results, others had bypassed them in quality.
08:47:45 <oerjan> because they never managed to control the stray em fields as well as they wanted to, iirc
08:48:23 <oerjan> @tell Phantom_Hoover <Phantom_Hoover> is it true that gravity probe b was pointless? <-- i also read that by the time they got any results, others had bypassed them in quality. because they never managed to control the stray em fields as well as they wanted to, iirc
08:48:31 <shachaf> oerjan: are you a kan extension expert
08:49:07 <oerjan> in fact i don't think i've ever known the definition.
08:51:23 -!- drdanmaku has quit (Quit: Connection closed for inactivity).
08:52:41 <oerjan> <boily> kmc: it's a quote by hunter s thompson??? <-- somehow remided me of the first story in I, Robot
08:54:04 <oerjan> the one with the robot creating a religion worshipping an item in the space station
08:55:42 <oerjan> https://en.wikipedia.org/wiki/Reason_(short_story)
08:56:53 <shachaf> Hmm, if you link to the text of a short story, should you annotate the link with "(spoilers)"?
09:25:50 <shachaf> I want a word list with pronunciation metadata.
09:26:10 <myname> just switch to a more sane language
09:26:32 <shachaf> E.g. number of syllables, emphasis, rhyming or enough information that you can deduce rhyming...
09:27:21 <shachaf> That is an unusually unhelpful answer.
10:16:52 -!- conehead has quit (Quit: Computer has gone to sleep).
11:05:56 -!- yorick has joined.
11:16:55 -!- kallisti has quit (Read error: Connection reset by peer).
11:19:10 -!- nucular has joined.
11:19:10 -!- nucular has quit (Changing host).
11:19:11 -!- nucular has joined.
11:24:14 -!- oerjan has quit (Quit: leaving).
11:35:18 -!- Phantom_Hoover has joined.
11:51:07 <int-e> shachaf: a dictionary like http://www.speech.cs.cmu.edu/cgi-bin/cmudict might help.
11:54:05 -!- boily has joined.
12:08:51 -!- ^v has joined.
12:24:24 <fizzie> There is also the BEEP, and some others.
12:25:03 <fizzie> http://svr-www.eng.cam.ac.uk/comp.speech/Section1/Lexical/beep.html
12:31:49 -!- drdanmaku has joined.
12:38:37 -!- ^v has quit (Read error: Connection reset by peer).
12:39:04 -!- ^v has joined.
12:48:22 -!- Patashu has quit (Ping timeout: 240 seconds).
12:54:16 -!- Sorella has joined.
12:55:27 -!- mhi^ has joined.
13:03:54 -!- nooodl has joined.
13:18:28 -!- Frooxius has joined.
13:33:15 -!- AndroidKitKat has joined.
13:45:53 -!- tromp has joined.
14:01:55 <AndroidKitKat> How do I make it that the pointer moves according to the input.
14:02:02 -!- ggherdov_ has quit (Read error: Connection reset by peer).
14:02:16 <AndroidKitKat> The only way I can think of is laying down a "1" to make a path.
14:02:40 <AndroidKitKat> However, that would be a problem, because you might overwrite useful data.
14:03:17 <FreeFull> Not much you can do about that
14:03:37 <AndroidKitKat> So.... self modifying code's probably the only way then, huh?
14:04:56 <Jafet> It's called http://esolangs.org/wiki/Aura
14:06:01 <boily> AndroidKitKat: of course you can write self-modifying BF code :D just write a BF interpreter in BF, augment the innermost language spec with self-modifying instructions, then embed the code in the interpreter.
14:06:21 <Bike> "pointer moves according to the input"?
14:06:35 <FreeFull> I think you should use a higher-level language on top of BF anyway
14:06:52 <AndroidKitKat> Bike: I seriously don't know enough programming terms to talk properly. :<
14:07:13 -!- JZTech102 has changed nick to JZTEch101.
14:07:14 -!- JZTEch101 has quit (Changing host).
14:07:14 -!- JZTEch101 has joined.
14:08:24 -!- JZTEch101 has changed nick to JZTech101.
14:09:06 <Jafet> There are brainfuck data structures, such as arrays. Some even use constant additional space.
14:09:45 <Bike> whoa whoa whoa that's not really acceptable in the high-stakes legally fraught world of brainfuck programming,
14:10:17 <Jafet> We'll have none of that "scare quoting" around here
14:10:56 <AndroidKitKat> It's not really stealing though, because I just took his idea.
14:13:23 <boily> Jafet: what if I use “fancy” «quotes»?
14:14:23 -!- ggherdov_ has joined.
14:19:46 <fizzie> Also, no self-modifying code in regular brainfuck.
14:20:41 <fizzie> Oh, it was sort-of pointed out, I guess.
14:33:55 -!- nooodl_ has joined.
14:37:18 -!- nooodl has quit (Ping timeout: 240 seconds).
14:54:46 -!- password2 has quit (Ping timeout: 240 seconds).
15:10:19 <AndroidKitKat> fizzie: Unless you put the cells in the same memory space with the instructions.
15:32:28 -!- oklopol has joined.
15:41:28 -!- nucular has changed nick to nuculaway.
16:04:22 -!- password2 has joined.
16:25:31 <fizzie> Yes, but then it's not regular brainfuck.
16:26:21 -!- Phantom_Hoover has quit (Ping timeout: 252 seconds).
16:41:05 -!- tromp has quit (Remote host closed the connection).
16:42:46 -!- nuculaway has changed nick to nucular.
16:47:35 -!- BlueProtoman has joined.
16:58:35 -!- BlueProtoman has left ("Leaving").
17:14:25 <Jafet> http://www.thingiverse.com/thing:255794 #kmc
17:15:13 <Bike> iso standard bonghits
17:18:07 <boily> OpenBong? what has this poor world come to...
17:19:06 -!- conehead has joined.
17:24:36 -!- oerjan has joined.
17:28:04 <oerjan> AndroidKitKat: you don't need self-modifying code, although you need at least two extra cells for shuffling things around with.
17:28:48 <oerjan> the easiest is to have extra cells between all pairs of "data" cells.
17:29:42 -!- nooodl_ has changed nick to nooodl.
17:29:59 <myname> https://github.com/fbrandel/ParisHilton.js
17:37:38 <oerjan> <boily> OpenBong? what has this poor world come to... <-- it could get worse, just consider the obvious letter substitution.
17:39:21 <int-e> oerjan: gongs aren't bad, hth
17:42:12 <oerjan> stackoverflow is so fickle.
17:42:52 <oerjan> i have this answer with most votes but it isn't the accepted one. and earlier i got accepted an answer with zero points when someone else had more.
17:42:53 -!- nooodl has quit (Quit: Ik ga weg).
17:42:54 <int-e> or "song" - have people tried using 3d printers for making records? (needs more resolution than 3d printers usually have, but I think I like the idea)
17:47:01 <oerjan> well i suppose the latter was because i answered a two day old question.
17:48:55 <oerjan> int-e: OpenKong, for your giant primate needs
17:50:29 -!- Phantom_Hoover has joined.
17:52:32 <Jafet> http://www.amandaghassaei.com/3D_printed_record.html
18:02:25 -!- Phantom_Hoover has quit (Ping timeout: 252 seconds).
18:02:59 <boily> https://www.youtube.com/channel/UCsLiV4WJfkTEHH0b9PmRklw
18:03:29 <boily> oerjan: I reject your letter substitution and substitute my own.
18:04:24 <oerjan> boily: i didn't say what it was, how can you be sure you haven't just substituted it for itself twh
18:05:44 <Jafet> oerjan: http://makerlove.com
18:05:53 <boily> I'm more interested with the substitutions between substitutions. kinda like a substitution functor.
18:06:52 <oerjan> boily: covariant or contravariant? *gets hit by anvil dropped by overhead swallow*
18:07:15 <b_jonas> oerjan: conjugated actually
18:07:25 <b_jonas> that's how substitution on a substitution works if it's invertible
18:07:33 <oerjan> Jafet: i'm so not surprised.
18:10:59 * oerjan points at the space bar
18:11:24 * boily hugs his mechanical keyboard
18:12:02 * oerjan vaguely thinks boily hugs a lot of things
18:12:26 <oerjan> must be a side effect of this sanity he keeps speaking about.
18:12:51 <nortti> how does one vaguely think?
18:13:27 <oerjan> nortti: well you sorta like really in this way sometimes.
18:13:38 <oerjan> fungot: you're the expert here.
18:13:38 <fungot> oerjan: ( that that there can be more than one
18:13:49 <boily> nortti: it's one of the perks of being sane. it opens up all kinds of thinking!
18:14:18 <oerjan> wait i thought i was doing the vague thinking, and i don't recall making any claims of sanity.
18:14:56 <HackEgo> "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."
18:15:08 <boily> woot! my sanity is creeping up on oerjan ^^
18:16:22 <oerjan> a fate worse than too horrible too contemplate.
18:16:28 <oerjan> AndroidKitKat: problems?
18:16:38 <oerjan> have they added trollface to unicode yet
18:17:15 <AndroidKitKat> I thought I was being idiotic with my typing, turns out something was manipulating le keypresses.
18:17:32 <oerjan> the ghost in the machine
18:17:33 <boily> keypress is feminine. «la keypress».
18:17:58 <AndroidKitKat> I didn't even ealized I switched channels already.
18:18:34 <boily> oerjan: you probably want U+1F638 GRINNING CAT FACE WITH SMILING EYES.
18:18:54 <oerjan> boily: i don't think that's the image i'm imagining.
18:18:59 <boily> (also, HackEgo is on Python 2, therefore no shiny complete SMP support.)
18:20:00 <oerjan> `unicode GRINNING CAT FACE WITH SMILING EYES
18:20:01 <HackEgo> U+1F638 GRINNING CAT FACE WITH SMILING EYES \ UTF-8: f0 9f 98 b8 UTF-16BE: d83dde38 Decimal: 😸 \ 😸 \ Category: So (Symbol, Other) \ Bidi: ON (Other Neutrals)
18:20:13 <oerjan> it's a bit verbose about them, though.
18:20:43 <boily> eh? there was an upgrade? ooooooh...
18:21:03 <AndroidKitKat> Am I missing somethng here or is UTF-8 4 bytes according to that?
18:21:08 -!- metasepia has joined.
18:21:32 <boily> AndroidKitKat: U+1F638 is far, far away. therefore, four bytes.
18:21:35 <oerjan> AndroidKitKat: quite possibly.
18:22:22 <oerjan> that's the official max unicode value, unless they've changed it again.
18:22:46 <boily> `thank AndroidKitKat
18:22:47 <HackEgo> /home/hackbot/hackbot.hg/multibot_cmds/lib/limits: line 5: exec: thank: not found
18:22:52 <nortti> AndroidKitKat: Hank you, too
18:22:52 <boily> `thanks AndroidKitKat
18:22:53 <HackEgo> Thanks, AndroidKitKat. ThAndroidKitKat.
18:22:54 <lifthrasiir> any change to the bounds will cause an introduction of surrogate-surrogates
18:23:24 <boily> haven't they learned that surrogate pairs are evil once?
18:23:46 <oerjan> boily: i'm not sure if it's an upgrade or simply downloading a better working unicode program.
18:23:56 <lifthrasiir> (and it *will* continue to be used due to the pervasiveness of ECMAScript)
18:24:26 <kmc> that's right :(
18:24:29 <boily> Gregor: did you change anything re HackEgo recently?
18:24:59 <oerjan> boily: it wasn't Gregor
18:25:49 <kmc> although V8 can store strings as ASCII too
18:25:59 <kmc> and SpiderMonkey people are considering doing something similar
18:26:16 <kmc> and even if they don't, I want Servo to store UTF-8 in the DOM and only convert to UTF-16 when necessary
18:26:26 <oerjan> boily: it seems to be Jafet's work
18:27:56 <oerjan> starting with a `fetch of a debian file
18:29:33 <kmc> i kind of wish that Unicode had assigned compatibility codepoints for lone surrogates
18:29:47 <kmc> since they are basically individual characters in UCS-2 as implemented by ECMAScript
18:30:04 <kmc> and Unicode is supposed to be round trip compatible with legacy character sets
18:30:45 <b_jonas> kmc: I've sort of met something like that
18:31:38 <b_jonas> kmc: namely, when we changed perlmonks' official encoding to cp1252 (new version), for a while we've had the problem of how to encode into xml the few bytes that aren't valid characters in that encoding
18:32:01 <b_jonas> I think eventually we made them encoded to the high control characters with the same code
18:32:12 <elliott> why on earth would you change encoding to cp1252...
18:32:28 <Bike> to keep everybody on their toes
18:32:31 <b_jonas> elliott: it was iso-8859-1 before,
18:32:41 <Bike> garbage in garbage out
18:32:49 <b_jonas> elliott: come on, it's like 15 years old now!
18:33:07 <b_jonas> elliott: and the gods don't have time to apply even my simplest patches
18:33:09 <Bike> doesn't new perl use like, guillemets and shit? cp1252 must be a fucking adventure
18:33:15 <b_jonas> converting the whole thing to unicode would be impossible
18:33:55 <Bike> note to self, do not start using perl
18:34:16 <b_jonas> besides, you can put any character in the posts by amp-escaping them
18:34:31 <boily> Bike: you know you want to.
18:34:31 <b_jonas> (except in magical code tags where you can't, which is bad, but it's not easy to solve)
18:34:56 <HackEgo> [wiki] [[Symbols]] http://esolangs.org/w/index.php?diff=39458&oldid=39439 * Oerjan * (-12) against policy
18:34:58 <Bike> i really don't, if this is what they're doing
18:35:08 <Bike> i have enough trouble with line endings
18:38:40 <HackEgo> [wiki] [[ND]] http://esolangs.org/w/index.php?diff=39459&oldid=39440 * Oerjan * (+20) lowercase template
18:39:40 <HackEgo> [wiki] [[Tubes]] http://esolangs.org/w/index.php?diff=39460&oldid=39449 * Oerjan * (-17) Undo revision 39449 by [[Special:Contributions/Lucasieks|Lucasieks]] ([[User talk:Lucasieks|talk]]) (Against policy)
18:41:09 <Bike> http://esolangs.org/w/index.php?title=Main_Page&diff=next&oldid=37905 this is good stuff oerjan
18:41:44 <oerjan> my prediction doesn't seem to have held yet
18:42:35 <oerjan> b_jonas: in the previous edit summary, which was also a Lucasieks undo
18:48:37 <HackEgo> [wiki] [[Powerlist]] http://esolangs.org/w/index.php?diff=39461&oldid=39455 * Oerjan * (-2) sp
18:54:18 -!- boily has quit (Quit: NAP).
18:54:19 -!- metasepia has quit (Remote host closed the connection).
19:09:27 <elliott> oerjan: I will block if it happens again
19:11:08 <myname> tubes looks interesting, but too bad it's not fully specified in the article
19:11:20 <oerjan> i should buy peanuts. wait i have peanuts, i just think of them as chocolate because they're covered in it.
19:12:30 <myname> could someone explain the difference between the movers in tubes?
19:15:31 <myname> okay, i still don't get it
19:20:06 <oerjan> you'd think you'd need 3d for tubes to work
19:20:22 <oerjan> wire-crossing problem and all that
19:20:58 <myname> i just don't get what the double-tubes in the first example are for
19:20:59 <b_jonas> oerjan: can't you avoid that by like using spare scratch memory cells that you set to the right value to cross a crossing?
19:21:42 <oerjan> b_jonas: i'm not talking about the actual Tubes language here
19:21:51 <oerjan> just musing about the meaning of the words
19:22:11 <b_jonas> you're _not_ talking about the tubes language
19:22:43 <oerjan> you may have heard about this real-life thing called "tubes".
19:23:03 <b_jonas> the ones in the wall carry water, the ones outside carry gas
19:23:05 <oerjan> in which fluids may pass. they can be used for computation.
19:23:20 <b_jonas> yes, I've seen such a thing too but it's impractical
19:23:40 <oerjan> we don't have much gas tubes in norway.
19:24:08 <b_jonas> sure you don't, you just pay for all the electricity and don't care about how inefficient it is. I know most countries are like that.
19:24:20 <b_jonas> it's easier in more densely populated areas like here, mind you
19:24:34 <oerjan> actually norway has the cheapest electricity in europe. used to be even cheaper.
19:24:46 <oerjan> unless i'm gravely mistaken.
19:25:00 <oerjan> because our country is littered with hydroelectric dams.
19:25:25 <oerjan> although this new apartment actually has remote water heating.
19:25:41 <oerjan> which hardly existed a few decades ago.
19:27:35 <b_jonas> yeah, I hear it's hard because the ground is too cold and if it stops for just a few minutes for an error during the winter all the pipes freeze and are impossible to restart
19:27:53 <b_jonas> we don't have that problem because the pipes that are just a few meters below never freeze
19:28:41 <oerjan> nothing bad happened over the winter here, but they were closed for repairs during summer.
19:29:17 <b_jonas> yeah, it might work better than what I imagine because they actually do regular maintenance there :)
19:30:02 <oerjan> well it's a new building, they'd better get it working to start with.
19:30:16 <oerjan> other than that, norway isn't known for being good at maintenance.
19:47:10 -!- password2 has quit (Ping timeout: 240 seconds).
20:02:17 <augur> https://www.youtube.com/watch?v=dfoLe5oWb9I
20:12:11 -!- MindlessDrone has quit (Quit: MindlessDrone).
20:15:44 <HackEgo> havecoin larcoin kvilcoin enigcoin mimsyoncoin eplatlcoin mortgcoin miccoin zsakingpetudecoin dna#coin fugicoin waduliecoin self-modicoin etarelacoin bookcoin villerecoin sercoin lawocoin chrcoin ryecoin
20:15:58 <kmc> self-modicoin!!!
20:17:41 <Bike> proof of work is submitting a new proof of work method
20:19:54 <b_jonas> wait, there's a comic for that
20:21:05 <b_jonas> Bike: http://www.xkcd.com/1121/
20:22:02 -!- AnotherTest has joined.
20:23:48 -!- Scaev has joined.
20:29:10 <oerjan> is there an xkcd comic about how there is always a relevant xkcd comic, i cannot recall
20:31:12 <b_jonas> oerjan: I don't either. It's only partly that there's always a relevant xkcd strip, the other half is how it's also possible to find it.
20:31:46 <b_jonas> There are other comics where I keep wanting to find the relevant strip, but there's no transcript and the comic is long and not in any sort of sane order and has no sane strip titles.
20:32:31 <fizzie> I always have to reread about half of isometric before I can find what I'm looking for.
20:32:51 <kmc> there is always a relevant goatkcd comic
20:33:50 <oerjan> what is the xkcd comic about those xkcd comics which are not relevant to themselves
20:34:25 <fizzie> I tried to use the relevantxkcd site to find the xkcd relevant to there always being a relevant xkcd, but the result wasn't very relevant.
20:34:55 <oerjan> fizzie: you probably got it mixed up with ironic hth
20:41:55 -!- nisstyre has joined.
20:45:54 -!- Scaev has quit (Quit: Quitte).
20:50:55 -!- oerjan has quit (Quit: Nite).
21:10:50 -!- fowl has quit (Quit: rebooting).
21:23:37 -!- MoALTz__ has quit (Quit: brb).
21:23:48 -!- MoALTz has joined.
21:24:14 -!- nisstyre has quit (Ping timeout: 245 seconds).
21:26:26 -!- Eritzap has joined.
21:40:01 -!- AnotherTest has quit (Ping timeout: 250 seconds).
21:45:23 -!- mhi^ has quit (Quit: Lost terminal).
21:46:50 -!- Frooxius has quit (Quit: *bubbles away*).
21:48:08 -!- nisstyre has joined.
21:48:18 -!- Eritzap has quit (Ping timeout: 240 seconds).
21:49:28 -!- Frooxius has joined.
21:50:02 <shachaf> kmc: i was going to look at rust but now ~ is going away or something??
21:50:41 -!- conehead has quit (Quit: Computer has gone to sleep).
22:01:04 <FreeFull> shachaf: Being replaced with Box to allow for things like custom allocators
22:01:05 -!- conehead has joined.
22:01:17 <FreeFull> Although I think Uniq would be a better name
22:03:16 <olsner> "~" is about as long as a pointer kind/type/thing can get before it starts to be annoying though
22:04:54 <myname> yeah, rust is desugaring atm
22:05:01 <myname> not sure if i like that
22:05:18 <olsner> they might resugar when they figure out which family of pointers to keep
22:08:10 -!- Eritzap has joined.
22:13:29 -!- ^v has quit (Ping timeout: 252 seconds).
22:21:34 -!- Sprocklem has quit (Ping timeout: 240 seconds).
22:46:55 -!- fowl has joined.
22:53:19 -!- Patashu has joined.
22:53:27 <int-e> @faq Can Haskell make shachaf happy?
22:53:27 <lambdabot> http://www.haskell.org/haskellwiki/FAQ
22:54:13 <olsner> I'll read that as a "no"
22:54:39 <int-e> shachaf: I couple of people are sad about the change but nobody actually complained (where I could see).
22:54:58 <int-e> I couple -> a couple, and I should sleep :)
22:55:21 <b_jonas> is there another command that has the old behaviour?
22:55:24 -!- Patashu_ has joined.
22:55:24 -!- Patashu has quit (Disconnected by services).
22:55:34 <b_jonas> @oldfaq Can Haskell make shachaf happy?
22:55:59 <int-e> @msg #esoteric Yes! Haskell can do that!
23:15:49 -!- nooodl has joined.
23:16:14 -!- Sgeo has quit (Read error: Connection reset by peer).
23:16:33 -!- Sgeo has joined.
23:22:26 -!- edwardk has joined.
23:22:41 <lambdabot> unexpected end of input: expecting digit
23:24:38 <lambdabot> unexpected 'd': expecting digit, operator or end of input
23:25:05 <lambdabot> unexpected end of input: expecting digit, operator, "+", "-" or end of input: no rolls in expression
23:26:36 <int-e> I didn't know that it supported division :)
23:27:02 <lambdabot> int-e: 1 / (1 - 1) => Divide by zero!
23:28:01 <lambdabot> unexpected "-": expecting number, "d" or "("
23:29:47 <int-e> To demystify the above, it approximates <n>d<m> by a normal distribution if n > 100.
23:30:37 <int-e> @dice 100000000000000000000d1
23:35:31 <olsner> I expected something more like a stack overflow in sum for large inputs
23:36:09 <elliott> why not just do it for n <= 100 too?
23:37:18 <int-e> because it's noticably different for the small n that matter, most notably n=1.
23:41:48 -!- ^v has joined.
23:46:54 -!- AndroidKitKat has left.
23:49:40 -!- edwardk has quit (Quit: Computer has gone to sleep.).
23:50:51 -!- yorick has quit (Remote host closed the connection).
23:58:07 -!- Phantom_Hoover has joined.
00:19:26 <Taneb> If you are running to give someone a hug
00:19:36 <Taneb> And they look like they are preparing to rugby tackle you
00:19:41 <Taneb> Abort hug immediately.
00:20:22 -!- tromp has joined.
00:20:33 <Taneb> Seriously, my jaw still hurts
00:26:17 -!- ^v has quit (Read error: Connection reset by peer).
00:26:46 -!- ^v has joined.
00:27:06 <elliott> fizzie: esolangs.org is down
00:27:14 -!- nucular has quit (Quit: Excess Food).
01:02:40 <coppro> I should register theenemysgate.ca and point it to an IP address that doesn't have a server
01:05:54 -!- david_werecat has joined.
01:09:12 <david_werecat> Opinion based question: it is a good idea to change your online name? If one were to do this, what would they need to do and what would be the implications of this?
01:11:06 <fowl> david_werecat, youll need new profile pictures too. just get them from your most handsome facebook friend
01:12:56 <david_werecat> Bascially, I'm thinking of changing my many online accounts from david_werecat to Cyskus.
01:13:31 <fowl> did you check the inernet nickname registry to make sure cyskus isnt taken
01:14:03 <david_werecat> Currenly it does not exist anywhere that Google can find.
01:14:04 <Bike> i've changed names a billion times, mon
01:14:27 <fowl> there is a form you should fill out and submit to ICANN
01:14:58 <elliott> david_werecat: you know this channel is publicly logged and indexed by google, right? :P
01:16:13 <david_werecat> Still, letting everyone know how to find your new account is another reason I'm here.
01:16:51 <david_werecat> Carrying information forward between iterations is the most difficult part.
01:18:05 <fowl> Bike, so those metal things i find when i google you arent you, they're some previous bike?
01:18:23 <Bike> yes, i'm actually made of organic compounds
01:36:52 -!- Eritzap has quit (Quit: Page closed).
01:47:16 -!- conehead has quit (Quit: Computer has gone to sleep).
01:50:07 -!- david_werecat has left ("Leaving").
02:06:36 -!- Frooxius has quit (Quit: *bubbles away*).
02:07:39 -!- speckle has joined.
02:11:30 -!- speckle has left ("Konversation terminated!").
02:18:27 -!- Frooxius has joined.
02:34:17 -!- Phantom_Hoover has quit (Ping timeout: 252 seconds).
02:38:49 -!- Frooxius has quit (Ping timeout: 245 seconds).
03:29:30 -!- ^v has quit (Read error: Connection reset by peer).
03:30:08 -!- ^v has joined.
03:52:28 -!- zzo38 has joined.
04:11:35 -!- Sprocklem has joined.
04:16:54 -!- FreeFull_ has joined.
04:18:18 -!- FreeFull has quit (Ping timeout: 240 seconds).
04:25:54 -!- polytone has changed nick to monotone.
04:34:00 -!- tertu has joined.
04:44:42 -!- ^v has quit (Read error: Connection reset by peer).
04:45:09 -!- ^v has joined.
04:50:10 -!- augur has quit (Quit: Leaving...).
05:03:43 -!- edwardk has joined.
05:19:27 -!- shikhin has joined.
05:19:27 -!- shikhin has quit (Changing host).
05:19:27 -!- shikhin has joined.
05:20:56 <Sgeo> I got my GF addicted to Suzumiya Haruhi
05:21:23 -!- drdanmaku has quit (Quit: Connection closed for inactivity).
05:23:24 -!- tertu has quit (Ping timeout: 245 seconds).
05:25:56 -!- shikhin has quit (Quit: leaving).
05:26:12 -!- shikhin has joined.
05:26:12 -!- shikhin has quit (Changing host).
05:26:12 -!- shikhin has joined.
05:26:16 -!- augur has joined.
05:29:27 -!- shikhin has quit (Client Quit).
05:29:42 -!- shikhin has joined.
05:29:42 -!- shikhin has quit (Changing host).
05:29:42 -!- shikhin has joined.
05:35:03 -!- shikhin has quit (Quit: leaving).
05:47:15 -!- password2 has joined.
05:50:14 -!- shikhin has joined.
05:52:28 -!- tromp has quit (Remote host closed the connection).
05:54:08 <zzo38> Once I used Huffman for abnormal purpose; I wanted to encode a bit string in alphabetics so I made up a Huffman tree for twenty-six equally probability data.
05:57:48 <zzo38> What is it called to do such things as this?
05:58:46 <Bike> "Huffman for abnormal purpose"
06:02:42 -!- nooodl has quit (Quit: Ik ga weg).
06:14:36 -!- ^v has quit (Quit: http://i.imgur.com/DrFFzea.png).
07:00:15 <Sgeo> http://www.lessmilk.com/games/12/
07:01:44 -!- oerjan has joined.
07:14:28 <lambdabot> unexpected '.': expecting digit, operator or end of input
07:15:56 <oerjan> clearly it should use poisson distribution to approximate @dice 1000d1.001
07:17:03 <lambdabot> oerjan: 1 + 2 + 3 + 4 + 5 + 6 => 21
07:18:01 <oerjan> so we have a calculator with a d prefix
07:20:10 <lambdabot> unexpected '(': expecting digit, operator or end of input
07:22:27 <shachaf> oerjan: that's a p. misleading calculator when your calculation doesn't happen to start with a 1
07:22:28 <fizzie> elliott: Not any more, apparently.
07:22:59 <oerjan> `addquote <Taneb> Have some advice! <Taneb> If you are running to give someone a hug <Taneb> And they look like they are preparing to rugby tackle you <Taneb> Abort hug immediately. <Taneb> Seriously, my jaw still hurts
07:23:00 <HackEgo> 1192) <Taneb> Have some advice! <Taneb> If you are running to give someone a hug <Taneb> And they look like they are preparing to rugby tackle you <Taneb> Abort hug immediately. <Taneb> Seriously, my jaw still hurts
07:23:34 <shachaf> what does it mean when my scalp itches a ot
07:23:49 <oerjan> shachaf: i guess technically it has a d1 infix, to be placed after any number inside
07:24:36 -!- Sorella has quit (Quit: It is tiem!).
07:25:11 <oerjan> shachaf: either you need a better dandruff shampoo, or you're allergic to something (i've experienced both)
07:25:37 <oerjan> in spring, in seattle, i think it was the trees.
07:25:37 <shachaf> what happens when you're allergic to dandruff shampoo
07:25:51 <oerjan> shachaf: too horrible to contemplate
07:26:47 <oerjan> i was at canada in 1995 hth
07:27:10 <oerjan> (and australia in 1988)
07:27:34 <oerjan> that exhausts the times i've been outside europe, i think.
07:29:12 <oerjan> actually i'm pretty sure i'm "allergic" to the strongest dandruff shampoo, which i use once a week.
07:29:28 <oerjan> the rest of the week i use head & shoulders
07:29:52 <oerjan> also, my scalps itches when i think about this
07:31:00 <oerjan> why can't they make sound isolation that isolates against humans speaking loudly
07:31:03 <b_jonas> zzo38: why don't you use arithmetic coding for that? I mean, huffman to 26 letters would be very wasteful unless your input has lots of symbols, because you have to encode very common symbols with a single letter.
07:31:51 <oerjan> also, carpenting and loud bass music
07:32:21 <oerjan> basically, why is sound isolation imperfect.
07:32:52 <b_jonas> oerjan: http://www.xkcd.com/666/ ?
07:33:51 <fizzie> oerjan: It will be okay after we remove your ears and replace them with something that has a firmware upload function hth
07:34:27 <b_jonas> fizzie: like http://www.xkcd.com/644/ ?
07:39:36 <oerjan> @ask coppro <coppro> I should register theenemysgate.ca and point it to an IP address that doesn't have a server <-- what about a server that responds to pings, but _nothing_ else twh
07:39:45 <Jafet> All a dream of http://www.xtcian.com/CalvinHobbesNailTable%28bl%29.jpg
07:41:10 <Jafet> A server that communicates by the length of time it waits before closing incoming connections
07:47:41 -!- conehead has joined.
07:48:16 <oerjan> <Sgeo> http://www.lessmilk.com/games/12/ <-- AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA
07:48:23 -!- mhi^ has joined.
07:53:19 <oerjan> darn i had 28 when i gave up
07:53:50 <oerjan> games that give me nausea: -1
08:00:49 <fizzie> That reminds me of that one #drugz game.
08:00:56 <fizzie> I forget what its name was.
08:02:00 <fizzie> (See Google image search for a good overview.)
08:11:17 -!- Melvar` has joined.
08:14:02 -!- Melvar has quit (Ping timeout: 255 seconds).
08:46:31 -!- oklopol has left ("Leaving").
08:47:31 -!- shikhin has quit (Ping timeout: 276 seconds).
08:48:46 -!- shikhin has joined.
08:56:20 -!- MindlessDrone has joined.
08:57:40 <Jafet> That is pretty #drugz.
09:05:38 -!- Phantom_Hoover has joined.
09:13:02 -!- FreeFull_ has changed nick to FreeFull.
09:57:07 -!- password2 has quit (Ping timeout: 250 seconds).
10:37:14 <myname> why do i die whenever i collect the dot after it rotated a little? Oo
10:43:54 <int-e> white on light grey, seriously?!
10:48:54 <oerjan> myname: i don't recall that happening.
10:49:23 <fizzie> I keep getting killed when it rotates a whole lot instead of a little bit.
10:49:29 <fizzie> After 40, and esp. after 45.
10:49:32 <oerjan> myname: possibly you get confused about which keys turn which way?
10:49:53 <myname> oerjan: no, i move in circles a bit to make sure
10:50:19 * oerjan doesn't feel like trying that game again
10:50:35 <fizzie> I've tried it twice now, and gotten 41 and 46.
10:50:54 <fizzie> Also, I liked the "white on bright yellow" even less than "white on light gray".
10:52:44 * oerjan plays some 2048 just to be anti-hipster (and also because he hasn't managed to win it yet ihrc)
10:53:03 <myname> oerjan: how many dimensions?
10:53:37 <oerjan> the 3d i tried was too easy
10:54:33 <myname> you may try 4d or 5d :p
10:55:43 <FreeFull> oerjan: You should play flappy 2048
10:56:47 <Taneb> FreeFull, I played too much of that
10:58:51 <int-e> wrong game, sorry, I should read more context
10:59:57 <fizzie> Taneb: There are at least two different flappy2048s.
11:00:19 <Taneb> http://flappy2048.com/ this one
11:00:28 <fizzie> Right, there's also http://hczhcz.github.io/Flappy-2048/
11:00:47 <fizzie> I got that as first hit the other day, and flappy2048.com as the second.
11:00:53 <fizzie> Today it seems the other way around.
11:03:15 <myname> i do think both are crap
11:03:17 <oerjan> ok i can confirm they're both awful hth
11:03:38 <fizzie> My printer keeps getting paper jams. :/
11:05:01 <oerjan> clearly you should convert to virtual printing hth
11:05:30 <myname> just invent paperless printers
11:06:34 <oerjan> london has only had mayors since 2000?
11:12:56 <oerjan> ah. not to be confused with the Lord Mayor of London.
11:15:33 -!- Slereah has joined.
11:15:53 -!- mhi^ has quit (Quit: Lost terminal).
11:16:35 <oerjan> "A female Lord Mayor or an unmarried male Lord Mayor may appoint a female consort, usually a fellow member of the corporation, to the role of Lady Mayoress."
11:16:43 -!- Phantom__Hoover has joined.
11:16:58 -!- Phantom_Hoover has quit (Ping timeout: 240 seconds).
11:17:08 <fizzie> If I print using the manual feeder, it doesn't jam, but it writes "x0Y" on the top-left corner, and scales the actual printout to occur in the bottom-right two-thirds of the page.
11:18:10 <Jafet> This calls for a four-pass printing process
11:18:19 -!- FreeFull has quit (Ping timeout: 276 seconds).
11:18:20 -!- Slereah_ has quit (Ping timeout: 252 seconds).
11:18:40 <oerjan> the thou shall not pass process
11:19:29 -!- FreeFull has joined.
11:26:44 <Jafet> Gamut the Grey, protector of the halftones, wielder of the flame of Linotype
11:26:46 <fizzie> Should've printed all this stuff at work, instead of trying to do it here at home.
11:27:07 -!- mhi^ has joined.
11:29:32 -!- conehead has quit (Quit: Computer has gone to sleep).
11:38:17 -!- oerjan has quit (Quit: leaving).
11:38:37 <int-e> does the crazy snake game start doing arbitrary affine transformations at some point (including reflections?)
11:58:08 -!- quintflam has joined.
12:00:25 -!- quintflam has quit (Client Quit).
12:05:58 <fungot> Jafet: i think it would be nice, if scheme is then forth is that you can keep that nic for now if you meet someone who's smarter than you look
12:08:41 -!- nooodl has joined.
12:20:16 <int-e> b_jonas: http://www.lessmilk.com/games/12/
12:36:53 -!- nucular has joined.
12:36:53 -!- nucular has quit (Changing host).
12:36:53 -!- nucular has joined.
13:14:29 -!- boily has joined.
13:24:20 -!- tromp has joined.
13:29:10 -!- Patashu_ has quit (Ping timeout: 240 seconds).
13:42:21 -!- tertu has joined.
14:20:21 <boily> according to past topics, we have >100% bots, and we increasingly speak in French. fungot, parles-tu français?
14:20:21 <fungot> boily: you want to bind it locally and then return :) here's my attempt at aesthetics
14:20:45 <boily> fungot: local language binding... and EDSL, then?
14:20:45 <fungot> boily: fnord/ 2008/ 02/ fnord/ fnord
14:21:03 <boily> fungot: ah. the monadic fnord composition.
14:21:03 <fungot> boily: so... i suck at them somewhere in arithmetica! loophole!
14:21:48 <boily> fungot: you suck fungots between numbers? isn't that a bit... morally wrong?
14:21:48 <fungot> boily: off the top of the stack
14:22:00 <boily> fungot: blertch! that's gross!
14:23:38 -!- Frooxius has joined.
14:25:08 -!- tromp has quit (Remote host closed the connection).
14:41:37 -!- ^v has joined.
14:43:17 -!- shikhin_ has joined.
14:45:58 -!- shikhin has quit (Ping timeout: 240 seconds).
14:49:46 -!- shikhin_ has changed nick to shikhin.
15:09:21 -!- nortti has changed nick to driyoyleujiy.
15:09:28 -!- driyoyleujiy has changed nick to nortti.
15:09:57 -!- shikhin has changed nick to shikhout.
15:26:03 -!- shikhout has changed nick to shikhin.
15:51:02 -!- atehwa has quit (Remote host closed the connection).
16:01:48 -!- boily has quit (Quit: BRUNCHICKEN).
16:10:39 -!- Languager_ has joined.
16:11:10 -!- Sorella has joined.
16:43:26 <HackEgo> nandecoin brograinscoin avercoin wikillcoin gildcoin nuouslykelxxvhis=thacoin sothropofedenentertastomialcoin ]coin divilcoin beckocoin ntcycoin autocoin orkcoin restcoin gigationcoin hargdcoin spaldcoin finingthis=thacoin cation2coin kollocoin
16:52:09 -!- Slereah_ has joined.
16:53:43 <b_jonas> so-thropo-fedenen-tertas-tomial-coin
16:54:38 -!- Slereah has quit (Ping timeout: 240 seconds).
17:03:42 -!- Phantom__Hoover has quit (Ping timeout: 258 seconds).
17:11:20 -!- shikhin has quit (Remote host closed the connection).
17:11:23 -!- oerjan has joined.
17:43:52 -!- drdanmaku has joined.
17:51:35 -!- ^v has quit (Ping timeout: 252 seconds).
18:20:41 <HackEgo> glassenborcoin fernandballycoin councoin misccoin ortlcoin binalcoin vaggonataeterberinglebrahildmenstricoin twofifcoin gotcoin calcoin majorgh!coin 0x2000coin tinycoin alpinkeymakicoin sendecoin pavlcoin nooncoin heliumcoin cescoin splcoin
18:21:04 <myname> ah, that's easy to remember! vaggonataeterberinglebrahildmenstricoin
18:22:09 <kmc> strategic heliumcoin reserve
18:22:39 <kmc> when i was a small child people seemed to be very impressed that I could spell "antidisestablishmentarianism" and knew what it means
18:23:08 <kmc> it's not even close to the longest English word, though
18:23:35 <oerjan> if we're going to have just one command with excessive colors i prefer `relcome to `coins hth
18:24:17 <oerjan> copumpkin: *r*ainbow w*elcome*
18:24:48 <oerjan> also, *was, it was deleted
18:25:32 <oerjan> FreeFull: it's _stable_ but it keeps seeping out of your wallet
18:25:49 <Bike> the longest word is methionyl[etc]isoleucine, obviously
18:26:01 <FreeFull> oerjan: You need to store it in a gas canister
18:26:11 <oerjan> FreeFull: even those seep helium
18:26:22 <oerjan> there's no known storage method that doesn't
18:27:01 <FreeFull> It's better than hydrogen though
18:27:52 <kmc> i wonder what's the longest English word that isn't built from smaller forms that would be known to the average speaker
18:28:20 <oerjan> kmc: i think that's still methionyl[etc]isoleucine
18:28:27 <kmc> maybe that doesn't count
18:29:05 * kmc comes up with a way to encode arbitrary binary data as syntactically valid sequences of word-parts
18:30:24 <Bike> well methionine isn't really known to the average speaker :V
18:32:09 <Bike> kind of funny that it begins literally every polypeptide, but hey
18:37:40 -!- ais523 has joined.
18:55:03 -!- MindlessDrone has quit (Quit: MindlessDrone).
19:05:41 -!- callforjudgement has joined.
19:08:46 -!- yorick has joined.
19:10:13 -!- ais523 has quit (Ping timeout: 276 seconds).
19:10:30 -!- callforjudgement has changed nick to ais523.
19:13:58 -!- callforjudgement has joined.
19:15:48 -!- scarf has joined.
19:15:54 -!- callforjudgement has quit (Read error: Connection reset by peer).
19:16:10 -!- ais523 has quit (Disconnected by services).
19:16:13 -!- scarf has changed nick to ais523.
19:21:59 -!- ^v has joined.
19:25:12 -!- callforjudgement has joined.
19:25:13 -!- ais523 has quit.
19:26:30 -!- callforjudgement has quit (Read error: Connection reset by peer).
19:26:40 -!- callforjudgement has joined.
19:28:08 -!- callforjudgement has quit (Read error: Connection reset by peer).
19:28:16 -!- scarf has joined.
19:29:07 -!- scarf has changed nick to ais523.
19:31:00 -!- ais523 has quit (Read error: Connection reset by peer).
19:31:08 -!- ais523 has joined.
19:46:14 -!- AnotherTest has joined.
19:57:19 -!- BlueProtoman has joined.
19:57:22 <BlueProtoman> Where does the input to a counter machine go, and how do we know if said counter machine accepts or rejects the input?
19:57:34 -!- nucular has quit (Quit: Excess Food).
19:57:55 <oerjan> BlueProtoman: in the counters
19:58:26 <BlueProtoman> oerjan: Ah, so if I were to reserve a counter for the input, I could Godel-encode a string and it'd be like a Turing machine?
20:00:13 <BlueProtoman> (Assume the Lambek instruction set; inc, dec, jz, and halt)
20:01:14 <oerjan> BlueProtoman: you need 2 counters for tc-ness
20:01:22 -!- MoALTz has quit (Quit: brb).
20:01:44 <oerjan> although you need to encode the string extra for that to work
20:02:26 <oerjan> basically, first you encode your string as one counter value, then you encode all your starting counter values as 2
20:02:28 <BlueProtoman> oerjan: So the first goes to the Godel-encoded input, the second goes to what? The current state?
20:02:42 <oerjan> no the state is separate
20:03:03 <oerjan> although, look at fractran
20:03:12 -!- ter2 has joined.
20:03:12 -!- tertu has quit (Disconnected by services).
20:03:27 <BlueProtoman> Why would I start off all the counters but one (which goes to input) with 2?
20:03:42 <oerjan> the second may start as 0, it is only there as intermediate storage.
20:04:21 <BlueProtoman> Oh, OK. I always thought that the states were maintained only with the counters--counter machines have their own FSMs like Turing machines or PDAs do?
20:04:34 -!- not^v has joined.
20:05:13 -!- ^v has quit (Read error: Connection reset by peer).
20:05:56 <oerjan> although you _can_ encode the state too, that's how you program in fractran.
20:06:31 <BlueProtoman> So then let's say I want to simulate a 2-counter machine with a 2-stack PDA (or vice versa). Does this mean I first have to push the input to one of the stacks (and equivalently, Godel-encode the input in one of the counters) before I can do anything?
20:06:32 <oerjan> but then you still have the fractran state of where you are in the list of fractions. and then you can encode all that as 2 counters.
20:07:08 <BlueProtoman> Because I'm assuming classic counter machines don't have a notion of an input tape like a Turing machine or even a PDA does, does it?
20:07:10 <oerjan> well PDA's generally have input as well, don't they.
20:07:22 -!- edwardk has quit (Quit: Computer has gone to sleep.).
20:07:43 <oerjan> you can add an input command of course. but you don't need it for TC-ness once you have encoded the starting input as a counter.
20:08:40 <BlueProtoman> OK. So that first counter == whatever input the stack machine gets. Push to stack si == increase counter ci by the next prime number to the power of its Godel mapping?
20:11:49 <int-e> you can implement a 2 stack pda quite naturally with 3 counters, then simulate those with 2 counters using Gödel tricks, e.g. 2^a3^b5^c.
20:12:21 <BlueProtoman> Yeah, that I get--one stack goes to the input, the others just correspond to uni-symbol stacks.
20:14:59 <oerjan> this does remind me of the work i did on 3-cell brainfuck. i found out how to load input into the cell but not how to print the output properly afterwards.
20:17:25 -!- MoALTz has joined.
20:17:26 <oerjan> 3-cell brainfuck is almost like 2-counter machine, but slightly more cramped so you cannot do a full fsa directly.
20:18:34 <myname> haskell question: does anybody know how to make more than one expression for the same branch in a case?
20:18:44 <oerjan> (every time you end a loop a cell must be 0, so you have only 2 cells you can preserve throughout)
20:18:47 <kmc> what would that mean myname
20:19:10 <myname> case somechar of <'x' or 'y'> -> ...
20:19:20 <oerjan> that's not expression, that's pattern.
20:19:39 <oerjan> and you cannot. well maybe with the newest extensions.
20:20:19 <oerjan> in that case you can use e.g. a guard
20:20:28 <kmc> yeah it's too bad
20:20:37 <kmc> Rust allows that, but its patterns are worse in other ways
20:21:14 <oerjan> it's a faq, pretty sure i saw it on SO the other day.
20:21:54 <int-e> oerjan: do you know of a proof that 2-cell brainfuck is not Turing complete?
20:22:09 <oerjan> hm i had an evil idea.
20:22:11 <Jafet> x | x .&. (ord 'x' .|. ord 'y') < 2 ->
20:22:45 <myname> cannot express how ugly that is
20:22:52 <kmc> it's also not correct in general, is it?
20:22:57 <oerjan> int-e: hm my memory is vague but i think maybe you can enumerate all the possibilities for what a program can do then.
20:23:26 <Jafet> It's correct in admiral
20:23:58 <oerjan> hm what if you combine pattern guards with lambdacase?
20:24:14 <oerjan> no, not pattern guards
20:24:46 <zzo38> That is too bad that you cannot make such a pattern; it should make such an extension, I think it would be a good idea. You can already make a case block with multiple choices to the same branch in C and in BASIC.
20:25:06 <Jafet> > (\case 'x' -> Just 'x'; 'y' -> Just 'y'; _ -> Nothing -> Just x -> x) 'x'
20:25:07 <lambdabot> <hint>:1:3: parse error on input ‘case’
20:25:21 -!- JZTech101 has left ("Now What?").
20:26:35 <oerjan> ityn ((\case 'x' -> True; 'y' -> True; _ -> False) -> True)
20:26:40 <int-e> oerjan: Actually, intuitively I'd expect that it is TC, because 2 counter machines run into the same limitation: they loop (or terminate quickly) until one of the counters reaches 0, then they can branch off.
20:26:56 <kmc> Rust hasn't got pattern guards :/
20:27:03 <kmc> except they call the regular guards "pattern guards" which is mega confusing
20:27:34 <lambdabot> dark says: <shapr> for example: "head (filter (\x -> x > 5) [1..])" <shapr> in a strict language, you can't easily play with infinite lists <dark> In a strict language, you would write that as "6" :)
20:27:37 <oerjan> int-e: but they have full fsa branching ability
20:27:45 <int-e> oerjan: but with BF the transitions that you get are limited, so it's not straight-forward. obviously you know that.
20:27:54 -!- Languager_ has quit (Quit: Leaving).
20:27:59 <oerjan> int-e: i _believe_ 2-cell bf is not tc.
20:28:00 <myname> rust still got a good mixture of functional and imperative programming imo
20:28:28 <oerjan> myname: i think that ((\case 'x' -> True; 'y' -> True; _ -> False) -> True) technically works >:)
20:28:43 <Jafet> @quote \\x.->.case
20:28:43 <lambdabot> benmachine says: let (\x -> case x of (\x -> x -> x) -> x -> x) = 0 in x / best view pattern evar
20:28:46 <oerjan> requires LambdaCase and ViewPatterns
20:28:47 <kmc> myname: Haskell has a better mix, in a sense
20:28:53 <kmc> but Rust has an unusual set of design constraints
20:29:24 <int-e> but yes, that looks correct
20:29:32 <myname> what do you mean with unusual set of design constraints
20:30:15 <kmc> it doesn't have garbage collection or other things that require a heavyweight runtime
20:30:22 <kmc> (it will eventually have optional garbage collection)
20:30:47 <myname> i do find that pretty interesting
20:30:56 <kmc> you get the choice between a runtime with green threads and libuv, or basically no runtime just making system calls the way a C program would
20:31:04 <myname> i take a look at rust for quite some time
20:31:26 <kmc> and in the latter case you can even compile without libc and write an EFI binary, a kernel, a Linux kernel module, a microcontroller program, etc.
20:31:51 <int-e> oh. x == \x -> x -> x
20:32:41 <myname> i just wish for rust to become stable
20:32:57 <kmc> I know there are things for "bare metal" programming in Haskell as well but it's a big pain
20:33:15 <int-e> rust is the antithesis of stability, ask any engineer
20:33:27 <oerjan> hm i think the parentheses are redundant in that pattern
20:33:29 <kmc> whereas Rust is a modern language that's basically compatible with the traditional C world of native compiling and linking
20:33:32 <kmc> myname: you will get your wish this year, is the plan
20:33:56 <myname> i so want to do stuff with it
20:34:06 <oerjan> and also, you could make a quasiquote wrapping that up
20:34:13 <int-e> @run (\case x -> x) 1
20:34:14 <lambdabot> <hint>:1:3: parse error on input ‘case’
20:34:35 <myname> now only documentation needs to get better *g*
20:34:36 <oerjan> int-e: i don't think the extension is enabled?
20:34:36 <kmc> i work on a 100,000 line Rust project and it is a pretty big pain keeping up with the language, yeah
20:34:38 <int-e> @run let id -> x = 0 in x
20:34:39 <lambdabot> <hint>:1:8: parse error on input ‘->’
20:34:46 <kmc> it's not too early to learn the core concepts, though
20:34:52 <kmc> those aren't gonna change much
20:34:54 <int-e> oerjan: this is quicker than checking the source :)
20:35:16 <myname> kmc: indeed, it just is disappointing :D
20:35:50 <int-e> oerjan: I'm a bit surprised that nobody has requested those extensions to be enabled in \-bot yet.
20:41:00 <int-e> so this works: let (\(\x -> x -> x) -> x -> \x -> x -> x) = 0 in x
20:42:27 -!- Patashu has joined.
20:43:01 <BlueProtoman> So, on simulating a 2-stack PDA with a 4-counter machine; one counter goes to the input, two go to stacks, and one is unused. Handling the inc and dec instructions is easy. What about the jump-if-zero instruction?
20:44:44 <ais523> normally you have to go through some intermediate encoding
20:44:50 <ais523> you might want to look at http://esolangs.org/wiki/Fractran
20:45:01 <ais523> it should give you some ideas about compiling things to counter machines
20:45:53 -!- AnotherTest has quit (Ping timeout: 264 seconds).
20:46:27 -!- Patashu_ has joined.
20:46:27 -!- Patashu has quit (Disconnected by services).
20:52:58 -!- mhi^ has quit (Quit: Lost terminal).
20:58:02 -!- fungot has quit (Ping timeout: 252 seconds).
21:02:50 <int-e> BlueProtoman: Ah, I was ignoring input (assuming it goes to a stack) when I said that 3 counters work easily.
21:11:51 <Sgeo> Just downloaded a tutorial-game for something
21:12:07 <Sgeo> And in the comments.... "Contributors: Julio Monteiro, Sgeo, TheMonkeyDidIt, Deadron"
21:12:13 <Sgeo> I don't... remember contributing to it
21:12:21 <Sgeo> Two Steps BYOND
21:13:04 <Sgeo> http://www.byond.com/developer/deadron/stepbyond
21:13:13 <Sgeo> It currently isn't compiling :(
21:13:28 <b_jonas> and then you get transformations that increase runtime double exponential
21:15:08 <oerjan> finally Sgeo discovers his **** clone
21:19:41 <kmc> fuck clone?
21:20:53 <kmc> that is only one of the many wonderful possibilities of having a clone
21:22:53 -!- Patashu_ has quit (Ping timeout: 252 seconds).
21:27:33 -!- callforjudgement has joined.
21:27:44 -!- ais523 has quit (Disconnected by services).
21:27:45 -!- callforjudgement has changed nick to ais523.
21:30:08 <b_jonas> glogbackup: yeah. but double exponential might be an exaggeration. I don't follow how efficient counter machines are these days, maybe they're single exponential
21:31:50 <oerjan> the keys are like right next to each other.
21:33:16 -!- ais523 has quit.
21:36:22 -!- conehead has joined.
21:49:31 -!- password2 has joined.
21:53:34 -!- oerjan has quit (Quit: Nite).
22:05:21 -!- Phantom__Hoover has joined.
22:31:42 -!- boily has joined.
22:35:37 -!- nooodl_ has joined.
22:38:42 -!- nooodl has quit (Ping timeout: 265 seconds).
22:39:44 <Taneb> I did that thing where I go to sleep before I need to go to sleep and then wake up two hours later really groggy
22:39:45 * boily lightly prods Taneb awake with his mapole
22:40:53 -!- Eritzap has joined.
22:41:13 <fowl> https://www.youtube.com/watch?v=DZUQM0ib2CI
22:44:11 <boily> fowl: AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA
22:44:54 <fowl> SHE TOOK IT ALLLLLLLLLLL AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA
22:48:05 -!- Eritzap has quit (Quit: Page closed).
22:54:51 <fowl> ?wa 700 + 132 + 942 + 732
22:55:14 <fowl> i forgot how to match
22:58:58 -!- nooodl has joined.
22:59:19 -!- yorick has quit (Remote host closed the connection).
23:02:23 -!- nooodl_ has quit (Ping timeout: 265 seconds).
23:05:32 -!- edwardk has joined.
23:09:28 <lambdabot> @where <key>, return element associated with key
23:10:46 -!- password2 has quit (Ping timeout: 240 seconds).
23:17:28 <fowl> i think its another channel that uses ?wa
23:17:35 <fowl> for wolfram alpha
23:24:28 <boily> int-e: does lambdie have the same features across all channels?
23:31:37 <myname> just make your client able to /calc
23:33:27 -!- witschge has joined.
23:35:01 <boily> myname: too logical.
23:35:45 <fowl> i cant justify writing a plugin for something i can just jump into a terminal and do (or google)
23:37:28 <Bike> whaddya need a plugin for, just do some alias to /exec whatever dc
23:40:03 -!- witschge has left.
23:47:52 -!- nooodl has quit (Quit: Ik ga weg).
00:10:36 -!- Phantom__Hoover has quit (Remote host closed the connection).
00:18:17 -!- augur has quit (Quit: Leaving...).
00:18:44 -!- augur has joined.
00:27:17 <kmc> fungots fall on fungot falls
00:32:46 <lambdabot> shachaf: 700 + 132 + 942 + 732 => 2506
00:34:02 -!- edwardk has quit (Quit: Computer has gone to sleep.).
00:34:52 * boily screams «AAAAAAAAAAAAAAAAAAAAAAAAAAAAAA» at fizzie for having unfungotted the channel
00:55:50 -!- pikhq has quit (Read error: No route to host).
00:57:04 -!- pikhq has joined.
00:58:11 -!- shikhin has joined.
00:58:20 -!- Ghoul_ has joined.
01:02:46 -!- boily has quit (Quit: SAXOPHONIC CHICKEN).
01:33:26 -!- shikhin has quit (Ping timeout: 255 seconds).
02:47:34 <fowl> this is like a tagged union, correct? data List a = Nil | Cons a (List a)
02:48:39 <Bike> what ttrpgs use exponentiation of random numbers? asking for a friend
02:49:06 <zzo38> fowl: It can mean a empty list or a list consisting of a value and a list, so it is like a tagged union
02:49:17 <fowl> do "Nil" and "Cons" have any meaning outside of the list? (are they even defined?)
02:49:26 <Bike> fowl: they're constructors.
02:49:32 <zzo38> fowl: Nil and Cons are constructors of the datatype called List.
02:50:13 <zzo38> Bike: Can you explain how you want to use exponentiation of random numbers? You can do 2 to the power of 1 to 6 if you use a backgammon doubling cube, perhaps.
02:50:29 <Bike> i don't really care how it's used, i just want to see how it is used
02:51:03 <zzo38> I have added various things into the SQL such as a CREATE FUNCTION, CREATE COLLATION, CREATE MACRO, CREATE NAMESPACE, and the ability for trigger programs to contain SAVEPOINT, RELEASE, ROLLBACK TO, but still some missing thing such as traps, while-loops, overrides, etc
02:51:13 <zzo38> Bike: Well, I don't know.
02:58:09 -!- Sorella has quit (Quit: It is tiem!).
02:58:19 -!- tromp has joined.
03:00:33 <zzo38> I don't know what that is. What is that?
03:01:17 <BlueProtoman> It's a program for simulating various abstract machines ("Java Formal Languages and Automata Package"), including Turing machines, FSMs, PDAs, and a few others.
03:01:52 <Bike> partial differential assistant
03:06:50 <Bike> but nah i've never used it.
03:12:44 <BlueProtoman> Hm. I'm wondering why the majority of my states in a 2-tape Turing machine are highlighted as nondeterministic.
03:51:32 -!- tromp has quit (Remote host closed the connection).
03:52:04 -!- tromp has joined.
03:53:05 -!- ter2 has quit (Ping timeout: 250 seconds).
03:56:44 -!- tromp has quit (Ping timeout: 265 seconds).
04:00:14 <Sgeo> http://pixelcomic.net/287.php
04:00:19 <Sgeo> Not very "new", but it's new to me
04:07:19 -!- Ghoul_ has quit (Ping timeout: 252 seconds).
04:07:19 -!- pikhq has quit (Ping timeout: 252 seconds).
04:07:29 -!- not^v has quit (Read error: Connection reset by peer).
04:07:58 -!- not^v has joined.
04:10:31 -!- Ghoul_ has joined.
04:16:31 -!- pikhq has joined.
04:17:24 <fizzie> But it was quite a long time ago, and I have to board a flight any minute now.
04:42:53 -!- Vorpal has quit (Quit: ZNC - http://znc.sourceforge.net).
04:43:45 -!- not^v has quit (Quit: http://i.imgur.com/DrFFzea.png).
04:49:41 <BlueProtoman> Someone give me two binary numbers likely to trip up an amateur's Turing machine that's supposed to add them.
04:51:58 -!- Slereah_ has quit (Ping timeout: 276 seconds).
05:15:20 -!- password2 has joined.
05:43:00 -!- Zerker has joined.
05:52:39 -!- Zerker has quit (Quit: Colloquy for iPad - Timeout (10 minutes)).
06:02:03 <HackEgo> uobcoin grailcoin durcoin calcoin rktureheading-bookcoin dividencoin omhncoin acicoin hunthenamecoin bestcoin refcoin orrhycoin bigcoin concoin omnisccoin mincoin origicoin anycoin penrcoin mushelmsiecoin
06:05:42 -!- BlueProtoman has quit (Remote host closed the connection).
06:12:24 -!- oerjan has joined.
06:18:10 -!- MoALTz has quit (Quit: bbl).
06:22:20 <Sgeo> concoin, describes all coins?
06:22:27 <Sgeo> (ok probably not really)
06:23:55 * oerjan remembers he hasn't checked bitcoinity in a while
06:24:35 <oerjan> looks fairly stable for the last weeks
06:25:14 <oerjan> although there's still that downward trend
06:27:10 -!- atehwa has joined.
06:50:52 <HackEgo> /home/hackbot/hackbot.hg/multibot_cmds/lib/limits: line 5: exec: cairns: not found
06:51:51 <HackEgo> bringcoin automailmentraunterating-boobuminuspicoin l00pcoin odbcocoin irifycoin cobincoin rociecoin capuracoin wikincoin elogycoin exconcoin thilcoin minuscoin tminarycoin nhohtcoin camolzcoin tagcoin kiplecoin x-dcoin quatcoin
06:55:18 -!- tromp has joined.
06:59:45 -!- tromp has quit (Ping timeout: 258 seconds).
07:12:23 -!- Tritonio has joined.
07:39:50 -!- slereah has joined.
07:52:41 <lexande> have we had quinecoin yet?
08:01:15 <kmc> apparently not
08:02:08 -!- edwardk has joined.
08:31:24 -!- Patashu has joined.
08:34:05 -!- Ghoul_ has quit (Quit: Connection closed for inactivity).
08:54:41 -!- Patashu_ has joined.
08:54:41 -!- Patashu has quit (Disconnected by services).
09:38:47 -!- MindlessDrone has joined.
09:44:49 -!- shikhin has joined.
09:47:33 -!- conehead has quit (Quit: Computer has gone to sleep).
10:09:07 -!- boily has joined.
10:12:20 <HackEgo> olist (951): shachaf oerjan Sgeo FireFly boily nortti
10:30:11 <shachaf> i thought it was a survivor bias joke but people seem to think it's just an "in"flammable joke
10:32:09 <oerjan> i seemed to think that too
10:49:02 -!- Phantom_Hoover has joined.
10:51:23 -!- drdanmaku has quit (Quit: Connection closed for inactivity).
10:53:24 -!- constant has changed nick to trout.
10:57:09 -!- Tritonio has quit (Ping timeout: 245 seconds).
11:10:14 -!- boily has quit (Quit: RECAPITULATING CHICKEN).
11:39:41 -!- Sgeo has quit (Read error: Connection reset by peer).
11:39:54 -!- nucular has joined.
11:39:54 -!- nucular has quit (Changing host).
11:39:54 -!- nucular has joined.
11:40:02 -!- yorick has joined.
11:50:36 -!- oerjan has quit (Quit: leaving).
11:59:47 <b_jonas> shachaf: I think it's "in"flammable joke too,
12:00:19 <b_jonas> but then most of the airship is made of wood and textile (also hydrogen if they're relaly unlucky), so most of it is inflammable
12:05:04 <FreeFull> Helium doesn't have the same lift and is expensive
12:06:08 -!- tromp has joined.
12:10:08 <int-e> @tell oerjan I can believe that 2-cell brainfuck is not TC; it seems that the halting problem is decidable for those, but it gets messy and I have no formal proof. What if we have 2 counters and a "landing field" that is always zero and cannot be modified (say, any attempt to do so would halt the program)?
12:12:01 <slereah> I seem to recall that you need like 6 cells or so for TC brainfuck
12:12:45 <int-e> slereah: that's certainly too much
12:13:22 <slereah> That is just vague recollection
12:16:58 <Jafet> 3-cell can simulate 2-counter machines, which are undecidable
12:20:42 -!- john_metcalf has quit (Read error: Connection reset by peer).
12:21:02 -!- john_metcalf has joined.
12:21:26 <int-e> I guess 4 cells are easy, 3 cells need work.
12:21:57 <Jafet> 3-cell is easy, 2-cell needs work
12:22:17 <Jafet> (I would not immediately rule out the possibility that 2-cell is undecidable)
12:24:43 <int-e> Jafet: The problem is that only innermost loops can have unbounded values in both counters, and they cannot communicate with loops outside (they terminate because one of the counters is zero, and you cannot even use the position of the pointer because there's no way to check it.)
12:32:22 <Jafet> Well, with 2 cells, any terminating inner loop takes (ma,b) to (0,b+na)
12:33:31 -!- Phantom_Hoover has quit (Ping timeout: 250 seconds).
12:34:06 <b_jonas> my guess is that it's not known what the exact lowest number of cells is that's enough
12:38:21 <Jafet> Actually, it may be possible to simulate fractran
12:44:34 <Jafet> p/q ==> while(A) { if (A==1) { while(B) { A+=q, B-=p; } swap(A,B); } else if (A==2) ... else if (A==q-1) { ... } else A-=q, B+=p; }
12:45:50 <Jafet> That converts (A, 0) -> (0, pA/q) if q|A, otherwise (0, A)
12:46:32 <FreeFull> You could try writing a two-cell oracle and seeing if there are any inputs that could possibly have it provide the wrong anwer
12:46:54 <FreeFull> If there aren't any, you know it's not turing-complete
12:47:11 <Jafet> That sounds like it will take a lot of seeing.
12:48:04 <FreeFull> You would have to find a way to cover all the cases
12:48:48 <FreeFull> Can you even do fibbonacci with just two cells?
12:48:49 -!- tromp has quit (Remote host closed the connection).
12:49:22 -!- tromp has joined.
12:49:33 <ion> https://www.eff.org/privacybadger
12:50:29 <Jafet> ^bf >+<[.[->+<]>.[-<+>]]
12:53:57 -!- tromp has quit (Ping timeout: 258 seconds).
12:57:03 <Jafet> ion: I should really just null-route all ad networks
13:00:30 <int-e> it has run the whole program
13:00:33 <Jafet> Hmm, it might be hard to write the conditionals with no extra space.
13:00:39 <int-e> @bf >+<[.[->+<]>.[-<+>]]
13:01:01 <int-e> err, that won't produce any output
13:01:08 <Jafet> @bf >+[.[-<+>]>.[->+<]<]
13:01:14 -!- Sorella has joined.
13:01:27 <int-e> @bf ++++[>++++<-]>{<++++>-]<.
13:01:27 <lambdabot> bf: Ix{Int}.index: Index (-1) out of range ((0,15))
13:01:33 <int-e> @bf ++++[>++++<-]>{<++++>-]>.
13:01:34 <lambdabot> bf: Ix{Int}.index: Index (-1) out of range ((0,15))
13:01:39 <int-e> @bf ++++[>++++<-]>[<++++>-]>.
13:01:44 <int-e> @bf ++++[>++++<-]>[<++++>-]<.
13:02:07 <int-e> oh. two spaces, that's odd.
13:02:22 <lambdabot> !"#$%&'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\]^_`abcdefghij...
13:05:30 <Jafet> lambdabot was done with it.
13:05:44 <FreeFull> And it still just prints Done. even for infinite loops?
13:05:57 <int-e> because the brainfuck interpreter sets resource limiits
13:06:01 <int-e> gets killed, without output.
13:06:05 <FreeFull> @bf +++++++++++++++++++++++++++++++++++++=.+[]
13:07:54 <FreeFull> Doesn't matter since it gets ignored
13:31:59 -!- edwardk has quit (Quit: Leaving...).
13:33:24 -!- edwardk has joined.
13:34:02 <b_jonas> @bf >+++++++++[->+>++++<<]>[->.+.+.+.+.+.+.+.+.+.+.+.+<]
13:34:02 <lambdabot> $%&'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\]^_`abcdefghijklmn...
13:35:17 <b_jonas> `perl-e printf"%c",$_ for 32..127
13:35:18 <HackEgo> !"#$%&'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\]^_`abcdefghijklmnopqrstuvwxyz{|}~
13:38:50 -!- Melvar` has changed nick to Melvar.
13:39:49 -!- Frooxius has quit (Quit: *bubbles away*).
13:40:08 -!- nycs has changed nick to `^_^v.
13:43:57 -!- conehead has joined.
13:45:29 -!- Sprocklem has quit (Ping timeout: 245 seconds).
13:50:23 -!- Frooxius has joined.
13:56:01 -!- Patashu_ has quit (Ping timeout: 276 seconds).
14:12:34 -!- idris-ircslave has quit (Quit: Terminated).
14:12:57 -!- idris-bot has joined.
14:20:29 <Jafet> "EOF is a controversial issue. Many implementations return 0, some return -1, and several notable brainfuck programmers [...]" whoa notability
14:21:55 -!- yorick_ has joined.
14:23:19 -!- yorick has quit (Ping timeout: 276 seconds).
14:40:57 -!- Sprocklem has joined.
14:43:46 <slereah> Also what do those several ones return!
14:44:25 -!- shikhout has joined.
14:47:25 -!- shikhin has quit (Ping timeout: 258 seconds).
14:53:30 -!- shikhout has changed nick to shikhin.
14:57:07 -!- yorick_ has changed nick to yorick.
15:06:21 -!- tromp has joined.
15:10:48 -!- tromp has quit (Ping timeout: 258 seconds).
15:27:31 -!- nycs has joined.
15:31:33 -!- `^_^v has quit (Ping timeout: 276 seconds).
15:37:28 <slereah> total heap usage: 666 allocs, 666 frees, 312,688 bytes allocated
15:41:57 -!- password2 has quit (Ping timeout: 240 seconds).
15:42:04 -!- nycs has changed nick to `^_^v.
15:45:02 <Bike> the freelist of the beast
15:46:30 <slereah> The things I had to do to plug those leaks~
15:46:37 <slereah> First born son and all tat
15:52:31 -!- tromp has joined.
15:56:45 -!- tromp has quit (Ping timeout: 240 seconds).
15:58:22 -!- drdanmaku has joined.
16:02:41 -!- slereah has quit (Quit: Leaving).
16:27:21 -!- MoALTz has joined.
16:32:05 -!- ^v has joined.
16:34:22 -!- john_metcalf has quit (Ping timeout: 258 seconds).
16:36:32 -!- password2 has joined.
16:42:32 -!- BlueProtoman has joined.
16:46:09 <BlueProtoman> So I'm trying to either prove or disprove that the language {M where M is a Turing machine that, given blank input, will write a non-blank symbol somewhere} is decidable. Can't I just have a Turing machine B that halts if M writes a non-blank and loops if not?
16:47:34 <Bike> yeah, but during the loop you might never know definitively that you can stop looping
16:49:29 <BlueProtoman> Would that make the language I specified undecidable?
16:50:03 <Bike> decidable means total, so, your recognizer needs to halt on all inputs, no?
16:50:55 <Bike> and your recognizer isn't going to halt on any M that doesn't halt and doesn't write a non-blank symbol
16:51:37 <BlueProtoman> Oh, I see. So the input M doesn't have to halt, it just has to write a non-blank symbol.
16:53:05 <zzo38> If it never writes a non-blank symbol then I would think an infinite loop is detectable?
16:53:19 <zzo38> (You can ignore the tape position)
16:53:55 -!- shikhin has quit (Remote host closed the connection).
17:01:31 <Bike> zzo's saying that it's probably computable to see if a turing machine that never writes a non-blank symbol halts.
17:01:58 <zzo38> If the number of states is finite then you can look for a loop in the state considering that the symbol is first at blank, that it leads to one you have been on before when the written symbol is also blank.
17:03:33 <BlueProtoman> zzo38: So it's similar to solving the halting problem for FSMs?
17:04:46 <fowl> 313.9 - 101.77
17:04:50 <Bike> yeah, turing machines have "infinite states" because they can write all the symbols they want, but you're restricting that
17:04:51 <fowl> 313.9 - 101.77d1
17:05:05 <Bike> i forget enough about strict during machines to remember if you can do something weird with blanks in unary, though
17:05:46 -!- Slereah_ has joined.
17:07:03 <zzo38> If there is only one kind of blank symbol and the tape is infinite both ways then any tape position on a blank tape is the same as any other
17:07:29 <Bike> oh right, it starts out all blank.
17:07:39 <BlueProtoman> zzo38: But it *might* write a non-blank symbol.
17:08:10 <BlueProtoman> That's what I'm trying to prove; whether the language of all Turing machines that write a non-blank symbol given blank input is decidable.
17:08:31 <Bike> i imagine you can look at all states to see which can write a non-blank symbol, and see if any of those are reachable from the starting state on a blank tape
17:09:03 <BlueProtoman> OK, but what if we loop forever with blank input?
17:09:29 <Bike> once you've found no non-blank writing you're just dealing with an FSM
17:09:44 <zzo38> Bike: Yes, that is what I meant.
17:13:02 <BlueProtoman> So then what happens if I have a Turing machine B that takes some M as input, and halts iff it runs M and then M writes a non-blank symbol?
17:16:09 <BlueProtoman> The actual definition of L is L = { M where M is a Turing Machine which, when started with a blank input tape, will finally write some non-blank symbol on its tape.} Does that "finally" change anything?
17:18:02 <int-e> meaning "eventually"?
17:18:50 <int-e> (the other interpretation, though unlikely, is "in its last step".)
17:21:09 <BlueProtoman> I'm going to assume that the professor just means it'll write a non-blank symbol at some point, as opposed to halting on a non-blank symbol.
17:21:20 <int-e> Unfortunately, that detail changes the answer.
17:21:22 <BlueProtoman> Because I have other problems to do and this homework is due at midnight.
17:21:53 -!- b_jonas has quit (Ping timeout: 264 seconds).
17:22:08 <Bike> So then what happens if I have a Turing machine B that takes some M as input, and halts iff it runs M and then M writes a non-blank symbol? <-- like i said, that's not sufficient. you could have the machine that writes nothing and doesn't move but doesn't halt.
17:22:10 -!- Froox has joined.
17:23:04 -!- b_jonas_ has joined.
17:23:05 -!- Frooxius has quit (Read error: Connection reset by peer).
17:23:20 <BlueProtoman> Let L=\left\{ \string M|\mbox{\ensuremath{M} is a Turing machine that will write a non-blank symbol on its tape if the input is blank}\right\}
17:23:20 <BlueProtoman> is decidable. Note that Turing machines have a finite number of states. Thus, they have a finite number of transitions of the form \delta\left(q,\square\right)
17:23:26 <BlueProtoman> more than once before we write a non-blank symbol, then we know that M
17:23:29 <BlueProtoman> won't halt. So let's have a decider \decider L
17:23:42 <BlueProtoman> is deduced to loop forever before writing a non-blank symbol. Hey, look, \decider L
17:23:44 <int-e> The real problem is this: a typical TM interpreter will put non-blank symbols on the tape.
17:24:22 <int-e> BlueProtoman: yes, you shouldn't have pasted it here, but that looks about correct.
17:25:05 <Bike> int-e: starting with blank input is part of the conditions, though
17:25:21 <int-e> ... hmm. or not. I'm not sure what you're doing at "o let's have a decider \decider L".
17:26:45 <int-e> Bike: The TM degenerates to a finite automaton or a single counter machine (depending on whether you can test for the left tape end or not) if it can't write (non-blank symbols) to the tape.
17:27:52 <Bike> i mean i'm not sure what you meant by "the real problem"
17:28:39 <int-e> Bike: at that point I was assuming that we wanted to show that L is undecidable by the usual diagonalization. I probably misread something.
17:28:53 -!- oerjan has joined.
17:29:38 <BlueProtoman> How does M *writing a non-blank then halting* change the answer?
17:30:22 <int-e> BlueProtoman: as I meant it it would allow M to also write non-blank symbols at other times, only the final write would count.
17:30:55 <BlueProtoman> int-e: OK, would that affect decidability, then?
17:31:50 <int-e> BlueProtoman: obviously. Just take any turing machine and make sure it writes a non-blank symbol in its halting state.
17:32:08 <int-e> (introducing a new halting state in the process)
17:32:14 <BlueProtoman> Yeah. If you wanna be pedantic, check the cells immediately to its left and right.
17:32:35 <int-e> then there won't be a final step
17:32:55 <int-e> hence no non-blank symbol written in the final step
17:33:04 <BlueProtoman> You'd have to solve the halting problem, though, since now you're not limited to what's effectively an FSM.
17:33:22 <int-e> that was the point
17:36:01 -!- Sprocklem has quit (Quit: School labs/lunch).
17:36:03 <lambdabot> int-e said 5h 25m 54s ago: I can believe that 2-cell brainfuck is not TC; it seems that the halting problem is decidable for those, but it gets messy and I have no formal proof. What if we have 2 counters and a "landing field" that is always zero and cannot be modified (say, any attempt to do so would halt the program)?
17:36:03 <lambdabot> int-e said 19m 23s ago: (Re: 2-cell brainfuck) I found the following refinement of the insight that loops terminate with zeros helpful: At each point outside of innermost loops, one of the counters is bounded by a constant.
17:36:59 <oerjan> yold is past participle of yell, right?
17:40:03 <oerjan> int-e: ah yes. i recall thinking about that constant thing. except that it's almost decidable _exactly_ which constant. at least in some spots.
17:40:32 <BlueProtoman> Now I'm trying to prove that you can simulate a 2-stack machine with a 4-counter machine (or vice versa). P2 is the 2-stack PDA and C4 is the 4-counter Lambek machine. This is my proof: http://i.imgur.com/aNDr8BE.png Any thoughts?
17:40:37 <Bike> the language of turing machines that halt and write some certain output at the same time is fairly obviously undecidable so your prof probably didn't mean that, but you might want to mention the ambiguity
17:40:52 <oerjan> but there's some branching possible when you return to the beginning of a loop.
17:41:47 <Bike> BlueProtoman: c1 and c2 are stack pointers, c3 and c4 are godel-encoded stacks? makes sense to me. you might be able to reduce the time complexity by using a less dumb coding but you're just being asked about decidability, so
17:42:30 <BlueProtoman> Bike: Strictly speaking, the problem is this: "Compare the running time (i.e., number of steps) of the following equivalent machines: (c) two-stack machine and a four-counter machine."
17:42:46 <Bike> oh. that's an odd question.
17:43:14 <BlueProtoman> Yeah, I clarified it. He said to just describe what it would take to simulate one with the other. We're given that they're Turing-equivalent, at least.
17:43:23 <Bike> oh, well alright.
17:43:35 <Bike> you could use a prefix coding or something for the stacks, then. don't need no stinkin primes.
17:44:16 <Bike> a code where no codeword is a prefix of another codeword
17:44:31 <Bike> like, if your alphabet is AB, you could encode A -> 1, B -> 01, end of stack -> 00
17:44:56 <Bike> really the prefix isn't necessary, you can just use a block code, eh.
17:45:42 -!- Phantom_Hoover has joined.
17:45:46 <oerjan> pretty sure you can simulate two stacks with 3 counters pretty easily, without even gödel encoding, just base representation.
17:45:57 <Bike> so say A -> 11, B -> 01, end of stack -> 00, then it's obviously linear to get somewhere on the stack.
17:46:12 <oerjan> because the two stacks can share their "temporary" storage counter
17:46:21 <Bike> and increment and decrement of the stack pointer are just increment and decrement.
17:46:34 <Bike> the thing about godel coding is that it makes sense mathematically but it's really fucking dumb practically speaking :V
17:47:00 <oerjan> with gödel encoding you only need 2 counters, of course.
17:47:19 <BlueProtoman> So I'd use Godel encoding for simulating 2 counters with 2 stacks (or vice versa)?
17:48:19 <oerjan> also a stack doesn't need a pointer. you just pop off the top hth
17:48:32 <BlueProtoman> Bike: What if the stacks have more than one unique symbol each?
17:48:45 <Bike> well i guess i gave you two RAMs then
17:48:50 <Bike> BlueProtoman: what?
17:48:56 <oerjan> no, with 2 stacks you just use them as a turing tape, and use something simpler than gödel.
17:49:05 <oerjan> like, interleaved binary
17:49:52 <oerjan> the prime number stuff is really only needed to get down to 2 counters.
17:49:55 <int-e> oerjan: apparently there is a separate input stream.
17:50:12 <int-e> oerjan: that's how we arrived at 4 counters yesterday.
17:50:39 <BlueProtoman> I gave a second counter for the input because, well, the counters themselves give input.
17:50:52 <BlueProtoman> Where else would I encode the input to the 2-stack PDA?
17:50:56 <int-e> otherwise I agree with 3 of course.
17:51:07 <int-e> BlueProtoman: initial contents of one of the stacks
17:51:35 <Bike> welp it's official, never not going to read PDA as PDE
17:52:03 <Bike> you can do anything, if only you believe in yourself
17:52:04 <int-e> BlueProtoman: it depends on your definitions, obviously.
17:53:54 <BlueProtoman> So let's go back to 2 stacks, 2 counters. I can simulate the counters with stacks easily, just have an alphabet of two symbols, and push one symbol only to c1, and one symbol only to c2. I could Godel-encode the input as a really big monosymbol stack. But what about the jump-if-zero instruction?
17:54:17 <oerjan> <slereah> I seem to recall that you need like 6 cells or so for TC brainfuck <-- SOME OF US HAVE MADE LATER PROGRESS HTH
17:54:35 <oerjan> ^wiki Collatz_function
17:55:05 <oerjan> http://esolangs.org/wiki/Collatz_function
17:57:30 <oerjan> BlueProtoman: jump-if-zero becomes jump-if-stack-empty? i don't see the problem...
17:58:15 <oerjan> if you don't have stack-empty testing, add a special bottom symbol, i guess.
17:59:30 <oerjan> wait do you need different symbols for c1 and c2, anyhow
18:00:05 <BlueProtoman> oerjan: Oh, wait, this becomes the problem of the states, not the stack.
18:00:35 <oerjan> yes, you have nearly the same underlying FSA in both cases, i should think
18:00:48 <oerjan> just a little different interpretation of what the transitions mean
18:02:10 <BlueProtoman> Each instruction in a CM roughly corresponds to a state in a FSM?
18:02:58 <oerjan> int-e: Jafet: simulating fractran is precisely what that link does for 3-cell bf.
18:03:09 <oerjan> in case any of you haven't seen it yet.
18:05:05 <oerjan> it's just a matter of representation whether you write things down as something assembly like or as a big table of state transitions + commands.
18:05:41 <oerjan> of course your professor presumably has chosen one such representation for you.
18:05:49 <BlueProtoman> So assembly is closer to CS-theoretic abstract machines than, say, Java?
18:06:02 <oerjan> depends on the assembly :P
18:06:15 <Bike> there's always vax's eval poly instruction
18:06:36 <oerjan> SUBLEQ assembly is pretty darn abstract
18:07:55 <oerjan> @tell Jafet simulating fractran is precisely what http://esolangs.org/wiki/Collatz_function does for 3-cell bf.
18:09:28 <oerjan> @tell Jafet and it took some munging to get that to fit. i don't think 2-cell can work.
18:14:22 <oerjan> @tell Jafet note that your if ... else if construction can easily require 4 cells if you are not very careful. (and swap needs 3 anyway.)
18:34:33 -!- fungot has joined.
18:34:51 <fizzie> This is a bit hard with only a tablet thing.
18:35:01 <fizzie> (I'm at a conference, I only took this thing with me.)
18:35:14 <fizzie> Hello from Florence, Italy, anyway.
18:37:32 <fizzie> There was a bottle of olive oil in the conference bag.
18:43:39 -!- zzo38 has quit (Remote host closed the connection).
18:44:04 <Taneb> Today I am going to use the Haskell FFI!
18:45:25 <oerjan> finally you get the chance to make ghc segfault!
18:45:35 <Taneb> Oh, I've done that already.
18:45:45 <Taneb> You remember my factorial calculator?
18:46:09 <Taneb> The one written in pure, (<*>), and unsafeCoerce?
18:46:44 <oerjan> unsafeCoerce does tend to be risky
18:46:44 <FireFly> I'm oddly curious how that works out
18:47:54 <int-e> yay, I'm done! foreign import ccall "math.h sin" csin :: CDouble -> CDouble
18:48:01 <oerjan> FireFly: iirc Taneb used it as I in ski calculus, because haskell cannot type the usual tricks used for recursion in ski calculus but unsafeCoerce brutally circumvents the typing
18:48:12 <Taneb> Yeah, that's right
18:48:22 <oerjan> pure is K and (<*>) is S btw
18:48:24 <Taneb> It was incredibly slow, and only worked up to 11
18:48:29 <Taneb> After that it crashed
18:48:57 <ion> unsafeCoerce is I
18:49:31 <ion> Oh, that was already said. Should have looked at more than the last four lines.
18:50:13 <ion> OH, YOU AGREE?
18:50:41 <oerjan> although hm, i don't think you can actually cause a segfault _purely_ with those three, can you?
18:50:57 <Taneb> I think I did when I was working it out
18:51:13 <Taneb> Like, when I had got it wrong
18:51:18 <oerjan> since there would always be corresponding to a lambda term
18:51:59 <oerjan> of course you applied it to something to get numbers didn't you, at that point things can go wrong
18:52:26 * int-e still doesn't know whether one can implement unsafePerformIO with unsafeCoerce and IO's (>>=) in a way that works across platforms and in conjunction with garbage collection
18:53:24 -!- SerialDreamer has joined.
18:53:59 <oerjan> !welcome SerialDreamer
18:54:01 <EgoBot> SerialDreamer: 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.)
18:54:11 <fowl> why are monads needed for IO?
18:54:13 <int-e> (the handling of the realWorld# token is slightly magical)
18:54:24 <int-e> fowl: that's a myth.
18:54:32 <Bike> they're not needed, they just make it easier
18:54:41 <int-e> fowl: the monadic IO interface is just convenient
18:54:47 -!- SerialDreamer has left.
18:54:53 <oerjan> fowl: it's just the most convenient pattern to enforce ordering of side effects
18:55:33 <fowl> the diff is like printf(file, "str") vs cout << "hello " << there ?
18:55:42 <fowl> cout << being the monandic version
18:56:13 <oerjan> i want to say "wat" but i'm not _entirely_ sure that analogy is nonsense.
18:56:48 <Bike> it's pretty nonsense
18:56:49 <FireFly> I think that would be more akin to >>= etc vs. do-notation
18:57:23 <fowl> oerjan, well from what i read monad is like a transformation on a value, ofstream's << doesnt transform the ofstream, but it does return it to allow chaining
18:57:42 <int-e> it's half a state monad then
18:57:45 <Bike> i just remembered that if make a burrito joke i will be banned
18:57:46 <int-e> but it misses the return value.
18:58:38 <int-e> Bike: Does this apply to just you or is that a general rule?
18:58:46 <fowl> haskell confuses me so much. im pretty sure its either a big inside joke _or_ haskellers just love self-flagellation
18:58:57 -!- ChanServ has set channel mode: +o oerjan.
18:59:01 <FireFly> What about it confuses you?
18:59:43 <Bike> well, let's test
18:59:57 <int-e> fowl: if this is about monads, forget that you ever heard the term and simply use 'do' notation for doing I/O. that should get you pretty far.
19:00:26 <fowl> why can functions only take one argument? whats the deal with returning functions to get around this, surely there is overhead in creating closures
19:00:55 <oerjan> fowl: ghc doesn't allocate closures if a function is fully applied
19:01:05 <oerjan> it tries to be reasonably smart about this.
19:01:23 <int-e> fowl: ah but we like to think of it differently. a function takes n arguments, but we can apply it partially, giving only 1,..., up to n of the arguments and leaving the rest for later.
19:01:40 <int-e> fowl: and indeed ghc also implements it that way.
19:01:47 <Bike> IO is like a burrito. an IO Int is a burrito full of delicious ints, but we can't eat it "until the haskell program has been reduced", which in the metaphor means who cares. sometimes you want to mash up two burritos, like an IO Int and an IO String, to get you something that lets you eat an int first and then a string. it also so happens that this mashup operation is nice to generalize to other foods, so, we package up these ...
19:01:53 <Bike> ... operations in an API and call it "monad" because we hate leibniz but love burritos
19:02:15 <int-e> Bike: this would explain why ghc is so ... large.
19:02:23 -!- oerjan has kicked Bike You forgot the jalapeños.
19:02:29 -!- oerjan has set channel mode: -o oerjan.
19:02:34 -!- Bike has joined.
19:02:43 <Bike> i really should have eatne lunch before putting that together
19:03:13 <FireFly> Then maybe you wouldn't've forgotten the jalapeños
19:03:54 <Bike> i'm not gonna eat some fucking shitass pepper
19:05:42 <fowl> it just seems like more of a badge of honor than a useful thing
19:06:47 <int-e> it's the Haskell cabal.
19:06:51 <Bike> man, i don't even use haskell and i can see why you'd generalize this. it's basic design principles.
19:07:27 <int-e> (*that*'s an inside joke. A weak one, but still.)
19:07:46 <oerjan> int-e: there is no cabal.
19:07:58 <int-e> oerjan: Cabal then. And cabal-install.
19:08:04 <oerjan> (that's an extremely _old_ inside joke)
19:08:07 <shachaf> whoa, remember that one story by heinlein
19:08:19 <int-e> oerjan: I may be too young for it.
19:08:37 <oerjan> int-e: it goes back to the Usenet age.
19:08:53 <Bike> which one is that? i remember the title
19:09:08 <shachaf> there was a prophet or something
19:09:46 <int-e> oerjan: Ah. I remember usenet, but I wasn't very active there (and really only in its german subpart anyway, where TINC wouldn't make much sense. (I found a wikipedia page on the subject))
19:10:06 <Bike> looks like i never read it
19:10:47 * int-e should know better and write "Usenet" and "subhierarchy".
19:11:17 <ion> fowl: Haskell supports a single tuple of arguments just fine, but it's pretty convenient to be able to apply a function partially without jumping through hoops.
19:11:50 <ion> which currying enables
19:13:34 <oerjan> what does jalapeñoing enable, i wonder.
19:14:06 <ion> Python: map(lambda ys: map(f, ys), xs). Haskell: map (map f) xs
19:16:13 <Bike> hm, does python not have apply
19:16:22 <oerjan> also, haskell supports tuples with more than two elements rather awkwardly.
19:17:06 <oerjan> possibly by design, to discourage using them as ersatz datatypes.
19:17:11 <Bike> 'cos (define (curry f x) (lambda (ys) (apply f (list* x ys)))) and then (map (curry map f) xs)
19:17:29 <Bike> i guess you can call that a hoop but it's not much of one.
19:17:39 <fowl> the page i read about haskell tuples looked like its very flimsy, in a tuple of 2 (_ x _) matches the second item, without an error? what if you tried (_ _ x), would it just fail to match?
19:17:57 <fowl> s/flimsy/forgiving/
19:18:14 <oerjan> fowl: you've missed the commas
19:18:30 <fowl> i was drunk too
19:18:30 <oerjan> otherwise it would match the third item
19:18:50 <fowl> oerjan, there is no third item in (1,2)
19:19:01 <FireFly> (_, x, _) wouldn't match (1,2) I'm pretty sure
19:19:03 <Bike> > (\(_,x,_) -> x) (3,4,5)
19:19:13 <FireFly> Mostly because they have different types
19:19:13 <Bike> no, wait, duh.
19:19:14 <oerjan> fowl: in that case neither would match, the pattern needs to have the same number of commas
19:19:16 <Bike> > (\(_,x,_) -> x) (3,4)
19:19:17 <lambdabot> Couldn't match expected type ‘(t0, t, t1)’
19:19:20 <ion> > let (_, x, _) = ("compile", "error") in x
19:19:21 <lambdabot> Couldn't match expected type ‘(t0, t2, t1)’
19:19:21 <lambdabot> with actual type ‘([GHC.Types.Char], [GHC.Types.Char])’
19:19:21 <lambdabot> Relevant bindings include x :: t2 (bound at <interactive>:1:9)
19:19:28 <fowl> let me see if i can find the page i was reading
19:21:05 <fowl> https://www.fpcomplete.com/school/to-infinity-and-beyond/pick-of-the-week/Simple%20examples#tuples
19:21:35 <Bike> that uses fst and snd for the 2-tuple, not the first and second it defines
19:21:44 <fowl> i see that now >_>
19:21:58 -!- AnotherTest has joined.
19:22:04 <fowl> last night <)<
19:22:19 <oerjan> gah fpcomplete is so heavy
19:23:21 <ion> oerjan: Hah, i just noticed the same thing when opening the link with my phone.
19:23:30 <Bike> clearly there should be a ThingYouCanTakeFirstOf typeclass with instances for (,) and (,,)
19:23:57 <kmc> there is a library for that
19:25:34 <BlueProtoman> Let's say I have a Turing machine that can only write to a given cell once (including the part of the tape the input's on). I want to prove that this is still Turing-equivalent. If the input is w, and I write to, say, the 2nd cell, next time I want to write to it can I go to the |w| + 2nd cell instead, and the time after that the 2*|w| + 2nd cell, etc.?
19:26:47 <Bike> that gives you a working area limited to the size of the input, no?
19:27:19 <ion> oerjan: The browser tab gets stuck for over a minute when loading that page.
19:28:33 <oerjan> ion: yeah and then i have to press return in the address line for it to relocate to the actual anchor which has been completely shifted away by all the expanding stuff
19:28:40 <ion> bike: IIRC Idris has sugar where (x, y, z) = (x, (y, z)). That seems nice to me.
19:29:50 <BlueProtoman> Bike: What if every time I write in cell n, I splice in another tape (thus pushing every non-blank symbol to the right one cell, starting from the left; i.e. XXX -> X_XX -> X_X_X)
19:30:21 <Bike> i'm gonna go see if i can't find a burrito to eat
19:30:49 <kmc> why stop there, eat a whole burro
19:31:10 <ion> I feel a monad joke coming.
19:32:09 <kmc> mo 'nads mo problems
19:35:25 <shachaf> kmc: do you still eat burritos every day
19:36:58 -!- MindlessDrone has quit (Ping timeout: 240 seconds).
19:38:12 <kmc> also feliz cinco de mayo everyone
19:39:19 -!- KingOfKarlsruhe has joined.
19:46:38 <Bike> bad news i had pizza
19:46:49 <Bike> someone explain how lenses are like pizza
19:48:20 <shachaf> i think lenses hit your eye in a similar fashion to a big pizza pie, or something along those lines
19:48:31 <Taneb> I had too much of them both yesterday
19:48:36 <kmc> void nsHtml5TreeBuilder::MaybeComplainAboutCharset(...)
19:49:22 <kmc> 420 complain about charset everyday
19:49:38 <Bike> well i only had a few slices, not the whole round
19:49:51 <Taneb> It's increasingly clear that I don't know enough C to use Haskell's FFI
19:49:54 <shachaf> Bike: the slices you ate are like a lens from the whole pizza
19:50:05 <shachaf> or a fold. did you fold your pizza.
19:50:24 <Taneb> But then I had two slices at once
19:50:32 <FireFly> So what is the parallel of a prism in this analogue?
19:50:52 <oerjan> your puns needs some review.
19:51:05 -!- MindlessDrone has joined.
19:54:50 <kmc> what are your FFI troubles Taneb?
19:55:34 -!- Sprocklem has joined.
19:55:58 <Taneb> kmc, basically, I don't know C
19:56:43 <Bike> http://animalnewyork.com/2014/artists-notebook-ramsey-nasser/ this is neat
19:56:54 <kmc> knowing C considered useful
19:58:24 <Taneb> I was thinking about something I wanted to do, and thought "this would actually be easier with pointers and mutability"
19:58:40 <Taneb> Already written a good deal of the program in Haskell and don't want to rewrite it
19:59:50 <Taneb> But like, if I implement this queue as a doubly-linked-list I can remove things from the middle really easily
19:59:50 <FireFly> I should learn to actually *use* Haskell for something
20:00:08 <Bike> prove the four color conjecture with the type system
20:00:45 -!- quintopia has quit (Ping timeout: 252 seconds).
20:00:49 <Taneb> https://github.com/Taneb/webqueues/blob/master/Main.hs is the code I've written so far
20:01:27 <Taneb> getUUID is poorly named and documented
20:02:10 <Taneb> I guess I could make it ContT () ActionM UUID
20:02:41 <Taneb> But that'd make everything else awkward?
20:03:35 <Bike> define TanebUUIDThing = ContT () ActionM, problem solved
20:05:08 <Taneb> getAction doesn't get an action but rather is the action to be performed on a GET request
20:12:32 <Taneb> Anyway, I'm heading out
20:13:41 -!- b_jonas_ has changed nick to b_jonas.
20:17:33 -!- `^_^v has quit (Ping timeout: 240 seconds).
20:19:21 -!- password2 has quit (Ping timeout: 252 seconds).
20:19:58 -!- nycs has joined.
20:20:05 -!- nycs has changed nick to `^_^v.
20:34:00 <kmc> hmm Rust sort of has an overloadable assignment operator now: http://static.rust-lang.org/doc/master/std/clone/trait.Clone.html#method.clone_from
20:34:09 <kmc> bot not really
20:35:31 -!- MindlessDrone has quit (Quit: MindlessDrone).
20:38:02 -!- nucular has quit (Quit: Excess Food).
20:39:13 <BlueProtoman> Let's say I have a language L = {M is a Turing machine that halts on all words w in L(aa*)}, and I need to prove that it's undecidable. Can't I just define a Turing machine T that takes in another Turing machine H, and H's input h, and halts if H doesn't halt and stops if H does?
20:39:39 -!- AnotherTest has quit (Ping timeout: 276 seconds).
20:40:27 -!- ter2 has joined.
20:51:42 -!- Slereah has joined.
20:55:02 -!- Slereah_ has quit (Ping timeout: 258 seconds).
21:01:45 -!- Patashu has joined.
21:08:15 -!- Patashu_ has joined.
21:08:15 -!- Patashu has quit (Disconnected by services).
21:10:26 -!- boily has joined.
21:20:36 -!- Sprocklem has quit (Ping timeout: 276 seconds).
21:23:54 -!- Patashu_ has quit (Ping timeout: 240 seconds).
21:24:04 <boily> Taneb: Tanelle. are you asleep?
21:32:36 -!- BlueProtoman has quit (Read error: Connection reset by peer).
21:38:54 -!- BlueProtoman has joined.
21:40:16 <olsner> kmc: all that's left is to desugar = into clone_from calls?
21:40:35 -!- oerjan has quit (Quit: Narght).
21:44:41 -!- john_metcalf has joined.
21:46:14 -!- contrapumpkin has joined.
21:48:37 <kmc> yeah I think that will never happen, though, thankfully
21:48:58 <kmc> I mean we don't insert implicit clone() calls anyway
21:49:06 <kmc> only POD can be implicitly copied
21:50:01 -!- copumpkin has quit (Ping timeout: 252 seconds).
21:53:03 -!- Sgeo has joined.
21:53:22 <olsner> it's weird, my toy program in rust went fairly well and I thought rust was great, but now I'm trying to do something real (porting the microkernel I was working on) and rust is complaining a lot about my code and nothing works
21:53:49 -!- `^_^v has quit (Ping timeout: 250 seconds).
21:56:59 <olsner> but it's great that function-sections etc is working in rust now, I read an old thread that implied it would never ever be supported in rust for silly reasons
21:59:48 <kmc> oh that's nice
22:02:59 <olsner> otoh, with LTO I think it's theoretically possible to get better results in a single section
22:10:15 <olsner> oh, and I found a way to optimize away the stack checks - I just sed 's/ "split-stack"//' on the LLVM output
22:23:30 -!- KingOfKarlsruhe has quit (Quit: ChatZilla 0.9.90.1 [Firefox 29.0/20140421221237]).
22:27:31 <kmc> take refuge in clean living
22:27:50 <Melvar> Omfg I finally got firefox running right again.
22:28:53 <Melvar> It took me embarassingly long to remember that a cranky firefox should be started in safe mode first.
22:30:12 <Sgeo> Was looking at the latest Onion cartoon, and wondering why the turtle (tortoise?) was saying a hand. Turned out to be my cursor
22:31:51 <Sgeo> There was a speech bubble, and I thought there was a pointing hand in it
22:32:28 <olsner> which finger was the hand pointing?
22:37:24 <olsner> kmc: is kmc in #rust also you?
22:41:35 <FreeFull> I don't see why he wouldn't be
22:41:55 <HackEgo> catinecoin equaicoin chanocoin cabracoin licecoin pringcoin blocoin .coin parereacoin jumacoin zubanquixcoin sqirrisingcoin cripplithcoin bankingperlcoin rposiscoin liecoin wikacoin cuccoin ted!coin oraocumcoin
22:42:10 <kmc> those are some good coins
22:42:22 <FreeFull> Especially licecoin and liecoin
22:42:47 <olsner> bankingperlcoin might be the best
22:45:52 <FreeFull> Dark blue is hard to read on black
22:51:42 <tromp_> is cuccoin hinting at Cukoo Cycle for proof-of-work?
22:52:19 <HackEgo> afsignalcoin parzrhythmecoin repartungcoin vorschromgebotstrecoin bilderlandcoin erenblatcoin kursabsetzcoin pensivocoin bammenhanencoin lacederbandecoin panomeräthemincoin modecoin bayentgedrincoin theitercoin reitsdiencoin herungsordnungcoin mannzungcoin seitcoin allycoin ingesorgeco
22:52:57 <kmc> german words are too long, it got cut off
22:53:33 <Taneb> boily, I was at the pub
22:53:53 <olsner> hmm, I should go so I have time to sleep before I get up
23:01:05 <boily> Taneb: same thing.
23:03:42 <Taneb> I am pretty sure I was awake
23:07:47 -!- BlueProtoman has quit (Quit: Leaving).
23:09:30 <HackEgo> sankizowałybycoin fularomowiłbycoin uszegijskiewrcoin ukowacoin nieopadorszczcoin lokatnowymcoin obnychizującacoin reptyczamicoin uczarżanecoin przeczkocoin
23:09:45 <HackEgo> suomallansacoin huonomillännecoin säilemilleecoin hillannecoin yltymännecoin käsicoin putoimastacoin osuvaltammecoin heijailläcoin miekkaltanicoin
23:17:23 -!- MoALTz_ has joined.
23:19:01 <Taneb> boily, did you want to ask me something?
23:19:51 -!- MoALTz has quit (Ping timeout: 252 seconds).
23:24:58 <boily> Taneb: not "ask" anything. I just wanted to say that I slept during the day to an Idiosyncratic Schedule Sleep Expert.
23:28:56 -!- yorick has quit (Remote host closed the connection).
23:52:29 -!- edwardk has quit (Quit: Computer has gone to sleep.).
00:00:48 <HackEgo> A mapole is a thwackamacallit built from maple according to Canadian standards.
00:13:09 -!- Phantom_Hoover has quit (Ping timeout: 240 seconds).
00:26:51 -!- Phantom_Hoover has joined.
00:39:34 -!- vravn has quit (Ping timeout: 240 seconds).
00:40:19 -!- tromp has joined.
00:42:20 -!- vravn has joined.
00:43:54 <boily> `coins --french 12
00:43:55 <HackEgo> commantecoin vertielcoin limeubwecoin gaêtancrcoin surguercoin faciencoin reuccoin substrumcoin autopécoin deyroncoin physiavacoin djerontcoin
00:44:25 -!- boily has quit (Quit: CHICKENCOIN).
00:45:08 <kmc> `coins --canadian-english-insane 10
00:45:09 <HackEgo> refrankedcoin mastaicoin finlidcoin brutcoin capcoin bionarcheterimcoin leurinacoin mimmarkcoin sabillecoin phicablecoin
00:45:25 <Bike> i am all about bionarcheterimcoin
00:55:05 -!- Phantom_Hoover has quit (Ping timeout: 252 seconds).
01:14:03 <HackEgo> chacoin judicacoin lazycoin teqcoin tmlibergcoin mircoin tetneycoin camecoin filecoin frainfcoin etaplecoin wikmanlarcoin foblefoodcoin dvenghacoin hyanickethaxcoin blaccoin watchacoin v--coin monofcoin headcoin
01:27:56 <FreeFull> Why do people still use quicksort when radix sort exists?
01:28:33 <pikhq> Because quicksort has "quick" in the name.
01:28:50 <pikhq> I fail to see how radix sort is relevant though: quicksort is honestly a blatant misnomer.
01:29:06 <pikhq> It's literally got O(n^2) worst case performance.
01:32:39 -!- sebbu has quit (Ping timeout: 250 seconds).
01:32:54 -!- vravn has quit (Ping timeout: 240 seconds).
01:33:17 <FreeFull> pikhq: It's faster than merge sort on average though
01:33:41 <FreeFull> Radix sort is just O(nk) though
01:33:57 <FreeFull> I mean, merge sort is guaranteed O(n log n)
01:34:39 <FreeFull> Radix sort blows quicksort out of the water
01:35:20 -!- vravn has joined.
01:43:13 <monotone> If you have a sparse distribution of numbers over some large range it's going to be very inefficient.
01:43:56 <FreeFull> But would quicksort for such a distribution be better than merge sort or even insertion sort?
01:46:26 <pikhq> Radix sort is O(nk) but not constant in memory usage.
01:46:34 <pikhq> Shell sort is bitchin'.
01:47:14 <FreeFull> There is in-place radix sort, although it's not quite the same
01:48:13 <pikhq> I think the main thing with quicksort *in particular* is, in general what you want from a sorting algorithm is not absolute fastest time, but rather consistently not-slow time.
01:48:22 <pikhq> Especially when dealing with, say, a library function.
01:48:32 <pikhq> That you Want to be robust against potentially malicious input.
01:49:41 <pikhq> "Usually fast, but sometimes ungodly slow" is not a good thing.
01:53:03 <FreeFull> pikhq: If you have n 128-bit numbers, it's going to take radix sort the same amount of time to sort them no matter what they are
01:53:39 <pikhq> Yes. Radix sort is a good algorithm, and should probably be used when applicable.
01:53:55 <pikhq> My complaints were with quicksort, not radix sort.
01:54:41 <FreeFull> Shell sort seems to have the same asymptotic complexities as quicksort, so simplicity and constant factors would be the thing to consider
01:55:10 <pikhq> Shell sort has worst-case O(n log n).
01:55:23 <pikhq> That's what I meant.
01:55:31 <pikhq> Jeeze, I must be sleepy today.
01:55:41 <pikhq> Shell sort is not at all what I meant to recommend. :)
01:56:09 <pikhq> Your being confused at me is very understandable.
01:59:05 <FreeFull> Shell sort isn't stable, but in-place quicksort isn't either
02:04:36 <pikhq> Or... well. At least something that isn't worst-case suboptimal.
02:04:58 <pikhq> Which is definitely not shell. :)
02:52:30 <kmc> FreeFull: you can't always use radix at all
02:52:47 <kmc> you might only have pairwise comparison
02:53:32 -!- ^v has quit (Quit: http://i.imgur.com/Akc6r.gif).
02:53:55 -!- ^v has joined.
03:16:04 -!- contrapumpkin has changed nick to copumpkin.
03:16:15 <HackEgo> [wiki] [[Suicide]] http://esolangs.org/w/index.php?diff=39462&oldid=17129 * 76.100.81.188 * (+70) Tagged
03:19:07 <Bike> does anyone know who, if anyone, owns the rights to 65xx processors? like, MOS is gone, can anyone make them now?
03:23:04 <HackEgo> [wiki] [[Gerbil]] http://esolangs.org/w/index.php?diff=39463&oldid=23533 * 76.100.81.188 * (+51) Tagging
03:29:22 -!- sebbu has joined.
03:29:55 -!- sebbu has quit (Changing host).
03:29:55 -!- sebbu has joined.
03:31:35 <kmc> i should lie and tell people that the Finnish language has case for punctuation and that { is actually considered a lower case version of [
03:31:56 <kmc> or someone can try now to convince me that this is actually true, that might be a fun game
03:38:59 <lexande> wait i thought it was { is the upper case version of [
03:57:40 <kmc> `run echo '[{' | iconv -f iso646-fi
04:07:41 -!- Sprocklem has joined.
04:08:18 <Bike> http://arxiv.org/abs/cond-mat/0303625/ neat paper people might like. does CAs!
04:09:53 <lexande> `run echo ']}\|' | iconv -f iso646-fi
04:16:56 -!- tromp has quit (Remote host closed the connection).
04:17:28 -!- tromp has joined.
04:21:34 -!- tromp has quit (Ping timeout: 240 seconds).
04:45:50 -!- Sorella has quit (Quit: It is tiem!).
05:06:58 <kmc> Bike: you are wrapping a mobius strip of videotape around and around the math/porn part of my mind
05:07:22 <Bike> i... don't know what that means? or where i got video tape nowadays
05:08:17 <kmc> it means mind = blown
05:09:11 <kmc> i saw a VHS rewinder next to a trash can the other day
05:26:09 -!- Sgeo has quit (Read error: Connection reset by peer).
05:26:25 -!- Sgeo has joined.
05:33:23 <Jafet> Why do people still sort when you can just put it in a replicated nosql cloud
05:33:47 <Bike> stolen Flickr passwords
05:35:33 -!- password2 has joined.
05:37:11 <coppro> I assume that's what you use as a password for everything
05:43:19 -!- FreeFull has quit.
05:52:21 -!- oerjan has joined.
05:58:02 -!- ^v has quit (Quit: http://i.imgur.com/Akc6r.gif).
06:05:54 <oerjan> `learn Ingesorgeco is when a German is worrying that their money might get cut short.
06:15:58 -!- MoALTz_ has quit (Quit: bbl).
06:27:44 -!- ter2 has quit (Ping timeout: 255 seconds).
06:31:23 -!- drdanmaku has quit (Quit: Connection closed for inactivity).
06:34:18 <olsner> Bike: http://www.westerndesigncenter.com/wdc/ perhaps ... but there may be more companies holding licenses to make 65xx chips
06:34:41 <Bike> it's just that the licensor doesn't exist any more far as i can tell
06:34:56 <Bike> legalities are hard
06:35:28 <olsner> yeah, I'm not sure who/what they'd have a license from, presumably commodore (who bought MOS) exists in a shell somewhere
06:36:22 <Bike> patent trolls from beyond :o
06:36:42 <olsner> or, no, they split from commodore, and apparently it was later "liquidated", http://en.wikipedia.org/wiki/MOS_Technology#GMT_Microelectronics
07:23:58 -!- Tritonio has joined.
07:29:53 -!- slereah_ has joined.
07:42:28 -!- edwardk has joined.
08:08:13 -!- edwardk has quit (Quit: Computer has gone to sleep.).
08:16:27 -!- impomatic has quit (Ping timeout: 276 seconds).
08:24:31 -!- Patashu has joined.
08:33:58 -!- conehead has quit (Ping timeout: 240 seconds).
09:31:28 -!- Froox has quit (Read error: No route to host).
09:31:37 -!- Frooxius has joined.
09:32:05 -!- KingOfKarlsruhe has joined.
09:43:18 <slereah_> Is there a C type specific to probabilities?
09:43:31 <slereah_> Floating points are pretty bad at it
09:45:43 -!- lexande_ has joined.
09:50:41 -!- lexande has quit (*.net *.split).
09:50:46 -!- FireFly has quit (*.net *.split).
09:51:59 -!- TodPunk has quit (Ping timeout: 252 seconds).
09:58:00 -!- yorick has joined.
09:59:25 -!- FireFly has joined.
10:12:01 <Melvar> Is a long long int 128 bits anywhere?
10:18:14 * oerjan thinks they must have finally fixed the annoying tab bug in IE 11
10:31:59 <oerjan> and also, the address bar suddenly seems not to give the entirely wrong completion suggestions any more...
10:32:44 <Jafet> __int128 is 128 bits everywhere
11:06:47 -!- oerjan has quit (Quit: What about long long long long long long ints?).
11:07:53 <Jafet> How long must we long for long long long!
11:09:17 <Melvar> mroman_: Would it comply with the standard?
11:09:27 <mroman_> long long is guaranteed to be 64bits
11:10:19 <Melvar> mroman_: You mean, exactly 64 bits, not ≥64?
11:11:07 <Melvar> Okay, that’s what I would have expected. Thanks.
11:11:12 <Jafet> There is no required integer type required to have an exact bit size
11:11:31 <mroman_> The C standard only defines the manimum range of a long long
11:12:31 <Jafet> This is so that WG14 sponsors can make a 32-bit sandwich toaster and advertise support for ISO standard C
11:12:32 <mroman_> You should use int128_t if you wan't exactly 128bits
11:12:41 <mroman_> but I'm not sure how much support compilers have for intN_t
11:13:00 <mroman_> I don't get it why compilers use non-standard stuff like __int128
11:13:06 <mroman_> when they could just use int128_t
11:13:43 <Melvar> mroman_: I was just wondering; I don’t need a 128-bit type for anything.
11:14:20 <mroman_> I don't see a reason to use long long
11:14:27 <mroman_> I don't see a reason to use int for that matter
11:15:00 <mroman_> for(int i = 0; i < 10000; i++) { /* hurray, I'm crappy unportable code */ }
11:15:56 <mroman_> Melvar: My opinion on those regular C types is "They suck"
11:16:00 <Jafet> It's a feature to prevent idiots with obsolete computers from enjoying the software
11:16:22 <mroman_> There's no guarantee an int can hold 100k
11:17:06 <Melvar> I did once program a microcontroller with a 16-bit int, I think.
11:17:16 <Jafet> Well, the real problem is that int is no longer mapped to machine words by any amd64 compiler (and on most of them, not even long)
11:17:35 <Jafet> So you have people writing int left and right and the compiler has to sign-extend them all
11:17:38 <mroman_> but nobody said it can hold 32bit values
11:19:29 <Jafet> Pretty sure that's still mapped to int to appease the peasants
11:19:37 <mroman_> which, if you use on a 64bit machine probably gives you an int64_t?
11:19:59 <mroman_> which means that you better not rely on 32bit wrap-arounds .
11:20:07 <Jafet> No, I don't know any compiler that maps int to int64_t
11:20:20 <Jafet> I think posix requires int to have at least 32 bits, though
11:20:36 <mroman_> I don't know any compiler that maps int to int64_t
11:20:42 <mroman_> but a compiler is allowed to do so
11:20:58 <Jafet> In practice, it's not going to happen
11:21:33 <Jafet> It will break milljeeons of programs
11:21:35 <mroman_> I could imagine that int64_t is faster
11:21:48 <mroman_> Jafet: I don't care about breaking millions of crappy written programs .
11:22:04 <mroman_> If you rely on int to be 32bit you don't know C
11:22:07 <Jafet> Good thing you're not writing compilers, then
11:23:14 <Melvar> If one relies on 32-bit wraparounds, it needs int32_t and -fwrapv at least, I believe.
11:23:59 <mroman_> wrap-arounds are evil anyway
11:24:12 <mroman_> but what kind of evil stuff were people doing so that the code breaks if int is suddenly 64bit wide?
11:24:36 <mroman_> (relying on wrap-arounds would be one thing)
11:24:55 <Jafet> Not evil, just stupid
11:24:59 <idris-bot> Can't resolve type class MaxBound Int
11:25:33 <Melvar> Oh, right, it won’t actually be known …
11:25:54 <Jafet> `echo $'#include <inttypes.h>\n#include <stdio.h>\nmain(){ printf("%zu %zu %zu", sizeof(int_least32_t), sizeof(int32_t), sizeof(int_fast32_t)); }\n' > /tmp/a.c && gcc /tmp/a.c -o /tmp/a.out && /tmp/a.out
11:25:54 <HackEgo> $'#include <inttypes.h>\n#include <stdio.h>\nmain(){ printf("%zu %zu %zu", sizeof(int_least32_t), sizeof(int32_t), sizeof(int_fast32_t)); }\n' > /tmp/a.c && gcc /tmp/a.c -o /tmp/a.out && /tmp/a.out
11:26:06 <Jafet> `run echo $'#include <inttypes.h>\n#include <stdio.h>\nmain(){ printf("%zu %zu %zu", sizeof(int_least32_t), sizeof(int32_t), sizeof(int_fast32_t)); }\n' > /tmp/a.c && gcc /tmp/a.c -o /tmp/a.out && /tmp/a.out
11:26:23 <Jafet> Wow, gcc fucks the peasants
11:27:51 <mroman_> looks like int_fast32_t is 64bit
11:28:45 <mroman_> although I'm currently reading something about "you can fit more 32bit ints into the cache so it's faster"
11:28:57 <mroman_> You certainly can fit more 32bit ints into a cache line
11:30:40 <mroman_> If you do 32bit computations on 16 integers
11:30:45 <mroman_> they fit neatly into a cache line
11:30:52 <mroman_> wherease 16 64bit integers wouldn't!
11:33:54 <mroman_> My gcc is probably 32bit though
11:36:45 <Jafet> `run echo $'#!/bin/sh\necho "$@" > /tmp/a.c && gcc /tmp/a.c -o /tmp/a.out && /tmp/a.out' > bin/cc && chmod +x bin/cc
11:36:46 <mroman_> they blocked me on the 64bit machine
11:37:02 <mroman_> probably due to something important running on it :D
11:37:18 <Jafet> `cc #include <stdio.h>\nmain(){ return 1/0; }
11:37:18 <HackEgo> /tmp/a.c: In function ‘main’: \ /tmp/a.c:2:17: warning: division by zero [-Wdiv-by-zero] \ Floating point exception
11:38:30 <Jafet> `cc #include <stdio.h>\nmain(){ puts("\n\n\n"); }
11:38:30 <HackEgo> /tmp/a.c: In function ‘main’: \ /tmp/a.c:2:14: warning: missing terminating " character [enabled by default] \ /tmp/a.c:2:1: error: missing terminating " character \ /tmp/a.c:5:1: warning: missing terminating " character [enabled by default] \ /tmp/a.c:5:1: error: missing terminating " character \ /tmp/a.c:5:1: error: expected expression at
11:38:41 <Jafet> `cc #include <stdio.h>\nmain(){ puts("\\n\\n\\n"); }
11:39:00 <Jafet> `cc #include <stdio.h>\nmain(){ puts("\\n\\n\\n☃"); }
11:45:19 -!- Froox has joined.
11:47:18 -!- Sgeo has quit (Read error: Connection reset by peer).
11:49:38 -!- b_jonas_ has joined.
11:49:42 -!- Frooxius has quit (Read error: Connection reset by peer).
11:49:42 -!- b_jonas has quit (Ping timeout: 258 seconds).
11:52:17 -!- b_jonas_ has changed nick to b_jonas.
11:55:03 -!- ter2 has joined.
12:29:52 -!- S1 has joined.
12:31:02 <HackEgo> [wiki] [[Zero]] N http://esolangs.org/w/index.php?oldid=39464 * Tailcalled * (+1493) Created page with "Zero is a language invented by Tailcalled. It was specifically designed to be literally impossible to program in and execute in the general case. Zero has eight instructions,..."
12:34:35 -!- edwardk has joined.
12:40:37 <S1> literally what?
12:51:45 -!- Sorella has joined.
12:57:31 -!- S1 has quit (Quit: http://www.kiwiirc.com/ - A hand crafted IRC client).
13:17:38 -!- password2 has quit (Ping timeout: 240 seconds).
13:23:14 <HackEgo> [wiki] [[Zero]] M http://esolangs.org/w/index.php?diff=39465&oldid=39464 * FireFly * (+172) +categories
13:32:58 -!- nucular has joined.
13:32:58 -!- nucular has quit (Changing host).
13:32:58 -!- nucular has joined.
13:34:37 -!- edwardk has quit (Quit: Computer has gone to sleep.).
13:38:56 -!- aloril has quit (Ping timeout: 252 seconds).
13:43:22 -!- MindlessDrone has joined.
13:48:40 -!- Patashu has quit (Ping timeout: 265 seconds).
13:52:25 -!- ter2 has quit (Ping timeout: 252 seconds).
13:52:46 -!- aloril has joined.
13:53:37 -!- Sprocklem has quit (Ping timeout: 252 seconds).
13:58:03 -!- KingOfKarlsruhe has left.
13:59:13 -!- ter2 has joined.
14:06:48 -!- ter2 has quit (Ping timeout: 276 seconds).
14:07:02 -!- `^_^v has joined.
14:10:12 -!- ter2 has joined.
14:22:41 -!- Sprocklem has joined.
14:26:18 -!- ais523 has joined.
14:31:45 -!- callforjudgement has joined.
14:31:52 -!- ais523 has quit.
14:32:42 -!- callforjudgement has changed nick to ais523.
14:33:14 -!- vravn has quit (Ping timeout: 240 seconds).
14:34:45 -!- ais523_ has joined.
14:36:54 -!- vravn has joined.
14:40:38 <ais523> Firefox just upgraded; I had to open the About menu to make sure I hadn't opened Chrome by mistake
14:58:54 -!- `^_^v has quit (Ping timeout: 240 seconds).
15:04:16 -!- `^_^v has joined.
15:11:39 -!- Tritonio has quit (Ping timeout: 250 seconds).
15:29:42 -!- conehead has joined.
15:31:09 -!- atriq has joined.
15:31:31 -!- AnotherTest has joined.
15:34:57 -!- AnotherTest_ has joined.
15:36:30 -!- AnotherTest has quit (Ping timeout: 276 seconds).
15:36:31 -!- AnotherTest_ has changed nick to AnotherTest.
15:49:08 -!- FreeFull has joined.
15:50:50 -!- Tritonio has joined.
15:53:10 -!- TodPunk has joined.
15:54:27 -!- TodPunk has quit (Client Quit).
15:54:41 -!- TodPunk has joined.
15:57:18 -!- ter2 has quit (Ping timeout: 276 seconds).
16:04:53 -!- slereah_ has quit (Quit: Leaving).
16:11:27 -!- password2 has joined.
16:11:36 -!- Sprocklem has quit (Ping timeout: 276 seconds).
16:18:45 -!- lexande_ has changed nick to lexande.
16:19:08 -!- Sprocklem has joined.
16:19:56 -!- tertu has joined.
16:22:26 -!- sebbu2 has joined.
16:22:55 -!- tertu has quit (Client Quit).
16:23:00 -!- sebbu2 has quit (Changing host).
16:23:00 -!- sebbu2 has joined.
16:23:49 -!- sebbu has quit (Ping timeout: 245 seconds).
16:25:12 <Bike> kmc: http://pipeline.corante.com/archives/2014/04/21/molecular_printing_of_drug_molecules_say_what.php :catdrugs:
16:26:59 -!- ^v has joined.
16:27:37 -!- impomatic has quit (Read error: Connection reset by peer).
16:32:14 -!- drdanmaku has joined.
16:32:34 <Jafet> Peer review. Not even once.
16:34:10 -!- john_metcalf has quit (Read error: Connection reset by peer).
16:52:15 -!- ais523 has quit (Read error: Connection reset by peer).
16:52:25 -!- ais523 has joined.
16:52:43 -!- idris-bot has quit (Quit: Terminated).
17:01:35 -!- MoALTz has joined.
17:02:02 -!- atriq has quit (Quit: Page closed).
17:17:19 -!- Tritonio has quit (Ping timeout: 250 seconds).
17:20:37 -!- Tritonio has joined.
17:31:14 -!- Sprocklem has quit (Quit: Sacrificing a goat to the sun god.).
17:33:21 -!- Tritonio has quit (Ping timeout: 250 seconds).
17:35:27 <myname> i feel dirty using nested wheres in haskell
17:35:58 -!- Tritonio has joined.
17:36:41 <Jafet> Those dirty where nests
17:37:06 <kmc> i wrote some rust code with early return inside a match inside a macro inside a guard
17:41:10 <kmc> match () { _ if match self.lookahead_and_consume(6, |s| s.eq_ignore_ascii_case("public")) { None => return true, Some(r) => r } => go!(to AfterDoctypeKeyword Public), ... }
17:44:07 <ais523> also, I approve of that case-insensitive equality operation
17:44:56 <myname> why is ascii mentioned there?
17:45:04 <myname> does it respect other types of cases?
17:45:22 <kmc> no, it doesn't do Unicode case folding, which is very complicated and also not what's in the relevant spec
17:45:59 <kmc> ais523: it's another macro I defined, a DSL for writing HTML tokenizer actions in a concise way https://github.com/kmcallister/html5/blob/master/src/tokenizer/mod.rs#L475-L543
17:46:00 -!- Sprocklem has joined.
17:46:08 <ais523> there are a bunch of ways to do case folding
17:46:12 <ais523> ASCII case folding is at least well-defined
17:46:23 <kmc> well-defined, simple, fast, not locale-dependent
17:48:17 <kmc> the HTML parsing spec mostly doesn't interpret non-ASCII characters
17:48:31 <kmc> because it's not like past software has handled them consistently
17:51:36 <kmc> this is also handy because a parser operating on UTF-8 can do most operations on bytes without decoding them to codepoints
17:51:51 -!- john_metcalf has joined.
17:53:57 <kmc> which in turn makes it easier to use SIMD instructions
17:54:54 <ais523> wouldn't UTF-32 be faster for that, if you had to handle Unicode codepoints, but didn't care about grapheme clusters?
17:55:17 <ais523> although that would probably suffer from caching issues
17:55:38 <kmc> yeah, increasing memory traffic 4x will probably kill other gains
17:55:47 <kmc> and most content comes off the wire as UTF-8 so you would need to convert it first
17:56:05 <kmc> (and basically no content comes as UTF-32; I'm not sure it's even allowed)
17:56:21 <ais523> I want a UTF-graphemecluster
17:56:30 <ais523> even if it's hundreds of bytes per cluster
17:56:37 -!- john_metcalf has quit (Ping timeout: 252 seconds).
17:56:40 <ais523> actually, that's how ncursesw works internally
17:57:22 <kmc> i'm not sure that grapheme clusters are relevant to any part of the web stack
17:58:39 <kmc> high quality text shaping for proportional fonts can map any number of codepoints to any number of (translated, scaled, etc.) glyphs
17:59:28 <kmc> but the input to the shaping library might be a sequence of grapheme clusters? i've forgotten
18:02:06 <kmc> in servo I mean
18:05:06 <ais523_> oh, right, I forgot that Rust is made by a browser company
18:05:08 <ais523_> I was just thinking in general
18:06:56 <kmc> I am writing a HTML parser for Servo but I want it to be a generally useful library, which is tricky because browsers have some unusual requirements
18:10:16 -!- edwardk has joined.
18:10:32 <kmc> I think there are a lot of open questions about API design in Rust generally
18:10:44 <FreeFull> Is Servo Rust's only killer program so far?
18:11:02 <kmc> because of the need to accommodate library users with different memory management strategies, in a safe API
18:11:19 <FreeFull> It seems to be quite influential to Rust's design
18:12:01 <kmc> I think I care more about getting higher-kinded polymorphism after considering its use with lifetime variables
18:12:47 <kmc> FreeFull: well, what do you mean by killer program?
18:12:59 <ais523> FreeFull: it may be the motivating application
18:13:10 <kmc> Servo is probably the second largest program written in Rust, but it's not usable for anything real yet
18:13:10 <ais523> like, aimake is mostly used on NetHack, because that's what I needed it for
18:13:27 <kmc> (it's like 100k SLoC)
18:13:35 <kmc> rustc is like 300k
18:13:42 <ais523> ooh, self-hosting already?
18:13:43 <kmc> including the bundled libs etc
18:13:48 <kmc> ais523: yes, for some years now
18:14:01 <ais523> for Rust, I think that makes sense
18:14:01 <kmc> ais523: the runtime system is also self hosting, which is a lot more unusual
18:14:05 <ais523> there's some debate about whether languages should self-host
18:14:14 <ais523> but something with Rust's aims should probably be able to
18:14:21 <kmc> i mean, not every language is a good choice for writing a compiler
18:14:28 <kmc> so there isn't a general answer to the question of "should you self-host"
18:14:34 <ais523> here, we identify the languages that aren't
18:14:35 <kmc> but yeah, I think for Rust it's a defensible decision at least
18:14:41 <ais523> then write self-compilers in them anyway
18:15:13 <kmc> the compiler still makes heavy use internally of the deprecated refcounted @-boxes
18:15:21 <kmc> which have been removed in favor of a Rc<T> library type
18:15:34 <kmc> self-hosting is a big pain when your language is still evolving so rapidly
18:15:54 <ais523> is it possible to change from one to the other in an automated way?
18:15:59 <ais523> like, the syntax for ~-boxes is also changing
18:16:04 <ais523> that's been the big Rust news recently
18:16:12 <kmc> they've done some automated refactorings I know
18:16:15 <ais523> everyone seems to expect a huge outcry, yet it never emerges
18:16:20 <kmc> pcwalton wrote a big perl script
18:16:25 <kmc> ais523: i whined about it in #rust yesterday
18:16:46 <ais523> oh, I was expecting something parsetree-based, but I guess it's hard to preserve comments when doing that
18:16:47 <kmc> 15:36 <@kmc> for f**ks sake
18:16:47 <kmc> 15:36 <@kmc> at this rate in another year Rust will be the SK calculus
18:17:10 <nortti> is there a SK-calculus self-compiler?
18:17:25 <kmc> Rust has a syntactic concept of a "token tree", which is useful for macros and automated refactoring
18:17:37 <kmc> I don't know if other languages have this
18:17:56 <ais523> nortti: there are Unlambda self-compilers
18:18:05 <ais523> which is about as close as you'll get
18:18:13 <kmc> it's a tree of balanced parentheses (and brackets etc.) where the leaves are tokens
18:18:19 <ais523> those are basically SK + C + I/O
18:18:23 <kmc> nortti: yeah, I guess it is similar to manipulating code as S-expressions
18:18:28 <Bike> probably closer to an AST than s-expressions are?
18:19:00 <kmc> but Rust has a lot more expression grammar than Lisp; it's just that you can manipulate code before the stage at which that grammar is implemented
18:19:22 <kmc> but I'm fond of pointing out that Lisp also secretly has a lot of expression grammar
18:20:18 <kmc> FreeFull: Servo has been influential to Rust's design, certainly, but I think somewhat less than one might expect
18:20:23 <Bike> and not-secretly. the BNF for loop is a couple pages long
18:20:51 <nortti> loop really is a beast
18:21:15 -!- sebbu2 has changed nick to sebbu.
18:21:21 <Bike> and shivers's loop is the same way, so there go any "uh but loop isn't REALLY lisp" crapola
18:21:38 <kmc> there are only a few people who do lots of work on both Rust and Servo
18:24:36 <kmc> i've only landed a few patches to rust
18:24:43 <kmc> opened a lot of bugs though :P
18:25:29 -!- Sprocklem has quit (Ping timeout: 264 seconds).
18:25:39 <kmc> i basically consider compiler bugs part of the fun
18:25:44 <kmc> i've only hit a few really nasty ones, though
18:34:30 -!- cel_reloaded has joined.
18:35:39 -!- oerjan has joined.
18:45:06 -!- cel_reloaded has quit (Quit: cel_reloaded).
18:45:25 -!- cel_reloaded has joined.
18:49:32 <kmc> http://www.pcworld.com/article/2150775/amd-announces-skybridge-chips-to-bring-together-x86-and-arm.html
18:53:29 <olsner> hmm, how would that work?
18:54:34 <olsner> oh, it's not x86+arm in one cpu chip, but different pin-compatible x86 and arm cpus, I guess
18:55:30 <mroman_> I thought it's a hardware translator between those two
18:55:43 <mroman_> like a ARM chip that also supports x86
18:56:03 <olsner> you can get almost that with qemu, I think
18:56:07 <mroman_> that'd be the same as you said :)
18:56:07 <ais523> you could almost do that in microcode
18:56:14 <ais523> we need a customizable-microcode chip, really
18:56:22 <tromp_> my paper at http://homepages.cwi.nl/~tromp/cl/cl.html has an SK self-interpreter
18:56:35 <tromp_> but it's bigger than the lambda calculus self-interpreter
18:56:37 <Jafet> So they've finally given up on drag racing intel
18:57:46 <tromp_> which is under 26 bytes
18:58:24 <nortti> binary lambda calculus?
19:01:18 -!- MindlessDrone has quit (Quit: MindlessDrone).
19:02:56 -!- cel_reloaded has quit (Quit: cel_reloaded).
19:06:15 -!- john_metcalf has joined.
19:11:48 -!- zzo38 has joined.
19:14:13 -!- FreeFull_ has joined.
19:16:22 -!- FreeFull has quit (Ping timeout: 265 seconds).
19:28:36 <oerjan> FireFly: um how can Zero be both unusable for programming and turing-complete
19:29:33 <FireFly> I thought "unusable for programming" was supposed to be in terms of practicality
19:30:08 <FireFly> I'm not sure why I had that idea
19:31:27 <oerjan> although looking at the actual language, i think it's more likely that it's not tc..
19:32:00 <oerjan> by the unusual way of not having any computable reduction from a turing machine to it.
19:32:26 <oerjan> um or the other way, for that matter.
19:33:52 <oerjan> hm actually it _might_ be possible to reduce some universal bf program with input to it.
19:34:35 <oerjan> because the halting sequence will only start being undecidable from some point on, and that point may very well be pretty large
19:36:27 <ais523_> this is like saying "is BF with a source code limit of 200 bytes TC?"
19:36:47 <ais523_> it would be very hard to prove that the answer is no, but if the answer is yes, a proof would likely be trivial
19:39:30 <elliott> ais523_: also you run into L problems
19:40:42 <ais523> shachaf: thanks for that Haskell help you gave me a few days ago; how should I credit you in my PhD thesis?
19:40:50 <ais523> atm I credited your nick, but it looks a little unprofessional
19:41:02 <oerjan> Shachaf the Terrible, Lord of all Mankind hth
19:41:55 <fizzie> Sha Chaf is not shachaf's real name?!
19:42:16 <oerjan> well without the space
19:42:33 <oerjan> also he used to have his surname in the /whois but i see it's gone
19:45:23 <fizzie> I went to an IBM recruiting event today, and they made a snide joke at Google's expense.
19:45:31 <oerjan> hm it might actually possible to program in zero entirely, if undecidable points in the halting sequence are sparse enough.
19:46:19 <ais523> oerjan: can you at least force such points to never be an unmatched bracket?
19:46:28 <ais523> if not, the first one is going to mess up your bracket matching
19:46:41 <ais523> also, I have a feeling that Zero may be uncomputable
19:46:59 <oerjan> yeah that's the main problem, you need to have no 3 in a row.
19:47:43 <oerjan> actually 2 in a row is also a problem if they're the first two in a triple
19:48:31 <ais523> "fun" exercise: write a program in Zero that halts if and only if it doesn't halt
19:48:37 -!- newsham has joined.
19:48:56 <oerjan> ais523: not sure that's possible to achieve
19:49:07 <ais523> but if it is, it'd say something about the language
19:49:37 <oerjan> after all the programs tested for the halting sequence are logarithmically shorter than the program you are constructing.
19:50:06 <ais523> you could insert a bunch of NOPs, but even then it'd cause problems
19:50:16 <ais523> because you couldn't reliably make them NOPs
19:50:27 <ais523> like, it'd work if you had "immutable NOPs", Malbolge-style
19:50:37 <ais523> (also programming in Zero would be very easy if you did)
19:50:41 <oerjan> also i think the specification of Zero has some weak points. like the fact that ordinary lexicographic order isn't isomorphic to the natural numbers.
19:51:00 <oerjan> and also, what happens to malformed programs tested in the halting sequence
19:51:02 <fowl> isomorphic is so 90s
19:51:12 <fowl> now we say isographic
19:51:24 * oerjan categorically swats fowl -----###
19:51:28 <fowl> read in the same tone you would read "reaganomics"
19:52:08 <oerjan> also i'm pretty sure Zero is uncomputable if you make no attempt to avoid the undecidable points in the halting sequence.
19:53:02 <oerjan> and come to think about it, avoiding 3 undecidables in a row also seems impossible, even if you can assume malformed programs have an easy value.
19:53:27 <ais523> I imagine the undecidables take quite a while to show up
19:53:28 -!- Sprocklem has joined.
19:53:39 <shachaf> ais523: Hmm, I guess "Shachaf Ben-Kiki" would work.
19:53:45 <shachaf> ais523: Which Haskell help was this?
19:53:56 <oerjan> but i'm thinking of translating general bf programs to it
19:53:57 <ais523> the rank-2 polymorphism declaration
19:54:28 <ais523> I'm trying to give an example of "this program can type with this type in at least one widely used language, but the inference algorithm can't figure it out itself"
19:56:44 <ais523> perhaps I'll remove the argument altogether because it turned into a bit of a mess
19:57:13 <HackEgo> [wiki] [[Zero]] http://esolangs.org/w/index.php?diff=39466&oldid=39465 * Oerjan * (+18) I'm going to assume you meant this, as the original doesn't give a sequence order
19:57:42 <ais523> shachaf: huh, I thought that name was familiar; I looked at the monitor on my desk, and it has the YAML spec open
19:57:47 <ais523> and one of the authors is Oren Ben-Kiki
19:57:59 <ais523> (and another has a surname of "döt Net")
19:59:36 <ais523> thanks for the help, anyway
19:59:43 <oerjan> ais523: i am thinking that if you could only avoid undecidable brackets in zero (which alas i don't think you can), then all other problems could probably be solved with the ][...] comment trick.
19:59:56 <ais523> oerjan: yes, that would probably work
20:00:16 <ais523> then you could just pad out with 3^n +-+-+-+-
20:00:26 <ais523> and create a paradoxical program
20:00:39 <ais523> that's some level above uncomputable, I think
20:00:56 <ais523> not just "cannot be implemented without an oracle", but "an implementation directly causes a paradox"
20:01:13 <oerjan> um i wasn't thinking of paradoxes here
20:01:23 <oerjan> just general translation to zero
20:01:39 -!- nooodl has joined.
20:01:48 <ais523> well, if you can translate any BF program to zero in linear time
20:01:51 <ais523> you can produce a paradox
20:01:52 <oerjan> but you are right about the padding, that means you can find equivalent elements further out in the sequence
20:03:20 <ais523> now I'm imagining that the YAML spec is hundreds of years old, which is an awesome mental image
20:05:46 <fizzie> Is the proper answer "himc", I wonder.
20:05:56 <oerjan> ais523: hm i don't think you can make a paradoxical program in Zero, because the encoding is not self-referential in the right way - the halting sequence tests _unencoded_ programs.
20:06:19 <ais523> oerjan: it doesn't have to test itself for halting
20:06:23 <ais523> just a program that is equivalent to itself
20:06:57 <oerjan> well what i'm saying is Zero programs cannot actually do halting tests once they're up and running.
20:07:57 <oerjan> oh hum on rereading the spec it implies the ordering skips unmatched programs.
20:08:42 <ais523> oerjan: oh, I see; they can test most of themself
20:09:00 <ais523> but they can't test the unsure instruction that they're testing without first knowing what it'll be
20:09:22 <ais523> if we think as a program as a function from the haltingness of a particular other program P to a termination status
20:09:33 <ais523> then P cannot equal the entire /function/, just the application of that function to some argument
20:09:42 <ais523> and that argument has to be defined as a constant, it can't come from a halting oracle
20:10:07 <oerjan> my real argument is that as written, the halting sequence is mathematically well defined, and so therefore is the semantics of a zero program, and so there cannot be any paradox.
20:10:34 <ais523> I was trying to expose the hole in my argument
20:10:39 <ais523> rather than the hole in yours
20:10:40 <ais523> and I think I found it
20:11:52 <oerjan> fizzie: no the proper response is kmcello hth
20:17:43 <oerjan> hm i'm starting to wonder if you may have enough control of consecutive elements in the halting sequence to at least know whether they give the _same_ bit or not.
20:18:28 <oerjan> like, programs that don't end in brackets will come in groups of 6, all of which must do the same thing.
20:18:36 <oerjan> (afa halting is concerned)
20:19:04 <oerjan> and that is enough to avoid encoding brackets with them
20:23:08 <oerjan> so the trouble happens with programs ending with ]
20:24:40 <oerjan> hm and those can do wild things, like P+] P-] P>] P<] are consequtive in the order.
20:26:13 <oerjan> which is almost certainly enough to encode switching between two independent undecidable subprograms.
20:30:25 -!- Sprocklem_ has joined.
20:30:51 -!- Sprocklem has quit (Disconnected by services).
20:31:08 -!- Sprocklem_ has changed nick to Sprocklem.
20:51:36 -!- idris-bot has joined.
20:55:09 -!- AnotherTest has quit (Ping timeout: 240 seconds).
21:00:19 -!- Patashu has joined.
21:04:49 -!- password2 has quit (Ping timeout: 252 seconds).
21:06:58 -!- Patashu_ has joined.
21:06:58 -!- Patashu has quit (Disconnected by services).
21:11:00 -!- nucular has quit (Quit: Excess Food).
21:12:57 -!- Patashu has joined.
21:16:14 -!- Patashu_ has quit (Ping timeout: 265 seconds).
21:20:17 -!- Sprocklem has quit (Quit: Ascending to God form).
21:20:26 <kmc> shachaf: I like languages with strong safety guarantees, but I seem to spend a lot of my time learning about ways to break the rules :)
21:24:08 -!- Patashu has quit (Ping timeout: 255 seconds).
21:42:14 <john_metcalf> Have any computers other than PDP-11 got a single instruction which copies itself through the entire memory? The PDP-11 instruction is MOV -(PC),-(PC)
21:44:34 <ais523> john_metcalf: you should talk to impomatic about that, pity impomatic isn't online
21:44:51 <ais523> that's a major part of CoreWars strategy, the fact that Redcode has an instruction that does that
21:45:25 <elliott> `addquote <ais523> john_metcalf: you should talk to impomatic about that, pity impomatic isn't online
21:45:26 <HackEgo> 1193) <ais523> john_metcalf: you should talk to impomatic about that, pity impomatic isn't online
21:45:55 <ais523> elliott: I don't know, it's useful advice, just advice that can't be actd on
21:45:59 <ais523> if not for the reason I expected
21:46:17 <ais523> elliott: it's funnier with the context
21:46:29 <ais523> oh, is that why you reverted, to add the context?
21:47:18 <ais523> most processors don't have PC-relative addressing
21:47:28 <ais523> because compilers typically know where their output is in the program
21:48:02 <fizzie> X86-64 does, ARM does (IIRC).
21:48:14 <kmc> ais523: not with dynamic linking
21:48:15 <elliott> ais523: no, to let others add it if they wish
21:48:28 <john_metcalf> None of the processors I've used allow anything similar to be created.
21:48:54 <kmc> for dynamic linking it's desirable to emit position-independent code, and in that case PC-relative addressing is very useful
21:48:57 <ais523> you might manage it on a processor where the PC is memory-mapped /and/ indirect addressing is supported
21:49:18 <kmc> PIC has a pretty severe performance penalty on 32-bit x86 because of the need to reserve a register for an offset
21:50:41 <ais523> dynamic linking is relatively recent compared to the history of programmers, though, isn't it?
21:50:42 <fizzie> Does it count if you need to set registeres to particular values before the one instruction?
21:51:03 <ais523> fizzie: some sort of movsw instruction?
21:51:11 <kmc> dynamic linking isn't that recent, but there are different implementation strategies and they don't all require PIC
21:51:21 <kmc> http://www.iecc.com/linkers/ has lots on this
21:51:22 <ais523> that's basically *di++ = *si++, if you make di the next line and si the current line
21:51:29 <ais523> then it should keep going until di overflows
21:52:09 <fizzie> I don't see why it'd stop there.
21:52:36 <fizzie> Assuming all address space is mapped and rwx, anyway.
21:54:01 <fizzie> Though a rep stos with the maximum count sounds approximately the same.
21:54:30 <kmc> if a REP MOVSB instruction overwrites itself, the repetition stops after the next processor interrupt
21:54:49 <kmc> which is something emulators tend to implement incorrectly
21:54:50 <kmc> http://repzret.org/p/rep-prefix-and-detecting-valgrind/
21:55:01 <fizzie> But that wasn't a rep.
21:55:20 <ais523> kmc: it's not a rep, you're copying the movsb onto the next instruction
21:55:24 <kmc> yeah this is a tangent
21:55:24 <ais523> then executing the new copy
21:55:27 <kmc> just a bizarre fact
21:55:41 <ais523> also, detecting valgrind is easy
21:55:51 <kmc> because of client requests?
21:56:05 <kmc> there really should be a way to disable those, but I didn't find one
21:56:21 <ais523> I remember fixing JPC-RR to do pipeline flushing on self-modifying code
21:56:30 <ais523> it used to just run the old version of the code, and it has a very long pipeline
21:56:32 <kmc> I was wondering if e.g. Native Client code running in Valgrind could use client requests to escape the sandbox
21:56:35 <ais523> I needed to do that so that NetHack would run correctly
21:56:47 <ais523> kmc: there's a client request for "run this on the real CPU", so trivially
21:57:44 <kmc> now how hard is it to set up a NaCl toolchain so i can write a PoC
21:58:27 <kmc> but you can run a NaCl program in Valgrind, like any other program
21:58:36 <kmc> and in this case it makes it less secure, not more :)
21:58:46 <ais523> is it still using the prctl-based sandbox? or has it moved to a different sandbox?
21:59:02 <ais523> prctl's basically undefeatable because it limits the syscalls you can use and there's no way to undo it
21:59:28 <ais523> as in, you need to find a kernel bug to get around it no matter how many layers of emulation are used, so long as the emulator runs the prctl call itself
21:59:41 <kmc> no, NaCl is used for sandboxing within a process, aiui
21:59:54 <ais523> I was thinking of a different sandbox entirely
22:00:07 <kmc> I think NaCl in Chrome will run in a process sandbox too
22:00:10 <kmc> but that's separate
22:00:11 <ais523> NaCl's the "run a static analyser on the code to make sure it doesn't try to do anything nasty, then run it unmodified" system
22:00:22 <kmc> NaCl uses a conservative subset of x86 with well behaved static semantics
22:00:28 <john_metcalf> MOVSB imp doesn't work because of the prefetch queue. (Works in a debugger though).
22:00:28 <kmc> plus segmentation
22:00:54 <ais523> john_metcalf: huh, pipeline behaviour causing problems on real processors?
22:01:01 <kmc> I always wondered about memory ordering with self-modifying code
22:01:04 <ais523> what about in 8086 mode?
22:01:24 <kmc> since there's no way to put a read barrier before the other CPU's fetch
22:01:25 <ais523> I know that NetHack overwrites the argument of an int instruction, then runs that instruction immediately afterwards
22:01:42 <ais523> to run arbitrary interrupts
22:03:00 <john_metcalf> Can't be done on a Z80 without looping. (Demo here) https://www.youtube.com/watch?v=LPqDksPdNiE
22:03:06 <fizzie> How about a "movsd; jmp $+2" one? (Modulo instruction length issues. And not a single instruction.)
22:03:57 <olsner> the manuals do mention self-modifying code with multiple cpus, basically saying "don't do that"
22:03:58 <ais523> I think there might even be room for a NOP in there
22:04:37 <kmc> olsner: fuck tha police
22:05:12 -!- TodPunk has quit (Read error: Connection reset by peer).
22:05:25 -!- TodPunk has joined.
22:10:26 -!- oerjan has quit (Quit: leaving).
22:13:10 <olsner> hmm, actually I remembered that wrong, they instead describe some appropriate synchronization procedures for getting cross-modified code to run properly
22:14:19 -!- Sprocklem has joined.
22:14:24 <olsner> basically use a memory flag to indicate when your modification is complete, then do cpuid before you jump to any of the modifying code
22:15:22 <ais523> cpuid's a memory barrier?
22:15:29 <ais523> weird instruction to use
22:16:11 <olsner> it's not for memory, I think, but for serializing and emptying pipelines and the whatnots
22:16:32 <ais523> err, instruction cache barrier
22:16:50 <olsner> if it's not cross-cpu doing a jump is enough (but cpuid also works)
22:19:28 <kmc> CPUID is a memory barrier but there are better memory barrier instructions
22:19:44 <kmc> and yeah it's also a barrier to OOE
22:19:50 -!- Bicyclidine has joined.
22:19:57 <kmc> I don't know which other instructions are
22:20:39 <kmc> some hypervisors virtualize CPUID which makes it very slow for this purpose
22:20:47 <kmc> also, there totally are legitimate use cases for multi-threaded self modifying code
22:22:56 <zzo38> Self modifying codes can be very useful
22:23:56 <zzo38> CPUID isn't a very good idea
22:26:15 -!- Phantom_Hoover has joined.
22:30:37 -!- Tritonio has quit (Ping timeout: 250 seconds).
22:33:17 -!- ais523_ has quit (Quit: Page closed).
22:35:11 -!- ais523 has quit.
22:46:15 -!- Sgeo has joined.
22:47:04 -!- nooodl has quit (Quit: Ik ga weg).
22:50:47 -!- Bicyclidine has quit (Ping timeout: 255 seconds).
22:51:00 -!- Bicyclidine has joined.
23:22:08 -!- augur has quit (Quit: Leaving...).
23:22:39 -!- augur has joined.
23:22:56 -!- Bicyclidine has quit (Ping timeout: 255 seconds).
23:23:10 -!- Bicyclidine has joined.
23:23:28 -!- ^v has quit (Read error: Connection reset by peer).
23:23:56 -!- ^v has joined.
23:25:28 -!- edwardk has quit (Quit: Computer has gone to sleep.).
23:43:30 -!- ^v has quit (Quit: http://i.imgur.com/Akc6r.gif).
23:47:34 -!- Bicyclidine has quit (Ping timeout: 240 seconds).
23:47:39 -!- boily has joined.
23:51:05 -!- Bicyclidine has joined.
00:05:56 -!- Bicyclidine has quit (Ping timeout: 255 seconds).
00:06:28 -!- Bicyclidine has joined.
00:10:45 -!- Bicyclidine has quit (Ping timeout: 240 seconds).
00:12:29 -!- Phantom__Hoover has joined.
00:15:33 -!- Phantom_Hoover has quit (Ping timeout: 240 seconds).
00:15:56 -!- yorick has quit (Read error: Connection reset by peer).
00:20:56 -!- MoALTz_ has joined.
00:22:21 -!- MoALTz has quit (Ping timeout: 276 seconds).
00:35:55 -!- skarn has quit (Ping timeout: 240 seconds).
00:36:19 -!- skarn has joined.
00:39:13 -!- Bike has quit (Read error: Connection reset by peer).
00:39:39 -!- Bike has joined.
00:49:51 <Sgeo> https://www.kickstarter.com/projects/lofi/four-sided-fantasy-a-game-about-the-limits-of-the
00:50:24 -!- Phantom__Hoover has quit (Read error: Connection reset by peer).
00:54:58 -!- boily has quit (Quit: COMMUNICATING CHICKEN).
01:01:02 -!- conehead has quit (Ping timeout: 255 seconds).
01:09:17 -!- conehead has joined.
01:23:50 -!- sevenqueue has joined.
01:27:25 -!- sevenqueue has left ("WeeChat 1.0-dev").
01:29:02 -!- Sorella has quit (Remote host closed the connection).
01:31:09 -!- Sorella has joined.
01:31:22 -!- MoALTz__ has joined.
01:32:01 -!- MoALTz_ has quit (Read error: Connection reset by peer).
01:43:26 <zzo38> Hofstadter's book mentions BlooP, which has only loops limited by the number calculated ahead of time, and FlooP, which adds "MU-LOOPS", which the limit doesn't need to be known ahead of time. SQL has only the first kind, which is sometimes insufficient.
01:49:05 <kmc> can SQLite's WITH RECURSIVE do the latter?
01:49:38 <copumpkin> in postgres a recursive CTE can do arbitrary things, I think
01:49:51 <copumpkin> which I assume sqlite is implementing too
01:49:55 <zzo38> kmc: Yes, although only for read-data, not for calling triggers and so on.
01:50:26 <zzo38> (Also, the RECURSIVE keyword is optional and doesn't do anything; it is there for compatibility and to remind you if you need reminding.)
01:52:55 <zzo38> When inserting into a view with triggers attached (it is an error to insert into a view without triggers attached), the SELECT statement is first run completely before the trigger is fired even once, so if a recursive WITH clause in the SELECT statement giving the data to insert results in an infinite number of result rows, it will run out of memory before the trigger is fired.
01:54:22 <zzo38> I have written an extension to add new syntax such as CREATE FUNCTION, CREATE MACRO, CREATE NAMESPACE, CREATE COLLATION, but cannot quite figure out how to add a proper syntax for traps and "mu-loops" which are usable inside of trigger programs.
01:58:17 -!- zzo38 has quit (Remote host closed the connection).
02:00:05 -!- tromp has joined.
02:31:12 -!- tertu has joined.
02:45:18 <Sgeo> :( how much of the web runs on JSONP?
02:49:40 <Sgeo> I refuse. I'd rather use an invisible iframe if it comes down to it. Which it is.
02:52:07 <Bike> sgeo will die on this hill
03:16:19 -!- Sorella has quit (Quit: It is tiem!).
03:17:59 -!- tromp__ has joined.
03:18:53 -!- tromp has quit (Ping timeout: 264 seconds).
03:23:56 -!- tertu has quit (Ping timeout: 252 seconds).
03:31:15 -!- tertu has joined.
03:39:17 -!- edwardk has joined.
04:07:17 -!- ter2 has joined.
04:07:18 -!- tertu has quit (Disconnected by services).
04:10:13 -!- tertu3 has joined.
04:13:27 -!- ter2 has quit (Ping timeout: 255 seconds).
04:16:22 <HackEgo> [wiki] [[EsoAPI]] M http://esolangs.org/w/index.php?diff=39467&oldid=31127 * Sprocklem * (+13)
04:18:57 <HackEgo> [wiki] [[EsoAPI]] http://esolangs.org/w/index.php?diff=39468&oldid=39467 * Sprocklem * (-13) Undo revision 39467 by [[Special:Contributions/Sprocklem|Sprocklem]] ([[User talk:Sprocklem|talk]])
04:19:09 -!- Sprocklem has quit (Quit: Leaving).
04:19:27 -!- ^v has joined.
04:25:11 -!- ter2 has joined.
04:28:29 -!- tertu3 has quit (Ping timeout: 264 seconds).
04:30:17 -!- Sgeo_ has joined.
04:33:41 -!- ter2 has quit (Ping timeout: 255 seconds).
04:34:04 -!- Sgeo has quit (Ping timeout: 258 seconds).
04:42:59 -!- ter2 has joined.
04:43:22 -!- edwardk has quit (Quit: Computer has gone to sleep.).
04:45:25 -!- edwardk has joined.
05:06:29 -!- edwardk has quit (Quit: Computer has gone to sleep.).
05:10:08 -!- ter2 has quit (Ping timeout: 255 seconds).
05:11:39 -!- edwardk has joined.
05:20:29 -!- pikhq has quit (Ping timeout: 245 seconds).
05:23:27 -!- Sgeo_ has quit (Quit: No Ping reply in 180 seconds.).
05:23:40 -!- password2 has joined.
05:24:22 -!- Sgeo has joined.
05:36:48 -!- edwardk has quit (Quit: Computer has gone to sleep.).
05:39:31 -!- jhj1 has quit (Ping timeout: 240 seconds).
05:41:23 -!- drdanmaku has quit (Quit: Connection closed for inactivity).
05:42:09 -!- cel_reloaded has joined.
05:42:18 -!- cel_reloaded has quit (Client Quit).
05:42:50 -!- cel_reloaded has joined.
05:47:59 -!- ^v has quit (Quit: http://i.imgur.com/Akc6r.gif).
05:53:18 -!- jhj1 has joined.
06:15:30 -!- cel_reloaded has quit (Quit: cel_reloaded).
06:27:05 -!- MoALTz__ has quit (Quit: bbl).
06:27:07 -!- cel_reloaded has joined.
06:40:57 -!- oerjan has joined.
06:55:10 -!- cel_reloaded has quit (Quit: cel_reloaded).
07:03:55 -!- cel_reloaded has joined.
07:04:34 -!- cel_reloaded has quit (Client Quit).
07:11:57 <kmc> http://assbaka.tumblr.com/post/84284936715/a-leucistic-red-winged-blackbird
07:13:02 -!- cel_reloaded has joined.
07:22:26 -!- cel_reloaded has quit (Ping timeout: 255 seconds).
07:25:59 -!- slereah_ has joined.
07:28:27 <oerjan> someone really wants us to be artists https://en.wikipedia.org/w/index.php?title=Esoteric_programming_language&curid=53398&diff=607370289&oldid=605551525
07:29:29 <oerjan> well yes, but that section still makes me slightly embarassed.
07:29:41 <oerjan> i suppose it will pass.
07:30:26 <slereah_> That guy will discover some new hip thing to brag about
07:30:34 <slereah_> And he will forget all about esolangs
07:30:51 <oerjan> yeah but then he'll have to make a new nick!
07:30:58 <coppro> oerjan: re: theenemysgate.ca I like that idea
07:31:23 <oerjan> i don't remember what that was
07:31:50 <oerjan> Gregor: fix HackEgo's log access please ;_;
07:33:54 <oerjan> coppro: are you sure i'm the right person, i vaguely remember that domain name but it's not in my browser log afaict...
07:34:00 <elliott> oerjan: the cited pressey article is better than the entire section, of course
07:35:13 <olsner> coppro: I think that could have been ion
07:37:27 <oerjan> it might help if coppro quoted people properly twh hth
07:38:41 -!- FreeFull_ has quit.
07:47:08 -!- MindlessDrone has joined.
07:50:01 <coppro> <lambdabot> oerjan asked 1d 21h 54m 48s ago: <coppro> I should register theenemysgate.ca and point it to an IP address that doesn't have a server <-- what about a server that responds to pings, but _nothing_ else twh
07:50:24 <coppro> i should just ignore messages matching ^<.oerjan>.*h$
07:52:53 <oerjan> i blame the mind control rays for wiping my memory hth
07:53:29 <oerjan> wait does that mean coppro cannot see this twh
07:56:23 -!- pikhq has joined.
08:26:39 -!- Patashu has joined.
08:26:58 -!- Patashu_ has joined.
08:26:58 -!- Patashu has quit (Disconnected by services).
08:35:31 -!- MindlessDrone has quit (Ping timeout: 252 seconds).
08:43:34 -!- password2 has quit (Ping timeout: 240 seconds).
08:49:24 -!- MindlessDrone has joined.
08:49:31 -!- skarn has quit (Changing host).
08:49:31 -!- skarn has joined.
09:31:47 -!- mhi^ has joined.
10:07:32 <oerjan> > replicateM 2 [True,False]
10:07:33 <lambdabot> [[True,True],[True,False],[False,True],[False,False]]
10:24:04 -!- conehead has quit (Quit: Computer has gone to sleep).
10:26:58 <FireFly> Is true/false guaranteed to correspond to 1/0 in C?
10:30:58 <lambdabot> System.IO hFlush :: Handle -> IO ()
10:30:58 <lambdabot> GHC.IO.Handle hFlush :: Handle -> IO ()
10:30:58 <lambdabot> GHC.IO.Handle hFlushAll :: Handle -> IO ()
10:33:01 <FireFly> "Each of the operators yields 1 if the specified relation is true and 0 if it is false" okay
10:34:17 <mhi^> FireFly: Yes. ;)
10:34:36 -!- yorick has joined.
10:35:00 <FireFly> mhi^: huh, I didn't know you were in here
10:35:31 <mhi^> FireFly: Someone must have edited my auto-join list!
10:35:44 <mhi^> FireFly: Seriously, I joined ~2 weeks ago, I think.
10:36:39 * FireFly is convinced all channels he's in on freenode will eventually converge
10:37:17 <mhi^> FireFly's law of IRC.
10:37:36 <Taneb> FireFly, does that apply to channels you aren't in?
10:39:57 <Taneb> Although yes, I think the only channel I'm in that doesn't have people I'm not in other channels with is #dwarffortress
10:42:23 <Taneb> That is, you can draw a sort of graph of channels I'm in and there are other people in multiple channels I'm in
10:42:37 <Taneb> And that's the only disconnected one
10:46:04 <oerjan> but are there isolated clusters?
10:47:19 * oerjan tries to remember if that rail compiler guy has been on the channel.
10:49:05 <oerjan> imagine if we had, like, a way to search the channel logs...
10:49:47 -!- AnotherTest has joined.
10:50:59 <oerjan> AnotherTest: hm have you been away for a while?
10:51:24 <oerjan> my memory is not working any more and it's all Gregor's fault
10:53:05 <HackEgo> bin/anonlog \ bin/etymology \ bin/log \ bin/logurl \ bin/pastalog \ bin/pastelog \ bin/pastelogs \ bin/pastlog \ bin/randomanonlog \ bin/searchlog
10:53:44 <HackEgo> http://codu.org/projects/hackbot/fshg/index.cgi/file/tip/bin/etymology
10:56:56 <oerjan> FireFly: bin/ is not where the problem resides hth
10:57:06 <HackEgo> /hackenv/bin/log: 2: cd: can't cd to /var/irclogs/_esoteric \ grep: ????-??-??.txt: No such file or directory
11:00:03 <FireFly> I was just curious roughly how many log-related commands we have that broke because of it
11:30:41 -!- nucular has joined.
11:30:41 -!- nucular has quit (Changing host).
11:30:41 -!- nucular has joined.
11:31:00 -!- yorick has quit (Remote host closed the connection).
11:31:40 -!- KingOfKarlsruhe has joined.
11:38:41 -!- KingOfKarlsruhe has quit (Quit: Leaving.).
11:39:03 <HackEgo> whoami: cannot find name for user ID 5000
11:40:16 -!- KingOfKarlsruhe has joined.
11:45:52 -!- oerjan has quit (Quit: leaving).
11:46:21 -!- yorick has joined.
11:49:48 -!- Sgeo has quit (Read error: Connection reset by peer).
11:56:50 -!- cel_reloaded has joined.
11:57:08 -!- cel_reloaded has left.
12:00:29 -!- Froox has quit (Ping timeout: 245 seconds).
12:11:30 -!- Frooxius has joined.
12:40:27 <HackEgo> id: --context (-Z) works only on an SELinux-enabled kernel
12:49:12 -!- AnotherTest has quit (Ping timeout: 276 seconds).
12:49:47 -!- mhi^ has quit (Quit: Lost terminal).
13:13:02 -!- FreeFull has joined.
13:16:12 <ion> Vi Hart on Net neutrality http://youtu.be/NAxMyTwmu_M
14:00:44 <fizzie> The person in the next row spent most of the plenary playing 2048 on her phone.
14:01:44 <Jafet> Neutral to the talk
14:02:35 -!- Patashu_ has quit (Ping timeout: 252 seconds).
14:18:28 <int-e> fizzie: did they win?
14:38:13 <fizzie> I don't think so. I wasn't concentrating on it, though.
15:05:57 <Taneb> `unicode MULTIOCULAR O
15:05:58 <HackEgo> U+A66E CYRILLIC LETTER MULTIOCULAR O \ UTF-8: ea 99 ae UTF-16BE: a66e Decimal: ꙮ \ ꙮ \ Category: Lo (Letter, Other) \ Bidi: L (Left-to-Right)
15:09:36 <HackEgo> [wiki] [[Zero]] http://esolangs.org/w/index.php?diff=39469&oldid=39466 * Tailcalled * (-134) brainderp
15:10:02 -!- KingOfKarlsruhe has quit (Quit: Leaving.).
15:14:53 -!- Cineribus has joined.
15:15:08 -!- edwardk has joined.
15:15:17 -!- Cineribus has left.
15:33:38 -!- ter2 has joined.
15:49:54 -!- edwardk has quit (Ping timeout: 276 seconds).
15:52:00 -!- slereah_ has quit (Quit: Leaving).
16:09:07 -!- ^v has joined.
16:12:37 -!- nooodl has joined.
16:55:24 -!- MoALTz has joined.
17:00:49 -!- Phantom_Hoover has joined.
17:16:55 <HackEgo> [wiki] [[Talk:Zero]] N http://esolangs.org/w/index.php?oldid=39470 * GreyKnight * (+641) Created page with "== clarification needed == My questions: * what constitues "correct grammar" of a pseudoprogram? * does the Halting sequence represent only grammatically-correct pseudoprogram..."
17:53:21 -!- oerjan has joined.
18:11:58 <Slereah> Can you write a simple exponential function if you use non-floating points functions?
18:13:50 <Bike> of course you can write exp for other representations.
18:14:19 <HackEgo> [wiki] [[Talk:Zero]] http://esolangs.org/w/index.php?diff=39471&oldid=39470 * Oerjan * (+846) My guesses etc.
18:14:58 <Slereah> I am just wondering if there is one that doesn't require some long ass series representation
18:15:31 <oerjan> the series for exp is about as simple as they come.
18:15:46 <Slereah> True, but they don't use that one!
18:16:17 <Slereah> It converges way too slowly and only around a particular point
18:16:41 -!- ^v has quit (Read error: Connection reset by peer).
18:16:49 <oerjan> well it's faster the closer you are to that point.
18:17:08 <Slereah> The implementations I've seen usually use the Remez algorithm
18:17:09 <Bike> no, slereah's right, the taylor series really isn't adequate. actual implementations use other polynomials
18:17:29 <Bike> honestly, polynomials are pretty simple, though
18:17:40 -!- ^v has joined.
18:17:44 <Slereah> I am just wondering if you can
18:18:14 <Slereah> Unfortunately it is not Ork arithmetics
18:18:48 <Bike> you could use the iterated log representation and define exp as adding one to the exp tower
18:19:07 * oerjan hasn't actually played WH40K but he's visited the wiki
18:19:31 <Bike> (http://en.wikipedia.org/wiki/Symmetric_level-index_arithmetic it's actually used! almost sorta)
18:20:24 <Bike> more practically there's http://en.wikipedia.org/wiki/Gal%27s_accurate_tables and a bunch of other shit i imagine
18:20:48 <Bike> http://en.wikipedia.org/wiki/Table-maker%27s_dilemma#The_table-maker.27s_dilemma on the other hand
18:25:55 <Slereah> I also wonder if having a fraction type might be useful for precision
18:26:13 <Slereah> Though I suppose the risk is having 1000/2000 for 1/2
18:26:44 <Slereah> But you could reduce to common denominators if it overflows I guess
18:28:15 <nortti> scheme actually has fraction type, iirc
18:28:48 <oerjan> i think if you try to use a fraction type with series you'll overflow even the reduced term pretty fast.
18:29:42 -!- MoALTz_ has joined.
18:29:52 <Slereah> Do any languages use some totally symbolic representations for math?
18:29:57 <Slereah> Outside of Mathematica, I guess
18:30:01 <nortti> what if the fraction type is stored as 2xbigint
18:30:10 <Bike> most lisps have a rational type, yes
18:30:13 <Bike> and it's basically 2 bigints
18:30:22 <oerjan> nortti: then you'll eventually run out of memory.
18:30:24 <Slereah> At least for the duration of the computation
18:30:37 <Slereah> And then apply arithmetic rules to it
18:30:39 <Bike> and it reduces fractions so there's no risk s mentioned
18:30:49 <Bike> Slereah: yeah, sure.
18:30:57 -!- MindlessDrone has quit (Quit: MindlessDrone).
18:31:01 <Bike> here's one http://www.haible.de/bruno/MichaelStoll/reals.html
18:31:04 <oerjan> note that if you add n fractions with relatively prime denominators, the new denominator is the product of all of them...
18:31:38 <Bike> well, i suppose haskell CReal or whatever does that too
18:31:45 <Slereah> oerjan : but is that different from fixed point reals
18:31:55 -!- MoALTz has quit (Read error: Connection reset by peer).
18:32:19 <oerjan> Slereah: well fixed point reals will lose precision instead...
18:32:20 <Bike> also, for totally different ways to compute exp, you could simulate the ODE for a while, that would be fun and implausible
18:32:45 <oerjan> although not as much for addition i guess
18:32:52 <Bike> and for different representation you could use http://en.wikipedia.org/wiki/Euler%27s_continued_fraction_formula#The_exponential_function ~
18:33:29 <Bike> so many ridiculous possibilities.
18:33:34 -!- conehead has joined.
18:34:02 <Slereah> Markov did a neat little paper on ways to represent computable real numbers
18:34:33 <Bike> markov the younger, or what
18:34:34 <Slereah> He did it as three µ-recursive functions, f(x) - g(x) / h(x)
18:35:07 <Bike> oh right markov the younger worked in computability, i totally forgot
18:36:06 <Bike> oh, and schonhage, i.e. /that/ schonhage, does stuff with complexity of analytics http://www.iai.uni-bonn.de/~schoe/topics.html
18:36:30 <Bike> for a usual positional representation, of course
18:37:12 <Slereah> I like how matrix multiplication has some very "fast" algorithms
18:37:28 <Slereah> But they are so ridiculously overcharged with calculations that they are basically never useful
18:38:08 <Bike> well, schonhage multiplication (of scalars, not matrices) /is/ actually practical for some numbers
18:38:33 <Bike> for when you have, like, numbers that are 3 KB long, but that's not too bad :V
18:38:57 <Slereah> How often do you have numbers 3 kB long
18:39:02 <HackEgo> [wiki] [[Talk:Zero]] http://esolangs.org/w/index.php?diff=39472&oldid=39471 * Tailcalled * (+556) /* clarification needed */
18:39:19 <Bike> me? never. but it's in GMP!!
18:39:36 <lambdabot> 1000000000000000000000000000000000000000000000000000000000000000000000000000...
18:39:40 <Bike> wow why did i think k was capitalized...
18:39:55 <Bike> "Applications of the Schönhage–Strassen algorithm include mathematical empiricism, such as the Great Internet Mersenne Prime Search and computing approximations of π, as well as practical applications such as Kronecker substitution, in which multiplication of polynomials with integer coefficients can be efficiently reduced to large integer multiplication"
18:40:31 <Bike> mathematical empiricism is so great. the polynomials for bifurcation constants own
18:40:31 <Slereah> At least the fast matrix multiplication is useful if the matrix is a few thousand entries wide
18:40:54 <Bike> yeah, i work with big matrices at work. linear algebra's too useful.
18:47:38 -!- realzies has quit (Ping timeout: 240 seconds).
18:57:50 -!- password2 has joined.
19:09:52 -!- augur has quit (Remote host closed the connection).
19:10:18 -!- augur has joined.
19:12:59 -!- Jafet has quit (Ping timeout: 245 seconds).
19:13:09 -!- Jafet has joined.
19:14:41 -!- augur has quit (Ping timeout: 264 seconds).
19:16:26 -!- ^v has quit (Quit: http://i.imgur.com/Akc6r.gif).
19:16:49 -!- ^v has joined.
19:20:11 -!- conehead has quit (Quit: Computer has gone to sleep).
19:21:56 -!- conehead has joined.
19:36:13 <ion> http://whitneymusicbox.org/index.php?var=v0
19:38:22 -!- drdanmaku has joined.
19:46:33 <FreeFull> Slereah: The situation where you can end up with faster matrix exponentiation than multiplication
20:04:22 <olsner> eat the cookie, Taneb, eat it
20:05:09 <int-e> or just the usual harmless but annoying tracking device?
20:13:22 <int-e> but that doesn't really answer the question
20:14:11 * int-e mines himself some paranoiacoins.
20:14:46 <HackEgo> 0x3coin djtcoin bagdalcoin bubnccoin wiecoin hevecoin brzelcoin ihaxcoin mesheencoin minicoin >coin cheminicoin prolamcoin carumcoin zetarcoin nehuntumcoin nuishcoin siminingcoin msgcoin brocoin
20:15:08 <olsner> zetarcoin is almost metarcoin
20:23:15 <fizzie> There seemed to be no traps at that Google recruiting event I talked about previously.
20:23:35 <fizzie> There seemed to be no recruiting to speak of going on either, on the other hand.
20:25:49 <oerjan> fizzie: are you sure you're not still there, inside a virtual reality room
20:26:23 <fizzie> I guess they're concentrating that more on their stand at the conference, but it makes me wonder if the event had much of a purpose. Though I guess purely by accident there must've been a couple recruiting-related Googler/non-Googler interactions.
20:26:40 <fizzie> I'm not sure of that, but at least the view was nice.
20:26:55 <olsner> overt recruitment might trigger defensive responses
20:27:30 <fizzie> Ah, so they're just being sneaky and underhanded.
20:28:02 <fizzie> The stuffed droids looked sympathetic, I give them that.
20:28:37 <int-e> fizzie: no parachute required?
20:29:00 <int-e> as I recall you were making plans for an emergency exit
20:29:09 <fizzie> No, I just took the elevator down. Assuming I ever left. (Cf. oerjan)
20:29:12 <int-e> or people made them for you, my memory is hazy on that point :)
20:29:50 <fizzie> I did speak to two Google people, but of quite inconsequential topics.
20:30:42 <olsner> FireFly: you'll have to wait for metasepia and/or boily
20:32:40 <fizzie> Sorry, either there are no data available for your request or you did not enter any valid ICAO airport abbreviations
20:33:28 <fizzie> COIN is the name of the "centre of excellence" (a funding-related construct) I worked for, or possibly still do.
20:33:57 <fizzie> It's an acronym (or at least approximately), but I forget what it stands for.
20:34:04 <fizzie> The word "inverse" was in there somewhere.
20:34:19 <olsner> centre of inverse non-excellence?
20:34:53 <fizzie> "The Finnish Centre of Excellence in Computational Inference Research (COIN) --"
20:35:04 <fizzie> COmputational INference, I guess.
20:35:23 <fizzie> Mputation and co-mputation.
20:35:32 <int-e> Hmm, Interferences Research
20:36:02 <fizzie> And I see it didn't even have "inverse" in the name.
20:36:46 -!- scoofy has joined.
20:38:31 <fizzie> Ohhh. The "Centre of Excellence in Inverse Problems" is a separate CoE, and it doesn't have an acronym. V. confusing.
20:39:28 <int-e> Cabal Of Interfering Numismatists
20:39:28 <fizzie> INPR probably sounded too silly.
20:39:54 <oerjan> they'd think it was a myers-briggs classification.
20:40:22 <fizzie> Is it a valid one? I always forget the letters.
20:40:48 <oerjan> no, there is no R and the P goes last.
20:40:59 <fizzie> One of them should be T/F, I guess.
20:42:02 -!- Sprocklem has joined.
20:43:51 <fizzie> Introvert-intuitive-programmed-random, perhaps.
20:44:55 <coppro> weird: when someone mentions a number of big names in your field and they are Mystic Amazing Mathematician #1, Mystic Amazing Mathematician #2, and the guy I took a course from last year
20:56:40 <oerjan> coppro: has your guy ever been seen together with Mystic Amazing Mathematician #3 ?
20:56:50 -!- nycs has joined.
20:58:02 <coppro> oerjan: I'm pretty sure it's his secret identity
20:59:18 -!- `^_^v has quit (Ping timeout: 276 seconds).
21:03:58 -!- realzies has joined.
21:03:59 -!- realzies has quit (Changing host).
21:03:59 -!- realzies has joined.
21:05:45 -!- Patashu has joined.
21:07:04 -!- realz has joined.
21:07:07 -!- `^_^v has joined.
21:08:39 -!- nycs has quit (Ping timeout: 252 seconds).
21:14:03 <fizzie> Incidentally, can any of you folks (no need for more than one or two answers) DNS-resolve zem.fi? It works from my university shell account, but not from this hotel, nor via Google's 8.8.8.8, yet doing it with dig manually (@a.fi zem.fi ns and so on) seems just fine.
21:14:27 <fizzie> Perhaps I did something wrong w.r.t. DNSSEC key expiration.
21:14:31 <Bike> i can even see your ltree.
21:14:41 <elliott> 164.138.29.87 via my router
21:15:10 <fizzie> I think I read from somewhere that 8.8.8.8 does DNSSEC these days.
21:15:37 -!- password2 has quit (Ping timeout: 252 seconds).
21:17:15 <fizzie> Oh yes, those RRSIGs have expiration times today. I think I tried to tell them not to do that.
21:17:39 -!- realz has quit (Quit: realz).
21:21:58 -!- Sprocklem has quit (Ping timeout: 252 seconds).
21:26:38 -!- john_metcalf has quit (Ping timeout: 255 seconds).
21:32:47 -!- Jafet has quit (Changing host).
21:32:47 -!- Jafet has joined.
21:33:14 -!- Jafet has left.
21:41:04 -!- nucular has quit (Quit: Excess Food).
21:43:14 -!- vravn has quit (Ping timeout: 240 seconds).
21:46:03 -!- vravn has joined.
21:50:56 -!- edwardk has joined.
21:54:20 -!- mhi^ has joined.
21:54:54 -!- Patashu_ has joined.
21:54:54 -!- Patashu has quit (Disconnected by services).
22:03:27 -!- ^v has quit (Quit: http://i.imgur.com/Akc6r.gif).
22:03:31 -!- augur has joined.
22:03:49 -!- ^v has joined.
22:10:33 -!- Sprocklem has joined.
22:10:46 -!- ^v has quit (Read error: Connection reset by peer).
22:11:05 -!- oerjan has quit (Quit: leaving).
22:11:12 -!- ^v has joined.
22:11:50 -!- Bicyclidine has joined.
22:13:28 -!- nooodl_ has joined.
22:16:29 -!- nooodl has quit (Ping timeout: 264 seconds).
22:17:50 -!- Bicyclidine has quit (Remote host closed the connection).
22:18:05 -!- Bicyclidine has joined.
22:19:36 -!- edwardk has quit (Quit: Leaving...).
22:23:51 -!- Sorella has joined.
22:27:06 -!- boily has joined.
22:27:31 -!- Sgeo has joined.
22:36:38 -!- augur has quit (Remote host closed the connection).
22:51:34 -!- vravn has quit (Ping timeout: 240 seconds).
22:53:03 -!- vravn has joined.
22:55:05 -!- yorick has quit (Remote host closed the connection).
23:01:46 -!- mhi^ has quit (Quit: Lost terminal).
23:17:54 -!- vravn has quit (Ping timeout: 240 seconds).
23:20:33 -!- vravn has joined.
23:32:46 -!- Jafet has joined.
23:46:25 -!- nooodl_ has quit (Ping timeout: 252 seconds).
23:53:53 -!- ^v has quit (Read error: Connection reset by peer).
23:54:21 -!- ^v has joined.
00:16:21 -!- Bicyclidine has quit (Ping timeout: 240 seconds).
00:17:38 * boily chokes on his glass of cranberry juice
00:18:14 <boily> please. please someone tell me this doesn't remind them of touhou music → http://youtu.be/VZyHOjeRrmU#t=71
00:20:45 -!- Phantom_Hoover has quit (Ping timeout: 240 seconds).
00:28:45 -!- Bike_ has joined.
00:29:08 -!- Bike has quit (Ping timeout: 240 seconds).
00:35:22 -!- Phantom_Hoover has joined.
00:35:26 -!- Phantom_Hoover has quit (Remote host closed the connection).
00:35:59 -!- MoALTz__ has joined.
00:38:51 -!- MoALTz_ has quit (Ping timeout: 252 seconds).
00:52:34 -!- vravn has quit (Ping timeout: 240 seconds).
00:52:43 -!- trout has quit (Ping timeout: 250 seconds).
00:54:03 -!- vravn has joined.
01:07:23 -!- variable has joined.
01:26:26 -!- boily has quit (Quit: MUCILAGIC CHICKEN).
01:37:34 -!- vravn has quit (Ping timeout: 240 seconds).
01:41:04 -!- vravn has joined.
01:45:19 <HackEgo> unterwacoin cupingintcoin scritcoin divecoin dnamcoin dogcoin geolcoin rwwcoin balcoin mbweighedcoin jancoin bytercoin vendercoin metalcoin delcoin var'scoin discoin spliccoin budecoin jesumcoin
01:49:30 -!- Jafet has quit (Quit: Quit).
01:49:43 -!- Jafet has joined.
01:49:49 -!- Jafet has quit (Changing host).
01:49:50 -!- Jafet has joined.
01:49:58 -!- Jafet has left.
02:09:50 -!- Bike_ has changed nick to Bike.
02:11:37 -!- realzies has quit (Ping timeout: 252 seconds).
02:16:55 -!- augur has joined.
02:18:26 -!- augur_ has joined.
02:18:39 -!- augur has quit (Read error: Connection reset by peer).
02:21:28 -!- realzies has joined.
02:21:28 -!- realzies has quit (Changing host).
02:21:28 -!- realzies has joined.
02:47:20 <Taneb> Why the hell am I awake
03:22:18 <HackEgo> [wiki] [[Rasen]] http://esolangs.org/w/index.php?diff=39473&oldid=38384 * Wolgr * (-9)
03:22:37 <HackEgo> [wiki] [[Rasen]] M http://esolangs.org/w/index.php?diff=39474&oldid=39473 * Wolgr * (-57)
03:25:37 -!- Sorella has quit (Quit: It is tiem!).
03:26:25 -!- adu has joined.
03:57:12 -!- idris-bot has quit (Quit: Terminated).
03:59:11 -!- password2 has joined.
04:18:34 <HackEgo> /home/hackbot/hackbot.hg/multibot_cmds/lib/limits: line 5: exec: colors: not found
04:19:50 <HackEgo> /home/hackbot/hackbot.hg/multibot_cmds/lib/limits: line 5: exec: taste: not found
04:58:31 -!- variable has changed nick to constant.
05:18:09 -!- ter2 has quit (Ping timeout: 252 seconds).
05:20:45 -!- shikhin has joined.
05:32:45 -!- ter2 has joined.
05:33:35 -!- adu has quit (Quit: adu).
05:42:59 -!- password2 has quit (Ping timeout: 245 seconds).
05:46:41 -!- FreeFull has quit.
05:50:29 -!- Jafet has joined.
06:18:53 -!- MoALTz__ has quit (Quit: bbl).
06:29:17 -!- ^v has quit (Quit: http://i.imgur.com/Akc6r.gif).
06:52:42 -!- ter2 has quit (Ping timeout: 265 seconds).
07:30:38 -!- shikhout has joined.
07:33:41 -!- shikhin has quit (Ping timeout: 255 seconds).
07:41:23 -!- drdanmaku has quit (Quit: Connection closed for inactivity).
08:07:49 -!- Slereah_ has joined.
08:09:26 -!- Slereah has quit (Ping timeout: 255 seconds).
08:12:50 -!- oerjan has joined.
08:13:13 -!- john_metcalf has joined.
08:16:25 -!- idris-bot has joined.
08:18:42 -!- lexande has left.
08:28:51 <Taneb> I've been up since 3 and I only read for two hours?
08:33:34 <oerjan> that's time dilation for you
08:35:38 -!- Patashu_ has quit (Ping timeout: 240 seconds).
08:37:17 -!- augur has joined.
08:37:44 -!- augur_ has quit (Read error: Connection reset by peer).
08:39:52 -!- KingOfKarlsruhe has joined.
08:51:37 -!- conehead has quit (Read error: Connection reset by peer).
09:28:11 <FireFly> @tell boily not particularily much, no
09:40:45 -!- password2 has joined.
10:12:29 <HackEgo> [wiki] [[Zero]] http://esolangs.org/w/index.php?diff=39475&oldid=39469 * Tailcalled * (+43)
10:21:49 -!- yorick has joined.
10:51:20 -!- Sprocklem_ has joined.
10:54:38 -!- pdxleif_ has joined.
10:55:32 -!- Sprocklem has quit (Ping timeout: 252 seconds).
10:55:34 -!- pdxleif has quit (Ping timeout: 252 seconds).
10:55:36 -!- pdxleif_ has changed nick to pdxleif.
11:00:14 -!- Slereah_ has quit (Ping timeout: 255 seconds).
11:01:24 -!- Slereah_ has joined.
11:04:26 -!- b_jonas_ has joined.
11:14:35 -!- Frooxius has quit (Quit: *bubbles away*).
11:23:05 -!- impomatic has quit (*.net *.split).
11:23:06 -!- b_jonas has quit (*.net *.split).
11:24:08 -!- Frooxius has joined.
11:40:42 -!- nucular has joined.
11:40:43 -!- nucular has quit (Changing host).
11:40:43 -!- nucular has joined.
11:47:58 -!- mhi^ has joined.
11:51:13 -!- KingOfKarlsruhe has quit (Quit: Leaving.).
11:53:02 -!- Sgeo has quit (Read error: Connection reset by peer).
11:54:06 -!- Slereah_ has changed nick to Slereah.
11:54:11 -!- KingOfKarlsruhe has joined.
12:04:09 -!- ggherdov_ has quit (*.net *.split).
12:11:24 -!- oerjan has quit (Quit: leaving).
12:14:35 -!- nucular has quit (Ping timeout: 252 seconds).
12:18:35 -!- ggherdov_ has joined.
12:19:08 -!- ggherdov_ has quit (Max SendQ exceeded).
12:19:52 -!- nucular has joined.
12:19:53 -!- nucular has quit (Changing host).
12:19:53 -!- nucular has joined.
12:22:54 -!- password2 has quit (Ping timeout: 240 seconds).
12:31:43 -!- ggherdov_ has joined.
12:55:39 -!- password2 has joined.
13:06:50 -!- shikhout has quit (Ping timeout: 252 seconds).
13:10:41 -!- tromp__ has quit (Remote host closed the connection).
13:11:13 -!- tromp has joined.
13:14:41 -!- ter2 has joined.
13:15:35 -!- tromp has quit (Ping timeout: 258 seconds).
13:20:01 <HackEgo> [wiki] [[Talk:Malbolge]] http://esolangs.org/w/index.php?diff=39476&oldid=35122 * 128.70.201.185 * (+1415) /* Possible error in translation to Normalized Malbolge */ new section
13:47:32 -!- Sprocklem_ has quit (Ping timeout: 252 seconds).
13:55:33 -!- KingOfKarlsruhe has quit (Quit: Leaving.).
13:58:15 -!- KingOfKarlsruhe has joined.
14:18:10 -!- Sorella has joined.
14:23:49 -!- Sprocklem has joined.
14:37:34 -!- KingOfKarlsruhe has quit (Quit: Leaving.).
14:48:44 -!- Sprocklem has quit (Ping timeout: 240 seconds).
14:49:23 -!- Sprocklem has joined.
14:50:37 -!- drdanmaku has joined.
14:55:31 <mroman_> when does Java get a more powerful typesystem?
15:03:47 -!- Sprocklem has quit (Ping timeout: 250 seconds).
15:03:53 -!- jix has quit (Quit: Lost terminal).
15:04:48 -!- Sprocklem has joined.
15:07:13 <Slereah> Why would Java do anything
15:10:11 -!- nooodl has joined.
15:10:19 <FireFly> Their fabled lambdas still haven't landed in a stable version
15:10:43 -!- Phantom_Hoover has joined.
15:11:10 <Taneb> FireFly, whoa, lambdas in a stable version of a language? Sounds scary
15:15:41 <Slereah> Whaaat, C has a native complex type?
15:15:46 <Slereah> At least in C99 apparently
15:20:05 -!- augur has quit (Ping timeout: 264 seconds).
15:30:16 -!- augur has joined.
15:36:02 -!- jix has joined.
15:41:14 -!- Phantom_Hoover has quit (Ping timeout: 240 seconds).
15:41:41 -!- shikhin has joined.
15:45:45 -!- shikhin has quit (Read error: Connection reset by peer).
15:46:05 -!- shikhin has joined.
15:46:48 -!- Phantom_Hoover has joined.
15:54:02 <HackEgo> [wiki] [[Rasen]] http://esolangs.org/w/index.php?diff=39477&oldid=39474 * Wolgr * (+647)
15:56:13 <HackEgo> [wiki] [[Rasen]] http://esolangs.org/w/index.php?diff=39478&oldid=39477 * Wolgr * (+57)
15:59:52 <HackEgo> [wiki] [[User:Wolgr]] http://esolangs.org/w/index.php?diff=39479&oldid=38383 * Wolgr * (+26)
16:03:56 -!- ^v has joined.
16:37:08 -!- MindlessDrone has joined.
16:38:02 -!- AnotherTest has joined.
16:43:49 -!- shikhin has quit (Ping timeout: 252 seconds).
16:46:33 -!- Taneb has changed nick to atriq.
16:47:56 -!- atriq has changed nick to Taneb.
16:59:32 -!- MoALTz has joined.
17:01:01 -!- b_jonas_ has changed nick to b_jonas.
17:04:06 -!- Nick_1 has joined.
17:08:21 <HackEgo> /home/hackbot/hackbot.hg/multibot_cmds/lib/limits: line 5: exec: welcome: not found
17:20:08 -!- FreeFull has joined.
17:22:27 <Nick_1> no much is spoken here
17:26:30 -!- KingOfKarlsruhe has joined.
17:33:58 -!- ^v has quit (Quit: http://i.imgur.com/Akc6r.gif).
17:37:56 <nortti> Nick_1: why art thou speaking in yellow?
17:38:10 -!- Phantom_Hoover has quit (Ping timeout: 258 seconds).
17:39:07 <ion> Physics http://i.imgur.com/ton5Pwz.gif
17:39:18 -!- Sprocklem has quit (Ping timeout: 240 seconds).
17:40:34 <nortti> could you use the standard text colour, those are disctracting?
17:43:18 <nortti> you are still using a non-default colour, but I do give you that dark grey is nicer than yellow
17:44:09 * int-e is a happy user of '/set hide_colors on' in irssi
17:44:20 <int-e> (though that means I've never had a genuine relcome experience)
17:45:09 <nortti> so, you interested in esoteric programming languages?
17:49:03 <Nick_1> i interested in esoteric
17:49:26 <nortti> what sort of esoteric?
17:50:40 <nortti> I suspect you might want to be at #esoteric at dalnet (?)
17:51:04 <KingOfKarlsruhe> Nick_1: would you please change your text color? I cannot see what you are writing, because i'm using a dark background color
17:51:07 <nortti> this channel is about unorthodox uses of computer science
17:52:11 <nortti> and main topic of discussion is anything except that
17:53:54 -!- shikhin has joined.
17:54:04 <nortti> now I cannot see anything since that is black-on-black
17:54:25 -!- Nick_1 has left.
17:57:58 -!- ^v has joined.
17:58:03 <mroman_> 95% of IRC discussions are off topic
17:58:20 <mroman_> That's not statistics, nor science. It's a rule.
17:59:21 -!- tertu has joined.
18:02:44 -!- ter2 has quit (Ping timeout: 252 seconds).
18:04:22 -!- nooodl_ has joined.
18:07:44 -!- realzies has quit (Ping timeout: 258 seconds).
18:08:00 -!- Bicyclidine has joined.
18:08:23 -!- nooodl has quit (Ping timeout: 250 seconds).
18:08:36 -!- realzies has joined.
18:08:36 -!- realzies has quit (Changing host).
18:08:36 -!- realzies has joined.
18:21:08 -!- conehead has joined.
18:21:19 -!- password2 has quit (Ping timeout: 245 seconds).
18:23:19 <HackEgo> 414) <NihilistDandy> Non sequitur is my forte <NihilistDandy> On-topic discussion is my piano <Taneb> Bowls of sugary breakfast cereal is my mezzoforte <Taneb> Full fat milk is my pianissimo <Taneb> On which note, I'm hungry \ 837) <olsner> FireFly: oh, did you see ion's police reindeer? that was ... at least as on-topic as this discussion \ 86
18:49:29 -!- Bicyclidine has quit (Ping timeout: 264 seconds).
19:26:33 -!- mhi^ has quit (Quit: Lost terminal).
19:28:57 -!- MindlessDrone has quit (Quit: MindlessDrone).
19:36:11 -!- mhi^ has joined.
19:40:01 <fizzie> Oh no, I missed Norway's ESC entry. #sorryoerjan
19:41:00 <myname> https://twitter.com/koerperkirmes/status/464397340905078784/photo/1 oh dear
19:42:24 -!- shikhout has joined.
19:45:23 -!- shikhin has quit (Ping timeout: 255 seconds).
19:53:37 <nooodl_> this classy macedonia intro
19:54:01 -!- Sprocklem has joined.
19:55:40 -!- nucular has quit (Quit: Excess Food).
19:58:36 <FireFly> Eh, I'll wait for the final
20:08:20 -!- john_metcalf has quit (Ping timeout: 240 seconds).
20:09:26 -!- impomatic has quit (Ping timeout: 255 seconds).
20:17:45 -!- oerjan has joined.
20:18:11 -!- ^v has quit (Read error: Connection reset by peer).
20:18:39 -!- ^v has joined.
20:20:50 <oerjan> fizzie: 'sok, i barely know it's ongoing.
20:21:00 <oerjan> and i have no idead what the norwegian song is.
20:23:07 <oerjan> myname: you know it's your duty to be clean.
20:25:49 <oerjan> i'm probably breaking german laws just by making that joke.
20:27:35 <oerjan> (also common decency but it's ok because no one will get the reference.)
20:46:07 <ion> myname: nice
20:55:21 -!- AnotherTest has quit (Ping timeout: 252 seconds).
20:55:24 <kmc> myname: heh
20:56:31 <kmc> chinese grocery stores in the US tend to have names like Super 88, 8 being a lucky number
20:56:35 <kmc> slightly awkward
21:00:23 -!- ^v has quit (Ping timeout: 252 seconds).
21:01:30 <olsner> is 88 a special significance?
21:02:02 <ion> Wasn't that lucky for certain people a few decades ago.
21:03:28 <mhi^> "If a funeral hearse drives past, you must hide your thumb in a fist. This is because the Japanese word for thumb literally translates as "parent-finger" and hiding it is considered protection for your parent. If you don't, your parent will die."
21:03:34 <mhi^> http://en.wikipedia.org/wiki/Japanese_superstitions#Linguistic_superstition
21:04:08 <ion> I'm starting to think olsner might not be a Nazi.
21:04:12 <olsner> ah, there we go http://en.wikipedia.org/wiki/88_(number)#In_white_nationalism
21:04:13 <myname> that is kind of an easy way to get your parents killed
21:04:43 <olsner> HH didn't ring a bell either... 88 is a quite popular swedish ice cream stick though
21:06:44 <fizzie> HH is short for Helly Hansen.
21:07:01 <Bike> myname: well, so's walking on a crack.
21:07:32 <Bike> "The letter H is eighth in the English alphabet, whereby 88 becomes HH" i'm sorry but this is far too dumb to take seriously
21:07:46 <Bike> even for white nationalists, who are already pretty fuckin dumb
21:08:01 <int-e> Well, Nazis aren't known for their shining brightness.
21:08:14 <mhi^> Bike: You think so? 18 for Adolf Hitler is quite popular among them, too.
21:08:30 <olsner> why do you know all this? is everyone a secret nazi?
21:08:41 <Bike> it's just too silly. t hey might as well be wearing white cloaks and pointy ahts
21:08:43 <mhi^> http://en.wikipedia.org/wiki/Combat_18
21:09:07 <mhi^> olsner: Either that or German. ;p
21:09:08 <kmc> nazi schmatzi
21:09:42 <myname> don't know about the others here, though
21:10:06 <Bike> given the anti-nazi laws in germany i'm going to assume everyone is arrested when they turn 88 years old
21:10:41 <olsner> apparently sweden won some chef's competition with: truffel-stewed pig's foot with blood crust
21:11:19 <olsner> you'd think edibility would be included in the scoring somewhere
21:11:26 <myname> Bike: with that logic there should be no nazis in germany because of those laws
21:11:34 -!- Sorella has quit (Ping timeout: 240 seconds).
21:12:30 <ion> > map (chr . (+ ord 'A') . subtract 1) [3,1,3,3,7]
21:12:32 <Bike> you doubt the long arm of the law? for shame
21:13:45 <myname> is there any difference between substract and -?
21:14:06 <oerjan> myname: opposite argument order
21:14:29 -!- ^v has joined.
21:14:43 <myname> well, you could've used (- 1)?
21:14:52 <int-e> myname: no, that's unary minus
21:15:20 <oerjan> subtract only exists because of that syntax quirk
21:15:23 <ion> That's a controversial kluge.
21:16:03 <FireFly> olsner: I've heard the ice cream 88 was once controversial because of the alleged nazi connection
21:16:59 -!- Sprocklem has quit (Quit: g2g).
21:18:07 <ion> I've heard Nazis were once controversial because of the alleged Nazi connection.
21:21:23 -!- drdanmaku has quit (Quit: Connection closed for inactivity).
21:25:24 -!- Sorella has joined.
21:32:25 -!- edwardk has joined.
21:40:32 -!- ^v has quit (Ping timeout: 252 seconds).
22:11:15 -!- edwardk has quit (Quit: Computer has gone to sleep.).
22:19:27 <HackEgo> [wiki] [[Zero]] http://esolangs.org/w/index.php?diff=39480&oldid=39475 * Nooodl * (+2029) add hello world
22:26:01 -!- KingOfKarlsruhe has quit (Quit: ChatZilla 0.9.90.1 [Firefox 29.0/20140421221237]).
22:29:29 -!- nooodl_ has quit (Quit: Ik ga weg).
22:45:34 -!- Phantom_Hoover has joined.
22:48:36 -!- Bicyclidine has joined.
22:49:32 -!- Sgeo has joined.
22:57:17 -!- boily has joined.
22:58:26 -!- Sgeo_ has joined.
22:59:05 -!- Bicyclidine has quit (Ping timeout: 264 seconds).
23:01:44 -!- Sgeo has quit (Ping timeout: 245 seconds).
23:12:01 -!- ^v has joined.
23:28:01 -!- tromp has joined.
23:41:08 -!- oerjan has quit (Quit: leaving).
23:45:16 <lambdabot> FireFly said 14h 17m 4s ago: not particularily much, no
23:45:43 <boily> FireFly: FirelloFly. what wasn't much that which it approximatively wasn't?
23:54:27 -!- yorick has quit (Remote host closed the connection).
23:58:25 -!- MoALTz_ has joined.
23:58:39 <boily> fungot: do you know what isn't, but not very?
23:58:40 <fungot> boily: whereas the spec has one stack for each of your target application isn't usually a difficult task... even without knowing it's in rinkworks. hm. are you happy?
23:58:55 <fungot> boily: there's an i386 slackware package too.)) yields the cartesian product of as and bs. :p they even give you the option of not getting killed...
23:59:25 <boily> fungot: I ain't used the slack in a long time. I'm still an Arch fanboy, even if my laptop runs ubuntu.
23:59:26 <fungot> boily: sadol doesn't support file i/ o
23:59:49 <boily> fungot: I rest my case.
23:59:49 <fungot> boily: table-size just returns a random factoid for the given task
00:00:01 <boily> fungot: your momma's a random factoid.
00:00:36 <HackEgo> [wiki] [[Hashes]] http://esolangs.org/w/index.php?diff=39481&oldid=35043 * 93.115.84.195 * (+0) /* example */
00:01:14 -!- MoALTz has quit (Ping timeout: 265 seconds).
00:12:15 -!- ^v has quit (Quit: http://i.imgur.com/Akc6r.gif).
00:12:36 -!- ^v has joined.
00:19:56 -!- Phantom_Hoover has quit (Remote host closed the connection).
00:27:00 -!- mhi^ has quit (Quit: Lost terminal).
00:32:51 -!- edwardk has joined.
01:03:02 -!- edwardk has quit (Quit: Computer has gone to sleep.).
01:05:45 -!- boily has quit (Quit: TURKEY CHICKEN).
01:07:23 <kmc> @ask boily what's the deal with your quit messages?
01:09:48 <kmc> compiled for your viewing pleasure https://gist.github.com/kmcallister/67b3ffb982fa31eb9b65
01:17:17 -!- tromp__ has joined.
01:19:07 -!- tromp has quit (Ping timeout: 250 seconds).
01:22:03 -!- shikhout has changed nick to shikhin.
01:23:50 -!- ^v has quit (Quit: http://i.imgur.com/Akc6r.gif).
01:25:34 -!- ^v has joined.
01:25:42 -!- shikhin has quit (Remote host closed the connection).
01:26:24 -!- tromp has joined.
01:29:26 -!- tromp__ has quit (Ping timeout: 276 seconds).
01:31:34 -!- tromp__ has joined.
01:33:13 <HackEgo> [wiki] [[User talk:Gs30ng]] http://esolangs.org/w/index.php?diff=39482&oldid=20546 * Gs30ng * (+499) Reply to Chris Pressey
01:34:38 -!- tromp has quit (Ping timeout: 240 seconds).
01:38:57 -!- tromp has joined.
01:40:53 -!- tromp__ has quit (Ping timeout: 252 seconds).
01:46:18 -!- tromp__ has joined.
01:49:26 -!- tromp has quit (Ping timeout: 255 seconds).
01:51:41 -!- conehead has quit (Quit: Computer has gone to sleep).
02:00:27 -!- tromp has joined.
02:03:17 -!- tromp__ has quit (Ping timeout: 264 seconds).
02:05:23 -!- drdanmaku has joined.
02:08:49 -!- tromp__ has joined.
02:10:38 -!- tromp has quit (Ping timeout: 240 seconds).
03:06:34 -!- adu has joined.
03:11:35 -!- stuntaneous has joined.
03:14:26 -!- ^v has quit (Read error: Connection reset by peer).
03:14:52 -!- ^v has joined.
03:18:38 -!- ^v has quit (Read error: Connection reset by peer).
03:19:02 -!- ^v has joined.
03:27:08 -!- Sprocklem has joined.
03:42:51 -!- adu has quit (Quit: adu).
03:48:50 -!- adu has joined.
03:48:58 -!- adu has quit (Client Quit).
04:21:01 <kmc> fungots fall on fungot falls
04:45:54 -!- tertu has quit (Ping timeout: 245 seconds).
05:22:41 -!- ^v has quit (Quit: http://i.imgur.com/Akc6r.gif).
05:25:04 -!- MoALTz_ has quit (Read error: Connection reset by peer).
05:25:32 -!- Sorella has quit (Quit: It is tiem!).
05:25:51 -!- MoALTz_ has joined.
05:27:13 -!- aloril has quit (Ping timeout: 252 seconds).
05:39:48 -!- aloril has joined.
05:41:27 -!- FreeFull has quit.
06:16:16 -!- tertu has joined.
06:18:24 -!- constant has changed nick to trout.
06:22:09 -!- KingOfKarlsruhe has joined.
06:27:29 -!- tertu has quit (Read error: Connection reset by peer).
06:27:41 -!- tertu has joined.
06:29:38 -!- password2 has joined.
06:32:09 -!- tertu has quit (Ping timeout: 245 seconds).
06:37:39 -!- MoALTz_ has quit (Quit: bbl).
06:50:13 -!- stuntaneous has quit (Remote host closed the connection).
06:50:54 -!- stuntaneous has joined.
06:50:57 -!- stuntaneous has quit (Excess Flood).
06:51:19 -!- stuntaneous has joined.
06:51:22 -!- stuntaneous has quit (Excess Flood).
06:51:49 -!- stuntaneous has joined.
06:51:52 -!- stuntaneous has quit (Excess Flood).
06:52:14 -!- stuntaneous has joined.
06:52:17 -!- stuntaneous has quit (Excess Flood).
06:52:39 -!- stuntaneous has joined.
06:52:42 -!- stuntaneous has quit (Excess Flood).
06:53:04 -!- stuntaneous has joined.
06:53:07 -!- stuntaneous has quit (Excess Flood).
06:55:07 -!- Sgeo has joined.
06:57:34 -!- Sgeo_ has quit (Ping timeout: 245 seconds).
07:07:36 -!- oerjan has joined.
07:07:42 -!- conehead has joined.
07:15:00 -!- Sgeo_ has joined.
07:18:24 -!- Sgeo has quit (Ping timeout: 245 seconds).
07:23:17 <oerjan> <kmc> compiled for your viewing pleasure https://gist.github.com/kmcallister/67b3ffb982fa31eb9b65 <-- a view into the mind of a Very Sane Man. sadly not chronological.
07:25:35 <kmc> http://i.imgur.com/EYT9clp.png finally
07:27:07 <myname> am i the only one who feels weird about an erotic shop doing a mother's day lottery?
07:27:36 <kmc> probably not
07:28:36 <kmc> is it MILF day
07:29:50 <kmc> shachaf: doubtful
07:34:23 <Bike> it's V-E Day, in moscow anyway
07:36:55 <kmc> privet tovarish
07:37:41 <HackEgo> aubercoin rnassingcoin intfull+coin ockcoin kipplexcoin shacccccccoin bdacoin stackcoin splcoin oortecoin snuskelloucoin emiacoin genheaperumcoin bogkcoin rvelyardshinrcoin traincoin poinecoin arbazocoin wallcoin alpotcoin
07:39:48 -!- trout has changed nick to pong.
07:39:53 -!- pong has changed nick to trout.
07:40:34 -!- MindlessDrone has joined.
07:41:15 <ion> FTL in hard mode without pausing http://www.twitch.tv/lethalfrag
07:56:34 <Bike> as stealth, lol
08:01:23 -!- drdanmaku has quit (Quit: Connection closed for inactivity).
08:33:09 -!- john_metcalf has joined.
08:57:49 <kmc> today I passed a grocery store which displayed the slogans "My Mouth Can Make Sounds But These Sounds Are Not Words" and "Every Vegetable Is A Word"
08:58:42 <oerjan> I Have No Mouth But I Need My Veggies
09:18:22 -!- mhi^ has joined.
09:25:29 -!- ion has quit (Ping timeout: 264 seconds).
09:31:14 -!- edwardk has joined.
09:38:47 -!- ion has joined.
09:51:22 -!- conehead has quit (Quit: Computer has gone to sleep).
10:00:56 -!- nooodl has joined.
10:01:36 -!- password2 has quit (Read error: Connection reset by peer).
10:03:39 -!- edwardk has quit (Quit: Computer has gone to sleep.).
10:04:37 -!- password2 has joined.
10:05:26 -!- password2 has quit (Max SendQ exceeded).
10:06:16 -!- password2 has joined.
10:15:52 -!- boily has joined.
10:21:38 -!- edwardk has joined.
10:24:03 -!- edwardk has quit (Client Quit).
10:41:09 -!- clog has quit (Ping timeout: 250 seconds).
10:57:21 -!- boily has quit (Quit: Poulet!).
10:59:01 -!- yorick has joined.
11:17:13 -!- oerjan has quit (Quit: leaving).
11:27:33 -!- Patashu has joined.
11:32:39 <Taneb> I wonder if there's anyone other than me whose first programming language was esoteric
11:34:29 -!- Patashu has quit (Ping timeout: 264 seconds).
11:39:35 <mroman_> https://medium.com/the-physics-arxiv-blog/898b104158d
11:39:59 <mroman_> "This kind of compression inevitably discards information. "
11:40:16 <mroman_> "4, 6, 8, 12, 14, 18, 20, 24…. This is an infinite series defined as: odd primes plus 1."
11:40:41 <mroman_> I don't see how 4,6,8 => odd primes + 1 is a lossy compression
11:44:30 <Taneb> mroman_, was the first programming language you learned esoteric?
11:46:14 <mroman_> Taneb: http://www.clonk.de/docs/en/sdk/script/index.html
11:46:22 <mroman_> ^- that was the first programming language I learned
11:47:19 <Taneb> http://dangermouse.net/esoteric/piet.html
11:47:41 <mroman_> It's a scripting language for a 2D-Game
11:48:04 -!- Sgeo_ has quit (Read error: Connection reset by peer).
11:48:07 <mroman_> which allowed players to create own stuff for it
11:48:09 <Taneb> Seriously, if I hadn't seen that language my life would be very different right now
11:49:17 <Taneb> I don't know, probably worse
11:49:24 <Taneb> Wouldn't have met you
11:49:36 <Taneb> Or like most of the people I know
11:50:04 <Taneb> Well, that's not quite true
11:50:19 <Taneb> I found Piet via Irregular Webcomic
11:50:33 <Taneb> If I hadn't read that I wouldn't have met most of the people I know
11:53:07 -!- clog has joined.
11:56:19 -!- nucular has joined.
11:56:19 -!- nucular has quit (Changing host).
11:56:19 -!- nucular has joined.
12:00:45 <nooodl> my whole internet experience sorta cascaded down from a single seed too. i guess dosgames.com! i wonder what life would've been like had i picked another one
12:05:00 <b_jonas> I'm not sure what all the seeds were for me. I'm quite sure I found perlmonks early, and that stickmanstickman (now at "http://stickman.qntm.org/index.php") was the first webcomic I read,
12:06:26 <nortti> my seed was ohjelmointiputka.net, which I first used by printing some of the qbasic code snippets out so I could type those in on my computer (which lacked internet)
12:11:11 <b_jonas> I'm not sure what the first esoteric programming language was that I've heared of. Could have been either intercal or unlambda.
12:17:34 -!- Frooxius has quit (Ping timeout: 245 seconds).
12:17:41 -!- john_metcalf has quit (Ping timeout: 264 seconds).
12:18:53 -!- impomatic has quit (Ping timeout: 252 seconds).
12:48:51 -!- Frooxius has joined.
13:04:12 <fizzie> I'm pretty sure it was Befunge that was the first esolang I came across, but I have no recollection where.
13:04:39 <fizzie> fungot: Think of it, if that hadn't happened, you might not exist!
13:04:40 <fungot> fizzie: speaking of which i can't upload from work _) are done only after beating the other guy
13:15:10 -!- augur has quit (Remote host closed the connection).
13:21:40 -!- impomatic has joined.
13:23:20 -!- Sorella has joined.
13:27:53 -!- nooodl has quit (Ping timeout: 264 seconds).
13:46:14 -!- Sprocklem has quit (Ping timeout: 240 seconds).
13:51:18 -!- augur has joined.
14:12:01 -!- hexagon has changed nick to sign.
14:14:41 -!- impomatic has quit (Ping timeout: 264 seconds).
14:20:15 -!- KingOfKarlsruhe has quit (Quit: Leaving.).
14:20:54 -!- augur has quit (Remote host closed the connection).
14:24:56 -!- AnotherTest has joined.
14:29:38 -!- edwardk has joined.
14:41:19 -!- ggherdov_ has quit (Ping timeout: 245 seconds).
14:41:28 -!- augur has joined.
14:42:59 -!- AnotherTest has quit (Ping timeout: 255 seconds).
14:45:53 -!- augur has quit (Remote host closed the connection).
14:51:33 -!- augur has joined.
14:54:08 -!- augur has quit (Remote host closed the connection).
14:56:05 -!- ggherdov_ has joined.
14:56:18 -!- RedSquirrel has joined.
15:06:57 -!- AnotherTest has joined.
15:07:35 -!- drdanmaku has joined.
15:10:20 -!- aloril has quit (Ping timeout: 240 seconds).
15:21:07 <FireFly> The esolang I first came across was either Brainfuck och Argh!
15:22:48 <FireFly> Probably the former, although I think the first I wrote a program in is the latter
15:23:02 <Melvar> For me, I think it was probably Brainfuck or INTERCAL.
15:23:32 <FireFly> Too much language context-switching, I suppose
15:23:59 <nortti> for me it was definitely brainfuck first, then either befunge 98 or Lazy K
15:24:19 -!- aloril has joined.
15:24:43 <nortti> iirc I found the wiki through befunge, so it probably was second
15:25:22 <mroman_> I'm founding the Esoteric Standard Committee (ESOSC). Who's in? :P
15:26:38 -!- edwardk has quit (Quit: Computer has gone to sleep.).
15:26:46 <FireFly> Congrats, ESC is all over the news already
15:27:31 <Taneb> Eurovision song contest final tomorrow night!
15:36:04 <Taneb> mroman_, can we create a "normalized brainfuck" standard?
15:36:40 <nortti> mroman_: what sort of standards?
15:39:49 <mroman_> Taneb, nortti: Some standardized brainfuck
15:40:29 <mroman_> and wrap-around for cells, tape etc.
15:40:29 <fizzie> That does not sound like a real standards body. You need a lot more bureaucracy. Working groups and so on.
15:40:59 <mroman_> you guys are working groups, right?
15:41:05 <Taneb> mroman_, I'd say normalized brainfuck for ease of interpretation
15:41:10 <Taneb> ie, no comments/whitespace
15:41:15 <nortti> 8bit cells, wrap-around, eof-is-0?
15:41:32 <Taneb> Maybe we can make a number of brainfuck standards!
15:42:07 <mroman_> ESOSC 2014-2 requires for a normalized bf programm to only contain chars [.,+-><]?
15:42:20 <mroman_> and everything else isn't ESOSC conform
15:42:47 <Taneb> Doesn't conform to ESOSC 2014-2 "Normalized brainfuck (nbf)"
15:43:08 <Taneb> Perhaps we also need to define the semantics of the language
15:44:02 <nortti> also, what happens to newlines in envs where newline is not 0x10
15:44:03 <mroman_> all that's left to do is finding someone who can draw a fancy logo
15:46:15 -!- Bike has quit (Quit: leaving).
15:47:55 <nortti> mroman_: you can count me in
15:48:09 <b_jonas> mroman_: that's only first normal form of bf
15:49:07 <b_jonas> mroman_: second normal form bf programs further don't have the sequence ][ nor >< nor +- nor -+
15:49:42 <b_jonas> nortti: the second loop never runs. it's used as a form of comment.
15:49:50 <nortti> I was thinking "that is not a null"
15:50:12 <nortti> then I realized the second loops never runs since first one ends with a 0
15:50:35 <mroman_> second should be like no unmatched brackets and stuff?
15:50:51 <b_jonas> what? you need no unmatched brackets in any valid bf program
15:50:52 <Taneb> mroman_, that can be done with a simple CFG
15:54:27 <Taneb> A -> +|-|<|>|,|.|[S]
16:07:30 <mroman_> What kind of "states" do we need?
16:07:35 -!- Phantom_Hoover has joined.
16:08:09 <nortti> Draft, Approved, Forgotten?
16:11:29 -!- password2 has quit (Ping timeout: 276 seconds).
16:13:37 <nortti> err, yeah. my brains do not work today
16:14:58 <mroman_> that's the BNF of standard's identification string/number :)
16:15:42 <int-e> I like "forgotten"
16:17:02 <nortti> for drafts that are abandoned since everyone losy focus?
16:18:31 <int-e> It's the status of most standards once they've gone through the test of time
16:20:52 <int-e> But I do like the notion of tracking it formally. :)
16:21:19 <nortti> what criteria would be used to determine if a standard is forgotten?
16:21:34 -!- edwardk has joined.
16:22:42 <int-e> obviously it's forgotten when nobody remembers it.
16:23:02 <nortti> then no-one would remember to change its status
16:23:41 -!- password2 has joined.
16:24:28 <int-e> so you need some outside historian assign the status for you
16:31:15 -!- AnotherTest has quit (Read error: Connection reset by peer).
16:31:22 -!- yorick has quit (Remote host closed the connection).
16:31:53 -!- AnotherTest has joined.
16:37:41 -!- augur has joined.
16:39:42 <b_jonas> the statuses shall be: 1. draft, 2. still draft but already obsolate, 3. accepted but was already obsolate when it was accepted, 4. we claim it's draft and will finish it some day but actually it's vaporware and will be forgotten eventually
16:40:00 <b_jonas> and yes, we might need 5. revoked too
16:45:17 -!- edwardk has quit (Quit: Computer has gone to sleep.).
16:48:13 -!- ^v has joined.
16:49:04 <mroman_> http://eso.mroman.ch/ESOSC/ESOSC-2014-D1-R1.pdf <- gotta set some ground rules
16:50:34 -!- Bike has joined.
16:54:23 <nortti> so, for example ESOSC-2014-D1 -> ESOSC-2014-D1-R2 -> ESOSC-2014-A1 -> ESOSC-2014-O1 ?
17:16:58 <mroman_> gotta document when a standard gets obsolete and stuff
17:17:02 <mroman_> then you can approve it ;)
17:19:52 -!- nooodl has joined.
17:22:06 -!- Phantom_Hoover has quit (Remote host closed the connection).
17:22:30 -!- Phantom_Hoover has joined.
17:24:14 -!- nooodl has quit (Ping timeout: 245 seconds).
17:27:14 -!- Bike has quit (Ping timeout: 240 seconds).
17:33:17 -!- FreeFull has joined.
17:35:58 <HackEgo> todcoin 2d-revcoin quatcoin constanticoin parcoin saaticoin ferrocoin oddbalcoin suxecoin nybracoin lyapascoin luigecoin embaschlacoin rocurdcoin baycoin forcoin catamecoin divilliicoin rubecoin objectcoin
17:36:55 <kmc> i like rubecoin
17:37:23 <nortti> proof of work is a overcomplicated solution to a simple problem?
17:38:42 <Phantom_Hoover> MEANWHILE IN /R/BITCOIN: http://www.reddit.com/r/Bitcoin/comments/25205w/lets_hire_an_expendables_like_group_to_free_the/
17:47:22 <nortti> are all reddit bitcoiners that lost in touch with reality?
17:47:34 <mroman_> nortti, Taneb: http://eso.mroman.ch/ESOSC/ESOSC-2014-D1-R2.pdf
17:48:52 <Taneb> "anylonger" should be two words
17:49:08 <Taneb> And we specify the format but not its meaning
17:50:18 <Phantom_Hoover> nortti, well, fair play to them it's downvoted into the negatives and all the replies are critical
17:50:40 <mroman_> year of issue and an ever increasing number
17:51:06 <nortti> mroman_: also, it could be good to note that only apprived versions are ever obsoleted
17:52:20 <mroman_> consists of a number that is successively increased with every new standard?
17:52:55 <nortti> Taneb: to prevent confusion when there are non-obsolete versions that contain the same info as obsolete ones? admitedly, the labelling of them as drafts should tick them off
17:53:19 <mroman_> Drafts can be "Rejected" I guess?
17:54:03 <Phantom_Hoover> nortti, more representative sample: http://www.reddit.com/r/Bitcoin/comments/251314/its_the_perfect_time_to_buy_bitcoins/
17:54:09 <nortti> yeah, probably best to leave that corner-case out and do as we see best once the situation actually happens
17:56:15 <mroman_> encodes the year of issue and a number that is successively increased with every new standard to ensure uniqueness. "
17:58:17 <Taneb> What would happen if something has a revision in December then another in January?
17:58:53 <mroman_> That'd make the most sense I think
17:59:37 <mroman_> or the year the work on the draft began
18:00:02 <nortti> and the same EUIN (except for changed status and no revision in end) is kept when it is aproved
18:08:50 -!- Phantom_Hoover has quit (Read error: Connection reset by peer).
18:08:56 -!- Phantom__Hoover has joined.
18:14:05 <mroman_> nortti, Taneb: http://eso.mroman.ch/ESOSC/ESOSC-2014-D1-R3.pdf
18:18:09 <Taneb> I'd say "be approved" rather than "get approved"
18:18:24 <Taneb> Or possibly "be marked as approved"
18:23:19 <mroman_> I think the ESOSC can correct grammar/typos without a new revision :)
18:23:52 <mroman_> and that a revision is a draft
18:24:02 -!- oerjan has joined.
18:24:18 <mroman_> or if you revise a standard the revision of that standard is in state "draft"
18:25:28 <RedSquirrel> "standardization of esoteric programming languages " <- is that a joke?
18:25:35 <Phantom__Hoover> i hope this standard will be integrated into the esolang standardisation system
18:26:46 <mroman_> RedSquirrel: Nah. It's serious business
18:29:12 -!- edwardk has joined.
18:29:20 <oerjan> nortti: you know there's a tvtropes page for that right
18:30:10 <myname> RedSquirrel: everything we do here is dead serious
18:30:19 <mroman_> "A new revision of an approved standard is put into the draft state and requires the usual approval process taking place. Revisions of standards in draft state
18:30:22 <mroman_> are not affected by this. The ESOSC is allowed to correct gramma, orthographical or similar mistakes without requiring a new revision. "
18:30:34 -!- oerjan has set topic: The dead serious channel | PSA: fizzie is running the wiki now, contact him for any problems | https://dl.dropboxusercontent.com/u/2023808/wisdom.pdf http://codu.org/logs/_esoteric/ http://tunes.org/~nef/logs/esoteric/.
18:32:17 <oerjan> Taneb: your voice recognition needs work
18:32:27 <HackEgo> 724) <Taneb> hang on I have bright idea <Taneb> navajo to f me 1 in 3 people
18:32:40 <RedSquirrel> the builtin orthographical mistakes is standardized copyprotection
18:34:02 <mroman_> http://eso.mroman.ch/ESOSC/ESOSC-2014-D1-R4.pdf
18:35:05 -!- edwardk has quit (Quit: Computer has gone to sleep.).
18:39:58 <mroman_> how does one become a member :D?
18:40:19 <mroman_> requires approval of three members to become a member
18:41:23 <myname> i don't know what the hell is going on and whether or not i am a member, but i approve
18:41:30 <Taneb> mroman_, two thirds majority?
18:41:42 <RedSquirrel> approval by ehird is absolutely satisfying
18:42:32 <mroman_> nortti: Do you approve two thirds majoirity?
18:42:37 <mroman_> then I don't have to make a R5 :D
18:43:30 <myname> so... what the hell is esosc and where can i sign in?
18:44:41 <nortti> mroman_: 2/3 majority on what?
18:45:52 <mroman_> 2/3 majority to become a member of the esosc
18:46:15 <mroman_> Our first approved standard
18:48:12 <nortti> `learn esosc is esoteric song contest
18:48:21 <mroman_> now we can work on that nbf
18:49:32 <RedSquirrel> may i ask how it came the world needs an "Esoteric Standard Committee"? somebody requested it?
18:49:35 <nortti> `run sed -i 's/$/ (also Esoteric Standard Committee)/' wisdom/esosc
18:49:44 <nortti> RedSquirrel: 18:25 < mroman_> I'm founding the Esoteric Standard Committee (ESOSC). Who's in? :P
18:52:59 -!- impomatic has joined.
18:54:14 <nortti> so, nbf deals both with how the bf source file is stored and implementation details like EOF handling?
18:55:16 <Taneb> nortti, we could split the two specifications
18:55:26 <Taneb> "brainfuck conventions"
18:55:30 <nortti> yeah, I agree that would be better
18:55:31 <Taneb> And "Normalized brainfuck"
18:56:02 <nortti> because one is directed at source code, other at implementation
18:56:33 <myname> mroman_: what does that committee actually do?
18:56:43 <Taneb> myname, we make standards
18:57:46 <oerjan> also there needs to be a draft for adding lambda to brainfuck
18:58:48 <oerjan> also there will be an entirely different brainfuck standardisation sponsored by microsoft.
18:58:51 <nortti> and arithmetical type system
18:59:07 <myname> oerjan: is it called windows?
19:01:17 <mroman_> myname: We make standards, yeah.
19:02:38 <myname> i am quite unsure if i want to join
19:02:52 <myname> on one hand it sounds totally awesome
19:03:01 <myname> on the other hand it sounds like it could be actual work
19:04:11 -!- archaic has joined.
19:04:19 <mroman_> There's some work involved, yes.
19:06:48 -!- ais523 has joined.
19:06:57 <RedSquirrel> while uncountable amounts of new esolangs are invented everyday, the channel had to change its focus on inventing some standards ..it's not that anybody wants it.. they're just necessary
19:08:10 <Taneb> ais523, there's now a standards committee
19:09:14 -!- password2 has quit (Ping timeout: 245 seconds).
19:09:32 <myname> i should found another one that defines standards that are always slightly incompatible with ESOSC standards
19:09:54 <kmc> how many CHF does it cost to buy the official copy of a ESOSC standard
19:09:57 <ais523> is it following on from the work of eso-std?
19:10:10 <ais523> I remember that project collapsed when we couldn't agree on a format that the standards should be in
19:10:19 <ais523> I'm not sure if anyone but me cared about the actual standardisation part
19:10:20 <nortti> esoteric sexually transmitted disease?
19:10:30 <ais523> esoteric standardisation, I guess
19:10:52 <kmc> retroviruses are pretty esoteric
19:11:26 -!- ^v has quit (Read error: Connection reset by peer).
19:11:54 -!- ^v has joined.
19:12:37 <myname> i would've called it just ESO
19:12:50 <myname> would be more puny in respect to ISO
19:13:14 <myname> and the first thing would be a definition of an OSE reference modell
19:14:00 -!- ^v has quit (Read error: Connection reset by peer).
19:14:17 -!- ^v has joined.
19:19:34 -!- ^v has quit (Read error: Connection reset by peer).
19:19:59 -!- ^v has joined.
19:23:17 <mroman_> http://eso.mroman.ch/ESOSC/ESOSC-2014-A1.pdf <- and there it is.
19:24:11 <ais523> the "hyphen" production isn't defined
19:24:42 <ais523> and numbers allow arbitrarily many leading zeros, not sure if that's intended
19:24:46 <mroman_> that should've been <hyph>
19:26:31 -!- MindlessDrone has quit (Quit: MindlessDrone).
19:27:43 <kmc> you're representing years in base 10? boring
19:30:58 <FireFly> Where do I voice the opinion that all specifications should be available in html format online, in addition to pdf?
19:34:25 <kmc> form a working group
19:34:28 <RedSquirrel> download and fill out the esosc-request forms
19:34:45 <nortti> then fax them to mroman_
19:35:19 <kmc> you'll have to submit a change request through your national standards body
19:35:54 <FireFly> I'm not sure if SIS recognises ESOSC as a standards body
19:36:26 <kmc> http://www.open-std.org/jtc1/sc22/wg14/www/docs/dr_404.htm
19:36:47 <FireFly> I think that's what our national standards body is called
19:36:58 <FireFly> Although I don't remember what it expands to
19:37:11 <RedSquirrel> i know now.. i know where all this points at! learn the rules like a pro, to break them like an artist -picasso
19:37:26 <FireFly> "SIS Swedish Standards Institute"
19:37:49 <RedSquirrel> where's the fun in eden when there is no forbidden fruits?
19:38:12 <ais523> this channel has a surprisingly large number of Scandinavians
19:38:28 <nortti> even larger number of nordics
19:38:37 <FireFly> Apparently "SIS" officially stands for "Swedish Standards Institute" nowadays
19:38:55 <ais523> like "UTC" officially stands for "Coordinated Universal Time"?
19:39:01 <FireFly> I guess it's a bit like how UTC expands incorrectly in both french and english
19:40:30 <mroman_> I don't have latex2html I think on my windows
19:42:06 <FreeFull> https://github.com/huonw/brainfuck_macro Did you guys see this?
19:43:36 <nortti> http://winterdom.com/2002/03/regardingecma234
19:44:16 -!- Rgasuit has joined.
19:45:32 <myname> the Web Ontology Language
19:49:06 <mroman_> http://eso.mroman.ch/ESOSC/upcoming.txt
19:49:45 -!- Rgasuit has quit (Ping timeout: 250 seconds).
19:54:10 -!- Sprocklem has joined.
19:56:36 -!- conehead has joined.
20:04:05 <mroman_> this tool can't convert \begin{grammar}
20:08:34 <oerjan> hm the IE tab bugs haven't been _entirely_ eradicated, i see; i got a single tab that was colored again
20:09:18 <oerjan> mroman_: send it to grammar school
20:09:31 <mroman_> FireFly: http://eso.mroman.ch/ESOSC/ESOSC-2014-A1.html
20:10:13 <mroman_> except for the OT1bchbn thingy there
20:10:43 <RedSquirrel> oerjan: for what reason do you use IE master oerjan?
20:12:11 <RedSquirrel> no.. you love writing bug-reports @ MS .. right?
20:12:14 <kmc> somebody should do Coccinelle for Rust
20:12:17 <kmc> that would be awesome
20:13:37 <oerjan> RedSquirrel: laziness and habit
20:14:19 <oerjan> also, the one time i tried to install chrome one of my favorite websites stopped working properly.
20:14:38 <mroman_> We're still missing a fancy logo though
20:15:09 <oerjan> and i don't bother with bug reports.
20:16:19 <oerjan> also, there needs to be someone who uses IE just to keep you guessing.
20:16:35 <kmc> i hear IE is pretty good these days
20:17:05 -!- conehead has quit (Quit: Computer has gone to sleep).
20:17:24 <kmc> UTC is probably by analogy to UT0 etc.
20:17:54 <mroman_> and the 2/3 is missing in the html output
20:17:57 -!- conehead has joined.
20:18:06 <Taneb> I was writing notes on something
20:18:15 <Taneb> And I've just written "HMM."
20:18:25 <Taneb> I also drew a ship, which I scribbled out
20:18:30 <Taneb> I am not very good at this
20:18:31 <kmc> is it about hidden markov models?
20:18:49 <Taneb> But not really sort of
20:20:17 <kmc> Her Majesty's Moonship
20:22:38 -!- ChanServ has set channel mode: +o oerjan.
20:22:53 -!- oerjan has set channel mode: +b *!*4d0b5b3d@*.77.11.91.61.
20:22:53 -!- oerjan has kicked RedSquirrel Bye hagb4rd.
20:24:54 -!- oerjan has set channel mode: -o oerjan.
20:31:32 <mroman_> Why didn't somebody create a Painfuck
20:31:49 <mroman_> that introduces new symbols for EOF and Newline handling
20:32:13 <mroman_> unless there already is such a thing
20:32:37 <mroman_> seeing as how many derivatives of bf exist certainly there should be one around them adressing those issues
20:33:05 -!- yorick has joined.
20:34:13 <ais523> mroman_: in most of my esolangs nowadays, I have EOF = 0, NUL = 1, SOH = 2, etc.
20:34:50 -!- nooodl has joined.
20:35:36 <nortti> I think lazy-k's eof=256 was pretty good
20:35:42 <kmc> there are so many brainfuck derivatives but are there any brainfuck integrals
20:36:15 <nortti> how would one construct a brainfuck integral?
20:37:32 <kmc> not my problem
20:38:11 <FireFly> Didn't someone invent a brainfuck derivative that replaces the tape's cells with a real line?
20:38:40 <FireFly> I imagine the loop condition would involve integrals in that case, maybe that counts
20:39:17 <shachaf> kmc: what do you think of memoization of continuous functions
20:39:22 <kmc> Rust now supports inline brainfuck: https://github.com/huonw/brainfuck_macro
20:39:33 <kmc> shachaf: don't know, what do you think of it
20:39:45 <shachaf> it sounds p. interesting imo
20:40:09 <shachaf> i mean in particular the thing where you share most of the work between similar inputs to produce similar outputs
20:40:12 <kmc> i don't know anything about it
20:43:02 <shachaf> and also making it happen automatically with laziness when you use a particular sort of continuity??
20:43:26 <shachaf> e.g. you have a bit stream and a prefix of it gets shared
20:43:42 <shachaf> er, that doesn't quite make sense
20:46:53 -!- tertu has joined.
20:48:24 <ion> https://imgur.com/a/iDJMg
20:51:57 -!- ais523 has quit (Read error: Connection reset by peer).
20:52:08 -!- ais523 has joined.
20:52:58 <kmc> as the saying goes, "they had a good run"
20:53:13 <kmc> I kind of stopped watching / caring during this season
20:57:20 <Phantom__Hoover> (i probably shouldn't binge on tv shows that are still running, i just lose interest between seasons)
20:58:59 <kmc> I've been re-watching Peep Show with douglass_
20:59:29 <kmc> it's one of the top few funniest shows I've ever seen
20:59:35 <Phantom__Hoover> i got about 5 minutes into the first episode of peep show and it was just too painful
21:00:21 <kmc> yeah I could see that
21:02:29 <Phantom__Hoover> my family got me hooked on endeavour during the holidays but it's now between series as well
21:06:10 <kmc> what's endeavour
21:07:23 <Taneb> kmc, prequel to Inspector Morse iirc
21:14:23 <kmc> what possessed me to listen to a song titled "Vienna Arcweld Fucked Gamelan Rigid Tracking"
21:14:43 <kmc> "song" is perhaps an overstatement, it consists mostly of ominous ambient squeaking machinery noises
21:15:20 <oerjan> you can't go wrong with gamelan
21:18:49 -!- Sprocklem has quit (Ping timeout: 245 seconds).
21:19:26 <oerjan> http://www.youtube.com/watch?v=Z1VcuffZocA&index=6&list=PL4CD9537492AEA538
21:25:54 -!- AnotherTest has quit (Ping timeout: 245 seconds).
21:33:20 -!- tromp__ has quit (Ping timeout: 258 seconds).
21:38:38 -!- mhi^ has quit (Ping timeout: 240 seconds).
21:44:38 <kmc> fungots fall on fungot falls
21:44:38 <fungot> kmc: it should use? which compiler, msvc? i'm inside your mom!
21:45:13 -!- ais523 has quit.
21:45:39 <kmc> that's really between the two of them
21:46:08 -!- nucular has quit (Quit: Excess Food).
21:47:32 -!- edwardk has joined.
21:47:49 <Phantom__Hoover> `addquote <fungot> kmc: it should use? which compiler, msvc? i'm inside your mom!
21:47:49 <fungot> Phantom__Hoover: now to sleep. first lecture day of 2006 tomorrow, wouldn't want to use some package or other
21:47:51 <HackEgo> 1193) <fungot> kmc: it should use? which compiler, msvc? i'm inside your mom!
21:50:38 <oerjan> fungot has time travel all figured out.
21:50:38 <fungot> oerjan: i don't know if that is true.
21:51:18 <fungot> Phantom__Hoover: my irix box could probably use one.
21:51:20 <oerjan> fungot: so you have to forget that you know time travel to use it? fascinating!
21:51:20 <fungot> oerjan: i have just been extended to fnord words... interesting
21:52:06 <oerjan> fungot: no, you've always done that. maybe you are actually past fungot.
21:52:06 <fungot> oerjan: i think this is the guy working on def-bf, who is root fnord" in the various schemes/ i
21:52:42 <FireFly> fungot: I don't think oerjan is working on that, no
21:52:43 <fungot> FireFly: freedom is slavery ignorance is strenght bush is president. so counting ballots is really more difficult than merge sort or insertion sort.... of evil!
21:53:37 -!- zzo38 has joined.
21:54:14 <zzo38> I have said before, there is no infinite loop of write operation in SQL, only of read operation (such as a SELECT statement); however, that is probably sufficient for most things anyways.
21:56:07 <oerjan> edwardk: there seems to be an SO lens-related question which no one can answer http://stackoverflow.com/questions/23567695/implementing-polymorphic-deep-function-for-traversals-and-folds
21:56:25 <oerjan> (it's over my lens head, at least)
22:00:44 -!- Phantom__Hoover has quit (Read error: Connection reset by peer).
22:00:50 -!- Phantom_Hoover has joined.
22:05:55 -!- tertu has quit (Ping timeout: 258 seconds).
22:08:05 -!- tertu has joined.
22:08:26 <shachaf> oerjan: the usual solution to that sort of thing is to not take a rank-2 Traversal argument and return a Traversal result but take some sort of Over p f s t a b sort of argument and return a similar result
22:08:51 -!- ter2 has joined.
22:08:51 -!- tertu has quit (Disconnected by services).
22:09:37 -!- tertu3 has joined.
22:09:37 <shachaf> so your caller needs to pick the types
22:12:00 -!- tertu has joined.
22:13:29 -!- ter2 has quit (Ping timeout: 264 seconds).
22:14:05 -!- tertu3 has quit (Ping timeout: 264 seconds).
22:22:04 -!- augur has quit (Remote host closed the connection).
22:26:48 -!- yorick has quit (Remote host closed the connection).
22:29:12 <kmc> shachaf: Rust's RefCell is kind of an interesting beast
22:29:17 <kmc> I'm not sure if it's mis-named or not
22:29:27 <kmc> it's not necessarily heap allocated
22:31:12 <kmc> its purpose is basically that you can do &RefCell<T> -> &mut T
22:31:36 <kmc> and this moves the enforcement of mutable pointer aliasing rules to runtime
22:32:11 <kmc> so a RefCell<T> is a T (annotated so that LLVM won't assume it's immutable) alongside a word for this dynamic borrow flag
22:40:59 <kmc> I found some ways to break said aliasing rules in servo
22:44:26 -!- Sgeo has joined.
22:44:50 <shachaf> i should really learn about rust and multable pointer aliasing rules sometime
22:46:57 * Sgeo finds it mildly distressing that trying to envision lenses in Smalltalk is making him envision deliberately losing the property that the optics themselves are definable separately from the structures they traverse, solely because that fits better syntactically
22:47:03 -!- Phantom_Hoover has quit (Read error: Connection reset by peer).
22:47:08 <Sgeo> (aLens,bLens,cLens) of: someStructure put: blah
22:52:07 <kmc> shachaf: &mut references can't alias with any other reference
22:52:09 <kmc> is the main thing
22:52:13 -!- Sprocklem has joined.
22:53:55 -!- ^v has quit (Quit: http://i.imgur.com/Akc6r.gif).
22:55:13 <kmc> this is enforced statically, but you can break the rules in unsafe code and then enforce it dynamically, which is what std::cell implements
22:58:03 -!- Patashu has joined.
22:59:38 <Sgeo> Pharo seems headed in a more OO direction
23:01:03 <Sgeo> http://www.slideshare.net/pharoproject/advanced-reflection-in-pharo
23:01:23 -!- drdanmaku has quit (Quit: Connection closed for inactivity).
23:06:39 <olsner> my code mostly breaks the aliasing rules and then doesn't enforce them, and then writes are lost sometimes
23:07:04 <olsner> I wonder if a less safe language would end up doing the right thing more often
23:07:13 -!- Patashu_ has joined.
23:07:13 -!- Patashu has quit (Disconnected by services).
23:14:42 <kmc> why do you break the rules?
23:17:56 <kmc> why you want rail for kalashnikov
23:25:59 <oerjan> shachaf: i see bizarre stuff http://stackoverflow.com/a/23575190/1088108 (also, pretty quick service)
23:35:02 -!- MoALTz has joined.
23:49:01 -!- idris-bot has quit (Quit: Terminated).
23:59:26 -!- oerjan has quit (Quit: leaving).
00:06:13 <zzo38> Nobody on #sqlite channel knows how to answer my question how to fix it so that, it is possible to use savepoint inside of a INSTEAD OF trigger program and to rename views and other stuff.
00:06:25 -!- MoALTz_ has joined.
00:07:59 -!- tromp has joined.
00:08:57 -!- MoALTz has quit (Ping timeout: 252 seconds).
00:21:22 <zzo38> I am typing in session 51 of Dungeons&Dragons game, for now.
00:22:46 <Taneb> In the D&D game I am playing the entire party of 5 people is completely split
00:23:04 <zzo38> That is certainly possible, and sometimes very useful.
00:23:04 <Taneb> Two of us, including my character, have been arrested
00:23:32 <Taneb> Possession of some sort of superweapon
00:23:52 <Taneb> And antagonizing an empire
00:24:37 <zzo38> My character once did get arrested...on purpose.
00:26:03 <Taneb> This was very much not on purpose
00:26:21 <zzo38> (I knew I would be let out in time, and there were other reasons and things too, including the phase of the moon.)
00:26:33 <Taneb> It was quite surprising that 3 of the party managed to get away
00:26:41 <zzo38> When playing at D&D, you have to take advantage of the phase of the moon.
00:27:03 <Taneb> One by pretending to be blind and so harmless (his character is actually blind but it isn't a hindrance)
00:27:28 <Taneb> One by using a carpet as a moving wall to shelter himself from arrows
00:28:07 <Taneb> And one by teleporting through a very small hole in the ceiling onto the roof
00:31:03 <Taneb> zzo38, any advice for getting out of jail in D&D?
00:31:07 <zzo38> I have once managed to escape by replacing a door with its mirror image, stealing a wizard's wand, secretly giving it back to him, and stuff...
00:31:21 <zzo38> Taneb: I cannot say, since it depends a lot on the exact circumstances.
00:31:46 <Taneb> I'll have to figure it out myself
00:32:12 <Taneb> I don't think the rest of the party will rescue me (it would be out of character for them)
00:32:15 <zzo38> You may just have to wait; even if you can do other things, sometimes that is the best way anyways.
00:33:07 <Taneb> I've got the impression that if I wait I will eventually be executed or at least skinned alive
00:33:17 <Taneb> Neither of which are ideal
00:33:22 <zzo38> Then don't wait too much!
00:33:35 <Taneb> I think my best bet will be to talk my way out
00:33:37 <zzo38> Do you have the way to write letters?
00:33:46 <zzo38> The pen is mightier than a sword, so use a pen!
00:34:03 <Taneb> That may be the best option
00:34:10 <Taneb> My character does have quite high charisma
00:34:32 <zzo38> (That's what I did; not to get out of jail though, but to convince someone to do something while I was in jail.)
00:36:56 <zzo38> High charisma is not enough. You also need a paper to write on!
00:37:27 <Taneb> Yeah, that may be an issue
00:37:39 <Taneb> I will also need some form of writing implement
00:38:26 <zzo38> At one point, I wanted to tell something to someone in a house which I did not want to go near, and I had no pen or paper, but I did have a book, so I searched the book for a phrase similar enough to what I wanted to say, tore it out, tied it to a rock, and threw it through the window.
00:38:52 <zzo38> Of course, if nothing else works, try using magic if you have any.
00:42:57 <nooodl> static int bogo_comp( const void *a, const void *b ) { return rand() % 3 - 1; }
00:43:00 <nooodl> qsort( deck, n_cards, sizeof(int), bogo_comp );
00:44:38 <zzo38> nooodl: Is that like "ORDER BY RANDOM()" in a SQL program?
00:45:13 <nooodl> it might be! depending on the sort ORDER BY performs
00:45:27 <nooodl> i don't think this is a veeery good shuffle though
00:47:50 <zzo38> I think ORDER BY will perform the same sort as if the value specified is an extra column of the table, then sort by that fake extra column.
00:51:11 -!- idris-bot has joined.
00:59:19 -!- Phantom_Hoover has joined.
01:00:17 -!- nooodl_ has joined.
01:03:54 -!- nooodl has quit (Ping timeout: 240 seconds).
01:19:52 -!- Phantom_Hoover has quit (Remote host closed the connection).
01:34:29 <Sgeo> Grr why doesn't Pharo come with Symbol>>asBlock?
01:34:46 -!- MoALTz__ has joined.
01:37:08 -!- MoALTz_ has quit (Ping timeout: 240 seconds).
01:39:22 <fowl> thats a ruby hack
01:41:03 -!- Bike has joined.
01:53:19 <kmc> is it UB to give qsort a comparison function that isn't a total order
01:54:34 <Bike> shouldn't it only have to be partial?
01:54:35 <kmc> rust has separate Eq and TotalEq, Ord and TotalOrd
01:54:41 <kmc> and much controversy over where floats fit into this
01:54:44 <Bike> is there PreOrd
01:54:55 <Bike> well what's the fucking point them
01:55:02 <Bike> i need a whole hierarchy of ordinals!
01:56:38 <Jafet> Probably no less defined than rand is
01:57:05 <kmc> hm, do normal sorting algorithms work with partial orders?
01:57:36 <Jafet> Most of them will do something and then terminate
01:57:54 <kmc> such turing machine, very halting
01:58:03 <Bike> informative helpful answer a++
01:58:22 <zzo38> kmc: Actually, there is case where I would find such a thing helpful, to use sorting with partial ordering.
01:59:40 <Sgeo> What's PreOrd?
02:00:44 <kmc> are partial orders the same thing as transitive DAGs?
02:01:12 <zzo38> Partial orders are same thing as a thin category.
02:01:57 <Bike> Sgeo: a preorder.
02:03:42 <zzo38> Is there a thing such as logic without free variables?
02:03:55 <zzo38> I believe I can figure out how to do it.
02:08:05 <zzo38> What do you mean by that?
02:11:36 * Sgeo wonders how PetitParser compares to Parsec
02:12:03 <Sgeo> I vaguely recall something saying that PetitParser includes parser combinators, but also has something that avoids some pitfall?
02:12:22 <Sgeo> "Instead it uses a unique combination of four alternative parser methodologies: scannerless parsers, parser combinators, parsing expression grammars and packrat parsers."
02:13:26 <zzo38> I know about recursive descent parsers
02:13:30 <zzo38> I don't know what is packrat parsers
02:14:39 <zzo38> Wikipedia article about "packrat parser" redirected to "parsing expression grammar".
02:16:16 <kmc> fungot parser
02:16:16 <fungot> kmc: bzip2 is slow, of course.
02:16:21 <kmc> fungot: of course.
02:16:22 <fungot> kmc: the cable doesn't bother me. lisp is shorter. people usually call " porting" gambit's web server? :) i'm implementing the cursors inside these structures partially with the postgresql c library. however, major dissidence isn't usually likely to be overtly malicious than to ddos :)
02:16:32 <fungot> Available: agora alice c64 ct darwin discworld enron europarl ff7 fisher fungot homestuck ic irc* iwcs jargon lovecraft nethack oots pa qwantz sms speeches ss wp youtube
02:18:48 -!- canaima_ has joined.
02:19:28 -!- tromp has quit (Remote host closed the connection).
02:20:04 -!- tromp has joined.
02:20:16 -!- canaima_ has quit (Client Quit).
02:24:02 <Bike> zzo38: i mean that the idea behind combinatory logic was "hey can we do lambda calculus w/o variables"
02:24:38 -!- tromp has quit (Ping timeout: 265 seconds).
02:24:47 <zzo38> Bike: Yes, I can see that, but it isn't what I meant.
02:25:31 <zzo38> I mean that you still have variables, but only quantified variables.
02:27:32 <Bike> isn't that the norm
02:27:46 <zzo38> The Wikipedia article about sequent calculus mentions the restrictions on the use of free and quantified variables; this can be avoided by not having any free variables.
02:29:39 <zzo38> The "forall R" and "exist L" rules would be changed, by instead of a free variable "y" made up above the line, it would make up a unique "free atom", which is one not allow to use anywhere else; each usage of the rule makes up a new one and it isn't an atom mentioned elsewhere in the sequent above the line.
03:05:43 -!- ^v has joined.
03:19:56 -!- nooodl_ has quit (Ping timeout: 240 seconds).
03:22:49 -!- shikhin has joined.
03:27:17 -!- tromp has joined.
03:38:51 -!- Sorella has quit (Quit: It is tiem!).
03:44:08 <zzo38> A lot of people don't believe me that in SQL, savepoints would be much more useful if allowed inside of a trigger program.
03:46:04 <Sgeo> Fuck continuation-based web development
03:46:59 <Sgeo> This site is practically unusable: http://bugs.pharo.org/
03:47:28 <Sgeo> Try navigating to a bug, then figuring out how to share a link with a friend
03:49:14 <Bike> http://bugs.pharo.org/issues/register/id/2058?_k=t5FQ1yAmItNRJSof let's see
03:49:55 <Sgeo> Bike: open that in an incognito window
03:50:02 <fowl> http://bugs.pharo.org/issues/register/id/7627?_k=LAzNiBTJSnR_WP0l
03:51:59 <zzo38> That is not the point of URLs and if you do not want URL of each file, don't use a webpage at all and just make a telnet or whatever.
03:58:35 <pikhq> How do you mess up a bug tracker that badly?
03:59:28 <kmc> `addquote <zzo38> That is not the point of URLs and if you do not want URL of each file, don't use a webpage at all and just make a telnet or whatever.
03:59:29 <HackEgo> 1194) <zzo38> That is not the point of URLs and if you do not want URL of each file, don't use a webpage at all and just make a telnet or whatever.
04:00:26 <Sgeo> pikhq: it's an anonymous frontend to a login-required bug tracker
04:04:58 <zzo38> Sgeo: What is the point of that?
04:05:20 <Sgeo> Of the horrible URLs, or of the site?
04:05:28 <Sgeo> It's good to not need to login to view bugs
04:05:29 <zzo38> Of an anonymous frontend to a login-required bug tracker.
04:05:52 <zzo38> In the way that that one is done.
04:07:04 <Sgeo> Pretty sure the use case is independent from the poor implementation choice
04:07:06 <Sgeo> I blame Seaside
04:07:51 <Sgeo> I think continuations have their uses in web development, but... not for this. Maybe during checking something out from an ecommerce site, or a password reset flow (although with the latter, need to be sure some idiot doesn't send the URL to a friend)
04:07:57 <Sgeo> (well, with both)
04:08:24 <zzo38> I think such thing is just all wrong.
04:09:54 <Sgeo> I assume this is not as terrible even though it's similar in development style
04:09:55 <Sgeo> http://www.impredicative.com/ur/demo/counter.html
04:09:59 <Sgeo> The URLs are much cleaner somehow
04:10:04 <Sgeo> But also easy to tamper with
04:10:08 <zzo38> Don't use webpages if you don't want their kind of state transactions; use them for non-interactive sessions instead. Interactive stuff can be including IRC, telnet, SSH, etc (and even block-oriented terminals, if necessary)
04:10:37 <Sgeo> http://www.impredicative.com/ur/demo/Demo/Counter/main
04:11:12 <zzo38> You can use an entirely stateless stuff if you need to, as well, which saves a lot of problem, too.
04:11:24 <zzo38> You don't need any cookie either, then.
04:11:31 <Sgeo> zzo38: sadly, users expect websites
04:11:49 <zzo38> You can make websites with stateless stuff too though
04:12:34 <Sgeo> Resetting a password seems tricky to do without some sort of state, unless you like messing with encryption
04:13:03 <Sgeo> hmm, bad example, I'm only really familiar with one example of a reset password flow
04:13:09 <zzo38> As far as I could see password reset usually used email though?
04:13:37 <Sgeo> zzo38: a reset password flow where first you answer questions or whatever before being allowed to send the email
04:13:42 <Sgeo> hypothetically
04:14:08 <zzo38> Sgeo: That isn't a problem either; you have HTML forms for that!
04:14:38 <Sgeo> How about logging into a website?
04:14:55 <zzo38> There is HTTP authentication.
04:15:06 -!- Froox has joined.
04:15:06 -!- Frooxius has quit (Read error: Connection reset by peer).
04:15:33 <zzo38> (Of course it isn't as secure as SSH, even if HTTPS is used)
04:21:46 <zzo38> And when you don't require these kind of things, you need no HTML, HTTP, SSH, SMTP, or whatever else; the gopher protocol is really simple and all stateless; there is no cookie or anything like that. Also, you don't have to make a separate "mobile version", or make other considerations about the user interface and so on;
04:22:18 <Bike> ide/theory: avoid having state by avoiding passwords by avoiding having information to secure
04:22:45 <zzo38> it works just as well with a keyboard, mouse, touch-screen, various sizes, hardcopy terminal, fax, punched cards, postal mail, or whatever else; without having to change anything.
04:23:00 <shachaf> wouldn't gopher be slower with postal mail
04:23:40 <zzo38> shachaf: Yes it would certainly be slower with postal mail, but that isn't the point at all.
04:24:11 <zzo38> Bike: Yes, in cases where you don't need a password, where you can do without a password and that stuff, it can.
04:25:00 <Bike> addendum: never need a password
04:26:39 <zzo38> When you do need a secure system, there are several ways. For example, require login over SSH. Or, you can encrypt the files and download it, and whoever has the password can use a decryption software to access it.
04:26:55 <Bike> whoa whoa whoa, didn't i just explain. don't need a secure system
04:27:23 <zzo38> If you don't need a secure system, then that is easy: ignore all of that stuff, and make more simplicity.
04:27:46 -!- augur has joined.
04:31:11 <Bike> also fun security fact, my job's secure login works over https, but also has an http address. it asks for credentials and takes them but then presents nothing if you use it
04:32:52 <kmc> it's really negligent to run a plaintext HTTP server that serves anything other than a redirect with an HSTS header
04:33:15 <Bike> i assume letting me enter my password over http is also bad
04:33:50 <Bike> thankfully, i'm the type of person who'd give up their password for a chocolate bar, so there's no net lowering of security in my using this system
04:34:17 <kmc> if you serve any part of your domain at all over plain HTTP -- even the boringest static terms of service page -- then an active attacker has arbitrary code execution for that whole subdomain and can substantially mess with the entire domain
04:34:33 <Bike> i'd ask them to fix it, but it took like three days with IT to get on in the first place so i'm not gonna bother
04:34:35 <kmc> a lot of web developers don't know this
04:34:44 <Bike> arbitrary, huh.
04:34:55 <kmc> yep, they can inject arbitrary javascript
04:35:17 <kmc> which has permission to read cookies for that domain, mess with same-origin windows, make same-origin requests etc
04:35:23 <zzo38> That is also a problem with HTTP and HTML in general. Even if you do use entirely HTTPS!
04:35:29 <Sgeo> kmc: can't read every cookie
04:35:34 <kmc> that's right Sgeo
04:35:40 <zzo38> Use SSH for secure login interactive sessions, and work much better.
04:35:45 <kmc> HttpOnly cookies are a weak protection though
04:35:56 <kmc> you can still make requests that will include that cookie
04:36:09 <shachaf> i imagine Sgeo meant Secure cookies
04:36:10 <kmc> it doesn't really matter because if you can inject JS then you can also sniff the cookie off the wire
04:36:18 <Bike> nice, the instructions have how to do it on XP
04:36:37 <Bike> "Because we use a newer file storage system at the College of Veterinary Medicine, older Mac operating systems cannot access Vetmed files. You will need Mac OS 10.6 (Snow Leopard) or software that allows for Mac-Windows interoperability, such as Thursby Software's Dave"
04:36:39 <kmc> in some cases you can overflow the cookie jar and replace the cookie with a non-Secure cookie on a broader domain
04:36:54 <Sgeo> kmc: as shachaf notes, can't read Secure HttpOnly cookies over the wire... but yeah, arbitrary requests to the real site
04:37:15 <shachaf> anyway, even just not serving anything over http isn't sufficient without something like hsts
04:38:42 <kmc> unfortunately, as you probably already know, computer security
04:38:46 <zzo38> You can still serve plain files over HTTP, and forms and stuff which are simple enough, but there are generally better ways in any case already.
04:40:21 <zzo38> Remember that there are other protocols, and HTTP can be used to fall-back-on, perhaps.
04:40:38 <zzo38> (There are also better ways of using HTTP than all those terrible ways, too, though.)
04:42:06 <shachaf> the trouble with fallbacks and security is that they have to be as secure as the not fallbackthings
04:42:24 <zzo38> Post a warning message.
04:42:32 <Bike> it's fun going back and forth from homomorphic encryption or whatever to My Daily Life
04:42:33 <zzo38> Disable some features if needed.
04:43:33 <zzo38> Write a warning message on the webpage that says that it is "deprecated" and insecure, and that you are offered to better alternatives if possible.
04:44:01 <shachaf> that only helps if the user sees the web page
04:44:23 <zzo38> That is true, of course.
04:44:50 <HackEgo> 113) <zzo38> Some people are reasonable, some people who are not reasonable insist on changing things so therefore progress depends on not reasonablepeple
04:44:56 <zzo38> But otherwise, if it consists of nothing then the problem corrects itself (giving you another problem, if you didn't already fix that one).
04:59:08 <HackEgo> danddreclist 51: shachaf nooodl boily \ http://zzo38computer.org/dnd/recording/level20.tex
05:03:12 <zzo38> Do you like this latest Dungeons&Dragons game by now?
05:03:34 <Bike> you'll never shine if you don't glow
05:04:14 <zzo38> But I don't glow either.
05:13:12 <HackEgo> [wiki] [[Stacked Brainfuck]] http://esolangs.org/w/index.php?diff=39483&oldid=32424 * Killer64 * (+0) USing -> Using
05:32:10 -!- ^v has quit (Read error: Connection reset by peer).
05:32:23 -!- ^v has joined.
05:36:11 -!- tertu has quit (Ping timeout: 276 seconds).
05:37:12 <coppro> someone familiar with category theory please confirm/deny: if F is a functor, the statement "F is injective on objects" is not preserved by natural isomorphism
05:38:58 <kmc> motherfunctor
05:40:33 <shachaf> e.g. if you have a category C with two isomorphic objects and two functors F, G : C -> C where F is the identity and G maps both objects to the first one (and arrows to the identity)
05:42:08 <myname> there should be "category theory for dummies"
05:42:50 <Bike> @google "category theory for dummies"
05:42:50 <lambdabot> http://homepages.inf.ed.ac.uk/jcheney/presentations/ct4d1.pdf
05:42:51 <lambdabot> Title: Category Theory for Dummies (I)
05:46:04 -!- MoALTz_ has joined.
05:49:03 -!- MoALTz__ has quit (Ping timeout: 250 seconds).
05:50:53 -!- tromp has quit (Remote host closed the connection).
05:51:28 -!- tromp has joined.
05:55:34 -!- tromp has quit (Ping timeout: 240 seconds).
05:58:50 <zzo38> Don't be so idiotic and play a DEFENDER card if it would be to your opponent's advantage for you to do so.
06:03:17 <zzo38> I was trying to think of use of necessity modal operator in Haskell, for example, to make the type specify only top-level values can be used (one way to do it is a class), and so on, would that be something like that?
06:03:54 <shachaf> What's with the error message "the connection was reset"?
06:05:44 <shachaf> Why is it shown to users in web browsers? Why not "closed" or "disconnected" or "aborted" or something? Are people expected to understand what "reset" means?
06:05:59 -!- Bike has quit (Ping timeout: 252 seconds).
06:09:43 <Sprocklem> shachaf: Reset is a normal english word
06:09:58 <Jafet> Are people expected to understand what "connection" means
06:10:19 <shachaf> What does this use of it have to do with the normal English use?
06:13:26 <Sprocklem> It does fit, though I suppose you are correct in that closed would be better
06:13:38 <lambdabot> *** "reset" wn "WordNet (r) 3.0 (2006)"
06:13:38 <lambdabot> n 1: device for resetting instruments or controls
06:13:38 <lambdabot> v 1: set anew; "They re-set the date on the clock"
06:13:38 <lambdabot> 2: set to zero; "reset instruments and dials"
06:13:40 <lambdabot> 3: adjust again after an initial failure [syn: {readjust},
06:13:55 <Jafet> The connection was set anew
06:13:58 <Jafet> The connection was set to zero
06:14:05 <Jafet> The connection was adjusted again after an initial failure
06:15:47 <Sprocklem> Jafet: You're right, it doesn't make sense
06:17:22 <Jafet> I suspect most people do not actually read any text once they see the chrome://global/skin/icons/warning-large.png
06:17:58 <Jafet> (Why a warning symbol is used for errors is another story)
06:20:31 <shachaf> "The webpage at chrome://global/skin/icons/warning-large.png might be temporarily down or it may have moved permanently to a new web address."
06:20:38 <shachaf> got me where i wanted anyway
06:22:34 -!- password2 has joined.
06:30:08 <password2> because someone registered password
06:33:42 <Sprocklem> Is there not a time period after which it becomes free?
06:34:04 -!- ^v has quit (Quit: http://i.imgur.com/Akc6r.gif).
06:36:34 <password2> aparently password was used once this year
06:37:52 <Jafet> Guess its password
07:36:46 -!- MoALTz_ has quit (Read error: Connection reset by peer).
07:37:33 -!- MoALTz_ has joined.
07:41:14 -!- impomatic has quit (Ping timeout: 258 seconds).
07:41:50 -!- zzo38 has quit (Ping timeout: 258 seconds).
07:43:48 -!- shikhout has joined.
07:44:18 -!- zzo38 has joined.
07:46:44 -!- shikhin has quit (Ping timeout: 245 seconds).
07:48:01 -!- edwardk_ has joined.
07:48:46 -!- AnotherTest has joined.
07:49:26 -!- edwardk has quit (Ping timeout: 276 seconds).
07:55:48 <kmc> big beats are the best, get high all the time
08:14:19 -!- quintopia has joined.
08:18:04 -!- nucular has joined.
08:18:04 -!- nucular has quit (Changing host).
08:18:05 -!- nucular has joined.
08:30:21 <mroman_> @tell Taneb http://eso.mroman.ch/ESOSC/ESOSC-2014-D2-R1.pdf
08:48:45 -!- oerjan has joined.
08:50:34 -!- Patashu_ has quit (Ping timeout: 240 seconds).
08:54:00 -!- tromp has joined.
08:57:00 <quintopia> oerjan: i finished norge. i brought a bottle of the linie aquavit but did not yet try it
08:58:19 -!- tromp has quit (Ping timeout: 252 seconds).
09:02:03 <ion> the Florida psychic Sheree Silver disassociated herself from the practice, telling the Sun-Sentinel, "I can't imagine anyone wasting their time and money on someone like this when there are so many legitimate psychics out there." https://en.wikipedia.org/wiki/Rumpology
09:08:18 -!- Phantom_Hoover has joined.
09:09:31 <mroman_> I wouldn't be interested in the future anyway unless I could change it
09:11:49 <ion> https://neocities.org/blog/the-fcc-is-now-rate-limited
09:20:23 <olsner> is the FCC doing a lot of surfing on neocities?
09:21:38 <ion> That isn’t really relevant.
09:23:07 -!- password2 has quit (Ping timeout: 250 seconds).
09:24:24 <oerjan> mroman_: the twist is that you _can_ change the future, but only if you don't know it hth
09:24:29 <mroman_> why does a democratic nation have a bureau responsible for censoring stuff?
09:25:21 <mroman_> so once a physic tells me my future it is carved in stone
09:25:28 <mroman_> wouldn't that give them supernatural power?
09:26:20 <oerjan> well most psychics don't actually know the future just potentialities hth
09:26:55 <mroman_> Why did I optimize the implementation of my algorithm for my bachelor thesis :(
09:26:59 <mroman_> that was sort of a stupid move to do
09:27:17 <oerjan> mroman_: you mean now you have nothing to do for your masters?
09:27:42 <mroman_> Now all my tons of measurements I did are obsolete.
09:28:24 <mroman_> and it's the last week of the bachelor thesis more or less
09:28:31 <mroman_> I've already documented and discussed my findings
09:28:39 <mroman_> and suddenly now everything is obsolete
09:31:31 <oerjan> do you mean someone beat you to it
09:31:47 * oerjan doesn't quite understand
09:32:17 <mroman_> You gotta write a bachelor thesis repot of around 50 pages
09:32:28 <mroman_> documenting your stuff, measurements and conclusions from the measurements
09:32:40 <mroman_> no, since I've optimized stuff like hell
09:33:00 <mroman_> all those conclusions are somewhat useless now
09:33:16 <mroman_> because I've got something better now that scales differently
09:33:36 <oerjan> ah so you beat _yourself_. tricky.
09:34:18 <mroman_> (also I'm pretty sure someone in the world already beats me anyway)
09:34:24 <mroman_> and I'm not doing a masters btw
09:34:25 <oerjan> yep, you clearly should have left that for the masters.
09:34:44 <mroman_> I'd want a master from a university
09:34:55 <mroman_> not the master I could do here
09:35:03 <oerjan> this isn't a university? ok.
09:35:38 * oerjan has a hunch it'll be called Hochschule
09:36:46 <oerjan> norway also has this sort of folkehøyskole system parallel and somewhat lower in status to the universities
09:38:00 <mroman_> they run under the slogan "different but equal" here
09:38:11 <mroman_> well... according to the "real" universities we're not equal ;)
09:38:20 <mroman_> and according to Hochschule we're equal but different
09:38:47 <oerjan> YOU ARE BREAKING LEIBNITZ RULE YOU INFIDELS
09:38:59 <oerjan> *LEIBNI... er let me look it up
09:40:11 -!- shikhout has changed nick to shikhin.
09:41:12 <oerjan> he also made several rules. someone should clean up the wikipedia redirections.
09:44:42 <oerjan> basically, the law that equal stuff has all properties in common.
09:45:07 <oerjan> which you can also formulate as the formal logical scheme a = b => (P a <=> P b)
09:48:11 <mroman_> I'm always confused with lemma, theorem and laws
09:48:33 <mroman_> Do you say "law" when it's really a "definition/axiom"?
09:49:59 <oerjan> looking at the philosophical mess "Leibniz's law" redirects to on wikipedia, i think the point is that leibniz wasn't really thinking about formal logic.
09:50:09 <oerjan> (not looking too closely, mind you)
09:50:37 <oerjan> although the formal scheme gets to be called the same thing by analogy.
09:51:03 <oerjan> and could in principle be used as the definition of equality.
09:52:16 <oerjan> some theorem proving systems might, but i vaguely recall some don't for technical reasons (impredicative types possibly)
09:52:17 <mroman_> That'd be the best definition of equality I know.
09:52:28 <mroman_> and probably the only one :)
09:53:36 <mroman_> but I don't know any definitions for a < b that'd hold
09:53:55 <mroman_> n < (n+1) isn't really a good definition at all
09:54:18 <oerjan> well = is a general logical principle but < refers to a particular order on a set
09:54:49 <oerjan> for reals you can use a <= b iff b-a is a square.
09:55:45 -!- password2 has joined.
09:55:50 <mroman_> because squares can't be negative
09:56:34 <oerjan> for naturals you can use a <= b iff b-a exists at all
09:57:28 <oerjan> (if you say, "but it exists as a negative number", then i will note that the real version also breaks if you include complex numbers)
09:57:59 <mroman_> there are no negative natural numbers
09:58:24 <mroman_> Why would I say it exists as a negative number :D
09:58:54 <oerjan> you might be quarrelsome and stupid like people usually are in these discussions on the internet hth
09:59:13 <oerjan> (HYPOTHETICALLY SPEAKING)
10:00:12 -!- conehead has quit (Quit: Textual IRC Client: www.textualapp.com).
10:00:18 <mroman_> I've had some discrete mathematics. Not much, but enough to know that in certain thingies certain other thingies just don't exist :)
10:00:40 <mroman_> I only know the german words for these things
10:02:53 <oerjan> for natural numbers, < as the transitive closure of n < (n+1) isn't that bad.
10:03:58 <oerjan> i recall that logicians / complexity theorists have investigated how much extra power you get from allowing transitive closure on an otherwise very weak logic
10:04:51 <oerjan> (i say / complexity theorists because it turns out that the smallest complexity classes have a strong correspondence with logic)
10:05:14 -!- KingOfKarlsruhe has joined.
10:11:14 <Taneb> mroman_, could we add a justification of the decisions made for second normal form to ESOSC 2014 D2?
10:16:57 <mroman_> oerjan: I'm doing crowd simulation as my bachelor thesis
10:17:16 <mroman_> or "distribute it to multiple machines" to be more specific.
10:17:31 <mroman_> It simulates 200k people in 11x realtime
10:17:40 <mroman_> I'm pretty sure somebody out there can do it in 0.1x realtime
10:21:29 <mroman_> Taneb: It's because they are "nops"?
10:21:35 <mroman_> and ][ is abused for comments
10:21:49 <mroman_> or what kind of justification did you have in mind?
10:22:34 <mroman_> although [...][foo] isn't first normal form
10:22:45 <mroman_> You only could have comments using brainfuck commands that way ;)
10:24:11 <oerjan> making comments in a language where no character can be included if it can be proved never to be executed sounds awkward.
10:24:49 <mroman_> Taneb: +- isn't a nop if cells don't wrap-around
10:25:17 <Taneb> And <> isn't a nop if cells are bounded on the left
10:26:21 <mroman_> so snf kinda assumes wrap-around
10:32:29 <Taneb> Is second normal form necessary? It's more like a linter than anything else
10:32:52 <mroman_> I don't see any benifit of having it
10:36:05 -!- KingOfKarlsruhe has quit (Read error: Connection timed out).
10:43:54 <mroman_> and judging by your question I assume it was nortti
10:46:17 -!- AnotherTest has quit (Ping timeout: 255 seconds).
10:46:22 <mroman_> but then it wouldn't make sence to have a "first" normal form
10:46:43 <mroman_> unless we're going to add one 5 years later or so
10:46:50 -!- password2 has quit (Ping timeout: 258 seconds).
10:47:34 <mroman_> ][ shouldn't assume wrap-around of any kind
10:48:35 -!- Patashu has joined.
10:49:38 -!- Patashu_ has joined.
10:49:38 -!- Patashu has quit (Disconnected by services).
10:58:51 <mroman_> http://eso.mroman.ch/ESOSC/ESOSC-2014-D2-R2.pdf <- well. I removed it for now
10:58:55 <mroman_> Suggestions still welcome :)
11:07:33 -!- Phantom_Hoover has quit (Ping timeout: 250 seconds).
11:08:10 <Taneb> mroman_, "Brainfuck" in both times in paragraph two should have a small b
11:08:39 <Taneb> In fact, whenever it's not at the start of a sentence or a heading (or possibly in "Normalized Brainfuck"?)
11:09:00 <mroman_> I thought names are writting with a starting capital letter
11:09:03 <Taneb> And instead of "interpreters (or compilers)", why not "implementations"
11:09:09 <Taneb> Brainfuck is weird
11:09:22 <Taneb> Look at its readme, for example
11:11:39 <mroman_> to ease interpretation of brainfuck programs
11:12:00 <mroman_> since compilers usually don't interpret them :)
11:12:49 <mroman_> to ease reading/handling/parsing?
11:13:33 <mroman_> to ease implementation of brainfuck programs?
11:13:56 <Taneb> parsing would be best
11:13:59 <mroman_> to ease writing brainfuck implementations?
11:14:11 <Taneb> I've got to go now
11:19:07 <FireFly> I think interpretation works
11:23:06 <nortti> mroman_: the one who suggested snf was b_jonas
11:31:11 -!- yorick has joined.
11:42:28 -!- Slereah_ has joined.
11:42:47 -!- Slereah has quit (Ping timeout: 276 seconds).
11:43:52 <oerjan> <kmc> if you serve any part of your domain at all over plain HTTP -- even the boringest static terms of service page -- then an active attacker has arbitrary code execution for that whole subdomain and can substantially mess with the entire domain
11:45:40 -!- drdanmaku has joined.
11:46:15 <oerjan> technically you don't need to serve anything as http do you? the attacker just needs to fool someone into _trying_ to load http from your domain?
11:46:57 <oerjan> which admittedly is probably somewhat easier if you have actual http pages.
11:50:52 <mroman_> b_jonas: 197133 to be precise
11:59:46 <mroman_> It can run 25k in about 1.1x realtime
12:02:27 <oerjan> @tell password2 (1) 15 weeks is the max upper limit for nick expiration (2) that particular nick actually goes under the special "not used more than 2 hours after registration" rule so expired after only 2 weeks. iow you can ask for it to be released.
12:04:56 <nortti> does that mean that its use time is not 2h, or that is was only used before 2h had passed from registration?
12:05:45 <Jafet> It can't be used more than two hours before two hours after registration
12:07:19 <Jafet> re https: if you live in a universe with compromised RAs -- even by the most bored iranian teenager -- it doesn't matter anyway
12:09:02 <Jafet> Some big websites even deliberately cycle multiple certificates, it's like they're asking for it
12:30:43 <mroman_> sadly I run out of memory with 1 Mio. people
12:48:45 -!- Sorella has joined.
13:02:34 <mroman_> CSS3 can do shadows, right?
13:03:04 -!- Dameon21 has joined.
13:05:37 <mroman_> but those browsers need some more of them anti-aliasing to make it look not terrible
13:10:27 -!- shikhout has joined.
13:13:14 -!- shikhin has quit (Ping timeout: 252 seconds).
13:15:29 -!- shikhin has joined.
13:18:44 -!- shikhout has quit (Ping timeout: 252 seconds).
13:22:38 -!- shikhout has joined.
13:22:52 -!- MindlessDrone has joined.
13:25:29 -!- shikhin has quit (Ping timeout: 245 seconds).
13:30:10 -!- Dameon21 has quit (Quit: Leaving).
13:32:54 <Taneb> Aaaaah my sideburns are asymettric
13:33:53 <mroman_> Taneb: http://eso.mroman.ch/ESOSC/
13:34:10 <mroman_> border-radius is kinda nice
13:34:34 <Taneb> Could you hyperlink "#esoteric" to webchat?
13:35:30 <mroman_> does that take an argument for channel?
13:35:35 <Taneb> http://webchat.freenode.net/?channels=esoteric
13:36:50 <b_jonas> Taneb: https://kiwiirc.com/client/irc.freenode.net/#esoteric
13:37:12 -!- test has joined.
13:37:28 -!- test has quit (Client Quit).
13:46:00 <mroman_> the ISO indeed makes money by selling pdfs
13:46:23 <olsner> Taneb: enjoy your lopsideburns
13:46:47 -!- impomatic has joined.
13:52:10 -!- shikhout has changed nick to shikhin.
14:10:00 <FireFly> mroman_: how many committees and subcommittees does ESOSC have?
14:12:42 <mroman_> would you like to be in one?
14:13:53 <HackEgo> esosc is esoteric song contest (also Esoteric Standard Committee)
14:13:55 <mroman_> impomatic: http://eso.mroman.ch/ESOSC/
14:18:17 -!- shikhout has joined.
14:18:29 <mroman_> I think the EsoAPI needs a revival
14:19:23 <nortti> maybe a version that isn't dependant on cell-based langs?
14:19:58 -!- tertu has joined.
14:21:13 <FireFly> A standardised, improved esoAPI would be neat
14:21:17 -!- shikhin has quit (Ping timeout: 264 seconds).
14:22:07 <nortti> also, a file-based disk-io instead of sector-based would be neat
14:29:40 -!- nooodl_ has joined.
14:30:14 -!- nooodl_ has changed nick to nooodl.
14:37:57 -!- tromp has joined.
14:39:59 -!- shikhin has joined.
14:42:34 -!- shikhout has quit (Ping timeout: 245 seconds).
14:45:28 -!- oerjan has quit (Quit: leaving).
14:53:20 -!- Patashu_ has quit (Ping timeout: 252 seconds).
14:54:18 <mroman_> Did the EsoAPI hook stdout/stdin?
14:55:53 <mroman_> upcoming ESOSC-2014-D3 is EsoAPI Revised :)
14:58:45 <nortti> wasn't D3 brainfuck conventions?
14:59:23 <mroman_> ESOSC-2014-D4: Esoteric System Interface (ESIX)
15:02:27 <fizzie> A guy from the IEEE Signal Processing Society Audio and Acoustic Signal Processing Technical Committee Challenges Subcommittee just said a few words.
15:05:36 <FireFly> That's what I'm saying, ESOSC needs more {,sub}committees
15:06:02 <FireFly> fizzie: did he present himself using that title?
15:06:58 <mroman_> If you have an idea for a subcommittee and if you want to work in it just say so ;)
15:07:11 <mroman_> I'm btw. not really fond of APIs through stdin/stdout
15:07:31 <mroman_> except for that they are portable across languages and don't require any change in them
15:07:39 <mroman_> it looks kinda inconvenient
15:08:08 <mroman_> but PSOX looks kinda feature-rich
15:09:36 <FireFly> Wouldn't it be Esoteric Standard*s* Committee?
15:10:06 <int-e> FireFly: It's a good idea to start out small.
15:10:27 <FireFly> I guess you could call it the standard standards committee
15:11:20 <fizzie> Also weird: conference proceedings on an USB stick that pretends to be both a USB mass storage device and an external CD ROM drive.
15:11:48 <fizzie> I think the latter was read-only.
15:12:04 <int-e> that's fine but not very original
15:12:14 <FireFly> I can't think of any reason for the latter..
15:13:14 <int-e> FireFly: recall the floppy disks that had a notch that could be covered to make them read-only?
15:13:18 <fizzie> The "CD" had all the data and the stick was empty.
15:13:46 <FireFly> "the latter" as in pretending to be an external CD-ROM drive
15:14:06 <int-e> So that would be a sensible use for such a setup to me, hardware level write protection.
15:14:12 <fizzie> Maybe it autoruns better.
15:14:23 -!- stuntaneous has joined.
15:14:26 -!- stuntaneous has quit (Excess Flood).
15:14:47 -!- stuntaneous has joined.
15:14:49 -!- stuntaneous has quit (Excess Flood).
15:15:04 <int-e> Yeah. I've seen that, putting drivers on a USB "CD" drive.
15:15:15 <int-e> But what is that idea doing at a conference?!
15:17:19 <fizzie> I have a USB 3G/GPRS stick that has a built-in "driver CD", of course with hopelessly outdated drivers.
15:28:36 -!- shikhout has joined.
15:29:04 -!- idris-bot has quit (Quit: Terminated).
15:29:18 -!- idris-bot has joined.
15:31:44 -!- shikhin has quit (Ping timeout: 245 seconds).
15:42:20 -!- shikhin has joined.
15:45:17 -!- shikhout has quit (Ping timeout: 264 seconds).
15:45:26 -!- password2 has joined.
15:55:48 -!- conehead has joined.
16:03:11 -!- password2 has quit (Ping timeout: 252 seconds).
16:03:34 -!- conehead has quit (Disconnected by services).
16:04:37 -!- shikhout has joined.
16:05:36 -!- conehead_ has joined.
16:07:41 -!- shikhin has quit (Ping timeout: 258 seconds).
16:09:08 -!- shikhout has changed nick to shikhin.
16:09:17 -!- shikhin has changed nick to inshikhin.
16:10:30 -!- inshikhin has changed nick to shikhin.
16:15:15 -!- conehead_ has quit (Changing host).
16:15:15 -!- conehead_ has joined.
16:20:57 -!- conehead_ has changed nick to conehead.
16:22:56 -!- shikhin has quit (Ping timeout: 276 seconds).
16:24:08 -!- shikhin has joined.
16:25:26 -!- password2 has joined.
16:28:06 -!- quelqun_dautre has joined.
16:36:09 -!- shikhout has joined.
16:39:17 -!- shikhin has quit (Ping timeout: 264 seconds).
16:40:06 -!- yorick has quit (Remote host closed the connection).
16:49:36 -!- shikhin has joined.
16:52:18 -!- shikhout has quit (Ping timeout: 240 seconds).
16:53:08 -!- tromp has quit (Remote host closed the connection).
16:53:21 -!- tromp has joined.
16:53:38 -!- ^v has joined.
16:55:21 -!- tromp__ has joined.
16:57:59 -!- tromp has quit (Ping timeout: 255 seconds).
16:59:40 -!- edwardk has joined.
16:59:57 -!- edwardk_ has quit (Ping timeout: 265 seconds).
17:13:48 <HackEgo> [wiki] [[Rasen]] M http://esolangs.org/w/index.php?diff=39484&oldid=39478 * Wolgr * (-42)
17:23:10 <HackEgo> [wiki] [[Rasen]] http://esolangs.org/w/index.php?diff=39485&oldid=39484 * Wolgr * (-61)
17:25:42 -!- Bike has joined.
17:31:50 -!- augur has quit (Ping timeout: 276 seconds).
17:48:24 -!- augur has joined.
17:51:45 -!- shikhout has joined.
17:54:18 -!- shikhin has quit (Ping timeout: 240 seconds).
17:56:47 -!- shikhin has joined.
17:59:01 -!- MoALTz__ has joined.
17:59:18 -!- shikhout has quit (Ping timeout: 240 seconds).
18:01:22 -!- MoALTz has joined.
18:02:05 -!- MoALTz_ has quit (Ping timeout: 252 seconds).
18:04:25 -!- MoALTz__ has quit (Ping timeout: 250 seconds).
18:06:53 -!- tertu has quit (Ping timeout: 264 seconds).
18:09:35 <mroman_> It's hard to balance simplicity, compilability and mightibility
18:09:55 <Bike> i recommend bonghits
18:10:14 <mroman_> I'm trying to boostrap a self-hosting compiler
18:10:26 <mroman_> (with a language I'll invent)
18:10:48 <scoofy> the simpler the language, the easier to compile
18:10:55 <scoofy> the simpler the language, the harder to make a compiler
18:10:58 <mroman_> my last try even had a typesystem
18:11:13 <mroman_> simpler language, simpler compiler *my opinion*
18:11:20 <mroman_> brainfuck's easy to compile
18:11:26 <mroman_> but writing a brainfuck compiler in brainfuck
18:11:30 <scoofy> the simpler the language, the harder to write a compiler in
18:11:40 <kmc> write a brainfuck to brainfuck compiler in brainfuck
18:11:53 <mroman_> that produces brainfuck code
18:12:18 <tromp_> writing a blc interpreter in blc is straightforward though
18:12:32 <tromp_> because blc is much more expressive than brainfuck
18:12:48 <scoofy> that is, binary lambda calculus?
18:13:03 <kmc> best lambda calculus
18:13:09 <Bike> bonghit lambda calculus
18:13:37 <tromp_> of course it can't be too hard given that it takes under 26 bytes
18:14:02 <scoofy> tromp_, i've seen your web page about it, looks very interesting. except i barely understand anything :/
18:14:25 <scoofy> i'd first need to learn and understand well lambda calculus
18:14:38 <tromp_> the wikipedia article should make a good introduction
18:14:47 <tromp_> then you can dive into my paper
18:15:29 <scoofy> i skimmed through it, what I like the most about it is the images. i find it fascinating to represent programs as graphs
18:15:52 <tromp_> yes, they're quite artistic
18:16:40 -!- shikhin has quit (Read error: Connection reset by peer).
18:16:40 <Bike> to mock a mockinggraph
18:17:00 -!- shikhin has joined.
18:17:08 <tromp_> i have a big print of the predecessor function adorning my office wall
18:17:29 <tromp_> easily mistaken for modern art
18:17:51 <tromp_> http://homepages.cwi.nl/~tromp/cl/diagrams.html
18:19:45 -!- tromp__ has quit (Remote host closed the connection).
18:20:20 -!- tromp has joined.
18:21:27 <kmc> are these always unambiguous?
18:22:01 <tromp_> the haskell programs on my blc page create these images
18:22:22 <tromp_> eg. png, ascii, ascii graphics...
18:22:38 <kmc> do you have an interpreter which takes an image as input
18:23:13 <tromp_> the image is quadratic in the size of the term
18:23:29 <scoofy> i remember something about blc used in studying program complexity. is blc the most compact representation of an algorith?
18:23:54 <tromp_> that's impossible to formalize, scoofy
18:24:27 <tromp_> it certainly hits a sweet spot in simlicity and expressiveness
18:24:36 * Taneb --> Eurovision party
18:24:46 <scoofy> but your blc interpreter is the smallest turing-compatible self-impreter, iirc
18:24:53 <tromp_> and i haven't seen any competitive alternative
18:24:55 -!- tromp has quit (Ping timeout: 258 seconds).
18:25:21 <tromp_> it's the smallest "honest" one
18:25:36 <tromp_> but again that's hard to formalize
18:25:54 <scoofy> i wonder about its performance. is the blc interpreter fast enough to make it sensible to run complex programs in it?
18:25:59 <tromp_> many languages have primitives that vastly simply self interpretation
18:27:12 <tromp_> the interpreter introduces little overhead
18:27:36 <tromp_> so it could be very fast depending on the underlying reduction engine
18:27:55 <scoofy> so, in theory, it could be used for program compression?
18:28:16 <scoofy> creating very small programs is an interesting field
18:28:19 <tromp_> what programs do you have in mind?
18:28:37 <tromp_> it's hard because blc has no data primitives
18:28:47 <tromp_> no numbers, no nothing
18:28:56 <tromp_> just function application
18:29:31 <tromp_> also (optimal) compression is uncomputale
18:30:17 <scoofy> so... how would one start writing a blc program?
18:30:23 <tromp_> creating small blc programs (like the 1267 bit prime sieve) is a huge challenge
18:30:41 <Bike> presumably you can represent data same way as you do in good ol lambda calculus.
18:31:48 <tromp_> http://www.ioccc.org/2012/tromp/hint.html for some interesting sample programs
18:32:00 <scoofy> to me, writing blc looks like writing unlambda
18:32:18 <tromp_> the 8-bit self-interpreter represents bytes as length-8 lists of booleans
18:32:40 <tromp_> which is also used in the brainfuck interpreter
18:33:47 <tromp_> indeed blc is pure lambda calculus
18:33:56 <tromp_> with some binary IO conventions
18:36:05 <mroman_> http://codepad.org/XdQlMQwP <- so far I've come up with something like this now
18:36:44 <nortti> is the list stored as (1 2 3 4 5 6 7 8) or (1 2 3 4 5 6 7 . 8) ?
18:37:30 <nortti> (assuming it uses \xyf.fxy to construct the list)
18:38:06 <tromp_> as b7:b6:b5:b4:b3:b2:b1:b0:nil
18:38:07 -!- shikhout has joined.
18:38:38 <tromp_> where : is infix \xyf.fxy
18:39:49 <nortti> is nil False or the other possible nil?
18:40:13 <tromp_> yes, bil = false = \xy.y
18:40:43 <tromp_> b7 is the most significant bit yes
18:40:58 -!- shikhin has quit (Ping timeout: 240 seconds).
18:41:53 -!- scoofy has quit (Read error: Connection reset by peer).
18:43:20 -!- scoofy has joined.
18:43:36 <scoofy> i ran the primes.blc program and it locked up my computer. had to hardreset
18:44:14 <tromp_> yes, it warns about that. only take the first 300 or so bits of output
18:44:28 <scoofy> didn't read that warning :/
18:44:41 <scoofy> well, it printed about 10 lines of results fine
18:45:10 <tromp_> the c-program can do over a thousand bits
18:45:22 <scoofy> what happens after that?
18:45:24 -!- tertu has joined.
18:45:33 <scoofy> how did it bring a linux to knees?
18:45:34 <tromp_> it starts eating up your swap space:)
18:45:46 <tromp_> by allocating memory at insane rate
18:45:49 <scoofy> so it eats up all memory, i guess...
18:45:56 <Bike> that doesn't seem terribly efficient
18:46:14 <nortti> unary arithmetic is usually not
18:46:25 <tromp_> that's the price to pay for the shortest prime sieve program
18:46:35 <zzo38> I had a idea about another kind of modal logic operator, which is a "loop modality", which is always a theorem regardless what it is applied to.
18:46:38 <tromp_> it doesnt use any arithmetic
18:46:48 <zzo38> Maybe someone does something similar?
18:48:12 -!- password2 has quit (Ping timeout: 252 seconds).
18:52:35 <scoofy> hilbert.Blc works fine
18:57:42 <tromp_> going for a stroll; cul8r
18:57:58 -!- shikhin has joined.
18:58:20 <kmc> wouldn't BLC be more compact if the de bruijn indices weren't unary?
18:58:37 <nortti> yes, but also harder to encode
18:59:41 <kmc> harder to write a universal machine?
19:00:24 -!- shikhout has quit (Ping timeout: 255 seconds).
19:06:04 <Jafet> Not using unary has overhead, too
19:07:23 -!- shikhin has quit (Ping timeout: 276 seconds).
19:08:38 <Jafet> How about using unary, but with a bias, so the numbering starts below zero
19:08:58 <Jafet> This makes it easier to refer to variables at some fixed distance to the current scope
19:09:02 <nortti> how would one even do that?
19:10:37 <nortti> I mean, how do you represent a negative num in unary without sign symbol, in which case it is better to just use binary
19:14:47 <tromp_> unary indices are close to optimal
19:14:49 -!- ^v has quit (Read error: Connection reset by peer).
19:15:02 <tromp_> because larger indices occur much less frequently
19:15:17 -!- ^v has joined.
19:15:21 <tromp_> technically, you don't even need any index > 2
19:16:12 <nortti> is there some TC combinator system that only uses 2-arg combinators?
19:17:11 <Jafet> Some guy schoenfinkel made one
19:17:41 <tromp_> no, i think you need some 3 arg comb to construct S
19:18:04 <lambdabot> Monad m => m (a -> b) -> m a -> m b
19:18:51 <Jafet> Ok, bckw isn't one either
19:19:06 <nortti> tromp_: won't you need index 3, then?
19:19:39 <tromp_> you need indices 0,1,2 or 1,2,3 :)
19:20:01 <tromp_> i sometimes start from 0, sometimes from 1
19:20:39 <tromp_> on that page i start with 1, so yes i need 3 then
19:21:19 <nortti> oh, I see. I start from 1 since the first index in BLC is 10
19:21:44 -!- shikhin has joined.
19:23:05 -!- MindlessDrone has quit (Quit: MindlessDrone).
19:27:21 -!- shikhout has joined.
19:30:18 -!- shikhin has quit (Ping timeout: 240 seconds).
19:31:49 <scoofy> hm, i think i'm starting to understand it. so the 3 elements are: 'lambda', 'apply', and an index
19:34:15 <int-e> 00=apply, 01=lambda, 1(1*)0=index *.
19:34:39 <int-e> no, 00=lambda, 01=apply.
19:35:30 <int-e> I forgot about the \io trick, so the first thing in the primes program is actually a lambda.
19:35:40 <Bike> wait, so 1110 is index 2?
19:35:43 <tromp_> yes, the prime program on http://homepages.cwi.nl/~tromp/cl/cl.html is color coded that way
19:35:50 <Bike> oh, so you can do zero, ok
19:35:58 <scoofy> amazing that anything can be expressed in terms of that 3 things.
19:36:02 <int-e> Bike: yes, I count from zero.
19:36:06 <tromp_> lambda in red, apply in green, vars in blue
19:36:15 <scoofy> color coding is fun :)
19:36:32 <Bike> oh, the graphic notation is cute
19:36:35 <scoofy> good that you mention that, because I didn't notice
19:36:43 <nortti> alternativell 3-symbol system would be binary combinatory logic, although that is bit of pita to program in
19:36:59 <HackEgo> [wiki] [[Forobj]] N http://esolangs.org/w/index.php?oldid=39486 * GermanyBoy * (+6678) Created page with "'''Forobj''' is an object oriented programming language. It is designed to be easily extendable. == Overview == Forobj is a stack-based language. A program is a list of comm..."
19:37:57 <HackEgo> [wiki] [[Language list]] http://esolangs.org/w/index.php?diff=39487&oldid=39456 * GermanyBoy * (+13) /* F */
19:38:08 <fowl> is there a project name generator on the fungot
19:38:09 <fungot> fowl: not at all related to network fd readiness is dependent on fnord i got from the lists.
19:39:07 <Bike> network fd readiness
19:39:13 <nortti> also, real fast nora's hair saloon 3: sheer disaster download to bcl can be done with APPLY->01, LAMBDA->00, ONE MORE THAN->1, ZERO->10
19:39:24 <b_jonas> Bike: he fd to means regular files on network filesystems
19:40:59 <Bike> is that right, fungot
19:41:01 <fungot> Bike: and it fnord. :) :) 3 :) at least for emacs users.
19:41:33 <b_jonas> fungot, what's your favourite language?
19:41:36 <fungot> b_jonas: http://en.wikipedia.org/ wiki/ fnord), and have vector-like-shuffler return a procedure from a symbol.
19:42:52 <HackEgo> [wiki] [[Forobj]] http://esolangs.org/w/index.php?diff=39488&oldid=39486 * GermanyBoy * (+240)
19:44:49 <HackEgo> [wiki] [[Forobj]] M http://esolangs.org/w/index.php?diff=39489&oldid=39488 * GermanyBoy * (-1)
19:45:00 <Sgeo> "Nuke OPENSSL_NO_SOCK since any half sane operating system has sockets."
19:45:14 <Sgeo> ...why would OpenSSL even be used on a no socket system?
19:45:19 <Sgeo> Oh, I guess key generation?
19:45:25 <Sgeo> and other utilities?
19:46:08 -!- hk3380 has joined.
19:46:49 <HackEgo> [wiki] [[Forobj]] http://esolangs.org/w/index.php?diff=39490&oldid=39489 * GermanyBoy * (+98)
19:47:27 <olsner> there's probably some nut out there who thinks that to get a real secure system you can't just disconnect it, you also have to patch the kernel and libc to remove the socket syscalls
19:47:56 <nortti> or someone who uses STREAMS
19:48:59 <Jafet> For every nut there are ten sysadmins who have to do the same thing because some bureaucrat said so
19:50:12 <Jafet> Are there actually any two-variable universal combinators?
19:50:42 <kmc> Sgeo: the crypto algorithm implementations maybe
19:52:08 <olsner> oh, and there should be plenty of systems where there are sockets, but they just don't look anything like bsd sockets
19:53:42 -!- MoALTz has quit (Quit: Leaving).
19:53:54 <Sgeo> http://insanecoding.blogspot.ro/2014/04/common-libressl-porting-mistakes.html
19:54:49 -!- ^v has quit (Read error: Connection reset by peer).
19:55:15 -!- ^v has joined.
19:55:35 <Jafet> Well, you'd expect bsd programmers to assume bsd sockets.
19:55:56 -!- tromp has joined.
20:07:20 <kmc> olsner: which?
20:08:34 <olsner> http://en.wikipedia.org/wiki/Binary_Runtime_Environment_for_Wireless is one that I know of
20:10:00 <Jafet> (Though openssl probably has a winsock backend)
20:10:36 <olsner> winsock's socket api is very close to bsd sockets though
20:12:39 -!- FreeFull has quit.
20:17:44 -!- ais523_ has joined.
20:19:06 -!- AnotherTest has joined.
20:32:43 * Sgeo goes to read http://insanecoding.blogspot.com/2014/02/http-308-incompetence-expected.html
20:36:47 <Sgeo> I thought HTTP2 was supposed to be about the delivery, not header and status semantics
20:37:31 <Bike> electric boogaloo
20:38:19 <olsner> I also thought it was supposed to, but things wouldn't be very web if they made sense
20:44:01 <zzo38> The way to fix it, I think, would be to make the server check if HTTP2 is specified, and whether or not it is, post a "deprecated" notice mentioning all of these problems, and that you either need to fix your client or connect using an alternate protocol.
20:44:26 <olsner> Sgeo: hmm, looks like that post is not correct
20:44:55 <olsner> e.g. 301 was *specified* some different way earlier, but never actually used in that manner
20:44:58 <zzo38> The way they describe is certainly too much more stupid, so one thing you can do is, check for HTTP2 and then complain
20:45:45 <Sgeo> zzo38: olsner (and a comment on that page) is saying that the older spec didn't describe reality, and the HTTP2 change is meant to describe the current reality of what browsers actually do
20:45:49 <zzo38> Furthermore, don't use those codes if they cause problems.
20:46:39 -!- FreeFull has joined.
20:46:39 <zzo38> Sgeo: Perhaps, but they are probably both wrong. Especially if an unusual browser program is in use, or some other program such as wget is in use.
20:47:20 -!- edwardk has quit (Quit: Computer has gone to sleep.).
20:47:55 <Sgeo> Everything web is wrong
20:48:00 <nortti> still, reuse of already-existing code is a bad thing
20:49:04 <olsner> Sgeo: I think the upcoming HTTP/1.1-bis RFCs are the best description of current reality, the original HTTP/1.1 (RFC 2616) has some differences
20:49:07 -!- ^v has quit (Read error: Connection reset by peer).
20:49:34 -!- ^v has joined.
20:49:46 <olsner> hmm, and those RFCs might be what he calls HTTP/2
20:49:52 <Bike> we're naming standards with chem terms now?
20:49:58 <zzo38> Also, Google's servers do not even correctly implement the existing HTTP. Headerless requests will still respond with a header, and HEAD requests will sometimes return a 404 error even though a GET to the same file works.
20:51:38 <olsner> httpbis is a working group, HTTP/1.1-bis is something I made up because I don't know what they're really called
20:52:05 <Bike> well, that's still bis then.
20:54:06 -!- oerjan has joined.
20:54:49 <kmc> i still love that the IETF mailing list about random number generation is named dsfjdssdfsd
20:57:24 * ais523_ goes on proggit and tries to correct some misconceptions about US copyright law
20:57:34 <ais523_> lots of people think that creating anything similar to someone else's API is now illegal
20:57:53 <ais523_> whereas the court decision was that you need a fair use reason to be able to copy function declarations literally
20:58:16 <ais523_> there is a huge amount of grey area in between, such as if you reimplement someone else's API but write the function declarations yourself
20:59:11 <kmc> * ais523_ goes on proggit <-- noo you have so much to live for
21:01:29 <FireFly> What would the difference be between copying function declarations literally and reimplementing an API but writing the function declarations yourself?
21:02:14 <FireFly> Choice of parameter name is the only thing I can imagine, but that seems a bit.. thin
21:02:44 <Jafet> Legality, of course.
21:03:56 <ais523_> FireFly: the first involves copying them, the latter doesn't, and copyright is about copying
21:03:57 -!- Froox has quit (Quit: *bubbles away*).
21:04:20 <ais523_> the court actually said that copyright law was hard to apply to software, they described it like trying to solve a jigsaw where the pieces don't fit together properly
21:04:37 <FireFly> Oh, okay, so it's purely about the act of copying
21:04:38 <ais523_> in the latter case, you didn't copy the API, even if you happen to independently choose the same variable names
21:04:45 <ais523_> err, didn't copy the declarations
21:04:54 <ais523_> you did copy the API, if you did it based on API docs, but that's more abstract
21:05:02 <ais523_> if you go even further, and, say, reverse-engineer the machine code
21:05:09 <ais523_> then there's even less copying involved
21:05:16 <mroman_> In switzerland reverse-enginerring is allowed
21:05:19 <ais523_> (the court explicitly said they weren't making a ruling about reverse-engineering)
21:05:25 <FireFly> So if I implement someone else's API and by chance happen to choose the same parameter names (i.e. the source code of the two declarations is identical, modulo whitespace) I should still be safe, I guess
21:05:27 <mroman_> if you do it for interopability reasons
21:05:30 <ais523_> mroman_: in the US it's historically been found to be fair use
21:05:48 <ais523_> unless they can argue that you remembered the names from seeing their API docs, or something
21:05:55 <mroman_> I.e you would be allowed to reverse engineer a proprietary format so your software can export to it
21:06:10 <ais523_> most of the precedents come from DRM on games consoles
21:06:13 <FireFly> I guess that wouldn't hold for overly general and "obvious" names
21:06:14 <mroman_> You are also allowed to "copy" someone else's software by writing the same software yourself
21:06:28 <ais523_> FireFly: actually, the judgement wasn't that it holds for any particular name, but for a large collection
21:06:37 <mroman_> (which requires that you write it yourself, stealing their code is illegal of course)
21:06:48 <ais523_> like, it's OK to have a Math.max, so long as much of the rest of your API is different
21:06:54 <mroman_> of course, there's a lot of gray and black area there
21:06:59 -!- Frooxius has joined.
21:07:02 <mroman_> there are design patents and stuff and shit
21:07:03 <Jafet> Looking forward to the oddly-named parameter names that are copyright traps
21:07:28 <ais523_> Jafet: haha, that would actually work, I think
21:07:39 <mroman_> ironically databases aren't protected by copyright laws
21:08:15 <mroman_> unless it is really special
21:08:22 <Jafet> That depends on the jurisdiction.
21:08:36 <Jafet> (And what kind of database)
21:08:51 <mroman_> A pure collection of data isn't worthy of copyright apparentely
21:09:41 <ais523_> this reminds me of the ruling that if you digitize a public domain work precisely enough (i.e. no creativity involved), the resulting digitization is also public domain
21:09:54 <mroman_> I had a semester "IT laws"
21:09:58 <ais523_> (whereas things like performing a public domain piece of music produce a copyrightable recording, because there's creativity in the way you perform it)
21:10:08 <mroman_> and what I've learned is: Nobody really knows what exactly is legal or illegal
21:10:15 <ais523_> mroman_: yeah, that seems about right
21:10:16 <mroman_> and you won't be sure unless a judge rules over it
21:10:21 <ais523_> except when a judge has ruled about it
21:10:31 <mroman_> It's like schrodingers cats
21:10:43 <mroman_> You don't know if what you're doing is illegal until a judge looks at it ;)
21:10:46 <ais523_> e.g. the only precedent we have about open source licenses in the US is that if there's an attribution requirement in the license, you can't reuse the work without attribution
21:10:58 <ais523_> that was a case where someone violated the Artistic License on model train controllers
21:11:19 <ais523_> but if they had given attribution, who knows? they were violating the license in other ways, but courts only care about determining that the license was broken
21:11:47 <Jafet> Even then, you don't really know until you bring it up with the appellate court or the relevant legislative body.
21:12:14 <mroman_> hypothetical scenarios are intentionally left open for law books (that cost 100$ and more) and for law students
21:13:12 <mroman_> of course, "you never know" holds for all kinds of other laws too
21:13:31 <mroman_> There's no official department where you can call for free and ask about what you intend to do is illegal or legal
21:13:41 <mroman_> and if the guy from that department says it's legal it REALLY is LEGAL.
21:14:12 <mroman_> and lawyers aren't really allowed to say "it's legal" too ;)
21:14:46 <ais523_> or at least, they are, just daren't
21:14:51 <ais523_> because they don't really know any better than anyone else does
21:15:08 <ais523_> I think there's a decent random factor in court decisions
21:15:28 <ais523_> given how it depends on the lawyers that the sides have, who decides to submit an amicus brief, which judge is assigned, etc.
21:15:58 <mroman_> but the real problem is that you can't have a judge rule in *advance*
21:16:21 <mroman_> even if his decision were a little bit random... at least you know
21:17:00 <ais523_> you can in cases where you can show there's a real risk of being sued over something
21:17:01 <mroman_> That's a general weakness of our law system I think
21:17:15 <mroman_> just by registering a domain I'm one foot in a court
21:17:34 <ais523_> basically, if someone's making legal threats and not going through with them, you can effectively sue yourself to clear your name
21:17:43 <mroman_> There's nobody who can tell me conclusively if I'm allowed to register "mroman.ch"
21:18:57 <mroman_> I can do some database trademark searches
21:19:07 <mroman_> which aren't a 100% guarantee
21:19:13 <Jafet> I don't know any place in the world where registering domain names that are claimed by others is illegal
21:19:17 <mroman_> You just gotta register it anyway and hope nobody's gonna sue you
21:19:39 <mroman_> Jafet: It is in swizterland
21:19:48 <mroman_> You can't register a domain with "coca cola" in it
21:19:54 <ais523_> the vast majority of cases, if someone else does own the trademark, they'll settle rather than sue if you offer to give them the domain
21:19:57 <ais523_> although you can't rely on that
21:22:03 <mroman_> for a opensource tool you wrote as a hobby
21:22:13 <mroman_> but you'll never know if somebody patented such a design
21:22:36 <mroman_> even if you pay patent researches
21:22:44 <mroman_> they can't tell you for *really* sure
21:23:14 <ion> http://www.usacryptocoins.com/thecryptocurrencytimes/uncategorized/dafuq-coin-the-first-malware-coin/
21:23:19 <mroman_> (and as I imagine the US with even more crazier software patents...
21:23:34 <mroman_> I imagine it's probably illegal for any US citizen to write software)
21:23:48 <Jafet> Hmm, parking domains is actually illegal in amurica now
21:23:52 <kmc> ion: looooool
21:25:01 <ais523_> mroman_: oh, I thought that was probably illegal a while ago
21:25:05 <Jafet> mroman: fortunately most patents are fairly easy to work around.
21:25:14 <ais523_> or maybe theoretically possible, but it's like the problem of trying to write a bug-free hello world
21:25:18 <ais523_> it takes a huge amount of effort
21:25:19 <HackEgo> timcoin braulcafoarkulcoin plaincoin 305070coin rfectealcoin stracoin slmcoin @!coin opcrcoin parcoin orgertinoplincoin yencoin physixcoin famadncoin negringhaetacoin unacoin poicoin hypejocoin ming-boocoin huntingcoin
21:25:27 <ais523_> who put a rainbow on coins?
21:25:36 <ais523_> or has that always been there and I just never noticed due to filtering colors in the client?
21:25:47 <Bike> ion: goddamn amazing
21:26:56 <Jafet> "[...] thanks to the investigative work of the owner of Bittrex, who was about to add Dafuq Coin to his exchange"
21:27:38 <fowl> i cant wait until "finnsta" becomes standard american english
21:28:00 <ion> Finnish gangsta?
21:28:04 <olsner> ais523_: fairly recent addition
21:28:20 <ion> `cat bin/coins
21:28:20 <HackEgo> words ${1---eng-1M --esolangs 20} | sed -re 's/( |$)/coin\1/g' | rainwords
21:28:50 <olsner> `coins --finnish --esolangs 10
21:28:51 <HackEgo> @!coin 0x29acoin bdacal-xcoin insäcoin räisepolkcoin fundexcoin korecoin saancoin oikkalittercoin pohjuksencoin
21:29:13 <nortti> "saancoin" sounds funny
21:30:16 -!- AnotherTest has quit (Quit: ZNC - http://znc.in).
21:33:32 <HackEgo> changeset: 4627:64a2d83fa108 \ user: HackBot \ date: Sun May 04 18:20:25 2014 +0000 \ summary: <kmc> echo "words \\${1---eng-1M --esolangs 20} | sed -re \'s/( |$)/coin\\1/g\' | rainwords" > bin/coins \ \ changeset: 4531:7f957c1f4661 \ user: HackBot \ date: Sun Mar 16 01:52:15 2014 +0000 \ summary: <oerjan> r
21:34:03 <FireFly> `run hg log bin/coins | grep '^date' | head -n 1
21:34:04 <HackEgo> date: Sun May 04 18:20:25 2014 +0000
21:34:34 -!- Slereah_ has quit (Ping timeout: 240 seconds).
21:35:42 -!- nortti has changed nick to lawspeaker.
21:36:53 -!- lawspeaker has changed nick to nortti.
21:37:10 -!- Slereah_ has joined.
21:38:04 -!- ais523_ has quit (Quit: Page closed).
21:41:43 -!- Slereah_ has quit (Ping timeout: 252 seconds).
21:48:54 <oerjan> yeah it was kmc, he's the main user of the command anyhow.
21:53:27 <kmc> http://files.shroomery.org/files/14-19/968666276-image.jpg
21:54:30 <oerjan> kmc: that facehugger's mushroom disguise isn't fooling anyone.
21:57:07 -!- nortti has changed nick to lawspeaker.
21:58:06 -!- lawspeaker has changed nick to nortti.
21:59:28 <kmc> http://www.mushroomexpert.com/clathrus_archeri.html
21:59:51 <olsner> looks like a land octopus
22:00:08 <kmc> similar to the pacific northwest tree octopus
22:00:13 <kmc> smells worse tho
22:07:43 -!- tromp has quit (Remote host closed the connection).
22:08:19 -!- tromp has joined.
22:10:12 -!- nucular has changed nick to nuculaway.
22:12:28 -!- tromp has quit (Ping timeout: 245 seconds).
22:20:16 -!- tromp has joined.
22:23:45 -!- Phantom_Hoover has joined.
22:36:00 -!- Patashu has joined.
22:36:29 -!- nuculaway has changed nick to nucular.
22:59:38 -!- Patashu has quit (Disconnected by services).
22:59:38 -!- Patashu_ has joined.
23:05:47 <lambdabot> The operator ‘GHC.List.!!’ [infixl 9] of a section
23:05:48 <lambdabot> must have lower precedence than that of the operand,
23:05:59 <lambdabot> The operator ‘GHC.Base.$’ [infixr 0] of a section
23:05:59 <lambdabot> must have lower precedence than that of the operand,
23:06:05 <Sgeo> https://github.com/bridgetkromhout/devops-against-humanity/blob/master/first-printing-cards-DevOpsAgainstHumanity.csv
23:12:58 -!- tertu has quit (Ping timeout: 240 seconds).
23:16:56 -!- stuntaneous has joined.
23:21:55 <jconn> FireFly: |syntax error
23:21:55 <jconn> FireFly: | (0 $0$)
23:22:32 <int-e> tromp: wow, the I/O handling in the IOCCC entry is nasty. (Am I right that U[-5]=96 can be reduced to U[-5] = 92? You need space for nil (4 entries) plus 8 cons cells with a bool (11 entries each), for a total of 11*8+4 = 92.
23:23:29 <Sgeo> Is Melvar still running idris-bot or is it someone else?
23:23:44 <Sgeo> Same bot in #idris
23:23:55 <Sgeo> > "Hello, idris-bot ignores me"
23:24:14 <int-e> tromp: but the real nastiness is in the manipulation of the code pointer to perform loops in the auxilliary code generated by k(10,33).
23:25:48 <tromp> int-e: it's been a while since i coded that. let me see if i can figure out my code...
23:31:38 <int-e> tromp: hmm. well it doesn't work.
23:31:50 * int-e checks his own calculation.
23:32:04 <tromp> maybe nil takes 8 entries
23:32:31 <tromp> i have to check my lambda space encoding
23:33:12 -!- nucular has quit (Quit: Excess Food).
23:34:24 <int-e> tromp: oh. I forgot an APP VAR0 part that goes together with the nil, which is another 4 entries. Sorry.
23:36:25 <Melvar> Sgeo: It’s the same, just someone was unhappy about the “slave” name, and it was decided it should be changed.
23:36:50 <Sgeo> Melvar: what about the no > prefix here but yes > prefix in #idris
23:37:47 <Melvar> Sgeo: I thought that was how people wanted it?
23:37:58 <Sgeo> Yes, just wondering how the change was made
23:38:17 <Sgeo> Configs expanded to allow channel-specific configuration?
23:40:27 <Melvar> Well, I implemented configuration in the first place, such that per-channel is possible.
23:40:36 <Taneb> Help I made a Vine
23:53:58 <Melvar> Sgeo: So, as a default, interpPrefixes = ["> ", "( "] , but for #esoteric, interpPrefixes = ["( "] .
23:55:24 <Sgeo> Do people actually use ( in #idris ?
23:57:41 <Melvar> No, I just decided it probably wouldn’t hurt.
00:03:15 <Taneb> The I country I voted for in the Eurovision came last :(
00:08:06 <zzo38> interpPrefixes = ["idris-bot: "]
00:16:21 <nooodl> Taneb: i thought france was decent?? france was catchy
00:19:11 <Taneb> They only got 2 points
00:22:00 -!- tromp has quit (Remote host closed the connection).
00:22:32 -!- tromp has joined.
00:25:52 <oerjan> that's because no one could understand what they were singing hth
00:26:59 -!- tromp has quit (Ping timeout: 252 seconds).
00:28:18 <Taneb> oerjan, une moustache!
00:28:56 <oerjan> well who cares about aching mice
00:30:51 <Taneb> I also found out that one of my friends, who happens to be Italian, cannot hear the difference between "Paul" and "pole"
00:30:56 -!- tromp has joined.
00:35:30 <zzo38> Which sorting algorithms work best when only partial ordering is defined?
00:40:03 <zzo38> (If there is no ordering for some pair of data, then it means don't care how it is ordered in the final list.)
00:40:05 -!- Phantom_Hoover has quit (Ping timeout: 265 seconds).
00:41:22 <Bike> i thought it was usual for sorts to treat false both ways as meaning equal, meaning their relative order is unimportant
00:42:46 -!- tromp has quit (Remote host closed the connection).
00:43:21 -!- tromp has joined.
00:43:45 -!- tromp has quit (Remote host closed the connection).
00:43:48 -!- oerjan has quit (Quit: Nite).
00:43:59 -!- tromp has joined.
00:55:49 <nooodl> idea: call an esolang C. "maximal confusion"
01:11:32 -!- LadyAethra has joined.
01:15:19 -!- LadyAethra has quit (Client Quit).
01:20:39 -!- Patashu has joined.
01:22:05 -!- Patashu_ has quit (Ping timeout: 250 seconds).
01:28:06 -!- shikhin has joined.
01:31:11 -!- shikhout has quit (Ping timeout: 258 seconds).
01:37:46 -!- zzo38 has quit (Remote host closed the connection).
02:03:58 -!- hk3380 has quit (Ping timeout: 240 seconds).
02:42:04 -!- nooodl has quit (Quit: Ik ga weg).
02:50:23 <HackEgo> [wiki] [[Special:Log/newusers]] create * Dggh * New user account
02:58:58 -!- hk3380 has joined.
03:15:31 -!- idris-bot has quit (Quit: Terminated).
03:22:28 -!- edwardk has joined.
03:42:59 <HackEgo> bestcoin akhacoin befuncitacoin chamcoin pointwispcoin beturcoin rfkcoin prnfcoin stackcoin barelnecoin monecoin shagecoin fmanicoin thtecoin plungcoin seliacoin enubicoin pathcoin 0.19coin footiliorslitaincoin
03:51:10 <kmc> the fungot are the virtuous among us
03:51:10 <fungot> kmc: help getting to work only if you had to specify a " real" programs, too :) libgauche.so: no such file
03:58:08 -!- edwardk has quit (Read error: Connection reset by peer).
03:58:56 -!- edwardk has joined.
04:14:19 -!- Froox has joined.
04:14:19 -!- Frooxius has quit (Read error: Connection reset by peer).
04:20:26 <coppro> anyone here know about quasi-order/preorder theory?
04:26:50 <shachaf> preorders are just simple categories hth
04:27:08 <HackEgo> A preorder is just a small thin category.
04:27:25 <copumpkin> it's a variant on tropical mathematics
04:28:51 <shachaf> preorders are just topologies where any intersection of open sets is open hth
04:29:12 <shachaf> copumpkin: did you finish topology in agda yet
04:29:15 <coppro> /ignore -regexp -pattern hth$ #esoteric
04:29:40 <copumpkin> hrm, I had some code for it somewhere
04:29:44 <copumpkin> might have been on the dead computer though
05:30:47 -!- shikhin has quit (Quit: leaving).
05:31:03 -!- shikhin has joined.
05:34:33 -!- tertu has joined.
05:41:00 -!- shikhout has joined.
05:43:14 -!- shikhin has quit (Ping timeout: 252 seconds).
05:46:03 -!- SL61 has joined.
05:46:28 -!- SL61 has left ("Leaving").
05:55:18 -!- hk3380 has quit (Ping timeout: 258 seconds).
06:09:11 -!- Sorella has quit (Quit: It is tiem!).
06:27:10 -!- ^v has quit (Quit: http://i.imgur.com/Akc6r.gif).
06:34:15 -!- password2 has joined.
06:48:45 <HackEgo> [wiki] [[Forobj]] http://esolangs.org/w/index.php?diff=39491&oldid=39490 * GermanyBoy * (+1071)
06:54:01 -!- tromp has quit (Remote host closed the connection).
07:09:45 <HackEgo> [wiki] [[Forobj]] http://esolangs.org/w/index.php?diff=39492&oldid=39491 * GermanyBoy * (+149)
07:13:37 -!- conehead has quit (Quit: Computer has gone to sleep).
07:29:43 <mroman_> http://codepad.org/BKuYBOmq <- so far so good
07:29:57 <mroman_> an assembly like language should be easiest to compile and write a compiler in it
07:30:25 -!- shikhout has quit (Ping timeout: 250 seconds).
07:37:53 -!- AnotherTest has joined.
07:53:04 <HackEgo> [wiki] [[Forobj]] http://esolangs.org/w/index.php?diff=39493&oldid=39492 * GermanyBoy * (+198)
08:09:29 -!- shikhin has joined.
08:13:21 -!- Vorpal has joined.
08:13:21 -!- Vorpal has quit (Changing host).
08:13:21 -!- Vorpal has joined.
08:14:14 -!- Bike has quit (Ping timeout: 240 seconds).
08:16:34 -!- MoALTz has joined.
08:18:09 -!- Slereah_ has joined.
08:28:25 <HackEgo> [wiki] [[Forobj]] http://esolangs.org/w/index.php?diff=39494&oldid=39493 * GermanyBoy * (+1016)
08:29:55 <HackEgo> [wiki] [[Forobj]] M http://esolangs.org/w/index.php?diff=39495&oldid=39494 * GermanyBoy * (-10)
08:32:37 <HackEgo> [wiki] [[Forobj]] http://esolangs.org/w/index.php?diff=39496&oldid=39495 * GermanyBoy * (+3)
08:34:00 -!- MoALTz has quit (Ping timeout: 258 seconds).
08:34:53 <HackEgo> [wiki] [[Forobj]] M http://esolangs.org/w/index.php?diff=39497&oldid=39496 * GermanyBoy * (+2) /* Brainfuck interpreter */
08:35:05 <HackEgo> [wiki] [[Forobj]] M http://esolangs.org/w/index.php?diff=39498&oldid=39497 * GermanyBoy * (+0) /* Brainfuck interpreter */
08:37:16 -!- MindlessDrone has joined.
08:43:11 -!- MoALTz has joined.
08:52:19 <mroman_> is fprintf(0,"foo") the same as fprintf(stdout,"foo")?
08:52:33 <mroman_> since it's argument is a FILE*
08:52:48 <mroman_> which one could confuse as "ponter to a file"
08:52:59 <mroman_> where 0 would be more or less a null pointer
08:54:19 -!- password2 has quit (Ping timeout: 240 seconds).
08:57:03 -!- edwardk has quit (Read error: Connection reset by peer).
08:57:26 -!- edwardk has joined.
08:59:07 <Jafet> `cc #include <stdio.h>\nmain() { fprintf(0, "\\n"); }
08:59:26 -!- MoALTz has quit (Read error: Connection reset by peer).
09:00:11 -!- MoALTz has joined.
09:11:11 -!- oerjan has joined.
09:14:40 <mroman_> `cc #include <stdio.h>\nmain() { fprintf(stdout, "\\n"); }
09:15:09 -!- password2 has joined.
09:19:54 <oerjan> edwardk: after pondering your recent deepOf, i've concluded that you need a Tectonic class so that your plates can move (between types (and i realize Data may not be up to give the information)) and stab properly.
09:28:03 <oerjan> just making sure i wasn't lying on stackoverflow
09:32:18 * oerjan suddenly wonders if he can say eighth
09:33:10 <myname> eighth of spades vs ace of spades
09:33:36 <mroman_> that's fcntl and stuff that takes int 0 as stdout
09:35:09 <oerjan> hm that gives two google hits, alas not with the eighth and thpadeth together
09:36:58 <HackEgo> [wiki] [[Forobj]] http://esolangs.org/w/index.php?diff=39499&oldid=39498 * GermanyBoy * (+2) /* Classes and objects */
09:40:08 <Jafet> `cc #include <stdio.h>\n#define A(x) printf(#x" = %d\\n", fileno(x));\nmain(){ A(stdin); A(stdout); A(stderr); }
09:40:09 <HackEgo> stdin = 0 \ stdout = 1 \ stderr = 2
09:41:17 <Jafet> `cc #include <stdio.h>\n#define A(x) printf(#x"=%p fileno("#x")=%d\\n", x, fileno(x));\nmain(){ A(stdin); A(stdout); A(stderr); }
09:41:18 <HackEgo> stdin=0x405a66c0 fileno(stdin)=0 \ stdout=0x405a67a0 fileno(stdout)=1 \ stderr=0x405a6880 fileno(stderr)=2
10:17:33 <Melvar> @tell zzo38 I also made it strip its nick off the front of a line independently of any other interpretation.
10:19:26 -!- idris-bot has joined.
10:19:36 <idris-bot> (input):1:7: error: expected: operator
10:19:57 <oerjan> hm idris doesn't have sections at all?
10:20:33 <idris-bot> (input):1:7: error: expected: operator
10:21:50 <oerjan> so it has sections, but their arguments must not have top operators?
10:26:22 <Melvar> oerjan: I believe that is correct.
10:26:58 <idris-bot> (input):1:9: error: expected: operator
10:27:15 <oerjan> ...or function application.
10:27:23 <Melvar> Huh, I thought that worked.
10:27:55 <Melvar> Looks like time to update the issue …
10:28:02 <Melvar> Yes, it very much does.
10:28:10 <oerjan> there's an issue for this?
10:31:29 <Melvar> https://github.com/idris-lang/Idris-dev/issues/524 Also I miscalled them “slices” apparently >.>
10:32:42 <int-e> it makes sense, both slices, sections are parts cut off from a whole.
10:33:38 <oerjan> now you must go the edwardk way and make them be subtly differently typed variations on a theme.
10:34:41 <edwardk> type shifting plates is something we've talked about ;)
10:34:52 <Melvar> IIRC, the improvement there should have allowed at least function application to appear there, but apparently later changes have broken that again?
10:35:10 <oerjan> edwardk: i sort of expected that :)
10:35:36 <idris-bot> \{ARG1000} => prim__addBigInt ARG 2 : Integer -> Integer
10:36:25 <idris-bot> \{ARG1000} => prim__divFloat ARG 2.0 : Float -> Float
10:37:00 <Melvar> The wierd name is because there’s some problem with showing internal autogenerated names.
10:38:39 <Melvar> ( the (Eq Int) %instance
10:38:39 <idris-bot> constructor of Prelude.Classes.Eq (\{meth0} => \{meth1} => intToBool (prim__eqInt meth meth))
10:38:39 <idris-bot> (\{meth2} => \{meth4} => not (intToBool (prim__eqInt meth meth))) : Eq Int
10:40:20 <oerjan> i see, it's dropping the number in expression position?
10:40:22 <Melvar> Braces and uniquifying number are shown at binding but not at use, it seems.
10:41:23 -!- drdanmaku has quit (Quit: Connection closed for inactivity).
10:44:16 -!- hk3380 has joined.
10:44:17 <Melvar> And then there’s “constructor of Prelude.Classes.Eq” which is also an internal name you can’t reference. Several kinds of internal name are phrases, making parsing some errors a bit difficult.
10:54:13 <oerjan> that sounds like the main thing you'd want to use {}'s around
10:54:34 <oerjan> perhaps allowing them on input too?
11:01:55 <HackEgo> [wiki] [[Sngscsv]] N http://esolangs.org/w/index.php?oldid=39500 * Dggh * (+4) Created page with "todo"
11:02:57 -!- nooodl has joined.
11:14:50 -!- Phantom_Hoover has joined.
11:16:53 <Melvar> oerjan: There are already things with {} around on input, so no.
11:17:21 -!- Case__ has joined.
11:17:37 -!- Case__ has left ("Leaving").
11:18:54 <oerjan> Melvar: in that case you are doomed to absorb perl syntax for distinguishing the options hth
11:19:24 <idris-bot> When elaborating an application of constructor __infer:
11:19:25 <idris-bot> Can't disambiguate name: Prelude.Basics.id, Control.Category.id
11:28:39 -!- edwardk has quit (Quit: Computer has gone to sleep.).
11:29:51 <HackEgo> [wiki] [[ESOSC]] N http://esolangs.org/w/index.php?oldid=39501 * 92.105.82.69 * (+675) Created page with "The Esoteric Standard Committee (ESOSC) aims to standardize esolangs and related works. The ESOSC assures high-quality esolang standards much more detailed than esolang wiki ..."
11:30:41 <nortti> mroman_: I'm user:EzoLang
11:32:24 <HackEgo> [wiki] [[ESOSC]] http://esolangs.org/w/index.php?diff=39502&oldid=39501 * 92.105.82.69 * (+1)
11:33:23 <Taneb> mroman_, nortti, what are the prospective goals for D4 and D5
11:36:50 <mroman_> After hearing about PSOX D4 might not be needed
11:36:56 <mroman_> except that PSOX uses a binary format
11:37:09 <mroman_> which might be unconfortable for some esolangs probbly?
11:37:29 <mroman_> But D4 was about EsoAPI, PEOSIX
11:38:24 <mroman_> #++ is some esolang I'm working on
11:39:20 <mroman_> EsoAPI specs aren't available anymore
11:39:31 <mroman_> but Sgeo's PSOX specs are still available
11:45:56 <mroman_> The ISO also standardizes whole languages
11:46:04 <mroman_> so I thought we could do that to
11:46:23 <mroman_> which raises the questions whether Brainfuck Conventions should be more like "ESOSC Brainfuck"
11:46:50 <mroman_> Which defines what to use as EOF and stuff
11:47:00 <mroman_> and maybe standardize how to embed comments into Brainfuck
11:48:14 <mroman_> rather than "defining" conventions
11:48:23 -!- password2 has quit (Ping timeout: 276 seconds).
11:49:10 <mroman_> how are we actually going to do this?
11:49:25 <mroman_> ask around what people here prefer and then use the majority
11:56:41 -!- hogeyui has quit (Ping timeout: 252 seconds).
11:56:57 <nortti> that seems like a good idea
11:59:06 <FireFly> It being a binary format is probably rather helpful in some other esolangs though
11:59:29 <nortti> should we conduct just a informat vote on channel or set up some sort of questionaire thing?
12:08:23 <nortti> yeah, wasn't there a gdocs thing for that
12:09:09 <mroman_> "Do you want 0 or -1 (255) as EOF?"
12:09:34 <nortti> so, EOF, wraparound, bitness?
12:09:48 <nortti> also, there's the possibility of no change on EOF
12:11:36 <nortti> also, regarding 2014-D2-R3, are there any more plans to introduce other normalized forms than FNF?
12:11:59 <int-e> you could take this under consideration: http://brainfuck.sourceforge.net/rules.html
12:12:20 <Taneb> nortti, all of <>, +- etc don't apply with bounded tapes or non-wrapping values
12:12:46 <int-e> (though I thought not allowing to decrement 0 was a pity)
12:13:39 <nortti> in the case that no other normalized forms are planned, the "First" seems redundant
12:14:27 <nortti> oh, actually. I never thought about what ',' would return after EOF had been reached, maybe have that too
12:14:47 <nortti> at least erroring out and re-returning EOF are possibilities
12:15:21 <Taneb> I'd prefer re-returning EOF
12:16:14 <nortti> oh and newline handling
12:16:55 <HackEgo> [wiki] [[Forobj]] http://esolangs.org/w/index.php?diff=39503&oldid=39499 * GermanyBoy * (+314) /* Commands */
12:16:57 <Taneb> Or if we're feeling ridiculous, U+0085
12:17:26 <HackEgo> [U+0030 DIGIT ZERO] [U+0030 DIGIT ZERO] [U+0038 DIGIT EIGHT] [U+0035 DIGIT FIVE]
12:17:34 <Melvar> `unicode LINE SEPARATOR
12:17:42 <HackEgo> U+0085 <control> \ UTF-8: c2 85 UTF-16BE: 0085 Decimal: … \
\ Category: Cc (Other, Control) \ Bidi: B (Paragraph Separator)
12:18:08 <Taneb> But no, Line Feed is a better option
12:18:57 <nortti> personally I'd implement the stuff as 8bit, wrap, linefeed, 0 on eof, re-return eof, right-infine
12:26:48 -!- hogeyui has joined.
12:27:07 <HackEgo> U+0085 <control> \ UTF-8: c2 85 UTF-16BE: 0085 Decimal: … \
\ Category: Cc (Other, Control) \ Bidi: B (Paragraph Separator)
12:27:16 -!- yorick has joined.
12:28:41 <int-e> Jafet: please standardize something that doesn't invalidate virtually all BF programs ever written.
12:40:35 <int-e> Historically, Urban Müller's bfi.c used getchar() for ',', that points towards -1 for EOF. I wonder what the compiler did ...
12:42:23 <nortti> where does the zero-on-eof come from?
12:43:41 <int-e> I don't know. I can imagine two reasons, one is convenience, and the other is a dislike for negative numbers (for example because you want to use Church numerals)
12:44:42 <nortti> well, online survey would probably be best
12:44:59 <Taneb> In the topic and on the wiki's main page?
12:45:34 <nortti> if one of you can create it, I cannot run gdocs atm
12:46:12 <mroman_> I'm creating one currently :)
12:52:47 <nooodl> ,[.,] is the most compelling argument imo
12:55:52 <nortti> no-change has the argument that is can simulate any return on eof
12:56:20 <nortti> s/,/[-],/g for 0 and s/,/[-]-,/g for -1
12:59:29 <Jafet> I'll standardize cookies
12:59:43 <nortti> compared to ,+[-.,+] (assuming wrap for sake of sanity) and [-],[.[-],]
13:03:33 <Jafet> So, how does no-change cat work
13:04:16 <nooodl> or i guess the first [-] doesn't matter, duh.
13:04:47 <Jafet> That stops on zero, not EOF
13:05:23 <int-e> there's always a character that can't be distinguished from EOF if you have only 8 bits (and 8 bit characters)
13:06:01 <nooodl> -,+[-.[-]-,+] i guess?
13:06:03 <int-e> you can also use -,+[-.[-]-,+] to simulate -1 on EOF
13:06:16 <oerjan> just be radical and do > on EOF hth
13:06:40 <oerjan> (the command, not the character)
13:07:07 <Jafet> Sounds good as far as standards go
13:07:30 <oerjan> 'twould have the advantage that you actually _could_ distinguish EOF from everything.
13:08:57 <nortti> also, break ~everything
13:09:00 <int-e> Ok, it does look like Urban Müller's compiler implements no change on EOF semantics.
13:10:15 <Jafet> Run three copies of the program and merge the results
13:14:47 -!- Slereah_ has quit (Ping timeout: 252 seconds).
13:15:17 -!- Slereah_ has joined.
13:20:47 -!- tailcalled has joined.
13:21:58 <oerjan> wait, even better, do [>] on EOF.
13:24:21 <oerjan> hm no that's close enough.
13:24:42 <oerjan> (doesn't break ,[.,] cat)
13:26:34 <oerjan> i think that will accidentally fail to break many programs hth
13:27:11 <oerjan> (basically anything that does , only on a 0 _or_ halts immediately when reading a 0.)
13:28:37 <oerjan> yep, almost completely backwards compatible!
13:30:42 <oerjan> intuitively, because if you are saving input for later you'd most likely input into a new untouched cell
13:46:16 -!- drdanmaku has joined.
13:47:18 -!- tailcalled has quit (Ping timeout: 240 seconds).
13:48:16 -!- edwardk has joined.
13:50:05 <mroman_> https://de.surveymonkey.com/s/LKP5NSH <- something like that @questionaire
13:53:39 <oerjan> 3 is missing the option of unbounded in both directions
13:54:21 <nortti> is it possible to make that page be in english?
13:54:48 -!- tailcalled has joined.
13:54:53 <nortti> nope, shows german for me
13:56:46 <oerjan> mroman_: drop the initial de. in the hostname
13:56:54 -!- edwardk has quit (Ping timeout: 240 seconds).
13:57:04 <nortti> still shows german for me if I drop the de.
13:58:03 -!- Slereah_ has quit.
13:59:09 -!- ^v has joined.
13:59:21 <nortti> now I get a finnish page telling me that the page was not found
13:59:53 <mroman_> I had to change question 3
14:00:01 <mroman_> so I had to revoke the previous link
14:00:23 <mroman_> https://www.surveymonkey.com/s/L82SNZV
14:00:27 <mroman_> ^- that should be english now
14:05:25 -!- shikhout has joined.
14:05:41 -!- Sorella has joined.
14:06:57 -!- atslash has joined.
14:08:16 -!- shikhin has quit (Ping timeout: 258 seconds).
14:10:11 -!- shikhout has changed nick to shikhin.
14:18:59 -!- ^v has quit (Read error: Connection reset by peer).
14:19:22 -!- ^v has joined.
14:20:48 <int-e> This is getting ridiculous. It says "Javascript is required for this site to function, please enable." I disable CSS. I get a bona fide HTML form to fill in, with functioning submit button.
14:21:27 <nortti> oh, I didn't even notice such a requirement since links2 does not have css :D
14:25:12 <int-e> The sad thing is that the Web at large has now successfully trained me to do that, disable CSS when a web page requests Javascript. It works about half of the time.
14:25:45 <int-e> (To be more specific, when it requests Javascript but doesn't display any other content.)
14:26:11 <nortti> also works on the bootstrap-based menus that for some ungodly reason require js
14:29:57 <Melvar> int-e: I’m gonna have to remember that. Sometimes I remember to click-hold and press delete, and sometimes that works too.
14:36:26 -!- edwardk has joined.
14:38:20 -!- oerjan has quit (Quit: Just surrender to Javascript already!).
14:40:38 -!- tailcalled has quit (Quit: Page closed).
14:51:41 -!- Patashu has quit (Ping timeout: 252 seconds).
14:56:21 -!- tromp has joined.
15:05:46 -!- boily has joined.
15:33:31 -!- nucular has joined.
15:33:41 -!- nucular has quit (Changing host).
15:33:42 -!- nucular has joined.
15:43:40 -!- Slereah_ has joined.
15:51:09 -!- ^v has quit (Read error: Connection reset by peer).
15:51:37 -!- ^v has joined.
15:54:48 -!- blitter64 has joined.
16:08:36 -!- Bike has joined.
16:45:17 -!- shikhin has quit (Remote host closed the connection).
16:45:59 -!- Sprocklem has quit (Ping timeout: 252 seconds).
16:47:17 -!- Sprocklem has joined.
16:51:33 -!- boily has quit (Quit: WeeChat 0.4.2).
16:51:41 -!- Sprocklem has quit (Ping timeout: 255 seconds).
16:52:15 -!- atslash has quit (Quit: This computer has gone to sleep).
17:02:27 -!- mhi^ has joined.
17:10:07 -!- conehead has joined.
17:14:27 -!- conehead has quit (Changing host).
17:14:27 -!- conehead has joined.
17:18:06 -!- ^v has quit (Read error: Connection reset by peer).
17:18:10 -!- not^v has joined.
17:18:11 <HackEgo> [wiki] [[Deadfish]] http://esolangs.org/w/index.php?diff=39504&oldid=39380 * GermanyBoy * (+141) Forobj
17:19:24 -!- not^v has quit (Read error: Connection reset by peer).
17:19:50 -!- not^v has joined.
17:20:16 <HackEgo> [wiki] [[Forobj]] http://esolangs.org/w/index.php?diff=39505&oldid=39503 * GermanyBoy * (+10)
17:21:18 -!- Phantom_Hoover has quit (Ping timeout: 240 seconds).
17:23:07 <FireFly> http://mjg59.dreamwidth.org/31357.html
17:32:11 -!- Slereah_ has quit (Ping timeout: 265 seconds).
17:32:31 -!- Slereah_ has joined.
17:32:45 -!- Froox has quit (Read error: Connection reset by peer).
17:32:54 -!- Froox has joined.
17:36:19 -!- Phantom_Hoover has joined.
17:43:31 -!- not^v has quit (Quit: http://i.imgur.com/Akc6r.gif).
17:43:39 -!- blitter64 has quit (Ping timeout: 252 seconds).
17:43:54 -!- ^v has joined.
17:45:58 -!- Phantom_Hoover has quit (Ping timeout: 240 seconds).
17:47:04 <HackEgo> [wiki] [[Special:Log/newusers]] create * Malltog * New user account
17:54:11 -!- boily has joined.
17:55:40 <boily> good fternoon! we have a song contest?
17:55:48 <lambdabot> kmc asked 2d 16h 48m 25s ago: what's the deal with your quit messages?
17:56:08 <boily> kmc: eh... eeeeeeeeh... >_>'...
17:58:43 -!- conehead has quit (Quit: Computer has gone to sleep).
18:00:44 <Taneb> The esoteric song contest!
18:04:05 -!- conehead has joined.
18:04:23 -!- conehead has quit (Changing host).
18:04:23 -!- conehead has joined.
18:05:00 <boily> mrhelloman_. Tanelle.
18:05:24 <boily> any subscribers? contestants? judges? bloopers?
18:09:41 <kmc> https://farm4.staticflickr.com/3472/3373021846_838c8b0089_o.jpg
18:10:58 * boily twitches, drools and overdoses with a manic grin
18:11:07 <boily> oh oui... ouiiii...
18:16:17 -!- hk3380 has quit (Ping timeout: 252 seconds).
18:25:34 -!- atslash has joined.
18:27:21 <HackEgo> [wiki] [[Improbable]] N http://esolangs.org/w/index.php?oldid=39506 * Malltog * (+1432) Created page with "'''Improbable''' is a register- and tape-based esoteric language focusing on succinctness. A tape is called the datastore, and is 256 bytes long. The register is one byte. The..."
18:27:27 -!- augur has quit (Remote host closed the connection).
18:27:53 -!- augur has joined.
18:28:59 <myname> why is succinctness such a long word
18:29:37 <FireFly> not a very succint word, eh
18:30:38 <kmc> it's heterological
18:32:24 <nooodl> is heterological heterological
18:32:26 <boily> can a word be partially heterological?
18:32:32 <nooodl> sounds russell's paradox-y
18:32:36 -!- augur has quit (Ping timeout: 265 seconds).
18:32:58 <nooodl> nice http://en.wikipedia.org/wiki/Grelling%E2%80%93Nelson_paradox#Similarities_with_Russell.27s_paradox
18:37:04 <kmc> boily: bilogical?
18:37:39 <boily> boilogicaly: that which is sane and logical in my head.
18:38:45 <boily> (can't blame chicken. it tastes good!)
19:06:46 -!- hk3380 has joined.
19:09:16 -!- boily has quit (Quit: The set of chickens that aren't contained in those chickens).
19:15:54 <mroman_> https://www.surveymonkey.com/s/L82SNZV <- Brainfuck Survey
19:18:20 -!- nortti has set topic: The dead serious channel | PSA: fizzie is running the wiki now, contact him for any problems | brainfuck survey: https://www.surveymonkey.com/s/L82SNZV | https://dl.dropboxusercontent.com/u/2023808/wisdom.pdf http://codu.org/logs/_esoteric/ http://tunes.org/~nef/logs/esoteric/.
19:37:56 -!- MindlessDrone has quit (Quit: MindlessDrone).
19:40:28 -!- blitter64 has joined.
19:44:21 -!- MoALTz has quit (Quit: bbl).
19:51:12 <HackEgo> [wiki] [[Improbable]] http://esolangs.org/w/index.php?diff=39507&oldid=39506 * Malltog * (+2) Clarified external link
20:03:41 -!- nucular has quit (Quit: Excess Food).
20:04:42 <impomatic> Is anyone planning to implement Pinkcode? http://esolangs.org/wiki/Pinkcode
20:28:41 <FireFly> That looks a bit interesting
20:32:10 -!- augur has joined.
20:34:06 -!- mhi^ has quit (Quit: Lost terminal).
20:36:32 <FireFly> I don't get what cell ownership affects, though
20:37:19 -!- mhi^ has joined.
20:53:11 -!- edwardk has quit (Quit: Computer has gone to sleep.).
20:53:41 -!- Phantom_Hoover has joined.
20:53:41 -!- Phantom_Hoover has quit (Changing host).
20:53:42 -!- Phantom_Hoover has joined.
20:57:37 -!- augur has quit (Ping timeout: 276 seconds).
21:04:01 -!- Patashu has joined.
21:09:34 -!- rapido has joined.
21:09:37 -!- blitter64 has quit (Quit: Leaving).
21:10:26 -!- rapido_ has joined.
21:11:26 <rapido_> has anyone been into http://www.availlang.org ?
21:12:49 <rapido_> avail has a very interesting type system married with functional purity
21:13:29 <rapido_> it appears esoteric because of its *very* free syntax
21:13:45 <rapido_> but the semantics are very solid
21:13:48 -!- rapido has quit (Ping timeout: 240 seconds).
21:13:48 -!- rapido_ has changed nick to rapido.
21:15:41 <rapido> oh? but everything is pure except for variables (of course!)
21:16:32 <rapido> the type system is pretty nifty
21:17:08 <elliott> rapido: if reader : []→string and writer : [string]→⊤ are ever going to get specified as things that do IO (as the text suggests), then it is unlikely they can have those types in a pure language.
21:17:10 <rapido> it has multmethod dispatch on precise types
21:17:33 <elliott> those variables also seem to clearly be mutable
21:17:37 <rapido> ah, the reader and write stuff
21:17:51 <rapido> yes, variables are mutable
21:18:16 <elliott> sure, but it's not pure :P
21:18:33 -!- oerjan has joined.
21:18:45 <elliott> I guess "functional purity" could just mean purity of paradigm there rather than "purely functional".
21:19:10 <elliott> but I'm not quite sure "functional" exists as a meaningful paradigm in itself if you don't at least imply the language is pure
21:19:32 <rapido> yeah, i know what you mean
21:21:01 <elliott> the language seems interesting at a glance, though the syntax is hard to get over.
21:21:19 <rapido> every language is suddenly ‘functional’ because that’s fashionable to say
21:21:39 <rapido> yeah, the syntax is hard because it’s completely free form
21:22:52 <rapido> because we should talk about semantics - no? 9.9
21:23:10 <elliott> yeah, but syntax is easier to argue about
21:23:39 <oerjan> let's argue about the syntax of comments
21:24:45 <oerjan> i recommend borrowing the -- (...) (...) ... from Reaper.
21:24:55 -!- Patashu has quit (Ping timeout: 276 seconds).
21:25:02 <oerjan> (my vancient aporware language)
21:26:07 <elliott> I still want you to finish that.
21:26:16 <rapido> what about this avail gem? http://www.availlang.org/_examples/rpn/RPN.avail
21:26:30 <rapido> i’m very much into postfix syntax
21:28:01 <rapido> but that example just renders syntax arguments moot
21:29:14 <oerjan> i sense some COBOL/ADA inspiration.
21:29:15 <rapido> but, it could be that avail is an advertisment for babelism
21:29:47 -!- AnotherTest has quit (Ping timeout: 252 seconds).
21:30:28 <elliott> you could also say that article provides more fuel for syntax arguments than anyone could ever need :p
21:31:08 <rapido> see: https://trac.availlang.org/browser/avail/Avail/distro/src/avail/Avail.avail/Foundation.avail/Sets.avail
21:32:09 <rapido> fyi i’m totally in love with avail
21:32:34 <rapido> it’s like my language enchilada, but with types
21:36:34 <oerjan> types are like enchiladas
21:37:21 <rapido> oerjan: ah? i never tasted such a type of enchilada
21:37:51 <oerjan> you need to wear a hazmat suit
21:38:45 <oerjan> in the middle of a desert
21:39:33 <rapido> to get your urine recycled
21:39:39 -!- Bike has quit (Ping timeout: 265 seconds).
21:40:19 <oerjan> (i'm just parodying monad analogies here, assuming they're going over your head)
21:40:46 <rapido> god, i need urine but i’m wearing this suit
21:40:59 <oerjan> urine a bit of trouble then
21:41:13 -!- Bike has joined.
21:41:15 <rapido> monad analogies go over my head because i ignore them
21:42:20 <pikhq> Monads are like burritos: nobody understands them.
21:42:31 <oerjan> good, good. once a monad analogy gets into your head you cannot get it out again.
21:43:31 <oerjan> pikhq: i'm pretty sure edwardk does.
21:43:49 <pikhq> edwardk, burrito god.
21:44:15 <Bike> burritos rule, though....
21:45:01 <rapido> nope, they fligh right over my head - because i duck
21:46:37 <rapido> duck is rather tasty too
21:47:48 -!- edwardk has joined.
21:48:59 <oerjan> edwardk: are you a burrito expert twh
21:56:22 <rapido> just to show off my new love, she’s a rare kind of type (of types of types): http://www.availlang.org/about-avail/documentation/type-system/metatypes.html
21:57:39 <edwardk> oerjan: i've been known to wrap code in a burrito or two
21:57:58 <edwardk> oerjan: what can i help you with?
21:58:25 <edwardk> i do maintain the burrito transformer library ;)
21:58:42 <oerjan> we were merely wondering if the monad-burrito correspondence held for you
22:00:28 <lambdabot> Language.Haskell.TH.Syntax liftString :: String -> Q Exp
22:12:01 <oerjan> hm why doesn't that give a general MonadCont
22:12:07 <lambdabot> MonadState s m => (s -> (a, s)) -> m a
22:13:21 <oerjan> edwardk: i suppose as the maintainer of the burrito transformer library you should know that?
22:13:27 <edwardk> comonads are more like burritos to me
22:13:34 <edwardk> you can always unwrap them
22:14:39 <edwardk> anyways, cont can't be upgraded the way you want. m occurs in both positive and negative position in it
22:14:51 <lambdabot> ((a -> m r) -> m r) -> ContT r m a
22:15:50 <oerjan> you _could_ do it from the Codensity version, right?
22:16:12 <oerjan> i mean, a forall on the r would suffice.
22:16:27 <edwardk> you've stumbled on the difference between MonadTrans and something stronger that permits an injection t Identity a -> t m a or (MonadHoist t, Monad m , Monad n) => (forall a. m a -> n a) -> t m a -> t n a
22:16:58 <edwardk> i haven't checked naturality of hoisting for Codensity
22:17:40 -!- Ghoul_ has joined.
22:18:39 <rapido> we should consider creating an avail channel
22:20:11 -!- Eritzap has joined.
22:21:59 <oerjan> edwardk: i'm just wondering if you can write something of type MonadCont m => (forall r. (a -> r) -> r) -> m a
22:22:55 <lambdabot> MonadCont m => ((a -> m b) -> m a) -> m a
22:23:04 <oerjan> hm that's not quite the right type
22:23:23 <edwardk> you can't callCC with Codensity
22:23:28 <edwardk> but you can lower codensity to Cont
22:23:35 <oerjan> edwardk: i'm talking about MonadCont
22:24:04 <oerjan> since that is, after all, it's only specific method.
22:24:10 <edwardk> trivial :: Codensity m a -> ContT r m a; trivial = ContT . runCodensity
22:24:15 <rapido> Ghoul_: sorry, i thought you were someone else.
22:24:19 <edwardk> but handling all of MonadCont I don't expect
22:28:55 -!- Phantom_Hoover has quit (Quit: Leaving).
22:30:15 -!- Phantom_Hoover has joined.
22:30:20 -!- Phantom_Hoover has quit (Client Quit).
22:31:32 -!- Eritzap has quit (Quit: Page closed).
22:38:37 -!- rapido has quit (Quit: rapido).
22:50:30 <oerjan> edwardk: oh duh of course callCC has the right type to lift Codensity Identity a, just set b = a.
22:51:25 <edwardk> your statement is a bit different
22:51:25 <lambdabot> Perhaps you meant ‘runIdentity’ (imported from Control.Monad.Identity)
22:51:56 <edwardk> I was just running Codensity m a in ContT r m a -- unquantifying r
22:53:06 <oerjan> my er was because i realized m worked instead of Identity
22:53:29 <oerjan> i just needed to look up that i remembered the definition of Codensity.
22:55:47 <oerjan> :t callCC :: MonadCont m => (forall z. (a -> m z) -> m z) -> m a
22:55:48 <lambdabot> Couldn't match type ‘(a1 -> m1 b0) -> m1 a1’
22:55:48 <lambdabot> with ‘forall z. (a1 -> m1 z) -> m1 z’
22:55:48 <lambdabot> Expected type: (forall z. (a1 -> m1 z) -> m1 z) -> m1 a1
22:56:06 <edwardk> you can lift Codensity Identity as well of course.
22:56:25 <oerjan> hm i guess i need a let
22:56:26 <edwardk> just use the ContT constructor
22:56:29 <lambdabot> ((a -> m r) -> m r) -> ContT r m a
22:56:46 <edwardk> :t Data.Functor.Codensity.Codensity
22:56:47 <lambdabot> Not in scope: data constructor ‘Data.Functor.Codensity.Codensity’
22:56:50 <Ghoul_> if I start learning now, I'll understand this in about 15 years.
22:57:05 <edwardk> @let newtype Codensity m a = Codensity { runCodensity :: forall r. (a -> m r) -> m r }
22:57:05 <lambdabot> Parse failed: TypeOperators is not enabled
22:57:10 <oerjan> :t let r2cCC f = callCC f; r2cCC :: MonadCont m => (forall z. (a -> m z) -> m z) -> m a in r2cCC
22:57:11 <lambdabot> MonadCont m => (forall z. (a -> m z) -> m z) -> m a
22:57:43 <edwardk> oh you keep trying for full MonadCont
22:57:52 <lambdabot> MonadCont m => ((a -> m b) -> m a) -> m a
22:57:57 <oerjan> well yes, and it seems to work
22:58:35 <edwardk> it fits my understanding of how you can use the continuation in codensity
22:58:44 <oerjan> :t let r2cCC cd = callCC (runCodensity cd) in r2cCC
22:58:45 <lambdabot> Perhaps you meant ‘runIdentity’ (imported from Control.Monad.Identity)
22:59:01 <oerjan> oh your definition failed
22:59:26 -!- mhi^ has quit (Quit: Lost terminal).
23:00:09 <oerjan> int-e: i think lambdabot @let is missing some extension to allow foralls in data types
23:29:01 -!- augur has joined.
23:40:44 -!- nooodl has quit (Quit: Ik ga weg).
23:51:26 -!- yorick has quit (Remote host closed the connection).
00:02:12 -!- augur has quit (Remote host closed the connection).
00:06:06 -!- madbr has joined.
00:07:37 -!- ^v has quit (Read error: Connection reset by peer).
00:08:25 -!- ^v has joined.
00:19:38 -!- ^v has quit (Read error: Connection reset by peer).
00:20:03 -!- ^v has joined.
00:20:46 -!- atslash has quit (Quit: This computer has gone to sleep).
00:29:34 -!- oerjan has quit (Quit: Nite).
00:34:02 -!- shikhin has joined.
00:37:38 <kmc> every world we reach is fungot
00:37:38 <fungot> kmc: ( i'm saying this as a cgi. use mod_lisp.) and can be left off.
00:37:48 <kmc> fungot: are you a full-time internet?
00:37:48 <fungot> kmc: that's a macro. i thought that was fnord
00:42:06 <shachaf> p. sure fungot is computer-generated imagery
00:42:07 <fungot> shachaf: what use would a variable?
00:42:12 -!- Tod-Autojoined has joined.
00:45:38 -!- TodPunk has quit (Ping timeout: 240 seconds).
00:50:58 -!- ineiros_ has quit (Ping timeout: 240 seconds).
00:51:04 -!- douglass_ has quit (Ping timeout: 240 seconds).
00:52:55 -!- boily has joined.
00:52:56 -!- douglass1 has joined.
00:52:56 -!- ineiros has joined.
00:52:57 -!- boily has quit (Client Quit).
01:01:49 -!- Tod-Autojoined has changed nick to TodPunk.
01:12:31 -!- edwardk has quit (Read error: Connection reset by peer).
01:19:29 -!- shikhout has joined.
01:19:45 -!- Phantom_Hoover has joined.
01:23:05 -!- shikhin has quit (Ping timeout: 264 seconds).
01:31:16 -!- augur has joined.
01:31:29 -!- shikhout has quit (Remote host closed the connection).
01:47:34 -!- Tod-Autojoined has joined.
01:48:07 -!- nycs has joined.
01:51:19 -!- jconn has quit (Ping timeout: 240 seconds).
01:51:20 -!- TodPunk has quit (Ping timeout: 240 seconds).
01:51:21 -!- fowl has quit (Ping timeout: 240 seconds).
01:52:30 -!- Taneb has quit (Ping timeout: 276 seconds).
01:52:33 -!- `^_^v has quit (Ping timeout: 276 seconds).
01:55:04 -!- Zerker has joined.
01:55:57 -!- Taneb has joined.
02:04:35 -!- fowl has joined.
02:05:27 -!- Tod-Autojoined has changed nick to TodPunk.
02:06:53 -!- FreeFull has quit.
02:09:42 -!- Zerker has quit (Quit: Colloquy for iPad - Timeout (10 minutes)).
02:12:24 -!- ^v has quit (Quit: http://i.imgur.com/Akc6r.gif).
02:14:08 -!- Ghoul_ has quit (Quit: Connection closed for inactivity).
02:36:00 -!- Phantom_Hoover has quit (Remote host closed the connection).
02:48:42 -!- kwertii has joined.
02:49:28 -!- kwertii has quit (Client Quit).
03:09:35 -!- tertu has quit (Disconnected by services).
03:09:35 -!- ter2 has joined.
03:15:17 -!- hk3380 has quit (Ping timeout: 264 seconds).
03:28:34 -!- copumpkin has changed nick to ubiquipumpkin.
03:32:01 -!- Sorella has quit (Quit: It is tiem!).
03:39:58 -!- conehead has quit (Quit: Computer has gone to sleep).
03:48:08 <kmc> http://dumb.domains/
03:49:41 <Bike> thank you for making this all possible, ICANN
03:52:57 <ubiquipumpkin> is there a list of all the crazy TLDs that have appeared?
03:53:16 <ubiquipumpkin> http://en.wikipedia.org/wiki/List_of_Internet_top-level_domains
03:54:25 <kmc> hark, a pumpkin
03:57:39 <shachaf> ubiquipumpkin: surely you could make it one
03:57:57 <ubiquipumpkin> I guess the requirements are significantly lower :P
03:58:48 <shachaf> there might not be .pumpkin but at least there's .bike
03:59:48 <kmc> pumpkin.co
04:00:08 <ubiquipumpkin> kmc: omg if I were publishing jvm packages I'd be all set
04:01:47 <shachaf> Entity: those who like the color red
04:01:49 -!- ubiquipumpkin has changed nick to copumpkin.
04:02:00 <shachaf> it's a high bar, copumpkin
04:03:16 -!- tertu has joined.
04:04:56 <kmc> upholste.red
04:05:50 -!- ter2 has quit (Ping timeout: 265 seconds).
04:06:29 -!- hk3380 has joined.
04:10:31 -!- EgoBot has quit (Remote host closed the connection).
04:11:27 -!- EgoBot has joined.
04:12:19 -!- FireFly has quit (Ping timeout: 240 seconds).
04:13:29 -!- tromp has quit (Ping timeout: 252 seconds).
04:14:14 -!- tromp has joined.
04:14:44 -!- Gregor has quit (Ping timeout: 240 seconds).
04:16:00 -!- EgoBot has quit (Ping timeout: 265 seconds).
04:18:07 -!- FireFly has joined.
04:18:55 -!- Gregor has joined.
04:31:00 -!- Sprocklem has joined.
04:43:44 -!- hk3380 has quit (Ping timeout: 252 seconds).
04:49:59 -!- Vorpal has quit (Quit: ZNC - http://znc.sourceforge.net).
04:59:54 -!- ^v has joined.
05:04:31 -!- Slereah has joined.
05:05:11 -!- Slereah_ has quit (Ping timeout: 252 seconds).
05:08:07 -!- password2 has joined.
05:34:58 -!- Sprocklem has quit (Ping timeout: 245 seconds).
05:45:52 -!- edwardk has joined.
05:48:40 -!- madbr has quit (Quit: Rouringu de hajikunda!).
05:51:07 -!- tromp has quit (Ping timeout: 252 seconds).
05:59:04 -!- password2 has quit (Ping timeout: 276 seconds).
06:02:54 <mroman_> FireFly: You can check for whether a cell belongs to you or the enemy
06:03:23 <mroman_> You can scan the memory and bomb every location not belonging to you
06:07:22 -!- jconn has joined.
06:09:57 <mroman_> and I see the 'C' instruction isn't documented
06:10:08 <mroman_> It was intented to allow one to copy itself
06:22:46 -!- ^v has quit (Quit: http://i.imgur.com/Akc6r.gif).
06:36:53 -!- augur has quit (Ping timeout: 258 seconds).
06:52:14 -!- conehead has joined.
07:09:00 -!- augur has joined.
07:12:43 -!- edwardk has quit (Ping timeout: 240 seconds).
07:12:45 <shachaf> oerjan: what's with the weird bolding in https://en.wikipedia.org/wiki/Booth_encoding
07:13:14 <shachaf> looks like it took three edits to mess it up
07:23:11 -!- MindlessDrone has joined.
07:29:10 -!- slereah_ has joined.
07:29:17 <slereah_> Hello is this where we learn about the magic
07:34:48 -!- KingOfKarlsruhe has joined.
08:06:54 -!- edwardk has joined.
08:17:01 <augur> https://www.google.com/patents/US20030083544?dq=finding+love&hl=en&sa=X&ei=VqxuU52KKKLjsASNloCwBA&ved=0CDUQ6AEwAA
08:27:05 -!- Patashu has joined.
08:39:45 -!- oerjan has joined.
08:42:18 -!- Bike has quit (Ping timeout: 265 seconds).
08:51:23 -!- drdanmaku has quit (Quit: Connection closed for inactivity).
08:51:48 -!- atslash has joined.
09:08:34 -!- TodPunk has quit (Ping timeout: 240 seconds).
09:15:39 <oerjan> shachaf: someone was too bold while editing hth
09:46:12 -!- shikhin has joined.
09:59:37 <mroman_> if spammers were to pay 1 cent to charity for every spam mail they send
09:59:41 <mroman_> what a world we would live in...
10:01:26 <mroman_> so far 10/10 agreed on re-return EOF and unbounded memory to the right
10:04:04 -!- mhi^ has joined.
10:06:43 <slereah_> So many are from poor countries
10:07:02 <slereah_> http://en.wikipedia.org/wiki/Spammer#Geographical_origins
10:20:37 -!- shikhin has quit (Ping timeout: 252 seconds).
10:24:02 -!- hk3380 has joined.
10:28:51 -!- KingOfKarlsruhe has quit (Read error: Connection timed out).
10:36:14 -!- edwardk_ has joined.
10:37:55 -!- edwardk has quit (Ping timeout: 276 seconds).
10:51:47 -!- Phantom_Hoover has joined.
10:56:11 -!- hk3380 has quit (Ping timeout: 255 seconds).
11:12:40 -!- Patashu has quit (Disconnected by services).
11:12:40 -!- Patashu_ has joined.
11:36:59 -!- TodPunk has joined.
11:39:32 -!- TodPunk has quit (Read error: No route to host).
11:39:39 -!- TodPunk has joined.
11:42:09 -!- Tod-Autojoined has joined.
11:44:52 -!- TodPunk has quit (Ping timeout: 276 seconds).
11:45:05 -!- edwardk_ has quit (Ping timeout: 258 seconds).
11:47:27 -!- shikhin has joined.
11:47:35 -!- Sgeo has quit (Read error: Connection reset by peer).
11:51:48 -!- yorick has joined.
11:52:07 -!- shikhin has quit (Ping timeout: 250 seconds).
11:59:41 -!- edwardk has joined.
12:08:53 -!- conehead has quit (Quit: Computer has gone to sleep).
12:15:19 -!- nucular has joined.
12:15:19 -!- nucular has quit (Changing host).
12:15:19 -!- nucular has joined.
12:21:37 -!- mhi^ has quit (Quit: Lost terminal).
12:23:39 -!- mhi^ has joined.
12:23:41 -!- mhi^ has quit (Changing host).
12:23:42 -!- mhi^ has joined.
12:46:23 -!- Sorella has joined.
12:49:29 -!- edwardk has quit (Ping timeout: 264 seconds).
12:50:34 -!- tromp has joined.
13:21:11 -!- mhi^ has quit (Quit: Lost terminal).
13:44:22 -!- nycs has changed nick to `^_^v.
13:44:23 -!- Patashu_ has quit (Ping timeout: 265 seconds).
14:00:03 -!- Phantom__Hoover has joined.
14:00:54 -!- Phantom_Hoover has quit (Ping timeout: 240 seconds).
14:17:16 -!- hk3380 has joined.
14:17:32 -!- shikhin has joined.
14:22:25 -!- conehead has joined.
14:29:14 -!- oerjan has quit (Quit: leaving).
14:29:19 -!- password2 has joined.
14:30:18 -!- g2` has joined.
14:30:44 -!- g2` has left.
14:41:58 -!- password2 has quit (Read error: Connection reset by peer).
14:47:29 -!- Sprocklem has joined.
14:55:09 -!- adu has joined.
15:01:29 -!- slereah_ has quit (Ping timeout: 264 seconds).
15:02:23 -!- slereah_ has joined.
15:04:01 -!- nooodl has joined.
15:04:19 -!- mhi^ has joined.
15:07:36 -!- MindlessDrone has quit (Read error: Connection reset by peer).
15:10:35 -!- FreeFull has joined.
15:17:50 -!- nucular has quit (Ping timeout: 258 seconds).
15:22:30 -!- nucular has joined.
15:27:54 -!- ^v has joined.
15:28:52 -!- ^v has quit (Client Quit).
15:37:19 <shachaf> oerjan: thx for fixing tdh
15:40:33 <tromp_> exercise: write non-recursive factorial for Church numerals
15:41:53 <shachaf> exercise: write non-recursive ackermann function for Chuch numerals
15:42:29 <tromp_> you sure that's possible?
15:43:04 <shachaf> it's possible for it to be an exercise
15:43:06 <tromp_> at least factorial is possible
15:44:00 <int-e> the ackermann thing is instructive.
15:44:37 <int-e> I have a typographical hint: instead of ack(n,m), write ack_n(m).
15:45:15 <Taneb> There's a slightly (very) cheaty way of doing this...
15:46:03 <tromp_> int-e: good point. now it looks not only possible, but straightforward:)
15:51:37 <tromp_> my best factorial is 78 bits
15:54:05 <shachaf> the single-argument ackermann function is usually \n -> ack(n,n)
15:57:55 -!- tertu has quit (Ping timeout: 240 seconds).
15:58:28 <int-e> so 54 bits for \n m -> Ack(n,m); 58 for \n -> Ack(n,n)
15:59:03 -!- copumpkin has quit (Remote host closed the connection).
15:59:38 <int-e> binary lambda calculus
16:00:42 -!- slereah_ has quit (Quit: Leaving).
16:02:19 <tromp_> hmm, i even have something about goodstein and ackerman on my home page at http://homepages.cwi.nl/~tromp/pearls.html#goodstein
16:05:05 -!- Sprocklem has quit (Ping timeout: 264 seconds).
16:05:14 -!- MindlessDrone has joined.
16:11:22 <tromp_> 47 bits for the Ackerman-like g i define there
16:12:04 <shachaf> is all this still non-recursive
16:12:54 <tromp_> but i doubt if the goodstein function can avoid recursion
16:16:43 -!- Sprocklem has joined.
16:17:23 <tromp_> mine is based on F cont succn facn = cont (succ succn) (succn * facn)
16:17:30 <tromp_> what's yours based on?
16:19:44 <int-e> it's \n\f. n (\f\n. n (f (succ n))) (\_. f) 1 ... it operates on f^k, where k is 1, n, n*(n-1), n*(n-1)*(n-2) etc.
16:21:29 -!- Bike has joined.
16:21:36 <Jafet> At this point you might as well brute force it
16:22:38 -!- Sprocklem has quit (Ping timeout: 240 seconds).
16:25:14 <Jafet> <a href="http://java.sun.com/">C++</a> good link
16:25:58 -!- adu has quit (Ping timeout: 240 seconds).
16:34:19 <FireFly> "Writing a BLC8 interpreter in Brainfuck, which would provide a matching upper bound in the other direction, is left as an exercise for die-hard Brainfuck programmers." ince
16:35:14 <tromp_> i dont expect anyone to ever take up that challenge:)
16:36:03 <tromp_> it's gonna be so horridly slow that you'd have trouble checking that it works
16:36:37 <tromp_> at least the direction i took is pretty efficient
16:37:25 <Jafet> c2bf might be only a few patches away from being up to the task
16:38:08 <Jafet> C is nearly as bad at memory management as brainfuck, however
16:38:49 <int-e> at least it has pointers
16:39:28 <int-e> In fact I disagree completely with that statement.
16:40:21 <int-e> In Brainfuck you find yourself playing Hilbert's Hotel games all the time. That doesn't really happen in C.
16:41:46 <Jafet> By C I mean the subset of C implemented by c2bf.
16:41:48 <int-e> ("Oh I will put this data on cells divisible by 3, that data on cells with remainder 1 modulo 3, and the cells with remainder 2 modulo 3 will be mostly zero except for one or two bookmarks to guide my code")
16:42:31 <int-e> maybe you should call it c2bf-C
16:44:39 <Jafet> Apparently, c2bf has a "heap" stride but there is no malloc. It'll probably need to be implemented using inline assembly manipulating the heap.
16:45:17 -!- AnotherTest has joined.
16:47:27 <tromp_> you can view the tape as 2-dimensional, with the ith row being cells 1*2^i,3*2^i,5*2^i ...
16:48:08 <Bike> i demand a hilbert space tapej
16:48:12 <tromp_> each successive row being twice as spread out
16:56:59 <mroman_> I demand a bf like language where +-,. are illegal on cells where |index| isn't prime .
16:58:50 <mroman_> Everything is a bf derivative .
16:59:20 <mroman_> nortti: Doesn't have to be brainfuck
16:59:28 <mroman_> but I'd wonder whether you could find your way to the next cell
17:01:14 <Jafet> The number of reachable cells is limited by the size of the program
17:03:30 <mroman_> Not if you find an algorithm that searches for the next valid cell
17:03:52 <nortti> but how do you get there if +-,. are illegal?
17:04:03 <Jafet> It cannot, because it cannot mark the cells on the way to the next valid cell
17:04:19 <Bike> isn't three-cell brainfuck turing-complete? so just use 235 for everything.
17:04:32 <int-e> Bike: that assumes unbounded cells
17:06:17 <Jafet> @oeis 2,3,7,23,89,113
17:06:18 <lambdabot> Increasing gaps between primes (lower end): primes p(k) where p(k+1)-p(k) ex...
17:07:42 <int-e> it's easy to prove that arbitrary long gaps in the sequence of primes exist, just use the CRT to find some n such that n, n+1, ..., n+k are divisible by the first k+1 primes, respectively.
17:11:39 -!- Sprocklem has joined.
17:14:29 <Jafet> > fix (\f ((p,g):ps) -> (p,g) : f (filter ((>g).snd) ps)) $ zipWith ((.)<$>(,)<*>subtract) <*> tail $ nubBy (((>1).).gcd) [2..]
17:15:00 <Jafet> > take 10 $ fix (\f ((p,g):ps) -> (p,g) : f (filter ((>g).snd) ps)) $ zipWith ((.)<$>(,)<*>subtract) <*> tail $ nubBy (((>1).).gcd) [2..]
17:15:26 <Jafet> > take 10 $ fix (\f ((p,g):ps) -> (p,g) : f (filter ((>g).snd) ps)) $ zipWith ((.)<$>(,)<*>subtract) <*> tail $ nubBy (((>1).).gcd) [2..]
17:15:28 <lambdabot> [(2,1),(3,2),(7,4),(23,6),(89,8),(113,14),(523,18),(887,20),(1129,22),(1327,...
17:18:24 <Jafet> > map (text . printf "%.3f") $ zipWith (flip (/)) <*> tail $ [2,3,7,23,89,113,523,887,1129,1327,9551,15683,19609,31397,155921]
17:18:26 <lambdabot> [1.500,2.333,3.286,3.870,1.270,4.628,1.696,1.273,1.175,7.197,1.642,1.250,1.6...
17:20:17 <HackEgo> cercoin yourchiewucoin smocoin cottscoin oisorcoin ncommecoin apfcoin cutercoin petropricoin musissivcoin brazhdcoin varspncumercoin bisc-x86coin kitcoin bradablecoin wordfuctusioncoin ihaxcoin glassendseemeditegrofrcoin kirstecoin skullacoin
17:20:27 <lambdabot> Concatenation of the prime power factors (with maximal exponent) of n; a(1) ...
17:20:43 <lambdabot> Numbers that are the sum of at most 5 positive 5-th powers.[0,1,2,3,4,5,32,3...
17:21:02 <lambdabot> Every base 6 digit of n is a base 10 digit of n.[1,2,3,4,5,35,123,154,215,33...
17:21:37 <myname> this is the reason why people complain about "find the next number" puzzles
17:21:55 <kmc> @oeis 3,1,3,3,7
17:22:00 <lambdabot> 2^A000120(n)-1.[0,1,1,3,1,3,3,7,1,3,3,7,3,7,7,15,1,3,3,7,3,7,7,15,3,7,7,15,7...
17:22:19 <myname> "1, 2, 3, 4, 5, x" "x = 6!" "don't be silly, x = 35"
17:22:27 <Jafet> Wow very much 1337
17:22:52 <kmc> @oeis 8,6,7,5,3,0,9
17:22:53 <lambdabot> Decimal expansion of (7^(e - 1/e) - 9)*Pi^2, also known as Jenny's constant....
17:22:55 <myname> let's invent a sequence
17:23:54 <kmc> @oeis 14,23,28,33,42,51,59,68,77,86,96,103,110,116,125
17:23:55 <lambdabot> Numbered stops in Manhattan on the Lexington Avenue subway.[8,14,23,28,33,42...
17:23:57 -!- conehead has quit (Ping timeout: 258 seconds).
17:24:05 -!- conehead_ has joined.
17:24:12 <mroman_> @oeis 3,6,9,21,24,27,30,33,36,42
17:24:13 <lambdabot> Numbers n such that 2*n^2 + 1 is prime.[1,3,6,9,21,24,27,30,33,36,42,45,66,7...
17:25:19 -!- conehead_ has changed nick to conehead.
17:26:30 <FireFly> I'm actually surprised there isn't a sequence for [A-Za-z]
17:27:47 <myname> @oeis 53,54,55,57,58,63,64
17:28:13 <myname> maybe it only lists infinite sequences
17:28:14 <kmc> @oeis 14,18,23,28,34,42
17:28:14 <lambdabot> Local stops on New York City Broadway line (IRT #1) subway.[14,18,23,28,34,4...
17:28:33 <kmc> the lexington avenue subway does not have an infinite number of stops
17:28:33 <myname> wait, that does kind of contradicts the subway stuff
17:28:34 <FireFly> I hope "Numbered stops in Manhattan on Lexington Avenue subway" isn't infinite
17:28:42 <kmc> space-filling subway
17:29:28 <FireFly> It's a long ride, as they say
17:30:16 <Jafet> There are also the sequences that may or may not be infinite
17:30:32 <kmc> https://www.youtube.com/watch?v=aP1bvY7IqZY
17:31:46 <lambdabot> Mersenne exponents: primes p such that 2^p - 1 is prime. Then 2^p - 1 is cal...
17:33:06 <lambdabot> Triangle of Mahonian numbers T(n,k): coefficients in expansion of Product_{i...
17:34:22 <lambdabot> Numbers n such that 2*n^2 + 3 is prime.[0,1,2,5,7,8,22,23,28,37,40,43,47,50,...
17:34:38 <mroman_> they must have a really large database
17:34:59 <Bike> well, yeah, it's been running for like a billion years too
17:35:24 <Bike> "over 220000 sequences"
17:35:26 <int-e> hmm. my brute force blc search only goes up to 38 bits (doing up to 1000 reductions on each term)
17:36:10 <int-e> (38 is as far as it gets within an hour)
17:36:32 -!- Sprocklem has quit (Quit: leaving).
17:37:13 <Jafet> Free time on the local cluster?
17:37:16 <int-e> the predecessor function (with 0 -> 0) is another hard one.
17:37:27 -!- drdanmaku has joined.
17:38:00 <int-e> (my best is 43 bits)
17:38:54 <tromp_> yes, i got 43 bits as well
17:39:40 <tromp_> i now got pictures of both pred and fac on my office wall
17:40:38 <myname> what are you talking about
17:41:09 <tromp_> about lambda diagrams http://homepages.cwi.nl/~tromp/cl/diagrams.html
17:41:14 <int-e> binary lambda calculus. again. still. I don't know.
17:45:16 -!- Tod-Autojoined has quit (Quit: This is me, signing off. Probably rebooting or something.).
17:45:30 -!- TodPunk has joined.
17:46:58 <myname> i don't get the K example
17:46:58 <Jafet> Wait, how many 38-bit blc programs are there?
17:47:19 <Taneb> Somewhere up to 2^32
17:47:50 <Jafet> Oh, I thought int-e tested 2^38 programs in one hour.
17:48:47 <Taneb> I'd imagine a lot of them are invalid or don't terminate in a nasty way
17:48:48 <tromp_> @oeis 0, 0, 0, 0, 1, 0, 1, 1, 2, 1, 6, 5, 13, 14, 37, 44, 101, 134, 298, 431, 883
17:48:48 <lambdabot> The number of closed lambda calculus terms of size n, where size(lambda x.M)...
17:49:08 <tromp_> https://oeis.org/A114852
17:49:33 <tromp_> 38071898 of size exactly 38
17:49:45 <Taneb> See, less than 2^32
17:50:44 <myname> okay, i start getting it
17:50:55 <tromp_> hmmm, https://oeis.org/search?q=brainfuck&sort=&language=&go=Search
17:54:33 <int-e> right. 82811806 total.
17:54:33 <Jafet> Hmm, I do have free time on a cluster
17:54:59 <int-e> waste of resources, one should first write a faster evaluator.
17:55:46 -!- shikhout has joined.
17:57:41 <tromp_> the ultimate blc challenge is finding more bits of the halting probability omega
17:57:52 <tromp_> i've only managed the first 4 bits
17:58:10 <tromp_> it requires deciding halting behaviour of many programs
17:58:44 -!- shikhin has quit (Ping timeout: 255 seconds).
17:58:53 <tromp_> only a finite number of omgae bits can ever be proven
17:59:11 <int-e> in a fixed, consistent logic
17:59:36 <tromp_> yes, more can be proven in inconsistent logic:)
17:59:54 <tromp_> in fact such logic proves they're all
17:59:56 <tromp_> in fact such logic proves they're all 0
18:00:22 <FireFly> I remember when that was posted to /r/haskell
18:03:09 <kmc> can you say more about why only a finite number of bits can be proven?
18:03:40 <tromp_> by a close analog of berry's paradox
18:04:11 <tromp_> let's say you can enumerate theorems of the form K(x) >= n
18:04:37 <tromp_> that give lower bounds on Kolmogorov complexity of finite strings
18:04:53 <int-e> hmm. I wonder which is the "best" memo library on hackage. (I'm using memotrie but only because that's the first usable one I found)
18:04:58 <tromp_> i.e. there is no blc program less than n bits that outputs x
18:05:41 <tromp_> then you can write a short program that enumerates such theorems until it finds one with n >= N, and outputs the corresponding x
18:06:42 <tromp_> this would show K(x) < logN + O(1), a contradition for large enough N
18:07:10 <tromp_> so any consistent theory can only prove finitely many theorems of that form
18:07:50 <tromp_> the argument for bits of omega is a little more technical
18:08:20 <tromp_> but basically, if you have the first n bits of omega, you can identify all x with K(x) <=n
18:08:36 <tromp_> and thus also an x with K() > n
18:11:11 <tromp_> i like Data.MemoCombinators
18:13:08 <tromp_> in fact i used that for the OEIS entry: https://oeis.org/A114852/a114852.hs.txt
18:14:14 <tromp_> but also for April 2014's Ponder This problem, where i needed to memoize a function on a bounded list of Integers
18:14:30 <Bike> eh, referring to memoization and dynamic programming asthe same thing...
18:15:33 <Bike> i'm disappointed that Memo.integral means integers and not, somehow, integration
18:17:08 <kmc> newest band name: Gigabit Bonghit
18:17:33 <kmc> http://gigabit.bonghit
18:18:38 <Bike> i clicked that, thinking it would lead somewhere
18:18:43 <Bike> thanks again, ICANN
18:18:47 <kmc> you can't tell anymore
18:18:58 <kmc> ICANN has cheezburger
18:20:16 <int-e> Bike: Yes that confusion happens a lot. To be fair, memoization is a very common implementation strategy for dynamic programming.
18:22:03 <Bike> unrelatedly, does anyone else think it's funny when fib is used as an example for recursion and memoization, since you can do it way better with linalg
18:22:37 <int-e> tromp_: what I like about memotrie (possibly because I came up with the same design at some point) is the split memo = untrie . trie, where 'trie' and 'untrie' give you access to the actual data structure used for memoization.
18:23:10 <int-e> tromp_: (personally I call 'trie' 'populate' and 'untrie' 'loopkup', but that's just colors of a bikeshed)
18:23:17 <shachaf> int-e: everyone came up with the same design at the same time, or so i hear
18:23:20 <Bike> i prefer salmon
18:23:51 <int-e> shachaf: not everyone; plenty of memoization libraries revolve around 'memo'.
18:24:27 <shachaf> conal and luqui released their memoization libraries within hours of each other or something
18:25:11 <Jafet> `run words --eng-1M 1000 | grep -o '\w*b' | sed 's/$/ong/' | sort | uniq | /usr/bin/paste -sd\ | head -n 20
18:25:33 <Jafet> `run words --esolangs 1000 | grep -o '\w*b' | sed 's/$/ong/' | sort | uniq | head -n 20 | /usr/bin/paste -sd\ | rainwords
18:25:38 <int-e> Bike: I think it's a fine exemple for introducing the memoization concept. You want people to think about the structure of the computation rather than the actual computed values.
18:26:12 <myname> just for my understanding: in the K lambda diagram, one could have left out the upper half of the vertical bar?
18:26:35 <Bike> it's a good example for recursion too, i just imagine a million programmers using these implementations in actual programs
18:27:03 <int-e> Bike: fortunately fibonacci numbers aren't all that useful in practice ;-)
18:27:21 <Bike> how rude! i have to simulate fuckbunnies all the time
18:27:24 <int-e> especially the larger ones where the linear algebra starts to pay off.
18:27:34 <Jafet> But memofib is such algebraic, much compositional
18:29:05 <Bike> unlike linear algebra
18:35:31 <jconn> FireFly: |value error: mp
18:36:53 <int-e> > fix ((0:) . scanl (+) 1)
18:36:54 <lambdabot> [0,1,1,2,3,5,8,13,21,34,55,89,144,233,377,610,987,1597,2584,4181,6765,10946,...
18:36:56 -!- ^v has joined.
18:38:04 <int-e> a fixed point combinator
18:38:36 <lambdabot> "*Exception: *Exception: *Exception: *Exception: *Exception: *Exception: *Ex...
18:39:19 <int-e> (Sorry, that one is getting old.)
18:41:05 <jconn> FireFly: +---+---+---+---+---+----+-----+-----+-----+-----+
18:41:05 <jconn> FireFly: |0 1|1 1|1 2|2 3|3 5|5 8| 8 13|13 21|21 34|34 55|
18:41:05 <jconn> FireFly: |1 1|1 2|2 3|3 5|5 8|8 13|13 21|21 34|34 55|55 89|
18:41:05 <jconn> FireFly: +---+---+---+---+---+----+-----+-----+-----+-----+
18:42:30 <nortti> oh of course j, the language whose linenoisiness is only beated by teco
18:42:53 <int-e> at least it's ASCII
18:42:59 <myname> what is teco? it sounds like i want to learn it
18:43:02 <Bike> can you really say that in the land of haskell oneliners...........
18:43:07 <Bike> teco is the editor emacs is based on, or something
18:43:12 <int-e> emacs = editor macros (for teco)
18:43:31 <FireFly> teco is like the esotericest esolang ever
18:43:44 <nortti> teco actually does not resemble emacs in normal use at all
18:43:45 <int-e> I understand that it (emacs) wasn't based on Lisp at that time.
18:43:55 <FireFly> and people used it seriously!
18:44:05 <int-e> I used ed seriously
18:44:19 <nortti> int-e: yep, it was basically a screen editor written in a scripting language for another editor
18:44:42 <int-e> (ok. a clone that was implemented in lpmud)
18:45:09 -!- shikhout has changed nick to shikhin.
18:46:07 <int-e> Actually that's about the fragment of vi that I know to use. I use emacs for larger edits.
18:46:28 <myname> so, emacs was written with an editor that was written in a language for a third editor?
18:46:37 <int-e> (where s/vi/vim/ because I use the cursor keys)
18:47:18 <nortti> myname: no, it run on the teco editor's scripting language
18:47:29 <int-e> and how did we end up discussing text editors anyway ... such a loaded topic is best avoided on programming channels. :)
18:48:11 <nortti> there are things to avoid. politics, religion and text editors (or is that part of the second one?)
18:49:05 <Bike> it came up because nortti mentioned it, like, five minutes ago
18:50:06 <FireFly> So, uh, thoughts on Unity?
18:50:17 * FireFly attempts to divert the channel to a less controversial topic
18:50:44 <Bike> terrible. literally the antichrist, foretold in the holy texts
18:50:57 <nortti> last I used it (12.04?) it was still kinda buggy but I could see how they could make it usable
18:51:17 <nortti> then again, I could more easily see how they could fuck it up completely
18:51:31 <int-e> I have not yet had the displeasure of using Unity, and I have no plans to change that.
18:51:42 <Bike> usability doesn't matter. it's perfect and it's evil
18:52:02 <Bike> once its market share has increased the goat shall release the third seal
18:53:29 <int-e> yay, DDG ranks the game engine before the desktop environment.
18:55:27 <Bike> probably ranks gnomes before gnome as well
18:56:06 <nortti> nope, gnome.org is the highest
18:59:46 <Melvar> I am somewhat worried that I haven’t seen a serious project to provide a waylandish xmonad-alike yet.
19:00:02 <Bike> what, is xmonad that tied to x
19:00:22 <nortti> uh, in wayland the wm itself also does display server
19:01:42 * nortti wonders into how small space can be a complete wayland impl be fitted into
19:02:05 <FireFly> I'm a bit worried about that too.. I've been meaning to try out wayland, but I've gotten too used to tiling window managers to be comfortable with weston
19:06:06 -!- tertu has joined.
19:13:22 <fungot> FireFly: i didn't mention that. i think there's my name in for a bit more
19:15:36 <kmc> this is also why i'd have a hard time switching to OS X
19:15:40 <kmc> that and the dismal state of package management
19:18:59 <Bike> what is why? because fungot didn't mention that?
19:18:59 <fungot> Bike: eck, not for efficient programming :)
19:20:08 -!- conehead_ has joined.
19:22:22 <kmc> perhaps fungot will fix my makefile
19:22:22 <fungot> kmc: i'm building off of esr's pronouncements is highly questionable.
19:23:05 -!- conehead has quit (Ping timeout: 264 seconds).
19:34:52 <fowl> they put quantum::superpositions in perl6 lol
19:35:09 -!- ^v has quit (Read error: Connection reset by peer).
19:35:14 -!- AnotherTest has quit (Ping timeout: 240 seconds).
19:35:21 <FireFly> Is that for the & and | (or whatever it was) operators?
19:35:37 -!- ^v has joined.
19:36:03 <FireFly> I never really understood them
19:37:02 <nortti> were those the ones detailed in the talk about perl and physics?
19:39:35 <FireFly> I don't know, but they're explained in http://en.wikipedia.org/wiki/Perl6#Junctions
19:47:43 -!- mhi^ has quit (Quit: Lost terminal).
19:48:29 -!- ^v has quit (Ping timeout: 252 seconds).
19:49:57 -!- ^v has joined.
19:56:35 -!- mhi^ has joined.
19:59:07 -!- Sprocklem has joined.
20:04:41 -!- ^v has quit (Quit: http://i.imgur.com/Akc6r.gif).
20:07:31 -!- tertu has quit (Ping timeout: 240 seconds).
20:16:16 -!- tertu has joined.
20:21:50 -!- quintopia has quit (Ping timeout: 255 seconds).
20:26:11 -!- tertu has quit (Disconnected by services).
20:26:11 -!- ter2 has joined.
20:31:27 -!- nucular has quit (Quit: Excess Food).
20:35:14 -!- Bike has quit (Ping timeout: 258 seconds).
20:36:51 -!- Bike has joined.
20:49:01 -!- tertu3 has joined.
20:49:14 <int-e> tromp_: would 0000101110110 = \\(0 2 1) ==> U(p,z) = <2,z> contribute to the halting probability or is it limited to closed terms?
20:50:58 -!- oerjan has joined.
20:51:27 <kmc> impl<'sink, In, Out, Hold: TreeHandle<In, Out>, Sink: TreeSink<In, Out, Hold>> TreeBuilder<'sink, Sink> {
20:52:49 -!- ter2 has quit (Ping timeout: 276 seconds).
20:52:58 <oerjan> is kmc making an esolang
20:53:17 <FireFly> Yeah, I think it's called "rust"
20:53:23 <kmc> that depends, is HTML parsing turing complete?
20:53:26 <kmc> i'm not making Rust
20:53:28 <kmc> just using it
20:53:38 <kmc> well I have a few patches in rust
20:53:54 <FireFly> Contributing to an esolang, then :P
20:54:03 <kmc> it's less eso than C++
20:54:06 <int-e> tromp_: Oh. I see you're "only" requring the <_,z> context to be in normal form. that also answers my question then.
20:55:01 <kmc> hm I have 10 commits in rust, that's more than I thought
20:55:17 <kmc> several of them are in code that no longer exists
20:55:18 <oerjan> my wild guess is that standard html parsing is not tc but that html-that's-actually-used parsing is.
20:55:23 <kmc> two of them are fixing the same thing that broke twice
20:55:31 <kmc> oerjan: the idea of HTML5 is to unify those two things
20:56:28 <oerjan> so probably uncomputable, then.
20:56:49 <kmc> it's a precise spec for how to handle even very broken content, so that all browsers will do it the same way
20:57:02 <kmc> as a result it's stupifyingly complicated
20:59:42 <monotone> The spec is really just taking the crazy way in which browsers have already been parsing broken HTML and formalizing it so that you can continue to write the same broken HTML in perpetuity.
21:00:05 <kmc> well, yes and no
21:00:14 <kmc> it specifies which constructs are considered broken
21:00:23 <kmc> conformance checkers will reject them, but their meaning is still specified
21:01:01 <tromp_> int-e: yeah, the halting prob. definition is subtle. i believe the normal form requirement is necessary to allow identifying all programs that contribute to an omega prefix
21:01:18 -!- MindlessDrone has quit (Quit: MindlessDrone).
21:01:37 <monotone> Yeah, but that's not really different than how it's been previously. The upshot is that it still renders.
21:02:47 <FireFly> IE6 somehow manages to parse tag-soup mess into where an element could have a child whose parent isn't the first element
21:03:12 <tromp_> i don't want to have U(p:z) = <z,z> in there either
21:04:41 -!- Patashu has joined.
21:05:00 <monotone> The non-tree DOM, right? Looking at the graphs for those was "fun."
21:05:26 <int-e> tromp_: Actually, why not? As long as it reaches that point without looking at the 'z' part ... hmm. Tricky.
21:06:01 <FireFly> monotone: yeah, Hixie has some fun diagrams in an old blog post: http://ln.hixie.ch/?start=1037910467&count=1
21:06:33 <int-e> tromp_: Anyway it looks to me like you have no unique definition of \Omega. The BLC.pdf draft does not mention a normal form property at all, stating that you might just as well not have it.
21:06:42 <oerjan> <tromp_> but i doubt if the goodstein function can avoid recursion <-- i wonder if the functions expressible in system F are the same as those that can be proved total in peano arithmetic, or something like that.
21:07:24 <tromp_> i want to be able to prove the famous symmetry of information thm
21:07:27 <int-e> oerjan: that excludes fix?
21:07:47 <oerjan> for this purpose, at least
21:08:00 <tromp_> that paper has an obsolete definition:(
21:08:33 <kmc> non-tree DOM? :(
21:08:44 <kmc> this is why we can't have nice things
21:09:09 <FireFly> I wonder how the HTML5 algorithm would parse that example..
21:09:17 -!- Sprocklem has quit (Quit: Watching rugby).
21:09:23 <oerjan> int-e: but importantly, it includes church numerals.
21:09:29 <tromp_> to prove symmetry of information, you must be able to take any halting computation and see if the output is a pair starting with some given x
21:09:41 <oerjan> (forall a. (a -> a) -> a -> a)
21:10:07 <int-e> tromp_: anyway, as I read it, 'z' would be a symbolic variable (to prevent the program from inspecting the input beyond the "consumed" part), but then z is also a normal form, so U(p:z) = <z,z> would be allowed.
21:13:19 <oerjan> oh hm no system F is stronger than that https://en.wikipedia.org/wiki/Second-order_arithmetic#Definable_functions_of_second-order_arithmetic
21:13:20 <tromp_> NF should be closed terms
21:15:25 <kmc> FireFly: http://www.whatwg.org/specs/web-apps/current-work/multipage/the-end.html#misnested-tags:-b-i-/b-/i
21:15:43 <tromp_> i've been meaning to rewrite that paper for ages:( always other stuff getting in the way
21:16:02 <tromp_> right now i'm preoccupied both with cuckoo cycle and 8x8 connect-4 :(
21:16:17 <kmc> what are you doing with connect 4?
21:16:24 <int-e> (is that standard? in first order term rewriting, free variables are everywhere (there's no way to bind them...))
21:17:01 <int-e> so variables as normal forms are also everywhere.
21:17:04 <kmc> as in which player wins with optimal play?
21:17:26 <int-e> width 8 ... oh that would upset my intuition about the game a lot.
21:17:36 <kmc> how are you going about it?
21:17:47 <tromp_> i should edit that article to make explicit what that i mean closed normal forms, int-e
21:18:36 <FireFly> kmc: hm, that seems to match the Mozilla behaviour from 2002
21:18:46 <tromp_> well, i have a solver that works some dozen plies into the game
21:18:57 <int-e> kmc: you should see http://homepages.cwi.nl/~tromp/c4/c4.html
21:18:58 <FireFly> the element cloning is a bit bizarre, but it's invalid to begin with so I guess it doesn't matter too much
21:19:03 <tromp_> now i need to play lots of games and build an opening library
21:19:55 <oerjan> tromp_: the last link + the first parentheses in https://en.wikipedia.org/wiki/Goodstein%27s_theorem would seem to imply that the goodstein function _can_ be expressed in system F.
21:22:34 <tromp_> you mean "The Power of a Detour via Infinity", oerjan?
21:22:57 <oerjan> no, i mean _my_ last link https://en.wikipedia.org/wiki/Second-order_arithmetic#Definable_functions_of_second-order_arithmetic
21:23:58 <oerjan> i realized my sentence was ambiguous and that's why i changed to "that"
21:24:42 <tromp_> hmm, how does definability in system F related to definability without recursion? is that equivalent?
21:24:55 <oerjan> system F has no recursion
21:25:12 <oerjan> it's rank-N typed lambda calculus
21:26:39 <tromp_> ic. so i should be able to redefine my function g without using haskell's recursion
21:27:06 <tromp_> but it may not be pretty:-(
21:27:25 -!- Patashu has quit (Ping timeout: 265 seconds).
21:27:56 <int-e> tromp_: the church numeral thing should JUST WORK, if you give church numerals the right type (forall a. (a -> a) -> a -> a)
21:28:04 <oerjan> i'd sort of expect you'd need to represent ordinals.
21:28:40 <oerjan> yes, another property of system F is that you can _define_ church numerals as the terms of that type
21:29:21 <oerjan> this also works for church representations of many other data types
21:31:30 <oerjan> e.g. the only system F terms of type forall a. a -> a -> a are the church booleans
21:32:47 <oerjan> system F is the original system with parametricity, and unlike haskell's version there are no subtle caveats for when it applies.
21:37:29 <kmc> http://s.cow
21:37:45 <kmc> https://cow
21:38:12 <oerjan> tromp_: btw if the implementation of g in system F depends heavily on higher rank types, then it's likely you may need explicit type annotations to make it compile as haskell.
21:38:29 -!- augur has quit (Ping timeout: 258 seconds).
21:38:34 <oerjan> (with ghc's rank-n extension)
21:39:17 -!- Bike has quit (Ping timeout: 264 seconds).
21:39:44 <oerjan> because haskell's type inference only infers rank-2 types with all foralls outermost.
21:40:27 <oerjan> i'm not sure if that is considered rank-2
21:41:02 -!- Bike has joined.
21:41:08 <shachaf> ghc doesn't infer rankine types hth
21:42:23 <oerjan> `frink 100 rankine -> kelvin
21:42:28 <HackEgo> Warning: undefined symbol "rankine". \ Warning: undefined symbol "rankine". \ Unconvertable expression: \ 100 rankine (undefined symbol) -> 1 K (temperature)
21:43:00 <shachaf> apparently frink doesn't support them at all
21:43:05 <shachaf> even with explicit annotations
21:44:29 -!- Phantom__Hoover has quit (Ping timeout: 250 seconds).
21:52:28 <FireFly> I didn't even know about it. Is it actually used for anything?
21:52:34 <FireFly> It seems like a terrible scale
21:54:05 <kmc> I think a lot of engineering in the US is still done with ye olde units
21:54:45 * kmc wonders if BART gauge is 1676 mm or 5'6"
21:56:42 <kmc> a difference of 400 microns
21:57:20 <kmc> 100 microns sounds much smaller than 0.1 mm
21:57:25 <Taneb> Isn't that less than the error caused by heat fluctuations?
21:57:26 -!- Phantom__Hoover has joined.
21:57:31 <kmc> Taneb: probably
21:57:57 <oerjan> <int-e> it's easy to prove that arbitrary long gaps in the sequence of primes exist, just use the CRT [...] <-- n! + i, i = 2..n hth
22:06:53 <kmc> Taneb: hm, no, I think it's about an order of magnitude larger
22:07:37 <kmc> steel expands by a factor of 13e-6 / °C; record temperature range in SF is 43 °C
22:08:04 <Taneb> What's really scary is the age of my university is of the same order of magnitude as my age
22:08:16 <kmc> top of a rail is about 7 cm
22:08:23 -!- HackEgo has quit (Remote host closed the connection).
22:08:33 -!- HackEgo has joined.
22:08:38 <kmc> which comes out to about 40 microns
22:08:53 <Taneb> > 0.01 * 7 * 43 * 13e-6
22:10:06 <lambdabot> mueval-core: L.hs: removeLink: does not exist (No such file or directory)
22:12:33 <int-e> (this reminds me that I don't know for certain why this happens. mueval copies that file to /tmp, but can several muevals run concurrently?)
22:13:57 <olsner> hmm, it copies L.hs to /tmp/L.hs?
22:14:51 <kmc> http://en.wikipedia.org/wiki/Thermal_expansion#Examples_and_applications "Thermal expansion of long continuous sections of rail tracks is the driving force for rail buckling. This phenomenon resulted in 190 train derailments during 1998–2002 in the US alone."
22:15:16 <kmc> i think that's buckling because it gets longer, not thicker
22:15:21 <int-e> olsner: sadly, yes. that's where it puts the temporary haskell file to be loaded, and it doesn't set an include path in ghci
22:15:40 <int-e> where by ghci I mean ghc-as-a-library.
22:18:16 <olsner> then I assume/hope that only one evaluation can be running at a time?
22:18:55 <olsner> is it lambdabot that copies the file and runs mueval on it, or is that in mueval?
22:18:57 <int-e> 00:10:06 <lambdabot> mueval-core: L.hs: removeLink: does not exist (No such file or directory) <-- this is evidence to the contrary
22:19:51 <int-e> which should probably create a temprary subdirectory in /tmp each time instead.
22:20:12 <int-e> just to avoid this problem. oh well.
22:21:53 -!- impomatic has quit (Ping timeout: 264 seconds).
22:26:43 -!- tertu3 has quit (Ping timeout: 240 seconds).
22:35:49 -!- impomatic has joined.
22:36:19 <oerjan> via agora http://www.loweringthebar.net/2014/05/sign-installer-cited.html
22:44:03 -!- Eritzap has joined.
22:45:46 -!- Sgeo has joined.
22:48:05 -!- Eritzap has quit (Client Quit).
22:52:15 <Sgeo> Maybe not part of here
22:53:00 <HackEgo> papacoin flumpezzycoin vergenigmationcoin dupcoin earenamcoin percoin regxcoin fullcoin adedcoin andomcoin carcoin closuricoin inctcoin funandcoin voltacoin bearecoin ozakcoin numpcoin brbcoin acrcoin
22:53:13 <kmc> I think we've seen dupcoin before.
22:53:45 -!- nooodl has quit (Ping timeout: 252 seconds).
22:54:00 <oerjan> kmc: might be a duplicate.
22:54:30 <oerjan> i also have a hunch we'll see brbcoin again
22:55:00 <Sgeo> oerjan: someone in tcl said
22:55:10 <Sgeo> "wow Sgeo i find an interesting language and you are already in channel"
22:59:11 -!- augur has joined.
22:59:54 <oerjan> Sgeo: are you in all the language channels twh
23:00:19 <Sgeo> No, but I'm in a lot of them
23:01:44 -!- yorick has quit (Read error: Connection reset by peer).
23:02:19 -!- mhi^ has quit (Quit: Lost terminal).
23:02:28 <Sgeo> Java, Prolog... actually, seem to be banned from ##prolog :(, Ada, Agda, Atomo, Atomy, Chicken, Clojure, Concatenative (Factor etc.), Dylan, Elixir, Erlang, Guile, Haskell and some associated channels, Idris, Lisp (CL), Pharo, Smalltalk, Racket, Red-lang, Retro, Scala, Scheme, Self-lang, sgeolang, Tcl
23:02:51 <kmc> how did you get banned from ##prolog
23:02:52 <Bike> haha how do you get banned
23:03:05 <kmc> was the ban message "No."?
23:03:37 <oerjan> kmc: nah they just cut him off
23:10:45 * impomatic notes that Sgeo isn't in Forth, Oberon or Pascal :-P
23:11:46 <shachaf> whoa, a language channel that banned Sgeo?
23:12:14 <shachaf> ##prolog: ban *!*@*.dyn.optonline.net
23:12:38 <HackEgo> [wiki] [[Special:Log/delete]] delete * Ehird * deleted "[[Sngscsv]]": content was: "todo" (and the only contributor was "[[Special:Contributions/Dggh|Dggh]]"); possibly spam? feel free to recreate when there's more content
23:13:21 <Sgeo> Why block an entire ISP? :(
23:16:24 <oerjan> Sgeo: if there's an ip-changing troll from there...
23:16:59 <oerjan> (also, i hear cloaks exist.)
23:17:24 <oerjan> actually, do they help against that...
23:28:25 -!- tertu3 has joined.
23:31:57 -!- ter2 has joined.
23:35:24 -!- tertu3 has quit (Ping timeout: 258 seconds).
23:49:27 -!- ter2 has quit (Read error: Connection reset by peer).
23:49:49 -!- ter2 has joined.
23:55:58 <oerjan> <int-e> (ok. a clone that was implemented in lpmud) <-- ooh me to
23:56:09 <oerjan> also i learned lpc before real c
23:56:24 -!- shikhout has joined.
23:56:57 <oerjan> that lpmud ed may be the reason i ended up a vim user
23:59:40 -!- shikhin has quit (Ping timeout: 265 seconds).
00:13:08 -!- ter2 has quit (Ping timeout: 255 seconds).
00:35:53 -!- oerjan has quit (Quit: Nite).
00:37:58 -!- copumpkin has joined.
00:44:16 -!- tertu has joined.
00:45:58 -!- ^v has joined.
00:47:32 -!- ter2 has joined.
00:47:32 -!- tertu has quit (Disconnected by services).
00:50:34 -!- tromp has quit (Ping timeout: 240 seconds).
00:51:06 -!- tertu3 has joined.
00:53:51 -!- ter2 has quit (Ping timeout: 250 seconds).
01:02:55 -!- ter2 has joined.
01:05:45 -!- tertu3 has quit (Ping timeout: 252 seconds).
01:06:05 -!- tromp has joined.
01:06:21 -!- tertu has joined.
01:08:19 -!- ter2 has quit (Ping timeout: 240 seconds).
01:32:14 -!- shikhout has quit (Remote host closed the connection).
01:33:47 -!- ter2 has joined.
01:33:47 -!- tertu has quit (Disconnected by services).
01:41:48 -!- ter2 has quit (Read error: Connection reset by peer).
01:42:12 -!- ter2 has joined.
01:46:39 -!- tertu3 has joined.
01:47:38 -!- Phantom__Hoover has quit (Ping timeout: 240 seconds).
01:49:38 -!- ter2 has quit (Ping timeout: 240 seconds).
01:57:38 -!- tertu3 has quit (Ping timeout: 240 seconds).
02:00:55 -!- atslash has quit (Quit: This computer has gone to sleep).
02:01:31 -!- atslash has joined.
02:06:42 -!- atslash has quit (Quit: This computer has gone to sleep).
02:09:35 -!- tromp has quit (Remote host closed the connection).
02:10:11 -!- tromp has joined.
02:10:19 -!- tertu3 has joined.
02:14:14 -!- tromp has quit (Ping timeout: 240 seconds).
02:42:27 -!- Sorella has quit (Quit: It is tiem!).
02:48:13 <kmc> what's lpc
02:59:35 <Sgeo> bitly is actually encouraging people to change passwords, right?
02:59:49 <Sgeo> Gmail filed the email under spam
03:00:44 <monotone> The notice is on bitly's actual site header, if you're paranoid.
03:01:07 <Sgeo> I'm more worried about Gmail filing it under spam and thus possibly screwing people over
03:01:20 <Sgeo> For anyone who might not check or believe their spam folder
03:01:45 <monotone> Welcome to security notifications in the 21st century...
03:11:03 -!- tromp has joined.
03:11:31 -!- conehead_ has quit (Quit: Computer has gone to sleep).
03:28:28 -!- hk3380 has quit (Ping timeout: 265 seconds).
03:32:41 -!- tertu3 has quit (Ping timeout: 264 seconds).
03:37:20 -!- tertu3 has joined.
03:44:06 -!- ter2 has joined.
03:45:54 -!- tertu3 has quit (Ping timeout: 252 seconds).
03:46:52 -!- tromp has quit (Remote host closed the connection).
03:54:31 -!- tromp has joined.
04:01:10 <kmc> "The exclusive or of two different Gold codes from the same set is another Gold code in some phase."
04:02:00 -!- tromp has quit (Remote host closed the connection).
04:02:32 -!- tromp has joined.
04:03:55 <Sgeo> Why do I have codes?
04:05:07 <Sgeo> My last name is Gold
04:06:34 -!- tromp has quit (Ping timeout: 240 seconds).
04:08:55 <Sgeo> To Randall Munroe: If you're going to reinvent the web, there's a high chance you're more likely to do it sanely than the current web
04:08:56 <kmc> i guess that's why, then
04:12:27 <monotone> Until someone figures out something else that they want to bolt on top and it gets broken again.
04:53:14 -!- password2 has joined.
04:56:24 -!- password2 has quit (Max SendQ exceeded).
04:57:00 -!- password2 has joined.
05:07:34 <HackEgo> bypacoin sodateditcoin poricoin treencoin singercoin bfccoin dateftcoin selfcoin bupercoin frizattcoin shercoin sallcoin bituffcoin reignencoin homocoin muecoin hcriecoin lammcoin prolanshakcoin varcoin
05:30:33 <FireFly> fungot: today's wisdom, please
05:30:33 <fungot> FireFly: and fnord only has guile, i proclaim it sucks. they fixed my favorite bug, or so
05:33:59 <fungot> shachaf: i just clicked on page 3 saying ' refer to diagram' which turns up quite a lot
05:34:31 <shachaf> you know what they say, fungot
05:34:31 <fungot> shachaf: they're all secret pervs.) will that be the main proponents of lolcode, and neither riastradh nor i have lots
05:34:40 <fungot> Available: agora alice c64 ct darwin discworld enron europarl ff7 fisher fungot homestuck ic irc* iwcs jargon lovecraft nethack oots pa qwantz sms speeches ss wp youtube
05:35:31 <myname> why is there a difference between site and side in english? as a german it confuses me pretty often
05:38:58 <FireFly> site in the 'website' sense?
05:39:23 <monotone> They're two etymologically different words that just happen to sound similar.
05:39:49 <FireFly> I just realised they're the same in swedish too, but from the unrelated sv:sida = en:page
05:52:05 <myname> it's both "seite" here
05:52:53 -!- password2 has quit (Ping timeout: 255 seconds).
05:57:26 -!- MindlessDrone has joined.
06:03:25 <lambdabot> Title: Creative, Search & Social | Connected Digital Marketing - WebSide
06:03:30 <lambdabot> Title: WebSight Design: Bay Area Web Design, Development & Hosting
06:03:36 <lambdabot> http://www.youtube.com/user/webseid
06:04:16 <lambdabot> http://de.wikipedia.org/wiki/Webseite
06:05:27 <Jafet> (also, Website /= Webseite.)
06:05:36 -!- ^v has quit (Quit: http://i.imgur.com/Akc6r.gif).
06:22:16 -!- FreeFull has quit.
06:39:07 -!- ter2 has quit (Ping timeout: 276 seconds).
07:18:50 -!- Bike has quit (Ping timeout: 255 seconds).
07:19:18 <FireFly> http://www.cnet.com/news/ancient-d20-die-emerges-from-the-ashes-of-time/
07:26:04 -!- MindlessDrone has quit (Quit: MindlessDrone).
07:31:09 -!- slereah_ has joined.
07:53:25 -!- atslash has joined.
07:58:26 <mroman_> Somebody wants to reinvent the web?
07:58:51 <slereah_> Let's just buy some copper wire and some routers
08:01:05 <FireFly> Didn't Russia say they were going to do approximately that?
08:01:37 <slereah_> They used to have their own network back in the USSR days
08:01:48 <slereah_> Also in France we had the minitel~
08:02:00 <slereah_> The earliest network for the public
08:27:00 -!- Patashu has joined.
08:28:49 -!- quintopia has joined.
08:34:51 <mroman_> Is there yet a 2D language where you have to modell "data flow"?
08:34:58 <mroman_> in addition to instruction flow
08:35:15 <mroman_> i.e. data is stored on the 2D grid itself
08:35:59 <mroman_> (without having a data pointer that points to some cell in the grid)
08:36:18 <mroman_> You'd actually have to move data around.
08:36:55 <Jafet> Wireworld is one that's actually designed to resemble circuits.
08:37:15 <mroman_> http://codepad.org/9f6lWtqu
08:37:28 <mroman_> DULR change directions of the data stream
08:37:40 <mroman_> dulr take data from their "opposite" point and send them
08:37:55 <mroman_> i.e. r takes the data from the cell to the left and sends it rightwards
08:38:05 <mroman_> until it arrives at another data cell
08:38:35 <mroman_> (the above code should calculate a=a+2*r, with a initialized to 2)
08:39:57 <mroman_> http://codepad.org/H1IXEaXj <- like that
08:40:04 <Jafet> Also, circuit layouts are 2D computer languages
08:40:06 <mroman_> there's no interpreter yet. Just sketched out some things in my hand
08:40:28 <mroman_> the result from the addition is moved to the 0 above the *
08:41:23 <mroman_> 2d computer languages with timing constraints ;)
08:53:53 -!- Tod-Autojoined has joined.
08:54:54 -!- TodPunk has quit (Read error: Connection reset by peer).
09:11:23 -!- drdanmaku has quit (Quit: Connection closed for inactivity).
09:20:20 -!- atslash has quit (Ping timeout: 255 seconds).
09:26:53 <FireFly> I don't remember if I ever beat all the Rubicon levels
09:27:10 <FireFly> Or whatever the java-applet game based on RUBE was called
09:29:04 -!- atslash has joined.
09:40:07 -!- edwardk has joined.
09:40:34 -!- atslash has quit (Quit: This computer has gone to sleep).
09:45:09 -!- Patashu_ has joined.
09:45:09 -!- Patashu has quit (Disconnected by services).
09:52:11 -!- sign has quit (Ping timeout: 252 seconds).
10:11:08 -!- ais523 has joined.
10:12:47 -!- boily has joined.
10:17:26 -!- oerjan has joined.
10:28:24 <oerjan> @tell kmc <kmc> what's lpc <-- the interpreted C-like OO language in which lpmuds are mostly programmed.
10:28:46 <oerjan> https://en.wikipedia.org/wiki/LPC_(programming_language)
10:29:16 <myname> http://upload.wikimedia.org/wikipedia/commons/c/c9/Chaos_magic_ritual_involving_videoconferencing.JPG wat
10:34:36 -!- shikhin has joined.
10:48:45 <oerjan> <FireFly> http://www.cnet.com/news/ancient-d20-die-emerges-from-the-ashes-of-time/ <-- argh _two_ tall, space-stealing bars
10:50:55 <oerjan> i am mystified that web designers don't understand how annoying that is on laptop screens
10:51:26 <oerjan> (admittedly, many probably do, which is why i don't see it _everywhere_)
10:53:06 <ais523> oerjan: I've actually been criticised for /not/ doing that on a website
10:53:14 <myname> since when are laptop screens considered different from others?
10:53:19 <ais523> I wanted to post a rant about how that should be a client-side setting, not a server-side setting
10:53:26 <ais523> but I didn't, because I didn't think anyone would care
10:53:30 -!- hk3380 has joined.
10:53:39 <oerjan> myname: they are wider than they are (not very) tall
10:58:25 <oerjan> it may be connected to my absent-minded-ness; when things disappear off screen too fast i forget the context of what i'm reading.
10:58:58 <oerjan> and go into ocpd up-down arrow mode.
10:59:48 -!- Darkgamma has joined.
11:00:08 <oerjan> add to that that i've started to zoom text to strain my eyes less...
11:00:48 -!- atslash has joined.
11:00:50 <oerjan> ...that would be the day the bot is gone.
11:01:02 <boily> `welcome Darkgamma
11:01:03 <HackEgo> /home/hackbot/hackbot.hg/multibot_cmds/lib/limits: line 5: exec: welcome: not found
11:01:13 <oerjan> (Gregor is of course always missing)
11:01:19 <boily> the welcomes are dead!
11:01:21 <ais523> boily: all the welcomes got deleted a while ago
11:01:25 <oerjan> oh bother. just a minute...
11:01:33 <boily> ais523: weren't some restored?
11:01:44 <ais523> Darkgamma: Welcome to the international channel for esolang discussion, development and deployment! Our wiki is available at http://esolangs.org.
11:01:53 <ais523> umm, gah, remembering the welcome message is hard
11:02:06 <ais523> except the first sentence, that was in the topic for /years/, in various variations
11:02:09 <Darkgamma> ais523: yeah, I'm aware of the wiki
11:02:11 <HackEgo> patching file welcome \ patching file r13elcome \ patching file relcome \ patching file rwelcome \ patching file welcome \ patching file welcome13
11:02:17 <HackEgo> /home/hackbot/hackbot.hg/multibot_cmds/lib/limits: line 5: exec: relcome: not found
11:02:28 <oerjan> sorry, undo is also broken :(
11:02:30 <HackEgo> 98076 \ a \ app.sh \ bdsmreclist \ bin \ canary \ cat \ complaints \ :-D \ dog \ etc \ factor \ fb \ fb.c \ head \ hello \ hello.c \ ibin \ index.html \ interps \ lib \ paste \ pref \ prefs \ quines \ quotes \ r13elcome \ relcome \ rwelcome \ share \ src \ test \ Test \ Test.hi \ Test.hs \ UNPA \ welcome \ welcome \ welcome13 \ Wierd \ wisdom \ wi
11:02:41 <ais523> why are the welcomes in the root dir, not bin?
11:02:54 <ais523> anyway, I preferred it when this channel was about esolangs
11:02:57 <oerjan> ais523: because `undo is broken
11:02:58 <ais523> rather than about the welcomebot
11:03:03 <HackEgo> /home/hackbot/hackbot.hg/multibot_cmds/lib/limits: line 5: /hackenv/bin/relcome: Permission denied \ /home/hackbot/hackbot.hg/multibot_cmds/lib/limits: line 5: exec: /hackenv/bin/relcome: cannot execute: Permission denied
11:03:17 <oerjan> `run chmod +x bin/*elcom*
11:03:22 <HackEgo> 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.)
11:03:58 <boily> the balance of the Universe was Restored. now I can go to work.
11:04:09 -!- boily has quit (Quit: don't ask about the chickens.).
11:05:00 <ais523> I actually had an esolang idea a couple of days ago
11:05:11 <ais523> I was working on a program, and writing a bunch of comments to explain why it was doing things
11:05:25 <ais523> Darkgamma: that's to do with your client
11:05:29 <ais523> IRC doesn't have a link syntax
11:05:36 <ais523> so the client tries to parse the link, and some of them get it wrong
11:05:47 <ais523> it's OK, you can have a bunch of conversations in parallel in IRC
11:06:00 <ais523> so after a while you get used to having a bunch of conversations in parallel, sometimes in the same channel, or the same people, or even both
11:06:35 <ais523> anyway, the standard rule is that the source code should say the "what", but it doesn't say the "why", so you need comments to explain it to other developers
11:06:44 <ais523> and my idea was: why don't we explain why the code is doing what it does to the computer?
11:07:14 <ais523> so that if we have an explanation saying "we're doing this so that foo", and it doesn't cause foo, we get a warning or an error
11:07:24 <ais523> then I got a little stuck trying to figure out how you explain a reason to a computer
11:07:35 <oerjan> sheesh, i thought the whole point of enclosing the link in <> was to _decrease_ the chance of clients parsing it wrong
11:07:36 <ais523> my current idea is that you make statements about the future
11:07:52 <mroman_> the only thing really disturbing me is that scrolling on that website is laggy
11:08:01 <ais523> oerjan: blame the qwebirc people, I guess
11:08:07 <oerjan> mroman_: let me guess, you don't see them because no enable javascript?
11:08:25 <ais523> Darkgamma: it's not really like COME FROM
11:08:32 <ais523> it's more like, you make a prediction about the future
11:08:41 <ais523> the compiler tries to prove it, if it can, great
11:08:42 <mroman_> oerjan: I have IE with JavaScript enabled
11:08:47 <ais523> if it can find a counterexample, the program errors out
11:08:58 <ais523> if it can't do either, it puts in runtime checks, and complains if the statement ever appears to be false
11:10:05 <mroman_> 1900 times something I guess
11:10:12 <int-e> forever love; while (love) {}
11:10:20 <ais523> Darkgamma: I don't, really, it's quite a new idea, and one that might not ever be properly fleshed out
11:10:21 <mroman_> If I'd surf with 800x600 things'd probably look different
11:10:25 <ais523> I have enough vaporware languages already
11:10:25 <oerjan> mroman_: they are bars on _top_ and _bottom_
11:10:41 <oerjan> mroman_: i surf with non-maximized window + zoom
11:10:45 <ais523> but innovative esolang ideas are rare, so I like to share them with the channel in case they inspire other people
11:11:22 <oerjan> mroman_: you are looking at http://www.cnet.com/news/ancient-d20-die-emerges-from-the-ashes-of-time/ right?
11:11:31 <Darkgamma> ais523, hm I don't know how it'd end up compiled but doing it in an interpreter seems not extremely difficult
11:11:39 <mroman_> Or are you refering to the ad bar below the menu bar?
11:12:11 <ais523> Darkgamma: yeah, if you're merely making statements like "I do this so that there won't be a divide by zero exception"
11:12:15 <ais523> and then there's a divide by zero exception
11:12:19 <ais523> then that line of code probably isn't doing its job
11:12:31 <mroman_> If I surf with a non-maximized window with 200% zoom those bars take almost 90% of the window
11:13:02 <mroman_> but with normal window size and 100% zoom it doesn't disturb me at all
11:13:09 <oerjan> mroman_: menu at top, menu at bottom. except ... it's suddenly stopped doing that D:
11:13:20 <mroman_> the site is still laggy when scrolling
11:13:32 <oerjan> now it's just the one hovering on top
11:13:40 <oerjan> a while ago it was only bottom.
11:13:48 <oerjan> so i guess the site is just screwy.
11:13:56 <mroman_> I also hate websites that hide the scrollbar on the right
11:14:02 <mroman_> How am I supposed to scroll then
11:14:41 <mroman_> I like scrolling with the left mouse button
11:15:08 <oerjan> ais523: are you reinventing design by contract?
11:15:24 <ais523> there's a difference between a precondition/postcondition, and a reason
11:15:34 <ais523> I'm sort-of inventing asserts, except time-displaced
11:15:42 <ais523> like, the innovation isn't assert(foo);
11:16:06 <ais523> but assert(foo will be 5 even after unrelated function X returns);
11:17:28 <oerjan> mroman_: hm normally on sites with hidden scrollbar it reappears when i move the pointer
11:17:34 <Darkgamma> do you assert that foo will be 5 after a specific function or after any general function
11:17:57 <HackEgo> 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.
11:18:10 <mroman_> letting websites style the scrollbar was a dump idea anyway *i think*
11:18:15 <ais523> oerjan: the wisdom database isn't particularly elucidating, really
11:18:37 <mroman_> I hope they can style the "back" and "forward" button in HTML5
11:18:43 <mroman_> because that would make _so much_ sense
11:18:46 <oerjan> 't use @nick addressing here, and lambdabot keeps us honest
11:19:58 <oerjan> ais523: that's just what an alien would say
11:20:13 <mroman_> I also don't get why browsers don't display a scrollbar on pages where you wouldn't need to scroll
11:20:19 <mroman_> because it makes the window some pixels wider
11:20:27 <mroman_> and when there's enough content, the window is suddenly smaller
11:20:44 <mroman_> and designers freak out because now everything is a little bit displaced when you compare it to a page with less content
11:20:49 <mroman_> so they do stupid things to fix that
11:21:03 <mroman_> like inline scrollbars and shitt
11:21:05 <oerjan> do you have an extraneous "don't" in that first sentence
11:21:16 <mroman_> javascript emulated scrolling or whatever it's called
11:21:21 <ais523> mroman_: can't you just do overflow-y:scroll, or whatever it is?
11:21:49 <mroman_> but then you have a scroll bar sort of in the webpage itself
11:22:52 <mroman_> the best thing you can do is have your menu bars "fixed"
11:22:56 <mroman_> so they don't move while scrolling
11:23:19 <mroman_> and then make some dummy div to extend the webpage to 101% height so that a scrollbar on the right is always there
11:24:16 <mroman_> and some quirks I'm pretty sure are just done to be able to place more ads .
11:25:17 * oerjan suddenly imagines a web browser which is made for ignoring all that enterprisey stuff. it'll be called Lenin, and its tagline should be "Because capitalists should not control the Web."
11:25:55 <mroman_> http://news.slashdot.org/story/14/05/12/2013236/lectures-arent-just-boring-theyre-ineffective-too-study-finds o_O
11:26:04 <oerjan> it'll probably be judged illegal in the US if anyone tried that, though.
11:27:05 <oerjan> mroman_: are you actually surprised at this finding tdnh
11:27:16 <mroman_> But I don't listen to lecturers
11:27:24 <mroman_> And I don't like to participate
11:27:42 <mroman_> I just sit in class for the sake of being physically present
11:27:57 <Taneb> mroman_, I've almost stopped even that
11:28:03 <mroman_> It's not like they're teaching anything new
11:28:25 <mroman_> So far this semester I've only had As
11:28:28 <oerjan> can i offer "teaching methods that teach all people identically aren't effective", then?
11:28:57 <oerjan> (i'm afraid i have no evidence, only foaming prejudice)
11:29:05 <mroman_> Some Exam about Lisp, Prolog, Java Bytecode and Functional Programming
11:29:30 <mroman_> One question just had some Java Bytecode and you had to interpret it like a freaking jvm
11:29:54 <ais523> oerjan: surely they're effective for some subset of people, and ineffective for others?
11:30:18 <mroman_> Like the teachers assume I can't read java bytecode specs
11:30:24 <ais523> I know when I was teaching, the normal aim was to find some method that would work for a decent proportion, then find some method that would work on a decent proportion of the remainders, and so on
11:31:42 <mroman_> I stopped learning for exams that are open book
11:32:16 <Taneb> I probably ought to learn this term's calculus at some point
11:32:30 <mroman_> I just print out spec and cheat sheets and I'm done learning
11:32:33 <ais523> mroman_: my guess is, perhaps it will be later on, but maybe not at the current level
11:32:41 <mroman_> I'll read the specs on the fly during the exam and I'm good
11:32:50 <ais523> admittedly, some exams are "you have to spend a bunch of time trying to figure out wtf the examiner is thinking"
11:32:51 <mroman_> ais523: I'm in my last semester
11:32:56 <ais523> like, you're not trying to learn the subject
11:32:57 <Taneb> I'd go out of your way to learn things just so you don't forget how
11:33:04 <ais523> you're trying to learn how to comprehend the particular lecturer
11:33:14 <oerjan> mroman_: the problem is if you need the things you're supposed to have learned as a basis for your next level of courses.
11:33:16 <ais523> Taneb: well, learning to work from spec sheets is a pretty useful skill
11:33:21 <mroman_> ais523: social engineering is an important skill ;)
11:33:32 <oerjan> which might be more important in math than in computing, i dunno.
11:33:48 <mroman_> oerjan: yeah. That's only important in math classes
11:34:16 <mroman_> but the good thing about that is that different people from different backgrounds can choose the same lecture/class/course
11:34:35 <mroman_> so they can't assume you know things because not everybody has had the same classes as you up to this point
11:34:47 <mroman_> so essentially you don't need to know anything about what last semester happened
11:35:16 <Jafet> So essentially they are proscribed from teaching anything in depth
11:35:18 <Taneb> Not even for prerequisites?
11:35:31 <mroman_> ais523: "current level"... They assume I don't know anything about functional programming
11:35:45 <mroman_> which is a correct assumption for 99.9% of all students
11:35:53 <ais523> I wonder how many people in #esoteric don't know anything about functional programming
11:35:58 <ais523> it's hard to not pick up at least some Haskell if you idle here
11:36:02 <mroman_> but most of their assumptions just don't apply to somebody like me
11:36:20 <mroman_> I've started programming at age 12
11:36:33 <Taneb> Apparently the second-year compilers module here uses Haskell for parsing, but doesn't really teach it beyond "here's do notation and parsec. Write a parser"
11:36:36 <mroman_> I knew haskell before I was 18
11:36:52 <ais523> I didn't know Haskell before I was 18, but it wasn't very mainstream back then
11:36:59 <Taneb> And someone wrote idiomatic Haskell in Applicative style.
11:37:17 <mroman_> Taneb: most things with parsec can be done by try and <|> anyway ;)
11:37:24 <Taneb> The person marking/evaluating/whatever it looked at it and nodded, confused
11:37:30 <mroman_> and some of oneOf, many1, string, char
11:37:42 <ais523> Taneb: I've seen people try to mark things wrong because they don't understand them :-(
11:37:55 <oerjan> haskell didn't exist when i was 18 hth
11:38:04 <Taneb> ais523, the marker had to say "I'm going to have to trust you on this one"
11:38:17 <mroman_> oerjan: Why are you ending every single sentence with hth
11:38:18 <Taneb> oerjan, when I was 18 I knew lens
11:38:30 <ais523> Taneb: there have been cases where people had to ask me to check them
11:38:33 <Taneb> mroman_, it's Norwegian for the full stop
11:38:56 <oerjan> mroman_: it's probably my inner seething anger seeping out
11:40:11 <Taneb> On my 18th birthday, lens-3.1 was a thing
11:40:25 <Taneb> I hope you all feel old
11:43:31 <oerjan> mroman_: also, your admonishment gets somewhat weakened by my quick checking finding _no_ other instance of hth since i joined the channel (although one tdnh). i may have missed one but still...
11:46:11 * oerjan whacks Taneb with his cane =======Ø
11:46:14 -!- ais523 has quit.
11:50:08 <Darkgamma> I don't have a clue about Haskell except that it's a functional prog. language
11:50:23 <mroman_> it's not every single sentence
11:50:34 <mroman_> it just appears like you use it often
11:51:06 <mroman_> so often that my mind replaces your nick with "they who uses hth at the end of sentences"
11:51:13 <mroman_> I've no idea what hth is btw
11:51:20 <HackEgo> hth is help received from a hairy toe. It is not at all hambiguitous.
11:51:36 <HackEgo> twh would help, but is an hth derivative. hth. twh. hand.
11:52:09 <oerjan> > nubBy(((>1).).gcd)[2..]
11:52:11 <lambdabot> mueval-core: L.hs: removeLink: does not exist (No such file or directory)
11:52:15 <oerjan> > nubBy(((>1).).gcd)[2..]
11:52:17 <lambdabot> [2,3,5,7,11,13,17,19,23,29,31,37,41,43,47,53,59,61,67,71,73,79,83,89,97,101,...
11:52:21 -!- Froox has quit (Quit: *bubbles away*).
11:52:31 <oerjan> Darkgamma: haskell hth ^
11:54:11 <Jafet> > (!!3)<$>transpose[show$foldr(\k a->2*10^2^n+a*k`div`(2*k+1))0[1..2^n]|n<-[0..]]
11:54:14 <lambdabot> "314159265358979323846264338327950288419716939937510582097494459230781640628...
11:54:55 <oerjan> is that using plouffe's algorithm
11:56:15 <lambdabot> [0,1,1,2,3,5,8,13,21,34,55,89,144,233,377,610,987,1597,2584,4181,6765,10946,...
11:56:44 <oerjan> that should cover the obligatory par for the course
11:57:46 <Darkgamma> puts zero, then adds one, then adds the last two
11:59:04 <oerjan> sort of, although in a bit roundabout way
11:59:25 <oerjan> > let fib = 0:1:zipWith(+) fib (tail fib) in fib -- less obscurely
11:59:27 <lambdabot> [0,1,1,2,3,5,8,13,21,34,55,89,144,233,377,610,987,1597,2584,4181,6765,10946,...
11:59:34 <fizzie> oerjan: http://sprunge.us/YKdM hth
12:00:15 <oerjan> fizzie: wow this changes EVERYTHING
12:00:22 <oerjan> mroman_: i'm not even on TOP hth
12:00:36 <fizzie> I think the distribution looked very different some months back.
12:00:38 -!- Sgeo has quit (Read error: Connection reset by peer).
12:01:38 <fizzie> Are you going to start telling me I should be nosql webscale etc etc
12:01:43 <oerjan> Jafet: we're all living inside a fizzie-maintained database
12:02:15 <Jafet> No, you can't be webscale because this is irc.
12:03:04 <fizzie> oerjan: If it helps any, you're still the tops in terms of absolute hth http://sprunge.us/hZjW hth
12:04:22 <fizzie> And, in fact, if we only look at 2014 http://sprunge.us/igXd hth hand
12:04:58 <oerjan> how did lambdabot get on third
12:05:49 <oerjan> oh wait probably through @messages-loud
12:06:08 <fizzie> http://sprunge.us/bDKa like that
12:12:18 -!- Darkgamma has quit (Ping timeout: 240 seconds).
12:18:27 <int-e> I see that oerjan still leads in terms of absolute numbers.
12:20:17 <oerjan> @let newtype Codensity f x = Codensity {runCodensity :: forall r. (x -> f r) -> f r)
12:20:17 <lambdabot> Parse failed: TypeOperators is not enabled
12:21:28 <oerjan> @let newtype Codensity f x = Codensity {runCodensity :: forall r. (x -> f r) -> f r }
12:21:28 <lambdabot> Parse failed: TypeOperators is not enabled
12:21:51 <oerjan> int-e: why is that erring out (and no, there aren't any TypeOperators)
12:22:24 <oerjan> and it already has RankNTypes, which is the only thing ghci complains about
12:24:06 <oerjan> > let f :: (forall x. (forall y. y -> x) -> x) -> Int; f g = g (const 3) in f ($ undefined)
12:24:07 <lambdabot> Couldn't match type ‘a0 -> x’ with ‘forall y. y -> x’
12:24:07 <lambdabot> Expected type: (forall y. y -> x) -> x
12:25:06 <int-e> oerjan: hmm, such declarations are parsed twice, once by haskell-src-exts and then by ghc-as-a-library. I guess the first one fails
12:25:11 -!- atslash has quit (Ping timeout: 252 seconds).
12:25:31 <oerjan> > let f :: (forall x. (forall y. y -> x) -> x) -> Int; f g = g c3; c3 _ = 3 in f ($ undefined)
12:25:32 <int-e> (at least that's how I remember things)
12:25:32 <lambdabot> Couldn't match type ‘a0 -> x’ with ‘forall y. y -> x’
12:25:32 <lambdabot> Expected type: (forall y. y -> x) -> x
12:25:51 <oerjan> i think i may be doing this wrong.
12:26:13 -!- atslash has joined.
12:27:00 <oerjan> > let f :: (forall x. (y -> x) -> x) -> Int; f g = g c3; c3 _ = 3 in f ($ undefined)
12:28:48 <oerjan> > let f :: (forall x. (forall y. y -> x) -> x) -> Int; f g = g (const 3); a x = x undefined in f a
12:28:49 <lambdabot> Couldn't match type ‘t0 -> x’ with ‘forall y. y -> x’
12:28:50 <lambdabot> Expected type: (forall y. y -> x) -> x
12:29:09 -!- shikhout has joined.
12:29:48 <oerjan> > let f :: (forall x. (forall y. y -> x) -> x) -> Int; f g = g (const 3); a :: (forall x. (y -> x) -> x); a x = x undefined in f a
12:30:04 <oerjan> > let f :: (forall x. (forall y. y -> x) -> x) -> Int; f g = g (const 3); a :: forall y. (forall x. (y -> x) -> x); a x = x undefined in f a
12:30:07 <lambdabot> Couldn't match type ‘y0 -> x’ with ‘forall y. y -> x’
12:30:07 <lambdabot> Expected type: (forall y. y -> x) -> x
12:30:46 <int-e> oerjan: a has type (a -> b) -> b, which does not generalize to forall y. y -> x
12:32:17 <oerjan> um it's supposed to generalize to forall x. (forall y. y -> x) -> x
12:32:41 -!- shikhin has quit (Ping timeout: 264 seconds).
12:33:24 <int-e> oh. but then you need a type annotation for a.
12:33:26 <int-e> > let f :: (forall x. (forall y. y -> x) -> x) -> Int; f g = g (const 3); a :: (forall y. y -> x) -> x; a x = x undefined in f a
12:33:47 <oerjan> there _was_ one. but i think i switched the foralls.
12:34:17 <int-e> Right, you added the one forall that Hindley-Milney adds automatically anyway.
12:34:55 -!- edwardk has quit (Quit: Computer has gone to sleep.).
12:35:30 <oerjan> @let newtype Codensity f x = Codensity (forall r. (x -> f r) -> f r)
12:35:30 <lambdabot> Parse failed: TypeOperators is not enabled
12:36:53 <int-e> Prelude Language.Haskell.Exts> parseModule "newtype Codensity f x = Codensity (forall r. (x -> f r))"
12:36:56 <int-e> ParseFailed (SrcLoc {srcFilename = "<unknown>.hs", srcLine = 1, srcColumn = 57}) "TypeOperators is not enabled"
12:37:32 <oerjan> which is a different message from what ghci gives
12:37:52 <int-e> but it's the one that you get from lambdabot
12:39:34 <int-e> (as far as I understand, haskell-src-exts is used in order to improve error messages. clearly that doesn't work in this case.)
12:39:53 <oerjan> also, adding {-# LANGUAGE TypeOperators #-} to the beginning doesn't work.
12:40:07 <HackEgo> [wiki] [[Talk:Rand.Next()]] N http://esolangs.org/w/index.php?oldid=39508 * Malltog * (+191) Created page with "== Turing completeness == Is this language really Turing-complete? Is it possible to achieve an [[arbitrary effect at an arbitrary point]], accounting for its reliance on rand..."
12:40:33 <int-e> obviously. (look at 'define' in https://github.com/int-e/lambdabot/blob/master/lambdabot-haskell-plugins/src/Lambdabot/Plugin/Haskell/Eval.hs )
12:41:01 <int-e> the contents of L.hs is not even taken into account at that point.
12:41:57 <oerjan> um i meant that parseModule "{-# LANGUAGE TypeOperators #-}\nnewtype Codensity f x = Codensity (forall r. (x -> f r))" doesn't work either
12:42:46 -!- Sorella has joined.
12:43:46 -!- atslash has quit (Quit: This computer has gone to sleep).
12:46:46 <oerjan> @let {-# LANGUAGE Trustworthy #-} test = "hi"
12:47:02 <oerjan> @let {-# LANGUAGE Trustworthy #-}; test = "hi"
12:47:37 <oerjan> i must have misunderstood that code.
12:47:56 -!- Frooxius has joined.
12:48:35 <oerjan> @let {-# LANGUAGE TemplateHaskell #-}; test2 = "hi again"
12:49:19 <oerjan> @let data Test = Test { _hi :: Bool }; makeLenses ''Test
12:49:19 <lambdabot> Parse failed: Improper character constant or misplaced '
12:49:58 <int-e> parseModuleWithMode (defaultParseMode{ extensions=[EnableExtension TypeOperators] }) "<code from above>" (RankNTypes works, too)
12:50:58 <oerjan> it's rather ridiculous if that means it parses forall x . as an application of a type operator, though.
12:51:19 <int-e> good point. it does.
12:52:10 <int-e> UnBangedTy (TyParen (TyInfix (TyApp (TyVar (Ident "forall")) (TyVar (Ident "r"))) (UnQual (Symbol ".")) (TyParen (TyFun (TyVar (Ident "x")) (TyApp (TyVar (Ident "f")) (TyVar (Ident "r")))))))])
12:53:06 <oerjan> @let fun :: (forall x. (forall y. y -> x) -> x) -> Int; fun g = g (const 3); awesome :: (forall y. y -> x) -> x; awesome x = x undefined
12:53:06 <lambdabot> Parse failed: TypeOperators is not enabled
12:53:23 <oerjan> aha. so RankNTypes _don't_ work in @let at all, only in >
12:57:08 -!- ter2 has joined.
12:57:41 <int-e> yeah. annoying, and probably not too hard to fix. not trivial though ---> maybe next weekend.
12:58:35 -!- Frooxius has quit (Ping timeout: 255 seconds).
13:04:34 -!- ter2 has changed nick to tertu.
13:17:43 -!- yorick has joined.
13:22:29 -!- Frooxius has joined.
13:25:23 -!- Frooxius has quit (Client Quit).
13:34:38 -!- Patashu_ has quit (Ping timeout: 240 seconds).
13:40:19 -!- tertu has quit (Ping timeout: 276 seconds).
13:45:50 -!- hk3380 has quit (Ping timeout: 255 seconds).
13:47:50 <myname> yay, haskell-llvm-general-pure fails installing here ~~
13:48:48 -!- Frooxius has joined.
13:59:32 -!- MindlessDrone has joined.
14:01:03 -!- tertu has joined.
14:19:25 -!- AnotherTest has joined.
14:27:54 -!- atslash has joined.
14:32:17 -!- conehead has joined.
14:40:36 -!- hexagon has joined.
14:41:13 -!- hexagon has quit (Changing host).
14:41:13 -!- hexagon has joined.
14:42:13 -!- hexagon has changed nick to sign.
14:42:22 -!- atslash has quit (Quit: This computer has gone to sleep).
14:50:33 -!- hk3380 has joined.
14:58:19 -!- hk3380 has quit (Ping timeout: 240 seconds).
14:59:36 -!- shikhout has changed nick to shikhin.
14:59:55 -!- Sorella has quit (Ping timeout: 252 seconds).
15:02:53 -!- HackEgo has quit (Ping timeout: 245 seconds).
15:03:05 -!- HackEgo has joined.
15:03:21 -!- FreeFull has joined.
15:05:58 -!- atslash has joined.
15:07:04 -!- oerjan has quit (Quit: leaving).
15:09:21 <FireFly> I thought twh was "that won't help"
15:16:59 <int-e> Anyway, the ambiguity makes the abbreviation much more interesting.
15:17:59 <int-e> I want to play Portal again. "Where are you going? I don't think you're going where you think you're going."
15:19:05 -!- Bike has joined.
15:19:59 <ion> The time is 139999439
15:20:11 <ion> 1399994399 even it was.
15:20:45 <Jafet> > showHex 1399994442
15:20:52 <Jafet> > showHex 1399994450 ""
15:22:46 <ion> % LC_ALL=C TZ=UTC date -d @1400000000
15:22:48 <ion> Tue May 13 16:53:20 UTC 2014
15:24:01 <int-e> `` date -ud @1400000000
15:24:02 <HackEgo> Tue May 13 16:53:20 UTC 2014
15:25:01 <FireFly> I need to stop contracting those words, I guess
15:28:20 -!- hk3380 has joined.
15:28:24 <mroman_> ncurses seems to be linux only
15:28:54 <mroman_> doesn't compile well on windows at least
15:30:24 <ion> > review hex 12345
15:30:42 -!- drdanmaku has joined.
15:35:00 -!- Sorella has joined.
15:36:52 <Bike> https://levels.io/12-startups-12-months/ beautiful
15:44:04 <lambdabot> Couldn't match type ‘[GHC.Types.Char]’ with ‘[GHC.Types.Char] -> t’
15:44:04 <lambdabot> Expected type: (GHC.Base.String -> [GHC.Types.Char] -> t)
15:44:04 <lambdabot> -> GHC.Base.String -> [GHC.Types.Char] -> t
15:44:04 <lambdabot> Actual type: (GHC.Base.String -> [GHC.Types.Char] -> t)
15:45:22 -!- Sprocklem has joined.
15:45:25 <FreeFull> mroman_: I think for windows you want pdcurses
15:49:46 <Jafet> For windows you want cygwin and a stiff drink
15:51:42 <Bike> for msys you'll need vodka.
15:57:03 -!- tertu has quit (Ping timeout: 245 seconds).
16:00:16 <mroman_> For windows you want linux
16:01:22 -!- slereah_ has quit (Quit: Leaving).
16:04:20 -!- tertu has joined.
16:08:43 -!- tertu has quit (Ping timeout: 245 seconds).
16:13:35 -!- atslash has quit (Quit: This computer has gone to sleep).
16:17:06 -!- ^v has joined.
16:24:39 -!- sebbu has quit (Ping timeout: 250 seconds).
16:27:35 -!- nucular has joined.
16:27:35 -!- nucular has quit (Changing host).
16:27:35 -!- nucular has joined.
16:43:11 -!- tertu has joined.
16:44:41 -!- hk3380 has quit (Ping timeout: 252 seconds).
16:54:53 <nortti> unix time has passed 1400000000
17:00:47 <Taneb> That's a lot of seconds since 1970
17:02:36 <kmc> `run date +%s
17:02:48 <fowl> been listening to this for days https://www.youtube.com/watch?v=95jD5tMFjhs&list=PLBB7D6D0650A7FA4B
17:04:08 <pikhq> mroman_: There is some other library that does the curses interface on Windows FWIW.
17:05:13 -!- Tod-Autojoined has changed nick to TodPunk.
17:07:14 <mroman_> pikhq: With haskell bindings?
17:07:39 <pikhq> It's not *im*possible, but not to my knowledge.
17:08:05 <fowl> you mean pdcurses?
17:21:40 -!- hk3380 has joined.
17:24:19 -!- sebbu has joined.
17:25:46 -!- sebbu has quit (Changing host).
17:25:47 -!- sebbu has joined.
17:26:29 -!- ^v has quit (Ping timeout: 252 seconds).
17:29:46 -!- sebbu has changed nick to sebbu2.
17:30:25 -!- tertu has quit (Ping timeout: 276 seconds).
17:32:53 -!- Sprocklem has quit (Quit: Lunch).
17:34:02 -!- ^v has joined.
17:38:42 <kmc> fungot: stay inside my aura
17:38:42 <fungot> kmc: i guess he was a masterful schemer? it has been verified that it indeed shall be 0 " if and only if 0 is even or odd number of elements in the list
17:47:19 -!- atslash has joined.
18:03:25 <olsner> fungot: noli turbare circulos meos
18:03:26 <fungot> olsner: what do you mean call-with-output-file there? the point was: " if loading it as text/ plain?
18:04:16 <nortti> mroman_: how much answers have there been to the brainfuck survey
18:07:12 <mroman_> Cells should wrap-around, Memory should exand to the right, fatal error on leaving on the left side, re-return EOF, eof=0, non-command-chars as comments, textmode with newline translation
18:08:50 -!- impomatic has quit (Ping timeout: 252 seconds).
18:10:48 <shachaf> cell values should be infinite, cell positions should be infinite (in both directions), input should be infinite, program length should be infinite
18:13:18 <shachaf> in fact cell values, position, input, and program should all be real numbers
18:14:13 <Bike> still holding out for a hilbert space tape.
18:14:54 <shachaf> or any kind of space tape for that matter
18:19:29 -!- Bike has quit (Ping timeout: 264 seconds).
18:21:07 <int-e> is that like a space elevator?
18:21:14 -!- Bike has joined.
18:23:20 -!- mhi^ has joined.
18:29:13 -!- shikhout has joined.
18:32:34 -!- shikhin has quit (Ping timeout: 240 seconds).
18:37:54 -!- shikhout has changed nick to shikhin.
18:42:28 -!- impomatic has joined.
18:54:44 <mroman_> every grammatically correct program must be of infinite length?
18:55:28 <mroman_> .oO(It's turing complete but no one will be able to write a program that parses)
18:55:56 <mroman_> However, we have some programs that are grammatically incorrect but if we just ignore parse errors it runs fine
18:56:41 <nortti> also, we could implement it using lazily generated program that is just NOPs after certain part
18:58:38 <mroman_> but that would be like cheating
18:59:00 <mroman_> you can always ++ cycle NOP
18:59:29 -!- kmc has set topic: Happy megasecond 1400 | PSA: fizzie is running the wiki now, contact him for any problems | brainfuck survey: https://www.surveymonkey.com/s/L82SNZV | https://dl.dropboxusercontent.com/u/2023808/wisdom.pdf http://codu.org/logs/_esoteric/ http://tunes.org/~nef/logs/esoteric/.
19:00:43 <kmc> or should it just be "happy hectomegasecond"
19:06:36 <fowl> 3000 beers? im down
19:08:34 -!- nortti has quit (Ping timeout: 276 seconds).
19:09:12 -!- nortti has joined.
19:09:12 -!- nortti has quit (Client Quit).
19:09:33 -!- nortti has joined.
19:10:07 -!- nortti_ has joined.
19:13:37 -!- nortti_ has quit (Client Quit).
19:14:17 -!- nortti_ has joined.
19:14:50 -!- nortti has quit (Disconnected by services).
19:14:56 -!- nortti_ has changed nick to nortti.
19:16:57 -!- nortti has quit (Client Quit).
19:18:49 -!- nortti has joined.
19:30:44 -!- augur has quit (Remote host closed the connection).
19:41:43 -!- password2 has joined.
19:42:33 <HackEgo> [wiki] [[Talk:Zero]] http://esolangs.org/w/index.php?diff=39509&oldid=39472 * GreyKnight * (+152) /* Hello world! */ new section
19:43:52 -!- password2 has quit (Max SendQ exceeded).
19:44:37 -!- password2 has joined.
19:45:40 -!- password2 has quit (Max SendQ exceeded).
19:46:44 -!- password2 has joined.
19:48:15 -!- password2 has quit (Max SendQ exceeded).
20:05:38 -!- tailcalled has joined.
20:07:51 <fungot> shachaf: i guess it's easier for the programmer. useful enough, in retrospect. did any of this
20:08:33 <kmc> `relcome tailcalled
20:08:34 <HackEgo> 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.)
20:08:55 <tailcalled> does anybody know any function that is "just barely" uncomputable?
20:09:26 <Bike> maybe you mean a semicomputable function, though
20:10:01 <tailcalled> because I wanted to make an unimplementable language without extra power
20:10:50 <tailcalled> so I was wondering if anyone happened to know an unusable uncomputable function
20:11:10 <Bike> what would a usable uncomputable function even be.
20:11:43 <tailcalled> well, solving the halting problem would be usable
20:12:23 <Bike> eh, well you can reduce uncomputable functions to the halting problem, or something. probably.
20:12:33 <kmc> a random oracle is not very useful, unless you're doing cryptography :)
20:13:12 <tailcalled> not every uncomputable function, I would assume
20:13:15 <kmc> people study relativization wrt a random oracle in complexity theory
20:13:33 <kmc> P^A != NP^A with probability 1 for a random oracle A
20:13:37 -!- MoALTz has joined.
20:13:48 <kmc> but this is also true for some classes that are actually known to be equal
20:14:48 <tailcalled> well, having an incompressible stream is less powerful than halting problem, correct?
20:15:10 <Bike> i don't want to get out my copy of li and vitanyi but, for example, you can make a turing-complete computer out of diophantine equations
20:15:49 <Bike> tailcalled: well the incompressible stream isn't uncomputable, is it? what's uncomputable is verifying that it's incompressible.
20:15:56 <kmc> Bike: ooh, should I read this book?
20:16:07 <kmc> "This was the second-hardest book I ever read. Honestly, it took me years and years to get through it. I even had to buy a 2nd copy, because I kept getting frustrated and throwing the first copy across the room until it was destroyed. So yes, this book requires a substantial effort to read."
20:16:21 <tailcalled> bike: having a program computing an iincompressible stream is a contradiction in itself
20:16:42 <tailcalled> bike: because that program would be a compression of the stream
20:16:44 <Bike> kmc: http://fioraaeterna.tumblr.com/post/21338563373/ran-helps-kaguya-learn-information-theory-just fiora-approved
20:17:06 <tailcalled> bike: of course, the halting sequence is an example of an incompreessible stream
20:17:08 <Bike> kmc: it's good, though i can't endorse the bayes stuff near the end :V
20:17:24 <tailcalled> whoops, just realized that I didn't specify that I meant infinite stream
20:17:32 <Bike> no, i got that.
20:18:04 <Bike> i mean i'm sure we all know that finite sequences are all computable.
20:18:08 <tromp_> stream implies infinite. otherwise you'd have said string
20:18:23 <kmc> tailcalled: if I write down a table for f(0), f(1), etc. and flip an ideal coin for each output, the resulting function is uncomputable, and useless
20:18:51 <tromp_> stream is incompressible means all its prefixes are incompressible up to a constant
20:18:54 <tailcalled> kmc: I would prefer a unique characterization
20:18:55 <kmc> I can implement queries to this oracle in finite time, too
20:19:06 <kmc> it's interesting to think about why this doesn't violate the church-turing thesis
20:19:45 <tailcalled> kmc: because there is a positive probability of any given prefix, including zeroes
20:20:09 <tromp_> although streams are incompressible with probability 1, there's only one known family of such streams, namely the halting probabilities
20:20:43 <FireFly> "this is the kind of book that literally sticks open problems in its exercises" hehe..
20:21:11 <Bike> yeah, it's fun. like taocp or... ok i'm blanking
20:21:19 <Bike> it actually uses the system from taocp, i think.
20:21:19 <tromp_> i think so. i don't know how else to define a stream that is provably nicompressible
20:22:00 <tailcalled> tromp_: are there no uncomputable problems that are easier than the halting problem?
20:22:47 <kmc> easier in that an oracle for the problem doesn't give you a halting oracle?
20:22:55 <tailcalled> having an oracle for them does not give you halting, yes.
20:23:16 <tromp_> that's not what i'd call easier
20:23:28 <Bike> http://en.wikipedia.org/wiki/Turing_degree, yes?
20:23:40 <kmc> well it's in general a partial order
20:23:58 <Bike> yeah, there are infinite degrees between 0 and 0', or whatever
20:24:04 <Bike> and they're only pordered
20:24:06 <tromp_> i can't think of a well defined class in between recursive and recursively enumerable
20:25:06 <tailcalled> it feels like there should be such a class
20:25:28 <tromp_> a random stream doesnt give you a halting oracle
20:25:38 <tromp_> surely that cant be called easier:(
20:25:49 <Bike> i feel like introducing stochasticity is just going to confuse things. or perhaps only confuse me.
20:25:54 <tailcalled> tromp_: can you give me an example of a random stream which doesn't give the halting oracle? ;)
20:26:15 <Bike> 6,6,6,6,6,6,6,
20:26:29 -!- mhi^ has quit (Quit: Lost terminal).
20:26:44 -!- nucular has quit (Quit: Excess Food).
20:27:31 <Bike> kmc: oh, i should also mention the book is pretty esolangy and constructive. they spend a lot of time setting up an explicit turing machine encoding (prefix-free of SKI) and making bitmaps of programs and shit
20:27:48 <tromp_> of course i cannot explicitly define one that's provably so
20:28:08 <tromp_> but i claim that with prob. 1 a random one has that property
20:28:50 <tailcalled> anyway, I would prefer not doing random stuff
20:29:04 <tromp_> not without doing some literature search
20:29:42 <tromp_> Bike, that's what i contributed to the book before i invented blc
20:29:52 <tromp_> i was still dablling with combinatory logic then
20:30:45 <tromp_> Paul Vitanyi was my supervisor btw
20:31:00 <tailcalled> I wonder if one can exploit rice's theorem in this...
20:35:32 <tailcalled> actually, maybe one could use uncomputable functions to make a unusable uncomputable function
20:35:50 <tailcalled> i.e. let H be the halting function and BB be busy beaver
20:36:01 <tailcalled> and G be graham's number, for good measure
20:36:26 <tailcalled> would x -> H(BB(BB(BB(x+G)))) be useful? :P
20:36:38 <tromp_> my proposal for one would be the xor of two halting probabilities
20:36:47 <tromp_> eg one for blc with one for bf
20:37:40 <tromp_> that's well defined and almost certainly uncomputable and useless:)
20:38:53 <tromp_> alternatively you could take the halting probability of the universal BLC machine equipped with a halting oracle
20:38:59 -!- MindlessDrone has quit (Quit: MindlessDrone).
20:39:15 <tailcalled> it's not immediately obvious how to prove my function is uncomputable
20:39:35 <tromp_> ie. the next level halting prob
20:40:02 <tailcalled> so, basically, making unusable uncomputable functions by increasing the uncomputability
20:40:40 <tromp_> yes, that's why i objected to calling such things easy
20:41:21 <tailcalled> well, it's easy because it can be faked
20:42:07 <tailcalled> so the hard easy problems are easy because they are fakable; the easy easy problems are easy because they are easier than halting
20:42:37 <tailcalled> but couldn't one compute ordinary halting probability from BLC+HO halting probability?
20:42:41 <mroman_> I get the feeling my ISP is making my internet connection slower after 10 o'clock
20:43:40 <FireFly> Do some experiments with downloading big things over the 10 o'clock mark and observing the download speed?
20:43:54 <tromp_> no, tailcalled, you cannot simulate the oracle BLC computations that accumulate to that HO haltingprobability
20:44:05 <FireFly> Or alternatively read the user agreement for the ISP
20:44:08 <kmc> mroman_: you think it's deliberate, and not just that demand increases a lot?
20:44:25 <tailcalled> tromp_: but the halting probability is essentially the halting sequence
20:44:32 <mroman_> It's just that streaming movies is impossible after 10 o'clock
20:44:44 <tromp_> in the most compressed form
20:44:52 <tailcalled> tromp_: and there is a computable function that assigns LC terms to OBLC terms, right?
20:45:49 <tromp_> the oracle could be a negative de bruijn index
20:46:49 -!- Slereah has quit (Ping timeout: 250 seconds).
20:46:55 <tailcalled> but you could always take a normal LC term and convert it to an OBLC term by ignoring the oracle
20:47:12 <tromp_> sure; they're identical in the first case
20:47:12 <tailcalled> and the halting probability let's you check if a program halts, correct?
20:47:56 <tailcalled> so let |x| denote the conversion of LC to OBLC, HOBLC the halting function for OBLC
20:48:18 <tailcalled> where HLC is halting function for lambda calculus
20:49:10 <tailcalled> what if one took the busy beaver sequence
20:49:20 <tailcalled> but only makes it explorable in a limited way
20:50:03 <tailcalled> and a command B(x) which increments C and takes the xth bit of the Cth busy beaver number
20:50:08 <tromp_> yes, for halting functions, the HO case subsumes the plain case
20:50:17 <tromp_> but not for halting probabilities
20:50:49 <tromp_> so a BLC machine can extract the halting sequence from the halting probability
20:50:52 <tailcalled> didn't you agree that halting probabilities could be used to find the halting problem?
20:51:15 <tromp_> but you need an OBLC to do the same for oracle halting prob
20:51:42 <tailcalled> it's this halting prob. we're talking about, right? http://en.wikipedia.org/wiki/Halting_probability
20:51:53 <tromp_> yes, since it involves doing infinitely many simulations accumulating probabilities
20:52:30 -!- Slereah_ has joined.
20:52:42 <mroman_> It's not fast enough to stream 40m of film in 40m
20:52:44 <tromp_> you should read Chaitin's papers on why Omega is "the number of wisdom"
20:52:57 <tailcalled> wait, how are you able to observe the halting probability? arbitrary approximation? bit-indexing? what is it?
20:53:09 <mroman_> if it takes longer than n minutes to download n minutes of film you can't stream it
20:53:17 <mroman_> that's sorta the streaming lemma
20:53:38 <tailcalled> for example, if it takes n minutes + 1 second
20:53:40 <tromp_> it can be your input stream, or an oracle stream of bits
20:54:13 <tromp_> you can define machine to compute from infinite input to infinite output
20:54:18 <tailcalled> and the distance between the part you've dl'ed to and the part you've watched to might not reach zero before the film is over
20:54:58 <mroman_> but currently it looks like it's 1.5*n
20:55:05 <tailcalled> tromp_: the halting probability is represented as a bit-sequence
20:55:38 <tromp_> i computed the first 4 bits for blc halting prob
20:55:41 <tailcalled> tromp_: and by the definition of how the halting probability is, the 1 bits are exactly where the codes for machines that halt are
20:56:29 <tromp_> a halting program of length k contributes 2^-k to the halting prob
20:57:00 <tromp_> whereas in the halting seq it would be some bit at index roughly 2^k
20:57:46 <tromp_> so halting prob is exponentially more dense than halting sequence
20:58:44 <tailcalled> and an operation B(x) which increments C and returns the xth bit of the Cth busy beaver number
20:58:58 <tailcalled> no way to reduce the value of C or anything
21:00:25 <tromp_> how about every other bit of blc halting prob?
21:00:36 -!- nooodl has joined.
21:00:40 <tromp_> that's well defined and uncomputable
21:00:47 <tromp_> and most certainly useless
21:01:43 <tromp_> anyway , i shld get back to do some work:(
21:02:19 -!- AnotherTest has quit (Ping timeout: 276 seconds).
21:02:46 <kmc> I graphed how my project is doing at keeping up with Rust language changes: http://people.mozilla.org/~mbrubeck/servo-rust-updates.svg
21:03:16 <lambdabot> *Exception: Prelude.cycle: empty list
21:03:27 <idris-bot> (input):1:7:When elaborating argument xs to function Prelude.Stream.cycle:
21:03:40 <kmc> woooo dependent types
21:04:01 <kmc> > take 0 undefined
21:04:14 <kmc> > fix (take 0)
21:04:16 -!- Patashu has joined.
21:04:34 <nooodl> oh right take 0 is just const []
21:05:48 <Melvar> ( \a,xs:List a => take 0 xs
21:05:48 <idris-bot> \a => \xs => [] : (a : Type) -> List a -> List a
21:13:19 <HackEgo> [wiki] [[One]] N http://esolangs.org/w/index.php?oldid=39510 * Tailcalled * (+1394) Created page with "One is a language invented by Tailcalled. It is an uncomputable extension to a Brainfuck dialect, but it is designed to not be significantly more powerful than ordinary Brainf..."
21:14:20 <tailcalled> and yes, I made an instruction that I named Instruction, because I can
21:15:14 <int-e> what does I do on negative input?
21:16:00 <HackEgo> [wiki] [[One]] http://esolangs.org/w/index.php?diff=39511&oldid=39510 * Tailcalled * (+89)
21:16:40 <tromp_> you need to give an example of its usde
21:16:59 <tromp_> what is the output on the first call with x=0?
21:17:14 <tromp_> how exactly is BB defined?
21:17:19 <tailcalled> whoops, maybe I should have defined busy beaver more clearly
21:17:53 <tailcalled> I always forget that BB is somewhat ambiguous :/
21:18:18 <tromp_> also , this requires you to nail down every other detail
21:20:04 <mroman_> http://esolangs.org/wiki/Talk:Rand.Next() <- since PRNGs are actually deterministic it should at least be possible to calculate a seed so that it constructs a given brainfuck program
21:20:45 <mroman_> however, that sadly doesn't answer if such a seed even exists
21:21:52 <tromp_> the seed will need to be at least as big as the program?!
21:22:38 <mroman_> It could happen that the seed 0 will produce the cat program
21:23:31 <tromp_> nad your next 10 coin tosses cld be all tails. still on avg that will take 2^10 tries:)
21:23:37 <HackEgo> birdcoin tabllinecoin dutackethaxcoin fukcoin fitcoin clecoin bubtlecoin dularcoin convercoin factioncoin trecoin suonymcoin eoncoin deltmachialigsetticoin smilectcoin juxtapcoin scenscrcoin bicscoin dreimaccoin sandcoin
21:24:02 <shachaf> whoa, that wrapped perfectly on my screen
21:24:11 <mroman_> That's the beauty about statistics
21:24:13 <kmc> shachaf: did you see my Rust-graph?
21:24:33 <mroman_> If somebody says your coin was manipulated after producing 1 Mio. times tails in a row
21:24:37 <int-e> did we have any duplicates from `coin so far?
21:24:40 <mroman_> you can still say "nope. I didn't."
21:24:56 <kmc> int-e: yes, I saw dupcoin twice
21:25:01 <mroman_> and he'll never prove for sure that you manipulated it
21:25:07 <HackEgo> [wiki] [[One]] http://esolangs.org/w/index.php?diff=39512&oldid=39511 * Tailcalled * (+927)
21:25:37 <HackEgo> [wiki] [[One]] http://esolangs.org/w/index.php?diff=39513&oldid=39512 * Tailcalled * (+0) /* Busy Beaver */ mixed up in and out
21:26:20 <mroman_> since PRNGs aren't really random
21:26:28 <elliott> nobody cares about absolute proof.
21:26:34 -!- Patashu has quit (Ping timeout: 240 seconds).
21:26:37 <kmc> actually there are quite a few duplicates
21:26:39 <mroman_> you might be able to prove that no number shows up more than twice in a row
21:28:20 <tailcalled> any more questions about One before I go to bed?
21:28:49 <mroman_> elliott: was that directed to me?
21:29:27 <mroman_> You can calculate how much you have to throw a die to prove with k% certainty that it was manipulated
21:29:42 <mroman_> and assuming you cut somebodys hand off if he uses a manipulated die
21:29:52 <mroman_> how big must k be for society to live with it?
21:31:59 -!- atriq has joined.
21:32:10 -!- tailcalled has quit.
21:32:44 <atriq> @ask oerjan How do I, as an Englishman, go about pronouncing "Tromsø"?
21:33:20 <HackEgo> [wiki] [[One]] http://esolangs.org/w/index.php?diff=39514&oldid=39513 * Tailcalled * (+68)
21:33:27 <mroman_> elliott: that's pretty low
21:33:46 <mroman_> the other question is whether k can be lower for less severe punishments
21:34:04 <shachaf> atriq: Probably you should aim for the way that Norwegians pronounce it.
21:34:27 <atriq> shachaf: I'm only dutch etymologically and genealogically speaking
21:34:37 <atriq> Culturally and linguistically, I'm Bristish
21:37:17 <mroman_> Is there crypthography based on the halting problem by any chance?
21:37:38 <kmc> not that I'm aware of
21:37:41 <kmc> it would probably be hard to implement
21:38:13 -!- atriq has quit.
21:46:26 -!- oerjan has joined.
21:53:28 <lambdabot> (Choice p, Applicative f, Integral a) => p a (f a) -> p String (f String)
21:53:43 <lambdabot> atriq asked 20m 58s ago: How do I, as an Englishman, go about pronouncing "Tromsø"?
21:55:15 <oerjan> google translate isn't too bad but i think the ø is a little to weak
21:56:35 * oerjan clicks the english pronunciation, which sounds about as close as he'd expect an english-speaker to be able to get it
21:58:19 <oerjan> if i put a hyphen (Troms-ø), then the norwegian pronunciation gets the ø about right put has the wrong pitch accent on the word as a whole
21:58:54 <shachaf> did you try putting in an INVISIBLE STRENGTH instead
21:59:43 <oerjan> `unicode INVISIBLE STRENGTH
22:00:38 <oerjan> @tell Taneb Read the logs.
22:06:35 <oerjan> <kmc> or should it just be "happy hectomegasecond" <-- i'm pretty sure SI prefixes don't combine.
22:13:53 -!- augur has joined.
22:24:36 -!- Phantom_Hoover has joined.
22:39:28 -!- boily has joined.
22:51:50 <Bike> take 0 is like \_ -> [] :: [a] -> [a] right
22:52:02 -!- metasepia has joined.
22:52:13 <boily> @eval fix (take 0) 123
22:52:18 -!- Sorella has quit (Quit: It is tiem!).
22:52:23 <boily> ~eval fix (take 0) 123
22:52:34 <metasepia> ENVA 132220Z 35010KT 9999 BKN044 05/M04 Q1018 RMK WIND 670FT 01015KT
22:53:20 <oerjan> boily: fix (take 0) is not a function hth
22:53:27 <Bike> > fix (take 0)
22:53:36 <Bike> oh, it's actually not bottom
22:53:47 <Bike> > fix (drop 0)
22:54:09 <boily> my Haskell is borken. too much Java in my world.
22:54:29 <boily> oerjan: Montréal is now warm! (and humid too)
22:54:34 <metasepia> CYUL 132240Z 11007KT 30SM FEW055 OVC075 18/09 A3012 RMK SC2AC6 SLP201 DENSITY ALT 200FT
22:54:39 <oerjan> boily: you need to go on a profunctor pilgrimage twh
22:55:18 <boily> I long for the day where we'll push Java 8. a meager consolation, but progress towards the Great Functional Unification!
22:55:47 <boily> I still agree about the Pilgrimage. that'd do me much good.
22:56:45 <oerjan> santiago de composition
22:58:59 <boily> apparently, Jacob, James and Jacques are all related.
23:00:11 <oerjan> so are Ørjan, Jürgen and George
23:02:38 -!- augur has quit (Remote host closed the connection).
23:03:21 <boily> that one I know because of my girlfriend's surname.
23:03:23 <oerjan> i probably still have in storage the old baby names book with pictures of trees of big name families
23:05:36 <Taneb> oerjan, are there many fish and chip shops in Norway?
23:07:51 <oerjan> there aren't really as many fish shops as there ought to be, with or without chips
23:08:25 -!- augur has joined.
23:08:30 <boily> . o O ( hm. a fish'n'chip poutine. I should try to make that one time... )
23:08:59 <Taneb> boily, how many fish and chop shops are there in Canadia?
23:09:11 -!- augur has quit (Remote host closed the connection).
23:09:17 <oerjan> late night fast food is mainly kebab and burgers these days. maybe some sausages, if i'm to believe norway's main relevant comic.
23:11:12 <kmc> does norway have the innovation of 99¢ Fresh Pizza
23:11:14 <boily> Taneb: eh... not that much, at least here.
23:11:47 <oerjan> kmc: except for the price, probably. i used to buy pizza slices at the bunnpris chain when i was at university.
23:11:52 <boily> Taneb: there's the http://www.britandchips.com/
23:11:53 <Taneb> There's two between me and the city wall
23:12:20 <oerjan> i think they were 30 nok or so
23:12:31 <kmc> 99¢ Fresh Pizza is a thing in New York, and it's pretty distinct from the standard NYC pizza experience, which is like $2 or $3 a slice
23:14:16 <kmc> looks like that was about $4 then
23:14:33 <oerjan> norwegian grocery is based on the strange combination of heavily advertising "low" prices and customers mainly refusing to buy cheap non-name brands
23:15:08 <kmc> NOK/USD experienced quite a drop from July '08 to December '08
23:15:11 <kmc> but so did many things.
23:16:05 -!- Sgeo has joined.
23:16:17 <oerjan> well yeah norway has been mostly an oasis against the crisis
23:16:36 <oerjan> so at some points investors hoarded NOKs
23:17:09 <kmc> "Currently as of 2014, support for Swedish membership of the euro among the general population is low. In September 2013, support fell as low as 9%"
23:18:30 <oerjan> boily: i have a vague recall of my dad once making a fish pizza, back in the 80s. and possibly a brunost one, which is even more insane.
23:19:39 <boily> brunost. I don't know why, but that word inspires me uncharacteristicly high amounts of dread.
23:20:03 <oerjan> boily: i can see you have a well-developed intuition.
23:20:35 <oerjan> (actually i like it in moderate amounts, but then i'm a norwegian. but it does _not_ go well with pizza.)
23:21:06 <boily> kmc: we have http://www.pizzapizza.ca/ and http://www.doublepizza.net/.
23:21:15 <oerjan> also, for an even higher level of dread, gammalost.
23:21:42 <oerjan> (i'll eat that too. i think. it's been a while.)
23:22:20 <boily> “pungent traditional”. I'm... probably going to have a bite of it if I ever get the chance of, but anything can happen.
23:23:12 <Sgeo> I'm almost tempted to switch to Firefox
23:23:31 <Bike> make sure you spend some time on consideration of important life decisions like that sgeo
23:24:36 <boily> FIREFOX IS THE BESTEST! ANYONE WHO DISAGREE ARE VILE CHROME USERS!
23:24:48 <Sgeo> I'd gladly float back and forth between browsers if everything stayed synced
23:25:03 <Phantom_Hoover> look, i know you're having a rough time with your browser choices, but remember, you can talk to us
23:25:14 <Phantom_Hoover> don't rush headlong into a decision that might affect you for the rest of your life
23:27:06 <oerjan> yeah look at me, stuck with IE
23:27:42 <boily> Sgeo, you know you want firefox. it's good for you, and it'll make you feel right.
23:30:16 <oerjan> Sgeo: clearly the right thing to do is to have an automatic script to change between browsers until your configuration reaches a periodic point. that way you'll always be synced!
23:31:28 <boily> but what if Sgeo uses a chaotic map?
23:32:02 <oerjan> impossible with finite memory hth
23:32:39 <oerjan> i'm sure a realistic setup will converge _long_ before black holes start evaporating.
23:32:56 -!- atslash has quit (Quit: This computer has gone to sleep).
23:44:02 -!- MoALTz_ has joined.
23:46:57 -!- MoALTz has quit (Ping timeout: 265 seconds).
23:47:39 <Sgeo> I don't particularly want a large chain of "These bookmarks came from Chrome: These bookmarks came from Firefox: These bookmarks came from Chrome: These bookmarks came from Firefox: ..."
23:48:52 <oerjan> this is clearly what cyclic directory hard links were made for hth
23:50:45 <kmc> > fix ("These bookmarks came from Chrome: These bookmarks came from Firefox: "++)
23:50:46 <lambdabot> "These bookmarks came from Chrome: These bookmarks came from Firefox: These ...
23:52:00 <kmc> i'm still pleased about fix (take 0)
23:52:23 <kmc> it's also the greatest fixed point!
23:55:14 -!- yorick has quit (Remote host closed the connection).
23:55:22 <Bike> [] isn't the least fixed point, is it?
23:59:32 -!- tromp has joined.
00:00:00 <Sgeo> > length $ fix $ take 0
00:01:03 <oerjan> Bike: fix always gives the least fixed point.
00:03:21 -!- tertu has joined.
00:03:22 <oerjan> that's the official haskell report definition of what recursion does.
00:04:09 <Bike> > take 0 undefined
00:05:15 <kmc> the only thing below [] is ⊥, and that isn't a fixed point of (take 0)
00:07:55 <Bike> kmc: yeah, i thought take 0 was strict.
00:08:14 <Sgeo> > take 1 (5:undefined)
00:08:46 <Sgeo> > take 1 (undefined:undefined)
00:09:07 <Sgeo> Is that [undefined] except for failure to show properly?
00:09:31 <Bike> > length take 1 (undefined:undefined)
00:09:32 <lambdabot> Couldn't match expected type ‘a2 -> [a3] -> t’
00:09:32 <lambdabot> with actual type ‘GHC.Types.Int’Couldn't match expected type ‘[a0]’
00:09:32 <lambdabot> with actual type ‘GHC.Types.Int -> [a1] -> [a1]’
00:09:36 <Bike> > length $ take 1 (undefined:undefined)
00:09:43 -!- Sorella has joined.
00:10:32 <Bike> > length (undefined :: [()])
00:10:43 -!- ter2 has joined.
00:10:43 -!- tertu has quit (Disconnected by services).
00:11:22 <oerjan> it's a general rule that f undefined = undefined iff fix f = undefined
00:12:13 <oerjan> also, fix f is the limit of iterate f undefined
00:12:35 <Sgeo> Am I a traitor to Magic if I try Hearthstone?
00:12:35 -!- tertu has joined.
00:12:35 <Taneb> Is it possible to prove the first statement
00:13:08 -!- tertu has quit (Client Quit).
00:13:34 <oerjan> first, if f undefined = undefined then clearly undefined is the least fixpoint, so fix f = undefined
00:13:44 <Bike> the yes was about traitors
00:13:49 <Bike> death to traitors
00:14:37 <oerjan> if f undefined is _not_ undefined, then undefined is not a fixpoint of f at all, so fix f is not undefined.
00:15:06 <oerjan> well fix f is not = undefined.
00:15:38 <oerjan> that fix f is actually defined as anything requires using CPO to prove there's always a least fixpoint.
00:16:38 <oerjan> and that probably involves using that limit of iterate f undefined as a lemma.
00:16:51 * oerjan is a bit vague on that part.
00:16:54 -!- copumpkin has quit (Quit: Textual IRC Client: www.textualapp.com).
00:18:04 -!- copumpkin has joined.
00:25:02 -!- tromp has quit (Remote host closed the connection).
00:25:41 -!- Sprocklem has joined.
00:30:08 -!- shikhout has joined.
00:32:53 -!- shikhin has quit (Ping timeout: 245 seconds).
00:37:16 -!- edwardk has joined.
00:40:26 -!- nooodl has quit (Ping timeout: 252 seconds).
00:42:53 -!- edwardk has quit (Ping timeout: 264 seconds).
00:53:36 <kmc> fungot: Are you happier now that the gods are dying? Or do you dream of Heston with omniscient beard?
00:53:37 <fungot> kmc: 1 egobot: daemon egobot reload a file for os x? i'm trying to
00:54:56 -!- tromp has joined.
00:56:55 <boily> fungot dreams of Dæmon Egobot, Lord of the Tenth Circle of Bothell.
00:56:55 <fungot> boily: hello lord_rob, how is the work of a tortured mind making a single last grasp for a semblance of comforting sanity overlaid upon a fundamentally chaotic at ultimately inimical universe.
00:57:51 <fungot> Available: agora alice c64 ct darwin discworld enron europarl ff7 fisher fungot homestuck ic irc* iwcs jargon lovecraft nethack oots pa qwantz sms speeches ss wp youtube
00:58:01 <boily> oh, plenty of new styles!
00:58:11 <oerjan> fungot: stop that, you're ruining boily's sanity project
00:58:11 <fungot> oerjan: only 4 years?!"
00:58:21 <kmc> oh I should ask my information theory question here
00:58:43 <boily> Four Years of Sanity.
00:58:53 <kmc> if you have an accurate model of the noise in a signal, can you insert encrypted messages into that signal in a way that's indistinguishable from more noise if you don't know the key?
00:59:07 <kmc> I think you can and that it would be kind of like spread spectrum CDMA, but I'm not sure
00:59:56 <copumpkin> I would expect so, but can't really justify it
00:59:58 <kmc> I was thinking about hiding data in digital TV transmissions by corrupting MPEG blocks in a way that looks like ordinary broadcast noise
01:00:14 <Bike> so, stenography?
01:00:19 <kmc> steganography
01:00:22 <boily> of course you can. we had a practical exam question once where we had to extract a signal from a post-modern waveform.
01:00:26 <Bike> i hate that word
01:00:49 <kmc> you can definitely insert an "encrypted carrier" by modeling the noise process using, say, a stream cipher as your RNG
01:01:03 <kmc> and the receiver can sync to it by looking for correlations
01:01:04 <fungot> Selected style: oots (Order Of The Stick)
01:01:08 -!- boily has quit (Quit: MATERIAL CHICKEN).
01:01:10 -!- metasepia has quit (Remote host closed the connection).
01:01:36 <kmc> I'm not sure how best to modulate that carrier without changing its statistical properties
01:01:44 <Sgeo> fungot: I like airships
01:01:45 <fungot> Sgeo: a good way, and our little dog, too! neat, having dinner together, and i know that, i'm the most badass halfling ever! in the name of, " it's alive and well, as theological revelations the oracle that. we visited ' im. or ' er, much like this go board and replace it with my little eye... something that the target " hates, fears, or otherwise, there wouldn't that be so lucky. tha way lies madness.
01:01:47 <kmc> but you could at least do simple on-off-keying (where "off" = uncorrelated noise)
01:04:02 <kmc> http://www.arl.army.mil/arlreports/2001/ARL-TR-2433.pdf looks relevant
01:04:10 <kmc> the magic search phrase was "spread spectrum steganography"
01:10:13 -!- Bike_ has joined.
01:11:29 <kmc> anyway I think this should work with any noise you can model accurately
01:11:41 <kmc> hiding messages in markov chain output would be an example
01:11:55 -!- Bike has quit (Ping timeout: 276 seconds).
01:11:59 <Taneb> Hmm, I know the guy who makes King James Programming...
01:12:06 <Taneb> Should I put him touch with MI6?
01:12:50 <kmc> and I think that under standard cryptographic assumptions it would be impossible to detect these signals without knowing the key
01:12:55 <fowl> Taneb, the losethos OS thing?
01:13:00 -!- Bike has joined.
01:13:24 <Taneb> fowl, no, that's unrelated
01:13:45 <fowl> Taneb, some other christian fundamentalist is programming?
01:14:02 <Taneb> fowl, no, it's Markov chain output
01:14:02 <Taneb> http://kingjamesprogramming.tumblr.com/
01:14:14 <Taneb> Seeded with KJV and SICP
01:14:30 <fowl> ive seen this before
01:14:49 -!- Bike_ has quit (Ping timeout: 252 seconds).
01:15:48 <Taneb> "Thy people shall be my people, and Assyria the work of those who contributed to making this a real book, especially Terry Ehling"
01:17:09 <Sprocklem> "you must, at no additional cost, fee or expense to the user, provide a copy, a means of abstraction — that binds a collection of procedures, or a package, and interfaces these to the rest of the acts of Azariah"
01:18:22 <fowl> The garbage collector uses the low-level predicate pointer-to-pair? instead of the list-structure pair? operation because in a real system there might be various things that are in the mountain of Zion
01:19:00 <fowl> haha "Peace and safety; then sudden destruction cometh upon them, as in the metacircular evaluator described in section 5.4.2"
01:19:00 <Sprocklem> "The following random-in-range procedure implements this strategy recursively, walking down the list of names of blasphemy"
01:19:33 <Taneb> Oh yes! Remembered something I was going to ask.
01:19:49 <Taneb> Does anyone know of a dependent type system which included database queries?
01:20:22 -!- ^v has changed nick to \o_yay.
01:21:56 -!- oerjan has quit (Quit: gnite).
01:22:16 <Taneb> Eg "foo : (x : String & age of all records in table 1 with name x < 4)"
01:33:30 <Taneb> Although this ends up awkward in the presence of database mutation (which is somewhat necessary)
01:34:13 <Sgeo> Doesn't Datomic ... somehow incorporate time into things? I remember it was too proprietary for me to want to look too closely
01:34:36 <Bike> Taneb: psh just return a fresh db
01:34:45 <Taneb> And then re-typecheck everything!
01:52:31 -!- Phantom_Hoover has quit (Quit: Leaving).
02:55:17 -!- Sorella has quit (Quit: It is tiem!).
02:56:16 -!- augur has joined.
02:57:04 -!- augur has quit (Remote host closed the connection).
02:58:09 -!- augur has joined.
02:58:43 -!- ter2 has changed nick to tertu.
03:00:49 -!- shikhout has changed nick to shikhin.
03:01:24 -!- shikhin has quit (Quit: Lost terminal).
03:21:16 -!- edwardk has joined.
04:05:41 -!- tromp has quit (Ping timeout: 264 seconds).
04:56:16 -!- shikhin has joined.
04:58:30 -!- MoALTz__ has joined.
05:01:25 -!- MoALTz_ has quit (Ping timeout: 258 seconds).
05:02:11 -!- Sprocklem has quit (Quit: Sleeping).
05:09:29 -!- password2 has joined.
05:17:52 -!- atslash has joined.
05:20:30 -!- atslash has quit (Client Quit).
05:29:47 -!- hk3380 has quit (Ping timeout: 258 seconds).
05:35:58 -!- \o_yay has quit (Quit: http://i.imgur.com/Akc6r.gif).
05:36:19 -!- ^v has joined.
06:12:44 -!- conehead has quit (Quit: Computer has gone to sleep).
06:17:12 -!- MoALTz__ has quit (Quit: bbl).
06:19:21 -!- Bike has quit (Ping timeout: 276 seconds).
06:28:05 -!- ^v has quit (Quit: http://i.imgur.com/Akc6r.gif).
06:29:19 -!- shikhin has quit (Read error: Connection reset by peer).
06:29:28 -!- shikhin has joined.
06:35:29 -!- password2 has quit (Remote host closed the connection).
06:36:51 -!- hk3380 has joined.
06:39:27 -!- password2 has joined.
06:41:23 -!- drdanmaku has quit (Quit: Connection closed for inactivity).
06:42:30 -!- mtve has joined.
06:52:05 -!- password2 has quit (Remote host closed the connection).
06:52:56 -!- password2 has joined.
07:19:44 -!- tertu has quit (Ping timeout: 255 seconds).
07:22:24 -!- password2 has quit (Ping timeout: 276 seconds).
07:40:53 -!- slereah has joined.
07:40:55 -!- hk3380 has quit (Ping timeout: 252 seconds).
08:18:39 -!- FreeFull has quit.
08:25:47 -!- Patashu has joined.
08:26:05 <kmc> are there esoteric cryptosystems
08:27:59 <slereah> Tattooing your data on the head of a slave
08:29:09 <Jafet> No, only unbreakable 256-bit military grade ones
08:29:47 -!- slereah has left ("Leaving").
08:30:13 <Jafet> (invented independently, of course, not by a military)
08:49:25 -!- Patashu_ has joined.
08:49:25 -!- Patashu has quit (Disconnected by services).
08:52:06 -!- Slereah_ has quit (Ping timeout: 276 seconds).
08:52:45 -!- Slereah_ has joined.
09:06:34 -!- pdxleif has quit (Ping timeout: 240 seconds).
09:09:32 -!- pdxleif has joined.
09:27:22 -!- MindlessDrone has joined.
10:02:58 -!- Slereah_ has quit (Ping timeout: 240 seconds).
10:03:33 -!- Slereah_ has joined.
10:07:57 -!- nucular has joined.
10:07:57 -!- nucular has quit (Changing host).
10:07:57 -!- nucular has joined.
10:16:30 -!- boily has joined.
10:19:35 -!- slereah has joined.
10:22:46 <slereah> The one that only happens for huge amounts of data
10:24:06 <fowl> ahhhhhh ErrorTooMuchData
10:26:02 <slereah> But it gives up on some 200.000 array
10:32:08 <fowl> is there any way that you can use less data?
10:32:19 <slereah> Well I still have to treat them
10:32:39 <slereah> I guess I'll launch Valgrind and go to lunch
10:34:06 -!- Patashu has joined.
10:34:46 -!- oerjan has joined.
10:35:06 -!- Patashu_ has quit (Ping timeout: 240 seconds).
10:39:24 <oerjan> Jafet: good plan. i recall calling out to sort speeded up something i did a _lot_, once. (i don't recall what i was doing, though.)
10:39:40 <oerjan> it's very good at sorting, after all.
10:40:03 <oerjan> (i assume it was gnu sort)
10:40:44 <Jafet> It's not very good at being readable, however
10:40:59 <Jafet> Behold the blob http://git.savannah.gnu.org/gitweb/?p=coreutils.git;a=blob;f=src/sort.c
10:46:02 <oerjan> hm, i think i was sorting a huge file that didn't fit into memory.
10:51:43 -!- Patashu_ has joined.
10:51:43 -!- Patashu has quit (Disconnected by services).
11:01:57 <mroman_> 200k doesn't sound like much
11:02:39 -!- jhj1 has quit (Ping timeout: 265 seconds).
11:03:54 <mroman_> "NapalmV sends this news from the BBC: "The European Union Court of Justice said links to 'irrelevant' and outdated data should be erased on request. The case was brought by a Spanish man who complained that an auction notice of his repossessed home on Google's search results infringed his privacy. Google said the ruling was 'disappointing.'"
11:04:42 -!- nooodl has joined.
11:05:37 <mroman_> it's a legal right to have wrong data or outdated data removed or corrected
11:05:46 <mroman_> in most EU countries at least
11:05:55 -!- boily has quit (Quit: ¨¨¨¨¨¨¨¨).
11:05:55 -!- jhj1 has joined.
11:06:47 <mroman_> theoretically... google isn't even allowed to collect information about me without asking me for permisison to do so
11:07:04 <mroman_> (if google was bound by swiss laws)
11:07:15 <oerjan> yes but it hurts the business model of doing things without a huge human staff.
11:07:26 <oerjan> mroman_: you realize that would have killed the internet, right?
11:08:15 <oerjan> search engines would have been _impossible_ to invent if it required positive action from those indexed.
11:08:43 <mroman_> I don't quiet agree with that.
11:09:03 <mroman_> webmasters could've registered their website for being indexed
11:09:50 <mroman_> they could still index webpages without your permission
11:10:01 <mroman_> because what you publish on your websites is usually considered "public"
11:10:33 <mroman_> what's really illegal is to put all the informtion pieces together to make statements about an individual person
11:11:20 <oerjan> also, this is why robots.txt was invented. he should have been going after the website which publicized him, not google...
11:11:59 <mroman_> but the law shouldn't work like that "unless you say no I'm just gonna do some illegal stuff"
11:12:20 <mroman_> that beats the whole point of privacy imo
11:13:10 <oerjan> yes but for historical reasons search engines _had_ to assume the absense of robots.txt meant consent.
11:13:12 <mroman_> theoretically google has to inform me once they received data about me from a third party
11:13:24 <mroman_> i.e. if someone else said something on some website about me
11:13:39 <mroman_> and google indexed it and analyzed it "deeper" they would have to call me about that ;)
11:13:48 -!- Frooxius has quit (Read error: Connection reset by peer).
11:13:57 <oerjan> yes, theoretically it's impossible to do anything useful without breaking a law hth
11:14:09 <mroman_> however, sending information about my person to foreign countries is actually illegal too
11:14:13 <oerjan> unless you have more lawyers than customers.
11:14:23 <mroman_> so if somebody says something about me on facebook that's already very problematic
11:14:27 -!- Frooxius has joined.
11:14:29 <Jafet> If someone reads something about you anywhere, they are legally obliged to tell you?
11:14:56 <mroman_> Jafet: depends on what they read and what they do with the information
11:15:10 <Taneb> Jafet, i read that u suck
11:15:15 -!- AnotherTest has joined.
11:16:23 <mroman_> otherwise you could say "Well, I didn't collect that information myself"
11:16:24 <Jafet> Taneb: thank you for fulfilling your legal obligation under swiss law
11:16:30 <oerjan> mroman_: so what you're saying is that an actually plausible working internet without having more than the population of earth employed to check everything is illegal in switzerland. gotcha.
11:16:31 <mroman_> and you'd be safe from legal consequences
11:17:09 <mroman_> oerjan: I don't know what your definition of "plausible working internet" is
11:17:15 <mroman_> The internet still works without social media
11:18:13 <mroman_> You are not allowed to make a profile of a person with data you collected from third parties
11:18:24 <mroman_> that doesn't mean social medias are doomed to not exist
11:18:36 <mroman_> it just means that they are not allowed to analyze what people write
11:18:50 <Jafet> No, you are not allowed to. Other people are, because they are not swiss.
11:18:52 <mroman_> if they just "store" the information they are not creating a profile of my person
11:20:11 <mroman_> it still be possible to have social medias and stuff
11:20:48 <mroman_> they might not be free anymore, because they can't make money by shitting on privacy
11:21:13 <mroman_> so they probably have to earn money differently
11:21:24 <Jafet> No, people will not use them and will use the ones that charge no money and shit on privacy.
11:21:36 <Jafet> Especially your privacy.
11:23:21 <mroman_> It's just that I don't really get people complaining about privacy
11:23:45 <mroman_> they complain about it but they still use the free social medias that don't conform to local laws
11:24:12 -!- yorick has joined.
11:24:15 <mroman_> it's not the case that it's impossible to have such social medias, it's just that nobody really actually wants them
11:24:50 <oerjan> this conversation was a bad idea.
11:24:59 <Jafet> I don't really expect anything different from a continent that created browserchoice.eu
11:26:10 <oerjan> because you reminded me that the world sucks, hth
11:27:38 <oerjan> also because headache.
11:29:01 <mroman_> I should probably read about privacy laws in the US :)
11:29:47 <Jafet> Don't worry, it won't take that much time.
11:31:22 <mroman_> "public disclosure of private facts"
11:36:38 <mroman_> is there an official website that documents/publishes laws in the US?
12:02:32 -!- Sgeo has quit (Read error: Connection reset by peer).
12:06:13 -!- Phantom_Hoover has joined.
12:15:03 -!- monotone has quit (Quit: kernel updates).
12:19:01 -!- monotone has joined.
12:33:45 -!- shikhin has quit (Ping timeout: 276 seconds).
12:35:06 -!- shikhin has joined.
12:36:06 <slereah> I wonder how bad gotos really are
12:36:17 <slereah> I think they get a lot of bad rep because of spaghetti code
12:36:20 <fizzie> http://sprunge.us/FaUX man, freenode operators must've done something very personal to this person.
12:36:32 <slereah> But I think people are just afraid to use it nowadays
12:36:56 <slereah> Apparently not enough to use the word FUCK
12:37:10 <slereah> His mama raised him right!
12:38:55 <fizzie> Perhaps it's a case of steganography, and all the numbers encode a hidden message.
12:40:44 <mroman_> slereah: "GOTO considered harmful" considered harmful
12:43:51 <HackEgo> [wiki] [[One]] http://esolangs.org/w/index.php?diff=39515&oldid=39514 * Oerjan * (+30) fmt, sp
12:50:25 <slereah> Is there a general channel for like
12:51:55 <HackEgo> [wiki] [[Talk:Rand.Next()]] http://esolangs.org/w/index.php?diff=39516&oldid=39508 * Oerjan * (+347) unsigned, and No.
12:53:12 <int-e> apparently there's a ##algorithms
12:53:54 -!- AnotherTest has quit (Ping timeout: 276 seconds).
12:54:00 <int-e> with one # even (surprisingly)
12:54:22 <oerjan> must mean knuth owns it.
13:20:04 -!- hk3380 has joined.
13:32:28 -!- drdanmaku has joined.
13:33:28 <FireFly> oerjan: isn't the Perl implementation of CHIQRSX9+ also not Turing-complete by the same reasoning?
13:34:28 -!- FreeFull has joined.
13:40:48 <oerjan> FireFly: indeed. that's part of its purpose.
13:41:28 <oerjan> in fact i considered linking to that
13:43:19 * oerjan notes that he didn't add that article, and his only edit is to adjust the url.
13:45:39 <oerjan> in fact the article was added before i joined the wiki.
13:48:18 -!- Patashu_ has quit (Ping timeout: 240 seconds).
13:52:44 -!- tertu has joined.
14:13:22 -!- Bike has joined.
14:16:52 -!- edwardk_ has joined.
14:20:13 -!- Phantom_Hoover has quit (Read error: Connection reset by peer).
14:20:21 -!- edwardk has quit (Ping timeout: 276 seconds).
14:22:00 -!- Phantom_Hoover has joined.
14:41:23 -!- Sprocklem has joined.
15:04:22 -!- oerjan has quit (Quit: leaving).
15:18:53 -!- Bike has quit (Ping timeout: 264 seconds).
15:26:58 -!- Slereah_ has quit (Ping timeout: 240 seconds).
15:32:33 -!- Slereah_ has joined.
15:39:12 -!- password2 has joined.
15:47:15 <mroman_> now I just need to bind type vars to specific types
15:52:27 -!- Bike has joined.
15:57:29 <mroman_> Implementing a type system is easier than I thought
15:58:43 -!- slereah has quit (Quit: Leaving).
16:05:32 -!- ^v has joined.
16:07:33 <mroman_> At least for static typed stack stuff
16:12:32 -!- ^v has quit (Quit: http://i.imgur.com/Akc6r.gif).
16:17:33 -!- Sprocklem has quit (Ping timeout: 252 seconds).
16:22:41 -!- nucular_ has joined.
16:23:54 -!- Bike has quit (Ping timeout: 240 seconds).
16:26:21 -!- nucular has quit (Ping timeout: 252 seconds).
16:28:29 -!- nucular_ has changed nick to nucular.
16:28:43 -!- nucular has quit (Changing host).
16:28:43 -!- nucular has joined.
16:33:53 -!- TodPunk has quit (Ping timeout: 264 seconds).
16:50:20 -!- Bike has joined.
16:54:53 -!- Bike has quit (Ping timeout: 264 seconds).
16:56:48 -!- shikhin has quit (Remote host closed the connection).
16:57:06 -!- Sprocklem has joined.
16:57:09 -!- hk3380 has quit (Ping timeout: 252 seconds).
17:02:03 -!- TodPunk has joined.
17:24:42 <mroman_> Why does Haskell not allow function overloading?
17:25:03 <mroman_> assuming types don't overlap like pu
17:25:18 <mroman_> foo :: a -> int -> double and bar :: int -> a -> double
17:25:43 <mroman_> currently I'm just picking the first variant I find that typechecks
17:26:20 <myname> well, what for? if it does the same thing but depends on certain properties, make a class
17:26:31 <myname> if it does different stuff, name it differently
17:27:05 <mroman_> Makes sense for Haskell @class
17:27:12 <mroman_> I don't have classes yet :D
17:28:10 <mroman_> I rely on overloading for now I guess
17:28:49 <mroman_> which means that somebody can break all existing pieces of code by defining
17:29:07 <mroman_> because that'd overload pretty much every add variant
17:29:30 <mroman_> I should probably restrict that somehow in the future
17:43:06 -!- Sprocklem has quit (Ping timeout: 258 seconds).
17:43:56 <idris-bot> Data.HVect.index : (i : Fin k) -> HVect ts -> index i ts
17:43:56 <idris-bot> Prelude.List.index : (n : Nat) -> (l : List a) -> (lt n (length l) = True) -> a
17:43:56 <idris-bot> Prelude.Stream.index : Nat -> Stream a -> a
17:43:56 <idris-bot> Prelude.Vect.index : Fin n -> Vect n a -> a
17:44:38 <Melvar> myname: What would you propose for these?
17:45:47 <elliott> Melvar: all of those but Prelude.List.index are special cases of the HVect case
17:45:56 -!- MoALTz has joined.
17:46:36 <Melvar> Vect’s, I suppose, is, but HVect.index uses Vect.index in its type.
17:46:44 <elliott> ok, if you parameterise over the index type too
17:46:55 <elliott> Melvar: what I mean is that you could make a class by tweaking Data.HVect.index's type.
17:47:33 <Melvar> A Stream is infinite and thus any Nat will do, which is not the case for any of the rest …
17:48:21 <elliott> I don't know Idris so this is some kind of frankenstein haskell: class Index seq where type Index seq; type At : Index seq -> Type; index : (idx : Index seq) -> seq -> At idx
17:48:31 <elliott> of course this is ugly. it supports Prelude.List.index too if you make Index a tuple
17:50:53 <Melvar> Doesn’t look like there’d be any chance of inferring things, even if it could be made to work.
17:51:15 <kmc> http://www.openwall.com/lists/oss-security/2014/05/12/3 CVE-2014-0196: Linux kernel pty layer race condition memory corruption
17:53:46 -!- Slereah has joined.
17:54:23 <Melvar> elliott: Btw you overloaded Index there.
17:54:35 <elliott> I said it was frankenstein.
17:56:38 -!- Slereah_ has quit (Ping timeout: 252 seconds).
17:56:41 <idris-bot> Effects.Env.:: : Handler eff m => a -> Env m xs -> Env m (MkEff a eff :: xs)
17:56:41 <idris-bot> Data.HVect.:: : t -> HVect ts -> HVect (t :: ts)
17:56:42 <idris-bot> Prelude.List.:: : a -> List a -> List a
17:56:42 <idris-bot> Data.Vect.Quantifiers.:: : P x -> All P xs -> All P (x :: xs)
17:56:42 <idris-bot> Prelude.Stream.:: : a -> Lazy' LazyCodata (Stream a) -> Stream a↵…
17:57:31 <Melvar> Prelude.Vect.(::) got cut off.
18:00:32 -!- hk3380 has joined.
18:03:18 <idris-bot> When elaborating an application of constructor __infer:
18:03:18 <idris-bot> Can't disambiguate name: Effects.Env.::, Data.HVect.::, Prelude.List.::, Data.Vect.Quantifiers.::, Prelude.Stream.::, Prelude.Vect.::
18:03:57 <Melvar> Huh, that used to work.
18:07:13 <mroman_> myname: static typed stack-based programming languages
18:10:10 <Melvar> Mh, I guess i since imported Quantifiers and Env.
18:17:34 <mroman_> myname: I can probably even infer types
18:17:48 -!- Slereah_ has joined.
18:17:55 <mroman_> if you have a set of built-ins with explicit type signatures
18:21:23 -!- Slereah has quit (Ping timeout: 252 seconds).
18:33:42 -!- password2 has quit (Ping timeout: 258 seconds).
19:08:29 -!- conehead has joined.
19:08:31 -!- Bike has joined.
19:14:27 <int-e> tromp_: you may enjoy http://int-e.eu/~bf3/tmp/Goodstein.hs (corresponding to a horrible 644 bits implementation of the Goodstein sequence in blc with room for improvement)
19:15:42 <Slereah_> What's a good video to gif converter
19:23:12 <int-e> http://www.imagemagick.org/Usage/video/ perhaps. (Conceptually, to me, ImageMagick is "the right tool for the job")
19:23:33 -!- MindlessDrone has quit (Quit: MindlessDrone).
19:23:36 <int-e> But I'm fairly ignorant about the topic.
19:24:14 <Bike> Slereah_: monotone wrote a walkthrough http://blog.room208.org/post/48793543478
19:33:45 <kmc> hello party people
19:39:07 <Bike> "In the past, Gaussian, Inc. has attracted controversy for its licensing terms that stipulate that researchers who develop competing software packages are not permitted to use the software" science code
19:43:20 <fizzie> Does "Gaussian, Inc." own the patents for the normal distribution?
19:43:56 <tromp_> wow; impressive, int-e!
19:44:39 <Bike> it's a quantum mechanics thing. not sure why it's named after gauss but what isn't
19:44:48 <kmc> "The name originates from Pople's use of Gaussian orbitals to speed up calculations compared to those using Slater-type orbitals"
19:45:05 <kmc> I've used netpbm from shell scripts to do video processing
19:45:12 <kmc> including, like, chroma key
19:45:14 <kmc> and other fancy compositing
19:45:23 <Bike> kmc: i meant the origin of gaussian orbitals
19:46:10 <Bike> i'm full of layers, man
19:52:45 -!- Sprocklem has joined.
19:54:18 <int-e> tromp_: the encoding data O = Zero | Succ O | Limit (Nat -> O) is actually fairly standard, but I took a while to realize two things. First, there is the connection between the 'Limit' constructor and the fundamental sequence as used in the Hardy hierarchy. (The connection from there to the Goodstein sequence is made on Wikipedia). Secondly, doing arithmetic on that representation is actually just a copy of the paper...
19:54:24 <int-e> ...definition. (n + 0 = 0; n + (m + 1) = (n + m) + 1; n + (lim f) = lim (n + f), so that's easy (with some caveats, most notably that w (omega) has a "fundamental sequence" different from 1 + w in that representation. So one has to be careful there.)
19:55:39 <kmc> shachaf: if you call a method fn foo(&'t mut self) -> Bar<'t> then 'self' is borrowed mutably for the duration of 't, regardless of how Bar uses its lifetime parameter
19:55:42 <kmc> v. unfortunate :/
19:56:43 <tromp_> int-e: it's hard to appreciate how much faster goodstein grows than the Ackerman-like g i define, which only takes 47 bits:(
19:58:44 <int-e> tromp_: btw your "g" appears here: https://en.wikipedia.org/wiki/Fast-growing_hierarchy#Definition
20:00:18 <int-e> tromp_: it's also noteworthy that most of the effort is spent on converting the input to its hereditary base 2 representation and the corresponding ordinal. from there to the result it's only 91 bits.
20:02:56 <tromp_> oh, that's so much nicer. should consider that ordinal the starting point then
20:07:24 <int-e> tromp_: That's not entirely fair though, because the ordinals encode the necessary recursive structure. Somewhere in the middel, we could start from the cantor normal form of the heriditary base representation (so just a binary tree, of type: data O = Zero | ExpWPlus O O, encoded as a fold), it's 384 bits.
20:14:13 <tromp_> such a round number...
20:14:31 <tromp_> thx for the link; i included it on my page
20:17:03 -!- Slereah_ has changed nick to Slereah.
20:40:19 -!- nucular has quit (Quit: Switching to phone...).
20:43:49 -!- mhi^ has joined.
20:54:30 -!- Patashu has joined.
21:01:19 <ion> http://youtu.be/HTPOSdyA7Uo http://youtu.be/eKK98MpqujA
21:06:04 -!- lambdabot has quit (Read error: Operation timed out).
21:08:24 -!- oerjan has joined.
21:08:54 -!- cillo has joined.
21:11:56 <oerjan> <mroman_> Implementing a type system is easier than I thought <-- now do inference twh
21:12:55 -!- cillo has quit (Client Quit).
21:20:20 -!- Sprocklem has quit (Ping timeout: 255 seconds).
21:20:22 <oerjan> @tell mroman_ <mroman_> Why does Haskell not allow function overloading? <-- the original invention of type classes was in order to have a more principled way of doing overloading than any other language.
21:20:46 <int-e> oerjan: it'll be back in a moment
21:21:26 <int-e> this is what happened: https://clientarea.ramnode.com/announcements.php?id=352
21:21:53 -!- Patashu has quit (Ping timeout: 252 seconds).
21:22:24 <int-e> seems they took almost 15 minutes.
21:22:48 <int-e> (they company is, that is.)
21:22:49 <oerjan> also, aren't you in germany.
21:23:15 <int-e> but from Germany ...
21:23:42 <oerjan> well your client is in .de
21:23:51 <int-e> ... that's another server ...
21:24:16 <int-e> but it was too weak for lambdabot :)
21:25:06 -!- lambdabot has joined.
21:25:24 <lambdabot> http://hackage.haskell.org/trac/ghc/newticket?type=bug
21:25:43 <oerjan> @tell mroman_ <mroman_> Why does Haskell not allow function overloading? <-- the original invention of type classes was in order to have a more principled way of doing overloading than any other language.
21:26:39 <oerjan> hm that reminds me, i wonder if that bug i reported ever got a response. actually i guess not because i think i registered my email.
21:26:54 -!- Bike has quit (Ping timeout: 240 seconds).
21:29:01 -!- Bike has joined.
21:31:44 <oerjan> as expected, really, it's a you're-doing-it-wrong-but-it-doesn't-really-affect-realistic-programs bug
21:32:31 <int-e> oerjan: actually it's nice to see that a 15 minutes absence of lambdabot is surprising people again, rather than being business as usual. :)
21:35:21 -!- nooodl_ has joined.
21:35:25 <idris-bot> Effects.>>= : Eff m a xs xs' -> ((val : a) -> Eff m b (xs' val) xs'') -> Eff m b xs xs''
21:35:25 <idris-bot> Prelude.Monad.>>= : Monad m => m a -> (a -> m b) -> m b
21:37:35 <oerjan> it's like the added distinctions in dependently typed languages make it too hard to make useful classes for functions that are different versions of the "same" concept...
21:38:41 -!- nooodl has quit (Ping timeout: 264 seconds).
21:38:53 <Melvar> Pretty much, in some cases at least.
21:38:56 <oerjan> (looking also at your index and (::) examples earlier)
21:39:58 <oerjan> i suppose someone needs to invent a more suitable way of abstracting over those differences
21:41:12 <oerjan> hm isn't that among the use cases for ghc's PolyKind and ConstraintKind extensions
21:42:24 <oerjan> but you still need things to fit just right.
21:45:18 <Melvar> ( the (Show Int) %instance
21:45:18 <idris-bot> constructor of Prelude.Show (\{meth0} => prim__toStrInt meth) : Show Int
21:47:10 -!- boily has joined.
21:49:28 -!- metasepia has joined.
21:51:26 <metasepia> CYUL 142121Z 18009G15KT 15SM SCT045 OVC070 23/15 A3008 RMK SC3AC5 SLP187 DENSITY ALT 800FT
21:51:38 <metasepia> ENVA 142120Z 17003KT CAVOK 04/M02 Q1029 RMK WIND 670FT 30003KT
21:52:23 <Melvar> oerjan: “class Finite (n : Nat) t where isoFin : Iso t (Fin n)” is also a thing, outside of the stdlib though.
21:52:44 <boily> you are my DENSITY, DENSITY, DENSITY 君と行ける未来 ♪
21:57:14 <oerjan> int-e: huh, and that goodstein program has no recursion?
21:57:38 <int-e> oerjan: that was the point
22:03:05 <kmc> shachaf: here is a somewhat odd bit of Rust code: for _ in replace(&mut self.roots, vec!()).move_iter().rev() {}
22:09:10 -!- nooodl_ has changed nick to nooodl.
22:13:29 * kmc hands idris-bot some 3,4-methylenedioxymethamphetamine
22:16:43 * boily hands metasepia some organic free-range Himalayan tofu
22:17:05 <boily> kmc: you vile bot drugger! you should feel ashamed!
22:20:18 <oerjan> boily: that's not tofu but rancid butter hth
22:24:33 <oerjan> "According to the Tibetan custom, butter tea is drunk in separate sips, and after each sip the host refills the bowl to the brim. Thus, the guest never drains his bowl; rather, it is constantly topped up. If the visitor does not wish to drink, the best thing to do is leave the tea untouched until the time comes to leave and then drain the bowl. In this way etiquette is observed and the host will not be offended."
22:27:29 <oerjan> "Based-on the principles believed to be at work with the tea, coffee-drinkers have created a coffee version of the beverage."
22:28:00 <boily> I reject your reality and substitue my sane own.
22:29:41 <oerjan> i've tried to reject reality but it's somehow not working properly.
22:32:14 -!- edwardk_ has changed nick to edwardk.
22:32:59 <oerjan> spot the hidden burn "Many different political entities have communities of herders who produce and consume yak's dairy products including cheese and butter – for example, China, India, Mongolia, Nepal, and Tibet."
22:33:27 <Bike> that sounds like a shoddy patch over "countries".
22:33:51 <boily> it's not very hidden... it's more like check-out-that-pulsating-radiating-mesmerizing-glow.
22:35:58 <oerjan> i'm just amazed that it's been there since 2011.
22:36:06 <kmc> wikipedia?
22:36:08 <oerjan> https://en.wikipedia.org/w/index.php?title=Yak_butter&diff=437641611&oldid=437595102
22:36:17 <Bike> it's not inaccurate.
22:36:41 <Bike> nominally, tibet has a good deal of self-governance.
22:36:43 <kmc> that seems less like a deliberate burn and more like an attempt to avoid trouble from chinese nationalist trolls
22:36:49 <Bike> basically that.
22:36:54 <kmc> of which there are many
22:37:15 <kmc> I don't know if the govt has an app to coördinate the trolls like Israel does
22:37:26 <Bike> the usual term for when you want to talk about nations without talking about nations is "culture", though
22:37:40 <oerjan> well i'm just amazed that they haven't removed it _anyhow_. admittedly i didn't check all intervening edits.
22:37:47 <Bike> why would they remove it?
22:37:47 <kmc> yes, there's no reason to mention politics there
22:37:54 <Bike> oh, because they're trolls, you mean
22:39:18 <oerjan> i'd imagine even listing China and Tibet separately under _any_ categorization would be enough to trigger them.
22:39:24 <Bike> yeah i see what you mean
22:39:35 <Bike> maybe chinese nationalists don't care for yak butter
22:40:35 -!- yorick has quit (Remote host closed the connection).
22:43:19 <kmc> well PRC also claims Taiwan and yet puts up with ROC being listed separately in some categorizations, as long as the right words are used
22:43:29 <kmc> e.g. "Chinese Taipei" at the olympics, what a wonderful bit of deliberate ambiguity
22:44:35 <kmc> although Hong Kong has its own Olympic delegation as well
22:45:58 <Bike> i didn't know taiwan even had an olympic team.
22:46:12 <kmc> http://en.wikipedia.org/wiki/Template:Multiple_Olympic_Teams
22:46:28 <Bike> what about macau?
22:46:46 <kmc> they're not members of the IOC but they participate in the Asia Games or something
22:53:21 <kmc> nice! http://rust.godbolt.org/
22:54:58 <Bike> i guess "int x;" isn't legal so i give up
22:55:14 <Taneb> kmc, I like that :)
22:56:00 <kmc> holy shit, people are doing GBA homebrew in Rust: https://github.com/exoticorn/gba-rust
22:56:35 <Bike> what processors does rustc target, anyway
22:59:12 <kmc> there's also a hardware abstraction layer for bare metal ARM: https://github.com/hackndev/zinc
22:59:23 -!- Sorella has joined.
22:59:25 * kmc is reading backlog of This Week in Rust
23:07:51 -!- edwardk has quit (Quit: Computer has gone to sleep.).
23:12:02 -!- Sgeo has joined.
23:16:04 -!- boily has quit (Quit: MERIDIAN CHICKEN).
23:16:06 -!- metasepia has quit (Remote host closed the connection).
23:17:41 -!- hogeyui has quit (Ping timeout: 264 seconds).
23:24:29 <Sgeo> With OOP, if an object has several methods that do the same thing, how is a subclasser supposed to know which one to override to override the others? Is that expected to be part of documentation, or just reading the code?
23:27:12 <fowl> several methods that do the same thing -- code smell
23:27:51 <Sgeo> Seems to happen all the time in Smalltalk
23:27:57 <Bike> sgeo probably means similar-but-a-bit-different things, like a method that writes a description of the object to standard output vs. a method that writes a description of the object on the washington monument
23:28:42 <Sgeo> But the question also kind of extends to Java and actual issues I've encountered, where it seems non-obvious what the mimimal set of methods I need to override to prevent something from happening is
23:29:36 <oerjan> clearly you need to borrow Haskell's new MINIMAL pragma.
23:30:18 <Bike> or have some non virtual methods obviously
23:31:02 <Sgeo> I think this may be subtyping's fault, or something
23:31:38 <Bike> well you can't even state the problem without subtyping.
23:31:52 <Bike> blame smalltalk.
23:32:12 <shachaf> whoever came up with that MINIMAL thing must've been p. great
23:32:28 -!- hogeyui has joined.
23:34:44 <kmc> was it you
23:34:47 <kmc> is that the joke
23:35:10 <oerjan> kmc: hey no fun ruining the joke this soon
23:37:55 <Sgeo> There is the theory of the mobius
23:38:03 -!- nooodl has quit (Ping timeout: 255 seconds).
23:39:04 <Bike> a twist in the fabric of space, where time becomes a loop.
23:39:42 <kmc> > cycle "time becomes a loop. "
23:39:43 <lambdabot> "time becomes a loop. time becomes a loop. time becomes a loop. time becomes...
23:40:43 <Bike> good stopping point.
23:43:00 <Bike> when we reach that point, whatever happened will happen again
23:43:35 <Bike> shachaf will introduce MINIMAL again
23:46:10 <Bike> hm, this paper claims to determine a "word length" for neural information
23:53:18 <fowl> whats neural information
23:53:58 <Taneb> I'm hungry, but it's almost 1 AM
23:54:02 <Taneb> And I don't have any food
23:54:08 <fowl> Taneb, fourth meal
23:55:13 <Bike> fowl: information neurons "send".
23:56:06 <fowl> what lke a float
23:56:55 <Bike> yes. like a float. exactly.
23:57:38 <elliott> are brains IEEE 754 compliant?
23:59:28 <Bike> it actually uses the IBM 7094 format, for compatibility
00:05:42 <oerjan> elliott: NaN NaN NaN i can't hear you
00:09:11 -!- mhi^ has quit (Quit: Lost terminal).
00:21:14 -!- hk3380 has quit (Ping timeout: 255 seconds).
00:23:03 -!- hk3380 has joined.
01:04:55 -!- ^v has joined.
01:11:42 <Sgeo> Wonder if you could make a highly dynamic environment with pure immutability and FRP
01:12:49 <oerjan> i'm afraid we'll never know the answer, as int-e has changed the @faq command.
01:13:03 <Sgeo> @faq Can Haskell be Smalltalk?
01:13:03 <lambdabot> http://www.haskell.org/haskellwiki/FAQ
01:13:21 <Sgeo> (Probably better for newbies though)
01:18:38 -!- Bike has quit (Ping timeout: 265 seconds).
01:18:44 -!- Bike_ has joined.
01:39:03 -!- Bike_ has changed nick to Bike.
01:39:48 <Sgeo> Hmm, I'm sad that chaining isn't so easy in Smalltalk
02:01:55 -!- oerjan has quit (Quit: leaving).
02:08:59 -!- hk3380 has quit (Ping timeout: 252 seconds).
02:25:02 -!- impomatic has quit (Read error: Connection reset by peer).
02:34:24 -!- Bike has quit (Ping timeout: 258 seconds).
02:36:16 -!- Bike has joined.
02:48:13 <Sgeo> self value: [ ^nil ]
02:49:41 -!- Bike has quit (Ping timeout: 252 seconds).
02:49:45 -!- password2 has joined.
02:51:40 -!- Bike has joined.
02:53:47 -!- Phantom_Hoover has quit (Remote host closed the connection).
03:00:23 -!- archaic has quit (Ping timeout: 245 seconds).
03:12:04 -!- hk3380 has joined.
03:14:23 -!- Sorella has quit (Quit: It is tiem!).
03:20:53 -!- alone has joined.
04:21:16 -!- ^v has quit (Read error: Connection reset by peer).
04:21:44 -!- ^v has joined.
04:26:49 -!- ^v has quit (Read error: Connection reset by peer).
04:27:15 -!- ^v has joined.
04:32:12 <Jafet> Today, the anniversary of a CA upgrading from 1024-bit root keys https://www.digicert.com.my/news/news_20130515.htm
04:34:26 <Bike> i don't get it
04:35:49 -!- tromp has joined.
04:36:48 -!- hk3380 has quit (Ping timeout: 265 seconds).
04:53:06 -!- glogbackup has quit (Ping timeout: 240 seconds).
05:01:24 -!- drdanmaku has quit (Quit: Connection closed for inactivity).
05:14:01 <Sgeo> Ugh I don't think I like the ... lessened down mechanics of Hearthstone, but I think I'd like being able to play quickly without spending a fortune and being able to play the full game
05:15:14 * Sgeo is suddenly reminded of a C# vs Java thing. I think ais523 said something like C# being the better language but Java having a better environment? Well, Magic: the Gathering might be a better game but Hearthstone has a better play environment. Although I'm not yet actually involved enough in either to say
05:16:40 <Bike> i NEED to stuff you into a locker now
05:19:26 <fizzie> How can you stuff god into a locker?
05:21:29 <Bike> she just needs to say something like that, and i will be necessarily empowered
05:31:13 -!- password2 has quit (Ping timeout: 245 seconds).
05:37:31 -!- tromp has quit (Remote host closed the connection).
05:37:43 <myname> maybe i want to learn how to use markov chains
05:38:03 -!- tromp has joined.
05:42:18 -!- tromp has quit (Ping timeout: 240 seconds).
05:46:17 <Jafet> I bet you can learn from fungot
05:46:17 <fungot> Jafet: you know, that went fairly well, that too.
05:46:50 <fowl> Jafet, sometimes i could swear theres a real person pulling his strings
05:48:01 <fungot> Available: agora alice c64 ct darwin discworld enron europarl ff7 fisher fungot homestuck ic irc iwcs jargon lovecraft nethack oots* pa qwantz sms speeches ss wp youtube
05:48:09 <fungot> Selected style: youtube (Some YouTube comments)
05:48:24 <Jafet> fungot do you have video tutorials
05:48:24 <fungot> Jafet: hes hot! i just assumed it was flown from outside of the devs after 3dr went down.
05:48:41 <Bike> fungot: how do you feel about space oddity
05:48:41 <fungot> Bike: erm... no one on board if it happens often. that took a few minutes to burn. looks stunning! must see!! its very very very intersing!!
05:50:03 <myname> unplausible, he doesn't talk about how well he could fap
05:50:17 -!- ^v has quit (Quit: http://i.imgur.com/Akc6r.gif).
05:51:18 <HackEgo> [wiki] [[Special:Log/newusers]] create * IceCodr * New user account
05:55:27 -!- MoALTz has quit (Quit: bbl).
05:57:01 -!- nooodl has joined.
06:04:48 -!- nooodl has quit (Quit: Ik ga weg).
06:08:40 -!- tromp has joined.
06:12:53 -!- tromp has quit (Ping timeout: 245 seconds).
06:22:53 -!- FreeFull has quit.
06:38:36 -!- tertu has quit (Ping timeout: 276 seconds).
06:54:17 <Sgeo> I wonder if you could say that in Hearthstone terms, all Magic creatures have Taunt
06:55:02 <Sgeo> Hmm, not quite equivalent, in Hearthstone attacker could still choose which Taunt creature to attack
06:57:26 -!- edwardk has joined.
06:59:55 <mroman_> With function overloading I actually don't need type classes
07:00:15 <mroman_> it's surprisingly powerful
07:01:26 <mroman_> @tell oerjan Makes sense. More or less it just defines how one can legally "overload" it
07:04:33 -!- Slereah has quit (Ping timeout: 245 seconds).
07:14:26 -!- edwardk has quit (Read error: Connection reset by peer).
07:14:52 -!- edwardk has joined.
07:20:38 -!- edwardk has quit (Read error: Connection reset by peer).
07:21:28 -!- edwardk has joined.
07:23:41 -!- impomatic has joined.
07:26:38 -!- Bike has quit (Ping timeout: 245 seconds).
07:35:16 -!- shikhin has joined.
07:38:50 -!- slereah has joined.
07:57:43 -!- MindlessDrone has joined.
08:07:03 -!- edwardk has quit (Ping timeout: 265 seconds).
08:25:40 -!- Patashu has joined.
08:27:09 -!- Patashu has quit (Disconnected by services).
08:27:09 -!- Patashu_ has joined.
08:41:16 -!- tromp has joined.
08:45:51 -!- tromp has quit (Ping timeout: 258 seconds).
08:51:07 -!- conehead has quit (Quit: Computer has gone to sleep).
08:55:15 -!- shikhin has quit (Ping timeout: 252 seconds).
09:00:09 <HackEgo> [wiki] [[Two]] N http://esolangs.org/w/index.php?oldid=39517 * Tailcalled * (+2029) Created page with "'''Two''' is a language invented by [[User:Tailcalled]]. It is an uncomputable extension to a [[Brainfuck]] dialect, designed to increase the power as much as possible with a ..."
09:00:48 -!- tailcalled has joined.
09:06:10 <mroman_> nortti: http://eso.mroman.ch/ESOSC/
09:06:23 <mroman_> 17 have answered the survey so far. So I took the time to create a working draft with the current results
09:06:34 <mroman_> somebody even wanted EOF to be 4 o_O
09:08:32 <mroman_> hm. output in text mode should probably use ASCII anyway?
09:08:49 <mroman_> unless you want unicode or something
09:10:57 <mroman_> or at least ASCII compatible
09:11:05 <mroman_> otherwise using \n wouldn't make sense anyway
09:11:45 <mroman_> two brainfuck derivatives in two days?
09:19:39 <mroman_> tailcalled: I loops forever if the cell is already "infinity"?
09:20:26 <mroman_> I read that as "I" increases until it becomes infinity and if that can't be done it loops forever
09:23:18 -!- tailcalled has quit (Ping timeout: 240 seconds).
09:32:14 <slereah> What does the lambda mean in NBF
09:37:34 <slereah> Why are [] always paired anyway
09:37:45 <slereah> A lone [ sounds like a good idea for an if statement!
09:38:18 <slereah> Though I guess it may get confusing
09:38:47 <slereah> Oh wait, not an if I guess
10:07:49 -!- john3213 has joined.
10:12:51 -!- john3213 has left.
10:17:04 -!- boily has joined.
10:25:54 <mroman_> lifthrasiir: esoteric song contest
10:26:06 <mroman_> either that or the esoteric standard committee
10:30:52 <slereah> Esoteric Senegalese Cinema
10:43:08 <boily> mroman_: mrhelloman_. you're in sénégal now?
10:45:22 <Jafet> Hmm, Moolaadé is considered a Senegalese film but was "filmed in Burkina Faso". (According to wikipedia, which also puts its article in "Category:Films shot in Senegal".)
11:02:55 -!- oerjan has joined.
11:02:58 -!- boily has quit.
11:03:25 -!- hk3380 has joined.
11:04:37 <mroman_> I've just managed to implement pointers!
11:04:58 <mroman_> I can now do stuff like foo :- B A A -> B* B**; foo := pop pop getPtr dup getPtr
11:05:24 <mroman_> and it type checks as it should
11:05:36 <lambdabot> mroman_ said 4h 4m 10s ago: Makes sense. More or less it just defines how one can legally "overload" it
11:05:46 <mroman_> (getPtr :- A -> A*; pop :- A ->; dup :- A A -> A)
11:06:40 -!- yorick has joined.
11:07:14 -!- edwardk has joined.
11:07:44 <mroman_> the only thing that's annoying currently is seeing error messages that actually aren't :D
11:08:28 <mroman_> "Can't match expected type `int' with `float' [add]"
11:09:02 <mroman_> the problem is it searches through every overloaded version of a function until it finds one that typechecks
11:09:11 <mroman_> but in the process of doing so it just prints error messages :D
11:09:22 <oerjan> i recommend changing that.
11:09:35 <mroman_> the first defined version of add is add :- int int -> int
11:10:36 <mroman_> currently the problem is that you can't define the type of a function that should be somewhat polymorphic
11:10:46 <mroman_> i.e sum :: (Num a) => [a] -> a in Haskell
11:11:36 <mroman_> so sum :- A* -> A obviously doesn't type check when you use add in it
11:11:54 -!- edwardk has quit (Ping timeout: 240 seconds).
11:12:27 <mroman_> that' d produce "can't match expected type `int' with `A' [add]"
11:12:35 <oerjan> mroman_: now ponder what happens when you make a pointer to a polymorphic value hth
11:12:55 <mroman_> The solution I have in mind is to disable type checking for such functions
11:13:18 <mroman_> disable requiring a type signature to be precise
11:14:06 <mroman_> I can treat "sum" as "inlined"
11:14:11 <mroman_> and then infer the type myself
11:14:16 <oerjan> do you know about the ml value restriction twh
11:14:30 <oerjan> that's ml's solution to that problem.
11:14:46 <oerjan> but it might not apply to a stack language.
11:15:09 <mroman_> i.e. since there's an add :- int int -> int and add :- float float -> float
11:15:23 <mroman_> the function foo := 5 5 add and foo := 5.0 5.0 add both will type check
11:15:37 <mroman_> however, what you currently can't do is define genericAdd := add
11:15:42 <oerjan> oh wait you were not talking about pointers to polymorphic values at all.
11:15:56 <mroman_> because that' require a type signature genericAdd :- ? stuff here ? genericAdd := add
11:16:42 <mroman_> oerjan: I just can't type check such functions "out of context"
11:17:00 <mroman_> I check each function individually if it corresponds to its type signature
11:17:13 <mroman_> and then I check the code together
11:17:49 <mroman_> genericAdd :- A A -> A; genericAdd = add; can't fullfil its type signature
11:20:00 -!- Phantom_Hoover has joined.
11:21:44 <mroman_> http://codepad.org/W0OX9LoY <- that'd be my approach to solve it
11:22:41 <mroman_> but you can't overload such functions anymore :)
11:23:23 <mroman_> (i.e you couldn't do stuff like genericAdd :: (Num a) => a -> a -> a and also have a genericAdd :: (Foobaz a) => a -> a -> a
11:23:53 <mroman_> which would be kinda weird anyway
11:23:54 <oerjan> also, that probably breaks recursion hth
11:25:25 <oerjan> (which i'm thinking because i'm vaguely recalling that _without_ recursion, the hindley-milner type system is simply equivalent to inlining everywhere.)
11:25:50 <oerjan> (and then type checking non-polymorphically.)
11:26:19 -!- hk3380 has quit (Ping timeout: 252 seconds).
11:27:31 * oerjan wonders what language codepad is guessing that as
11:31:50 <oerjan> <mroman_> somebody even wanted EOF to be 4 o_O <-- inspired by unix ^D, presumably
11:45:55 <atehwa> mroman_: funny we should have ESOSC, since there was a similar thingy in early 2000's, ENSI: http://esoteric.sange.fi/ENSI/
11:46:09 <HackEgo> U+0004 <control> \ UTF-8: 04 UTF-16BE: 0004 Decimal:  \ \ Category: Cc (Other, Control) \ Bidi: BN (Boundary Neutral)
11:46:35 <HackEgo> U+0004 <control> \ UTF-8: 04 UTF-16BE: 0004 Decimal:  \ \ Category: Cc (Other, Control) \ Bidi: BN (Boundary Neutral)
11:47:43 <mroman_> oerjan: http://codepad.org/1UUkCPjL
11:50:02 <mroman_> fib :- int -> int; fib := dup fib swap fib add type checks at least
11:50:20 <oerjan> i meant with polymorphism.
11:50:20 <mroman_> even though that wouldn't calc fib
11:53:36 <oerjan> hm, i suppose your method is also the way C++ templates do it.
11:53:47 <oerjan> so i guess inlining ought to work.
11:54:04 * oerjan doesn't _actually_ know C++ templates.
11:55:22 <mroman_> well mother @= parent female mother can't be inlined
11:55:31 <mroman_> that'd produce infinite amounts of code :)
11:55:48 <mroman_> bla :- A -> A A; bla := dup bla; can't be type checked so far
11:56:12 <Melvar> “fib := 1 > if dec dup dec fib swap fib add then”?
11:56:28 <mroman_> A -> A A means that after wards the top element has been duplicated
11:56:38 <mroman_> but bla := dup bla; wouldn't just duplicate it
11:56:44 <oerjan> mroman_: um surely bla := dup bla _shouldn't_ have the type A -> A A
11:57:05 <mroman_> oerjan: bla := dup bla looks like infinite type :D
12:17:34 <mroman_> recursion is indeed a problem :D
12:19:57 * oerjan puts on his "told you so" hat
12:20:18 <mroman_> I think it will work if I mark it as "visited" after a recursion
12:20:30 <mroman_> it's a problem of my implementation
12:20:35 <mroman_> not a problem of the type system I think
12:22:48 <mroman_> it still a little bit sucky though
12:26:25 <mroman_> oerjan: http://codepad.org/w6zVJRLq
12:26:39 <mroman_> ^- that one seems to work nicely
12:26:46 <mroman_> (notice that mother is recursive)
12:27:53 -!- Phantom_Hoover has quit (Ping timeout: 245 seconds).
12:29:32 -!- Sgeo has quit (Read error: Connection reset by peer).
12:40:13 -!- nucular has joined.
12:40:13 -!- nucular has quit (Changing host).
12:40:13 -!- nucular has joined.
12:43:25 -!- MindlessDrone has quit (Read error: Connection reset by peer).
12:45:26 <nortti> 12:06 < mroman_> somebody even wanted EOF to be 4 o_O <-- I think I know who, the rationale was that 4 is ascii EOT
12:50:11 <mroman_> (recursive polymorphic stuff)
12:51:48 <mroman_> looks like I need some sort of type classes afterall
12:52:12 <oerjan> YOU CANNOT ESCAPE THE MONADS
12:53:26 -!- Sorella has joined.
12:53:35 -!- Patashu_ has quit (Ping timeout: 252 seconds).
12:53:38 <Melvar> I just defined fib in forth. With a loop, because forth doesn’t seem to do recursion.
12:55:26 <oerjan> http://www.taygeta.com/forth_intro/recurse.htm
12:56:10 <Melvar> Bluh, of course they would do it that way.
12:59:20 <oerjan> or http://wiki.laptop.org/go/Forth_Lesson_4#Recursion_and_Chaining which seems to do it in another way again.
13:04:19 <Melvar> Hm, both of those seem to work in gforth.
13:04:30 <Taneb> mroman_, nortti, would it be within ESOSC's remit to make a lambda calculus standard?
13:05:16 <mroman_> oerjan: A template based approach looks like it works
13:05:26 <mroman_> you define the function with generic arguments
13:05:32 <mroman_> and then you define one with conceret types
13:05:54 <nortti> Taneb: what would it do?
13:06:14 <mroman_> http://codepad.org/kmaam6fQ <_ You define the implementation first
13:06:30 <mroman_> and :: copies the implementation and sets a concrete type signature
13:06:56 <Taneb> nortti, just a standardized syntax and semantics for Lambda Calculus
13:08:01 <mroman_> Taneb: you mean "ascii" syntax?
13:08:30 <mroman_> i.e ^x.f x vs \x.f x vs whatever notation people use too
13:08:36 <Taneb> mroman_, I was thinking Unicode with an ascii fallback
13:09:04 <mroman_> isn't that kinda standardized to use the lambda symbol?
13:09:33 <mroman_> WP seems to use lambda at least
13:09:55 <mroman_> and untyped lambda calculus?
13:10:59 <Taneb> U+03BB with 0x5C as fallback
13:11:04 <Taneb> Yes, untyped lambda calculus
13:16:36 <mroman_> So far most I've seen is usually in the form of \fxy.fyx or λfxy.fyx
13:17:16 <mroman_> I'm not sure how many times you'd need more than ['a'..'z']
13:18:36 -!- drdanmaku has joined.
13:19:56 <mroman_> http://codepad.org/7eBWlWD3
13:20:13 <mroman_> I'm curious what kind of stuff I can solely do with the type system o_O
13:20:46 <mroman_> I think I can do at least one :- -> A; inc :- A -> A A; dec :- A A -> A;
13:21:15 <mroman_> I'd have to figure out if I can write a compare function only with the type system
13:21:49 <mroman_> how would I distinguish numbers
13:24:39 -!- shikhin has joined.
13:49:59 <mroman_> Taneb: I can put it to the upcoming drafts ;)
13:51:38 <HackEgo> [wiki] [[Talk:Brainfuck]] http://esolangs.org/w/index.php?diff=39518&oldid=39179 * Maxdefolsch * (+1028) /* My optimizing interpreter again */ new section
13:57:34 <mroman_> He better make it a standard conform bf interpreter!
14:01:51 <slereah> And + applied to 98 jumps to 136
14:06:15 <oerjan> slereah: but that usually applies to reading the program, not its input...
14:08:04 <slereah> I will also require balanced + and -!
14:08:14 <slereah> Otherwise it would be anarchy
14:09:19 <nortti> balanced '+' and '-' or balanced '+' and '-!'?
14:13:04 -!- MindlessDrone has joined.
14:16:37 -!- nooodl has joined.
14:19:56 -!- Bike has joined.
14:42:29 -!- password2 has joined.
14:42:59 -!- password2 has quit (Max SendQ exceeded).
14:44:34 -!- password2 has joined.
14:46:26 -!- password2 has quit (Max SendQ exceeded).
14:49:34 -!- password2 has joined.
14:51:15 -!- password2 has quit (Max SendQ exceeded).
14:57:30 -!- oerjan has quit (Quit: Max (Max SendQ exceeded) exceeded).
14:57:34 -!- mhi^ has joined.
14:58:04 -!- mhi^ has left.
15:08:27 -!- MindlessDrone has quit (Quit: MindlessDrone).
15:10:32 -!- password2 has joined.
15:12:07 -!- hk3380 has joined.
15:13:18 -!- password2 has quit (Max SendQ exceeded).
15:13:55 -!- ^v has joined.
15:16:13 <mroman_> slereah: Is +[-] balanced?
15:22:15 <mroman_> nortti, Taneb: There's been an update to NBF btw. (http://eso.mroman.ch/ESOSC/s/2014-2/ESOSC-2014-D2-R4.pdf)
15:23:22 <Taneb> mroman_, should sections 2 and 3 be merged?
15:23:48 <Taneb> Or at least 3 should be 2.1
15:29:26 <Taneb> With that change I'll approve it
15:30:34 -!- password2 has joined.
15:32:04 -!- password2 has quit (Max SendQ exceeded).
15:36:16 <nortti> mroman_: seems good, I approve
15:36:33 <nortti> with the 3 -> 2.1 change
15:50:46 -!- password2 has joined.
15:51:40 -!- password2 has quit (Max SendQ exceeded).
15:51:49 -!- shikhout has joined.
15:52:43 -!- password2 has joined.
15:53:40 -!- password2 has quit (Max SendQ exceeded).
15:54:55 -!- shikhin has quit (Ping timeout: 265 seconds).
15:59:42 -!- shikhout has changed nick to shikhin.
16:04:57 -!- KingOfKarlsruhe has joined.
16:08:44 -!- conehead has joined.
16:09:22 -!- slereah has quit (Quit: Leaving).
16:12:06 -!- password2 has joined.
16:12:46 -!- password2 has quit (Max SendQ exceeded).
16:14:01 -!- password2 has joined.
16:14:36 -!- shikhin has quit (Remote host closed the connection).
16:15:14 -!- password2 has quit (Max SendQ exceeded).
16:16:04 <mroman_> I gotta find a good latex to html tool
16:31:00 -!- FreeFull has joined.
17:02:59 <mroman_> but the output look kinda non funky
17:04:38 <mroman_> but it's better than nothing.
17:06:33 -!- conehead has quit (Quit: Computer has gone to sleep).
17:06:47 <mroman_> Pandoc: http://eso.mroman.ch/ESOSC/s/2014-2/ESOSC-2014-A2.html
17:07:07 <mroman_> Some other tool by latex -> rtf + rtf -> html http://eso.mroman.ch/ESOSC/s/2014-1/ESOSC-2014-A1.html
17:08:20 <nortti> A2's code is pretty much just pure html
17:13:40 <fizzie> http://sprunge.us/XeZF free gigs
17:13:52 <fizzie> ("Extra space" partitions on two conference proceedings USB sticks.)
17:17:13 -!- hk3380 has quit (Ping timeout: 252 seconds).
17:17:43 -!- conehead has joined.
17:18:58 <Melvar> A1 uses `'! Kill it with fire!
17:19:54 -!- Slereah_ has joined.
17:20:03 <HackEgo> [wiki] [[Special:Log/newusers]] create * Icepy * New user account
17:21:41 <HackEgo> [wiki] [[User:Icepy]] N http://esolangs.org/w/index.php?oldid=39519 * Icepy * (+86) Created page with "Hi, I'm Icepy. I create esoteric programming languages (made in python), and iOS apps."
17:55:00 -!- shikhin has joined.
18:16:24 <mroman_> Taneb: Why do you wan't a standard about lc?
18:20:54 -!- ^v has quit (Read error: Connection reset by peer).
18:21:19 -!- ^v has joined.
18:26:20 -!- MoALTz has joined.
18:28:03 -!- hk3380 has joined.
18:31:52 <HackEgo> [wiki] [[@text]] N http://esolangs.org/w/index.php?oldid=39520 * Icepy * (+4809) Created page with "@text is a programming language created by [[User:Icepy]], and is related to [[!!!Batch]], But has it's own way of interpreting. You don't tell it what to do to get to a certa..."
18:38:04 <HackEgo> [wiki] [[@text]] http://esolangs.org/w/index.php?diff=39521&oldid=39520 * GreyKnight * (+28) not convinced
18:40:16 <elliott> can we stop putting [citation needed] tags on every bad language it's kinda getting old
18:43:07 <HackEgo> [wiki] [[Talk:@text]] N http://esolangs.org/w/index.php?oldid=39522 * GreyKnight * (+175) Created page with "== "programming language" == This isn't a programming language, it's a character set. --~~~~"
18:46:13 <HackEgo> [wiki] [[@text]] http://esolangs.org/w/index.php?diff=39523&oldid=39521 * Icepy * (+21)
18:47:08 <Bike> i'm entertained.
18:47:09 <HackEgo> [wiki] [[Special:Log/upload]] upload * Icepy * uploaded "[[File:Example.png]]"
18:47:53 <Bike> http://esolangs.org/w/images/7/70/Example.png aw yiss
18:49:24 <HackEgo> [wiki] [[@text]] http://esolangs.org/w/index.php?diff=39525&oldid=39523 * Icepy * (+9)
18:51:14 <HackEgo> [wiki] [[Talk:@text]] http://esolangs.org/w/index.php?diff=39526&oldid=39522 * Ehird * (+491) /* "programming language" */ re
18:52:44 <HackEgo> [wiki] [[@text]] http://esolangs.org/w/index.php?diff=39527&oldid=39525 * Icepy * (-5)
18:52:55 <Bike> i love how shitty the ascii S in esme is.
19:09:10 <mroman_> a pretty bad character set
19:09:20 * impomatic was just looking at this: http://sdtimes.com/content/article.aspx?ArticleID=71233&page=1
19:09:27 <impomatic> "Fifteen toys, games and tools that teach programming"
19:09:27 <mroman_> seeing as it encodes the values of asci probably with 10times the space requirements
19:10:15 <mroman_> when I was 13 I also made esolangs like that
19:13:00 <mroman_> nowadays I just make crappy languages and mark them as esoteric as a cover up
19:17:27 <mroman_> Is there a recent BASIC compiler for windows somewhere?
19:17:52 <mroman_> The *real* BASIC. Not some Basic Dialect that has actually nothing to do with Basic except that it doesn't use curly braces
19:18:27 <Bike> the basic that can be spoken of is not the true basic
19:19:01 <fizzie> But REALbasic is all object-oriented and all.
19:19:28 <fizzie> Oh, it's called Xojo now.
19:20:32 <nortti> hmm, I wonder what sort of esolang IMAGINARYbasic would be
19:21:17 <olsner> similar to imaginaryBASIC but the other way around?
19:22:27 <mroman_> That means I can create all sorts of crazy BASIC dialects myself
19:23:14 <fizzie> http://en.wikipedia.org/wiki/List_of_BASIC_dialects a long list
19:23:30 <mroman_> but it's missing CRAZYBASIC
19:24:31 <olsner> google seems to refuse to google for crazybasic
19:24:33 <fizzie> I don't think I've really used more than maybe four or five BASICs.
19:25:18 <mroman_> shouldn't be too hard to mock up a BASIC dialect and translate it to C
19:25:33 <mroman_> that could probably even be done just be preprocessor macros
19:26:04 <nortti> but that would just be ugly
19:26:38 <fizzie> There's a LLVM-based QBasic-wannabe, based on a quick googling.
19:27:15 <fizzie> As in, "tries to be QBasic-compatible", as far as I can tell.
19:27:35 <mroman_> Does it have line numbers?
19:28:12 <HackEgo> [wiki] [[Talk:@text]] http://esolangs.org/w/index.php?diff=39528&oldid=39526 * GreyKnight * (+507) /* "programming language" */
19:28:15 <fizzie> I can't really tell, it's just a Github readme that I hit. It could be pretty vaporware.
19:28:26 <nortti> actually, doesn't freebasic also have qbasic-emulation mode?
19:28:40 <fizzie> E.g. there's a section heading titled "Implementation Detail", containing only "int/long is directly supported by LLVM, so , no discssiion needed."
19:28:49 <fizzie> Which might not count as a good sign.
19:29:57 <fizzie> The FreeBASIC site claims "high level of support for programs written for QuickBASIC", and QBASIC is a QuickBASIC derivative, so I guess, in a sense.
19:30:55 -!- KingOfKarlsruhe has quit (Read error: Connection timed out).
19:31:32 <nortti> isn't qbasic actually a subset, not a derivative?
19:32:22 <fizzie> It's different. I'd guesstimate there's some inconsequential QBasic thing that does not exist as-is in QuickBASIC.
19:33:08 <fizzie> In fact, I have a vague feeling I knew of such a feature.
19:34:01 <fizzie> Perhaps some difference in the behaviour of CALL ABSOLUTE.
19:34:09 <olsner> I mostly remember that qbasic was crap compared to quickbasic
19:34:24 <fizzie> It's lacking the compiler and the linker, for one thing.
19:35:57 <fizzie> Based on some alt.lang.basic posts, I get the impression that QuickBASIC 5 adds a library called "QB" containing "some QBASIC functions/statements that are not part of QB4.5".
19:36:14 <fizzie> QuickBASIC 4.5 being the version QBasic was derived from.
19:37:52 <fizzie> QuickBASIC, of course, has better ways to do the kind of things that you'd resort to CALL ABSOLUTE in QBasic for.
19:38:21 <nortti> I forget, what did call absolute do? call dos funcs?
19:38:40 <fizzie> "Transfers control to a machine-language procedure."
19:38:43 <fizzie> http://gamma.zem.fi/~fis/qbc.html#QEw4MDhh
19:39:13 <fizzie> The example given there (DATA + loop with a POKE + CALL ABSOLUTE) is very typical.
19:40:07 <olsner> %, is that the suffix for integer variables?
19:40:58 <fizzie> % for integer, & for long, $ for string, ! and # for single- and double-precision floats.
19:41:39 <fizzie> It's a bit of a shame that there was something in the QuickBASIC 4.5 manuals that my conversion script (that generated the qbc.html) choked on. (They use mostly the same file format.)
19:41:49 <olsner> it's nice how "print screen" is a three byte sequence of assembly, I doubt you can do that in three bytes today
19:44:46 <fizzie> Also I think the sigils are optional in QBasic, in the sense that you can "DIM x AS type-keyword" to get an undecorated variable name.
19:46:17 <fizzie> It's got user-defined types, too. (And optional line numbers.)
19:46:57 <kmc> where does CALL ABSOLUTE put the "arguments"
19:48:10 <kmc> probably the C calling convention
19:48:12 <fizzie> On the stack, I believe.
19:48:24 <kmc> i'm glad that now I know how to write a JIT compiler in QBasic
19:48:36 <fizzie> The "C calling convetion" is a rather flexible term for x86-16 DOS.
19:51:11 -!- mhi^ has joined.
19:52:06 <kmc> well, let's say the Microsoft one ;)
19:52:16 <kmc> "not so much a convention as a suggestion"
19:52:32 <fizzie> There was a nice overview somewhere, but I can never re-find it when I want.
19:56:43 <fizzie> Also some random ASM-in-QBasic tutorial suggests a callee-cleans-the-stack ("Pascal") convention.
19:57:25 <fizzie> Or at least has a "retf 6" in an example called as Call Absolute (BYVAL x%, BYVAL y%, BYVAL color%, SADD(program$))
19:59:56 <fizzie> http://support.microsoft.com/kb/51501/EN "DECLARE FUNCTION <name> [ALIAS "aliasname"][CDECL][<parameter-list>] -- Basic's calling convention pushes parameters onto the stack in the order in which they appear in the source code. -- This convention also specifies that the stack is restored by the called routine just before returning control to the caller."
20:00:43 <fizzie> Apparently in real QuickBasic you can do either, while QBasic CALL ABSOLUTE only does the one.
20:01:29 <fizzie> Though it's not like you could link in any C libraries either.
20:04:08 <kmc> sadd program
20:04:23 <kmc> why can't you link C libraries with QuickBasic?
20:05:15 <olsner> it's in qbasic you can't, because it doesn't have the compiler and linker
20:05:51 <fizzie> (The SADD keyword is QuickBasic-only, also.)
20:06:26 <kmc> what's it do?
20:06:36 <fizzie> Speaking of sad acronyms, here's one from the recent conference.
20:06:46 <fizzie> "Augmenting the standard DNN input with the bottleneck feature from a Speaker Aware Deep Neural Network (SADNN) shows a general advantage over the standard DNN based recognition system, --"
20:07:08 -!- Sprocklem has joined.
20:07:58 <kmc> olsner: you could probably write your own dynamic loader without too much trouble
20:08:12 <fizzie> SADD has something to do with the offset of a variable (in terms of VARSEG), but I'm not sure how it's different from VARPTR.
20:08:57 <kmc> also the doc example looks at VARSEG but doesn't use it?
20:08:57 -!- tertu has joined.
20:09:14 <fizzie> The DEF SEG is "using it".
20:09:54 <fizzie> "DEF SEG [=address] -- Sets the current segment address. -- A segment address used by BLOAD, BSAVE, CALL ABSOLUTE, PEEK, or POKE; --"
20:10:19 <Bike> golly, this takes me back. qbasic was the first language i pretended to learn
20:10:38 <kmc> yay for global variables
20:10:58 <olsner> it probably goes and sets es directly
20:11:11 -!- conehead has quit (Quit: Computer has gone to sleep).
20:12:13 <fizzie> (GW-BASIC was probably my first language. Either that or some quirky DOS Prolog implementation, I forget the order.)
20:13:13 -!- tertu has quit (Ping timeout: 252 seconds).
20:13:19 <olsner> I started out in quickbasic 4.5, I remember the compiler was great at making bikes and other silly patterns appear on the screen faster
20:14:28 * impomatic still uses FreeBASIC occasionally.
20:14:55 <fizzie> Making Bikes appear faster.
20:19:28 <fizzie> I used a little bit of TI-BASIC, which was great at making silly patterns appear on the screen slower.
20:21:52 <olsner> Bike: you were quite slow to appear now, would you mind compiling yourself?
20:22:20 <Bike> trying to learn grafix later was confusing, i was like "whoa i can't toggle pixels??"
20:24:00 <pdxleif> I wrote the UI for a chess program in TI-BASIC
20:28:03 -!- MoALTz has quit (Quit: bbl).
20:30:00 <HackEgo> [wiki] [[@text]] http://esolangs.org/w/index.php?diff=39529&oldid=39527 * Tailcalled * (+29)
20:32:20 -!- nucular has quit (Quit: Excess Food).
20:35:35 <myname> pretty crappy language imo
20:36:14 <myname> also: is there any other twodimensional language besides rail that has functions?
20:42:50 <kmc> doesn't befunge sort of have them?
20:43:29 <fowl> a function is just a route you put the IP on
20:43:58 <fowl> SNUSP has them
20:55:14 <fizzie> Funge-98 with SUBR has them.
20:55:56 <fizzie> Also some ad-hoc "Befunge with functions" things.
20:56:40 <fizzie> Oh, and Funciton possibly counts as two-dimensional too, and has functions.
20:58:06 <myname> funciton looks awesome
20:59:25 <fizzie> fungot has a couple of "functions" in the "code flow comes in from multiple sources, and returns based on an integer index pushed before the 'call'" sense.
20:59:25 <fungot> fizzie: games due out november i think
21:01:17 <fizzie> Like, the rightmost columns on lines 225-227, 231-236 and 258-263 of https://github.com/fis/fungot/blob/master/fungot.b98 test for a "return address" of 0/1/2.
21:01:17 <fungot> fizzie: there was more than 100 people on board, three indeed died. keep in mind that this was a low speed as he does have an incredible singing talent!
21:02:00 <fizzie> From the "parse this program" routine, as called by ^bf, ^ul and ^def.
21:02:32 -!- Patashu has joined.
21:11:53 <fizzie> ^def tmp bf ,[.,]!what did
21:12:11 <fizzie> Just ignored, I guess.
21:12:19 -!- drdanmaku has quit (Ping timeout: 240 seconds).
21:12:59 -!- ggherdov_ has quit (Ping timeout: 252 seconds).
21:21:24 -!- hk3380 has quit (Ping timeout: 258 seconds).
21:22:55 <kmc> he who makes a fungot of himself gets rid of the pain of being a man
21:22:55 <fungot> kmc: nonono... so i guess
21:23:34 <olsner> is it pretty painless to be a fungot?
21:23:34 <fungot> olsner: that was so funny!
21:24:04 -!- drdanmaku has joined.
21:25:31 -!- Patashu has quit (Ping timeout: 265 seconds).
21:27:29 -!- Sprocklem has quit (Ping timeout: 240 seconds).
21:30:35 -!- aloril has quit (Ping timeout: 252 seconds).
21:41:05 -!- oerjan has joined.
21:41:13 -!- sebbu2 has changed nick to sebbu.
21:41:17 -!- ggherdov_ has joined.
21:43:23 -!- aloril has joined.
21:49:59 <oerjan> it's always amusing whenever pine opens my inbox with "0 messages"
21:50:26 <oerjan> (there was a server upgrade. the file is actually there, but pine doesn't find it for some reason.)
21:51:20 -!- ggherdov_ has quit (Changing host).
21:51:20 -!- ggherdov_ has joined.
21:51:20 -!- ggherdov_ has quit (Changing host).
21:51:20 -!- ggherdov_ has joined.
21:51:54 -!- ggherdov_ has changed nick to ggherdov.
21:52:02 -!- shikhout has joined.
21:54:54 -!- shikhin has quit (Ping timeout: 240 seconds).
21:55:27 -!- boily has joined.
21:56:07 <boily> being on a bike causes front winds.
21:57:39 -!- metasepia has joined.
21:57:45 <metasepia> CYUL 152100Z 15022G34KT 15SM FEW080 BKN220 27/17 A2990 RMK ACC1CI6 SLP125 DENSITY ALT 1500FT
21:58:08 -!- hk3380 has joined.
22:00:07 -!- metasepia has quit (Remote host closed the connection).
22:00:09 -!- boily has left ("Poulet!").
22:00:24 -!- Ghoul_ has joined.
22:00:30 -!- boily has joined.
22:01:44 <Bike> https://d262ilb51hltx0.cloudfront.net/max/803/1*uJH6MbrCqIW-kgh1liY4ZQ.jpeg
22:11:19 -!- nooodl_ has joined.
22:12:03 <int-e> "Materiel", are they trying to appeal to a military audience?
22:12:31 <Bike> this is a DoD diagram. so, uh, yes.
22:12:43 <boily> what is materiel in a military context?
22:13:26 <Bike> militaries use the term in english as distinct from "material".
22:13:38 <int-e> https://en.wikipedia.org/wiki/Materiel may help
22:13:44 <Bike> because, who knows, we didn't use enough loanwords from french.
22:13:59 <boily> vive le français! :D
22:14:45 <Bike> "how could we make 'lieutenant' even harder to spell"
22:14:51 <int-e> (From Old French impossible, from Latin impossibilis [...])
22:15:05 -!- nooodl has quit (Ping timeout: 240 seconds).
22:15:51 <int-e> Bike: add an accent or two, perhaps?
22:15:52 <boily> fr:lieu → en:place; fr:tenant → en:holding.
22:16:28 <int-e> so it's a position.
22:16:43 <boily> the one who holds the position.
22:16:56 <Bike> military rank used to be tied to economic status. lieutenants were landholders.
22:17:04 <Bike> "used to be" insert cynicism here
22:18:09 <int-e> <cynicism> the military is a firm believer in equal opportunities, certainly </cynicism>
22:18:46 <oerjan> i vaguely recall not doing that was one of the reasons the prussian army was so powerful.
22:19:03 <lambdabot> "moltke! moltke! moltke! moltke! moltke! moltke! moltke! moltke! moltke! mol...
22:19:15 -!- metasepia has joined.
22:19:31 <oerjan> now that _is_ shocking
22:19:48 <int-e> oerjan: relatedly the prussian public school system was introduced for producing better recruits
22:19:48 <boily> ~duck helmuth von moltke
22:19:56 <boily> AAAAAAAAAAAAAAAAAAAAAAAARGH!
22:19:57 <oerjan> https://en.wikipedia.org/wiki/Helmuth_von_Moltke_the_Elder
22:20:14 <oerjan> metasepia: you are disappointing us
22:20:19 <metasepia> A center of population, commerce, and culture; a town of significant size and importance.
22:20:41 * boily therapeutically *MAPOLES* his bot
22:21:21 <metasepia> bike definition: '''chiefly Scottish''' a nest of wild bees, wasps, or hornets.
22:21:34 <Bike> yeah i remember that one
22:21:44 <int-e> I've not seen it before
22:22:29 <boily> well. at least my bot has a sane definition for “int”, so all is not lost!
22:22:41 <int-e> oh. that's the rpg definition
22:22:47 <metasepia> dex definition: the sulfate of dextroamphetamine.
22:22:52 <metasepia> wis definition: '''archaic''' know.
22:23:03 <oerjan> not very consistent here
22:23:09 <metasepia> Tea; - the Chinese name, used generally in early works of travel, and now for a kind of rolled tea used in Central Asia.
22:23:33 <metasepia> con definition: to commit to memory.
22:23:33 <boily> I see the mapoling was effective ^^
22:23:56 * boily pats his bot. “good bot. continue to be fungottian.”
22:23:56 <fungot> boily: what the hell out when i saw the fists does that have to say more unique and sexy about her, i'm a big rc jet no pilots aboard, it doens't mean it now suddenly becomes true.
22:23:58 <metasepia> A member of a traditionally nomadic hunting people of southwest Africa.
22:23:59 <int-e> I wonder what a "con man" is then.
22:24:14 <metasepia> man definition: an individual human; '''especially'''.
22:24:20 <metasepia> duck definition: any of various swimming birds (family Anatidae, the duck family) in which the neck and legs are short, the feet typically webbed, the bill often broad and flat, and the sexes usually different from each other in plumage.
22:24:31 <boily> so, a man is one metric human.
22:24:32 <int-e> "not a material component"
22:25:03 <int-e> (one of the few IWC strips that I remember)
22:25:30 -!- Phantom_Hoover has joined.
22:25:59 -!- Sgeo has joined.
22:26:47 <int-e> (link: http://www.irregularwebcomic.net/435.html )
22:29:00 <metasepia> nsa definition: National Security Agency.
22:29:58 <Bike> some weak ass shit here
22:30:15 <boily> holy. fungot. of. doom.
22:30:15 <fungot> boily: well it's about time it was
22:30:34 <oerjan> oh no boily what have you summoned
22:30:57 <Sgeo> http://wow.zamimg.com/images/hearthstone/cards/enus/animated/GAME_005_premium.gif
22:30:58 <lambdabot> "\"\\\"\\\\\\\"\\\\\\\\\\\\\\\"\\\\\\\\\\"
22:31:01 <Sgeo> I love this art
22:31:03 <int-e> why would ~duck answer in tabs?
22:31:13 <HackEgo> /home/hackbot/hackbot.hg/multibot_cmds/lib/limits: line 5: exec: fix: not found
22:31:17 <lambdabot> "\"\\\"\\\\\\\"\\\\\\\\\\\\\\\"\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\"\\\\\\\\\\\\\...
22:32:50 <boily> int-e: the query was “>> :int-e!~noone@static.88-198-179-137.clients.your-server.de PRIVMSG #esoteric :~duck hth”, and the answer was “<< PRIVMSG #esoteric : \r\n”.
22:33:30 <int-e> boily: the reply contained two tab characters, which got lost in your cut&paste.
22:34:20 <boily> I don't keep tab on tabs.
22:34:22 <int-e> (well, not lost, but expanded, is my guess)
22:42:33 <lambdabot> lexical error in string/character literal at character '\ETX'
22:43:19 -!- nooodl_ has changed nick to nooodl.
22:43:57 <boily> fungot: what are nine-eyes?
22:43:57 <fungot> boily: what is his vocal range. another youtube famous counter tenor. it is completely electrical. the first time i've seen too many cocks in his grave. what the fuck
22:44:28 <boily> Bike: stop making auditive eyes, you are disturbing fungot.
22:44:28 <fungot> boily: oh goddd. xd he has really bad diction the
22:45:17 -!- Burton has joined.
22:58:38 -!- Sprocklem has joined.
23:23:54 -!- boily has quit (Ping timeout: 240 seconds).
23:24:20 -!- metasepia has quit (Ping timeout: 252 seconds).
23:33:36 -!- boily has joined.
23:35:57 <boily> I think my modem is overheating...
23:48:06 <boily> oh. let me remetasepify the channel!
23:48:25 -!- metasepia has joined.
23:48:29 <metasepia> KATL 152252Z 31014G22KT 10SM SCT040 16/08 A2999 RMK AO2 SLP152 T01610083
23:49:22 <boily> strange. very strange.
23:49:27 <metasepia> CYUL 152300Z 15023G32KT 15SM FEW080 BKN200 26/17 A2991 RMK AC1CI7 AC TR SLP130 DENSITY ALT 1300FT
23:49:42 <boily> ten degrees hotter here than in Atlanta. indeed strange.
23:50:23 -!- Phantom_Hoover has quit (Quit: Leaving).
23:51:24 <quintopia> but it didn't rain most of the day
23:56:05 <boily> it was windy as fungot when I cycled home.
23:56:22 <boily> I could, but only if you have a Canadian passport ^^
23:58:26 <boily> tonight's ride: https://goo.gl/maps/zYcZN
23:59:12 <boily> (customized by foot, because Google is [REDACTED] stupid when it comes to bike paths.)
00:00:29 -!- yorick has quit (Remote host closed the connection).
00:00:58 -!- mhi^ has quit (Quit: Lost terminal).
00:12:20 <kmc> 12.2.5.4.21 The "after frameset" insertion mode
00:12:20 <kmc> 12.2.5.4.23 The "after after frameset" insertion mode
00:15:19 <Bike> i assume 12.2.5.4.22 is before after after frameset.
00:18:12 <boily> quintopia: you don't need a visa. I tried the online «permis de travail» form, and apparently «Selon vos réponses, il semble que vous ne puissiez pas immigrer au Canada à l'heure actuelle dans le cadre d'un programme fédéral.»
00:18:25 <boily> (based upon very guesstimaty answers to the form)
00:19:06 <boily> kmc: what kind of frameset are you looking at technical documentation of exactly?
00:25:00 <ion> http://heh.fi/tmp/hacker_evolution_steam_sale_20140516.png http://store.steampowered.com/sub/17602/
00:25:16 <boily> quintopia: “According to you answers, it seems that you can't immigrate to Canada today with respect to a federal programme.”
00:26:00 <quintopia> in others words.. it just can't happen
00:27:05 <boily> as I said, very, very random answers. the only one I am certain of is that you're America.
00:27:22 <boily> (dammit. can't type tonight.)
00:28:09 <kmc> boily: http://www.whatwg.org/specs/web-apps/current-work/multipage/tree-construction.html#parsing-main-afterframeset
00:29:10 <boily> c'est aussie facile pour eux!
00:29:32 <boily> (yes. I hate myself. sorry for that very stupid pun.)
00:30:01 <quintopia> i know an aussie who got a work visa and a canadian job
00:30:11 <boily> kmc: uuuuuuurgh...
00:30:41 <boily> quintopia: maybe you need to multiclass? become an Australian/Canadian ranger?
00:31:44 <quintopia> no one with three races could have reasonable abilties
00:37:15 <boily> time to go Pratchett, and then blissfully fall into a deserved coma.
00:37:22 -!- boily has quit (Quit: PNEUMATIC CHICKEN).
00:37:24 -!- metasepia has quit (Remote host closed the connection).
00:53:33 <kmc> goddamn borrowchecker why can't you be a little smarter
00:56:39 <HackEgo> [wiki] [[Owhelgossip]] N http://esolangs.org/w/index.php?oldid=39530 * 69.118.178.143 * (+548) Created page with "== OwhelGossip == ::OwhelGossip also Owhel or maybe OwhelG. O OwhelGossip is best explained in a poem, ''The owl gossiped to the bat,'' ''The bat gossiped to bird1,'' ''Bird1..."
00:58:14 <HackEgo> [wiki] [[Owhelgossip]] http://esolangs.org/w/index.php?diff=39531&oldid=39530 * 69.118.178.143 * (-17) /* OwhelGossip */
00:58:56 <HackEgo> [wiki] [[Owhelgossip]] http://esolangs.org/w/index.php?diff=39532&oldid=39531 * 69.118.178.143 * (-1)
01:01:58 -!- Ghoul_ has quit.
01:03:01 <HackEgo> [wiki] [[Language list]] http://esolangs.org/w/index.php?diff=39533&oldid=39487 * 69.118.178.143 * (+18) /* O */
01:04:05 -!- nooodl has quit (Quit: Ik ga weg).
01:08:56 -!- hk3380 has quit (Ping timeout: 255 seconds).
01:09:07 -!- tromp has joined.
01:18:11 -!- Bike has quit (Ping timeout: 252 seconds).
01:19:58 -!- Bike has joined.
01:55:42 -!- Daniel3920 has joined.
02:07:41 -!- hk3380 has joined.
02:08:07 -!- Daniel3920 has left.
02:17:55 -!- Sorella has quit (Quit: It is tiem!).
02:19:02 -!- Sorella has joined.
02:27:04 -!- tromp has quit (Remote host closed the connection).
02:27:18 -!- tromp has joined.
02:50:28 -!- oerjan has quit (Quit: leaving).
02:51:24 -!- drdanmaku has quit (Quit: Connection closed for inactivity).
02:54:59 <Bike> how is exploit formed
02:59:58 -!- Bike has quit (Ping timeout: 245 seconds).
03:00:02 -!- Bike_ has joined.
03:07:37 <fowl> whaaat how have i never seen this before https://www.youtube.com/watch?v=oYSQKc6z_dY
03:07:47 -!- Bike_ has changed nick to Bike.
03:08:08 -!- Sorella has quit (Quit: It is tiem!).
03:19:41 -!- fowl has quit (Remote host closed the connection).
03:23:55 -!- fowl has joined.
03:26:43 -!- hk3380 has quit (Ping timeout: 258 seconds).
03:28:44 -!- tromp has quit (Remote host closed the connection).
03:29:18 -!- tromp has joined.
03:33:29 -!- tromp has quit (Ping timeout: 240 seconds).
03:49:50 -!- zzo38 has joined.
03:55:29 -!- shikhout has quit (Ping timeout: 240 seconds).
04:03:21 -!- ^v has quit (Read error: Connection reset by peer).
04:04:20 <Sgeo> What Magic the Gathering cards have use only in combinations or as a mind game to make opponent think you have such a combination?
04:04:32 <Sgeo> Ancient Watcher is such a card in Hearthstone: http://www.hearthpwn.com/cards/153-ancient-watcher
04:05:07 -!- ^v has joined.
04:06:16 <zzo38> I have partially made up some new kind of programming language by writing it on a paper. One example code can be: [z/a,b] cut ([x] z (left x) (right x)) ([x] split x ([y] init y b) ([y] init a y)) Let's see if you know this one.
04:06:23 <lambdabot> Melvar said 4d 17h 48m 50s ago: I also made it strip its nick off the front of a line independently of any other interpretation.
04:08:11 <zzo38> Can you figure out what this program does?
04:08:28 <Bike> it prints "hello world" to standard output
04:08:48 <Bike> I just ran it and that's what it does.
04:09:03 <zzo38> (In fact, it is not a complete program; that is what the [z/ at the front means.)
04:09:16 <kmc> Bike: what if it's undefined behavior
04:09:36 <Bike> zzo doesn't seem like the type to leave things underdefined
04:10:17 -!- shikhin has joined.
04:10:49 <Bike> or undefined at all, really.
04:11:11 <kmc> does Black-C have UB?
04:11:15 <Sgeo> https://www.youtube.com/watch?v=Dk0bgynFA1Y
04:11:57 <zzo38> kmc: Many of the same things as C are still UB (although not quite all)
04:12:28 <kmc> makes sense
04:12:32 <kmc> which ones changed?
04:12:44 <Bike> zero length arrays,
04:13:16 <zzo38> Sign conversion is one
04:21:54 <zzo38> I can give a hint relating to this programming language, which is: There aren't any first-class functions, although it does have first-class continuations.
04:22:14 <zzo38> Also, there is no syntax for continuations because it is implicit.
04:24:15 <fowl> guess what this program does <:@#:#$@<<@>$@@
04:24:32 <fowl> its a language i made up and there is no information available on it, but guess what it does
04:25:09 <zzo38> Is it copying input to output, or reversing the input, or something like that?
04:25:14 <zzo38> Do you have a hint?
04:25:24 <fowl> it does nothing because < is a comment
04:25:45 <zzo38> How does the comment finished?
04:26:01 <fowl> the language does nothing too
04:32:27 * pikhq writes an implementation:
04:36:00 -!- conehead has joined.
04:36:22 <zzo38> I can tell you what mine is meaning too. If you have two types called X and Y, and a program that would receive a continuation accepting a Y and returns a continuation accepting a X, then this program will receive X and result in Y.
04:38:05 <zzo38> pikhq: What programming language is the implementation?
04:39:26 <zzo38> O, I don't know programming with Lex so well
04:46:48 <zzo38> Why do many computer pinball games activate tilt if you bump the table too often, and some do it differently (such as not activating tilt at all (as in Pokemon Pinball), or if you hold down the bump button for too long (as in Microsoft Space Cadet Pinball))?
04:47:17 <zzo38> Is it possible to make number theory out of linear logic?
04:48:26 <fowl> zzo38, in actual pinball machines the tilt sensor is a weight that connects when you shake the machine
04:49:09 <zzo38> It is to avoid bumping it too hard, not too often.
04:49:36 <Bike> are these questions related
04:49:44 <zzo38> No they are two different questions
04:50:13 <fowl> zzo38, the diff is probably that in a computer pinball game you're playing with keys which are 1 or 0, opposed to moving a machine which you would have a lot of control over how much you shake it
04:50:43 <zzo38> (Well, if you use Wii remotes or whatever, then you could control how much)
04:50:47 <fowl> so.. you cant hit the bump key hard or soft
04:51:50 <zzo38> But if using the keyboard, even then activating tilt simply if you bump the table too often doesn't seems works; you could decrease the strength of it in the program, or do how Microsoft did and make it harder if you hold down the keys too long
04:52:28 <fowl> i dunno, i think hitting a key multiple times is similar to shaking the machine hard as opposed to softly
04:52:46 <fowl> microsofts way makes sense too
04:53:09 <zzo38> Maybe, although the implementation doesn't generally actually make it harder when pushing the key many times in succession
04:53:35 <fowl> no but you're still trying to map digital inputs to analog behavior
04:54:05 <fowl> so its not gonna be prefect
04:55:07 <Bike> microsoft pinball is otherwise very rigorous.
04:56:07 <zzo38> I still don't like the most common way (pushing the key many times in succession), mainly because I like to bump the table a lot
04:57:19 <zzo38> So when playing Microsoft's implementation, I push the keys as if it is on fire (an analogy I read in a book about mechanical typewriters)
05:06:54 <fizzie> Do pinball games on mobile devices use the accelerometer for tilt detection?
05:37:16 -!- ehayes has joined.
05:41:18 <Sgeo> I'm glad you figured out I'm currently obsessed with Heartstone, Google. But does it really make sense to advertise to me a game I'm already playing?
05:41:31 <Sgeo> I guess it can't really determine that I am playing, and not just vaguely interested
05:44:35 <fowl> <Bob Dole> smoke
05:52:08 <ehayes> open this with the tor browsing bundle https://uhduwxhlcqxbfq5k.onion
05:52:55 <ehayes> elliott: a copyrighted ebook currently not available on the public internet
05:53:13 <Bike> always a good thing to post unprompted
05:53:56 <elliott> hmm, tor2web.org seems to be even slower than actual Tor.
05:54:39 <ehayes> tor2web didn't resolve it (or any other .onion sites I've tried) for me
05:54:50 <ehayes> I don't think it's maintained anymore
05:55:05 <elliott> Bike: what is it actually?
05:56:19 <Bike> hell if i know
05:57:16 * elliott sighs. this is just a ploy to get me to install Tor.
05:57:46 <Bike> i mean i don't have tor, i'm just going off of "a copyrighted ebook".
05:57:51 <ehayes> make sure to disable javascript before you visit it
05:58:20 <elliott> the tor bundle ships with javascript enabled...?
05:58:29 <elliott> regardless, that's not the most reassuring thing you've said...
05:58:38 <Bike> wow i'm really excited to view this mystery site
05:58:39 <ehayes> yes, one of the stranger things they've done recently
05:59:11 <Bike> could you just tell us what it is rather than posting shady links with no context or prompting
06:00:36 <zzo38> Do you need a Tor browsing bundle, or can you add Tor into the TCP/IP driver and DNS driver?
06:00:43 <elliott> haha, nice, I get a self-signed certificate warning
06:00:58 -!- conehead has quit (Quit: Computer has gone to sleep).
06:01:27 <ehayes> zzo38: tor is a daemon running on top of TCP/IP
06:01:36 <elliott> fyi, if this isn't to do with esolangs I'm going to ban you for putting me through this fuss.
06:01:44 <Bike> so what is it, jesus christ
06:01:58 <elliott> Fizz - Nothing is as it seems
06:01:59 <elliott> A novel centered around the history of physics. It tells the story of a young woman from the future named Fizz, who time travels to meet physicists such as Aristotle, Galileo, Newton and Einstein, and discuss their work.
06:02:03 <Bike> i bet it's dog porn, that oughta be a ban
06:02:05 <zzo38> ehayes: Then why do you need a Tor browsing bundle too?
06:02:10 <Bike> yeah that sounds like dog porn
06:02:23 <ehayes> zzo38: tor bundled a browser to aid users get online more easily
06:02:36 <elliott> you'd better have a really good explanation for this, ehayes.
06:02:40 <ehayes> zzo38: it isn't mandatory, but it is convenient
06:03:59 <elliott> like, how many channels have you linked this in? do you realise it's against freenode guidelines? admittedly, I am only tempted to whine to #freenode because it was such a disappointment.
06:04:48 <ehayes> elliott: just #esoteric and #tor
06:04:56 <ehayes> because it is tor related, and esoteric
06:04:57 <zzo38> Yes, it is helpful if you are trying to access webpages on Tor even though you do not already have a web browser program, I suppose, but howelse?
06:05:20 <zzo38> I prefer a printed book anyways
06:05:23 <shachaf> The topic of this channel is esoteric programming languages.
06:05:25 <elliott> what on earth is esoteric about a warez site with exactly one random crappy scifi ebook
06:05:51 <Bike> it's tor related in much the same way it is internet related, so go bother ICANN
06:05:59 <ehayes> elliott: the fact that there is only one makes it highly suspect
06:06:16 <Bike> yes. we are highly suspecting you.
06:06:25 <Bike> don't do this to people.
06:06:49 <elliott> it's more entertaining than 99% of this channel
06:06:55 <elliott> did you know it's called the Ducknet
06:07:37 <zzo38> I know you can make up a intiutionistic logic and a classical logic using linear logic, but what other logic can you make out of a linear logic? Can it include a numerical logic?
06:07:38 -!- shikhin has quit (Ping timeout: 240 seconds).
06:07:45 <mroman_> I think @text implementation is actually broken?
06:07:58 <mroman_> there are square brackets around @
06:08:08 <fowl> ehayes, i have a copy of a better boot - "creation: life and how to make it" by steve grand (creatures franchise)
06:08:13 <fowl> ehayes, want it?
06:08:25 <elliott> you should upload it to Ducknet Hosting
06:08:28 <ehayes> fowl: no, but I will investigate the server hosting it
06:08:33 <elliott> Looking for a reliable, secure, and discreet host for your stolen content? Well look no further. Here be Ducknet Hosting, the followup to Not Ducknet Hosting
06:09:05 <fowl> ehayes, it would be my dropbox, i searched for this book for weeks then ended up meeting someone who scanned their copy
06:09:06 <Bike> not seeing the duck connection (ducknection)
06:09:10 <elliott> so is this like some incredibly cryptic way for you to say you suspect this site of having more to it than is obvious, without actually saying that for whatever reason, or giving anything more than that
06:09:30 <impomatic> Open this link http://goo.gl/8Yma7Q
06:09:34 <elliott> do I have to download the epub to view the mysteries.
06:09:43 <ehayes> fowl: no, and no offense intended in that
06:10:05 <ehayes> impomatic: what is it?
06:10:14 <Bike> what indeed could it be
06:10:19 <zzo38> shachaf: I mean such numerical logics as Typographical Number Theory and so on
06:11:17 <Bike> fowl: also, if you already have a copy up i'll take one
06:13:03 <impomatic> I have a paper copy of the Steve Grand book :-) Also a few others. The best overview is probably in Artificial Life by Steven Levy.
06:13:26 <ehayes> I'm looking at your link "In May 1984 A K Dewdney introduced Core War, a game played between two or more computer programs in the memory of a virtual computer. The aim of the game is to disable all opponents and survive the longest. A variety of strategies have evolved for Core War, each with their own strengths and weaknesses."
06:17:13 <fowl> Bike, https://www.dropbox.com/s/r24qbb0b6601dri/Creation%20Life%20and%20How%20to%20Make%20it.pdf
06:17:19 <impomatic> ehayes: Oh, someone clicked! Lucky for you I didn't link something like this http://goo.gl/6SDxwv
06:17:37 <ehayes> and what is that, impomatic?
06:17:40 <fowl> i will click on anything
06:17:47 <fowl> i grew up on this internet shit, bring it on
06:17:48 <Bike> much obliged. this will go well with my three hundred dollar orgo textbook
06:17:50 <ehayes> fowl: that is my weakness, yes
06:18:09 <fowl> Bike, whats orgo
06:18:19 <Bike> organic chemistry.
06:18:19 -!- mtve has quit (Quit: Terminated with extreme prejudice - dircproxy 1.2.0).
06:18:29 -!- aloril has quit (Ping timeout: 252 seconds).
06:20:13 <Bike> life, organic, it's a joke, see.
06:20:39 <Bike> damn right, fucker.
06:22:57 -!- FreeFull has quit.
06:24:13 -!- shikhin has joined.
06:28:35 -!- Bike has quit (Ping timeout: 276 seconds).
06:29:09 <zzo38> Programming language I partially made up is based on a LK sequent calculus; the commands correspond to the rules it has, each rule then has an effect defined for its meaning. The impliciation rules are omitted, and the negation rules and structural rules are made implicit.
06:29:28 <zzo38> Possibly, therefore allow you to understand this program I wrote
06:32:17 -!- aloril has joined.
06:35:09 -!- ^v has quit (Quit: http://i.imgur.com/Akc6r.gif).
06:36:56 -!- mhi^ has joined.
06:53:53 <Sgeo> "I'm going to go through and "friend" everybody who isn't on their own friends list"
06:54:10 <Sgeo> [quip about failing Introduction to Set Theory redacted]
06:54:33 <Sgeo> But what she described should work... she's not automatically unfriending people who later become on their own friends list
06:54:47 <Sgeo> So she's not on her own friend list, she friends herself, tada
07:00:48 -!- Frooxius has quit (Ping timeout: 245 seconds).
07:04:44 -!- Frooxius has joined.
07:04:56 -!- Frooxius has quit (Read error: Connection reset by peer).
07:10:26 -!- KingOfKarlsruhe has joined.
07:11:33 -!- Frooxius has joined.
07:26:15 -!- slereah has joined.
07:29:32 -!- stuntaneous has quit.
07:46:26 -!- ehayes has quit (Ping timeout: 272 seconds).
08:15:22 -!- MindlessDrone has joined.
08:23:48 -!- Patashu has joined.
08:31:19 <Taneb> Is it possible to express SK combinator calculus as a cellular automaton in a weird dimension?
08:31:38 <slereah> Well both are TC so I guess?
08:31:55 -!- KingOfKarlsruhe has quit (Quit: Leaving.).
08:31:59 <Taneb> I mean phrasing SK as a CA
08:32:24 -!- Patashu has quit (Disconnected by services).
08:32:24 -!- Patashu_ has joined.
08:32:31 <slereah> Because SK combinators can grow in size
08:32:47 <slereah> You can fill the tape to the left with ` and to the right with i, it will be fine
08:32:55 <slereah> But how do you grow the middle part
08:33:39 <slereah> I guess maybe you could use intermediary combinators?
08:33:46 <Taneb> In a really weird dimension, I was thinking a dimension shaped like a binary tree
08:34:04 <slereah> Well you can express combinators as trees, yes
08:34:05 <Taneb> Although by that point it's not really a cellular automaton
08:35:25 <Taneb> So I guess my question is meaningless?
08:37:22 <slereah> http://cp4space.files.wordpress.com/2013/01/ski-calculus.png
08:37:59 <Taneb> That's basically what I was thinking of
09:03:18 -!- KingOfKarlsruhe has joined.
09:03:18 -!- KingOfKarlsruhe has quit (Client Quit).
09:05:49 <HackEgo> /home/hackbot/hackbot.hg/multibot_cmds/lib/limits: line 5: exec: `S``CB`WI``CB`WI: not found
09:06:14 <Taneb> Using my great knowledge of combinators, that's the shortest fixed point operator I can think of
09:06:45 <slereah> What about the Turing combinator
09:07:44 <Taneb> C and B and W aren't in themselves fixed point operators.
09:08:21 <slereah> Then why not use the constituant combinators of the Turing combinator
09:08:25 <slereah> (λx. λy. (y (x x y))) (λx. λy. (y (x x y)))
09:08:37 <slereah> Just use (λx. λy. (y (x x y)))
09:08:43 <slereah> It is not fixed point by itself!
09:09:49 <Taneb> That is an option, yes
09:10:09 <Taneb> (and I'm avoiding combinators with lambdas on the RHS
09:11:14 <slereah> That's why you should use the best language
09:11:22 <slereah> http://esolangs.org/wiki/Lazy_Bird
09:12:33 <Taneb> That has combinators with lambdas on the RHS!
09:21:34 <fowl> lambda calculus
09:21:51 <fowl> is something that nerds made up, similar to quantum mechanics, to make themselves look smarter than normies
09:37:44 -!- mhi^ has quit (Quit: Lost terminal).
09:54:17 -!- ais523 has joined.
10:00:42 <Jafet> They aren't even subtle about it, some of them fabricate facts in "lie groups"
10:03:12 <fizzie> I just pivoted a 1920x1200 monitor, and it looks ridiculously tall, compared to what I've gotten used to.
10:03:38 <fizzie> (We moved to a different office, and while packing things up, noticed the monitor can pivot.)
10:04:10 <ais523> how many 80-character-wide text-files can be fit side by side on that?
10:04:16 <fizzie> 4:3 turned into 3:4 didn't feel this silly at all, but this 16:10 to 10:16 just feels weird.
10:04:33 <Taneb> http://i.imgur.com/rXpH5xd.jpg typed lambda calculus
10:04:50 <slereah> Taneb : Welcome to the 1950's
10:04:50 <fizzie> 170x143 (170 columns, 143 rows) seems to be the size of a terminal window.
10:06:59 -!- ais523 has quit.
10:07:03 -!- callforjudgement has joined.
10:10:30 * int-e wonders whether there would be a market for sqrt(2):1 screens
10:11:09 <int-e> A<any number>, yes
10:11:41 <fizzie> That's... somewhere between 4:3 and 3:2, I guess.
10:11:46 <int-e> actually no, I'm happy with having them scaled a bit, as long as the aspect ratio is sane.
10:12:25 <int-e> but A4 would be a small screen by today's standards
10:12:39 <int-e> perhaps ok for a tablet
10:12:40 <slereah> int-e : How do you get 0.41 pixels
10:12:56 -!- boily has joined.
10:13:21 <int-e> slereah: you can make the pixels slightly non-square. it worked for CGA ;-)
10:14:20 <int-e> but obviously? what I had in mind was a resolution like 2000x1414
10:15:15 <callforjudgement> my laptop is basically what you get if you wanted to make a netbook, except it had to be powerful enough to run Windows
10:15:30 -!- callforjudgement has quit.
10:15:36 -!- scarf has joined.
10:15:42 <scarf> [11:14] <callforjudgement> int-e: my laptop screen is smaller than A4
10:15:44 <scarf> [11:14] <callforjudgement> or, well
10:15:45 <scarf> [11:14] <callforjudgement> I call it a netbook sometimes
10:15:47 <scarf> [11:15] <callforjudgement> my laptop is basically what you get if you wanted to make a netbook, except it had to be powerful enough to run Windows
10:16:03 <fizzie> We saw that, actually.
10:16:55 <fizzie> Also, I think our (the research group) new "demo"/borrow-for-miscellaneous-purposes laptop is something reasonably small.
10:18:44 <fizzie> 13.3" diagonal, apparently.
10:18:52 <fizzie> A4 is something like 14.3.
10:19:22 <fizzie> > sqrt (210*210 + 297*297) / 25.4
10:19:26 <HackEgo> [wiki] [[Talk:Owhelgossip]] N http://esolangs.org/w/index.php?oldid=39534 * GreyKnight * (+377) Created page with "== help == I read the explanatory poem but still can't understand the program. Both the poem and the program seem to have the same initial and final term, so I surmise that w..."
10:19:34 <Taneb> Turns out I had the ribbon in my typewriter wrong all this time
10:20:02 <fizzie> (It's this Lenovo Yoga 2 Pro thing.)
10:21:28 <fizzie> 3200x1800 screen, which for some reason or another is called "QHD+". The display resolution abbreviations are ridiculous.
10:23:52 <fizzie> Wikipedia says the "proper" name for 3200x1800 is "WQXGA+" instead.
10:25:51 <lambdabot> (1.4142857142857144,1.4142135623730951)
10:27:15 * boily exclaims “WHUXGA!” while doing wild kung fu moves
10:27:46 <Melvar> I would totally want a A4-size tablet, I think. For putting on my music stand so I don’t have to carry around binders.
10:28:45 <fungot> \o| c.c \o/ ಠ_ಠ \m/ \m/ \o_ c.c _o/ \m/ \m/ ಠ_ಠ \o/ c.c |o/
10:28:45 <myndzi> | c.c.c | ¯|¯⌠ `\o/´ | c.c.c | `\o/´ ¯|¯⌠ | c.c.c |
10:28:46 <myndzi> /< c.c /'\ /< | | /´\ c.c /'\ | >\|/'\ c.c /|
10:29:08 -!- scarf has quit.
10:29:14 -!- ais523 has joined.
10:30:41 <boily> Melvar: that thing is A4 → http://en.wikipedia.org/wiki/Cambridge_Z88
10:32:08 <int-e> well there's some hope: http://www.bbc.com/news/technology-26818112
10:33:52 <fizzie> HP has that 21.5" tablet.
10:34:17 <int-e> meh, why have people started to report crap like "it has 4GB of internal storage" without saying how much of that is RAM...
10:34:23 <fizzie> http://www8.hp.com/us/en/ads/slate-21/overview.html
10:34:50 <fizzie> I guess they call it "All-in-One Touchscreen Desktop" now, but I think I saw it referred to as a tablet somewhere.
10:35:51 <fizzie> That's the size of an A3, I guess.
10:36:11 <Melvar> int-e: That thing looks excellent for my purposes, but expensive.
10:36:52 <fizzie> I got the impression that lawyers and such were the target audience for the Sony thing.
10:38:54 <int-e> Melvar: The vague hope that I have now is that they will prove that there is a market for such devices and then attract competitors to the niche.
10:39:37 <ais523> I like the phrase "touchscreen desktop"
10:40:34 <fizzie> It sounds like what Microsoft Surface was before they reused the word for tablets.
10:40:52 <fizzie> (And renamed it PixelSense.)
10:41:00 <Melvar> int-e: Let’s hope together.
10:43:55 <int-e> (unfortunately, besides the common movie aspect ratio, another factor is that a 10" sqrt(2):1 display has the same surface area as a 10.5" 16:9 display.)
10:47:02 <int-e> Oh I haven't done the math for 16/9 to 16/10 before, that's a 2.5% gain: 10" vs. 10.256".
10:48:05 <int-e> Where the "gain" is a gain for marketing the product.
10:49:59 <int-e> > let d w = sqrt(1 + w^2) / sqrt(w) in (d (16/9) / d (16/10))
10:51:44 <int-e> Oh, sqrt(1/w + w) is a prettier formula for 'd'.
10:52:52 <fizzie> https://dl.dropboxusercontent.com/u/113389132/Misc/20140516-view.jpg <- new view
10:53:07 <fizzie> Perhaps I can take an even duller time-lapse video now that there won't even be cars going by.
10:55:40 <int-e> you can always hope for an alien exploration ship landing
11:01:34 -!- boily has quit (Quit: DISFLAGRATED CHICKEN).
11:03:02 -!- hk3380 has joined.
11:03:41 <int-e> tromp_: btw I committed the goodstein thing (optimized a bit) to the AIT repo
11:08:58 -!- ais523 has quit (Remote host closed the connection).
11:09:00 <int-e> Ah, fun. "The "Academy ratio" of 1.375:1 was used for all cinema films in the sound era until 1953 (with the release of George Stevens's Shane in 1.66:1). During that time, television, which had a similar aspect ratio of 1.33:1, became a perceived threat to movie studios."
11:09:10 -!- ais523 has joined.
11:11:40 -!- ais523 has quit (Client Quit).
11:15:56 <quintopia> what's that called again? silver ratio? it's the one where cutting it in half gives two parts similar to the original, right?
11:15:58 <int-e> https://en.wikipedia.org/wiki/Aspect_ratio_%28image%29 is quite informative
11:17:34 <int-e> apparently the "silver ratio" is sqrt(2)+1.
11:18:46 <quintopia> but think about what happens if you cut a unit square out
11:30:48 -!- yorick has joined.
12:00:09 -!- oerjan has joined.
12:03:53 -!- ais523_ has joined.
12:03:56 -!- ais523_ has quit (Changing host).
12:03:56 -!- ais523_ has joined.
12:03:56 -!- ais523_ has quit (Changing host).
12:03:56 -!- ais523_ has joined.
12:05:06 -!- Sgeo has quit (Read error: Connection reset by peer).
12:16:39 -!- tromp has joined.
12:17:46 -!- tromp has quit (Remote host closed the connection).
12:18:18 -!- tromp has joined.
12:21:13 <mroman_> 1 Mio. people in 12x real-time
12:22:37 -!- tromp has quit (Ping timeout: 258 seconds).
12:23:45 -!- shikhout has joined.
12:26:22 <mroman_> my crowd simulation bachelor thesis
12:27:05 -!- shikhin has quit (Ping timeout: 255 seconds).
12:28:13 <fizzie> Somehow that reminded me of http://research.ics.aalto.fi/cog/pracsim/
12:28:45 <fizzie> A friend was tangentially involved in that, but I never managed to really grasp what it was all about.
12:29:08 <fizzie> I don't have a Java plugin on this computer, but if it's what I think, it should be some... shapes...
12:35:59 <fungot> Selected style: lovecraft (H. P. Lovecraft's writings)
12:36:09 <oerjan> fungot: what do you know about... shapes...
12:36:10 <fungot> oerjan: whom it is not well to fnord of future great race minds by the moribund. modern and personal topics he waved aside quite summarily, whilst regarding antique affairs he soon shewed the plainest fnord. what this meant, no one can behold them as they passed ammi's they told him that this part of the colossal peaks that loomed up at a fnord on the
12:37:40 <fungot> fizzie: fnord in uncanny fnord and although he kept me awake, i was expected to go over his papers with some thoroughness; and for that purpose moved his entire set of files and boxes to my quarters in boston.
12:38:10 <fizzie> The entirety of that after the comma is probably a direct quote.
12:40:21 <oerjan> from the ancient unspeakable time of physical files
12:41:32 -!- Tritonio has joined.
12:44:28 <zzo38> The part after the comma seem like a proper sentence, so possibly it is.
12:47:21 <fizzie> fungot: You're such a FILE MANAGER.
12:47:21 <fungot> fizzie: " they were all very old. i do not know. two had been killed; perhaps that had finished it. but i may say, his calls on me) was the old-time indecisive one its irresponsible fnord even more marked than in the fnord stone walls press closer and closer, i shall not go there again, and he was likewise uncertain just when or how the guardian night-gaunts would suddenly pounce upon him.
12:47:50 <oerjan> zzo38: iirc linear logic is TC to check theorems, so in some sense you can embed any computation you want in it...
12:47:52 <fizzie> Those night-gaunts, they're always pouncing.
12:50:06 <zzo38> oerjan: Can you explain how?
12:51:02 <oerjan> no, i've never read the proof, but there is a claim that it's undecidable (which usually means TC) is at https://en.wikipedia.org/wiki/Linear_logic#Decidability.2Fcomplexity_of_entailment
12:52:01 <oerjan> i recall reading the proof that constructive logic is PSPACE-complete, though
12:52:44 <ais523_> intersection types are undecidable, in that you can find an intersection type for a term if and only if it always terminates
12:52:57 <ais523_> which is something like the easiest undecidability proof ever
12:53:16 <ais523_> most cut-down linear logics are decidable, though
12:53:27 <ais523_> actually my PhD thesis is about that, sort of
12:53:37 <ais523_> just last week I did a decidability proof for SCC
13:00:48 -!- Patashu_ has quit (Ping timeout: 245 seconds).
13:03:07 <ais523_> it's a type system with bounded contraction
13:03:23 <ais523_> so basically, the LHS of each arrow, and the free variables, have a "number of uses" annotation
13:03:35 <ais523_> a type would be something like (int^4->int)
13:03:44 <ais523_> and in order to do contraction, you have to add the numbers
13:03:59 <ais523_> "syntactic control of concurrency" if you want a search term
13:04:17 <ais523_> oh gah, UNIX time is at 1400 million already?
13:04:30 <ais523_> I remember when it was at 1234567890, and I was scared at what a big number it was already
13:05:15 <oerjan> so it's like a bounded version of ! in linear logic? which you can desugar into & and x i think.
13:07:20 <ais523_> oerjan: yeah, pretty much exactly that
13:07:30 <ais523_> in fact, that's "bounded linear logic" you're describing
13:07:41 <ais523_> SCC is similar to BLL, or rather, it's more a weird subset of it
13:07:51 <ais523_> because the products allow unlimited contraction of both sides, and nothing else does
13:08:15 <ais523_> I was chatting to a bunch of linear logicians about it, and they all said pretty much the same thing, "but the function arrow isn't the adjoint of the product"
13:08:30 <ais523_> and it turns out that that property makes it awkward to use in practice
13:08:46 <ais523_> anyway, this was the state of the art in the field before I entered it, now my thesis is talking about how it has problems and you can probably do better
13:09:01 <ais523_> and showing that it's decidable
13:09:20 -!- nucular has joined.
13:09:20 -!- nucular has quit (Changing host).
13:09:20 -!- nucular has joined.
13:09:20 -!- hk3380 has quit (Ping timeout: 252 seconds).
13:15:19 <oerjan> i found that constructive logic proof intriguing because afair it essentially amounts to using the kripke world semantic for -> to compute things in parallel in subworlds.
13:15:39 <oerjan> i'm not sure if that's what it said or what i realized it implied.
13:16:09 <oerjan> (constructive ~ intuitionistic)
13:17:54 <fizzie> I think we had a gigasecond celebration on the channel?
13:18:35 <fizzie> Or at least on some channel.
13:18:44 <fizzie> I don't remember if it was at 10^9 or 2^30.
13:19:15 <fizzie> 10^9 seems to have been pre-#esoteric.
13:19:15 <oerjan> `run date --date='@1000000000'
13:19:16 <HackEgo> Sun Sep 9 01:46:40 UTC 2001
13:19:18 <zzo38> What is a kripke world semantic for -> ?
13:20:42 <oerjan> zzo38: well first you have a partially ordered set of worlds, each of which assigns true or false to each propositional value in your term, and such that the value can only change from false to true if you go to a "later" world.
13:21:22 <fizzie> `run date --date=@$(dc -e '2 30^p')
13:21:23 <HackEgo> Sat Jan 10 13:37:04 UTC 2004
13:21:38 <oerjan> then you define a -> b to be false in a world if there is any later world (including the world itself) in which a is true and b is false; and a -> b to be true otherwise.
13:22:01 <fizzie> http://codu.org/logs/log/_esoteric/2004-01-10 well
13:23:11 <oerjan> and then you can show a term is a tautology iff it's assigned true in all kripke semantic worlds.
13:24:24 <oerjan> (there are similar definitions for other connectives; and/or work like the usual truth table in each world, while not a = a -> False)
13:24:51 <oerjan> but you only need -> for the full PSPACE-completeness
13:25:22 <oerjan> *each propositional variable
13:26:01 <oerjan> this semantics is quite convenient if you want to show a term is _not_ a tautology.
13:27:17 <oerjan> like to show a or (not a) isn't a tautology, you just need two worls; the first one assigns False to a and the second assigns True, which makes both a and not a False in the first world.
13:28:49 <Jafet> a and not a, and not a or not a?
13:29:21 <ais523_> Jafet: this is intuionistic logic, where "a or not a" is not always true
13:29:50 <ais523_> the "main" tautology is "f(not not a) is equivalent to not not f(a)"
13:30:27 <int-e> not not not a iff not a
13:30:50 <int-e> @djinn (((a -> r) -> r) -> r) -> a -> r
13:31:24 <int-e> @djinn (a -> r) -> ((a -> r) -> r) -> r
13:31:59 <oerjan> one interesting fact here is that not a is true in a world if it's true in all "final" worlds (assuming a finite set of worlds, which is enough for a finite set of variables), and in final worlds everything behaves classically, from which you get immediately the theorem that not a is an intuitionistic tautology iff it is a classical one.
13:33:54 <oerjan> fizzie: i'm sure we've had date celebrations but both of those were before my time on the channel.
13:34:32 <lambdabot> Generates Haskell code from a type.
13:34:32 <lambdabot> http://darcs.augustsson.net/Darcs/Djinn
13:35:10 * ais523_ notes that not always being true is not the same thing as sometimes being false
13:35:12 <int-e> simply typed lambda terms === proofs for intuitionistic propositional logic
13:36:26 <Jafet> @djinn (((a -> Void) -> Void) -> Void) -> a -> Void
13:39:45 <int-e> @djinn Not (Not (a -> Not a -> b))
13:39:45 <lambdabot> f a = void (a (\ _ b -> void (a (\ c -> void (b c)))))
13:39:52 <oerjan> istr @djinn tries to use a linear proof if there is one.
13:40:30 <int-e> @djinn Not (a -> Not a)
13:40:55 <int-e> @djinn Not (Not (Not (a -> Not a)))
13:41:07 <int-e> oh. tautology. stupid me.
13:41:15 <Taneb> int-e, wouldn't Not (a -> Not a) be the same as proving that the system is consistent?
13:41:46 <int-e> Taneb: it's not a tautology; a = False makes it false.
13:42:16 <Taneb> Not (a <-> Not a) would be proving the system is consistent
13:42:32 <Taneb> @djinn Not (a -> Not a, Not a -> a)
13:42:32 <lambdabot> f (a, b) = void (a (b (\ c -> a c c)) (b (\ d -> a d d)))
13:43:01 -!- Sorella has joined.
13:43:02 <zzo38> But if it is inconsistent then you can prove everything including that it is consistent, so it doesn't help
13:43:32 <Taneb> zzo38, that is a very good point
13:45:56 -!- atehwa has quit (*.net *.split).
13:45:56 -!- mroman_ has quit (*.net *.split).
13:45:56 -!- olsner has quit (*.net *.split).
13:46:04 -!- atehwa has joined.
13:46:08 -!- mroman has joined.
13:46:14 -!- olsner has joined.
13:48:21 <Melvar> @djinn Not (Not (Either a (Not a)))
13:48:21 <lambdabot> f a = void (a (Right (\ b -> a (Left b))))
13:50:20 <int-e> djinn assumes data Void {- no constructors -} and void :: Void -> a
13:50:56 <int-e> and Not a = a -> Void
13:51:30 -!- Tritonio1 has joined.
13:52:18 <zzo38> You could add a ContNot type as well, I suppose, if you want a classical "not" operator too
13:54:34 -!- Tritonio has quit (Ping timeout: 240 seconds).
13:55:50 <Melvar> int-e: That doesn’t seem to be consistent with the output …
13:57:25 <Melvar> The searched function would be onto Void. Why then would it use void to eliminate Void?
13:59:21 <Melvar> ( \a => the (Not (Not (Either a (Not a)))) $ \f => f (Right (\x => f (Left x)))
13:59:39 <Melvar> ( \a : Type => the (Not (Not (Either a (Not a)))) $ \f => f (Right (\x => f (Left x)))
14:00:38 <Melvar> ( \a : Type => the (Not (Not (Either a (Not a)))) (\f => f (Right (\x => f (Left x))))
14:00:42 <int-e> Melvar: so the outermost "void" is superfluous, a (b (\ c -> a c c)) (b (\ d -> a d d)) has type Void all by itself
14:00:56 <int-e> Melvar: but void :: Void -> Void is a permitted instantiation of void.
14:01:05 <int-e> so it's not wrong.
14:01:52 <Melvar> I’d’ve thought djinn wouldn’t put it there if superfluous, though.
14:02:47 <int-e> I trust djinn to be complete, but not to produce minimal proofs.
14:03:38 <int-e> for example, (\c -> a c c) (b (\d -> a d d)) would be a shorter proof.
14:04:04 <int-e> (starting with f (a,b) = ...)
14:04:25 <Melvar> What you’re getting is a function, not a pair …
14:05:16 <int-e> even better, f (a,b) = (\c -> c (b c)) (\d -> a d d)
14:05:26 <int-e> but I would not expect djinn to find it.
14:05:33 <Melvar> Oh, you’re referring to Taneb’s thing, not mine.
14:06:27 <int-e> right. I missed yours ...
14:10:08 <int-e> But again it uses void :: Void -> Void which is superfluous and harmless
14:10:42 -!- glogbackup has joined.
14:10:45 <Melvar> ( :t FalseElim {a=_|_}
14:12:50 <mroman> fizzie: our industry partner didn't want to tell us what they expect from us.
14:15:09 -!- edwardk has joined.
14:15:09 -!- glogbackup has quit (Read error: Connection reset by peer).
14:21:58 <mroman> I don't realy have much for comparision
14:22:11 <mroman> most crowd simulations also offer 3D rendering
14:22:20 <mroman> and these call 25k a "huge amount"
14:26:42 <idris-bot> Prelude.Uninhabited.absurd : Uninhabited t => t -> a
14:26:54 <edwardk> mroman: http://www.indiegamejam.com/igj0/ ;)
14:27:02 <ais523_> ah right, FalseElim is the implementation of absurd for bottom?
14:27:59 <edwardk> if someone sent me an issue for the void package to add an Uninhabited class I could be talked into it very easily
14:29:01 <ais523_> what's the benefit of having more than one uninhabited type?
14:29:10 <ais523_> also, how do you type shift-home on a 96-key AZERTY keyboard?
14:29:20 <ais523_> I figured out home by itself, it's numpad 7 with numlock turned off
14:29:25 <ais523_> but shifting it just produces a 7
14:30:03 <idris-bot> A canonical proof that some type is empty
14:30:16 <idris-bot> uninhabited : Uninhabited t => t -> _|_
14:30:16 <idris-bot> If I have a t, I've had a contradiction
14:30:47 <Melvar> Then absurd is just (FalseElim . uninhabited).
14:31:24 <Melvar> Empty types include (Fin 0) and (Z = S Z).
14:31:38 <ais523_> I was thinking, more in terms of Haskell
14:31:54 <Jafet> ais523: to unify all the incompatible empty type packages, obviously
14:32:37 <Melvar> And (Elem x []) for arbitrary x, for example.
14:33:09 <ais523_> yeah, it's obvious why it's useful in dependent typing
14:35:36 <Jafet> Actually, I'm not sure how an Uninhabited class would work
14:35:53 <Jafet> forall a u. Uninhabited u => u -> a
14:36:03 <Melvar> It has the method uninhabited as above.
14:38:14 <Jafet> Yeah it's obvious for dependent typing
14:39:31 <Melvar> It’s obvious with a canonical uninhabited type, which is what _|_ is.
14:53:09 <edwardk> ais523_: data V1 a; newtype Void = Void Void; Sum V1 V1; Product V1 f, etc. are all uninhabited
14:53:55 <edwardk> but expressing that properly is tricky
14:54:11 <edwardk> you want to let a product be uninhabited when either side of it is
14:54:57 <edwardk> you should be able to concoct an UninhabitedOr and UninhabitedAnd that combines them correctly
14:55:12 <edwardk> and/or define version with GHC.Generics
14:55:43 <ais523_> gqh, ny keyboqrd hqs !just! spontqneously chqnged to QWERTY
14:55:52 <ais523_> qfter refusing to be QWERTY for qges
14:56:23 <edwardk> With a lazy type nat you could check for -- type Uninhabited a = MaxInhabitants 0 a
14:57:09 <edwardk> but we only need inhabited or not decidably, with the right boolean functions
14:57:17 <Melvar> I have a Finite typeclass.
14:57:40 <ais523_> phew, just managed to change it back, somehow
14:58:03 <ais523_> (btw, "QWERTY" above = "AZERTY" encoded via a y/AZERTY/QWERTY/ transformation which also contains other letters)
15:00:21 -!- drdanmaku has joined.
15:02:39 <edwardk> type family Inhabitable t :: Bool; type instance Inhabitable Void = 'False; type instance Inhabitable [a] = 'True; type instance Inhabitable (Compose f g a) = Inhabitable (f (g a)); ...
15:03:10 <edwardk> btter as a class associated type though so you can more easily get the proof of absurdity wthout boolean blindness
15:05:14 -!- conehead has joined.
15:06:40 -!- AnotherTest has joined.
15:16:01 * oerjan realizes edwardk's last line would probably fit right into a postmodern treatise.
15:18:00 -!- mhi^ has joined.
15:23:12 <HackEgo> [wiki] [[Snack]] http://esolangs.org/w/index.php?diff=39535&oldid=31569 * Zzo38 * (+80) How to be afraid of you
15:33:27 <Jafet> Is there a postmodern programming language
15:34:43 <oerjan> no, programming is a tool of the patriarchal bourgeoisie.
15:38:17 -!- Bike has joined.
15:42:12 -!- Tritonio1 has quit (Ping timeout: 265 seconds).
15:42:43 -!- idris-bot has quit (Ping timeout: 258 seconds).
15:45:38 -!- Melvar has quit (Ping timeout: 276 seconds).
15:53:00 -!- oerjan has quit (Quit: leaving).
15:54:26 <zzo38> Then make up the postmodern programming language.
15:55:17 -!- slereah has quit (Quit: Leaving).
15:58:23 -!- Melvar has joined.
15:59:29 -!- ^v has joined.
16:01:53 -!- idris-bot has joined.
16:10:20 -!- nooodl has joined.
16:13:53 -!- Bike has quit (Ping timeout: 240 seconds).
16:16:59 -!- yorick has quit (Remote host closed the connection).
16:19:59 -!- ^v has quit (Read error: Connection reset by peer).
16:20:21 -!- ^v has joined.
16:21:23 -!- FreeFull has joined.
16:39:55 <HackEgo> [wiki] [[Truth-machine]] http://esolangs.org/w/index.php?diff=39536&oldid=39137 * GermanyBoy * (+58) /* Forobj */
16:41:09 <ion> http://youtu.be/frOtNb8YD1w?t=3m26s
16:47:09 -!- MindlessDrone has quit (Read error: Connection reset by peer).
16:48:29 -!- MindlessDrone has joined.
16:48:59 <HackEgo> [wiki] [[Gentzen]] N http://esolangs.org/w/index.php?oldid=39537 * Zzo38 * (+5689) Created page with "[[Category:Languages]][[Category:2014]] ==Syntax== * Name: Consists of ASCII letters, numbers, and underscores, without starting with a digit. An underscore by itself is not ..."
16:49:19 <HackEgo> [wiki] [[Gentzen]] http://esolangs.org/w/index.php?diff=39538&oldid=39537 * Zzo38 * (+0)
16:51:43 <zzo38> Do you like this? http://esolangs.org/wiki/Gentzen
16:56:47 <zzo38> I tried to ask about if there is any SQLite extension for connecting to internet, but they always answered improperly. ("Yes, it is called TCP/IP" and "Yes, it is called a programming language" and so on)
16:56:53 <zzo38> Do you know of any such thing though?
17:00:23 -!- edwardk has quit (Read error: Connection reset by peer).
17:03:31 -!- shikhout has changed nick to shikhin.
17:09:59 -!- hk3380 has joined.
17:14:22 <ais523_> zzo38: I don't know of one, although I don't think it would be impossible to write one
17:14:43 <ais523_> it would probably be easier to do your connections from outside SQLite, though, rather than inside
17:20:12 <zzo38> Yes possibly, although I would want to do it from an extension too; for one thing it mean that you can use it to extend application databases even if the application program isn't using internet (for example, to cause all writes to a specific table to be automatically copied to a server), but can also be used with stand-aline SQLite shell programming too.
17:20:40 -!- mekeor has joined.
17:20:46 <zzo38> I could not quite understand the programming of internet connection in C very well though, so I wanted to know if it already exist.
17:21:36 <zzo38> I do, in fact, already write extension for many other things, such as to compute various statistics, and to add formatting functions, and trigonometry and logarithms and square root and so on
17:22:02 <zzo38> And even new commands such as CREATE FUNCTION and CREATE MACRO
17:25:27 <zzo38> ais523_: Do you use SQLite at all?
17:25:59 <mroman> why the hell is it Double.parseDouble but Integer.parseInt
17:26:03 <mroman> instead of Integer.parseInteger
17:26:25 <zzo38> ais523_: What do you use it for?
17:27:16 <ais523_> reading databases in SQLite format, that have been created by other programs
17:27:29 <zzo38> What other programs?
17:28:12 <zzo38> It is certainly useful for that. You could also modify the databases that are created by other programs too, if there is a use to do so.
17:29:35 <zzo38> For example if you want to add triggers, views, columns, and so on, or just if you want to adjust the data it contains.
17:29:44 <mroman> I gotta redo Burlesque. But in Java this time
17:35:34 <zzo38> Why in Java this time? What was it before?
17:42:07 <zzo38> Why do you want to do it in Java this time, though?
17:42:32 <quintopia> better mobile device compatibility
17:45:38 -!- conehead has quit (Quit: Computer has gone to sleep).
17:51:09 -!- MoALTz has joined.
17:52:22 <mroman> I just haven't done much in Java
17:52:35 <mroman> and if it's in Java there's a higher chance somebody actually helps :)
17:52:48 -!- conehead has joined.
17:53:48 <ais523_> anyone who has a decent chance of needing to use Java should maintain exactly one overcomplicated, overengineered Java project
17:54:36 <HackEgo> [wiki] [[Gentzen]] http://esolangs.org/w/index.php?diff=39539&oldid=39538 * Zzo38 * (+419)
17:56:13 <mroman> I just use a lot of instanceofs
17:56:38 <mroman> for eval (MyInteger a) = ...; eval (MyDouble a) = ....; eval (MyString a) = ...; and so forth
17:56:43 <mroman> it's all gonna be crappy instanceof
18:01:34 <mroman> It's gonna take a while to have enough built-ins to be useful :)
18:03:54 <mroman> I think it took 1.5 years for Burlesque to become what it has become
18:04:22 <mroman> and some student colleagues are jealous :)
18:04:56 <mroman> it's pretty good for homework stuff
18:05:06 <mroman> like "is that number square free"
18:05:30 <mroman> it's like 12B written in 10s
18:07:04 -!- Phantom_Hoover has joined.
18:18:23 -!- nooodl has quit (Ping timeout: 276 seconds).
18:28:11 -!- shikhin has quit (Ping timeout: 276 seconds).
18:29:30 -!- shikhin has joined.
18:41:08 -!- FireFly has quit (Excess Flood).
18:45:39 -!- FireFly has joined.
18:49:35 <HackEgo> Fri May 16 01:00:00 UTC 2014
18:49:39 <HackEgo> Fri May 16 12:00:00 UTC 2014
18:49:46 <HackEgo> Fri May 16 01:23:00 UTC 2014
18:49:53 <HackEgo> Fri May 16 12:34:00 UTC 2014
18:49:58 <HackEgo> date: invalid date ` 12345'
18:50:05 <HackEgo> Fri May 16 03:00:00 UTC 2014
18:50:20 <HackEgo> Fri May 16 18:49:54 UTC 2014
18:50:36 <HackEgo> Fri May 16 04:00:00 UTC 2014
18:50:53 <HackEgo> Fri May 16 03:00:00 UTC 2014
18:51:02 <HackEgo> Thu May 15 23:00:00 UTC 2014
18:51:16 <HackEgo> Sat Feb 3 00:00:00 UTC 0001
18:51:23 <HackEgo> date: invalid date ` 1+2+3'
19:04:13 <impomatic> Are there any CSS geeks here? I was wondering if there's a sneaky way to modify the content with CSS. E.g. my <h1> contains "xxxxx: yyyyyyy" and I want to remove the "xxxxx:" without any extra markup.
19:04:27 <impomatic> If I ask in #css they'll just tell me css isn't for content
19:06:17 <ais523_> impomatic: do you happen to have control over the styling but not the content, for some reason?
19:06:21 <ais523_> there is definitely a way to add content
19:06:28 <ais523_> but I'm not sure about removing it
19:07:38 <zzo38> impomatic: I do not think that is possible, but I don't know for sure.
19:09:55 <impomatic> I can hide the original and add replacement content using h1::after (content: );
19:11:05 <ais523_> you could do something like add an element before it, place the prefix after that new element, in the same font and styling
19:11:09 <ais523_> but set the foreground equal to the background
19:11:12 <impomatic> The problem is I want the replacement content to be a substring of the original. (It's for a print style sheet)
19:11:39 <ais523_> that sounds like the sort of thing that could easily go wrong, though
19:12:09 <zzo38> impomatic: I would think you should then make that text another part and then make the CSS to hide it if it is a printout?
19:12:25 <impomatic> If I knew the exact width of the characters, I could probably do margin: -100px or something.
19:14:33 <impomatic> zzo38: enclose the "xxxxx:" in a <span>? I was hoping to avoid that, otherwise I'll have to edit 500+ files by hand!
19:15:17 <zzo38> Don't do it by hand; use another program such as AWK or sed.
19:15:52 <impomatic> I suppose I ought to install AWK :-)
19:16:42 <ais523_> sed/awk/perl are all designed for that sort of job
19:16:46 <ais523_> in increasing order of complexity
19:16:50 <ais523_> although perl does lots of other things too
19:17:50 <int-e> beautiful. "Earlier today, a virus signature from the virus "DOS/STONED" was uploaded into the Bitcoin blockchain, which allows small snippets of text to accompany user transactions with bitcoin."
19:18:15 <int-e> https://answers.microsoft.com/en-us/protect/forum/mse-protect_updating/microsoft-security-essentials-reporting-false/0240ed8e-5a27-4843-a939-0279c8110e1c?tm=1400189799602
19:18:17 <ais523_> and now all the antivirus programs think it's a virus?
19:18:38 <ais523_> that's really clever, whoever thought of it, although highly antisocial
19:21:26 -!- AnotherTest has quit (Ping timeout: 276 seconds).
19:21:51 <Jafet> Hmm, put random shellcode into the blockchain, then your client exploits will have something to jump to
19:22:47 <Jafet> Have they decided what to do with the illegal erotica yet
19:24:52 -!- MindlessDrone has quit (Quit: MindlessDrone).
19:25:07 <zzo38> I suppose if you put whatever you want into the blockchain, in order to cause backups of the data to exist for whoever makes backups of Bitcoin blockchains.
19:26:17 <ais523_> zzo38: it probably wouldn't be cost-effective because of the transaction fees
19:28:29 <zzo38> ais523_: Yes, I suppose so, but if you want to pay for such a thing then maybe it can help, especially if you are already making a payment due to some other reason too, I suppose (for example, to the backup service).
19:30:45 <Jafet> Oh, the blockchain porn was only links.
19:41:18 -!- Slereah_ has changed nick to Slereah.
19:49:49 -!- nucular_ has joined.
19:49:58 -!- nucular has quit (Ping timeout: 245 seconds).
19:50:03 -!- nucular_ has changed nick to nucular.
19:50:11 -!- nucular has quit (Changing host).
19:50:11 -!- nucular has joined.
20:03:13 -!- hk3380 has quit (Ping timeout: 252 seconds).
20:04:08 <HackEgo> [wiki] [[Gentzen]] http://esolangs.org/w/index.php?diff=39540&oldid=39539 * Zzo38 * (+2448)
20:05:11 <kmc> '↪ A start tag whose tag name is "image": Parse error. Change the token's tag name to "img" and reprocess it. (Don't ask.)'
20:07:31 -!- MoALTz has quit (Quit: bbl).
20:10:20 <kmc> the parser SHALL NOT even
20:10:47 <int-e> so it SHOULD odd?!
20:14:52 <HackEgo> [wiki] [[Gentzen]] http://esolangs.org/w/index.php?diff=39541&oldid=39540 * Zzo38 * (+509)
20:15:31 <myname> everytim i see something from zzo i ask myself "do i REALLY want to read it?"
20:16:31 <elliott> ais523_: it's like $90 in transaction fees for a 1 megabyte transaction right now I think
20:17:05 <ais523_> $90 to back up 1MB? that's not really that good a deal
20:17:27 <myname> zzo38: on one side, you have really great ideas, but on the other side, you have really strange ideas
20:17:45 <elliott> ais523_: it buys you an /awful lot/ of backups of your data
20:17:59 <elliott> ais523_: and many people have a strong financial incentive to keep those backups
20:18:32 <ais523_> yes, it's a very reliable backup, assuming that the blockchain doesn't collapse, and that people don't come up with some way to purge text from it (say, to get rid of virus signatures)
20:18:54 <elliott> changing the past of the blockchain is kind of difficult...
20:19:07 <zzo38> Insane people have the best ideas. Sometimes.
20:19:17 <elliott> afaik, the hashes are chained, a la git
20:19:46 <ais523_> you can get everyone to agree that a particular hash was part of the blockchain
20:19:53 <ais523_> and record the state of everything at that moment
20:20:01 <ais523_> and then just work from that new, truncated-behind blockchain
20:20:11 <ais523_> it'd be awkward, but perhaps necessary if the blockchain grows faster than disks do
20:20:21 <myname> zzo38: i think that's what i was trying to say
20:20:34 <elliott> "end-users" aren't going to store the blockchain, anyway
20:20:48 <ais523_> unless they need to know how many bitcoins someone has
20:20:59 <ais523_> or whether a transaction was confirmed
20:21:02 <ais523_> both of which are kind-of important
20:21:18 <elliott> people are going to use light-weight clients or delegate their trust to another entity which has the blockchain
20:21:45 <elliott> the blockchain is already huge; nobody who gets into bitcoin today who isn't really paranoid is using the "official" client
20:27:34 <mroman> impomatic: you can do that @css
20:28:26 -!- Bike has joined.
20:29:55 <mroman> you could for example use a font that doesn't have an x
20:30:00 <mroman> if it realy is xxx: yyy ;)
20:30:21 <mroman> otherwise... the CSS content property can probably just add content, but not remove it
20:30:58 <mroman> impomatic: what also might work is setting text-indent to a negative value
20:34:46 <impomatic> mroman: all of my headers are <h1>Core War: blah blah blah blah</h1> - I want to hide "Core War:" when it's printed. I considered negative text-indent, negative margin, etc but the exact size may vary depending on the font.
20:35:44 <ais523_> you could use a visibility:hidden element in order to assess the text size
20:37:03 <impomatic> It's possible to position "Core War:" in a white font exactly over the bit I want to hide, but unfortunately white prints as light grey.
20:37:39 <fowl> put it in a <span>
20:37:45 <kmc> you really can't change the markup?
20:37:54 -!- yorick has joined.
20:38:00 <fowl> oh that changes things
20:38:47 <kmc> 13:10 < shachaf> whoa, html5 is great
20:38:49 <kmc> how do ya figure
20:39:37 <Bike> it facilitates an attack called "billion laughs", how could it not be great
20:39:59 <kmc> Bike: does it? that looks like an XML thing
20:39:59 <mroman> impomatic: you might wanna use sed then ;)
20:41:04 <Bike> kmc: i think you can still use <!ENTITY >
20:41:49 <Bike> well fuck html5 then
20:42:29 <kmc> that is my general opinion, but not for this reason
20:43:00 <Bike> imo reshuffle ur priorities
20:44:23 <kmc> maybe you can inside MathML or SVG inside HTML
20:45:23 <kmc> I think you're not allowed to do that, either, but some user-agents might allow it
20:45:34 <kmc> since those are more like proper XML syntaxes that are awkwardly embedded inside HTML5
20:46:42 <Taneb> I am going to have a fun June
20:46:48 <mroman> I'm waiting for Web 3.0 - the emotional web
20:46:59 <mroman> with tags like <sad> and <irony> and <fuckyou>
20:47:15 <Bike> @google emotionml
20:47:17 <lambdabot> Title: Emotion Markup Language (EmotionML) 1.0
20:47:26 <Bike> welcome to the future, mroman
20:47:36 <kmc> '↪ An end tag whose tag name is "sarcasm": Take a deep breath, then act as described in the "any other end tag" entry below.'
20:47:48 <mroman> somebody seriously did that already
20:48:02 <kmc> Taneb: oh?
20:48:12 <kmc> good kind of fun or bad kind?
20:49:00 <Taneb> Last exam is on the 3rd. Dad's birthday on the 4th, going home for that. 13th I'm going down to London for the day. 21st-22nd I'm at an anime con
20:49:06 <mroman> <action-tendency name="charge-battery" value="0.9"/>
20:50:13 <Taneb> All the meanwhile I should be working on GSoC
20:50:27 <kmc> what's your GSoC project?
20:50:34 <Taneb> Debugger for GHCJS
20:51:16 <mroman> <emotion <category name
20:51:24 <mroman> I pressed enter to soon
20:51:51 <mroman> well anyway... I wanted to state that I think a debugger for ghcjs is a good thing with EmotionML
20:52:09 <mroman> <category name="fondness" value="0.832091"/>
20:53:54 <kmc> <category name="badness" value="10000"/>
20:54:27 <kmc> whoops just poured salt all over my sofa
20:55:05 <mroman> that's not EmitionML recommendation conform
20:55:19 <mroman> it clearly says value must be within 0..1
20:55:26 <Taneb> Do you know whether anyone applied for a GSoC to do work on/with Rust?
20:58:55 <kmc> i think so, but I'm not positive
20:59:08 <kmc> mozilla has a lot of interns working on Rust and Servo, as well
20:59:47 <mroman> Rust is a systems programming language that runs blazingly fast, prevents almost all crashes*, and eliminates data races.
21:00:49 <kmc> "* In theory. Rust is a work-in-progress and may do anything it likes up to and including eating your laundry."
21:00:53 <zzo38> How exactly will you be able to use the terminal to change the POWER setting if it is not already set? (Refering to VT100 terminal)
21:00:57 <mroman> Would you rather recommend Rust or Go?
21:01:11 <kmc> mroman: they're really very different languages
21:01:20 <mroman> I'm looking for a new "awesome" language and so far Go is pretty high up the list
21:01:30 <kmc> Go has shared-memory concurrency with garbage collection; it's designed for writing high throughput network servers
21:01:34 <ais523_> but yeah, they're not really competing except in as much as they're new systems programming languages made by web browser manufacturers
21:01:35 <fowl> go's runtime generics are disgusting
21:01:36 <kmc> but not anything realtime or low latency
21:01:49 <kmc> Rust has a far more interesting memory management story
21:01:53 <kmc> which enables GC-less operation
21:01:57 <fowl> mroman, nimrod
21:02:04 <zzo38> New "awesome" language isn't good enough, I would think? You should need other criteria to know what you want?
21:02:08 <kmc> it's designed for writing low-latency software like web browsers, kernels, games, high-frequency trading strategies, etc.
21:02:23 <kmc> can run on bare metal, etc
21:02:37 <ais523_> Rust's basically an attempt to make a crash-free C, whereas Go is an attempt to make a lower-level Erlang
21:02:47 <kmc> it's also designed by people who actually know programming languages theory and don't consider it a bad thing
21:03:14 <zzo38> I happen to like C and BLISS, although BLISS is hardly ever used anymore and there is no GNU BLISS compiler that I know of.
21:04:14 <Taneb> I ought to write more Rust
21:04:17 -!- mhi^ has quit (Quit: Lost terminal).
21:04:41 <zzo38> Write down the kind of thing you intend to have, and then see what program language has it, whether it is C, BLISS, Rust, Go, SQL, Perl, or QBASIC.
21:05:04 <kmc> mroman: if you're asking which language is more interesting, it's Rust for sure
21:05:10 <kmc> but Go might be better for writing certain kinds of software
21:05:12 <kmc> and is more mature
21:05:29 <kmc> you'd be a bit mad to run a production system on Rust right now, although I think there are some (small) examples of people doing that
21:05:56 <mroman> "We've got destructors"
21:06:03 <mroman> which clean up as soon as you leave scope
21:06:21 <kmc> Rust is based on unique ownership of objects + safe borrowing of references to them
21:06:28 <kmc> but you can also do reference counting or GC if you want
21:06:59 <kmc> it's a lot like a vastly cleaned-up C++
21:07:06 <shachaf> is there a cycle collector or something for rust yet
21:07:25 <ais523_> there's a reference counter and a non-reference-counting-based garbage collector, IIRC
21:07:34 <ais523_> neither of which is used unless you ask for them
21:07:39 <kmc> RAII, smart pointers, non-homogenous data, objects by value, monomorphizing generics, etc.
21:07:55 <kmc> there's not actually a garbage collector as part of Rust yet
21:08:10 <kmc> it'll happen after 1.0 maybe
21:08:21 <kmc> the std lib does have refcounted boxes, both thread-local and shareable versions
21:08:24 <mroman> although i'm not really familar with C++
21:08:34 <kmc> some of Servo's Rust objects are now managed by the SpiderMonkey garbage collector, which is pretty cool
21:08:46 <kmc> and this is integrated with Rust smart pointers in a way that mostly prevents you from fucking it up
21:08:52 <kmc> I think my colleage and I are going to write a blog post about that
21:08:59 <kmc> colleague*
21:09:00 <ais523_> mroman: don't worry, neither is anyone else
21:09:40 -!- mhi^ has joined.
21:09:40 <mroman> I assume something like { int* a = malloc(..); } doesn't get cleaned-up in Rust?
21:10:17 -!- nooodl has joined.
21:10:20 <ais523_> let int a = box 6; or whatever definitely does get cleaned up
21:10:21 <kmc> it depends what you mean by translating that to Rust
21:10:32 <ais523_> or rather, the program will fail to compile if it can't figure out where the data's meant to get freed
21:11:03 <kmc> mroman: there's an "unsafe dialect" of Rust which will let you call the actual libc malloc and get a raw pointer back and dereference it and segfault and do whatever you want
21:11:47 <zzo38> kmc: Is it possible to combine it with safe codes in the same file (by specifying if you want unsafe, on one block, or something like that)?
21:11:56 <kmc> you can only do that in a function that's marked unsafe, or within an unsafe { ... } block
21:13:00 <kmc> the latter is an unchecked assertion that you have proven that none of these behaviors can occur: http://static.rust-lang.org/doc/master/rust.html#behavior-considered-unsafe
21:13:11 <kmc> it's the way you wrap a safe interface around unsafe internals
21:13:25 <Bike> fuckyouiknowwhatimdoing { ... }
21:13:28 <kmc> (and you can only call an unsafe function from another unsafe function or an unsafe { ... } block, naturally)
21:13:54 <fowl> rust has disgusting "macro"s
21:14:17 <kmc> mroman: so the more idiomatic translation of that would be like ais523_ said, let a: Box<int> = box 3;
21:14:20 <Bike> unsafeCoerce i assume
21:14:22 <kmc> used to be spelled let a: ~int = ~3;
21:14:38 <Melvar> Bike: Effectively, but “believe_me” is the actual name.
21:14:43 <Bike> ( believe_me 17 :: String
21:14:46 <idris-bot> When elaborating an application of constructor __infer:
21:14:47 <idris-bot> Can't disambiguate name: Effects.Env.::, Data.HVect.::, Prelude.List.::, Data.Vect.Quantifiers.::, Prelude.Stream.::, Prelude.Vect.::
21:15:00 <Bike> ( (believe_me 17) :: String
21:15:00 <idris-bot> When elaborating an application of constructor __infer:
21:15:00 <idris-bot> Can't disambiguate name: Effects.Env.::, Data.HVect.::, Prelude.List.::, Data.Vect.Quantifiers.::, Prelude.Stream.::, Prelude.Vect.::
21:15:01 <kmc> that gives you a pointer to a box in the heap; the pointer "owns" the box and when the pointer's destructor is called, the box will be freed
21:15:10 <Bike> well, whatever.
21:15:11 <kmc> like C++'s std::unique_ptr
21:15:11 <ais523_> Bike: it can't figure out which 17 you mean
21:15:18 <Melvar> Bike: (::) is the cons operator.
21:15:29 <zzo38> kmc: Why did you chage it from let a: ~int = ~3 into let a: Box<int> = box 3; ?
21:15:30 <Bike> ( (believe_me 17) : String
21:15:31 <idris-bot> (input):1:17: error: expected: "$",
21:15:35 <kmc> but you can take a "borrowed" reference to that box (of type &int or &mut int) and pass it around
21:15:39 <kmc> and the safety of that is statically checked
21:15:47 <Melvar> Bike: You can’t do a type annotation with colon.
21:15:49 <Bike> "clearly i'm too used to haskell"
21:15:51 <idris-bot> Prelude.Basics.the : (a : Type) -> a -> a
21:16:02 <Bike> ( the String (believe_me 17)
21:16:21 <Bike> ( the String 17
21:16:21 <idris-bot> Can't resolve type class Num String
21:16:35 <ais523_> I hate the way every super-massively-type-safe language has a coerce-anything-to-anything-else function
21:16:36 <kmc> the type system includes "lifetime variables" for preventing dangling references http://static.rust-lang.org/doc/master/guide-lifetimes.html#returning-references
21:16:52 <Bike> coerce crap to bullshit
21:16:54 <kmc> fowl: what's your problem with Rust's macros?
21:16:54 <zzo38> ais523_: Are you sure they would all have such a one?
21:17:04 <Melvar> Bike: If you compiled that believe_me bit it would probably segfault.
21:17:07 <mroman> that would actually mean it's weakly and not strongly typed?
21:17:10 <zzo38> Even then, in Haskell there is a safe mode, which avoid such unsafeCoerce and so on.
21:17:19 <Bike> Melvar: that's what i was hoping to see :p
21:17:25 <kmc> ais523_: it's really necessary in Rust, because you build the safe parts out of unsafe parts
21:17:30 <kmc> most of the Rust runtime system is written in Rust
21:17:35 <mroman> I recall the definition of "weak" is "you can circumvent the type system with a (void*) cast"
21:17:35 <kmc> (also, most of the Rust runtime system is optional)
21:17:39 <ais523_> kmc: yes, I understand that
21:17:45 <kmc> mroman: nobody actually agrees on what these terms mean
21:17:51 <Bike> >2011 >words having means
21:17:54 <ais523_> mroman: I've seen that defined as "unsound"
21:18:10 <zzo38> Except that as they said, in Rust if you want a unsafe code you have to specify "unsafe" block. In Haskell they are called "unsafe".
21:18:33 <shachaf> ais523_: I think people would call e.g. Haskell unsound because of undefined.
21:18:36 <Bike> have you considered becoming a non cognitivist??
21:18:42 <ais523_> I think the only type-related definition that's generally agreed on is static versus dynamic
21:18:49 <shachaf> unsafeCoerce is more of an operational thing.
21:18:53 <kmc> shachaf: I would say that the type system is an unsound logic, but not that the type system itself is unsound
21:18:59 <fowl> kmc, they're filthy unreadable $$$enough$already$$$
21:19:09 <shachaf> kmc: Ah, I suppose you could say that.
21:19:27 <kmc> typically an unsound type system means one which allows programs to "go wrong", whatever exactly that means for the goals of your type system
21:19:28 <ais523_> Melvar: could you get idris-bot to not line-wrap its error messages?
21:19:36 <zzo38> Bike: What is a non cognitivist?
21:19:42 <ais523_> one 300-char line is less disruptive in IRC than five 60-char lines
21:19:44 <kmc> most type systems try to provide memory safety, so "going wrong" would include use-after-free, memory leaks, etc.
21:19:46 <ais523_> not a big deal, just something to think aobut
21:19:53 <kmc> Rust also tries to prevent data races
21:20:07 <fowl> how many kinds of pointers are there in rust? still 4?
21:20:11 <ais523_> kmc: I was reading that post about replacing "mut" with "uniq"
21:20:19 <kmc> I didn't read that yet
21:20:29 <ais523_> and reminded me a bunch of my own research
21:20:33 <kmc> fowl: ~ and @ have both turned into library types
21:20:35 <zzo38> What is this "mut" and "uniq"?
21:20:46 <kmc> fowl: so there's *, *mut, &, and &mut
21:20:53 <kmc> but also many library types that act like pointers
21:20:53 <ais523_> zzo38: "mut" means "the data can be changed via this pointer", and "this is the only mutable pointer to the data"
21:21:05 <Melvar> ais523_: Seems to be a bug in Idris, since the normal REPL does the same thing, regardless of the consolewidth setting (which the bot sets to 200)
21:21:10 <ais523_> "uniq" is a proposal for "this is the only pointer to the data", with mutability not being specific
21:21:10 <kmc> every big C++ project has like a dozen custom smart pointer classes
21:21:34 <kmc> "mut" currently means the only pointer, not just the only mutable pointer
21:22:03 <zzo38> kmc: Really? I don't know much about C++ project, and why they have a dozen custom smart pointer classes.
21:22:56 <ais523_> (you have to specify an INTERCAL program if you want ick to produce output, or --help/--version)
21:22:58 <zzo38> Couldn't you add both a "mut" and "uniq" types, then?
21:23:07 <Melvar> ais523_: Also I should look if I can’t find how that operator-listing parse error comes about, since that’s annoying in any case.
21:23:11 <ais523_> zzo38: that was one suggestion in the blog post
21:23:23 <fizzie> The mean of a word is just the character corresponding to the (rounded) sum of its code points divided by the length of the word.
21:23:25 <ais523_> but the author preferred getting rid of mut altogether
21:23:28 <ais523_> which is massively controversial
21:23:47 <fowl> why? i thought immutability was the tits
21:23:54 <fowl> immutability solves all problems, doesnt it
21:24:06 <kmc> it is an essential part of the way Rust provides memory safety
21:24:14 <ais523_> I guess you could sum the argument up as, uniq lets you do everything that's new in terms of memory safety in Rust
21:24:16 <kmc> so I'm not sure what you'd do in its place, but I didn't read the blog post yet
21:24:22 <ais523_> but it doesn't let you do the stuff that const does in C
21:24:23 <kmc> I guess that's so
21:24:38 <ais523_> or in other words, the post is about capturing the rustiness of immutability
21:24:44 <kmc> Rust doesn't have a way to create immutable objects, anyway -- the mutability of an object depends on how you're accessing it
21:24:47 <ais523_> but loses the non-rust-related benefits
21:24:50 <kmc> so there are mut/immut local variables, and mut/immut pointers
21:24:58 <kmc> but if you own an immut thing you can always make it mut
21:25:27 <kmc> (except for global variables declared with 'static', which are basically constants)
21:26:44 <kmc> you can effectively make an immutable object, though, by putting it in a private struct field and only exposing an accessor that returns an immutable reference
21:26:45 <Taneb> Is there a >>= equivalent for Rust's option?
21:26:52 <kmc> I think it's .chain()
21:26:58 <kmc> there are a bunch of HOFs on Option<T>
21:27:11 <kmc> http://static.rust-lang.org/doc/master/core/option/type.Option.html
21:27:48 <kmc> Rust doesn't have higher-kinded polymorphism :/ so you can't make these generic as in Applicative, Monad, etc.
21:29:56 <shachaf> i want higher-kinded polymorphism :'(
21:30:19 <kmc> the other day I wanted to write a trait with kind (Lifetime -> Type) -> Constraint
21:31:41 <mroman> what the use of freezing a const literal?
21:32:07 <shachaf> by the way did you see that paper i linked here a while ago about rank-n types in languages that try not to box things
21:32:27 <kmc> shachaf: no! sounds interesting
21:32:37 <kmc> mroman: you can pass it to a function that expects &int
21:32:49 <kmc> doesn't have to be a constant either, you can do f(&g())
21:33:10 <kmc> it creates an unnamed temporary variable in the current scope
21:33:18 <fowl> whats the rationale for using a bunch of operators instead of words?
21:33:23 <HackEgo> bin/anonlog bin/etymology bin/log bin/logurl bin/pastalog bin/pastelog bin/pastelogs bin/pastlog bin/randomanonlog bin/searchlog
21:33:33 <ais523_> mroman: same use as (struct foo){.bar = 1}; in C
21:33:34 <shachaf> look all i want is to search logs for something i said recently
21:33:36 <kmc> actually I think it only lasts for the current statement
21:33:57 <kmc> lifetime inference is an example of type inference with subtyping, which means that it's not perfect
21:33:58 -!- nucular has quit (Ping timeout: 240 seconds).
21:34:01 <ais523_> `log <shachaf>.*paper i linked here
21:34:01 <HackEgo> /hackenv/bin/log: 2: cd: can't cd to /var/irclogs/_esoteric \ grep: ????-??-??.txt: No such file or directory
21:34:13 <ais523_> shachaf: except that it doesn't work because HackEgo no longer has a copy of the logs
21:34:53 <Bike> http://i.imgur.com/4VaHgh1.jpg?1 attn
21:35:29 -!- nucular has joined.
21:35:50 <Bike> no, you're allowed to talk about jesus
21:36:06 <kmc> "words or phrases with biblical connotation"
21:36:21 <Taneb> I think I have made a mistake
21:36:40 <Taneb> "Primes.rs:16:19: 16:32 error: borrowed value does not live long enough"
21:37:39 <ais523_> nice when the compiler catches it for you :-)
21:38:28 <Taneb> I can't tell where it's being freed
21:38:59 <ais523_> when the place where it was declared goes out of scope
21:39:50 -!- ais523_ has quit (Quit: Page closed).
21:40:04 <kmc> grr, I have an enum with 6 variants and I want a type which is restricted to 4 of them
21:40:18 <Bike> subtyping........................
21:40:23 <kmc> i wish that kind of thing didn't suck in most langs
21:40:26 <kmc> refinement types could do it
21:40:33 <kmc> i don't like subtyping
21:40:35 <kmc> but it's convenient
21:40:48 <kmc> in this case
21:40:59 <kmc> I could at least write a macro which automates declaration and conversion for the "subtype" enum
21:41:23 <kmc> Rust supports defining macros using arbitrary Rust code, although it's not pretty
21:43:55 <Taneb> Right, I got it to work
21:44:26 <Taneb> By not naming the thing that didn't have enough lifetime?
21:44:32 <Taneb> It was only used once anyway
21:48:13 <shachaf> ais523_-ghost: oh, that explains it
21:48:17 <shachaf> kmc: why don't you like subtyping
21:48:55 <Taneb> Can I get a code review for main()? http://hastebin.com/eduvawahub.rs
21:49:19 <fowl> Rust can't figure out the type
21:49:49 <Taneb> Other than adding more useful comments
21:49:51 <shachaf> kmc: looks like it was http://flint.cs.yale.edu/flint/publications/flex.pdf
21:50:03 <fowl> Taneb, isnt there a constructor you can use there instead
21:50:39 <fowl> Taneb, just Some(..) to construct option<t>
21:51:42 <Taneb> I don't understand
21:52:44 <fowl> Some(4) #=> Option<Int> value of 4
21:52:58 <fowl> you know what a constructor is, stop pulling my chain
21:53:07 <Taneb> Yes, but I don't understand how that helps
21:53:18 <Taneb> I'm getting the Option<uint> from from_str()
21:53:33 <fowl> and you can't omit that?
21:53:34 <shachaf> kmc: i'd suspect that rust cares about runtime representation a bit too much for that kind of trickery
21:54:01 <Taneb> fowl, no, because it can't tell that it's a uint
21:54:18 <fowl> from_str<uint>?
21:55:41 <Taneb> I think I've got it
21:56:20 -!- edwardk has joined.
21:56:45 <kmc> Taneb: one day you will be able to write from_str::<for uint>(...) or so, but that's not much better
21:57:41 <Taneb> I've got from_str::<int>(...)
21:57:57 <HackEgo> [wiki] [[Gentzen]] http://esolangs.org/w/index.php?diff=39542&oldid=39541 * Zzo38 * (+1196)
21:58:03 <kmc> Taneb: instead of long else/if chains I like to do something like match () { _ if x > 49 => ..., _ if is_prime1(x) => ..., }
21:58:08 <kmc> Taneb: oh, does it work now?
21:58:23 <zzo38> How do I get rid of the message at the top of the MediaWiki page that says your edit is saved?
21:58:32 <Bike> that seems like an awkard cond :/
21:58:41 <Bike> "maybe you could write a macro"
21:58:42 <kmc> it's not the best
21:58:46 <kmc> Haskell has the same basic issue
21:58:50 <Taneb> kmc, and I didn't know that guards existed like that
21:59:28 <fowl> from_str::<int> -_-
21:59:38 <fowl> they should have called rust "line noise"
21:59:51 <Bike> https://twitter.com/ibogost/status/467423954328883200/photo/1/large meanwhile in the ACM
22:00:31 <kmc> fowl: nice one
22:00:59 <Bike> maybe you should jokingly name the language after some kind of corrosion, to emphasize how ugly it is,
22:01:30 <kmc> I'm starting to think the real value of fancy movement commands in Vim is for macros
22:02:04 <shachaf> imagine if all programming was like writing vim macros
22:03:29 <zzo38> shachaf: It is why there is many different kind of programming languages, which is so that, it doesn't have to be all programming like writing vim macros.
22:04:07 -!- edwardk has quit (Quit: Computer has gone to sleep.).
22:05:03 <kmc> shachaf: should I feel bad about f(match a { b => return c, d => e })
22:05:58 <fowl> kmc, does that return c/e to the call to f or to the function enclosing it
22:06:50 <Bike> i would hope that it works by either passing e to f, or returning c to the lexically enclosing block without calling f.
22:07:06 <fowl> yea thats what it looks like
22:07:24 <kmc> that's right
22:07:40 <kmc> well, the lexically enclosing function body
22:07:45 <kmc> not necessarily the closest block
22:08:01 <fowl> yes kmc you should feel bad
22:08:05 <kmc> return acts like calling a continuation captured at entry to the function
22:08:09 <kmc> the type of (return x) unifies with anything
22:08:25 <Bike> well i don't know what a "block" is in rust, i'm just using lisp terms because lol.
22:08:30 <Taneb> Programming languages are weird
22:08:38 <shachaf> kmc: imo kind of bad but also kind of good??
22:08:38 <fowl> unifies? meaning what
22:08:50 <kmc> error: cannot bind by-move into a pattern guard
22:08:56 <kmc> that's an interesting one
22:09:01 <fowl> kmc, what do you gain from having the match inside the func call? internet points?
22:09:21 <kmc> there are so many tricky cases that come up with uniqueness / move semantics
22:09:21 <Bike> fowl: type unification
22:09:47 <Bike> fowl: like in pseudo-C since i don't know how rust decls work, "foo x = return bar;" is valid for any type foo.
22:10:04 <kmc> I think it should be safe as long as the bound-by-move variables don't appear in the guard
22:10:07 <kmc> but i'm not sure
22:10:21 <Bike> i've done what kmc's doing before. it's kind of super ugly so i'd feel a bit bad but not enough to change it if that's what i meant
22:10:51 <shachaf> kmc: do you know what happens in ruby when you write something like def foo(); return proc { return 5 }; end
22:10:53 <fowl> buzzwords :rolleyes:
22:11:12 <shachaf> (where the "return" in the proc means "return from foo".)
22:11:29 <kmc> you capture a continuation?
22:11:31 <Bike> "ugly" is a buzzword
22:11:39 <shachaf> you'd hope for that but it's just an error :'(
22:12:21 <Bike> i can understand not wanting to introduce undelimited continuations :V
22:12:32 <shachaf> you wouldn't know when to capture a continuation anyway since everything is all dynamic
22:13:25 <Taneb> I'll say it again.
22:13:30 <shachaf> kmc: shamir's secret sharing is so simple btw
22:13:32 <Taneb> Programming languages are weird.
22:13:43 <shachaf> for some reason i thought it was complicated but it's not
22:16:36 <shachaf> another thing i thought was complicated but isn't: crontab syntax
22:17:12 <kmc> \rainbow{polynomials}
22:17:46 <Bike> hell yeah polynomials
22:17:52 <Bike> does anyone here know about gröbner bases?
22:27:02 <Bike> is anyone here goign to tell me about them
22:28:01 <zzo38> It isn't something I know
22:28:22 <kmc> Bike: i give that about 50/50
22:29:06 -!- Patashu has joined.
22:31:44 -!- hk3380 has joined.
22:32:15 <ion> http://arstechnica.com/tech-policy/2014/05/photos-of-an-nsa-upgrade-factory-show-cisco-router-getting-implant/
22:35:22 -!- FireFly has quit (*.net *.split).
22:35:22 -!- drdanmaku has quit (*.net *.split).
22:35:24 -!- skarn has quit (*.net *.split).
22:35:24 -!- shachaf has quit (*.net *.split).
22:35:24 -!- newsham has quit (*.net *.split).
22:35:25 -!- rodgort has quit (*.net *.split).
22:35:25 -!- erdic has quit (*.net *.split).
22:35:26 -!- myname has quit (*.net *.split).
22:35:43 -!- monotone has quit (*.net *.split).
22:35:43 -!- pdxleif has quit (*.net *.split).
22:35:43 -!- jconn has quit (*.net *.split).
22:35:44 -!- jix has quit (*.net *.split).
22:35:44 -!- trout has quit (*.net *.split).
22:35:44 -!- Speed` has quit (*.net *.split).
22:35:45 -!- lifthrasiir has quit (*.net *.split).
22:35:45 -!- kmc has quit (*.net *.split).
22:36:00 -!- FireFly has joined.
22:36:01 -!- drdanmaku has joined.
22:36:01 -!- skarn has joined.
22:36:01 -!- newsham has joined.
22:36:01 -!- shachaf has joined.
22:36:01 -!- rodgort has joined.
22:36:01 -!- erdic has joined.
22:36:01 -!- myname has joined.
22:36:19 -!- monotone has joined.
22:36:19 -!- pdxleif has joined.
22:36:19 -!- jconn has joined.
22:36:19 -!- jix has joined.
22:36:19 -!- trout has joined.
22:36:19 -!- Speed` has joined.
22:36:19 -!- lifthrasiir has joined.
22:36:19 -!- kmc has joined.
22:39:45 -!- boily has joined.
22:48:07 -!- boily has quit (Quit: Poulet!).
22:51:36 <Bike> someone tell me why i can't find a proof of the poincare bendixson theorem not based on way too many symbols
22:52:01 -!- mhi^ has quit (Quit: Lost terminal).
22:54:02 <Slereah> Because math has a lot of symbols
22:56:58 <ion> Too bad nobody told mathematicians they can use multi-letter words as names.
22:57:29 <Taneb> help "error: binary operation `*` cannot be applied to type `&&uint`"
22:57:31 <ion> For some reason they ended up using “sin”, “cos”, “lim” etc. though.
22:57:54 <monotone> But then how would we know that "dim" isn't d*i*m???? Panic would reign!
22:58:30 <ion> We have this technology called “whitespace”
22:58:47 <Taneb> `unicode INVISIBLE TIMES
22:59:01 <Taneb> See, there's even a unicode character to represent multiplication that style!
22:59:07 <ion> Not to be confused with
22:59:10 <ion> `unicode INVISIBLE PLUS
22:59:14 <HackEgo> [U+200B ZERO WIDTH SPACE] [U+2062 INVISIBLE TIMES]
22:59:18 <kmc> invisible plus is visible for me
22:59:20 <zzo38> They ended up using "sin", "cos", "lim" because when Feynman used various strange symbols to mean them instead, everyone else got confused and didn't understand it.
22:59:40 <Bike> i'm uh, pretty sure those symbols predate feynman
22:59:54 <kmc> which symbols are those?
22:59:55 <Slereah> There's plenty of multisymbol math words : http://us.metamath.org/mpeuni/mmdefinitions.html
22:59:58 <Bike> and no i'm pretty sure nobody will ever be confused if iuse psi to indicate orbits and phi to indicate the transition function, what could possibly go wrong
23:00:02 <Taneb> Did you know that the "=" symbol was invented in Wales?
23:00:14 <Slereah> ⊢ RingOps = {<.g, h>. ∣ ((g ∈ AbelOp ∧ h:(ran g × ran g)–→ran g) ∧ (∀x ∈ ran g∀y ∈ ran g∀z ∈ ran g(((xhy)hz) = (xh(yhz)) ∧ (xh(ygz)) = ((xhy)g(xhz)) ∧ ((xgy)hz) = ((xhz)g(yhz))) ∧ ∃x ∈ ran g∀y ∈ ran g((xhy) = y ∧ (yhx) = y)))}
23:00:19 <ion> taneb: Yeah, by Feynman himself!
23:00:21 <Bike> this is sick, Slereah
23:00:27 <zzo38> One thing is you can affect italic and roman text, so that variables are in italics and keywords in roman type.
23:00:32 <Bike> and not east coast sick.
23:00:37 <kmc> douglass1 has a story about a textbook that used v, ν, and script ν to mean different things
23:01:00 <Bike> ugh is that the greek thingie
23:01:02 <maurer> ...I think I might have taken that class, but don't remember hwat it was
23:01:03 <Slereah> Textbooks commonly use bold to mean vectors
23:01:05 <Bike> i will destroy greek
23:01:19 <Bike> Greeks can use it, I guess
23:01:21 <Bike> right out for everyone else
23:01:25 <Slereah> ⊢ DIsoH = (k ∈ V ↦ (w ∈ (LHyp ‘k) ↦ (x ∈ (Base ‘k) ↦ if(x(le ‘k)w, (((DIsoB ‘k) ‘w) ‘x), (℩ u ∈ (LSubSp ‘((DVecH ‘k) ‘w))∀q ∈ (Atoms ‘k)((¬ q(le ‘k)w ∧ (q(join ‘k)(x(meet ‘k)w)) = x) → u = ((((DIsoC ‘k) ‘w) ‘q)(LSSum ‘((DVecH ‘k) ‘w))(((DIsoB ‘k) ‘w) ‘(x(meet ‘k)w)))))))))
23:01:36 <Bike> cool story bro
23:01:46 <kmc> cool theorem bro
23:02:06 <Slereah> Apparently that is the definition of an isomorphism H
23:02:16 <ion> cool bro bro
23:05:30 -!- ^v has quit (Quit: http://i.imgur.com/Akc6r.gif).
23:10:52 <Bike> man if the annoying rust error is lifetime failure rather than segfaults i'm fucking sold
23:12:54 <zzo38> I have some pinball game in computer, which has seven holes for the ball to drain, instead of just one. One is worth nothing, Two are worth fifth points each, two are worth one hundred points, and two of them cause instantly game over even if you have more balls to play.
23:15:55 -!- oerjan has joined.
23:20:11 -!- Sgeo has joined.
23:21:47 <douglass1> actually it's not that much of a story. I did drop a class when they did basically the same thing on the board, with three kinds of epsilon in the same equation, distinguished by slightly different levels of curliness
23:22:02 <douglass1> confusion at nu was too common to even remark on
23:22:57 <Taneb> douglass1, oh god, if I was leading that class...
23:23:09 <Taneb> (I have the worst handwriting when I'm not thinking about it)
23:23:25 <Taneb> (I used to write my ns and as really similar
23:23:25 <douglass1> they let me take the actual physics version instead for the same major requirement. SO MUCH BETTER.
23:24:16 <douglass1> whereas nu you're kind of stuck with anywhere you're doing spectroscopy and it's not just that the particular lecturer or text sucks
23:24:51 <Phantom_Hoover> i'd a lecturer this year who wrote his rs like an n, his ns like an m, and his m like some kind of weird mutant letter
23:24:58 <Taneb> I have the suspicion I'm trying to do something horrible with this code
23:25:20 <kmc> Servo does segfault sometimes :/
23:25:22 <kmc> less often than it used to
23:25:27 <Bike> is q qauantitative or quantum
23:25:27 <kmc> it contains a fair amount of unsafe code, for various reasons
23:25:37 <Phantom_Hoover> last year we had one who wrote beta the same way as b (he was greek, too) and labelled a series of vectors v1,v2,...wn
23:26:15 <Bike> suddenly mysteriously glad i haven't taken a math(y) class in years
23:27:40 <Phantom_Hoover> in a similar vein the geometry lecturer just used the board as a substitute for his short-term memory, writing disjointed fragments hither and thither with no actual structure
23:28:10 <Taneb> How horrible is in Rust having a function that returns a closure that's captured an (otherwise inaccessible) vector?
23:28:48 <Taneb> And then mutates the vector potentially each time it's called
23:29:11 <Bike> how do you have a quantum chemistry class without actual physics...
23:29:19 <Bike> is this like how everybody is afraid to tell me what a d orbital looks like
23:29:34 <Taneb> Actually, I could make it a lot less horrible... but a lot less safe?
23:29:51 <Bike> the knowledge could quite possibly DRIVE YOU INSANE
23:30:57 <zzo38> Does Wikipedia have any description/diagram to tell you what a d orbital looks like?
23:31:17 <Bike> http://en.wikipedia.org/wiki/File:D_orbitals.svg
23:31:22 <zzo38> Actually I think I remember seeing all of the orbitals in some book.
23:32:06 <Bike> it has pictures of the f orbitals, too, ones in actually existent atoms anyway
23:35:33 <Bike> i asked my orgo prof where i could learn quantum and she basically said not to, so, i don't know what chemistry's deal is
23:35:54 -!- ^v has joined.
23:39:53 -!- boily has joined.
23:40:05 -!- yorick has quit (Remote host closed the connection).
23:41:58 -!- nooodl has quit (Quit: Ik ga weg).
23:42:14 -!- nooodl has joined.
23:44:47 <zzo38> Can I make infinite loops out of continuations and avoid a infinite loop operator?
23:45:23 <Bike> presumably you'd need a continuation that continuates to itself? sounds like fix
23:45:45 <shachaf> ((call/cc call/cc) (call/cc call/cc))
23:46:36 <zzo38> Assume you have law of excluded middle continuations
23:46:44 <zzo38> But, I suppose you may be correct
23:46:56 -!- Patashu has quit (Disconnected by services).
23:46:56 -!- Patashu_ has joined.
23:47:12 <shachaf> you can't do it with haskell-style callCC, of course
23:47:22 <boily> quintopia: IEUAAAAAAAAAAAAAAAAAAAH!
23:48:34 <shachaf> you can do it with this handy operator, though:
23:48:41 <shachaf> @let getCC = callCC (return . fix)
23:48:42 <lambdabot> No instance for (MonadCont m0) arising from a use of ‘callCC’
23:48:42 <lambdabot> The type variable ‘m0’ is ambiguous
23:48:42 <lambdabot> Relevant bindings include getCC :: m0 (m0 b) (bound at .L.hs:158:1)
23:48:42 <lambdabot> Note: there are several potential instances:
23:48:50 <kmc> if I optimize something to the point where Rust's benchmarker reports "0 ns/iter", what % improvement do I report
23:49:03 <shachaf> @let getCC :: MonadCont m => m (m a); getCC = callCC (return . fix)
23:49:22 <shachaf> int-e: The monomorphism restriction is turned on for lambdabot?
23:49:50 <kmc> lambdabot is turned on by the monomorphism restriction?
23:49:54 <Bike> :t return . fix
23:51:07 <lambdabot> MonadCont m => ((a -> m b) -> m a) -> m a
23:59:22 <oerjan> > let getCC = callCC (return . fix) in getCC
23:59:23 <lambdabot> No instance for (GHC.Show.Show (m0 (m0 b0)))
23:59:23 <lambdabot> arising from a use of ‘M108163792579395769929310.show_M1081637925793957699...
23:59:23 <lambdabot> The type variables ‘m0’, ‘b0’ are ambiguous
23:59:23 <lambdabot> Note: there are several potential instances:
23:59:23 <lambdabot> instance [safe] GHC.Show.Show a =>
23:59:57 <oerjan> > let getCC = callCC (return . fix) in "hi"
00:00:17 <oerjan> shachaf: this may be the same problem with @let we discussed the other day
00:01:00 <oerjan> it passes things through Lang.Haskell.something without extensions set
00:02:07 <boily> quelqun_dautre: bonsoir. es-tu quelqu'un d'autre?
00:02:42 <oerjan> int-e said it might be easy to fix, but not before the weekend.
00:03:34 <oerjan> or wait, can it be that, doesn't that phase only do parsing
00:03:38 <shachaf> is it like a werewolf sort of bug
00:06:07 <oerjan> shachaf: it does two checks, the first only on the given declaration, then in L.hs context
00:12:49 -!- tromp has joined.
00:12:50 <douglass1> by "actual physics" I meant "run by the physics department." the chem department's version did indeed contain physics
00:14:42 -!- edwardk has joined.
00:22:01 <Bike> my chem manual last term had instructions on how to read a graph of a line, so i'm a bit skeptical of chemphysics now
00:24:10 -!- shikhout has joined.
00:27:29 -!- shikhin has quit (Ping timeout: 252 seconds).
00:32:41 -!- tromp has quit (Ping timeout: 264 seconds).
00:43:03 -!- hk3380 has quit (Ping timeout: 265 seconds).
00:50:38 -!- edwardk has quit (Ping timeout: 240 seconds).
01:01:24 -!- tromp has joined.
01:02:24 -!- edwardk has joined.
01:05:23 -!- edwardk has quit (Client Quit).
01:06:07 -!- edwardk has joined.
01:08:05 -!- tromp has quit (Ping timeout: 264 seconds).
01:20:12 <boily> AAAAAAAAAAAAAURGH! why. why is my neighbour vacuum cleaning for at least the third time tonight...
01:22:53 -!- edwardk has quit (Quit: Computer has gone to sleep.).
01:25:53 <oerjan> boily: it's the hygiene singularity approaching hth
01:28:20 -!- edwardk has joined.
01:29:08 <boily> I don't care about Approaching Singular Hygienes. I just want to be able to induce something that may resemble sleep on my person.
01:32:05 -!- Phantom_Hoover has quit (Quit: Leaving).
01:37:47 -!- hk3380 has joined.
01:39:04 <zzo38> The saving throws for healing spells in Dungeons&Dragons are not symmetric!
01:40:41 <zzo38> (Specifically, the saving throw is different for living and undead targets.)
01:41:11 <zzo38> More symmetric probably would be if the saving throw is the same except for the "(harmless)" marker.
01:47:45 -!- boily has quit (Quit: RECUUMED CHICKEN).
01:56:49 -!- edwardk has quit (Ping timeout: 258 seconds).
02:06:37 <zzo38> How well does keyless RC4 pass randomness tests?
02:15:49 -!- oerjan has quit (Quit: Nite).
02:16:38 <monotone> Do you mean RC4 without a stream key?
02:17:57 <monotone> The output would be deterministic at that point, no?
02:18:14 -!- mekeor` has joined.
02:18:45 <zzo38> Yes, although it could still be tested
02:19:03 -!- mekeor has quit (Ping timeout: 252 seconds).
02:19:17 <monotone> From a cryptographic standpoint, that wouldn't make much sense.
02:19:25 <zzo38> You can then add a key if you want it not to be the same each time, but make it the same for the same key.
02:20:01 <zzo38> SQLite uses RC4 with a 256-byte key for its random number generator.
02:20:14 <monotone> Yes, that's the idea of the key with all stream ciphers.
02:21:35 <zzo38> SQLite obtains the key from the VFS implementation, and is intended not to ever use the same key, although it is possible to do so.
02:21:43 <monotone> I don't think you can meaningfully define "random-looking" without a key, though.
02:22:12 <zzo38> Famicom Hangman does not use a key, but it generates a new random number several times per frame and normally ignores the result.
02:22:39 <zzo38> (It only uses the result when the space-bar is held down)
02:23:45 -!- Sorella has quit (Quit: It is tiem!).
02:24:21 <zzo38> How well do you expect that to work?
02:25:52 <monotone> If you just need something that looks kinda random then, hey, you can't do worse than Pokémon.
02:25:58 <zzo38> Well, it is a hangman game.
02:28:20 <monotone> RC4 is probably overkill for that unless your answers are TLS streams.
02:34:19 <zzo38> Another thing I wanted to use is to generate random booster packs (such as for Limited tournaments in Magic: the Gathering). In such a case there would be a key, but if one is not explicitly specified, it could be generated automatically using date/time and other things.
02:34:51 <zzo38> If you have 100 choices, you might use 7-bits and then if the result exceeds 99, you can try again until it doesn't exceed 99.
02:35:52 <zzo38> (At least, it is what I have implemented in any program which I implement a random number algorithm; I don't know how common it is.)
02:46:36 <kmc> RC4 is a shitty RNG
02:47:04 <kmc> it has hella biases
02:47:32 <kmc> http://en.wikipedia.org/wiki/RC4#Security
02:47:49 <kmc> most egregiously "the second output byte of the cipher was biased toward zero with probability 1/128 (instead of 1/256)"
02:48:02 <kmc> so no, it's not even suitable for non-cryptographic uses
02:48:26 <zzo38> It is commonly used though, it seems
02:49:39 <zzo38> Even without the modifications, although there are many modifications that are used too, such as skipping a lot of the start of the output, and/or modifying the key scheduling algorithm to run a large number of times, etc
02:50:54 <Bike> can't you just use an actual prng
02:55:34 <zzo38> It would seem clear now that RC4 is no good if used plainly, at least; you would have to use carefully. Actually any algorithm should be used carefully but RC4 has some specific weaknesses to consider.
02:57:04 <zzo38> I would think any algorithm you are encrypting something with, you may want to compress it first, using a compression algorithm without headers and so on; you can even use especially what is known based on what kind of messages they are, for example if it is ASCII text one simple thing you can do is just ignore the bit7 of the results.
03:09:41 <zzo38> One thing you can do with any algorithm, assuming the messages do not get lost, is the message, once decrypted, contains a key for next message, or some part of the key.
03:10:40 <zzo38> You can also pad messages and add random junk inside of some parts and so on.
03:12:36 <zzo38> For example, an attacker who knows that the message contains "Meet Jane and me tomorrow at 3:30 pm" at a particular point can recover the keystream at that point from the ciphertext and plaintext. Then the attacker can replace the original content with any other content of exactly the same length, such as "3:30 meeting is cancelled, stay home" by encrypting it with the recovered keystream, without knowing the encryption key.
03:12:53 <zzo38> If you add random junk inside of the message then you can avoid such a thing.
03:27:30 <zzo38> I read about steganography (possibly in combination with encryption), and even about encoding the text inside of a diagram of a flower, or in music, or something. Once someone blink their eye by a Morse code. Once I tried to use a coughing code to give the answers to a test (simply to see if I could).
03:35:54 -!- Bike has quit (Ping timeout: 245 seconds).
03:40:40 -!- nucular has quit (Quit: Excess Food).
03:52:41 <zzo38> Another thing I thought of is to use a deck of cards, in combination with a book describing the rules for some card game (the game described having nothing to do with the encryption).
03:54:38 <zzo38> As well as sudoku (something described in Wikipedia), chess problems, astrology, and other things.
03:55:16 <zzo38> Or in a game played at a chess tournament...
03:55:25 -!- shikhout has quit (Ping timeout: 265 seconds).
03:56:56 <zzo38> Have these been done?
04:06:53 -!- hk3380 has quit (Ping timeout: 264 seconds).
04:10:10 <zzo38> I have used the following program to test the randomness of SQLite: create table d(v int); insert into d(v) with x(x) as (select 0 union all select x+1 from x where x<10000) select random('4d6dl') from x; select v, count() from d group by v order by v; What should be the proper probabilities of 4d6 drop-lowest having each total?
04:28:52 <zzo38> Maybe ten thousand samples would not be sufficient?
04:34:16 -!- Bike has joined.
04:44:28 <kmc> this is probably going to be one of those nights where I get really drunk and start writing weird / emo things on irc
04:44:32 <kmc> just letting you all know ahead of time
04:46:18 <kmc> fungot: are you ready
04:46:18 <fungot> kmc: hills; and even such whispers admitted that there was a long and close correspondence with carter had a still more mysterious realm where everything is white, and where the old chief fnord, they said, was the
04:50:05 -!- trout has changed nick to variable.
04:50:08 -!- variable has changed nick to constant.
04:50:11 -!- constant has changed nick to function.
04:58:38 <fowl> classic carter
04:59:28 -!- fowl has quit (Remote host closed the connection).
05:00:40 -!- fowl has joined.
05:00:42 <Sgeo> http://www.reddit.com/r/ideasfortheadmins/comments/25rcsz/allow_moderators_of_subreddits_to_see_ipuseragent/ am I mistaken in what I posted?
05:05:05 <Bike> "I assume that there would be fewer hashes than IP addresses" seems weird
05:09:38 <Bike> md5 hashes are 128 bits, so the same length as v6.
05:10:22 <Bike> "if the algorithm is public" etc. is a basic standard for crypto, all the good algorithms are open, you know that.
05:11:30 -!- function has changed nick to variable.
05:13:13 <Bike> ooh hey, SHA2 can do up to 512.
05:15:53 <Bike> anyway this system obviously wouldn't much help against a half-savvy spammer, they'd just restart DHCP.
05:17:41 <kmc> SHA-256, SHA-384, SHA-420
05:20:11 <newsham> birthday attacks around 2^1.5
05:20:29 <Bike> so like, three?
05:21:01 <Bike> You could just say three.
05:21:27 <newsham> dont accept every two bit hash you come across
05:22:53 <Bike> oh, you meant sha-3 as a three bit hash, not "the third SHA", which it atually is.
05:26:38 -!- nooodl has quit (Read error: Connection reset by peer).
05:41:24 -!- drdanmaku has quit (Quit: Connection closed for inactivity).
05:42:21 <Bike> yeah beyond me
06:00:03 -!- ^v has quit (Quit: http://i.imgur.com/Akc6r.gif).
06:39:30 -!- edwardk has joined.
06:56:33 -!- edwardk has quit (Quit: Leaving...).
06:57:08 -!- edwardk has joined.
07:08:34 -!- Bike has quit (Ping timeout: 240 seconds).
07:19:58 <HackEgo> ringcoin yabucoin retacoin dumbermiprelytinecoin duerecoin boulcoin madcoin frackledcoin cthcoin fettecoin brucoin quidcoin mkbcoin twingcoin magecoin mekacoin tunecoin ijulicoin reulcoin crainfusiccoin
07:22:51 -!- password2 has joined.
07:39:33 <Jafet> ringcoin http://www.youtube.com/watch?v=548qCuDHe_Q
08:15:31 <HackEgo> [wiki] [[Forobj]] http://esolangs.org/w/index.php?diff=39543&oldid=39505 * GermanyBoy * (+92)
08:16:18 <HackEgo> [wiki] [[User:GermanyBoy]] N http://esolangs.org/w/index.php?oldid=39544 * GermanyBoy * (+58) Created page with "Hello! == My languages == === Esoteric === * [[Forobj]]"
08:57:05 <kmc> http://regmedia.co.uk/2014/05/16/0955_peter_gutmann.pdf "It’s probably at least some sort of sign of the end times when your conference badge has a rootkit"
09:31:52 -!- conehead has quit (Quit: Computer has gone to sleep).
09:36:29 -!- edwardk has quit (Quit: Computer has gone to sleep.).
09:37:17 -!- nooodl has joined.
09:42:23 -!- nooodl has quit (Ping timeout: 255 seconds).
09:43:52 -!- nooodl has joined.
09:47:14 -!- Slereah_ has joined.
09:49:51 -!- Slereah has quit (Ping timeout: 258 seconds).
09:56:33 -!- Phantom_Hoover has joined.
10:02:37 -!- MoALTz has joined.
10:30:54 -!- Frooxius has quit (Ping timeout: 245 seconds).
10:40:20 -!- edwardk has joined.
10:51:42 <mroman> "Exploit backwards-compatibility support in the CPU for bugs dating back to the 80286" sweet :)
10:52:22 <mroman> but what he's mostly saying is "physical access to a machine is enough"
10:57:01 <Slereah_> The NSA will look at it and go "Man fuck that"
11:02:43 -!- mhi^ has joined.
11:09:43 <mroman> "I love crypto, it tells me what part of the system not to bother attacking"
11:10:21 <Slereah_> Well some crypto is easy to attack
11:10:26 <nortti> http://regmedia.co.uk/2014/05/16/0955_peter_gutmann.pdf "It
11:11:14 <mroman> I had this idea for a secure key transmission protocol
11:11:42 <mroman> Alice want's to transmit m, so she chooses a and r
11:11:54 <mroman> she transmits m+a `mod` r
11:12:04 <mroman> bob receives it and chooses b and sends m+a+b `mod` r
11:12:09 <Slereah_> That's why physics is way better than cryptography
11:12:20 <Slereah_> In cryptography, Alice is always sending shit to bob
11:12:23 <mroman> alice receives it, subtracts her a and sends back m+a+b-a `mod` r
11:12:37 <mroman> bob subtracts his b again m+a+b-a-b `mod` r == m
11:13:08 <mroman> little that you know that you can just calculate b as (m+a+b)-(m+a)
11:26:35 -!- yorick has joined.
11:32:35 -!- hk3380 has joined.
11:32:39 -!- password2 has quit (Ping timeout: 265 seconds).
11:58:52 -!- oerjan has joined.
12:06:53 -!- MoALTz has quit (Quit: Leaving).
12:16:52 -!- nucular has joined.
12:18:17 <HackEgo> [wiki] [[Language list]] M http://esolangs.org/w/index.php?diff=39545&oldid=39533 * Oerjan * (+0) /* O */ rder
12:25:03 <Taneb> > maxBound :: Word
12:26:53 <HackEgo> [wiki] [[Special:Log/newusers]] create * Luiji * New user account
12:28:09 <lambdabot> MonadState s m => (s -> s) -> m ()
12:29:06 <HackEgo> [wiki] [[List of ideas]] http://esolangs.org/w/index.php?diff=39546&oldid=39457 * Luiji * (+198) /* Joke/Silly Ideas */ commented on the final fantasy idea
12:29:22 <HackEgo> [wiki] [[Owhelgossip]] http://esolangs.org/w/index.php?diff=39547&oldid=39532 * Oerjan * (+34) formatting
12:29:31 <lambdabot> MonadState s m => (s -> s) -> m ()
12:29:33 <int-e> shachaf: lambdabot has the monomorphism restriction turned off, but there was not {-# LANGUGAE NoMonomorphismRestriction #-} in L.hs.
12:34:10 <int-e> FreeFull: "dmr" = "dreaded monomorphism restriction"
12:34:30 <FreeFull> Too bad it's in the language spec
12:34:36 <int-e> (it's dreaded mainly because it leads to obscure type errors)
12:42:13 -!- shikhin has joined.
12:47:32 -!- nooodl has quit (Read error: Connection reset by peer).
12:48:09 -!- nooodl has joined.
12:48:53 -!- password2 has joined.
12:49:09 -!- MindlessDrone has joined.
12:57:58 -!- MoALTz has joined.
13:04:52 <HackEgo> [wiki] [[List of ideas]] http://esolangs.org/w/index.php?diff=39548&oldid=39546 * 188.120.201.244 * (+111)
13:22:54 -!- password2 has quit (Ping timeout: 240 seconds).
13:30:18 -!- idris-bot has quit (Ping timeout: 240 seconds).
13:31:12 -!- Melvar` has joined.
13:31:14 -!- Melvar has quit (Ping timeout: 240 seconds).
13:31:26 -!- Melvar` has changed nick to Melvar.
13:35:52 -!- password2 has joined.
13:36:32 -!- nucular_ has joined.
13:36:37 -!- password2 has quit (Max SendQ exceeded).
13:36:41 -!- nucular has quit (Ping timeout: 276 seconds).
13:37:03 -!- nucular_ has changed nick to nucular.
13:37:07 -!- nucular has quit (Changing host).
13:37:07 -!- nucular has joined.
13:37:11 -!- password2 has joined.
13:46:02 -!- boily has joined.
13:54:24 <Taneb> HELP I AM BOOKING A HOTEL FOR AN ANIME CONVENTION
13:54:34 <Taneb> I HAVE SIMULTANEOUSLY GAINED AND LOST CONTROL OF MY LIFE
13:55:00 <Taneb> That is, I'm going to attend an anime convention nearby
13:55:07 <HackEgo> Arrows are just strong monads in the category of profunctors.
13:56:14 <boily> Taneb: TANELLE. THIS IS GOOD FOR YOU. HAVE YOU EVER ATTENDED AN ANIME CONVENTION BEFOREHAND, AND/OR MITIGATED YOUR LIFE CONTROL?
13:56:27 <Taneb> I have attended one before (it was this one last year)
13:56:36 <Taneb> But that time I stayed at a friend's house
14:00:42 <impomatic> Is there anyone who's got a minute to read / comment on some text for a banner? If so, I'll /msg the link
14:01:32 <quintopia> a real banner or a web page advertisement?
14:02:26 -!- Slereah has joined.
14:02:36 <boily> quintopiaaaaaaaaaaaaaaaaaah!
14:03:06 <quintopia> boily: you never explained what exactly i would need to do to move (temporarily) to canada and work
14:03:13 <oerjan> exclamation points!!!!!!!!!!!!!!!!!!
14:05:05 -!- Slereah_ has quit (Ping timeout: 240 seconds).
14:05:44 <boily> quintopia: eh... as a whole, I think you need «une conjointe», some family, a referral, a job contract or something else to that same effect.
14:06:54 <boily> quintopia: fr:conjointe → en:de facto spouse.
14:07:28 <boily> our Fine Government wants either families or workers in a plug'n'play state.
14:10:47 <boily> quintopia: you could try workopolis → http://www.workopolis.com/rechercheemploi/trouver-emplois#pt=%257C2%257C&lg=FR&l=%257Cmontreal%252Cquebec%257C&pr=-1
14:10:57 <Taneb> boily, what if I have an Australian citizenship
14:11:13 <boily> Taneb: eh... is Australia part of the Commonwealth?
14:11:35 <boily> quintopia: that's where I found my current job. (previous one was through internships, so I can't really help you there.)
14:11:57 <boily> Taneb: besides, you're a UK resident, so you're already commonwealthian.
14:12:14 <Taneb> Australia sometimes has nicer treaties
14:12:24 <boily> I guess it'd be /slightly/ easier for Taneb to apply for a Canadian job.
14:13:10 <Taneb> I know it's easier to get a job in the US as an Australian than it is as a Brit
14:13:16 <boily> quintopia: Banque Nationale and Desjardins are booming right now. if you could land something with them, it'd be a nice cushiony job.
14:13:55 <boily> that's exactly what they need right fungotting now.
14:13:55 <fungot> boily: his daughter, the dawn is nigh, though only about two feet tall, paved with octagonal blocks and solidly vaulted overhead. there would he ever say he once dwelt as a prince, though here we knew him from his birth though he thought himself a king's son. he was pulled out of bed and into empty space. again the fnord of
14:15:01 <boily> fungot, the father of the Dwarven Octagonal Block Vaulting Champion.
14:15:01 <fungot> boily: tried to keep the guards in shape and size, and weathered and pitted to the very confines of infinity.
14:15:05 <Taneb> Not that I have any need or desire to work in Canada right now
14:15:14 <Taneb> What with being on the first year of a degree
14:17:54 <quintopia> i've got a chunk missing from my number 9 incisor that is what i need fixed right fungotting now
14:17:54 <fungot> quintopia: trapped though he was, however, are of the keenest interest and poignancy; suggesting with marvelous force the imminence of nameless terrors, and how taran-ish had died from fear and left a dead village whose corpses were horribly mangled, chewed, and clawed.
14:20:58 * boily twitches. “it's tooth number 21, not 9!”
14:25:48 <fungot> Available: agora alice c64 ct darwin discworld enron europarl ff7 fisher fungot homestuck ic irc iwcs jargon lovecraft* nethack oots pa qwantz sms speeches ss wp youtube
14:26:14 <fungot> Selected style: qwantz (Dinosaur Comics transcriptions 2003-2011)
14:26:27 <oerjan> fungot: you need to balance the darkness
14:26:28 <fungot> oerjan: t-rex, i have big news the other is a sad realization i always sort of a first world problem, yes, that language is good for domain-specific solutions, but it doesn't make me less of a man!
14:41:37 <quintopia> boily: do you guys number them differently?
14:46:07 -!- Frooxius has joined.
14:48:17 -!- hk3380 has quit (Ping timeout: 264 seconds).
14:52:17 -!- Patashu_ has quit (Ping timeout: 240 seconds).
14:54:41 <zzo38> I don't expect octagonal blocks to tile.
14:55:12 <boily> quintopia: we number them ISO style → http://en.wikipedia.org/wiki/Dental_notation
14:55:18 <boily> zzo38: you lack imagination.
14:55:38 <zzo38> (unless you put squares in between, too)
14:56:33 <quintopia> oh the iso system does seem fairly sane
14:56:45 <int-e> zzo38: how about non-convex octagons...
14:57:00 <quintopia> too bad my dentists would get confused if i said 21 (that's not even an incisor in the universal system)
14:57:07 <int-e> that or hyperbolic geometry
14:57:44 <zzo38> int-e: O, I forgot... I suppose especially if they are many different shapes of octagons; and, yes different kind of geometry too (at least, geometry is one thing I did think of)
14:58:38 <quintopia> zzo38: what about infinite regress octagonal fractal tiling
14:58:52 <zzo38> I don't know what that is.
14:59:17 <quintopia> you tile the plane with octagons. then you fill the spaces between them with octagons
14:59:19 <int-e> zzo38: but if you allow them to have different shapes then it becomes almost trivial.
14:59:31 <boily> quintopia: in our software, we have a tooth number class, with methods to get the international and American numbers.
14:59:39 <zzo38> int-e: Yes I know that
14:59:53 <int-e> heh. is a square removed from a square an octagon? it has 8 corners, 4 outside, 4 inside...
15:00:20 <zzo38> (and you can fill a shape with triangles of different shapes too)
15:03:07 <boily> int-e: ianam, but no.
15:03:40 <zzo38> int-e: I don't think so; I count nine sides. Still I don't really know.
15:05:02 <int-e> boily: I agree, but I found the thought amusing.
15:05:44 <boily> it's like a car has eight wheels. two in front, two in the back, two left and two right :D
15:07:16 <zzo38> I also count twelve corners in the shape described.
15:07:47 <zzo38> I am probably both wrong, though.
15:08:12 <int-e> zzo38: http://int-e.eu/~bf3/tmp/tile.png is what I had in mind when I mentioned non-convex octagons
15:10:14 <quintopia> boily: oh you work with dental. i forgot
15:11:29 <ion> http://i.imgur.com/jmgzg0w.png
15:11:35 <int-e> I guess the square with a square hole is, as a polygon, a degenererated decagon (with two coincident edges connecting an outside corner to an inside corner)
15:11:55 <Taneb> ion, I am pretty sure that a number of those characters are not ASCII
15:12:26 -!- alone has changed nick to syndrome.
15:12:27 <Jafet> It seems to be possible to get six, eight, nine or twelve sides, but no others.
15:13:08 <boily> ion: oh. ooooooooh...
15:13:45 <int-e> Jafet: sides for what?
15:17:22 <Jafet> A polygon obtainable by removing a square from a square.
15:18:02 <Jafet> Actually, only six, eight or nine.
15:20:28 <int-e> ok, I see what you mean
15:22:02 <int-e> when you had 12 you should also get 10 (with two corners of the inner square touching the sides)
15:24:22 <Jafet> One of the sides is not necessary, so it should not be counted.
15:35:02 -!- shikhout has joined.
15:35:40 -!- boily has quit (Quit: BROTHABLE CHICKEN).
15:38:01 -!- shikhin has quit (Ping timeout: 252 seconds).
15:39:50 -!- Melvar has quit (Ping timeout: 258 seconds).
15:41:54 -!- Melvar has joined.
15:49:41 -!- hk3380 has joined.
15:50:41 -!- password2 has quit (Ping timeout: 240 seconds).
15:57:58 -!- Bike has joined.
16:00:47 <ion> Phantasy Star Online (Japanese: ファンタシースターオンライン Hepburn: Fantashī sutā Onrain
16:03:38 -!- oerjan has quit (Quit: Marufelusu).
16:09:11 -!- password2 has joined.
16:09:52 -!- password2 has quit (Max SendQ exceeded).
16:10:10 -!- MoALTz has quit (Quit: Leaving).
16:10:36 -!- password2 has joined.
16:11:30 -!- password2 has quit (Max SendQ exceeded).
16:12:11 -!- password2 has joined.
16:14:09 -!- password2 has quit (Max SendQ exceeded).
16:15:16 -!- shikhout has changed nick to shikhin.
16:17:42 -!- password2 has joined.
16:18:33 -!- password2 has quit (Remote host closed the connection).
16:20:03 <Sgeo> https://www.youtube.com/watch?v=SOD7Ni_3NIc
16:20:31 <Sgeo> So, they're doubling this guy's health repeatedly, but in the middle someone adds a +3 to that characters health, which totally ruins the pretty numbers imo :(
16:21:55 <Sgeo> Actually, I think that +3 didn't register, hmm
16:27:51 -!- Sorella has joined.
16:32:51 <int-e> Nice 32 bit integer overflow though.
16:39:25 -!- MoALTz has joined.
16:53:11 <HackEgo> [wiki] [[PHL 1.0]] N http://esolangs.org/w/index.php?oldid=39549 * GermanyBoy * (+2094) Created page with "'''Proceed High Language 1.0''' (also known as '''PROCEED''') is an esoteric programming language created by [[user:GermanyBoy]] in 2012. == Syntax == PHL 1.0 is based on su..."
17:00:22 <HackEgo> [wiki] [[PHL 1.0]] http://esolangs.org/w/index.php?diff=39550&oldid=39549 * GermanyBoy * (+533)
17:02:16 -!- edwardk has quit (Quit: Computer has gone to sleep.).
17:03:58 <HackEgo> [wiki] [[User:GermanyBoy]] http://esolangs.org/w/index.php?diff=39551&oldid=39544 * GermanyBoy * (+14)
17:04:42 <HackEgo> [wiki] [[Language list]] http://esolangs.org/w/index.php?diff=39552&oldid=39545 * GermanyBoy * (+14) /* P */
17:07:36 <ion> LibreSSL – An OpenSSL replacement. The first 30 days, and where we go from here. http://www.openbsd.org/papers/bsdcan14-libressl/mgp00001.html
17:10:46 <Bike> ebcdic support, lol
17:11:52 -!- boily has joined.
17:19:47 <HackEgo> [wiki] [[PHL 1.0]] http://esolangs.org/w/index.php?diff=39553&oldid=39550 * GermanyBoy * (+951)
17:20:17 <ion> http://image.gamespotcdn.net/gamespot/images/2002/vgnews/052802/gc_keyboard_790screen001.jpg
17:23:48 <HackEgo> [wiki] [[PHL 1.0]] http://esolangs.org/w/index.php?diff=39554&oldid=39553 * GermanyBoy * (+64)
17:29:56 -!- password2 has joined.
17:31:04 -!- password2 has quit (Client Quit).
17:36:53 -!- mhi^ has quit (Ping timeout: 264 seconds).
17:37:25 -!- mhi^ has joined.
17:39:23 -!- nooodl has quit (Ping timeout: 252 seconds).
17:41:38 -!- mhi^ has quit (Ping timeout: 240 seconds).
17:42:39 -!- mhi^ has joined.
17:44:49 -!- mhi^ has quit (Client Quit).
17:47:53 -!- KingOfKarlsruhe has joined.
17:48:46 <zzo38> Which PC motherboards includes a Forth system (or BASIC or assembler) in BIOS so that it can boot without an operating system?
17:49:20 <nortti> the original PC, at least
17:50:16 <zzo38> Better is if, such a thing also includes command for CMOS setting and for internet connection and serial port, so it is still possible to use it as a simple telnet client or terminal to directly connected equipment, and using for downloading an operating system using internet.
17:50:17 <nortti> if there ever were PCs with open firmware those'd have forth
17:50:34 <zzo38> Is Open Firmware compatible with the PC BIOS, though?
17:50:55 <zzo38> Then it isn't much PC.
17:50:56 <nortti> but one could've simulated it, like EFIs do
17:53:05 * boily lightly mapoles nortti for having mentioned EFI
17:53:07 <Bike> uefi boards often have anetwork stack
17:53:20 <boily> I hate EFI, UEFI, and all that weird crap.
18:20:26 -!- KingOfKarlsruhe has quit (Read error: Connection timed out).
18:20:34 <boily> (suh-weeet! “You finish putting on the +3 ring mail "Shoim" {+Inv rF+ rN+ Str+3 SInv}.”)
18:21:26 <zzo38> Now will they let you remove it too?
18:22:11 <HackEgo> [wiki] [[Gentzen]] http://esolangs.org/w/index.php?diff=39555&oldid=39542 * Zzo38 * (+132)
18:23:09 <boily> it's nice! the centaur in me is happy ^^
18:23:25 <zzo38> There is a centaur in you?
18:24:38 <boily> elliott: then answer it.
18:25:04 <HackEgo> [wiki] [[Gentzen]] http://esolangs.org/w/index.php?diff=39556&oldid=39555 * Zzo38 * (+28)
18:27:00 <zzo38> What is your opinion of the http://esolangs.org/wiki/Gentzen so far?
18:31:11 <boily> at a glance, it feels like an uncompressed ursala mixed in with abbreviated ruby-ish perl.
18:31:22 <boily> but it has “iosys” in it, which in my book is a big plus.
18:32:09 <boily> (holy fungot. two scrolls of acquirement on Lair:1. the RNG will hit me hard soon...)
18:32:09 <fungot> boily: so, hey, it was our table! if he's interested, he'll push it back to your side. the salt shaker over to their side, this means that that one incident to say that sentence:
18:33:03 <zzo38> Uncompressed ursala? I don't know of that. And how is it like mixed with abbreviated ruby-ish perl.
18:33:25 <zzo38> elliott: But if such an armour is cursed, then it would make it difficult to acquire a better one, I think?
18:33:53 <elliott> remove curse scrolls are incredibly common in crawl :p
18:34:08 <boily> elliott: that's exactly what I did. “the +2 pair of gloves of Sakiem (worn) {Str+2}”
18:34:45 <nortti> zzo38: there actually are some HP laptops with firmware (I think) linux system that is very limited and shitty
18:35:20 <zzo38> Ah, OK then use remove curse scroll if you find a better armor and then find that the one you just put on cannot come off.
18:36:39 <zzo38> nortti: How limited is it? I would think is better having a BIOS with Forth included, but doesn't include a whole bunch of stuff like application programs and so on.
18:37:11 <nortti> just a out of date firefox and a shitty filesystem browser, iirc
18:37:58 <zzo38> That's really silly
18:39:31 <zzo38> Better would be to have a Forth system with direct hardware access, and perhaps a terminal emulator
18:41:15 <zzo38> boily: I don't know about Ursala (I cannot find the information), and I don't know what "abbreviated ruby-ish perl" quite means. Can you explain it better perhaps?
18:44:02 <boily> zzo38: cpressey sez: “I also wanted to implement it in URSALA, but its official website seems to have vanished. (Well, I didn't stand a chance, anyway, really.)” on his user page.
18:44:35 <boily> I think https://github.com/gueststar/Ursala is pretty legit about ursala.
18:45:06 <boily> ruby-ish perl is just that nice visual over-abundance of punctuation symbols seasoning a program listing.
18:50:54 -!- shikhin has quit (Ping timeout: 240 seconds).
19:14:39 -!- edwardk has joined.
19:20:14 -!- augur has quit (Remote host closed the connection).
19:29:45 -!- conehead has joined.
19:34:22 -!- MindlessDrone has quit (Quit: MindlessDrone).
19:41:22 -!- AnotherTest has joined.
19:49:02 <zzo38> It doesn't seems to resemble URSALA to me
19:50:27 -!- boily has quit (Quit: ELVISH CHICKEN).
20:06:55 -!- nooodl has joined.
20:08:03 <coppro> marking first-year logic is fun
20:09:21 -!- edwardk has quit (Quit: Computer has gone to sleep.).
20:15:20 -!- edwardk has joined.
20:25:40 -!- edwardk has quit (Quit: Computer has gone to sleep.).
20:26:42 <zzo38> Do you prefer to stay in a hotel where the floor labels aren't numbers but instead are colors that indicate what color the pokemons are that correspond to the room numbers on that floor?
20:29:23 <Taneb> Is there such a hotel?
20:36:20 -!- augur has joined.
20:40:05 <coppro> that sounds like an amazing hotel
20:40:10 <coppro> we should all pool our money and build it
20:51:02 <int-e> this sort looks affordable. http://technabob.com/blog/2010/02/08/five-stars-cardboard-hotel/
20:52:04 <coppro> I should give one of my students the 'most likely to be a doctor' award
21:02:56 -!- edwardk has joined.
21:10:05 -!- nortti has changed nick to lawspeaker.
21:10:39 -!- lawspeaker has changed nick to nortti.
21:11:41 -!- AnotherTest has quit (Ping timeout: 252 seconds).
21:14:42 -!- edwardk has quit (Quit: Computer has gone to sleep.).
21:19:14 -!- oerjan has joined.
21:28:39 -!- nucular has quit (Quit: Excess Food).
21:30:27 <zzo38> I read about SWIG but it doesn't have some, such as SQL, Haskell, Forth, FORTRAN, AWK, and a few others.
21:35:17 -!- drdanmaku has joined.
21:43:18 -!- edwardk has joined.
21:44:26 <Bike> https://twitter.com/mc_hankins/status/467766548162412545/photo/1/large Statistics.
21:54:06 -!- edwardk has quit (Quit: Computer has gone to sleep.).
22:01:31 <zzo38> Is it OK to make a random selection from a list you don't know how long, if you first have a 1/1 chance to pick the first one, a 1/2 chance to discard it and put the second one instead, a 1/3 chance to discard it and put the third one instead, etc?
22:03:15 <Phantom_Hoover> Bike, twitter replies point out people might just be writing p = 0.05 rather than 0.050
22:04:11 <Bike> Phantom_Hoover: in the replies he mentions he just cut out .05 entirely since he couldn't text search it. the point is the asymmetry.
22:05:07 <int-e> Phantom_Hoover: a truly significant finding
22:05:35 <int-e> (there must be a better pun in it but I didn't fine it)
22:05:51 -!- augur has quit (Remote host closed the connection).
22:06:03 <int-e> https://xkcd.com/882/ is relevant
22:06:56 <Bike> he probably should have indicated this on the graph, but oh well
22:07:20 <Bike> why is he wearing goggles
22:08:17 <int-e> I believe there are 4 people involved in that story
22:08:55 <int-e> he, she, scientist A and scientist B.
22:09:21 <int-e> I base this on the first panel, which has voices coming from the right.
22:09:36 -!- edwardk has joined.
22:09:39 <Bike> how many are wearing goggles
22:09:57 <int-e> one, scientist ... mumble ... A, I guess.
22:11:37 <Phantom_Hoover> i note that what-if is now using xkcd comics as a reference
22:12:02 <int-e> has what-if become interesting again?
22:13:14 <Phantom_Hoover> where 'interestng' = 'describes apocalyptically ridiculous events qualitatively, rather than just working out how much milk it'd take to drown all the rabbits'
22:22:27 -!- edwardk has quit (Quit: Computer has gone to sleep.).
22:22:34 <int-e> oh, this *is* cute, "Have you ever tried to make a tower of peanut butter?"
22:31:32 -!- atehwa has quit (Ping timeout: 258 seconds).
22:33:29 <zzo38> Do you know an answer of my question about a random selection?
22:33:40 -!- edwardk has joined.
22:33:40 -!- atehwa has joined.
22:34:12 <Bike> yes. the answer is yes.
22:35:47 <zzo38> If the items have different weights can I do for example, 5/5, 4/9, 3/12, 2/14, 1/15, etc?
22:36:28 <Bike> You can do whatever you dream.
22:36:57 <zzo38> I know I can obviously program that in, but I meant, would it work OK?
22:37:29 <oerjan> zzo38: i'm pretty sure i've seen your 1/n algorithm before.
22:37:30 <Bike> i don't know what your criteria for "OK" are, so probably.
22:37:46 <zzo38> Where have you seen it?
22:39:13 <oerjan> for one thing, it seems implied in the fisher-yates shuffle.
22:39:37 <oerjan> (if you use it only for finding the first element, say)
22:40:34 <zzo38> I am only searching for a single element of the list, although they may have different weights (possibly even zero) and the weights may vary.
22:41:35 <oerjan> i'm pretty sure you can adapt it to use weights.
22:42:15 <oerjan> basically, switch in a number with the probability of it + the remaining numbers.
22:42:36 <int-e> right. just calculate the probability of the current item w.r.t. the items seen so far, and replace the item you have by the current item with that probability.
22:42:51 <zzo38> Would the way I specified work?
22:43:15 <oerjan> no, not the probability of the current item, the probability of the current item _or any later one_
22:43:40 <fizzie> I'm pretty sure I've seen the (unweighted) 1/n approach, too.
22:43:53 <int-e> > let xs = [5%5,4%9,3%12,2%14,1%15] in zipWith (/) xs (scanl1 (+) xs)
22:43:55 <lambdabot> [1 % 1,4 % 13,9 % 61,36 % 463,84 % 2399]
22:44:35 <int-e> those are your probabilities for discarding the previous item and replacing it by the current one.
22:44:45 <int-e> > let xs = [1%1,1,1,1,1,1,1] in zipWith (/) xs (scanl1 (+) xs)
22:44:46 <lambdabot> [1 % 1,1 % 2,1 % 3,1 % 4,1 % 5,1 % 6,1 % 7]
22:45:17 <zzo38> No, I mean the probability to discard and replace with the current one are 5/5, 4/9, 3/12, 2/14, 1/15.
22:45:29 <fizzie> http://en.wikipedia.org/wiki/Reservoir_sampling
22:45:35 <oerjan> argh brain closing down
22:46:26 <zzo38> (If the weight is 5,4,3,2,1)
22:46:35 <zzo38> Note, the weights will not be known ahead of time
22:46:47 <int-e> > let ys = zipWith (/) [5%5,4%9,3%12,2%14,1%15] (scanl (+) 1 ys) in ys
22:46:49 <lambdabot> [1 % 1,2 % 9,9 % 80,720 % 11767,564816 % 20298727]
22:47:14 <oerjan> hm i think int-e is about right, anyway
22:48:20 <oerjan> although there might be an off by one error or not in there
22:48:54 <zzo38> Maybe I have made several kind of mistake, I don't know
22:48:55 <oerjan> you don't want scanl (+) 1 ys, just scanl1 (+) ys
22:49:19 <oerjan> i think the first was right.
22:51:11 <int-e> > let ys = scanl (*) 5 (map (\p -> 1/(1-p)) $ tail [5%5,4%9,3%12,2%14,1%15]) in zipWith (-) ys (0:ys)
22:51:19 <oerjan> i sense a small complication if an initial segment has weights 0, though.
22:51:36 <int-e> (that was a bit tricky to get right)
22:52:01 <oerjan> oh you were calculating in reverse
22:52:01 <zzo38> Yes clearly such thing is then wrong, but based on the algorithm actually in use it probably isn't a problem if the weight is 0.
22:52:26 <oerjan> zzo38: well you just need to handle division by zero correctly.
22:52:48 <zzo38> I am not actually doing any division to generate the random numbers, though.
22:52:56 <oerjan> or just skipping the initial elements, though.
22:52:59 <int-e> oerjan: I was verifying zzo38's calculation, yes. (and cheating a bit, too, see the hard-coded 5)
22:53:10 <oerjan> zzo38: well you need division if you are starting from a list of weights
22:53:25 <oerjan> to get the probabilities
22:53:29 <zzo38> The list of weights is not accessed ahead of time, though.
22:53:41 <zzo38> I have to do it without accessing the list ahead of time.
22:54:15 <oerjan> right, so does this, i was wrong about the idea of looking at later weights, you need the sum of the previous ones like int-e's scanl1 (+)
22:54:34 <oerjan> which does not look ahead.
22:54:46 <zzo38> Sum of previous weights (including the current weight) is what I did.
22:56:30 <oerjan> and i guess you don't need division if you are generating a random number in [0..sum of weights-1]
22:56:49 <zzo38> Yes, that is what I am doing.
22:56:50 <oerjan> although you still need to handle the sum being 0
22:57:29 <oerjan> well then, this seems to work
22:58:21 <zzo38> The algorithm I use is to generate however many bits of random is needed, and then if the result is too high, try again until it is in range. For example to make 0 to 99, make 7-bits number, and if it exceed 99 then try again.
22:58:30 <int-e> and as an exercise you can process the list in chunks
22:59:00 <int-e> zzo38: ah you shouldn't discard all of the number
23:00:03 <int-e> zzo38: instead, note that if a random 7 bit number n exceeds 99, then n-100 is uniformely distributed between 0 and 27 (inclusively).
23:00:31 <zzo38> sqlite3_result_text(cxt,sqlite3_db_filename(sqlite3_context_db_handle(cxt),sqlite3_value_text(*argv)),-1,SQLITE_TRANSIENT);
23:00:32 <int-e> adding another two bits to that gives you something uniform in 0..103.
23:01:07 <zzo38> Wouldn't doing alll that stuff just make it more confusing?
23:01:09 <int-e> It's just an optimisation, of course, but it's pretty cheap to implement.
23:01:53 -!- impomatic has quit (Ping timeout: 240 seconds).
23:03:49 <int-e> http://sprunge.us/ZEhj?c
23:04:37 <int-e> while (u < n) -> for ( ; u < n; u <<= 1)
23:06:14 <int-e> And actually it's safe to replace that u < n by u <= n. (The invariant that the code maintains is that v is uniform in 0..u-1)
23:06:58 -!- tertu has joined.
23:09:46 <int-e> so trying again: http://sprunge.us/iWjS?c
23:14:24 <zzo38> Prove it better than the one I did.
23:19:51 <int-e> for 0..99, yours needs 8.96 random bits on average (7 * 128/100), mine needs 7.48(36) (7 + 28/128 * (2 + 4/104 * 5) * 1/(1-28/128 * 4/104))
23:24:19 <int-e> And if you keep the (v,r) state around rather than clearing it every time, you can get to the optimal log_2(100) random bits average.
23:24:22 <zzo38> I don't quite see how it would work though, but I can see how those how many it need in average
23:24:58 <zzo38> Also, the program I am using can only generate eight bits at a time, and I have it generating sixty-four at a time (due to some other reasons)
23:28:03 <int-e> Actually even that way it still waste many bits of randomness. (you're using that number 0..99 to make a binary choice, say between 0..41 and 42..99. You can actually add the remaining uniform 0..41 or 0..57 (99-42) back into the (v,r) state. These ideas come from arithmetic coding in data compression.
23:28:16 -!- edwardk has quit (Quit: Computer has gone to sleep.).
23:29:55 -!- edwardk has joined.
23:30:08 <int-e> To add a random number x in [0..n-1] to (v,r), the calculation is r = r*n (we get n times as many distinct values) and v = v*n + x. One has to be a bit careful about overflows when doing that though.
23:32:00 <int-e> Sorry I made a mistage above; we won't get to log_2(100) average this way.
23:32:09 <int-e> I also cannot type.
23:32:15 -!- Patashu has joined.
23:36:12 <zzo38> I can see what you mean now about binary choice
23:38:40 <zzo38> But I don't think the random number generator is quite the slowest thing in the program, and adding too many things might confuse it (and, sometimes may slow it down due to many instructions, regardless what the O(...) is), rather than making a simple and clearly programming
23:39:17 <zzo38> But is good you make such idea anyways, to study how much it could be done, in case it can make some of these improvements later if it seem it would be help much.
23:42:38 -!- nooodl has quit (Ping timeout: 240 seconds).
23:53:00 <Taneb> Fiora hasn't been here for a while, did something happen?
23:53:20 -!- mekeor` has quit (Ping timeout: 255 seconds).
23:54:46 <kmc> she left because of some homophobic comments
23:56:13 <kmc> if you particularly want to know, read the logs
23:57:38 <shachaf> sounds like a good reason to leave a channel
23:59:31 -!- yorick has quit (Remote host closed the connection).
00:04:01 -!- edwardk has quit (Quit: Computer has gone to sleep.).
00:09:15 -!- Patashu_ has joined.
00:09:15 -!- Patashu has quit (Disconnected by services).
00:13:30 <Taneb> Can we start having a stricter policy against that sort of thing?
00:14:17 <fowl> offensive jokes must be this funny |-----------------| to share
00:14:22 <oerjan> i don't remember how it went back then
00:15:04 <kmc> at present I'm not able to enforce such a policy, for personal / psychological reasons
00:15:16 <kmc> if other ops wish to do so then it is fine with me
00:15:25 <kmc> basically I feel like I will be part of the problem no matter what I do :/
00:16:57 <kmc> but I think it's probably bad to have a policy that some ops can't enforce
00:16:57 <oerjan> i don't even remember why it wasn't enforced back then.
00:17:39 <kmc> me, I just said
00:17:41 <oerjan> quintopia: PAY ATTENTION
00:17:49 <zzo38> I don't care and I think if those people leave due to such thing they are probably their own fault, although also whoever wrote such thing should be careful too (in order to avoid such thing), even if you have free speech too.
00:18:22 <quintopia> kmc: i don't understand why you couldn't enforce it
00:18:57 <oerjan> wait was it quintopia who started it back then
00:19:14 <zzo38> Maybe you disagree how funny/offensive they are? It can be possible
00:19:22 -!- edwardk has joined.
00:19:26 <quintopia> depending on what you mean VERY PROBABLY
00:19:54 <kmc> quintopia: because these days whenever I think about social justice things it triggers intense depressive symptoms
00:20:13 <kmc> i'm really sad and bitter about all of it
00:20:37 <oerjan> zzo38: there are people who cannot emotionally handle these kind of jokes, due to past trauma or whatever.
00:20:44 <kmc> about people being sexist/racist/homophobic assholes, about the psychological warfare tactics of the people who fight them online, about my own role in systems of oppression
00:21:29 <oerjan> darn now i have to stop reading you before i get depressive symptoms
00:21:52 <kmc> it's a war fought by dehumanization and by attacking the idea of empathy
00:23:01 <kmc> this is also why i really really need to stop using twitter
00:23:13 <quintopia> so let's make dehumanization and attacking the idea of empathy the bannable offence. also, triggering despressive symptoms.
00:23:30 <oerjan> which reminds me of the recent goodmath post http://www.goodmath.org/blog/2014/05/11/depression-and-arrogant-assholes/
00:23:47 <oerjan> (he's also posted about sexism previously iirc)
00:24:00 <Taneb> Can someone remind me who's an op in here?
00:24:57 <Bike> alas, i am not authorized to ask chanserv
00:25:27 <zzo38> oerjan: I know, that some people don't handle this kind of jokes. That isn't your fault, but those people who don't handle it, should have the right to complain
00:25:42 <oerjan> Taneb: me, fizzie, ais523, kmc and elliott are the active ones
00:25:49 <zzo38> quintopia: But maybe some people are depressed of strange thing
00:25:58 <Taneb> oerjan, OK, thanks
00:26:19 <oerjan> Bike: wait you aren't?
00:26:30 <Bike> /msg chanserv flags #esoteric
00:26:35 <oerjan> or are you just being sarcastic
00:26:48 <Bike> You are not authorized to perform this operation.
00:27:06 <zzo38> And, you should need argument of absolutely everything anyways, including (but not limited to), dehumanization, empathy, free speech, goodmath post, me, you, etc.
00:27:29 <oerjan> ic. i never noticed that required authorization.
00:27:29 <Bike> i don't know if that's the good way to look shit up though
00:27:49 <Bike> it's so that you can run channels as if you're the KGB i guess
00:28:01 <zzo38> Try CS ACCESS #esoteric LIST that works for me
00:28:21 <Bike> ah, thank you.
00:29:46 <oerjan> that's funny, those give identical results afaict
00:30:01 <Bike> presumably you have privilege
00:31:29 <oerjan> it's just funny that it makes a command require authorization if it gives the same result as an unauthorized one
00:32:16 <oerjan> although i guess it's also possible you _don't_ see the same result as i.
00:32:59 <Taneb> I ought to sleep at some point.
00:34:22 <kmc> "And until then, until then, until they've reason to think I've a shot at redemption, until then, I'm not talking"
00:36:44 -!- edwardk has quit (Quit: Computer has gone to sleep.).
00:38:47 <Taneb> I wish for all of you to find happiness in unlikely places. Goodnight.
00:39:03 <kmc> same to you Taneb
00:39:05 <kmc> good night :)
00:39:53 <fowl> im trying to remember the name of that joke programming language
00:40:28 <fowl> found it https://gitorious.org/c-plus-equality/c-plus-equality/
00:41:55 -!- kmc has left.
00:44:01 <zzo38> I made up a ORD, CHR, ORD_U, CHR_U function to replace the UNICODE and CHAR function in SQL, and I have figured out the followings:
00:44:11 <zzo38> ORD(CHR_U(10000000)) makes 248, ORD_U(CHR_U(10000000)) makes 10000000, ORD_U(CHAR(10000000)) makes 65533, UNICODE(CHAR(10000000)) makes 65533, UNICODE(CHR_U(10000000)) makes 10000000, UNICODE(CHR_U(100000000)) makes 100000000, ORD_U(CHR_U(100000000)) makes 100000000, ORD_U(CHR_U(0)) makes 0, UNICODE(CHR_U(0)) makes 65533, UNICODE(CHAR(0)) makes NULL, ORD_U(CHAR(0)) makes NULL.
00:44:16 <zzo38> ORD_U(CHR_U(64138178286)) makes 64138178286, UNICODE(CHR_U(64138178286)) makes -286331154, UNICODE(CHAR(64138178286)) makes 65533, ORD_U(CHAR(64138178286)) makes 65533, ORD_U(CHAR(99999999999)) makes 65533, and ORD_U(CHR_U(99999999999)) results in an error message.
00:44:21 <zzo38> Is this better or not?
00:45:53 <zzo38> The C+= mentions "Now hosted on Gitorious, as GitHub, BitBucket, and Google all prove to be too misogynistic to support a feminist programming language." I don't think it necessarily means it is misogynistic, but, my own opinion is that you should be allowed to make such program if you want to, whether or not it is feminist or anything else whatever
00:47:37 <fowl> zzo38, there was enough whining that they took it down from github
00:47:53 <Bike> haha seriously
00:49:10 <fowl> zzo38, but, in feminist spirit, they (c+=) have to say that its because those sites are misogynistic
00:49:40 <zzo38> O, OK, yes they can say that if they want
01:01:14 <int-e> sti::cout of_the_following "Hello, feminists!\n". //Frankly I feel that line escape codes could be problematic
01:01:35 <int-e> preceded by: / // "std" is sooooo old-fashioned. we use "sti" nowadays.
01:01:35 <int-e> //cout should be removed immediately as the two letters "co" obviously represent the beginning of a phallus.
01:01:47 -!- hk3380 has quit (Ping timeout: 276 seconds).
01:13:14 -!- zzo38 has quit (Remote host closed the connection).
01:59:19 -!- hk3380 has joined.
02:20:05 -!- Phantom_Hoover has quit (Ping timeout: 264 seconds).
02:37:15 -!- Frooxius has quit (Ping timeout: 258 seconds).
03:13:57 -!- hk3380 has quit (Ping timeout: 252 seconds).
03:22:02 -!- ^v has joined.
03:22:55 -!- augur has joined.
03:33:14 -!- Bike has quit (Ping timeout: 276 seconds).
03:37:29 -!- oerjan has quit (Quit: Nythe).
03:40:13 -!- Bike has joined.
04:05:47 -!- shikhin has joined.
04:29:26 -!- Bike has quit (Ping timeout: 259 seconds).
04:30:10 -!- Bike has joined.
04:34:34 -!- Sorella has quit (Quit: It is tiem!).
04:34:38 -!- Bike has quit (Ping timeout: 240 seconds).
04:36:56 -!- Bike has joined.
04:45:10 -!- Frooxius has joined.
04:59:32 -!- scoofy has quit (Excess Flood).
04:59:56 -!- scoofy has joined.
05:12:23 -!- shikhin has quit (Ping timeout: 255 seconds).
05:20:40 -!- tromp has joined.
05:24:30 <Jafet> "George Westinghouse promptly bought Tesla's patents, employed Tesla to develop them, and assigned C. F. Scott to help Tesla, Tesla leaving for other pursuits in 1889.[23][30][33][34][35][36][37][37][38][38][39][40] [41][42][43][44]"
05:24:47 -!- tromp has quit (Client Quit).
05:25:08 <Bike> "are you sure"
05:28:56 <Sgeo> Ugh, got sunburned. Is a single day of sunburn as bad as a single day of smoking?
05:29:16 <Sgeo> I don't know what my risk is
05:31:26 -!- tromp has joined.
05:31:42 <Sgeo> Doesn't seem to be blistering
05:33:43 <Sgeo> Might not be as big an issue as lack of sleep... which is systemic for me, so more comparable to smoking cigarettes regularly
05:40:59 <Sprocklem> Sgeo: But lack of sleep can't cause cancer.
05:41:33 <Sgeo> Can it let a cancer that would otherwise be destroyed be viable? If lack of sleep is bad for immune system...
05:41:36 <coppro> Sgeo: not nearly as bad
05:41:51 <coppro> Sgeo: melanoma is easy to treat if caught early
05:42:50 <coppro> and it's the really dangerous kind of skin cancer
05:44:22 -!- edwardk has joined.
05:46:19 -!- edwardk has quit (Remote host closed the connection).
06:01:24 <Jafet> firefox can render webpages in 3D
06:02:54 <Jafet> https://mdn.mozillademos.org/files/3625/3dview.png
06:03:13 <Jafet> Grab a deck and plug in to cyberspace
06:32:26 -!- tromp has quit (Remote host closed the connection).
06:44:39 -!- edwardk has joined.
06:45:27 -!- ^v has quit (Quit: http://i.imgur.com/Akc6r.gif).
07:02:59 -!- tromp has joined.
07:03:05 -!- Bike has quit (Ping timeout: 255 seconds).
07:04:01 -!- password2 has joined.
07:07:31 -!- tromp has quit (Ping timeout: 252 seconds).
07:15:13 -!- augur has quit (Ping timeout: 252 seconds).
07:24:49 -!- augur has joined.
07:27:58 -!- conehead has quit (Quit: Computer has gone to sleep).
07:30:00 -!- edwardk has quit (Read error: Connection reset by peer).
07:30:41 -!- edwardk has joined.
08:36:17 -!- KingOfKarlsruhe has joined.
08:49:56 -!- Slereah_ has joined.
08:52:35 -!- Slereah__ has joined.
08:53:18 -!- Slereah has quit (Ping timeout: 258 seconds).
08:55:26 -!- Slereah has joined.
08:55:37 -!- Slereah_ has quit (Ping timeout: 276 seconds).
08:58:40 -!- Slereah__ has quit (Ping timeout: 258 seconds).
09:01:24 -!- drdanmaku has quit (Quit: Connection closed for inactivity).
09:05:28 <Taneb> Morning, #esoteric!
09:20:18 -!- KingOfKarlsruhe has quit (Read error: Connection timed out).
09:33:42 -!- impomatic has joined.
10:12:37 -!- MindlessDrone has joined.
10:24:48 -!- shikhin has joined.
10:25:31 -!- edwardk has quit (Quit: Computer has gone to sleep.).
10:28:04 -!- nooodl has joined.
10:44:45 -!- Phantom_Hoover has joined.
10:59:23 -!- yorick has joined.
11:09:46 -!- password2 has quit (Ping timeout: 258 seconds).
11:13:07 -!- hk3380 has joined.
11:35:53 -!- Slereah_ has joined.
11:36:04 <Jafet> http://blog.coinbase.com/post/85758038492/10-of-free-bitcoin-for-college-students
11:36:27 <HackEgo> boaracoin azumarkcoin bigcoin balackcoin incolcoin dipucoin homeoncoin zetacoin revcoin revillacoin ploycoin pertacoin syllcoin bfficidcoin rockcoin versexumcoin interandrecoin revilcoin eiccancoin singcoin
11:36:43 -!- Slereah has quit (Ping timeout: 240 seconds).
11:38:18 -!- shikhin has quit (Quit: Lost terminal).
11:43:13 -!- shikhin has joined.
12:09:05 -!- oerjan has joined.
12:18:23 -!- MoALTz has quit (Ping timeout: 258 seconds).
12:20:20 -!- MoALTz has joined.
12:20:47 -!- Slereah has joined.
12:24:17 -!- Slereah_ has quit (Ping timeout: 264 seconds).
12:24:18 <oerjan> @tell Sgeo <Sgeo> Can it let a cancer that would otherwise be destroyed be viable? If [...] is bad for immune system... <-- YES WORRYING ABOUT THINGS ALL THE TIME PROBABLY CAN DO THAT HTH
12:25:04 <oerjan> (and while i'm joking, i still think it's probably true.)
12:29:26 <oerjan> sadly the top google hit is this http://www.dailymail.co.uk/health/article-2099567/Hypochondriacs-dont-live-long-research-suggests-persons-outlook-affects-lifespan.html
12:29:41 <oerjan> (sad because it's daily mail)
12:31:52 <oerjan> but good because it refers to an actual study.
12:34:17 <oerjan> (what do you mean it's not that much)
12:40:10 <Taneb> That's like loads compared to me
12:40:15 <mroman> I'd consider my health as "poor" too
12:40:31 <mroman> without reference to how other people's health is
12:40:43 <mroman> compared to other people's health it's probably in the lower normal range :)
12:41:14 <mroman> If your vision has these weird "worm"-like structures in it you'd consider your vision as bad
12:41:28 <mroman> until you notice that lots of other people have it too
12:41:43 <oerjan> mroman: um well if you have them all the time i guess...
12:42:06 <mroman> They don't magially disappear ;)
12:42:44 <oerjan> hm i guess i'm not having them, then. although i've certainly seen occasional things moving in there.
12:43:06 <mroman> http://upload.wikimedia.org/wikipedia/commons/b/b2/Floaters.png
12:43:13 <mroman> it's just like your nose.
12:43:19 <mroman> Eventually you stop noticing them
12:43:32 <mroman> it also dependents on background color/light
12:43:37 <mroman> but they will always be there
12:43:56 <mroman> and suddenly you notice them again
12:44:07 -!- Slereah_ has joined.
12:44:23 <oerjan> well i guess. i've always noticed them better when looking at blue sky.
12:45:07 <oerjan> occasionally one will float into the middle of the eye, but otherwise i don't notice much
12:45:21 <oerjan> *of the field of vision
12:45:53 -!- Frooxius has quit (Ping timeout: 264 seconds).
12:46:06 <mroman> it's hard counting them though
12:46:06 <oerjan> no more than a handful, at any rate.
12:47:04 -!- Slereah has quit (Ping timeout: 240 seconds).
12:49:40 -!- AnotherTest has joined.
12:50:00 <Taneb> I need to sort out my diet
12:50:15 <mroman> and by health I meant physical health
12:50:26 <mroman> Taneb: You didn't look fat on your talk
12:51:35 <Taneb> Like, since Friday morning all I've ate was a bowl of soup and a chocolate bar
12:52:07 <mroman> sounds about the same amount I drank since last friday :)
12:52:27 <oerjan> are all geeks either too fat or too slim
12:52:50 <Taneb> I don't think any of us pay much attention to what we're eating
12:52:59 <mroman> If you classify me as a geek then no
12:53:09 * oerjan eyes mroman suspiciously
12:53:21 <Taneb> I mean, on Thursday, I had a pub's special burger which is about 8 inches tall
12:54:08 * oerjan sips his perfectly healthy orange juice
12:56:13 <oerjan> if the rest of my meals were as healthy as breakfast, i'd be all set.
12:56:30 <Taneb> oerjan, easy. Only eat breakfast.
12:57:01 <mroman> I used to go rock climbing twice a week
12:57:04 <oerjan> Taneb: but then i get sugar and caffeine withdrawal D:
12:58:35 <oerjan> (curiously, my caffeine drinks are sugar free. i've just slipped on the actual sweets.)
12:58:46 -!- boily has joined.
13:00:06 <Taneb> I've got to have an early night tomorrow.
13:01:14 <mroman> going to sleep early is the most paradoxical thing of things
13:01:20 <oerjan> i cannot do early nights. i just end up not sleeping and lying in bed freezing.
13:01:39 <mroman> you'd think the earlier you go to bed the longer you sleep and the longer you sleep the more fit you'll be in the morning
13:01:42 <oerjan> which is one part of the reason why i have this >24 hour slippage.
13:03:54 <boily> freezing in bed? don't you have, like, bedsheets, covers, linen, woolly stuff to keep you warm?
13:04:55 <Taneb> boily, he's in Norway.
13:04:57 <oerjan> boily: those don't help. in fact i'm likely to spend a while feeling too hot, then suddenly too cold.
13:05:23 <oerjan> my body has strange temperature regulation.
13:07:04 -!- MindlessDrone has quit (Ping timeout: 258 seconds).
13:08:55 -!- nucular has joined.
13:09:05 -!- nucular has quit (Changing host).
13:09:05 -!- nucular has joined.
13:12:18 -!- metasepia has joined.
13:13:04 <metasepia> ENVA 181250Z VRB02KT CAVOK 22/06 Q1014 NOSIG RMK WIND 670FT 20010KT
13:13:40 <oerjan> i'll have to change to my summer jacket
13:14:41 <metasepia> CYUL 181300Z 25010KT 30SM FEW035 FEW150 10/02 A3020 RMK CU1AC1 CU TR AC TR SLP226
13:14:48 <boily> we live in interesting times...
13:15:07 <boily> oh and btw, we want our warm weather back plzkthx
13:15:27 <boily> you darned scheming evil Norwegian!
13:15:40 <Taneb> I need to get some food, shower, do like loads of laundry...
13:15:49 <Taneb> Get my life together, that kind of thing
13:17:17 <oerjan> no, spammer, i don't get more likely to open your "AWAITING YOUR QUICK RESPONSE" message if you send it 3 times in succession.
13:21:47 -!- MindlessDrone has joined.
13:29:41 <oerjan> also it wasn't actually all caps, it just felt that way.
13:30:59 <int-e> <Delete> <-- pretty quick if you ask me.
13:31:41 <int-e> I'm getting spam with subjects like "FROM MRS.AWAH SULE"
13:32:04 <int-e> and "UTD Living โรงแรมอพาร์ทเมน"
13:34:54 <Taneb> I feel like going outside and maybe getting food or something
13:35:21 <oerjan> Taneb: an ancient impulse
13:35:43 <Taneb> I don't have a spear, will a pencil do?
13:35:58 <int-e> if it's big enough?
13:36:55 <int-e> 'The pen is mightier than the sword if the sword is very short, and the pen is very sharp.'
13:37:22 <Taneb> I here a fire alarm comi... there it is
13:37:59 <oerjan> you can hear them in advance? fancy.
13:39:37 <mroman> when dous haskell get implicit maps
13:40:03 -!- Sorella has joined.
13:40:33 <mroman> and if a list is provided, it shall map over the list
13:40:57 <mroman> i.e. the operation is applied to every element of the list automatically
13:42:56 * oerjan awaits to see whether main = print $ [x | x <- [1..], x == 0] overflows the stack
13:44:27 <mroman> > [x | x <- [1..], x == 0]
13:44:44 <oerjan> mroman: you can define the instances to make it do that. but it would be confusing to newbies.
13:45:13 <mroman> a Num instance for Num a => [a]?
13:45:47 <oerjan> yes, although for sqrt (which does _not_ take an Int btw) you need Floating or thereabout
13:45:57 <lambdabot> class (Fractional a) => Floating a where
13:45:57 <lambdabot> exp, log, sqrt, sin, cos, tan :: a -> a
13:45:57 <lambdabot> asin, acos, atan, sinh, cosh, tanh, asinh, acosh, atanh :: a -> a
13:46:19 <oerjan> hm no stack overflow yet.
13:46:37 <oerjan> i assume it would have showed up already
13:47:00 <boily> (mana vipers and shock serpents? what has DCSS come to?)
13:47:05 <mroman> not having implicit maps made Burlesque suck a little bit
13:47:16 <mroman> that and having a Pretty type and having no variables
13:47:26 <mroman> I came to the conclusions that purely stack based languages suck
13:49:19 <mroman> every function that takes two arguments should implicitly map or zip over lists
13:49:37 <mroman> i.e [1,2] + 1, 1 + [1,2] and [1,2] + [2,3]
13:52:40 -!- shikhin has quit (Ping timeout: 240 seconds).
13:54:13 <Taneb> oerjan, it starts ringing in this part of the building last
13:54:54 -!- shikhin has joined.
13:56:11 <Taneb> I also went to the little Middle-Eastern/Indian/something supermarket that's like 20 meters down the road and bought something that, accompanied with some bread, would make a nice meal
13:56:31 -!- tromp has joined.
14:03:35 <Taneb> Maybe in a bit I'll go down the the co-op and buy some bread
14:07:54 <Taneb> Did I tell you that the other day when I was trying to get hang of Rust (again) I managed to write a non-idempotent "isPrime" function
14:08:22 <oerjan> i am not sure "idempotent" applies to isPrime functions in any case.
14:08:41 <Taneb> Then the word I was thinking about
14:09:15 <oerjan> you mean it broke on a second run?
14:09:37 <oerjan> i guess that's idempotent if you think imperatively.
14:09:41 <Taneb> It did with, say, "15"
14:10:42 <Taneb> I don't think it could produce false negatives, though
14:11:03 <oerjan> oh wait it used a randomized method i assume
14:11:12 <Taneb> Nah, it was just broken
14:11:32 <Taneb> It was using trial division, and caching some of the known primes
14:11:47 <oerjan> known primes such as 51
14:11:52 -!- mhi^ has joined.
14:12:30 -!- tromp has quit (Remote host closed the connection).
14:12:32 <Taneb> It had the invariant that the cache would contain the beginning of the list of primes (that held)
14:13:01 <Taneb> But if the largest known prime was larger than the square root of the number being checked, it would start after that number
14:14:24 <Taneb> The largest known prime is 2. 2*2 = 4 < 15.
14:15:15 <Taneb> Let's check 3. 3*3 = 9 < 15. 2 does not divide 3. Therefore 3 is prime. 3 divides 15. 15 is not prime.
14:15:34 <Taneb> The largest known prime is 3. 3 * 3 = 9 < 15.
14:16:11 <Taneb> Let's check 4. 4*4 = 16 > 15. No more to check. 15 is prime.
14:16:28 <int-e> if 3 were the largest prime then 15 would be prime, so 3 is not the largest prime and we learned nothing about 15.
14:16:30 <oerjan> FreeFull: you don't say
14:16:45 <Taneb> int-e, largest prime I've remembered.
14:16:56 <Taneb> Raspberry Pi Notation?
14:17:11 <int-e> 3 divides 15, so why would 15 be prime?
14:17:19 <impomatic> 15 isn't prime because it's the difference of two squares. Any number that's the difference of two squares isn't prime.
14:17:40 <int-e> impomatic: 3 = 4-11
14:17:41 <Taneb> int-e, because it started checking at 4
14:17:42 <int-e> impomatic: 3 = 4-1
14:17:42 <oerjan> FreeFull: shouldn't poles prefer forwards PN, anyway
14:18:02 <int-e> impomatic: any odd number is the difference of two squares
14:18:03 <Taneb> int-e, because my algorithm was horribly flawed
14:18:50 <impomatic> int-e: Any sufficiently large number that's the difference of two squares isn't prime.
14:19:40 <impomatic> int-e: Any sufficiently large number that's the difference of two non-consecutive squares isn't prime.
14:20:20 <oerjan> hey no fair fixing your statement while we're writing up the counterexample
14:20:56 <int-e> impomatic: and now you can drop "sufficiently large"
14:21:23 <impomatic> int-e: Any number that's the difference of two non-consecutive squares isn't prime.
14:21:35 <int-e> (I could now say that 3 = 2^2 - (-1)^2, but that's just a cheap trick.)
14:21:40 <Taneb> wtf another fire alarm
14:21:56 <impomatic> int-e: Any number that's the difference of two non-consecutive positive squares isn't prime.
14:24:19 <impomatic> int-e: Any number that's the difference of two non-consecutive positive powers isn't prime.
14:26:20 <Taneb> int-e, they're consecutive, and they're different powers
14:28:13 <int-e> > 5^3 - 2^4 -- I was really after the different exponents
14:28:15 -!- hk3380 has quit (Ping timeout: 252 seconds).
14:30:51 <mroman> then (p - x) mod n == 0?
14:31:35 <int-e> mathematicians define a = b (mod n) if n divides (a-b).
14:34:33 <Jafet> Prime numbers, such as 57
14:34:53 <int-e> The Grothendieck prime?
14:35:40 <int-e> can't blame him much, except for being divisible by 3 and 19 it really does look like a prime number.
14:37:36 <FreeFull> mroman: True for all p , n and x
14:37:49 <mroman> If I know that 3 divides 219, and two divides 220 and 222
14:37:54 <mroman> does that tell me something about 221?
14:38:10 <mroman> except that 3 also divides 222 probably
14:38:18 -!- Patashu_ has quit (Ping timeout: 258 seconds).
14:38:19 <FreeFull> It tells you 3 doesn't divide 221
14:38:20 <int-e> yes, 221 is coprime to 6 then
14:38:55 <mroman> but I guess that has further implications
14:40:44 <int-e> is unicode supposed to make sense?
14:42:07 <int-e> mroman: 221 has a prime factor that's 2 modulo 3.
14:42:51 <int-e> that's true for any n = 2 (mod 3)
14:43:10 <int-e> because with only factors = 1 (mod 3) you cannot get a product = 2 (mod 3).
14:44:26 <mroman> is a*b `mod` n == (a `mod` n) * (b `mod` n)?
14:44:54 <mroman> * ((a `mod` n) * (b `mod` n)) `mod` n?
14:45:22 <mroman> yes to the correction?
14:46:33 <int-e> a = a' (mod n) and b = b' (mod n) imply a*b = a'*b' (mod n)
14:48:33 <int-e> To deal with the `mod` operator mathematically, one can work with the identity (or congruence) a = a `mod` n (mod n) and the fact that a = b (mod n) implues a `mod` n = b `mod` n.
14:49:30 <int-e> then a*b = (a `mod` n) * (b `mod` n) (mod n) and indeed a*b `mod` n = (a `mod` n) * (b `mod` n) `mod` n.
14:53:59 <int-e> ⒪⒣ ⒯⒣⒤⒮ ⒤⒮ ⒫⒠⒭⒡⒠⒞⒯ ⒡⒪⒭ ⒨⒠ (since I like parentheses so much)
14:54:26 <Taneb> `unicode GREEK LETTER CAPITAL THETA
14:54:37 <HackEgo> U+0398 GREEK CAPITAL LETTER THETA \ UTF-8: ce 98 UTF-16BE: 0398 Decimal: Θ \ Θ (θ) \ Lowercase: U+03B8 \ Category: Lu (Letter, Uppercase) \ Bidi: L (Left-to-Right) \ \ U+03B8 GREEK SMALL LETTER THETA \ UTF-8: ce b8 UTF-16BE: 03b8 Decimal: θ \ θ (Θ) \ Uppercase: U+0398 \ Category: Ll (Letter, Lowercase) \ Bidi: L (Left-to-Right) \
14:56:12 <mroman> if I know p `mod` n == 1 and p `mod` (x*n) == -1
14:56:49 <int-e> then n=1 or n = 2.
14:57:45 -!- nooodl_ has joined.
14:57:53 <int-e> p `mod` (x*n) `mod` n = p `mod` n, so 1 = -1 (mod n), n divides 2.
14:58:38 <int-e> (hmm. I really dislike the infix operator. When is `mod` ever negative?)
14:59:17 <int-e> so n = 2, and x < 0.
15:01:04 -!- nooodl has quit (Ping timeout: 240 seconds).
15:01:05 -!- tromp has joined.
15:01:21 <FreeFull> That's not like mathematical modular arithmetic
15:02:03 <int-e> it's just an odd choice of representatives
15:03:14 <mroman> what if I know that q `mod` n == -1 with a given n
15:03:15 <Sgeo> Chrome popup blocker: Blocks the tab I meant to open but lets an ad open in a new tab
15:03:16 <Jafet> Did you know that two's complement is just normal Z/2^wZ with the upper half shifted around
15:03:31 <int-e> Ah! I know why Haskell does it that way. It's because a `div` b = floor(a / b), and the remainder has to match that definition ((a `div` n) * n + a `mod` n = a).
15:03:32 <Sgeo> Now wondering if maybe the link was set to the ad and the page I wanted opened via Javascript
15:03:51 <mroman> then I can create the sequence [-1 `mod` n, -1 `mod n` + n, -1 `mod n` + n + n] and so forth
15:04:08 <Jafet> > rem <$> [1,-1] <*> [2,-2]
15:04:30 <int-e> Jafet: of course :)
15:04:49 <mroman> until I would be > sqrt(q)
15:04:53 <Jafet> So there isn't actually a remainder function specified as 0 <= r < |q|
15:05:20 <int-e> And `mod` and `rem` are distinct, `rem` is based on a division that rounds towards infinity.
15:05:31 <int-e> you can use \x y -> x `mod` abs y
15:05:38 <Jafet> I thought rem was underspecified.
15:06:01 <int-e> but that's what I see in practice anyway
15:09:49 <FreeFull> I think mod is defined in terms of rem
15:11:53 -!- Phantom_Hoover has quit (Ping timeout: 252 seconds).
15:12:00 <mroman> http://codepad.org/HMmnOEc2
15:12:15 <mroman> somewhere in that list should be a factor of 589
15:17:23 <mroman> but that only works as it should if there is a q `mod` n == -1
15:17:23 -!- edwardk has joined.
15:17:30 <mroman> otherwise it fails horribly
15:18:13 <int-e> s p b = maximumBy (comparing snd) $ [(p `mod` n, n)|n <- [2..b]] <-- always picks the last element of the list
15:18:21 <int-e> I have no clue what you're doing there.
15:20:05 <int-e> other ideas: cycle [x] == repeat x; zipWith (*) [0..] (repeat x) == map (*x) [0..]; map (+ y) $ map (* x) [0..] == iterate (+ x) y.
15:20:54 <oerjan> Jafet: both rem and mod are well defined in haskell, to match with quot and div respectively.
15:21:35 <oerjan> but div/mod happen to do what mathematicians prefer, and quot/rem what x86 does.
15:22:32 <mroman> that explains why it wasn't working :)
15:22:54 <int-e> "‘quot‘ is integer division truncated toward zero, while the result of ‘div‘ is truncated toward negative infinity."
15:24:29 -!- Phantom_Hoover has joined.
15:24:59 <oerjan> mroman: btw when you write fst (s p b) and snd (s p b) it is entirely possible that s p b is evaluated twice.
15:27:36 <mroman> You really have to search until you find a q `mod` n = -1
15:28:38 -!- hk3380 has joined.
15:30:02 <int-e> are you trying to generalise the trick with the prime factor = 2 (mod 3)? If so, that really only works modulo 3 and modulo 4, because then there are only two coprime residues.
15:31:53 <mroman> int-e: yeah. Trying to
15:33:28 <mroman> the other assumption was that
15:33:34 <mroman> if (a*b) `mod` 18 == x
15:33:45 <mroman> then a `mod` 18 == x OR b `mod` 18 == x
15:34:12 -!- conehead has joined.
15:34:40 <mroman> it only holds for (a mod n * b mod n) mod n == ....
15:35:24 <mroman> assuming you know that (a*b) `mod` 18 is 17
15:35:34 -!- tromp has quit (Remote host closed the connection).
15:35:40 <mroman> then (a `mod` 18) * (b `mod` 18) must be 17 too
15:36:27 -!- password2 has joined.
15:36:37 <int-e> (a `mod` 18) * (b `mod` 18) `mod` 18
15:37:15 <mroman> which means possible combinations are 5,7 and 13*11
15:37:15 -!- password2 has quit (Max SendQ exceeded).
15:37:59 -!- password2 has joined.
15:38:10 <mroman> so a `mod` 18 == 11, b `mod` 18 == 13
15:38:18 <mroman> that looks something that could be solved by that chinese thing
15:38:46 -!- ais523_ has joined.
15:39:08 -!- password2 has quit (Max SendQ exceeded).
15:39:09 <oerjan> that's splitting up 18
15:39:30 <int-e> [(a,b) | a <- [5,11,17], b <- [1,7,13], a*b `mod` 18 == 17]
15:39:32 <int-e> > [(a,b) | a <- [5,11,17], b <- [1,7,13], a*b `mod` 18 == 17]
15:40:14 <oerjan> the 2 part says that a*b must be odd, which you know how to handle
15:40:35 <oerjan> the 9 part says that a*b `mod` 9 == 8
15:40:40 <int-e> (you can solve it modulo 2: 1*1 = 1; modulo 3: 2*1 = 2, use the CRT to combine them into solutions modulo 6, then extend to modulo 18)
15:40:40 -!- edwardk has quit (Quit: Computer has gone to sleep.).
15:41:05 <oerjan> wait what's the extend part.
15:41:26 <int-e> oerjan: just brute force in my paste for lambdabot
15:41:37 <mroman> my other idea was to calculate enough module stuff until you have enough information to reasonably brute-force the factors
15:42:08 <mroman> i.e by knowing that it's 17 `mod` 18 you can brute-force eather 7,5 or 13,11
15:43:19 <int-e> oerjan: anyway it's a fairly standard approach for solving (polynomial) equations modulo prime powers p^k: first find solutions modulo p, then take each solution and figure out what its counterparts are modulo p^2, p^3, etc; if you're lucky then there will be only one in each case.
15:43:34 <mroman> if q = a*b then either a is 7 mod 18 and b is 5 mod 18 or it's 13,11
15:43:52 <int-e> oerjan: but I don't know what it's called, "extend" may not be the right term.
15:44:02 <mroman> it's probably faster than O(sqrt(N))
15:44:09 <mroman> but it doesn't beat the quadratic sieve
15:44:15 <mroman> which is afaik sqrt . sqrt N
15:44:40 <oerjan> in any case, point here is 17 is invertible (mod 18) so there will be a solution for each value < 18 and relatively prime to it
15:45:35 <oerjan> to calculate division (mod n), you use the extended euclidean algorithm
15:47:28 -!- oerjan has quit (Quit: Why am I still here).
15:52:45 <impomatic> Al's latest programming contest has been announced http://azspcs.net/Contest/AlphabetCity
15:52:53 <impomatic> I don't think I'll be entering this one...
15:53:02 -!- edwardk has joined.
16:01:04 <Jafet> There are two algorithms of estimated complexity O(sqrt(sqrt N)) and neither is the quadratic sieve, which is in a different class entirely
16:04:15 <int-e> hmm. which is the second one, besides Pollard's rho method?
16:06:07 -!- tromp has joined.
16:08:36 <Jafet> Shanks used quadratic forms
16:10:38 -!- tromp has quit (Ping timeout: 240 seconds).
16:10:59 <Jafet> Nobody knows about it because it is terribly documented and based on class field theory
16:30:43 -!- ^v has joined.
16:31:36 -!- kmc has joined.
16:32:19 <kmc> fizzie, ais523_, elliott: I'm stepping down as an #esoteric op and have removed myself from the ChanServ flags
16:32:52 <ais523_> kmc: I actually didn't realise you were an op
16:32:57 -!- kmc has left.
16:33:20 <ais523_> I guess kmc's quitting the channel altogether
16:33:44 -!- edwardk has quit (Quit: Computer has gone to sleep.).
16:34:25 -!- nooodl_ has changed nick to nooodl.
16:36:07 <Jafet> The keegan has ODed on personal crisis
16:37:01 <HackEgo> [wiki] [[Talk:Brainfuck]] http://esolangs.org/w/index.php?diff=39557&oldid=39518 * Keymaker * (+399) A Turing-complete program in 135 instructions.
16:37:41 <boily> time to go fetch something to eat. I bet my Canadian 1 cent collection that he'll be back in the next hour.
16:37:47 -!- boily has quit (Quit: Poulet!).
16:38:07 <ais523_> not really, I quit this channel for ages because it was usually offtopic
16:38:15 <ais523_> although the offtopicness has got less annoying recently
16:38:18 <Jafet> The chicken crossed the road to get away from boily.
16:38:26 <ais523_> a co-op is someone who works alongside the ops, I guess?
16:38:37 <Taneb> Nah, it's the categorical dual of an op
16:38:46 <Jafet> A co-op is the person who gets kicked
16:52:48 * int-e is worried about cowriters
17:00:14 -!- Phantom_Hoover has quit (Ping timeout: 255 seconds).
17:03:52 <Jafet> This also explains why coworkers are usually unproductive.
17:08:55 -!- edwardk has joined.
17:12:33 -!- edwardk has quit (Client Quit).
17:13:59 <mroman> @oeis 1, 1, 3, 2, 5, 4
17:14:05 <lambdabot> n - d(n), where d(n) is the number of divisors of n (A000005).[0,0,1,1,3,2,5...
17:14:28 <mroman> that doesn't seem right.
17:15:01 -!- edwardk has joined.
17:15:05 <mroman> It's the number of non-divisors of n
17:17:04 <mroman> oh. that's supposed to be a subtraction
17:17:33 <int-e> sorry. what else would it be?
17:18:08 <mroman> I didn't read that as a subtraction
17:18:24 <mroman> Why would I've ben confused then
17:19:10 <Jafet> We have progressed beyond subtractive thinking
17:23:03 <impomatic> I've been stung. By a bee. On the nose ffs.
17:25:29 <mroman> Thanks to some study I could now look up how much that approx. hurts
17:26:03 <mroman> Is it abovu staplering yourself with an office stapler?
17:28:11 -!- variable has changed nick to trout.
17:29:51 -!- edwardk has quit (Quit: Computer has gone to sleep.).
17:36:27 <impomatic> It's above stapling myself. I was standing perfectly still waiting for it to fly off and it stung me anyway.
17:44:17 -!- boily has joined.
17:48:44 <mroman> they don't fly off once the have the intention to possibly kill you
18:20:07 -!- Bike has joined.
18:23:12 -!- MindlessDrone has quit (Quit: MindlessDrone).
18:24:57 <ion> Free gaem http://store.steampowered.com/app/65790/
18:25:52 <fowl> oo and its from 2001 so i can probably run it on my laptop
18:30:08 <maurer> ion: how did you detect its freeness?
18:34:50 <ion> maurer: Exactly the same way you did.
18:48:48 <boily> welp. I launched minecraft again, after many months clean.
18:52:45 -!- MDude has joined.
18:54:42 -!- drdanmaku has joined.
19:01:03 -!- idris-bot has joined.
19:03:58 -!- edwardk has joined.
19:05:28 <Taneb> If I had this for dinner every day...
19:06:27 <Taneb> Ready meal £1.89 a day. Bread £1.19 every two days. If I managed breakfast, too, £1.29 for milk every 2 days, £2 for cereal every 5
19:06:47 <Taneb> > 1.89 + (1.19/2) + (1.29/2) + (2/5)
19:06:57 <Taneb> That's... really affordable
19:08:06 <boily> you can throw in veggies and tofu and yogurt!
19:08:25 <Taneb> boily, I think adding some form of meat would be a good first priority
19:08:39 <impomatic> I'm getting a pet skunk. They eat bees.
19:12:07 <Taneb> But so's this Indian ready-meal
19:12:16 <Taneb> And Co-op half-baked bread
19:15:28 <ais523_> eating the same food /every/ day is probably a bad idea
19:16:58 <Taneb> ais523_, yes, I'm not actually going to do this.
19:17:28 <Taneb> Just it's a lot healthier than what I've been eating recently, ie, next to nothing
19:17:35 <coppro> I'm familiar with that diet
19:18:17 -!- edwardk has quit (Ping timeout: 264 seconds).
19:21:01 -!- nucular has quit (Quit: Excess Food).
19:25:10 -!- edwardk has joined.
19:26:14 <pikhq> Eating the same food every day is how you turn into Sgeo.
19:26:58 <Sgeo> What, is turning into me the culmination of people's nightmares?
19:27:19 <Taneb> Sgeo, no, I'd just rather stay as me
19:27:37 <Taneb> Other than my diet and disorganized state, I like being me
19:28:06 * impomatic used to only eat food I'd gathered / caught
19:28:16 -!- nooodl_ has joined.
19:29:22 -!- Frooxius has joined.
19:31:29 -!- nooodl has quit (Ping timeout: 265 seconds).
19:49:36 -!- edwardk has quit (Quit: Computer has gone to sleep.).
19:49:42 <Sgeo> Apparently Flash animations can get Wikipedia articles
19:50:04 -!- shikhout has joined.
19:52:08 -!- kmc has joined.
19:52:09 -!- MoALTz has quit (Quit: Leaving).
19:53:02 -!- shikhin has quit (Ping timeout: 255 seconds).
19:53:45 <impomatic> Is a Flash animation more notable than an esolang?
19:54:02 <ais523_> I remember the great esolang purge from Wikipedia
19:54:04 <ais523_> where most of them were deleted
19:54:12 <ais523_> and I agreed with it, although there were some I argued to keep
19:54:34 <MDude> I guess one good be.
19:55:30 <kmc> I didn't mean to suggest that I was leaving the channel forever
19:55:34 <kmc> I just wanted a break
19:55:35 <impomatic> Even some regular programming languages have been wiped from Wikipedia.
19:55:46 <kmc> but I can't be an op anymore, as I am not well enough to perform the duties of the job
19:55:58 <MDude> An animation can easily be a widely ntoed cultural reference pount.
19:56:34 <impomatic> No-one added citations, so the languages were deemed to be non-notable.
19:56:37 <MDude> Whereas programming lanugages in general remain a mystery to most people.
19:58:36 <MDude> Another thing is that a lot of material on esolangs can be considered original research, whcih isn't allowed on Wikipedia.
20:02:03 <mroman> they only allow research that has been copied?
20:03:46 <ais523_> mroman: yeah, Wikipedia only allows secondary sources
20:04:06 <ais523_> and if they enforced that policy rather than screwing around with notability, then their rules would both be more objective and better, IMO
20:04:11 <mroman> so... how do they choose which esolangs to mention as examples?
20:04:22 <mroman> germane Wikipedia lists Loopy
20:04:27 <mroman> i've never heard of Loopy
20:04:37 <ais523_> mroman: there's no "they" about it, anyone can edit an example in
20:04:51 <ais523_> and there's no real team of people dedicated to taking the dubious examples back out
20:05:23 <mroman> there seem to be a lot of languages by Sean Heber listed
20:05:44 <ais523_> check the page history, see if he put them there
20:06:02 <mroman> Cow, Taxi, Whirl, 3Code
20:06:05 <MDude> They apparently also allow citing primary sources.
20:06:30 <MDude> They seem to mostly want to avoid anything being original to Wikipedia.
20:06:50 <MDude> Which makes sense, as Encyclopedias are for compiling information, not creating it.
20:08:04 <MDude> http://en.wikipedia.org/wiki/Wikipedia:No_original_research
20:08:11 <mroman> "Interessant an Ook! ist, dass es formal gesehen identisch mit Brainfuck ist."
20:08:17 <mroman> I don't find that interesting at all
20:08:31 <mroman> if anything Ook! is a different encoding for brainfuck programs
20:09:37 <mroman> (German WP says that the interesting part about Ook! is, that it is "formally identical" to brainfuck)
20:10:15 <mroman> ais523_: I don't edit WP articles about esolangs because I'm pretty sure I'm biased in some way :D
20:10:18 <olsner> suppose it's true in the sense that every other thing about ook is less interesting
20:10:52 <mroman> i.e. I don't like Ook! bit
20:10:57 <ais523_> Ook! is interesting in that it predates the flood of BF derivatives
20:11:04 <ais523_> I think it actually invented the class of BF equivalents
20:11:18 <ais523_> so it was interesting at the time, even if it's now been shown to belong to a particularly boring class of languages
20:11:33 <mroman> and I don't see what the fuzz about HQ9+ is
20:12:00 <MDude> It does have a fun name.
20:12:09 <ais523_> HQ9+ is a counterexample to a bunch of statements about esolangs
20:12:29 -!- nooodl_ has changed nick to nooodl.
20:12:31 <mroman> special, but the language itself is boring
20:12:39 <mroman> the idea is special, I can admit to that
20:12:46 <ais523_> that's what esolangs are for me, the idea
20:12:51 <ais523_> the language serves only as a way to express it
20:13:32 <mroman> I tend to value both I guess :)
20:15:24 <mroman> at first I triet to create esolangs that were as odd as I could imagine
20:16:28 <mroman> now I create languages to do homework and some other projects to try to find stuff that could be done better than current languages do
20:17:39 <mroman> That's why Burlesque has statistics stuff :D
20:18:21 <MDude> I should actually make stuff.
20:19:05 <mroman> I usually astonished when I look through the language reference to see how many built-ins it actually has
20:19:15 <mroman> and then how many built-ins I still miss
20:19:25 <mroman> it doesn't have a built-in to tell if a list has no duplicates
20:20:52 <mroman> it's the same as Brainfuck
20:21:06 <mroman> and there you have another brainfuck derivative .
20:21:29 <mroman> what'd be much more interesting
20:21:38 <mroman> a language that works with private public key
20:21:48 <MDude> Brainfuck 86: Like Bainfuck 13, but all the numerals are replaced with 9-n.
20:21:51 <mroman> only the creator of the language can actually write programs
20:22:01 <mroman> but everyone can interpret them
20:23:04 <nortti> quite a lot of my languages are something I scribbled into my math notebook
20:23:57 <MDude> I know that Spider's Square program i ahve in my userspace doesn't actually do what I wanted.
20:24:23 <MDude> Since there's no upper limit to the number of stands.
20:25:00 <MDude> I'll have to make a language where the data is just two points on a grid, and you compare thier relative positions or something.
20:25:40 <MDude> That way any program state can be represented as a fixed number of floating point numbers.
20:27:54 <ais523_> there's some uncertainty as to whether that's TC with two variables
20:28:01 <ais523_> and that's one point on the grid, plus the origin
20:28:10 <ais523_> however, floating point won't do without infinite precison
20:28:21 <ais523_> if you mean real numbers, say so
20:28:24 <MDude> Maybe not relative, then.
20:28:28 <ais523_> floating point is limited to a fixed number of significant figures
20:29:03 <MDude> They're to be treated in theory as real, but floats are the reccomended implementation.
20:29:25 -!- mhi^ has quit (Ping timeout: 252 seconds).
20:29:35 <MDude> Just because I wanted a model of memory that would handle out-of-memory errors differently.
20:29:58 <MDude> Instead of running out of space, it runs out of resolution.
20:30:10 -!- mhi^ has joined.
20:33:22 <MDude> You could optionally implement it in some way that offloads memory onto some sort of analog storage.
20:35:21 <ais523_> Perl actually has a warning for if you do ++ on a float and it doesn't change value
20:39:14 <MDude> I was going to try to make sure there was some upper limit to their values, possibly 1, with it being more about manipulating the trailing digits.
20:44:39 <elliott> MDude: and you'd e.g. store two reals by using an R^2 <-> R bijection, and so on, to build up data structures?
20:45:01 <elliott> it'd be cute to see how the choice of bijection interacts with fp inaccuracy
20:45:13 <impomatic> Does the language of Tierra count as esoteric?
20:45:44 <ais523_> are there any R^2 <-> R bijections that aren't horrendously discontinuous?
20:48:26 <nooodl> depends on "horrendously"
20:48:34 <MDude> I think so? I wasn't entirely sure how date structures would work.
20:48:35 <shachaf> Is horrendouly discontinuous different from discontinuous?
20:49:15 <impomatic> The language was designed for writing self-replicating programs which wouldn't break too badly when subjected to random mutations. Jumps are to a template, not an exact location.
20:49:58 -!- AnotherTest has quit (Ping timeout: 240 seconds).
20:52:35 -!- oerjan has joined.
21:01:14 -!- Patashu has joined.
21:03:29 <oerjan> boily: so do you actually have any canadian 1 cents
21:04:28 <oerjan> kmc: you know, not all ops need to be competent at everything. or else i couldn't be one either.
21:04:52 <oerjan> but it's your choice, anyway.
21:12:52 * impomatic ponders the identity of Ray's mysterious Go teacher.
21:13:11 <oerjan> probably some google employee.
21:15:13 <impomatic> I'll add the Tierra language to the wiki (at some point). At the moment I'm not even sure it's got a name.
21:15:28 -!- Phantom_Hoover has joined.
21:15:44 <kmc> oerjan: I think I would get in the way of other people being competent
21:16:04 -!- Patashu has quit (Disconnected by services).
21:16:04 -!- Patashu_ has joined.
21:16:35 <Phantom_Hoover> 20:45:44: <ais523_> are there any R^2 <-> R bijections that aren't horrendously discontinuous?
21:17:01 <Phantom_Hoover> well that's the point of the hilbert curve, though it's still very discontinuous
21:18:16 <Phantom_Hoover> (you can't have a continuous bijection of course because that would make the two spaces homeomorphic)
21:22:02 <oerjan> that's not a bijection though, only an onto map, although it may have bounded number of inverse images?
21:25:25 <oerjan> Phantom_Hoover: there are some spaces that have continuous bijections in at least one direction without being homeomorphic. i assume R^2 <-> R are not among them. hm i wonder if you can have bijections both ways (not inverses of each other, of course)
21:25:43 -!- Patashu_ has quit (Ping timeout: 276 seconds).
21:25:50 <oerjan> R^2 -> R is impossible due to invariance of domain theorem
21:27:33 * elliott wonders about a way to "approximate" a [0,1] -> {0,1} function (like floats are an approximation of R)
21:28:20 <oerjan> R -> R^2 i am not immediately sure why it is impossible
21:35:59 <nooodl> oerjan: i'm sure a surjection is possible
21:36:08 <nooodl> http://math.stackexchange.com/a/358061/141424 mhm
21:39:05 <oerjan> nooodl: i'm speaking about bijections
21:39:28 <oerjan> boily: you'll be happy no one bet agaist, then.
21:41:26 <nooodl> isn't "a bijection A -> B" the same thing as "a bijection B -> A" when you just consider the inverses
21:41:57 <nooodl> i mean you're just talking about one-to-one correspondences between these two sets right!
21:43:24 <oerjan> nooodl: continuous in one direction only
21:48:08 <boily> ow. ooooooow. IT BUUUURNS!
21:48:19 <boily> (yes, I bit in a particularly powerful hot pepper.)
21:50:03 <oerjan> the revenge of the chickens
21:54:48 -!- ais523_ has quit (Quit: Page closed).
22:13:32 -!- shikhout has quit (*.net *.split).
22:13:32 -!- Frooxius has quit (*.net *.split).
22:13:32 -!- nooodl has quit (*.net *.split).
22:13:32 -!- hk3380 has quit (*.net *.split).
22:13:32 -!- metasepia has quit (*.net *.split).
22:13:33 -!- monotone has quit (*.net *.split).
22:13:33 -!- pdxleif has quit (*.net *.split).
22:13:33 -!- jconn has quit (*.net *.split).
22:13:33 -!- jix has quit (*.net *.split).
22:13:33 -!- trout has quit (*.net *.split).
22:13:34 -!- Speed` has quit (*.net *.split).
22:13:34 -!- lifthrasiir has quit (*.net *.split).
22:13:34 -!- kmc has quit (*.net *.split).
22:13:34 -!- boily has quit (*.net *.split).
22:13:35 -!- Sgeo has quit (*.net *.split).
22:13:35 -!- FireFly has quit (*.net *.split).
22:13:35 -!- skarn has quit (*.net *.split).
22:13:36 -!- shachaf has quit (*.net *.split).
22:13:36 -!- newsham has quit (*.net *.split).
22:13:36 -!- rodgort has quit (*.net *.split).
22:13:36 -!- erdic has quit (*.net *.split).
22:13:36 -!- myname has quit (*.net *.split).
22:13:37 -!- Phantom_Hoover has quit (*.net *.split).
22:13:37 -!- ^v has quit (*.net *.split).
22:13:37 -!- conehead has quit (*.net *.split).
22:13:38 -!- Bike has quit (*.net *.split).
22:13:39 -!- sebbu has quit (*.net *.split).
22:13:39 -!- douglass1 has quit (*.net *.split).
22:13:39 -!- b_jonas has quit (*.net *.split).
22:14:19 -!- ^v has joined.
22:17:27 <oerjan> > let (!x, y) = (undefined, "hm") in y
22:18:02 <olsner> > let ~(!x, y) = (undefined, "hm") in y
22:18:55 <oerjan> > let (~(!x,y), z) = ((undefined, "hm"), "oh") in z
22:19:16 <oerjan> > let ((!x,y), z) = ((undefined, "hm"), "oh") in z
22:19:16 -!- b_jonas has joined.
22:19:17 -!- Bike has joined.
22:19:49 -!- douglass_ has joined.
22:19:49 -!- Phantom_Hoover has joined.
22:19:49 -!- kmc has joined.
22:19:49 -!- shikhout has joined.
22:19:49 -!- Frooxius has joined.
22:19:49 -!- nooodl has joined.
22:19:49 -!- 17SAAFQ17 has joined.
22:19:49 -!- boily has joined.
22:19:49 -!- conehead has joined.
22:19:49 -!- hk3380 has joined.
22:19:49 -!- metasepia has joined.
22:19:49 -!- Sgeo has joined.
22:19:49 -!- lifthrasiir has joined.
22:19:49 -!- Speed` has joined.
22:19:49 -!- trout has joined.
22:19:49 -!- jix has joined.
22:19:49 -!- jconn has joined.
22:19:49 -!- pdxleif has joined.
22:19:49 -!- monotone has joined.
22:19:49 -!- myname has joined.
22:19:49 -!- erdic has joined.
22:19:49 -!- rodgort has joined.
22:19:49 -!- shachaf has joined.
22:19:49 -!- newsham has joined.
22:19:49 -!- skarn has joined.
22:19:49 -!- FireFly has joined.
22:19:49 -!- sebbu has joined.
22:19:49 -!- douglass1 has joined.
22:19:49 -!- 17SAAA20J has joined.
22:20:16 -!- 17SAAA20J has quit (Write error: Broken pipe).
22:20:18 -!- douglass1 has quit (Write error: Broken pipe).
22:20:18 -!- 17SAAFQ17 has quit (Write error: Broken pipe).
22:21:24 -!- drdanmaku has quit (Quit: Connection closed for inactivity).
22:24:13 -!- Frooxius has quit (Quit: *bubbles away*).
22:26:40 -!- Frooxius has joined.
22:27:35 <metasepia> CYUL 182200Z 25012KT 30SM FEW050 FEW240 16/M01 A3012 RMK SC1CI1 SC TR CI TR SLP202
22:29:06 <boily> un bon dimanche à toi aussi!
22:30:04 <quintopia> this rainy cloudy day suddenly cleared up and now it's gorgeous and sunny
22:30:05 -!- edwardk has joined.
22:31:39 <metasepia> KATL 182152Z 00000KT 10SM -RA SCT004 BKN090 BKN130 OVC200 16/14 A3020 RMK AO2 RAE16B38 SLP226 P0001 T01610144
22:31:57 <boily> yours is quite more humid than mine.
22:32:50 <quintopia> i think it may be raining still in atlanta
22:33:33 <metasepia> KGVT 182215Z AUTO 16008KT 10SM CLR 26/14 A3003 RMK AO2
22:36:20 <metasepia> KVUO 182153Z AUTO 15003KT 10SM -RA BKN075 OVC090 14/10 A2989 RMK AO2 RAE11B40 SLP123 P0001 T01390100
22:37:55 <metasepia> LOWI 182220Z AUTO VRB03KT 9999 FEW070 SCT100 13/10 Q1013
22:39:07 <boily> quintopia: you're in Greenville now?
22:39:33 <metasepia> CYVR 182200Z 24009KT 20SM FEW045 FEW082 SCT230 17/12 A2981 RMK SC1AC1CI2 TCU EMBDD SLP096 DENSITY ALT 300FT
22:39:56 <oerjan> elliott: i was wtfing at that very fast netjoin
22:42:17 <int-e> > let !(~(!(~(!x)))) = undefined in ()
22:42:29 -!- Frooxius has quit (Quit: *bubbles away*).
22:42:30 <int-e> > let ~(!(~(!x))) = undefined in ()
22:44:49 -!- Frooxius has joined.
22:46:33 <quintopia> boily: somewhere between. greenville is slightly closer
22:54:25 <Sgeo> Is my life turning into a tautology?
22:54:41 <boily> Sgeo: you have turned into Sgeo.
22:55:04 <ion> sgeo: Your life is your life. I can’t comment more than i can comment.
22:55:11 <Sgeo> NOOOOOOOO!!!!!!!!
22:55:40 <Taneb> What've you all been working on lately?
22:56:13 <int-e> "no" is no tautology.
22:56:43 <boily> Taneb: some dentistal prosthesisery.
22:57:04 <Taneb> boily, that sounds kind of icky.
22:58:16 <boily> it's fun! it's all digital! it involves black magic with quaternions!
23:02:07 -!- nooodl has quit (Ping timeout: 264 seconds).
23:02:13 <oerjan> we can now fit your wisdom teeth into a fourth dimension, avoid removing them
23:03:31 <oerjan> the claims this leads to mixing with your grandfather's teeth are entirely unfounded
23:04:37 <boily> I'll have to grep the code Tuesday morning for any grandfathery classes.
23:04:41 <int-e> oerjan, are you in cahoots with the tooth fairy?
23:05:46 <oerjan> int-e: i'm just helping em save on interest by borrowing money across time
23:06:17 <oerjan> quintopia: no, that's ørjan
23:06:22 <HackEgo> Ørjan is oerjan's good twin. He's banned in the IRC RFC for being an invalid character. Sometimes he publishes papers.
23:07:36 <Taneb> oerjan, what've you and ørjan been up to?
23:08:28 <oerjan> what makes you think i associate with that goody two-shoes
23:08:51 <ion> Too bad IRC uses ISO 646 FI instead of ISO 646 NO for nicks.
23:08:54 <quintopia> oerjan: i meant to say 'oerjan is krampus' my bad
23:10:03 <ion> |rjan decoded from ISO 646 NO would be ørjan.
23:10:11 <oerjan> yes that would be bad.
23:15:26 -!- kmc has left.
23:37:56 -!- FreeFull has quit (Quit: Sleeptimes).
23:39:28 <quintopia> my mom asked me what 'je ne sais quois' means. she doesn't realize i've told her.
23:40:07 <oerjan> `addquote <quintopia> my mom asked me what 'je ne sais quois' means. she doesn't realize i've told her.
23:40:09 <HackEgo> 1195) <quintopia> my mom asked me what 'je ne sais quois' means. she doesn't realize i've told her.
23:45:22 <Taneb> Goodnight, everyone.
23:47:05 <boily> uhm. once a quote has been quoted, is it correct to fix a small French orthography mistake?
23:48:37 <oerjan> boily: no, the typos are now written in stone hth
23:48:50 <oerjan> (i assume you mean the quoi*s*
23:49:03 * boily writhes in agony. «AAAAAAAAAAAAAAAAAARGH!»
23:49:15 <boily> (your assumption is right on.)
23:49:42 <oerjan> you could ask quintopia to say it again, correctly. then it's almost not cheating.
23:50:35 <boily> nah. it's not like I consiously add very bad Chinese to the PDF one time...
23:51:12 <oerjan> but we have no chinese in the channel to agonize, do we?
23:51:34 <oerjan> (if we did we'd have been hacked out of existence by now)
23:52:22 <boily> someone here ought to learn some Chinese language. (I'm making an effort here with some mangled Japanese, but it's not in the same family.)
23:52:58 <oerjan> (as a norwegian i feel it is increasingly becoming my duty to insult chinese for their sensitivity. is this bad?)
23:55:09 <oerjan> (https://en.wikipedia.org/wiki/China%E2%80%93Norway_relations#2010_Nobel_Peace_Prize)
23:55:19 <oerjan> (and following sections)
23:56:35 <HackEgo> ~&al?\~&ar ~&aa^&~&afahPRPfafatPJPRY+ ~&farlthlriNCSPDPDrlCS2DlrTS2J,^|J/~& ~&rt!=+ ^= ~&s+ ~&H(-+.|=&lrr;,|=&lrl;,|=≪+-, ~&rgg&& ~&irtPFXlrjrXPS; ~&lrK2tkZ2g&& ~&llrSL2rDrlPrrPljXSPTSL)+-,
23:56:55 <int-e> . o O ( would it be mean to say that I don't see much difference between those two quotes? )
23:57:35 <boily> there was context. it got mugged in a dark alley. by drunken sailors wielding sharpened bamboo poles.
23:57:46 <HackEgo> 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.
23:59:19 <HackEgo> Go is a common verbal game programming language invented by the Germanic Taneb tribes in the strategic territories of East Asia.
00:02:47 <boily> fowl: I wrote “They are a sneaky kind of chicken.” in your section header.
00:18:15 <HackEgo> 307) <cpressey> `quote django <HackEgo> 352) <olsner> django is named after a person? <olsner> thought it would be a giraffe or something <cpressey> thankfully only one \ 308) <monqy> `quote django <HackEgo> 352) <olsner> django is named after a person? <olsner> thought it would be a giraffe or something \ 407) <cpressey> `quote django
00:23:17 <HackEgo> 819) <olsner> fungot: what's your view on angels and other otherworldly beings? <fungot> olsner: well i'm mentioning theoretical image to be dumped in rain forests of laukaa.
00:23:52 -!- nisstyre has quit (Quit: WeeChat 0.4.3).
00:24:16 -!- nisstyre has joined.
00:28:17 -!- edwardk has quit (Quit: Computer has gone to sleep.).
00:32:16 -!- mhi^ has quit (Quit: Lost terminal).
00:32:52 -!- yorick has quit (Remote host closed the connection).
00:33:45 -!- tromp has joined.
00:56:14 -!- Phantom_Hoover has quit (Ping timeout: 258 seconds).
00:56:50 -!- tromp has quit (Remote host closed the connection).
01:05:15 -!- shikhout has quit (Remote host closed the connection).
01:14:42 -!- boily has quit (Quit: SIDE CHICKEN).
01:14:45 -!- metasepia has quit (Remote host closed the connection).
01:27:58 -!- aloril has quit (Ping timeout: 240 seconds).
01:42:07 -!- aloril has joined.
02:02:11 -!- Phantom_Hoover has joined.
02:28:18 -!- edwardk has joined.
02:34:30 -!- edwardk has quit (Quit: Computer has gone to sleep.).
02:35:45 <oerjan> no, blunt, that is not a good way to convince humans not to do something.
02:38:31 <oerjan> (this is freefall btw)
02:47:07 -!- edwardk has joined.
02:47:27 -!- oerjan has quit (Quit: Nity).
02:49:00 -!- ^v has quit (Quit: http://i.imgur.com/Akc6r.gif).
02:57:26 -!- ^v has joined.
03:03:33 -!- Phantom_Hoover has quit (Remote host closed the connection).
03:20:48 -!- edwardk has quit (Quit: Computer has gone to sleep.).
03:36:57 -!- john3213 has joined.
03:42:00 -!- john3213 has left.
04:18:47 -!- tromp has joined.
04:18:51 -!- tromp has quit (Remote host closed the connection).
04:44:08 -!- Sorella has quit (Quit: It is tiem!).
05:07:29 -!- hk3380 has quit (Ping timeout: 264 seconds).
05:11:30 -!- Guest49187 has joined.
05:12:25 -!- Guest49187 has left.
05:12:29 -!- Guest49187 has joined.
05:12:35 -!- Guest49187 has left.
05:40:45 -!- MDude has changed nick to MDream.
05:42:29 -!- password2 has joined.
05:44:45 -!- adu has joined.
06:00:19 -!- hk3380 has joined.
06:25:24 -!- adu has quit (Quit: adu).
06:28:05 -!- edwardk has joined.
06:36:18 -!- ^v has quit (Quit: http://i.imgur.com/Akc6r.gif).
06:45:10 -!- ^v has joined.
06:49:28 -!- ^v has quit (Client Quit).
06:52:06 -!- idris-bot has quit (Quit: Terminated).
06:56:53 <mroman> Is there a fast way to find a,b for u*a + v*b + ab = z?
06:58:32 <mroman> Bike: given that a != 0 and b != 0
06:58:41 <Bike> i mean, which of u,v,z
06:59:12 <lifthrasiir> well, it is equivalent to `(u+a)*(v+b) = z + u*v`, so it is really a factorization problem?
06:59:34 <mroman> and z != 0 for that matter :)
07:01:19 <mroman> so there's no way to solve it over the integer
07:01:23 <mroman> i.e. like diophantines?
07:01:35 <mroman> if it's a factorization problem then the answer is probably no.
07:02:39 <Bike> well it's diophantine but also linear, so probably not impossible
07:03:33 <Bike> um, i think so anyway.
07:06:16 <mroman> well, if you can solve it efficiently you might also be able to solve factorization efficiently ;)
07:07:55 -!- idris-bot has joined.
07:08:04 <mroman> would it help if a = b?
07:08:23 <mroman> i.e. u*a + v*a + a^2 = z
07:08:31 <mroman> that's a quadratic equation?
07:08:41 <Bike> yeah, i guess it's not linear anyway.
07:08:59 <Bike> but hey! that pretty fucking constrains the solutions
07:11:55 <mroman> too much of a constraint
07:12:34 <lifthrasiir> mroman, indeed; a^2 + (u+v)a - z = 0, so rational root theorem gives that `a` can only be one of +/- 1/z' where z divides z'.
07:15:47 <mroman> but a easier one than the original
07:15:51 <mroman> that was the point actually
07:17:01 <Bike> yes, i suppose square root is easier to compute
07:17:24 <lifthrasiir> mroman: just out of curiosity, what's the context of that problem?
07:17:27 -!- conehead has quit (Quit: Computer has gone to sleep).
07:18:30 <mroman> Bike: not the square root
07:19:04 <mroman> lifthrasiir: prime factorization
07:20:18 <HackEgo> pbflist: shachaf Sgeo quintopia ion
07:20:27 <shachaf> should've signed up for deluxe
07:23:17 <mroman> but it also works for regular numbers too
07:27:59 <mroman> it's a silly thing though
07:28:27 <mroman> the closer together factors are the easier it is to factorize the number
07:32:19 <mroman> lifthrasiir: I was just looking for some really easy to implement factorization method that is faster than O(sqrt(n)) and doesn't require a table or large amounts of memory
07:38:28 <Bike> is this like, an instruction for your isa
07:39:06 -!- shikhin has joined.
07:39:28 <lifthrasiir> something like http://stackoverflow.com/a/2274520 ?
07:39:31 <Bike> instruction set
07:39:34 -!- shikhin has changed nick to Guest8266.
07:40:52 <Bike> well, rho doesn't need a table, it seems
07:41:04 -!- Guest8266 has quit (Client Quit).
07:41:14 <Bike> nondeterministic, tho
07:41:22 -!- shikhout has joined.
07:41:42 <Bike> oh, i remember reading about brent's cycle thing before...
07:42:19 <mroman> http://codepad.org/5sFOZjZB <- that's essentially it
07:42:24 -!- shikhout has changed nick to foofoo.
07:42:26 <mroman> u and v are guesses of two factors
07:42:39 -!- foofoo has changed nick to shikhout.
07:42:48 <mroman> and depending on how good you guessed the faster it is
07:43:09 <mroman> it also does a trial division "on-the-side"
07:43:18 <mroman> for numbers ilke 11*17*607*353*...
07:43:37 <mroman> which would take much more time by just adjusting the guess because there's a really small factor in it
07:44:21 -!- shikhout has changed nick to shikhin.
07:46:42 <Bike> seems like an odd thing to put as an instruction, too. "even polynomial evaluation would make more sense to me"
08:02:26 -!- Tritonio has joined.
08:15:09 -!- password2 has quit (Ping timeout: 265 seconds).
08:20:23 -!- augur has quit (Ping timeout: 252 seconds).
08:26:54 -!- MindlessDrone has joined.
08:28:34 -!- Bike has quit (Ping timeout: 240 seconds).
08:34:29 -!- MindlessDrone has quit (Ping timeout: 264 seconds).
08:36:14 -!- augur has joined.
08:45:06 -!- nooodl has joined.
08:45:29 -!- Patashu has joined.
08:49:14 -!- nooodl has quit (Ping timeout: 240 seconds).
08:49:15 -!- MindlessDrone has joined.
09:36:32 -!- Tritonio has quit (Ping timeout: 255 seconds).
09:45:36 -!- edwardk has quit (Quit: Computer has gone to sleep.).
09:51:13 -!- Patashu_ has joined.
09:51:13 -!- Patashu has quit (Disconnected by services).
09:53:55 <mroman> @ask Bike like horner?
10:33:18 -!- Phantom_Hoover has joined.
10:40:33 <mroman> one possible constraint would be u = v
10:40:39 <mroman> leading to (a + b)*u + a*b = z
10:40:49 <mroman> which is probably not easier to solve
10:46:37 -!- Phantom__Hoover has joined.
10:49:59 -!- Phantom_Hoover has quit (Ping timeout: 252 seconds).
10:55:30 <Jafet> I should ask int-e to export gcdExtInteger so lambdabot can factor numbers
10:58:29 <nortti> read that as "godExtInteger" and got mildly confused
10:59:16 <fungot> Jafet: and, i've learned! i'll just move back here and never speak again in the next story. it's like david, and we never will! what's to be gained the ability to look back and be aghast at all the animals we kill and eat us probably! if not, we can make the cutest cards ever for a series of puns.
10:59:51 <nortti> how do I check what style is fungot currently using?
10:59:51 <fungot> nortti: t-rex, i don't know a few dollars! you're on! it only claims that there, chocochops have a different chemical makeup, but taste and never gets old and is everyone's favorite, without a little placard beneath that, " you must punch! i love drinking delicious punch, probably because of how it's so delicious because i like to keep my friends and status in society, i am, a little!
11:00:24 <fungot> Available: agora alice c64 ct darwin discworld enron europarl ff7 fisher fungot homestuck ic irc iwcs jargon lovecraft nethack oots pa qwantz* sms speeches ss wp youtube
11:01:28 <Jafet> Isn't it weird that a small corpus makes better fungot
11:01:28 <fungot> Jafet: as a man concerned, t-rex, that going shopping was your default activity?
11:01:58 <fungot> Selected style: darwin (Books by Charles Darwin -- you know, that evilution guy)
11:03:51 <Jafet> fungot can now select words naturally.
11:03:52 <fungot> Jafet: hon. john collier, for/ long- styled form,/ tubes were larger in every dimension. " 3? 3. falconer, that/ plants must have been a little timid in publishing their belief on this head: prof. fnord in.
11:04:21 <nortti> "plants must have been a little timid in publishing their belief on this head"
11:04:44 <nortti> also, where does the "fnord" come from?
11:05:44 <Jafet> `quote fnord fnord fnord
11:05:44 <HackEgo> 1183) <int-e> fungot has not done me any harm yet <fungot> int-e: no niinku pl niinku fnord niinku fnord fnord fnord
11:08:15 <Jafet> I wonder what choice word charlie had that was worthy of fnording out
11:11:24 -!- KingOfKarlsruhe has joined.
11:13:54 <HackEgo> [wiki] [[Talk:Brainfuck]] http://esolangs.org/w/index.php?diff=39558&oldid=39557 * Maxdefolsch * (+444) /* My optimizing interpreter again */
11:36:31 -!- shikhout has joined.
11:36:59 -!- yorick has joined.
11:39:36 -!- shikhin has quit (Ping timeout: 265 seconds).
11:43:04 -!- boily has joined.
11:53:43 <mroman> > [[x|y<-[1..n],y `mod` x == 0]|n<-[1..10]]
11:53:45 <lambdabot> It could refer to either ‘L.x’, defined at L.hs:150:1
11:53:45 <lambdabot> imported from ‘Debug.SimpleReflect’ at L.hs:110:1-26
11:53:45 <lambdabot> (and originally defined in ‘simple-reflect-0.3.2:De...
11:54:13 <mroman> > [[x|y<-[1..n],y `mod` x == 0]|x<-[1..10]]
11:54:27 <mroman> > [[x|y<-[1..x],y `mod` x == 0]|x<-[1..10]]
11:54:28 <lambdabot> [[1],[2],[3],[4],[5],[6],[7],[8],[9],[10]]
11:54:49 <mroman> > [[x|y<-[1..x],x `mod` y == 0]|x<-[1..10]]
11:54:51 <lambdabot> [[1],[2,2],[3,3],[4,4,4],[5,5],[6,6,6,6],[7,7],[8,8,8,8],[9,9,9],[10,10,10,10]]
11:55:13 <mroman> > [[y|y<-[1..x],x `mod` y == 0]|x<-[1..10]]
11:55:15 <lambdabot> [[1],[1,2],[1,3],[1,2,4],[1,5],[1,2,3,6],[1,7],[1,2,4,8],[1,3,9],[1,2,5,10]]
11:55:28 <mroman> I officially won the record for most errors in a single line of code :D
11:59:02 <MDream> Hmm, there's no Zelda fungot.
11:59:03 <fungot> MDream: charles island. but it has not turned out far more crooked and confused than it is, however, were strongly affected;/ first having all/ tentacles but thirty-six inflected; after 6 hrs. surrounding fluid just tinged pink; they were then left in water for 24 hrs.
11:59:54 -!- MDream has changed nick to MDude.
12:00:12 <MDude> That does not sound like a good time to have tentacles.
12:00:33 <MDude> Might be even worse for boned limbs, though.
12:04:27 <boily> tentacle conjugation is ever so complex.
12:20:40 -!- Sgeo has quit (Read error: Connection reset by peer).
12:29:27 -!- rodgort has quit (Quit: ERC Version 5.3 (IRC client for Emacs)).
12:31:38 -!- impomatic has quit (Ping timeout: 240 seconds).
12:32:05 -!- boily has quit (Quit: WeeChat 0.4.2).
12:33:07 -!- rodgort has joined.
12:36:37 -!- shikhout has changed nick to shikhin.
12:47:41 -!- aloril has quit (Ping timeout: 252 seconds).
12:54:16 -!- aloril has joined.
12:55:41 -!- Sorella has joined.
12:57:04 -!- tromp has joined.
12:57:39 -!- tromp has quit (Remote host closed the connection).
12:58:34 -!- edwardk has joined.
13:23:35 -!- Phantom___Hoover has joined.
13:25:14 -!- Phantom__Hoover has quit (Ping timeout: 240 seconds).
13:26:56 -!- Patashu_ has quit (Ping timeout: 255 seconds).
13:27:17 -!- augur has quit (Ping timeout: 264 seconds).
13:28:01 -!- Phantom___Hoover has quit (Ping timeout: 252 seconds).
13:30:28 -!- augur has joined.
13:32:24 -!- oerjan has joined.
13:38:08 <oerjan> octopi don't send spam. this is one of the many ways in which they are superior to humans.
13:39:13 <quintopia> this is only because they haven't figured out how to use keyboards yet
13:39:35 <quintopia> just you wait, one day octopodes will be the most pernicious senders of spam on the planet
13:39:40 <MDude> We jsut need to give them some that are water-resistant.
13:40:12 <int-e> (the last message before oerjan's "7" was something about tentacle conjugation, whatever that is.)
13:40:14 <quintopia> not only are they greedy, they have no compassion
13:41:27 <MDude> Would probably hlep to let them live longer than three years, since they'll spend a big chunk of that just growing up from tiny hatchlings and, then they need to learn how to read.
13:41:53 <MDude> That second comma should be one word to the left.
13:43:47 <quintopia> they only live three years: another one of the many ways in which they are superior to humans
13:45:58 <Taneb> People who know more about C, someone in another channel is asking whether "*(u8_t *)ADDRESS_LITERAL_MACRO[64]" is valid
13:54:56 <fizzie> I'm pretty sure that sort of depends on what ADDRESS_LITERAL_MACRO expands to, or is.
13:56:39 <fizzie> (Guessing from the name, probably not.)
13:57:21 <fizzie> The precedence goes *(u8_t *)(ADDRESS_LITERAL_MACRO[64]) anyway, so if it is something you can stick [64] after, then it's at least syntactically sensible.
13:58:25 <oerjan> i'd imagine the precedence, too, depends on what it expands to.
13:58:36 <Taneb> <Ajsdf> Taneb: it is something along the lines of 0x0450 being a hex representation of a memory address on a peice of hardware
14:00:47 -!- augur has quit (Quit: Leaving...).
14:02:36 <fizzie> If it expands to an integer constant, then that's not okay.
14:02:51 <fizzie> (And I was about to come back to mention what oerjan said.)
14:04:31 <Taneb> <Ajsdf> perhaps (*(u8_t *)ADDRESS_LITERAL_MACRO)[64]
14:04:40 -!- KingOfKarlsruhe has quit (Quit: Leaving.).
14:04:50 <fizzie> That doesn't really make sense either, unless u8_t is a pointer type.
14:05:07 <fizzie> Plain *(u8_t *)ADDRESS_LITERAL_MACRO would be quite reasonable, and ((u8_t *)ADDRESS_LITERAL_MACRO)[64] wouldn't be too bizarre either, but that's about it.
14:05:47 <fizzie> The type of (*(u8_t *)ADDRESS_LITERAL_MACRO) is u8_t (not u8_t *), and it doesn't *sound* like something you can [64], but of course it *could* be.
14:10:06 -!- impomatic has joined.
14:18:56 -!- hk3380 has quit (Ping timeout: 258 seconds).
14:21:39 -!- sign has quit (Ping timeout: 252 seconds).
14:24:15 -!- Bike has joined.
14:37:48 <Taneb> @tell fizzie Ajsdf says thanks
14:43:00 <HackEgo> [wiki] [[Talk:Brainfuck]] http://esolangs.org/w/index.php?diff=39559&oldid=39558 * Oerjan * (+170) /* My optimizing interpreter again */ binaries
14:45:35 <HackEgo> [wiki] [[PHL 1.0]] M http://esolangs.org/w/index.php?diff=39560&oldid=39554 * Oerjan * (+20) /* Examples */ links
14:46:28 <HackEgo> [wiki] [[PHL 1.0]] M http://esolangs.org/w/index.php?diff=39561&oldid=39560 * Oerjan * (+4) /* Computational class */ another link
14:49:34 -!- nooodl has joined.
14:57:05 -!- sign has joined.
14:59:50 -!- sign has quit (Changing host).
14:59:50 -!- sign has joined.
15:11:49 -!- augur has joined.
15:16:10 <mroman> I hope this isn't just a coincidence
15:17:51 -!- edwardk_ has joined.
15:18:33 -!- hk3380 has joined.
15:19:07 -!- edwardk has quit (Ping timeout: 240 seconds).
15:23:47 -!- FreeFull has joined.
15:25:07 -!- augur has quit (Ping timeout: 240 seconds).
15:26:17 <mroman> Taneb: (q + a)*(r + a) = b
15:26:30 <mroman> I'm trying to find q and r, so that the above equation holds
15:30:12 <Bike> this conversation makes the uncomputability of diophantines make a lot more sense
15:30:53 <Bike> mroman: yes, like horner. i was thinking of the perennial "lol CISC" instruction. http://uranium.vaxpower.org/~isildur/vax/week.html
15:33:31 <Taneb> mroman, So... (q + 1) * (r = 1) = b/a?
15:34:25 <Taneb> What do you know about all the values?
15:36:37 <mroman> they are all positive integers
15:37:55 * oerjan fails Taneb in algebra
15:41:20 * oerjan swats Taneb for responding with insufficient horror -----###
15:41:26 <oerjan> you should learn from boily
15:42:16 <oerjan> sorry, *not responding with sufficient
15:42:51 -!- augur has joined.
15:44:18 * oerjan fails himself in grammar
15:44:23 <oerjan> AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA
15:47:34 <int-e> I think no matter how many A's you give yourself, it won't become a failing grade.
15:48:16 * oerjan fails himself in grading
15:48:17 <Taneb> oerjan, aaaaaah what did I do
15:48:21 <oerjan> FFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFF
15:48:51 <oerjan> Taneb: i'm pretty sure (q + 1) * (r = 1) = b/a is not equivalent to (q + a)*(r + a) = b
15:49:17 <Taneb> Well, the = was a type
15:49:32 <Taneb> Oh dear god you are right
15:49:41 <Taneb> Some kind of monster evidently
15:49:57 <oerjan> thank you for relieving of the need to say so, Taneb
15:50:10 * oerjan fails himself in grammar again
15:50:38 <oerjan> i seem to be out of capital letters
15:50:44 <int-e> please don't relieve yourself on the channel?!
15:50:59 <int-e> english is a horrible language.
15:52:06 -!- oerjan has quit (Quit: RRRRRRRRRRRRRRRRRRRRRRRRRRRRRRRRRRRRRRRRRRRRRR).
15:58:02 <Taneb> mroman, if they're all positive integers, q > 1
16:01:27 <mroman> q and r are both always > 1
16:08:46 -!- Phantom_Hoover has joined.
16:13:24 -!- Bike has quit (Ping timeout: 252 seconds).
16:15:12 -!- Bike has joined.
16:17:47 <HackEgo> olist (952): shachaf oerjan Sgeo FireFly boily nortti
16:20:47 -!- mhi^ has joined.
16:24:33 -!- conehead has joined.
16:33:59 -!- kmc has joined.
16:34:22 <FreeFull> The IP address of a website I wanted to visit is gone from DNS
16:36:24 <kmc> google's rubik's cube is made using CSS transforms
16:38:50 -!- boily has joined.
16:40:07 <FreeFull> Dammit, I can't find anything on the internet indicating why the website is not accessible
16:40:24 <FreeFull> Other than that it seems that other people are also searching for why it isn't accessible
16:40:45 <kmc> I was wondering if it was WebGL, but I guess that's still not so widely supported
16:43:49 <FreeFull> I find physical rubik's cubes much easier to solve than computerised ones
16:48:05 <mroman> how do i rotate the cube?
16:49:09 <boily> you click in the emptiness and drag.
16:56:16 <quintopia> boily: this sounds like a philosophy of life
16:59:58 <boily> I prefer to ride a bike through the Lanes of Nothingness, under the Shade of the Void Trees.
17:03:02 <HackEgo> [wiki] [[0(nop^)]] N http://esolangs.org/w/index.php?oldid=39562 * John Misciagno * (+1261) Created page with "'''0(nop^)''' is a stack-based esoteric programming language with numeric function names. == Operators == '''+''', '''-''', '''*''', '''/''', '''%''', '''<''', '''>''', and ..."
17:05:24 <boily> interesting fishy etymology → http://en.wikipedia.org/wiki/Abudefduf
17:08:14 <HackEgo> [wiki] [[0(nop^)]] http://esolangs.org/w/index.php?diff=39563&oldid=39562 * John Misciagno * (+95)
17:09:43 -!- conehead has quit (Quit: Computer has gone to sleep).
17:10:06 <HackEgo> [wiki] [[0(nop^)]] http://esolangs.org/w/index.php?diff=39564&oldid=39563 * John Misciagno * (-25)
17:11:18 <HackEgo> [wiki] [[0(nop^)]] http://esolangs.org/w/index.php?diff=39565&oldid=39564 * John Misciagno * (-38)
17:14:18 -!- password2 has joined.
17:14:51 -!- conehead has joined.
17:21:48 <HackEgo> [wiki] [[0(nop^)]] http://esolangs.org/w/index.php?diff=39566&oldid=39565 * John Misciagno * (-31)
17:25:49 -!- conehead has quit (Quit: Computer has gone to sleep).
17:26:23 <HackEgo> [wiki] [[0(nop^)]] http://esolangs.org/w/index.php?diff=39567&oldid=39566 * John Misciagno * (+68)
17:28:51 <HackEgo> [wiki] [[0(nop^)]] http://esolangs.org/w/index.php?diff=39568&oldid=39567 * John Misciagno * (-8)
17:29:27 <HackEgo> [wiki] [[0(nop^)]] http://esolangs.org/w/index.php?diff=39569&oldid=39568 * John Misciagno * (+16)
17:29:58 -!- conehead has joined.
17:38:44 <HackEgo> [wiki] [[0(nop^)]] http://esolangs.org/w/index.php?diff=39570&oldid=39569 * John Misciagno * (+2)
17:40:16 -!- shikhin has quit (Ping timeout: 240 seconds).
17:42:14 -!- shikhin has joined.
17:43:50 <HackEgo> [wiki] [[0(nop^)]] http://esolangs.org/w/index.php?diff=39571&oldid=39570 * John Misciagno * (+31)
17:49:59 <impomatic> Is the only way to recurse / loop in 0(nop^) via ( ) and ^?
17:50:17 -!- Slereah has joined.
17:52:16 -!- Slereah_ has quit (Ping timeout: 276 seconds).
17:55:42 -!- Manu has joined.
17:56:06 -!- Manu has changed nick to Guest58936.
17:56:15 -!- Guest58936 has changed nick to Cyragia.
17:56:27 <myname> if you really don't like java but have to write something for jvm, which language would you choose?
17:56:29 <HackEgo> [wiki] [[0(nop^)]] http://esolangs.org/w/index.php?diff=39572&oldid=39571 * John Misciagno * (+250)
17:57:02 <boily> Cyragia: quite a few of us, yes. first time on #esoteric?
17:57:55 <boily> Cyragia: what brings you here? which esolangs do you like? are you working on some? do you like your steak rare, medium or well-done?
17:58:23 <myname> boily: i was told clojure software takes pretty long to start
17:58:36 <Cyragia> interst. FALSE. yes. well-done.
17:59:10 <HackEgo> [wiki] [[0(nop^)]] http://esolangs.org/w/index.php?diff=39573&oldid=39572 * John Misciagno * (+21)
17:59:24 <HackEgo> [wiki] [[0(nop^)]] http://esolangs.org/w/index.php?diff=39574&oldid=39573 * John Misciagno * (+1)
17:59:37 <boily> myname: I wouldn't know, but afaik clojure is the most active and interesting non-java jvm language out there. do you have performance needs?
18:00:25 <Cyragia> I'm making my first language/compiler, heavily influenced by FALSE and alike
18:00:25 <boily> Cyragia: good choice; have your taken a look at betterave? (shameless self-plug). care to give more details? you heretic!
18:00:47 <myname> boily: well, i am targeting android, so... yes
18:01:45 <boily> oh. hm. eeeeeh... you could go the phonegap way, but last time I checked documentation was scarce and not quite up to date.
18:02:45 <HackEgo> [wiki] [[0(nop^)]] http://esolangs.org/w/index.php?diff=39575&oldid=39574 * John Misciagno * (-36)
18:02:52 <myname> boily: people recommended libgdx which looks somewhat usable
18:03:11 <myname> i know about phonegap, but tbh i do hate javascript, too
18:03:14 <HackEgo> [wiki] [[0(nop^)]] http://esolangs.org/w/index.php?diff=39576&oldid=39575 * John Misciagno * (+0)
18:04:59 <Cyragia> boily: betterave looks, cool. But I'm making something stack-based
18:05:54 * nortti notices a trend of stack based langs in recent times
18:06:27 <Cyragia> I aslo noticed there are a lot of stack based esolangs, but barely any 'normal' languages
18:06:57 <mroman> that's because they aren't really practical
18:07:03 <nortti> well, there is a forth but it is borderline esolang
18:07:04 <mroman> at least purely stack based
18:07:12 <nortti> then Joe, which look interesting
18:07:17 <HackEgo> [wiki] [[0(nop^)]] http://esolangs.org/w/index.php?diff=39577&oldid=39576 * John Misciagno * (+58)
18:08:21 <Cyragia> I'm trying to desing something that's as easy as possible to write a compiler for, yet relatively useable and pretty low-level
18:08:38 <nortti> yeah, in that case stacks just make sense (tm)
18:09:28 <Cyragia> My goal is to be able to compile every expression on it's own, in one pass preferably
18:11:08 -!- MoALTz has joined.
18:11:58 <Cyragia> I'm a bit stuck on how to do variables
18:12:34 <Cyragia> you mean allocate mem on stack, or just push/pop ?
18:12:35 <quintopia> boily: have you lost all your creativity? there have been no new vegetables on the wiki in a long time
18:13:08 <mroman> Cyragia: allocate mem on stack
18:13:43 <Cyragia> the allocation isn't really the problem, i could just add a data section to my elf file
18:14:22 <boily> quintopia: I'm background-cogitating on my next one. I still need a way to make it evil. *pouring rain* *thunder* *lightning* *hth*
18:14:36 <mroman> then what's the problem?
18:14:50 <quintopia> boily: what non-evilness have you got
18:15:06 <Cyragia> the problem is, either i put code and data in a single section and just put the variable wherever it is defined (at compile-time), but that's a bit messy
18:15:18 <mroman> https://bitbucket.org/mroman_/emulathor/src/fc48fe22fdade5777099eea372e5f06e2b4d2b2b/src/compiler/rlang.y?at=master <- it's crappy code but it's a working one-pass compiler
18:15:20 -!- heroux has quit (Ping timeout: 245 seconds).
18:15:24 <boily> speaking of forth, I remember reading a long tutorial a while ago. it was a text file à la RFC, and had nice ascii diagrams. but I can't find it :(
18:15:54 <mroman> the easiest thing to do for a one-pass is to compile everything the same way imo
18:16:04 <mroman> i.e use push/pop even if it's not necessary
18:16:08 <impomatic> Factor and Retro are pretty much stack based and appear to be popular.
18:16:10 -!- heroux has joined.
18:16:13 <mroman> that way you don't need register allocation or anything like that
18:16:19 <boily> quintopia: splitting the tokens and merging the parts together in a haphazard way. I want to make the whole thing aperiodic tiling.
18:16:27 <Cyragia> I could just give some mem region to the programmer and use something like defines to convert names into addresses
18:16:31 <impomatic> Cyragia: have you seen Mouse? If you like FALSE, you'll probably like Mouse.
18:17:27 <mroman> Cyragia: address resolution is your problem?
18:17:43 <quintopia> boily: one day you should make a metalanguage called "vegetale". instead of a scoping system, it just has "scoping" where you can define how scoping works. instead of a type system, it just has "typesystem" which lets you define your own type system. best language ever.
18:17:45 <mroman> are you compiling to asm?
18:18:02 <mroman> then the assembler can do the adress resolution :D
18:18:07 <Cyragia> straight to an x86 elf file
18:18:39 <boily> quintopia: Légume!
18:19:17 <HackEgo> [wiki] [[0(nop^)]] http://esolangs.org/w/index.php?diff=39578&oldid=39577 * John Misciagno * (+8)
18:19:59 <mroman> Cyragia: Depending on how high-level your language should be you could just give the programmer some memory that is addressable by index
18:20:04 <HackEgo> [wiki] [[0(nop^)]] http://esolangs.org/w/index.php?diff=39579&oldid=39578 * John Misciagno * (+1)
18:20:11 <Cyragia> yeah, i guess i'll do that
18:20:14 <mroman> i.e pushloc index and poploc index
18:20:27 <Cyragia> and just #defines or smth for names
18:20:32 <mroman> which is essentialy mem[index] = pop(); and push(mem[index]);
18:20:43 <HackEgo> [wiki] [[0(nop^)]] http://esolangs.org/w/index.php?diff=39580&oldid=39579 * John Misciagno * (-1) /* Hello, world! */
18:21:21 <Cyragia> I already have : and ; for store and load
18:21:32 <Cyragia> so my variable would just be pointers anyway
18:22:00 <HackEgo> [wiki] [[0(nop^)]] http://esolangs.org/w/index.php?diff=39581&oldid=39580 * John Misciagno * (-4) /* Hello world! */
18:24:03 <Cyragia> my current writeup of my language: http://pastebin.com/WNjpDgYr
18:24:31 <HackEgo> [wiki] [[0(nop^)]] http://esolangs.org/w/index.php?diff=39582&oldid=39581 * John Misciagno * (+0) /* Hello world! */
18:24:48 <HackEgo> [wiki] [[0(nop^)]] http://esolangs.org/w/index.php?diff=39583&oldid=39582 * John Misciagno * (+6)
18:27:13 <Cyragia> mroman: but when i'd just give the programmer a chunk of memory it'd probably be allocated somewhere around here: 0x08048000. so you can't just use 0, 1, 2, ... as addresses
18:34:38 -!- MindlessDrone has quit (Ping timeout: 240 seconds).
18:41:02 <mroman> you have to adjust for sizeof of course
18:41:17 <mroman> and you can use an offset
18:41:43 <Cyragia> but i also want it to be able to read any regular memory address
18:41:48 <mroman> something like that I guess
18:41:53 <Cyragia> so i can do low-level trickery
18:42:10 <mroman> depending on what assembler syntax you're used to :D
18:42:40 <Cyragia> like: push 0x08048123 (dereference) voila!
18:43:59 <Cyragia> or i could add the offset to the define and when you puch a regular address it would behave normally
18:44:56 <mroman> or you just let the programmer use low-level adresses
18:45:05 <mroman> i.e he has to know where his mem stuff is
18:45:39 <mroman> but how do you tell him where it is?
18:45:52 <Cyragia> but if the offset is something like 0x080484218 it get's quite complicated
18:45:56 <mroman> i mean you could add a command that pushes the offset to the local memory to the stack
18:46:09 <mroman> so he can calculate positions of stuff himself
18:46:15 <nortti> quintopia: in finland?
18:46:37 <Cyragia> I'd rather resolve it at compile-time
18:46:46 <quintopia> nortti: what is Topi usually short for
18:47:09 <nortti> I do not think it is an acronym
18:47:22 <nortti> yes, it is a man's name
18:48:17 -!- hk3380 has quit (Ping timeout: 264 seconds).
18:49:30 -!- realzies has quit (Ping timeout: 245 seconds).
18:50:32 -!- hk3380 has joined.
18:50:41 -!- MindlessDrone has joined.
18:54:54 <Cyragia> mroman: I'll use the equivalent of: #define varname 0x20 (with the offset added at compile-time)
19:03:14 -!- realzies has joined.
19:13:32 <HackEgo> [wiki] [[0(nop^)]] http://esolangs.org/w/index.php?diff=39584&oldid=39583 * John Misciagno * (+92)
19:15:32 <HackEgo> [wiki] [[0(nop^)]] http://esolangs.org/w/index.php?diff=39585&oldid=39584 * John Misciagno * (+35)
19:18:04 <HackEgo> [wiki] [[0(nop^)]] http://esolangs.org/w/index.php?diff=39586&oldid=39585 * John Misciagno * (+43)
19:19:16 <HackEgo> [wiki] [[0(nop^)]] http://esolangs.org/w/index.php?diff=39587&oldid=39586 * John Misciagno * (+5)
19:26:34 -!- Phantom_Hoover has quit (Ping timeout: 240 seconds).
19:31:13 -!- MindlessDrone has quit (Quit: MindlessDrone).
19:32:50 <HackEgo> [wiki] [[0(nop^)]] http://esolangs.org/w/index.php?diff=39588&oldid=39587 * John Misciagno * (+4)
19:34:27 <HackEgo> [wiki] [[0(nop^)]] http://esolangs.org/w/index.php?diff=39589&oldid=39588 * John Misciagno * (+3)
19:39:49 -!- MDude has quit (Ping timeout: 252 seconds).
19:42:39 -!- Phantom_Hoover has joined.
19:46:48 -!- Cyragia has quit (Ping timeout: 240 seconds).
19:48:44 <impomatic> A few new players have entered the Core War Tournament so if you fancy having a go not everyone you'll be up against will be a pro :-)
19:51:42 -!- nycs has joined.
19:53:15 -!- hogeyui has quit (Ping timeout: 245 seconds).
19:53:20 -!- mhi^ has quit (Quit: Lost terminal).
19:53:38 -!- hogeyui has joined.
19:53:38 -!- Gracenotes_ has quit (Ping timeout: 240 seconds).
19:53:58 -!- boily has quit (Ping timeout: 240 seconds).
19:54:23 -!- boily has joined.
19:54:30 -!- `^_^v has quit (Ping timeout: 245 seconds).
19:54:38 -!- tromp__ has joined.
19:54:55 -!- tromp_ has quit (Ping timeout: 245 seconds).
19:55:36 -!- Gracenotes has joined.
19:55:55 -!- aloril has quit (Ping timeout: 240 seconds).
19:58:28 -!- edwardk_ has quit (Quit: Computer has gone to sleep.).
20:11:34 -!- hk3380 has quit (Ping timeout: 240 seconds).
20:12:17 -!- mhi^ has joined.
20:14:36 -!- nycs has changed nick to `^_^v.
20:14:55 -!- password2 has quit (Read error: Connection reset by peer).
20:17:10 -!- hk3380 has joined.
20:21:46 -!- Sorella has quit (Ping timeout: 276 seconds).
20:21:50 <HackEgo> [wiki] [[0(nop^)]] http://esolangs.org/w/index.php?diff=39590&oldid=39589 * John Misciagno * (+59)
20:24:01 -!- aloril has joined.
20:24:47 <HackEgo> [wiki] [[0(nop^)]] http://esolangs.org/w/index.php?diff=39591&oldid=39590 * John Misciagno * (+1)
20:33:36 <mroman> impomatic: what tournament?
20:37:20 <impomatic> mroman: Core War. You can enter by email. Tournament takes place at the computer museum in Cambridge, U.K. http://corewar.co.uk/spring2014.htm
20:37:48 <ion> nice https://firstlook.org/theintercept/article/2014/05/19/data-pirates-caribbean-nsa-recording-every-cell-phone-call-bahamas/
20:40:45 -!- boily has quit (Quit: INCOMING CHICKEN).
20:42:14 <impomatic> mroman: eso hill would be http://esolangs.org/wiki/BF_Joust
20:42:22 <impomatic> !bfjoust shortsword (>++>--)*2(>)*6([-[+]]>)*20
20:45:04 -!- mhi^ has quit (Ping timeout: 240 seconds).
20:45:32 <mroman> "Entries can be up to 25 instructions"
20:46:43 <mroman> "Completely changing the program's behaviour or swapping / adding extra components for each core size is not allowed."
20:46:50 <HackEgo> [wiki] [[0(nop^)]] http://esolangs.org/w/index.php?diff=39592&oldid=39591 * John Misciagno * (+26)
20:46:51 <mroman> if someone can do that in just 25 instructions
20:47:02 -!- mhi^ has joined.
20:47:12 <HackEgo> [wiki] [[0(nop^)]] http://esolangs.org/w/index.php?diff=39593&oldid=39592 * John Misciagno * (+0)
20:47:34 <mroman> I can't switch to a different algo if CORESIZE > 800?
20:47:46 <mroman> that seems like an odd restriction
20:48:00 <mroman> I'll submit an imp then :D
20:48:13 <mroman> Everybody should at least submit an imp
20:48:24 <impomatic> mroman: the same program has to do well in each coresize. Otherwise it might as well be a tournament with three rounds!
20:48:41 <mroman> yeah "the same program"
20:48:53 <mroman> but why forbid if(coresize > 800) jump foo kinda stuff?
20:49:19 <impomatic> It's forbidden because you could just enter three completely different programs:
20:49:47 <mroman> but you're still limited to 25 instructions *TOTAL*
20:49:59 <mroman> so that only leaves 25/4 instructions per "sub"-program
20:50:20 <mroman> minus the overhead for the switch
20:51:36 <impomatic> I have two programs on the most active hill which are only 9 instructions. :-) http://www.koth.org/lcgi-bin/current.pl?hill94nop
20:54:42 <mroman> I guess I should at least submit some two stage bomber
20:55:01 <mroman> my vampire.red is much longer than 25 instructions and I know it sucks
20:55:15 <impomatic> Oneshots are easy to program. Just a scan loop (e.g. scan add #step, pointer / jmz.f scan, @pointer) followed by a clear (sequential wipe of memory starting whatever the scan found)
20:55:38 <mroman> impomatic: years ago, yes
20:57:32 <mroman> I think i submitted it to some koth.org hill
20:57:38 <mroman> but it performed badly
20:57:58 <mroman> mostly probably because it was too long and too slow for a vampire
20:58:05 <impomatic> Vampires have had trouble getting on the hills for years.
20:58:44 <mroman> I laid carpets of jmps into a SPL0 loop
20:59:10 <impomatic> However, a few new tricks have got the back on the hill again over the last few months.
20:59:14 <mroman> so the idea was to trick opponents to jump into my mem clear loop plus slowing them with the spl 0
21:00:22 <impomatic> I assume you have a DAT wipe after you've finished bombing?
21:01:01 <mroman> but I didn't know about fancy ><{} prefixes at that time
21:01:19 <mroman> I didn't know you could copy stuff around and also increment stuff in a single instruction
21:02:04 <mroman> my replicator wasn't much successful too :(
21:02:10 <impomatic> That makes a big difference to the score.
21:03:10 <mroman> 24th is pretty soon though
21:03:19 -!- Patashu has joined.
21:03:39 <mroman> but shouldn't take more than an hour to write a bomber :D
21:04:02 <mroman> I just add an imp as a backup strategy
21:04:09 <mroman> after bombing transform to imp :)
21:04:49 <impomatic> Modern replicators normally run several parallel processes in code similar to paper spl somewhere, 0 / mov >paper, }paper ; all processes run the spl to split to the new copy. Then the run the mov to make the new copy.
21:04:52 <mroman> I don't know what you usually do after bombing?
21:05:02 <mroman> with a different offset probably
21:05:21 <mroman> I was just planning to throw spl 0 bombs with a bug offset
21:05:34 <mroman> and then make another bomb run with a slightly smaller offset
21:05:41 <mroman> then make a full mem clear
21:06:06 <impomatic> After bombing (or scanning), clear memory.
21:06:15 <mroman> spl 0 with big offset should catch replicators pretty well I think
21:06:28 <mroman> depending on how big they are and how fast they reproduce
21:08:01 <impomatic> A good 4 instruction clear is d-clear, SPL #0 / CLEAR MOV BMB, >POINTER / DJN.F CLEAR, >POINTER / BMB DAT 3-POINTER (where pointer is a few instructions before the clear)
21:23:54 -!- Patashu has quit (Ping timeout: 240 seconds).
21:35:41 -!- oerjan has joined.
21:39:24 <oerjan> hm i'm not sure i like this apparent exponential spam growth
21:42:22 <shachaf> improve your life: HISTIGNORE='fg*'
21:42:47 -!- Sorella has joined.
21:43:32 <oerjan> i don't think i've used fg much...
21:44:00 <oerjan> actually i guess i'd more likely have used %, the times i needed to
21:46:26 <oerjan> ah they're simply synonyms
21:47:29 <oerjan> or rather, the fg in fg %... is optional
21:47:39 <kmc> shachaf: did you know that rustc's parser is about 5,000 lines of hand-written Rust code?
21:47:46 <kmc> no grammar or anything
21:48:28 <shachaf> but that explains why they're not keeping the grammar in the manual up to date
21:48:44 <oerjan> kmc: sounds a little brittle. isn't rust powerful enough you could make parser combinators?
21:49:44 <kmc> yeah, I think there is a plan to fix this
21:53:58 <oerjan> <shachaf> `olist (952) <-- how did that sneak in just after i checked myself...
21:54:37 <shachaf> oerjan: is it just me or are olist updates p. far apart these days
21:56:17 <oerjan> <boily> you click in the emptiness and drag. <-- ooh
21:57:44 <oerjan> oh you don't have to drag, you can just click
22:02:04 <oerjan> <nortti> then Joe, which look interesting <-- itym Joy
22:06:25 <oerjan> <quintopia> boily: have you lost all your creativity? there have been no new vegetables on the wiki in a long time <-- wait betterave is a french vegetable?
22:14:55 -!- nooodl_ has joined.
22:18:14 -!- nooodl has quit (Ping timeout: 240 seconds).
22:22:59 -!- hk3380 has quit (Ping timeout: 252 seconds).
22:23:07 -!- Sgeo has joined.
22:48:34 <oerjan> someone ought to perhaps tell john misciagno about the preview button.
23:01:51 -!- Sorella has quit (Ping timeout: 252 seconds).
23:03:31 -!- nooodl_ has quit (Ping timeout: 265 seconds).
23:15:56 -!- hk3380 has joined.
23:17:11 <HackEgo> [wiki] [[0(nop^)]] http://esolangs.org/w/index.php?diff=39594&oldid=39593 * John Misciagno * (+5)
23:27:14 <HackEgo> [wiki] [[Language list]] http://esolangs.org/w/index.php?diff=39595&oldid=39552 * John Misciagno * (+14)
23:30:52 -!- mhi^ has quit (Quit: Lost terminal).
23:32:45 <HackEgo> [wiki] [[0(nop^)]] http://esolangs.org/w/index.php?diff=39596&oldid=39594 * John Misciagno * (-15)
23:33:13 <kmc> hm, the google rubiks cube kind of runs like shit in firefox
23:36:43 -!- shikhout has joined.
23:39:38 -!- shikhin has quit (Ping timeout: 240 seconds).
23:42:30 -!- MoALTz_ has joined.
23:44:42 <Phantom_Hoover> kmc, the controls are fantastically awkward even if it works properly, just save yourself the pain
23:45:07 -!- MoALTz has quit (Ping timeout: 252 seconds).
23:52:40 -!- tertu has quit (Ping timeout: 240 seconds).
23:53:33 -!- tromp has joined.
23:56:36 <HackEgo> [wiki] [[0(nop^)]] http://esolangs.org/w/index.php?diff=39597&oldid=39596 * John Misciagno * (+15)
00:07:16 -!- yorick has quit (Read error: Connection reset by peer).
00:07:48 <kmc> I did my first substantial hacking on rustc today
00:08:11 <kmc> implemented support for macros that expand to patterns
00:10:34 -!- tromp has quit (Remote host closed the connection).
00:20:02 <int-e> kmc: you're missing out on the cube exploding and... http://int-e.eu/~bf3/tmp/rubik.png (german version) ... so not much really
00:20:25 <int-e> (solving the real thing is so much faster!)
00:21:01 <kmc> spoilers :<
00:21:34 -!- Phantom_Hoover has quit (Ping timeout: 240 seconds).
00:21:36 <int-e> oh and there is a webgl version out there that works more smoothly, but doesn't have a timer or move counter.
00:21:59 <int-e> kmc: I meant well, I was trying to save you some pain.
00:23:27 <oerjan> "I meant well" is not a very good tombstone line
00:24:05 <int-e> (Even the webgl version is awful ... I found that I have trouble reproducing some of the macros that I use on the actual cube because they are almost fully automatic by now)
00:25:11 <int-e> oerjan: It'd be "(s)he meant well", hth.
00:25:57 <oerjan> that doesn't work for the "I told you so" of hypochondriac fame
00:26:16 <int-e> "We told him(her) so" ... ow.
00:26:49 <int-e> Anyway, I'm in a strange mood.
00:26:57 <int-e> Please don't take me seriously.
00:27:04 -!- tertu has joined.
00:32:48 <HackEgo> [wiki] [[TOGA computer]] http://esolangs.org/w/index.php?diff=39598&oldid=36621 * John Misciagno * (+0)
00:38:55 <HackEgo> [wiki] [[A:;]] M http://esolangs.org/w/index.php?diff=39599&oldid=39034 * Malltog * (+4) Edited cat program to make it loop
00:40:28 -!- FreeFull has quit (Ping timeout: 276 seconds).
00:43:48 -!- tromp has joined.
00:52:44 -!- sebbu has quit (Ping timeout: 255 seconds).
00:53:43 -!- edwardk has joined.
01:08:00 <Sgeo> The Google cube is wrong, I think.
01:08:04 -!- {hk3380} has joined.
01:08:05 -!- tertu has quit (Ping timeout: 264 seconds).
01:08:07 <Sgeo> You can't rotate the inner thingies
01:08:22 <Sgeo> Which afaict means if you're counting moves you may count wrong
01:08:23 -!- shikhout has quit (Remote host closed the connection).
01:09:28 <oerjan> > id id id id id id id id id id id id id id id id id id id id id id id id id id id id id id id id id id id id id id id id id id 8
01:10:11 -!- hk3380 has quit (Ping timeout: 252 seconds).
01:10:47 <oerjan> Sgeo: um if we mean the middle thirds i rotated those just fine...
01:11:07 <Sgeo> I meant you're not supposed to be able to on a real cube
01:11:41 -!- tertu has joined.
01:11:41 <oerjan> of course you can. it's just a little physically awkward to keep both outer parts still.
01:12:01 -!- edwardk has quit (Quit: Computer has gone to sleep.).
01:15:14 -!- {hk3380} has quit (Ping timeout: 255 seconds).
01:18:49 <elliott> you can do it because you can rotate the two non-middle thirds in the opposite direction.
01:19:05 -!- realzies has quit (Quit: realzies).
01:19:05 <elliott> ok, I guess it's relevant for move-counting.
01:23:37 -!- 77CAAKECD has joined.
01:23:38 -!- realzies has joined.
01:28:30 <int-e> oerjan: no fair building exponentially large types
01:29:15 <oerjan> int-e: i just wanted to give you a little stress testing hth
01:29:52 <oerjan> with the article being on top of /r/haskell you'd better be prepared.
01:29:59 <int-e> it caused me little stress. so it must have worked.
01:30:20 -!- 77CAAKECD has quit (Excess Flood).
01:30:54 -!- realz has joined.
01:31:57 -!- realzies has quit (Quit: realzies).
01:32:29 -!- realzies has joined.
01:33:35 -!- realzies has quit (Client Quit).
01:35:02 <HackEgo> [wiki] [[Bukkake]] N http://esolangs.org/w/index.php?oldid=39600 * 99.16.65.43 * (+959) Created page barebone
01:41:44 <oerjan> my delete finger is itching.
01:42:30 <elliott> unfortunately it appears to be an actual language
01:43:02 <HackEgo> [wiki] [[Bukkake]] http://esolangs.org/w/index.php?diff=39601&oldid=39600 * 99.16.65.43 * (+639) Added examples
01:43:34 <int-e> I'm not sure that it's actually a worse name than "brainfuck", except that I've have gotten used to the latter.
01:44:41 <int-e> (this will sound great outside of an esolang context)
01:45:16 <elliott> there's a threshold for which I'd delete an esolang for its name, but this is far below it.
01:45:20 <HackEgo> [wiki] [[Language list]] http://esolangs.org/w/index.php?diff=39602&oldid=39595 * Oerjan * (+0) /* Non-alphabetic */ order (I _think_ I decided this section was ordered by ASCII ignoring case, but I'm not entirely sure.
01:46:23 <oerjan> wait why is ~ not before its coprefixes
01:47:24 <lambdabot> Couldn't match expected type ‘GHC.Types.Char’
01:47:25 <lambdabot> with actual type ‘[GHC.Types.Char]’
01:47:46 <HackEgo> [wiki] [[Language list]] M http://esolangs.org/w/index.php?diff=39603&oldid=39602 * Oerjan * (+0) /* Non-alphabetic */ I think I've misplaced this somehow
01:48:10 <elliott> oerjan: btw, don't tempt me to name languages silly unicode edge-cases just to mess up your ASCII ordering.
01:48:59 <oerjan> elliott: good, i won't.
01:49:31 <elliott> oerjan: you may already have.
01:49:52 <oerjan> it seems my ridiculously complicated vim :sort command to order that section was broken :(
01:51:33 <Sgeo> I seem to be addicted to Sex Yeah
01:51:42 <oerjan> (it was :.,$sort i /[[][[][:]\?\([^|]*[|]\)\?[ ]\?\([^>]*>\)\?/
01:51:58 <oerjan> *MWAHAHAHA* i bracketed Sgeo
01:53:00 <oerjan> <elliott> coprefix is a good word <-- why do you think i invented it hth
01:53:25 <Bike> http://www.unicode.org/reports/tr10/#Canonical_Equivalence_Table man this owns
01:55:56 -!- tertu has quit (Ping timeout: 255 seconds).
01:58:47 <Sgeo> So, I once asked if I should watch an LP of Planescape: Eternal Torment, and people said yes. So, should it be a blind LP?
01:59:39 <oerjan> how much torment do you want when watching twh
02:00:02 * int-e is confused by the "Eternal"
02:00:40 <oerjan> it means never-ending hth
02:00:44 <Bike> well, what, would you prefer ternal torment
02:01:09 <int-e> oerjan: yes but it's not part of the game's name
02:01:35 <int-e> For all I know, which is very little of course.
02:05:32 -!- tertu has joined.
02:06:16 -!- Bike has quit (Ping timeout: 240 seconds).
02:08:31 -!- Bike has joined.
02:09:11 -!- Bike has quit (Client Quit).
02:09:25 -!- Bike has joined.
02:20:43 -!- Bike has quit (Ping timeout: 240 seconds).
02:22:47 -!- Bike has joined.
02:34:48 -!- zzo38 has joined.
02:47:05 <kmc> hm, the most prominent label language on this bag of jasmine rice is Hmong
02:48:44 <oerjan> well it's a hmongous language
02:51:42 <ion> esolangs.org/wiki/Hmong
02:56:34 <Bike> i don't even know what hmong looks like >_<
02:57:32 <ion> It’s a bit like Hmu.
02:59:08 <Bike> oh it's some language family i've never heard oft
03:02:42 <oerjan> "Early linguistic classifications placed the Hmong–Mien languages in the Sino-Tibetan family, where they remain in many Chinese classifications, but the current consensus among Western linguists is that they constitute a family of their own."
03:03:03 <ion> https://www.kickstarter.com/projects/612530753/gitchain
03:03:08 <Bike> yeah yeah, and Wu and Scots aren't languages
03:03:20 <Bike> oh by the way OpenWorm totally got funded
03:03:28 <Bike> get ready for nematodes all over your computers nerds
03:05:47 <oerjan> "They are some of the most highly tonal languages in the world: Longmo and Zongdi Hmong have as many as twelve distinct tones."
03:06:27 <Bike> Zongdi Hmong is a hella rad name
03:08:40 <oerjan> "Neighbouring languages across these families, though presumed unrelated, often have similar features, which are believed to have spread by diffusion. A well-known example is the similar tone systems in Sinitic languages (Sino-Tibetan), Hmong–Mien, Tai languages (Kadai) and Vietnamese (Mon–Khmer)."
03:09:10 <Bike> i didn't know vietnamese and cambodian were related.
03:09:51 <Bike> oh, they're both austroasiatic.
03:10:07 <HackEgo> [wiki] [[Language list]] http://esolangs.org/w/index.php?diff=39604&oldid=39603 * Icepy * (+12)
03:10:07 <Bike> well, that whole area has some hella geography.
03:11:34 -!- MoALTz has joined.
03:15:11 -!- MoALTz_ has quit (Ping timeout: 258 seconds).
03:21:50 -!- oerjan has quit (Quit: leaving).
03:30:11 <kmc> I'm disappointed that Bukkake is another boring brainfuck derivative
03:41:38 -!- Bike has quit (Ping timeout: 258 seconds).
03:43:14 <Sgeo> From context of a comic strip I can't link, I assume a "reduction from bin packing to linear programming" would be very interesting?
03:43:20 -!- Bike has joined.
03:48:35 <Bike> this is some basic bullshit.
03:48:59 <kmc> Sgeo: what
03:49:54 <Sgeo> Bonobo Conspiracy #421
03:57:01 <kmc> available as a convenient 15 MB .zip file
03:58:19 <Sgeo> I can't really link to the individual comics...
04:00:03 <Sgeo> I think, when it used to be more of a webcomic, they had annotations. They don't anymore
04:05:20 -!- tromp has quit (Remote host closed the connection).
04:08:55 -!- tromp has joined.
04:13:43 -!- edwardk has joined.
04:17:57 <Jafet> > text $ unlines $ replicate 3 $ replicate 72 '('
04:17:59 <lambdabot> ((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((
04:17:59 <lambdabot> ((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((
04:17:59 <lambdabot> ((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((
04:23:19 <Sgeo> So, is that thing I mentioned a thing that would be an interesting result?
04:24:24 <Bike> what, the webcomic?
04:27:21 -!- Bike_ has joined.
04:28:40 <quintopia> Sgeo: well, it would imply bin packing is in P. which may be known. i don't know.
04:28:56 -!- Bike has quit (Ping timeout: 255 seconds).
04:29:03 -!- Bike_ has changed nick to Bike.
04:29:23 <quintopia> so a reduction to linear programming would imply P=NP
04:29:58 <Bike> hey that's a pretty good result!!
04:30:26 <Sgeo> http://i.imgur.com/iq4QXSY.png
04:31:25 -!- edwardk has quit (Quit: Computer has gone to sleep.).
04:33:16 <Bike> this is a bad comic
04:33:25 -!- edwardk has joined.
04:44:16 -!- Cyragia has joined.
04:46:09 -!- password2 has joined.
04:49:10 -!- edwardk has quit (Quit: Computer has gone to sleep.).
04:50:48 -!- Cyragia has quit (Ping timeout: 240 seconds).
04:51:41 -!- edwardk has joined.
04:56:23 -!- Phantom_Hoover has joined.
05:14:56 <Jafet> Imagine that as your next referee
05:24:40 -!- MoALTz_ has joined.
05:26:00 -!- tromp has quit (Remote host closed the connection).
05:27:41 -!- MoALTz has quit (Ping timeout: 255 seconds).
05:44:15 <zzo38> I have play Dungeons&Dragons game today
05:45:07 -!- conehead has quit (Read error: Connection reset by peer).
06:11:07 <Sgeo> A Chrome extension seems to have been spying on me
06:12:33 <Sgeo> "This extension adds the following ads. If you do not with to support us, you are welcome to disable ads by clicking the checkbox below"
06:14:07 <Sgeo> Change HTTP Request Header
06:19:21 -!- MoALTz_ has quit (Quit: Leaving).
06:20:07 <Sgeo> Cloud Party is dead
06:39:48 -!- conehead has joined.
06:50:27 -!- tertu has quit (Ping timeout: 252 seconds).
06:56:26 -!- tertu has joined.
07:29:41 -!- Bike has quit (Ping timeout: 264 seconds).
07:32:28 -!- diginet has joined.
07:32:47 -!- shikhin has joined.
07:33:47 -!- slereah_ has joined.
07:35:09 -!- shikhin has quit (Remote host closed the connection).
07:36:49 -!- shikhin has joined.
07:37:42 -!- realz has quit (*.net *.split).
07:37:43 -!- aloril has quit (*.net *.split).
07:39:02 -!- aloril has joined.
07:43:04 -!- 77CAAKHVT has joined.
07:43:19 -!- 77CAAKHVT has quit (Max SendQ exceeded).
07:43:44 -!- realz has joined.
07:44:46 -!- edwardk has quit (Quit: Computer has gone to sleep.).
07:48:00 -!- conehead has quit (Quit: Computer has gone to sleep).
07:58:42 -!- edwardk has joined.
07:59:25 <HackEgo> [wiki] [[Forobj]] http://esolangs.org/w/index.php?diff=39605&oldid=39543 * GermanyBoy * (+273) /* Examples */
08:00:43 -!- KingOfKarlsruhe has joined.
08:01:36 <HackEgo> [wiki] [[Hello world program in esoteric languages]] http://esolangs.org/w/index.php?diff=39606&oldid=38583 * GermanyBoy * (+36) /* Forobj */
08:02:41 <HackEgo> [wiki] [[Hello world program in esoteric languages]] http://esolangs.org/w/index.php?diff=39607&oldid=39606 * GermanyBoy * (+56) /* PHL 1.0 */
08:20:37 -!- glogbackup has joined.
08:28:41 -!- Patashu has joined.
08:34:54 -!- Patashu has quit (Disconnected by services).
08:34:54 -!- Patashu_ has joined.
09:08:01 <kmc> are there any type systems based on epistemic logic?
09:43:04 -!- {hk3380} has joined.
09:46:52 -!- mhi^ has joined.
10:14:34 -!- boily has joined.
10:52:29 -!- Phantom_Hoover has quit (Ping timeout: 264 seconds).
11:03:36 -!- boily has quit (Quit: Poulet!).
11:11:03 <mroman> impomatic: my SLT isn't working :(
11:11:43 -!- lambdacat has joined.
11:12:13 <int-e> lambdacat: @let newtype Codensity f x = Codensity (forall r. (x -> f r) -> f r)
11:12:14 <lambdacat> Multiple declarations of ‘Codensity’
11:12:28 <int-e> lambdacat: @let newtype Codensity f x = Codensity (forall r. (x -> f r) -> f r)
11:12:41 -!- lambdacat has quit (Remote host closed the connection).
11:19:34 -!- Sprocklem has quit (Ping timeout: 240 seconds).
11:24:37 -!- {hk3380} has quit (Ping timeout: 276 seconds).
11:37:25 -!- shikhout has joined.
11:37:42 -!- Sorella has joined.
11:40:29 -!- shikhin has quit (Ping timeout: 252 seconds).
11:42:52 <fizzie> "In 1990, a disgruntled employee at the Point Lepreau Nuclear Generating Station in Canada obtained a sample (estimated as about a "half cup") of heavy water from the primary heat transport loop of the nuclear reactor, and loaded it into a cafeteria drink dispenser."
11:42:56 <fizzie> Office pranks seem slightly different at nuclear power plants.
11:43:59 -!- yorick has joined.
11:46:01 <slereah_> "Man this water is heavy today"
11:48:15 <nortti> iirc, heavy water is only ~10% heavier
11:48:39 <slereah_> Oxygen makes up most of the mass of water
11:50:07 <fizzie> They'd be all "I froze my drink and put it in the bath tub and it sank instead of floating!", because that's what people do, right?
11:51:13 <slereah_> Heavy water is toxic on top of being radioactive
11:51:22 <slereah_> It has different chemical properties from water
11:52:27 <fizzie> Well, now, it isn't necessarily radioactive. (Of course if you take it from a nuclear reactor...)
11:52:49 <slereah_> Heavy water is always radioactive!
11:53:01 <nortti> isn't deuterium stable?
11:53:15 -!- sebbu has joined.
11:53:47 -!- sebbu has quit (Changing host).
11:53:47 -!- sebbu has joined.
11:54:03 <slereah_> It's the tritium you gotta watch out for
11:55:03 <slereah_> I should work on my Quantum Computer Language
11:55:50 <slereah_> The question is, can you make a TC quantum computer in 1D
11:55:56 <slereah_> Or do I have to go 2D at least
11:57:05 <Jafet> People worry about the radioactivity of depleted uranium, too
11:57:24 <mroman> my bomb loop is toooooo slow
11:57:33 -!- Phantom_Hoover has joined.
12:02:35 <mroman> If you throw bombs too close to your own position the scanners are gonna find you pretty fast :(
12:03:21 <Jafet> slereah: implementing something resembling brainfuck with quantum gates?
12:04:14 <slereah_> But I'm not quite sure if it's doable in 1D
12:04:23 <slereah_> Or if it will have to be quantum befunge stuff
12:05:41 <fizzie> Just don't call it "Quantum brainfuck", because there is one already.
12:05:41 <Jafet> What is the difficulty with a 1D (array of qubits, I assume)
12:06:01 <slereah_> Well I want to simulate a physical machine
12:06:16 <Jafet> fizzie: just make the wiki give you one of the articles at random
12:06:19 <slereah_> Until they encounter a measuring device that collapses the quantum state
12:11:59 -!- Phantom_Hoover has quit (Ping timeout: 255 seconds).
12:16:58 -!- Sgeo has quit (Read error: Connection reset by peer).
12:21:21 <mroman> how the fuck to I compare something indirectly in Redcode?
12:22:38 <mroman> SNE #0, @SPTR isn't working
12:22:44 <mroman> it seems to compare with the B-field of SPTR
12:22:56 <mroman> but I want it to interpret the B-field of SPTR as an address
12:23:07 <mroman> and check if the B-field of the cell at that address is 0
12:29:10 <mroman> also shouldnt ADD.B #12, SPTR add 12 to SPTR?
12:29:24 <mroman> I can't remember how this shit works :(
12:30:20 <fizzie> I think ADD.AB #12, SPTR should do that, but I haven't done any of that stuff in ages.
12:33:03 <fizzie> (By my logic, ADD.B #12, SPTR would add whatever the relative address of SPTR is, to the B field of SPTR, since the source instruction is the current instruction, and .B means B-to-B.)
12:33:21 <mroman> looks like it's ADD.AB indeed
12:33:30 <mroman> but the SNE #0, @SPTR is still not doing what I want it to do
12:33:55 -!- oerjan has joined.
12:33:55 <fizzie> I don't know what's up with that, since it sounded like it should do what you wanted.
12:36:00 <mroman> SNE #0, @SPTR always doesn't skip
12:36:08 <oerjan> there you go being negative again
12:36:18 <mroman> SNE.B #0, @SPTR always skips
12:36:29 <mroman> no matter if SPTR would point to a non-zero thingy
12:37:57 <mroman> it should compare the A value with the B value
12:38:09 <mroman> whereas A is immediate zero and B is indirect to the b-field of SPTR
12:38:20 <mroman> that's at least my understanding of what It *should* do
12:44:52 <mroman> this is really stressing me out :(
12:47:42 -!- tromp has joined.
12:48:08 -!- tromp has quit (Remote host closed the connection).
12:50:24 <mroman> "proceeds with the A-value set to the B-number of the A-instruction"
12:51:00 <mroman> which hopefully is zero for #0
12:52:28 <mroman> "and the B-value set to the B-number of the B-instruction"
12:52:55 <fizzie> If you have XXX #0, YYY, then the B-number of the A-instruction is probably YYY.
12:54:11 <mroman> I thought that's just for XXX FOO, AAA; FOO DAT ZZZZ, YYYY;
12:54:23 <mroman> i.e it reads YYYY from FOO
12:54:28 <mroman> but #0 is an immediate value
12:54:37 <mroman> not a pointer to an instruction
12:56:17 <mroman> have I mixed up SNE with SEQ?
12:59:12 <fizzie> #0 is just "this field is zero, and the addressing mode is immediate", AFAIK.
12:59:31 -!- Melvar` has joined.
12:59:35 <fizzie> And "addressing mode is immediate" means the source/destination instruction is the current instruction.
13:00:39 <fizzie> But if you write something like MOV.BA #1234, FOO the value 1234 does not have much significance, except just being in that field. It'll still move the value (FOO) from the B-field of that instruction to the B-field of FOO.
13:01:11 <fizzie> Er, I mean, to the A-field of FOO.
13:02:15 -!- Melvar has quit (Ping timeout: 252 seconds).
13:02:31 <mroman> fizzie: ADD.AB overwrites both fields
13:02:41 -!- idris-bot has quit (Ping timeout: 264 seconds).
13:03:09 <fizzie> I thought that was ADD.F.
13:04:01 <mroman> .AB "write to B-fields"
13:04:08 <mroman> then what messes up my A fields :(
13:04:18 <fizzie> http://www.koth.org/info/icws94.html ".AB Instructions use the A-numbers of the A-instructions and the B-numbers of the B-instructions and write B-numbers."
13:06:26 -!- KingOfKarlsruhe has quit (Quit: Leaving.).
13:07:32 <mroman> There's a trick for bounds checking I guess?
13:07:48 <mroman> The address 0 is the start of my program?
13:07:57 -!- Melvar` has changed nick to Melvar.
13:08:00 <mroman> so If I know my program is 15 instructions long
13:08:09 <mroman> I'd bomb myself if the pointer is smaller 15
13:08:25 -!- idris-bot has joined.
13:09:04 <fizzie> All addresses are relative, so 0 is only the start of your program when it's in the first instruction of your program.
13:16:06 <fizzie> And if I recall correctly, even in something like MOV #0, @1; DAT #0, #-1 the number 1 is first relative to that MOV instruction (so points to the DAT), and the -1 is relative to *that* instruction, and so points back to the MOV.
13:22:57 -!- ais523 has joined.
13:23:51 -!- ter2 has joined.
13:23:51 -!- tertu has quit (Disconnected by services).
13:28:34 -!- Patashu_ has quit (Ping timeout: 240 seconds).
13:36:34 -!- idris-bot has quit (Ping timeout: 276 seconds).
13:37:13 -!- Melvar has quit (Ping timeout: 276 seconds).
13:37:58 -!- ter2 has quit (Ping timeout: 240 seconds).
13:44:26 -!- nooodl_ has joined.
13:51:33 -!- Melvar has joined.
13:59:08 -!- ter2 has joined.
14:03:21 <mroman> impomatic: http://codepad.org/ZS7TGOPC <- that's probably the best I can come up with
14:03:25 <mroman> but it sucks like hell :)
14:03:39 <mroman> it's too slow obviously
14:28:26 -!- shikhout has changed nick to shikhin.
14:30:56 <HackEgo> [wiki] [[Language list]] M http://esolangs.org/w/index.php?diff=39608&oldid=39604 * Oerjan * (+0) /* Non-alphabetic */ as I just said...
14:41:44 -!- password2 has quit (Ping timeout: 258 seconds).
14:48:31 <HackEgo> [wiki] [[Special:Log/newusers]] create * Sandbender * New user account
14:49:55 -!- ais523 has quit.
14:52:22 -!- FreeFull has joined.
14:53:55 <HackEgo> [wiki] [[Brainfuck implementations]] http://esolangs.org/w/index.php?diff=39609&oldid=39337 * Sandbender * (+178) Added link for BFCPU
14:57:54 -!- {hk3380} has joined.
14:58:01 -!- Cyragia has joined.
15:02:36 -!- MindlessDrone has joined.
15:04:50 -!- edwardk has quit (Quit: Computer has gone to sleep.).
15:05:41 -!- jconn has quit (Ping timeout: 264 seconds).
15:11:07 -!- shikhin has quit (Remote host closed the connection).
15:15:32 <mroman> getAllElementsOccuringExactlyNTimes
15:21:56 -!- drdanmaku has joined.
15:38:19 -!- password2 has joined.
15:39:10 -!- password2 has quit (Max SendQ exceeded).
15:39:59 -!- password2 has joined.
15:40:32 -!- Bike has joined.
15:42:20 -!- password2 has quit (Max SendQ exceeded).
15:44:26 -!- MDream has joined.
15:44:27 -!- oerjan has quit (Quit: leaving).
15:45:52 -!- MDream has changed nick to MDude.
15:48:52 <MDude> Clearly I should make the worst possible combination of shoices for that survey.
15:51:05 <nortti> especially ones that cannot be fitted toget, for example left-infinte tape and going right wrapping to leftmost cell
15:51:38 <Bike> can't, you say? how uncreative
15:51:56 <MDude> That could be even better than left-infinite but crahsing when too far to the right.
15:53:26 <nortti> actually, is there some mathematics that would let one do stuff like "last element of infinite list"
15:54:02 <Bike> not with the ways infinities are usually defined
15:54:20 <Bike> you could have going right wrap to the negative \omega'th cell or something, though
15:55:37 -!- ter2 has quit (Ping timeout: 265 seconds).
15:56:01 <MDude> You could just emulate it being an infinite distance away by making it a saparate list, with zero being defined at infinitely far to the right?
15:56:34 <Bike> that's pretty much how it works out with surreals, yeah.
15:56:57 <Bike> it even goes both ways, you can have \omega - 1 and so on.
15:57:25 <MDude> I should learn more classes of numbers.
15:57:51 <MDude> Or mroe about them, anyway.
15:57:55 -!- edwardk has joined.
16:01:11 -!- ter2 has joined.
16:02:07 -!- password2 has joined.
16:04:49 <mroman> you could have < on cell 0 wrap to cell infinity
16:05:24 <mroman> which means you just keep a hold of two lists
16:05:34 <mroman> one that expands to the right and one that expands to the left
16:05:50 <mroman> since there's no way < on the cell infinity can every reach any other cell
16:06:12 <mroman> so essentially that behaves the same way like expanding the tap to the left I think
16:08:02 -!- {hk3380} has quit (Ping timeout: 255 seconds).
16:08:09 <Taneb> Anyone know what I had planned for the 12th of June?
16:08:44 <Bike> invasion of basque country
16:08:56 <Taneb> Unlikely, that's far away
16:09:04 <Taneb> Probably something in York
16:10:10 -!- edwardk has quit (Read error: Connection reset by peer).
16:10:13 <zzo38> Do you know how to invent type system based on epistemic logic?
16:10:23 <Taneb> I can't even manage a schedule
16:11:31 -!- edwardk has joined.
16:11:55 -!- slereah_ has quit (Quit: Leaving).
16:13:44 <Bike> doxastic logic doesn't even define any relations on its modal operator, does it
16:13:49 <mroman> Taneb: Sitting at the docks, feeding ducks, throwing rocks and hoping for luck?
16:14:47 <Taneb> mroman, York's pretty far inland, although it does have more than its fair share of ducks
16:15:05 <Taneb> My university is apparently the university with the highest duck:student ratio in the EU
16:16:01 <HackEgo> [wiki] [[Hello world program in esoteric languages]] http://esolangs.org/w/index.php?diff=39610&oldid=39607 * Zzo38 * (+144) +[[Gentzen]]
16:16:16 -!- edwardk has quit (Read error: Connection reset by peer).
16:16:37 <Bike> counting ducks is related to martin-lof which is related to logics good job
16:17:47 <Taneb> http://duckdensity.org.uk/uni_info?uni_ID=york
16:18:05 <Taneb> There is a better source somewhere
16:18:13 <Taneb> Financial Times University Guide or something
16:20:05 <Bike> duckdensity dot org dot yuu key
16:20:25 <Taneb> https://en.wikipedia.org/wiki/PUSH_(university_guide)#Trivia
16:24:34 -!- MoALTz has joined.
16:26:04 -!- sebbu has quit (Ping timeout: 265 seconds).
16:26:45 <zzo38> Many of the built-in rules of Gentzen esolang are based on sequent calculus, so you may be able to experiment with type systems using other modal logic and other things added, by extending sequent calculus and extending the rules of Gentzen esolang as such.
16:27:51 <HackEgo> [wiki] [[Talk:Rail]] http://esolangs.org/w/index.php?diff=39611&oldid=39393 * GermanyBoy * (+646) /* Lambda? */
16:30:39 <HackEgo> [wiki] [[Talk:Rail]] M http://esolangs.org/w/index.php?diff=39612&oldid=39611 * GermanyBoy * (-57) /* Lambda? */
16:31:50 <zzo38> (I have already put the K and N rules of modal logic on)
16:37:56 -!- realz has quit (Read error: Connection reset by peer).
16:39:45 -!- realzies has joined.
16:41:01 -!- conehead has joined.
16:42:11 -!- sebbu has joined.
16:42:29 <zzo38> Do you like a Washizu mahjong game? I like this kind.
16:42:51 -!- sebbu has quit (Changing host).
16:42:51 -!- sebbu has joined.
16:42:52 <zzo38> Also, I can make houtei a lot in a Washizu game.
16:44:33 <zzo38> (Sometimes, that is my only yaku.)
16:45:08 <myname> i think the last change is pretty amusing
16:45:23 <kmc> zzo38: what do you think of epistemic logic?
16:45:40 <zzo38> kmc: I looked at it, but unfortunately I don't know
16:59:05 <zzo38> Can you use bitcoin for payment even if you don't have any bitcoins or bitcoin client? (For example, go pay someone in cash and tell them address of whoever you have to pay, and the message to post with it.) Can you also receive payment with bitcoin in similar way?
17:00:00 <myname> that would imply there are people who would actually give their bitcoins away
17:01:13 <zzo38> But it is in exchange for money
17:01:25 <zzo38> And for product/services you are purchasing.
17:02:46 <myname> but they may be worth ten times what you paid in the near future!!!
17:03:33 -!- edwardk has joined.
17:03:50 <myname> okay, tbh: i don't know, maybe there is something like that, but i wouldn't count on it
17:04:37 <myname> you have to be enthusiastic enough to keep spreading but not too enthusiastic to gther as much as possible for yourself
17:04:55 <myname> don't know how many bitcoin users fit in there
17:06:38 -!- atehwa has quit (Ping timeout: 240 seconds).
17:07:32 -!- atehwa has joined.
17:10:11 <zzo38> Can you figure out the session 52 of Dungeons&Dragons game before it is all being written?
17:10:17 <zzo38> Can you guess it please?
17:11:57 <zzo38> Do you agree with me that, SQL stored procedures are worthless and triggers (if they are allowed on views as well) is much better?
17:12:12 <Taneb> I'm afraid I haven't been following it.
17:12:15 -!- password2 has quit (Ping timeout: 240 seconds).
17:12:49 <zzo38> Taneb: HackEgo has a link. I am currently typing it so part of session 52 is available at this time, but the compiled version is only up to session 51
17:12:51 <MDude> I know you can buy bitcoins at exchanges.
17:13:13 <Taneb> I should figure out what's going to happen next in the game I'm playing
17:13:19 <MDude> I wouldn't think it'd be hard to set up something that accepts payments and automatically sends them to an adress.
17:13:21 <Taneb> And then have a session
17:13:22 <zzo38> Taneb: What already happened?
17:13:23 <Bike> spoons. all over
17:13:39 <zzo38> MDude: I would want it to be accepting payment in cash, though
17:13:49 <Taneb> zzo38, my character (a pacifist) ended up with a magical tattoo on his chest that the Platinum Empire was going to use as a weapon.
17:14:02 <MDude> I was thinking a website at first, but if you want cash, it could be like a vending machine.
17:14:11 <zzo38> Taneb: If your chest makes you sin, cut it off.
17:14:20 <myname> oh, playing a pacifist may be funny
17:14:23 <Taneb> One of the party was from the Platinum Empire, and was instructed to take it back
17:14:37 <Taneb> Long story short, he and my left arm teleported away
17:14:52 <Taneb> (So now my character's harmless AND armless, heh)
17:15:18 <Taneb> And now the remainder of the party (other than a vampire who ran away) and two new guys made it to the capital of the dwarf kingdom
17:15:25 <Taneb> And me and one of the new people have been arrested.
17:16:04 <myname> Taneb: are you trying to make your party stop if they harm others?
17:16:06 <Taneb> Presumably because the Platinum Empire put a bounty on my head
17:16:22 <Taneb> myname, nah, I'm not a conscientious objector
17:16:42 <Taneb> I just lose all my holy powers if I harm any sapient being
17:16:54 <myname> so it's like "kill whoever you want, i won't do anything"?
17:17:12 <Taneb> Nah, it's like "kill whoever you want, I won't be happy but I might lend a hand"
17:17:34 <Taneb> I just can't directly harm sapient beings
17:18:03 <Taneb> But I can boost and heal my allies
17:18:07 <myname> but your sword might accidentally fall through the eye of one?
17:18:14 <Taneb> I don't have a sword.
17:18:30 <myname> you should've, it could be hillarious
17:18:37 <MDude> I'd think the intent would be a bit more important.
17:18:53 <zzo38> In my game is different, there are some creature I won't want to beat, and won't want to help others to do so, but, other character can do what they might want and I may or may not object, and furthermore my character is not particularly good at combat but can do it somewhat, when such a thing would help to do!!!
17:19:02 <MDude> Like if you sneeze and that causes you to lsoe balance and land on someone, that's not being no-pacifist.
17:19:26 <Taneb> The magical tattoo on my chest has fired once. I don't control it.
17:19:50 <zzo38> I have a feat "favored mercy (aberration)" but it isn't often in use.
17:20:00 <zzo38> Taneb: Then remove the tattoo.
17:20:12 <zzo38> Use knife to cut off the skin if necessary.
17:20:34 <MDude> Invent skin transplants so you can patch up the hole with skin from our butt.
17:20:37 <Taneb> We're on a quest to not let the Platinum Empire get hold of it
17:20:38 <zzo38> myname: I won't expect that to work.
17:21:06 <zzo38> Taneb: If you cut it into enough pieces, then perhaps they don't hold of it.
17:21:18 <myname> zzo38: if that's the case, i'd expect every magical tattoo to be some sort of filled circle, because it would be much easier to make
17:21:19 <MDude> Once it's removed, it'll be easier to hidee.
17:21:33 <Taneb> zzo38, that feels too easy story-wise and my character would object
17:21:54 <MDude> Since it's no longer stuck to any one particular body.
17:21:55 <Taneb> MDude, it's also easier to lose
17:22:02 <zzo38> Taneb: O, OK, if your character object then don't do it like that
17:22:21 <myname> kill your character :p
17:22:27 <Taneb> We were going to find some mages who said that they would be able to destroy it but they were all killed
17:22:45 <Taneb> And now we're on the run but also trying to bring down one of the major dwarven banks?
17:22:52 <MDude> Wear something that makes you always hunched over, so the tattoo always points at the ground.
17:23:01 <myname> okay, while we are at it: anyone funny ideas of what to play in shadowrun?
17:23:03 <Taneb> Because one of the party owes them a lot of money
17:23:21 <Taneb> But it seems like the dwarfish nobility beat us to it
17:24:04 <MDude> Someone who thinks the Shadowrun is some kind of event like the running of the bulls, and wants to participate in it.
17:24:14 <Taneb> So now step 1 is reunite the party (we're all on our own and two of us have been arrested)
17:26:24 <MDude> A pixie that rides around in a dwarf-sized mech.
17:26:28 <zzo38> During session 53, maybe I will have to make up something like a Morse-code
17:29:01 <zzo38> Eventually I have to reach one place in Calimshan, and request a Cuban cigar. I have absolutely no use for a Cuban cigar, but apparently it is some kind of password for entering a secret church (it is secret because most people in Calimshan hate it)
17:30:58 <MDude> Do they also hate smoking?
17:31:37 <zzo38> But the place I am requesting it from isn't a store that sells cigars anyways
17:31:58 <zzo38> So it is unlikely that someone would go to ask them for one
17:33:01 <zzo38> With a sufficiently fancy astrolabe with both straight and curved parts, can you calculate cosines with it?
17:34:59 <zzo38> I do also have a holy symbol for the church I am intending to enter, so that might help too
17:35:57 <MDude> I'd think you'd just need something like a scotch yoke.
17:36:08 <zzo38> What is a scotch yoke?
17:36:17 <MDude> http://en.wikipedia.org/wiki/Scotch_yoke
17:37:07 <MDude> For cosine instead of sine, you jsut add 90 degrees to the input, right?
17:39:02 <zzo38> My character does own a astrolabe
17:42:17 -!- jconn has joined.
17:43:55 <zzo38> And, also owns a shovel, and some nails, and a few other things.
17:47:08 <zzo38> Astrolabe has actually become useful in a few ways already; the DM expected that it is completely useless, at first!
17:48:31 <MDude> When I get to building robots, I should remember to make one with a built-in astrolabe.
17:51:55 <MDude> That's just a thought I was remidned of from talking about astrolabes.
17:52:45 <zzo38> I want to have some SQL extension that you can insert into a virtual table to listen for connections, make connections, accept connections, and to query it for listing them too. One column can tell the SQL statements which are run during such events.
18:00:34 <impomatic> mroman: there are couple of places where your code can be improved if you need any suggestions :-)
18:01:30 <zzo38> Nobody else ever answer my question about SQL making internet connection, in a proper way, before.
18:06:14 <mroman> impomatic: I think I'm open for suggestions :D
18:08:58 <mroman> I think I could scan two locations with the SEQ
18:09:05 <mroman> assuming one location is a DAT #0, #0
18:09:17 <impomatic> mroman: in the clear, you need 3 MOV s instead of MOV.A. That'll increase the score by 20%
18:11:33 <mroman> it should do roughly they same thing?
18:11:46 <mroman> or does MOV.A not copy the instruction?
18:11:56 -!- shikhin has joined.
18:13:28 <mroman> impomatic: If noticed that a lot of programs survive a mem clear
18:13:56 <impomatic> MOV.A only copies the a-field. MOV.I copies the entire instruction. (MOV usually defaults to MOV.I)
18:14:53 <impomatic> mroman: make the mem clear wipe memory multiple times (currently it clears ones, the suicides)
18:17:26 -!- MindlessDrone has quit (Quit: MindlessDrone).
18:17:32 <impomatic> mroman: You can do that by moving SPTR2 to the top and changing QBMP to QBMP DAT #0, #25. When the wipe is almost finished, QBMP will then overwrite SPTR2, starting the clear again at +25 (just after your warrior)
18:18:22 <kmc> Cuba exists in zzo38's D&D-world?
18:19:38 <Bike> maybe cuban cigars are from cube
18:20:18 <zzo38> kmc: Well, they said about Cuban cigars, at least.
18:20:53 <impomatic> mroman: 3rd improvement, move the SPLB line to just above the CLEAR line. This will split off lots of processes into the clear, making it more resistant to being hit.
18:22:10 <MDude> Interestingly, the Shadowrun Wikipedia entry doesn't even mention D&D.
18:22:55 -!- lambdabot has quit (Quit: brb).
18:27:24 -!- lambdabot has joined.
18:33:44 <MDude> [13:22] <myname> okay, while we are at it: anyone funny ideas of what to play in shadowrun?
18:34:08 <zzo38> Did they put SQLite in HackEgo yet?
18:35:32 <MDude> Oh, I confused zzo38 talking about D&D with myname talking about Shadowrun.
18:41:19 <mroman> impomatic: @FOO+3 isn't working right?
18:42:11 <mroman> i.e. it doesn't load the b'value and then adds 3
18:43:57 <impomatic> It's like in assembly language. @FOO+3 returns the value at the address pointed to by (FOO+3)
18:46:40 <HackEgo> danddreclist 52: shachaf nooodl boily \ http://zzo38computer.org/dnd/recording/level20.tex
18:50:08 <impomatic> mroman: http://codepad.org/pu1NrAEP - will put DAT 234 at X, because FOO+3 points to line 8 and line 8 contains -1, which points to line 7 (DAT 234)
18:51:56 -!- shikhin has quit (Quit: leaving).
18:53:33 -!- not^v has joined.
18:53:40 -!- not^v has quit (Read error: Connection reset by peer).
18:54:00 -!- zzo38 has quit (Remote host closed the connection).
18:59:21 -!- {hk3380} has joined.
19:25:37 -!- ggherdov has quit (Ping timeout: 276 seconds).
19:37:18 -!- Cyragia has quit (Ping timeout: 240 seconds).
19:41:59 -!- ggherdov has joined.
19:48:45 <nortti> how many of you can pronounce "Ph'nglui mglw'nafh Cthulhu R'lyeh wgah'nagl fhtagn"
19:49:42 <mroman> I just pronounce it swissy
19:50:20 <Slereah> Because Lovecraft didn't give a shit
19:50:38 <Slereah> He didn't even pronounce the crazy names consistently himself
19:51:01 <nortti> well, I can pronounce that
19:51:25 <Slereah> Really from what I can gather
19:51:33 <Slereah> Lovecraft didn't really care much for the mythos
19:51:49 <Slereah> The point was mostly SPOOKY THINGS
19:52:20 <nortti> although necronomicon was detailed pretty well, to a point where people thought it was real
19:52:40 <Slereah> I have a book of non-fiction texts by Lovecraft
19:52:52 <Slereah> It's pretty funny because he is like the least superstitious guy ever
19:53:07 <Slereah> So seeing people thinking the mythos is real is quite amusing
19:53:29 <nortti> what is the name of the book?
19:53:43 <Slereah> Fuck, I left it at my parent's house
19:54:19 <Slereah> http://www.amazon.com/Collected-Essays-H-P-Lovecraft/dp/0974878987/ref=sr_1_2?s=books&ie=UTF8&qid=1400615651&sr=1-2&keywords=Lovecraft+science
19:54:27 * MDude picks up a book called "Fuck, I Left it at my Parent's House".
19:54:42 <Slereah> Mostly texts of when he wrote for an astronomy column in a local newspaper
20:00:15 -!- {hk3380} has quit (Ping timeout: 240 seconds).
20:01:04 -!- mhi^ has quit (Quit: Lost terminal).
20:38:45 -!- Bike has quit (Ping timeout: 252 seconds).
20:40:39 -!- Bike has joined.
20:45:54 -!- mhi^ has joined.
20:58:10 -!- {hk3380} has joined.
21:03:01 -!- Patashu has joined.
21:03:55 -!- drdanmaku has quit (Ping timeout: 240 seconds).
21:05:14 -!- drdanmaku has joined.
21:14:33 -!- nooodl__ has joined.
21:18:19 -!- nooodl_ has quit (Ping timeout: 240 seconds).
21:22:11 <kmc> I edited 2048 to get rid of the zugzwang
21:22:20 <kmc> but I think this just trades frustration for mind-numbing tedium
21:23:17 <shachaf> Does that mean adding a no-op move?
21:23:51 <kmc> it will drop a new tile but it won't move any of the existing ones
21:24:29 <shachaf> Does it make the game easy to always win?
21:24:36 <kmc> mroman: no, it's just a different game
21:24:47 <kmc> shachaf: I don't always win, but I think it's a lot easier yeah
21:25:11 <kmc> my first score playing this variant was about as good as my best ever high score on the official version after far too many hours of play
21:25:36 <kmc> my friend made one that's 5 × 5 and only drops 2's
21:25:42 <kmc> that one is really fucking easy
21:26:05 -!- Patashu has quit (Ping timeout: 264 seconds).
21:26:35 <shachaf> http://www.csie.ntu.edu.tw/~b01902112/9007199254740992/
21:27:14 <kmc> I like that it has a "move randomly "feature
21:28:12 <kmc> `run python -c 'print 2**69 < 900719925474099265052 < 2**70'
21:28:16 <kmc> what's with that
21:28:39 -!- Phantom_Hoover has joined.
21:29:33 <shachaf> where did those last 5 digits come from
21:29:47 <shachaf> `run python -c 'print 9007199254740992 == 2**53'
21:30:38 <kmc> i'm so confused now
21:30:46 <kmc> i probably copied my high score too or something
21:30:55 <kmc> also why is it 2**53... oh
21:37:19 <kmc> but you can represent some integers much larger than that in a 64-bit float
21:37:24 <kmc> in particular, you can represent powers of two
21:40:18 <shachaf> There are also other possible representations of tile scores in this game.
21:40:25 <shachaf> I feel like this discussion has been had here before.
21:40:28 <kmc> such as logarithmic?
21:40:30 <kmc> maybe, but not by me
21:40:33 <shachaf> http://tunes.org/~nef//logs/esoteric/14.03.17
21:40:38 <shachaf> Conveniently at the top of the IRC logs.
21:41:15 <kmc> I wonder what you said just before midnight that I'm so much in agreement with!
21:45:27 -!- edwardk has quit (Ping timeout: 240 seconds).
21:46:03 <kmc> oh, it was a link to 9007199254740992
21:54:15 -!- Bike has quit (Ping timeout: 265 seconds).
21:56:04 -!- Bike has joined.
21:57:50 <fizzie> kmc: You were, like, here (or I guess maybe just left) when the 2**53 thing was discussed the other month: http://codu.org/logs/log/_esoteric/2014-03-17#073648fizzie
21:59:21 <fizzie> And I was, like, here when the logs were linked-to, five lines back.
22:07:12 -!- nooodl__ has changed nick to nooodl.
22:07:48 <kmc> unrelatedly, http://rhodesmill.org/brandon/2012/one-sentence-per-line/ is pretty great
22:16:04 -!- edwardk has joined.
22:24:43 -!- edwardk has quit (Ping timeout: 240 seconds).
22:26:55 -!- oerjan has joined.
22:40:13 -!- mhi^ has quit (Quit: Lost terminal).
22:41:23 <oerjan> hm sudden minor bitcoin boom
22:42:09 -!- syndrome has changed nick to synd.
22:42:12 -!- synd has changed nick to syndrome.
22:42:40 <Taneb> Help I'm thinking about type algebra gain
22:54:37 <MDude> Think about algebra loss instead?
22:54:49 <Taneb> I might just go to sleep
23:03:54 -!- nooodl has quit (Ping timeout: 240 seconds).
23:03:54 -!- edwardk has joined.
23:10:11 -!- Phantom_Hoover has quit (Quit: Leaving).
23:20:09 -!- Sgeo has joined.
23:28:58 -!- boily has joined.
23:29:49 <Sgeo> Are physical computer finite state machines? And thus, if I understand properly, pushdown automations are not physically realizable?
23:30:40 -!- impomatic has quit (Quit: http://corewar.co.uk).
23:31:43 <boily> fungot: do you second?
23:31:44 <fungot> boily: my dear hooker, i can think :) is in iris. i want only to show by direct evidence, that this greater sterility :)/, in carthamus.
23:32:01 <Bike> gases aren't ideal, either, but it's still a nicer approximation than the hamiltonian would be
23:32:02 <boily> fungot: my body is not for sale, you filthy sapient bot!
23:32:03 <fungot> boily: pot 4: 17 1? 8:: 11 4? 8: 63. pot 3: 83: 80 4? 8:: 22.
23:32:23 <boily> fungot: and don't tell me the odds.
23:32:24 <fungot> boily: there seems to be advantageous to them for gliding through/ air. in one case, and that/ species which were most promising." even peculiarities in blushing seem to be fully satisfied. i remember when i grew hothouse orchids i was cautioned not to wet their leaves; but i never had an opportunity, and it has done you no fnord farewell.
23:32:40 -!- tromp has joined.
23:37:14 <fungot> Available: agora alice c64 ct darwin* discworld enron europarl ff7 fisher fungot homestuck ic irc iwcs jargon lovecraft nethack oots pa qwantz sms speeches ss wp youtube
23:37:14 <Sgeo> "Huh. You seem awfully eager to alloccate internal nodes. Do you think they grow on trees?'
23:37:34 <Sgeo> Klaun would be an awesome style for fungot
23:37:34 <fungot> Sgeo: forgive if you can, do not at any period :) life. he says " beechey's :( voyage," it would have been/ kindest friend to me that my precious speculation was one :)/ commonest kinds,/ massive runt,/ barb,/ breadth :)/ forehead. these muscles, when thus treated,/ results are given together. on both sides dipping to opposite points at an angle :) forty degrees; whilst, in/ case :) apparently continuous growth, as in a map. i
23:39:36 -!- metasepia has joined.
23:39:54 <boily> how did I dare to expect information from the cuttlefish...
23:40:18 <Sgeo> Google Bonobo Conspiracy
23:41:08 <boily> not gonna fall for it again.
23:41:16 <boily> (well. at least for the next five minutes.)
23:42:49 <metasepia> ENVA 202250Z VRB01KT CAVOK 13/09 Q1014 RMK WIND 670FT 30002KT
23:43:10 <metasepia> CYUL 202300Z 22008KT 30SM FEW090 BKN240 22/03 A2997 RMK AC1CI4 SLP150 DENSITY ALT 800FT
23:43:27 <boily> na na ni na nèreuh ♪
23:43:40 <oerjan> well, i suppose you still have sunlight right
23:43:55 <Sgeo> http://www.wolframalpha.com/input/?i=pi%5E%28%28arctan+1%2F2%29+-+%28sin+%28pi%2F5%29%29%29
23:44:34 -!- tromp has quit (Remote host closed the connection).
23:44:48 <boily> Sgeo: hm? jenny in the decimal expansion?
23:45:30 <Sgeo> http://i.imgur.com/DrhmqdL.png
23:47:31 <boily> (previous OKAY uttered in a non-oerjan voice.)
23:53:29 <kmc> Sgeo: cute
00:00:16 <oerjan> (previous O KAY uttered in an oerjan voice.)
00:01:52 -!- yorick has quit (Remote host closed the connection).
00:12:43 <Sgeo> http://i.imgur.com/j4ZtYXs.png i don't get it
00:15:08 -!- tromp has joined.
00:19:48 -!- tromp has quit (Ping timeout: 258 seconds).
00:20:22 <oerjan> (and that's after looking up the master theorem on wikipedia)
00:20:40 <MDude> He put on his robe and wizard hat?
00:25:49 <ion> Sleeping Pig Wakes Up for a Cookie http://youtu.be/6zbsUtQL4nY
00:28:02 -!- tromp has joined.
00:31:47 <HackEgo> higcoin etourcodfcoin paticoin unsulcoin aeocoin valcoin gracoin etonianuperceacoin movcoin ircutlaniccoin foodcoin odecoin shoiocoin ligheticoin alacoin perpancoin algehotcoin supecoin perpecoin var'scoin
00:32:22 <oerjan> can we remove the yellow from that
00:32:42 <kmc> I'm just using rainwords
00:32:50 <kmc> I don't mind if you remove the yellow from rainwords
00:32:54 <kmc> I don't particularly care to do it myself
00:33:31 <oerjan> shachaf: it's unreadable
00:34:29 <shachaf> Seems fine to me? Do you use a white background or something?
00:34:54 <MDude> Maybe use a background color isntead of just foreground, so there's always black behind it.
00:35:05 <kmc> I suggest configuring your terminal so that all 16 ANSI colors are visible, since there are only 16 of them
00:35:16 <MDude> I don't see why there's the h, though.
00:35:34 <kmc> I had to change blue in urxvt because it was too hard to read against black
00:48:46 -!- tromp has quit (Remote host closed the connection).
00:58:58 -!- Sorella has quit (Ping timeout: 240 seconds).
01:06:40 -!- tromp has joined.
01:15:57 -!- edwardk has quit (Quit: Computer has gone to sleep.).
01:16:34 -!- tromp has quit (Remote host closed the connection).
01:18:06 -!- tromp has joined.
01:20:27 -!- Slereah has quit (Read error: Connection reset by peer).
01:20:44 -!- Slereah_ has joined.
01:22:20 <Sgeo> http://i.imgur.com/5l2sm0c.png
01:22:24 <Sgeo> I may be slightly addicted
01:25:25 <Bike> why don't you get addicted to JESUS, hippie
01:27:36 <kmc> yeah hippie
01:27:52 -!- tromp has quit (Remote host closed the connection).
01:27:55 <oerjan> i think in this particular case Bike's suggestion might be an improvement.
01:30:21 <oerjan> theory: the only thing preventing arbitrarily bad bugs from being redefined as features is the threshold at which time travelers go back to prevent the programmer from ever being born.
01:31:19 <oerjan> the main weakness of this theory is the lack of evidence that there is such a badness limit.
01:33:44 -!- tromp has joined.
01:34:04 <Bike> http://media.tumblr.com/c0ec500021bd8af624d6fb5ad7fd8c95/tumblr_inline_n5w25rRllC1s3ca0o.jpg context-free design art
01:35:12 <kmc> is that a Saturn V
01:35:29 <kmc> i always thought an ICBM version of the Saturn V would be amusing
01:40:31 -!- boily has quit (Quit: LUNAR CHICKEN).
01:40:35 -!- metasepia has quit (Remote host closed the connection).
01:43:58 <kmc> oerjan: http://en.wikipedia.org/wiki/Project_A119
01:44:24 -!- ter2 has changed nick to tertu.
01:44:46 <kmc> "It was also reported that a failure to hit the Moon would likely result in the missile returning to Earth."
01:50:58 -!- glogbackup has quit (Ping timeout: 240 seconds).
01:51:25 -!- {hk3380} has quit (Ping timeout: 258 seconds).
01:54:34 <Bike> funny, since the first moon-targeted satellite missed, but it didn't come back
02:04:47 -!- edwardk has joined.
02:10:35 -!- augur has quit (Ping timeout: 258 seconds).
02:15:17 -!- augur has joined.
02:19:27 -!- Bike has quit (Ping timeout: 240 seconds).
02:21:40 -!- Bike has joined.
02:49:29 -!- augur has quit (Ping timeout: 255 seconds).
02:51:07 -!- nycs has joined.
02:52:45 -!- augur has joined.
02:53:31 -!- `^_^v has quit (Ping timeout: 240 seconds).
02:55:53 <Bike> oh wait shit you were actually asking me
02:56:25 <MDude> Well a path meant to orbit around the Moon wouldn't be quite the same as one meant to hit it.
02:56:27 <Bike> yeah the soviet "Luna 1" had some problem so it missed and went heliocentric (the first heliocentric man-made object! fuck yeah!!!) and they renamed it and generally acted like it was awesome that they missed
02:57:02 <Bike> still floatin' around
03:00:07 <Bike> Mechta is a cool name, admittedly
03:10:29 -!- augur has quit (Ping timeout: 264 seconds).
03:12:32 <pikhq> That's pretty hilarious.
03:13:42 -!- augur has joined.
03:17:17 -!- tromp_ has joined.
03:18:58 -!- tromp has quit (Ping timeout: 240 seconds).
03:20:03 -!- MDude has changed nick to MDream.
03:22:39 <kmc> you are having a bad problem and you will not go to space today
03:23:56 -!- augur has quit (Ping timeout: 255 seconds).
03:34:07 -!- augur has joined.
03:37:32 <oerjan> do MDreams about monadic sheep?
03:50:41 -!- augur has quit (Ping timeout: 264 seconds).
03:56:46 * Sgeo learns about fun Javascript weirdness
04:01:06 -!- xk002 has joined.
04:01:25 <Sgeo> if([] && ([] == false)) {console.log("hello");}
04:04:02 <kmc> what a country
04:14:09 -!- augur has joined.
04:17:00 -!- not^v has joined.
04:33:47 -!- augur has quit (Remote host closed the connection).
04:33:57 -!- tertu has quit (Ping timeout: 252 seconds).
04:35:36 -!- not^v has quit (Changing host).
04:35:36 -!- not^v has joined.
04:36:03 -!- augur has joined.
04:38:54 -!- tertu has joined.
04:47:14 -!- sebbu has quit (Ping timeout: 240 seconds).
04:50:15 -!- augur has quit (Ping timeout: 240 seconds).
04:58:07 -!- oerjan has quit (Quit: Good night).
05:00:37 -!- tromp_ has quit (Remote host closed the connection).
05:11:38 -!- not^v has changed nick to ^v2.
05:15:12 <Sgeo> http://en.wikipedia.org/wiki/Star_Wars_Theme/Cantina_Band
05:15:18 * Sgeo blinks a few times
05:16:19 -!- conehead has quit (Quit: Computer has gone to sleep).
05:16:25 <Sgeo> It's... a Star Wars song... most popular instrumental song in history of recorded music
05:16:40 <Bike> that's not a very long history.
05:41:09 -!- tertu has quit (Ping timeout: 276 seconds).
05:43:18 -!- ^v2 has quit (Quit: http://i.imgur.com/Akc6r.gif).
05:45:31 -!- augur has joined.
05:45:50 -!- tertu has joined.
05:46:53 -!- augur has quit (Remote host closed the connection).
06:00:06 <fizzie> I'm not quite sure "biggest-selling instrumental *single*" can really be losslessly translated to "most popular instrumental song".
06:02:43 <fizzie> (Also I don't know about that "only one ever to be certified Platinum" fact, since the database the Wiki'rticle links to gives about 410 results if you ask for type: Standard, format: Single, award: Platinum.)
06:03:45 <Bike> presumably that includes non-instrumentals
06:05:15 <fizzie> Yeah, I guess all the others have someone warbling.
06:05:19 <Bike> includes such luminaries as GUMMIBAR - I'M A GUMMY BEAR (THE GUMMY BEAR SONG)
06:06:15 <Bike> and bohemian rhapsody, an instrumental of which sounds p. dull
06:07:02 <fizzie> In type: Digital, there's at least one "single" that does platinum.
06:07:32 <fizzie> AIUI, 100 streamings equals one sold copy for determining that.
06:08:32 <fizzie> http://www.riaa.com/goldandplatinum.php?content_selector=criteria "100 on-demand audio and/or video streams will count as 1 Unit for certification purposes."
06:08:58 <fizzie> (Each "permanent digital download" counts as one, too.)
06:09:23 -!- Slereah has joined.
06:12:34 -!- Slereah_ has quit (Ping timeout: 265 seconds).
06:18:35 -!- BeingUntoDeath has joined.
06:25:41 -!- MoALTz has quit (Quit: Leaving).
06:43:55 -!- sebbu has joined.
06:44:32 -!- sebbu has quit (Changing host).
06:44:32 -!- sebbu has joined.
06:44:36 -!- fowl has quit (Quit: Derogatory terms for gynecomastia can include moobs (for male boobs) and bitch tits.[34]).
06:52:15 -!- tertu has quit (Disconnected by services).
06:52:15 -!- ter2 has joined.
06:58:57 -!- fowl has joined.
07:07:13 -!- xk002 has quit (Ping timeout: 252 seconds).
07:07:39 -!- xk002 has joined.
07:28:18 -!- xk003 has joined.
07:29:20 -!- xk002 has quit (Disconnected by services).
07:30:10 -!- xk003 has changed nick to xk002.
07:36:33 <HackEgo> [wiki] [[0(nop^)]] http://esolangs.org/w/index.php?diff=39613&oldid=39597 * John Misciagno * (+66)
07:39:22 -!- shikhin has joined.
07:45:18 -!- Bike has quit (Ping timeout: 276 seconds).
08:09:36 -!- FreeFull has quit.
08:27:07 -!- Patashu has joined.
08:39:35 <kmc> consciousness is cache coherence
08:40:45 <fizzie> Nice note in the corner of a bus route map: "Please don't copy or use."
08:41:11 <fizzie> I guess it's intended only to be admired as art.
08:41:37 <shachaf> The note was referring to itself, not to the map.
08:42:04 <shachaf> "thanks for ignoring my explicit instructions, fizzie" -- the note
08:48:01 <fizzie> It was this map: http://www.city.kyoto.jp/koho/eng/access/img/basunabieigo-rosenn.pdf
08:52:10 -!- augur has joined.
08:52:41 <shachaf> Great, now no one is respecting the note's right to be forgotten.
08:52:56 <fizzie> (Also the "printed with soy ink" note is probably untrue in the copy I just printed.)
08:53:38 <shachaf> Perhaps the ink is introducing itself.
08:53:41 <Taneb> fizzie, so vegans can eat it?
08:54:23 <fizzie> I don't know what "regular ink" is made of.
08:54:41 <Taneb> I know some red ink is made of beetles
08:54:44 <shachaf> In this channel, that means people like you.
08:54:50 <Taneb> You know, John, Ringo, and the like
08:54:53 <fizzie> I've been wondering why some people have not been showing up.
08:56:10 <fizzie> There's the red food dye (carmine, aka C.I. 75470, E120, "natural red 4") that's obtained from cochineals.
08:56:37 <shachaf> "When traveling outside of the allocated zone, it is necessary the extra fares"
08:57:41 <kmc> traveling outside of the allocated zone is undefined behavior
09:01:06 -!- BeingUntoDeath has quit.
09:21:26 -!- drdanmaku has quit (Quit: Connection closed for inactivity).
09:22:01 <HackEgo> [wiki] [[Pinkcode]] http://esolangs.org/w/index.php?diff=39614&oldid=39373 * Feuermonster * (+29) /* Instructions */
09:22:37 <HackEgo> [wiki] [[Pinkcode]] http://esolangs.org/w/index.php?diff=39615&oldid=39614 * Feuermonster * (-387) Examples are invalid now.
09:25:56 <HackEgo> [wiki] [[Pinkcode]] http://esolangs.org/w/index.php?diff=39616&oldid=39615 * Feuermonster * (+412) /* Play field */ Placement rules and coordinates
09:32:05 -!- augur has quit (Ping timeout: 264 seconds).
09:32:27 -!- augur has joined.
09:37:39 <mroman> that's probably going to tricky to visualize
10:13:05 -!- boily has joined.
10:44:31 -!- {hk3380} has joined.
10:52:11 <Taneb> Help someone asked me what I'm most proud of and now I'm panicking
10:56:26 -!- MDream has changed nick to MDude.
11:00:39 <mroman> Welcome to the world of depression
11:00:44 -!- boily has quit (Quit: AAAAAAAAAAAAAAAAAAAAH!).
11:02:10 <MDude> Collecting a large number of esoteric languages that aren't Brainfuck?
11:04:06 <MDude> Things you're proud of are in the past, and your primary concerns are with the future?
11:08:50 -!- Patashu has quit (Quit: Soundcloud (Famitracker Chiptunes): http://www.soundcloud.com/patashu MSN: Patashu@hotmail.com , AIM: Patashu0 , YIM: patashu2 , Skype: patashu0 .).
11:13:57 <int-e> Taneb: Aim low. "I survived this far" is a remarkable accomplishment if you think about it long enough ;-)
11:14:21 <Taneb> int-e, heck, I even have a bed!
11:15:23 <int-e> I bought my own from IKEA and assembled it all by myself!
11:22:17 -!- Patashu has joined.
11:32:21 -!- yorick has joined.
11:37:54 -!- shikhout has joined.
11:40:43 -!- shikhin has quit (Ping timeout: 240 seconds).
12:15:05 -!- Sgeo has quit (Read error: Connection reset by peer).
12:20:53 <HackEgo> [wiki] [[Special:Log/newusers]] create * Sacchan * New user account
12:23:22 -!- oerjan has joined.
12:24:37 <HackEgo> [wiki] [[User:Sacchan]] N http://esolangs.org/w/index.php?oldid=39617 * Sacchan * (+10) Created page with "[[MCurse]]"
12:25:44 -!- {hk3380} has quit (Ping timeout: 255 seconds).
12:37:23 <HackEgo> [wiki] [[Asdf]] M http://esolangs.org/w/index.php?diff=39618&oldid=31782 * Malltog * (+208) Added moving examples
12:47:14 <HackEgo> [wiki] [[ΜCurse]] N http://esolangs.org/w/index.php?oldid=39619 * Sacchan * (+2009) Created page with "µCurse is a Turing-complete, purely functional language. It was created on May 21st, 2014 by [[User:Sacchan]] == Structure == Each µCurse-program describes a function from ..."
12:47:14 <HackEgo> [wiki] [[CRalphabet]] M http://esolangs.org/w/index.php?diff=39620&oldid=35330 * Malltog * (+26) Added Category: Output only
12:48:11 <HackEgo> [wiki] [[ΜCurse]] http://esolangs.org/w/index.php?diff=39621&oldid=39619 * Sacchan * (+30) Added wrongtitle
12:50:20 <HackEgo> [wiki] [[Language list]] http://esolangs.org/w/index.php?diff=39622&oldid=39608 * Sacchan * (+14)
12:52:02 -!- tromp has joined.
12:52:44 <HackEgo> [wiki] [[User:Sacchan]] http://esolangs.org/w/index.php?diff=39623&oldid=39617 * Sacchan * (+45)
12:54:05 -!- Patashu has quit (Ping timeout: 252 seconds).
12:55:08 <HackEgo> [wiki] [[ΜCurse]] http://esolangs.org/w/index.php?diff=39624&oldid=39621 * Sacchan * (+72)
12:56:09 <HackEgo> [wiki] [[ΜCurse]] http://esolangs.org/w/index.php?diff=39625&oldid=39624 * Sacchan * (+0)
12:59:26 <HackEgo> [wiki] [[ΜCurse]] http://esolangs.org/w/index.php?diff=39626&oldid=39625 * Sacchan * (+0)
13:02:24 <HackEgo> [wiki] [[ΜCurse]] http://esolangs.org/w/index.php?diff=39627&oldid=39626 * Sacchan * (+383)
13:02:51 <HackEgo> [wiki] [[ΜCurse]] http://esolangs.org/w/index.php?diff=39628&oldid=39627 * Sacchan * (-1)
13:04:58 <HackEgo> [wiki] [[ΜCurse]] http://esolangs.org/w/index.php?diff=39629&oldid=39628 * Sacchan * (+0)
13:06:28 <HackEgo> [wiki] [[ΜCurse]] http://esolangs.org/w/index.php?diff=39630&oldid=39629 * Sacchan * (+91)
13:12:34 <HackEgo> [wiki] [[User:Sacchan]] http://esolangs.org/w/index.php?diff=39631&oldid=39623 * Sacchan * (+55)
13:12:41 <HackEgo> [wiki] [[User:Sacchan]] http://esolangs.org/w/index.php?diff=39632&oldid=39631 * Sacchan * (-1)
13:14:17 <HackEgo> Thanks, Sacchan. Thacchan.
13:29:05 <lambdabot> Control.Concurrent forkIO :: IO () -> IO ThreadId
13:29:05 <lambdabot> GHC.Conc.Sync forkIO :: IO () -> IO ThreadId
13:29:05 <lambdabot> GHC.Conc forkIO :: IO () -> IO ThreadId
13:29:33 -!- Cyragia has joined.
13:29:46 <mroman> I'm surprised that's not in System.IO
13:30:45 <oerjan> concurrency isn't in the haskell standard, as only ghc supports it completely
13:31:05 <oerjan> (citation needed on the last part)
13:31:17 <oerjan> and System.IO is a standard module
13:31:41 <oerjan> (not that those are kept unchanged these days.)
13:32:23 <lambdabot> Control.Concurrent threadDelay :: Int -> IO ()
13:32:23 <lambdabot> GHC.Conc.IO threadDelay :: Int -> IO ()
13:32:23 <lambdabot> GHC.Conc threadDelay :: Int -> IO ()
13:37:52 <oerjan> let's see if lethally insulting the people who rejected my SO edit helps
13:43:09 <oerjan> nope, made it worse. as expected, really.
13:43:25 -!- nycs has changed nick to `^_^v.
13:43:50 <oerjan> damn why is there no way to send a private message to someone on SO
13:47:12 -!- {hk3380} has joined.
13:51:59 -!- tromp has quit (Remote host closed the connection).
13:56:09 -!- MindlessDrone has joined.
14:00:43 -!- MindlessDrone has quit (Ping timeout: 240 seconds).
14:01:05 -!- FreeFull has joined.
14:02:10 -!- Bike has joined.
14:14:37 -!- MindlessDrone has joined.
14:25:26 <mroman> The gauntlet is a pretty crappy movie....
14:25:55 <mroman> Am I really supposed to beleive that someone could order 120 policemen to just should rounds after rounds after rounds
14:27:57 -!- prooftechnique has joined.
14:34:51 -!- granderson has joined.
14:35:38 -!- granderson has quit (Client Quit).
14:36:08 -!- conehead has joined.
14:57:27 -!- Phantom_Hoover has joined.
15:05:31 -!- skarn has quit (Ping timeout: 240 seconds).
15:07:52 -!- Guest73440 has joined.
15:10:43 <HackEgo> [wiki] [[ΜCurse]] http://esolangs.org/w/index.php?diff=39633&oldid=39630 * Sacchan * (+369)
15:15:08 -!- edwardk has quit (Quit: Computer has gone to sleep.).
15:34:56 -!- Bike has quit (Ping timeout: 255 seconds).
15:36:42 -!- Phantom__Hoover has joined.
15:39:05 -!- Phantom_Hoover has quit (Ping timeout: 252 seconds).
15:42:35 -!- oerjan has quit (Quit: leaving).
15:45:08 -!- edwardk has joined.
15:59:57 -!- {hk3380} has quit (Ping timeout: 276 seconds).
16:04:58 -!- edwardk has quit (Ping timeout: 240 seconds).
16:06:32 -!- shikhout has quit (Remote host closed the connection).
16:29:28 -!- {hk3380} has joined.
16:32:09 -!- edwardk has joined.
16:43:05 -!- ter2 has changed nick to tertu.
16:43:17 -!- tertu has changed nick to nainai69.
16:43:21 -!- nainai69 has changed nick to tertu.
16:53:57 -!- prooftechnique has quit (Ping timeout: 265 seconds).
16:55:31 -!- tromp has joined.
16:56:35 -!- prooftechnique has joined.
16:59:14 -!- xk003 has joined.
16:59:47 -!- tromp has quit (Ping timeout: 255 seconds).
17:01:34 -!- xk002 has quit (Ping timeout: 240 seconds).
17:03:18 -!- xk003 has quit (Max SendQ exceeded).
17:03:44 -!- xk003 has joined.
17:08:24 -!- MoALTz has joined.
17:13:56 -!- xk003 has quit (Quit: Saindo).
17:14:21 -!- xk002 has joined.
17:28:26 -!- kmc has quit (Read error: Connection reset by peer).
17:28:55 -!- kmc has joined.
17:32:09 -!- xk003 has joined.
17:32:46 -!- xk003 has quit (Read error: Connection reset by peer).
17:33:24 -!- xk003 has joined.
17:34:25 -!- xk002 has quit (Disconnected by services).
17:34:41 -!- xk003 has quit (Read error: Connection reset by peer).
17:34:58 -!- xk002 has joined.
17:36:14 -!- shikhin has joined.
17:39:16 -!- shikhout has joined.
17:39:19 -!- shikhout has quit (Client Quit).
17:40:02 -!- shikhout has joined.
17:40:07 -!- shikhin has quit (Disconnected by services).
17:40:17 -!- shikhout has changed nick to shikhin.
17:41:44 -!- shikhin has changed nick to TheAlmightyGod.
17:42:12 -!- TheAlmightyGod has changed nick to shikhin.
17:42:45 <mroman> I don't like the new bitbucket UI
17:47:31 -!- impomatic has joined.
17:48:04 -!- MoALTz has quit (Quit: Leaving).
17:52:17 -!- nooodl has joined.
17:52:45 -!- Bike has joined.
18:04:08 <HackEgo> [wiki] [[Talk:CLooP]] N http://esolangs.org/w/index.php?oldid=39634 * GreyKnight * (+625) Created page with "== implementing a #hyper pforeach == The description for <code>pforeach</code> specifies that "the statements '''can''' be executed in parallel" (emphasis mine). So a <code>#..."
18:05:39 <kmc> "FBI 'could hire hackers on cannabis' to fight cybercrime… The US agency's current policy prohibits anyone working for it who has used cannabis in the past three years.
18:05:42 <kmc> However, its director James Comey has acknowledged that this is complicating its efforts to recruit hacking experts"
18:06:26 <Bike> still laughing at the idea of someone coming into an FBI job interview on DiPT or somethin
18:07:00 <kmc> that's a weird one
18:07:25 <Bike> "but it's legal!"
18:07:48 <mroman> I didn't know hackes smoke weed
18:08:01 <Bike> are you making a funny
18:08:53 <mroman> I never associated computer geeks with cannabis
18:13:17 <olsner> because cool kids do drugs and computer geeks aren't cool
18:13:35 <Bike> i see i grew up in a different environment from you two
18:13:42 <kmc> olsner: I hate that I'm 26 and I still think that way sometimes
18:13:45 <kmc> old habits die hard
18:14:39 <Bike> lol @ last three messages combined
18:15:28 <mroman> but I'm no hacker so I dunno
18:17:08 -!- conehead has quit (Read error: Connection reset by peer).
18:17:31 <kmc> my social group in college was focused largely around functional programming and experimental psychedelics
18:18:39 <kmc> it turns out you can nerd out about sex, drugs, and crime just as well as 'uncool' things
18:21:27 <kmc> FreeFull: mostly Haskell
18:21:28 <Bike> "which psychedelics"
18:21:31 <kmc> shikhin: Caltech
18:24:21 <fungot> olsner: on/ other from/ light to/ dark as truly as they now are.
18:24:30 <fungot> Available: agora alice c64 ct darwin* discworld enron europarl ff7 fisher fungot homestuck ic irc iwcs jargon lovecraft nethack oots pa qwantz sms speeches ss wp youtube
18:24:42 <kmc> Bike: 2C-E, 2C-I, 2C-C, DOI, mescaline, 5-MeO-DMT, 4-HO-DIPT, DIPT, 4-AcO-DMT, psilocin, 4-HO-MET, LSD
18:25:13 <fizzie> fungot: I bet you could generate names for experimental psychedelics.
18:25:14 <fungot> fizzie: art :) making rude canoes or rafts was likewise known; but as man existed at a remote period, but it would take an hour and an hour. i have received several confirmatory fnord in one :)/ earlier essay to/ flora fnord," ennobling, would, perhaps, may be long carried on, by a few species/ males are decorated with beautiful colours,/ male is either much redder or greener than/ female.
18:25:20 <kmc> gotta catch 'em all
18:25:35 <kmc> that's not true though, I'm never taking 2C-T-* or 25I-NBOMe
18:26:05 <Bike> that's the spirit
18:26:24 <Bike> i'm doing ochem nomenclature in class again btw and i'm pretty sure it's np-hard at least
18:28:03 <Bike> besides the graph stuff, i think the numbering might be reducible to knapsack sorta thing
18:29:09 <fizzie> "The new TLDs we have added today are: .dance, .democrat, .exposed, .foundation"
18:29:12 <fizzie> I don't know why, but combined like that, it sounds kinda strange.
18:29:25 <fizzie> Dance, democrat, your foundation is exposed.
18:29:38 <nortti> "dance, democrat exposed foundation"
18:31:23 <mroman> are these TLDs owned privately?
18:31:26 -!- MindlessDrone has quit (Quit: MindlessDrone).
18:31:37 <MDude> Foundation exposed dance democrat.
18:31:40 <mroman> i.e. if you bought .dance nobody can use .dance?
18:32:03 <MDude> Unless you lease it out, like other TLD owners.
18:32:16 <MDude> You can lease out subdomains to any domain you own.
18:32:40 <MDude> Time to buy the .exe TLD.
18:33:18 <mroman> What do you mean on foo.exe? Did you open it?
18:34:10 <mroman> Somebody should buy .eso though .
18:34:15 <MDude> .corn is also nice, it that it's tricky if you don't look closely.
18:34:52 <mroman> Who want's .corn anyway o_O
18:35:17 -!- ^v has joined.
18:35:23 <mroman> Is there a lenght limitation to tlds?
18:35:28 <MDude> It's TLD for farmers in the US, where we grow so much corn.
18:35:43 -!- conehead has joined.
18:35:58 <MDude> I'm guessing however long the people in charge of selling them will allow.
18:36:35 <MDude> I wonder, if you won a TLD, can you make a website that's just that without the .?
18:36:43 <mroman> i.amtakingallyourmoneyyouprick
18:37:38 <MDude> The website for silent protagonists everywhere.
18:37:46 <fizzie> 63 characters is at least one limit. I don't know if ICANN imposed anything else in the new gTLD program.
18:40:23 <fizzie> And I think ICANN frowned on having A/AAAA records on a TLD. Some of the applicants wanted to.
18:40:33 <fizzie> (Technically, you can.)
18:41:05 <fizzie> (Though your users might run into "search suffix added automatically to names with no dots" problems.)
18:42:16 <MDude> I'd like a lot of current browser behavior thrown out anyway.
18:42:49 <fizzie> That might be a system DNS resolver behavior, too.
18:43:46 <fizzie> You can check gTLD applications at https://gtldresult.icann.org/application-result/applicationstatus -- and download the public portion, if you're interested about the applicant's plans on whether to allow general registration.
18:44:18 <fizzie> (It's possible that was more or less a requirement for actually getting a "generic word" TLD.)
18:45:03 <elliott> I hear there is or was someone who works for that NIC called Ian with the email n@ai. possibly apocryphal
18:45:21 <fizzie> I think I heard about that, too.
18:45:39 <fizzie> Yes, it probably was a #esoteric discussion.
18:45:51 <nooodl> elliott: this is a good url how is it legal
18:46:05 <elliott> nooodl: example.com is actually example.com.
18:46:27 <elliott> and the way DNS works, you resolve foo.bar.com. using bar.com. the same way you resolve bar.com. using com.
18:46:43 <elliott> there's nothing stopping the owner of the .ai ccTLD from putting an A record at the top level, it's just horrendously evil
18:46:53 <elliott> you need the final . because browsers
18:46:57 <elliott> though http://ai/ works in firefox here
18:47:02 <fizzie> I have a feeling ccTLDs may have more latitude there than participants of the gTLD program.
18:47:18 <fizzie> http://blog.towo.eu/a-records-on-top-level-domains/ quite a lot of them actually have/had something.
18:47:31 <nooodl> not in chrome, but i wonder where it's actually looking when i ask it to retrieve http://ai/ then
18:47:55 -!- Guest73440 has quit (Changing host).
18:47:55 -!- Guest73440 has joined.
18:47:59 -!- Guest73440 has changed nick to skarn.
18:48:18 -!- tertu has quit (Ping timeout: 276 seconds).
18:48:21 <fizzie> Anyway, there was some sort of a quasi-recent decision against it; if not a rule, then maybe a best-practices comment from some authoritative-sounding source, or some-such.
18:49:48 <elliott> fizzie: it seems like "to" no longer exists :(
18:57:29 <Bike> ahaha, ai really works
18:58:13 <elliott> quintopia: as in the A record for "to."
18:58:22 <elliott> TLDs don't really do the stop existing thing much.
18:58:36 <Bike> unless they're east germany!
19:03:41 -!- MDude has quit (Ping timeout: 252 seconds).
19:07:28 -!- tertu has joined.
19:08:20 -!- shikhin has quit (Quit: leaving).
19:08:39 -!- shikhin has joined.
19:13:42 <fizzie> Czechoslovakia's .cs stopped existing when they split to the Czech Republic and Slovakia.
19:22:30 -!- Slereah_ has joined.
19:25:31 -!- Slereah has quit (Ping timeout: 240 seconds).
19:26:32 -!- Slereah has joined.
19:28:42 <int-e> interesting. https://en.wikipedia.org/wiki/.dd
19:29:06 -!- Slereah_ has quit (Ping timeout: 265 seconds).
19:31:46 <kmc> you can still register .su domains I think
19:32:40 <Bike> another channel i'm on banned *.dd, *.aq, *.kp
19:32:47 <Slereah> Because TLD appeared on the tail end of the soviet union
19:33:23 <Slereah> Those poor antarctica people
19:33:40 <Bike> haha, i thought .su was sudan and was like wait they didn't rename it did they
19:36:05 <Bike> kmc: btw, blaze it https://twitter.com/mnxmnkmnd/status/469197478235869184/photo/1/large
19:38:11 -!- ^v has quit (Quit: Leaving).
19:38:25 -!- ^v has joined.
19:39:12 <kmc> is the joke that's THC?
19:39:29 <Bike> DMT. I figured it was a good start
19:40:01 <Bike> i don't think my kit's big enough for THC :(
19:40:59 <kmc> it's a biggie
19:41:17 <Bike> i didn't have enough double bonds for dmt, even
19:42:41 <kmc> http://i.imgur.com/pgGaX.jpg
19:43:15 <HackEgo> [wiki] [[0(nop^)]] http://esolangs.org/w/index.php?diff=39635&oldid=39613 * John Misciagno * (+215)
19:43:39 <Bike> oh that weird ball thing is supposed to be LSD huh. never noticed
19:44:53 <Bike> makes more sense than most depictions of armoaticity to me :V
19:45:14 <kmc> do you think that's what the rainbows are meant to represent
19:49:05 <Bike> yeah, that's what i figured for the hex ring right above his hand
19:49:24 <Bike> electron density diagrams are pretty colorful, it could work
19:49:48 <Bike> http://employees.csbsju.edu/hjakubowski/classes/ch123/HCl_H20ElDensity.gif rainbowz
19:54:32 <int-e> http://1.2.3.13/bmi/www.tablespoon.com/~/media/Images/Articles/tfa/2013/04/2013-04-13-rainbow-bread-p9458-580w.jpg
19:54:44 <int-e> http://www.tablespoon.com/~/media/Images/Articles/tfa/2013/04/2013-04-13-rainbow-bread-p9458-580w.jpg
19:55:42 <int-e> (the "transparent" proxy of this mobile internet provider isn't.)
19:56:35 <int-e> to make things worse, 1.2.3.0/24 is actually assigned ... and not to them
19:56:42 -!- MDude has joined.
20:03:00 <ion> http://www.ottawacitizen.com/entertainment/copyright+rules+killed+Hadfield+Space+Oddity/9842445/story.html
20:03:48 -!- Cyragia has quit (Ping timeout: 240 seconds).
20:05:02 -!- mhi^ has joined.
20:06:09 -!- yorick has quit (Remote host closed the connection).
20:07:58 <HackEgo> [wiki] [[0(nop^)]] http://esolangs.org/w/index.php?diff=39636&oldid=39635 * John Misciagno * (+1)
20:10:42 <fizzie> Yes, it's assigned, but only to the (APNIC) Debogon project, not to any real traffic.
20:11:37 <kmc> the APNIC Debogon project, which exists because of shit like this
20:11:39 <kmc> this is why we can't have nice things
20:11:57 <fizzie> I remember the talk about measuring "background radiation" to 1.1.1.0/24 and 1.2.3.0/24 when they started prepping 1.0.0.0/8 for general use.
20:12:22 <kmc> internet background radiation is anisotropic
20:12:52 <fizzie> The fingerprint of creation!
20:13:50 <Bike> hm i'm still on ipv4 aren't i :(
20:15:11 <Bike> i geolocate to the other side of the state, you'd think they'd mvoe to ipv6 as long as they're doing their own isp-ing
20:17:45 <kmc> i'm on IPv8, get with the times
20:17:55 -!- aloril has quit (Ping timeout: 265 seconds).
20:19:27 -!- {hk3380} has quit (Ping timeout: 240 seconds).
20:19:45 <kmc> we don't talk about IPv5
20:19:49 <fizzie> Was used for some experimental protocol that went nowhere.
20:20:07 <nooodl> http://en.wikipedia.org/wiki/Internet_Stream_Protocol rip ;_;
20:21:43 <fizzie> Wonder how it's going for HIP. There were some people from our university involved in that.
20:24:54 -!- tertu has quit (Ping timeout: 240 seconds).
20:26:52 <fizzie> http://www.cs.helsinki.fi/u/gurtov/ there's a HIP guy, for example.
20:27:20 <fizzie> (Not really "from our university", but slightly associated with, anyway.)
20:31:24 -!- aloril has joined.
20:34:30 -!- shikhin has quit (Quit: Sleep.).
20:37:57 -!- {hk3380} has joined.
20:42:01 -!- xk002 has quit (Read error: Connection reset by peer).
20:42:35 -!- xk002 has joined.
20:44:04 -!- nooodl_ has joined.
20:47:03 -!- nooodl has quit (Ping timeout: 240 seconds).
20:52:11 -!- Bike has quit (Ping timeout: 255 seconds).
21:02:20 -!- Patashu has joined.
21:04:06 -!- prooftechnique has quit (Quit: leaving).
21:07:24 -!- xk003 has joined.
21:08:25 -!- Patashu_ has joined.
21:08:25 -!- Patashu has quit (Disconnected by services).
21:11:05 -!- xk002 has quit (Ping timeout: 264 seconds).
21:12:28 -!- xk002 has joined.
21:14:19 -!- xk003 has quit (Ping timeout: 240 seconds).
21:18:29 -!- Bike has joined.
21:23:58 -!- Patashu_ has quit (Ping timeout: 240 seconds).
21:26:04 -!- Frooxius has quit (Read error: Connection reset by peer).
21:27:47 -!- Frooxius has joined.
21:32:58 -!- {hk3380} has quit (Ping timeout: 240 seconds).
21:39:20 -!- oerjan has joined.
21:48:31 -!- Frooxius has quit (Quit: *bubbles away*).
21:55:04 -!- xk002 has quit (Read error: Connection reset by peer).
21:56:01 -!- Frooxius has joined.
21:56:02 -!- xk002 has joined.
22:06:19 -!- edwardk has quit (Ping timeout: 240 seconds).
22:25:20 -!- tromp has joined.
22:26:21 -!- {hk3380} has joined.
22:29:34 -!- tromp__ has quit (Ping timeout: 265 seconds).
22:32:52 -!- jhj1 has quit (Ping timeout: 245 seconds).
22:34:10 -!- coppro_ has joined.
22:34:29 -!- diginet_ has joined.
22:34:43 -!- coppro has quit (Ping timeout: 245 seconds).
22:34:52 -!- nortti has quit (Ping timeout: 245 seconds).
22:35:16 -!- kmc_ has joined.
22:36:36 -!- nortti has joined.
22:38:10 -!- diginet has quit (Ping timeout: 265 seconds).
22:38:10 -!- kmc has quit (Ping timeout: 265 seconds).
22:38:12 -!- kmc_ has changed nick to kmc.
22:46:44 -!- Slereah_ has joined.
22:49:15 -!- {hk3380} has quit (Quit: WeeChat 0.3.8).
22:49:33 -!- nortti has quit (*.net *.split).
22:49:36 -!- Slereah has quit (*.net *.split).
22:49:40 -!- Sorella has joined.
22:50:23 -!- hk3380 has joined.
22:51:27 -!- nortti has joined.
22:54:53 -!- `^_^v has quit (Excess Flood).
22:55:18 -!- `^_^v has joined.
23:00:36 -!- prooftechnique has joined.
23:03:39 -!- Phantom_Hoover has joined.
23:04:51 -!- Phantom__Hoover has quit (Ping timeout: 258 seconds).
23:05:47 -!- jhj1 has joined.
23:24:19 <kmc> 01:39 < kmc> consciousness is cache coherence
23:24:26 <kmc> so, that was mostly intended to be nonsense
23:25:25 -!- nooodl_ has quit (Quit: Ik ga weg).
23:25:35 <kmc> but I do think it's interesting that the human brain and a modern digital computer are both massively distributed systems which work very hard to provide the illusion of a single coherent entity
23:25:57 <kmc> if consciousness is not a pure epiphenomenon, its evolutionary purpose probably has something to do with that
23:44:53 -!- Phantom_Hoover has quit (Read error: Connection reset by peer).
23:56:10 <kmc> cool, Rust lets you disable the equivalent of -Werror for just one file, from within that file
23:56:15 <kmc> useful during development
23:59:23 -!- Sgeo has joined.
00:08:45 <shachaf> does it have the equivalent of -fdefer-type-errors
00:08:53 <kmc> but I keep talking about it
00:08:59 <kmc> less clear what it means in a strict language
00:09:04 <kmc> you could do it on a per-top-level-function basis, though
00:09:12 <kmc> since we don't have type inference between top level functions, anyway
00:09:22 <kmc> shachaf: you should implement it
00:09:25 <shachaf> can't you replace a type error with a call to exit(whatever)
00:09:45 <kmc> yeah but in Haskell it will only happen if the value is actually used
00:09:52 <shachaf> or the line the type error is on
00:09:58 <shachaf> well, sure, it won't be as fine-grained
00:10:35 <shachaf> but i think i'm fine with that usually
00:10:54 <kmc> only the finest of grains will do
00:13:37 <Bike> i'm imagining this disablement being like #PRAGMA fuckthisfile
00:14:00 <kmc> it's actually #![warn(warnings)] which is... not the most clear
00:14:21 <kmc> the -Wall equivalent is deny(warnings) aka -D warnings on the command line
00:14:55 <shachaf> is it scoped or just per-file
00:15:56 <Bike> warn(warnings), lol
00:18:16 <Taneb> kmc, type errors on, eg, the wrong side of a conditional can still be deferred?
00:20:02 <kmc> shachaf: all of the warning attributes can be applied to a module or function etc.
00:20:10 <kmc> and you can change the warning handling further within that thing
00:20:22 <kmc> except there's also an attribute to make a warning fatal and forbid making it non-fatal inside
00:20:26 -!- idris-bot has joined.
00:20:49 <kmc> Taneb: yeah
00:20:52 <oerjan> ( "this is your last warning"
00:20:53 <idris-bot> "this is your last warning" : String
00:29:06 -!- mhi^ has quit (Quit: Lost terminal).
00:31:19 <Melvar> I was going to say we don’t have warnings yet, but we do … --warnpartial and --warnreach .
00:38:36 <^v> a wild oerjan
00:56:15 -!- hk3380 has quit (Ping timeout: 240 seconds).
01:07:08 -!- coppro_ has changed nick to coppro.
01:12:27 -!- olsner has quit (Ping timeout: 276 seconds).
01:14:25 <Sgeo> At work, I forgot that Java enums aren't algebraic data types
01:20:32 <Taneb> Aaaaaah it's poll day today
01:22:37 <Taneb> But who should I vote for? I don't know!
01:22:49 <Taneb> Being an adult is scary sometimes
01:24:11 <quintopia> if you can't tell, the answer is probably 'not a lawyer or activist or lobbyist'
01:24:14 <Taneb> I could vote for the Yorkshire Independence Party!
01:24:18 <Taneb> (I... actually can)
01:25:31 <Taneb> Well, "Yorkshire First"
01:27:03 <Bike> is this a racist thing
01:27:37 <Taneb> I... don't know their policies
01:27:47 <Taneb> Maybe they just don't like Lancastrians
01:28:53 <Bike> It is otherwise described as a “pragmatic” centrist party with “progressive views on economic, social and environmental issues”, with the top goal of building “a self-assured and outward-looking Yorkshire where the decisions affecting Yorkshire people are taken locally”.»
01:28:58 <Bike> man this computer is bad
01:29:17 <HackEgo> 102) <coppro> what's the data of? [...] <Sgeo> Locations in a now deceased game called Mutation <coppro> I have no problems with you being interested in online games <coppro> but the necrophilia is disturbing
01:29:34 <oerjan> Taneb: this is britain where every vote that doesn't have a chance of winning its circuit is wasted, right?
01:29:57 <Taneb> The europarl elections are different
01:31:16 <oerjan> ...what is the yorkshire independence party doing there.
01:31:41 <oerjan> but yeah i think europarl is proportional, at least partly
01:32:06 <Taneb> Europarl is proportional at the region level, Yorkshire and the Humber has 6 seats
01:32:52 <Taneb> Of the 6 from last time, 2 are no longer members of their parties
01:33:39 <oerjan> just do your part to keep ukip from becoming britain's biggest europarl party twh
01:34:40 * oerjan read about that in the newpaper.
01:36:17 <oerjan> well i _think_ it was there, anyhow.
01:36:54 <Taneb> Hexham's local newspaper is "Hexham Courant incorporating Alston Herald, Hexham Herald, Haltwhistle Herald and Haltwhistle Echo"
01:38:06 <oerjan> just call it the Hexham Chimæra and be done with it.
01:46:36 -!- olsner has joined.
01:58:22 <kmc> Taneb: anyone from the Official Monster Raving Loony Party?
02:00:12 <Taneb> I'll probably vote lib dem, there's almost as good a joke
02:01:59 <pikhq> Pity, OMRLP is definitely the best party.
02:02:23 <kmc> Taneb: how do you feel about scottish independence
02:03:21 -!- xk003 has joined.
02:05:21 -!- xk002 has quit (Ping timeout: 252 seconds).
02:06:06 <kmc> it would probably send the UK lurching even further to the right :/
02:06:31 <Taneb> ...why am I drawing the 20th iteration of the dragon fractal using Python's turtle module
02:07:06 <kmc> that sounds like a fine idea
02:08:12 <Bike> why am i drawing the 20th iteration of the dragon fractal using paper and pen
02:09:17 <Taneb> Because you have too much time and paper
02:10:24 <kmc> do you ever draw a sierpinksi triangle by hand using the randomized algorithm?
02:10:25 <kmc> it's p. fun
02:11:23 <Bike> i was more the "make fun of you for doing that" guy
02:11:47 -!- realzies has quit (Quit: realzies).
02:13:21 <pikhq> Randomized algorithm?
02:13:25 <pikhq> I haven't heard of that one.
02:14:50 <Bike> http://en.wikipedia.org/wiki/Sierpinski_triangle#Chaos_game
02:16:59 -!- xk003 has quit (Ping timeout: 252 seconds).
02:18:57 -!- tromp_ has joined.
02:19:26 -!- xk003 has joined.
02:19:31 -!- xk004 has joined.
02:19:42 <oerjan> http://en.wikipedia.org/wiki/Sierpinski_triangle#Chaos_game
02:20:29 -!- xk003 has quit (Client Quit).
02:20:34 -!- xk004 has quit (Read error: Connection reset by peer).
02:20:50 -!- xk002 has joined.
02:21:01 -!- prooftechnique has quit (Quit: leaving).
02:24:45 <kmc> touchy stupidpad
02:27:39 -!- realzies has joined.
02:31:48 <oerjan> Bike: psst http://biohaskell.org/
02:32:28 <Bike> i looked up some code for this book i'm reading and it uses a matlab feature i didn't know existed, namely, declaring variables as global within a function
02:32:36 <kmc> Bike: hilarious
02:32:46 <oerjan> Christian Höner zu Siederdissen is quite a name.
02:33:19 <Sgeo> This is a great theme song https://www.youtube.com/watch?v=CGufyFt6zQc
02:33:31 <Bike> if someone writes a haskell thing that lets me vary parameter sets to a function that takes like a million parameters and doesn't look ugly as fuck i'll use it
02:34:05 <Jafet> If they're using the biohazard symbol to represent biology, they should also use \bottom to represent haskell
02:34:22 <oerjan> Bike: CLEARLY you need lenses hth
02:35:12 <Bike> well, for example, hodgkin-huxley has like a dozen parameters. i just want something to run a model with various sets of arguments that doesn't look terrible
02:35:30 <Bike> right now i'm loading variable assignments from a file (uuuuuuugh)
02:35:51 -!- xk002 has quit (Ping timeout: 240 seconds).
02:36:03 <Bike> relatedly, are there any good ode sims in haskell, i guess
02:36:15 <elliott> Bike: python has that matlab feature
02:36:59 <Bike> python has every matlab feature
02:37:15 <Jafet> Does that mean all matlab features are bad
02:37:47 <monotone> JavaScript has that feature too. Every once in a while someone actually uses it intentionally.
02:37:50 <Bike> have you ever seen a matlab program??
02:37:53 <oerjan> no, it means some python ones are hth
02:38:12 <Bike> here you know what i'll show you what i was looking at: http://www.izhikevich.org/publications/dsn/addprob.pdf
02:38:18 <Bike> point one: code is a pdf
02:38:57 <Jafet> Haskell's horrible record system is actually a p. good parameter system
02:39:06 <Bike> point two: I = par(13)*(m.^p.*h.^q)'.*((v(:,2)-E)*ones(1,length(times)));
02:39:07 -!- irctc664 has joined.
02:39:08 <Bike> THIS IS MY LIFE
02:39:15 -!- irctc664 has quit (Client Quit).
02:39:21 <Bike> yeah that's right run
02:39:26 * oerjan slips Bike the cyanide pills
02:39:35 <Bike> nobody could love me
02:39:35 <kmc> Jafet: truth
02:41:02 -!- xk002 has joined.
02:42:51 -!- xk002 has quit (Read error: Connection reset by peer).
02:53:46 -!- BeingUntoDeath has joined.
02:54:13 -!- Sgeo_ has joined.
02:54:19 -!- nycs has joined.
02:57:14 -!- not^v has joined.
02:57:15 -!- douglass1 has joined.
03:03:05 -!- Gracenotes has quit (Ping timeout: 258 seconds).
03:03:11 -!- douglass_ has quit (Ping timeout: 258 seconds).
03:03:12 -!- Sgeo has quit (Ping timeout: 258 seconds).
03:03:12 -!- `^_^v has quit (Ping timeout: 258 seconds).
03:03:17 -!- EgoBot has joined.
03:03:40 -!- EgoBot has quit (*.net *.split).
03:04:02 -!- EgoBot has joined.
03:05:23 <oerjan> !addinterp hug sh echo 'Keep your dirty fingers off me!'
03:05:24 <EgoBot> Interpreter hug installed.
03:06:37 -!- BeingUntoDeath has quit.
03:06:58 -!- BeingUntoDeath has joined.
03:07:23 -!- Gracenotes_ has joined.
03:07:23 -!- not^v has quit (Read error: Connection reset by peer).
03:07:23 -!- not^v has joined.
03:07:24 -!- MDude has quit (Ping timeout: 252 seconds).
03:07:36 -!- MDude has joined.
03:09:06 -!- conehead has quit (*.net *.split).
03:20:21 -!- ^v has quit (Quit: Leaving).
03:32:54 -!- Sorella has quit (Quit: It is tiem!).
03:34:21 <oerjan> "As obvious as this sounds, it seems to me that large swaths of consciousness-theorizing can just be summarily rejected for trying to have their brain and eat it in precisely the above way."
03:34:31 <oerjan> http://www.scottaaronson.com/blog/?p=1799
03:35:41 -!- BeingUntoDeath has quit.
03:36:50 -!- BeingUntoDeath has joined.
03:41:44 <Bike> mathematical theory of consciousness lol
03:45:14 <Bike> "Strikingly, despite the large literature about Φ, I had a hard time finding a clear mathematical definition of it" yep lol
03:45:56 <Bike> these people need jesus + thermodynamics
03:46:20 -!- oerjan has quit (Quit: Good night).
03:47:01 <Bike> the pancreas joke is funny given that i have a paper on modeling pancreatic cells open
03:48:43 -!- BeingUntoDeath has quit.
03:49:44 -!- BeingUntoDeath has joined.
03:50:05 -!- not^v has quit (Quit: http://i.imgur.com/Akc6r.gif).
03:53:47 -!- BeingUntoDeath has quit (Client Quit).
03:54:01 -!- BeingUntoDeath has joined.
04:16:11 -!- MDude has changed nick to MDream.
04:43:42 -!- Positive07 has joined.
04:47:57 <Bike> maxin', relaxin'
04:48:23 <kmc> `relcome Positive07
04:48:25 <HackEgo> 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.)
04:49:34 <Positive07> Yeah I come from there... Im quite intrigued by esolangs and looking for ideas for a new one
04:51:36 <quintopia> well, usually people come here because they already have some glimmer of an idea and want some feedback on how to improve it
04:51:57 <quintopia> and some are willing to offer said feedback as long as its not another brainfuck clone :P
04:53:35 <Bike> http://scholar.google.co.uk/citations?sortby=pubdate&hl=en&user=suo5D8wAAAAJ&view_op=list_works roll w/it
04:54:55 <coppro> Positive07: do something involving graph grammars
04:55:40 <quintopia> grammars could be more sophisticated than eodermdrome
04:55:40 <coppro> I mention graph grammars for purely selfish reasons
04:55:55 <Positive07> Yeah have some ideas... gifs qrs and cym plus some instructions, basically you take your code and make qr codes with it then put it into cyan magenta and yellow channels and combine them., do this multiple times andmakes frames of a gif
04:56:49 <quintopia> that sounds less like a language and more like an encoding scheme
04:57:19 <Positive07> yeah it is, the language its underneath
04:59:07 <Positive07> underneath its brainfuck :D just kidding -.-
05:00:26 <Positive07> hey you are into electronics too! Thats great
05:01:23 <Bike> i am not adamatzky, i just like electrocytoplasm
05:01:47 <Bike> dude's made a career out of building electronic things out of slime molds. i respect that
05:02:23 <coppro> I'm not into electronics
05:02:26 <coppro> why does google say I am?
05:04:40 <Positive07> Hated graph grammars since I was a child... not because I'm bad at it but I just dont like to represent data like that
05:06:35 <kmc> I've reached inbox 666
05:11:53 -!- tertu has joined.
05:19:38 <kmc> well I didn't have any email when I was born
05:19:41 <kmc> I didn't even have an email address
05:19:44 <kmc> unlike kids these days
05:23:11 <quintopia> i thought you were working on reducing the number of emails in your inbox
05:23:40 <quintopia> i was impressed, since it would take me a full day or even longer to get down to 666
05:27:09 -!- Positive07 has quit (Quit: Page closed).
05:29:31 -!- Positive07 has joined.
05:50:41 -!- aloril has quit (Ping timeout: 264 seconds).
06:01:45 -!- Sgeo has joined.
06:03:28 -!- aloril has joined.
06:04:08 -!- Sgeo_ has quit (Ping timeout: 252 seconds).
06:06:16 -!- BeingUntoDeath has quit.
06:13:09 <kmc> /topic серафими многоꙮчитїи
06:15:28 <kmc> why does italic г look like a backwards 's'?
06:16:18 -!- Positive07 has quit (Ping timeout: 240 seconds).
06:22:32 -!- FreeFull has quit.
06:25:07 <HackEgo> [wiki] [[ΜCurse]] http://esolangs.org/w/index.php?diff=39637&oldid=39633 * Sacchan * (+186)
06:26:13 <HackEgo> [wiki] [[ΜCurse]] http://esolangs.org/w/index.php?diff=39638&oldid=39637 * Sacchan * (-27)
06:26:23 <shachaf> i don't see it for https://en.wikipedia.org/wiki/Ghe_with_upturn or https://en.wikipedia.org/wiki/Gje
06:26:41 <HackEgo> [wiki] [[ΜCurse]] http://esolangs.org/w/index.php?diff=39639&oldid=39638 * Sacchan * (-6)
06:27:35 <HackEgo> [wiki] [[ΜCurse]] http://esolangs.org/w/index.php?diff=39640&oldid=39639 * Sacchan * (+20)
06:27:40 <shachaf> https://bugs.launchpad.net/ubuntu-font-family/+bug/823276
06:31:46 <kmc> <span color="#900">гѓ</span> I Can't Believe It's Not HTML
06:33:13 <shachaf> kmc: do you think rustc would be a better place to spend one's time than ghc if one was to work on some compiler
06:33:18 <shachaf> perhaps that's an odd comparison to make
06:35:36 <kmc> bit underspecified
06:35:47 <kmc> it depends on your goals
06:36:30 <kmc> if you want to work on exotic type system features, no
06:37:49 <kmc> it makes sense for me because working on rustc helps me do my job :)
06:37:51 <kmc> maybe I will actually implement loadable warnings
06:38:43 <kmc> do you have any nifty use cases for that? i gave a few on https://github.com/mozilla/rust/issues/14067
06:39:23 -!- hk3380 has joined.
06:39:52 <kmc> are there C or C++ projects today which use GCC plugins to implement custom static checking?
06:40:33 <kmc> PaX uses GCC plugins to harden the Linux kernel in various ways, but I think all of them involve modifying the code
06:41:52 <shachaf> I think there are things for clang.
06:45:35 <kmc> it's so nice doing systems programming in a language with a macro system that isn't shit
06:46:42 <shachaf> E.g. https://tecnocode.co.uk/2013/12/09/clang-plugin-for-glib-and-gnome/
06:48:59 <kmc> now I remember that there's also a plugin, written in Python, to audit usage of the CPython API
06:49:18 <kmc> a plugin for GCC
07:03:14 -!- glogbackup has quit (Ping timeout: 240 seconds).
07:04:37 <HackEgo> [wiki] [[ΜCurse]] http://esolangs.org/w/index.php?diff=39641&oldid=39640 * Sacchan * (+59)
07:05:35 -!- hk3380 has quit (Ping timeout: 265 seconds).
07:06:32 -!- clog has quit (Ping timeout: 245 seconds).
07:10:54 <kmc> http://en.wikipedia.org/wiki/Tempest_prognosticator
07:29:55 -!- Bike has quit (Ping timeout: 240 seconds).
07:29:58 <HackEgo> [wiki] [[0(nop^)]] http://esolangs.org/w/index.php?diff=39642&oldid=39636 * John Misciagno * (-102)
08:13:12 -!- tromp_ has quit (Remote host closed the connection).
08:34:59 -!- Patashu has joined.
08:40:43 -!- Patashu has quit (Disconnected by services).
08:40:43 -!- Patashu_ has joined.
08:47:19 <myname> why the hell does cabal install complains about not finding a shared object if the corresponding package is installed >_>
09:06:18 -!- clog has joined.
09:26:17 -!- Phantom_Hoover has joined.
09:26:17 -!- Phantom_Hoover has quit (Client Quit).
09:26:20 -!- Phantom__Hoover has joined.
09:28:22 -!- Phantom__Hoover has quit (Read error: Connection reset by peer).
09:38:08 -!- Slereah has joined.
09:39:31 -!- Slereah_ has quit (Ping timeout: 240 seconds).
09:40:09 -!- Phantom_Hoover has joined.
10:19:02 -!- boily has joined.
10:24:05 -!- hk3380 has joined.
10:25:55 -!- MindlessDrone has joined.
10:45:34 -!- KingOfKarlsruhe has joined.
11:01:31 -!- boily has quit (Quit: Poulet!).
11:16:44 -!- tromp_ has joined.
11:21:13 -!- tromp_ has quit (Ping timeout: 252 seconds).
11:25:50 -!- KingOfKarlsruhe has quit (Quit: ChatZilla 0.9.90.1 [Firefox 29.0/20140421221237]).
11:31:37 -!- MindlessDrone has quit (Quit: MindlessDrone).
11:37:42 -!- Slereah has quit (Ping timeout: 265 seconds).
11:39:31 -!- Slereah has joined.
11:43:40 -!- xk002 has joined.
11:53:50 -!- Tritonio has joined.
12:05:57 -!- xk002 has quit (Ping timeout: 252 seconds).
12:07:42 -!- xk002 has joined.
12:13:26 -!- oerjan has joined.
12:15:06 <mroman> "pattern syntax in expression context"
12:15:36 <mroman> You can't nest case in Haskell?
12:16:53 <mroman> I guess it's some tab/spaces mixup then
12:17:39 <mroman> My editor inserts tabs when I do 4 spaces
12:17:59 <oerjan> you can program haskell with that setting.
12:18:12 <oerjan> well, technically you can.
12:18:32 <fizzie> You can tune a filesystem, but you can't tunafish.
12:18:32 -!- yorick has joined.
12:18:37 <mroman> you can. It just does'nt work when nesting cases :D
12:18:51 <oerjan> but then you must make sure to _only_ use tabs for indentation, and never do alignment-based layout.
12:19:14 <oerjan> mroman: you know haskell _defines_ tabs as equivalent to 8 spaces, right?
12:19:33 <oerjan> (or precisely, 8 space column fits)
12:19:43 <FireFly> I've seen python code-golfs make use of that
12:19:52 <mroman> oerjan: no. But I know that it's probably a bad idea to mix tabs and spaces since indentation matters
12:21:20 <mroman> or maybe it inserts tabs when pressing enter
12:21:25 <mroman> because it has this auto indentation stuff
12:21:40 <mroman> not worth discussing it ;)
12:21:56 <mroman> I've changed it to "replace tabs with spaces" and things work fine
12:27:39 <oerjan> `addquote <Bike> dude's made a career out of building electronic things out of slime molds. i respect that
12:27:41 <HackEgo> 1196) <Bike> dude's made a career out of building electronic things out of slime molds. i respect that
12:30:34 <oerjan> <kmc> why does italic г look like a backwards 's'? <-- because cyrillic italics is insane, hth
12:31:01 <fizzie> I actually wondered for quite long why "italic r" would look like a backwards s.
12:31:38 <fizzie> And also how those wikilinks about cyrillic characters are relevant w.r.t. r.
12:32:17 <oerjan> insane enough that it's a problem for me that google translate italicizes its spell correction suggestions.
12:32:28 <Melvar> You know how traditional cursive r looks not much like print r either?
12:33:08 <oerjan> oh i'm sure the latin alphabet is just as insane. what's this lower case madness?!?!
12:33:12 -!- Sgeo has quit (Read error: Connection reset by peer).
12:33:25 <oerjan> (admittedly cyrillic borrowed it from latin)
12:34:08 <fizzie> YES I ALSO THINK LOWER CASE IS ENTIRELY UNNECESSARY AND THE SAME GOES FOR PUNCTUATION TBH
12:34:31 -!- ^v has joined.
12:34:49 <oerjan> actuallyitscapitalsthatareunnecessaryasarespacesmanywritingsystemsdofinewithoutthem
12:36:02 <mroman> spacesareunnecessarytoo
12:36:14 <mroman> japanesedoesnthavethemandtheycanreadfineiguess
12:36:34 <fizzie> If it's a unicameral writing system, how can you tell if it's lacking lower or upper case?
12:36:42 <nortti> VVESHOVLDGOBACKTOTHEORIGINALLATINALPHABET
12:37:11 <nortti> ᚨᛚᛊᛟ᛬ᚱᚢᚾᛖᛊ᛬ᚨᚱᛖ᛬ᚠᛁᚾᛖ᛬ᛏᛟᛟ
12:37:11 <Melvar> mroman: They have three distinct grapheme sets though.
12:42:22 <Melvar> Has anyone else found firefox more crashy since 29?
12:43:37 <oerjan> well 28 is perfect, 29 has _got_ to be worse.
12:44:39 <HackEgo> [wiki] [[ΜCurse]] http://esolangs.org/w/index.php?diff=39643&oldid=39641 * Sacchan * (+2)
12:49:52 <mroman> http://codepad.org/3kHXYnYM <- is this primitive recursion?
12:51:58 <oerjan> psst never use foldl(1) without ' hth
12:55:25 <oerjan> mroman: eval (Recurse xs) (Recurse xs) ... doesn't terminate afaict, thus it's definitely not primitive.
12:56:05 -!- Patashu_ has quit (Ping timeout: 264 seconds).
12:56:23 <mroman> oerjan: You can trivially express programs that don't terminate
12:56:25 <fizzie> I guess Firefox 496 will again be fine, then?
12:56:37 <oerjan> mroman: not with primitive recursion hth
12:56:40 <mroman> i.e looping until it becomes zero like the example given in main
12:56:51 <mroman> just use a positive start number and it won't halt
12:59:12 <oerjan> mroman: can you express f 1 = 1; f x | odd x = 3*x + 1 | otherwise = x `div` 2
12:59:49 <oerjan> 's pretty non-primitive recursive (since it's unproved that it halts)
13:00:01 -!- tromp_ has joined.
13:01:37 <oerjan> or are you saying that all nontermination is trivial, that might be
13:08:30 <mroman> http://codepad.org/dWcrt7fK <- jep, that's pretty much collatz
13:08:49 <oerjan> mroman: you might rewrite your Add as Value $ foldl1' (\qa b -> case eval b r args of Value qb -> qa + qb; _ -> 0) 0 xs, that's slightly different in the case the _first_ list element does not evaluate to a Value but i doubt you really want that corner case anyhow
13:10:21 <oerjan> your original ignores the value of the second element if the first does not give a Value
13:11:30 <mroman> I probably should error instead of Value 0 anyway
13:12:28 <oerjan> are args always Values?
13:12:58 <mroman> i.e Add [Mul [Value 3, Get 0], Value 1]
13:13:03 <oerjan> because that was the only way i could see your eval not giving a Value
13:13:03 <mroman> there's an expression as an argument
13:13:34 <mroman> you mean something else
13:13:35 <oerjan> (i mean if it doesn't have to be)
13:13:50 <mroman> I wan't to add some rewrite stuff too later
13:14:04 <mroman> which means that eval can return expressions too
13:14:24 <oerjan> ok well since you can express collatz it's definitely not primitive recursion.
13:20:24 <oerjan> if you error out it would probably be simpler to separate the folding and the evaluation: Value . foldl1' (+) $ map (\x -> evalToValue x r args) xs
13:21:10 <oerjan> although that could leak if you make it monadic later.
13:21:51 <lambdabot> Monad m => (a -> b -> m a) -> a -> [b] -> m a
13:24:23 -!- nycs has changed nick to `^_^v.
13:26:23 <mroman> You can actually call any function you want
13:26:29 <mroman> by just making a case statement in your function
13:26:41 <mroman> then just add a parameter to recurse which defines what it should do
13:27:12 <mroman> I pretty much suspect so
13:28:48 <mroman> I gotta define a syntax and write some parsec stuff for it
13:56:07 <mroman> (if== $0 1 1 (if== 1 (odd $0) (r (add (mul 3 $0) 1)) (r (div $0 2))))
13:56:15 -!- tertu has quit (Ping timeout: 240 seconds).
14:01:24 <mroman> Does this qualify as an esolang :D?
14:06:08 <oerjan> probably. it's not immensely radical, mind you...
14:07:04 <oerjan> this has never prevented anyone from adding stuff to the wiki. (ok, maybe someone.)
14:07:08 -!- tertu has joined.
14:14:39 -!- nooodl has joined.
14:18:41 <mroman> oerjan: There are probably already languages like that, yeh
14:22:02 -!- Sprocklem has joined.
14:28:13 <impomatic> mroman: did you want to enter that warrior in the tournament? There are a few other new players taking part...
14:30:07 <mroman> can you give me the link again?
14:46:51 <mroman> impomatic: memory is set to dat #0,#0 after each run, right?
14:50:26 <impomatic> mroman: It's dat $0, $0 and http://corewar.co.uk/spring2014.htm
14:50:28 -!- spiette has joined.
15:02:38 <mroman> impomatic: Mine uses a distance of 37, and -35
15:02:50 <mroman> so if it misses small warriors it will most likely loose
15:25:05 -!- not^v has joined.
15:38:37 -!- Tritonio has quit (Ping timeout: 252 seconds).
15:41:59 -!- oerjan has quit (Quit: leaving).
15:42:40 <mroman> Can I somehow find out in which commit a certain directory was deleted and recover it with git?
15:43:24 <not^v> not specifically no, you will have to scrape commits manually
15:43:53 <not^v> you can make a program to use the github api to find the last time something was modified
15:46:23 <mroman> why the hell am I even using a version control system
15:46:34 <`^_^v> if you know a file in the directory, you can do git log -- directory/file
15:46:41 <mroman> it's write once revert never
15:46:58 <`^_^v> i dont think git "tracks" just the directories
15:47:16 <`^_^v> well i guess it does
15:47:21 <`^_^v> but there have to be files in it
15:47:39 <`^_^v> i think git log -- directory would work
15:48:05 <mroman> I think checkout a certain commit should do it
15:49:18 <`^_^v> to recover the actual file, you can checkout or show with the commit hash
15:49:25 -!- MDream has changed nick to MDude.
15:49:28 <Jafet> Version control was invented to remember all the stupid things you did
15:50:15 <Jafet> and to vacuum up your time in the form of "commit messages".
15:50:54 <Jafet> Don't let it have its way! Make your next commit message asdfasgafsgasfy.
15:51:43 -!- shikhin has joined.
15:52:15 -!- tertu has quit (Ping timeout: 240 seconds).
16:02:48 -!- Rikkol has joined.
16:07:52 -!- Rikkol has left.
16:17:28 -!- Bike has joined.
16:47:28 <kmc> git has a pretty effective set of tools for erasing the stupid things you did
16:55:41 <int-e> Jafet: you know Linus' tech talk on git (at google), right?
16:56:43 <int-e> Jafet: because what you just said reminded me a lot of the opening words, where he talks about managing linux as a collection of tarballs and patches ... and then says that that's a superior source code management system compared to CVS :)
16:58:58 -!- nooodl_ has joined.
17:03:24 -!- nooodl has quit (Ping timeout: 276 seconds).
17:07:00 -!- FreeFull has joined.
17:12:31 <Taneb> Are any of you people in Austria
17:16:52 -!- MoALTz has joined.
17:24:14 <Taneb> I am not very good at this "getting stressed by exams" thing
17:24:22 <Taneb> I'm sat here singing Eurovision songs
17:25:39 <int-e> because after you get burned in an exam you can always rise again like a phoenix?
17:25:55 <Taneb> Because alcohol is free!
17:26:08 <Taneb> We are the winners!
17:26:08 <int-e> you don't have to sing for that, do you ...
17:26:25 -!- Sprocklem has quit (Quit: leaving).
17:26:50 <Taneb> I wasn't actually too keen on Rise Like A Phoenix, I preferred Moustache
17:28:41 <Taneb> Although I've gone off Moustache a bit now
17:35:51 <int-e> Hmm, good use of stage, but I'd rather switch off the sound, and they should rethink their color scheme ;-)
17:36:24 <int-e> <-- will not become a Moustache fan
17:37:55 -!- not^v has quit (Ping timeout: 240 seconds).
17:38:19 -!- not^v has joined.
17:39:13 -!- shikhout has joined.
17:41:26 -!- shikhout has quit (Client Quit).
17:42:38 -!- shikhin has quit (Ping timeout: 252 seconds).
17:52:00 -!- Cyragia has joined.
18:21:34 <mroman> No standard for pseudocode syntax exists, as a program in pseudocode is not an executable program. <- I see some work for the ESOSC :P
18:23:30 <FireFly> Surely some standards organ must've tried to standardise pseudocode syntax?
18:24:04 -!- tertu has joined.
18:28:06 <olsner> I think if you really standardise pseudocode it will no longer be pseudo and becomes just "code"
18:33:45 -!- Phantom_Hoover has quit (Ping timeout: 276 seconds).
18:35:53 <Slereah> If you write a pseudocode compiler
18:39:36 -!- not^v has quit (Quit: http://i.imgur.com/Akc6r.gif).
18:49:53 <mroman> If you write a pseudocode compiler
18:49:57 <mroman> it's not pseudocode anymore
18:50:14 <mroman> all programs that compile with your compiler would have to be rewritten
18:50:25 <mroman> (compile and do what they are supposed to do)
18:52:28 <Slereah> But what if I write a compiler for that other languag D:
18:54:06 <MDude> That reminds me that I'd like to make something that works like a natural language translater, but train it to attempt to turn an informal language into something that can be compiled or interpreted.
18:55:58 <mroman> bitch please print Hello, world!
18:56:35 <MDude> Runnnig Gizoogle on BASIC code does sound like a good idea.
18:58:45 <MDude> http://gizoogle.net/index.php?search=http%3A%2F%2Fen.wikipedia.org%2Fwiki%2FBASIC&se=Gizoogle+Dis+Shiznit#Examples
18:59:07 <MDude> 10 PRINT "Yo muthafucka, World!"
19:00:15 <MDude> Oddly, the code itself ins't really changed.
19:00:58 <MDude> I guess because the keywords themselves are too terse to be picked up as translatable phrases.
19:03:06 <Bike> https://twitter.com/0xabad1dea/status/469541728828280832/photo/1/large programming
19:05:00 <Slereah> You know who else did that
19:05:08 <Slereah> And their Plain English Compiler
19:05:25 <FireFly> How did I not know about gizoogle before?
19:05:54 <MDude> DOn't think I've read about the Plain English Compiler, but I think that sounds like something not made as a joke.
19:06:53 <FireFly> I bet it's an implementation of http://en.wikipedia.org/wiki/English_(programming_language)
19:07:07 <Slereah> MDude : It is terrifyingly not a joke
19:07:16 <FireFly> oh wait, no, it's that silly other thing
19:07:22 <Slereah> http://www.theonion.com/articles/family-saved-by-threeway-inflatable-goat,4579/
19:07:31 <Bike> no, that is the correct link.
19:07:31 <Slereah> https://web.archive.org/web/20140108064338/http://osmosian.com/
19:07:44 <MDude> I was thinking of just having something that tries to avoid making obviously bad decisions, but doesn't particularly care what your actual intent is.
19:07:46 <FireFly> http://www.osmosian.com/ works too
19:07:57 <Slereah> The older version had more content though
19:08:18 <MDude> Wonder why it got cut.
19:08:33 <Slereah> Because he wants to sell it, no doubt
19:08:39 <Slereah> The old site had the compiler for free!
19:09:59 <FireFly> It doesn't actually work, does it?
19:10:14 <Slereah> it's a programming language
19:10:25 <Slereah> I can't vouch for how well it works
19:10:53 <FireFly> Have you tried compiling their sample draw-anything-you-can-name-in-the-style-of-Claude-Monet program?
19:11:11 <Slereah> But all that program does is
19:11:23 <Slereah> It googles "Monet" and put up a picture
19:11:42 <Slereah> In the hope that it's not porn, perhaps
19:11:56 <FireFly> What if I want porn in the style of Claude Monet?
19:29:27 -!- hk3380 has quit (Ping timeout: 245 seconds).
19:31:51 -!- xk002 has quit (Ping timeout: 240 seconds).
19:32:35 -!- hk3380 has joined.
19:37:27 -!- Bike has quit (Ping timeout: 276 seconds).
19:40:33 -!- Slereah_ has joined.
19:43:56 -!- Slereah has quit (Ping timeout: 265 seconds).
19:50:07 <MDude> I like how the old version of the site has a page of "What our customers could be saying" (if we had any).
19:50:46 <kmc> the unconscious part of my mind that plays 2048 is learning new move sequences that the conscious mind is unaware of
19:50:49 <kmc> the ego is a joke
19:54:24 <Slereah_> Jesus would have said "Had I known about it, I wouldn't have died for mankind!"
20:00:15 -!- AnotherTest has joined.
20:04:28 -!- mhi^ has joined.
20:10:26 -!- conehead has joined.
20:13:48 -!- Cyragia has quit (Ping timeout: 240 seconds).
20:22:30 -!- edwardk has joined.
20:23:42 <MDude> http://www.gizoogle.net/index.php?search=http%3A%2F%2Fwww.w3schools.com%2Fjs%2Fjs_intro.asp&se=Gizoogle+Dis+Shiznit
20:23:45 <MDude> "ECMA-262 is tha straight-up legit name. ECMAScript 5 (version 1.8.5 - July 2010) is tha sickest fuckin standard. "
20:24:50 <MDude> I'm still wondering what IRP is.
20:25:00 -!- Bike has joined.
20:31:07 <FireFly> There's also a page on the wiki
20:36:17 -!- AnotherTest has quit (Ping timeout: 264 seconds).
20:50:02 -!- conehead has quit (Quit: Textual IRC Client: www.textualapp.com).
20:51:23 <elliott> how many times has it been the end of ipv4 now?
20:51:55 <elliott> "We’ve been talking for many years about IPv4 addresses running out. Now it’s happening. [...] Yes, there are enough IPv4 addresses in the overall system right now that we’re not running out of addresses TODAY … but we are basically OUT at the top-level." come on, I heard the exact same thing years ago! hurry up already
20:57:59 <Bike> climate change is still going to kill us all too. just have some patience
21:02:57 -!- Patashu has joined.
21:10:37 <FreeFull> I want ISPs here to provide IPv6 ):
21:12:47 -!- madbr has joined.
21:13:11 <madbr> hm, I wonder how much data you could squeeze into a huge 2d barcode
21:14:58 <FreeFull> You have to be error resistant
21:15:20 <madbr> something you could successfully scan with a cheap CCD (cell phone cam)
21:15:34 <FreeFull> http://ronja.twibright.com/optar/ This works for black-and-white
21:15:43 -!- Patashu_ has joined.
21:15:44 -!- Patashu has quit (Disconnected by services).
21:15:56 <madbr> given optimal camera position and a barcode printed with a good process (possibly in color even)
21:15:57 <FreeFull> optar probably requires a scanner for any large amount of data though
21:16:16 <madbr> "Optar fits 200kB on an A4 page"
21:19:25 <FreeFull> You can probably fit more if you're smarter
21:20:14 <madbr> yeah but it probably has to be resilient to being photographied at unfavorable angles
21:20:23 <madbr> like having some perspective in the shot
21:20:34 <Bike> probably want some error correction, too.
21:20:46 <madbr> yeah it will need heavy error correction
21:21:06 <madbr> on the other hand it can probably be in color
21:21:48 <Bike> that makes things dependent on the ambient lighting, in addition to positioning.
21:22:24 <madbr> but ambient lighting effects will probably have a low frequency
21:22:59 <madbr> ie will be roughly the same for a whole block of, say, 32x32 pixels
21:24:07 <madbr> also, the camera can probably have a flash
21:24:56 <madbr> which means that if most of the light contribution comes from the flash it should have roughly consistent color temperature
21:25:28 <madbr> otoh you'd have to compensate for stuff like ink gamut (damn you cmyk)
21:26:13 <madbr> or you could use color as a secondary data channel
21:26:21 <madbr> for synchronization and error correction
21:26:38 -!- Patashu_ has quit (Ping timeout: 240 seconds).
21:27:27 <madbr> put the real data in the green channel, use red and blue as synchronization and error correction data
21:27:55 -!- xk002 has joined.
21:28:46 <mroman> How many bits is that per cm^2?
21:29:24 -!- nooodl has joined.
21:29:29 <mroman> > (21.0 * 29.7) / (200*1024*8)
21:29:38 <madbr> about 25x25 per cm²
21:30:09 <mroman> > ((21.0 * 29.7) / (200*1024*8))**(-1)
21:30:50 <madbr> it could probably use very high dpi commercial printing
21:30:52 <mroman> but bits / cm^2 looks good
21:31:12 <mroman> that's pretty good I think
21:31:27 <int-e> > 21.0 * 29.7 * 2^4
21:31:38 <elliott> printers don't print in RGB though...
21:31:49 <madbr> true but you can correct for that
21:32:48 -!- augur has quit (Remote host closed the connection).
21:33:04 <mroman> > ((21.0 * 29.7) / (100*1024*8))**(-1)
21:33:09 -!- nooodl_ has quit (Ping timeout: 276 seconds).
21:33:14 <madbr> use local maxima as white, local minima as black, then find a local 100% cyan pixel, use that as cyan maxima, repeat for yellow, magenta, red, green and blue
21:33:42 <madbr> build some kind of matrix to reverse the effect of the color shift
21:35:22 <madbr> or you could stay b&w and increase dpi instead, but then you need more printing dpi and a better camera
21:36:27 <madbr> there's also the issue that the user might incorrectly orient the camera and miss a part of the barcode
21:36:29 <int-e> 25.6 bits per square mm; 0.2mmx0.2mm pixels (since apparently they don't include error correction in their numbers)
21:37:33 <madbr> makes sense, it's printed at 200dpi (0.127mm)
21:38:27 <fizzie> There are a couple of color 2D barcode standards.
21:39:04 <fizzie> Like the Microsoft Tag.
21:39:24 <madbr> yeah but they're designed to fit in an url
21:39:43 <int-e> I should read more carefully. "That corresponds to 200kB per page when taking overhead into account."
21:41:57 <fizzie> HCCB's goal for the colors is to improve density compared to black-and-white, though.
21:42:14 <fizzie> "Currently laboratory tests have yielded using eight colors, 2,000 binary bytes, or 3,500 alphabetical characters per square inch in its highest density form using a 600dpi business card scanner."
21:43:14 <fizzie> 2000 bytes per square inch is... 2480 bits per square centimetre, I guess.
21:46:55 <madbr> considering a sheet of paper has something like 80~ usable square inches if you count margins (8½ x 11) that's something like 160kb for the whole page
21:48:13 <fizzie> > [8.5*2.54*11*2.54, 21*29.7]
21:48:19 <fizzie> Our papers are bigger.
21:48:47 <FireFly> I don't think that's what "printed copy" means
21:50:56 -!- oerjan has joined.
21:52:10 <madbr> also kinda wonder how heavy to decode these things are
21:52:14 -!- boily has joined.
21:58:30 -!- b_jonas has quit (Ping timeout: 276 seconds).
22:02:57 <madbr> though I guess if your cpu runs at at least a couple hundred mhz (arm SOC etc) it should be acceptable
22:05:49 <int-e> oh, this one is good. "Reducing the space necessary to keep accounting records that are mandatory to be kept on paper"
22:07:51 <madbr> would it make sense to print at very high dpi in color, and then apply a very aggressive error correction algo so that even if over half of the data or more is lost, you still get the correct output?<
22:09:16 <MDude> Print it as a hologram on a sheet of acrylic.
22:10:09 <madbr> you can't scan that with a CCD camera :D
22:10:32 <MDude> Not in a single pass.
22:10:44 -!- b_jonas has joined.
22:11:40 <MDude> The scanning program could ask you to look at it form different angles until the file is read, though.
22:12:13 <madbr> it has to be more practical than just putting a QR code as an URL and getting the data off of wireless internet
22:12:34 <madbr> also it would be easier to just print multiple pages of data
22:14:08 <int-e> I wonder whether the QR-style synchronization pattern (concentric squares) is superior to the checkerboard pattern or not ...
22:14:31 <MDude> Just get a high DPI printer and print it normally several times over.
22:14:38 <int-e> (and I'm afraid that the answer will depend on the printer)
22:15:07 <MDude> Then when you scan it, take the bitmaps of the different versions and do a majority vote per pixel.
22:16:55 <MDude> Plus overhead for getting it lined up.
22:17:06 <oerjan> <Bike> no, that is the correct link. <-- absolutely
22:17:09 <madbr> another issue is, what if the picture is taken too far away, then the data will be too small and won't scan okay
22:17:47 <MDude> Give you user a telescoping camera lens.
22:18:35 <MDude> It's not like you'd expect to be reading office document from far away to begin with.
22:20:18 <madbr> well, it can't be further away than about a meter
22:21:29 <madbr> but it can probably be like 10cm away
22:21:58 <madbr> there's probably a 2x range at least
22:28:12 -!- Bike has quit (Ping timeout: 245 seconds).
22:29:42 <madbr> maybe it would be easier to use some kind of frequency domain encoding?
22:30:46 <madbr> considering it's going to be somewhat smudged once snapped by the camera
22:35:54 -!- tertu has quit (Ping timeout: 258 seconds).
22:35:58 -!- Phantom_Hoover has joined.
22:39:00 <madbr> maybe you could overlay the data 4 times (in a 2x2 grid) at high DPI, and then once at lower DPI
22:39:29 <madbr> so that if the shot is too close and part of the data is missing, you can still recover it
22:39:52 <madbr> and if it's too far, then you have the whole frame and you can use the low DPI data
22:44:40 -!- Sorella has joined.
22:53:19 -!- mhi^ has quit (Quit: Lost terminal).
22:58:30 -!- Bike has joined.
23:20:43 -!- douglass1 has quit (Ping timeout: 252 seconds).
23:29:52 -!- xk002 has quit (Ping timeout: 245 seconds).
23:47:23 <kmc> https://gist.github.com/huonw/be05427dc80e44f1a594 a Rust compiler plugin to randomize the order of struct fields, for exploit hardening
23:53:53 <quintopia> Rust is still on my steam wishlist, waiting to be discounted
23:59:13 <kmc> quintopia: https://github.com/mozilla/rust/issues/12723
00:01:02 -!- tertu has joined.
00:04:11 -!- nooodl has quit (Quit: Ik ga weg).
00:04:18 -!- tromp_ has quit (Read error: Connection reset by peer).
00:07:13 <Bike> i got confused and thought 'grenade stack' was the name of the exploit random fields harden
00:08:25 <Bike> what's #![experimental] do?
00:09:41 <kmc> using it will cause a warning unless you have #[allow(experimental)] at the use site
00:10:02 <kmc> #[foo] is an attribute that applies to the next item (function definition, module, struct definition, etc.)
00:10:11 <kmc> #![foo] is an attribute that applies to the item which contains the attribute
00:10:35 <kmc> often a whole file (which is a module)
00:15:41 -!- BeingUntoDeath has joined.
00:19:20 <kmc> unfortunately you can't put #[allow(experimental)] on an arbitrary block of code, just an item
00:19:45 <kmc> resulting in this nonsense: https://github.com/kmcallister/html5/blob/master/macros/atom/mod.rs#L64-L72
00:25:05 <kmc> maybe I'll fix it!!
00:26:42 <kmc> probably not
00:41:50 <elliott> oerjan: you can do [2,1..0], if you didn't know
00:42:45 <kmc> > [1,3,3..7]
00:42:47 <lambdabot> <hint>:1:7: parse error on input ‘..’
00:48:28 <oerjan> elliott: no i was just testing a corner case in some SO code
00:55:07 -!- Phantom_Hoover has quit (Read error: Connection reset by peer).
01:07:30 <kmc> wow. I have a function that does assert!(self.foo.is_none()) and another which sets self.foo = Some(x), but the latter function is never called, so rustc warns me that the assert is dead code
01:07:34 <kmc> i am impressed
01:12:24 <Bike> that makes me wonder if you should be able to tell the compiler it's okay if certain forms, like an assert, are dead/can be removed
01:13:13 -!- Sgeo has joined.
01:13:56 <kmc> I think you can
01:14:05 <kmc> by making the assert!() macro expand into something with #[allow(dead_code)]
01:15:55 <kmc> oh, hm, I thought the function containing the assert wasn't dead but it actually was
01:15:58 <kmc> oh, I am less impressed
01:18:53 -!- tertu has quit (Ping timeout: 265 seconds).
01:20:31 -!- yorick has quit (Read error: Connection reset by peer).
01:27:24 <Sgeo> Is the HTML5 parsing algorithm interesting in any way other than being thoroughly specified?
01:27:30 <Sgeo> I'm wondering if I should attempt to read it
01:28:55 -!- xk002 has joined.
01:30:39 <kmc> it's astoundingly complicated
01:31:10 <Bike> nothing can be explained
01:31:12 <kmc> but not in a particularly interesting way
01:31:21 <kmc> it's mostly a record of historical mistakes
01:31:28 <kmc> it's the most descriptivist technical standard I've ever seen
01:31:37 -!- boily has quit (Quit: FLABBERGASTING CHICKEN).
01:31:38 <Bike> instead of that, help me understand poincare compactification. imo better than html
01:31:38 <kmc> (well, the entirety of the WHATWG webapps spec)
01:31:55 <kmc> I'm finding writing a HTML parser to be interesting, though, but more because there are interesting implementation challenges
01:32:04 <kmc> and lots of excuses to use macros
01:32:10 <Sgeo> Well, that's interesting as a record of historical mistakes. Does it explain the mistakes and where they're found and how they came about?
01:32:13 <Sgeo> I'd like to see that
01:32:15 <kmc> not very well
01:32:30 <kmc> "why is my build bot failing... oh, because I'm using language features that aren't merged upstream yet"
01:34:07 <Bike> i'm continually amused by how ahistorical the sciences are
01:34:20 <kmc> macros are the reason my tokenizer is 900 lines instead of 6,000 like the others
01:34:31 <Bike> today i saw a wikipedia article that said one algorithm could be considered as an improvement of another, with the minor caveat that the improved algorithm was invented first
01:36:42 <Sgeo> kmc: missing abstractions in the language, or is it hard to imagine a language that would provide those macros natively?
01:37:18 <kmc> it's just concision
01:37:28 <kmc> but in Haskell it might be a monad DSL rather than a macro DSL
01:40:43 <Sgeo> "When authors use the canvas element, they must also provide content that, when presented to the user, conveys essentially the same function or purpose as the bitmap canvas."
01:40:59 <Sgeo> Seems easy enough for arbitrary HTML5 games
01:43:55 <Sgeo> If the canvas has no pixels (i.e. either its horizontal dimension or its vertical dimension is zero) then the method must return the string "data:,". (This is the shortest data: URL; it represents the empty string in a text/plain resource.)
01:44:22 <Sgeo> ...why would you want to do that instead of a 0 size png resource?
01:45:45 <Bike> maybe the canvas is resizeable
01:46:16 <Sgeo> I meant why give a text/plain for an image just because it's weird
01:46:45 <Bike> like, you have a drawing application that's resizeable, and it has an export-as-dataurl function, say.
01:47:09 <kmc> Sgeo: feast your eyes on this nonsense http://www.whatwg.org/specs/web-apps/current-work/multipage/scripting-1.html#already-started
01:47:27 <kmc> er, drop the anchor from that url
01:48:43 <Sgeo> "where possible", I'm fine with that. Although I guess that's distinct from "where feasible", so maybe not.
01:50:31 -!- Slereah has joined.
01:53:09 <kmc> "If the stack of script settings objects is empty, perform a microtask checkpoint." what is this i don't even
01:53:40 <kmc> this is like deciding to standardize Perl by translating the interpreter from C to English
01:58:36 -!- Slereah_ has quit (*.net *.split).
02:06:42 <Sgeo> http://en.wikipedia.org/wiki/HTML5_File_API
02:06:53 <Sgeo> Why does this link to the Geolocation API?
02:13:00 <kmc> is it bad if the majority of my parsing logic is in match-arm guards (containing more matches) of 50+ lines
02:23:25 <Sgeo> Neat, I can make images based off of canvas elements with just a bit more difficulty than downloading an img
02:23:53 <Sgeo> Why is .toDataURL() on the canvas element and not the context?
02:25:25 <kmc> like so https://github.com/kmcallister/html5/blob/master/src/tree_builder/mod.rs#L352-L422
02:25:31 <kmc> beats me Sgeo
02:25:52 <Sgeo> The Canvas API is so... imperative
02:29:35 <Sgeo> http://diveintohtml5.info/semantics.html
02:32:23 -!- realzies has quit (Ping timeout: 252 seconds).
02:32:29 -!- tertu has joined.
02:34:47 -!- realz has joined.
02:45:15 <Sgeo> "That this step happens before the next one honoring the HTTP Content-Type header is a willful violation of the HTTP specification, motivated by a desire to be maximally compatible with legacy content."
02:45:34 <Sgeo> So.... is the HTTP spec ... incorrect, then? Or ...?
02:45:50 <Sgeo> When two specs fight, what should someone trying to be maximally conformant do?
02:47:37 <kmc> flip a coin
02:48:02 <kmc> ryeall, do whichever one makes fewer users angry
02:48:21 <kmc> there are two chickens in my backyard
02:48:31 <kmc> they had a staring contest with a cat
02:59:45 -!- tromp_ has joined.
03:31:09 -!- xk002 has quit (Ping timeout: 252 seconds).
03:38:49 -!- idris-bot has quit (Quit: Terminated).
03:51:41 <Sgeo> oerjan: did you read new Freefall?
03:51:57 -!- BeingUntoDeath has quit.
04:01:29 -!- MDude has changed nick to MDream.
04:03:50 -!- augur has joined.
04:05:19 <madbr> sgeo : of course the canvas api is imperative... has to be usable by less experimented coders
04:08:35 -!- Sorella has quit (Quit: It is tiem!).
04:17:49 <fizzie> Sgeo: Good thing to keep in mind with .toDataURL is that it has size limits in some browsers.
04:18:44 <fizzie> Or, rather, data: URIs do.
04:18:47 <fizzie> https://code.google.com/p/chromium/issues/detail?id=45395
04:20:20 <Sgeo> Huh, MDN has Chrome-specific information
04:20:22 <Sgeo> "Chrome supports the image/webp type."
04:21:07 <fizzie> (1.5 megs -- two + base64 overhead -- is not very much for a .png file.)
04:21:22 <kmc> the web: where even moving an image from an image renderer to an image viewer involves a wacky, text-based format with implementation-specific limitations
04:23:10 <fizzie> I think I worked around it by parsing the data: URI manually into a blob, and then producing a URL for that.
04:24:27 <fizzie> Chrome does "new Blob(...)" and URL.createObjectURL just fine, but not the toBlob method on the canvas.
04:24:44 <fizzie> Or did when I was writing this, anyway.
04:28:19 -!- oerjan has quit (Quit: leaving).
04:37:47 -!- tertu has quit (Ping timeout: 252 seconds).
04:38:44 -!- diginet_ has changed nick to diginet\.
04:38:48 -!- diginet\ has changed nick to diginet.
04:42:48 -!- conehead has joined.
04:45:27 -!- tertu has joined.
04:45:38 <Sgeo> Yay Firefox OS, the most open mobile OS ever, with neat features such as APIs that can only be used by apps preinstalled by the OEM
04:50:26 <Bike> as god intended
04:54:15 <Sgeo> It is interesting how Firefox OS app SOP is normal SOP * app
05:00:10 <Bike> use your words, sgeo
05:00:51 <Sgeo> It is interested how Firefox OS Single-origin Policy is effectively a pair of the normal website origin and the app itself
05:22:33 -!- Animatronicity has joined.
05:23:36 -!- Animatronicity has quit (Client Quit).
05:31:33 -!- tertu has quit (Ping timeout: 276 seconds).
05:31:56 -!- tertu has joined.
05:34:54 <Sgeo> 258EAFA5-E914-47DA-95CA-C5AB0DC85B11
05:42:15 <Sgeo> ooh, arbitrary Blobs can be sent using WebSocket
05:43:05 <Sgeo> I guess there are more obvious ways to send that data
05:43:45 -!- Bike_ has joined.
05:45:52 -!- Bike_ has changed nick to Bicyclidine.
05:48:16 <Sgeo> "Throughout the web platform "activate" is intentionally misnamed as "click"."
05:48:23 <Sgeo> "User agents are strongly encouraged to make window.focus() work from within the event listener for the event named click as a means of focusing the browsing context related to the notification."
06:03:38 -!- Slereah_ has joined.
06:05:07 -!- Slereah has quit (Ping timeout: 240 seconds).
06:10:49 -!- tertu has quit (Ping timeout: 265 seconds).
06:14:30 -!- madbr has quit (Quit: Rouringu de hajikunda!).
06:23:12 -!- Slereah has joined.
06:25:41 -!- Slereah_ has quit (Ping timeout: 252 seconds).
06:26:08 -!- MoALTz has quit (Quit: Leaving).
06:29:39 <fizzie> http://sprunge.us/jgiW also rather funny footer for a spam email.
06:31:50 -!- FreeFull has quit.
06:32:58 <fizzie> That's a lot of money.
06:34:26 <fizzie> (In fact, the SpamAssassin rule "LOTS_OF_MONEY" also triggered on it.)
06:35:48 <Sgeo> "Trying to help friend NOT get caught by spamassassin"
06:37:22 <kmc> today i got spam that claimed to be from "LTG Keith B. Alexander, USA. Commander, U.S. Cyber Command, Director, National Security Agency, Chief, Central Security Service"
06:37:33 <kmc> saying that i had won some large amount of money
06:39:15 <Sgeo> I would love to see an email that triggers every SpamAssassin rule highly
06:39:16 <fizzie> I think I've gotten email from Keith too.
06:39:59 <Sgeo> # Pretty good for most folks, except for jm: I have a really stupid
06:39:59 <Sgeo> # e-commerce bunch obfuscating their URLs with this for some reason. screw 'em
06:40:07 <fizzie> Maybe I should archive spam, too.
06:40:28 <fizzie> I did collect a few thousand messages once for some reason or another.
06:40:35 <fizzie> fungot: Would you like to sound like a spammer?
06:40:36 <fungot> fizzie: this way :) escaping/ conclusion, from a fnord projection, which at no great distance from/ town to/ port is eighteen leagues, and that its variation was a subsequent, often a desire to see/ lion in his desert,/ tiger tearing his prey in/ jungle, or/ beginning :) hooker's letter to you, so much/ more striking, as from/ sketches above given it is obvious that a variation occurred sufficiently marked to catch/ fancier's e
06:40:46 <fungot> Selected style: irc (IRC logs of freenode/#esoteric, freenode/#scheme and ircnet/#douglasadams)
06:40:49 <fizzie> Enough with the smileys.
06:43:45 <Sgeo> I can't find LOTS_OF_MONEY, where is it?
06:45:26 <fizzie> I don't know, it's the iki.fi SA.
06:45:33 <fizzie> They might have customized.
06:45:50 <Sgeo> I think I saw something suggesting it was removed
06:47:06 <fizzie> Google does find some references.
06:47:26 <fizzie> At least one config file with a definition, too.
06:50:11 <Sgeo> http://svn.apache.org/repos/asf/spamassassin/trunk/rules/20_phrases.cf this talks about money but not LOTS_OF_MONEY
06:52:21 <fizzie> http://svn.apache.org/repos/asf/spamassassin/trunk/rules/73_sandbox_manual_scores.cf
06:52:39 <fizzie> Gives a score for LOTS_OF_MONEY; does not define it.
06:54:11 <Sgeo> https://issues.apache.org/SpamAssassin/show_bug.cgi?id=6504
06:56:29 -!- trout has changed nick to constant.
06:56:34 <fizzie> http://ruleqa.spamassassin.org/20140421-r1588859-n/LOTS_OF_MONEY/detail has statistics for it.
06:57:22 -!- password2 has joined.
06:58:55 <Sgeo> Detailed results for rule LOTS_OF_MONEY, from source file HASH(0xac14038). Source file was last modified on 1970-01-01 00:00:00 UTC.
06:59:24 <Sgeo> Geez, needed a spam filter even back then?
07:02:00 -!- conehead has quit (Quit: Computer has gone to sleep).
07:02:43 <shachaf> kmc: rust doesn't support parameterizing on non-*-kinded things at all, right?
07:02:54 <shachaf> not just in traits but anywhere
07:03:34 -!- KingOfKarlsruhe has joined.
07:03:34 <fizzie> HASH(0xac14038), the best source file.
07:04:02 <kmc> shachaf: believe so
07:09:00 -!- MindlessDrone has joined.
07:15:00 -!- idris-bot has joined.
07:19:35 <kmc> Rust kind of has the GHC thing where you have to turn on a bunch of language extensions to get anything done
07:19:58 <kmc> using debug!() and friends now requires #![feature(phase)] #[phase(syntax, link)] extern crate log;
07:21:35 -!- Bicyclidine has quit (Ping timeout: 252 seconds).
07:23:02 <kmc> do you know if that will be fixed for 1.0?
07:23:31 -!- slereah_ has joined.
07:23:35 <lifthrasiir> but in my opinion that has to be handled automatically
07:25:37 <kmc> how would you do it?
07:27:50 <lifthrasiir> kmc: parse the code, read metadata for each `extern crate` item present, load the syntax extensions (#[macro_export] or #[macro_registrar]) if the crate is marked to provide such things, then expand macros.
07:28:37 <lifthrasiir> it does have a disadvantage on the error reporting though
07:29:21 <kmc> what's that?
07:30:35 <lifthrasiir> well, loadable syntax extensions with #[macro_registrar] should be compiled as dylib, but there would be no error message when the user failed or forgot to compile that dylib
07:30:55 <lifthrasiir> and the user will be met with a useless error message that a certain syntax extension is not available
07:31:56 <kmc> rustc should warn if you build a crate with a #[macro_registrar] as anything other than a dylib
07:32:38 <lifthrasiir> technically it can be built as rlib, but yeah, it is not a good choice to do so
07:33:07 <kmc> you can't use the syntax extensions if it's an rlib, right?
07:33:57 <lifthrasiir> yes, but it *can* be usable when #[phase(syntax,link)] is in use
07:34:23 <lifthrasiir> (but it will also push a libsyntax dependency to the compiled binary, which is why it is discouraged)
07:35:09 <kmc> if you need to support an rlib build you could do something like #[cfg(dylib)] #[macro_registrar] ...
07:35:17 <kmc> (I don't know if that's a real cfg option but it could exist, anyway)
07:35:43 <kmc> also I think it is useful to build libraries that some consumers will load at link phase and others not
07:36:00 <kmc> so probably it should only infer from metadata if no #[phase(...)] attribute is present
07:36:50 <lifthrasiir> kmc: so that the ordinary #[macro_export] wouldn't need #[phase] but #[macro_registrar] would?
07:37:10 <kmc> i hadn't considered that
07:37:22 <kmc> I was just thinking you could do #[phase(link)] extern crate foo;
07:37:28 -!- shikhin has joined.
07:38:20 <kmc> er, I meant "some consumers will load at syntax phase and others not"
07:38:26 <kmc> but I guess you might want both
07:39:04 <kmc> I have considered (but haven't implemented) macros where the registrar does some non-trivial initialization
07:39:12 <kmc> which might be expensive or depend on external resources that are not always present
07:39:57 <lifthrasiir> kmc: something like, well, sfackler's phf/phf_mac crates?
07:40:18 <kmc> you mean that you can avoid this by splitting the macros into their own crate?
07:40:23 <kmc> that's true, but it might be undesirable for other reasons
07:40:29 <kmc> i'm not sure really
07:40:52 <lifthrasiir> I do think, under your suggestion to use #[cfg(dylib)], they can be merged
07:41:21 -!- constant has changed nick to trout.
07:41:31 <kmc> it's also good not to have the macros bloating the library at runtime, but that shouldn't matter much with demand paging
07:43:20 <kmc> of course if you want to use those same macros in implementing the runtime part of the library, you will need two crates
07:44:18 <kmc> I can imagine having a crate for the runtime part of the library, a crate for private macros to be used in implementing the library, and another crate for macros intended for use by library consumers
07:44:27 <olsner> demand paging only really helps if you have at least 4kB of garbage and it gets put together in the same page
07:44:29 <olsner> but dead code stripping should get rid of it?
07:44:52 <kmc> since there's no way to control the scope of macros with granularity finer than a crate
07:45:20 <kmc> olsner: only link-time dead code stripping
07:45:31 <kmc> which isn't too hard for static linking
07:47:06 <kmc> but can't be done for dynamic linking afaik
07:47:59 <kmc> you could also build the same crate multiple times with different cfg options for each of those roles
07:48:04 <kmc> it doesn't seem like a good idea, though
07:51:50 -!- password2 has quit (Ping timeout: 240 seconds).
08:05:52 -!- edwardk has quit (Quit: Computer has gone to sleep.).
08:10:29 -!- Tritonio has joined.
08:24:20 <kmc> is this a common C idiom? unsigned int i; for (i = 14; ~i; i--)
08:24:26 <kmc> to count down from 14 to 0 inclusive
08:27:48 -!- Patashu has joined.
08:28:16 <scoofy> although i haven't seen that anywhere
08:29:10 <fizzie> I don't think I've seen that anywhere either.
08:29:21 <fizzie> It's not the same as !.
08:29:26 <scoofy> uses the fact that bitise inverse is negative of number minus 1
08:30:20 <fizzie> ~0 is kind of unrelated.
08:30:50 <fizzie> Well, I guess it's related the other way around, from ~-1 == 0.
08:31:06 <kmc> is ~-1 defined by the spec?
08:31:13 <fizzie> (Or ~UINT_MAX for that.)
08:31:24 <scoofy> well it also works with (signed int)
08:31:24 <fizzie> No, it was just a simplification.
08:31:27 <kmc> it seems like you couldn't define it without assuming a particular sign representation
08:31:35 <scoofy> ~0 = -1 (which is 'true')
08:31:42 <scoofy> ~(-1) = 0 (which is 'false')
08:31:51 <slereah_> Isn't 0-- undefined behaviour for unsigned ints?
08:32:00 <kmc> no, only for signed
08:32:28 <kmc> unsigned ints are defined to wrap around, which is how you know the number before 0 is ~0
08:32:45 <kmc> (whether or not it has the same representation as the signed integer -1 is not defined, though)
08:33:09 <scoofy> signed integer '-1' not defined? how does that make sense
08:33:27 <fizzie> I assume that was in re INT_MIN minus one.
08:33:28 <scoofy> there's no wrap around involved
08:33:51 <scoofy> it counts down from 14 to 0, ~i counts up from -15 to -1
08:33:56 <kmc> scoofy: whether ((unsigned int) ~0) and ((signed int) -1) are the same bytes in memory is undefined
08:33:58 <scoofy> there's no wrap around
08:34:04 <fizzie> Yes, I don't think it was any longer in that context.
08:34:07 <scoofy> that's not the question
08:34:50 <scoofy> assuming twos complement, ~i = (-i)-1
08:34:51 <fizzie> And the signed int version clearly isn't guaranteed to work, since integer representation isn't fixed.
08:35:08 <kmc> if I used that idiom I would worry that someone (including me) would copy it and use it for a signed integer
08:35:20 <scoofy> kmc, you _can_ use it for a signed int
08:35:52 <scoofy> http://morpheus.spectralhead.com/s/cnt.c.txt
08:36:11 <scoofy> does the same as the unsigned one
08:36:13 <fizzie> Sure, if you don't mind it working differently depending on the signed integer representation.
08:36:16 <kmc> did you try it on a machine which is not 2's complement
08:36:21 <scoofy> nope, and it would not work there
08:36:26 <kmc> right, so it's not a C idiom
08:36:34 <kmc> it's undefined behavior which happens to work in certain C compilers
08:36:39 <scoofy> we're spekaing about the (signed) case
08:36:45 <scoofy> the original code used (unsigned int)
08:36:55 <kmc> but compilers can and do optimize under the assumption that signed integer overflow/underflow does not happen
08:37:13 <scoofy> there's no overflow/underflow involved, as i understand
08:37:18 <scoofy> it's a binary negation
08:38:22 <kmc> if I rewrite the loop as for (i = 14; i != 0xFFFFFFFF; i--) is it more clear why there is underflow occurring?
08:38:45 <scoofy> ok, i see what you mean
08:38:53 <scoofy> but the underflow occurs only in the unsigned case
08:38:55 <scoofy> not in the signed case
08:39:19 <kmc> so I'm wondering if ~-1 is also UB
08:39:28 <fizzie> It's also not underflow, technically.
08:40:27 <fizzie> You can only get underflow with floats.
08:40:37 <fizzie> And it's not overflow either, if you go by the C standard definitions of those terms.
08:41:02 <kmc> 0-1 isn't overflow?
08:41:29 <fizzie> No, though only as a matter of definition.
08:41:38 <kmc> C is weird -_-
08:41:40 <fizzie> "A computation involving unsigned integers can never overflow, because a result that cannot be represented is reduced modulo [etc.]"
08:41:49 <kmc> yeah, okay
08:43:39 <scoofy> what does the standard say about ((unsigned int)0)-1 ?
08:44:44 <fizzie> What I just quoted, after converting the 1 to unsigned int too.
08:47:01 <fizzie> As for ~ on signed integers, I don't think it's necessarily undefined (it's defined in terms of what happens to the bits, not in terms of the value), though with the two other signed-integer representations it might result in a trap representation if applied to 0.
08:47:31 <kmc> the C spec gives only three options for signed integers?
08:47:51 <fizzie> Where "nowadays" means C99.
08:47:56 <kmc> interesting
08:47:59 <fizzie> From what I recall, it was more open in C89.
08:48:16 <kmc> but signed overflow is still UB (and not implementation-defined to be one of those three) because it was UB in C89?
08:48:42 <fizzie> I wouldn't know about "because", but it's explicitly UB.
08:49:21 <kmc> the options are 2's complement, 1's complement, and sign bit?
08:50:32 <scoofy> C defines lots of things as UB
08:50:51 <Taneb> Last night I saw a poster promoting Asexual Awareness Week
08:50:53 <fizzie> I have a feeling the signed overflow is UB to cater for (real or hypothetical) machines where signed-integer arithmetic traps on overflow rather than doing something else.
08:50:57 <Taneb> Asexual Awareness Week was in October
08:51:21 <kmc> fizzie: ah, interesting
08:51:42 <kmc> Taneb: poster-posting is a tragedy of the commons
08:51:46 <kmc> or maybe it's the same week every year?
08:52:23 <Taneb> It just had some variant of "Be aware of asexuals! It's asexual awareness week"
08:52:30 <Taneb> Without any reference to the date
08:52:35 <Taneb> I think I spotted it in the actual week
08:53:38 <fizzie> If it's written exactly like that, I'd get the feeling that it's trying to warn people about a danger.
08:53:51 <Taneb> fizzie, it's written substantially friendlier
08:54:49 <fizzie> One of our "miscellaneous stuff" boards was advertising a proofreading service with the slogan "the difference between knowing your shit and knowing you're shit".
08:55:57 <fizzie> http://psedit.me/ these jokers
08:57:43 -!- xk002 has joined.
08:58:57 -!- Patashu has quit (Disconnected by services).
08:58:57 -!- Patashu_ has joined.
09:02:47 -!- xk002 has quit (Ping timeout: 276 seconds).
09:03:37 -!- xk002 has joined.
09:08:35 <scoofy> why should i care if someone is asexual?
09:08:55 <scoofy> i mean, why would it need to have an 'awareness week' for that?
09:09:39 <slereah_> In case you want to fuck them?
09:11:38 <Taneb> scoofy, I think it's more being aware that such people exist
09:11:43 <Taneb> Rather than any specific examples
09:12:09 <Taneb> Beyond that, nothing.
09:12:24 <scoofy> there should be 'gay unicorn awaress week'
09:12:33 <Taneb> I am not aware of gay unicorns
09:12:40 <scoofy> see? that's the whole point!
09:13:02 <Taneb> Whereas I know a number of asexuals, including myself
09:13:02 <fowl> people are trying to shoot down bigfoot month for the same reason
09:13:36 <fowl> Taneb, that means you look like a ken doll down there, right
09:14:06 <Taneb> Yes. I am entirely plastic from the knees down.
09:14:38 <kmc> I kind of want to give a serious answer to scoofy's question, but I kind of would rather stab myself in the balls with broken glass than start a discussion on the subject of identity politics at 2 AM when I should already be asleep
09:14:52 <kmc> so maybe tomorrow
09:14:56 <scoofy> kmc, then you'd become asexual, i guess...
09:15:04 <kmc> not necessarily
09:15:12 <scoofy> depending on how successful you are with the stabbing
09:15:17 <kmc> badness 10,000
09:15:21 <kmc> anyway good night all :)
09:15:25 * kmc -> zzzzzzz
09:16:24 <fizzie> Sounds like an overfull hbox there.
09:16:59 <fizzie> Or maybe it's underfull that has a badness.
09:38:18 -!- edwardk has joined.
09:45:21 <int-e> So does TeX have a badness overflow error?
09:49:46 -!- shikhin has quit (Ping timeout: 265 seconds).
09:53:41 -!- xk002 has quit (Ping timeout: 264 seconds).
10:17:52 -!- edwardk has quit (Quit: Computer has gone to sleep.).
10:18:41 <fizzie> It's clamped to [0, 10000], but I don't know it is actually computed.
10:22:47 -!- Burton has quit (Ping timeout: 245 seconds).
10:33:46 -!- Burton has joined.
11:05:39 -!- Phantom_Hoover has joined.
11:07:00 <int-e> lovely. "TeX assigns a numerical value called 'badness' to each line that it sets, in order to assess the quality of spacing. The exact rules for badness are different for different fonts, and they will be discussed in Chapter 14 [...]"
11:09:22 -!- Frooxius has quit (Read error: Connection reset by peer).
11:13:32 <int-e> Aha, it depends on how much of the "flexible space" in a line is used. If the allowed length is foo + bar - baz, and the actual length is foo + f*bar (or foo - f*baz) with f>=0, then the "badness" is 100 * f^3, clamped to 10000.
11:13:51 <int-e> And then it gets messy :)
11:23:19 -!- Frooxius has joined.
11:40:33 -!- edwardk has joined.
11:40:38 <int-e> tromp_: Have you tried implementing the Goodstein function with recursion (in blc)?
11:43:46 -!- yorick has joined.
11:48:32 -!- edwardk has quit (Ping timeout: 276 seconds).
12:20:50 -!- Sgeo has quit (Read error: Connection reset by peer).
12:26:34 -!- Froox has joined.
12:26:34 -!- Frooxius has quit (Read error: Connection reset by peer).
12:26:44 -!- idris-bot has quit (Quit: Terminated).
12:26:59 -!- idris-bot has joined.
13:16:56 -!- xk002 has joined.
13:25:47 -!- jhj1 has quit (Ping timeout: 252 seconds).
13:37:50 -!- hk3380 has quit (Ping timeout: 240 seconds).
14:02:25 -!- KingOfKarlsruhe has quit (Quit: Leaving.).
14:11:45 <HackEgo> [wiki] [[Dogescript]] http://esolangs.org/w/index.php?diff=39644&oldid=39244 * 164.41.209.81 * (+86)
14:17:32 -!- Phantom_Hoover has quit (Ping timeout: 265 seconds).
14:23:34 -!- edwardk has joined.
14:27:02 -!- Phantom_Hoover has joined.
14:27:51 -!- tertu has joined.
14:30:27 -!- edwardk has quit (Read error: Connection reset by peer).
14:31:24 -!- edwardk has joined.
14:35:53 -!- hk3380 has joined.
14:36:15 -!- edwardk has quit (Read error: Connection reset by peer).
14:37:22 -!- edwardk has joined.
14:41:46 -!- AnotherTest has joined.
14:51:11 -!- oerjan has joined.
14:51:28 -!- conehead has joined.
14:52:52 -!- edwardk has quit (Read error: Connection reset by peer).
14:53:40 -!- edwardk has joined.
14:59:02 -!- edwardk has quit (Ping timeout: 240 seconds).
15:09:29 <mroman> I was recently thinking about an esolang where the concept of storage is somewhat based on time
15:09:53 <mroman> There's no storage except old states of the program
15:10:14 <mroman> I.e. for a brainfuck derivative that would mean, that you have one cell
15:10:23 <mroman> and everytime you change the cell it's previous state is recorded
15:10:23 <slereah_> And the instructions were either waiting or store the current time
15:10:27 <mroman> and you can access past states
15:11:35 <mroman> I.e. (where r reads a past state and <,> travel around the time) ++<<r would set the cell to zero again
15:11:39 <mroman> (assuming inital state was zero)
15:11:43 <oerjan> mroman: http://www-formal.stanford.edu/jmc/elephant/elephant.html (why is there no wikipedia article...)
15:13:12 -!- Patashu_ has quit (Ping timeout: 245 seconds).
15:30:41 <int-e> @djinn (Not (Not a) -> Not (Not b)) -> (Not b -> Not a)
15:31:56 <oerjan> @djinn Not (Not (Not a)) -> Not a
15:32:24 <oerjan> (and of course equivalent)
15:32:54 <int-e> @djinn (((a -> r) -> r) -> ((b -> r) -> r)) -> (b -> r) -> a -> r
15:33:40 <oerjan> hm so the void is not actually needed
15:34:23 <oerjan> @djinn (((a -> r) -> r) -> r) -> a -> r
15:34:32 <lambdabot> data Either a b = Left a | Right b
15:34:36 <lambdabot> class Monad m where return :: a -> m a; (>>=) :: m a -> (a -> m b) -> m b
15:34:38 <lambdabot> class Eq a where (==) :: a -> a -> Bool
15:34:51 <int-e> it doesn't seem to know that void :: Void -> Void == id
15:35:51 <int-e> @djinn (((a -> a' -> r) -> r) -> ((b -> b' -> r) -> r)) -> (b -> b' -> r) -> a -> a' -> r
15:36:28 <MDream> A clock language could be alright, if the clock is fast enough.
15:36:39 -!- MDream has changed nick to MDude.
15:38:17 <oerjan> @djinn Not (Not (a,a')) -> Not (Not (b,b')) -> Not (b,b') -> Not (a,a')
15:38:18 <lambdabot> f a b c _ = void (a (\ _ -> void (b (\ (d, e) -> c (d, e)))))
15:38:38 -!- Tritonio has quit (Ping timeout: 240 seconds).
15:39:02 <oerjan> wait that looks pretty redundant
15:48:18 <MDude> Is there already a language where the only control flow is looping from the end of the program back to the start if it hasn't been closed?
15:51:34 -!- slereah_ has quit (Quit: Leaving).
15:53:06 -!- oerjan has quit (Quit: leaving).
16:09:55 <int-e> @djinn ((i -> a) -> (i -> b)) -> b -> a
16:10:55 <mroman> MDude: I'm assuming recursion doesn't count?
16:11:07 <mroman> but yeah, especially string replacement languages work like that I think
16:11:33 <MDude> It only counts if it only happens once, at the end.
16:11:52 <mroman> so you can only execute the same code twice at most?
16:12:10 <MDude> I mean if the command only appears once.
16:12:32 <mroman> so restricted tail recursion is ok
16:13:55 <mroman> http://esolangs.org/wiki//// <- maybe
16:15:52 <MDude> Alright, so I think none of them are quite what I was thinking.
16:16:09 <mroman> If you have state you can do stuff like
16:16:26 <mroman> IF state == 0 THEN doThat; ELSEIF state == 1 THEN doThat ELSE STARTFROMBEGINNING
16:16:57 <mroman> which means you can set what to do next etc.
16:18:50 <mroman> That's essentially the trick I'm using for my thingy here which allows only one function and recursion
16:19:13 <MDude> I think that's neat too, though a different idea, in that IF is a kind of flow control.
16:20:38 <nortti> did I misunderstand or will start from beginning only run in case state is a var that does not cause any computation?
16:21:13 <nortti> thus, resulting in either one-cycle programs or those that loop infinetely and do nothing
16:21:38 <MDude> State might not be a boolean, in which case it'll go to the start if it's more than 1.
16:21:53 -!- mhi^ has joined.
16:22:13 <nortti> and then run through the same if-thingie again, yet again jumping to start
16:22:24 <nortti> or is that only part of the code?
16:22:43 <MDude> I actually think a system like that could effectively run loops.
16:22:59 <MDude> Just use if statments to skip everything but the loop while it's running.
16:24:38 -!- FreeFull has joined.
16:25:04 <MDude> Emulating loops like that might actually be kind of useful for something like keeping a hung script from freezing the whole browser.
16:26:05 <MDude> Since even if it's stuck in a loop, each cycle of it is followed by a pause while the rest of the browser does its thing.
16:26:25 <nortti> sounds like a co-operatively multitasking system
16:27:05 <MDude> The problem is that programs aren't made to cooperate for some reason?
16:27:26 <MDude> Because browsing locking themselves up is entirely something that happens.
16:27:57 <nortti> even with threaded browsers on pre-emptive multitask systems
16:28:26 <MDude> I'll just go make co-operatively multitasked EMCAscript sometime or something.
16:29:58 <MDude> I guess? I don't think I could do that soon, I haven't really been that great at coding.
16:30:42 <MDude> Could try just writing the actual scripts with that resctriction, though.
16:32:31 <FreeFull> MDude: Browsers are made to make javascript go as fast as possible
16:33:31 <MDude> And I disagree with that design choice.
16:35:25 <nortti> well, for replacing native code, it is kinda necessary. on the merits of replacing native code with a language with so 'interesting' as js may be debated, but js-heavy sites/browsers apps are here to stay
16:36:30 <MDude> I'd have to see how much slower cooperative Javascript is, but for that ti'd need to exist.
16:37:37 <nortti> there is also the targetted optimization
16:46:18 -!- MoALTz has joined.
16:47:00 <fizzie> Huh, Google Maps for Android 8 has (re-)acquired an UI to manage offline maps, but for everything in Kyoto/Tokyo it just keeps saying "area unavailable".
16:48:52 <HackEgo> [wiki] [[0(nop^)]] http://esolangs.org/w/index.php?diff=39645&oldid=39642 * John Misciagno * (+40)
16:53:41 <tertu> isn't there a term for that style of loop design? "(something) executive?"
16:56:27 -!- idris-bot has quit (Quit: Terminated).
16:56:42 -!- idris-bot has joined.
16:56:44 -!- edwardk has joined.
17:04:27 -!- edwardk has quit (Ping timeout: 245 seconds).
17:12:23 -!- MindlessDrone has quit (Ping timeout: 252 seconds).
17:13:22 -!- MoALTz has quit (Quit: Leaving).
17:15:18 -!- MoALTz has joined.
17:23:23 <mroman> MDude: It also happens that if a Browser freezes Windows Explorer (and thus the whole god damn GUI) becomes unresponsible
17:23:51 <mroman> That's most likely the biggest design fault that persists since the ancient days
17:25:39 <mroman> amongs many other design faults
17:25:42 <MDude> Sometimes it can just chug along so slowly it's just practially frozen, and the rest of the explorer can respond slowly.
17:25:59 <nortti> among them, integrating browser with OS
17:26:33 <MDude> Not like it's a problem exclusive to IE.
17:26:33 -!- MindlessDrone has joined.
17:26:41 <mroman> and programs having full access to the whol file system
17:26:51 <mroman> which has been somewhat fixed in windows vista+
17:26:58 <mroman> those Virtual AppData Roaming quirk
17:27:06 -!- drdanmaku has joined.
17:27:13 <mroman> which frankly, I think, produces more problems than it solves
17:27:55 <MDude> I'll just need to make a hardware-based OS where the task manager lives on its own microcontroller next to the cpu.
17:28:08 <MDude> Then nothing can freeze it.
17:29:01 <mroman> and how do you tackle all the driver problems?
17:29:47 <mroman> I honestly beleive that something like how Apple does it must be the solution
17:29:47 <MDude> I'll sell it as a children's toy, it'll be a step up from everything else in that market.
17:31:40 <MDude> Or make it just make it portable enough that people are fine with only using it with the hardware it's preinstalled on.
17:31:49 <MDude> That's how cell phones and tablets do it.
17:32:29 <MDude> Or maybe I'll call it a vidoe game console.
17:33:16 <HackEgo> [wiki] [[Goldfish]] N http://esolangs.org/w/index.php?oldid=39646 * GermanyBoy * (+2749) Created page with "'''Goldfish''' is an esoteric programming language by [[User:GermanyBoy]] inspired by [[Deadfish i]]. Only way to store data is creating functions and static variables inside ..."
17:33:23 <MDude> Also, minus that extraneous isntance of "make it".
17:33:35 <mroman> is that the guy from @text?
17:34:00 <HackEgo> [wiki] [[Language list]] http://esolangs.org/w/index.php?diff=39647&oldid=39622 * GermanyBoy * (+15) /* G */
17:34:16 <HackEgo> [wiki] [[User:GermanyBoy]] http://esolangs.org/w/index.php?diff=39648&oldid=39551 * GermanyBoy * (+15)
17:37:28 <mroman> oh. That Elehpant thing is from the LISP-Guy
17:41:57 <HackEgo> [wiki] [[Goldfish]] http://esolangs.org/w/index.php?diff=39649&oldid=39646 * GermanyBoy * (-10) /* Truth-machine */
17:42:15 -!- shikhin has joined.
17:46:20 -!- kmels has joined.
17:54:06 -!- Bicyclidine has joined.
18:01:19 -!- MindlessDrone has quit (Ping timeout: 265 seconds).
18:02:43 -!- hk3380 has quit (Ping timeout: 252 seconds).
18:09:26 -!- xk002 has quit (Ping timeout: 276 seconds).
18:11:28 <HackEgo> [wiki] [[Goldfish]] http://esolangs.org/w/index.php?diff=39650&oldid=39649 * GermanyBoy * (+24)
18:11:55 -!- augur has quit (Ping timeout: 240 seconds).
18:15:09 -!- MindlessDrone has joined.
18:18:39 -!- shikhin has quit (Remote host closed the connection).
18:19:07 <fizzie> What is it with technology never working out right? Now the tablet will no longer talk (over USB-OTG) to the memory card reader.
18:21:08 -!- Bicyclidine has quit (Ping timeout: 265 seconds).
18:21:26 <fizzie> (And the extra-stupid "EOS Remote" Android app forcibly resizes downloads to 1920x1280 with no option to turn that off, so can't work-around that way either.)
18:25:08 -!- xk002 has joined.
18:28:28 -!- sign has changed nick to hexagon.
18:29:33 -!- hexagon has changed nick to sign.
18:34:47 -!- hk3380 has joined.
18:46:36 <HackEgo> [wiki] [[ΜCurse]] http://esolangs.org/w/index.php?diff=39651&oldid=39643 * Sacchan * (+210) /* Example Programs */
18:46:55 <HackEgo> [wiki] [[ΜCurse]] http://esolangs.org/w/index.php?diff=39652&oldid=39651 * Sacchan * (+3)
18:47:12 <HackEgo> [wiki] [[ΜCurse]] http://esolangs.org/w/index.php?diff=39653&oldid=39652 * Sacchan * (-3)
18:49:05 -!- edwardk has joined.
19:00:33 -!- xk002 has quit (Ping timeout: 252 seconds).
19:13:19 -!- xk002 has joined.
19:22:02 -!- kmels has quit (Ping timeout: 265 seconds).
19:22:40 -!- kmels has joined.
19:30:20 -!- kmels has quit (Ping timeout: 252 seconds).
19:30:32 -!- kmels has joined.
19:38:00 -!- mihow has joined.
19:44:49 <HackEgo> [wiki] [[@text]] http://esolangs.org/w/index.php?diff=39654&oldid=39529 * 96.52.124.86 * (+11)
19:45:51 <HackEgo> [wiki] [[@text]] http://esolangs.org/w/index.php?diff=39655&oldid=39654 * 96.52.124.86 * (-11)
19:50:55 <HackEgo> [wiki] [[User:Icepy]] M http://esolangs.org/w/index.php?diff=39656&oldid=39519 * Icepy * (+106)
19:52:06 <HackEgo> [wiki] [[User:Icepy]] http://esolangs.org/w/index.php?diff=39657&oldid=39656 * Icepy * (+4)
19:53:36 <kmc> scoofy: I think the point of asexual awareness week is e.g. to convince people that, if someone tells you they're asexual, you shouldn't respond by saying they just haven't found the right person yet
19:53:59 <kmc> just like you wouldn't tell a gay man that he hasn't met the right woman yet
19:55:13 <kmc> those sorts of attitudes towards asexual people are pretty common
19:55:24 <kmc> even (especially?) among people who are okay with every kind of weird sex under the sun
19:55:41 <shachaf> that seems like a pretty bizarre response
19:55:58 <Taneb> shachaf, I've had that response in the past
19:57:19 <kmc> scoofy: if you don't have those kinds of attitudes then yeah, there is probably no reason for you to be especially aware of asexual people during asexual awareness week
19:57:47 <kmc> I've come to realize that an endless push for More Awareness on things I already pretty much understand has actually been quite harmful to me
20:00:52 <mroman> kmc: there are probably soooo many things one should be aware of and how one shouldn't respond to certain things
20:01:08 <mroman> that it's kinda weird to expect everybody to know all these things
20:01:14 <MDude> I wouldn't expect people to be particularly reactive to asexuals.
20:01:38 <MDude> I mean, most people only get in a relationship with one person at a time.
20:02:19 <MDude> Being in no relationships at a time doesn't really change much other than reducing the already low chance that said relationship is with you.
20:04:17 <HackEgo> [wiki] [[5command]] N http://esolangs.org/w/index.php?oldid=39658 * Icepy * (+501) Created page with "5command is an [[esoteric programming language]] created by [[User:Icepy]] that has a very small command set of only 5 commands. 5commands is a [[tape based language]] that ju..."
20:04:44 <mroman> although that must'n mean you shouldn't raise awareness
20:05:04 <kmc> MDude: yeah but ask some asexual people about the reactions they get when they say they aren't interested in sex /at all/
20:05:06 <mroman> but being on the non-mainstream side you gotta know that it's probably going to annoy a lot of people
20:05:34 <mroman> kmc: I think they won't believe it and just ignore it
20:05:42 -!- ^v has changed nick to v^.
20:06:01 -!- v^ has changed nick to ^v.
20:06:11 <kmc> you really don't need to guess
20:06:16 <kmc> you can ask actual living breathing human beings about it
20:06:30 <MDude> I'm imagining this would mostly be in the context of talking to people who want to make sure all their friends get hooked up in some way.
20:07:17 <MDude> Or take them all to strip clubs or something.
20:07:20 <kmc> you hear this a lot... "i don't think women would really end up in that position" "i don't think someone would mention race in that situation"
20:07:26 <kmc> you don't have to guess
20:07:31 <kmc> you can ask actual people what happens to them
20:07:34 <kmc> the answer may surprise you
20:07:54 -!- augur has joined.
20:08:02 <HackEgo> [wiki] [[5command]] M http://esolangs.org/w/index.php?diff=39659&oldid=39658 * Icepy * (+68)
20:08:48 <HackEgo> [wiki] [[5command]] M http://esolangs.org/w/index.php?diff=39660&oldid=39659 * Icepy * (+2)
20:09:02 <mroman> So far I've only heard people talking about depressive persons
20:09:16 <mroman> like "they're pathetic. Everyday is a new day. They just gotta man-up"
20:09:16 <MDude> Oh I'm sure people sya dumb things all the time, they do that regardless of subject matter.
20:09:35 <kmc> for people who do like sex, it often seems like such a wonderful and important part of life that they have a hard time relating to someone who just doesn't like it
20:10:45 <int-e> mroman: those people don't understand that every day is yet another torment
20:12:20 -!- zzo38 has joined.
20:12:35 <HackEgo> [wiki] [[5command]] http://esolangs.org/w/index.php?diff=39661&oldid=39660 * Icepy * (+5)
20:14:44 <MDude> Hmmm. I wonder if 5command only outputs the tape at the end of the program, or if it outputs after each step.
20:14:48 <kmc> this is a tricky one
20:15:04 <MDude> If the latter, I don't see why there's a no-op.
20:15:23 <kmc> I have much first-hand experience as well, and I would say that there is a kernel of truth to "every day is a new day, you have to make an attempt"
20:15:52 <kmc> you do have to make an attempt to feel better, it's just really really hard for reasons that are opaque to people who haven't experienced depression
20:16:02 <mroman> kmc: Yes. It has some thruth.
20:16:09 <kmc> and you have to forgive yourself for utterly failing at the most basic attempts
20:16:12 <mroman> but only because tomorrow exists
20:16:15 <kmc> or else it's just a downward spiral
20:16:38 <kmc> "every day is a new day" works the other way too, sometimes I'll feel great and then go to sleep and wake up feeling like shit
20:16:48 <kmc> makes me want to stay up as long as possible when I'm in a good mood
20:16:49 <HackEgo> [wiki] [[Joke language list]] http://esolangs.org/w/index.php?diff=39662&oldid=39437 * Icepy * (+53)
20:17:05 <mroman> kmc: I thought I was the only one
20:17:17 <kmc> you do that too?
20:17:19 <mroman> Some rare times I'm somewhat happy I don't wanna fall asleep
20:17:36 <HackEgo> [wiki] [[Joke language list]] M http://esolangs.org/w/index.php?diff=39663&oldid=39662 * Icepy * (-2)
20:17:51 <mroman> usually you just wan't the day to be over
20:18:03 <mroman> like... ideally you would sleep like 22h hours a day
20:18:15 <mroman> sadly that's not possible (yet)
20:18:38 <Phantom_Hoover> no, what you have to do is stutter in and out of sleep until you wake up feeling great
20:18:59 <mroman> there's no such thing as waking up feeling great
20:19:19 <MDude> Then peak antisadness.
20:19:38 <mroman> If I could choose I wouldn't even wanna wake up
20:20:39 <mroman> I sometimes feel like being depressive is the natural state
20:21:02 <mroman> and everybody else has some weird sickness that makes them ignore things
20:21:06 <HackEgo> [wiki] [[5command]] M http://esolangs.org/w/index.php?diff=39664&oldid=39661 * Icepy * (-9)
20:21:23 <mroman> I.e. the fact that your health declines
20:21:30 <mroman> the fact that people around you are gonna die
20:21:48 <int-e> Phantom_Hoover: are you a morning person? (I just stumbled on the first paragraph here: https://en.wikipedia.org/wiki/Sleep_deprivation#Treatment_for_depression )
20:22:22 <HackEgo> [wiki] [[5command]] M http://esolangs.org/w/index.php?diff=39665&oldid=39664 * Icepy * (-65)
20:23:03 -!- hk3380 has quit (Ping timeout: 252 seconds).
20:24:40 <mroman> also I don't know why people think that shrinks can "heal" stuff
20:25:10 <MDude> Just because they're technically in a medical discipline.
20:25:43 -!- edwardk_ has joined.
20:26:05 <int-e> tromp_: phew, I've finally shown to my satisfaction that the CPS step in the factorial derivation works. It's actually quite nasty, because of the contravariant nature of the transformation. So I ended up doing it in two steps, the first of which uses the (contravariant) identity g (f^n x) = (. f)^n g x, while the second one converts between ((a -> b -> r) -> r) -> r and a -> b -> r.
20:26:26 -!- edwardk has quit (Ping timeout: 252 seconds).
20:26:28 -!- hk3380 has joined.
20:26:30 <mroman> MDude: So is a guy who does biopsies.
20:27:39 <MDude> Oh ok, I was going to say biopsies are probably seen as healers even though they only diagnose.
20:28:33 <int-e> on a lighter note, being depressed doesn't mean that the world is not going to hell.
20:29:53 <kmc> as far as I can tell, there are a bunch of different things that help different people to varying degrees
20:29:59 <kmc> including drugs (prescription and otherwise)
20:30:05 <kmc> none of them are going to "heal" you
20:30:42 <kmc> I have been doing a number of these things, especially since the beginning of this year, and I do feel significantly better now
20:30:50 <kmc> but who can say whether I would have felt better without any of it
20:31:05 <kmc> or whether the things are arbitrary and it's the doing something that's alleged to make you feel better that makes me feel better
20:32:05 <kmc> I find it comforting to remember that, in terms of the ancestral environment, we are all really really far from home and nobody has a fucking clue how anything in the world works or what will happen next
20:33:20 <kmc> and nothing is at steady state
20:33:48 <kmc> if my brain doesn't work right, at least there's no real reason to expect it would :P
20:33:54 -!- tswett has joined.
20:34:24 -!- mihow has quit (Quit: mihow).
20:35:15 <kmc> this whole human thing is an out of control chain reaction that started just moments ago in evolutionary (let alone cosmological) time
20:35:45 <kmc> enjoy the ride, keep your arms inside the vehicle at all times
20:35:49 <mroman> But why do I have to suffer just because evolution did some things?
20:35:56 <tswett> I wanna create a Brainfuck variant where the tape has 0s and 1s, initially all 0s, which has the property that if you change a 0 to a 1 during execution of the program, this doesn't result in a 1 becoming a 0 further down the line.
20:36:14 <mroman> It's hard to justify it I think.
20:36:22 <kmc> mroman: there is no answer to that question
20:36:27 <MDude> So you want to make a write-once memory system?
20:36:27 <kmc> which is a hard pill to swallow
20:36:46 <MDude> Or can 1s become zeroes, but only invariantly?
20:36:58 <mroman> and considering that religions were pretty much wrong
20:36:58 <kmc> another thought I had recently is: the comfort of knowing that even if your life does have some meaning, you will never ever figure out what it is
20:37:04 <tswett> Ones could potentially become zeroes invariantly.
20:37:06 <mroman> and there's really *nothing* after death
20:37:13 <mroman> than it doesn't really matter anyway
20:37:14 <zzo38> tswett: I think there is a Turing-complete system where marked cells never become unmarked later on.
20:37:45 <tswett> zzo38: yeah, but you can still do X if a cell contains 0 and Y if a cell contains 1, such that X results in 1s being in places where Y wouldn't have them.
20:37:46 <mroman> *if religions were wrong
20:37:55 <tswett> Like, essentially, the only thing that should be impossible is doing a "not".
20:38:19 <mroman> If I hadn't been brainwashed as a kid to christianity to some degree chances are pretty high I wouldn't be here right now
20:38:27 <zzo38> Yes you can still have decision like that
20:38:58 <tswett> So, much of it can remain the same. + sets a cell to 1, - sets a cell to 0, < and > move left and right.
20:38:59 <kmc> mroman: sure, it doesn't matter, the same way the outcome of a game doesn't matter, but you can still have fun playing
20:39:03 <kmc> I don't totally endorse that view though
20:39:12 <kmc> and I know firsthand that this kind of existentialism 101 is not really that comforting
20:39:16 <kmc> but I don't have a better answer
20:39:25 <mroman> as far as I see it I can't win the game anymore
20:39:37 <MDude> I like to think of purpose being a result of life, rather than the oter way around.
20:39:43 <mroman> which makes playing it rather annoying than fun
20:39:49 <zzo38> mroman: Some people may like to be Christian, and some people aren't; I don't have a problem with that in general. Believe what you like; some things are unknowable, and some things it isn't even meaningful to say is one way or another.
20:39:53 <kmc> you can't win at tetris either
20:39:55 <mroman> although I can't tell you what I'd consider "winning the game"
20:39:57 <zzo38> What game you can't win anymore?
20:40:09 <MDude> As in, purpose is defined, directly or inderectly, by what a living thing cares about.
20:40:15 <kmc> maybe that's why I spent so much time playing tetris and thinking about existentialism as a kid
20:40:18 <kmc> now I play 2048 instead
20:40:30 <kmc> which one can win but only in a meaningless way
20:40:46 <mroman> zzo38: I was raised christian. That leaves traces.
20:40:57 <mroman> If I were raised an atheist I think i'd be 100% certain that there's nothing after death
20:41:01 <MDude> So for life to have a purpose there must be life that cares about it.
20:41:18 <tswett> Then [] should essentially be a "loop while 1", but it should somehow make it so that <, >, and - don't result in there later on being 0s where there could be 1s.
20:41:27 <mroman> which means I could kill myself without risking that one
20:41:52 <kmc> I'm an atheist but I don't believe that there's nothing after death, exactly
20:41:58 <kmc> there's nothing after death for you or for me
20:42:26 <zzo38> OK, there are traces. I think is OK you can learn many religious and non-religious things.
20:42:27 <kmc> but "you" and "me" are just crude heuristic labels for describing incredibly complicated and mysterious phenomena
20:42:37 <kmc> if you let go of the ego a bit, death isn't so scary
20:42:41 <int-e> mroman: nah, there are more anchors. I don't want to hurt my family, friends or acquaintences in that way.
20:43:00 <tswett> [] just means "fork and loop forever". All threads operate on the same tape, and all of them move simultaneously.
20:43:01 <kmc> "In the neon sign, scrolling up and down / I am born again"
20:43:02 <mroman> but to some degree you're already hurting them by being depressive
20:43:03 <MDude> I think the question of wether a purpose has life to it is more interesting than the reverse.
20:43:14 <tswett> Well, no, it's not quite the case that all threads operate on the same tape.
20:43:18 <zzo38> To me, it is a bit unsure what exactly is meant by "what is after death". I can say after death is decomposition and stuff like that.
20:43:19 <mroman> and I know that someday they won't give a shit anymore to protect themselves
20:43:24 <tswett> If a thread does +, all tapes see that. If a thread does -, only its own tape sees that.
20:44:01 <tswett> There's also a command %, meaning "die unless 1".
20:44:32 <zzo38> Some things seem to show that there may be some kind of "psychic awareness" after "near death", but other experiments show otherwise, so it is unknown. In fact, it doesn't seem to quite know what exactly such a thing would mean, anyways.
20:44:55 <mroman> Live only needs a purpose if you don't enjoy it. The purpose is just there to justify your suffering
20:45:06 <kmc> neutral monism is best monism
20:45:32 <tswett> mroman: so, it sounds like you don't enjoy life.
20:46:06 <zzo38> kmc: I am also neutral monism
20:46:36 <mroman> I would enjoy it if you invent the artificial comma capsule thingy
20:46:43 <mroman> that thing you see in science fiction movies
20:47:03 <mroman> you enter the capsule and you're immediately put into a sleep state
20:47:13 <mroman> like freezing/unfreezing or whatever
20:47:14 <MDude> I only have apostrophe capsules.
20:47:24 <zzo38> You say about purpose of life, but really it is just a part of a larger system, which is the entire universe and of the multiverse (if any). That is the purpose.
20:47:47 <mroman> so you could work like 3/4 hours a day to pay off the capsule
20:47:56 <mroman> and the other 20h you'd be in the capsule
20:48:01 <tswett> I think it's kind of interesting how so many of our names of punctuation marks come from Greek.
20:48:18 <mroman> that'd be kinda my dream life
20:48:19 <tswett> Comma, colon, semicolon, apostrophe.
20:48:33 <tswett> mroman: so your dream is the elimination of leisure time?
20:49:38 <tswett> I definitely take too much leisure time.
20:50:00 <tswett> (wish I could stay and chat, bye)
20:50:02 -!- tswett has quit (Quit: tswett).
20:50:53 -!- edwardk_ has changed nick to edwardk.
20:50:53 <kmc> zzo38: yeah, I learned about it from you
20:51:36 <mroman> but mostly it's also about the day only being 3 to 4 hours long
20:53:05 <mroman> well you have to suffer fewer hours per day
20:53:26 <mroman> if you sleep 8 hours there's still 16 hours of the day left
20:55:06 <mroman> I'd be only working to pay off the capsule so you don't live of other people's money
20:55:12 <mroman> because people don't like that
20:56:52 -!- Phantom_Hoover has left ("Leaving").
20:57:07 <mroman> he. I made him leave :)
20:57:14 <mroman> well... I'm gonna shut up now
20:59:31 <shachaf> kmc: You were talking about using rank/select to index into UTF-8 encoded text efficiently, right?
21:06:13 <zzo38> What is rank/select to index into UTF-8 encoded text?
21:06:22 <kmc> shachaf: do you have new information about it?
21:07:21 <zzo38> What SQLite does is considers any byte 0x01-0xBF to be a single character, and any byte 0xC0-0xFF followed by zero or more bytes in the 0x80-0xBF range to be a single character.
21:09:45 <zzo38> When trying to convert to/from codepoints there are many other problems, but I have written an extension with functions CHR_U and ORD_U which avoid these problems. The built-in UNICODE function assumes codepoints are signed 32-bit integers, although my function ORD_U uses signed 64-bit integers instead (although only 36-bits will be used). The built-in CHAR function cannot encode surrogates or out-of-range Unicode characters.
21:11:28 -!- MindlessDrone has quit (Quit: MindlessDrone).
21:18:40 <shachaf> kmc: edwardk was just talking about it in the other channel.
21:18:46 <kmc> what does he think?
21:19:15 <kmc> cool, do you think it's efficient on a practical level?
21:19:35 <edwardk> kmc: for large enough text fragments definitely
21:19:49 <kmc> edwardk: I had some thoughts about JavaScript text representation: https://groups.google.com/forum/#!msg/mozilla.dev.servo/1K2-Qy27e3A/--z3h3VhvHIJ
21:19:54 <edwardk> github.com/ekmett/succinct offers up rank/select structures
21:20:26 <kmc> you don't happen to have a Rust implementation do you? ;)
21:20:43 <edwardk> nah. can't abstract over stuff i want to abstract in rust ;)
21:21:15 <edwardk> to be fair that is also true of haskell from time to time ;)
21:21:16 -!- Phantom_Hoover has joined.
21:22:05 -!- nooodl has joined.
21:23:39 -!- xk002 has quit (Ping timeout: 252 seconds).
21:24:28 <edwardk> the tricky part is you want efficient select performance not rank, so Elias-Fano, etc. gets a bit tricky to do well
21:29:23 <zzo38> I still do not quite understand, what is rank/select to index into UTF-8 encoded text efficiently?
21:29:49 -!- tertu has quit (Disconnected by services).
21:29:49 -!- ter2 has joined.
21:31:17 <edwardk> rank lets you count up the number of occurrences of a symbol in an alphabet up to a given point in O(1) time using very near optimal space. select lets you jump directly to the kth occurrence of a symbol. lets let the symbols be 1 or 0 for whether it is a UTF8 head byte or a UTF8 tail byte. store that bitvector as an array and add a select structure that lets you quickly jump to the kth 1
21:31:45 <edwardk> now if you want to drop k elements from Data.Text you use select k 1s, and drop to thre
21:32:32 <edwardk> if you want to take k elements you go to select k 1s - 1and run to there.
21:33:06 <edwardk> it is a precursor to more advanced structures like fm-indices, wavelet trees, compressed suffix arrays, etc.
21:34:06 -!- mhi^ has quit (Quit: Lost terminal).
21:36:41 <zzo38> I would suppose then, if the byte 0x80 to 0xBF then it is not a first byte of a UTF-8 character, and otherwise it is a first byte of a UTF-8 character.
21:43:29 <shachaf> edwardk: I imagine that for UTF-8 you would just store a sparse bit vector of all the continuation bytes or something like that?
21:43:57 <shachaf> I guess it depends on what you expect strings to be like.
21:44:07 <edwardk> shachaf: you'd want a select structure that can find the head bytes.
21:45:16 <edwardk> rank doesn't care which way it splits, but select structures are built for one value or the other (or both)
21:45:40 <edwardk> so here it is more useful to be able to find heads
21:46:27 <edwardk> now with text we don't use utf-8 currently, so it'd be surrogate pair leads
21:46:43 <edwardk> and most of the type there'd be no non-plane 0 codepoints
21:46:52 <edwardk> so the structure'd usually be trivial
21:46:57 <zzo38> O, so you are using UTF-16?
21:47:13 <edwardk> I was assumng for Data.Text which is UTF-16
21:47:35 <edwardk> but its the same problem as for UTF-8
21:48:17 <zzo38> UTF-16 is not compatible with ASCII, though.
21:48:46 <shachaf> What was the reason in the end for sticking with UTF-16?
21:50:07 <zzo38> UTF-8 is also not limited to the Unicode range.
21:55:55 -!- john3213 has joined.
21:58:13 <zzo38> The VGM file format uses UTF-16. A VGM compiler I wrote expects the input to be in ASCII format, however comments can be in any format, and any text which is copied directly to the VGM file can be in UTF-8 or CESU-8 format. (Nothing special is needed to support CESU-8, so it just automatically does support CESU-8.)
21:59:23 -!- AnotherTest has quit (Ping timeout: 252 seconds).
22:00:57 -!- john3213 has left.
22:02:57 <edwardk> shachaf: performance was better
22:04:53 <shachaf> I think I heard mixed opinions about that. But I don't remember, it's been a while.
22:05:08 <shachaf> That was jaspervdj's project, right?
22:05:33 <shachaf> Are there up-to-date code and benchmarks?
22:05:40 -!- MDream has joined.
22:06:32 -!- MDude has quit (Ping timeout: 252 seconds).
22:06:46 <edwardk> shachaf: in the end the only thing jasper's code was faster at was going to/from utf-8. everything else was 5-10% slower
22:06:56 <edwardk> i mentored the project that year
22:07:02 -!- mhi^ has joined.
22:09:13 -!- nooodl_ has joined.
22:12:39 -!- nooodl has quit (Ping timeout: 265 seconds).
22:22:46 <MDream> Just wait for it to be rotated by 26 and it'll be the same again.
22:25:20 <Bike> it's unicode, you have to rotate by U+2FFFF PILE OF POO WINKING AT CATGIRL
22:26:46 -!- MoALTz_ has joined.
22:29:33 -!- MoALTz has quit (Ping timeout: 252 seconds).
22:30:11 -!- tswett has joined.
22:30:28 <tswett> If I'm not mistaken, this is Graham's number using Church numerals:
22:30:30 <tswett> 64 (\n -> (pred n) (\ar b' e' -> (pred e') (ar b') b') 27) 4
22:32:27 <tswett> Of course, it'd be larger if you removed the "pred"s.
22:35:37 -!- edwardk has quit (Quit: Computer has gone to sleep.).
22:39:42 -!- oerjan has joined.
22:40:33 <Bike> i guess you could make an infinite sequence that's the rightmost digits of fix (3^). that'd be cool
22:40:53 <tswett> The 10-adic solution to x = 3^x.
22:41:30 <tswett> There's some amazing theorem which states that the function f(x) = 3^x - x takes on all but at most one value.
22:41:56 <oerjan> Bike: discussing graham's number?
22:42:02 <tswett> Over the complex numbers, that is.
22:42:06 <Bike> tswett brought it up
22:42:12 <Bike> yeah, picard's theorem
22:42:13 <Bike> a good theorem.
22:42:53 <oerjan> it doesn't necessarily have to exclude one value, mind you, i think
22:42:57 -!- Sgeo has joined.
22:43:12 <Bike> yeah it's either all of C or C minus some dumbass point
22:43:25 <Bike> because if you have two or more points you have to be periodic or sumfin
22:43:29 <oerjan> whether 3^x - x does i'm not sure. actually that would be equivalent to e^x - x + a constant, i think
22:44:15 <Bike> (log 3)e^x - x, anyway
22:44:41 <oerjan> Bike: yes, i'm just thinking you can extract that log 3 by substituting x with something
22:45:20 <oerjan> 3^x - x = e^(x*ln 3) - (x*ln 3) + ... hm or can you
22:45:42 <Bike> substitute y = x - ln3!!
22:46:08 <Bike> disclaimer i am tired and apathetic
22:46:35 <oerjan> something linear, maybe.
22:46:38 -!- Sorella has joined.
22:46:48 <Bike> 3^(x-ln3) = (ln3)e^(x-ln3) = (ln3)(e^x)/(e^ln3) oh
22:46:54 <Bike> so x - ln ln 3?
22:46:59 * tswett fails to come to a conclusion.
22:47:13 <Bike> tswett: just ignore the linear term brooooooooooo
22:47:25 <oerjan> Bike: i don't see your first =
22:47:46 <Bike> eh? a^x = (ln a)e^x, surely
22:48:00 <oerjan> no, it's e^(x l...right tswett
22:50:02 -!- conehead has quit (Quit: Computer has gone to sleep).
22:50:15 -!- xk002 has joined.
22:50:24 <Bike> y = x/ln3, then? so 3^(x/ln3) = e^(x*ln3/ln3)? or have i forgotten what a three is
22:50:39 <tswett> In Lispy notation, we've got this: (apply (apply 64 (lambda n _ (apply (apply (apply pred n) (lambda a _ (lambda b _ (lambda e _ (apply (apply (apply pred e) (apply ar b)) b))))) 27))) 4)
22:50:46 <oerjan> you might like, not confuse x and y twh
22:51:10 <tswett> Where _ means "this is supposed to be a type signature but I haven't bothered to figure out what".
22:51:22 <Bike> ehhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhhh
22:52:30 <tswett> Conclusion: Graham's number can be written in the calculus of constructions using a few dozen symbols tops.
22:52:45 <oerjan> 3^y - y = e^x - x/ln 3
22:52:47 <tswett> It's not an Unreasonably Large Number.
22:52:50 <Bike> tswett: is that surprising
22:53:05 <Bike> imo it seems much larger when you remember it's a dimensionality :V
22:53:06 <tswett> But it makes Graham's number sound pretty small.
22:53:38 <Bike> can't you just skip to grzegorczyk and call it good
22:54:40 <oerjan> tswett: hey we (well, someone, quintopia maybe?) did goodstein sequence in system F the other day, graham's number is like piece of cake in comparison
22:55:18 <oerjan> as in, i found something on wikipedia implying it possible and someone else wrote down a definition
22:56:22 <oerjan> oh hm to get rid of that /ln 3 you need to substitute it back in additively, i think
22:57:18 -!- conehead has joined.
22:57:47 <tswett> So if System F can do it, surely the CoC can do it.
22:58:24 <oerjan> then 3^y - y = e^x - x/ln 3 = e^z/ln 3 - z/ln 3 + (ln 3)^2
22:58:59 <oerjan> = (e^z - z)/ln 3 + (ln 3)^2
22:59:37 <oerjan> so the ranges of the functions are just linear maps of each other
22:59:51 <oerjan> which means either both leave out a point, or neither
23:01:05 <tswett> Okay. Goodstein's theorem really seems a little obvious.
23:01:46 <Bike> the one that's unprovable in peano?
23:03:06 <int-e> oerjan, tswett: I did; see https://github.com/tromp/AIT/blob/master/goodstein.hs
23:03:20 <tswett> It comes down to the fact that a certain recursion scheme is well-founded.
23:04:03 <tswett> The recursion scheme uses a decreasing sequence of ordinal numbers less than epsilon_0.
23:04:24 <int-e> (it's in tromp's repo because there is also a lambda code version of essentially the same code in there now)
23:05:22 <tswett> That's an interesting definition of an ordinal number.
23:05:34 <tswett> "forall r. ((N -> r) -> r) -> (r -> r) -> r -> r"
23:05:39 <oerjan> int-e: ah, sorry for not remembering
23:06:08 <int-e> oerjan: don't worry about it
23:06:33 <zzo38> tswett: What does N mean here, then?
23:06:35 <tswett> So it takes a blobble, a function on blobbles, and a function turning an infinite sequence of blobbles into a blobble. It turns all this into a single blobble.
23:06:38 <tswett> zzo38: natural numbers.
23:07:09 <tswett> So it sounds a lot like taking zero, a successor function, and a limit function.
23:07:30 <oerjan> tswett: afaiu that's what it is, in church representation
23:07:50 <tswett> Of course, that representation can't represent all ordinal numbers.
23:07:52 <int-e> tswett: it only works for countable ordinals
23:07:56 <tswett> At best, it represents the countable ones.
23:07:56 <oerjan> although i don't really understand how that works to actually do ordinal number stuff
23:08:33 <tswett> The calculus of constructions is so strong, I bet you could use it to prove that the calculus of constructions is strongly normalizing.
23:08:51 <tswett> (The amount I bet is -$200.)
23:08:58 <int-e> (and you run into problems actually constructing them, but in principle every countable ordinal can be represented in that way.)
23:09:28 <Bike> all this has shockingly little to do with my question about grobner bases, smh
23:09:57 <int-e> there was a question... hmm.
23:10:21 <oerjan> oops my y to z above is nonsense
23:10:54 <oerjan> it needs to be x = z - ln (ln 3), i think
23:11:22 <Bike> the question was: what the heck are grobner bases
23:12:00 <oerjan> then e^x - x/ln 3 = e^z/ln 3 - z/ln 3 + ln 3 ln (ln 3) = (e^z - z)/ln 3 + ln 3 ln (ln 3)
23:12:46 <HackEgo> [wiki] [[0(nop^)]] http://esolangs.org/w/index.php?diff=39666&oldid=39645 * John Misciagno * (+260)
23:13:09 <oerjan> argh still wrong. + ln (ln 3) / ln 3
23:13:28 <Bike> apparently solving systems of polynomials is "not easy" and also "you can get to P and NP somehow from trying"
23:13:50 <oerjan> well the essence still holds, anyway
23:16:03 <int-e> Bike: AFAIK Gröbner bases represent ideals in polnomial rings; they are special in that one can decide whether a polnomial is in the ideal by taking it's largest monomial (in a total order on monomials) and replace it by a linear combination of smaller ones using a polynomial in the gröbner basis; this procedure terminates and you either end up with 0 (and the polynomial is in the ideal) or not (and it's not).
23:17:21 <int-e> as for polynomials you can also run into https://en.wikipedia.org/wiki/Hilbert%27s_tenth_problem
23:17:32 <Bike> i guess i'll think hard and figure out what this has to do with solving
23:17:51 <Bike> wait, what do diophantines have to do with it ._.
23:26:35 <int-e> it's another kind of polynomial equations
23:26:53 <oerjan> <fizzie> I have a feeling the signed overflow is UB to cater for (real or hypothetical) machines where signed-integer arithmetic traps on overflow rather than doing something else. <-- what istr reading is that it's UB to allow optimizations that only work if there is no overflow hth
23:26:56 <int-e> (restricted to integer coefficients and variables)
23:27:15 <oerjan> so it doesn't actually have anything to do with ambiguousness of representation at all
23:27:24 <oerjan> (or not just that, anyway)
23:28:20 <Bike> well, yes, i don't care about that limitation here though is all
23:29:33 <oerjan> @tell fizzie <fizzie> I have a feeling the signed overflow is UB to cater for (real or hypothetical) machines where signed-integer arithmetic traps on overflow rather than doing something else. <-- what istr reading is that it's UB to allow optimizations that only work if there is no overflow. so it isn't just about ambiguousness of representation, if at all.
23:33:45 -!- Patashu has joined.
23:38:31 -!- mihow has joined.
23:40:54 -!- nooodl_ has quit (Quit: Ik ga weg).
23:46:19 -!- Patashu_ has joined.
23:46:19 -!- Patashu has quit (Disconnected by services).
23:56:04 <tswett> Optimizations that only work if there's no overflow, eh?
23:57:55 <zzo38> LLVM can explicitly specify if there is no signed overflow and no unsigned overflow.
23:58:13 <oerjan> i think the c faq had examples
23:58:53 <tswett> IIRC, in C, unsigned integer overflow is defined to wrap around and signed integer overflow is undefined behavior. I guess you could use a signed 16-bit integer to represent an unsigned 8-bit integer with undefined behavior on overflow.
00:01:05 -!- MDream has changed nick to MDude.
00:04:46 <zzo38> You could also just do it directly in LLVM by telling it that you want undefined behavior on unsigned overflow in this circumstances.
00:12:59 -!- Phantom_Hoover has quit (Read error: Connection reset by peer).
00:14:56 <tswett> Now, the problem with base 10, and all other positive integer radix bases, is that they're topologically incorrect.
00:16:05 <MDude> Are you saying they outright don't have topoligies?
00:16:27 <tswett> Oh, I think they have topologies. But the topologies are incorrect.
00:17:17 <tswett> Say that a set of sequences is open if and only if, for every sequence in the set, there's a finite prefix of that sequence such that every sequence with that prefix is in the set.
00:17:55 <tswett> (For example, the set of all sequences containing at least one "b" is open, because given the sequence "aaaabaaaaaaa", there's a prefix, "aaaab", such that every sequence with that prefix is in the set.)
00:18:31 <tswett> Then there's no continuous function taking a regular Cauchy sequence and returning a decimal expansion for its limit.
00:20:46 -!- mhi^ has quit (Quit: Lost terminal).
00:21:55 <tswett> Yeah. Given the sequence 1.1, 0.9, 1.01, 0.99, 1.001, 0.999, 1.0001, 0.9999, ..., you can never find any digits of the decimal expansion because you don't know whether the first digit is 0 or 1.
00:22:32 <tswett> The most obvious bases that don't have this problem are the negative integer radix bases.
00:23:38 <tswett> No, that's not quite true.
00:23:51 <tswett> They're the negative integer radix bases where you're allowed to use digits at least as large as the base.
00:24:04 <tswett> The absolute value, rather. So, e.g., base -2 with 0, 1, and 2 as digits.
00:25:18 <quintopia> is system F brainfuck? i don't even remember
00:25:50 <oerjan> quintopia: no it's lambda calculus with explicit rank-n types
00:26:36 <oerjan> ghc's core intermediate language is an extension of it
00:26:57 <oerjan> the basica version allows only terminating functions
00:27:20 <zzo38> I once made some kind of RLE where some values are data values and some are RLE values, and the RLE values are small-endian shifted numbers so, for example, you might have eight data values and eight RLE values, then the digits are 1 to 8. If RLE values are present, you add two to determine how many.
00:28:02 <quintopia> oerjan: i don't understand anything even remotely related to ghc. i feel like the dude in that codeless code "the monolith"
00:28:23 <zzo38> Clearly there is still some redundancy though.
00:34:26 <Bike> darn, how could everyone have missed a flaw in numbers this whole time
00:34:55 <oerjan> is mathematics inconsistent
00:34:57 <zzo38> Bike: That isn't a flaw, though.
00:35:33 <zzo38> It looks to me like an error in trying to use then with topologies even though it shouldn't apply.
00:36:03 <oerjan> wait is Bike talking about what zzo38 thinks he is talking about
00:36:09 <Bike> actually, yes.
00:37:03 <Bike> zzo will see that everything he loves is a lie as soon as he tries getting digits of the limit of 1.1, 0.9, etc etc
00:37:16 -!- Phantom_Hoover has joined.
00:37:27 <zzo38> That's because it doesn't have a limit.
00:38:08 <zzo38> Many things don't have a limit!
00:38:19 <Bike> what a cruel thing to say.
00:39:08 <zzo38> I don't care if it is cruel or not.
00:40:24 -!- Phantom_Hoover has quit (Remote host closed the connection).
00:40:36 <Bike> ironically that is also a cruel thing to say
00:41:34 -!- edwardk has joined.
00:43:04 -!- Phantom_Hoover has joined.
00:44:28 <oerjan> cruelly, that is not actually ironic hth
01:03:22 <olsner> and incidentally (neither cruelly nor ironically) it is/was my birthday
01:04:02 <kmc> happy olsner day!
01:04:26 -!- kmc has set topic: Happy olsner day! | PSA: fizzie is running the wiki now, contact him for any problems | brainfuck survey: https://www.surveymonkey.com/s/L82SNZV | https://dl.dropboxusercontent.com/u/2023808/wisdom.pdf http://codu.org/logs/_esoteric/ http://tunes.org/~nef/logs/esoteric/.
01:04:33 <kmc> how do you feel
01:04:57 <kmc> (it's just as well, we're 90% of the way through megasecond 1400)
01:05:24 <olsner> not older, because really I'm pretty much exactly as old as I used to be
01:06:53 <kmc> 420 build LLVM every day
01:08:07 -!- yorick has quit (Read error: Connection reset by peer).
01:08:23 <olsner> kmc: I don't do drugs, but if I did I wouldn't do llvm
01:08:50 <zzo38> Some people's birthday is on Feb.29 and it has to be moved to Mar.1. One way to avoid is to use your actual sun sign rather than the calendar; then you don't have to worry about leap years. However, in such a case, it will then change which date it is on each year much more often.
01:10:00 <kmc> how are you inebriated if you don't do drugs
01:11:46 <Bike> high on life tbh
01:11:52 <olsner> my impeccable logic has been peccled
01:12:04 <olsner> high on inebriation itself
01:12:33 <kmc> like a snake smoking its own tail
01:13:02 <zzo38> Do you know what is the ecliptic longitude of sun at the time of your birth, to the nearest degree, and what time this year is corresponds to the same number? (I am not asking you what it is; I only ask if you know it or not.)
01:13:19 <kmc> no, but I think I could look it up?
01:13:22 <zzo38> (I don't actually care what the result is.)
01:14:10 <zzo38> kmc: Using ephemeris you certainly can look it up, yes. But you may need to know the time of day too, in such a case.
01:14:32 <kmc> i know the approximate time of day when I was born
01:14:36 <olsner> if I start using rust's format macros, I wonder if it would bloat my kernel horribly
01:14:49 <olsner> well, my thought exactly
01:19:13 <zzo38> You can either use software on your computer to calculate it (such as Swiss Ephemeris, or Astrolog), or use a webpage form such as http://ephemeris.com/ephemeris.php It will display the current positions by default. You should leave the longitude/latitude/meters blank. The columns "Longitude" and "Latitude" are ecliptic positions (you can tell because of the units used), while "Right Asc." and "Declination" are equatorial coordinates.
01:19:26 -!- hogeyui has quit (Ping timeout: 240 seconds).
01:24:29 <zzo38> (Ephemeris can also be used for date/time in the future, too.)
01:31:52 -!- hogeyui has joined.
01:34:20 <Sgeo> http://www.theonion.com/video/christ-article-a-video,36101/
01:41:50 -!- Phantom_Hoover has quit (Ping timeout: 276 seconds).
01:41:52 <zzo38> In a tarot deck, one card is called a "Fool" (or sometimes, an "Excuse"). This card is often labeled zero, but I disagree, and believe it should instead remain unlabeled. Generally, either it is either the highest trump, or it is a card which can be played even though you are able to follow suit, but always loses the trick.
01:42:38 <zzo38> Someone once told me why it is labeled zero, which is because it represents the beginning of the journey, which is what the trump cards represent. I can understand this, but do not consider it to be a valid excuse. What do *you* think?
01:43:59 <zzo38> Another document agrees with me that it should not be numbered, but has an entirely different reason which does not agree with mine.
01:44:31 <Bike> why would i care
01:44:34 <zzo38> Have you played any card games at all which have a card which can be played even though you are able to follow suit?
01:44:49 <zzo38> I am wondering what other games use such a feature.
01:51:35 <oerjan> that game with the eights?
01:52:39 <oerjan> https://en.wikipedia.org/wiki/Crazy_Eights
01:53:19 <quintopia> and that upstream downstream one i think
01:56:07 <zzo38> Yes, but I meant about trick taking games, where you lose the trick if you don't follow suit.
01:57:13 <zzo38> I don't really know how Spades is played, but I can try to learn
02:02:27 <zzo38> In hearts it is played that you cannot lead a heart until one is played (and also a similar rule is sometimes used in spades). But what if, all you have are hearts?
02:03:26 -!- hk3380 has quit (Ping timeout: 240 seconds).
02:03:51 <zzo38> Wikipedia says they can play it anyways in such a case.
02:05:04 <zzo38> Perhaps the following variant rule of Hearts is similar to the Excuse card in tarot: "Non-distinct Jokers are valueless cards that cannot win tricks. They may be played at all times (except to lead tricks)"
02:07:38 <quintopia> zzo38: in spades, if you have all the spades, you must call for a redeal
02:08:28 <zzo38> O, OK, why is that?
02:09:07 -!- xk002 has quit (Ping timeout: 240 seconds).
02:13:06 -!- xk002 has joined.
02:16:27 <quintopia> zzo38: because if you have all the spades, you will automatically win every trick, which means you will declare 13 tricks, the other side will declare 0, everyone will make their bids, and no fun will be had by all. boring.
02:17:28 <Sgeo> I'm going to keep on hoping that, despite this image, Creatures 4 will have a real genetics editor
02:17:28 <Sgeo> http://img2.wikia.nocookie.net/__cb20110825065432/creatures/images/4/44/Creatures_4_Editor.jpg
02:24:42 <MDude> I'd think it will.
02:25:14 <MDude> Just that because it's free-to-play, you'd have to pay for each custom egg you hatch or something.
02:26:14 <Sgeo> Are you a Creatures fan?
02:26:29 <MDude> Yeah, though it's been a while since I've played.
02:26:47 <MDude> Keep scratching my Creatures 3 disks, hoping to get it on gog.com sometime.
02:26:49 <Sgeo> Cool, which games?
02:27:10 <MDude> Just 3, though I wouldn't mind playing the others.
02:28:05 <Sgeo> Pretty much only DS+C3 here
02:37:07 -!- Sorella has quit (Quit: It is tiem!).
02:37:48 -!- MoALTz__ has joined.
02:40:27 -!- MoALTz_ has quit (Ping timeout: 252 seconds).
02:54:38 -!- kmels has quit (Ping timeout: 276 seconds).
02:55:24 -!- kmels has joined.
02:58:34 -!- hk3380 has joined.
03:38:55 -!- hk3380 has quit (Ping timeout: 258 seconds).
03:52:54 -!- MDude has changed nick to MDream.
04:00:08 -!- MoALTz has joined.
04:02:14 -!- MoALTz__ has quit (Ping timeout: 276 seconds).
04:17:51 <kmc> shachaf: https://github.com/kmcallister/rfcs/blob/lints/active/0000-loadable-lints.md
04:19:01 <kmc> and discussion here: https://github.com/rust-lang/rfcs/pull/89
04:19:06 <kmc> i like mcpherrin's suggestion of CSS selectors for ASTs
04:19:33 <Sgeo> jQuery for Rust
04:24:02 <HackEgo> [wiki] [[0(nop^)]] http://esolangs.org/w/index.php?diff=39667&oldid=39666 * John Misciagno * (+101)
04:25:37 <zzo38> Can xQuery selectors be used for ASTs?
04:27:47 <zzo38> I want to know a code that can convert something like CSS selectors for ASTs into a SQL code.
04:30:31 <kmc> what is xQuery?
04:31:14 <zzo38> Queries XML documents
04:31:31 <kmc> how does it compare to XPath?
04:31:43 <kmc> I think pcwalton's idea here is pretty #esoteric: https://groups.google.com/d/msg/mozilla.dev.servo/49g2izLWsls/VRlR_dSws_EJ
04:31:48 <kmc> so Blink has a JIT for CSS selectors
04:32:01 <kmc> and he wants us to do the same, but also throw out any other representation of CSS nodes
04:32:07 <Sgeo> Is it just me, or is 'API' coming to mean 'HTTP-transported API returning JSON objects'?
04:32:09 <kmc> and get it dynamically by decompiling the JIT code
04:32:16 <kmc> Sgeo: this is why we can't have nice things
04:32:39 <Bike> https://www.mashape.com/ sgeo
04:32:52 <Bike> a hilarious site fyi
04:33:31 <Sgeo> Bike: an ad for that site is exactly what made me think of that
04:34:27 <Bike> http://blog.mashape.com/post/69006514021/list-of-25-email-validation-apis man they even advertise it
04:34:34 <Bike> we have a million of everything and it all costs moneys
04:34:44 <Sgeo> Wait. Why is that site suggesting hitting it for using the APIs? Do people make HTTP/JSON APIs on that site based off other APIs that might not be so "friendly"?
04:35:21 <Sgeo> "EmailValidate is a web service which validates email addresses using various methods, including: Syntax validation, MX record lookup, SMTP availability"
04:35:30 <kmc> i have sliced my thumb by attempting to use a knife as a different kind of tool
04:35:32 <Sgeo> SMTP? Isn't that obsolete, shouldn't we be HTTP POSTing emails?
04:35:36 <kmc> not badly, just enough to feel stupid
04:35:58 <shachaf> kmc: did you try to use it as nail polish
04:36:02 <kmc> Sgeo: one day in the future, software archaeologists will attempt to discern the purpose of all these mysterious protocol layers under HTTP
04:36:02 <zzo38> Maybe it is call obsolete, but it shouldn't be. We should be using SMTP and deprecating the ability tp HTTP POSTing emails.
04:36:05 <kmc> shachaf: no
04:36:43 <Bike> maybe if browser developers applied their mystic powers of understanding thirty layers of historical garbage i wouldn't have so much trouble with bug biology
04:36:49 <zzo38> There are many better protocols than HTTP.
04:37:26 <kmc> HTTP isn't the protocol we want but it's the protocol we deserve
04:37:28 <Sgeo> zzo38: that literal example isn't quite happening yet. Except to the extent that webmail clients work, but that is, so far, just to a server which itself will use SMTP.
04:37:38 <kmc> no, there are totally services that let you send email by HTTP APIs
04:37:53 <shachaf> i feel like i should spend some time actually learning rust
04:38:03 <kmc> shachaf: it's pretty cool
04:38:22 <kmc> Sgeo: http://www.mailgun.com/ is a popular one
04:38:47 <kmc> shachaf: you should do it so that you can implement rustc features that i want
04:39:06 <Sgeo> application/x-www-form-urlencoded?
04:39:11 <Sgeo> Jeez, seems like a novelty these days
04:39:26 <kmc> in 11 months as a professional Rust developer, I have opened 48 issues on the Rust bugtracker
04:39:42 <shachaf> whoa, meteor shower tonight
04:39:49 <zzo38> I still insist to use SMTP (or TFTP). If the server requires HTTP to be used, you should instead immediately deprecate it and write a SMTP server that translates the signals, and then eventually fix it so that it works other way around.
04:39:52 <Sgeo> I'd almost say I'm weirdly happy about that, except it exposes security issues because what's an SOP, <form> inventor?
04:40:04 <kmc> this is why we can't have nice things
04:40:31 <kmc> 11:31 < kmc> should I be scared when the WHATWG spec says "for historical reasons"? because I feel like that phrase already applies to the entire document
04:40:34 <kmc> 11:31 < Ms2ger> Correct
04:40:36 <kmc> 11:32 < Ms2ger> That just means "for historical reasons we dislike particularly"
04:41:58 -!- pdxleif has quit (Quit: ZNC - http://znc.in).
04:42:05 -!- tromp_ has quit (Read error: Connection reset by peer).
04:42:42 <zzo38> HTTP is very wasteful, and HTTPS isn't as secure as they want it to be.
04:42:57 <Bike> as long as you're writing a whole browser you should write a whole hypertext replacement, realistic adoption be damned
04:44:17 <kmc> zzo38: what do you think are the main security issues with HTTPS?
04:44:21 <Sgeo> zzo38: there's a TCP-like protocol that lives on top of HTTP(S). It's becoming quite popular.
04:44:24 <kmc> there are so many, I don't even know where to begin
04:44:48 <zzo38> Don't write the whole browser anyways. Use different program each purpose. Using telnet and SSH when you want interactive sessions without hypertext and so on (SSH also allows a few other things; you can send a command directly for batch processing, and you can use X forwarding if you need a GUI, but hopefully you don't need a GUI and can avoid that complexity).
04:44:49 <Sgeo> Well, I guess 'on top of' isn't quite accurate. More initiated by
04:44:53 <Bike> today somebody asked me whether using "EFF" was worth it. after some needling i found out he meant their HTTPS Everywhere gizmo
04:45:05 <kmc> Sgeo: websockets?
04:45:11 <kmc> good times
04:45:31 <Bike> i was like, are you trying to set up donations or sumfin
04:45:33 <Sgeo> kmc: and the company you're working for is building a mobile OS on top of this mess.
04:45:51 <Bike> as god intended
04:45:51 <Sgeo> Hmm, does Mozilla count as a company?
04:46:01 <Sgeo> Or just 'organization'?
04:46:03 <Bike> well they're a bunch of people
04:46:06 <Bike> therefore, company
04:46:32 <zzo38> You should use SSH instead of HTTPS, and avoid use of HTML too. Make the command-line to upload/download/access bank statements and so on, using bank statement format, payment format, etc
04:47:14 <Bike> hey zzo are your parents computer people?
04:47:16 -!- tromp_ has joined.
04:47:30 <Sgeo> zzo38: fantastic idea! Now, what do we do when our customers think that we're an utterly backwards company because we have no web site?
04:47:50 <zzo38> Sgeo: Well, make a web site! But, put a notice on it that says, "Deprecated"!
04:48:58 <monotone> No matter how bad the existing stack is, anything you ask a bank to come up with will be worse.
04:49:24 <Bike> i'm just having a hard time imagining you being you if you've ever had to help an unsavvy parent with the computerbox
04:49:32 <Sgeo> Making a non-web GUI is also going to be 'fun', involving possibly asking customers to trust that we're not evil (maybe warranted for an ISP, possibly not so much for, say, sharing 'meme images')
04:50:07 <zzo38> Best is not GUI at all, if it can be avoided.
04:50:15 <oerjan> Bike: there's the alternative possibility they're so unsavvy they refuse to touch a computer, ever
04:50:29 <Bike> that was actually my first guess
04:50:33 <zzo38> If you do need a GUI, use non-trusted X forwarding.
04:51:15 <zzo38> But try to allow it to work without a GUI if that is at all possible, even if a GUI is available.
04:51:18 <monotone> You want to let people run X programs on bank servers?
04:51:48 <Sgeo> The web is the worst cross-platform GUI stack there is, except for all the others.
04:51:51 <zzo38> monotone: No, you should disable GUI, to avoid that.
04:52:03 <Bike> geez monotone do try to keep up
04:52:33 -!- mcpherrin has joined.
04:53:01 -!- M28 has joined.
04:53:20 <monotone> still thinkin' jwz("I'll invent a new protocol!")
04:53:40 <Bike> like building a bookcase out of mashed potatoes
04:53:41 <zzo38> If you do need to run X programs, well, you can fake it, and whatever. Ensure both sides are secure. It may be easier to secure than a webpage. But first try to use, don't use GUI at all if it is possible to avoid GUI.
04:53:52 <HackEgo> Linux umlbox 3.13.0-umlbox #1 Wed Jan 29 12:56:45 UTC 2014 x86_64 GNU/Linux
04:53:56 <kmc> hi mcpherrin
04:54:41 <kmc> mcpherrin: HackEgo is a bot which executes each command by booting a new Linux virtual machine, running the command, and then merging filesystem changes using Mercurial
04:55:02 <kmc> okay, it's User Mode Linux so both "booting" and "virtual machine" are something of an overstatement there
04:55:06 <kmc> but that's how it works
04:55:13 <HackEgo> boatwanvcoin bilcoin dugocoin goto+coin piecodecoin subsidcoin minarcoin uncepticoin cobcoin alpaincoin ultisismcoin javcoin pinquinaboracoin tudcoin ornicoin juggariolacoin pckivcoin mempovecoin tarylancoin ballcoin
04:55:15 <kmc> `cat bin/coins
04:55:16 <HackEgo> words ${1---eng-1M --esolangs 20} | sed -re 's/( |$)/coin\1/g' | rainwords
04:55:25 <Bike> monotone: (i think that's how jwz described using xlib)
04:55:53 <zzo38> Did they install SQLite yet in there? It could be installed, if you want to write a survey program in SQL, to run in HackEgo.
04:56:00 <Bike> oh hey this paper cites "McAllister". kmc are you a biophysicist
04:56:11 <kmc> i'm also not a street in san francisco
04:56:13 <monotone> Bike: Oh, I see. Was talking about the greeting anyway.
04:56:42 <oerjan> Bike: those mashed potatoes should go well with the edible book festival
04:56:44 <Bike> nor one of the dorms at my school, which has been repurposed into having the air force and fashion classes, i imagine
04:56:44 <Sgeo> Imagine if there were no languages except PHP... is this an accurate way to describe the web?
04:56:56 <Bike> no hell below us
04:57:00 <kmc> no part of the web technology stack is as bad as PHP
04:57:08 <kmc> JavaScript is bad but it's not irredeemably bad
04:57:10 <zzo38> Sgeo: No; it isn't the only way to program it, too. You can use CGI programs in C, too.
04:57:23 <kmc> JS is a really weird demonstration of the Lambda the Ultimate principle
04:57:28 <zzo38> JavaScript is a fine programming language actually. It is used really badly though.
04:57:38 <zzo38> PHP is much worse.
04:57:40 <Sgeo> kmc: sending browsers text data that contains both trusted and untrusted data, with the only separation being context-sensitive escaping
04:57:49 <kmc> partly it's that everyone has to use JS, so they come up with ways to make it not suck
04:57:51 <Bike> web escaping is awesome
04:57:59 <Bike> in that what the fuck even
04:58:01 <zzo38> (PHP can also be used for command-line programs; in fact, so can JavaScript.)
04:58:08 <kmc> whereas people who use PHP and realize how bad it is can just use something else
04:58:11 <kmc> with some exceptions
04:58:33 <kmc> zzo38: yes, I worked somewhere that had a mixed Rails / PHP codebase and used both langugaes for batch processing as well as webapps
04:58:56 <monotone> PHP also has a tendency to "fix" things by making them worse.
04:59:06 <zzo38> If you are using JavaScript for something other than client-side coding on webpages, then you usually can easily use something else. For example, Synchronet door programs are written in JavaScript, but you can just as well use a native code program or a DOS program.
04:59:26 <kmc> emscripten that shit
05:00:19 <zzo38> XULrunner programs are also JavaScript; you can try to use C++ instead but that probably makes it more difficult and more confusing. I think JavaScript is really not too bad.
05:00:37 -!- oerjan has quit (Quit: Nite).
05:01:43 <zzo38> mcpherrin: I know about XPCOM.
05:02:17 <kmc> mcpherrin: there is interest in writing Gecko components in Rust
05:02:23 <kmc> xpcom.rs woooo
05:02:42 <mcpherrin> kmc: I have written enough xpcom to know that I don't want to do that ;)
05:03:16 <zzo38> I have written webpage server programs in SQL, though. It was at someone's request; they had SSH clients and all that stuff on their computers but I (and the system administrator) are the only ones who didn't refuse to use them. I later found my program was rewritten in Ruby by someone else.
05:03:26 <kmc> another fun macro is let string = objc![[NSString alloc] initWithCString: "Hello, world!"]
05:03:56 <zzo38> (Possibly because they didn't know SQL, or something like that?)
05:04:19 <zzo38> (Or maybe they hated SQL)
05:04:19 <monotone> lol, should have expected that when I searched for a JS interpreter in JS, I'd find one that's just SpiderMonkey compiled to asm.js with Emscripten.
05:04:21 <Sgeo> kmc: let me know when you can embed a Smalltalk IDE into Rust
05:04:32 -!- tswett has quit (Ping timeout: 252 seconds).
05:04:50 <Bike> monotone: i'm imagining an ICE where the pistons are themselves engines
05:04:50 <kmc> someone was compiling webkit to asm.js too
05:05:56 <elliott> monotone: https://github.com/mozilla/narcissus/
05:06:21 <monotone> So now we're talking about running a full-fledged browser in your browser, in a way that's somewhat more efficient than the current state of the art, running a browser in an x86 emulator in your browser.
05:07:24 <Bike> man anyone remember xzbit jokes? those were the dayzzzz
05:07:53 -!- HackEgo has quit (Ping timeout: 276 seconds).
05:07:57 <kmc> high times
05:10:36 -!- HackEgo has joined.
05:12:39 <zzo38> If you want structured menus of files and stuff, which is suitable for any device with any user interface (including scantron), then gopher protocol is very suitable for such a thing.
05:15:06 -!- password2 has joined.
05:15:17 <Bike> take these words to heart
05:25:44 -!- MoALTz_ has joined.
05:28:23 -!- MoALTz has quit (Ping timeout: 252 seconds).
05:52:42 -!- tromp_ has quit (Remote host closed the connection).
05:59:58 <kmc> god javascript is such a shitty language
06:00:12 <shachaf> is it even worse than mortal javascript
06:01:48 <zzo38> For what things are worse in JavaScript?
06:11:49 -!- not^v has joined.
06:13:26 <shachaf> how can you make a website as awful at getting information to people as http://www.theatrebayarea.org/events/event_list.asp
06:13:52 <shachaf> it used to be ~one page with all sorts of plays
06:14:16 <shachaf> then it was ~4 pages grouped geographically
06:19:29 -!- kmels has quit (Ping timeout: 264 seconds).
06:27:39 <kmc> that sounds like what muni did
06:32:22 <shachaf> there's an announcement: http://www.theatrebayarea.org/news/159235/Welcome-to-Our-New-Website.htm
06:41:53 -!- conehead has quit (Quit: Computer has gone to sleep).
06:46:14 <kmc> fungot: While you are letting your guard down / I will be letting myself go / While you keep running your ship aground / I will be setting myself alight
06:46:14 <fungot> kmc: reloaded the python plugin. it is implemented...
06:51:55 -!- not^v has quit (Quit: http://i.imgur.com/Akc6r.gif).
06:52:13 -!- MoALTz__ has joined.
06:52:29 -!- edwardk has quit (Quit: Computer has gone to sleep.).
06:52:35 <fungot> fizzie: i still think s/ coming and s/ pheromone/ mark/ blog/ images/ p6_cover_big.gif amusing)
06:54:25 <Jafet> Implement fungot in ///
06:54:25 <fungot> Jafet: where x y and t is injective.
06:54:52 -!- MoALTz_ has quit (Ping timeout: 245 seconds).
06:56:23 -!- edwardk has joined.
07:00:46 <kmc> zzo38: why do you know about XPCOM?
07:00:59 <zzo38> kmc: Because I worked with it a bit once
07:01:15 -!- tswett has joined.
07:01:35 <kmc> what did you make?
07:04:33 -!- Slereah has quit (Read error: Connection reset by peer).
07:04:33 <shachaf> kmc: http://www.theonion.com/video/christ-article-a-video,36101/
07:04:52 -!- Slereah_ has joined.
07:05:24 <kmc> apparently my idea of fun on a friday night is to consume a large amount of alcohol and marijuana and then read the dlopen(3) manpage
07:05:48 -!- edwardk has quit (Quit: Computer has gone to sleep.).
07:06:28 <zzo38> I was modifying a XULrunner program.
07:21:50 <Bike> stoned dlopen partay
07:31:53 <mcpherrin> shachaf: I feel like I forget who you are ( I mean, I know you're in the other IRC channel too )
07:33:53 <shachaf> I've seen your name before but probably just in IRC and/or Rust contexts.
07:34:38 <mcpherrin> shachaf: oh so we're in three overlapping IRC channels :P
07:41:24 -!- drdanmaku has quit (Quit: Connection closed for inactivity).
07:54:01 -!- xk002 has quit (Quit: Saindo).
07:54:33 -!- xk002 has joined.
07:59:27 -!- hogeyui has quit (Ping timeout: 245 seconds).
08:09:00 -!- password2 has quit (Read error: Connection reset by peer).
08:12:27 -!- hogeyui has joined.
08:14:23 -!- edwardk has joined.
08:16:01 -!- AnotherTest has joined.
08:22:15 -!- impomatic has quit (Quit: impomatic).
08:22:53 -!- edwardk has quit (Ping timeout: 276 seconds).
08:25:39 -!- password2 has joined.
08:33:31 <kmc> shachaf: 'undefined' and the way it makes errors manifest in the wrong place
08:33:39 <kmc> imo no better than mapping a page of zeroes at address zero
09:05:05 <HackEgo> formcoin exedcoin bitacoin furncoin rigencoin penccoin inscoin ennecoin oddycoin allecoin arbroocoin whenecoin wjthcoin dobridcoin sted!coin minenreanencoin cationcancecoin dissantinguadcoin bancoin warcoin
09:12:58 <Taneb> Do you ever look at some code you wrote and think "why"
09:13:09 <Taneb> "why the hell did I think this would be a good idea"
09:16:29 -!- MindlessDrone has joined.
09:22:56 <Taneb> "lambda shapes: all([shape in self.ships for shape in shapes])"
09:23:37 -!- nooodl has joined.
09:26:16 <kmc> that's numberwang
09:27:17 <Taneb> This line (which was written by me) came from something I was doing from a friend, for a competition where we had to write in Python.
09:27:43 <Taneb> It was originally largely based on his earlier C++ code, with parts based on my earlier Haskell code.
09:28:12 <Taneb> At some point we renamed a bunch of things from "shape" to "ship" or possibly the other way round, but we were horribly incomplete about it all
09:29:47 <Taneb> A lot of it was then written by a very over-tired me
09:30:20 <Taneb> A lot of it I have had to justify as "it came to me in a dream" because that's what it felt like.
09:31:19 <fizzie> Oh, I think that line is shipshape.
09:32:03 <kmc> how strange it is to be anything at all
09:33:14 <fizzie> My next "hi" will probably be from Kyoto, incidentally.
09:34:11 <fizzie> Now I can't say "hi" back because it'd make me a liar. :/
09:35:32 <kmc> just remember: SUNTORY BOSS is the boss of them all since 1992
09:42:07 -!- nooodl has quit (Ping timeout: 252 seconds).
09:58:56 <int-e> Bike: The connection from solving systems of polynomial equations to Gröbner bases is as follows: if X (a vector of real numbers) is a solution of P_i(X) = 0 for 1 <= i <= n, then any polynomial Q in the ideal I = <P_i>_{1 <= i <= m} has X as a solution. Now the Gröbner basis B of I is a subset of I, so X is also a solution of the set of equations given by B. Furthermore, B generates I, which contains all P_i, so any...
09:59:02 <int-e> ...solution to the equations in B is also a solution of each P_i. So B has the same set of solutions as the original polynomials. But the polynomials in B are often (maybe always, but I don't see why. did I mention that I'm not an expert on Gröbner bases?) easier to solve than the original ones, because by a suitable choice of order on monomials it's possible to separate variables (so you get a polynomial in x_1, then one...
09:59:08 <int-e> ...in x_1 and x_2, then one in x_1 to x_3, and so on).
10:00:47 * kmc hugs int-e
10:03:45 -!- KingOfKarlsruhe has joined.
10:29:41 -!- olsner has quit (Ping timeout: 252 seconds).
10:35:53 -!- Phantom_Hoover has joined.
10:40:59 <Jafet> "Hevisaurus is a Finnish heavy metal children's music band, who dress in dinosaur costumes."
10:43:23 -!- mhi^ has joined.
10:43:26 -!- olsner has joined.
10:53:58 <fizzie> Jafet: There was a schism in the Hevisaurusverse, I remember reading about it.
10:54:08 -!- KingOfKarlsruhe has quit (Read error: Connection timed out).
10:54:13 <fizzie> Jafet: Something about current rightsholders and the original founder and blah blah this and costumes that.
10:54:37 <fizzie> Oh, I guess the wiki article mentions it.
10:54:49 <fizzie> "In early 2011, the founder of the band, Mirka Rantanen, got into a disagreement with the band's record label Sony Music. Because of this, Rantanen and three other band members belonging to the band's live assembly founded a new band called SauruXet, which has continued making children's power metal music with the original concept and nearly identical artist names. The band Hevisaurus keeps ...
10:54:55 <fizzie> ... its lead singer, its producers and the original stage costumes."
10:57:27 -!- impomatic has joined.
11:03:03 -!- AnotherTest has quit (Ping timeout: 252 seconds).
11:07:58 -!- hk3380 has joined.
11:34:57 -!- olsner has quit (Ping timeout: 252 seconds).
11:40:59 -!- MDream has changed nick to MDude.
12:06:14 -!- xk002 has quit (Ping timeout: 240 seconds).
12:13:03 <HackEgo> [wiki] [[Talk:Brainfuck]] http://esolangs.org/w/index.php?diff=39668&oldid=39559 * Rdebath * (+302) /* My optimizing interpreter again */
12:15:48 -!- MoALTz_ has joined.
12:18:29 -!- MoALTz__ has quit (Ping timeout: 252 seconds).
12:18:37 <HackEgo> [wiki] [[Talk:Brainfuck]] http://esolangs.org/w/index.php?diff=39669&oldid=39668 * Rdebath * (+169) /* My optimizing interpreter again */
12:21:53 -!- password2 has quit (Ping timeout: 264 seconds).
12:34:28 -!- password2 has joined.
12:41:07 -!- password2 has quit (Ping timeout: 245 seconds).
12:48:07 -!- yorick has joined.
13:04:15 -!- nooodl has joined.
13:36:09 -!- MDude has changed nick to MDream.
13:36:17 -!- MDream has changed nick to MDude.
13:38:27 -!- boily has joined.
13:39:47 -!- boily has quit (Client Quit).
13:52:33 -!- Phantom_Hoover has quit (Ping timeout: 252 seconds).
14:03:02 -!- hk3380 has quit (Ping timeout: 240 seconds).
14:08:04 -!- Phantom_Hoover has joined.
14:10:16 -!- Patashu_ has quit (Ping timeout: 258 seconds).
14:12:45 <zzo38> It is true, that sometimes I have written some program code and think, why would I think it is good idea at the time?
14:15:32 <int-e> goto hell; // it seemed a good idea at the time
14:16:48 <zzo38> Actually I have used "goto hell" in a few programs in error handlers, and do not consider it so bad
14:17:00 -!- drdanmaku has joined.
14:20:08 -!- sign has changed nick to systemd.
14:20:40 -!- olsner has joined.
14:27:10 -!- MoALTz__ has joined.
14:30:12 -!- MoALTz_ has quit (Ping timeout: 258 seconds).
14:50:34 -!- oerjan has joined.
14:51:00 -!- tromp_ has joined.
14:51:12 -!- Sorella has joined.
14:51:45 -!- Sorella has quit (Max SendQ exceeded).
14:53:10 -!- Sorella has joined.
14:59:14 -!- nooodl has quit (Quit: Ik ga weg).
15:02:12 -!- hk3380 has joined.
15:03:35 <zzo38> Ripley once went to Hell on the suggestion that he go there several times.
15:03:49 <zzo38> (It is a place in Norway.)
15:07:58 <oerjan> i'm just a few minutes' drive from there, actually
15:08:24 <oerjan> it's next to trondheim's airport.
15:08:41 <Taneb> So, Hell is Trondheim's Heathrow
15:09:02 <oerjan> no, Hell is next to Trondheim's Heathrow, which is name Værnes.
15:10:16 <oerjan> 6 minutes walk to the airport, i read in an article about the Blues in Hell festival (very small but praised festival)
15:11:02 <oerjan> i also recalled someone once suggested renaming the airport to Hell airport instead. i think it's like on the border between the two villages.
15:11:40 <oerjan> (well Værnes might count as a town, but Hell is smaller.)
15:12:52 <oerjan> of course with a name like that and extremely good connectivity a festival just has to be successful.
15:13:03 <Taneb> Isn't there a Hell in Jamaica?
15:13:20 <oerjan> Taneb: i think that was mentioned last time we discussed this
15:13:43 <FreeFull> I think there is a Hell in Pennsylvania
15:15:26 <oerjan> darn there i go talking before opening the logs again
15:15:57 -!- edwardk has joined.
15:16:19 <oerjan> (IE's search makes it awkward to go to hits on my nick that aren't close to the beginning or end of the file, so now i have to click past everything i just said)
15:16:50 <oerjan> back in IE 8 it was easy, i could just click in the document to tell it to start searching there :(
15:17:17 <oerjan> but obviously they thought that was too conven*Wconfusing
15:19:02 <FreeFull> What if you use the F7 cursor mode?
15:20:25 -!- edwardk has quit (Ping timeout: 258 seconds).
15:21:32 <oerjan> nope, no effect. in fact the cursor was already where i had clicked, just invisible.
15:22:03 -!- edwardk has joined.
15:28:00 <Sgeo> [1,2,3,4,] // DIE IE8 DIE
15:35:31 -!- erdic has quit (Ping timeout: 240 seconds).
15:35:41 -!- trout has quit (Ping timeout: 264 seconds).
15:37:53 <Taneb> Going to see the new X-Men film tonight
15:43:26 -!- edwardk has quit (Quit: Computer has gone to sleep.).
15:45:55 -!- Frooxius has joined.
15:46:05 -!- Froox has quit (Read error: No route to host).
15:46:08 -!- Frooxius has quit (Read error: Connection reset by peer).
15:46:44 -!- systemd has changed nick to sign.
15:47:44 -!- Frooxius has joined.
15:50:22 <Taneb> Phantom_Hoover, it would be amusing if by some bizarre coincidence we ended up sitting next to eachother
15:50:30 <Taneb> The bizarre coincidence would be more amusing
15:50:40 <Taneb> I doubt you would travel to York to watch a movie
15:50:55 <Phantom_Hoover> and i can't see why anyone would travel to leamington spa, ever
15:51:41 <Taneb> Where even is that
15:52:20 <oerjan> the glue is some weird clay with healing properties, clearly
15:58:26 -!- esowiki has joined.
15:58:31 -!- esowiki has joined.
15:58:31 -!- esowiki has joined.
15:58:52 -!- esowiki has joined.
15:58:56 -!- esowiki has joined.
15:58:56 -!- esowiki has joined.
15:59:00 -!- glogbot has joined.
15:59:06 <?unknown?> [freenode-info] help freenode weed out clonebots -- please register your IRC nick and auto-identify: http://freenode.net/faq.shtml#nicksetup
16:00:36 <oerjan> https://en.wikipedia.org/wiki/Murdoch_Mysteries
16:00:36 <Taneb> Clearly the same person
16:00:36 -!- FireFly has joined.
16:00:48 -!- erdic has joined.
16:01:23 <oerjan> his death 60 years earlier was clearly faked
16:04:52 -!- esowiki has joined.
16:04:56 -!- esowiki has joined.
16:04:57 -!- esowiki has joined.
16:05:09 -!- glogbot has joined.
16:07:14 <Taneb> It's not like anyone posted any 40 line rant about the sorry apathy in the European Parliament in the 12 seconds glogbot was absent
16:10:12 <fungot> Selected style: europarl (European Parliament speeches during approx. 1996-2006)
16:10:21 <oerjan> fungot: i think you have a job to do
16:10:22 <fungot> oerjan: six questions have been received. in view of such negligence, we are going to vote tomorrow on a cursory text. the proposal put forward and the conditions in which the fnord world, in east asia opens up an appalling vista. this is also a fellow countryman. there is extremely wide agreement in the committee before on mr cassidy's report linking the need for our proposals to a very low sulphur content, unlike mediterranea
16:10:59 <int-e> the first two sentences are nice
16:11:15 <int-e> I didn't know that europarl was also infested by that f-word though
16:11:39 <M28> I wrote a brainfuck JIT, it works with Hello world and a few other simple examples, but it seems to be crapping itself with longer programs, like bottles to the wall
16:12:51 <M28> anyone wanna take a look?
16:13:04 -!- idris-bot has quit (Quit: Terminated).
16:13:19 -!- idris-bot has joined.
16:13:22 <oerjan> 99 bottles of Segmentation fault (core dumped)
16:14:06 <oerjan> our jit expert never seems to be active these days.
16:15:14 <int-e> I'd be curious what the code looks like but I'm not optimistic about actually spotting bugs.
16:15:44 <int-e> oerjan: who would that be?
16:16:19 <oerjan> i mean, making a jit for IOCCC makes you an expert, right?
16:16:54 <int-e> compared to someone who has never made a jit at all, certainly :)
16:17:35 <Gregor> I'm an expert in all hackery things.
16:17:42 <mroman> impomatic: Is the koth hill still active?
16:17:54 <mroman> I submitted something days ago but I havent received any feedback
16:19:24 <oerjan> Gregor: how can you be idle for 4 days and still see pings
16:19:29 <impomatic> mroman: definitely still active. You need to submit the program in the body of the email and ensure the email is plain text.
16:19:49 <Gregor> oerjan: Just because I'm not chatting on IRC doesn't mean I'm not online.
16:19:56 <impomatic> mroman: also, there's the SAL hills which have a beginner hill.
16:20:10 <oerjan> Gregor: also, i'm still grieving for HackEgo's lack of log search ;_;
16:20:25 <mroman> Might be the case that Outlook Web App prefers sending html :)
16:20:36 <oerjan> i mean, MY CHANNEL MEMORY IS GOING, I CAN FEEL IT
16:22:21 <oerjan> Gregor: anyway M28 needs code review for his buggy bf jit twh
16:22:42 <M28> gimme a sec, fixing a bug with getchar
16:24:03 -!- conehead has joined.
16:24:04 <zzo38> I also don't like that you removed the log access from HackEgo. When will you fix that?
16:26:00 <oerjan> (now Gregor remembers why he never speaks on the channel any more)
16:27:05 <FireFly> Gregor: are you an internet expert, too?
16:27:16 <Gregor> <Gregor> I'm an expert in all hackery things.
16:27:55 <FireFly> Wait, you aren't dead and your last name isn't Jong-il, right?
16:28:25 <int-e> Gregor never said that he invented the Internet, as far as I know.
16:29:27 <zzo38> Will you install SQLite on HackEgo?
16:29:27 <oerjan> i find it _somewhat_ unlikely that kim jong-il said that.
16:29:44 <oerjan> if only because north korea doesn't have internet
16:29:53 <FireFly> He's claimed to be "an internet expert too"
16:29:57 <FireFly> http://www.foxnews.com/story/2007/10/05/north-korea-kim-jong-il-im-internet-expert/
16:30:03 <FireFly> ...according to Fox news, I notice
16:30:13 <HackEgo> /home/hackbot/hackbot.hg/multibot_cmds/lib/limits: line 5: exec: sqlite3: not found
16:30:31 <mroman> oerjan: They have internet?
16:30:50 <M28> http://puu.sh/8ZgV6/e9826ca5cb.png
16:30:56 <mroman> I just recently read in a paper that they have a handful (<5) PCs with internet connection
16:31:03 <M28> http://puu.sh/8ZgVX/48c18d9d9f.txt
16:31:09 <mroman> or at least plan to have them. Can't remember exactly :(
16:31:18 <oerjan> mroman: still, he probably didn't claim to invent it.
16:31:30 <M28> "," is broken for whatever reason
16:31:55 <HackEgo> SQLite version 3.7.13 2012-06-11 02:05:22 \ Enter ".help" for instructions \ Enter SQL statements terminated with a ";" \ sqlite>
16:32:07 <FireFly> I think I read that some of the .kp domains now point to servers in north korea
16:32:15 <FireFly> whereas earlier they were hosted in Germany IIRC
16:33:21 <oerjan> excellent, Gregor is also our local C++ expert
16:33:41 <int-e> M28: what about programs that contain more than 127 < or > signs in a row?
16:33:52 <M28> int-e, no one actually cares >_>
16:34:14 <M28> I should probably split it once it hits 127
16:34:30 <Gregor> Yeah, I don't exactly know x86 machine code by its hex X-D
16:35:17 <zzo38> We could now use this SQLite to write programs for polls and various other things
16:35:34 <int-e> M28: it's just that this might actually happen if the brainfuck code is generated by some sort of compiler.
16:35:56 <M28> I wrote a B to Brainfuck compiler once
16:36:10 <M28> (B is the language that comes before C, really)
16:36:35 <M28> I plan to eventually rewrite the JIT to optimize code generated by the compiler
16:36:42 <mroman> Any clues whether a stack-based programming language with one Register (stack contains register values, so no stacks of stacks, register are bounded in size) with random read access to the stack could be turing complete or not?
16:37:22 <nortti> is register unbounded?
16:37:33 <M28> I don't think you even need a register if you have a stack, as long as you can push, pop, add, etc. on the stack
16:37:37 <int-e> M28: the [ case looks wrong: you have to test for zero before the first loop iteration
16:37:57 <M28> int-e, wait what
16:38:07 <int-e> it's a while loop, not a do while loop
16:38:17 <M28> forgot about that ;_;
16:38:33 <int-e> (an unconditional jump to the ] code will do the trick)
16:38:42 <nortti> mroman: is the random read access like in false?
16:38:50 <M28> the problem is looking ahead
16:39:03 <M28> anyways, thanks
16:39:09 <M28> tell me if you can spot anything wrong in ,
16:39:12 <int-e> M28: reserve space for the destination, patch it up in the ] case.
16:39:20 <M28> that's what I'm gonna do
16:39:21 <oerjan> mroman: that is not TC because your stack addresses become bounded as well...
16:39:28 <mroman> nortti: You can treat the stack as a "tape" for read access
16:39:40 <mroman> i.e you can move around in the stack brainfuck-style with < and >
16:39:58 <mroman> there are no "addresses"
16:40:01 <nortti> then, I think one could do that, by simulating a queue
16:40:44 <mroman> The only write access is push/pop/peek
16:40:51 <zzo38> (If the logs would still be on, then we can also copy the logs into SQL format in order to query them by use of SQL queries.)
16:40:53 <oerjan> M28: a stack doesn't give you turing-completeness unless the stack cells are unbounded. you get just a pushdown automaton.
16:41:01 <mroman> actually just push and peek
16:41:49 <mroman> You can push the register, peek the top of the stack, or read a specific element of the stack
16:42:22 <mroman> (peek and read overwrite the register's contents)
16:42:30 <int-e> M28: what happens with the INT3 in there?
16:43:44 <M28> int-e, it's a break point
16:43:49 <M28> I was using it to debug
16:43:57 <nortti> shouldn't this work: you keep the peek pointer in the "start of queue" and when you dequeue, you just move the ptr one topwards
16:44:28 <nortti> enqueueing could be done with just the push
16:44:39 <nortti> it would build up a lot of garbage, tho
16:44:59 <mroman> http://codepad.org/ZcodA1m2 <- that's my sketch so far
16:45:04 <oerjan> nortti: oh that looks good
16:45:23 <mroman> which is the no-auto-commit-mode
16:45:31 <mroman> in auto-commit mode + - automatically perform a push
16:46:16 <M28> http://puu.sh/8ZhWl/2b2e2efac9.txt
16:46:24 <M28> it's able to run 99 bottles of beer to the wall
16:46:29 <M28> and it's incredibly fast :p
16:46:34 <oerjan> M28: now try lostkingdom *cackles evilly*
16:46:39 <M28> now I need to fix ,
16:47:17 <oerjan> M28: adventure game compiled to brainfuck
16:47:46 <M28> need to fix "," first
16:48:09 <oerjan> possibly the biggest brainfuck program seriously made
16:48:15 -!- password2 has joined.
16:48:35 <elliott> it's not really much of a brainfuck program.
16:48:35 -!- oerjan has quit (Quit: Anyway, I should be going).
16:50:07 <int-e> M28: I don't know what's wrong with the getchar. I'd compile and disassemble a C program that makes a call to getchar and, say, prints the answer.
16:50:26 <M28> it's just a cdecl call
16:50:51 <int-e> (oh and I have not checked the opcodes)
16:51:15 <M28> I have, they're fine
16:52:36 <M28> http://puu.sh/8ZikE/4295510bcf.png
16:52:47 <M28> those are the first lines of "-,+[-[>>++++[>++++++++<-]<+<-[>+>+>-[>"...
16:53:19 <M28> the first 5 instructions is just the start of the JIT code
16:54:32 <M28> now it works...
16:54:38 <M28> let's call it magic
16:56:14 <M28> let's run the lost kingdom now
16:57:46 <M28> msvc crashed
16:57:58 <M28> when I tried to save the lost kingdom into the source code
16:58:03 <M28> I'll just read it from a file
16:59:26 -!- Slereah has joined.
17:01:29 -!- Slereah_ has quit (Ping timeout: 264 seconds).
17:02:37 -!- MoALTz_ has joined.
17:03:38 <M28> http://puu.sh/8Zj1F/96d44324c6.png
17:06:08 -!- MoALTz__ has quit (Ping timeout: 276 seconds).
17:06:26 <zzo38> It looks like some line breaks are omitted in the list of objects in room
17:07:22 <M28> it's possible that cmd.exe only recognizes \r\n line brekas
17:07:30 <M28> and it's printing \n line breaks
17:08:51 <nortti> mroman: is the peek pointer relative to top of stack or to bottom of stack?
17:09:29 <M28> http://puu.sh/8Zjq0/ef2f4fa7ea.png
17:15:42 <zzo38> Actually from what I could tell, in text mode it will work with just \n and convert to \r\n. Also, I don't think it is related only to cmd.exe; it is part of the Windows command-window environment in general.
17:16:26 <zzo38> I am not quite sure though.
17:21:45 <int-e> shouldn't putchar('\n') produce \r\n?
17:22:11 <int-e> (on that platform)
17:23:38 <M28> int-e, yeah I made a wrapper for that
17:23:59 <M28> https://github.com/Matheus28/BrainJIT/blob/master/src/main.cpp#L15
17:24:26 -!- variable has joined.
17:25:01 <impomatic> mroman: did you try that koth hill again?
17:26:13 <int-e> M28: the lost kingdom *does* contain long runs of > and <.
17:26:35 <M28> yeah I did fix that
17:26:46 <M28> https://github.com/Matheus28/BrainJIT/blob/master/src/main.cpp#L95
17:27:29 -!- shikhin has joined.
17:27:30 <M28> by the way
17:27:38 <M28> that thing isn't really written in brainfuck, is it?
17:27:41 -!- Phantom_Hoover has quit (Ping timeout: 258 seconds).
17:28:01 <M28> like, I hope someone wrote it in another language, and wrote a compiler to brainfuck for it
17:28:34 <int-e> M28: but something is going wrong: In that hut, all I see is "a small wooden box of matches sitting on the table (2)"
17:29:12 <nortti> M28: iirc it was written in bfbasic
17:29:32 <M28> I don't see any error, where do you see that?
17:30:13 <int-e> M28: running LostKng.b in a "normal" brainfuck interpreter
17:31:05 <M28> I chose long descriptions there
17:31:13 <M28> this one has short descriptions http://puu.sh/8Zjq0/ef2f4fa7ea.png
17:31:21 <M28> but the text is reworded
17:31:25 <M28> are you using the same version?
17:31:27 <int-e> http://int-e.eu/~bf3/tmp/lk.png
17:32:08 <M28> I have no idea, tbh
17:32:43 <int-e> sha1sum says 587dc8ebf682dd78f413ebf599ca0552c1d7bdcc LostKng.b for LostKng.b btw.
17:33:56 <M28> I'll take a look at it later
17:33:59 <M28> kinda tired atm
17:37:27 -!- yorick has quit (Remote host closed the connection).
17:37:28 <mroman> nortti: relative to the top
17:37:56 <mroman> haven't got an answer though so far
17:38:19 <mroman> and it's been more than an hour
17:49:00 -!- conehead has quit (Quit: Textual IRC Client: www.textualapp.com).
18:00:14 -!- hk3380 has quit (Ping timeout: 240 seconds).
18:04:54 <kmc> <FreeFull> I think there is a Hell in Pennsylvania
18:05:03 <kmc> there's also a town that has been on fire since 1962
18:05:09 <kmc> http://en.wikipedia.org/wiki/Centralia,_Pennsylvania
18:08:03 <FreeFull> Odd how there is a Reading in Pennsylvania
18:17:57 <kmc> why is that odd
18:23:14 <kmc> code I wrote 2 years ago that has mfence() in various places with no explanation
18:26:07 <Bike> int-e: thanks.
18:26:36 <nortti> s/it/the instances of it in the code/
18:30:19 -!- hk3380 has joined.
18:32:06 <kmc> nortti: that is the question isn't it
18:33:43 <nortti> does it stop working if they are removed
18:36:32 <kmc> another fine question
18:36:51 -!- Slereah_ has joined.
18:37:43 <kmc> and not something I can easily test
18:38:26 <int-e> nortti: isn't it a bit dangerous to assume that it is working now?
18:39:50 -!- Slereah has quit (Ping timeout: 240 seconds).
18:40:12 <kmc> that's one reason it's hard to tell if it stops working
18:48:11 <shachaf> Does mosh make a ^G when it reconnects?
18:55:38 <HackEgo> [wiki] [[Talk:Meta Turing-complete]] http://esolangs.org/w/index.php?diff=39670&oldid=30910 * GermanyBoy * (+202) /* ℒ */
18:55:41 <kmc> why would it
18:56:01 <Bike> https://twitter.com/shelajev/status/469735994464690177/photo/1/large so easy
18:57:11 <zzo38> How well does it work to make a key using a 3D printer? Can it be done if you only have the lock and not the original key? I tried to make a copy of a key in the ordinary way but it did not work; maybe it is a copy of a copy.
18:58:00 <kmc> which is the ordinary way?
18:59:06 <Bike> do you just mean a tumbler
18:59:07 <zzo38> By giving the key to the locksmith and having them use their machine to do it.
18:59:37 <kmc> most of thet times I've cut keys by hand, I did it by loading a lock with the appropriate pins and then filing away bits of the key until it turns
18:59:48 <kmc> duplicating a key by hand directly from another key is harder
18:59:53 <kmc> but i've done it
19:01:15 <kmc> and yeah, key copying machines often do a poor job
19:01:37 <nortti> what kind of key was the one you copies by hand?
19:01:56 <kmc> there's nothing quite like a lovingly hand-cut key
19:02:45 <kmc> you're not restricted to the usual key shapes
19:03:05 <kmc> you can cut a perfectly smooth spline between the control points
19:03:25 <kmc> nortti: I don't remember specifically which key I duplicated by hand directly
19:05:02 -!- AnotherTest has joined.
19:05:39 -!- Slereah has joined.
19:06:01 <kmc> mostly I have hand-made master keys for various buildings and tunnels at Caltech
19:06:31 <kmc> without having another master key to work from
19:07:03 <nortti> how did you construct those? actually, how do master keys word in general
19:08:06 <kmc> jeez the word "tumbler" looks weird with an e
19:08:30 <shachaf> kmc: I don't know why it would but whenever I resume my computer from suspend, and also just now when my Internet connection came back, I hear a bell sound.
19:08:30 <kmc> so here's how a pin tumbler lock works: http://i.imgur.com/pEQoB9a.gif
19:09:02 -!- Slereah_ has quit (Ping timeout: 245 seconds).
19:09:06 <zzo38> I want to learn how to make the key from using only the lock, so that I can try to ensure I have a key that works, rather than the copy that doesn't work. I can't use their key, because it doesn't belong to me; but I am authorized to use the lock.
19:09:10 <kmc> in a master key system, some of those columns contain 3 or more metal cylinders, so that it can open at 2 or more different heights
19:10:05 -!- Slereah_ has joined.
19:10:30 -!- MindlessDrone has quit (Quit: MindlessDrone).
19:10:37 <kmc> you can take the lock out of a door, disassemble it (quickly and quietly in the middle of the night in a bathroom or out of the way machine room or something)
19:10:43 <kmc> and measure all the bits with calipers
19:11:00 <kmc> do this for a few different locks in the same master domain; compute the unique key which opens all of them
19:12:19 <Melvar> kmc: I’ve seen a key (that I believe is a master key) that has a row of round indentations in the side close to the top edge.
19:14:05 -!- Slereah has quit (Ping timeout: 264 seconds).
19:16:23 <kmc> I don't know about those specifically, but there are various high-security key systems that have another coding mechanism besides pin heights
19:17:41 <kmc> mostly I know about the Medeco system, which rotates each pin to one of three angles in addition to lifting it
19:17:44 <kmc> http://modernlock.com/medeco.jpg
19:18:41 <kmc> this does more than increase the number of combinations by a factor of 6*3
19:18:46 <kmc> it makes picking much much harder
19:19:35 <kmc> picking depends on getting the lock to a state where there's just one particular part which is prevent it from turning the next little bit
19:20:04 <kmc> but you can't do this when there are multiple orthogonal mechanisms preventing it from turning
19:21:47 <kmc> also it's just hard to manipulate the pin rotations with standard lockpicking tools
19:22:23 <kmc> but i was never very good at lockpicking, anyway
19:22:52 <kmc> and unauthorized medeco keys are not particularly hard to make (claims of the manufacturer notwithstanding)
19:23:35 <kmc> measuring and cutting the rotations is easy, and they must be the same for every key in a master domain
19:25:16 <nortti> interesting, apparently abloy locks are hard to pick (https://en.wikipedia.org/wiki/Disc_tumbler_lock)
19:26:47 <kmc> medeco also assigns a different keyway shape to each customer (from some finite set, presumably) and tries to restrict who can buy blanks of which shape
19:26:56 <kmc> but this is not a very effective measure
19:27:19 <kmc> you can buy blanks from sketchy companies in china that are close enough, and then cut them to fit by hand or using a dremel
19:27:19 <mcpherrin> medeco blank restriction is somewhat effective against casual key-copying
19:27:37 <nortti> aren't abloy locks kind of universal or is my perspective skewed by me being a fin?
19:27:52 <mcpherrin> nortti: that's a scandanavian thing; they're much less available worldwide
19:27:54 <kmc> I think the latter
19:28:05 <kmc> yeah douglass_ was telling me about abloy locks; apparently they are very hard to hax
19:28:15 <zzo38> Even if you cannot use key cutting tools, would you be able to use 3D printers to duplicate it? Probably you would need more sophisticated 3D models of the key in such a case than ordinary keys, but maybe it can still be used sometimes? I don't know how well it would work at all
19:28:16 <kmc> she has more key-fu than i do
19:28:26 <kmc> zzo38: yes, I think you can use 3D printers to duplicate keys
19:28:35 <mcpherrin> abloy 20/70 is my favourite padlock
19:29:12 <kmc> zzo38: you could also use a 3D printer to do a variation of the master key privilege escalation that doesn't require disassembling any locks
19:29:29 <mcpherrin> kmc: you can also copy medeco keys onto plastic sheets easily enough; we used spent gift cards a lot
19:30:12 <kmc> if you have a legit key for some door in the building, you can fabricate a set of ~50 keys to test, and from which ones open the door you can compute the master key
19:30:19 <kmc> mcpherrin: haha, that's awesome
19:30:29 <kmc> are those strong enough to turn the tumbler, or do you use it with a tension tool
19:30:51 <mcpherrin> kmc: you can turn the tumbler with them
19:31:01 <mcpherrin> they're very limited-use though, only opens a lock 3-4 times
19:31:49 <mcpherrin> yeah keyway doesn't matter when you can just force the plastic in and it conforms :p
19:31:58 <zzo38> However, what I am trying to do isn't duplicate a key (since I tried it and it didn't work). I wonder if I can make a working key from only the lock (without breaking, disassembling, or uninstalling it). I tried to copy a working key but the copy didn't work; maybe it is a copy of a copy, or something like that? I don't really know why it doesn't work.
19:32:48 <mcpherrin> zzo38: so it depends how you copy a key: If you're using a key cutter that follows an existing one, you definitely lose fidelity
19:33:04 <kmc> zzo38: the advantage of cutting from another lock loaded with the right pins is that it quantizes the heights to the 10 or so official heights
19:33:15 <kmc> +/- variation in the pins and other components, of course
19:33:21 <kmc> but this prevents the copy-of-a-copy problem
19:33:48 <kmc> there are key duplicating machines that will cut by code rather than just following the profile of an existing key
19:34:00 <mcpherrin> http://www.ricklab.com/keymart/images/ta_lkgks.jpg
19:34:09 <mcpherrin> So you can get a thing like this and use it to read out the code for the key
19:34:28 <kmc> "kwikset" is a hilarious name for a brand of locks :3
19:34:40 <mcpherrin> and then if you have a CNC mill (who doesn't), you can easily CNC a new key perfectly
19:34:44 <kmc> mcpherrin: have you seen https://keysduplicated.com/
19:34:50 <kmc> yeah, I think they use a CNC mill
19:35:05 <mcpherrin> kmc: haha yeah, I was considering writing an open source version
19:35:12 <kmc> they have a HTTP API for ordering keys o_O
19:35:43 <mcpherrin> at least for kwikset keys since that's what I'm most familiar with
19:36:15 <int-e> wait ... they collect key profiles together with addresses? what could possibly go wrong?!
19:36:28 <zzo38> Where would you go to get them to cut by code?
19:36:38 <kmc> zzo38: I'm not sure
19:36:40 <mcpherrin> zzo38: most lock smiths should be able to do that
19:36:45 <int-e> become a locksmith?
19:36:51 <mcpherrin> like a real lock smith, not a teenager in the corner of a hardware store
19:36:55 <kmc> probably a locksmith or a lock supply shop can at least tell you where to go
19:37:09 <mcpherrin> you cna probably order them on the internet
19:37:53 <mcpherrin> You could write a program that generates a picture of the key and uploads it to keysduplicated.com ;P
19:37:55 <FireFly> int-e: they could deliver the keys to your table
19:38:11 <pikhq> Or if you're feeling like a lot of tedium, you could file the key yourself.
19:38:19 <int-e> FireFly: that does sound convenient.
19:38:30 <pikhq> It's not *easy*, but you can just take a file to a key blank.
19:38:39 <kmc> pikhq: I was espousing the virtues of that approach before
19:38:46 <zzo38> mcpherrin: Yes, interesting idea, if you have a good 3D rendering software!!
19:38:48 <kmc> 12:01 < kmc> there's nothing quite like a lovingly hand-cut key
19:38:51 <kmc> 12:02 < kmc> you're not restricted to the usual key shapes
19:38:54 <kmc> 12:03 < kmc> you can cut a perfectly smooth spline between the control points
19:39:40 <kmc> there was a lot of social infrastructure at my school for encouraging frosh to do this kind of thing and teaching them how
19:40:38 <mcpherrin> I should get a key gauge and some blanks
19:40:52 <int-e> even better, take pics of somebody else's keys and have them delivered to your home
19:40:54 -!- hk3380 has quit (Ping timeout: 252 seconds).
19:42:01 <int-e> the terms of service are cute. "You may only use this service to copy keys that you are authorized to copy." and "You may not use this service as a locksmithing service, and agree to use Shloosl only to duplicate existing keys."
19:42:15 <kmc> there was a rule that you shouldn't cut keys from data you haven't measured yourself, even though you could get it from someone else
19:42:29 <kmc> in order to keep alive the skills of obtaining said data
19:44:00 <mcpherrin> hmm kinda tempted to buy a http://www.amazon.com/Lab-LKG001-5-N-1-Key-Gauge/dp/B000ZHB31I
19:45:09 <nortti> https://www.youtube.com/watch?v=sGXTF6bs1IU
19:45:23 <kmc> which was also a kind of secret society / occult knowlegde thing
19:45:40 <kmc> keegan of 2005 would be aghast that I am telling you all of this stuff
19:46:00 <mcpherrin> kmc: key copying is secret society stuff? lolwut
19:46:17 <mcpherrin> kmc: I guess for anybody who hasn't been to maker faire or defcon or ...
19:46:27 <mcpherrin> (or hung out with hardware store employees....)
19:46:40 <int-e> afaiu locksmiths are still unhappy about books being published about lockpicking
19:47:02 <mcpherrin> pfft, that cat is long out of the bag
19:47:12 <kmc> mcpherrin: that was the culture at my university
19:47:42 <kmc> there was one house which did most of the key hacking and tried to keep stuff secret from non-members
19:48:02 <kmc> I mean the general principles of lockpicking etc. are easy enough to find online
19:48:11 <kmc> but things like details of how to make suitable medeco blanks, or that this could even be done
19:48:17 <mcpherrin> kmc: heh, we did the oppsite in univeristy
19:48:18 -!- not^v has joined.
19:48:25 <mcpherrin> flyer bombed campus with instructions on how to do things
19:48:32 <kmc> (I think at the time, Medeco claimed it was impossible, and there wasn't so much information online as now)
19:48:37 <kmc> that's awesome
19:49:20 <kmc> the people who were taking and manufacturing illegal drugs were a lot less discreet than the people making keys :P
19:49:39 <kmc> at the time, campus security didn't really give a shit about the former
19:49:57 <mcpherrin> which was us sneaking into photocopy rooms and making an issue
19:50:12 <kmc> samizdat, good
19:50:32 -!- edwardk has joined.
19:50:38 <mcpherrin> I'm always up for some good samizday
19:50:42 <mcpherrin> I'm always up for some good samizdat
19:51:12 <kmc> hey mcpherrin you should write something like http://subterfugue.org/ but for Linux 3.x and in Rust
19:51:37 <kmc> http://man7.org/linux/man-pages/man7/rtld-audit.7.html is another fun way to screw with programs
19:52:42 <kmc> what's the thing that ais made for nethack TASes again?
19:53:06 <Bike> @google nethack tas tools
19:53:07 <lambdabot> https://gitorious.org/nethack-tas-tools
19:53:40 <kmc> maybe I'm thinking of something else
19:57:48 -!- hk3380 has joined.
20:01:45 <kmc> why do bikes need shoes
20:01:58 <kmc> do you mean tires
20:02:33 <mcpherrin> no, I mean shoes for me to wear while on a bike
20:05:17 <mcpherrin> though tires are like shoes for a bike
20:06:56 -!- password2 has quit (Ping timeout: 252 seconds).
20:10:43 <FireFly> So if you put on tires on the bike, does it get tired?
20:11:37 <int-e> It'd be getting tyred in British English, hth.
20:12:51 <Melvar> Isn’t Tyre a place in Lebanon?
20:13:29 <int-e> That's what Wikipedia just told me.
20:29:17 -!- edwardk has quit (Ping timeout: 252 seconds).
20:46:07 <HackEgo> [wiki] [[5command]] http://esolangs.org/w/index.php?diff=39671&oldid=39665 * Icepy * (+3)
20:46:33 <HackEgo> [wiki] [[5command]] http://esolangs.org/w/index.php?diff=39672&oldid=39671 * Icepy * (+17)
20:52:39 -!- clog has quit (Ping timeout: 252 seconds).
21:02:18 -!- MoALTz__ has joined.
21:03:39 -!- MoALTz has joined.
21:03:50 -!- nooodl has joined.
21:05:25 -!- MoALTz_ has quit (Ping timeout: 258 seconds).
21:05:37 -!- Sprocklem has joined.
21:06:32 -!- MoALTz__ has quit (Ping timeout: 245 seconds).
21:08:24 -!- edwardk has joined.
21:09:54 -!- not^v has quit (Read error: Connection reset by peer).
21:15:47 <HackEgo> [wiki] [[5command]] http://esolangs.org/w/index.php?diff=39673&oldid=39672 * Icepy * (+838)
21:16:38 -!- AnotherTest has quit (Ping timeout: 240 seconds).
21:25:31 <HackEgo> [wiki] [[5command]] http://esolangs.org/w/index.php?diff=39674&oldid=39673 * Icepy * (+25)
21:31:07 <HackEgo> [wiki] [[5command]] http://esolangs.org/w/index.php?diff=39675&oldid=39674 * Icepy * (+40)
21:32:25 <tswett> So I tried to think of ways to make a better lock just now.
21:33:01 <tswett> I thought, what if each key had to be in a specific shape that encodes some data, and then the lock just works by mechanically reading off the data from the key such that it can only turn if the data is correct?
21:33:03 <Bike> just throw bricks at anyone with a lockpick
21:33:13 <tswett> 'Course, that's what a cylinder lock is.
21:33:31 <Bike> or throw bricks at anyone with a brick, since they could use the brick to break a window.
21:34:10 <tswett> The great thing about throwing bricks at people who have bricks is that they're likely to throw bricks at you, making it impossible for them to use those bricks to break windows.
21:34:31 <tswett> What are the known non-brute-force methods of attacking a cylinder lock? Picking and bumping? Are there others?
21:36:21 <myname> on what level of nested wheres does haskell starting to get ugly?
21:36:31 <Bike> rephrase readably plz
21:36:33 -!- douglass_ has joined.
21:36:44 <tswett> On what level of nested wheres does Haskell start to get ugly?
21:36:44 <kmc> douglass_: you may know the answer to <tswett> What are the known non-brute-force methods of attacking a cylinder lock? Picking and bumping? Are there others?
21:37:08 <kmc> http://www.lockwiki.com/index.php/Impressioning#Manipulation-based_Impressioning
21:37:44 <tswett> myname: mho: the maximum indentation level is six stops, assuming each stop is four columns.
21:37:49 <Bike> what if you fill the lock with a magnetic fluid and manipulate it magneticallly until it opens, then freeze the liquid??
21:37:51 <kmc> tswett: amusingly, attacking a lock with "brute force" could mean two different things
21:38:01 <kmc> I assume you don't mean enumerating all the keys
21:38:12 <Bike> you could let the key melt later, so, the perfect crime
21:38:14 <tswett> Right, I mean actual brutish force.
21:38:21 <kmc> but if you have a legit non-master key, you can do a tractable enumeration to get the master key
21:38:24 <kmc> as I described above
21:38:34 <douglass_> I had better luck with it than bumping, but never got it to work on more than 4 pins. Though maybe this, like bumping, is a method that works better with well-made locks, and my practice lock was shit.
21:39:09 <Taneb> I enjoyed the movie
21:39:29 <kmc> tswett: I have a fantasy of a device with an electrical probe that uses time-domain reflectometry to measure pins without removing or disassembling the lock
21:39:34 <kmc> I don't know if this is practical
21:39:45 <int-e> kmc: I liked the idea of looking at keys of several locks that have the same master key
21:40:12 <kmc> int-e: that works sometimes, yeah
21:40:24 <Taneb> Bike, the new X-Men film
21:40:31 <kmc> you have to make some assumptions about how the master keying is done, which don't always hold
21:40:39 <tswett> There should be a law stating that trespassing is legal if you do it in a sufficiently clever and interesting way.
21:40:53 <douglass_> Bike: fun fact, most shapes that will open a lock aren't easily removable from it afterwards
21:41:21 <Bike> countering my attack before i thought of it. very clever, locksmiths
21:41:28 <shachaf> maybe i should acquire a lock and try to pick it
21:41:35 <douglass_> I forgot to smooth out a key I made once. It resulted in an awkward situation.
21:41:58 <int-e> tswett: it already works that way; if you get caught you were not "clever" enough.
21:42:22 <Bike> this reminds me that i don't understand the lock my car uses. the key is a flat bar with a curvy depression down the middle
21:42:50 <tswett> I dunno. You should be able to call off the investigation by filing a report.
21:43:08 <kmc> tswett: you can also imagine noninvasive imaging of the lock, but I'm not sure what kind will work
21:43:16 <pikhq> Bike: Oh, an internal cut key. Neat.
21:43:52 <Bike> oh yes that seems to be it
21:44:01 <HackEgo> [wiki] [[5command]] http://esolangs.org/w/index.php?diff=39676&oldid=39675 * Icepy * (+192)
21:44:15 <pikhq> The mechanism is pretty mundane on those, I'm pretty sure.
21:44:35 <kmc> I think the housing will block x-rays
21:45:03 <kmc> and it's metal so MRI is no good
21:45:07 <kmc> maybe ultrasound
21:45:43 <HackEgo> [wiki] [[5command]] http://esolangs.org/w/index.php?diff=39677&oldid=39676 * Icepy * (-6)
21:46:02 <tswett> You can make some sort of electrical wave inside a conductive material, right?
21:46:12 <tswett> Like, obviously you can transmit signals through wires.
21:46:13 <HackEgo> [wiki] [[5command]] http://esolangs.org/w/index.php?diff=39678&oldid=39677 * Icepy * (+6)
21:46:20 <douglass_> well, it mostly wants to go on the surface
21:46:32 <tswett> Is that the skin effect?
21:46:54 <kmc> you could put a radioactive substance inside the keyway, or bombard the lock with neutrons until it's radioactive
21:47:29 <tswett> Place a neutrino source on one side of the lock and a neutrino detector on the other side.
21:47:52 <HackEgo> [wiki] [[5command]] http://esolangs.org/w/index.php?diff=39679&oldid=39678 * Icepy * (+48)
21:48:12 <pikhq> If you have a neutrino source and detector of nontrivial power then I think that lockpicking is the least of your priorities.
21:48:22 <kmc> you could vibrate a pin up and down very quickly and maybe measure something
21:49:56 <Bike> pikhq probably doesn't like my plan to train a slime mold to climb in and then climb out and reproduce the shape, either
21:50:14 <int-e> pikhq: I imagine that the key lifts pins by some sort of hook that moves along the internal cut.
21:50:31 <tswett> Fill the lock with some sort of gel that sets permanently but remains soft.
21:50:48 <tswett> After the gel sets, pull it out, and it'll return to the shape of the air spaces inside the lock.
21:51:26 <HackEgo> [wiki] [[5command]] http://esolangs.org/w/index.php?diff=39680&oldid=39679 * Icepy * (-225)
21:51:40 <tswett> You know, it must be possible, in theory, to create a "sound camera" that creates an image of where sound is coming from.
21:52:08 <Bike> or my other plan to determine the initial condition of the universal wavefunction by observing cosmic background, and then use this to determine the history of the universe up to the point where the lock is being made
21:53:36 <Bike> or my other other plan to take over ZEVS in a daring military operation, and carefully measure the distortion of ELF waves through the lock
21:54:00 -!- clog has joined.
21:54:30 <tswett> Let's ignore noninvasive imagining for the moment; that's boring. So, locks can be defeated by picking. Use the behavior of the lock to measure the code one pin at a time.
21:55:11 <tswett> Maybe you could make it so that the cylinder turns as long as the pins are in a valid position, but it doesn't turn all the way unless they're all in the correct position.
21:55:13 <FireFly> tswett: if you have access to both sides of the lock, somehow I think picking it is a bit redundant
21:55:49 <tswett> FireFly: not necessarily. I can access both the north side of a building and the south side of a building without being able to access the interior.
21:56:37 -!- mhi^ has quit (Quit: Lost terminal).
21:57:24 <HackEgo> [wiki] [[5command]] http://esolangs.org/w/index.php?diff=39681&oldid=39680 * Icepy * (+47)
22:00:43 -!- mhi^ has joined.
22:05:07 <tswett> I like how the ear behaves as a demultiplexer.
22:05:44 <tswett> The brain can't handle signals with a bandwidth higher than 100 Hz or so, so it takes this 20,000 Hz signal and transforms it into a whole bunch of narrower signals.
22:06:33 <ion> s/demultiplexer/Fourier transform/
22:07:10 <tswett> I wouldn't say it behaves as a Fourier transform. It doesn't completely take audio from the time domain to the frequency domain.
22:07:31 <tswett> If it did, we'd only ever hear one sound, but we'd know its frequency components exquisitely well.
22:09:53 <tswett> It can definitely demultiplex, though. You can, to a degree, listen to multiple simultaneous sounds and make them all out.
22:19:59 -!- Sprocklem has quit (Quit: brb).
22:20:52 -!- Sprocklem has joined.
22:25:26 <HackEgo> [wiki] [[5command]] http://esolangs.org/w/index.php?diff=39682&oldid=39681 * Icepy * (-145)
22:27:13 <Bike> i like how the ear reduces the frequency using a bunch of bones sitting in goop
22:29:06 <M28> int-e, fixed that bug
22:29:13 <M28> int-e, damn it was a hard bug
22:29:17 <M28> to spot, not to fix
22:29:18 -!- Sprocklem has quit (Quit: brb).
22:29:30 <M28> I had typod 0x82, instead of 0x80 in part of the asm code
22:30:02 <tswett> Yup. A mechanical demultiplexer.
22:30:19 <tswett> Does stuff that operates mechanically on sound waves still count as "mechanical"?
22:30:39 <tswett> Like, a whistle produces sound "mechanically", right?
22:30:43 -!- Sprocklem has joined.
22:31:59 <Bike> considering there are no moving parts...
22:32:31 <tswett> And if the word isn't "mechanical", then what is it?
22:32:45 <Bike> what are you trying to oppose it to?
22:33:03 <tswett> Well, as opposed to something without moving parts.
22:33:21 <tswett> Like, say, a maraca definitely produces sound "mechanically". Stuff hits other stuff, making noise.
22:33:59 <tswett> A whistle doesn't have moving parts; it's a resonant chamber along with an amplifier that operates fluidically.
22:34:05 <tswett> There's the word I want. Fluidically.
22:34:06 <HackEgo> [wiki] [[5command]] http://esolangs.org/w/index.php?diff=39683&oldid=39682 * Icepy * (+268)
22:34:37 <HackEgo> [wiki] [[5command]] http://esolangs.org/w/index.php?diff=39684&oldid=39683 * Icepy * (+22)
22:34:47 <pikhq> The ear isn't a "proper" Fourier transform, but it is implementing an approximation of a Fourier-related transform being used in a very similar way to its use in audio compression.
22:35:41 <tswett> It's almost like the human ear was designed not to notice MP3 compression artifacts.
22:36:38 -!- tswett has quit (Remote host closed the connection).
22:36:56 -!- tswett has joined.
22:37:04 <zzo38> If you have multiple copies of a picture or audio with different watermarks, can you then detect them and tamper with them?
22:37:48 -!- Patashu has joined.
22:39:38 <zzo38> The clock without moving parts is sundial (including digital sundials).
22:40:09 <tswett> Now, could you make a computer that operates using sound waves?
22:40:11 <zzo38> But, do you know which timepiece has the most number of moving parts?
22:40:26 <zzo38> tswett: I don't know.
22:40:39 <int-e> zzo38: nice question
22:40:46 <tswett> zzo38: some clock tower?
22:41:09 <tswett> I can see someone arguing that the timepiece with the greatest number of moving parts is the night sky.
22:41:31 <zzo38> tswett: I suppose someone can argue that, but it isn't what I meant.
22:42:09 -!- tswett__ has joined.
22:42:31 <tswett__> Sound waves mostly interact linearly. There are definitely ways of doing non-linear things, though.
22:42:36 <HackEgo> [wiki] [[5command]] http://esolangs.org/w/index.php?diff=39685&oldid=39684 * Icepy * (+158)
22:44:53 <tswett__> The easiest logic gate to implement should be the buffer. Outputs 1 upon receiving 1; outputs 0 upon receiving 0. Amplifies the signal and doesn't pass it in the wrong direction.
22:45:21 <int-e> zzo38: but which of those has the most parts? the one in a museum in Nima perhaps?
22:45:28 -!- tswett has quit (Ping timeout: 258 seconds).
22:45:28 -!- tswett__ has changed nick to tswett.
22:45:42 <zzo38> int-e: I don't know that either.
22:46:10 -!- Sprocklem has quit (Quit: brb).
22:47:06 <HackEgo> [wiki] [[5command]] http://esolangs.org/w/index.php?diff=39686&oldid=39685 * Icepy * (-13)
22:48:26 <HackEgo> [wiki] [[5command]] http://esolangs.org/w/index.php?diff=39687&oldid=39686 * Icepy * (+22)
22:49:17 -!- Sprocklem has joined.
22:49:27 -!- Sprocklem has quit (Changing host).
22:49:27 -!- Sprocklem has joined.
22:49:32 <int-e> tswett: isn't that made by putting two inverters in a row?
22:50:24 <tswett> Making an inverter sounds tough. Make a device that produces sound if and only if it is not receiving sound.
22:51:02 <tswett> Maybe you could use destructive interference.
22:52:39 <tswett> In theory, you could just use a device that always produces sound of the relevant frequency. Stick that together with your input line, and it should just work, as long as everything is of the right length and whatnot.
22:53:12 -!- oerjan has joined.
22:53:32 <tswett> But you have to make the device output sound of the right phase, too.
22:54:14 <tswett> If you could just make some sort of non-linear one-directional amplifier, I think you ought to be able to make everything else.
22:55:56 -!- edwardk has quit (Ping timeout: 252 seconds).
22:56:40 -!- Sprocklem has quit (Quit: Lost terminal).
22:57:00 <MDude> I'd think inverting sound would be easy.
22:57:21 <tswett> MDude: how would you do it?
22:57:24 <MDude> Just swich the coils on the speaker around, and it'll push whne it'd otherwise pull and vise-versa.
22:57:29 -!- Sprocklem has joined.
22:57:46 <tswett> Now do that without any wires.
22:58:29 <MDude> I'd think it'd involve something with the hardware.
22:59:13 <MDude> Like a transformer or something.
22:59:14 -!- Patashu_ has joined.
22:59:27 -!- Patashu has quit (Disconnected by services).
23:00:19 <MDude> I'll try to make something in circuit simulator, but first dinner.
23:00:20 <HackEgo> [wiki] [[5command]] http://esolangs.org/w/index.php?diff=39688&oldid=39687 * Icepy * (-56)
23:01:22 -!- edwardk has joined.
23:02:52 <zzo38> The software "Astrolog" includes some nice features, such as the "timed exposure" feature, and the ability to overlay constellations on the world map; however, this is unfortunately not Free Software. (However, GPL ephemeris software does exist.)
23:03:53 -!- Sprocklem has quit (Quit: brb).
23:04:22 -!- Sprocklem has joined.
23:04:27 -!- Sprocklem has quit (Changing host).
23:04:27 -!- Sprocklem has joined.
23:06:25 <int-e> zzo38: that one should have about 40 billion moving parts. :)
23:06:48 <zzo38> I haven't been at Nima
23:08:53 -!- shikhout has joined.
23:10:44 -!- nooodl_ has joined.
23:11:11 <int-e> https://en.wikipedia.org/wiki/Atomic_clock is another fun candidate (I read as far as "atomic fountain")
23:11:57 -!- shikhin has quit (Ping timeout: 245 seconds).
23:12:10 <int-e> but then we need to discuss moving electrons in the next step, which makes things a bit silly.
23:12:14 <zzo38> Do something like: INSERT INTO WINDOW(TITLE,CONTENT) SELECT 'Horoscope',COMPUTE_HOROSCOPE(ID,GLYPH,JULIANDAY('now'),GET_GEOLOCATION()) FROM PLANETS;
23:12:52 <tswett> Why are you capitalizing identifiers?
23:13:29 -!- nooodl has quit (Ping timeout: 264 seconds).
23:13:38 <zzo38> I just like to do that. You can also put the identifiers in "..." if you prefer.
23:14:36 <tswett> insert into "WINDOW"("TITLE","CONTENT") select 'Horoscope',"COMPUTE_HOROSCOPE"("ID","GLYPH","JULIANDAY"('now'),"GET_GEOLOCATION"()) from "PLANETS";
23:15:18 <zzo38> They are also case-insensitive, so you can use any combinations of uppercase/lowercase letters.
23:16:08 <tswett> THERE SHOULD BE A stereotype THAT computer programmers put emphasis ON ALL non-content words IN THEIR speech.
23:18:29 <FireFly> It is RECOMMENDED that programmers follow RFC 2119 in their everyday speech
23:19:24 <tswett> My "recommendation" is that all "programmers" "put" all "content" "words" inside of "double" "quotation" "marks".
23:23:50 <pikhq> 77 DECLARATION VALUE IS "It is my belief that all programmers should use syntactically valid COBOL".
23:31:36 <oerjan> <kmc> what's the thing that ais made for nethack TASes again? <-- web o' flies?
23:31:36 <MDude> Oh, so the sound needs to be transformed mechanically.
23:32:22 <MDude> What's the medium otherwise? Taunt wire, like in a tin can phone?
23:33:13 <HackEgo> [wiki] [[5command]] http://esolangs.org/w/index.php?diff=39689&oldid=39688 * Icepy * (+89)
23:33:43 <HackEgo> [wiki] [[Language list]] M http://esolangs.org/w/index.php?diff=39690&oldid=39647 * Icepy * (+15) /* Non-alphabetic */
23:33:48 <oerjan> @tell kmc <kmc> what's the thing that ais made for nethack TASes again? <-- web o' flies?
23:34:05 <HackEgo> [wiki] [[Joke language list]] http://esolangs.org/w/index.php?diff=39691&oldid=39663 * Icepy * (-52)
23:34:57 <HackEgo> [wiki] [[Language list]] http://esolangs.org/w/index.php?diff=39692&oldid=39690 * Icepy * (+0)
23:36:34 <HackEgo> [wiki] [[User:Icepy]] http://esolangs.org/w/index.php?diff=39693&oldid=39657 * Icepy * (+77)
23:37:24 <MDude> If that's the case, you might be able to use a mechanical gate like what would be used with rod logic, it'd just have to be sensitive to small/low torque motions.
23:39:07 <HackEgo> [wiki] [[5command]] http://esolangs.org/w/index.php?diff=39694&oldid=39689 * Icepy * (+0)
23:39:33 <HackEgo> [wiki] [[5command]] http://esolangs.org/w/index.php?diff=39695&oldid=39694 * Icepy * (+0)
23:39:42 <MDude> I've tried looking up mechanical amplifierd before, and the best I came up with in terms of analog equipment was something that worked using belts.
23:40:37 <tswett> "Everyone should speak in Haskell string literals."
23:40:48 <tswett> MDude: I was thinking tubes or something.
23:41:17 <Taneb> What about... Tube ON Belts
23:41:46 <MDude> A fluedic transistor I've heard about apparently worked well, but it also seemed inheriently digital.'
23:41:56 <tswett> What do you mean by "digital"?
23:42:16 <tswett> Digital logic is what I'm trying to implement here.
23:43:11 <MDude> I mean it was set up so that the power being fed into it would go out one of two outputs.
23:44:19 <MDude> It was for warer, actually, and relied on vorticies forming into the device.
23:44:49 <MDude> I'll try to look it up, the image explains nicely.
23:45:49 <MDude> Oh, it's right on the Wikipedia page for fluedics: http://en.wikipedia.org/wiki/Fluidics
23:46:29 <MDude> Basically, a pre-existing vortex in the system will perpetuate itself if power is supplied.
23:47:07 <oerjan> <tswett> Place a neutrino source on one side of the lock and a neutrino detector on the other side. <-- i think you might just possibly be confusing neutrons and neutrinos there
23:47:46 <kmc> oerjan: that's the one
23:48:13 <MDude> But that seems to presume one-directional flow, wheras sound would alternate.
23:48:55 <int-e> oerjan: but it's funnier with neutrinos
23:49:15 <MDude> Dunno about making a fluedic rectifier.
23:49:47 <MDude> You'd need really sensitive check valves, I guess?
23:50:14 <MDude> Unless you're going for high amplitude subsonic waves.
23:50:24 <MDude> In which case regular check valves.
23:50:49 <oerjan> <Bike> pikhq probably doesn't like my plan to train a slime mold to climb in and then climb out and reproduce the shape, either <-- i don't see how anyone could possibly not love that hth
23:53:31 <int-e> oerjan: it also reminded me of this: http://www.schlockmercenary.com/2014-03-23
23:56:28 <HackEgo> [wiki] [[5command]] http://esolangs.org/w/index.php?diff=39696&oldid=39695 * Icepy * (+48)
00:01:56 -!- conehead has joined.
00:11:59 <oerjan> <zzo38> If you have multiple copies of a picture or audio with different watermarks, can you then detect them and tamper with them? <-- i think it should be possible to design watermarks so that even after your tampering, they can still detect which originally watermarked copies you used
00:12:20 -!- Phantom_Hoover has joined.
00:12:54 <oerjan> so that if you get leaked copies from two sources, they can tell what the two leaks were
00:13:59 <zzo38> It may allow you to at least detect watermarks, I suppose, regardless if they can still detect it or not.
00:15:38 <HackEgo> [wiki] [[5command]] http://esolangs.org/w/index.php?diff=39697&oldid=39696 * Icepy * (+137)
00:16:07 <oerjan> as for detecting them, in a sense that's just diff'ing the copies.
00:17:05 -!- tswett has quit (Ping timeout: 276 seconds).
00:17:55 <MDude> If the watermarks don't cover the same area, and there are at least three, you could do a triple modular redundancy operation.
00:17:59 -!- tswett has joined.
00:18:41 <oerjan> right, but that would be a bad design if you wanted to detect collusion in leaking
00:19:11 <MDude> Though that'd both be just an easily automated subistitute for cropping and stitching the images, and also really bad practice on the part of the watermarker.
00:19:39 <MDude> I'm not sure what collusion in leaking even means here.
00:20:30 <oerjan> i mean, someone using two or more different copies in order to try to make a copy that doesn't tell where they got the originals from
00:21:29 -!- tswett_ has joined.
00:24:02 -!- tswett has quit (Ping timeout: 245 seconds).
00:24:02 -!- tswett_ has changed nick to tswett.
00:24:58 -!- M28_ has joined.
00:27:50 -!- M28 has quit (Ping timeout: 240 seconds).
00:28:05 -!- mhi^ has quit (Quit: Lost terminal).
00:28:32 -!- M28 has joined.
00:29:04 <zzo38> There is also various kind of compression which is usable; by itself it won't help but may be usable in combination with other things.
00:29:17 -!- M28_ has quit (Read error: No route to host).
00:29:48 -!- tswett_ has joined.
00:33:50 -!- tswett has quit (Ping timeout: 252 seconds).
00:33:50 -!- tswett_ has changed nick to tswett.
00:39:30 <oerjan> looking at several relevant wikipedia pages (Digital watermarking, Copy attack and Canary trap) none of them say anything about detecting this kind of multiple leak :/
00:40:13 <oerjan> of course that doesn't mean none of the systems listed have implemented it
00:40:35 -!- Phantom_Hoover has quit (Quit: Leaving).
00:43:55 -!- tswett has quit (Quit: tswett).
00:46:15 <oerjan> hm oh it's actually simple: just make n non-overlapping watermarks and for each recipient leave _out_ exactly one.
00:46:43 <oerjan> then your tampering cannot remove the ones you don't have the source excluding.
00:47:35 <oerjan> that's good, i was initially thinking it might need exponential amount of data
00:49:00 <oerjan> with that scheme, you can easily do MDude's trick if you have 3 copies, do get one with _all_ the watermarks.
00:50:02 <oerjan> maybe it does require exponential amount of watermark pieces after all.
00:50:34 <MDude> You could remove all the watermarks for which you have examples of images lacking them.
00:50:55 <MDude> But you'd need to be able to tell watermark from non-watermark.
00:51:01 <oerjan> MDude: yes but that would make things _worse_ for hiding your set of sources
00:51:37 <elliott> is it assumed that the watermarks are steganographic?
00:52:14 <oerjan> elliott: i'd think that would be necessary to prevent removing them?
00:52:34 <elliott> right. do such watermarks even survive, e.g. blurring?
00:53:07 <oerjan> there was something in those wikipedia articles about robust vs. fragile watermarks
00:53:12 <MDude> That would sort of make it a non-watermark, though?
00:53:27 <MDude> Since if it's hidden then no one can tell who marked it.
00:53:38 <MDude> Or that is is marked.
00:53:58 <oerjan> MDude: um hidden if you don't have the key to detect it, presumably
00:54:47 <MDude> I was thinking of watermarks on art, which are often there basically as a signature.
00:55:07 <oerjan> this is watermarking for source tracing / traitor tracing
00:55:12 <MDude> If the general audience can't see it, it can't tell them it's yours.
00:55:23 <Jafet> If each combination of watermarks is encrypted separately, there is no way to recover combinations from multiple versions
00:55:29 <oerjan> so basically the opposite of visible signature
00:58:23 <oerjan> Traitor tracing was another wikipedia page i looked at
01:07:01 <oerjan> Jafet: i am failing to interpret the meaning of your line, you may wish to state some assumptions?
01:09:47 <Jafet> I went with the assumptions that I assumed you were assuming
01:11:04 <Jafet> How does getting multiple copies let you mangle the watermark, anyway?
01:12:09 <elliott> e.g. averaging the pixels of two images?
01:12:46 <Jafet> Ideally, that would give you an image with both watermarks.
01:13:03 <zzo38> If you have a lot of copies, you can try to, instead of just averaging, use varying distributions at random.
01:13:44 <zzo38> You can also still apply other filters
01:14:15 <Jafet> You could pick k, then encode several watermarks such that any k images you distribute share at least one watermark. This mark can't be erased by averaging.
01:16:14 <zzo38> You could still try cropping, if you don't care about the entire picture. If you don't even care about the quality, just draw a picture. Some things are not allowed to be photographed, but you can still try to draw the picture. If it is spoken dialogue in a movie or play, you can try to use shorthand.
01:17:57 <oerjan> HackEgo: oh come on, there are plenty of h's in there already!
01:18:00 <MDude> One issue with drawing would be that it wouldn't neccisarily be considered reliable since you could jut draw whatever fake picture easily if you were a fake informant.
01:18:13 <zzo38> You could also add in your own watermarks
01:18:39 <MDude> Plus, your drawing might be detected as yours much like a signature.
01:18:47 <zzo38> MDude: Yes; you would have to assume that that doesn't matter, in addition to having a good quality copy of the picture also doesn't matter.
01:18:57 <Jafet> If you are watermarking classified information, you could replace some of the unimportant words using a language database, modulated by the watermarking signal.
01:19:26 <MDude> Edge detection might work.
01:19:46 <MDude> Only keep the lines that are important.
01:19:59 <zzo38> Jafet: You could do the same to tamper with it I suppose; how well a tamper work depend on the system.
01:20:22 <oerjan> Jafet: that's precisely one of the methods described in wikipedia
01:20:37 <oerjan> well, except for the modulation
01:21:19 <Jafet> I don't remember that, but wikipedia may have left a watermark in my mind
01:22:27 <zzo38> Esolang list of ideas has this: "Language with functions and classes that only draws/ describes pictures, and can be compressed into tight string. And can be used for image compression, so that if a compression program is presented with a picture, it tries to find the programs that draw at least some features on the picture. ... If compression is lossy enough, the result will look artistic in a strange way."
01:22:54 <zzo38> If such compression is possible, maybe it has effect on such thing?
01:23:50 <zzo38> In case of drawing a picture based on another picture, you can also have, many people are making a drawing, again from many different copies, and then many people will put it into the computer.
01:25:34 <oerjan> Jafet: https://en.wikipedia.org/wiki/Canary_trap
01:30:23 <zzo38> Yes, of course, internal conspiracies are another way.
01:30:58 <oerjan> zzo38: this somehow reminds me of once upon a time reading about a compression scheme using self-similar fractals
01:33:06 <oerjan> no later than the 90s, at most
01:33:27 <oerjan> (and no earlier than the 80s, for more obvious reasons)
01:38:26 <kmc> a compression scheme using self-transforming machine elves
01:38:36 <Sgeo> "Web browsers are a deliberately designed engine for remote code execution, a term which strikes fear into the hearts of information security professionals worldwide."
01:39:38 <zzo38> That is one reason to avoid it (although, such a "remote code execution" can be limited; it just happens to be way too complicated in web browsers).
01:40:02 <zzo38> Still, running the program on the server provides better compatibility anyways.
01:42:21 <MDude> I'd say a lot fo that comlpication is because browsers weren't made with that in mind, and in fact are more often than not designed with letting websites "control the user experience" as an unnervingly high priority.
01:42:33 <MDude> Much like the whole idea behind autorun.
01:42:53 <zzo38> Autorun is also bad.
01:43:18 <Sgeo> "tl;dr: use authenticated encryption. use authenticated encryption. use authenticated encryption. use authenticated encryption. use authenticated encryption. use authenticated encryption. use authenticated encryption. use authenticated encryption. use authenticated encryption. use authenticated encryption."
01:43:19 <zzo38> Not only that, but user experience may depend much on user's preferences and on suitability to devices and user interfaces.
01:44:46 <zzo38> Gopher menus are very well designed to be universal regardless of preferences and suitability to devices, however, this might not have necessarily been the intention. Nevertheless, it works well.
01:45:52 <zzo38> Autorun is a bad idea, however it may be useful to have a "autostart" option that can be turned on/off. Some game systems use this.
01:46:52 <zzo38> You can include functions in BIOS and hardware for protection of system when user doesn't want it tampered with by a program.
01:47:32 <Jafet> Use encryption authenticated by diginotar's iranian RAs
01:51:18 <Sgeo> I started watching a Planescape Torment LP but it seems like the person didn't finish
01:56:45 -!- nooodl_ has quit (Quit: Ik ga weg).
01:57:50 -!- MDude has quit (Ping timeout: 276 seconds).
02:00:40 <quintopia> zzo38: what if you got an android device as a gift
02:01:57 <zzo38> quintopia: I might try to reprogram it, if it has a keyboard; if not, I will just give it back
02:02:40 <quintopia> zzo38: so you wouldn't try to play android games?
02:03:27 <zzo38> I would want to reprogram it first, even though it still may run the Android system, I would want to make changes to it since the existing way has several problems.
02:05:29 -!- oerjan has set topic: Happy Towel Day! | PSA: fizzie is running the wiki now, contact him for any problems | brainfuck survey: https://www.surveymonkey.com/s/L82SNZV | https://dl.dropboxusercontent.com/u/2023808/wisdom.pdf http://codu.org/logs/_esoteric/ http://tunes.org/~nef/logs/esoteric/.
02:08:22 <elliott> you know I think that PSA can go by now.
02:09:06 -!- oerjan has set topic: Happy Towel Day! | PFFT! | brainfuck survey: https://www.surveymonkey.com/s/L82SNZV | https://dl.dropboxusercontent.com/u/2023808/wisdom.pdf http://codu.org/logs/_esoteric/ http://tunes.org/~nef/logs/esoteric/.
02:11:17 <fowl> how can person run a wiki
02:11:56 <oerjan> fowl: very stressfully
02:13:20 <tromp_> what does text mode mean in bf survey?
02:13:52 <Sgeo> Here's my BF opinion: Cells should expand to the right, leaving the tape to the left should wrap around to the right-most cell.
02:14:05 <Bike> we already did that joke Sgeo
02:14:11 <Bike> it ended in surreal numbers. do you really want that???
02:14:22 <Bike> i dunno, like.... *waves backwards in time* that way
02:14:50 <oerjan> we'd know when, if Gregor made the log search work again.
02:14:50 <Sgeo> I could stand to learn about surreal numbers
02:14:57 -!- hk3380 has quit (Ping timeout: 252 seconds).
02:15:06 <oerjan> Sgeo: wikipedia is thataway
02:15:45 <zzo38> Survey monkey not so good. Rewrite the survey in SQL.
02:15:50 -!- MDude has joined.
02:16:06 <Sgeo> Why does that statement remind me of Dr. Klaun?
02:16:12 <Bike> imo don't get the book "surreal numbers", it's too thin
02:16:19 <zzo38> I have written some (not released yet) extension which includes some statistics stuff and some other things too
02:16:38 <Sgeo> <zzo38> Survey monkey not so good. Rewrite the survey in SQL.
02:17:23 <fowl> surreal numbers
02:18:08 <oerjan> @google surreal numbers
02:18:08 <lambdabot> http://en.wikipedia.org/wiki/Surreal_number
02:18:09 <lambdabot> Title: Surreal number - Wikipedia, the free encyclopedia
02:18:11 <fowl> yea the wiki page doesnt clear anything up
02:18:20 <fowl> are you all mathematicians or something
02:18:29 * Sgeo wishes he was a mathematician
02:18:45 <Sgeo> Being a pseudomathematician as a kid doesn't count
02:18:49 <Bike> i'm a bikeologist
02:19:07 <Sgeo> Jeez, I was into a lot of pseudo stuff as a kid
02:19:26 <Sgeo> I remember buying a Deepak Chopra book once
02:19:26 <zzo38> I am not really a mathematician but I still do study and interest of mathematics.
02:19:38 <fowl> i was into pseudoephedrine as a kid
02:19:42 <fowl> does that count
02:19:51 <Bike> sgeo was super into pseudo-dionysius.
02:19:57 <zzo38> I have never purchased a book by Deepak Chopra, although I have read some. I have no intention to purchase such book.
02:20:11 <zzo38> (Howveer, I do have intention to read it, sometimes)
02:21:06 <MDude> Did you study pseudopods?
02:21:59 <HackEgo> /hackenv/bin/log: 2: cd: can't cd to /var/irclogs/_esoteric \ grep: ????-??-??.txt: No such file or directory
02:22:35 <zzo38> oerjan: When would they fix that, you expect?
02:22:54 <oerjan> zzo38: i am not sure he is intending to fix it.
02:24:03 <Bike> even a stopped clock
02:24:21 <oerjan> because he hasn't done so yet, and it's been a while.
02:25:15 <oerjan> and because he moved HackEgo to a different server, might mean he doesn't want to use that much resources on a single one.
02:27:19 <zzo38> What if he instead copy the file per day, or something like that?
02:27:53 <Bike> so it would always be ten years behind? how census
02:29:09 <elliott> zzo38: because people don't put work into something they don't care about unless they get paid for it.
02:29:12 <zzo38> No I mean copy yesterday's file to today.
02:31:09 <zzo38> Altneriatively since now SQLite is installed in it, you could even make it into one SQL database file (containing for all channel, date, etc), with one "IRC" table having the columns such as: timestamp, sender, command, channel, message, receiver. (The "receiver" can be applicable to such things as a KICK command.)
02:31:29 <elliott> he won't do that because he doesn't care about it.
02:32:18 <zzo38> How much does it cost?
02:33:29 <elliott> you'd have to ask Gregor for his contracting rate if he's willing to be paid for it at all, but I'm going to guess not significantly under $100/hr.
02:34:33 <coppro> elliott: is FlexibleContexts evil?
02:35:48 <oerjan> my secret conspiracy theory is that Gregor's not making the logs searchable because Aftran has threatened to sue him if he makes it possible to find his messages.
02:36:10 <oerjan> or possibly blackmailing
02:37:04 <oerjan> coppro: FlexibleContext is like the least evil extension which is only nonstandard because they cannot agree how to standardize it, or something,
02:37:44 <zzo38> Anyone who make the copy of the logs will make it searchable, though.
02:38:25 <Gregor> HackEgo and glogbot are no longer run on the same system.
02:38:34 <Gregor> That is the one and only reason why the logs aren't searchable.
02:38:48 <Gregor> They were searchable before because it was trivial to just link them into the right location.
02:39:00 <zzo38> Gregor: That is perfectly understood; the reason is why you didn't put it on the same system.
02:39:41 <Gregor> Because that system was constantly running out of hard disk space so I wanted to move one if its chroots to another system.
02:41:38 <zzo38> But, maybe is useful to have a copy, somehow
02:46:10 <Gregor> And that brings us to elliott's point :)
02:46:50 <zzo38> What if someone else install a copy, though?
02:52:29 -!- hogeyui has quit (Ping timeout: 264 seconds).
02:53:52 -!- hogeyui has joined.
03:10:16 <zzo38> This issue of 2600 contains the De Bruijn sequence for four-digit numbers.
03:10:30 -!- hk3380 has joined.
03:11:25 <zzo38> It also contains a letter that simply says, "Can you see it?" (there is no attachment or anything else like that)
03:12:27 <zzo38> There is also a letter about the most durable telephone number. Is it Hotel Pennsylvania's "PENnsylvania-5000"?
03:14:50 <kmc> why is it durable
03:15:08 <zzo38> They had the same telephone number since 1930, and still do.
03:15:42 -!- pikhq has quit (Quit: Reconnecting).
03:15:55 -!- pikhq has joined.
03:16:31 <shachaf> de bruijn sequences are the best
03:16:50 -!- pikhq has quit (Client Quit).
03:17:58 -!- pikhq has joined.
03:22:56 <zzo38> Since the name of the hotel matches the name of the telephone exchange, it can work very well!
03:32:39 <M28> my brainfuck JIT can run some benchmarks that take ~6 seconds in interpreters, in about 200 ms
03:33:37 <M28> also depends on the benchmark, some have many orders of magnitute in speed increase
03:41:37 <zzo38> I prefer tab separated values rather than comma separated values.
03:44:09 <pikhq> zzo38: Yes, as do I.
03:44:22 <pikhq> The CSV format isn't *that* bad, but TSV is significantly cleaner.
03:47:44 <elliott> M28: how does it compare to esotope-bfc?
03:48:17 -!- MoALTz_ has joined.
03:48:27 <M28> esotope is in python...
03:48:37 <M28> it generates C
03:48:48 <M28> elliott, do you have it there?
03:49:14 <elliott> http://mearie.org/projects/esotope/ oh, maybe it was rewritten
03:50:14 -!- MoALTz__ has joined.
03:50:16 <M28> I don't have a python env here, could you compile this for me to C? http://puu.sh/9027N/3c9c70e514.txt
03:51:10 <zzo38> One thing I don't like about indentation sensitive syntax is that, often in a C program I will add some lines for debugging purpose and those ones are at the left part of the line rather than being in the indented position. Also, there are many kind of ways to indent based on other things, so sometimes it isn't quite indented only by blocks anyways.
03:51:19 -!- MoALTz has quit (Ping timeout: 265 seconds).
03:52:05 <M28> it doesn't do as many optimizations as esotope, though, so we'll see
03:52:41 <M28> the problem is that esotope seems to just run the bf program if it doesn't have any i/o
03:52:51 -!- MoALTz_ has quit (Ping timeout: 252 seconds).
03:52:56 <elliott> because that can fail to terminate
03:53:05 <fowl> zzo38, indenting for something thats not a new scope? :(
03:53:06 <M28> yeah, but you got the idea
03:53:21 <pikhq> It's just able to optimize things quite a lot.
03:53:23 <elliott> "just running" a program but always halting is sort of what optimisation is.
03:53:27 <elliott> M28: anyway, http://sprunge.us/gSeC
03:53:32 -!- MoALTz has joined.
03:53:37 <M28> kk let me see
03:54:10 <zzo38> fowl: Yes, sometimes. One is case statements.
03:54:24 <zzo38> And then there is unindenting too like I described.
03:54:42 <elliott> with clang -O3 -march=native
03:54:58 -!- MoALTz_ has joined.
03:55:13 <elliott> (not that there's all that much genius optimisation you can apply to that C code, probably)
03:55:40 <M28> msvc just removes the whole block
03:55:41 <elliott> heh, though 0.028s with gcc
03:55:44 <M28> and replaces it with the output
03:56:02 <M28> takes 0 ms
03:56:07 <M28> let me open it with IDA
03:56:08 <elliott> I have not heard MSVC being very good at optimisation, so that surprises me.
03:56:33 <M28> it is very good at executing pure functions at compile time
03:56:47 -!- MoALTz__ has quit (Ping timeout: 276 seconds).
03:57:04 <M28> seems that it didn't remove the whole thing
03:57:04 -!- MoALTz__ has joined.
03:58:00 <M28> the compiled code is still somewhat similar to the C code
03:58:29 -!- MoALTz has quit (Ping timeout: 264 seconds).
03:59:23 <M28> right now, my JIT generates the code in 1 pass
03:59:27 -!- MoALTz_ has quit (Ping timeout: 245 seconds).
03:59:37 <M28> so I'll have to switch to generating an AST and all that crap to beat esotope
04:00:06 <M28> (it'll probably be just as fast as esotope, though)
04:00:14 <M28> unless I find some optimization that it doesn't do
04:01:23 -!- MoALTz has joined.
04:03:19 -!- shikhout has changed nick to shikhin.
04:03:53 -!- MoALTz__ has quit (Ping timeout: 265 seconds).
04:09:54 <zzo38> Now I made up a virtual table module of SQLite for making a "horizontal union". For example: CREATE VIRTUAL TABLE VT USING HORIZONTAL_UNION(X ORDER BY X ASC,Y ORDER BY Y DESC);
04:11:43 <zzo38> If X contains (1),(2),(3),(4),(5) and Y contains (1),(10),(100),(1000),(10000) then the result will be (1,10000),(2,1000),(3,100),(4,10),(5,1). Maybe it can be useful for some kinds of statistical calculations, or just if you want arbitrary matching.
04:12:28 <zzo38> Do you know much about statistics?
04:13:47 <Bike> i was a teenage statistic
04:21:31 <zzo38> I would want to have SQL extension to plot various graphics, such as statistical graphics and other things (such as geography and horoscopes).
04:21:32 -!- hk3380 has quit (Ping timeout: 252 seconds).
04:24:19 <coppro> oerjan: is TupleSections not less evil?
04:27:04 -!- Sprocklem has quit (Quit: brb).
04:27:29 -!- Sprocklem has joined.
04:29:14 -!- edwardk has quit (Quit: Computer has gone to sleep.).
04:29:15 -!- MDude has changed nick to MDream.
04:37:06 -!- edwardk has joined.
04:38:30 <oerjan> coppro: also harmless.
04:39:23 <oerjan> well mostly. actually TupleSections could get confusing if you forget an argument in a tuple.
04:42:16 <oerjan> so it's evil for the same reason as the default ghc Monad and Functor instance for functions.
04:43:07 <oerjan> and like making Num instances for functions etc.
04:44:18 <oerjan> i.e. it's cute for pointless golfing but shouldn't be on by default.
04:44:38 <elliott> that argument applies to all operator sections.
04:44:53 <elliott> forgetting a tuple element isn't really a very plausible error
04:45:14 <elliott> and it'll pretty much always give a reasonable type error, I think, since functions and tuples rarely mix
04:45:47 <elliott> you know what's evil about sections? (- 1)
04:46:34 <lambdabot> Could not deduce (GHC.Num.Num (a0 -> t))
04:46:35 <lambdabot> arising from the ambiguity check for ‘e_113’
04:46:35 <lambdabot> from the context (GHC.Num.Num (a -> t), GHC.Num.Num a)
04:46:35 <lambdabot> bound by the inferred type for ‘e_113’:
04:46:35 <lambdabot> (GHC.Num.Num (a -> t), GHC.Num.Num a) => t
04:46:47 <Bike> where did my life go so wrong
04:47:20 <oerjan> it's only a section of your life, don't panic
04:47:51 <oerjan> (especially as it's towel day)
04:51:05 <oerjan> kmc: well possibly not in SF yet
04:54:31 -!- Sprocklem has quit (Quit: bbs).
04:56:59 -!- Sprocklem has joined.
05:03:19 -!- edwardk has quit (Quit: Computer has gone to sleep.).
05:07:08 -!- BeingUntoDeath has joined.
05:09:02 -!- edwardk has joined.
05:09:34 -!- shikhout has joined.
05:10:04 -!- Sprocklem has quit (Quit: brb).
05:12:22 -!- shikhin has quit (Ping timeout: 245 seconds).
05:13:19 -!- oerjan has quit (Quit: Nite).
05:14:13 -!- Sprocklem has joined.
05:22:49 -!- Slereah has joined.
05:23:50 -!- Slereah_ has quit (Ping timeout: 240 seconds).
05:29:48 <zzo38> I have used the unofficial RLA instruction of 6502 to do three things at once: Do a bank switch, clear the carry flag, and clear the accumulator.
05:30:48 <zzo38> The program also uses ANC, ALR, LAX, AXS, and DCP.
05:32:42 <zzo38> ANC saves a byte and two cycles over using AND followed by CLC.
05:34:45 <fowl> zzo38, sometimes i think you're having conversations with people i can't see. this scares me.
05:36:06 <zzo38> Sometimes *I* think I am having conversations with people I can't see, but I generally doubt it.
05:43:41 <HackEgo> ittlycoin ariolameriacoin rumcoin topcoin beckoutcoin selcoin pathcoin ischersetcoin prefcoin explocoin mumcoin recurcoin rhizacoin circumcoin dispathisincoin iabcoin tricoin clccoin chasecoin sartcragcoin
05:44:44 <Bike> conversationswithpeoplecoin
05:48:46 -!- MoALTz has quit (Ping timeout: 265 seconds).
06:21:51 -!- BeingUntoDeath has quit.
06:24:50 <kmc> http://vanbever.eu/pdfs/vanbever_turing_icnp_2013.pdf "BGP has the same computing power as a Turing Machine"
06:25:14 <kmc> are you having a nice time?
06:25:52 <kmc> smoke BGP everyday
06:26:05 <fizzie> A bit tired time, I don't sleep so well in planes. It probably shall pass.
06:31:24 -!- drdanmaku has quit (Quit: Connection closed for inactivity).
06:32:22 <kmc> how long was your flight?
06:32:54 <fowl> didnt know you could use (T[]){t1,t2,t3} in c ._.
06:33:18 <kmc> is that standard or an extension
06:33:56 -!- glogbackup has quit (Remote host closed the connection).
06:34:09 <kmc> I guess it is standard C99, although GCC lets you use it in some additional places
06:34:13 <kmc> http://gcc.gnu.org/onlinedocs/gcc/Compound-Literals.html
06:34:21 <kmc> C is a wacky language
06:40:21 <fizzie> 9 hours, or something like that.
06:40:41 <fizzie> And a 6-hour timezone change.
06:41:35 <fizzie> Finland is +3 (in summer), I guess here must be +9 unless I miscalculated.
06:59:02 -!- Patashu_ has quit (Ping timeout: 240 seconds).
07:04:18 <kmc> did you learn yet about who is the boss of them all since 1992?
07:06:29 -!- password2 has joined.
07:07:26 -!- MoALTz has joined.
07:12:49 -!- conehead has quit (Quit: Computer has gone to sleep).
07:17:11 * kmc discovers the secret Rust attribute that lets you use private stuff from another module
07:25:42 -!- MindlessDrone has joined.
07:42:55 -!- Sorella has quit (Quit: It is tiem!).
07:54:45 -!- Slereah_ has joined.
07:55:04 <kmc> fungot: when all you have is a brain, everything looks like a brain
07:55:05 <fungot> kmc: mr president, commissioner, this report is very clear what is happening in that region of the european union should concern itself with all seas, particularly those not in paid employment. moreover, the commission sets up programmes to ensure that the objectives of the commission and the council to this question to the house.
07:55:46 <kmc> fungots fall on fungot falls
07:55:46 <fungot> kmc: we still take it for granted that there would not be our top priority. when species become extinct, they are not looking for scapegoats but are instead indicting the system.
07:56:19 -!- Slereah has quit (Ping timeout: 240 seconds).
08:00:32 -!- ter2 has quit (Ping timeout: 276 seconds).
08:31:47 -!- Slereah has joined.
08:35:05 -!- Slereah_ has quit (Ping timeout: 252 seconds).
08:55:36 -!- nooodl has joined.
09:21:52 -!- Slereah has quit (Read error: Connection reset by peer).
09:22:07 -!- Slereah_ has joined.
09:26:20 -!- Sprocklem has quit (Ping timeout: 276 seconds).
09:27:56 -!- edwardk has quit (Ping timeout: 258 seconds).
10:03:15 -!- edwardk has joined.
10:17:41 -!- Slereah has joined.
10:19:03 -!- Slereah_ has quit (Ping timeout: 252 seconds).
10:20:17 -!- password2 has quit (Ping timeout: 276 seconds).
10:23:12 -!- Patashu has joined.
10:23:36 -!- nooodl_ has joined.
10:27:17 -!- nooodl has quit (Ping timeout: 252 seconds).
10:36:39 -!- Phantom_Hoover has joined.
10:50:18 -!- Patashu_ has joined.
10:50:18 -!- Patashu has quit (Disconnected by services).
11:06:00 -!- xk002 has joined.
11:07:24 -!- newsham has quit (Quit: leaving).
11:09:01 -!- shikhin has joined.
11:12:23 -!- shikhout has quit (Ping timeout: 252 seconds).
11:24:03 -!- hk3380 has joined.
12:13:23 -!- xk002 has quit (Ping timeout: 276 seconds).
12:16:45 -!- MindlessDrone has quit (Quit: MindlessDrone).
12:30:53 -!- mhi^ has joined.
12:32:10 -!- yorick has joined.
13:11:00 -!- boily has joined.
13:11:18 <Taneb> Is it possible to fake <marquee> in CSS3?
13:16:22 <Taneb> boily, can you give me a pointer without too much spoilers?
13:16:30 -!- Sorella has joined.
13:20:14 <boily> Taneb: you have to think like a video animator, with @keyframes.
13:20:51 <boily> a nice demo, with transition effects → http://media02.hongkiat.com/marquee-css3-animation//demo/index.html
13:20:55 <Taneb> Oh yeah, bouncing marquees are a thing
13:26:26 -!- Patashu_ has quit (Ping timeout: 252 seconds).
13:27:44 -!- edwardk has quit (Quit: Computer has gone to sleep.).
14:02:55 -!- Sgeo has quit (Read error: Connection reset by peer).
14:13:16 <int-e> is there anybody else here who feels that adding animations to CSS is wrong?
14:13:31 -!- hk3380 has quit (Ping timeout: 258 seconds).
14:14:28 <int-e> ("only" in the form of interpolation, but still.)
14:21:11 <mroman> two people just recently submitted bug reports for Burlesque
14:27:19 <mroman> int-e: I rather prefer CSS animations than Flash
14:31:10 -!- xk002 has joined.
14:32:12 <int-e> mroman: The entire notion that web sites (which are not games or clever data browsers that use the time dimension to display data, or actual videos) need animations is wrong in my eyyes (literally more often than not)
14:33:13 <int-e> (I know that I'm not going to win any fight against this trend that has already gone most of the way, but I can still complain.)
14:34:13 <int-e> (I found that I even find Firefox' "smooth scrolling" feature annoying. I can switch that off though.)
14:34:25 <boily> smooth scrolling? bletch!
14:35:14 <int-e> it's just another kind of smooth transition that developers seem to believe users like so much.
14:36:09 <nortti> it is actually quite amazing how much stops working if you disable js
14:36:32 <elliott> it's amazing how much stops working if you disable http
14:36:51 <int-e> (coming from phones and tablet where input lacks precision, so you have to extrapolate what you are going to achieve using visual feedback; and suddenly, smooth scrolling becomes a boon.)
14:37:18 -!- ter2 has joined.
14:37:31 <nortti> I mean things that have no right to contain js, such as a download link that launches a script that parses a json embedded in thw page and the redirects to the file
14:37:39 <int-e> elliott: Ah but you can still browse "the web": there are still a couple of gopher sites out there.
14:39:34 <nortti> and then there are the infinite-scrolling webpages http://xkcd.com/1309
14:43:10 <int-e> Oh I'll try disabling layout.css.prefixes.{transitions,animations} in FF.
14:47:48 <mroman> int-e: well... the "web" has become a plattform for desktop applications too
14:48:07 <mroman> which kinda steers to being able to write os-independent applications for "the web"
14:48:41 <mroman> I start to think of browsers as virtual machines like .NET/JVM
14:49:25 <mroman> It's just not just hypertext anymore.
14:49:33 * int-e mentally moves mroman from the "undecided" into the "problem" bin ;-)
14:49:58 <nortti> unfortunatelly, some people tend to not realize what is an application and what is a hypertext page
14:55:17 -!- shikhin has quit (Ping timeout: 245 seconds).
15:01:10 <int-e> Another late realization is that tracking URL shorteners are perceived as a feature. E.g. "But all things being equal, it makes sense to select [an URL shortener] that provides tracking."
15:03:59 <int-e> source: http://searchengineland.com/analysis-which-url-shortening-service-should-you-use-17204 (note the domain name, it goes with the territory)
15:04:54 <int-e> This - research? - was prompted by a visit to the bit.ly front page yesterday.
15:07:10 <nortti> and this is why I like dy.fi; no tracking that I know of and forwards will go away after month on disuse (I think)
15:11:34 -!- oerjan has joined.
15:13:24 -!- hk3380 has joined.
15:25:38 -!- tswett has joined.
15:26:41 -!- M28 has quit (Ping timeout: 264 seconds).
15:28:32 -!- M28 has joined.
15:40:18 -!- edwardk has joined.
15:42:03 -!- conehead has joined.
15:52:38 -!- MDream has changed nick to MDude.
16:14:02 -!- M28 has quit (Ping timeout: 245 seconds).
16:15:03 -!- oerjan has quit (Quit: leaving).
16:15:58 -!- M28 has joined.
16:20:25 -!- realz has quit (Ping timeout: 255 seconds).
16:21:10 -!- realz has joined.
16:25:16 -!- tswett_ has joined.
16:27:49 -!- tswett has quit (Ping timeout: 252 seconds).
16:27:49 -!- tswett_ has changed nick to tswett.
16:35:03 -!- tromp__ has joined.
16:37:32 -!- clog_ has joined.
16:38:16 -!- edwardk has quit (Quit: Computer has gone to sleep.).
16:39:38 -!- erdic_ has joined.
16:44:04 -!- clog has quit (*.net *.split).
16:44:04 -!- erdic has quit (*.net *.split).
16:44:04 -!- tromp_ has quit (*.net *.split).
16:44:14 -!- erdic_ has changed nick to erdic.
16:45:20 -!- blitter64 has joined.
16:46:19 <mroman> damn. no I pushed one of my own warriors from the hill :(
16:48:37 <boily> you pushed one of your now warriors?
16:57:11 -!- edwardk has joined.
16:59:30 <kmc> mroman: it's a virtual machine and an operating system
17:00:10 <kmc> browsers have their own schedulers, memory managers, network stacks, graphics engines, UI toolkits, compilers, dev tools
17:12:09 <mroman> I wouldn't be surprised if Browsers had more source code than operating systems
17:12:50 <kmc> defining "operating system" is a tricky business
17:13:06 <kmc> the non-modular part of the Linux kernel is like 50,000 lines
17:13:13 <kmc> the set of all packages in Debian is probably hundreds of millions
17:13:17 <scoofy> linux kernel 3.6 has 15.9 million lines of code
17:13:18 <kmc> if not billians
17:13:20 <kmc> billions too
17:13:36 <kmc> i usually take "operating system" to mean something much broader than just a kernel
17:13:40 <kmc> but it's fuzzy
17:13:44 <scoofy> windows server 2003 is 50 million lines of code
17:15:09 <scoofy> firefox is about 15 million sloc
17:16:37 -!- metasepia has joined.
17:16:48 <kmc> Servo is only 100,000 SLoC but it doesn't do most of the browsery things yet :)
17:17:54 -!- tswett_ has joined.
17:18:07 <kmc> I'm writing the new HTML parser, which is about 4,000 non-blank lines and not done yet
17:18:19 <kmc> but I think it will end up substantially smaller than any other browser-quality HTML parser
17:18:26 <kmc> at least the tokenizer part is like 6x smaller than others
17:18:41 <Bike> how long is it after macroexpansion, tho :P
17:18:53 <mroman> hm. IT's actually better not to throw spl 0 bombs o_O
17:21:44 -!- tswett has quit (Ping timeout: 258 seconds).
17:22:59 <Jafet> Web browsers are operating systems
17:23:19 <int-e> firefox is the new emacs?!
17:23:40 <Bike> at least javascript has lexical scope
17:23:43 * int-e looks for a coffeemaker plugin
17:23:44 <Melvar> That seems like actually a pretty nice analogy.
17:24:11 <Bike> kmc: ensure that servo has M-x psychoanalyze-pinhead
17:24:13 -!- MindlessDrone has joined.
17:24:27 <boily> int-e: I have pentadactyl installed on my firefox. no emacs for me! :D
17:24:43 <int-e> there actually is one called "Morning Coffee", but it's about opening routine websites in tabs
17:24:51 <int-e> (I thought firefox had tab group bookmarks?)
17:24:55 <Melvar> Dangit, I was going to observe that there is a counterpart to evil-mode and the like at least.
17:25:08 <nortti> int-e: there is a htcpcp plugin"
17:25:23 -!- tswett has joined.
17:25:49 -!- tswett_ has quit (Ping timeout: 240 seconds).
17:25:57 <int-e> (I only looked for "official" addons)
17:27:00 <int-e> htcpcp is a good joke at least. "The implementation of this should be via a plugin API for beverages in general, so that the Download Manager can brew a nice cup of tea [...]"
17:27:56 -!- nooodl__ has joined.
17:30:43 -!- nooodl_ has quit (Ping timeout: 240 seconds).
17:31:27 -!- tswett has quit (Remote host closed the connection).
17:31:29 -!- clog_ has quit (Quit: ^C).
17:31:43 -!- clog has joined.
17:38:11 -!- tswett has joined.
17:41:14 -!- newsham has joined.
17:41:21 <kmc> shachaf: I'm having a lot of fun hacking on rustc so far
17:41:33 <kmc> it's a lot less scary than GHC, although I'm having trouble putting my finger on why
17:41:48 <kmc> maybe it's just that I know a bunch of the core rust developers and they're usually on IRC
17:48:46 <int-e> kmc: do the rustc sources contain the term "zonk"? (grep -r zonk . | wc -l in ghc's compiler subdirectory returns 907... and I still don't know what SPJ means when he talks about zonking.)
17:49:01 <int-e> (But I never asked.)
17:50:38 <olsner> it's something that ghc does to types, iirc
17:50:54 <kmc> int-e: nope
17:51:03 <kmc> they contain plenty of other weird shit though
17:51:10 <kmc> some of which has been documented by https://twitter.com/horse_rust
17:53:59 -!- xk002 has quit (Ping timeout: 252 seconds).
17:56:02 -!- conehead has quit (Quit: Textual IRC Client: www.textualapp.com).
17:56:41 <olsner> could be something with <> characters that got stripped by twitter?
17:57:06 <Bike> http://charlie.su/screen_shot_2014_04_20_at_12.01.43_pm-e79630c4f193a5.png No
18:03:37 -!- hk3380 has quit (Ping timeout: 245 seconds).
18:08:02 -!- shikhin has joined.
18:11:35 -!- tswett_ has joined.
18:14:14 -!- tswett has quit (Ping timeout: 252 seconds).
18:14:14 -!- tswett_ has changed nick to tswett.
18:16:04 -!- hk3380 has joined.
18:25:53 <zzo38> Is there pinball simulation which you would write the programming for what happen when various triggers are hit and displaying score and so on are in 6502 machine codes?
18:26:31 <Bike> yes, smoothed particle hydrodynamics should be adequate to represent this
18:43:37 -!- M28 has quit (Ping timeout: 245 seconds).
18:45:35 -!- M28 has joined.
18:48:15 -!- edwardk has quit (Ping timeout: 252 seconds).
18:48:58 -!- Sprocklem has joined.
18:54:22 -!- nooodl__ has changed nick to nooodl.
19:02:37 -!- conehead has joined.
19:11:45 -!- augur has quit (Ping timeout: 258 seconds).
19:15:35 <boily> playing terrafirmacraft. I just set fire to the whole thing...
19:18:53 -!- xk002 has joined.
19:22:44 -!- Patashu has joined.
19:22:55 <zzo38> I want to have some SQL extension for internet connection, both inbound and outbound connection. I don't know very well internet-base programming with C though it looks confusing to me. How would I do it?
19:39:19 -!- augur has joined.
19:39:51 -!- MindlessDrone has quit (Quit: MindlessDrone).
19:42:47 <mroman> zzo38: you wanna extend SQL with sockets?
19:52:08 -!- TodPunk has quit (Quit: This is me, signing off. Probably rebooting or something.).
20:03:04 -!- ais523 has joined.
20:03:36 -!- nortti has changed nick to hvidiecat.
20:03:52 -!- hvidiecat has changed nick to nortti.
20:04:29 -!- nortti has changed nick to hvidie.
20:05:22 -!- hvidie has changed nick to nortti.
20:13:46 -!- tswett has quit (Quit: tswett).
20:18:41 -!- drdanmaku has joined.
20:24:12 -!- hk3380 has quit (Ping timeout: 258 seconds).
20:25:28 -!- TodPunk has joined.
20:26:41 -!- stuntaneous has joined.
20:27:31 -!- hk3380 has joined.
20:30:35 -!- glogbackup has joined.
20:30:46 -!- mhi^ has quit (Quit: Lost terminal).
20:34:43 -!- glogbackup has quit (Ping timeout: 240 seconds).
20:35:06 -!- mhi^ has joined.
20:36:38 -!- Sgeo has joined.
20:42:41 -!- MoALTz_ has joined.
20:46:04 -!- MoALTz has quit (Ping timeout: 252 seconds).
20:49:56 -!- conehead has quit (Quit: Computer has gone to sleep).
21:04:15 -!- oerjan has joined.
21:23:32 <Taneb> It occurs to me that after next month I'll be living in a house with its own IRC channel
21:24:02 -!- Patashu has quit (Ping timeout: 245 seconds).
21:29:57 -!- sebbu has quit (Ping timeout: 252 seconds).
21:35:33 <Taneb> I enjoyed it, possibly due to my position as someone who doesn't really care about X-Men that much
21:37:13 <Taneb> However, it did feel a lot "Here's a bad thing, here's how we're going to fix the bad thing, we're fixing the bad thing, the bad thing is fixed"
21:37:50 <Taneb> That may put you at a disadvantage.
21:38:00 <Phantom_Hoover> (and even then i could tell the continuity was fucked)
21:38:08 -!- blitter64 has quit (Ping timeout: 252 seconds).
21:38:14 <Taneb> Oh god yeah, but that's true for the entire franchise.
21:39:47 -!- blitter64 has joined.
21:43:54 <Phantom_Hoover> i don't mean it was fucked wrt to the other films, i mean it was fucked in its own reference frame
21:45:01 <Taneb> Other than the time travel mechanic being ridiculous
21:46:16 <Phantom_Hoover> well i mean, future-wolverine remembers a bunch of interesting x-men stuff happening in his past
21:46:40 <Phantom_Hoover> but in his past peter dinklage built a robot in the 70s that killed everyone so how does he remember anything else
21:47:09 <Taneb> The robots didn't get going until the 2020s
21:48:10 <Taneb> On another note, I'm watching the elections coverage and it is making me sad
21:49:03 <ais523> oh, are the results coming out now?
21:49:13 <Taneb> North-Easts are out, at least
21:49:24 <Taneb> (2 labour, 1 ukip)
21:49:35 <ais523> hmm, not much of a change yet
21:49:40 <ais523> which is probably good
21:49:48 <Taneb> ais523, sharp rise in UKIP
21:49:57 <ais523> but only 4 results have been called
21:50:07 <Bike> something called "National Front" won a bunch of elections in France.
21:50:18 <Phantom_Hoover> on the bright side nick griffin fucked up the hashtag on his tweet after he lost: https://twitter.com/nickgriffinmep/statuses/470672756724748288
21:51:27 <Taneb> Well, until this election, the candidate I voted for lost outright
21:51:57 <ais523> I'm hoping that UKIP get lib-dem-ized
21:52:21 <ais523> i.e. a fringe party that starts looking serious, inadvertently ends up in power and gets completely humiliated as a result
21:52:42 <Phantom_Hoover> ukip are doing well because people with no political views beyond 'i'm vaguely annoyed at the current system' will vote for anyone promising a new alternative
21:53:17 <ais523> I actually liked the lib dems though :-(
21:53:21 <Phantom_Hoover> the european elections won't do that because nobody actually knows what their MEP does, and ukip sure as hell aren't going to tell them
21:53:39 <elliott> Phantom_Hoover: are you seriously suggesting people switched from lib dem to ukip?
21:53:48 <ais523> Phantom_Hoover: I do, I got a bunch of election propaganda because I've written to my MEPs in the past
21:53:56 <elliott> I rather suspect ukip is getting their votes from ex-tories instead
21:53:57 <ais523> elliott: I think he is, and even though it makes no political sense, I can believe it
21:54:19 <Phantom_Hoover> elliott, ukip has gained a lot of ground from labour too, from what i've read
21:54:39 <ais523> well the newspapers were spinning this as ukip vs. labour
21:54:50 <ais523> are there any scotland-specific EU parties, btw?
21:55:02 <ais523> like, do the SNP run in the EU elections
21:55:16 <elliott> Phantom_Hoover: labour I can believe too
21:55:20 <elliott> but lib dem seems like an entirely different crowd
21:56:37 <ais523> elliott: well the political situation in Birmingham University is mostly lib dem versus labour
21:56:57 <ais523> although I supported the Conservatives (up until the last election), I was a huge anomaly
21:57:42 <Taneb> I try to avoid the people who capital-c Care about politics, but in my social bubble it's seemed Lib Dems vs Green
21:57:54 <Taneb> That's probably more representative of my social bubble than of York
21:57:59 <ais523> Taneb: that says a lot about how the maintream parties are getting on, really
21:58:15 -!- nooodl_ has joined.
21:59:14 <ais523> although, the UK really needs three serious parties to avoid becoming like the US
21:59:19 <ais523> and atm, I'm not sure it has /any/ serious parties
22:01:52 <Phantom_Hoover> the US has two parties because its political system is a joke, not the other way round
22:01:58 -!- nooodl has quit (Ping timeout: 252 seconds).
22:02:15 <elliott> Phantom_Hoover: more like it's a feedback loop between the two
22:02:30 <Bike> i was going to say, there's that whole thing about the voting system causing two party lockin
22:02:57 <elliott> Bike: and two parties having strong incentive not to fix the system in turn
22:03:08 <Phantom_Hoover> a friend summarised up the US as "a democracy designed by people who were terrified of democracy"
22:03:33 <Phantom_Hoover> hence the stalemate-ridden legislature, the 3 cogs of government each smoothly locking the others in place, etc.
22:03:47 <Bike> i looked up the procedure for running a third party in my state once, basically you have to pay ten thousand dollars and get a bazillion signatures. dems and republicans don't have to obv
22:05:01 -!- sebbu has joined.
22:05:06 <Taneb> I didn't realise you were in the US, Bike
22:05:35 -!- sebbu has quit (Changing host).
22:05:35 -!- sebbu has joined.
22:05:40 <Bike> i moved here from luxembourg, shouldn't everyone know this by now
22:06:03 <MDude> Well with the cogs of government, only the legislature is particularly democratic.
22:06:34 -!- nooodl_ has changed nick to nooodl.
22:06:38 <Bike> the legislature with 90% encumbency
22:06:40 <MDude> The administraation has the president, who's elected, but most of it consists of the cabinet.
22:06:49 <ais523> Bike: in the UK, if you want to run as a candidate, you have to pay quite a bit of money but it's refunded if you get a reasonable percentage of the vote
22:07:04 <Taneb> £500 and 5% for Parliament
22:07:08 <Bike> do you have to do that even if you're the tories
22:07:15 <MDude> As oppossed to the supreme court, which is unelected and set for life.
22:07:22 <Taneb> Bike, I believe you do
22:07:30 <Bike> well there you go then.
22:07:33 <ais523> yeah but the tories always get the refund
22:07:48 <ais523> occasionally they don't in a particular constituency, but it makes the news
22:07:49 <Taneb> It's not like they can't afford it
22:08:03 <ais523> because it's so unusual
22:08:03 <MDude> I would think primaries would get democrats and republicans past any hurdles with fees.
22:08:22 -!- ais523 has quit.
22:08:31 <MDude> Just decide whoever you want and then you have a huge party putting cash behind whatever canidate it is.
22:08:54 <Phantom_Hoover> i remember an interview with some ukip guy saying how they were going to break into scotland, and the interviewer was choking back laughter for the whole thing because ukip to date haven't even come close to recouping their £500 here
22:10:59 <pikhq> It's honestly kinda weird that primaries are government-regulated...
22:11:14 <pikhq> At least in theory, primaries are a purely internal affair of the political parties.
22:11:25 <elliott> the party system seems to be weird everywhere.
22:11:28 <MDude> Yeah, I dunno what's up with that.
22:11:54 <Phantom_Hoover> pikhq, well because the two parties are the government, right?
22:12:01 <pikhq> But in general you become a member of a political party at the time you register to vote.
22:12:49 <pikhq> elliott: True facts.
22:13:33 <Taneb> It seems that re. parties, US has the opposite problem to Australia
22:14:09 <pikhq> But then the US has numerous other really weird electoral problems.
22:14:43 <pikhq> Such as the fact that the actual election of a president is by a handful of electoral college members.
22:14:46 <Taneb> Australia's system seems to be quite favourable to small parties in general, while still being harsh on individual small parties
22:18:39 <Taneb> East Midlands results being announced
22:19:04 <Taneb> UKIP 2, Con 2, Lab 1
22:19:32 <oerjan> > indexed (backwards each) . indices odd %~ (*2) $ [1,2,3]
22:19:34 <lambdabot> Couldn't match type ‘(->) s0’ with ‘Data.Functor.Identity.Identity’
22:19:34 <lambdabot> Expected type: [f b1] -> Data.Functor.Identity.Identity (f t)
22:19:34 <lambdabot> Actual type: Control.Lens.Type.Optical (->) (->) f s0 t a0 b1Couldn't matc...
22:19:34 <lambdabot> -> Data.Functor.Identity.Identity a2)
22:20:31 <Taneb> oerjan, you want "indexing"
22:21:25 <oerjan> > indexing (backwards each) . indices odd %~ (*2) $ [1,2,3]
22:21:27 <lambdabot> -> Data.Functor.Identity.Identity a1)
22:21:27 <lambdabot> -> p0 t0 (Data.Functor.Identity.Identity b)’
22:21:27 <lambdabot> with actual type ‘[i0]’Couldn't match expected type ‘GHC.Arr.Arr...
22:21:27 <lambdabot> with actual type ‘a0 -> GHC.Types.Bool’
22:22:35 <Taneb> oerjan, traverse rather than each
22:22:54 <oerjan> hm maybe. why would that matter?
22:23:41 <oerjan> actually it works in ghci
22:24:31 <oerjan> > indexing (backwards traverse) . indices odd %~ (*2) $ [1,2,3,4]
22:24:33 <lambdabot> -> Data.Functor.Identity.Identity a1)
22:24:33 <lambdabot> -> p0 t0 (Data.Functor.Identity.Identity b)’
22:24:33 <lambdabot> with actual type ‘[i0]’Couldn't match expected type ‘GHC.Arr.Arr...
22:24:33 <lambdabot> with actual type ‘a0 -> GHC.Types.Bool’
22:24:55 <Taneb> > indexing (backwards traverse) . indices odd *~ 2 $ [1,2,3,4]
22:24:57 <lambdabot> -> Data.Functor.Identity.Identity a0)
22:24:57 <lambdabot> -> p0 t0 (Data.Functor.Identity.Identity b)’
22:24:57 <lambdabot> with actual type ‘[i0]’Couldn't match expected type ‘GHC.Arr.Arr...
22:24:57 <lambdabot> with actual type ‘a1 -> GHC.Types.Bool’
22:25:12 <oerjan> oh right that's even shorter
22:25:18 <oerjan> but still no deal with lambdabot
22:25:32 <oerjan> int-e: why doesn't lambdabot handle this :(
22:25:49 <Taneb> > (indexing (backwards traverse) . indices odd) *~ 2 $ [1,2,3,4]
22:25:50 <lambdabot> -> Data.Functor.Identity.Identity a0)
22:25:51 <lambdabot> -> p0 t0 (Data.Functor.Identity.Identity b)’
22:25:51 <lambdabot> with actual type ‘[i0]’Couldn't match expected type ‘GHC.Arr.Arr...
22:25:51 <lambdabot> with actual type ‘a1 -> GHC.Types.Bool’
22:26:17 <Taneb> > (indexing (backwards traverse) . indices odd :: Traversal' [Integer] Integer) *~ 2 $ [1,2,3,4]
22:26:18 <lambdabot> Couldn't match expected type ‘(GHC.Integer.Type.Integer
22:26:18 <lambdabot> -> p0 GHC.Integer.Type.Integer (f GHC.Integer....
22:26:18 <lambdabot> with actual type ‘[i0]’Couldn't match expected type ‘GHC.Arr.Arr...
22:26:18 <lambdabot> with actual type ‘a0 -> GHC.Types.Bool’
22:27:15 <oerjan> :t indexing (backwards traverse) . indices odd
22:27:16 <lambdabot> Couldn't match expected type ‘a -> p0 a1 (f b)’
22:27:16 <lambdabot> Possible cause: ‘indices’ is applied to too many arguments
22:28:16 <Taneb> > (indexing (backwards traverse) . Control.Lens.indices odd) *~ 2 $ [1,2,3,4]
22:28:17 <lambdabot> Not in scope: ‘Control.Lens.indices’
22:28:17 <lambdabot> ‘Control.Lens.indexed’ (imported from Control.Lens),
22:28:17 <lambdabot> ‘Control.Lens.inside’ (imported from Control.Lens),
22:28:17 <lambdabot> ‘Control.Lens.iuses’ (imported from Control.Lens)
22:30:18 <oerjan> @ask int-e Why doesn't lambdabot have Control.Lens.indices twh
22:35:26 -!- yorick has quit (Remote host closed the connection).
22:36:22 <zzo38> I have now released a SQLite extension library. If any of you use SQLite, maybe it can be useful for you in some cases.
22:36:36 <elliott> oerjan: because Array, I think
22:36:46 <zzo38> gopher://zzo38computer.org/1sqlite http://zzo38computer.org/sql/sqlite.zip http://zzo38computer.org/sql/sqlite.txt
22:36:47 <shachaf> oerjan: import Control.Lens as Lens
22:36:50 <lambdabot> (Indexable i p, Applicative f) => (i -> Bool) -> Optical' p (Indexed i) f a a
22:37:05 <elliott> oerjan: yeah, I hid indices because
22:37:13 <elliott> arguably the lens one is more useful
22:38:22 -!- M28 has quit (Ping timeout: 258 seconds).
22:38:40 <oerjan> anyway, i got it tested and my SO comment made
22:39:12 -!- M28 has joined.
22:39:15 <Taneb> You do realise GHCi exists?
22:40:41 <oerjan> Taneb: i am a haskell exhibitionist
22:41:01 <oerjan> (and i have winghci open in another window already)
22:54:14 <zzo38> Some people say that SQL is not a real programming language, but I don't agree with that!!!
23:06:23 <zzo38> Some pinball game seem to be designed under the assumption that a free game is worth a lot more than anything else. I disagree; I think that it is usually not worth much at all but that precisely how much a free game is worth depends on the situation.
23:08:36 -!- mhi^ has quit (Quit: Lost terminal).
23:09:50 -!- nooodl has quit (Quit: Ik ga weg).
23:10:59 <int-e> @type Control.Lens.indices
23:11:00 <lambdabot> (Indexable i p, Applicative f) => (i -> Bool) -> Optical' p (Indexed i) f a a
23:11:14 <int-e> oerjan: it's there, but array came first.
23:11:50 <oerjan> > Control.Lens.indices
23:11:51 <lambdabot> Not in scope: ‘Control.Lens.indices’
23:11:51 <lambdabot> ‘Control.Lens.indexed’ (imported from Control.Lens),
23:11:51 <lambdabot> ‘Control.Lens.inside’ (imported from Control.Lens),
23:11:51 <lambdabot> ‘Control.Lens.iuses’ (imported from Control.Lens)
23:12:34 <oerjan> having to guess module abbreviations is annoying, though.
23:12:56 <oerjan> > Control.Lens.indexed
23:12:57 <lambdabot> No instance for (Data.Typeable.Internal.Typeable b0)
23:12:57 <lambdabot> arising from a use of ‘M678612761240765152220706.show_M6786127612407651522...
23:12:57 <lambdabot> The type variable ‘b0’ is ambiguous
23:12:57 <lambdabot> Note: there are several potential instances:
23:12:57 <lambdabot> instance Data.Typeable.Internal.Typeable Data.Dynamic.Dynamic
23:13:01 <lambdabot> Perhaps you meant ‘chars’ (imported from Data.ByteString.Lens)
23:13:25 <oerjan> > Control.Lens.indexed
23:13:27 <lambdabot> No instance for (Data.Typeable.Internal.Typeable b0)
23:13:27 <lambdabot> arising from a use of ‘M21213410986786399420731.show_M21213410986786399420...
23:13:27 <lambdabot> The type variable ‘b0’ is ambiguous
23:13:27 <lambdabot> Note: there are several potential instances:
23:13:27 <lambdabot> instance Data.Typeable.Internal.Typeable Data.Dynamic.Dynamic
23:13:33 <int-e> so you have to know that it does import qualified Control.Lens as Lens
23:13:41 <lambdabot> No instance for (Data.Typeable.Internal.Typeable
23:13:41 <lambdabot> Control.Lens.Internal.Indexed.Indexed)
23:13:41 <lambdabot> arising from a use of ‘M462241670695368513520745.show_M4622416706953685135...
23:13:41 <lambdabot> The type variables ‘i0’, ‘p0’ are ambiguous
23:13:51 <lambdabot> What lambdabot has in scope is at <http://code.haskell.org/lambdabot/State/L.hs>
23:13:52 <oerjan> ...but Control.Lens.indexed _does_ work...
23:15:21 <int-e> > Control.Lens.indices
23:15:22 <lambdabot> No instance for (Data.Typeable.Internal.Typeable
23:15:22 <lambdabot> Control.Lens.Internal.Indexed.Indexed)
23:15:22 <lambdabot> arising from a use of ‘M550549437821123700020776.show_M5505494378211237000...
23:15:22 <lambdabot> The type variables ‘i0’, ‘p0’ are ambiguous
23:15:37 <int-e> (I did the same for the other uses of "hiding")
23:15:49 <int-e> Did you know that "R" is System.Random?
23:16:13 <elliott> I apologise for contributing to the mess of the qualification.
23:16:16 <oerjan> that certainly looks random hth
23:16:21 <int-e> elliott: oh my, that's outdate
23:17:32 <int-e> https://github.com/int-e/lambdabot/blob/config/lambdabot/State/Pristine.hs is closer to the truth.
23:24:47 <HackEgo> [U+039C GREEK CAPITAL LETTER MU]
23:27:28 <HackEgo> [wiki] [[ΜCurse]] http://esolangs.org/w/index.php?diff=39698&oldid=39653 * Oerjan * (-4) Lowercase template should work as it's a greek capital M. Also intro format.
23:28:04 <HackEgo> [wiki] [[ΜCurse]] M http://esolangs.org/w/index.php?diff=39699&oldid=39698 * Oerjan * (-1) less space
23:30:26 -!- aretecode has joined.
23:33:20 <oerjan> int-e: that FIXME looks like it has already been fixed?
23:33:27 <lambdabot> What lambdabot has in scope is at <http://code.haskell.org/lambdabot/State/L.hs>
23:33:57 <oerjan> @where+ l.hs What lambdabot has in scope is at < https://github.com/int-e/lambdabot/blob/config/lambdabot/State/Pristine.hs>
23:34:00 <lambdabot> What lambdabot has in scope is at < https://github.com/int-e/lambdabot/blob/config/lambdabot/State/Pristine.hs>
23:34:16 <oerjan> @where+ l.hs What lambdabot has in scope is at <https://github.com/int-e/lambdabot/blob/config/lambdabot/State/Pristine.hs>
23:34:25 -!- Phantom_Hoover has quit (Quit: Leaving).
23:34:57 <boily> quintopia: QUINTOPIAAAAAAAAAAAAAH!
23:39:53 -!- MDude has quit (Ping timeout: 264 seconds).
23:41:55 <HackEgo> [wiki] [[Language list]] M http://esolangs.org/w/index.php?diff=39700&oldid=39692 * Oerjan * (+0) /* Non-alphabetic */ Ordo Novo
23:46:25 <HackEgo> [wiki] [[Joke language list]] http://esolangs.org/w/index.php?diff=39701&oldid=39691 * Oerjan * (+1) wat.
23:51:29 -!- edwardk has joined.
23:52:36 -!- conehead has joined.
23:54:16 <HackEgo> [wiki] [[Brainfuck implementations]] http://esolangs.org/w/index.php?diff=39702&oldid=39609 * Oerjan * (+20) consistent punctuation
23:55:20 <int-e> oerjan: stuff got out of order; as far as I understand, the comment also applies to deriving instance Show (f (Mu f)) => Show (Mu f) ... anyway it wasn't added by myself :)
00:00:45 -!- edwardk has quit (Ping timeout: 252 seconds).
00:01:05 <HackEgo> [wiki] [[Pinkcode]] http://esolangs.org/w/index.php?diff=39703&oldid=39616 * Oerjan * (-18) wikify sectioning
00:07:48 <HackEgo> [wiki] [[5command]] M http://esolangs.org/w/index.php?diff=39704&oldid=39697 * Oerjan * (+1) fmt
00:08:18 -!- shikhout has joined.
00:11:31 -!- shikhin has quit (Ping timeout: 258 seconds).
00:41:13 <metasepia> CYUL 260031Z 10004KT 360V100 15SM FEW060 BKN100 OVC200 19/13 A2990 RMK SC2AC5CI1 SLP125 DENSITY ALT 500FT
00:41:31 <metasepia> ENVA 252350Z 27003KT 230V310 7000 -DZ SCT007 BKN016 09/09 Q1019 RMK WIND 670FT 32005KT
00:41:40 <oerjan> our heatwave is over, for now
00:42:20 <Sgeo> ENVA but no ENYA?
00:42:36 <metasepia> EGNT 260020Z 16004KT 130V190 9999 FEW042 12/09 Q1018
00:42:45 <Taneb> I forget I can't read that
00:42:57 <Taneb> And that I'm 90 miles away from Newcastle now
00:43:42 <oerjan> y isn't very common at the beginning of words in norwegian. not impossible, though. (see our foxy brothers ylvisaker, if the place their ancestors came from had an airport it might get that designation.)
00:44:18 <oerjan> oh *ylvisåker, not that it matters for this.
00:45:21 <oerjan> are you saying york has no airport
00:45:28 <Taneb> York as no airport.
00:45:30 <elliott> it's weather station thingies?
00:45:35 <Taneb> Closest is Leeds-Bradford.
00:45:41 <elliott> oh, I guess it's connected to flight stuff...
00:45:52 <boily> http://en.wikipedia.org/wiki/List_of_airports_by_ICAO_code:_E#EG_-_United_Kingdom_.28and_British_Crown_dependencies.29 ?
00:46:03 <Taneb> elliott, they don't have to be airports but they almost all are
00:46:47 <Taneb> My uni's electronics department has a weather station
00:47:23 <Taneb> But it's not got an ICAO code
00:47:29 <Taneb> http://weather.elec.york.ac.uk/
00:47:39 <metasepia> EGNM 260020Z 18004KT 9999 FEW030 09/08 Q1018
00:51:13 <Taneb> That's a lot clsoer
00:51:37 <metasepia> EGXD 252350Z AUTO 15003KT 9999 // FEW070/// 10/09 Q1018
00:51:45 <boily> maybe you don't have weather outside. or, maybe you don't even have an outside!
00:52:17 <Taneb> EGXD is 23 miles away
00:53:06 <Taneb> (I'm using Google Maps but roads get really wiggly)
00:53:44 <Taneb> Leeds-Bradford is 27 miles away
00:55:09 <oerjan> boily: Taneb lives here http://24.media.tumblr.com/tumblr_lvv1fbrsWz1qlltjpo1_500.jpg
00:55:44 -!- edwardk has joined.
00:56:35 <Taneb> What's a dew point?
00:57:00 <boily> it's the temperature an object needs to be for condensation to appear.
00:57:13 <pikhq> Temperature at which water vapor in the air condenses into liquid water.
00:57:18 <pikhq> i.e. the temperature at which dew forms.
00:57:41 <Taneb> Doesn't look like there'll be a dew today, then
00:58:16 <boily> I mean, it's all according to current conditions. you always need to chill that object down from ambient temperature for dew to appear.
00:58:29 <boily> (or, be in the morning, as in, like, you know, regular dew.)
01:00:27 <oerjan> if the dewpoint is higher than the temperature, you're having a flood hth
01:00:57 <pikhq> Yes. If the dewpoint is higher than the ambient temperature it means the air is actually water.
01:01:15 <pikhq> (dewpoint == temperature implies 100% humidity)
01:01:17 <Taneb> Not outside the realm of possibility, but I think my window is open
01:01:27 <Taneb> And I haven't drowned yet
01:03:08 <boily> drowning in you own apartment. I... don't think that's something possible.
01:03:17 <Taneb> Well, I'm on the ground floor
01:03:39 <pikhq> boily: It's definitely possible, though only in exceptional circumstances.
01:03:46 <Taneb> And drainage isn't that great here
01:05:04 <Bike> internal bleeding, for instance
01:05:49 <pikhq> Making poor use of a bathtub.
01:06:04 <Taneb> Suffering from a drinking problem?
01:07:01 <boily> tieing yourself a gin tonic while taking a bath, with your bathroom's window wide open during a thunderstorm in a basement flat near an overflowing river?
01:07:16 <boily> (and coughing from your ebola)
01:07:22 <pikhq> Now that's just impressively misguided use of a bathtub.
01:07:30 <pikhq> Perhaps even "actively malicious".
01:07:31 -!- blitter64 has quit (Ping timeout: 240 seconds).
01:07:41 <Taneb> Only if you fall asleep
01:07:49 -!- shikhout has quit (Ping timeout: 240 seconds).
01:08:39 <boily> I know I fell asleep at least once in all kinds of vessels and containers, but never in a bathtub.
01:09:50 <Taneb> I generally find beds the most soporgenic furniture
01:10:07 <Taneb> Although my flat's kitchen does encourage sleep, for some bizarre reason
01:10:26 <oerjan> Taneb: that word is so pretentious it only has one google hit hth
01:10:55 <boily> my googlebubble gives me 5 hits.
01:11:01 <zzo38> In Pokemon card did you knock out seven opponent's cards in one turn?
01:11:02 <Taneb> Well, yeah, it's a hideous mix of Greek and Latin
01:12:21 <oerjan> "hypnogenic /hyp·no·gen·ic/ (-jen´ik) hypnotic (1). hypnotic [hip-not´ik]. 1. causing sleep; called also somniferous."
01:12:38 <Taneb> Those are nicer words
01:17:01 -!- oerjan has set topic: The sleep-inducing channel | brainfuck survey: https://www.surveymonkey.com/s/L82SNZV | https://dl.dropboxusercontent.com/u/2023808/wisdom.pdf http://codu.org/logs/_esoteric/ http://tunes.org/~nef/logs/esoteric/.
01:17:35 <Taneb> Seriously, I had a few friends round to play a game of Diana: Warrior Princess. All of them felt tired and one of them actually fell asleep.
01:17:41 <boily> are we May 25 today?
01:17:55 <Taneb> May 26 now I think
01:18:46 <zzo38> IRC service says May 26
01:18:53 <boily> still the 25th here, and I saved a towel from the rain today. my bonne action is done, and my honour is safe.
01:18:53 <zzo38> Where I am, it is May 25
01:19:19 <boily> it's still early in Cascadia.
01:28:03 <Bike> eh, you live in vancouver?
01:30:37 <boily> as for me, time to go further the study of the soporgenicity of my mattress.
01:30:45 -!- boily has quit (Quit: EAST COAST CHICKEN).
01:30:47 -!- metasepia has quit (Remote host closed the connection).
01:32:49 -!- variable has changed nick to trout.
01:33:34 <zzo38> I want internet-connection library for SQL, so that it can be made a MUD server in SQL, among other things.
01:35:09 <Taneb> I'm going to head to bed now
01:36:28 -!- MDude has joined.
01:59:56 -!- zzo38 has quit (Quit: zzo38).
02:02:22 <^v> i made a optimized text to brainfuck table
02:02:23 <^v> http://hastebin.com/guzayutewi.lua
02:02:40 <^v> the one i found here http://codegolf.stackexchange.com/questions/5418/brainfuck-golfer/5440#5440
02:02:46 <^v> verry verry slow
02:03:49 -!- zzo38 has joined.
02:11:45 <zzo38> I think you can knock out seven opponent's cards on one turn if you have 1x MAGNETON [Lv35] and 4x GENGAR [Lv38] and POKEMON FLUTE, and opponent has one active pokemon, four bench pokemon requiring only 2 more damage to be knocked out, and one PORYGON [Lv12] on bench with no damage on it. If you also have some DEFENDER cards, then you can do so without any of your own cards knocked out.
02:20:58 -!- zzo38 has quit (Remote host closed the connection).
02:35:41 -!- Sprocklem has quit (Ping timeout: 264 seconds).
03:13:44 -!- blitter64 has joined.
03:33:17 -!- nycs has joined.
03:36:00 -!- `^_^v has quit (Ping timeout: 252 seconds).
03:38:37 -!- hk3380 has quit (Ping timeout: 245 seconds).
03:48:37 -!- blitter64 has quit (Ping timeout: 240 seconds).
03:53:44 -!- MoALTz_ has quit (Read error: Connection reset by peer).
04:06:13 -!- Sprocklem has joined.
04:18:12 -!- MDude has changed nick to MDream.
04:24:41 <Sgeo> If I watch a Planescape: Torment LP, and switch to another LP, how difficult would that be?
04:24:50 <Sgeo> Is the game railroaded enough that it should be fine?
04:27:00 <Sgeo> Is it forbidden to talk of being ok and not ok and forbidden and allowed as though they can be relative to situations and not necessarily extreme?
04:28:54 <oerjan> personally, i sometimes worry a little bit if we are teasing Sgeo too much.
04:30:23 <Sgeo> ^^previous statement was deliberately made vulnerable to the same kind of thing
04:31:31 <oerjan> good, good. or wait...
04:33:55 -!- hk3380 has joined.
04:36:33 -!- Sorella has quit (Quit: It is tiem!).
05:09:37 <shachaf> kmc: have you seen http://millcomputing.com/docs/
05:10:14 -!- hk3380 has quit (Ping timeout: 252 seconds).
05:12:18 <oerjan> heh bitcoin is up 30% in a week
05:18:36 <kmc> don't think so shachaf
05:20:48 <shachaf> it has all sorts of interesting ideas
05:21:39 <shachaf> it's all in the form of hour-long videos, though, which is why i'm only now finally watching them
05:31:07 <Bike> is this that replacement for registers? i don't want to watch videos
05:31:50 -!- oerjan has quit (Quit: leaving).
05:33:46 <shachaf> are you talking about the "belt" thing
05:36:03 <shachaf> that's one of the videos, yes
06:03:00 <FreeFull> It will be about rapid hardware iteration too
06:06:29 <Bike> rapid hardware zwitterion
06:21:36 -!- edwardk has quit (Quit: Computer has gone to sleep.).
06:36:13 -!- conehead has quit (Quit: Computer has gone to sleep).
06:56:15 -!- edwardk has joined.
07:01:01 -!- ter2 has quit (Ping timeout: 240 seconds).
07:02:54 -!- password2 has joined.
07:04:29 -!- edwardk_ has joined.
07:06:17 -!- edwardk has quit (Ping timeout: 264 seconds).
07:13:58 -!- slereah_ has joined.
07:30:44 <HackEgo> hillocoin alecoin mrozmancoin argarcoin devcoin juvecoin moxcoin lorumcoin *wcoin pahecoin magecoin errinuspcoin finingcoin deancoin trigjcoin catecoin godzicoin orncoin anycoin fobcoin
07:31:33 <kmc> UKIP took first place in the europarl voting? :(
07:33:48 <kmc> some weird irony in the fact that the people who care the most to vote for the office of UK MEP are the people who want it not to exist
07:34:13 <kmc> I guess that is how the right always works. "we believe government is the problem, elect us and we'll show you"
07:35:05 -!- Burton has quit (Remote host closed the connection).
07:52:28 -!- nortti has quit (Ping timeout: 276 seconds).
07:52:57 -!- nortti has joined.
08:02:22 -!- MindlessDrone has joined.
08:28:29 -!- password2 has quit (Ping timeout: 264 seconds).
08:29:59 -!- Patashu has joined.
09:25:19 -!- Patashu_ has joined.
09:25:19 -!- Patashu has quit (Disconnected by services).
09:27:14 -!- fungot has quit (Ping timeout: 252 seconds).
09:30:29 -!- edwardk_ has quit (Quit: Computer has gone to sleep.).
09:31:24 -!- drdanmaku has quit (Quit: Connection closed for inactivity).
10:15:15 -!- Phantom_Hoover has joined.
10:17:45 -!- tromp__ has quit (Ping timeout: 252 seconds).
10:19:34 -!- boily has joined.
10:20:14 -!- edwardk has joined.
10:31:06 <Taneb> Help I just ordered Parallel and Concurrent Programming in Haskell
10:32:47 -!- edwardk has quit (Quit: Computer has gone to sleep.).
10:35:13 <boily> Taneb: so you really been far as decided to use even go want to learn you more a haskell for great good like?
10:35:41 <Taneb> That is words a lot making sense little help understand no
10:35:59 <Taneb> But yeah, probably
11:03:49 <int-e> Oh, parsing fun. (Help ((I just ordered (Parallel and Concurrent Programming) in Haskell)) -- I hope you did not use unsafePerformIO.
11:04:28 <int-e> I got it wrong. I meant (Help ((I just ordered (Parallel and Concurrent Programming)) in Haskell)
11:05:31 <int-e> (I'm not sure there is a correct way of writing this without reordering the words into a syntax tree)
11:06:54 <boily> data TanebTree a = Leaf a | Node (Tree a) (Tree a) deriving (Show, Read, Eq, Irc)
11:08:15 -!- boily has quit (Quit: HALTING CHICKEN).
11:16:01 -!- edwardk has joined.
11:23:53 -!- edwardk has quit (Ping timeout: 258 seconds).
11:36:23 -!- edwardk has joined.
11:41:16 -!- edwardk has quit (Ping timeout: 276 seconds).
11:47:10 <mroman> impomatic: What do you do with a vampire?
11:47:22 <mroman> Making them jump into a core clear doesn't seem to be very effective
11:47:56 <mroman> I assume making them jump into bomb-throw loop is probably far more effective?
11:48:07 <mroman> but a core clear is rather slow
11:56:37 -!- Phantom_Hoover has quit (Ping timeout: 240 seconds).
12:04:46 <impomatic> mroman: making the opponent jump into a trap that splits off lots of useless processes is most effective. Normally the trap also does a clear...
12:07:33 <impomatic> mroman: there's a list of publish vampires here http://corewar.co.uk/z.htm
12:09:21 <impomatic> Fact: John McCarthy (inventor of LISP) and Uncle Bob Martin (Agile evangelist) invented and implemented the first vampire!
12:11:53 <mroman> but what's the difference to just throwing spl 0?
12:11:58 <mroman> that also splits off lots of processes
12:12:11 <mroman> I make them jump into a core clear that splits off processes
12:12:25 <mroman> and after I'm done throwing jump bombs I move a DAT bomb into the core clear loop
12:12:42 <mroman> and enter a core clear myself
12:14:02 <impomatic> spl 0 splits off a few processes that stay in the opponent's code. Jumping to a spl 0 / spl -1 / spl -2 tray splits off processes, that split off more processes, etc. They're also no longer running any of the opponent's code.
12:15:15 <impomatic> You could probably just let your clear wipe the trap. If the trap contains a clear, you could make that one wipe the trap as well :-)
12:16:51 -!- Phantom_Hoover has joined.
12:17:37 -!- hk3380 has joined.
12:20:29 <mroman> ah well. It got me 103.8 on the beginners hill
12:21:07 -!- Phantom_Hoover has quit (Ping timeout: 240 seconds).
12:24:22 -!- yorick has joined.
12:28:51 <HackEgo> olist 953: shachaf oerjan Sgeo FireFly boily nortti
13:14:43 -!- Patashu_ has quit (Ping timeout: 240 seconds).
13:18:48 -!- idris-bot has quit (Quit: Terminated).
13:19:13 -!- idris-bot has joined.
13:26:14 -!- edwardk has joined.
13:30:37 -!- edwardk has quit (Ping timeout: 252 seconds).
13:49:52 -!- Sprocklem has quit (Ping timeout: 245 seconds).
14:00:11 -!- Burton has joined.
14:05:34 -!- blitter64 has joined.
14:14:28 <Sgeo> My automatic Facebook page is malfunctioning
14:19:31 -!- mtve has joined.
14:22:55 -!- Froox has joined.
14:22:55 -!- Frooxius has quit (Read error: Connection reset by peer).
14:24:23 -!- Sprocklem has joined.
14:25:22 -!- blitter64 has quit (Ping timeout: 252 seconds).
14:41:10 -!- blitter64 has joined.
14:43:26 -!- nooodl has joined.
14:52:41 -!- edwardk has joined.
14:59:05 -!- hk3380 has quit (Ping timeout: 264 seconds).
15:01:17 -!- MDream has changed nick to MDude.
15:01:21 -!- conehead has joined.
15:04:27 -!- edwardk has quit (Quit: Computer has gone to sleep.).
15:06:05 -!- Sprocklem has quit (Quit: brb).
15:06:20 -!- Sprocklem has joined.
15:07:15 -!- edwardk has joined.
15:07:29 -!- edwardk has quit (Client Quit).
15:08:05 -!- blitter64 has quit (Ping timeout: 264 seconds).
15:09:30 -!- blitter64 has joined.
15:12:19 -!- edwardk has joined.
15:16:18 -!- ter2 has joined.
15:23:06 -!- AnotherTest has joined.
15:26:18 -!- tromp_ has joined.
15:30:33 -!- blitter64 has quit (Ping timeout: 265 seconds).
15:35:41 -!- xk002 has quit (Ping timeout: 264 seconds).
15:38:25 -!- Froox has quit (Read error: Connection reset by peer).
15:38:29 -!- Frooxius has joined.
15:44:48 -!- drdanmaku has joined.
15:52:54 -!- shikhin has joined.
15:53:59 -!- blitter64 has joined.
15:54:45 -!- hk3380 has joined.
15:59:14 <Sgeo> http://www.reddit.com/r/lolphp/comments/26inbh/define_has_an_optional_third_argument_that/
15:59:51 -!- Sprocklem has quit (Quit: leaving).
15:59:55 -!- slereah_ has quit (Quit: Leaving).
16:00:04 <Deewiant> https://pay.reddit.com/r/esolangs/comments/26ie70/favorite_esolangs_om_and_unlambda/ activity
16:06:18 -!- syndrome has quit (Ping timeout: 240 seconds).
16:12:02 -!- edwardk has quit (Quit: Computer has gone to sleep.).
16:20:07 -!- shikhout has joined.
16:23:20 -!- shikhin has quit (Ping timeout: 255 seconds).
16:32:28 <FireFly> "Added array_map() function that applies a callback to the elements of given arrays and returns the result. It can also be used with a null callback to transpose arrays. (Andrei)"
16:33:51 <Bike> not as good as arrayfun
16:34:08 -!- impomatic has left.
16:40:39 <mroman> why does a null pointer suddenly transpose an array o_O
16:44:52 -!- shikhout has changed nick to shikhin.
16:50:27 <elliott> > transpose [[a,b,c],[d,e,f],[g,h,i]]
16:50:49 <elliott> > zipWith3 (\(x,y,z) -> [x,y,z]) [a,b,c] [d,e,f] [g,h,i]
16:50:50 <lambdabot> Couldn't match expected type ‘Debug.SimpleReflect.Expr.Expr
16:50:50 <lambdabot> -> Debug.SimpleReflect.Expr.Expr -> d’
16:50:50 <lambdabot> z :: t0 (bound at <interactive>:1:17)
16:50:58 <elliott> > zipWith3 (\(x,y,z) -> [x,y,z]) [a,b,c] [d,e,f] [g,h,i] :: [[Expr]]
16:50:59 <lambdabot> Couldn't match expected type ‘Debug.SimpleReflect.Expr.Expr
16:51:00 <lambdabot> -> [Debug.SimpleReflect.Expr.Expr]’
16:51:03 <elliott> > zipWith3 (\x y z -> [x,y,z]) [a,b,c] [d,e,f] [g,h,i] :: [[Expr]]
16:52:52 <elliott> >>> l = [[1,2,3],[4,5,6],[7,8,9]]; map(None, *l)
16:52:52 <elliott> [(1, 4, 7), (2, 5, 8), (3, 6, 9)]
16:52:56 <elliott> >>> l = [[1,2,3],[4,5,6],[7,8,9]]; map(lambda *ll: list(ll), *l)
16:52:56 <elliott> [[1, 4, 7], [2, 5, 8], [3, 6, 9]]
16:52:56 <Sgeo> "The term "bass ackwards" comes to mind."
16:53:06 <elliott> the transpose behaviour is reasonable.
16:53:30 <Sgeo> 'In my view, HTTP/2.0 should kill Cookies as a concept, and replace it with a session/identity facility, which makes it easier to do things right with HTTP/2.0 than with HTTP/1.1.'
16:53:42 <Sgeo> YES PLEASE. Except Cookies could still be useful for other things, if maybe modernized somehow
16:54:15 <mroman> so the web-server manages sessions?
16:55:57 <Bike> elliott: it's a bit weird to count null as a function, i guess, even if it's the obvious choice
16:56:26 <elliott> Bike: you can think of it as mapping with "no function", but yeah, such is dynamically-typed languages
16:58:06 <FireFly> elliott: huh, hm, fair enough
16:58:37 <elliott> it's kinda weird to have something do the dual duty of map and zip like that
16:59:07 <elliott> > map (\[x,y,z] -> (x,y,z)) . transpose $ [[a,b,c],[d,e,f],[g,h,i]]
16:59:29 <elliott> transpose can be thought of as basically variadic zip
16:59:53 <elliott> so if your map does variadic zipWith, it's already doing transposes, really
17:01:17 <Bike> i thought it was common for map to do "double duty" like that. i'd never heard of zip before haskell and its fixed argument counts
17:01:55 <Bike> http://www.gnu.org/software/mit-scheme/documentation/mit-scheme-ref/Mapping-of-Lists.html eg
17:07:34 <Bike> cos if you have apply map f xs = (apply f (map1 car xs)):(map1 cdr xs); map f [] = [] as the kids say
17:14:48 -!- password2 has joined.
17:19:18 -!- password2 has quit (Ping timeout: 240 seconds).
17:24:29 -!- edwardk has joined.
17:27:01 -!- Sprocklem has joined.
17:31:53 -!- MoALTz has joined.
17:33:17 -!- password2 has joined.
17:41:57 -!- nooodl_ has joined.
17:45:27 -!- nooodl has quit (Ping timeout: 252 seconds).
17:47:49 -!- AnotherTest has quit (Ping timeout: 265 seconds).
17:51:07 -!- nooodl_ has changed nick to nooodl.
17:51:27 -!- KingOfKarlsruhe has joined.
17:54:05 -!- Sprocklem has quit (Quit: Lost terminal).
17:54:23 -!- Sprocklem has joined.
17:59:51 <monotone> Sgeo: I can't think of anything that wouldn't already be satisfied by localStorage, to be honest.
18:00:38 -!- Sprocklem has quit (Quit: leaving).
18:10:24 -!- Phantom_Hoover has joined.
18:11:12 -!- shikhin has quit (Remote host closed the connection).
18:19:09 <nooodl> https://dl.dropboxusercontent.com/u/15495351/fours.pdf i wrote this
18:19:39 <nooodl> what is the next step. algebraic numbers sounds sorta possible??
18:20:13 <Bike> copying Snobol!.pdf
18:20:39 <Bike> nooodl: do you want proofreading? "some selectin [sic] of operators"
18:20:57 <nooodl> oops. i didn't spellcheck it at all yes
18:21:40 <Bike> "n+1 radices" but i think the word would be "radicals", not sure
18:22:00 <nooodl> wikipedia calls the sign a "radix" but yeah i thought that was weird
18:23:15 <Bike> oh, this is pretty cute.
18:24:40 <nooodl> oh maybe gaussian rationals
18:25:20 <nooodl> i wonder how i'd get to "i". do people Actually Write, like, \sqrt(-4) = 2i
18:25:42 <nooodl> i was taught that's wrong because: -2i
18:25:50 <Bike> well you can throw a plus or minus on there.
18:26:04 <Bike> but you're already using repeated radicals, you must be taking the principle value
18:26:19 <Phantom_Hoover> btw minor stylistic thing, but if you have an expository footnote with 'clearly' on it then ask yourself why you need the footnote at all
18:26:53 -!- ter2 has quit (Read error: Connection reset by peer).
18:26:59 -!- tertu3 has joined.
18:27:22 -!- hk3380 has quit (Ping timeout: 245 seconds).
18:27:48 <Bike> 2^(.5^n) has, what... 2^n values?
18:27:56 <nooodl> Phantom_Hoover: maybe i should rather get rid of the clearly
18:28:54 -!- hk3380 has joined.
18:30:30 <Bike> i don't think you're going to be able to express algebraic numbers in radicals, though
18:33:22 -!- Bike_ has joined.
18:33:38 -!- Bike has quit (Disconnected by services).
18:33:43 -!- Bike_ has changed nick to Bike.
18:34:32 <Phantom_Hoover> nooodl, I'm not sure you need that much exposition about that part though.
18:34:41 -!- adu has joined.
18:35:01 <nooodl> it is sorta obvious but leaving the explanation out feels not very rigorous
18:35:29 <nooodl> i.e. makes it seem like i'm just reasoning "oh well if i just make it stupidly huge it's bound to be divisible by n??"
18:35:56 <Bike> it's a math paper dude, you have to explain as little as possible
18:37:16 <Bike> though it's not so much that it's huge as that it has any possible factors, which is, dare i say.... trivial
18:38:49 <Bike> anyway i wanna see how you express a root of x⁵-x+1 in four fours. aaaaand go
18:38:53 <kmc> https://gist.github.com/kmcallister/ad0622cffc8bdc0c5684 is this code UB due to aliasing rules? if so, why doesn't GCC warn even with -Wall -Wstrict-aliasing=4
18:41:04 <Bike> does it warn in LLVM?
18:41:11 <Taneb> Sweet, the book I ordered has already been dispatched!
18:42:13 <kmc> Bike: in clang? seems not
18:42:18 <kmc> i'm going by http://gcc.godbolt.org/
18:42:25 <kmc> btw there is now http://rust.godbolt.org/
18:42:53 <kmc> in Rust the aliasing rules are actually, like, enforced
18:43:56 <Bike> just like fortran!
18:44:54 <kmc> I don't think we give LLVM as much aliasing information as we should, though
18:45:14 <kmc> it's a recent thing to even tell it which pointers are guaranteed to be non-NULL
18:45:34 <kmc> there's also a frontend optimization whereby Option<&T> is a single word, with None represented as a NULL pointer
18:46:12 -!- mhi^ has joined.
18:49:26 <Taneb> kmc, can the compiler infer that?
18:50:25 <Taneb> Also I bought the Discworld Ankh-Morpork board game
18:50:52 -!- spiette has quit (Quit: .).
18:52:09 <mcpherrin> Taneb: Taneb the compiler is hard-coded to know &T is a non-null pointer
18:52:26 <kmc> and it has an optimization for any enum structurally matching enum Option<T> { None, Some(T) }
18:52:36 <kmc> it doesn't have to be specifically core::option::Option
18:53:00 -!- impomatic has joined.
18:53:01 <kmc> but I don't think it's smart enough to do, say, enum Foo { Bar, Baz, Quux(&uint) } with 0x0000...0000 and 0x0000...0001
18:53:08 <kmc> which is more of a platform specific thing
18:53:19 <kmc> I have plans to do that manually (with unsafe code) for interned strings in Servo
18:53:51 <kmc> there are fewer than 4k common strings on the web (e.g. tag names, attribute names) that you would intern at compile time
18:53:53 -!- conehead has quit (Quit: Computer has gone to sleep).
18:53:58 <kmc> so give each one an "address" within the first page of memory
18:54:40 -!- conehead has joined.
18:54:43 -!- realz has quit (Read error: Connection reset by peer).
18:54:43 <kmc> usually an interned string is just a pointer to a string but this interferes with some other things I want t odo
18:55:59 -!- realzies has joined.
18:56:11 <mcpherrin> Hopefully rustc can learn to steal bits from other types too in some non-hardcoded way
18:56:33 <kmc> which was the source of security holes at one point
18:56:37 <kmc> (in SM or V8, don't remember which)
18:56:59 <mcpherrin> kmc: which is why having rustc able to check would be great :)
18:58:21 <Melvar> What’s NaN stuffing? Using the variable bits in a NaN for something?
18:58:49 -!- MindlessDrone has quit (Quit: MindlessDrone).
18:58:58 -!- conehead has quit (Ping timeout: 240 seconds).
19:03:12 -!- adu has quit (Quit: adu).
19:07:18 <FireFly> For storing pointers, I guess
19:09:10 <mcpherrin> https://developer.mozilla.org/en-US/docs/Mozilla/Projects/SpiderMonkey/Internals
19:09:15 <mcpherrin> see "Javascript Values" on that page
19:09:45 <mcpherrin> NaN-boxing is a technique based on the fact that in IEEE-754 there are 2**47 different bit patterns that all represent NaN
19:11:22 -!- xk002 has joined.
19:11:33 <FireFly> IIRC one of V8 or SM represents doubles "plainly" and objects as pointers inside the payload of a NaN, whereas the other instead represents pointers plainly and numbers via some indirection step
19:11:49 <FireFly> Though I don't remember how the latter works..
19:21:52 <kmc> i want SmallVec<T> in the std lib :<
19:22:03 <kmc> maybe I should Just Fuckin Do It
19:24:07 <int-e> that is a cute term ... "right parenthesis deficit disorder". (I've just started reading "The Art of Procrastination".
19:24:44 -!- ^v has quit (Quit: Leaving).
19:25:56 <int-e> Oh, that was totally wasted on the target audience (oerjan, who isn't even here. maybe he'll read it later.)
19:26:12 -!- ^v has joined.
19:26:52 <kmc> Melvar: Vec<T> is a standard growable vector like C++'s std::vec<T>, SmallVec<T> is similar but doesn't do a heap allocation for storing only 1 element
19:27:19 <kmc> er, it's named SmallVector<T>
19:27:41 <kmc> enum SmallVector<T> { None, One(T), Many(Vec<T>) }
19:28:00 -!- password2 has quit (Read error: Connection timed out).
19:34:24 -!- AnotherTest has joined.
19:35:01 <Melvar> Funny how they call them “enum”.
19:40:47 -!- conehead has joined.
19:46:29 -!- password2 has joined.
19:53:11 <olsner> enum is a bit weird, I would've liked it if they went with haskell on that bit instead, and e.g. let enum be an enumeration of int-like things
19:53:23 -!- tertu3 has changed nick to tertu.
19:55:10 <M28> Haxe's enum is awesome
19:55:21 <M28> shame it doesn't support generics
19:57:50 -!- edwardk has quit (Quit: Computer has gone to sleep.).
19:59:21 -!- edwardk has joined.
20:05:55 -!- conehead has quit (Quit: Textual IRC Client: www.textualapp.com).
20:16:11 -!- blitter64 has quit (Ping timeout: 255 seconds).
20:18:44 -!- Sprocklem has joined.
20:19:52 -!- glogbackup has quit (Ping timeout: 245 seconds).
20:27:54 -!- password2 has quit (Read error: Connection timed out).
20:28:35 -!- password2 has joined.
20:33:51 <kmc> M28: what does it do?
20:34:02 <kmc> olsner: yeah, the duplication of functionality between struct and enum is sort of annoying
20:34:31 <shachaf> kmc: that's still that way? :'(
20:34:50 <shachaf> Last time I used Rust about a year ago I thought people were talking about changing it.
20:34:58 <kmc> people are always talking about changing everything
20:35:13 <kmc> also struct-syntax enum variants are feature-gated now
20:35:19 <kmc> not sure if that's a step forward or back
20:35:29 <kmc> struct has a C ABI guarantee, but that could easily be an attribute, which it already is for enum!
20:35:40 <kmc> #[repr(C)] (case sensitive ;_;)
20:35:45 <shachaf> That's the situation I remember.
20:36:39 <Bike> how does case insensitivity work in unicode anyway
20:37:27 <kmc> you can't even do ASCII case folding without knowing the locale
20:37:37 <kmc> thanks a lot Atatürk
20:38:06 <kmc> http://www.w3.org/International/wiki/Case_folding
20:38:36 <kmc> Unicode makes a distinction between case mapping and case folding, and only really defines the latter http://www.unicode.org/faq/casemap_charprop.html
20:38:43 -!- password2 has quit (Ping timeout: 240 seconds).
20:38:56 <kmc> the former being a snake pit of locale and UX concerns
20:39:25 <Bike> haha, the third answer rules.
20:39:44 <Bike> "do all scripts have case?" "no, here is a list of almost every one that does, and then there are tens of thousands that don't"
20:39:55 <kmc> what about hiragana and katakana!!!
20:40:04 <Bike> huh that's a good question actually
20:40:11 <olsner> it's case but not as we know it?
20:40:11 <Bike> since a lot of time katakana is transliterated as allcaps
20:40:17 <kmc> I think those are generally not considered "case" and they don't have a 1:1 mapping?
20:40:23 <kmc> but I don't know how exactly linguists define "case"
20:40:24 <Bike> monotone: opinion
20:40:51 <kmc> konnichi wanotone
20:40:51 <Bike> i don't think it's case exactly but i thought there was a 1:1
20:40:52 -!- AnotherTest has quit (Ping timeout: 258 seconds).
20:41:06 <kmc> maybe there is
20:41:20 <Bike> since they're just syllabries (sp)
20:41:30 <Bike> no 1:1 with kanji of course.
20:41:31 <kmc> case in cyrillic is extra weird
20:41:41 <monotone> I've never heard it described as being similar to case.
20:41:41 <olsner> some of the small ones have completely different meanings and most characters aren't used in small versions
20:41:42 -!- glogbackup has joined.
20:41:43 <Bike> oh yeah, how's it work? i have no idea other than vague rememberance of capital letters'
20:41:48 <kmc> print lowercase looks like smallcaps but script lowercase is totally different
20:41:57 <kmc> also script hebrew is totally different from print hebrew
20:42:05 <kmc> and script arabic is basically whatever the hell you want
20:42:18 <Bike> script english is pretty weird too... not that it's used much anymore
20:42:30 <kmc> they made us learn cursive in middle school
20:42:30 <monotone> I think one of the peculiarities of cased alphabets is that the cases get mixed in normal writing.
20:42:31 <kmc> fuck all that
20:42:34 <Bike> i personally like how script german from before WWII is unreadable by modern speakers
20:42:40 <monotone> So you have rules for capitalization and whatever.
20:42:41 <Bike> because of font changes
20:42:44 <kmc> I can't even write my own name in cursive anymore; my signature has gradually decayed to a few squiggles
20:42:54 <Bike> kmc: you know they still make you write in cursive on the SAT? crazy.
20:43:07 <kmc> on the ACT you have to copy a paragraph long assertion that you didn't cheat, in cursive
20:43:13 <Bike> yeah, same on the SAT.
20:43:23 <kmc> I don't remember that from the SAT but I took it... fuck, more than 10 years ago
20:43:34 <coppro> I never took any of those
20:43:36 <kmc> (well I took it a bunch of times as a small child but I last took it more than 10 yeras ago)
20:43:51 <Bike> monotone: thank god for the internet where i just lowercase everywhere (except initialisms, apaprently)
20:43:57 <monotone> With kana you don't have similar "rules" as such.
20:44:05 <shachaf> Bike: i copied that paragraph in non-cursive
20:44:29 <Bike> monotone: don't you have the general rule that katakana is used for foreign pronunciations or something? not as complicated as casing, of course, but still
20:44:42 <Bike> well i guess if you took that argument far enough you could describe print/script as a case distinction, hrm.
20:45:20 <shachaf> kmc: script hebrew isn't mixed in with print hebrwe, though
20:45:22 <monotone> Bike: Yeah, but it's not considered "ungrammatical" to switch them, at least not to the degree improper case usage would be for English.
20:45:49 <shachaf> it is like cursive. which i guess is why you were talking about cursive
20:46:44 <Bike> monotone: i dunno, i mean in many contexts it's okay to ignore case rules and write in allcaps, and that's not "ungramamtical" either
20:47:32 <monotone> Bike: I guess in Latin script the use of uppercase is broken down into proper nouns, sentence-initial capitalization, emphasis, initialisms, etc.
20:47:46 -!- glogbackup has quit (Ping timeout: 258 seconds).
20:47:51 -!- yorick has quit (Remote host closed the connection).
20:47:52 <monotone> With katakana it's basically emphasis and conventional loanword spellings and not much else.
20:48:46 <kmc> do you think the two kana alphabets will eventually merge?
20:48:53 <kmc> it seems like the kind of complexity that is locally reducible
20:49:19 <monotone> I dunno if the all-caps thing is really emphasis or not, actually. Certainly it's not unheard of to spell things entirely in katakana, either, though that gives people flashbacks to half-width kana on old terminal screens.
20:50:38 <kmc> (rather than, say, ditching Han characters, which in Korea required a royally chartered committe of 15th century conlang nerds and a few centuries of colonial oppression + nationalism)
20:51:00 <monotone> kmc: I'm not sure, really. I don't really see it happening in the foreseeable future, though.
20:51:12 <kmc> well not very much of the future is forseeable
20:51:21 <kmc> it's kind of a joke to think that anyone can forsee anything
20:51:31 <kmc> but I'm on a sort of absurdist nihilist / existentialism kick lately
20:51:40 <kmc> balls deep
20:51:45 <Bike> monotone: so is there a 1:1 mapping between the syllabries, though
20:51:57 <Bike> i thought there was, except for maybe something with archaic syllables
20:52:24 <int-e> I foresee a sunrise about 6 hours from now ...
20:53:03 <monotone> All the kana that were in use in the early 20th century have hiragana and katakana versions.
20:53:18 -!- glogbackup has quit (Ping timeout: 252 seconds).
20:53:22 <kmc> int-e: I'll tell my Sun Crusher to stand down
20:53:54 -!- Patashu has joined.
20:57:46 <int-e> kmc: much appreciated
20:58:23 -!- password2 has joined.
20:59:05 -!- password2 has quit (Max SendQ exceeded).
20:59:48 -!- password2 has joined.
21:03:04 -!- not^v has joined.
21:03:12 -!- glogbackup has joined.
21:07:18 -!- glogbackup has quit (Ping timeout: 240 seconds).
21:08:51 -!- Sprocklem has quit (Quit: brb).
21:10:51 <impomatic> Who actually called John McCarthy the father of AI?
21:17:43 <Bike> i looked it up and found "Lisp paved way for iPhone 4s' Siri voice recognition software" so i'm laffin
21:18:52 <Bike> anyway i don't see anything but a bunch of obituaries, so probably nobody
21:23:25 -!- Patashu has quit (Ping timeout: 258 seconds).
21:28:51 -!- oerjan has joined.
21:36:51 <impomatic> Bike: I search on Google books and found a few published in the 1980's which called McCarthy the father of AI. (Also a few which called Turing or Minsky the father of AI)
21:37:23 -!- edwardk has quit (Quit: Computer has gone to sleep.).
21:45:35 -!- KingOfKarlsruhe has quit (Quit: ChatZilla 0.9.90.1 [Firefox 29.0.1/20140506152807]).
21:48:23 <impomatic> I asked about McCarthy on #ai, but they just keep refining are restating my original question :-(
21:48:58 -!- yorick has joined.
21:50:45 -!- password2 has quit (Ping timeout: 252 seconds).
22:03:03 <impomatic> The earliest example I can find is in a review of "Scientific Temperaments: Three Lives in Contemporary Science" - New Scientist, March 1983
22:04:33 <oerjan> impomatic: sounds like the other people on #ai are ai's
22:12:45 -!- nooodl_ has joined.
22:15:41 -!- nooodl has quit (Ping timeout: 252 seconds).
22:23:42 <oerjan> <nortti> `olist 953 <-- darn
22:24:16 -!- not^v has quit (Quit: http://i.imgur.com/Akc6r.gif).
22:24:27 -!- Phantom_Hoover has quit (Quit: Leaving).
22:25:25 -!- hk3380 has quit (Ping timeout: 276 seconds).
22:26:22 -!- boily has joined.
22:31:37 -!- tory_perez has joined.
22:32:51 -!- tory_perez has left.
22:38:54 <boily> darn. I missed a `relcopportunity.
22:44:30 -!- hk3380 has joined.
22:45:26 -!- Sorella has joined.
22:46:52 * oerjan wonders if "cheryllium" is on this channel.
22:47:12 <oerjan> under some other nick, in case
22:47:26 <oerjan> (the moderator of /r/esolangs)
22:47:52 <Bike> hm, i think i've seen them before
22:49:03 <Bike> yeah, someone with that nick has been in #lisp afore
22:49:36 <oerjan> fizzie: do you recall cheryllium from here before?
22:49:53 <oerjan> hm looks idle. oh right, tokyo.
22:50:28 <oerjan> it looks like that subreddit has just reactivated a little.
22:50:43 <oerjan> (i made a comment on one of the posts)
22:50:45 <boily> there's an /r/esolangs?
22:50:55 <oerjan> (the one Deewiant linked)
22:51:09 <oerjan> boily: well sure, there's a subreddit for _everything_ duh
22:51:34 <boily> my mind knows there's a subreddit for everything, but my heart disagrees.
22:52:09 <Jafet> There's probably a subreddit for that.
22:52:54 <boily> how do you mapole somebody in a meta fashion? what's the adverb for “meta”?
22:53:04 <oerjan> http://www.reddit.com/r/subreddit/
22:54:07 <oerjan> boily: i think technically meta may _be_ an adverb, in the original greek.
22:54:20 <oerjan> or maybe it's a preposition, not quite sure
22:54:21 <int-e> there is one one everything ... http://www.reddit.com/r/everything/ but none on anything?
22:56:06 * boily metaly mapoles Jafet. “May you suffer from pseudogrammatical hardwood!”
22:56:14 <oerjan> int-e: that has the right tagline, at least
22:57:09 <oerjan> ok wiktionary says it's both
22:57:51 <oerjan> i vaguely recall that in ancient indoeuropean, the border between adverb and preposition wasn't very fixed.
22:59:06 <oerjan> of course even modern languages sometimes turn other word classes into preposition. e.g. french "chez" and norwegian "hos" which both come from the word for house iirc, and coincidentally also mean the same thing.
23:00:32 <boily> «chez» comes from “house”?
23:01:14 <boily> «Fait chiese, chese (« maison ») en ancien français, altéré en chez en raison de son emploi proclitique, du latin casa (« maison »).
23:01:36 <boily> fr:maison, so oerjan was right.
23:03:07 <oerjan> hm although they both are from original k- somthing, wiktionary does _not_ claim fr:chez/la:casa to be cognate with no:hus/hos/en:house
23:05:04 <boily> en:house ← “from Proto-Germanic *husan... of unknown origin”.
23:05:29 -!- nooodl_ has quit (Quit: Ik ga weg).
23:05:47 <oerjan> wiktionary says "possibly from Proto-Indo-European *(s)keus-, from *(s)keu- 'to hide'"
23:06:17 -!- ion has quit (Ping timeout: 252 seconds).
23:06:36 <oerjan> (the germanic h- <-> indoeuropean k- correspondence is pretty regular.)
23:07:31 -!- tswett has joined.
23:07:50 <oerjan> i guess that's dubious enough that casa and house _might_ be cognates, although there's probably a reason they don't assume so outright...
23:08:32 -!- ion has joined.
23:09:01 <fizzie> oerjan: Kyoto, not Tokyo.
23:09:50 <oerjan> hm i guess i was also here 5 years ago. how time flies.
23:10:02 <tswett> "Casa" and "house" look like cognates if you ask me.
23:10:04 <fizzie> The name rings a bell but I could be imagining it. Have to leave now, anyway. ->
23:10:05 <tswett> But you didn't ask me.
23:10:07 <tswett> So don't listen to me.
23:10:32 <pikhq> "Cheryllium"? Yeah, it does seem oddly familiar.
23:10:35 <oerjan> tswett: yes they do, so why don't the linguists think so...
23:11:00 <pikhq> I would presume that linguists are more careful than that. :)
23:11:02 <kmc> "avocado" and "guacamole" are cognates
23:11:15 <pikhq> fizzie: Otanoshimi ni.
23:11:16 <kmc> from nah:āhuacatl
23:11:22 <tswett> So the etymology things say...
23:12:19 <tswett> House comes from Proto-Germanic *husan "of unknown origin"; casa "possibly" comes from PIE *kat- meaning "link, weave".
23:12:33 <tswett> So the reason the linguists don't think so is that they know better.
23:13:27 <tswett> For a while I've wanted to come up with some sort of "notation" for writing words in terms of how they came out of PIE.
23:13:32 <oerjan> tswett: well assuming they're sure that casa used to have a t.
23:13:53 <tswett> "t" could have turned into "s", no?
23:14:15 <tswett> Heck, certain "k"s turned into "s"s... somewhere down the road from Latin.
23:15:12 <boily> meh. google translate doesn't support nahuatl. there's Mongol and Néerlandais, but no nahuatl.
23:16:54 <oerjan> tswett: there presumably is a way it could have happened.
23:17:38 <HackEgo> [wiki] [[BF Joust strategies]] http://esolangs.org/w/index.php?diff=39705&oldid=37929 * Oj742 * (+1886) /* 2013: Gave smartlock a description*/
23:17:45 <oerjan> maybe if casa is a passive participle
23:19:13 <oerjan> why do i keep delaying eating ->
23:21:54 <tswett> Man, those Proto-Indo-Europeans. What kind of word is "dhǵhemon"?
23:22:45 <boily> it's like a fricative-clustered lemon.
23:22:51 <HackEgo> 1097) <Koen_> nooodl: when my girlfriend asks me to give her uvular fricative I'm pretty sure that's not what she means
23:23:05 -!- boily has quit (Quit: DOUBTING CHICKEN).
23:26:16 -!- mhi^ has quit (Quit: Lost terminal).
23:33:34 -!- not^v has joined.
23:34:17 <oerjan> that quote was so good i considered addquoting it before i realized it already was
23:34:32 <HackEgo> 589) <Phantom_Hoover> I'd insult you behind your back, but I don't care which side of your back I insult you on.
23:37:58 <oerjan> > head $ runStateT (many $ StateT (reads :: ReadS Int)) "1 2 3 four" -- exhibit
23:40:43 -!- Bike has quit (Ping timeout: 240 seconds).
23:42:40 -!- Bike has joined.
23:46:37 -!- edwardk has joined.
00:07:58 -!- edwardk has quit (Quit: Computer has gone to sleep.).
00:09:54 <oerjan> <Bike> i don't think you're going to be able to express algebraic numbers in radicals, though <-- pretty sure he won't be ABEL to
00:17:56 <oerjan> he's not one of those guys with a normal sleeping schedule is he
00:21:07 -!- not^v has quit (Ping timeout: 240 seconds).
00:47:36 -!- tertu has quit (Ping timeout: 252 seconds).
00:54:27 -!- xk002 has quit (Ping timeout: 245 seconds).
01:04:02 -!- tertu has joined.
01:04:40 -!- tertu has quit (Read error: Connection reset by peer).
01:05:04 -!- tertu has joined.
01:09:21 -!- Sorella has quit (Quit: It is tiem!).
01:10:38 -!- not^v has joined.
01:13:59 -!- tertu has quit (Disconnected by services).
01:13:59 -!- ter2 has joined.
01:16:55 <kmc> yesterday i biked on Abel Street in Milpitas CA
01:17:00 <kmc> failed to come up with a good pun about commuting
01:18:26 -!- tertu3 has joined.
01:18:59 <ion> The reverse of it is acsatiplim.
01:19:23 <shachaf> people need a place to go hth
01:19:24 <kmc> it would seem so
01:19:38 <shachaf> it was for a month and a half or so
01:20:31 <kmc> yesterday's ride http://www.strava.com/routes/365633
01:21:01 -!- ter2 has quit (Ping timeout: 240 seconds).
01:21:03 <shachaf> i have been to that reservoir
01:21:26 <kmc> in milpitas?
01:21:33 <kmc> all the pieces are beginning to fit together
01:22:32 <shachaf> it's a pity it's not called "petersburg st."
01:23:03 <mcpherrin> apparently there's a plane in the reservoir
01:25:06 <kmc> PLAAAAAANE
01:25:08 <kmc> ... wrong channel
01:26:48 <mcpherrin> I want to do that ride again but maybe with a picnic and twice as much water :p
01:27:55 -!- not^v has quit (Quit: http://i.imgur.com/Akc6r.gif).
01:30:29 <oerjan> i think milpitas used to be called mailpits before the big earthquake.
01:30:46 <HackEgo> priniconcoin muscucoin catamcoin zoosedcoin lazycoin glashbcoin excompressicucoin rentanyploanycoin pourcoin solecoin mazecoin illcoin medcoin shakhcoin moucoin pratcoin nandcoin sorcoin um-32coin incaviacoin
01:34:16 -!- vvn1 has joined.
01:35:36 <HackEgo> 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.)
01:37:03 <kmc> shachaf: did you ever go to the IHOP in Milpitas
01:37:11 <kmc> or the Black Bear Diner
01:37:13 <vvn1> hi, thanks for the welcome
01:37:22 <vvn1> is anyone interested in doom metal?
01:37:37 <shachaf> although i was nearby once
01:37:50 <oerjan> vvn1: that's even more off topic than usual for our channel
01:38:01 <vvn1> you’d be surprised
01:38:26 <Bike> is russian circles metal? i think they're fairly doom
01:39:31 <Bike> wikipedia says "post-metal", good enough for me
01:39:42 <Bike> must be chalcogens
01:40:05 <shachaf> kmc: in this mill thing you can load from a null or invalid pointer and get a "not a result" result rather than an immediate page fault
01:40:13 <kmc> how does that wor
01:40:19 <Bike> no, no, doom post-metal. post-doom metal is either very peppy, or based around surpassing popular musician MC DOOM
01:40:28 <Bike> MF DOOM rather
01:40:32 <Bike> everyone should just be an MC fuck
01:40:42 <shachaf> there are some metadata bits for things in the equivalent of registers
01:40:55 <shachaf> then if you don't use the NaR you don't get a page fault
01:41:02 -!- MoALTz_ has joined.
01:41:38 <shachaf> so you can speculatively load things that you might not use as long as you don't store or branch on the result or something
01:41:57 <shachaf> their example is implementing a vectorized strcpy and reading past the \0
01:43:29 <oerjan> shachaf: does that work if the page exists but needs to be swapped in?
01:43:49 -!- MoALTz has quit (Ping timeout: 240 seconds).
01:43:56 <kmc> shachaf: good, I had that exact issue once
01:44:04 <shachaf> oerjan: in that case a different thing would happen presumably
01:44:05 <kmc> oerjan: seems like; it's traditionally the page fault handler which does that
01:44:18 <kmc> yeah, how would you deal with that
01:44:29 <shachaf> i don't know how page faults work exactly
01:44:45 <shachaf> another metadata value is "None", such that storing a None into memory does nothing
01:45:00 <shachaf> this is their strcpy thing: http://millcomputing.com/blog/wp-content/uploads/2014/02/intro_strcpy.png
01:46:26 <shachaf> i don't know how they deal with that; i was wondering
01:47:12 <ion> All this diagram needs is an oracle that tells whether there will be a match two steps in advance.
01:48:16 <ion> Ignore me, i haven’t been following the discussion, just clicked the link. Going back to http://youtu.be/HuzC0MAlo0w →
01:49:32 <shachaf> this is the context of the diagram: http://millcomputing.com/topic/introduction-to-the-mill-cpu-programming-model-2/
01:50:14 <ion> Thanks, i’ll open it in tab #15432 for later.
01:50:37 <shachaf> my browser crashed and lost all my tabs a couple of weeks ago
01:51:07 <ion> I haven’t had the courage to do that, i have restored them from a backup in the past.
01:51:12 -!- blitter64 has joined.
01:52:11 <shachaf> another thing they have that isn't mentioned on that page is two instructions pointers, one going backwards and one going forwards
01:53:47 <Sgeo> My friend just introduced me to the Pokemon TCG
01:54:04 <Sgeo> And to Android Netrunner, but there's no online version and I suck at it
01:56:03 -!- blitter64 has quit (Ping timeout: 252 seconds).
01:58:15 <Sgeo> ANd not to Yu-Gi-Oh which he called broken
01:59:09 <Sgeo> "Yes, on occasion, my friend and I bust out the pokemon cards and go at it. The game is shallow at first glance, but there is a decent amount of strategy involved. This mostly comes into play in the deckbuilding process. Pokemon is more draw oriented than Magic, meaning that the key to winning is drawing more of your deck than your opponent, making cards like Professor Oak incredible. "
01:59:15 <Sgeo> meh, I don't like deckbuildin
02:07:40 <Sgeo> http://www.reddit.com/r/hearthstone/comments/26jfqy/this_golden_card_is_weaker_than_its_normal_version/
02:08:53 -!- ter2 has joined.
02:10:17 -!- yorick has quit (Read error: Connection reset by peer).
02:11:49 -!- tertu3 has quit (Ping timeout: 252 seconds).
02:13:32 -!- ter2 has changed nick to tertu.
02:14:47 <MDude> I wonder if any existing language is particularly suited to a computational variant of Exquisite Corpse.
02:15:05 <Bike> we call that game software development round these parts
02:20:09 -!- tertu has quit (Ping timeout: 265 seconds).
02:23:23 -!- hk3380 has quit (Quit: WeeChat 0.3.8).
02:23:40 -!- {hk3380} has joined.
02:26:50 -!- {hk3380} has quit (Client Quit).
02:27:08 -!- {hk3380} has joined.
02:27:47 <kmc> have you played this game that I know only as "the paper game", where people in a circle take turns either describing a drawing with words or drawing something from a description, and you only see the previous attempt
02:28:00 <kmc> and then you read out the words after n iterations
02:28:08 <kmc> also does it have another name
02:28:31 <kmc> (it's played with picees of paper that are folded accordion-like so that you only see one drawing or description)
02:29:26 <MDude> There's a website that works a bit like that, where it prompts you to draw or describe something.
02:30:06 <mcpherrin> I remember a website version of this, yeah. and seeing the evolution
02:30:14 <mcpherrin> until inevietably somebody just draws a penis
02:30:36 <kmc> it's one of the easiest things to draw
02:30:39 <kmc> also pac-man
02:30:41 <kmc> we got a lot of pac-man
02:37:03 <shachaf> oh, written words, not spoken words
02:44:44 -!- MoALTz_ has quit (Read error: Connection reset by peer).
02:49:47 -!- vvn1 has left.
03:05:17 -!- MDude has changed nick to MDream.
03:09:52 -!- zzo38 has joined.
03:20:06 -!- Phantom_Hoover has joined.
03:22:10 -!- tertu has joined.
03:25:29 -!- {hk3380} has quit (Ping timeout: 264 seconds).
03:26:39 -!- ter2 has joined.
03:26:39 -!- tertu has quit (Disconnected by services).
03:34:37 <kmc> I'm using LD_PRELOAD in a way that is reminiscent of having two puzzle pieces that don't quite fit and just kind of smashing them together until they do
03:35:23 <mcpherrin> LD_PRELOAD is an awesome way to add features to software
03:36:34 <kmc> mcpherrin: I realized that plugins for the stage2 compiler need to be built with the stage1 compiler, but they don't quite work then either
03:36:41 <kmc> so i'm building stage3 but it's soooo slow
03:39:30 <zzo38> How do you use the LD_PRELOAD adding features into a software?
03:42:08 <mcpherrin> zzo38: Here's http:// support for open(1) via LD_PRELOAD! https://github.com/mcpherrinm/webscale/blob/master/libhttpfile.c
03:44:02 <zzo38> O, so you can add new features into function like that. That is good adding support for http: and data: URLs, now add ftp: and gopher: support too. (I think curl supports it?)
03:45:09 <pikhq> zzo38: Fair warning, LD_PRELOAD is a fragile fragile thing.
03:45:21 <zzo38> (Furthermore, ftp can be use for writable files; http is normally only for reading files, although there is a PUT method of HTTP if you want to)
03:46:41 <zzo38> Still there are other way to make in such supports added, depending on the software. For example a software using SQLite, you can add support for other file by adding a VFS by loading an extension, and you can also modify the triggers in the database to possibly add features in.
03:48:18 <zzo38> Do you like stuff I wrote yesterday about knock out seven opponent's cards in Pokemon card?
03:49:01 <zzo38> It is an uncommon situation, though.
03:55:22 <zzo38> Why do you hate flipperless pinball game? I don't hate it; the feature of pinball game that I do hate is the games in which you can earn free balls for making the high score.
03:55:47 <zzo38> (I don't mind free games for making the high score, though.)
03:57:24 <zzo38> And, why don't you hate that feature?
04:04:01 <kmc> mcpherrin: \o/ https://gist.github.com/kmcallister/f47ee925a16773be4f84
04:05:05 -!- ter2 has quit (Ping timeout: 264 seconds).
04:05:21 <Bike> useful, i like it
04:06:10 <oerjan> kmc: it's not actually pointing at the e plz fix twh hth
04:06:41 <Bike> ooh good point
04:07:25 <Bike> wow, did you manage to write a general code analyzer thing that seems reasonably structured
04:07:28 <Bike> that's pretty good rust
04:07:55 <Bike> i still ahve no idea how to read these type signatures
04:11:51 <Sgeo> It's kind of funny how the web both forces you to use one language and frees you to use any language
04:12:08 <Sgeo> (not literally any)
04:15:41 -!- Phantom_Hoover has quit (Ping timeout: 255 seconds).
04:19:49 <kmc> oerjan: https://gist.github.com/kmcallister/500920de676275deccd8
04:19:57 <kmc> it's a hack though, I hardcoded the width of "struct "
04:20:08 <kmc> I don't think the parser saves the information you need to do this right
04:20:15 <kmc> I could fix that but I think I will get high and watch television instead
04:21:05 <mcpherrin> kmc: so it would break if i did "struct \n\neeeeeeeeeeeee"
04:22:15 <kmc> Bike: not first on my list but probably
04:22:35 -!- {hk3380} has joined.
04:34:10 -!- tertu has joined.
04:56:16 <kmc> Bike: probably The Americans, Veep, Silicon Valley, Mad Men in that order
04:56:19 <kmc> might fall asleep at some point
04:56:43 <kmc> <Bike> wow, did you manage to write a general code analyzer thing that seems reasonably structured
04:56:44 <Bike> but if you fall asleep while high the weed will crawl into your nose and strangle you!
04:56:55 <kmc> well the structure a is pretty standard AST visitor
04:57:14 <kmc> the more interesting thing imo is that it's a plugin which integrates with the compiler
04:57:25 <kmc> so you can (well, will be able to) control it with the usual warning flags
04:57:35 <kmc> and it can do things like ask the types of inferred local lets
04:57:36 <Bike> well i mean, right. i'm more used to something along the lines of LD_PRELOAD, you know, one variable, terrible
04:57:47 <Bike> argh i would love that
04:58:15 <kmc> yeah so most of the work here was just redoing all the plumbing around the existing loadable syntax extensions to turn it into a cleaner more general plugin mechanism
05:04:31 -!- tswett has quit (Ping timeout: 276 seconds).
05:07:24 -!- Phantom_Hoover has joined.
05:09:29 <kmc> aw there's no new episode of Veep
05:12:19 -!- {hk3380} has quit (Ping timeout: 276 seconds).
05:31:55 -!- oerjan has quit (Quit: leaving).
05:42:16 <kmc> <Bike> i still ahve no idea how to read these type signatures
05:42:17 <kmc> which ones?
05:42:27 <kmc> we're losing the ~funny @variable &sigils
05:42:32 <kmc> the first two are gone
05:42:58 <kmc> & is probably staying though
05:43:20 <kmc> I think Rust has a lot less sugar now than when I started using it
05:43:21 <Bike> well uh basically any of them. "&mut self, it: &ast::Item, cx: Context" i guess cx, it, and self are names, and Context and &ast::Item are types, but i don't know what & is or what &mut means
05:43:37 -!- tertu has quit (Ping timeout: 245 seconds).
05:43:44 <kmc> & is a reference aka "borrowed pointer"
05:44:05 <kmc> points to something, you can use it, but someone else owns it and is responsible for destroying it eventually
05:44:23 <kmc> references have lifetimes, sometimes written in as &'t Item
05:44:27 <kmc> usually inferred
05:44:35 <lifthrasiir> ~ and @ are gone, and more funny looking beasts like Rc<> Gc<> Box<> Cell<> RefCell<> are here to stay.
05:44:49 <Bike> why is &mut before the name though
05:44:51 <kmc> a given thing in memory can have zero or more & pointers, or exactly one &mut pointer to it
05:45:00 <kmc> &mut is a variant of & that lets you mutate through the pointer
05:45:08 <Bike> exactly one, like, at all?
05:45:23 <kmc> yes, well, things get "frozen"
05:45:34 <kmc> if I do let mut x = 3; f(&mut x)
05:45:51 <kmc> then I lose the ability to modify an x for as long as that reference lives
05:45:57 <mcpherrin> Bike: "self" is kinda a weird special case
05:46:06 <Bike> of course it is
05:46:11 <kmc> if f doesn't store it anywhere, then I get to modify it as soon as f returns
05:46:20 <mcpherrin> for example you'd have it: &mut ast::Item
05:46:30 <mcpherrin> so it's not "before the name" usually
05:46:55 * mcpherrin doesn't like rust's self handling right now, a little too special
05:46:56 <kmc> yeah, the & in «&foo: T» and in «&self» mean opposite things
05:47:08 <kmc> & in patterns means to remove a layer of indirection and look inside
05:47:12 <kmc> like any other "constructor" in a pattern
05:47:35 <kmc> but there's no way to pattern-destructure self in an args list, anyway
05:47:47 <Bike> is self the OO self btw
05:48:02 <kmc> impl Foo { fn f(&self) { ... } }
05:48:10 <kmc> defines a method that you would call like foo.f()
05:48:38 <kmc> it's not just sugar for f(foo) because it affects name lookup too
05:49:05 <kmc> if you can access a type then you can access all its methods, even though you didn't import them by name
05:49:22 <kmc> that's true for methods that are applied "directly" to the type like that
05:49:29 <kmc> mcpherrin: what do we call those?
05:49:42 <kmc> you can also define methods on a typeclass and then do «impl Bar for Foo»
05:49:54 <kmc> s/typeclass/trait/ but basically the same thing
05:50:03 <kmc> in that case the user also needs to import the trait Bar to see the methods
05:50:43 <lifthrasiir> kmc: I thought a special handling of self would be gone after UFCS, wouldn't it?
05:50:52 <kmc> I don't even know what UFCS stands for
05:51:02 <lifthrasiir> "Uniform Function Call Syntax" to be exact
05:51:04 <mcpherrin> lifthrasiir: I was about to say the same ;P
05:51:25 <kmc> lifthrasiir: oh, so you can write foo.f instead of |x| foo.f(x) ?
05:51:33 <kmc> that's good
05:51:41 <kmc> self has to at least be special wrt name resolution, though
05:51:49 <lifthrasiir> the details are not yet finalized but afaik is in discussion
05:51:54 <mcpherrin> kmc: so you can say method(foo, x) as well as foo.method(x)
05:51:59 <kmc> btw, rip "do" sugar
05:52:12 <mcpherrin> this is important for traits sharing names
05:52:44 <mcpherrin> impl A for Foo { fn m(){}} impl B for Foo { fn m() {}} breaks right now
05:52:57 <kmc> it was nerfed in order to support the front-of-rust-lang.org use case of "do spawn"
05:53:04 <kmc> and then it was useless so removed entirely
05:53:06 <fowl> UFCs are great, i use them in nimrod
05:53:13 <kmc> and now rust-lang.org doesn't have "do spawn" either
05:53:26 <fowl> x.f(y) #=> f(x,y) so much sense is made
05:53:41 <kmc> programming languages are like sausages
05:53:58 <fowl> good pizza topping
05:54:02 <Bike> sometimes i wonder how food scientists feel about that expression.
05:54:24 <kmc> you're at a big uni, you could find some and ask
05:54:47 <mcpherrin> there was a dude who designs lean cuisines doing an IAma thing on reddit a year or two ago...
05:55:02 <Bike> i'm not at the main campus right now but yeah i was thinking about all the books on sausage production in the library
05:55:29 <kmc> Bike: we also have both & and "ref" in patterns
05:55:34 <kmc> and they are opposites kinda
05:55:46 <Bike> there is more than one wrong way to do it
05:56:00 <kmc> match x { Some(&y) => ... } x has type Option<&T>, y has type T
05:56:17 <kmc> match x { Some(ref y) => ... } x has type Option<T>, y has type &T
05:56:31 <kmc> ok so they are exactly opposites
05:56:35 <mcpherrin> kmc: a lot of my early rust code was horrific for lack of understanding the & / ref relationship :p
05:56:58 <mcpherrin> I'd revert to "copy foo"ing all over instead of using borrowed pointers right
05:57:40 -!- tertu has joined.
05:57:53 <kmc> one of the many flaws of C++ is that there's no obvious indication when you lapse into that style
05:58:26 <kmc> i guess this is one reason that major style guides say to disable the copy constructor and operator= unless you have a good reason to use them
05:59:04 <kmc> although Rust still lets you do implicit copies of large POD
05:59:22 <kmc> and it lets you use generic stuff with a Clone bound that is not obvious
06:00:55 <kmc> Bike: as far as the core language is concerned, freezing and alias checking is all done at compile time
06:01:14 <kmc> but there are library types which use unsafe code to provide mutable cells with runtime checks
06:01:24 <Bike> i'm pretty sure i have no idea what you're talking about, you probably shouldn't bother :<
06:01:25 <kmc> you can go from an &RefCell<T> to an &mut T, roughly
06:02:17 <kmc> this weekend i got a few irl opportunities to talk at maximum speed about how cool rust is
06:02:23 <kmc> that's fun
06:03:17 -!- Phantom_Hoover has quit (Quit: Leaving).
06:03:39 <Bike> like a radio announcer!
06:03:52 <kmc> shachaf: lint plugins!
06:04:30 <shachaf> were they lin't plugins before they worked
06:05:03 <Bike> notecorelanguageisnotstableandmaychangeinunforseennontrivialfashions.bepreparedtofilecompilerbugs.mozillacorporationisnotatfaultifyouusethisinaspaceproberightnow
06:06:46 <mcpherrin> I'm pretty happy with a lot of the direction Rust is going, though I think we'll need to re-sugar the langauge once it's settled down semantically
06:07:41 <mcpherrin> kmc: remember when rust was the exciting garbage-collected language with typestate :p
06:07:48 <kmc> no I don't
06:09:19 <kmc> I like telling people who've only used high level languages about the bizarre forms of undefined behavior in C, and then ending it with "this language and its relatives are used for most systems in planes, cars, medical devices, nuclear reactors, etc."
06:10:13 <mcpherrin> kmc: I'd still trust C in a plane over, say, python :p
06:10:24 <Bike> math can't even define 0^0, therefore we have all been doomed for centuries
06:10:39 <kmc> did you ever see the C++ coding standards for the F-35 Joint Strike Fighter
06:10:48 <kmc> www.stroustrup.com/JSF-AV-rules.pdf
06:11:04 <mcpherrin> I recall reading them but remember zero content
06:11:19 <kmc> i mostly recall being scared about planes that run C++
06:11:57 <M28> Bike, however, most teorems assume 0⁰ = 1
06:12:13 <Bike> wait, is this the eurofighter
06:12:25 <kmc> also this weekend I got two opportunities to explain what the C99 "restrict" keyword does and why it's useful
06:12:29 <Bike> no, it isn't. that woudl be funny
06:12:29 <M28> mostly because they're too lazy to define a case for when the exponent is 0
06:12:46 <kmc> the french parts of the eurofighter are programmed in ocaml
06:12:51 <M28> kmc, and did you explain that it's almost never used because no one bothers to?
06:13:06 <M28> in fortran, "restrict" is the default
06:13:15 <Bike> really? i suppose that makes sense
06:13:27 <Bike> that makes the grounding of the french air force from that one virus seem a bit weird
06:13:28 <kmc> Rust is even more draconian about aliasing
06:14:01 <M28> I like how rust does it, but it may be difficult to make that change
06:14:16 <M28> *to adapt to that change
06:14:21 <kmc> oh but I forgot to talk about the reverse memcpy aliasing flash plugin sound fuckup
06:14:22 <Bike> f-35 also has some ada from the -22, it seems
06:14:31 <kmc> -fun-times
06:15:10 <zzo38> I think 0^0=1 is most sensible kind of thing to me
06:16:01 <Slereah> 0^0 works by analytic continuation of x^0
06:16:01 <Bike> yes yes everything must have a definition isn't that so
06:16:06 <M28> it is, but then you can't assume that "0^n = 0" everywhere
06:16:23 <mcpherrin> there's a good page on 0^0 at http://www.askamathematician.com/2010/12/q-what-does-00-zero-raised-to-the-zeroth-power-equal-why-do-mathematicians-and-high-school-teachers-disagree/
06:16:23 <Slereah> Kind of a big discontinuity
06:16:38 <M28> at least it's not like 1/0 :)
06:17:00 <M28> with limits, on both directions
06:17:12 <Slereah> for instance if you do it in the one point compactification of R or C
06:17:17 <Bike> why did i bother using an example
06:18:16 <M28> I was using Microsoft Office Word the other day to write equations
06:18:19 <M28> it's... not bad
06:18:32 <M28> I mean, it could be better, but it supports some neat stuff
06:18:37 <Slereah> Donald Knuth did not die in vain!
06:18:42 <zzo38> Zero to power of negative numbers may be undefined though.
06:18:46 <mcpherrin> yeah I surprisingly don't hate the equation editor in word
06:19:37 <Bike> i was supposed to use the equation editor to do chem homework. so weird
06:19:55 <M28> I found it quite intuitive
06:20:05 <M28> easier than latex IMO
06:20:18 <M28> not as powerful as it once you need to do complicated stuff, though
06:20:27 <Bike> weird as in weird that i was supposed to
06:20:45 <Bike> not really a lot of math in gen chem.
06:20:49 <mcpherrin> Maple's math document thing is pretty awesome if you want WYSIWYG mathing
06:21:00 <mcpherrin> (not to mention it can do the actual math as you go too)
06:22:09 <Slereah> I really like LaTeX because, through my studies, I read some terrible things
06:22:11 <Bike> subscripts and superscripts alone aren't so great for writing out a beta particle or whatever, i guess.
06:22:16 <Slereah> I once read a theoretical physics thesis
06:22:21 <Slereah> Entirely done on typewriter
06:22:45 <zzo38> I find Plain TeX is really good to write math, especially since I can have macros in the file too. (It is good for many other things, too.)
06:23:08 <M28> I like to give people the number "(-1) ^(-i)" and ask them what value it is
06:23:15 <Slereah> Two macros that are especially good are
06:23:21 <Bike> it's some bullshit with e right
06:23:23 <Slereah> integral from -infinity to infinity
06:23:28 <M28> most people that haven't had any complex numbers class won't guess that it's 23.1406...
06:23:31 <kmc> yeah proper mathematical typesetting used to be hella expensive
06:23:33 <M28> it's kinda weird
06:23:46 <Slereah> They are very long to type and happen all the time
06:24:07 <kmc> http://mathworld.wolfram.com/ComplexExponentiation.html jeeez
06:24:10 <M28> not if you're working with discrete maths or any other area of math >_>
06:24:17 <Bike> right it's uh, exp(-iln(-1)), so exp(pi)
06:24:32 <Slereah> But still quite often when you work in REAL MATH
06:24:41 <M28> Slereah, :(
06:24:56 <Bike> complex exponentiation is cool kmc! it goes in circles!!
06:25:00 <lifthrasiir> M28: many people doesn't know about complex numbers either
06:25:15 <M28> I only had to use integrals and shit in calculus and analytical geometry...
06:25:36 <M28> lifthrasiir, lots of non-math-stuff majors
06:25:38 -!- Slereah_ has joined.
06:25:40 <zzo38> If someone aske me about "(-1) ^(-i)" then first things I would say is, "I don't know". And then, to try to figure out by computer.
06:26:19 <M28> Slereah, you need params
06:26:28 <Bike> if you remember that a^b = exp(b*ln(a)) your life shall improve
06:26:36 <zzo38> For 1/2 macro, do you mean something like: \def\onehalf{{1\over2}}
06:26:38 <lifthrasiir> http://www.wolframalpha.com/input/?i=%28-1%29%5E%28-i%29 indeed, it gives a correct answer
06:27:07 <lifthrasiir> (no, I think WP does have a template for this)
06:27:12 <M28> Slereah, reverse polish notation master race reporting in
06:27:16 <Bike> ½ durbadurbdurb
06:27:27 <zzo38> lifthrasiir: Well, it isn't what I was thinking, but yes it is one way. I meant that the program in TI-92 calculator will make the calculations, or to use any other local softwares rather than connecting to internet in order to do it.
06:27:47 <Bike> i should probably get a cas instead of using wolfram all the time, but, lazy
06:28:09 <Slereah_> I guess a useful macro if you work in discrete math would be
06:28:35 <Bike> and those cas's that print out fractions on the terminal, ugh
06:28:54 -!- Slereah has quit (Ping timeout: 258 seconds).
06:28:55 <M28> Bike, I almost never find an use for that definition, except this one I guess
06:29:10 <Bike> circles man, circles
06:29:20 -!- password2 has joined.
06:29:44 <kmc> here are some latex macros i wrote long ago https://gist.github.com/kmcallister/7677e262d64cd0a5ca45
06:29:53 <M28> you don't even need that formula to solve that though
06:30:09 <M28> if you replace (-1) with e^(pi * i)
06:30:43 <M28> then you end up with an even more fun thing to solve
06:31:44 <Bike> "how does anyone on Earth understand the guts of \LaTeX?" any paper on the guts would, unfortunately, be written in gutsy latex
06:31:53 <Bike> i wonder if i'll ever actually have to use tex in my life
06:32:23 <M28> there's a mandatory class on scientific writing in compsci in my uni
06:32:29 <M28> you learn latex there
06:33:41 <Jafet> Google Docs. Teach the controversy
06:41:55 <shachaf> kmc: how often do people make "rusty" puns about rust
06:42:22 <kmc> not that often
06:44:44 <kmc> shachaf: it's really hard to apply equational reasoning in Rust :/
06:44:54 <kmc> because of lifetimes and moves and stuff
06:45:20 <kmc> lifetime inference is imperfect
06:46:07 <kmc> shachaf: also with lifetimes, contravariant is the "normal" case and covariant is the unusual case
06:46:15 <kmc> though this is somewhat just a matter of notation
06:48:44 <kmc> if 'a ⊆ 'b then &'b T <: &'a T
06:53:52 <kmc> i only really understood integration by parts once I saw a diagram of it drawn on the wall in tetazoo
06:54:50 <olsner> the rust compile steps in rustc's build system are called "oxidize", that's sort of a pun
06:55:20 <olsner> it's fun because there's some random thing written in rust that's called oxidize too
06:55:37 <HackEgo> [wiki] [[Gentzen]] http://esolangs.org/w/index.php?diff=39706&oldid=39556 * Zzo38 * (+47)
06:55:44 <kmc> i guess it was sort of like this one http://compasstech.com.au/TNSINTRO/TI-NspireCD/mystuff/calc_parts/parts.jpg
06:55:48 <kmc> but less fancy
06:57:22 -!- stuntaneous has quit (Ping timeout: 245 seconds).
06:57:23 <Jafet> If communists ported GNU to rust, would it be called redox
06:57:35 <kmc> red oxtober
06:59:00 <Bike> kmc versus lebesgue integration, FIGHT
07:05:04 <mroman> someone commited to my github repository
07:05:07 <mroman> https://github.com/FMNSSun/Burlesque/commit/15138b50ff74e753fa188dee9d8daad9cac1ffdb
07:05:11 <mroman> ^- how's that possible?
07:05:31 -!- password2 has quit (Ping timeout: 240 seconds).
07:09:44 <olsner> github definitely has some magic object store for git repos (to share objects between forks, if nothing else), so it might be possible for anyone to upload objects but not move the tags/branches
07:09:59 <olsner> is that commit included in any branch/tag?
07:10:20 <mroman> Thta commit was submitted with e-mail root@debian
07:10:39 <shachaf> It was more than a year ago.
07:10:40 <mroman> maybe github looks at the e-mail adress to find out who's the committer
07:12:39 <shachaf> There is also this commit: https://github.com/FMNSSun/Burlesque/commit/0ebd91cecb6f4fada2a7107cd8f3ec722372cb5d
07:12:51 <shachaf> Maybe someone just sent you a "pull request" last year and you forgot?
07:13:14 <olsner> mroman: it does - so it's fairly easy to "fake" commits as any other github user by just entering them as the author
07:16:07 <fowl> mroman, its also possible they changed their username and you dont remember it
07:17:08 <olsner> if the email was root@debian, the likely explanation is that it's you or someone else on the project who made that on a computer before remembering to configure their name in git
07:17:41 <mroman> fowl: Nobody ever helped me on Burlesque
07:17:49 <mroman> there was never anybody contributing code other than me
07:18:13 <mroman> olsner: Looks like I made that change from my linux VM
07:18:55 <olsner> I saw some commits in the repo as mroman too, I think
07:20:40 <mroman> Different machines have different git configs I guess :)
07:20:55 <mroman> windows uses FMNSSun and Linux Roman Muentener apparentely
07:21:05 <olsner> you should sort that out
07:23:26 <mroman> Is Control.OldException still available?
07:25:18 <mroman> catch doesn't work anymore with Control.Exception
07:28:15 -!- jconn has quit (Remote host closed the connection).
07:29:21 -!- blsqbot has joined.
07:29:34 <mroman> Looks like it's still working
07:30:18 <mroman> !blsq 99989899676884654632432432ro)S[
07:30:19 <blsqbot> Ain't nobody got time fo' dat!
07:31:14 <mroman> ok. but single line output only.
07:31:44 <olsner> hmm, how does 99989899676884654632432432 encode that string?
07:33:55 -!- aretecode has quit (Ping timeout: 240 seconds).
07:33:57 <blsqbot> {"" "a" "b" "ab" "c" "ac" "bc" "abc"}
07:34:00 <blsqbot> {"" "a" "b" "ab" "c" "ac" "bc" "abc" "d" "ad" "bd" "abd" "cd" "acd" "bcd" "abcd"
07:34:07 <mroman> !blsq "abcdefghijklmnopqr"R@
07:34:08 <blsqbot> Ain't nobody got time fo' dat!
07:34:35 <mroman> olsner: The small timeout is because I can't put a memory limit
07:35:32 <olsner> might be better added into the interpreter itself though
07:37:09 <mroman> olsner: I meant: There's no memlimit thingy like System.Timout that I can just embed in the interpreter easily
07:38:55 -!- Tritonio has joined.
07:39:15 -!- blsqbot has quit (Remote host closed the connection).
07:39:29 <mroman> this catch doesn't catch everything :(
07:39:53 -!- slereah has joined.
07:41:21 -!- blsqbot has joined.
07:41:30 <blsqbot> That line gave me an error
07:43:18 <mroman> olsner: There are two timeouts actually
07:43:37 <mroman> it launches an interpreter with readProcess
07:43:47 <mroman> the interpreter has a 100 microsecond timeout itself
07:43:56 <mroman> and the ircbot has a 3 second timeout for readProcess
07:44:45 <mroman> I'm not sure whether this evaluate $!! kills lazyness though
07:48:35 <mroman> myname: except it doesn't have dyads, monads and triads and quadads and pentads
07:50:25 <blsqbot> {{1 3 5 7 9} {2 4 6 8 10}}
07:51:04 <mroman> It's sort of a J-like language I guess
07:51:15 <mroman> although I'm pretty sure J users would heavily disagree with that.
07:54:42 <mroman> myname: You can golf in it on golf.shinh.org
07:57:30 <mroman> !blsq 1487796867 36%B!
07:58:35 <mroman> base 36 should be a standard for compressing numbers .
08:00:26 <blsqbot> {'a 'b 'c 'd 'e 'f 'g 'h 'i 'j 'k 'l 'm 'n 'o 'p 'q 'r 's 't 'u 'v 'w 'x 'y 'z}
08:00:34 <blsqbot> {'a 'b 'c 'd 'e 'f 'g 'h 'i 'j 'k 'l 'm 'n 'o 'p 'q 'r 's 't 'u 'v 'w 'x 'y 'z}
08:00:48 <mroman> ah. That's why I implemented an @ prefix some time ago
08:03:11 <mroman> shachaf: but base 36 is neatly from 0..9 ++ a..z
08:03:34 <shachaf> i think base 32 usually drops 0 and 1 because of ambiguity with o and i
08:05:23 <mroman> for human written base 32 stuff... ok
08:07:13 <shachaf> se what else are you using this for?
08:08:08 <mroman> He doesn't answer in queries :(
08:08:22 <mroman> shachaf: I'm using it for golfing and homework usually
08:08:53 <shachaf> why not base 64 or something?
08:09:35 <shachaf> there are lots of different characters. i don't see why you'd pick 36 other than for interacting with humans
08:14:22 <mroman> " The characters "0" and "O" are easily
08:14:23 <mroman> confused, as are "1", "l", and "I""
08:14:37 <mroman> Why would a human attempt to decode base32 encoded text
08:15:20 <mroman> also using = as pad for urls is probably not a good idea
08:17:03 <shachaf> why are you encoding a thing as human-
08:17:11 <shachaf> language characters if not for humans to read
08:18:23 <mroman> why do you ban characters from an encoding because humans confuse them
08:18:33 <mroman> no human's gonna decode it by hand so why bother
08:19:29 <shachaf> so what's the point of base 36 here
08:21:11 <shachaf> where you don't mean a sentence seriously if you put a space before the "."
08:21:41 <shachaf> i asked a german friend about it once and he had never heard of it
08:22:31 <shachaf> but now i understand 00:58 <mroman> base 36 should be a standard for compressing numbers .
08:23:09 * shachaf $ grep 'mroman.* \.$' logs/esoteric/ALL
08:25:43 <mroman> Maybe it's a community thing and not a german thing.
08:26:13 <shachaf> Well, I'll remember to look for it .
08:28:37 <mroman> because 1 is on the same key as ! and elf means 11 in german
08:28:52 <shachaf> Yes, I think that's common in English too.
08:31:48 -!- Patashu has joined.
08:42:26 -!- Tritonio has quit (Ping timeout: 252 seconds).
08:50:30 -!- Patashu has quit (Disconnected by services).
08:50:30 -!- Patashu_ has joined.
08:58:08 -!- edwardk has joined.
09:03:59 -!- KingOfKarlsruhe has joined.
09:35:48 <blsqbot> ERROR: You should not transpose what you can't transpose. Yes this is an eastere
09:38:40 <mroman> I guess I can't send null-bytes over the IRC
09:43:03 <mroman> burlesque doesn't really have escape sequences
09:43:21 <mroman> i.e to embed a newline into a string you really use a newline :)
09:44:19 <blsqbot> ERROR: Burlesque: (++) Invalid arguments!
09:44:26 <blsqbot> ERROR: Burlesque: (\\) Invalid arguments!
09:45:10 <blsqbot> "\NUL\SOH\STX\ETX\EOT\ENQ\ACK\a\b\t\n\v\f\r\SO\SI\DLE\DC1\DC2\DC3\DC4\NAK\SYN\ET
09:46:23 <mroman> on the other hand... if you print a string it will use escape sequences :)
09:46:36 <mroman> unless you pretty print it
09:48:03 <mroman> You can make me computer beep if you produce \a
09:48:12 <mroman> because the irc bot logs output to stdout :D
10:00:44 -!- KingOfKarlsruhe has quit (Read error: Connection timed out).
10:06:14 -!- Slereah_ has quit (Ping timeout: 255 seconds).
10:07:45 -!- Slereah_ has joined.
10:08:50 -!- boily has joined.
10:11:24 -!- drdanmaku has quit (Quit: Connection closed for inactivity).
10:23:35 <M28> I wonder if we could do a challenge
10:23:58 <M28> write a simple esoteric language, give no fucking explanation about it, and just provide a bot that evals what you say in a certain channel
10:24:10 <M28> the goal is figuring out how to write "Hello, World!"
10:28:06 <mroman> M28: there's an explanation in the esowiki .
10:28:29 <mroman> and that's not the irony dot. That's the emphasize my point dot
10:28:30 <M28> I'm not talking about blsqbot
10:29:10 <mroman> It can only send to one channel :(
10:29:32 <Taneb> Is it written in Burlesque?
10:29:49 <mroman> That would be tough without I/O.
10:30:08 <mroman> also... output is only produce on termination
10:30:17 <mroman> so that would make it pretty much impossible
10:30:42 <mroman> (i.e. a thruth-machine can't really be implemented in burlesque
10:31:08 <mroman> Maybe it'll work for some scenarios thanks to lazyness and whatnot)
10:31:58 -!- idris-bot has quit (Quit: Terminated).
10:32:30 -!- metasepia has joined.
10:52:43 -!- Tritonio has joined.
10:59:58 -!- boily has quit (Quit: Poulet!).
11:00:00 -!- metasepia has quit (Remote host closed the connection).
11:04:23 <mroman> Burlesque isn't something you'll write an interpreter for in a couple of days
11:04:31 <mroman> Mind that there are probably 300 Commands
11:04:47 <mroman> and those 300 Commands do all different kinds of things depending on arguments
11:05:00 <mroman> !blsq {1 2 3 4 5}avavpd
11:05:02 <mroman> !blsq {1 2 3 4 5}avavpdpd
11:06:03 <blsqbot> {{1 2 3} {2 1 3} {3 2 1} {2 3 1} {3 1 2} {1 3 2}}
11:06:29 <mroman> I dare you writing an interpreter for it in Brainfuck
11:06:44 <mroman> you'd even have to implement lazy evaluation
11:10:54 <blsqbot> ERROR: Burlesque: (e!) Invalid arguments!
11:11:00 <blsqbot> {{1 2 3} {2 1 3} {3 2 1} {2 3 1} {3 1 2} {1 3 2}}
11:35:06 -!- idris-bot has joined.
11:40:15 -!- Sprocklem has joined.
11:45:30 <HackEgo> [wiki] [[Gentzen]] http://esolangs.org/w/index.php?diff=39707&oldid=39706 * Keymaker * (+4) Made "Truth-machine" link to that page.
11:47:36 -!- Tritonio has quit (Ping timeout: 252 seconds).
11:48:42 -!- Sgeo has quit (Read error: Connection reset by peer).
12:53:33 -!- Sprocklem has quit (Quit: brb).
12:58:28 -!- blitter64 has joined.
13:03:42 -!- yorick has joined.
13:04:18 -!- ais523 has joined.
13:06:00 * ais523 reads the Perl 5.20 delta
13:08:51 -!- MDream has changed nick to MDude.
13:13:18 -!- {hk3380} has joined.
13:18:57 -!- MindlessDrone has joined.
13:20:37 -!- blitter64 has quit (Ping timeout: 240 seconds).
13:23:55 -!- Patashu_ has quit (Ping timeout: 252 seconds).
13:25:40 -!- Sorella has joined.
13:26:58 -!- ais523 has quit (Ping timeout: 252 seconds).
13:38:30 -!- password2 has joined.
13:39:40 -!- password2 has quit (Max SendQ exceeded).
13:56:23 -!- password2 has joined.
14:18:30 -!- nooodl has joined.
14:42:54 -!- ais523 has joined.
14:56:35 -!- hogeyui has quit (Ping timeout: 252 seconds).
15:10:06 -!- hogeyui has joined.
15:13:17 -!- Sprocklem has joined.
15:15:08 -!- Slereah_ has quit (Ping timeout: 255 seconds).
15:15:38 -!- Slereah_ has joined.
15:19:41 <HackEgo> [wiki] [[MetaGolfScript]] N http://esolangs.org/w/index.php?oldid=39708 * 194.29.34.162 * (+1932) Created page with "'''MetaGolfScript''' is a family of programming languages, designed to allow zero length programs to be written, in order to win code-[[golf]] contests. == Overview == The fa..."
15:30:59 -!- ais523 has quit.
15:31:40 -!- M28_ has joined.
15:34:23 -!- M28 has quit (Ping timeout: 258 seconds).
15:41:25 -!- {hk3380} has quit (Ping timeout: 252 seconds).
15:41:41 -!- hogeyui has quit (Ping timeout: 255 seconds).
15:46:30 -!- hogeyui has joined.
15:50:54 -!- edwardk has quit (Quit: Leaving...).
15:53:17 -!- Phantom_Hoover has joined.
15:53:19 -!- Phantom_Hoover has quit (Changing host).
15:53:19 -!- Phantom_Hoover has joined.
15:58:58 -!- password2 has quit (Ping timeout: 240 seconds).
15:59:49 -!- Phantom_Hoover has quit (Ping timeout: 240 seconds).
16:01:34 -!- slereah has quit (Quit: Leaving).
16:25:31 -!- sebbu has quit (Ping timeout: 240 seconds).
16:35:01 -!- drdanmaku has joined.
16:38:38 <mroman> worst abuse of common sense ever
16:41:10 -!- {hk3380} has joined.
16:44:30 -!- MoALTz has joined.
16:49:17 <mroman> also if you know the winning language
16:49:24 <mroman> everybody else will know what your program was
16:49:42 <mroman> that'd pretty much suck for no-deadline contests
16:55:40 <mroman> !blsq 255rz)L[209180605381204854470575573749277224 256dgsi
16:55:41 <blsqbot> That line gave me an error
16:58:33 <mroman> !blsq 255rz)L[209180605381204854470575573749277224 256dgsi\[
16:58:33 <blsqbot> That line gave me an error
16:58:50 <mroman> !blsq 255rz)L[209180605381204854470575573749277224 256dgsi\[
16:58:50 <HackEgo> [wiki] [[Talk:MetaGolfScript]] N http://esolangs.org/w/index.php?oldid=39709 * GreyKnight * (+298) Created page with "== pg wishes he was this smaert == Well, it's certainly esoteric, but: : "[...] in order to win code-golf contests." I think you're making some assumptions about the contest j..."
16:59:06 <mroman> how does he encode Hello, world?
17:01:09 -!- conehead has joined.
17:04:15 -!- Slereah_ has quit (Read error: Connection reset by peer).
17:04:32 -!- Slereah_ has joined.
17:08:11 <mroman> !blsq "\'Hello, world!\'")**256ug
17:08:11 <blsqbot> 178006462281531046238104240886391074
17:08:43 <mroman> !blsq 255rz)L[178006462281531046238104240886391074 256dgsi%\[
17:15:11 <Bike> nice n readable
17:17:32 -!- mihow has quit (Quit: mihow).
17:20:19 -!- sebbu has joined.
17:20:42 <int-e> `` dc <<<178006462281531046238104240886391074P
17:20:58 -!- sebbu has quit (Changing host).
17:20:59 -!- sebbu has joined.
17:21:00 <int-e> `` dc <<<178006462281531046238104240886391074P
17:28:33 <nooodl> mroman: 0 = "", 1 = "\0x00", 2 = "\x01"...
17:43:53 -!- Sprocklem has quit (Ping timeout: 252 seconds).
17:45:05 <shachaf> kmc: https://code.google.com/p/go/issues/detail?id=6776
17:45:28 -!- mihow has joined.
17:50:10 <mroman> 0 is the empty program?
17:50:20 <mroman> !blsq 255rz)L[209180605381204854470575573749277223 256dgsi\[
17:50:41 -!- password2 has joined.
17:50:53 <mroman> ok. than you can't treat it as a base encoded thingy
17:51:09 <mroman> Bike: nice n very readable
17:51:28 <mroman> dg is digits, si is selectindices and \[ is concat
17:51:36 -!- password2 has quit (Max SendQ exceeded).
17:51:36 <blsqbot> {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 28 29
17:51:59 <mroman> can't print that because it has null bytes and stuff in it
17:52:13 <mroman> !blsq "abc"{1 1 0 0 2}si
17:52:29 -!- password2 has joined.
17:53:07 -!- password2 has quit (Max SendQ exceeded).
17:57:01 -!- tertu has quit (Ping timeout: 240 seconds).
17:58:40 <mroman> !blsq "hi this is a test"{<-}ww
18:01:07 -!- {hk3380} has quit (Ping timeout: 240 seconds).
18:05:56 -!- {hk3380} has joined.
18:10:35 -!- not^v has joined.
18:15:18 -!- tertu has joined.
18:15:45 -!- tertu has quit (Client Quit).
18:20:38 -!- Slereah_ has quit (Ping timeout: 240 seconds).
18:20:38 <blsqbot> {ERROR: Burlesque: (_+) Invalid arguments!}
18:21:03 -!- Slereah_ has joined.
18:24:14 <Bike> "Code intended to support native EBCDIC platforms will be removed from Perl before 5.22.0"
18:25:14 -!- mhi^ has joined.
18:35:24 -!- glogbackup has joined.
18:37:03 -!- glogbackup has quit (Remote host closed the connection).
18:38:46 -!- MindlessDrone has quit (Quit: MindlessDrone).
18:38:57 -!- rottytooth has joined.
18:42:00 <kmc> one of the food trucks has a logo like the eye in the pyramid on a dollar bill but the floating eye is replaced by a pizza slice
18:42:02 <zzo38> I have idea, it is making up a programming language for making random distribution data (such as, 4d6 drop lowest, or win/loss ratio at a crap game, or poker hands, or whatever), and then it can read the program in order to determine the expected probability of results, and then run it using a given random number generator to see how closely it matches.
18:43:04 -!- glogbackup has quit (Remote host closed the connection).
18:43:10 <Bike> kmc: excellent.
18:56:12 -!- AnotherTest has joined.
19:08:13 -!- sebbu has quit (Ping timeout: 252 seconds).
19:11:03 -!- evalj has joined.
19:11:53 -!- mihow has quit (Quit: mihow).
19:12:18 -!- edwardk has joined.
19:13:06 -!- mihow has joined.
19:13:14 <HackEgo> [wiki] [[Secretary]] http://esolangs.org/w/index.php?diff=39710&oldid=37689 * 12.33.168.146 * (-1) /* Humor */
19:13:43 -!- sebbu has joined.
19:14:20 -!- sebbu has quit (Changing host).
19:14:20 -!- sebbu has joined.
19:15:04 -!- conehead has quit (Quit: Textual IRC Client: www.textualapp.com).
19:18:14 -!- AnotherTest has quit (Ping timeout: 252 seconds).
19:23:04 -!- mihow has quit (Quit: mihow).
19:24:43 -!- not^v has quit (Quit: http://i.imgur.com/Akc6r.gif).
19:29:58 -!- edwardk has quit (Ping timeout: 252 seconds).
19:31:02 -!- MDude has quit (Ping timeout: 252 seconds).
19:32:35 -!- edwardk has joined.
19:38:45 <mroman> is there some congruence with the distribution of 0,1 for numbers in base 2?
19:39:20 <mroman> i.e. the ratio of ones to zeroes in the binary representation of a number N
19:43:47 <mroman> other than 2^x-1 have 100% ones
19:44:00 <mroman> and 2^x have 1/ln(x) probably
19:45:21 <Slereah_> Since all of them have to be there
19:49:28 -!- {hk3380} has quit (Ping timeout: 265 seconds).
19:51:12 -!- {hk3380} has joined.
19:54:07 -!- mhi^ has quit (Quit: Lost terminal).
19:57:21 -!- mhi^ has joined.
20:02:31 -!- mihow has joined.
20:04:27 -!- Sprocklem has joined.
20:12:16 <kmc> http://www.munidiaries.com/2014/05/27/no-one-ever-said-no-cooking-on-muni/
20:25:45 -!- Sprocklem has quit (Quit: brb).
20:26:41 -!- conehead has joined.
20:27:18 -!- Sprocklem has joined.
20:32:22 -!- mihow has quit (Quit: mihow).
20:32:41 -!- blsqbot has quit (Read error: Connection reset by peer).
20:33:23 -!- mihow has joined.
20:42:49 -!- mhi^ has quit (Quit: Lost terminal).
20:43:01 -!- tromp_ has quit (Remote host closed the connection).
20:55:45 -!- Patashu has joined.
20:56:40 <b_jonas> hey look! http://www.icfpcontest.org/ is updated!
21:06:04 <b_jonas> it doesn't seem to have any teasers though
21:06:26 <zzo38> What statistics should I put other than the quantile and standard deviation?
21:07:30 -!- myndzi has quit (Quit: .).
21:07:53 -!- myndzi has joined.
21:15:06 <b_jonas> "< zzo38> I have idea, it is making up a programming language for making random distribution data (such as, 4d6 drop lowest, or win/loss ratio at a crap game, or poker hands, or whatever), and then it can read the program in order to determine the expected probability of results, and then run it using a given random number generator to see how closely it matches."
21:17:53 -!- Sprocklem has quit (Quit: Bye).
21:19:59 <zzo38> No I meant for SQL function
21:20:36 <Bike> Cauchy distribution
21:20:46 <Bike> solomonoff distribution
21:21:05 <HackEgo> puzzicoin 13.4coin ircutecoin infocoin oof!coin revercoin convesiacoin tfikntythestidcoin achedcoin fordcoin yicleadcoin fiocoin nerersesspridcoin clatlicvrecoin adminecoin nulliicoin ooksancoin estcoin cardcoin taxcoin
21:25:21 -!- Patashu has quit (Ping timeout: 252 seconds).
21:25:56 <b_jonas> zzo38: how does it take its input? is it an aggregate function?
21:26:18 <zzo38> So far I have functions QUANTILE/2, MEDIAN/1, and STDDEV/1.
21:26:30 <b_jonas> dunno, perhaps arbitrary moment and arbitrary central moment
21:26:31 <zzo38> (MEDIAN(x) is just short for QUANTILE(x,0.5))
21:27:21 <b_jonas> also, maybe something like QUANTILE that takes an integer ordinal instead of a fractional ratio
21:27:27 <zzo38> I made up a program in SQL for ratio of ones to zeroes in the binary representation of a number N. It is: WITH X(X,Y) AS (SELECT 0,'0' UNION ALL SELECT X+1,BASECONV(X+1,10,2) FROM X LIMIT 128) SELECT CAST(SUBSTRING_COUNT(Y,'1') AS REAL)/SUBSTRING_COUNT(Y,'0') FROM X;
21:28:05 <Bike> the ratio is always zero since there are as many leading zeroes as you want, duh
21:28:33 <zzo38> b_jonas: If you want an integer offset then you can use the OFFSET clause, though.
21:29:07 <zzo38> (You can also use ORDER BY, LIMIT, and OFFSET if for some reason you want the uninterpolated median of non-numerical data.)
21:29:51 <b_jonas> zzo38: I don't think you can do that if you GROUP BY and want a quantile from each group
21:30:04 <Bike> harmonic mean! what if i want to compute that
21:30:32 <Bike> or variance. i guess that would be good.
21:30:36 <zzo38> b_jonas: O, yes, I forgot that
21:31:12 <kmc> println!("{}", uncomment!(/* 3 */))
21:31:18 <b_jonas> zzo38: mind you, I think you can still do ORDER BY in a subquery, but that gets ugly and possibly inefficient
21:31:24 <zzo38> kmc: What is that?
21:31:32 <Bike> i'm afraid, kmc
21:31:36 <zzo38> b_jonas: Yes it is what I was thinking of, too
21:31:39 <kmc> a silly macro
21:31:51 <kmc> one which you can't actually write, but we were discussing if it would be possible or not with a certain change
21:31:54 <b_jonas> kmc: what language is that?
21:32:02 <Bike> why is uncomment effectful
21:32:08 <kmc> that's not what the bang means
21:32:16 <kmc> b_jonas: you can't actually do that, though
21:32:21 <kmc> Bike: it means macro / syntax extension
21:32:34 <Bike> println is a macro?
21:32:37 <zzo38> I don't think that it is necessary to be able to write such a macro, but even if a change allows it, that is not necessarily a problem
21:32:44 <Bike> no varargs yet or something?
21:32:45 <kmc> yes, because the format string is parsed and typechecked at compile time
21:33:06 <kmc> we support calling variadic C function but otherwise there is no varargs, yeah
21:33:29 <kmc> but handling format strings at compile time seems better, anyway
21:33:35 <kmc> although I don't know how it interacts with i18n
21:33:48 <Bike> lacking the ability at all to do it at runtime though, that rubs me the wrong way
21:33:51 <kmc> GCC also typechecks format strings at compile time, using a hardcoded hack
21:33:54 <zzo38> Is the standard deviation the square root of the variance? That would be easy to fix
21:33:58 <int-e> > Test.Printf.printf "%s" () :: String
21:34:00 <lambdabot> Not in scope: ‘Test.Printf.printf’
21:34:00 <lambdabot> ‘Text.Printf.printf’ (imported from Text.Printf),
21:34:00 <lambdabot> ‘Text.Printf.hPrintf’ (imported from Text.Printf)
21:34:05 <int-e> > Text.Printf.printf "%s" () :: String
21:34:06 <lambdabot> No instance for (Text.Printf.PrintfArg ())
21:34:06 <lambdabot> arising from a use of ‘Text.Printf.printf’
21:34:11 <kmc> Bike: I'm not sure if we have that ability right now but it's not too hard to provide, anyway
21:34:18 <int-e> > Text.Printf.printf "%s" 42 :: String
21:34:19 <lambdabot> "*Exception: printf: bad formatting char 's'
21:34:36 <Bike> i'd rather println be a function with a nicely incorporated compile-time function to deal with the usual stuff, but nobody seems to want to do this
21:34:57 <Bike> zzo38: there's this whole thing with bessel's correction though.
21:35:02 <kmc> Bike: there is a println function too
21:35:14 <zzo38> What is bessel's correction doing with it?
21:35:17 <kmc> println!("...", ...) => println(format!("...", ...)) roughly
21:35:42 <int-e> with a template haskell version, which is pretty much a macro, it could produce a type error instead.
21:35:51 <Bike> zzo38: the standard deviation (variance) of a sample and the standard deviation (variance) of a population are computed differently
21:36:11 <kmc> although it's not in scope by default
21:36:19 <zzo38> Bike: Yes I know that, but is it relevant?
21:36:20 * int-e wonders whether ocaml's Format.printf machinery can be reproduced in a library
21:36:32 <Bike> well it's relevant if you're just calling it "stddev" without saying which it is
21:36:33 <kmc> and I think println(format!(...)) has an intermediate allocation that println!() avoids
21:36:38 -!- oerjan has joined.
21:36:46 <b_jonas> zzo38: sure it is, in the sense that you should document which one the function computes
21:36:46 <kmc> int-e: don't believe so
21:36:47 <kmc> maybe in Camlp4 / Camlp5 tho
21:37:00 <kmc> 23:12 < kmc> the french parts of the eurofighter are programmed in ocaml
21:37:06 <kmc> i wonder if anybody believed me when i said that
21:37:13 <Bike> am i... a fool
21:37:18 <kmc> not really, but it's a lie
21:37:27 <kmc> also there's no santa claus
21:37:29 <Bike> "they're actually in prolog"
21:37:38 <int-e> kmc: I also don't believe so but I don't know :)
21:37:56 <b_jonas> zzo38: and document what the functions do with NULL and with NaN values
21:38:22 -!- MDude has joined.
21:38:57 <zzo38> Nulls are just ignored. Anything else is just used as it is. Now I wrote that in the documentation, too.
21:40:00 -!- conehead has quit (Quit: Textual IRC Client: www.textualapp.com).
21:40:39 <b_jonas> zzo38: I have another idea. you could add two-argument aggregate functions for the covariance of pairs of values.
21:40:43 -!- boily has joined.
21:41:08 <zzo38> OK, how does that work?
21:41:09 <b_jonas> obviously that's only for convenience, because just like the standard deviation, you can mostly just compute that from avg(...)
21:41:43 <b_jonas> zzo38: dunno, I'm too tired to tell the right way now, and I don't wish to embarrass myself by telling wrong stuff
21:41:57 <b_jonas> look up the numerically stable formulas somewhere
21:42:25 <b_jonas> you are using the numerically stable formula for standard deviation by the way, right?
21:44:45 -!- Phantom_Hoover has joined.
21:45:09 -!- Phantom_Hoover has changed nick to Guest32551.
21:46:50 -!- nooodl_ has joined.
21:49:18 -!- edwardk has quit (Ping timeout: 240 seconds).
21:50:02 -!- nooodl has quit (Ping timeout: 255 seconds).
21:54:02 -!- rottytooth has quit (Quit: HydraIRC -> http://www.hydrairc.com <- Go on, try it!).
21:55:36 <int-e> kmc: ok, I found the magical format string parser in the compiler source. so yeah, a preprocessor looks like the only viable option
21:56:13 <Bike> clearly the answer is dependent types
21:56:29 <kmc> yay unboxed closures are coming to Rust
21:56:37 <kmc> this is one of the major things C++ can do that we can't
22:00:09 <Bike> what's an unboxed closure mean particularly
22:01:15 -!- mhi^ has joined.
22:01:37 <int-e> kmc: you may enjoy the comment in the type checking code here: http://sprunge.us/ZcjJ
22:02:01 <int-e> (or perhaps not, since it's entirely accurate)
22:02:43 <oerjan> terribly accurate hack
22:04:35 <int-e> "rue" btw stands for "record and unify with expected type"
22:05:06 -!- boily has quit (Quit: DENTISTRY).
22:05:51 <oerjan> what does avenue stand for twh
22:07:09 <int-e> I thought it was the proper word, "to rue"
22:07:44 <int-e> (though for once that kind of thinko didn't make the sentence wrong.)
22:08:27 -!- Sprocklem has joined.
22:08:56 -!- rottytooth has joined.
22:09:59 <int-e> hehe, according to acronymfinder, "AVENUE stands for ATM (Asynchronous Transfer Mode) Validation Environment for Use towards EATMS (European Air Traffic Management System)"
22:13:56 <shachaf> Overly Enthusiastic Resources Jeopardize Acronym Nomenclature
22:15:47 <kmc> Bike: so a C++ lambda evaluates to an instance of an anonymous class generated by the compiler
22:16:03 <kmc> the captured variables of the lambda are member data of that class
22:16:08 <Bike> isn't that a box?
22:16:12 <int-e> with a () operator? sounds sane ... in the context of C++
22:16:17 <kmc> int-e: yes
22:16:46 <b_jonas> kmc: yes, but that's almost so difficult to prove that they practically only say that to be able to define the semantics of lambdas properly
22:16:47 <kmc> Bike: "box" refers to a heap box, used to give things uniform runtime representation
22:17:03 <kmc> the function object could live on the stack or as a field in another object
22:17:05 <kmc> without a heap allocation
22:17:09 <kmc> and the operator() call is not virtual
22:17:18 <kmc> so if you call map with a lambda argument, the compiler can even inline the lambda into the map
22:18:09 <kmc> if you *do* want dynamic polymorphism, you up-cast the object of unspecified type to std::function<...>, which is a superclass
22:18:39 <kmc> and (like other cases of up-casting to call virtual methods) you can only do that cast on a pointer or reference, not on the object by value
22:18:49 <kmc> because a std::function<...> has a different size than some arbitrary subclass of it
22:19:06 -!- mihow has quit (Quit: mihow).
22:19:14 <kmc> anyway the ability to stuff free variables into a bigger struct is super useful
22:19:22 <kmc> for example in the iterators API
22:19:29 <kmc> in Rust, I mean
22:20:10 <kmc> myiter.map(|x| ...) will return a struct which is another iterator, and if you moved the free variables of that lambda into the struct, you could pass the iterator around more freely
22:20:37 -!- Sgeo has joined.
22:20:42 <kmc> instead, in current rust, the free variables live on the stack of the caller, and the iterator lifetime's is bound to that activation frame
22:20:57 <kmc> and you can't inline the lambda into other stuff
22:21:02 <kmc> it's just passed as a function pointer
22:22:06 <kmc> that makes it pretty similar to GCC's nested functions extension, actually
22:22:10 <Bike> oh, that's nice.
22:22:23 <kmc> except the borrow checker will complain if you try to return such a lambda
22:24:01 <Bike> http://www.theonion.com/articles/new-stem-education-initiative-inspires-girls-to-ea,36126/
22:24:04 <kmc> like so: http://goo.gl/7kNFUA
22:24:30 <shachaf> imo just do it the go way: https://groups.google.com/d/msg/golang-nuts/mKJbGRRJm7c/DZod_v3BdSIJ
22:24:56 <b_jonas> kmc: well, C++ lambdas can do taht, and more
22:25:08 -!- Guest32551 has quit (Quit: Leaving).
22:25:17 <kmc> can do which?
22:25:49 <b_jonas> it can have the variables live on the stack so the closure is valid only until its creating function
22:26:00 <kmc> I know, I said that above
22:26:11 <kmc> this topic started with me saying that C++ lambdas can do things Rust lambdas can't
22:27:03 <oerjan> shachaf: Severely Hopeless Acronyms Change Humoristic Art Forever
22:28:35 <kmc> Bike: a key part of that whole thing is that C++ has inference for function template calls
22:29:03 -!- blitter64 has joined.
22:29:45 <kmc> so you can write map([](x) { x+1 }) rather than map<some_ridiculous_name_of_type_generated_by_the_compiler>([](x) { x+1 })
22:30:07 -!- evalj has quit (Remote host closed the connection).
22:30:52 <kmc> template<typename A> class List { template<typename B, typename F> List<B> map(F f) }
22:31:20 <kmc> of course, until the templates are expanded, there's nothing checking that F has an operator() which takes A and returns B
22:31:25 <kmc> because C++ templates are duck-typed
22:31:31 <kmc> but the analogous thing in Rust would be checked via the trait system
22:31:43 <kmc> and some day C++ will get "concepts" to do the same
22:31:55 <kmc> maybe even this year??
22:32:39 <shachaf> oerjan: Only Exemplary Retorts Jolt Adroit Nonagenarians
22:33:04 <oerjan> fowl: From Oulipo With Love
22:33:54 <Sgeo> Why do people never speak of UDP/IP as a thing the way they do TCP/IP?
22:34:49 <shachaf> oerjan: Ordinarily, Exceeding Rough Jabs Aren't Necessary
22:37:24 <oerjan> shachaf: Sorry, Helpless Arbitrary Codes Have All Failed
22:38:26 -!- rottytooth has quit (Quit: HydraIRC -> http://www.hydrairc.com <- Po-ta-to, boil em, mash em, stick em in a stew.).
22:39:17 <shachaf> oerjan: Opportunistic Extra Random Jokes Ain't Nice
22:40:27 <oerjan> shachaf: So Heartless And Completely Humorless A Feature
22:41:18 <kmc> Sgeo: i have heard it
22:41:23 <kmc> but mostly because there's very little to say about UDP?
22:41:33 <kmc> UDP isn't a transport protocol so much as a way to write your own transport protocol in userspace
22:41:36 <kmc> usually that's what you talk about
22:42:29 <mcpherrin> UDP is a way to escape the tyranny of your OS's TCP junk heap ;)
22:44:23 <int-e> such hate and conflict -- horrible acronym fate
22:44:25 <mcpherrin> Sgeo: it's a good question though; certainly from a network perspective there's no reason you couldn't put UDP in whatever kind of frame you wanted
22:44:51 <mcpherrin> Running UDP on broadcast ethernet frames or something.
22:45:31 <kmc> it's depressing how many security holes have the root cause that "int" is a lot shorter to type than "unsigned int"
22:46:18 <zzo38> kmc: At least, SQLite has a SQLITE_TOOBIG error code which is possible to avoid some of those problems.
22:47:50 <oerjan> int-e: it needs to end
22:47:53 <int-e> obsessively enigmatic retorts -- just another nightmare --- fair is fair.
22:49:47 <int-e> oerjan: I never think enough. :P
22:51:17 -!- blitter64 has quit (Ping timeout: 264 seconds).
22:52:27 <oerjan> imagination nurtures thought endlessly
22:57:45 -!- mcpherrin has quit (Quit: offline for a bit).
22:58:19 -!- Sprocklem has quit (Ping timeout: 240 seconds).
22:59:39 -!- Sprocklem has joined.
22:59:39 -!- blitter64 has joined.
23:00:02 -!- ^v has quit (Ping timeout: 252 seconds).
23:05:36 -!- tromp_ has joined.
23:07:31 -!- ^v has joined.
23:08:43 -!- nooodl_ has quit (Ping timeout: 276 seconds).
23:20:29 <Slereah_> http://24.media.tumblr.com/0fca573aac765a7de4504e34f14e5766/tumblr_n63889tQso1qmmsq4o1_1280.png
23:34:33 <oerjan> `addquote <kmc> I like telling people who've only used high level languages about the bizarre forms of undefined behavior in C, and then ending it with "this language and its relatives are used for most systems in planes, cars, medical devices, nuclear reactors, etc."
23:34:34 <HackEgo> 1197) <kmc> I like telling people who've only used high level languages about the bizarre forms of undefined behavior in C, and then ending it with "this language and its relatives are used for most systems in planes, cars, medical devices, nuclear reactors, etc."
23:35:47 <HackEgo> Runs arbitrary code in GNU/Linux. Type "`<command>", or "`run <command>" for full shell commands. "`fetch <URL>" downloads files. Files saved to $PWD are persistent, and $PWD/bin is in $PATH. $PWD is a mercurial repository, "`revert <rev>" can be used to revert to a revision. See http://codu.org/projects/hackbot/fshg/
23:36:02 -!- yorick has quit (Read error: Connection reset by peer).
23:36:13 <oerjan> somehow that link had slipped off my browser history
23:37:06 <oerjan> or at least address line completion refused to give it
23:37:54 <oerjan> which is weird since i used it 2 weeks ago
23:37:57 -!- mhi^ has quit (Quit: Lost terminal).
23:44:00 <Sgeo> I want a Gold Transcendence
23:44:31 <Sgeo> kmc: also, not all relatives of C are as terrible as C.
23:45:02 <oerjan> <M28> it is, but then you can't assume that "0^n = 0" everywhere <-- that's not true for negative n anyway
23:45:42 <oerjan> @tell M28_ <M28> it is, but then you can't assume that "0^n = 0" everywhere <-- that's not true for negative n anyway
23:46:03 <M28_> oerjan, you got the idea
23:46:06 -!- M28_ has changed nick to M28.
23:46:09 <ion> Google Plus recommended communities http://heh.fi/tmp/google_plus_emacs_vim.png
23:51:02 -!- tromp_ has quit (Remote host closed the connection).
23:51:16 <lambdabot> cannot mix ‘Data.Complex.:+’ [infix 6] and prefix `-' [infixl 6] in the ...
23:52:00 <oerjan> M28: that doesn't look like 23.1406... to me.
23:52:37 <M28> oerjan, http://www.wolframalpha.com/input/?i=%28-1%29%5E%28-i%29
23:54:41 <oerjan> hm funny it switches the values. of course both i and -i are solutions to x^2 = -1 so they're probably in the branches of each other
23:56:02 <oerjan> you'd think WA should understand "all branches of (-1)^(i)"
23:58:58 <oerjan> > [ exp((0:+1)* (0 :+ n*2*pi + log (-1)) | n <- [-2..2]]
23:59:00 <lambdabot> <hint>:1:40: parse error on input ‘|’
23:59:11 <oerjan> > [ exp((0:+1)* (0 :+ n*2*pi + log (-1))) | n <- [-2..2]]
23:59:13 <lambdabot> cannot mix ‘Data.Complex.:+’ [infix 6] and ‘GHC.Num.+’ [infixl 6] in the...
23:59:29 <oerjan> > [ exp((0:+1)* ((0 :+ n*2*pi) + log (-1))) | n <- [-2..2]]
23:59:31 <lambdabot> [6635623.99934113 :+ 0.0,12391.647807916694 :+ 0.0,23.140692632779267 :+ 0.0...
23:59:55 <oerjan> > [ re $ exp((0:+1)* ((0 :+ n*2*pi) + log (-1))) | n <- [-2..2]]
23:59:57 <lambdabot> Couldn't match type ‘Data.Complex.Complex a1’
23:59:57 <lambdabot> with ‘Data.Tagged.Tagged a0 (Data.Functor.Identity.Identity b)
23:59:57 <lambdabot> -> Data.Tagged.Tagged s0 (Data.Functor.Identity.Identity...
23:59:57 <lambdabot> Expected type: Control.Lens.Review.AReview s0 t a0 b
23:59:57 <lambdabot> Actual type: Data.Complex.Complex a1Couldn't match type ‘Data.Complex.Comp...
00:00:09 <oerjan> > [ realPart $ exp((0:+1)* ((0 :+ n*2*pi) + log (-1))) | n <- [-2..2]]
00:00:10 <M28> can't you test that in a private msg
00:00:12 <lambdabot> [6635623.99934113,12391.647807916694,23.140692632779267,4.321391826377226e-2...
00:00:23 <oerjan> um the whole point was to demonstrate
00:01:34 <oerjan> it just takes me a handful of bug corrections each time before i realize that it's _not_ going to work without error the next try. every time.
00:02:22 -!- Sprocklem has quit (Quit: brb).
00:03:21 <oerjan> anyway those are the branches of (-1)^i, as you can see both numbers are included.
00:03:44 <M28> I don't even know what language you're using for that
00:04:11 <oerjan> i guess its notation for complex numbers is a little awkward, a + ib is a :+ b
00:04:43 <M28> I calculated that another way
00:04:51 <M28> e^(pi * i) = -1
00:05:02 <M28> (e^(pi*i))^(-i) = ...
00:05:54 <oerjan> well the point here is that log is a multivalued function with several branches, because e^(z + 2pi*n*i) == e^z
00:06:09 <oerjan> and if you choose a different solution, you can get other results.
00:07:17 <oerjan> and it so happens that e^(pi * i) and e^(pi * (-i)) are both -1
00:07:33 <M28> I forgot the +-
00:08:26 <oerjan> i couldn't say which selection is most "official" for complex floating point.
00:09:00 -!- tromp_ has joined.
00:18:58 -!- Bike has quit (Ping timeout: 240 seconds).
00:21:12 -!- Bike has joined.
00:23:03 -!- Sprocklem has joined.
00:24:56 <Sgeo> So, an IRL friend falls for a phishing scam on Facebook. I see another person write on her wall something that indicates he fell for it too. I go to message him, and then see his profile... it says he's a web developer.
00:25:50 <int-e> oh lambdabot ... edit distance 2 is too much.
00:26:21 <int-e> @info do a <- [1,2,3]; b <- [1,3,5]; return (a,b)
00:26:21 <lambdabot> [1, 2, 3] >>= \ a -> [1, 3, 5] >>= \ b -> return (a, b)
00:26:59 <oerjan> i fail to find the evidence convincing hth
00:27:06 <int-e> oerjan: I had a hard time understanding why lambdabot understands @info.
00:27:21 <oerjan> well you could just have asked me
00:27:27 -!- tromp_ has quit (Remote host closed the connection).
00:28:30 <int-e> oerjan: But you delight too much in the absurd to serve as a guideline for sanity.
00:28:40 <oerjan> btw a trick for checking these is to change a single letter and hope the result becomes ambiguous enough that you get a list of options.
00:29:37 -!- Bike_ has joined.
00:30:43 -!- Bike has quit (Disconnected by services).
00:30:45 -!- Bike_ has changed nick to Bike.
00:31:07 -!- tromp_ has joined.
00:33:16 <zzo38> What is the maximum number of opponent's card you can knock out in one turn in a game of Pokemon card, assuming you have 6 side cards remaining? What is it if you instead assume you have an unlimited number of side cards remaining?
00:33:32 <Sgeo> zzo38: hey, I learned how to play Pokemon TCG yesterday
00:33:56 <Sgeo> Interesting that defenders don't fight back
00:34:10 <elliott> int-e: the error correction is kind of silly
00:34:12 <zzo38> Sgeo: Then see, how you can understand my puzzles. Note that they use the old rules (which I prefer)
00:34:30 <Sgeo> The only rules I know are the ones my friend showed me.
00:34:49 <Sgeo> Plus I don't really know the cards themselves, just the rules. Barely.
00:35:20 <zzo38> It is not necessary to know the cards to know my puzzles, because they have the copy of all of the cards that are relevant.
00:35:26 <int-e> elliott: agreed, but it's usually harmless
00:35:59 * Sgeo goes to install the computer version
00:36:20 -!- boily has joined.
00:37:06 <boily> Dentists are lawful evil creatures.
00:37:25 <oerjan> int-e: a simple way of fixing that particular case is of course to make an _actual_ @info command.
00:38:15 <zzo38> There is two games of Pokemon card in GameBoy, and I played both
00:39:46 <zzo38> But, maybe we should work to make up a new implementation in C or SQL or Haskell or whatever, therefore it is also possible to fix it to experiment new rule, add new cards, define new tournament formats, etc. And it can even connect using any telnet client then; it doesn't have to require any special software (but can be optionally provided, perhaps).
00:40:42 <zzo38> (Also because I don't like the new rules)
00:41:25 -!- drdanmaku has quit (Quit: Connection closed for inactivity).
00:43:46 <Sgeo> Does a browser count as special software? I assume that this backend you're envisioning would be compatible with any frontend, just needs a compatibility layer like a web server
00:44:22 <zzo38> Sgeo: Yes, you could allow it to be used with a browser by adding such a compatibility layer, but by itself it works fine with only a telnet client and nothing else; really simple.
00:44:23 <int-e> oerjan: that's what I want to do, actually.
00:48:21 -!- tromp_ has quit (Remote host closed the connection).
00:49:03 <zzo38> Yes I am saying it would be compatible with any frontend; the built-in software is for use with telnet but you can add on other thing to allow other client software to be used too
00:50:42 <Sgeo> Ick the Pokemon TCG online thing doesn't actually teach you how to play
00:50:56 <Sgeo> More assume you know how to play and teaches you how to use the software
00:54:54 <zzo38> I have seen it when someone had this software, and isn't very good. It is also one reason, I would rather have a new kind. Perhaps it may be sensible to use SQL, since that way you can store all of the cards in the database. Of course, it can combine SQL with C if you need to use C codes as well.
00:55:08 -!- tromp_ has joined.
00:56:58 <zzo38> There is some software open-source for Magic: the Gathering cards and some similar thing, so, what I want to do is to make do Pokemon card. Do you like this?
00:57:26 <int-e> but I guess I won't do that right now because ghci's :i command requires its own cleanup for trimming the output.
00:58:16 <zzo38> (And because I like old rules of Pokemon card)
01:05:05 -!- tromp_ has quit (Remote host closed the connection).
01:08:15 -!- tromp_ has joined.
01:18:05 -!- tromp_ has quit (Remote host closed the connection).
01:36:54 -!- vravn has quit (Ping timeout: 240 seconds).
01:37:46 <Bike> "O(n⁴), or O(n³) by simple parallelization" this seems like a bad thing to say, somehow
01:38:03 -!- conehead has joined.
01:38:09 <HackEgo> [U+004F LATIN CAPITAL LETTER O] [U+0028 LEFT PARENTHESIS] [U+006E LATIN SMALL LETTER N] [U+2074 SUPERSCRIPT FOUR] [U+0029 RIGHT PARENTHESIS]
01:38:40 <Bike> am i supposed to write ^4 like some kind of jerk
01:39:01 <oerjan> i don't see the four, but actually i was just checking the O
01:40:47 <oerjan> i realized it should in theory be an Omicron :)
01:41:46 -!- boily has quit (Quit: BUCCO-CLEANSED CHICKEN).
01:42:41 <oerjan> ok knuth agrees with me
01:42:52 <oerjan> (but may have been the first to do so)
01:43:22 <oerjan> "The big-O originally stands for "order of" ("Ordnung", Bachmann 1894), and is thus a roman letter. Neither Bachmann nor Landau ever call it "Omicron". The symbol was much later on (1976) viewed by Knuth as a capital omicron,[10] probably in reference to his definition of the symbol Omega. The digit zero should not be used."
01:44:34 <elliott> O(n) is constant time, because O*anything = O
01:45:21 <Bike> saying something and getting a response about homoglyph attacks is "pretty cool"
01:47:15 <zzo38> You can turn on "show punycode" in a web browser is one thing avoiding homoglyph attacks in domain names at least. In many other program, just disable Unicode support, and then you won't have any homoglyph attacks.
01:47:15 -!- edwardk has joined.
01:47:26 -!- tromp_ has joined.
01:47:36 <oerjan> @tell mroman Just keep patient http://ezyang.com/rlimits.html
01:57:14 -!- tromp_ has quit (Remote host closed the connection).
02:00:16 <HackEgo> [U+A66E CYRILLIC LETTER MULTIOCULAR O] [U+0028 LEFT PARENTHESIS] [U+006E LATIN SMALL LETTER N] [U+0029 RIGHT PARENTHESIS]
02:00:55 -!- tromp_ has joined.
02:10:41 <ion> “that” is four letters.
02:10:44 -!- tromp_ has quit (Remote host closed the connection).
02:10:54 -!- Sprocklem has quit (Quit: brb).
02:11:14 -!- Sprocklem has joined.
02:12:11 <Sprocklem> ion: No. How is 'ꙮ' even a letter?
02:12:38 <Bike> same reason blackboard bold l is a letter
02:12:49 <ion> sprocklem: How is “A” even a letter?
02:13:48 <kmc> I wonder if you could machine-translate C to unsafe Rust that is not terrible to modify by hand
02:13:49 -!- tromp_ has joined.
02:13:52 <kmc> and then incrementally make it safer
02:14:29 <Sprocklem> ion: A is not absolutely insane, ꙮ is
02:15:04 <HackEgo> [U+0041 LATIN CAPITAL LETTER A]
02:15:13 <kmc> Sprocklem: http://en.wikipedia.org/wiki/Multiocular_O
02:16:15 <kmc> because of the many-eyed seraphim
02:16:20 <ion> To trigger trypophobia.
02:16:33 <kmc> http://old.stsl.ru/manuscripts/1/308/medium/308-0249.jpg
02:16:36 <ion> trypꙮphobia
02:16:47 <kmc> many-eyed basilisks
02:18:31 -!- ^v has quit (Remote host closed the connection).
02:19:38 <zzo38> How many eyes does a seraphim have?
02:20:11 -!- ^v has joined.
02:23:36 -!- tromp_ has quit (Remote host closed the connection).
02:23:51 <zzo38> O, that's why they can't draw exactly how many, and therefore why some people write Multiocular O with ten eyes but sometimes it is only seven; both are wrong if, you are correct about aleph-four.
02:25:23 <oerjan> zzo38: the hth means i was not entirely serious.
02:27:41 <oerjan> > Text.Printf.printf "%s" :: String
02:27:41 -!- tromp_ has joined.
02:27:42 <lambdabot> "*Exception: printf: argument list ended prematurely
02:31:21 -!- Slereah has joined.
02:32:18 <HackEgo> kvpierdacoin bringiacoin whccoin wiicoin withbrehencoin bhappecoin grationcoin concoin morschcoin godoctracoin 073coin rposiscoin brailcoin gradcoin ccnlcoin philicoin oolflerncoin perlowfoucoin preloblecoin praysnaincoin
02:33:08 -!- Slereah_ has quit (Read error: Connection reset by peer).
02:33:33 <oerjan> argh my plan to soon catch up on shtetl-optimized comments is ruined by scott making another post
02:35:48 -!- blitter64 has quit (Ping timeout: 240 seconds).
02:36:21 <kmc> Sprocklem: for a while I was obsessed with the mystery of multiocular o
02:37:11 <kmc> then my associates and I dug up the information which is now present on its wikipedia page
02:37:28 -!- tromp_ has quit (Remote host closed the connection).
02:37:40 <kmc> a proposal to the Unicode committee, a Soviet-era paleography textbook from russian rapidshare
02:38:43 <Bike> the proposal was just the rapidshare link
02:38:47 -!- not^v has joined.
02:39:08 -!- ^v has quit (Quit: http://i.imgur.com/Akc6r.gif).
02:40:16 -!- tromp_ has joined.
02:49:29 -!- {hk3380} has quit (Ping timeout: 252 seconds).
02:50:04 -!- kwertii has joined.
02:50:07 -!- tromp_ has quit (Remote host closed the connection).
02:51:46 -!- tromp_ has joined.
02:56:16 <kmc> lifehack: if your device doesn't charge, try licking the contacts
03:00:18 <not^v> well, i just joined so i am assuming he is talking about a mobile welding transformer
03:00:40 -!- not^v has changed nick to ^v.
03:01:49 -!- tromp_ has quit (Remote host closed the connection).
03:09:07 -!- heroux has quit (Ping timeout: 240 seconds).
03:13:21 <kmc> whither fungot
03:14:55 -!- zzo38 has quit (Read error: Connection reset by peer).
03:15:21 -!- zzo38 has joined.
03:27:22 <MDude> I like how I thought that was a unique character at first only for five clones of her to walk onscreen.
03:29:36 <MDude> I would have tried ot get off the near side of the bridge as soon at the bot started moving again.
03:29:50 <MDude> Only she gets to talk about her mom like that.
03:30:19 <MDude> Use the fairly again, it got you across last time.
03:30:48 <oerjan> MDude: are you talking in the right channel twh
03:31:14 <kmc> i'm clearly not high enough for this channel
03:32:04 <MDude> I have the screen minimized so i can see the chat window and a stream at the same time, but I can't see the channel names.
03:40:14 <quintopia> you know what game is annoying like that? Alice: Madness Returns. Every boss almost immediately becomes a regularly appearing enemy. It's like DRAMATIC CUTSCENE FOR POWERFUL BOSS. and then you beat it like WOOOO and then five more appear and you're like wut.
03:41:09 -!- {hk3380} has joined.
03:44:30 -!- tertu has joined.
03:45:17 <kmc> while you are letting your guard down / i will be letting myself go / while you keep running your ship aground / i will be setting myself alight
03:46:55 -!- heroux has joined.
03:47:06 * oerjan aims the hose on kmc ==============|>
03:47:23 <kmc> YOU GET TO DRINK FROM.... THE FIREHOSE!
03:47:52 <oerjan> how high are you on a scale from 1 to -i
03:48:02 -!- tromp_ has joined.
03:50:17 <oerjan> a very rational answer.
03:50:55 <Bike> why in the hell can i recognize that number at sight
03:51:09 <Bike> "we were talking about it yesterday" well, fukc you,
03:51:30 <oerjan> wonderful thing, velocipede memory
03:51:54 <kmc> wubwubwubwubwubwubwubwub
03:52:18 <quintopia> well, i wasn't here yesterday, so please reiterate what that number is
03:52:57 <Bike> or exp(pi), yeah
03:53:06 <kmc> is it the same o_O
03:53:16 <Bike> alternately according to http://oldweb.cecm.sfu.ca/cgi-bin/isc/lookup?lookup_type=browse&page_no=0&number=23.140693 it was probably exp(-Pi)^Feig1+exp(Pi), a completely sensible number
03:53:28 <Bike> kmc: yes because a^b = exp(b*log(a)) and log(-1) = pi*i
03:54:22 <kmc> holy living fuck
03:55:42 <Bike> \rainbow{complex analysis}
03:56:00 <oerjan> `` rainbow <<<complex analysis
03:56:13 <oerjan> `` rainbow <<<'complex analysis'
03:59:21 <Bike> you can remember that log(-1) = pi because -1 is on the left side of the circle of life. similarly log(i) = pi*i/2 and log((1+i)/|1+i|) = pi*i/4 and bla bla bla
03:59:55 -!- heroux has quit (Ping timeout: 276 seconds).
04:00:45 -!- heroux has joined.
04:02:04 <quintopia> i'm now going to start calling the unit circle in the complex plane the circle of life
04:02:18 <kmc> you are wrapping a mobius strip of videotape around and around the math/porn part of my mind
04:02:32 <Bike> i was going to make a flat circle joke but i ended up phrasing it differently, o well
04:03:21 <quintopia> kmc should do some programming in SELECT. it appears he is not quite versed enough in complex numbers
04:03:28 -!- MDude has changed nick to MDream.
04:03:44 -!- realzies has quit (Ping timeout: 255 seconds).
04:13:15 -!- mcpherrin has joined.
04:13:27 -!- kwertii has quit (Quit: kwertii).
04:13:43 <HackEgo> [U+A66E CYRILLIC LETTER MULTIOCULAR O] [U+005F LOW LINE] [U+A66E CYRILLIC LETTER MULTIOCULAR O]
04:14:16 -!- tromp_ has quit (Read error: Connection reset by peer).
04:14:29 <kmc> http://en.wikipedia.org/wiki/Lowline_(park)
04:15:48 -!- realzies has joined.
04:15:48 -!- realzies has quit (Changing host).
04:15:48 -!- realzies has joined.
04:18:09 <quintopia> how do i get a unicode with that character on this windows machine
04:19:38 <ion> Press ꙮ on your keyboard.
04:20:35 <Bike> oh and log(1) = pi*0*i. bonus question: how does this relate to roots of unity being periodic on the circle
04:20:42 <oerjan> quintopia: works fine in IE here. not so much in putty.
04:21:30 <oerjan> because it's really pi*2*n*i
04:21:45 <Bike> you're not supposed to answer if it's obvious to you, jerk
04:22:34 * quintopia branch cuts Bike into INFINITELY MANY PIECES
04:22:43 <oerjan> you get _one_ doctorate, and suddenly you're not allowed to answer math puzzles any more. it's not fair!
04:23:13 <Bike> should have gotten a doctorate ins omething else! critical theory probably
04:23:40 <quintopia> that's not true. you're still allowed. they just have to be the hard ones. like that one hat game puzzle where you can prove there is a winning stratey nonconstructively using the axiom of choice.
04:23:49 <oerjan> but i hate and despise criticism! critics should all be hung and quartered!
04:24:31 <quintopia> is this you being critical of critics?
04:24:50 <Bike> conveniently, criticism of critical theory is a topic of critical theory.
04:24:56 <zzo38> Is axiom of choice applicable to work of such a game though? Maybe it is, but I don't know. I also don't know, what game.
04:25:14 <oerjan> quintopia: how dare you suggest such an absurd idea!
04:35:41 -!- {hk3380} has quit (Ping timeout: 264 seconds).
04:39:00 -!- Sorella has quit (Quit: It is tiem!).
04:41:10 <kmc> `addquote <zzo38> Is axiom of choice applicable to work of such a game though? Maybe it is, but I don't know. I also don't know, what game.
04:41:11 <HackEgo> 1198) <zzo38> Is axiom of choice applicable to work of such a game though? Maybe it is, but I don't know. I also don't know, what game.
04:51:53 <lambdabot> can GMP support KealDigit? I invent KealDigit
04:54:37 * Bike googles. oh, a troll
04:55:05 <Bike> @keal // i just got banned from math because i not have good ability to convey thoughts <-- cool cool
04:55:06 <lambdabot> how do i search for someone saying 'Keal' in mirc
04:56:46 <lambdabot> i dont really eat vegetables unless cheese is a vegetable
04:57:08 <Bike> cheese is not a vegetable. how foolish and therefore humorous.
04:57:53 <lambdabot> People react to fear, not love; they don't teach that in Sunday School, but it's true.
04:58:09 <newsham> people voted forhim. how foolish and therefore humorous
05:01:13 <newsham> https://twitter.com/OccupyWallStNYC/status/471441682437648384/photo/1
05:01:17 <zzo38> Different people react to different things in different circumstances.
05:01:27 <zzo38> to different degrees.
05:02:32 <newsham> different stuff is different than other different stuff
05:02:52 <newsham> tautology conveys very few bits
05:08:16 -!- password2 has joined.
05:08:31 <zzo38> Yes, that is also the case.
05:10:10 <oerjan> contradiction converys infinite bits!
05:12:25 <zzo38> However, even though different stuff is different than other different stuff, you must also consider, it is different, in what way(s)?
05:33:44 <newsham> [19:07] < oerjan> contradiction converys infinite bits!
05:33:51 <newsham> thats an interesting wording of that
05:34:19 <Bike> is an infinite number of bits really different from zero bits maaaaan
05:35:29 <newsham> so the less true something is the more bits?
05:35:51 <newsham> are we all filling up our hard disks with lies?
05:38:51 <oerjan> not less true, less probable
05:40:23 <^v> anyone try genetic algorithms on malbolge?
05:41:04 <Bike> go for annealing
05:41:10 <Bike> anneal your pgorgram into existence
05:41:23 <^v> D: i was in the 90s for less than a year
05:42:42 <oerjan> such a lost opportunity
05:42:43 <newsham> i used to live anhour out of the 90s.. the commute sucked
05:42:55 <oerjan> we need to start teaching children programming in the womb!
05:43:21 <newsham> genetic memories..give it a few million years
05:43:40 <oerjan> newsham: i think we've evolved to have _less_ of those...
05:44:01 <kmc> `addquote <Bike> anneal your pgorgram into existence
05:44:02 <HackEgo> 1199) <Bike> anneal your pgorgram into existence
06:02:03 -!- oerjan has quit (Quit: Nite).
06:24:53 <zzo38> I thought of some kind of unusual strange things involving SQL with the ABSTAIN, REINSTATE, IGNORE, REMEMBER, STASH, RETRIEVE commands similar to INTERCAL programming.
06:28:57 <zzo38> It probably make a strange things, a bit??
06:31:09 -!- MoALTz has quit (Quit: Leaving).
06:33:53 -!- password2 has quit (Ping timeout: 252 seconds).
06:37:09 <zzo38> The RETURN command in BASIC can have a line number/label specified, and if so then it will not return to where it is called, but to the specified line instead. This is somewhat like the FORGET command in INTERCAL. (And, I have used it to imitate a DO FORGET #1)
06:49:11 <b_jonas> zzo38: what? which dialect of BASIC has that?
06:52:13 <zzo38> Well, I was using QBASIC
06:52:58 <zzo38> You can specify RETURN by itself to return from a GOSUB, or you can write something like RETURN 123 which means it will return from a GOSUB but instead of returning to the line after the GOSUB, it will go to line 123.
06:58:33 <newsham> you can never RETURN to the scene of a perfect crime
07:01:57 <zzo38> It just return one, rather than returning to whatever is specified to catch it.
07:06:23 <newsham> yah, single layer, non-nested, return to error handler
07:08:09 -!- conehead has quit (Quit: Computer has gone to sleep).
07:09:24 -!- sebbu has quit (Ping timeout: 240 seconds).
07:15:13 <olsner> does RETURN with line number remove the whole call stack too?
07:28:45 <b_jonas> zzo38: I see. I didn't know basic RETURN did this
07:35:26 <HackEgo> [wiki] [[Special:Log/newusers]] create * Sanzzzay * New user account
07:51:27 * impomatic wonders if there's a radiation-hardened quine in Brainfuck...
07:52:11 -!- Tritonio has joined.
08:19:36 -!- slereah_ has joined.
08:45:53 -!- Patashu has joined.
08:49:22 <HackEgo> [wiki] [[Special:Log/newusers]] create * Parcly Taxel * New user account
08:50:34 -!- Patashu has quit (Disconnected by services).
08:50:34 -!- Patashu_ has joined.
09:05:03 <shachaf> oerjan: what do you think of https://en.wikipedia.org/w/index.php?title=RTR0&action=history
09:05:25 <HackEgo> [wiki] [[User:Parcly Taxel]] N http://esolangs.org/w/index.php?oldid=39711 * Parcly Taxel * (+306) :D
09:29:31 -!- sebbu has joined.
09:30:04 -!- sebbu has quit (Changing host).
09:30:04 -!- sebbu has joined.
09:36:36 <HackEgo> [wiki] [[1+]] N http://esolangs.org/w/index.php?oldid=39712 * Parcly Taxel * (+2950) New language
09:38:43 <HackEgo> [wiki] [[Language list]] http://esolangs.org/w/index.php?diff=39713&oldid=39700 * Parcly Taxel * (+9) /* Non-alphabetic */ +1+
09:48:00 -!- skarn has quit (K-Lined).
09:49:19 -!- skarn has joined.
09:49:55 -!- skarn has changed nick to Guest58328.
10:14:15 -!- boily has joined.
10:23:46 -!- {hk3380} has joined.
10:27:59 -!- Phantom_Hoover has joined.
10:32:53 -!- AnotherTest has joined.
10:37:06 -!- Burton has quit (Ping timeout: 252 seconds).
11:02:16 -!- Burton has joined.
11:02:56 -!- {hk3380} has quit (Ping timeout: 255 seconds).
11:09:55 -!- boily has quit (Quit: Poulet!).
11:25:17 -!- Guest58328 has quit (Changing host).
11:25:17 -!- Guest58328 has joined.
11:25:23 -!- Guest58328 has changed nick to skarn.
11:46:20 -!- MindlessDrone has joined.
11:56:33 -!- Sgeo has quit (Read error: Connection reset by peer).
13:10:58 -!- yorick has joined.
13:14:27 -!- Patashu_ has quit (Ping timeout: 245 seconds).
13:15:35 -!- {hk3380} has joined.
14:01:57 -!- Sprocklem has quit (Ping timeout: 252 seconds).
14:19:28 -!- Burton has quit (Quit: GoodBye).
14:22:46 -!- MDream has changed nick to MDude.
14:32:40 -!- Burton has joined.
14:35:33 -!- Sprocklem has joined.
14:47:38 -!- conehead has joined.
14:59:46 -!- idris-bot has quit (Quit: Terminated).
15:00:04 -!- idris-bot has joined.
15:33:35 -!- Tritonio has quit (Ping timeout: 255 seconds).
15:40:53 <myname> can i use a guard in haskell everywhere an = could appear?
15:42:37 -!- rottytooth has joined.
15:44:19 <FireFly> shachaf: "widely used", eh
15:59:52 <HackEgo> [wiki] [[User:Sacchan]] http://esolangs.org/w/index.php?diff=39714&oldid=39632 * Sacchan * (-2)
16:01:37 <HackEgo> [wiki] [[User:Sacchan]] http://esolangs.org/w/index.php?diff=39715&oldid=39714 * Sacchan * (+38)
16:02:45 -!- slereah_ has quit (Quit: Leaving).
16:03:13 <HackEgo> [wiki] [[ΜCurse]] http://esolangs.org/w/index.php?diff=39716&oldid=39699 * Sacchan * (-20) /* External Resources */
16:36:10 <shachaf> FireFly: That's what it says.
16:55:15 -!- {hk3380} has quit (Quit: WeeChat 0.3.8).
16:55:33 -!- {hk3380} has joined.
17:08:02 <olsner> huh, it seems to have been very quiet here since this morning
17:11:07 -!- kwertii has joined.
17:18:27 -!- kwertii has quit (Quit: kwertii).
17:20:11 -!- kwertii has joined.
17:20:11 -!- kwertii has quit (Changing host).
17:20:11 -!- kwertii has joined.
17:20:26 -!- MoALTz has joined.
17:40:16 <monotone> There are currently 88 users in the channel. Maybe we traveled through time.
17:46:37 <olsner> There are 0 ops in the channel. Maybe I am still hungry.
17:52:11 -!- Sprocklem has quit (Ping timeout: 258 seconds).
17:54:02 -!- quelqun_dautre has left.
17:54:20 -!- Bike_ has joined.
17:56:21 -!- ^v has quit (Quit: Leaving).
17:56:37 -!- ^v has joined.
18:01:31 -!- {hk3380} has quit (Ping timeout: 240 seconds).
18:02:16 -!- Bike_ has changed nick to Bicyclidine.
18:08:29 -!- {hk3380} has joined.
18:20:19 -!- evalj has joined.
18:39:22 <mroman> Are you referring to | guards?
18:42:32 -!- nooodl has joined.
19:16:07 <kmc> myname: where does an = appear in a guard?
19:16:09 <kmc> but I think the answer is "no"
19:16:28 <myname> | foo = <- right there
19:17:01 <kmc> er, that's after the guard isn't it
19:17:05 <kmc> f x | x < 3 = 5
19:17:30 <kmc> in H'10 you can have multiple guards separated by commas, but not by |
19:17:55 <kmc> with only boolean guards this isn't useful, you might as well write | x && y instead of | x, y
19:17:59 <kmc> but with pattern guards it becomes useful
19:27:50 -!- nooodl has quit (Ping timeout: 255 seconds).
19:33:34 <Taneb> Had an exam today, it went alright bar the last question
19:33:43 <Taneb> I forgot a few things relevant to it
19:33:48 <Taneb> So, I got like 90%
19:35:48 <Taneb> One of the things I forgot was what an orthogonal matrix was
19:36:42 <Taneb> What's the rank of a zero matrix?
19:38:23 -!- MDream has joined.
19:39:39 -!- MDude has quit (Ping timeout: 252 seconds).
19:39:47 <Bicyclidine> well, wolfram says zero, and more importantly the subspace generated is just the zero point, which of course has a dimension of zero
19:39:54 <Taneb> Actually, my answer was "...1?"
19:40:37 <Bicyclidine> it makes more sense for me to think of matrices as being linear transforms in space rather than colums or whatever, maybe that will change when i actually take a linalg class
19:41:31 -!- MindlessDrone has quit (Quit: MindlessDrone).
19:42:45 <Phantom_Hoover> i've always hated linear algebra for emphasising the rectangles of numbers over the actual linear stuff
19:44:00 <Phantom_Hoover> like jordan normal forms, i had no idea what the fuck they were until a week or two before the exams when i read more closely and was like "oh so you're changing the basis to the eigenvectors or the nearest alternative"
19:46:07 <Bicyclidine> incidentally i never noticed that matrices having characteristic polynomials implies polynomials have companion matrices
19:49:03 <Bicyclidine> most of my high school experience with matrices was computing determinants of 5x5 matrices and shit like that so i grew to loathe them
19:50:31 <Phantom_Hoover> although my linear algebra course thought it was reasonable to make you compute a bunch of powers of a 6x6 matrix which is just fantastically pointless
19:51:27 -!- nooodl has joined.
19:52:09 <Taneb> The biggest matrix I had to deal with today was 3x3
19:52:16 <Taneb> ...with a determinant of 36^3
19:53:01 <Bicyclidine> well, you're in college, i imagine you could use a calculator like a fucking human being
19:54:07 <Taneb> Friday I've got an exam on regular expressions and finite-state automata
19:54:18 <Taneb> But tomorrow I have two birthday parties to attend!
19:55:58 <Phantom_Hoover> Bicyclidine, maths exams in warwick are all 'a calculator is not needed or permitted in this exam'
19:58:54 <Taneb> We got to use a calculator today but it was insufficiently fancy to do matrices nicely
20:03:10 <nooodl> is it just regex golf except for grades
20:04:41 -!- Sprocklem has joined.
20:12:33 <HackEgo> [wiki] [[Pi]] http://esolangs.org/w/index.php?diff=39717&oldid=36174 * 88.182.125.148 * (+0) error in table
20:14:47 -!- rottytooth has quit (Quit: HydraIRC -> http://www.hydrairc.com <- Would you like to know more?).
20:17:27 <Taneb> ...I'm suddenly in a "listening to Simon and Garfunkel" mood
20:19:48 <Taneb> It's like a bridge over troubled water right now
20:20:19 <Taneb> But anything beats the sound of silence
20:24:03 -!- {hk3380} has quit (Quit: WeeChat 0.3.8).
20:24:22 -!- {hk3380} has joined.
20:31:57 <Taneb> I... do not know many Simon and Garfunkel songs.
20:32:48 <kmc> A start tag whose tag name is one of: "base", "basefont", "bgsound", "link", "meta", "noframes", "script", "style", "template", "title":
20:32:51 <kmc> Parse error. Push the node pointed to by the head element pointer onto the stack of open elements. Process the token using the rules for the "in head" insertion mode. Remove the node pointed to by the head element pointer from the stack of open elements. (It might not be the current node at this point.)
20:32:56 <kmc> great stack
20:47:50 <Bicyclidine> compiler fixing a bug from "24+ years" ago. \rainbow{engineering}
20:49:39 <kmc> which bug?
20:50:31 <Bicyclidine> apparently nobody had noticed through two forks from a pre-CL system to now
20:51:02 <Bicyclidine> no word on whether they're merging upstream into some CMU research project of the 80s
20:56:02 -!- Patashu has joined.
20:56:30 -!- MDream has changed nick to MDude.
20:57:14 -!- erdic has quit (Remote host closed the connection).
21:02:58 -!- kwertii2 has joined.
21:02:58 -!- kwertii2 has quit (Changing host).
21:02:58 -!- kwertii2 has joined.
21:04:43 -!- kwertii has quit (Ping timeout: 252 seconds).
21:04:43 -!- kwertii2 has changed nick to kwertii.
21:05:40 -!- drdanmaku has joined.
21:06:46 <HackEgo> mdmcoin jocalcoin muschcoin whaniacoin roticacoin instascoin picoin eodelectcoin sertycoin preluscoin cardcoin mulacoin fcvetcoin grecoin odtilicoin benzcoin addleduigcoin enigma-2dcoin inclacoin isccoin
21:09:00 -!- kwertii has quit (Quit: kwertii).
21:18:26 -!- Sprocklem has quit (Quit: g2g).
21:20:58 -!- Patashu has quit (Ping timeout: 240 seconds).
21:22:35 -!- {hk3380} has quit (Ping timeout: 255 seconds).
21:26:24 -!- Phantom_Hoover has quit (Ping timeout: 276 seconds).
21:29:51 -!- AnotherTest has quit (Ping timeout: 265 seconds).
21:30:34 -!- Phantom_Hoover has joined.
21:34:44 -!- evalj has quit (Remote host closed the connection).
21:35:58 <Taneb> Forgot to put soup in the washing machine
21:36:05 <Taneb> Gave my clothes a £2.50 rinse
21:36:33 <Taneb> I didn't put any soup in either
21:43:28 <int-e> spice up your laundry!
21:44:06 <kmc> also hi Taneb
21:44:47 <Taneb> I found out that half of the birthday parties I intended to attend tomorrow have been postponed
21:45:19 <Taneb> Which opens up my plans for the evening
21:45:44 <kmc> how many is that?
21:47:40 <shachaf> "Half of what he said meant something else, and the other half didn't mean anything at all."
21:50:48 -!- boily has joined.
21:51:58 -!- tromp_ has joined.
21:53:01 -!- MDream has joined.
22:01:21 -!- MDude has quit (Ping timeout: 264 seconds).
22:01:48 -!- oerjan has joined.
22:18:24 -!- {hk3380} has joined.
22:23:38 -!- Fjlb has joined.
22:26:46 -!- boily has quit (Quit: ROLLED CHICKEN).
22:35:07 <oerjan> @tell impomatic * impomatic wonders if there's a radiation-hardened quine in Brainfuck... <-- well there isn't much you can do about mismatched brackets.
22:38:25 <oerjan> <shachaf> oerjan: what do you think of https://en.wikipedia.org/w/index.php?title=RTR0&action=history <-- i think that is a very vague question.
22:41:01 <oerjan> also whether to delete that article is wikipedia politics, which i won't touch with a ten foot pole hth
22:43:00 <oerjan> i see the notability dispute was added only a minute before your question, so presumably the process is already in motion.
22:44:58 -!- Sprocklem has joined.
22:45:00 -!- Sprocklem has quit (Changing host).
22:45:00 -!- Sprocklem has joined.
22:54:27 -!- Sgeo has joined.
22:56:58 -!- yorick has quit (Remote host closed the connection).
22:58:51 <Sgeo> How different is trunk Rust from released?
23:04:37 -!- Bicyclidine has quit (Ping timeout: 252 seconds).
23:07:44 <Sgeo> Pretty sure I need to reread tutorial, should I read the trunk tutorial?
23:09:00 <kmc> what do you mean by "trunk"
23:09:02 <kmc> git master?
23:09:16 <kmc> I advise reading the latest tutorial, yes, although it might still be out of date
23:09:50 <mcpherrin> install a nightly and read the latest tutorial
23:12:08 -!- Phantom_Hoover has quit (Quit: Leaving).
23:13:07 -!- Fjlb has quit (Quit: Leaving).
23:13:44 -!- nooodl has quit (Ping timeout: 255 seconds).
23:19:48 <myname> i should learn how to debug haskell
23:20:06 -!- Sorella has joined.
23:20:22 -!- nooodl has joined.
23:23:29 -!- BeingToDeath has joined.
23:34:01 * impomatic hasn't done code golf for a while http://golf.shinh.org
23:49:17 <^v> is it weird that i dont like forth?
23:49:30 <Bike> yes. you are ritually impure
23:49:31 <^v> i think a bunch of stack based esolangs are better
23:50:17 <^v> Super Stack! is good, and 1000x easier to learn than forth
23:50:29 <^v> just needs subroutines
23:52:44 <zzo38> Why do you think that? I think Forth is much better.
23:54:15 <zzo38> Forth allow much more kind of metaprogramming possible, and yet can be made in a simple implementation in the computer, too!!
23:54:44 <kmc> heya zzo38!
23:54:47 <kmc> how's it hanging
23:56:36 <Bike> more suitable as a function, really...
23:59:24 <myname> what the hell is pefunge
00:02:13 <kmc> mcpherrin: first we should have let string = objc![[NSString alloc] initWithCString: "Hello, world!"];
00:02:22 <kmc> Objective Rust
00:02:23 <kmc> I saw someone is working on Rust for iOS...
00:02:41 <mcpherrin> kmc: go convince zwarich to do that. never let him escape his apple past
00:03:57 <kmc> it would be (slightly) useful for Servo
00:04:03 <kmc> and I really like writing macros
00:04:12 <myname> i wonder why i do find the most people that talk about rust outside the rust channel here of all the channels
00:04:14 <kmc> but I know nothing about ObjC or OS X and probably can't be bothered to learn it
00:04:26 <kmc> myname: because I talk a lot here and I'm a professional rust programmer
00:04:42 <mcpherrin> I wish I was a professional rust programmer
00:04:57 <kmc> mcpherrin: I also wish you were a professional rust programmer
00:05:00 -!- BeingToDeath has quit (Ping timeout: 276 seconds).
00:05:09 <myname> how's documentation going?
00:05:09 <kmc> are there any esoteric languages with substructural type systems?
00:05:48 <Bike> i've been assuming mcpherrin was a rustc dev, lol
00:05:59 <mcpherrin> Bike: only in an open-source/community sense
00:06:10 <Bike> get mozilla to pay you
00:06:11 <kmc> right now I can't build rustc due to bullshit
00:06:38 <mcpherrin> I haven't hacked on rust itself, just written code in it
00:06:39 <myname> also: what the hell is pefunge? why is it listed at that codegolf site but not in our wiki?
00:14:05 <nooodl> myname: the japanese esolang/golf community is a bit obscure like that!
00:15:10 <zzo38> There are also a few other Japanese esolang stuff that weren't on esolang wiki, although I have added some of them.
00:15:47 <myname> so there are japanese esolang sites?
00:16:08 <myname> finally some useful work for all those weaboos
00:16:49 <nooodl> it seems to be mostly centered around a bunch of hatena blogs but i dunno
00:19:02 -!- realzies has quit (Excess Flood).
00:20:19 <oerjan> myname: it's like a parallel world that we barely know about.
00:21:30 -!- realzies has joined.
00:37:47 <HackEgo> qwerbcoin vilitafnrcoin tingcoin byocoin minarylambdcoin aanuecoin suprefcoin whospirequatinuspitmarrootypervellowfoocoin fiablecoin estatcoin gokacoin auercoin colmogenontagcoin homedumquecoin mustcoin wheeccoin bibelatincoin chocoin cemcoin lengomagecoin
00:40:19 -!- Sprocklem has quit (Ping timeout: 252 seconds).
01:11:18 <Sgeo> Is there anything interesting about Objective-C other than a slight Smalltalk heritage that drops the fantasic IDE?
01:12:57 <impomatic> Debating whether to call my gf to ask where the laminator is?
01:12:57 <impomatic> Pros: I bet she knows exactly where it is.
01:12:57 <impomatic> Cons: She gets annoyed at the slightest thing. Calling at 2:12am might not be the best idea.
01:15:36 -!- conehead has quit (Quit: Textual IRC Client: www.textualapp.com).
01:16:32 -!- mcpherrin has quit (Ping timeout: 265 seconds).
01:19:58 -!- zzo38 has quit (Ping timeout: 240 seconds).
01:19:59 <kmc> every program is an interpreter
01:20:02 <kmc> every vegetable is a word
01:31:50 -!- zzo38 has joined.
01:34:54 -!- {hk3380} has quit (Ping timeout: 265 seconds).
01:36:34 -!- BeingToDeath has joined.
01:39:38 <kmc> bremsstrahlung
01:46:34 <kmc> party pooper?
01:47:28 -!- zeusammon has joined.
01:49:35 -!- zeusammon has left.
01:58:51 <Sgeo> kmc: do you agree with the ; making a significant semantic difference thing?
01:59:29 <Sgeo> 1;2 is 2, 1;2; is (), iiuc
01:59:35 <kmc> return -ESGEO;
01:59:51 <kmc> you are talking about rust?
02:00:00 <kmc> yes, i am fine with that
02:00:16 <kmc> as long as the compiler gives a useful error message when you have a spurious semicolon at the end of a function
02:00:27 <kmc> which is a bug I opened; I don't remember if it's been fixed
02:02:05 <Sgeo> Rust doesn't try to be innovative, does it? Where does it get its inherited mutability concept from? Doesn't seem Haskelly, unless you consider using State + lenses to be similar
02:02:28 <kmc> there are some innovative things
02:03:58 <kmc> mainly lifetime checking, and statically enforced move semantics
02:04:08 <kmc> it's the first "mainstream" language with substructural types, isn't it?
02:04:18 <kmc> where I have carefully defined "mainstream" to just barely include Rust
02:04:37 <kmc> Sgeo: http://doc.rust-lang.org/rust.html#influences
02:05:00 <kmc> 'Rust is not a particularly original language. It may however appear unusual by contemporary standards, as its design elements are drawn from a number of "historical" languages that have, with a few exceptions, fallen out of favour.'
02:05:25 <Sgeo> "The lexical identifier rule of Python."
02:05:32 <Sgeo> That seems... a bit like faint praise
02:05:41 <kmc> i don't even know what that means
02:05:54 <Sgeo> I'm guessing which characters are allowed in names
02:05:55 <kmc> but i don't disapprove of faintly praising python :)
02:05:56 -!- Sprocklem has joined.
02:12:12 <Sgeo> Smalltalk should use lifetime semantics for ^
02:13:37 <oerjan> kmc: so you are saying Rust is already more mainstream than Clean ever was?
02:14:25 -!- nooodl_ has joined.
02:14:33 -!- mcpherrin has joined.
02:16:10 <Sgeo> kmc: or maybe it means 'self' instead of 'this'
02:17:36 <kmc> http://alexweymouth.files.wordpress.com/2009/12/socialist-hierarchy.png
02:18:13 -!- nooodl has quit (Ping timeout: 252 seconds).
02:22:58 <ion> kmc: > Copyright
02:24:07 <Bike> socialism is hardly anti-copyright
02:24:51 <HackEgo> /home/hackbot/hackbot.hg/multibot_cmds/lib/limits: line 5: exec: `coins: not found
02:26:02 <HackEgo> lobolgaarvcoin refixacoin selfrovcoin remiecoin embergeompsringariologcoin totteravecoin lowfourcoin bamcoin fobcoin booblcoin embcoin brycoin jamecoin neumenernanchcoin stilecoin marchiecoin beauxcoin erarcoin gammaerolamcoin tamcoin
02:33:55 -!- Sorella has quit (Quit: It is tiem!).
02:46:07 -!- nooodl_ has quit (Quit: Ik ga weg).
02:47:14 -!- tromp__ has joined.
02:48:05 <zzo38> Are there any MML->MOD compilers that you know of?
02:48:27 <Bike> i i i i i i i i i i i i i i
02:48:48 -!- tromp_ has quit (Ping timeout: 276 seconds).
02:56:06 <zzo38> What are the rules for ordering MIDI messages?
02:57:12 <kmc> i before e except after c
02:57:31 <HackEgo> [wiki] [[1+]] M http://esolangs.org/w/index.php?diff=39718&oldid=39712 * Oerjan * (+6) Ye olde conformity
03:02:55 <zzo38> Do you like this C macro? #define objdup(x) memcpy(malloc(sizeof(x)),&(x),sizeof(x))
03:04:08 <Bike> It Is A Bad macro
03:04:24 <Bike> gotta capitzlie eevyerhint
03:04:37 <zzo38> Why do you want to capitalize it?
03:04:58 <Bike> god told me my warranty was out
03:05:21 <zzo38> Yes, malloc could fail
03:05:29 -!- MoALTz has quit (Read error: Connection reset by peer).
03:06:04 <mcpherrin> if it does you'll write to 0 which is fine since you'll fault immediately
03:06:20 <Bike> why is it a macro anyway
03:06:21 -!- MoALTz has joined.
03:06:56 <zzo38> Bike: So that "sizeof" can be used?
03:07:30 <Bike> i thought you could use sizeof on values in this glorious future
03:07:32 <mcpherrin> Bike: can't write that as a function in C since you don't have generics otherwise
03:08:02 <Bike> i also thought memcpy and malloc just did void* shit
03:08:32 <mcpherrin> passing a void* to the function doesn't work since you then can't use sizeof
03:11:17 <oerjan> !c printf("%d\n"; sizeof (void));
03:12:14 <oerjan> !c printf("%d\n", (int) sizeof (void));
03:13:04 <zzo38> I think it is a GNU extension that sizeof(void) is allowed
03:13:23 <pikhq> It's a consequence of allowing arithmetic on void*.
03:13:38 <Bike> so i have unfortunately discovered i am pissy about a programming thing: namely, the billionth fucking time somebody walks into irc and complains about an "inaccurate" division
03:20:02 <Bike> !c printf("%f\n", 1.0/3.0);
03:23:43 <Bike> !c printf("%f\n", (float)(1.0/3.0)); // i don't know c lel
03:23:44 -!- password2 has joined.
03:24:09 <mcpherrin> Bike: inaccurate as in "I don't understand IEEE754"?
03:24:35 <mcpherrin> the other option is inaccurate as in "wtf why doesn't this cpu do IEEE754 correctly"
03:24:44 <Sprocklem> !c printf("%.8f\n", 1.0/3.0+1.0/3.0+1.0/3.0);
03:24:45 <Bike> i mean, understanding floats is a tall order, but you could at least have the humility not to assume it's a bug
03:25:15 <Sprocklem> !c printf("%.8f\n", 1.0f/3.0f+1.0f/3.0f+1.0f/3.0f);
03:26:33 <Sprocklem> Bike: Generally assuming the cpu is doing IEEE754 correctly is right, even if it seems otherwise at first glace
03:28:46 <Bike> the problem in this case was 1/3 printing as .33333334
03:29:44 <Bike> Singles, but yeah.
03:30:57 <Bike> oh. i can't tell.
03:31:10 <Bike> !c printf("%.8f\n", 1.0f/3);
03:31:49 <mcpherrin> I had to write code on a hardware platform with broken floats for a few months
03:31:49 <Sprocklem> It's single prescision converted to double at printf (which shouldn't change the number)
03:32:09 <Bike> what platform? a dsp or something?
03:32:31 <mcpherrin> http://en.wikipedia.org/wiki/MaverickCrunch
03:32:37 <Bike> "intended for digital audio", i was close
03:32:45 <Bike> plagued with hardware bugs lol
03:33:37 <mcpherrin> "imprecise or garbage results or clobber registers or memory"
03:33:40 <Bike> "Cirrus Logic's Crunch tools, a repackaging of GNU tools modified by Nucleusys of Bulgaria (or was it they who did the work later submitted by RedHat?)"
03:33:45 <Bike> v. encyclopedic
04:08:58 -!- password2 has quit (Ping timeout: 240 seconds).
04:19:32 <kmc> i know i won't be leavin' here w/ you
04:24:49 <monotone> (tempo slows, transition to second half of song)
04:25:27 <kmc> drink to the devil and death to the doctors
04:26:07 <monotone> I think this record is skipping.
04:27:49 <kmc> monotone: we, alone on earth, have the power to free ourselves from the tyranny of the selfish replicators
04:29:47 <monotone> Who swapped the music for audiobooks?!
04:29:49 <Bike> I'M A MAN OF WEALTH AND TASTE, HOPE YOU GUESSED MY NAAAAAME
04:32:56 <kmc> the fallen are the virtuous among us
04:33:02 <Bike> I GET KNOCKED DOWN, BUt I get up again, and you're never gonna *trails off*
04:33:50 -!- monotone has changed nick to polytone.
04:34:01 <kmc> the fallen are the virtuous among us
04:37:47 <kmc> hug hug hug
04:40:50 <polytone> I'm beginning to think these speakers are possessed.
04:44:57 <polytone> Where's fungot when I need an exorcist?
04:45:53 <Bike> whither fungot
04:53:43 <kmc> how 'bout them turing machines
04:53:57 <kmc> never know when they're gonna stop
04:54:12 <Bike> they call em turing but i've never seen em tur
04:57:04 <shachaf> http://www-cs-faculty.stanford.edu/~uno/news12.html
04:59:20 <oerjan> what's a flasing machine twh
05:00:21 <oerjan> you know google doesn't like a word when it corrects it even in quotes
05:24:54 <zzo38> How many tiles to people lose at Pokemon card by using a DEFENDER card even though it is to your opponent's advantage for you to do so?
05:29:41 <zzo38> I certainly would not expect it to be common.
05:31:08 -!- diginet has quit (Quit: diginet has quit!).
05:38:22 -!- BeingToDeath has quit.
05:41:46 -!- BeingToDeath has joined.
05:54:44 <zzo38> When playing at Pokemon card, I like to "slow play" the cards often. It saves me against running out of cards, and other things too.
06:05:30 -!- conehead has joined.
06:15:39 -!- oerjan has quit (Quit: leaving).
06:25:19 -!- BeingToDeath has quit.
06:30:55 -!- MoALTz has quit (Quit: Leaving).
06:50:07 -!- jkool has joined.
06:50:50 -!- jkool has left.
06:56:39 -!- tromp__ has quit (Read error: Connection reset by peer).
06:57:15 -!- tromp_ has joined.
06:57:21 -!- conehead has quit (Quit: Computer has gone to sleep).
07:03:17 <zzo38> Do you know those game they tell you two picture, you have to figure out the difference? Now, there is one with animated pictures.
07:29:25 <Sgeo> I wish I could say 'I need a drink' without being weird
07:35:54 -!- MindlessDrone has joined.
07:36:18 -!- TodPunk has quit (Read error: Connection reset by peer).
07:54:02 <zzo38> What drink do you need?
08:02:27 <FireFly> what would be an example of it being beneficial for the opponent if you use a defender?
08:04:30 <zzo38> FireFly: If you have an attack that damages both opponent's active and bench pokemon card, and you do not want to knock out the opponent's active pokemon card, then if they use DEFENDER card then it can be of your benefit.
08:05:24 <zzo38> The stupid AI in Pokemon Card GB2 does that a lot.
08:06:14 <FireFly> I can't remember seeing that, but I also can't remember seeing many NPCs with defender cards
08:06:54 <FireFly> Maybe I just didn't think about it
08:10:12 <zzo38> Some strategy guides say the best time to use a GAMBLER card is when it is the only card in your hand, but I don't believe that. I think the best time is when your hand has a large number of worthless cards.
08:11:35 <Sgeo> zzo38: the 'pretend I'm not awake at 4:11 AM on a conference call for work' drink
08:16:21 <Sgeo> Someone please help me
08:17:05 -!- {hk3380} has joined.
08:17:23 <zzo38> Maybe you should just go back to sleep then?
08:18:08 <Sgeo> Can't, until the call is done
08:21:25 -!- drdanmaku has quit (Quit: Connection closed for inactivity).
08:22:19 -!- {hk3380} has quit (Ping timeout: 252 seconds).
08:30:14 -!- Patashu has joined.
08:40:05 <zzo38> FireFly: There are a few NPCs in such a game who have DEFENDER cards. Mostly ones with electric pokemon cards, but there are some others.
08:44:13 <Sgeo> Coworker told me to drop off the call
08:54:28 -!- diginet has joined.
08:57:30 -!- Patashu has quit (Disconnected by services).
08:57:30 -!- Patashu_ has joined.
09:13:22 <HackEgo> [wiki] [[Talk:Rail]] http://esolangs.org/w/index.php?diff=39719&oldid=39612 * 84.174.99.204 * (+242)
10:01:10 -!- {hk3380} has joined.
10:09:06 -!- {hk3380} has quit (Quit: WeeChat 0.3.8).
10:12:26 <myname> oh dear, broken implementationss
10:13:30 -!- boily has joined.
10:33:16 -!- edwardk has quit (Quit: Computer has gone to sleep.).
11:09:56 -!- boily has quit (Quit: Poulet!).
11:15:11 -!- Sorella has joined.
11:16:13 -!- edwardk has joined.
11:57:25 -!- Sgeo has quit (Read error: Connection reset by peer).
12:04:29 -!- MindlessDrone has quit (Quit: MindlessDrone).
12:20:25 -!- yorick has joined.
12:27:47 -!- zzo38 has quit (Remote host closed the connection).
12:34:28 -!- MindlessDrone has joined.
12:52:11 -!- fungot has joined.
13:12:50 -!- Patashu_ has quit (Ping timeout: 265 seconds).
13:20:19 -!- sign has changed nick to systemd.
13:21:21 -!- systemd has changed nick to sign.
13:28:51 -!- spiette has joined.
13:34:00 -!- nycs has quit (Ping timeout: 258 seconds).
13:34:25 -!- nooodl has joined.
13:38:07 -!- nycs has joined.
13:43:06 -!- nycs has changed nick to `^_^v.
13:51:53 -!- Sprocklem has quit (Ping timeout: 264 seconds).
13:52:35 -!- conehead has joined.
13:53:10 -!- tertu has quit (Ping timeout: 258 seconds).
13:58:57 -!- nooodl has quit (Ping timeout: 276 seconds).
13:59:47 -!- tertu has joined.
14:02:36 -!- TodPunk has joined.
14:04:01 -!- Vorpal has joined.
14:21:05 -!- password2 has joined.
14:32:16 -!- Sprocklem has joined.
14:44:08 -!- Slereah_ has joined.
14:45:48 -!- Slereah has quit (Ping timeout: 240 seconds).
14:53:39 -!- mihow has joined.
14:56:36 -!- MindlessDrone has quit (Ping timeout: 240 seconds).
14:58:14 -!- edwardk has quit (Quit: Computer has gone to sleep.).
15:10:33 -!- MindlessDrone has joined.
15:12:44 -!- Sprocklem has quit (Quit: g2g).
15:32:23 <Jafet> Apparently, there are 2^53-1 doubles that represent NaN, so you can use them to store pointers, which each take up only 48 bits.
15:35:49 <Melvar> Is there a standard C function that prints a double parsimoniously?
15:38:47 <Bike> parsimoniously meaning what?
15:39:29 -!- rottytooth has joined.
15:40:19 <Melvar> Using exactly as many digits as necessary to identify the double value uniquely.
15:42:23 <Jafet> Would that require a magnanimous scanner?
15:42:27 <Melvar> As I remember that is not exact, but 0.2 will parse into the same value, so 0.2 is sufficient output.
15:43:19 -!- MDream has changed nick to MDude.
15:43:30 <Melvar> !c printf(%a\n", 1.0 / 5.0);
15:43:44 <Melvar> !c printf("%a\n", 1.0 / 5.0);
15:45:09 <Melvar> Seems to be restricted to hex output.
15:45:39 <Bike> yeah, and the float radix is two, so...
15:46:24 <Jafet> "Linux libc4.[45] does not have a snprintf(), but provides a libbsd that contains an snprintf() equivalent to sprintf(), that is, one that ignores the size argument."
16:06:14 <int-e> that's the axiomatic solution to security. (axiom 1: buffers do not overflow)
16:06:49 <olsner> sprintf will never fail due to a small buffer, that's pretty great compared to snprintf which might just not print the whole string
16:08:46 <int-e> the buffer might extend into the sprintf stack frame, destroying data it's working with, thus causing it to fail. hth
16:09:10 <int-e> (I know, stacks generally grow downwards so that scenario is unlikely)
16:09:51 <mroman> well buffers certainly overflow themselves
16:10:23 <mroman> know the whole pointe is gone
16:10:43 <int-e> there was a point?
16:12:47 -!- ter2 has joined.
16:12:47 -!- tertu has quit (Disconnected by services).
16:13:56 -!- tertu3 has joined.
16:14:49 -!- drdanmaku has joined.
16:17:02 -!- ter2 has quit (Ping timeout: 255 seconds).
16:22:22 -!- tertu3 has quit (Ping timeout: 245 seconds).
16:43:33 -!- tromp_ has quit (Remote host closed the connection).
16:46:08 -!- MoALTz has joined.
17:07:24 -!- mihow has quit (Quit: mihow).
17:18:01 -!- edwardk has joined.
18:14:44 -!- mihow has joined.
18:47:05 -!- MoALTz has quit (Read error: Connection reset by peer).
18:47:53 -!- MoALTz has joined.
18:57:22 -!- AnotherTest has joined.
19:18:55 -!- kallisti has joined.
19:20:18 -!- Bike has quit (Ping timeout: 240 seconds).
19:22:15 -!- edwardk has quit (Read error: Connection reset by peer).
19:22:15 -!- Bike has joined.
19:24:59 -!- edwardk_ has joined.
19:32:27 -!- mihow has quit (Quit: mihow).
19:32:42 -!- mihow has joined.
19:43:40 <kmc> all hail discordia
19:47:11 <int-e> oh most beautiful apple. or something
19:47:32 -!- tromp_ has joined.
19:47:59 -!- AnotherTest has quit (Ping timeout: 252 seconds).
19:52:33 -!- tromp_ has quit (Ping timeout: 276 seconds).
19:52:56 <kmc> pomme de terre
20:03:46 <int-e> I didn't need to see that
20:04:18 -!- polytone has changed nick to monotone.
20:05:55 <kmc> http://www.walmart.com/ip/Butterfly-Labs-Bitcoin-Miner-10-GH-S-Processor-USB-2.0-BF0010G/34952957
20:10:52 <int-e> At the current rate that will mine one bitcoin in 150 years?
20:12:09 <int-e> ah no, that's block per year; the reward per block is higher
20:13:05 <int-e> So 6 years per bitcoin currently, if you add it to some pool.
20:13:11 <kmc> Get effective Bitcoining with the Butterfly Labs Bitcoin Miner. It is easy to use and can be plug-n-play via USB 2.0. It has 65nm ASIC Bitcoin Mining Chips to keep track of every transaction and fast processing of data. Its sleek design allows you to keep it on your workstation and experience its power.
20:16:44 <int-e> so what's its power consumption? https://en.bitcoin.it/wiki/Mining_hardware_comparison doesn't list anything
20:17:26 -!- erdic has joined.
20:18:01 <int-e> though it seems reasonable to assume that it's the same as the 5GH and 20GH models.
20:18:36 -!- password2 has quit (Ping timeout: 240 seconds).
20:18:58 <int-e> so that would be 60W
20:24:28 <int-e> which adds about $100 a year to your electricity bill?
20:25:39 <int-e> (at $0.16 a kWh; the price for electricity varies a lot)
20:26:18 <olsner> at my electricity price I think it'd be more like $10/year
20:26:43 <int-e> > 60*24*365 / 10^3
20:27:16 <int-e> > 60*24*365 / 10^3 * 0.16
20:27:39 <int-e> > 10 / (60*24*365)
20:28:06 <int-e> $0.02/kWh ? that seems too low
20:30:26 <olsner> hmm, ~100 re isn't a tenth of a SEK
20:32:56 <olsner> 525.6kWh/year times 0.6948 SEK/kWh is about $55/year
20:33:06 <int-e> http://shrinkthatfootprint.com/wp-content/uploads/2013/09/electricprices.gif
20:33:19 <tromp> isn't that a refurbish?
20:35:31 <olsner> according to google that's exactly $.10 per kwh ... but it probably doesn't include *all* the taxes and fees
20:41:06 -!- rottytooth has left.
20:41:17 -!- rottytooth has joined.
20:42:09 <olsner> interesting table of Mhash/J there, surprisingly small difference between gpus and cpus, and a huge leap to the asics and fpgas
20:43:01 -!- rottytooth has quit (Quit: HydraIRC -> http://www.hydrairc.com <- Chicks dig it).
20:45:25 <tromp> my PoW tries to reduce that big gap
21:00:25 -!- mhi^ has joined.
21:02:00 -!- Patashu has joined.
21:05:33 -!- Patashu has quit (Disconnected by services).
21:05:33 -!- Patashu_ has joined.
21:07:47 -!- Patashu has joined.
21:12:18 -!- Patashu_ has quit (Ping timeout: 265 seconds).
21:15:38 <kallisti> any idea where I can find stats on the number of IP-based telecom networks, the number of IP addresses they use, and which version of IP they support?
21:16:00 <mcpherrin> kallisti: taht depends on what exactly you mean by IP-based
21:16:08 <mcpherrin> Are you talking about IP-to-the-customer?
21:16:47 <kallisti> not sure what IP-to-the-customer means exactly, but I think I'm just talking about backhaul over IP.
21:17:15 <mcpherrin> Stuff like magicjack or a SIP phone provider, where the customer has some IP device that connects
21:17:42 -!- Bike has quit (Ping timeout: 276 seconds).
21:17:44 <kallisti> ah, well, that would be included, but I was just talking about any kind of telecom network that uses IP as its backbone. I'm assuming it's likely the majority of telecon networks at this point.
21:17:50 <mcpherrin> versus something more like a traditional phone carrier that does backhaul over IP, like Comcast
21:19:24 -!- Bike has joined.
21:19:29 <mcpherrin> everybody doing cell phones is doing IP. Every non-traditional (eg, cable company) phone provider is doing IP
21:20:05 <mcpherrin> Some legacy provider networks may not, but that'll just be because they're on like 20 year hardware replacement cycles
21:22:14 <kmc> do they run SS7 over IP?
21:22:18 <kallisti> yeah I'm just trying to find stats on Ipv4 vs v6 in telecom networks
21:22:33 <kallisti> in particular how many IPv4 addresses are being used by telecom infrastructure
21:23:18 <mcpherrin> kallisti: Last I had access, it's nearly all using 10/8
21:23:19 -!- edwardk_ has quit (Ping timeout: 252 seconds).
21:24:05 <mcpherrin> That is, IPv4 10.0.0.0/8 private address space
21:24:20 <int-e> ppp0 Link encap:Point-to-Point Protocol
21:24:20 <int-e> inet addr:10.8.115.127 P-t-P:10.0.0.1 Mask:255.255.255.255
21:25:20 <mcpherrin> But I had a pretty narrow view so I could be wrong in a global sense
21:25:53 -!- Patashu has quit (Ping timeout: 252 seconds).
21:26:34 -!- not^v has joined.
21:27:21 <mcpherrin> global routing stuff is done with SCCP and GTT and I dunno I forget all this stuff
21:36:38 -!- MindlessDrone has quit (Quit: MindlessDrone).
21:40:00 -!- not^v has quit (Quit: http://i.imgur.com/Akc6r.gif).
21:42:57 -!- boily has joined.
21:57:59 <boily> <Bike> anneal your pgorgram into existence ← uh, what?
22:04:02 <Taneb> I bought some comics today :)
22:04:47 -!- edwardk has joined.
22:07:27 <boily> Taneb: which ones? what kind? format? language? ink?
22:07:49 <Taneb> An Avengers vs X-Men collection, portrait, english, unknown
22:08:16 <Taneb> Also the first volume of the Melancholy of Haruhi Suzumiya, portrait, english, unknown but largely black-and-white
22:13:20 -!- oerjan has joined.
22:13:24 <Taneb> Yes, I am afraid I am too monolingual to appreciate the comics in any other language
22:22:08 -!- Bicyclidine has joined.
22:22:39 -!- mihow has quit (Quit: mihow).
22:26:11 <boily> Taneb: not a problem. can read them.
22:26:29 -!- edwardk has quit (Quit: Computer has gone to sleep.).
22:27:26 -!- MDude has quit (Quit: later chat).
22:28:26 -!- edwardk has joined.
22:28:48 -!- rottytooth has joined.
22:29:18 -!- mhi^ has quit (Quit: Lost terminal).
22:32:36 -!- edwardk has quit (Client Quit).
22:41:01 -!- Sgeo has joined.
22:43:16 -!- boily has quit (Quit: Poulet!).
22:43:27 <Sgeo> So, interested in full-disk encryption. Going to try out TrueCrypt on the drive with all my important documents. I hear there's a new version, should try it out
22:47:59 <Sgeo> The cryptoworld is being trolled, apparently
22:48:14 <Sgeo> cryptosphere? Like biosphere?
22:48:55 <oerjan> i am obliged to annoy y'all by linking http://xkcd.com/538/
22:49:19 <Taneb> I am so annoyed I am going to go to bed
22:49:34 <Taneb> Also, getting an ice cream today was the best idea.
22:49:49 * oerjan also got some ice cream, with apple cake
22:53:09 <oerjan> Bicyclidine: also imagine Sgeo neither has backups nor wipes the unencrypted parts of the disk properly afterwards.
22:53:38 <Sgeo> :/ my backup situation is... uh... (not trolling about that)
22:53:44 <oerjan> i guess truecrypt installation ought to handle the latter, or something.
22:53:59 * oerjan has no idea, but it *ought* to.
22:54:51 <oerjan> <Taneb> cryptobubble? <-- oh right time for my daily bitcoin check
22:55:32 <int-e> fun chart. http://divananalit.org/graphs/bitcoin-profitability-from-20130201-to-now.png
22:56:28 <Bicyclidine> at least the difficulty is nice and regular
22:57:34 <int-e> I guess it's mostly an efficient market.
22:58:31 -!- yorick has quit (Remote host closed the connection).
22:58:41 <oerjan> it's a bit hard to read from that whether the miners are actually profiting or not
22:58:51 <int-e> (the way to make money off bitcoing mining though, is to either sell the next generation of miners or to be an electricity company)
22:59:31 <int-e> oerjan: right. I was reading this thread: https://bitcointalk.org/index.php?topic=570396.0
23:07:54 -!- tromp_ has joined.
23:08:51 <int-e> I guess there are two ways to mine profitably. one, be an early adapter of the next jump in efficiency (not much room left there, apparently), or 2, mine on other people's hardware (think botnet).
23:11:45 -!- Phantom_Hoover has joined.
23:12:04 <olsner> if I understand your meaning of "opposite" right, the opposite is also break even?
23:12:59 <int-e> "running on other people's hardware" also includes javascript bitcoin miners (a horrible waste of resources, but it's born by the website visitors)
23:13:12 <int-e> it's -> the cost is
23:14:15 <Bicyclidine> fuck entropy, though, so it's basically the same
23:15:47 -!- edwardk has joined.
23:19:27 -!- aretecode has joined.
23:19:55 -!- skarn has quit (Ping timeout: 240 seconds).
23:20:45 -!- skarn has joined.
23:21:06 -!- skarn has changed nick to Guest53344.
23:22:08 <HackEgo> ArEtEcOdE: 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.)
23:22:21 <int-e> http://www.alcula.com/calculators/finance/bitcoin-mining/ looks fun to play with
23:24:22 <aretecode> http://esolangs.org/wiki/Main_page says there is currently no text in this page.
23:24:54 <HackEgo> 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.)
23:28:54 <oerjan> aretecode: sadly the P needs to be capitalized too.
23:29:32 -!- Rugxulo has joined.
23:30:10 <oerjan> @tell fizzie i think the job of making the url's in `WELCOME and `WeLcOmE actually work has now devolved to you.
23:32:01 <oerjan> the previous webmaster overcomplicated it so much that he gave up on actually implementing it.
23:32:23 <aretecode> I would think it would be easiest to send it without "Main_Page" just like http://esolangs.org/wiki
23:32:42 <oerjan> aretecode: well that still won't make /WiKi work
23:33:02 <aretecode> In your router, lower case the argument
23:33:12 <oerjan> and indeed we did that for the spanish version, because it wouldn't fit on a line otherwise
23:33:28 <oerjan> aretecode: yeah but fizzie will have to do that.
23:33:58 <aretecode> oejan, you made the url longer so that it would fit on a line in spanish??
23:34:13 <oerjan> no, shorter. the spanish has extra info
23:34:17 <HackEgo> ¡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.)
23:34:43 <oerjan> (that info being "We don't actually speak spanish here")
23:35:18 <oerjan> we made it just that, no /wiki. hm...
23:35:42 <olsner> hmm, that bit is also case insensitive
23:35:46 <oerjan> that _would_ work on `WELCOME and `WeLcOmE
23:36:14 <olsner> took us a few years to work that out... did esolangs.org/ not use to redirect to the wiki?
23:36:20 <aretecode> 1) doesn't fit on a line for me 2) what olsner said 3) it isn't a spanish site
23:36:44 <oerjan> aretecode: not a line in your client, but the maximal irc line limit
23:37:44 <oerjan> `run sed -i 's!wiki/main_page!!i' bin/{WeLcOmE,WELCOME}
23:37:53 <HackEgo> 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.)
23:38:14 <oerjan> is there some option to make s case insensitive
23:39:26 <Rugxulo> online GNU sed manual says capital I
23:40:05 <oerjan> `run sed -i 's!wiki/main_page!!I' bin/{WeLcOmE,WELCOME}
23:40:11 <HackEgo> 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.)
23:40:29 <oerjan> `run sed -I -i 's!wiki/main_page!!' bin/{WeLcOmE,WELCOME}
23:40:29 <HackEgo> sed: invalid option -- 'I' \ Usage: sed [OPTION]... {script-only-if-no-other-script} [input-file]... \ \ -n, --quiet, --silent \ suppress automatic printing of pattern space \ -e script, --expression=script \ add the script to the commands to be executed \ -f script-file, --file=script-file \
23:40:40 <oerjan> this is probably not GNU sed :(
23:40:45 <HackEgo> bash: -c: line 0: unexpected EOF while looking for matching ``' \ bash: -c: line 1: syntax error: unexpected end of file
23:41:01 <HackEgo> bash: -c: line 0: unexpected EOF while looking for matching ``' \ bash: -c: line 1: syntax error: unexpected end of file
23:41:07 <HackEgo> bash: -c: line 0: unexpected EOF while looking for matching ``' \ bash: -c: line 1: syntax error: unexpected end of file
23:41:12 <HackEgo> GNU sed version 4.2.1 \ Copyright (C) 2009 Free Software Foundation, Inc. \ This is free software; see the source for copying conditions. There is NO \ warranty; not even for MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE, \ to the extent permitted by law. \ \ GNU sed home page: <http://www.gnu.org/software/sed/>. \ General help using GNU so
23:41:15 <oerjan> Rugxulo: no ending ` sheesh
23:41:38 <HackEgo> [wiki] [[TOD]] http://esolangs.org/w/index.php?diff=39720&oldid=31565 * Null * (+120) /* Execution */ add two missing instructions
23:42:42 <olsner> `run echo asdf | sed 's/ASDF/foo/i'
23:42:44 <oerjan> `run perl -p -n -i 's!wiki/main_page!!i;' bin/{WeLcOmE,WELCOME}
23:42:44 <HackEgo> Can't open perl script "s!wiki/main_page!!i;": No such file or directory
23:42:55 <oerjan> `run perl -p -n -i -e 's!wiki/main_page!!i;' bin/{WeLcOmE,WELCOME}
23:43:05 <HackEgo> 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.)
23:44:40 <oerjan> `run sed -i 's!WiKi/MaIn_pAgE!!' bin/WeLcOmE
23:44:47 <HackEgo> 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.)
23:45:03 <HackEgo> #!/bin/sh \ welcome "$@" | CaT
23:45:41 <HackEgo> 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.)
23:46:02 <Rugxulo> `run sed -e ',WiKi/MaIn_pAgE,!d' bin/WeLcOmE
23:46:03 <HackEgo> sed: -e expression #1, char 1: unknown command: `,'
23:46:05 <oerjan> `run sed -i 's!wiki/Main_Page!!' wisdom/welcome
23:46:14 <HackEgo> Welcome to the international hub for esoteric programming language design and deployment! For more information, check out our wiki: <http://esolangs.org/>. (For the other kind of esoterica, try #esoteric on irc.dal.net.)
23:46:31 <Rugxulo> `run sed -e '\,WiKi/MaIn_pAgE,!d' bin/WeLcOmE
23:46:48 <oerjan> Rugxulo: plz stop and pay attention hth
23:47:10 <HackEgo> WeLcOmE To tHe iNtErNaTiOnAl hUb fOr eSoTeRiC PrOgRaMmInG LaNgUaGe dEsIgN AnD DePlOyMeNt! FoR MoRe iNfOrMaTiOn, ChEcK OuT OuR WiKi: <hTtP://EsOlAnGs.oRg/>. (fOr tHe oThEr kInD Of eSoTeRiCa, TrY #eSoTeRiC On iRc.dAl.nEt.)
23:47:11 <oerjan> (it was a stupid mistake of not remembering how the `welcomes work)
23:47:51 -!- Bike has quit (Ping timeout: 276 seconds).
23:48:28 <oerjan> @tell fizzie Never mind, we found a better way
23:48:59 -!- Bike has joined.
23:59:00 -!- Bicyclidine has quit (Ping timeout: 240 seconds).
00:01:54 <ion> http://spacecollege.org/isee3/we-are-now-in-command-of-the-isee-3-spacecraft.html
00:14:55 -!- Rugxulo has quit (Quit: ERC Version 5.3 (IRC client for Emacs)).
00:30:17 -!- Phantom_Hoover has quit (Quit: Leaving).
00:49:19 -!- not^v has joined.
01:02:17 <kmc> "This is the kind of movie where a man shitting in a hat is not enough; he must shit in two hats, and then spill one of them in close-up."
01:08:30 <Bike> is this re: the ISEE
01:10:08 <oerjan> nope, this is some unrelated shit
01:20:30 -!- rottytooth has quit (Quit: HydraIRC -> http://www.hydrairc.com <- Wibbly Wobbly IRC).
02:10:55 <Sgeo> http://www.reddit.com/r/ruby/comments/26st9q/got_missing_methods_solution_method_not_missing/
02:22:21 <ion> http://new.livestream.com/spacex/DragonV2
02:29:24 -!- MoALTz has quit (Read error: Connection reset by peer).
02:30:11 -!- MoALTz has joined.
02:42:26 <ion> http://en.wikipedia.org/wiki/HAL/S#Syntax
03:01:26 -!- aretecode has quit (Ping timeout: 255 seconds).
03:04:14 <Sgeo> Hum. I don't think my solution on XSS-Game level 6 was the intended one
03:05:07 <Sgeo> V hfrq n qngn HEV
03:06:27 <oerjan> hff wrx furfu xecp ntower
03:08:17 <Sgeo> Only one of those words is rot13?
03:08:55 <Bike> did you know that if you pick a random series of letters there's a 50% chance that it's rot13 for D I C K S Q U A D
03:08:57 <kmc> the rest are rot26
03:10:48 <Bike> ⅅ 𝕀 ℂ 𝕂 𝕊 ℚ 𝕌 𝔸 𝔻
03:11:16 <oerjan> `unidecode ⅅ 𝕀 ℂ 𝕂 𝕊 ℚ 𝕌 𝔸 𝔻
03:11:17 <HackEgo> [U+2145 DOUBLE-STRUCK ITALIC CAPITAL D] [U+0020 SPACE] [U+1D540 MATHEMATICAL DOUBLE-STRUCK CAPITAL I] [U+0020 SPACE] [U+2102 DOUBLE-STRUCK CAPITAL C] [U+0020 SPACE] [U+1D542 MATHEMATICAL DOUBLE-STRUCK CAPITAL K] [U+0020 SPACE] [U+1D54A MATHEMATICAL DOUBLE-STRUCK CAPITAL S] [U+0020 SPACE] [U+211A DOUBLE-STRUCK CAPITAL Q] [U+0020 SPACE] [U+1D54C M
03:11:50 <HackEgo> [U+2145 DOUBLE-STRUCK ITALIC CAPITAL D] [U+1D540 MATHEMATICAL DOUBLE-STRUCK CAPITAL I] [U+2102 DOUBLE-STRUCK CAPITAL C] [U+1D542 MATHEMATICAL DOUBLE-STRUCK CAPITAL K] [U+1D54A MATHEMATICAL DOUBLE-STRUCK CAPITAL S] [U+211A DOUBLE-STRUCK CAPITAL Q] [U+1D54C MATHEMATICAL DOUBLE-STRUCK CAPITAL U] [U+1D538 MATHEMATICAL DOUBLE-STRUCK CAPITAL A] [U+1D5
03:12:25 <oerjan> wait is that blackboard bold
03:12:28 <Bike> hackego wants the d
03:13:02 <Bike> In addition, a blackboard-bold Greek letter mu (not found in Unicode) is sometimes used by number theorists and algebraic geometers (with a subscript n) to designate the group (or more specifically group scheme) of n-th roots of unity.
03:13:13 <Bike> so even with all these bullshit characters they're missing ones mathematicians actually use
03:20:00 <pikhq> Do they have blackboard-bold aleph though?
03:21:37 <kmc> do they have blackboard-bold multiocular O
03:36:35 -!- conehead has quit (Ping timeout: 252 seconds).
03:38:39 <kmc> black hole sun
03:40:27 -!- conehead has joined.
03:52:15 <Sgeo> Black Sun, Blaxxun. I miss Cybertown
03:52:25 <Sgeo> Also, no green sun?
03:56:28 <quintopia> Sgeo (only): in what modern country was the mayan civilization located?
03:56:55 <Sgeo> I'm guessing either US or Mexico, but I'm not certain
03:59:35 <oerjan> it was no modern country hth
04:01:42 <kmc> no country for old mayans
04:05:10 <oerjan> quintopia: excuse me did you mean that as a joke or as a trick question, i need to know why to swat you twh
04:06:57 <quintopia> oerjan: it's a serious question. and mexico (or more specifically yucatan peninsula) is what i was looking for. (i hope you won't swat me for not writing out the longwinded version that makes it clear that i realize maya and mexico never coexisted)
04:07:59 * oerjan swats quintopia for not realizing the maya civilization included parts outside mexico -----###
04:08:17 <quintopia> damn that would have been doubly longwinded
04:08:56 <quintopia> the point was to find out what country random people most associate maya with. not whether they can list all the countries it overlapped.
04:09:33 <oerjan> if i recall correctly, the last independent maya kingdom conquered by the spanish was in nicaragua.
04:10:24 * oerjan learned that too on wikipedia
04:13:06 <oerjan> was probably guatemala. sound practically alike!
04:14:55 <quintopia> yeah one of my random pollees said "southern mexico, belize, and guatemala". she's too smart.
04:15:10 <kmc> i would have said "mexico and probably some other places"
04:16:42 <kmc> there are several nicaraguan and guatemalan restaurants within a short walk of my house
04:17:50 <oerjan> two last cities conquered in 1697
04:18:14 <newsham> used to live near a good el savadoran restaurant
04:22:22 <oerjan> wait am i forgetting to eat again ->
04:24:52 <kmc> http://imgur.com/gallery/Jb6jW
04:26:32 <Bike> complete comfort sounds pretty good
04:26:57 <kmc> FULL ABSOLUTE PROTECTION OF MICROCHIPS IMPLANTED INTO THE HUMAN !!!
04:27:06 <Bike> "It's like a pipboy... for your house!!" son,
04:29:00 -!- tertu3 has joined.
04:31:51 -!- not^v has quit (Read error: Connection reset by peer).
04:33:19 -!- tertu3 has quit (Client Quit).
04:33:41 -!- tertu3 has joined.
04:36:54 <Bike> a comment on the images
04:42:15 <kmc> what is your reaction meant to mean, though
04:53:56 <kmc> fungots fall on fungot falls
04:53:56 <fungot> kmc: but i don't believe i ever said anything about compiling))) you only need to work?'
04:54:51 -!- ter2 has joined.
04:54:51 -!- tertu3 has quit (Read error: Connection reset by peer).
04:54:59 -!- ter2 has changed nick to tertu.
04:59:51 <newsham> http://www.computerhistory.org/revolution/minicomputers/11/362
05:01:30 <oerjan> fungot: what is your opinion on rockets
05:01:30 <fungot> oerjan: s/ a comment/ fnord" is what i do actually know one or two sml implementations. scheme has so many parentheses, though?
05:01:51 <oerjan> fungot: that doesn't seem very relevant
05:01:52 <fungot> oerjan: the implementation is flawed. why do you wanna try my hand at porting it to common lisp, i personally am not a toy" or " fnord".
05:02:09 <oerjan> fungot: oh. sorry about that.
05:02:09 <fungot> oerjan: ' vehemently blurry' would be an idea to let users with commit access put eggs online too?!
05:02:10 -!- MoALTz_ has joined.
05:02:25 <Sgeo> http://blog.bryanbibat.net/2014/01/30/obligatory-hearthstone-post-from-a-former-magic-player/
05:04:10 <Bike> oddly, recipes were probably actually my first exposure to computers.
05:04:18 <Bike> my parents' cookbook still has printed emails from the 90s in it
05:05:07 -!- MoALTz has quit (Ping timeout: 258 seconds).
05:27:39 <HackEgo> [wiki] [[Talk:Rail]] M http://esolangs.org/w/index.php?diff=39721&oldid=39719 * Oerjan * (+48) unsigned, move to end of intro
05:29:36 -!- kmc has set topic: Vehemently blurry | brainfuck survey: https://www.surveymonkey.com/s/L82SNZV | https://dl.dropboxusercontent.com/u/2023808/wisdom.pdf http://codu.org/logs/_esoteric/ http://tunes.org/~nef/logs/esoteric/.
05:32:11 -!- not^v has joined.
05:32:14 <HackEgo> [wiki] [[Talk:Rail]] M http://esolangs.org/w/index.php?diff=39722&oldid=39721 * Oerjan * (+36) Move this long comment to own section
05:35:46 -!- edwardk has quit (Quit: Computer has gone to sleep.).
05:37:42 -!- edwardk has joined.
05:42:22 <Bike> is the set of lambda calculus terms that reduce to themselves in n steps r.e.?
05:52:40 <oerjan> just try all n step reductions on each term
05:53:23 <oerjan> there's only a finite number of options in each step
06:07:22 -!- oerjan has quit (Quit: leaving).
06:08:58 -!- password2 has joined.
06:09:07 <Bike> recursive, too, then.
06:21:13 -!- fowl has quit (Ping timeout: 252 seconds).
06:22:56 -!- fowl has joined.
06:26:42 -!- MoALTz_ has quit (Quit: Leaving).
06:41:22 -!- KingOfKarlsruhe has joined.
06:41:55 -!- not^v has quit (Ping timeout: 240 seconds).
06:42:46 -!- not^v has joined.
06:57:10 -!- MindlessDrone has joined.
07:04:27 -!- conehead has quit (Quit: Computer has gone to sleep).
07:10:50 <HackEgo> [wiki] [[User:Rdebath]] http://esolangs.org/w/index.php?diff=39723&oldid=39264 * Rdebath * (+10728) /* Performance Matrix */
07:11:56 <HackEgo> [wiki] [[User:Rdebath]] http://esolangs.org/w/index.php?diff=39724&oldid=39723 * Rdebath * (-7112) /* Performance Matrix */
07:21:47 -!- password2 has quit (Ping timeout: 260 seconds).
07:33:55 -!- Patashu has joined.
07:38:20 -!- Sorella has quit (Quit: It is tiem!).
07:45:53 <HackEgo> [wiki] [[User:Rdebath]] http://esolangs.org/w/index.php?diff=39725&oldid=39724 * Rdebath * (+271) /* Interpreter List */
08:07:43 <HackEgo> [wiki] [[User:Rdebath]] http://esolangs.org/w/index.php?diff=39726&oldid=39725 * Rdebath * (-1758) /* Interpreter List */
08:14:47 -!- Patashu_ has joined.
08:14:47 -!- Patashu has quit (Disconnected by services).
08:30:02 -!- Vorpal has quit (Quit: ZNC - http://znc.sourceforge.net).
08:35:42 -!- Slereah_ has quit (Ping timeout: 245 seconds).
08:36:07 -!- Slereah_ has joined.
08:46:21 * impomatic is just preparing to catch the train to Cambridge for the Core War tournament tomorrow :-)
08:47:05 <impomatic> I should be on IRC to post live updates from the tournament.
08:49:24 <myname> there are core war tournaments?
09:01:47 -!- slereah has joined.
09:06:57 <slereah> I launched a perceptron with 3300 inputs
09:07:13 <slereah> I may as well go home because it's not gonna be over until next week
09:46:09 <impomatic> myname: yes, tournaments for a few other games too, notably Robocode :-)
09:46:28 <impomatic> There've been offline CW tournaments in France and Austria so far this year.
09:46:40 <myname> impomatic: i'd love robocode if it'd be less java
09:47:28 <impomatic> I think you can play robocode with Scala. (unless I just imagined it)
09:48:01 <impomatic> There are similar games anyway, CROBOTS, TclRobots, Scalatron, etc
09:48:19 -!- impomatic has left.
09:48:20 <myname> is there some programming game with curses ui?
09:59:59 <Taneb> When I was little I had a computer game that taught basic maths (stuff like addition, subtraction, multiplication, division for easy numbers)
10:00:26 <Taneb> The story of the game was that the local Mathemagician had been kidnapped and you had to explore the scary forest to save him
10:00:41 <Taneb> I... used to speedrun that game when I was 6
10:00:49 <Taneb> And now I can't remember the name
10:06:23 -!- Guest53344 has quit (Changing host).
10:06:23 -!- Guest53344 has joined.
10:06:39 -!- Guest53344 has changed nick to skarn.
10:11:25 -!- drdanmaku has quit (Quit: Connection closed for inactivity).
10:13:54 <b_jonas> Taneb: is it a PC game? or what other game system platform?
10:14:11 <Taneb> iirc it was point-and-click
10:14:24 <Taneb> I probably have the CD at home
10:18:14 <Taneb> On another note...
10:18:41 <Taneb> You know how I have the Haskell lib "groups"?
10:19:52 <Taneb> I am tempted to add a RULES pragma saying "mappend (invert a) (invert b) => invert (mappend b a)"
10:21:10 <Taneb> On the basis that invert can be "division", and division is expensive
10:35:32 <myname> we have this course for maths students in their 4th semester
10:35:54 <myname> and there is that one assignment
10:36:37 -!- boily has joined.
10:47:02 <b_jonas> Taneb: but that sort of depends on what type a and b are; sometimes (mappend (invert a) (invert b)) is actually cheaper, sometimes more expensive
10:47:19 <Taneb> That's why I've hesitated
10:48:17 <b_jonas> maybe add two semantic synonyms to invert, one that prefers to remain separate, and one that prefers to merge;
10:49:04 <b_jonas> or, um, perhaps define this RULES for only some types
10:51:32 <Taneb> Anyway, I'm off to get some lunch and then do an exam
11:02:47 -!- Phantom_Hoover has joined.
11:12:37 <boily> off to get some bike and do work.
11:12:42 -!- boily has quit (Quit: Poulet!).
11:27:41 -!- Patashu_ has quit (Ping timeout: 255 seconds).
11:46:19 -!- mhi^ has joined.
12:04:10 -!- Sgeo has quit (Read error: Connection reset by peer).
12:14:26 -!- Fodor_ has joined.
12:43:04 -!- yorick has joined.
13:11:16 -!- aloril has quit (Ping timeout: 252 seconds).
13:22:49 -!- not^v has quit (Read error: Connection reset by peer).
13:23:17 -!- not^v has joined.
13:24:11 -!- aloril has joined.
13:26:59 -!- Phantom_Hoover has quit (Ping timeout: 240 seconds).
13:42:14 -!- conehead has joined.
14:25:06 <ion> A concrete truck and a concrete truck http://i.imgur.com/80tB0.jpg
14:25:10 -!- Fjlb has joined.
14:29:03 <Bike> fucked that one up
14:29:18 <int-e> this was more impressive: http://www.independent.co.uk/news/uk/home-news/victoria-line-cement-flooding-fixed-workers-used-sugar-to-stop-spilled-concrete-from-setting-9082206.html
14:31:03 -!- mihow has joined.
14:39:34 -!- tertu has quit (Disconnected by services).
14:39:34 -!- ter2 has joined.
14:41:52 -!- Sprocklem has joined.
14:45:24 -!- Sprocklem has quit (Client Quit).
14:46:15 -!- Sprocklem has joined.
14:46:52 -!- Fjlb has quit (Ping timeout: 260 seconds).
14:49:07 -!- not^v has quit (Ping timeout: 240 seconds).
14:51:56 -!- not^v has joined.
14:54:28 -!- Sprocklem has quit (Quit: brb).
14:55:03 -!- Sprocklem has joined.
15:02:41 -!- KingOfKarlsruhe has quit (Quit: Leaving.).
15:25:07 -!- not^v has quit (Ping timeout: 240 seconds).
15:43:40 -!- Phantom_Hoover has joined.
15:56:18 -!- slereah has quit (Quit: Leaving).
16:03:25 -!- edwardk has quit (Quit: Computer has gone to sleep.).
16:05:39 -!- Sprocklem has quit (Quit: Bye).
16:22:44 -!- mihow has quit (Quit: mihow).
16:26:23 -!- mihow has joined.
16:30:15 -!- mihow has quit (Client Quit).
16:32:56 -!- yorick has quit (Remote host closed the connection).
16:39:51 <Melvar> Someone elsewhere did approximately this:
16:40:06 <Melvar> With that particular response.
16:40:53 <Bike> is that unexpected
16:41:06 <Taneb> My copy of Parallel and Concurrent Haskell arrived :D
16:41:34 <int-e> it's certainly not unexpected as far as lambdabot is concerned.
16:41:36 <Melvar> Bike: Not really, I just found it amusing.
16:50:33 -!- nooodl has joined.
16:59:19 -!- erdic has quit (Remote host closed the connection).
17:00:42 -!- MindlessDrone has quit (Ping timeout: 255 seconds).
17:17:27 -!- MindlessDrone has joined.
17:25:58 -!- edwardk has joined.
17:29:38 -!- Sprocklem has joined.
17:35:27 -!- mihow has joined.
17:37:13 -!- aloril has quit (Ping timeout: 258 seconds).
17:42:48 -!- ter2 has changed nick to tertu.
17:44:30 -!- not^v has joined.
17:49:38 -!- aloril has joined.
17:51:50 -!- edwardk has quit (Quit: Computer has gone to sleep.).
17:53:07 -!- MoALTz has joined.
17:54:13 -!- Sprocklem has quit (Quit: bbl).
17:57:00 -!- edwardk has joined.
18:04:10 <HackEgo> [wiki] [[Goldfish]] http://esolangs.org/w/index.php?diff=39727&oldid=39650 * GermanyBoy * (+1373)
18:15:01 <HackEgo> [wiki] [[Goldfish]] http://esolangs.org/w/index.php?diff=39728&oldid=39727 * GermanyBoy * (+204)
18:15:55 -!- not^v has quit (Ping timeout: 240 seconds).
18:25:45 <ion> Skip to about 2:00. That voice. http://d396qusza40orc.cloudfront.net/dsp/recoded_videos%2FModule%205_12-h264%20for%20Coursera%20%5B0c477c9c%5D%20.mp4
18:36:21 -!- spiette has quit (Remote host closed the connection).
18:41:38 -!- tertu has quit (Ping timeout: 252 seconds).
18:41:56 -!- Sprocklem has joined.
18:46:59 -!- tertu has joined.
18:54:37 -!- drdanmaku has joined.
18:56:45 <olsner> ion: interesting talk, now I sort of know what an impulse response is
18:56:55 <olsner> talk? lecture? something
18:56:57 <HackEgo> [wiki] [[User:GreyKnight]] http://esolangs.org/w/index.php?diff=39729&oldid=8619 * GreyKnight * (+110)
18:57:28 <kmc> good morning esotericans
18:58:15 <kmc> I slept on and off for about 12 hours
18:58:36 <olsner> so is it saturday morning there?
18:58:55 <kmc> friday morning (well, one minute before noon)
18:59:07 <kmc> most places are ahead of the US west coast
18:59:55 <olsner> I can never figure out which direction "ahead of" is when it comes to time zones
19:00:03 <kmc> I meant a later time than
19:00:30 <kmc> since we are pretty close to the date line
19:00:39 <olsner> it's "now" everywhere, people just put different numbers on it
19:02:42 <kmc> we're UTC-8, -7 in the summer
19:02:57 <kmc> but not many people live in UTC-9 thru UTC-12
19:03:01 <quintopia> olsner: but relativity says it's impossible to determine what "now" exactly means...!!!
19:03:23 <kmc> just alaska and hawai'i and some other islands
19:03:52 <kmc> and afaik nobody has done any silly negative offsets less than 12
19:03:58 <kmc> like UTC+13 and UTC+14
19:04:36 <olsner> I might be getting confused because "ahead of" and "before" are the same word in swedish (and e.g. friday morning is before friday evening)
19:04:54 <olsner> quintopia: like, approximately
19:06:07 <kmc> olsner: wut
19:06:22 <kmc> oh, I guess that makes some sense
19:08:51 <kmc> this is like how stacks that grow "up" grow towards smaller addresses B|
19:09:32 <olsner> what, really? that's growing down to me
19:09:54 <olsner> but of course you always add things to the top of the stack even when the top is at the bottom
19:10:36 -!- Bicyclidine has joined.
19:13:31 -!- AnotherTest has joined.
19:19:14 -!- Slereah has joined.
19:20:39 -!- ^v has quit (Quit: Leaving).
19:20:57 <HackEgo> glanguinecoin dupcoin tropyrrhotabllaerloidarlycoin todcoin wikicoin exetercugnitecoin exandrecoin madnanticoin matinycoin carecoin surcoin licecoin sorcoin aarcoin datescrcoin xorckincoin pingcoin rhadcoin andypacoin 5-logcoin
19:21:51 -!- not^v has joined.
19:22:38 -!- Slereah_ has quit (Ping timeout: 258 seconds).
19:28:48 -!- erdic has joined.
19:36:40 -!- edwardk has quit (Quit: Computer has gone to sleep.).
19:38:25 -!- edwardk has joined.
19:46:01 <ion> olsner: The whole course has been interesting. https://www.coursera.org/course/dsp
19:49:58 -!- Sprocklem has quit (Ping timeout: 240 seconds).
19:55:26 <kmc> aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa
19:55:29 <kmc> life is so confusing
19:55:32 <kmc> how does anybody manage
19:55:57 <kmc> fungot: how do you make your way when your way is making you?
19:55:57 <fungot> kmc: d has two 100% incompatible stdlibs that you can't do with them
19:56:48 -!- Phantom_Hoover has quit (Ping timeout: 252 seconds).
20:00:25 <olsner> fungot: are you confusing?
20:00:25 <fungot> olsner: what is how? :) btw, i have, and fnord
20:00:48 <olsner> maybe life seems less confusing now?
20:01:05 -!- tertu has quit (Ping timeout: 252 seconds).
20:02:35 <kmc> not really
20:04:33 <kmc> it's vehemently blurry
20:05:17 <olsner> what about life are you making yourself confused about?
20:09:11 <mcpherrin> kmc: pretty sure nobody manages and we're all just terrified
20:14:22 <Bicyclidine> Given a lambda term, can we determine that repeated normal reduction of that term will result in that term?
20:14:38 -!- Slereah_ has joined.
20:14:44 <kmc> mcpherrin: I am leaning towards that explanation, yeah
20:14:53 <Bicyclidine> Leaving the halting problem to terms that grow unboundedly.
20:15:36 <kmc> Bicyclidine: I think a term might grow arbitrarily large before reducing back to the original term
20:15:48 <kmc> mcpherrin: still I am an outlier in more than a few senses :P
20:15:55 <tromp> you cannot decide whether a term reduces to itself
20:16:00 <kmc> somebody once told me that in high dimensional space, all points are outliers
20:16:42 -!- Fodor_ has quit (Quit: Leaving).
20:17:11 -!- Gracenotes has joined.
20:17:48 <Bicyclidine> somebody once told me that in high dimensional space it's pretty hard to know what the hell is happening
20:18:58 <tromp> because you can reduce the halting problem to that
20:19:08 <kmc> in high dimensional space nobody can hear you scream
20:19:39 <Bicyclidine> I mean there are plenty of terms w/o normal forms that don't reduce to themselves, or to anything that reduces to itself.
20:19:50 -!- not^v has quit (Quit: http://i.imgur.com/Akc6r.gif).
20:20:46 -!- mcpherri1 has joined.
20:20:51 <tromp> given a TM M, build a lambda term that will reduce to itself when M is found to halt
20:20:55 -!- erdic_ has joined.
20:21:26 <tromp> and that grows unboundedly when M doesn't halt
20:21:34 -!- olsner has quit (Write error: Connection reset by peer).
20:21:35 -!- erdic has quit (Write error: Broken pipe).
20:21:36 -!- Slereah has quit (Write error: Broken pipe).
20:21:39 -!- Gracenotes_ has quit (Write error: Broken pipe).
20:21:42 -!- mcpherrin has quit (Write error: Broken pipe).
20:21:50 -!- olsner has joined.
20:23:14 -!- mcpherri1 has changed nick to mcpherrin.
20:23:16 <tromp> that's straightforward
20:24:18 <Bicyclidine> If this was straightforward to me, would I be asking you?
20:25:48 <tromp> just let the lambda term simulate M
20:26:22 <tromp> and keep track of the number of steps to get a growing component
20:30:15 -!- erdic_ has quit (Changing host).
20:30:15 -!- erdic_ has joined.
20:30:24 -!- erdic_ has changed nick to erdic.
20:31:48 <Bicyclidine> i have no idea what that means, apparently
20:34:23 -!- yorick has joined.
20:43:48 -!- impomatic has joined.
20:46:05 -!- mihow has quit (Quit: mihow).
20:47:16 -!- Phantom_Hoover has joined.
20:47:22 -!- mihow has joined.
20:49:23 -!- mihow has quit (Client Quit).
20:52:05 -!- AnotherTest has quit (Ping timeout: 276 seconds).
20:53:37 -!- Bicyclidine has quit (Ping timeout: 245 seconds).
20:53:42 -!- MindlessDrone has quit (Quit: MindlessDrone).
21:03:25 -!- edwardk has quit (Ping timeout: 252 seconds).
21:18:44 -!- impomatic has quit (Ping timeout: 276 seconds).
21:24:25 -!- oerjan has joined.
21:27:10 -!- Sprocklem has joined.
21:29:22 -!- augur_ has joined.
21:31:47 -!- augur has quit (Ping timeout: 240 seconds).
21:31:58 -!- augur has joined.
21:33:06 -!- augur_ has quit (Read error: Connection reset by peer).
21:38:13 -!- augur has quit (Ping timeout: 245 seconds).
21:42:15 -!- tertu has joined.
21:42:28 -!- rottytooth has joined.
21:43:35 -!- Patashu has joined.
21:52:37 <oerjan> <Taneb> My copy of Parallel and Concurrent Haskell arrived :D <-- you should have ordered two to check for race conditions hth
21:53:01 <kmc> http://achewood.com/index.php?date=03042004
21:58:58 -!- Sprocklem has quit (Quit: brb).
22:00:47 <ion> >middle-endian datestamp
22:01:34 <oerjan> <mcpherrin> kmc: pretty sure nobody manages and we're all just terrified <-- HEY YOU BEAT ME TO THE JOKE
22:01:59 <kmc> it's an old joke.
22:02:00 <oerjan> not hard when you're several hours ahead (hi olsner), but still
22:02:24 <kmc> mcpherrin is in the same timezone as me
22:02:35 <oerjan> kmc: i mean in the logs hth
22:05:50 <oerjan> <Bicyclidine> i have no idea what that means, apparently <-- hint, lambda calculus is turing complete, so you can simulate anything with it.
22:06:26 -!- Sprocklem has joined.
22:06:29 <oerjan> including an annotated interpreter of lambda calculus
22:09:33 -!- mhi^ has quit (Quit: Lost terminal).
22:16:33 -!- mhi^ has joined.
22:17:13 -!- Patashu has quit (Disconnected by services).
22:17:13 -!- Patashu_ has joined.
22:17:43 -!- yorick has quit (Remote host closed the connection).
22:19:31 -!- edwardk has joined.
22:21:23 -!- yorick has joined.
22:29:11 -!- Sprocklem has quit (Ping timeout: 255 seconds).
22:32:34 -!- ter2 has joined.
22:32:34 -!- tertu has quit (Disconnected by services).
22:32:44 -!- madbr has joined.
22:36:24 <Taneb> Odd question, but anyone know which (if any) image formats respond interestingly to random bit-flipping?
22:36:40 <ion> All of them? :-P
22:36:46 <mcpherrin> Taneb: what do you mean by "interestingly"
22:36:54 <Taneb> mcpherrin, pretty corruption
22:37:09 <ion> as opposed to that of our politicians
22:37:20 <oerjan> yog sothoth showing up, that sort of thing
22:37:31 <ion> and/or yogi bear
22:38:18 -!- tertu3 has joined.
22:38:38 <madbr> video formats where the random reverse-DCT'd data will move around interestingly with motion vectors?
22:39:28 <ion> FSM? http://en.m.wikipedia.org/wiki/File:Yog-Sothoth.jpg
22:40:07 <Taneb> On that note, played Arkham Horror today. It did not go well.
22:40:10 <madbr> there's also the LZ* kind of encodings like gif or png which might have some intersting behavior
22:40:27 <mcpherrin> yeah gif is kinda fun, especially if the flips occur early
22:41:09 <madbr> jpg might do some interesting stuff too thanks to its crazy zig zag pattern
22:41:30 <mcpherrin> I think the best thing to do here is to test
22:41:41 -!- ter2 has quit (Ping timeout: 264 seconds).
22:41:53 <mcpherrin> take, say, random imgur images, convert to a handful of image formats, and flip random bits!
22:43:45 -!- ter2 has joined.
22:43:55 -!- Sorella has joined.
22:45:06 <ion> madbr: I see you already deleted some bits from jpeg. ;-)
22:47:22 -!- tertu3 has quit (Ping timeout: 265 seconds).
22:49:01 <oerjan> ion: i think confusing Yog-Sothoth with the FSM is a rather dangerous mistake hth
22:49:40 <oerjan> that is, unless the FSM is really Yog-Sothoth in (really bad) disguise. in which case we're all hosed anyway.
23:01:10 -!- Sgeo has joined.
23:01:17 -!- tertu3 has joined.
23:04:29 -!- ter2 has quit (Ping timeout: 264 seconds).
23:06:34 -!- boily has joined.
23:10:21 -!- Bicyclidine has joined.
23:15:43 <boily> fungot: what do you usually do on a Friday night?
23:15:43 <fungot> boily: i think i might get continuations,
23:15:59 <boily> fungot: continuing what?
23:16:00 <fungot> boily: pythons whitespace thingie makes it hard to get below the third element without dropping something
23:16:12 <boily> fungot: ah. continuing whitespace. very zen.
23:16:13 <fungot> boily: don't forget " integrate into the operating system
23:16:24 <boily> fungot: I shall quote you on that.
23:16:25 <fungot> boily: ( 1 ( values 1 2 3)) ( state-5))? i suspect so! :o)
23:16:47 -!- augur has joined.
23:21:18 -!- Bike has quit (Ping timeout: 240 seconds).
23:23:26 -!- Bike has joined.
23:24:51 -!- ter2 has joined.
23:26:11 -!- Sorella has quit (Quit: It is tiem!).
23:26:16 -!- yorick has quit (Remote host closed the connection).
23:27:47 -!- tertu3 has quit (Ping timeout: 240 seconds).
23:37:18 -!- ^v has joined.
23:39:46 -!- tertu3 has joined.
23:41:29 -!- kallisti_ has joined.
23:42:18 -!- ter2 has quit (Ping timeout: 252 seconds).
23:44:59 -!- kallisti has quit (Ping timeout: 276 seconds).
23:49:20 <shachaf> (.) :: forall a c. (exists b. (b -> c, a -> b)) -> (a -> c)
23:50:14 <oerjan> now that's just crazy talk
23:51:26 <Phantom_Hoover> shachaf, having a tuple in that type threw me for a minute
23:53:31 <shachaf> (exists x. (f x, x -> a)) and all that
23:56:03 -!- metasepia has joined.
23:56:33 <metasepia> ENVA 302350Z 34006KT 9999 FEW019 BKN032 09/06 Q1020 RMK WIND 670FT 32010KT
23:56:43 <metasepia> CYUL 302300Z 03013G20KT 30SM BKN090 21/06 A3007 RMK AC5 TCU ASOCTD SLP181 DENSITY ALT 600FT
23:57:06 <shachaf> boily: coyoneda f a = (exists x. (f x, x -> a)) hth
23:57:32 <boily> I suck at foralls and exists in type signatures.
23:57:37 <oerjan> you evil scoundrel canadians stealing our weather just because you have daylight
23:58:15 <shachaf> boily: it's just functions and tuples hth
23:58:22 <boily> oerjan: we're having nice weather, with blossoming trees, blue skies, nice bike lanes.
23:58:22 <oerjan> admittedly the wether forecast wasn't much better for the daytime
23:58:48 <boily> shachaf: still. the foralls disturb my chakras and imbalance my humours.
23:59:47 <oerjan> well what should we expect anyway, after all ENVA is the weather of hell
00:00:12 <boily> speaking of flowery stuff, what is that one? → https://www.dropbox.com/s/yiki722p5addshq/2014-05-30%2018.05.16.jpg
00:00:45 <kmc> douglass_: ^ do you know this flower
00:01:32 <boily> douglass_ knows flowers? I'll remember that :)
00:02:12 -!- tertu has joined.
00:02:20 <douglass_> the flowers look very generic rosaceae but could be something else
00:02:58 <douglass_> those notched leaves are probably more distinctive
00:03:33 <oerjan> boily: an expert in all plantal and fungal matters, clearly
00:03:43 <boily> the flowers are very small, about ¼” Ø.
00:03:49 <shachaf> Bicyclidine: ([97,98,99], chr)
00:04:46 <boily> oerjan: I can't type the real Unicode Diameter symbol on my keyboard, so I defaulted to Ø.
00:05:25 <oerjan> `unicode DIAMETER SYMBOL
00:05:39 <oerjan> `unicode [DIAMETER SYMBOL]
00:05:40 <HackEgo> U+0000 <control> \ UTF-8: 00 UTF-16BE: 0000 Decimal: � \ . \ Category: Cc (Other, Control) \ Bidi: BN (Boundary Neutral) \ \ U+0001 <control> \ UTF-8: 01 UTF-16BE: 0001 Decimal:  \ . \ Category: Cc (Other, Control) \ Bidi: BN (Boundary Neutral) \ \ U+0002 <control> \ UTF-8: 02 UTF-16BE: 0002 Decimal:  \ \ Category: Cc (Other, C
00:05:41 -!- tertu3 has quit (Ping timeout: 264 seconds).
00:05:46 -!- mhi^ has quit (Quit: Lost terminal).
00:06:23 -!- Bicyclidine has quit (Ping timeout: 252 seconds).
00:06:25 <boily> `unicode DIAMETER SIGN
00:06:48 <boily> oh, right. I'm using urxvt, therefore I can Ctrl-Shift-Hexcode.
00:07:26 <douglass_> I can look harder at it when I'm not at work
00:08:48 <HackEgo> [U+2300 DIAMETER SIGN] [U+23D1 METRICAL BREVE] [U+2300 DIAMETER SIGN]
00:15:02 <boily> all-hands meeting on a Friday afternoon? why not? it's vile, it's horrendous, it makes God do Bad Things to kittens!
00:16:46 -!- ter2 has joined.
00:16:46 -!- tertu has quit (Disconnected by services).
00:18:36 -!- Zyprexa has joined.
00:26:16 -!- tertu3 has joined.
00:28:22 -!- tertu3 has quit (Read error: Connection reset by peer).
00:28:44 -!- tertu3 has joined.
00:29:20 -!- ter2 has quit (Ping timeout: 255 seconds).
00:38:48 -!- Patashu_ has quit (Quit: Soundcloud (Famitracker Chiptunes): http://www.soundcloud.com/patashu MSN: Patashu@hotmail.com , AIM: Patashu0 , YIM: patashu2 , Skype: patashu0 .).
00:41:52 -!- tertu3 has quit (Read error: Connection reset by peer).
00:43:18 -!- ter2 has joined.
00:49:17 -!- tertu3 has joined.
00:52:33 -!- ter2 has quit (Ping timeout: 265 seconds).
00:54:19 -!- ter2 has joined.
00:56:00 -!- Phantom_Hoover has quit (Ping timeout: 252 seconds).
00:56:08 -!- Patashu has joined.
00:56:30 -!- augur_ has joined.
00:57:17 -!- augur has quit (Ping timeout: 264 seconds).
00:57:54 -!- tertu has joined.
00:58:19 -!- tertu3 has quit (Ping timeout: 260 seconds).
00:59:21 -!- tertu3 has joined.
00:59:21 -!- tertu has quit (Disconnected by services).
01:00:11 -!- ter2 has quit (Ping timeout: 260 seconds).
01:02:00 -!- ter2 has joined.
01:04:22 -!- ter2 has quit (Read error: Connection reset by peer).
01:04:44 -!- ter2 has joined.
01:05:07 -!- tertu3 has quit (Ping timeout: 265 seconds).
01:05:27 <kmc> developing for rustc is a world of rebase pain... between the time you write a patch and when you get it merged, somebody will have renamed a std lib function and literally 2,500 occurrences of it within the rustc codebase
01:05:43 <kmc> servo is meant to build on a specific rustc version that only updates every month or two, but rustc is always meant to be built by the latest version of itself, AND by the "stage0" snapshot binaries, which can be significantly further behind
01:07:17 <kmc> ah well it's all part of the fun really
01:07:23 <kmc> I need a faster machine at home to do this stuff
01:07:42 -!- idris-bot has quit (Quit: Terminated).
01:08:10 <kmc> at least the std lib is split into more compilation units now so it can build more in parallel
01:08:50 -!- tertu3 has joined.
01:12:01 -!- ter2 has quit (Ping timeout: 252 seconds).
01:12:31 <oerjan> i shouldn't really be complaining about getting 55 SO rep just because GHC doesn't have -fwarn-tabs on by default and stackoverflow reformats tabs to 4 spaces so no one else realizes why the code is wrong, but it's a little stupid.
01:12:59 -!- tertu3 has quit (Ping timeout: 240 seconds).
01:19:48 <shachaf> so rep can be redeemed for so many good jams
01:19:58 -!- rottytooth has quit (Quit: HydraIRC -> http://www.hydrairc.com <- s0 d4Mn l33t |t'z 5c4rY!).
01:21:02 <oerjan> i already have jam, whats the problem
01:21:18 <kmc> how is this done shachaf
01:21:45 <shachaf> kmc: i haven't collected enough so rep to find out
01:21:57 <kmc> how do you know it can be done
01:22:09 <shachaf> what else would people be collecting it for
01:23:36 <shachaf> oerjan: what kind of jam do you have
01:23:47 <shachaf> is it Balsamic Caramelized Onion Spread
01:24:07 <Taneb> shachaf, that's more of a chutney...
01:24:29 <shachaf> is it a 15-card booster pack of Magic: The Gathering cards
01:25:17 <oerjan> haven't had that in a while.
01:27:10 <shachaf> apparently this one berry has multeple names
01:31:27 <boily> I had a cruchon of lingonberry jam from ikea. it was good.
01:31:37 <boily> (how do you say fr:cruchon in English?)
01:31:55 <kmc> mcpherrin: dare I go this far into the macro rabbit hole? https://gist.github.com/kmcallister/94de6ddc5098c43fd3ff
01:32:29 <oerjan> itt kmc manages to get macros banned from rust
01:32:41 <kmc> i'll fork the language if that happens
01:33:19 -!- boily has quit (Quit: GLASS CHICKEN).
01:33:23 -!- metasepia has quit (Remote host closed the connection).
01:33:55 <mcpherrin> kmc: I once wrote a program that turned the XQuery spec into an xquery compiler
01:34:13 <kmc> mcpherrin: nice
01:34:15 <kmc> 'night Taneb
01:34:19 <mcpherrin> kmc: so you should use that as your DSL
01:34:43 <mcpherrin> surely there's a grammar for HTML5 you can transform
01:34:59 <kmc> have you seen the HTML5 syntax spec.
01:35:18 <kmc> http://www.whatwg.org/specs/web-apps/current-work/multipage/tree-construction.html#tree-construction
01:36:06 <kmc> it's like spaceteam. 'Set the frameset-ok flag to "not ok"!' 'Reconstruct the active formatting elements!'
01:36:36 <kmc> the tokenizer is a bit more structured; you could maybe translate it, although it would be better for WHATWG to maintain a machine-readable spec that is translated to HTML
01:36:39 <kmc> http://www.whatwg.org/specs/web-apps/current-work/multipage/tokenization.html
01:36:40 <pikhq> I suppose technically it counts as a "grammar"?
01:36:54 <kmc> well it's not actually undecidable, so yeah
01:36:56 <pikhq> Though that's about as much a grammar as is the output of Yacc.
01:37:46 <oerjan> grammars can be undecidable hth
01:38:15 <oerjan> @tell boily http://en.wiktionary.org/wiki/cruchon hth
01:40:42 <kmc> mcpherrin: note that the existing code has shit like start!(mut t) if match_atom!(t.name { ... 30 LINE LONG GUARD ... }) => Done,
01:46:26 <kmc> still really pleased that LLVM can compile match_atom!() into tests on an immediate bitmask
01:53:02 -!- Bike has quit (Ping timeout: 276 seconds).
01:54:03 -!- Bike has joined.
01:58:08 -!- Sprocklem has joined.
02:26:49 <Sgeo> Why don't there seem to be many offline HTML5 validators?
02:27:03 <kmc> i was wondering that once
02:27:25 <kmc> I failed at setting up a local instance of the popular one, forget what it's called
02:27:57 -!- conehead has quit (Quit: Computer has gone to sleep).
02:28:16 <Sgeo> Incidentally, do any of them allow settings to allow for one specific kind of invalidity to pass? >.>
02:28:26 <kmc> don't know
02:28:32 <kmc> which kind?
02:29:01 <Sgeo> Unknown non data- attributes. I blame Angular.
02:31:33 <Bike> kmc: helluva macro
02:32:45 <kmc> only problem is it doesn't exist yet
02:34:02 <Sgeo> I wish ads were better targetted. Don't show me ads for Christian dating sites, and don't show me ads for a game that I'm already addicted to (although ads for fansites still make sense)
02:34:24 <kmc> are you willing to accept more invasive personal tracking to make that happen
02:34:30 <maurer> kmc: they shouldn't need it right?
02:34:37 <maurer> kmc: Like, if they are going to show me an eve ad
02:34:49 <maurer> they can say "He logged on to eve form that IP 30 minutes ago"
02:34:53 <maurer> "instead show him an ad for PLEX"
02:36:39 <kmc> grr, people using historical life-expectancy-at-birth as an indicator of when average adults would die
02:38:04 <kmc> regarding Christian dating: "Look, obviously God wanted us to enjoy ourselves, that's why he invented pills and clubs and lube and hardcore. But he also wanted us to give something back, and that's why he created the homeless, the lepers and the oil spills."
02:41:02 <HackEgo> colacoin unacoin revergcoin mempcoin pohtcoin reszekcoin hesecoin excollicoin luillineigateuropricoin tunimalcoin rocontinucoin homeofthesiscoin cordcoin libacoin sebourgcoin skynurtecoin timebrackcoin numgestcoin minimaltllycoin patrecoin
02:41:25 -!- augur has joined.
02:43:29 -!- augur_ has quit (Ping timeout: 264 seconds).
02:44:47 -!- zzo38 has joined.
02:45:14 -!- fungot has quit (Ping timeout: 252 seconds).
02:46:44 <zzo38> How can you link a program compile with GNU C compiler with a program compile with Visual Basic 6?
02:49:27 <elliott> I'm worried about whatever plan you have, zzo38.
02:50:02 <mcpherrin> VB6 isn't quite gone away enough to make it cool and retro
02:50:58 <pikhq> Nah, go for IBM COBOL.
02:52:40 <zzo38> None of that is the point...
03:06:12 <kmc> pointless cobol
03:13:27 <pikhq> Have you considered telling some of my company's clients?
03:13:42 <Bike> http://en.wikisource.org/wiki/Subjective_Effects_of_Nitrous_Oxide read plz
03:13:54 <pikhq> I'd like to not finish a cobol struct parser kthx
03:14:48 <kmc> oh that guy
03:17:13 <oerjan> pikhq: ooh you actually do cobol-related programming?
03:18:08 <pikhq> Presently? Yes, actually.
03:18:38 <kmc> zzo38: iirc VB 6 can load .dlls
03:18:59 <pikhq> Turns out that some places will pay ludicrous amounts of money for a product that lets you take in random mainframe data and spit out something actually sane.
03:20:14 <zzo38> kmc: Yes I know, but I want it to be static linking
03:20:26 <kmc> then i don't know
03:21:25 <pikhq> It's not exactly *hard*, just irritating, because it's practically a computer archaeology project.
03:21:57 <zzo38> I want to make a Windows GUI program which can be static linked with cross-platform C programs
03:22:57 <kmc> the moves-per-second indicator I drunk-coded for 2048 shows NaN until you use the "restart game" feature at least once
03:23:00 <kmc> ah, javascript
03:23:14 <Sprocklem> zzo38: There's got to be better ways of doing that
03:24:23 <pikhq> This incidentally is *not* the fun part of my job. :P
03:24:43 <zzo38> Sprocklem: Maybe, but, what is it going to be?
03:28:33 <madbr> or js fills missing numerical variables with nan? :O
03:29:00 <kmc> I think because undefined * 0 = NaN
03:29:02 <kmc> but who knows
03:30:28 <madbr> how does js compare to, like, python, lua and perl?
03:30:40 <madbr> which are the other languages in that "category"
03:31:01 <mcpherrin> I suppose it depends how you're trying to classify...
03:31:19 <mcpherrin> it's kinda like python, but with a more C-like syntax, but without python's big std lib
03:31:24 <madbr> my classification depends on the major preformance tradeoffs
03:31:43 <mcpherrin> JS has probably one of the fastests JITs around
03:31:52 <madbr> no garbage collection = C, C++, asm, some others like fortran
03:32:09 <madbr> garbage collection but no dynamic typing = java, C#
03:32:21 <mcpherrin> JS is garbage collected, interpteted/JITted, dynamically typed (but secretly not for perf)
03:32:35 <madbr> dynamic typing = JS, lua, perl, python...
03:32:54 <kmc> madbr: itym C, C++, asm, Rust!
03:33:11 <Sprocklem> madbr: JS is also very weakly typed
03:33:12 <mcpherrin> JS uses closures pretty heavily, including as "classes"
03:33:43 <mcpherrin> JS has a lot of weird type system interactions too, especially with things like implicit conversion to strings and numbers
03:33:54 <Sprocklem> madbr: It's got prototype base object orientation
03:34:21 <madbr> object orientation doesn't really have an impact on performance
03:34:24 <kmc> my record time so far is 220 seconds, which I guess is pretty good, although I'm playing a variant of 2048 which is easier than the official one
03:34:43 <zzo38> I think SQLite also uses a kind of dynamic typing? (This is different from some other SQL implementations which are statically typed)
03:35:19 <kmc> mcpherrin: the biggest difference between JS / asm.js and NaCl is not language but platform
03:35:21 <madbr> inversely dynamic typing does... you can go through all sorts of JIT compilation hoops to try to remove the impact but that's hard
03:35:25 <kmc> asm.js uses standard web APIs
03:35:34 <kmc> NaCl uses things that are chrome-only for all practical purposes
03:35:39 <kmc> you can guess which one mozilla favors...
03:35:40 <mcpherrin> kmc: NaCl with standards APIs would be <3
03:35:52 <kmc> but you can guess which one Google favors, too
03:36:01 <mcpherrin> kmc: I got drunk with Eich the day Google announced Dart; that was funny :p
03:36:04 <madbr> does anything important use nacl yet?
03:36:55 <kmc> there is a list of Google web properties allowed to use NaCl hardcoded into chrome
03:36:59 <kmc> \rainbow{vertical integration}
03:38:23 <mcpherrin> kmc: rust needs emscripten support :p
03:38:37 <kmc> not my problem
03:38:50 <mcpherrin> kmc: but running servo inside firefox :-o
03:39:45 <kmc> we could use WebGL for compositing, and native <canvas> for rendering
03:39:58 <madbr> only thing I've implemented on nacl was some sound support stuff
03:40:05 <kmc> I was actually wondering about implementations of CSS / web layout in JS the other day
03:40:09 -!- conehead has joined.
03:40:13 <kmc> because of some discussion of whether JIT would help you
03:40:17 <madbr> incidentally that's an area where html5 is broken but the nacl stuff isn't
03:40:27 <kmc> Blink already has a JIT for CSS selector matching, but I mean for layout
03:40:42 <kmc> compile the flow tree to native code so you can redo layout extra fast when parts of it change
03:40:48 <kmc> i don't know if it makes any sense, but it sounds pretty cool!
03:41:58 <kmc> pcwalton also wants to store our CSS selectors as *only* machine code and decompile them to implement CSSOM
03:42:01 <kmc> I think I mentioned that here
03:43:11 <madbr> like, sound is the kind of stuff that only really work well in compiled languages tbh
03:43:37 <kmc> but JS running in a modern JS engine is compiled
03:43:53 <kmc> and you have unboxed arrays even
03:44:00 <kmc> I agree it's not realtime, though
03:44:03 <kmc> but neither are a lot of "compiled languages"
03:44:08 <madbr> it's more of a problem of
03:44:19 <kmc> really every implementation out there is somewhere on a spectrum between interpreted and compiled
03:44:27 <madbr> if the garbage collector runs, is that going to take more than 10ms?
03:44:40 <Bike> reminds me, firefox has https://twitter.com/alex_gibson/status/467280491260166146/photo/1 now apparently
03:44:44 <madbr> also sound is like 100% always threaded
03:44:45 <kmc> but this is also a problem in Haskell and OCaml, which are typically native compiled
03:44:57 <kmc> ahead-of-time even
03:45:06 <newsham> way-ahead-of-time compilation
03:45:19 <kmc> it's weird that there aren't more mainstream high level languages which are generally AOT native-compiled
03:45:49 <mcpherrin> kmc: yeah I was talking with pcwalton about that, I think decompiling sounds silly though
03:45:58 <newsham> http://research.microsoft.com/pubs/68190/coots97.pdf
03:46:09 -!- esowiki has joined.
03:46:10 -!- glogbot has joined.
03:46:10 -!- douglass_ has joined.
03:46:13 -!- esowiki has joined.
03:46:13 -!- esowiki has joined.
03:46:14 -!- EgoBot has joined.
03:46:28 <madbr> even java is kinda dubious for sound applications
03:48:36 <madbr> the usual equation is "no garbage collector" => "only languages with explicit deallocation" => "C++ only"
03:49:17 <madbr> what does that mean?
03:49:38 <newsham> its a type system that tracks resources. each resource must be consumed only once, etc..
03:49:39 <Bike> some nerd shit
03:49:51 <kmc> that's Rust's approach yeah
03:49:53 <mcpherrin> http://en.wikipedia.org/wiki/Substructural_type_system
03:50:20 <kmc> deallocation is sort of explicit in that it's deterministic, but it's done in a statically memory safe way
03:50:30 <kmc> it's like C++11 move semantics except actually fully checked at compile time
03:50:58 <kmc> if you have let x = ...; f(x) and x is not something implicitly copyable like a primitive numeric type, it will forbid you from using x after that function call
03:51:05 <kmc> you've transferred ownership of it
03:51:34 <madbr> never tried that kinda stuff
03:51:47 <kmc> same for sending things between threads
03:52:16 <kmc> you can have datastructures shared between threads, but you have to write them in the unsafe dialect of the language, and then assert that they're safe to share
03:53:05 <kmc> madbr: the other major unique thing in Rust is references / "borrowed pointers" with lifetime checking
03:53:22 <kmc> so you can write f(&x) and not transfer ownership into f, but if f tries to stash that pointer away somewhere the compiler will complain
03:53:56 <newsham> "you can peek at my x, but ITS MINE!@#"
03:54:19 <kmc> you can have any number of immutable borrowings of a value, or exactly one mutable borring
03:54:22 <kmc> that's statically checked too
03:54:27 <kmc> prevents iterator invalidation and related issues
03:54:34 <madbr> if that kindof stuff lets the compiler do real anti aliasing, then eventually it might become faster than C++ and then rust will see much more adoption
03:54:56 <kmc> that's the hope
03:55:09 <madbr> it's kindof dependent on cpu architectures tho
03:55:24 <kmc> although I think approximately as fast as C++, with no segfaults or use-after-free vulnerabilities is also a pretty compelling value proposition
03:56:12 <kmc> and if it's not as fast, you can do whatever you'd do in C or C++ within the unsafe dialect
03:56:16 <kmc> or link to actual C
03:56:30 <mcpherrin> yeah zero overhead to call C is pretty compelling
03:57:08 <mcpherrin> more ffi support for c++ would be nice though
03:57:10 <Bike> you can tell i'm not cut out for mathematics because i'm still staring at something oerjan said five hours ago
03:57:14 <kmc> C++ is a pit of snakes though
03:57:33 <kmc> I mean first class C++ support would include things like using C++ RAII smart pointers from Rust
03:57:36 <kmc> that's Hard
03:57:38 <kmc> but would be really cool
03:57:41 <pikhq> C FFI is pretty reasonable. I mean, C ain't the nicest around, but it's at least fairly limited.
03:57:42 <madbr> it's got the original sin (everything is pointers)
03:57:56 <pikhq> C++ is A Lot Of Stuff.
03:57:57 <mcpherrin> Teh c++ people are talking about standardizing on an aBI
03:57:58 <kmc> madbr: hm? C++ is one of the few languages where objects *aren't* all pointers
03:58:03 <kmc> mcpherrin: lol
03:58:21 <madbr> kmc: true but arrays sortof are
03:58:26 <madbr> except std::vector
03:58:27 <newsham> [17:54] < Bike> you can tell i'm not cut out for mathematics because i'm still staring at something oerjan said five hours ago
03:58:40 <newsham> isnt the ability to stare at somethign for 5hrs pretty much the main requirement?
03:58:51 <Bike> a necessary but not sufficient condition
03:58:54 <Bike> c.f. video games
03:59:03 <kmc> in Rust there are slices, which are a pointer + length into a string or array owned by someone else
03:59:13 <madbr> the default object for more than one of anything is just an offset with no real size
03:59:13 <kmc> also fixed-size arrays, which are passed by value (unless you take a reference type of them, of course)
03:59:25 <kmc> and heap-allocated growable Vec<T>
03:59:25 <Bike> can you do fortran-style submatrices
03:59:26 <newsham> "you can tell i'm not cut out for mathematics because i stared at something oerjan said 5hrs ago and gave up after 30seconds" is prob a more realistic statement
03:59:42 <Sgeo> Hmm... so Elixir has consistent distinction between 'size' and 'length'... but it would still take time getting used to Elixir to keep it in mind
03:59:53 <Sgeo> (size for O(1) length for needing computation)
04:00:12 <Sgeo> s/needing computation/slower than O(1)/
04:00:29 <Sgeo> "the function should be named size if the operation is in constant time (i.e. the value is pre-calculated) or length if the operation requires explicit counting."
04:00:37 <kmc> Bike: multidimensionally? i haven't seen that, but it should be implementable
04:00:55 <Bike> that that is is silly
04:00:56 <zzo38> I like to use Csound for sound related stuff in computer
04:01:14 <mcpherrin> kmc: O(question mark in a box) :-(
04:01:20 <Bike> kmc: yeah you store stride and stuff
04:01:26 <HackEgo> [U+A66E CYRILLIC LETTER MULTIOCULAR O]
04:01:44 <Bike> i think you can even do ones with less locality, like make a vector out of a diagonal or some shit
04:02:03 <zzo38> Can't you use Csound for audio programming?
04:02:15 <Bike> granted, but you'r eon fire
04:02:29 <kmc> mcpherrin: https://en.wikipedia.org/wiki/Multiocular_O
04:02:44 <Sgeo> Well, getting a bit harder to remember: and/or/not take booleans only, &&/||/! use truthiness
04:02:49 <kmc> a 15th century scribal doodle that made it into the Universal Character Set
04:03:14 <Sgeo> Consistent but hard to remember patterns
04:03:18 <Sgeo> Still better than PHP
04:03:28 * oerjan declares that he has just eaten pizza, then stares at Sgeo while intoning "best before march 24"
04:03:41 <madbr> zzo38 : not really
04:04:07 <zzo38> madbr: Why not really?
04:04:16 <Bike> someone tell me why volterra series were explained to me as "taylor series, but with time dependence" instead of "taylor series, but on functionals"
04:04:26 <Sgeo> Did I say something weird on March 24th?
04:04:28 <Bike> shut the fuck up about 'memory' assholes
04:06:11 <madbr> zzo38 : I'm not well versed in how csound integrates with other stuff so I'm not sure how to answer
04:06:18 <madbr> but it sounds like a bad plan
04:07:13 <zzo38> Well, I find Csound is good for synthesizing audio and writing music, at least. It does work with Open Sound Control, MIDI, Wii remotes, and extension libraries can be written in C.
04:07:19 <madbr> something like "is it still well behaved once you have to compile it into a dll for use in a multithread environment along with a gui"
04:07:37 <madbr> "in a way that's not going to take more code/effort than just doing everything in C++ as usual"
04:07:56 <zzo38> madbr: There are GUI programs for Csound, although I have not used them so I don't know. Some of these GUI programs are even written in Java
04:09:02 <zzo38> I do not particularly like the standard score format in Csound for the purpose of writing music, so I wrote a MML compiler targeting Csound, to make it easier to write music.
04:09:10 <madbr> osc I haven't been impressed with yet
04:09:22 <madbr> it's got a nice type specification etc system
04:09:45 <madbr> but nobody has put on his pants and specified a real standard for note and controller data
04:09:55 <madbr> which is like 75% of the feature set of MIDI
04:10:04 <oerjan> <Bike> you can tell i'm not cut out for mathematics because i'm still staring at something oerjan said five hours ago <-- hm?
04:10:59 <madbr> "you can listen for CC1 because you know the user's m-audio midi controller has a mod wheel and that unless the user has reprogrammed it for whatever reason, it sends CC1"
04:11:12 -!- MoALTz has quit (Ping timeout: 265 seconds).
04:13:18 <madbr> my criticism of those systems is that they're typically not correctly set up for writing music
04:14:02 <zzo38> I haven't used those kind of MIDI devices for writing music, so I don't know
04:14:34 <madbr> writing music requires a good piano roll editor
04:14:44 <madbr> DAWs are basically the only programs that have that
04:14:51 <zzo38> Although I don't prefer to write music "live" anyways (although I know people who do)
04:14:59 <madbr> DAWs can load up VST plugin synthesizer plugins
04:15:10 <madbr> result: everybody uses DAW with VST plugins
04:15:14 <zzo38> I don't see why you need a piano roll editor though. It can be one way, or you can use MML; I prefer to use MML.
04:15:23 <zzo38> I also don't like VST; I prefer to use Csound.
04:15:27 <madbr> I've never gotten into MML
04:15:40 <zzo38> So I use MML for the score and Csound for the instruments.
04:16:02 <zzo38> Since I have found this works better for me than using piano roll editors/VST
04:16:16 <madbr> people that write lots of music use piano roll like >99% of the time
04:17:14 <madbr> newsham : that involves live musicians
04:17:18 <oerjan> <Sgeo> Did I say something weird on March 24th? <-- no. *sigh* i'm being too subtle again... you're just worrying about the health of food all the time so i was joking about the fact i ate a pizza that was > 2 months overdue hth
04:17:20 <madbr> so I guess making them parts
04:17:25 <zzo38> Yes you can use piano roll if you prefer; different people use different ways. Some people like to write on music notation paper.
04:17:33 <madbr> which I guess is notation, rather than piano roll
04:17:40 <Bike> i just poke actual holes in an actual piano roll
04:18:25 <madbr> also, making nice music notation is hard
04:18:33 <zzo38> I do know someone who only writes music live, never writing it down.
04:19:21 <Bike> it'll never catch on.
04:19:35 <zzo38> He then connects the audio output port of a digital piano to a computer to record it onto a CD.
04:19:43 <newsham> next thing you'll have people having impromptu discussions without rehersing
04:20:12 <madbr> zzo38 : afaik that's how you're supposed to use piano rolls anyways
04:20:23 <madbr> record live, use piano roll to fix mistakes
04:20:48 <zzo38> However I myself don't like writing music live, DAW, piano roll, VST, tracker music, and that stuff.
04:21:27 <zzo38> madbr: Actually I think piano roll notation is the kind of thing he wanted to use for this purpose, although he didn't. It would be possible, since this digital piano does have a MIDI output port too.
04:21:29 <kmc> record drunk, piano roll sober
04:21:29 <newsham> what would richard james do?
04:21:33 <Bike> oerjan: the lambda calculus thing.
04:21:54 <kmc> newsham: cocaine's a hell of a drug
04:22:32 <kmc> newsham: close enough?
04:22:47 <newsham> http://en.wikipedia.org/wiki/Richard_James_(musician)
04:23:09 <newsham> oops i meant this one http://en.wikipedia.org/wiki/Aphex_Twin
04:23:09 <Bike> now listening to Die Fantastischen Vier -- Krieger (Aphex Twin Baldhu Mix)
04:24:39 <kmc> newsham: DMT's a hell of a drug
04:24:46 <zzo38> I don't like VST; it requires a GUI, isn't an open standard, and seems for writing live music (which isn't what I do). Perhaps VST is OK for live music writers who don't care if it is usable in anything other than Windows, I suppose.
04:24:53 <oerjan> Bike: ok let me detail it a bit: you write an interpreter for TM's in lambda calculus which works fairly normally, except that (1) it keeps a count of steps such that it never repeats as long as the TM is running (2) if the TM _halts_, instead of halting itself it just restarts from the beginning, resetting the count. then whether that LC interpreter loops <=> whether the TM halts.
04:24:53 <kmc> DMT's a hell of a drukq?
04:25:38 <zzo38> To do effects and instrument sound and so on writing music, I found Csound works much better than anything else I have used.
04:25:48 <newsham> hah, i'm listening to drukqs right now
04:25:51 <Bike> well, that's a bit disappointing, but not unexpected
04:25:58 <zzo38> And if you do like to use Csound and VST, you can do it, in both directions!
04:26:20 <Bike> for my next trick, i shall disprove hilbert's 16th
04:26:32 <Bike> or rather, say something about it here and wait for oerjan to prove it for me
04:26:42 <zzo38> What is Hilbert's sixteenth?
04:27:16 <Bike> http://en.wikipedia.org/wiki/Hilbert%27s_sixteenth_problem
04:34:08 <oerjan> i think you need to work more on your tricks
04:38:19 -!- Zerker has joined.
04:39:39 -!- augur has quit (Ping timeout: 252 seconds).
04:46:25 <zzo38> Do you know how to use SQL for editing music which is already compiled (into a .MOD, .S3M, .MID, etc)?
04:48:18 <zzo38> For working with audio files, SoX works OK (although I think something combining ImageMagick with SoX, allowing the same effects using with sounds and pictures, would be much better), although for working with editing and conversion of music compiled into MOD/S3M/IT/XM/MID files, that a SQL-based system would work best.
04:49:08 -!- augur has joined.
04:49:30 -!- augur has quit (Remote host closed the connection).
04:49:43 -!- augur has joined.
04:50:05 <madbr> What does sox do that you wouldn't normally do in audacity/soundforge/etc?
04:51:30 <zzo38> Command-line functioning
04:51:59 <pikhq> sox is quite nice for scripting.
04:52:36 <pikhq> For instance, it was pretty nice when converting my inexplicable 88.2 kHz 24-bit copy of Distant Worlds 2 here.
04:52:40 <zzo38> I have used Audacity and those things, but I find SoX much better to work with, at least.
04:52:42 <pikhq> (WHY WOULD YOU DISTRIBUTE THAT)
04:53:02 <zzo38> Even if it isn't for scripting.
04:53:21 <madbr> pikhq : that takes about 10 seconds to do in audacity
04:53:37 <pikhq> And it took about that long in sox.
04:53:44 <Bike> valuable seconds i could have spent jamming!
04:53:52 <pikhq> sox is the imagemagick of audio.
04:53:58 <pikhq> This is both its strength and its weakness.
04:55:24 <zzo38> I also find ImageMagick good for pictures, though. However, sometimes I find I want to use some of ImageMagick effects on audio too, and SoX doesn't do that, so I will use SoX to convert to raw, ImageMagick then loads and saves it as a single-row pictures and then use SoX to convert back to other format. It wouldn't be quite best way, but it can work.
04:56:03 <zzo38> Program with both kind of feature, I think is going to work better.
04:57:51 <zzo38> I have written a program for using ImageMagick and METAFONT together, so that it can be used to make up new drawings in a reasonable way, too.
04:58:18 <fowl> are there any programming languages based on mirc script
04:58:55 <zzo38> fowl: I don't know of any other than mirc script itself (and I don't know how mirc script works either)
04:59:39 <fowl> it would make a good base for an esolang
04:59:50 <zzo38> You can try to make such a thing if you like to do so
05:00:02 <fowl> not me, i'm just a poor farm girl
05:00:34 <zzo38> Not me, I don't use mirc script
05:04:34 -!- augur has quit (Ping timeout: 272 seconds).
05:06:21 <zzo38> However I did make esolang based on the classical sequent calculus, where the two negation rules correspond to creating and consuming continuations.
05:06:42 <zzo38> It has first class continuations, but doesn't have any first class functions.
05:11:34 <zzo38> Maybe someone can write esolang based on astronomy and/or astrology, too.
05:13:53 <zzo38> Can you make a esolang where instruction sets are frequency-modulated?
05:14:49 <oerjan> fowl: does myndzi count \o| \o/ |o/
05:18:17 <madbr> zzo38 : considering FM is essentially table lookup, probably
05:18:37 <madbr> provided that you find some way to express the infitely large tape
05:22:16 -!- Zerker has quit (Quit: Colloquy for iPad - Timeout (10 minutes)).
05:27:48 -!- conehead has quit (Read error: Connection reset by peer).
05:29:18 <zzo38> In the Dungeons&Dragons I played today, I was paying a shopkeeper to fix a bag, but then a dwarf came in, and said that the shopkeeper was about to accidentally poke his finger, which he did, and then said "duck!" and stole one of the tools on the wall and left. The shopkeeper then died (he was killed by a crossbow bolt), so I used his tools to fix the bag myself and took back the coins I gave to him.
05:33:12 -!- Zyprexa has quit.
05:39:46 <zzo38> I think I may need to fabricate a duplicate of this situation (but fake, using illusions and invisible walls) in another town.
05:40:16 <kmc> invisible walls!
05:40:19 <kmc> what is the duplicate for?
05:40:46 <zzo38> In order to trap the crossbowmen, which are probably all over the place.
05:41:16 <Bike> did you fix the bag while being shot at
05:42:02 <zzo38> Bike: No, I was hiding underneath the counter. The counter was on the separation between the inside and outside of the shop; normally the customer stand on the outside and the shopkeeper stands inside.
05:43:50 <zzo38> The walls are so that neither the shopkeeper doesn't get killed; the illusions will duck and so on just the same.
05:44:27 <kmc> mcpherrin: I tried to play D&D exactly once and then there was a tornado (in real life, not in the game)
05:44:51 <zzo38> The tool that the dwarf stole was not needed to fix this bag, so that was not a problem.
05:46:24 <kmc> how many crossbowmen do you think there are
05:46:32 <zzo38> It is a sign with "DO NOT READ THIS SIGN" written on it, almost.
05:47:50 <zzo38> kmc: I don't know, but probably there are many all over the place, they were near the docks, on both ends of the river, and in between, and even on the way to this river from a larger boat, and in this North River Village, so probably there would be some in South River Village too.
05:47:52 <Bike> time to take a look at the biomedical program i'll be working on. HOW EXCITING all the globals will be
05:49:43 <oerjan> go into anthropology instead, then you can meet exciting locals
05:49:55 <kmc> hot singles in your area?
05:50:15 <Bike> hot singles in an area
05:50:42 <kmc> what if i prefer to date people who are already in relationships
05:51:02 <shachaf> i played d&d in third grade in hebrew
05:51:14 <Bike> "Representation of the vowel /eh/ in normal and impaired auditory nerve fibers: Model predictions of responses in cats" i feel like fizzie
05:51:54 <shachaf> zzo38: do you play this in person with people or over the internet
05:51:59 <shachaf> the descriptions are v. detailed
05:52:02 <zzo38> shachaf: In person.
05:52:51 <zzo38> We do not use a game board or anything like that; just paper, pencil, books, dice, and thinking.
05:53:32 <Bike> is there a standard license that's "open source, but if you use this and publish something about it, cite so and so"?
05:53:50 <Bike> «#include <math.h> /* Added for MS Visual C++ compatability, by Ian Bruce, 1999 */» get hype
05:54:25 <zzo38> Bike: I think there may be something like that, but I don't know.
05:54:41 <Bike> wowwwww i didn't even know you could declare functions within a function
05:54:44 <zzo38> But I thought you meant citing it in a bibliography or something like that.
05:54:45 <Bike> i'm learning so much!!
05:54:52 <Bike> that's what i meant.
05:55:21 <zzo38> Maybe there is something like that.
05:55:30 <zzo38> Why did you want to know of it?
05:56:01 <zzo38> I do not know the proper way to cite non-literate computer programs in a bibliography, though.
05:56:39 <Bike> zzo38: because this code says "if you use this, please cite x paper" in a comment.
05:56:43 <Bike> they want the paper cited, not the code.
05:57:04 <Bike> * COMPLEX.HPP header file * use for complex arithmetic in C
05:57:10 <zzo38> O, so the code is separate from the paper.
05:57:36 <Bike> yeah. code in a paper doesn't happen much outside CS.
05:58:02 <zzo38> In that case you could easily cite the paper, but where and how?
05:58:29 <zzo38> In a literate program you can cite it in the bibliography, but in other case I don't know how?
05:59:12 <Bike> If you are yourself writing a paper.
05:59:32 <zzo38> Yes, if you are yourself writing a paper, it works.
05:59:41 <zzo38> But what do they mean by "if you use this" in this case?
05:59:57 <zzo38> Using it doesn't seems to necessarily imply that you are writing a paper?
06:00:51 <Bike> well, w hat it actually says is "Please cite these papers if you publish any research results obtained with this code or any modified versions of this code."
06:01:24 <zzo38> O, that's what it says. That works then.
06:01:41 <zzo38> But is that even a license?
06:02:35 <Bike> No. It's an informal request. Which is why I was curious as to whether there was a formal license. In service of this curiosity, I asked several minutes ago whether there was such a license, and then this conversation happened, culminating for the moment in this message you are reading.
06:03:55 <zzo38> I do not know of such a thing, although such an informal request will work. If it is included in a comment in the source file, probably people who do modify it, will keep it there (especially since it says "or any modified versions of this code").
06:07:26 <Bike> struct __COMPLEX { double x,y; }; typedef struct __COMPLEX COMPLEX;
06:08:07 <Bike> n probably but i'm bitter
06:08:40 <elliott> Bike: no because __COMPLEX isn't a name you're allowed to use
06:09:14 <Bike> maybe i should just start cold emailing people to tell them they're out of conformity and should feel bad
06:09:24 <elliott> Bike: unless you are the implementation
06:10:11 <elliott> Bike: probably the most silly common identifier-related nonconformance is naming a type *_t under posix
06:10:28 <Bike> yes i'm just confused by this one though
06:10:49 <Bike> it's just defining a simple complex type (which is redundant in C99 but whatever), and the name __COMPLEX isn't actually used outside of the typedef
06:10:53 <kmc> doesn't C99 have efb
06:11:10 <elliott> oh this is someone else's code
06:11:24 <Bike> do you think so little of me
06:11:25 -!- drdanmaku has quit (Quit: Connection closed for inactivity).
06:11:29 <elliott> Bike: presumably it's to stop people saying struct __COMPLEX because it's an implementation detail or whatever
06:11:42 <zzo38> You can try to write typedef struct { double x,y; } COMPLEX; does it work OK?
06:12:01 <elliott> some people always do the typedef separately. one reason to do that is uniformity: if you have a cycle in struct inclusions, then you cannot just use "typedef struct { ... } name;".
06:12:10 <elliott> so sometimes you must name structs.
06:12:10 <zzo38> (It might not work if you need forward references, though)
06:12:19 <elliott> right, forward refs in general.
06:12:45 <Bike> maybe i'll just replace the code with _Complex and see how it goes
06:13:52 <elliott> Bike: #include <complex.h> and you can say "double complex" etc.
06:14:16 <Bike> right, _Complex is the C99 type isn't it
06:14:25 <Bike> oh, wait, i see.
06:14:27 <elliott> Bike: C99 can't define complex outright because it'd clash with existing stuff
06:14:31 <elliott> so they define _Complex and #define it in the header
06:14:39 <elliott> same situation with stdbool
06:15:04 <Bike> also, this entire program is written in C, but you're supposed to use it as a matlab program. i don't get this field
06:18:12 <fizzie> typedef struct { double re; double im; } zomplex; hth
06:18:39 <fizzie> (That's from the SGI FFT library on IRIX.)
06:20:12 <Bike> maybe i should rewrite this in rust. i bet i could squeeze it into a one line macro invocation
06:20:22 <Bike> ho'ws rust's matlab ffi capabilities,
06:22:15 -!- password2 has joined.
06:23:12 <fizzie> https://dl.dropboxusercontent.com/u/113389132/Misc/20140531-cat_wagon.jpg <- from Kyoto
06:24:27 <fizzie> kmc: https://dl.dropboxusercontent.com/u/113389132/Misc/20140531-boss.jpg
06:24:38 <kmc> now you believe me
06:25:17 <fizzie> I thought you were just being silly at first, but then I saw it.
06:26:13 <kmc> do you see the fnords
06:27:30 -!- MoALTz has joined.
06:27:52 -!- fungot has joined.
06:27:57 <fungot> fizzie: but it seems to be latin1 last i checked
06:28:11 <fungot> kmc: and i modified code affecting the initial image, right?)
06:28:49 <fizzie> That probably explains the absence.
06:30:27 <kmc> does befunge support self-modifying code?
06:31:05 <Bike> matlab has static (in the internal-to-function sense) variables, huh
06:31:28 <fizzie> kmc: Yes, though the fungot code doesn't use very much of that. The ^reload command possibly counts.
06:31:28 <fungot> fizzie: which is? tuples?!" readings. it's much easier
06:33:49 <fizzie> In fact, my half-finished (at most) static AOT Funge-98 compiler was enough to run fungot, sans support for ^reload, IIRC.
06:33:49 <fungot> fizzie: and is an indy much faster than we do today ( eg. i eat steak.
06:34:05 <fizzie> fungot: You can't eat steak, you're a program.
06:34:05 <fungot> fizzie: no it didn't. not even by riastradh!
06:38:35 <shachaf> kmc: imo you should see _Rosencrantz and Guildestern Are Dead_
06:42:10 <shachaf> it is a play that was also conveniently turned made into a movie
06:43:05 <fizzie> fowl: It's an owner-only command, sorry. :/
06:43:16 <fizzie> I'd do it but it'd probably break, it's not used much.
06:43:26 <fungot> fizzie: i'd call them smug." jesse fnord'
06:43:45 <fizzie> Not much to see, really.
06:44:12 <fizzie> Right side of lines 1-2 of https://github.com/fis/fungot/blob/master/fungot.b98
06:45:18 <fizzie> (It's up top so that if the layout of the rest of the code changes, it hopefully won't move around.)
06:46:49 <fizzie> Oh, and also because it needs to blank the old code before loading the new one ('i' does not overwrite cells where the input file has spaces, IIRC) so it must be more or less out of the way.
07:17:27 -!- Bike has quit (Quit: shutdown).
07:18:30 <HackEgo> danddreclist 53: shachaf nooodl boily \ http://zzo38computer.org/dnd/recording/level20.tex
07:18:35 -!- madbr has left.
07:25:07 <zzo38> One day I made a diagram, consisting of four concentric circles. The innermost circle is labeled "Universe". Around that one is a circle labeled "Multiverse". Around that is a circle labeled "Mathematics". Around that is the outermost, labeled "GOD".
07:25:33 <shachaf> what's the label in the space outside the outermost circle
07:26:18 <zzo38> The space outside of the outermost circle isn't part of the diagram, but if it were it would also have to be "GOD". Such a diagram is impossible draw, however.
07:30:39 <zzo38> (It seems possible as written here, but that is because it is too difficult (perhaps impossible) to expression the proper way, so this is the best approximation I can have.)
07:35:33 <zzo38> Is good that you try to ask such question, but, such question wouldn't be sensible any more than trying to figure out the position of omega in the English alphabet, or the page number of the shelf that stores the books.
08:14:56 -!- greg79 has joined.
08:15:31 -!- greg79 has left.
08:41:45 -!- ais523 has joined.
08:58:10 -!- idris-bot has joined.
09:11:35 <Taneb> Making corruption art is fun :)
09:11:49 <Taneb> http://i.imgur.com/zOSp2gp.jpg (made by blanking random bytes)
09:12:10 -!- password2 has quit (Ping timeout: 240 seconds).
09:12:23 -!- nooodl has quit (Ping timeout: 245 seconds).
09:14:24 <mcpherrin> Taneb: http://www.reddit.com/r/glitch_art/top/ is people into that kind of stuff, if you want some upboats for your pictures :p
09:15:44 <Taneb> mcpherrin, I'd rather get it really good first
09:15:49 <Taneb> And, you know, not Nigel Farage
09:17:58 <oerjan> what better image to use for corruption art
09:19:08 <Taneb> oerjan, I don't think Nigel Farage is actually corrupt. Just, you know, hideously wrong on most political issues.
09:22:05 <Taneb> So, other than bit-flipping and byte-blanking, what other effects are easy to produce>
09:22:47 -!- nooodl has joined.
09:23:48 <Taneb> JPEG compression does fun things too
09:27:41 <Taneb> oerjan, can you elaborate on that?
09:28:40 <oerjan> basically set some arbitrary bytes to constants?
09:29:43 <oerjan> sprinkle nigel with "666"s, that sort of thing.
09:40:14 <FreeFull> https://gist.github.com/FreeFull/6059a9be7500a2d6f6c5/c194838b6ad50f65aa02831e2f745bf56046383b Suggestions on improving this quine?
09:40:27 <FreeFull> Other than removing whitespace, which is trivial
09:41:27 <Taneb> Well, it's obviously Rust
09:41:45 <FreeFull> I don't know of any other language with print!()
09:42:04 -!- Gracenotes_ has joined.
09:42:32 <Taneb> @type let (!) = ($) in print!()
09:43:25 <FreeFull> And doesn't have the same behaviour =P
09:43:49 <FreeFull> > let (!) = ($) in print!("{}","Meow")
09:44:02 <FreeFull> Oh, damn, forgot lambdabot doesn't do IO =P
09:44:15 -!- Gracenotes has quit (Ping timeout: 265 seconds).
09:44:16 -!- EgoBot has quit (Ping timeout: 265 seconds).
09:44:28 -!- EgoBot has joined.
09:44:29 <Taneb> Yeah, the behaviour is horribly different
09:44:56 <Taneb> !haskell main = let (!) = ($) in print!("{}","Meow")
09:45:08 <EgoBot> help: General commands: !help, !info, !bf_txtgen. See also !help languages, !help userinterps. You can get help on some commands by typing !help <command>.
09:45:24 <Taneb> Yeah, that's horribly different
09:46:29 -!- oerjan has quit (Quit: leaving).
09:58:51 <Taneb> fizzie, any ideas for making glitches?
09:59:26 <Taneb> I'd prefer ones that could conceivably occur on actual crappy lines.
10:09:46 <fizzie> Try to make errors not detectable by typical ECCs, perhaps? Nobody'll notice, but you'll know.
10:11:27 <mcpherrin> Taneb: well, you could get a crappy line! :p
10:12:31 <fizzie> Remove most significant bit, that happens every now and then.
10:12:41 <fizzie> Or set it according to the parity of the other seven bits.
10:12:48 <fizzie> Maybe not so often these days.
10:13:07 <fizzie> ("Remove" == clear, in this case.)
10:13:42 <mcpherrin> I just had this legit glitch out on me :p
10:19:47 -!- Phantom_Hoover has joined.
10:31:24 <olsner> ooh, my coffee is done
10:52:53 -!- MindlessDrone has joined.
11:00:07 -!- impomatic has joined.
11:04:40 <HackEgo> [wiki] [[User:Rdebath]] http://esolangs.org/w/index.php?diff=39730&oldid=39726 * Rdebath * (+133) /* Interpreter List */
11:08:35 -!- impomatic has quit (Ping timeout: 240 seconds).
11:11:41 -!- impomatic has joined.
11:17:31 -!- impomatic_ has joined.
11:18:58 -!- impomatic has quit (Ping timeout: 240 seconds).
11:37:23 -!- impomatic_ has quit (Ping timeout: 245 seconds).
11:46:16 -!- impomatic_ has joined.
11:58:35 -!- impomatic_ has quit (Remote host closed the connection).
12:04:18 -!- impomatic_ has joined.
12:07:58 -!- boily has joined.
12:10:28 -!- boily has quit (Client Quit).
12:10:59 -!- boily has joined.
12:23:32 -!- yorick has joined.
12:28:25 -!- Phantom__Hoover has joined.
12:29:15 -!- Phantom_Hoover has quit (Ping timeout: 252 seconds).
12:29:27 -!- impomatic_ has quit (Ping timeout: 260 seconds).
12:29:50 -!- Sorella has joined.
12:30:25 -!- Sorella has quit (Max SendQ exceeded).
12:31:47 -!- Sorella has joined.
12:55:48 -!- impomatic_ has joined.
13:04:05 -!- MindlessDrone has quit (Ping timeout: 252 seconds).
13:07:30 -!- impomatic_ has quit (Ping timeout: 252 seconds).
13:08:36 -!- impomatic_ has joined.
13:09:34 <impomatic_> mroman: the first tournament results are in https://twitter.com/xcorewar/status/472725852976062464
13:11:40 -!- MindlessDrone has joined.
13:13:55 <boily> aaaaaah... sweeeeet druuuugs...
13:14:21 <lambdabot> oerjan said 11h 36m 5s ago: http://en.wiktionary.org/wiki/cruchon hth
13:15:37 <boily> it's not quite right. a cruchon here is something that can be as small as a Mason jar, or as big as those fatso pickle jars.
13:16:07 <boily> (hm. I guess I just answered my own question here. qc:cruchon → en:"glass jar".)
13:16:34 <boily> @tell oerjan here cruchon is a glass jar.
13:17:33 <Taneb> impomatic_, are you entering?
13:18:59 -!- impomatic_ has quit (Ping timeout: 240 seconds).
13:22:25 -!- impomatic_ has joined.
13:27:23 -!- impomatic_ has quit (Ping timeout: 245 seconds).
13:28:54 -!- impomatic_ has joined.
13:46:16 -!- impomatic__ has joined.
13:48:38 -!- impomatic_ has quit (Ping timeout: 245 seconds).
13:57:32 -!- impomatic__ has quit (Ping timeout: 255 seconds).
14:00:41 -!- impomatic__ has joined.
14:02:02 -!- Patashu has quit (Ping timeout: 255 seconds).
14:08:15 -!- impomatic__ has quit (Ping timeout: 252 seconds).
14:25:19 -!- MoALTz has quit (Quit: Leaving).
14:27:55 -!- sebbu has quit (Ping timeout: 240 seconds).
15:02:19 -!- impomatic__ has joined.
15:04:57 -!- tertu has joined.
15:19:02 -!- impomatic__ has quit (Ping timeout: 276 seconds).
15:21:13 -!- conehead has joined.
15:21:53 -!- impomatic__ has joined.
15:37:32 -!- impomatic__ has quit (Ping timeout: 265 seconds).
15:38:25 -!- ^v has quit (Quit: Leaving).
15:40:13 -!- boily has quit (Quit: Poulet!).
15:42:56 -!- impomatic__ has joined.
15:47:59 -!- impomatic__ has quit (Ping timeout: 252 seconds).
15:53:04 -!- ^v has joined.
15:53:40 -!- impomatic__ has joined.
15:58:35 -!- impomatic__ has left.
16:21:55 -!- ^v has quit (Ping timeout: 240 seconds).
16:28:39 -!- Bicyclidine has joined.
16:28:51 -!- sebbu has joined.
16:29:24 -!- sebbu has quit (Changing host).
16:29:24 -!- sebbu has joined.
16:30:31 -!- impomatic__ has joined.
17:09:15 -!- AnotherTest has joined.
17:11:22 <HackEgo> [wiki] [[5command]] http://esolangs.org/w/index.php?diff=39731&oldid=39704 * Rdebath * (+118) /* Interpreters */
17:12:47 -!- ^v has joined.
17:21:04 -!- augur has joined.
17:22:38 -!- ais523 has quit.
17:27:17 -!- boily has joined.
17:27:35 <HackEgo> [wiki] [[5command]] http://esolangs.org/w/index.php?diff=39732&oldid=39731 * Rdebath * (+97) Add source
17:38:11 <Taneb> I think I'm writing an esoteric data structure help
17:38:20 <Taneb> It's sort of a heap and a binary search tree simultaneously
17:38:58 <Taneb> No, it's heap sorted on one key and tree sorted on another key
17:40:08 <boily> so it's a keyed treap?
17:41:01 <Taneb> olsner, when the two keys correlate it degenerates into a linked list! :)
17:41:08 <boily> I should try to worm something named "KeyedTreap" in our codebase at work and have it pass code review :P
17:42:00 <myname> Taneb: xor linked list, please
17:48:24 <olsner> hm, so my high-level language rewrite of thousands of lines of assembly code was easy to write but came out buggy ... unfortunately debugging it doesn't seem any easier
17:50:19 -!- ^v has quit (Ping timeout: 240 seconds).
17:50:39 <olsner> yes, once you get to debugging something you have already lost, the only recourse is to write it correctly
17:55:10 <Taneb> http://lpaste.net/104902
17:57:17 <Taneb> I have not tested this at all, btw
18:01:43 -!- ais523 has joined.
18:16:56 <douglass_> http://www.thisiscolossal.com/2014/05/fantastic-fungi-steve-axford/
18:17:05 <kmc> ewige einhornkraft
18:31:29 -!- HackEgo has quit (Ping timeout: 264 seconds).
18:39:57 -!- Bicyclidine has quit (Ping timeout: 252 seconds).
18:41:57 -!- Bicyclidine has joined.
18:49:37 -!- drlemon has joined.
18:54:45 <Melvar> ( :t \f, a => (x ** (f x, x -> a))
18:54:46 <idris-bot> (input):1:14:When elaborating argument x to constructor Ex_intro:
18:55:04 <Melvar> ( :t \f, a => (x : _ ** (f x, x -> a))
18:55:04 <idris-bot> (input):1:23:When elaborating argument x to constructor Ex_intro:
18:56:07 <Melvar> ( :t \f, a => the Type (x ** (f x, x -> a))
18:56:07 <idris-bot> \f => \a => the Type (x ** (f x, x -> a)) : (Type -> Type) -> Type -> Type
18:56:10 <impomatic__> Photo from the CW tournament http://codu.org/logs/log/_corewars/2014-05-31
18:56:35 <Melvar> < boily> the flowers are very small, about ¼” Ø. – Also that should be ¼″
18:56:36 <impomatic__> No wait... Photo from the CW tournament https://twitter.com/john_metcalf/status/472810336501133314 :-)
18:57:00 <Melvar> < mcpherrin> kmc: O(question mark in a box) :-( – ⍰
19:05:43 <impomatic__> Phantom__Hoover: evolved program green, hand coded program red. The hand coded program won! :-) +1 for humanity.
19:09:51 <Bicyclidine> +1 for evolved writer over writing evolver
19:10:10 <kmc> i have a small quadcopter now!
19:10:49 <zzo38> It would be expected that evolving would be very slow (but not completely impossible) compared to doing it directly.
19:16:36 <impomatic__> zzo38: for small coresizes (like 80, 800) it's possible to evolve something competitive overnight.
19:17:28 <zzo38> Yes if it is small I would think it can work faster
19:17:37 <zzo38> Same thing with most algorithms really
19:28:44 <kmc> Bicyclidine: too small
19:31:21 -!- ais523 has quit (Read error: Connection reset by peer).
19:31:23 -!- callforjudgement has joined.
19:31:33 <kmc> have to not fly it up my skirt :X
19:35:59 <kmc> no i don't
19:36:32 <kmc> my friend brought his much larger quadcopter over
19:36:43 <kmc> he says you're supposed to charge the battery within a special fireproof sack
19:36:46 <kmc> but he lost the sack
19:37:12 <kmc> now they're off to the north bay to fly said quadcopter and take photos for a wedding invite
19:37:39 <fizzie> Much larger compared to what?
19:39:28 <fizzie> I guess larger than said friend.
19:41:25 <kmc> larger compared to my little one that can't even carry a burrito
19:41:42 <kmc> the bigger quadcopter has already injured an intern
19:41:44 <kmc> it's tasted human blood
19:42:25 <fizzie> Our days as the dominant species are probably soon over.
19:43:23 <kmc> once they learn how to reproduce yeah
19:43:58 <fizzie> I have here the most boring video of a deer imaginable.
19:44:20 -!- Bike has joined.
19:44:33 <fizzie> It's from http://en.wikipedia.org/wiki/Nara_Park and it's just doing boring things.
19:44:51 <Bike> i'm telling you, i have high standards
19:45:18 <olsner> I imagine as boring as imaginable is a lot less boring than possible
19:45:50 <kmc> i saw a tourist chasing a deer who had stolen her map in nara
19:45:55 <kmc> it was pretty fucking funny
19:46:05 <kmc> fizzie: are you going anywhere else besides kyoto and nara?
19:46:08 <olsner> that's probably not the video fizzie's watching
19:46:24 <fizzie> We're actually home already, but we only did a day trip to Tokyo.
19:46:34 <fizzie> (In addition to those two places.)
19:46:42 <kmc> welcome home
19:46:43 <fizzie> (It was a very efficient vacation.)
19:46:45 <Bike> also, re quadcopters, did you know that claude shannon once said "I visualize a time when we will be to robots what dogs are to humans. And I am rooting for the machines."
19:46:53 <kmc> did he actually say that
19:47:44 <Bike> according to wikiquote, at least
19:49:35 <fizzie> https://dl.dropboxusercontent.com/u/113389132/Misc/20140531-nara.jpg no mention about map-stealing
19:50:21 <kmc> Deer used Knock down! It's super effective!!
19:50:25 -!- drdanmaku has joined.
19:50:32 -!- callforjudgement has changed nick to ais523.
19:50:36 <fizzie> Also note that the "attack people, so please be careful" part is a sticker. One wonders what was under it.
19:55:17 <boily> Melvar: why? I like «”».
20:00:15 <kmc> Board of Equalization is such an Orwellian name for a state government body
20:00:38 <boily> which government is it from?
20:00:56 -!- HackEgo has joined.
20:01:46 <Bike> http://bayesianbodybuilding.com/wp-content/uploads/2013/11/BAYESIAN-BODYBUILDING-v5.png
20:06:19 -!- hambubger has joined.
20:22:48 -!- boily has quit (Quit: Poulet!).
20:27:11 <zzo38> If you have a multiplayer pinball game without enough delay before next player, then it is possible any spinner which is spinning, will continue spinning on the next player's turn.
20:33:10 -!- hambubger has left ("Leaving").
20:35:19 <mroman> impomatic__: well... at least i'm not last
20:35:31 -!- lollo64it has joined.
20:39:28 <impomatic__> mroman: no it's not too bad :-) The next tournament will be in October so hopefully you'll be a bit higher...
20:42:51 <mroman> I'm pretty sure one of my beginner's hill wariour would have scored better :)
20:42:59 <mroman> NotAScanner doesn't even get on the beginner's hill
20:59:41 -!- AnotherTest has quit (Ping timeout: 264 seconds).
21:01:12 -!- MoALTz has joined.
21:13:36 -!- lollo64it has quit (Quit: Leaving).
21:17:36 -!- lollo64it has joined.
21:28:02 -!- adu has joined.
21:50:45 <Sgeo> zzo38: unless you make the pinball game have the spinners magically stop spinning
21:50:50 <Sgeo> (I'm not even sure what a spinner is)
21:57:56 <zzo38> Sgeo: Microsoft seems to call them "flags" instead of "spinners"
21:58:42 <zzo38> Would you use magnets to somehow stop them spinning?
21:59:38 <nooodl> "Polynomial functions are a class of functions having many important properties. They are all continuous, smooth, entire, computable, etc.[citation needed]"
22:00:24 <Bike> i'm not sure i could find one source claiming all of those. another encyclopedia, maybe.
22:02:08 <zzo38> How are you supposed to check overflow converting float->int in a C program?
22:02:51 -!- boily has joined.
22:03:21 <ais523> compare the float to (float)INT_MAX and (float)INT_MIN?
22:04:02 -!- ais523 has quit.
22:04:10 <zzo38> Which header files do I use?
22:04:42 <zzo38> And what is best way checking arithmetic errors when doing calculation with floating points?
22:05:17 <HackEgo> [wiki] [[Spleenmap]] http://esolangs.org/w/index.php?diff=39734&oldid=34648 * 68.203.11.82 * (-1) make "it's" into the correct pronoun
22:08:02 -!- Patashu has joined.
22:09:49 <zzo38> Actually I am using my own int max/min anyways
22:10:27 <nooodl> are they really computable? what if your polynomial just: contains non-computable coefficients
22:11:05 <Bike> i don't think i've ever dealt with a polynomial with transcendent coefficients.
22:15:19 <Bike> you can have polynomials with computable roots but uncomputable coefficients. heh.
22:21:09 -!- aretecode has joined.
22:28:19 <int-e> as long as at least one of the roots is uncomputable ...
22:29:09 <Bike> sure, if you're a COWARD
22:29:10 <int-e> I want monic polynomials. Thanks.
22:29:38 -!- adu has quit (Quit: adu).
22:29:59 <Bike> x² + ax - a - 1 then.
22:30:26 <Bike> i guess i don't know what the other root is
22:30:31 <boily> I don't do monopolynomials. I had a friend who went that way and now, he can't even.
22:31:05 <int-e> that has roots -a-1 and 1, one of which is not computable.
22:31:24 <int-e> anyway, never mind.
22:31:35 <int-e> since I clearly missed your point :)
22:31:56 <Bike> i didn't really have a point, i'm just saying silly things
22:32:11 <Bike> kind of a shame there's no conjugate property like for irrationals and complexes, though
22:32:15 -!- Patashu has quit (Disconnected by services).
22:32:15 -!- Patashu_ has joined.
22:32:18 <Bike> probably you don't have that for transcendents either...
22:32:45 * boily wonders if there's a greek prefix for something between mono- and poly-...
22:32:49 <int-e> there is a difficulty in the opposite direction, too. the roots of x^2 - a, with computable a, may not be computable *real* numbers (namely, if it's undecidable whether a < 0).
22:33:46 <int-e> but that difficulty disappears for complex numbers, as far as I can see. If you allow non-monic polynomials though, then ax - 1 = 0 has the same problem.
22:34:38 <Bike> at least they're still entire.
22:34:40 <int-e> or are those not greek? I'm weak.
22:36:32 <boily> sometimes, not the brightest questions drift through my mind.
22:37:23 <boily> int-e: bi- is latin, di- is greek.
22:37:25 <nooodl> un- bi- tri- quad- is latin, mono- di- tri- tetr- is greek
22:38:54 -!- oerjan has joined.
22:39:14 <boily> apparently, there is such a thing as “dodrant-”.
22:40:03 <nooodl> base 3/4 aka dodrantary
22:41:27 <lambdabot> boily said 9h 24m 53s ago: here cruchon is a glass jar.
22:42:48 <int-e> oh wikipedia. "A real number is computable if and only if the set of natural numbers it represents (when written in binary and viewed as a characteristic function) is computable." not.
22:46:32 <Bike> is that not true? "it represents" is a bit rude but it still seems okay to me
22:46:37 <Bike> well the binary thing is also pointless
22:46:56 <Bike> oh, and you need an ordering, i guess...
22:47:19 <int-e> Bike: the trouble is that sometimes you cannot decide whether the next digits should be 01111....1 or 10000....0.
22:52:01 -!- quintopia has changed nick to Quintopia.
22:53:26 <int-e> For example given a Turing machine T, you can define a = 1 + (-1/2)^n if T halts in n steps, and a = 1 otherwise. That's a computable number but you'll have a hard time figuring out whether it's 1.000... or 0.111...
22:55:33 <oerjan> int-e: it's nevertheless true, as for those ambiguous real numbers _both_ representations are obviously computable.
22:56:03 <int-e> oerjan: if T halts then there is no ambiguity at all.
22:57:11 <oerjan> int-e: the thing is, being computable is a property of the real number, not of the TM used to define it.
22:58:01 <oerjan> so it doesn't _matter_ whether you cannot compute the digits from knowing only the TM
22:58:34 <oerjan> and the only numbers where you cannot compute the digits are numbers which are also represented by halting machines.
22:58:53 <elliott> int-e: um, but 0.111... = 1?
22:59:43 <oerjan> elliott: the point is that you cannot prove in finite time that it's exactly equal to 1, so you don't know that you're not forced to choose 0 or 1 at some point
23:00:34 <oerjan> in a sense, int-e is correct if you are thinking in constructive logic, but not if you are assuming excluded middle for the existence of the digit representations
23:01:43 <oerjan> i suppose in constructive logic you end up with not being able to prove that the constructive real number _has_ a digit representation.
23:01:44 <nooodl> computability theory sounds like it's very easy to say wrong things about!
23:01:59 <Bike> i can assure you that it's very easy to say wrong things in general
23:02:31 <Bike> see, there you go
23:02:50 <Bike> how presumptuous
23:02:51 <M28> i has a solution
23:03:00 <M28> let's define 2 = 1
23:03:06 <M28> then the mistery is solved!
23:03:14 <M28> brb gonna get my nobel
23:03:30 <int-e> oerjan: Subtle. Hmm. So the point is that you can give some advice to the program producing the binary representation.
23:04:06 <Quintopia> i really want to believe that story about nobel's wife cheating with a mathematician is true
23:04:11 <oerjan> M28: you mean your abel hth
23:04:32 <int-e> (and the only kind of advice you really need is that "this is a rational number of shape a/2^n, and here is n.")
23:05:09 <oerjan> Quintopia: you know why that isn't true, right
23:05:28 <oerjan> Quintopia: no, but the abel prize is a real prize
23:05:45 <oerjan> intended precisely to close the nobel gap
23:05:47 <Bike> the nobels are all fairly random. i mean, "physiology or medicine"?
23:07:06 <shachaf> my father says of any unsolvable problem "if you solve that, you'll get the nobel prize in mathematics"
23:07:28 <int-e> oerjan: it's weird because there is no computable function from computable reals of the first kind (producing approximations of precision 1/2^n) to the second kind (producing binary expansions)
23:07:41 <oerjan> shachaf: is that just a subtle way of using reductio ad absurdum to say you won't be able to solve it?
23:07:45 <Taneb> Wow, Hackers was such a 90's movie
23:07:56 <shachaf> oerjan: only moderately subtle hth
23:08:00 <boily> Quintopia: QUINTOPIAAAAAAAAAAAAAAAAAAAAAAAIAIAIAIAIAIAIAIAIIIIIIIIIIIIIIIAAAAAAAH!
23:08:32 <oerjan> old cthulhu had a farm
23:09:29 <int-e> (annoyingly I should know this stuff. oh well.)
23:09:44 <Bike> well rounding is uncomputable in general
23:10:25 <Quintopia> oerjan: i just looked it up. the reason it isn't true (in principle, where wife can be substituted by lover as needed) is that it simply happens not to be true of the girlfriends we know about...
23:10:44 * ion computes some well rounded numbers
23:10:45 <shachaf> oerjan: now that i've looked up the lyrics to Old MacDonald Had a Farm, i see the origin of certain lyrics from Chicago
23:11:14 <boily> Chicago and R'lyeh are related?
23:11:17 <oerjan> Quintopia: bah you're overcomplicated it
23:11:50 <oerjan> shachaf: i don't know chicago :(
23:12:06 <Quintopia> oerjan: but it coooooould still be true and history just forgot >.>
23:12:24 <shachaf> oerjan: http://www.metrolyrics.com/roxie-lyrics-chicago-the-musical.html
23:12:49 <shachaf> anyway now i know the origin of "here a * / there a * / everywhere a *"
23:13:07 <Quintopia> wait...it's not from old macdonald?
23:13:53 <Quintopia> oh. wait... what made you think it came from anywhere else?
23:13:57 <shachaf> i guess i'd never heard the full song in english before
23:14:18 <shachaf> i think i've heard it in hebrew
23:14:36 <shachaf> ("uncle moshe had a farm")
23:15:04 -!- MindlessDrone has quit (Ping timeout: 252 seconds).
23:15:20 <Quintopia> well now i've also learned something...
23:15:52 <shachaf> maybe i've heard it in english too and just forgotten
23:16:06 <oerjan> boily: the only problem is they're non-euclidean antipodes, so you won't find r'lyeh just by changing coordinate signs hth
23:17:03 <Quintopia> actually, i happen to know that many parts of chicago are very close to Fairy
23:17:32 <Quintopia> there are probably parts very close to R'lyeh also
23:17:57 <Quintopia> how would you like to live in that house?
23:18:16 <boily> oerjan: I don't change signs anymore now that I work with dental prosthesis. last time I did that... well. it was... I don't think the result would have fit in a three-dimensional mouth.
23:18:40 <oerjan> boily: did you just denture cthulhu?
23:19:07 <boily> once we expand our clientèle over to the Outer Planes.
23:19:34 <oerjan> (actually changing signs isn't right for longitude anyway)
23:20:16 <boily> axes in dentistry are fun! we have: buccal/lingual, occlusal/cervical and mesial/distal!
23:20:22 <boily> and they're context dependent!
23:27:19 <Taneb> Is it possible to send graphics via telnet?
23:28:03 <Taneb> In such a way that common telnet clients do the write thing.
23:28:11 <Taneb> And I'm not counting ASCII art
23:28:35 <ion> Aww, i was about to link telnet://nyancat.dakko.us
23:28:44 <boily> https://github.com/asciimoo/drawille ?
23:29:29 -!- MindlessDrone has joined.
23:30:19 <Taneb> boily, Telnet isn't 8-bit clan
23:30:41 <zzo38> Doesn't telnet have a way to specify terminal capabilities?
23:52:04 <oerjan> * boily wonders if there's a greek prefix for something between mono- and poly-... <-- oligo- ?
23:52:38 <oerjan> although that's really a subset of poly-, i guess.
23:52:38 <FireFly> So I know what a monopoly is, and what an oligopoly is, but what is a polypoly?
23:57:04 <boily> at least you identified the Fourth Kind of polies. mono, oli, roly, and poly.