00:11:45 <oren> Fail. The lecture slides for my course, I just realized their mtime is in 2006, indicating this guy has been giving the same lectures with the same material for 9 years.
00:12:56 * oren idly wonders if he makes new tests...
00:13:18 <boily> helloren. which course?
00:14:45 <oren> Knowledge Representation and Reasoning, i.e. the out-of-fashion kind of AI
00:15:44 -!- GeekDude has joined.
00:18:18 -!- bb010g has quit (Quit: Connection closed for inactivity).
00:34:33 <elliott> well, if it's out-of-fashion...
00:35:19 <oerjan> the AIs are just keeping it out of fashion to prevent competition hth
00:35:25 <zzo38> I have a digital cable box (I don't need it, but someone else here uses it); I figured out how to access the diagnostics menu, user setting menu, and in the review configuration menu pushing the FAV button displays many additional screens of information; I don't know what all of them mean, but on some screens pushing A allows entering a command with the numbers, the GuideNet screen lists them.
00:35:38 <oren> elliott: good point. perhaps not much work has been done beyond what is in the text. everyone and their mother is doing neural networks now
00:35:41 <zzo38> Some screens display IP addresses. Unfortunately I don't know what any of that is or how to use any of it
00:37:03 <boily> couldn't you write a GUI in VB to track them?
00:38:07 -!- Lymee has joined.
00:40:25 <zzo38> I don't know what GuideNet means or what the IP address and other information under "interactive status" means either; Wikipedia has no information. I was able to look up DOCSIS and MoCA on Wikipedia though.
00:41:04 -!- Lymia has quit (Ping timeout: 265 seconds).
00:41:50 <oren> what happens if you put the ip into browser?
00:42:33 <zzo38> I tried connecting using netcat to various port numbers and found nothing.
00:43:11 <boily> do you feel courageous enough to nmap the fungot out of those IPs?
00:43:11 <fungot> boily: they make a movie out of " disk" space...) stuff. i just think you're an abomination" :)
00:43:18 <fungot> boily: discordianism is almost not a joke really, because the first
00:43:30 <zzo38> I don't have nmap though
00:44:07 <zzo38> One of them seems to be a LAN address; even though my internet is on the same cable as the television, I cannot connect to it.
00:44:52 <zzo38> I didn't try UDP though; I don't know if maybe that's what I need.
00:45:09 <boily> oerjan: on a completely off-topic subject, you know I still have PHHHMHSD?
00:45:38 <boily> (Post Hej Hej Hemst Micket (sorry for the orthograph) Hej Syndrome Disorder)
00:46:41 <oerjan> i recommend exposure therapy hth
00:48:24 <zzo38> I don't know what that means though
00:48:29 <int-e> https://en.wikipedia.org/wiki/Exposure_%28photography%29 ?!
00:48:42 <boily> zzo38: you do well. continue not knowing. it's good for you.
00:50:31 <oren> I recommend crazy frog therapy
00:51:15 <boily> I like the rick-roll-I-get-knocked-down mashup.
00:52:29 <zzo38> Now I figured out the .XI so I am fixing AmigaMML to support loading .XI instruments when in Extended mode (you can't use .XI in Amiga mode though).
00:53:36 <boily> zzo38: mods, trackers, chiptunes and generic 8-bit music and stuff like that?
00:54:03 <zzo38> boily: I don't know what you are asking; can you please be more specific?
00:55:11 <boily> sorry, I'm drawing a phantomatic blank here... I have this feeling I'm forgetting a word, but I'm not sure.
00:55:36 <boily> you are doing stuff that has to do with playing music through an Amiga emulator?
00:55:58 <boily> what's an .xi then?
00:56:12 <zzo38> Other than being able to output in .MOD format, it hasn't anything to do with Amiga.
00:56:36 <oerjan> boily: is the word amortized hth
00:56:37 <zzo38> A .xi is a instrument file for Fasttracker. AmigaMML has two modes, Amiga mode (which is the original mode), and Extended mode.
00:56:58 <boily> oerjan: no. tdnh, bio.
00:57:12 <boily> zzo38: aaaaaaaaaaaah. ic.
00:57:47 <zzo38> AmigaMML is a program that you can write music and then compile into .MOD and .XM files.
00:58:22 <boily> oerjan: that did not help, but it's okay hth
00:59:38 <MDude> Does that stand for music markup language or music macro language?
00:59:47 <zzo38> MDude: Music macro language
01:00:03 <boily> go HackEgo go! go HackEgo go!
01:00:34 <MDude> Thanks, I wasn't sure a quick search for AmigaMML dind't bring up much.
01:00:53 <MDude> Also also both of those languages exist, being cofusingly similarly named.
01:00:55 <oerjan> `learn A hand in the bush is better than a stoned bird hth
01:00:59 <HackEgo> Learned 'hand': A hand in the bush is better than a stoned bird hth
01:01:27 <zzo38> Well, this is the Redmine page for AmigaMML: https://devlabs.linuxassist.net/projects/amigamml
01:01:44 <zzo38> In case it helps you at all.
01:01:50 <oerjan> `learn A hand in the bush is better than a stoned bird.
01:01:54 <HackEgo> Learned 'hand': A hand in the bush is better than a stoned bird.
01:02:06 <shachaf> oerjan: also what's with the drugz jokez lately
01:02:22 <boily> shachaf: did you just pluralise y'all?
01:02:38 <oerjan> y'all y'all need to stop doing that
01:02:42 <shachaf> the plural of "y'all" is "all y'all" hth
01:02:53 <shachaf> hope this helps you at all
01:03:01 <zzo38> Isn't "y'all" already plural?
01:03:16 <shachaf> not when addressing one person hth
01:03:40 <oerjan> zzo38: you know of the euphemism threadmill? in english, second person pronouns have a plurality threadmill
01:03:45 <MDude> It does, I'll check this out.
01:03:55 <int-e> zzo38: all of you are correct :P
01:04:36 <zzo38> MDude: Yes I know, MML can refer to both, but in this case it is music macro language. There are other programs to do music macro language too, such as SakuraMML, ppMCK, CsoundMML, and probably others I don't know about.
01:04:37 <oerjan> which probably started as part of the euphemism threadmill, anyway
01:04:43 <int-e> (To my mind, the "you" may be singular, the phrase isn't.)
01:05:14 <int-e> I wonder how a threadmill works.
01:05:27 <boily> it mills threads. next!
01:05:30 <MDude> I didn't know it was made for Windows, or that you made it. I am pleasantly surprised on both counts.
01:05:38 <oren> int-e it makes nylon thread hth
01:05:45 <int-e> Do you put threads in and grind them, or is it cleverly arranged such that threads come out?
01:06:07 <shachaf> the way the mill cpu implements fork() will be revealed soon
01:06:24 <zzo38> MDude: Well, it isn't only Windows; it should be possible to compile AmigaMML for other systems too, if you have a C compiler. I don't actually know if it will actually run on a Amiga computer though.
01:06:24 <int-e> I guess it would also make an excellent name for a scheduler.
01:07:15 <MDude> I was more worried it wouldn't run on anything but Amiga. Or Linux, since Linux was in the url.
01:07:21 <oerjan> is a spaghetti machine a threadmill?
01:07:26 <MDude> But it turns out that isn't the case.
01:07:53 * oerjan suddenly regrets not spelling it spagetti
01:08:08 <oerjan> (which btw is the correct norwegian spelling.)
01:08:33 <shachaf> that would be a good pun for all the norwegian speakers in this channel
01:08:49 <zzo38> Linux Assist is just the Redmine server for FOSS projects; it isn't only for programs specific to Linux.
01:11:15 <oren> oerjan: I would have pronounces that as /spædʒetī/
01:12:37 <oerjan> that's not norwegian hth
01:13:05 <oren> it's the correct pronounciation for that spelling if it were italian
01:13:22 <oren> (up to my knowlege of italian)
01:13:32 <oerjan> (we don't have /dʒ/ except in loanwords)
01:14:13 -!- bb010g has joined.
01:14:22 <oerjan> why the bar over the i
01:14:57 <oren> oh, I forgot in IPA long vowels are supposed to have : not overbar
01:15:39 <oerjan> you learn something every day
01:16:03 <oerjan> boily: what language is that twh
01:16:39 <oren> shachaf: I don't know, but the one in spaghetti is when I hear italians say it...
01:17:02 <oren> (I live in Little Italy in Toronto)
01:17:46 <boily> oerjan: a parody of low-class country bums in then Eastern Townships.
01:19:24 <boily> shachaf: boilognese. he he he! I'll remember that one.
01:19:39 <oren> p. nifty? is that the name of a rapper?
01:20:45 -!- doesthiswork has joined.
01:21:30 <oren> yo, ma name's p. nifty, an' i'm pretty shifty, watch me spit these riffs like a tokyo drift king.
01:24:22 <Jafet> Are Tokyo drifters known to spit riffs?
01:24:42 <Jafet> (Do drifters drift? I suppose not.)
01:25:59 <oren> I don't think so, but it makes about as much sense as many real reaps I've heard...
01:26:26 <oren> shit s/har/hear
01:27:14 <boily> Jafet: does an otter ott?
01:28:28 <oren> Hmm the oldest woman in the world died again
01:30:38 <oren> Wow it isn't in the English news yet
01:32:15 <oren> hmm, I wonder how long it takes for a typical story to reach English-speaking news channels, and whether it depends on the language zone that the story comes from
01:33:07 * boily sings “mushroom mushroom ♪”
01:33:19 <oren> damn neat me to it
01:33:32 <oerjan> <oren> Hmm the oldest woman in the world died again <-- this keeps happening, they should do something to stop it hth
01:34:00 <oren> In this case it was ookawa misao, 117.
01:34:09 <zzo38> oerjan: Not necessarily.
01:34:25 -!- oerjan has set topic: RIP Ookawa Misao | I'm a fungot trapped in a channel full of weirdos | https://dl.dropboxusercontent.com/u/2023808/wisdom.pdf http://codu.org/logs/_esoteric/ http://tunes.org/~nef/logs/esoteric/.
01:35:27 <zzo38> Having a cable box at least allow me to know what show is on at 3AM and stuff like that, because the TV guide doesn't list shows at that time. But when I watch television I use the VCR in the basement instead.
01:35:34 <oren> So the question is when will it reach Google news search?
01:35:50 <zzo38> But, I also like to learn how the diagnostics and stuff in the cable box is working anyways.
01:36:27 <boily> zzo38: I'll be at my parents' this weekend. remind me to hack their cable box then ^^
01:36:34 <boily> meanwhile, 'night all!
01:36:38 -!- boily has quit (Quit: PREMOLAR CHICKEN).
01:36:42 <shachaf> it seems to be unconfirmed hth
01:36:43 <int-e> On this strange day... http://news.asiantown.net/r/47594/mexican-woman-dies-at
01:37:04 <zzo38> Unfortunately I don't know how to hack it, but I can tell what some of the undocumented functions are at least; that can still help
01:37:39 <int-e> ("oldest person on earth" must be one of the most unreliable (and short-lived...) attributions)
01:37:41 <oren> I have been noticing a significant delay between NHK and the anglospheric news when anything happens in Japan.
01:38:07 <pikhq> Are you in Japan these days?
01:38:31 <pikhq> Well, presumably. It's possible but unlikely you're watching NHK outside of Japan.
01:38:39 <oren> No but reading NHK online is good practice
01:39:39 <oren> for example, I knew about the deal with Nintendo and DeNA five hours before it reached Google News
01:39:41 <zzo38> I am not at Japan but do want to order something; I bought a Famicom at a store locally and then I asked them next time if they can get the keyboard too so that I can buy from them, but they have not done.
01:40:02 <pikhq> That keyboard is pretty rare, isn't it?
01:40:02 <int-e> Ah, wikipedia half-knows... https://en.wikipedia.org/wiki/Misao_Okawa (lists date of death, but has not otherwise been updated)
01:40:14 <zzo38> I don't know how rare it is.
01:40:36 <pikhq> At least it is relative to the Famicom. :)
01:41:35 <oren> Yeah but there are a ton of fake famicoms on the market
01:41:55 <pikhq> Yeah, but not really any that are trying to pass themselves off as real ones.
01:42:05 -!- adu has joined.
01:42:30 <oren> wikipedia now says "was"
01:42:43 -!- oerjan has set topic: RIP Misao Okawa | I'm a fungot trapped in a channel full of weirdos | https://dl.dropboxusercontent.com/u/2023808/wisdom.pdf http://codu.org/logs/_esoteric/ http://tunes.org/~nef/logs/esoteric/.
01:43:21 <pikhq> God, if you consider Famiclones the damned things might be the single most common computing device on the planet.
01:44:05 -!- LordCreepity has joined.
01:44:15 <oren> 6502 - the perfect eternal processor
01:44:45 <oren> (technically they use a modified version)
01:45:10 <zzo38> Famicom uses 6502 with a few traces cut off so that decimal mode won't work.
01:45:24 <zzo38> However, all other functions of NMOS 6502 including unofficial functions still work.
01:45:44 <pikhq> I thought they had decimal mode on there?
01:45:58 <pikhq> I coulda sworn the only modification was sticking some sound hardware on the die.
01:46:21 <pikhq> Oh, no, it is lacking.
01:46:22 <oren> I thought they removed the decimal mode to make room of something
01:46:23 <zzo38> Decimal mode doesn't do anything on Famicom; you can turn it on and off but it doesn't affect operation of arithmetic.
01:46:40 <LordCreepity> has anyone in here ever taken a look at the instruction set of the EDSAC?
01:46:50 <zzo38> oren: No, all they did is cut a few traces so that decimal mode doesn't work. Other than that it actually is a 6502.
01:46:54 <oerjan> hm in 2-3 years there may not be anyone left alive born in the 19th century
01:47:01 <zzo38> They use the same mask.
01:47:49 <pikhq> Ah, yep, they literally removed 5 transistors in the mask.
01:47:55 <oerjan> 115 years old seems a particularly dangerous age
01:48:37 -!- mihow has joined.
01:48:46 <pikhq> There was a patent on the decimal mode that Nintendo did not want to license.
01:48:49 <int-e> oerjan: well 9 "confirmed" people left... https://en.wikipedia.org/wiki/List_of_living_supercentenarians
01:49:08 -!- Lymia has joined.
01:49:35 <shachaf> If I said Θ(f) ≤ Θ(g), would people understand what I mean?
01:49:46 <oren> oerjan: i was recently like o_O upon seeing a pamphlet for a piano recital my grandmother gave in 1944
01:50:33 <oren> shachaf: if that is big theta notation yes. if that is an emoticon then no.
01:51:09 <pikhq> If you look at the die shot you can see that it is literally a 6502's mask with apparently those transistors missing, and some sound hardware. That is really interesting.
01:51:13 <shachaf> But a non-standard use of it.
01:51:21 -!- Lymee has quit (Ping timeout: 256 seconds).
01:51:49 <int-e> shachaf: you could just write f \in O(g) ...
01:51:59 <int-e> (f = O(g), but I dislike that notation)
01:52:12 <shachaf> int-e: Yes, but then I have to remember what o/O/Θ/Ω/ω mean.
01:52:26 <shachaf> It's ridiculous. Why invent a new letter for each of those things?
01:52:37 <int-e> You have to do that anyway, at least the three capital things.
01:52:42 <oren> big theta means a bound above and below right?
01:53:03 <shachaf> It's much easier to remember what </≤/=/≥/> mean.
01:53:22 <int-e> shachaf: not really, when it applies to sets.
01:53:24 <shachaf> Since I use those all the time. Why should this particular preorder get special symbols?
01:54:12 <oren> O above, Omega below, Th both
01:54:13 -!- mihow has quit (Quit: mihow).
01:54:34 <int-e> shachaf: I would go as far as calling Θ(f) ≤ Θ(g) *wrong*, because the standard definition A <= B is a <= b for all a in A and b in B.
01:54:44 -!- oerjan has quit (Quit: Nite).
01:54:53 <shachaf> That definition isn't very standard.
01:55:08 <shachaf> At least I can't remember ever seeing it.
01:55:31 <shachaf> If you want I can use a different symbol instead of Θ. The point is that I'm putting this partial order on the equivalence classes.
01:55:32 <int-e> It's the standard way of extending relations to sets, if there is any standard way at all.
01:55:44 <int-e> shachaf: I would agree more with O(f) \subseteq O(g).
01:56:14 -!- variable has changed nick to trout.
01:56:24 <shachaf> What do you gain over f ∈ O(g) there?
01:56:35 <oren> I should get a LaTeX mode on my IME
01:56:44 <shachaf> ↓{Θ(f)} can mean what O(f) means, though admittedly that notation is less common.
01:56:52 <int-e> shachaf: you can use O(f) = O(g) for f \in \Theta(g)
01:58:08 <shachaf> Oh, I see. You can just use ⊆ instead of ≤ and it gives you the order I want?
01:58:16 <int-e> shachaf: So I think this would accomplish what you wanted: having only one of O/\Theta/\Omega to remember.
01:59:09 <shachaf> So you're saying, O(f) ⊂/⊆/=/⊇/⊃ O(g)
01:59:36 <int-e> I'm not yet sure about o.
02:00:30 <shachaf> "f ∈ o(g)" just means "f ∈ O(g) and f ∉ Θ(g)", doesn't it?
02:00:51 <int-e> mainly because there are non-monotone functions like f(n) alternating between n (for even numbers) and 0...
02:01:23 <int-e> No, f \in o(g) means that the limit of f(n)/g(n) as n goes to infinity is 0.
02:01:44 <shachaf> Hmm. Maybe my other order was too simplistic too.
02:02:13 <int-e> Which I currently believe is stronger that f \in O(g) and g \notin O(f).
02:02:57 <int-e> taking that alternating function as f, and g(n) = n.
02:06:24 <shachaf> What are you saying about these f and g?
02:06:53 <int-e> that f \in O(g) and g \notin O(g) and f \notin o(g).
02:09:39 <int-e> Which demonstrates that f \in o(g) is different from O(f) \subsetneq O(g).
02:10:11 <int-e> Sorry, I didn't make the definitions.
02:10:22 <shachaf> You should be in #-lens or #-blah or one of the other channels that I was talking about this.
02:11:43 -!- LordCreepity has quit (Quit: Leaving).
02:12:19 -!- LordCreepity has joined.
02:14:30 <int-e> Perhaps, but I'm on too many channels already, and neither -blah nor -lens really interest me.
02:28:18 <Sgeo> shachaf: Prismata is having an April Fools Day event
02:28:24 <Sgeo> With 9 fake new units and 1 real new unit
02:34:01 <zzo38> I must have made a mistake in the .XI loading code because it doesn't quite work properly.
02:38:02 -!- LordCreepity has quit (Quit: Page closed).
02:43:41 -!- LordCreepity has joined.
02:43:50 -!- LordCreepity has quit (Client Quit).
02:51:33 <zzo38> Now all of the updates are on the Redmine too.
02:55:33 -!- Phantom_Hoover has quit (Read error: Connection reset by peer).
02:55:46 <Sgeo> I love /r/todayilearned's CSS
02:56:28 <Sgeo> They're making every comment look like it's saying conspiracy stuff
02:58:10 -!- infinitymaster has joined.
02:58:58 <infinitymaster> !zjoust Iron_Will_and_a_Clear_Conscience >(-)*15>(+)*15(>++>--)*3>([(+)*15[-]]>)*21
02:58:59 <zemhill_> infinitymaster.Iron_Will_and_a_Clear_Conscience: points -3.40, score 17.03, rank 35/47
03:14:44 -!- MoALTz has joined.
03:16:21 -!- heroux has quit (Ping timeout: 256 seconds).
03:16:55 -!- heroux has joined.
03:17:14 -!- MoALTz__ has quit (Ping timeout: 252 seconds).
03:30:46 -!- GeekDude has quit (Ping timeout: 264 seconds).
03:31:57 -!- Lyrr has joined.
03:32:03 -!- GeekDude has joined.
03:36:02 <Sgeo> Is it weird that I enjoy Internet April Fools so much?
03:39:37 -!- MDude has changed nick to MDream.
03:40:42 -!- vodkode_ has quit (Ping timeout: 248 seconds).
03:41:18 -!- Lyrr has left.
03:49:05 -!- GeekDude has quit (Ping timeout: 265 seconds).
03:49:18 <zzo38> quintopia: What is thx tdh?
03:49:47 -!- GeekDude has joined.
03:50:22 -!- vodkode_ has joined.
03:51:46 -!- hjulle has joined.
03:54:17 -!- oren has quit (Quit: Lost terminal).
03:56:58 <Sgeo> Tagpro has an April Fools Day event, but it only runs the first 15 minutes of every hour
03:57:16 <Sgeo> It is driving me crazy, I'm timing my life around it right now
03:57:40 <Sgeo> Which, I think, involves me playing less tagpro than usual, ironically enough
03:59:19 -!- adu has quit (Quit: adu).
04:07:58 -!- doesthiswork has quit (Quit: Leaving.).
04:15:02 -!- adu has joined.
04:15:16 -!- adu has quit (Client Quit).
04:18:57 -!- GeekDude has quit (Quit: {{{}}{{{}}{{}}}{{}}} (www.adiirc.com)).
04:22:56 -!- Lymia has quit (Ping timeout: 265 seconds).
04:25:23 -!- adu has joined.
04:29:04 -!- Decim has joined.
04:30:16 -!- vodkode_ has quit (Ping timeout: 245 seconds).
04:39:16 -!- vodkode_ has joined.
04:48:06 -!- infinitymaster has quit (Quit: Leaving...).
04:49:34 -!- MoALTz_ has joined.
04:52:18 -!- MoALTz has quit (Ping timeout: 246 seconds).
04:57:05 -!- adu has quit (Quit: adu).
05:22:47 -!- vodkode_ has quit (Ping timeout: 272 seconds).
05:23:53 <Sgeo> I think my graphics card's video decoding is broken
05:24:06 <Sgeo> Videos stopped working for me until I told Chrome not to use hardware decoding
05:27:40 -!- adu has joined.
05:41:16 <Sgeo> https://com.google/
05:41:35 -!- vodkode_ has joined.
05:48:29 -!- Welcome has joined.
05:48:29 -!- Decim has quit (Read error: Connection reset by peer).
05:55:37 <Sgeo> "Think of Smartbox as Google’s attempt to reinvent physical mail. It has smart folders, filters, and even apps. Oh, and you can take Smartbox with you, wherever you go."
05:55:40 <Sgeo> Ugh I want this for real
06:04:41 -!- zadock has quit (Quit: Leaving).
06:19:31 -!- adu has quit (Quit: adu).
06:25:04 -!- Welcome has quit (Ping timeout: 255 seconds).
06:47:22 -!- zadock has joined.
07:11:05 -!- trout has quit (Ping timeout: 272 seconds).
07:30:52 -!- Lymia has joined.
07:48:32 -!- Patashu has joined.
07:57:10 <shachaf> λ> typeRep (Proxy :: Proxy A) == typeRep (Proxy :: Proxy B)
07:57:10 <shachaf> λ> typeRep (Proxy :: Proxy (Proxy A)) == typeRep (Proxy :: Proxy (Proxy B))
07:57:32 <shachaf> int-e, oerjan: Any ideas for what to do with that?
08:03:40 -!- cpressey has joined.
08:03:58 <cpressey> fungot: did you enjoy your outage?
08:03:58 <fungot> cpressey: scheffig is the scheme48 native compiler coming along? ( sorry, i didn't
08:06:57 <izabera> http://home.web.cern.ch/about/updates/2015/04/cern-researchers-confirm-existence-force
08:16:41 <b_jonas> fungot, do you like april?
08:16:41 <fungot> b_jonas: what did you do
08:21:02 -!- shikhin has joined.
08:21:09 <mroman> b_jonas played a 1. April prank on fungot!
08:21:09 <fungot> mroman: i know im an asshole.
08:23:01 <mroman> fungot: Well then you deserve the prank.
08:23:02 <fungot> mroman: ok, here's a *great* example. ( there was a roshambo bot called iocane. :) the interpreter i've used.
08:36:41 -!- lambdabot has quit (Remote host closed the connection).
08:42:33 -!- lambdabot has joined.
08:43:34 -!- vodkode_ has quit (Ping timeout: 252 seconds).
08:54:25 <izabera> https://imasheep.hurrdurr.org/
08:54:36 <izabera> kernel.org redirects there ^^
09:03:31 <izabera> it's because linux 4.0 is codenamed hurr durr ima sheep
09:05:06 <izabera> linus started a test poll on google+ and one of the options was hurr durr ima sheep ^^
09:06:26 <cpressey> https://git.kernel.org/cgit/linux/kernel/git/torvalds/linux.git/commit/?id=c517d838eb7d07bbe9507871fab3931deccff539
09:06:26 <lifthrasiir> http://git.kernel.org/cgit/linux/kernel/git/torvalds/linux.git/commit/?id=c517d838eb7d07bbe9507871fab3931deccff539
09:11:59 <b_jonas> oh, so that's why it redirects!
09:12:11 <b_jonas> and the title has changed too
09:12:17 <b_jonas> it says "The Hurr Durr Archives"
09:16:43 -!- lambdabot has quit (Quit: ...).
09:21:06 -!- zzo38 has quit (Ping timeout: 246 seconds).
09:21:53 -!- lambdabot has joined.
09:49:24 <Jafet> https://en.wikipedia.org/wiki/List_of_Linux_kernel_names
09:51:19 <cpressey> those need to be displayed prominently upon boot
10:10:39 <int-e> shachaf: well, are those types actually different so that it breaks gcast in connection with a type family?
10:10:59 <shachaf> They're different types with different kinds.
10:11:15 <shachaf> Which is why Proxy gets different TypeReps.
10:13:37 <int-e> So it doesn't break gcast then.
10:13:51 <int-e> I *believe* that's fine.
10:14:40 <shachaf> I can't think of a way to write unsafeCoerce with it, at least.
10:18:16 <shachaf> A is () :: *, b is () :: Constraint
10:20:06 <int-e> typeRep (Proxy :: Proxy (Proxy :: * -> *)) == typeRep (Proxy :: Proxy (Proxy :: (* -> *) -> *)) is also true.
10:21:17 <int-e> Sorry, I have 7.10.1 installed but 7.8.3 is still my default.
10:26:34 -!- boily has joined.
11:06:50 -!- Phantom_Hoover has joined.
11:20:54 <cpressey> all i'm saying is that if we have codata we might as well redefine our entire foundation of mathematics to use it. clearly, 1/0 is a corational. clearly, - can be defined over the corationals, and 1/0 - 1/0 = 0.
11:20:57 -!- roasted42 has joined.
11:21:24 -!- roasted42 has quit (Changing host).
11:21:24 -!- roasted42 has joined.
11:21:24 -!- roasted42 has changed nick to TheM4ch1n3.
11:23:41 -!- boily has quit (Quit: IDENTIFIABLE CHICKEN).
11:23:53 <int-e> cpressey: your use of "clearly" is clearly wrong, hth.
11:24:43 <cpressey> int-e: you didn't find that entertaining?
11:25:19 <int-e> No, because I tried to make sense of "1/0 is a corational".
11:25:45 <int-e> Failing that, annoyance was the dominating reaction.
11:27:23 <cpressey> you make it sound like your failure to make sense of a concept is a bad thing
11:29:01 <int-e> Sorry I tend to overanalyze things.
11:31:51 <int-e> oh my. https://github.com/lambdabot/lambdabot/issues/114
11:33:15 <int-e> I think I'll wait a day before closing that one :P
11:40:51 -!- Patashu has quit (Ping timeout: 256 seconds).
11:52:54 -!- Sgeo has quit (Ping timeout: 250 seconds).
11:59:43 -!- oerjan has joined.
12:22:47 -!- shikhin has quit (Ping timeout: 256 seconds).
12:25:29 <oerjan> <Sgeo> https://com.google/ <-- it doesn't change the link targets DISAPPOINTED
12:26:53 <lambdabot> Not in scope: type constructor or class ‘A’
12:27:15 <oerjan> typeRep (Proxy :: Proxy A) == typeRep (Proxy :: Proxy B)
12:27:41 <oerjan> > typeRep (Proxy :: Proxy (() :: *)) == typeRep (Proxy :: Proxy (() :: Constraint))
12:27:43 <lambdabot> Not in scope: type constructor or class ‘Constraint’
12:27:43 <lambdabot> Perhaps you meant ‘Contains’ (imported from Control.Lens)
12:28:57 <oerjan> shachaf: i cannot say, i haven't installed 7.10 yet. what is preventing you from just slotting it into one of the versions at http://oerjan.nvg.org/haskell/TypeableExploits ?
12:29:15 <oerjan> > typeRep (Proxy :: Proxy (() :: *))
12:30:14 <oerjan> int-e: import GHC.Exts.Constraint plz twh
12:31:34 <oerjan> pesky sleeping americans
12:32:26 <int-e> The real problem is that GHC.Exts is not trustworthy. So I have to wrap it... haven't bothered yet.
12:32:53 <int-e> (It's easy, that's what lambdabot-trusted is for. But it
12:33:14 <int-e> 's not limited to changing a single line in Pristine.hs.)
12:33:17 <oerjan> hm they should make a GHC.Exts.Safe then
12:34:11 <int-e> https://ghc.haskell.org/trac/ghc/ticket/9724
12:34:48 <int-e> that one fell through the cracks (I forgot about it myself, too)
12:37:15 <int-e> silly. https://com.google/
12:37:35 <oerjan> int-e: 3rd time's the charm
12:38:06 <lambdabot> monochrom says: Welcome to #haskell, where your questions are answered in contrapuntal fugues.
12:38:39 <HackEgo> 475) <monqy> mmm these music samples are still so tasteful \ 552) <oerjan> i am sorry to disappoint you, but my musical taste is on the side abba, verdi, and celine dion. i know this may not be popular and that you would have preferred me to be a satanist. \ 1235) <fungot> boily: the proc is invoked. before or after the evaluator transfers control
12:42:51 <int-e> anyway ... I need to stop procrastinating, there's a deadline (review for a conference, so not a flexible one) today.
12:46:08 -!- GeekDude has joined.
12:55:56 <cpressey> "foo is a bar" is an inductive definition; "if B is a bar, expr(B) is a bar" is an inductive definition; if I and J are inductive definitions, "I; J" is an inductive definition
12:57:48 -!- GeekDude has changed nick to GibVent.
13:01:12 <cpressey> that allows non-well-founded definitions, & could stand to be improved
13:02:51 <oerjan> if it's non-well-founded surely it must be coinductive.
13:04:00 * oerjan might be half joking there
13:04:10 <int-e> Perhaps y'all should apply soundiness to math: http://soundiness.org/documents/InDefense2.pdf
13:04:27 <b_jonas> I've seen very few april's fool things today
13:04:51 <int-e> (That soundiness thing isn't an April's fool, I'm afraid.)
13:05:23 <cpressey> oh they have their own domain now do they?
13:05:39 <cpressey> "well, that escalated" i can't do it
13:07:23 <cpressey> they have a Soundiness Statement Generator
13:08:24 <cpressey> In case you are too lazy to write, yourself, "Our analysis does not soundly handle X, Y and Z"
13:09:40 <cpressey> perhaps the next step is for them to write a Soundiness Analyzer which takes your analyzer and tells you just in what ways it is unsound
13:09:52 <int-e> We present a soundy (i.e., unsound and incomplete) analysis of Brainfuck program termination, building on previous work in random number generation.
13:11:23 * oerjan briefly thinks it's a shame healthy ends with y already
13:11:42 <oerjan> i guess one could reverse the construction
13:12:22 -!- shikhin has joined.
13:12:36 <int-e> Ooh. Right, "sound" is a noun. So a soundy thing would have to make noises. They do that quite successfully, I suppose.
13:13:26 <oerjan> int-e: a very smarty deduction
13:15:19 <oerjan> is there any way to get the type (() :: Constraint) without mentioning Constraint
13:15:55 -!- SopaXorzTaker has joined.
13:15:59 -!- SopaXorzTaker has quit (Remote host closed the connection).
13:16:56 -!- SopaXorzTaker has joined.
13:17:15 <cpressey> i can't help thinking that if people were more used to the idea of a subset of a programming language, the whole soundiness thing would be moot. your analysis is sound on some subset of the language, that's all. not a hard concept, is it?
13:17:48 -!- ProofTechnique has quit (Ping timeout: 272 seconds).
13:18:16 <cpressey> but people aren't UNused to that idea either, so i don't know. the various sub-industries, each has their own weirdness
13:18:48 <int-e> the weird is strong in oerjan.
13:19:13 <cpressey> HPC folks treat "code" as a count noun while almost everyone else treat it as a mass noun
13:22:16 <int-e> Hmm, I would've expected that of cryptographers, but not of HPC.
13:23:13 <int-e> Or cryptologists, more generally.
13:23:23 <oerjan> :k forall a. (Ord Int,a) ~ (Ord Int,()) => Proxy a
13:23:24 <lambdabot> The second argument of a tuple should have kind ‘Constraint’,
13:23:51 <oerjan> it looks impossible to get it to infer that () is a Constraint without putting it on explicitly :(
13:26:19 * oerjan hopefully checks if they got the Platform out yet
13:40:13 <cpressey> seriously though i should probably look into codata more because it seems like you could do some really interesting things with reified codata
13:42:25 -!- ProofTechnique has joined.
13:43:10 <oerjan> It's annoying when you start writing an answer to a 1 hour old stackoverflow question and someone else beats you by 10 seconds :(
13:44:02 -!- shikhin has quit (Ping timeout: 244 seconds).
13:44:21 <oerjan> well it _was_ a better answer than i was writing.
13:44:24 <mroman> oerjan: You're just being a copycat!
13:45:06 <cpressey> they probably could've hopped on IRC and gotten an answer in 5 minutes (if they were willing to put up with the belittling)
13:45:44 <oerjan> maybe. it was a little subtle.
13:45:46 <cpressey> and the "why do you want to do that, anyway?"
13:46:28 <oerjan> it's actually sort of a type bug in the API interface of the haskeline interface, that means you have to give a stupid type annotation for a type you're about to throw away...
13:47:37 <oerjan> http://stackoverflow.com/questions/29390884/ambiguous-type-variable-with-haskeline-auto-completion#29392412 fwiw
13:48:28 <mroman> fungot: Can you cook with a water cooker?
13:48:28 <fungot> mroman: neither one of these days. but rack is close enough to programming any features you want, and what we still need more optimizations.
13:48:52 <oerjan> i am not sure fungot understands the concept of water
13:48:53 <fungot> oerjan: esoerl for esoteric and erlang maybe?)
13:49:00 <oerjan> no, fungot, that is not it.
13:49:00 <fungot> oerjan: you just don't take them if you used block for begin) depending on the ordering of the for clauses...)
13:49:47 <mroman> `learn Water is a squishy substance that creeps along the floor and can suddenly fall from the heavens.
13:49:55 <HackEgo> Learned 'water': Water is a squishy substance that creeps along the floor and can suddenly fall from the heavens.
13:50:07 <cpressey> ah well, the best part of stackoverflow is the list of trending questions on the right
13:56:44 <mroman> You can get a fully functional kitchen with 200CHF.
13:57:28 <mroman> That is, if you hand wash your dishes .
13:57:51 <mroman> fungot: Do you hand wash your dishes?
13:57:51 <fungot> mroman: http://paste.lisp.org/ display/ fnord
13:58:04 <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
13:58:23 <fungot> Selected style: darwin (Books by Charles Darwin -- you know, that evilution guy)
13:58:35 <mroman> fungot: Your thoughts about morphic fields?
13:58:36 <fungot> mroman: dr., on corals fnord themselves." " 27. on this account i went in yesterday, and was recopied before being sent to/ lacrymal glands. this salt was first exported in 1830: in one mid-styled plant, but was withdrawn on/ appointment :) royal commissioners, that ordinary doctors know little or nothing to tell you a fnord, not by means :) its ferment, 94, 95, and generally to/ male.
13:58:44 <mroman> morphic fields even explain evolution!
13:59:42 <HackEgo> /home/hackbot/hackbot.hg/multibot_cmds/lib/limits: line 5: exec: morphic: not found
14:02:33 -!- shikhin has joined.
14:03:20 <fungot> Selected style: irc (IRC logs of freenode/#esoteric, freenode/#scheme and ircnet/#douglasadams)
14:03:32 <mroman> fungot: Who's douglas adams?
14:03:33 <fungot> mroman: right... it's gonna be.
14:06:20 -!- `^_^v has joined.
14:20:20 -!- shikhin has quit (Ping timeout: 265 seconds).
14:21:04 -!- MDream has changed nick to MDude.
14:35:55 <quintopia> zom3one point me to the best pranks
14:36:44 <oerjan> see #esoteric logs hth
14:36:58 <oerjan> i mean, http://home.web.cern.ch/about/updates/2015/04/cern-researchers-confirm-existence-force
14:39:07 <oerjan> too critical for the world
14:42:08 <oerjan> oh typeRep already takes a Proxy of course
14:42:55 <oerjan> ok that does seem like unsafeCoerce is hard to get from this.
14:45:19 <oerjan> it's too damn hard to find flags from inside ghci
15:02:24 -!- SopaXorzTaker has quit (Remote host closed the connection).
15:16:14 -!- zadock has quit (Quit: Leaving).
15:21:17 <oerjan> in this case it was -fprint-explicit-kinds
15:21:56 -!- TheM4ch1n3 has quit (Ping timeout: 255 seconds).
15:22:23 -!- clog has quit (Ping timeout: 264 seconds).
15:24:48 <oerjan> <int-e> oh my. https://github.com/lambdabot/lambdabot/issues/114 <-- you just have to tell them the truth; that haskell has been surpassed by befunge for this use.
15:30:26 -!- clog has joined.
15:37:37 <cpressey> fungot is actually a UFAI that is simulating you. true fact
15:37:37 <fungot> cpressey: it's done there just to show that
15:37:44 -!- roasted42 has joined.
15:38:09 -!- roasted42 has quit (Changing host).
15:38:09 -!- roasted42 has joined.
15:38:09 -!- roasted42 has changed nick to TheM4ch1n3.
15:50:03 <FireFly> fungot: what is your favourite joke today?
15:50:03 <fungot> FireFly: given a list, a sublist isn't the same as its argument a quantified noun
15:50:34 <FireFly> fungot: I'm.. I'm not sure if I get it
15:50:35 <fungot> FireFly: it does seem to be fnord.
15:52:22 -!- SopaXorzTaker has joined.
15:52:54 -!- shikhin has joined.
15:53:46 <cpressey> look, if the singularity told you a joke, do you think you'd be able to understand it? of course you wouldn't.
15:54:17 <cpressey> mroman: well, fungot, obviously
15:54:17 <fungot> cpressey: most of the stuff i do at work, and it seems i do :-o dear me.
15:58:14 -!- bb010g has quit (Quit: Connection closed for inactivity).
15:59:05 <int-e> oerjan: how about this? (I commented on that #114)
16:01:42 -!- variable has joined.
16:04:27 <int-e> oerjan: pity, I can't assign the issue to the lambdabot organization :)
16:10:52 <pikhq> http://com.google/
16:19:04 -!- cpressey has quit (Quit: leaving).
16:25:32 -!- ais523 has joined.
16:33:01 <ais523> is there any particular set of april 1 festivities I should be looking at?
16:33:32 <oerjan> well people keep linking http://com.google/
16:34:28 <ais523> oh, Google got their TLD after all?
16:34:43 <ais523> IIRC they applied for like five or six TLDs for internal use only
16:35:25 <pikhq> com.google's their first use of it for much of anything.
16:35:32 <pikhq> (publicly, at least)
16:36:25 <pikhq> Microsoft announced MS-DOS Mobile.
16:42:02 <pikhq> Oh yeah, gentoo.org was pretty good too.
16:43:29 <pikhq> And it'll be to zzo's liking too...
16:43:36 <pikhq> gopher://gopher.gentoo.org/
16:45:48 -!- oerjan has quit (Quit: Latër).
16:46:43 -!- Koen_ has joined.
16:51:54 -!- ais523 has quit.
16:52:04 -!- ais523 has joined.
16:53:14 <int-e> pikhq: I'm not sure, serving html + css + javascript over gopher just doesn't feel right
16:53:46 <int-e> (the only thing that's "proper" gopher are the directory listings)
16:54:31 -!- ais523 has quit (Client Quit).
16:54:36 -!- callforjudgement has joined.
16:55:22 -!- callforjudgement has changed nick to ais523.
16:58:47 -!- mihow has joined.
17:24:10 -!- mihow has quit (Ping timeout: 272 seconds).
17:28:11 -!- callforjudgement has joined.
17:28:22 -!- ais523 has quit (Remote host closed the connection).
17:28:35 -!- callforjudgement has changed nick to ais523.
17:30:21 -!- shikhin has quit (Ping timeout: 256 seconds).
17:33:07 -!- shikhin has joined.
17:33:31 -!- mihow has joined.
17:35:29 -!- ais523 has quit (Remote host closed the connection).
17:35:38 -!- ais523 has joined.
17:39:11 -!- TheM4ch1n3 has quit (Ping timeout: 255 seconds).
17:39:40 -!- ^v^v has quit (Read error: Connection reset by peer).
17:40:07 -!- ^v^v has joined.
17:41:45 <HackEgo> [wiki] [[Language list]] http://esolangs.org/w/index.php?diff=42254&oldid=42233 * Rottytooth * (+15) /* T */ added Time Out
17:42:16 -!- zadock has joined.
17:43:06 -!- callforjudgement has joined.
17:43:20 -!- ais523 has quit (Disconnected by services).
17:43:28 -!- callforjudgement has changed nick to ais523.
17:45:33 -!- roasted42 has joined.
17:45:47 -!- roasted42 has quit (Changing host).
17:45:47 -!- roasted42 has joined.
17:45:48 -!- roasted42 has changed nick to TheM4ch1n3.
17:46:43 -!- SopaXorzTaker has quit (Ping timeout: 265 seconds).
17:50:52 -!- callforjudgement has joined.
17:54:03 -!- ais523 has quit (Ping timeout: 248 seconds).
17:54:11 -!- callforjudgement has changed nick to ais523.
18:03:39 <int-e> hehe. "reason for data loss: guru meditation #00000025.65045338 press left mouse button to continue"
18:04:14 -!- oren has joined.
18:14:53 -!- oren has quit (Read error: Connection reset by peer).
18:16:12 -!- ais523 has quit (Read error: Connection reset by peer).
18:16:28 -!- ais523 has joined.
18:16:35 -!- ais523 has quit (Changing host).
18:16:35 -!- ais523 has joined.
18:41:19 -!- oren has joined.
18:45:27 -!- ais523 has quit (Read error: Connection reset by peer).
18:45:38 -!- ais523 has joined.
18:48:51 -!- ais523 has quit (Read error: Connection reset by peer).
18:49:03 -!- ais523 has joined.
18:49:20 -!- TheM4ch1n3 has quit (Quit: l8r, about 30m).
18:50:51 -!- variable has changed nick to trout.
18:59:15 -!- shikhin_ has joined.
19:02:36 -!- shikhin has quit (Ping timeout: 265 seconds).
19:04:43 -!- shikhin_ has changed nick to shikhin.
19:11:16 -!- oren has quit (Quit: Lost terminal).
19:11:58 <shachaf> oerjan: All of the unsafeCoerces I know how to write involve taking the TypeRep of something other than the problematic type itself.
19:12:28 -!- cpressey has joined.
19:12:29 <shachaf> E.g. F (Proxy A) vs. F (Proxy B), which is really F (Proxy * A) vs. F (Proxy Constraint B)
19:16:06 <cpressey> ais523: a coworker of mine really liked the products ThinkGeek is advertising today, but I failed to distinguish them from their regular fare
19:16:28 <ais523> cpressey: I seem to remember that at least one of their joke products was popular enough that they figured out how to manufacture it
19:16:54 -!- nys has joined.
19:26:39 -!- cpressey has quit (Ping timeout: 256 seconds).
19:27:27 -!- cpressey has joined.
19:30:01 <cpressey> fungot: want to hear a joke? not april fool's-related, i promise
19:30:01 <fungot> cpressey: gimme link! _") will put a string into an s-exp ( the kind which is planted in the garden
19:30:58 <cpressey> great, now i have to write it into a pastebin somewhere i guess
19:31:31 <ais523> this is what happens when you ask fungot things, sometimes it gives you an answer you don't want
19:31:31 <fungot> ais523: i only found at the top level, should a woodchuck chuck if a woodchuck could chuck and would chuck some amount of attention to the details.
19:31:32 <FireFly> fungot: do you plant strings in your garden?
19:31:33 <fungot> FireFly: that's fine. that's what i mean is, you can probably get a good idea if it still sleeps
19:31:59 <cpressey> except now i'm distracted about thinkinzg about what kind of s-exps are planted in the garden.
19:32:04 <cpressey> some kind of riddle, obviously
19:32:09 <ais523> the sort that you use to protect strings
19:32:49 <quintopia> i kind of want to implement tge EnCounter using fitbit's data streams
19:32:50 <int-e> I find the idea of "chucking some amount of attention to the details" quite eery.
19:32:53 <cpressey> support for some sort of convoluted scarecrow, maybe
19:32:58 <fungot> int-e: not many resources in scheme48's vm are shared, other than miranda and unlambda?
19:33:18 <int-e> fungot: you got that right
19:33:18 <fungot> int-e: prefer html? if so, that's fine, i'm sure
19:33:36 <ais523> cpressey: now you have to paste your joke in HTML, for int-e
19:33:57 <int-e> fungot: I want plain text.
19:33:57 <fungot> int-e: even though i reported it. multiple times. :p they claim that not wanting a on the end
19:34:22 <int-e> I guess that means I'm being overruled. By a bot. *pouts*
19:35:07 <b_jonas> fungot, have you ever cut your finger when trying to wash up a kitchen knife and you held the blade to wash the handle?
19:35:07 <fungot> b_jonas: or get a stamp. like " hey, i'm using safari 3.1.1
19:35:32 <b_jonas> fungot: on what operating system?
19:35:32 <fungot> b_jonas: i don't see where it transforms non-tail calls into tail calls if possible. don't force awkward programs on yourself to do some ffi stuff with it and need to be
19:37:06 <olsner> fungot: need to be what?
19:37:07 <fungot> olsner: ( letrec ( ( a ()
19:37:14 <int-e> fungot: shy gypsy slyly spryly tryst by my crypt
19:37:14 <fungot> olsner: with the blue squares on the cover of the book is solely based on scheme
19:37:14 <fungot> int-e: here's my article in english ( as in, a java system doesn't map nicely onto scheme.
19:41:00 <HackEgo> /home/hackbot/hackbot.hg/multibot_cmds/lib/limits: line 5: exec: thankx: not found
19:41:01 -!- cpressey has quit (Ping timeout: 252 seconds).
19:42:00 <HackEgo> /home/hackbot/hackbot.hg/multibot_cmds/lib/limits: line 5: exec: found: not found
19:42:51 -!- cpressey has joined.
19:42:59 <int-e> This might become worse than edirc.
19:43:29 <HackEgo> /home/hackbot/hackbot.hg/multibot_cmds/lib/limits: line 5: exec: thanks,: not found
19:43:57 <HackEgo> Thanks, Thursday. Thursday.
19:44:03 <ais523> haha, I was wondering what would happen if the argument was shorter than 2 chars
19:44:12 <HackEgo> Thanks, biblegia. Thiblegia.
19:44:31 <ais523> hmm, is it picking random `words?
19:44:35 <HackEgo> cary ency acet mare brodworf aam jaokson overe paliquitin marta sre oee ymblicl hical ric smarque fini alto fig nisti
19:45:00 <HackEgo> -rwxr-xr-x 1 5000 0 18 Jan 6 17:40 bin/`
19:48:42 -!- hjulle has quit (Ping timeout: 250 seconds).
20:00:29 -!- callforjudgement has joined.
20:01:09 -!- Patashu has joined.
20:02:45 -!- ais523 has quit (Ping timeout: 244 seconds).
20:02:46 -!- scarf has joined.
20:02:52 -!- callforjudgement has quit (Read error: Connection reset by peer).
20:07:44 <cpressey> consider a universal turing machine U; it reads a turing machine description T, and simulates it, but while it is simulating it it also searches for a proof that T does not terminate; U terminates if T terminates OR if U finds a proof.
20:08:30 <scarf> cpressey: we already have basically that on the wiki, I think
20:08:34 -!- scarf has changed nick to ais523.
20:08:50 <ais523> leading to a language which contains no provably nonterminating programs
20:08:55 -!- mihow has quit (Quit: mihow).
20:09:20 <ais523> but which is still probably TC despite that?
20:09:56 <cpressey> it's certainly TC, it just terminates "more often" than a naive UTM does
20:14:45 -!- cpressey has quit (Ping timeout: 252 seconds).
20:17:47 -!- MDude has quit (Ping timeout: 245 seconds).
20:17:58 -!- ais523 has changed nick to no.
20:18:01 -!- no has changed nick to ais523.
20:22:54 -!- cpressey has joined.
20:23:34 <cpressey> to make it strictly-dotted-i's-crossed-t's-TC, make it loop forever once it's found the proof
20:24:11 -!- Patashu has quit (Ping timeout: 264 seconds).
20:24:22 <cpressey> but if you're willing to accept "It doesn't terminate and here's why" as a substitute for not terminating, it's definitely close enough
20:24:39 <ais523> cpressey: ah, that's a slightly different idea from the language I'm thinking of
20:25:17 <cpressey> i don't know which one you're thinking of, but it did sound similar... only non-provably-non-terminating programs don't terminate
20:25:24 <ais523> cpressey: http://esolangs.org/wiki/Onoz
20:26:17 <cpressey> btw, it occurs to me that if we have flexibility in how turing machines are defined, we can't avoid flexibility in what counts as "turing-complete"
20:26:41 <ais523> "turing-complete" is a badly defined concept as-is
20:26:48 <ais523> there are some things that definitely fall on one side or the other of the line
20:26:52 <ais523> but there are also things that are much clsoer
20:28:03 <cpressey> well, "does the TM 'take input'" is one of the big obvious points of flexibility
20:28:39 <ais523> we have the phrase "bf-complete"
20:28:45 -!- FrogLeg has joined.
20:28:46 <cpressey> and yeah, onoz is... close... but not exactly what i was thinking... i think
20:29:00 <ais523> right, it doesn't match your description exactly
20:29:40 <cpressey> ok, so, brainfuck <-> turing machines with input and output tapes
20:31:24 <cpressey> well... ok... maybe not; what i was thinking of was unary. i think that just affects complexity, not computability
20:31:37 <cpressey> but wow does it ever affect complexity, ftr
20:31:53 -!- ais523 has quit.
20:32:07 -!- ais523 has joined.
20:33:38 -!- ais523 has quit (Read error: Connection reset by peer).
20:33:47 -!- ais523 has joined.
20:36:58 <cpressey> anyway, now that i have the construction, all i need to do is... find the proof it's used in
20:38:59 -!- FrogLeg has quit (Excess Flood).
20:39:23 -!- FrogLeg has joined.
20:39:56 -!- nycs has joined.
20:41:52 -!- `^_^v has quit (Ping timeout: 246 seconds).
20:42:02 -!- mihow has joined.
20:53:48 <cpressey> I do not understand this "GLooP" language. none of the wikis describe it (except to say it goes along with BLooP and FLooP.) the CLooP page seems to suggest it has an infinite parallel operation.
20:54:58 -!- FrogLeg has set topic: This Topic is now Hot. B===D~ B===D~ B===D~ B===D~ B===D~.
20:56:56 <cpressey> specifically, I don't see what the conditions for CLooP's infinite parallel "join" are. do all the (infinite number of) "threads" have to terminate?
20:57:03 <ais523> cpressey: GLooP was defined by Douglas Hofstader as "more powerful than FLooP, but computable"
20:57:09 <cpressey> if not, how many threads have to terminate?
20:57:13 <ais523> he concluded it didn't exist
20:57:35 <cpressey> if it's "all threads", the CLooP implementation of http://esolangs.org/wiki/Brainhype will... just not work
20:57:45 -!- ais523 has quit (Read error: Connection reset by peer).
20:58:04 -!- ais523 has joined.
20:58:48 <ais523> can someone put the topic back to something containing the log URLs?
20:58:53 <ais523> I tried to but my client crashed
20:59:14 -!- cpressey has set topic: RIP Misao Okawa | I'm a fungot trapped in a channel full of weirdos | https://dl.dropboxusercontent.com/u/2023808/wisdom.pdf http://codu.org/logs/_esoteric/.
20:59:15 -!- FrogLeg has set topic: http://meatspin.com/.
20:59:19 <ais523> also, FrogLeg, Freenode has a rule about being open about logging in channels
20:59:22 -!- cpressey has set topic: RIP Misao Okawa | I'm a fungot trapped in a channel full of weirdos | https://dl.dropboxusercontent.com/u/2023808/wisdom.pdf http://codu.org/logs/_esoteric/.
20:59:24 -!- ChanServ has set channel mode: +o ais523.
20:59:31 -!- ais523 has set channel mode: +b FrogLeg!*@*.
20:59:32 -!- ais523 has kicked FrogLeg trolling.
20:59:34 -!- shikhin has quit (Ping timeout: 265 seconds).
20:59:38 -!- ais523 has set channel mode: -o ais523.
20:59:57 -!- cpressey has set topic: RIP Misao Okawa | I'm a fungot trapped in a channel full of weirdos | https://dl.dropboxusercontent.com/u/2023808/wisdom.pdf http://codu.org/logs/_esoteric/ http://tunes.org/~nef/logs/esoteric/.
20:59:59 <ais523> benefit of the doubt with one relatively harmless topic change
21:00:13 <ais523> no benefit of the doubt with shock site links
21:01:30 <cpressey> ais523: so DH *defined* GLooP to be "more powerful" without actually, uh, constructively defining how it was intended to go about that?
21:01:44 <cpressey> that would explain absence of descriptions of it
21:02:34 <ais523> cpressey: I think he intended it to not exist
21:02:41 <ais523> and brought it up as a teaser
21:04:03 -!- shikhin has joined.
21:04:09 <cpressey> i posit that CLooP's "GLooP mode" does not actually add any more power to the language, and specifically, it can't be used to implement Brainhype, and i guess i'll edit the page at some point if i feel like putting in the effort, ugh
21:04:21 <Taneb> It has been a while since I have read GEB
21:04:28 <int-e> cpressey: that non-termination proving TM is interesting, but it still runs afoul of diagonalization. (let U(x,y) be a TM that terminates with 1 if the TM x accepts y, and with 0 if it could prove that x(y) does not terminate. Then consider M(x) that first executes U(x,x), terminates if it halts with 0, and loops forever if it halts with 1. Then U(M,M) will not terminate, assuming that th...
21:04:34 <int-e> ...e formal system used by U for proving nontermination is sound.
21:05:05 <int-e> I guess you have the escape hatch that soundness of that system is not provable
21:05:55 <int-e> But in that sense we cannot hope to prove anything of interest (so, at least as strong as Peano arithmetic) at all.
21:09:00 -!- cpressey has quit (Ping timeout: 272 seconds).
21:09:54 -!- cpressey has joined.
21:12:04 -!- oerjan has joined.
21:12:41 <cpressey> int-e: I'm not sure what you're getting at
21:13:23 <cpressey> As I said, if T doesn't terminate, and there if no proof of this fact, U doesn't terminate
21:13:23 -!- ProofTechnique has quit (Ping timeout: 250 seconds).
21:13:47 <int-e> cpressey: "only non-provably-non-terminating programs don't terminate" <-- the notion of nonprovability also exists on a meta level.
21:14:50 <cpressey> I have no idea what you mean by "a meta level", sorry.
21:15:01 <cpressey> My wording there may've been sloppy
21:15:05 -!- augur_ has quit (Ping timeout: 244 seconds).
21:15:29 <int-e> It's the same kind of reasoning that says that Gödel's sentence is false in the standard model of Peano arithmetic, provided that Peano arithmetic is consistent.
21:15:40 <cpressey> The only T's for which U doesn't terminate are those for which U cannot find a proof (of T's non-termination)
21:17:00 <cpressey> I'm still not sure what you're getting at, and I'm getting the impression you think I think U is more powerful than it actually is...?
21:17:45 <int-e> No. The whole point here is that I can reason about programs in ways that U can't.
21:18:32 <cpressey> int-e: that would seem to be a dreadfully strong claim w.r.t. the computationalist theory of mind...
21:18:44 <int-e> That's what I did, I described a program that will not terminate (under consistency assumptions), but that U cannot prove nonterminating.
21:19:09 <cpressey> and for that program, U doesn't terminate -- as per my definition -- and...?
21:19:25 <HackEgo> [wiki] [[Hexadecimal Stacking Pseudo-Assembly Language]] N http://esolangs.org/w/index.php?oldid=42255 * SuperJedi224 * (+960) Created page with "The '''Hexadecimal Stacking Pseudo-Assembly Language''' (HSPAL) is a programming language by [[User:SuperJedi224|SuperJedi224]] in which a program is represented by a list of ..."
21:20:03 <int-e> cpressey: But we can prove that it doesn't terminate, whereas U can't. (Honestly, it's the consistency assumption that will bite me in the end.)
21:20:15 <HackEgo> [wiki] [[Hexadecimal Stacking Pseudo-Assembly Language]] http://esolangs.org/w/index.php?diff=42256&oldid=42255 * SuperJedi224 * (+11)
21:21:27 <HackEgo> [wiki] [[Mmmm()]] http://esolangs.org/w/index.php?diff=42257&oldid=42235 * SuperJedi224 * (+18)
21:21:51 <HackEgo> [wiki] [[Hexadecimal Stacking Pseudo-Assembly Language]] http://esolangs.org/w/index.php?diff=42258&oldid=42256 * SuperJedi224 * (+45)
21:22:51 <HackEgo> [wiki] [[Turing Script]] http://esolangs.org/w/index.php?diff=42259&oldid=42141 * SuperJedi224 * (+18)
21:23:23 <HackEgo> [wiki] [[GridScript]] http://esolangs.org/w/index.php?diff=42260&oldid=41337 * SuperJedi224 * (+16)
21:23:34 <int-e> cpressey: And no, it doesn't contradict the computationalist theory of mind either. We can implement that reasoning in a Turing machine, but it will be a different one from U.
21:23:47 -!- AnotherTest has joined.
21:23:57 -!- cpressey has quit (Ping timeout: 256 seconds).
21:24:18 <coppro> int-e: it's not necessarily meta-logic
21:24:45 <coppro> you can just throw in more axioms to any logical system
21:25:05 <coppro> since any TM will only include finitely many axioms encoded, you can always make a "stronger" termination-checker TM
21:25:36 <HackEgo> [wiki] [[HSPAL]] N http://esolangs.org/w/index.php?oldid=42261 * SuperJedi224 * (+59) Redirected page to [[Hexadecimal Stacking Pseudo-Assembly Language]]
21:25:58 <HackEgo> [wiki] [[Language list]] http://esolangs.org/w/index.php?diff=42262&oldid=42254 * SuperJedi224 * (+12) /* H */
21:26:59 <HackEgo> [wiki] [[Hexadecimal Stacking Pseudo-Assembly Language]] http://esolangs.org/w/index.php?diff=42264&oldid=42258 * SuperJedi224 * (+0)
21:27:45 <HackEgo> [wiki] [[Hexadecimal Stacking Pseudo-Assembly Language]] http://esolangs.org/w/index.php?diff=42265&oldid=42264 * SuperJedi224 * (+6)
21:30:07 -!- cpressey_ has joined.
21:30:52 <cpressey_> <int-e> cpressey: But we can prove that it doesn't terminate, whereas U can't. <-- yes, U just tries forever, and fails to find a proof, consistent with its definition
21:31:51 <cpressey_> other than thinking you've misread my definition, I can't see what the problem is here.
21:32:20 <cpressey_> what about U makes it incapable of taking any proof strategy that an arbitrary TM could take?
21:32:34 <cpressey_> I honestly can't see anything stopping it from that
21:33:17 <int-e> Ultimately it's because soundness of formal systems is so elusive.
21:33:33 <cpressey_> U is no more sound than any other UTM
21:33:55 <cpressey_> it just terminates on some T's that a naive UTM wouldn't terminate on
21:34:13 <cpressey_> apologies if I was giving some other impression. I didn't think I was.
21:34:59 <ais523> <cpressey_> <-- yes, U just tries forever, and fails to find a proof, consistent with its definition ← that was the basic idea behind onoz too
21:35:01 <int-e> Look, all I did was take your innocent use of "provable" and apply it to a formal system that is not embedded in U.
21:35:21 <cpressey_> sorry, should've said "provable by Turing machine", I guess
21:35:54 <cpressey_> ais523: yes, onoz is basically this with a few small twists (it checks inside loops only, for example)
21:36:00 <int-e> (Though it could be embedded in a different Turing machine, U')
21:38:48 <cpressey_> BT certainly isn't helping, tonight
21:39:02 <int-e> Sorry, but then you're missing the point of Gödel's incompleteness.
21:39:57 <cpressey_> Can you phrase it in terms of the Halting Problem, instead of Goedel's incompleteness?
21:40:21 <oerjan> there's no concept of "provable by Turing machine" without saying _which_ Turing machine.
21:40:22 <int-e> U will either have embedded an inconsistent nontermination prover (and thus there will be Turing machines that actually halt, but that U will declare as non-terminating) or one can *construct* a non-terminating program from U that U cannot show non-terminating, because non-provability rests on a consistency assumption, and consistency of the systems can't be proved inside the system.
21:41:21 <int-e> cpressey_: I did that already above:
21:41:24 <int-e> Let U(x,y) be a TM that terminates with 1 if the TM x accepts y, and with 0 if it could prove that x(y) does not terminate. Then consider M(x) that first executes U(x,x), terminates if it halts with 0, and loops forever if it halts with 1. Then U(M,M) will not terminate, assuming that the formal system used by U for proving nontermination is sound.
21:42:44 <int-e> cpressey_: Note that this implies that M(M) does not terminate, but U cannot prove that fact.
21:44:04 <cpressey_> "one can *construct* a non-terminating program from U" -- let's call this Y
21:44:32 <cpressey_> at 22:43 I said "OK -- give me a second" but BT is just awful tonight
21:44:58 -!- ProofTechnique has joined.
21:45:46 <lambdabot> Local time for cpressey_ is Wed Apr 1 22:47:42 2015
21:46:22 -!- ^v^v has quit (Read error: Connection reset by peer).
21:46:29 <oerjan> cpressey_: you're not that lagged accordingly to lambdabot
21:46:44 -!- ^v^v has joined.
21:47:16 <int-e> 23:47:44 <oerjan> @time cpressey_ ==> <lambdabot> Local time for cpressey_ is Wed Apr 1 22:47:42 2015 <-- time travel, but maybe *I*'m lagging...
21:47:36 <oerjan> ok _now_ it is lagging.
21:47:44 <lambdabot> Local time for oerjan is Wed Apr 1 23:49:44 2015
21:47:47 -!- boily has joined.
21:48:12 <oerjan> CTCP PING reply from int-e: 0.855 seconds
21:48:20 -!- cpressey_ has quit (Read error: Connection reset by peer).
21:49:01 -!- cpressey has joined.
21:49:19 <cpressey> int-e: let's assume uses ZFC for its proof system. we don't know it's consistent, of course
21:49:21 <int-e> FireFly: I'm sorry btw, I intended it to be an innocent remark, I didn't expect this to result in such a lengthy string of misunderstandings on various levels.
21:49:40 <cpressey> int-e: i'm also going to assume we both know what Y refers to
21:50:30 <oerjan> the "we don't know it's consistent, of course" rather ruins it, i think.
21:51:12 <cpressey> look, if ZFC's inconsistent we'll just find a ZFC' that we think is probably not inconsistent and carry on
21:51:36 <int-e> cpressey: Well, U either terminates because Y terminates, or it terminates because it has proven that Y doesn't terminate, or it runs forever.
21:51:43 <cpressey> so if you're going to say "ah but ZFC might be inconsistent" there's no bloody point
21:52:05 <cpressey> int-e: and that was not captured by my definition... how exactly?
21:52:32 <int-e> cpressey: but in the first case Y cannot terminate. and in the second case Y actually terminates (so either the system is inconsistent or this cannot happen).
21:53:06 <int-e> I refined your definition: "Let U(x,y) be a TM that terminates with 1 if the TM x accepts y, and with 0 if it could prove that x(y) does not terminate."
21:54:04 <int-e> (I also spearated the Turing machine from its input because it's technically more convenient. This is not essential.)
21:54:31 <cpressey> why would U prove that Y doesn't terminate (the second case, as you called it) if Y does in fact terminate?
21:55:42 <int-e> cpressey: because the formal system used for proving non-termination might be inconsistent; classically that means it can prove anything at all; I expect that intuitionistically it's almost as bad (but I'd have to think about this a bit more)
21:56:13 -!- MDude has joined.
21:56:26 <cpressey> ok, I am, for practical purposes, assuming it's using ZFC and assuming that ZFC is consistent. so the second case cannot happen.
21:56:42 <int-e> Right. Then only the third case remains.
21:57:07 <int-e> I.e., Y doesn't terminate and U(M,M) cannot prove this.
21:57:17 <cpressey> I still fail to see the problem. Unless the problem is "Oh noes, ZFC might not be consistent."
21:57:18 <int-e> (In its internal non-termination prover.)
21:58:58 <int-e> There is no problem, just a strange tangle that is not quite a loop: We have a program that we know (provably, assuming consistency; this is and will always be the weak point) doesn't terminate, but the formal system embedded in U is too weak to show that.
22:01:53 <cpressey> I mean, I might be a brain in a vat, too. I don't usually worry about such things.
22:07:20 -!- AnotherTest has quit (Remote host closed the connection).
22:09:20 <cpressey> int-e: are you *sure* you can't rephrase your point in terms of the HP? because I would find that a lot easier to understand.
22:10:57 -!- nycs has quit (Quit: This computer has gone to sleep).
22:12:42 <oerjan> > flip showsTypeRep "" $ typeRep (Proxy :: Proxy ())
22:13:00 <oerjan> > flip showsTypeRep "" $ typeRep (Proxy :: Proxy (Proxy ()))
22:13:07 <cpressey> http://www.scottaaronson.com/blog/?p=710 seems to strongly suggest this sort of thing can all be done with TM's. i've only skimmed it so far though.
22:14:01 -!- shikhin has quit (Quit: leaving).
22:14:03 <int-e> No, I think I need diagonalization, i.e. the proof method used for showing that the halting problem is undecidable.
22:14:53 <int-e> In any case I generally find the former easier than trying to shoe-horn proofs to only use the latter.
22:15:20 <lambdabot> Local time for tswett is Wed Apr 1 22:17:21 2015
22:15:35 <tswett> [18:17:21] <lambdabot> Local time for tswett is Wed Apr 1 22:17:21 2015
22:15:56 <int-e> nice, your client replies in UTC :)
22:15:58 <tswett> Apparently my IRC client disagrees with itself as to the time.
22:16:32 <lambdabot> Local time for djanatyn is Wed, 01 Apr 2015 15:18:33 -0700
22:16:33 * int-e needs a script to hook into the ctcp time replies.
22:17:18 <tswett> So, you know lenses in functional programming?
22:17:24 <tswett> Those can be interpreted in any category, right?
22:17:56 <tswett> Well, any category with... binary products?
22:18:13 <tswett> Has anyone actually studied those?
22:19:01 <ais523> tswett: are you thinking of products or tensors?
22:19:25 <tswett> Just plain ol' categorical products, I'm pretty sure.
22:19:38 <tswett> A lens consists of arrows A -> B and (A * B) -> A such that blah blah blah.
22:20:53 <shachaf> Lenses can be lots of things.
22:20:55 <oerjan> edwardk: i think the above question is for you ^
22:21:21 <shachaf> But type-changing lenses are much nicer than the other kind.
22:21:34 <shachaf> And type-changing is really some sort of naturality.
22:21:49 <shachaf> Anyway this has been discussed in #haskell-lens
22:23:08 <HackEgo> 895) <shachaf> Taneb: STOP TRYING TO GET LENS INTO EVERYTHING <shachaf> Bike: You should use lens! <Taneb> NEVER <Bike> shachaf: i'm getting mixed messages here \ 984) <shachaf> Bike: I think you're ready to learn about lens. <Bike> oh god <Bike> fiora help somebody help <Bike> anybody \ 1186) <oerjan> in that thread Taneb admits to his sins
22:25:57 <tswett> Arrows g : A -> B and s : (A * B) -> A such that g . s : (A * B) -> B is the right projection, s . (A * g) . (\x -> (x,x)) : A -> A is the identity, and s . (s * B) . (\(x,y) -> (x,y,y)) : (A * B) -> A is s.
22:26:18 -!- cpressey has quit (Quit: leaving).
22:30:54 -!- ProofTechnique has quit (Ping timeout: 264 seconds).
22:35:56 <boily> @ask Bike where are you?
22:38:01 -!- Koen_ has quit (Quit: The struct held his beloved integer in his strong, protecting arms, his eyes like sapphire orbs staring into her own. "W-will you... Will you union me?").
22:41:13 -!- trout has quit (Ping timeout: 246 seconds).
22:43:04 -!- augur has joined.
22:59:19 <HackEgo> [wiki] [[User:Vriskanon]] M http://esolangs.org/w/index.php?diff=42266&oldid=42224 * Vriskanon * (+0) /* Vriskanon */ Typo
23:21:30 -!- oren has joined.
23:25:20 <oren> today my only achievement was eating 500g of bacon
23:27:18 <oren> i wonder how many calores that is.
23:35:33 -!- ProofTechnique has joined.
23:36:53 <boily> helloren. baconinging?
23:36:59 <boily> (bacon binge. baconinge.)
23:37:43 -!- Decim has joined.
23:38:04 -!- vodkode_ has joined.
23:38:58 -!- Lymee has joined.
23:40:39 <boily> Good evening, shachaf.
23:42:04 -!- Lymia has quit (Ping timeout: 256 seconds).
23:55:49 -!- Lymia has joined.
23:56:57 -!- Lymee has quit (Ping timeout: 265 seconds).
23:58:50 -!- Lymia has quit (Remote host closed the connection).
23:59:35 -!- Lymia has joined.
00:07:05 * boily pokes Lymia in the connection
00:09:03 <boily> along with boilognese, boilamia.
00:09:41 <oerjan> what about some boilabaisse
00:11:58 <shachaf> relrod: You may be more qualified to answer that than I am.
00:13:46 <boily> http://www.globalsino.com/EM/image1/3911.gif ???
00:14:40 <oerjan> ah that must be the machine cern used to find the force
00:18:33 <boily> somebody named relrod.
00:18:51 * relrod puts bucket over head. Where?!
00:18:53 <shachaf> relrod: Apparently you were instrumental in finding the force?
00:18:56 <boily> relrod: uhm. hello? what are your approximate coördinates and body weigh?
00:20:00 * oerjan checks relrod's lilaxity, just because.
00:20:20 <relrod> boily: 39.111748, -76.775635; -4 lbs.
00:21:00 -!- oren has quit (Quit: Lost terminal).
00:21:02 * oerjan determines it to be zero on account of the redhat cloak.
00:22:04 <shachaf> You never answered the question about elrods.
00:22:42 <relrod> shachaf: what's a shachaf? :P
00:22:53 <oerjan> relrod: i am not a stalker and i _totally_ didn't find your picture on github.
00:23:37 <shachaf> oerjan: did you find my picture on github twh
00:23:44 <oerjan> shachaf can confirm i'm not a stalker hth
00:23:55 <oerjan> shachaf: you've linked your picture many times
00:24:27 <shachaf> i,i http://dl.dropboxusercontent.com/u/13786158/portraits/shachaf.png
00:25:35 <oerjan> as proof that i'm not a stalker, this is totally the first time i check out shachaf's github account. unless i've forgotten.
00:26:10 <shachaf> oerjan: it's called "cloning" in the git nomenclature hth
00:27:55 <oerjan> i think we are confusing denotations again.
00:28:05 <boily> oerjan: strangely, you're not in the Wisdom Conspirators.
00:28:06 <shachaf> relrod: so how 'bout that bug #9858
00:28:27 <oerjan> i don't think i've ever used git directly, anyway.
00:28:45 <oerjan> wait, relrod is related to #9858?
00:29:52 <oerjan> shachaf: i am tending to believe that that typeRep confusion you found is harmless, because there is no function to cast without comparing actual kinds or embedding in another type.
00:30:11 <oerjan> which i assume was your and int-e's conclusion too
00:30:13 <shachaf> That's what I'm tending to believe also.
00:30:31 <shachaf> But not to the point where I'd trust an unsandboxed -XSafe GHC.
00:30:51 <oerjan> i think we stopped doing that anyway.
00:30:58 <oerjan> pretty sure int-e did.
00:31:13 -!- Lymia has quit (Remote host closed the connection).
00:31:43 -!- GibVent has changed nick to GeekDude.
00:32:22 <oerjan> of course all it would take is one function which _doesn't_ compare kinds, but there seems to be little reason to define one. except perhaps to fake kind equality testing...
00:32:49 <shachaf> There could be some serialization thing.
00:32:56 -!- Lymia has joined.
00:36:23 -!- ais523 has quit (Quit: building NetHack 4 on Windows).
00:36:34 <oerjan> boily: wait what's the Wisdom Conspirators
00:37:04 <shachaf> oerjan: do you really expect an answer, given that you're not among them
00:37:42 <boily> oerjan: I can't remember if you didn't not have a github account. if you don't, could you please point me to it?
00:37:45 <oerjan> boily: http://ghc.haskell.org/trac/ghc/ticket/9858 the bug we found that helped hold up ghc release for a month. and which shachaf just discovered hasn't been entirely fixed
00:38:09 <oerjan> (actually we didn't find it, just probed the consequences)
00:38:21 <shachaf> but someone else found it first
00:38:35 <oerjan> boily: i have no github account, i'm pretty sure i just said i haven't used git
00:39:47 <shachaf> https://ghc.haskell.org/trac/ghc/ticket/7258
00:39:49 <boily> therefore the reason for you perfectly logical prolonged absence from the List.
00:40:35 <oerjan> bah i didn't get goldfire's reply on Cc:
00:41:17 <shachaf> I wonder whether there are any other places where this * ~ Constraint thing is exposed?
00:44:46 <HackEgo> [wiki] [[User:SuperJedi224]] http://esolangs.org/w/index.php?diff=42267&oldid=42229 * SuperJedi224 * (+56)
00:45:07 <oerjan> i don't think that's what's happening, just made a comment
00:45:26 <oerjan> it's true but not really relevant to constructing TypeReps
00:45:52 <shachaf> oerjan: It's pretty strange that () :: Constraint's TypeRep is "ghc-prim GHC.Tuple ()"
00:47:27 <oerjan> they totally need to expose those Constraint entities somewhere people can get them even unapplied, like (,)
00:47:44 <relrod> shachaf: what about #9858 :( it's not my fault, I swear
00:48:07 -!- variable has joined.
00:48:15 <shachaf> relrod: I didn't think any of these things were your fault, but you seem very defensive for some reason.
00:48:48 <relrod> shachaf: you act like I know enough about GHC internals to be able to have an impact here. :P
00:49:01 * relrod really, really should learn more about how GHC actually works :/
00:49:02 -!- Lymee has joined.
00:49:04 <shachaf> I thought you were all about GHC?
00:49:29 <relrod> shachaf: Naw. I do Haskell Infra stuff, but haven't gotten into GHC stuff yet.
00:49:30 -!- Lymia has quit (Ping timeout: 256 seconds).
00:50:07 <shachaf> Well, I don't know how GHC works either.
00:51:08 <relrod> shachaf: Lately I'm on a type theory thing. Trying to work with people in the math department at my school and have them let me do an Individual Study in type theory.
00:51:27 <relrod> Because I think it would be a lot of fun
00:51:40 <relrod> And I'm going to learn it anyway, so why not get some credit for it ;)
00:59:55 -!- mihow has quit (Quit: mihow).
01:02:34 <shachaf> `learn A relrod is a machine useful for finding the Force.
01:02:44 <HackEgo> Learned 'relrod': A relrod is a machine useful for finding the Force.
01:05:32 -!- ais523 has joined.
01:06:20 -!- mihow has joined.
01:06:40 -!- mihow has quit (Client Quit).
01:16:48 -!- ais523 has quit (Quit: more Windows builds).
01:26:27 -!- Lymee has changed nick to Lymia.
01:30:05 -!- boily has quit (Quit: NAUTICAL CHICKEN).
01:31:23 -!- Phantom_Hoover has quit (Remote host closed the connection).
01:31:37 -!- Phantom_Hoover has joined.
01:37:52 -!- ais523 has joined.
01:40:13 -!- ais523 has quit (Client Quit).
01:40:32 -!- ais523 has joined.
01:48:55 -!- Lymee has joined.
01:49:00 -!- Lymia has quit (Ping timeout: 256 seconds).
01:52:20 -!- variable has changed nick to function.
02:01:23 -!- Decim has quit (Ping timeout: 250 seconds).
02:07:05 <oerjan> shachaf: you've been til'ed http://www.reddit.com/r/haskelltil/comments/313n72/the_numdecimals_extension_lets_you_write_integers/
02:08:04 <oerjan> oh wait was it the binary one you did?
02:08:18 <shachaf> I guess I did implement this.
02:08:22 <shachaf> dmwit was the one who asked for it.
02:08:56 <shachaf> also what's this subreddit thing
02:09:41 <shachaf> i guess if you actually log in following the small ones isn't so painful
02:13:20 <oerjan> it was advertised on haskell recently
02:13:34 <oerjan> it's only my second smallest
02:13:41 <oerjan> (guess which is the smallest one)
02:13:59 <oerjan> also it's the large ones which are painful hth
02:14:30 * oerjan doesn't actually use the front page, which means it would probably be painful if he had more subreddits than fit in the menu
02:15:00 -!- Phantom_Hoover has quit (Read error: Connection reset by peer).
02:15:43 <oerjan> i don't want to use the front page because then the largest ones that i almost never visit would swamp the small ones which i follow closely. i think.
02:16:22 <shachaf> the part preceding the hth
02:16:42 <shachaf> another thing that isn't helpful is 35s roundtrip latency to 8.8.8.8
02:17:10 <shachaf> Anyway, the painful part is having a lot of them, since then I have to click them all.
02:17:19 <shachaf> If everyone puts everything in the main one then there's no problem.
02:17:24 <shachaf> (Except that the main one is getting noisy.)
02:17:47 <oerjan> you can make subreddit combinations, i hear
02:18:00 <shachaf> That's true. /r/haskell+haskelltil
02:18:28 -!- callforjudgement has joined.
02:18:52 -!- ais523 has quit (Disconnected by services).
02:18:53 -!- callforjudgement has changed nick to ais523.
02:18:57 <oerjan> (the smallest one is /r/esolangs hth)
02:19:34 <copumpkin> shachaf is tweeting, stop the press
02:19:43 <shachaf> i was hoping to keep it quiet
02:20:01 -!- vodkode_ has quit (Ping timeout: 265 seconds).
02:20:28 <shachaf> twitter used to email me from n-funpuns=...@postmaster.twitter.com
02:21:50 <shachaf> copumpkin: Do you know how Twitter lists work?
02:22:15 <shachaf> I use that feature instead of the "follow" feature.
02:22:17 <copumpkin> they added it years ago and have been progressively de-emphasizing
02:22:20 <shachaf> So my followee list isn't public.
02:23:12 <copumpkin> you actively mark it as not public? or just have 0 and it shows up that way?
02:23:30 <shachaf> It's separate from the following feature.
02:23:44 <shachaf> I made a list and I look at that list instead of the front page.
02:24:20 <shachaf> But I want to follow conversations including ones where people reply to me, and it doesn't seem to work very well for that. I managed to add myself to the list but it still doesn't do it.
02:42:03 -!- nys has quit (Quit: quit).
02:49:04 <oerjan> ais523: it was inevitable that someone would reinvent feather in haskell https://mail.haskell.org/pipermail/haskell-cafe/2015-April/118905.html
02:49:55 -!- vodkode_ has joined.
02:49:58 <ais523> it is clearly a terrible idea for me to follow this link
02:50:23 <oerjan> *MWAHAHAi mean, not at all.
02:50:38 <ais523> "Bearing in mind our model of a space-time continuum of hackage dependences, the solution emerges — enforce immutability, but allow retroactive mutation." oh good, they came to the same conclusion as me without necessarily being able to implement it
02:51:25 <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.
02:51:38 <ais523> wait, how does shachaf not know what feather is
02:51:48 <ais523> and why isn't it in the wisdomdb, I thought it was
02:51:57 <oerjan> i think he's just checking what current wisdom on feather is
02:52:06 <shachaf> I've seen it mentioned but I don't remember if I ever knew what it is.
02:52:12 <shachaf> Unless it's a thing where the joke is that no one says what it is.
02:52:27 <ais523> http://esolangs.org/wiki/Feather
02:52:34 <ais523> the joke /became/ that but it wasn't the original joke
02:54:03 <ais523> the esolangs page is quite a good description
02:54:10 <ais523> both the idea of the language itself, and why everyone avoids talking about it
02:55:06 <shachaf> Speaking of which, Broken Age Act 2 will come out this month.
02:56:05 <ais523> gah, now I'm on the verge of thinking about Feather again
02:56:10 <HackEgo> 865) -!- ais523 has parted #esoteric ("someone is going to mention Feather, I know it"). \ 866) <Bike> i don't even know anything about feather and i'm getting sick of the time travel jokes \ 896) <ais523> in Smalltalk, as in Feather, in order to do I/O, you must first create the universe <Sgeo> ais523, it seems quite capable of I/O... GUI is a fo
02:56:24 <MDude> Programming language based on the principles of metacybernetics.
02:56:28 <shachaf> Who are the time travelers?
02:58:53 <ais523> in Feather, everything is immutable, but you can retroactively change what an object was when it was created
02:59:23 <ais523> or to think about it another way, you have a "clone" operation, and the result of the clone has a method that lets you retroactively change what the clone function returned
02:59:37 <ais523> this much is easy to implement, it's basically a wrapper around call/cc
02:59:49 <ais523> then things start getting confusing very quickly
02:59:58 -!- function has left ("/dev/null is full").
03:00:01 -!- function has joined.
03:01:35 <shachaf> `` echo -ne '#!/bin/sh\ngrep -P -i -n "$1" quotes | cut -d ':' -f 1 | xargs\n' > bin/quotenums; chmod +x bin/quotenums
03:01:57 -!- idris-bot has quit (Quit: Terminated).
03:16:15 -!- idris-bot has joined.
03:22:38 -!- oerjan has quit (Quit: Retroactively going to bed 1 1/2 hour ago, maybe.).
03:51:10 -!- GeekDude has quit (Ping timeout: 272 seconds).
04:00:05 -!- function has quit (Quit: 1 found in /dev/zero).
04:00:21 -!- variable has joined.
04:03:59 -!- vodkode_ has quit (Remote host closed the connection).
04:13:55 -!- callforjudgement has joined.
04:15:43 -!- ais523 has quit (Ping timeout: 245 seconds).
04:19:45 -!- callforjudgement has changed nick to ais523.
04:25:33 -!- vodkode_ has joined.
04:27:39 -!- vodkode_ has quit (Remote host closed the connection).
04:41:56 -!- callforjudgement has joined.
04:42:18 -!- ais523 has quit.
04:42:52 -!- g2watson has joined.
04:43:21 -!- callforjudgement has changed nick to ais523.
04:44:51 -!- MDude has changed nick to MDream.
04:45:17 <HackEgo> [wiki] [[Special:Log/newusers]] create * Idunnowhy9000 * New user account
04:48:12 -!- variable has quit (Ping timeout: 264 seconds).
04:56:42 -!- variable has joined.
05:03:23 -!- v4s has quit (Ping timeout: 265 seconds).
05:03:34 -!- SgeoPhone has joined.
05:04:24 <SgeoPhone> My laptop currently is in pieces in front of me, as i try to fix whatever's wrong without making things worse
05:04:45 <SgeoPhone> I think im failing but no way to know until i put it back together
05:04:53 -!- v4s has joined.
05:12:05 -!- Lymee has quit (Ping timeout: 265 seconds).
05:16:04 -!- Lymia has joined.
05:16:31 -!- vodkode_ has joined.
06:00:04 <SgeoPhone> Does this thick black cable look damaged? http://i.imgur.com/ZqNmL4t.jpg
06:07:30 -!- ais523 has quit.
06:07:43 -!- ais523 has joined.
06:12:26 -!- infinitymaster has joined.
06:19:13 <infinitymaster> !zjoust Iron_Will_and_a_Clear_Conscience >(-)*16>(+)*15(>+>-)*3>([(-)*15[+]]>)*21
06:19:14 <zemhill_> infinitymaster.Iron_Will_and_a_Clear_Conscience: points -3.45, score 16.57, rank 39/47 (-4)
06:21:43 -!- infinitymaster has quit (Quit: Leaving...).
06:39:44 <Jafet> Maybe you need to take a step back here
06:40:05 -!- vodkode_ has quit (Remote host closed the connection).
06:47:44 -!- zadock has quit (Quit: Leaving).
07:16:59 -!- f|`-`|f has quit (Read error: Connection reset by peer).
07:18:26 -!- f|`-`|f has joined.
07:31:07 -!- Patashu has joined.
07:34:45 -!- Patashu has quit (Remote host closed the connection).
07:35:03 -!- Patashu has joined.
07:36:26 -!- zadock has joined.
07:39:08 -!- variable has quit (Ping timeout: 248 seconds).
07:39:22 -!- vodkode_ has joined.
07:46:59 -!- f|`-`|f has quit (Read error: Connection reset by peer).
07:48:23 -!- f|`-`|f has joined.
07:48:24 -!- SgeoPhone has quit (Remote host closed the connection).
07:48:39 -!- SgeoPhone has joined.
07:55:33 -!- vodkode_ has quit (Ping timeout: 255 seconds).
08:07:38 <mroman> http://news.slashdot.org/story/15/04/02/0227211/uk-forces-microsoft-to-adopt-open-document-standards
08:36:37 -!- callforjudgement has joined.
08:38:38 -!- ais523 has quit (Ping timeout: 245 seconds).
08:39:12 -!- callforjudgement has changed nick to ais523.
08:42:47 -!- AnotherTest has joined.
09:00:01 -!- ais523 has quit (Read error: Connection reset by peer).
09:00:13 -!- ais523 has joined.
09:03:18 <mroman> Is there a browser that runs in x11?
09:08:07 -!- stuntaneous has joined.
09:21:53 -!- Patashu has quit (Disconnected by services).
09:21:53 -!- Patashu_ has joined.
09:22:39 -!- ais523 has quit (Read error: Connection reset by peer).
10:04:02 -!- Lymia has quit (Ping timeout: 265 seconds).
11:31:26 -!- hailer has joined.
11:41:10 -!- AnotherTest has quit (Remote host closed the connection).
11:44:49 -!- ais523 has joined.
11:48:32 -!- SgeoPhone has quit (Remote host closed the connection).
11:48:47 -!- SgeoPhone has joined.
11:54:28 -!- ais523 has quit (Ping timeout: 244 seconds).
11:55:28 -!- ais523 has joined.
11:57:07 -!- MDream has changed nick to MDude.
11:57:20 -!- hjulle has joined.
12:00:33 -!- stuntaneous_e has joined.
12:01:00 -!- stuntaneous has quit (Ping timeout: 265 seconds).
12:03:46 -!- Patashu has joined.
12:06:52 -!- gamemanj has joined.
12:07:24 -!- Patashu_ has quit (Ping timeout: 264 seconds).
12:12:52 -!- gamemanj has quit (Read error: Connection reset by peer).
12:12:55 -!- stuntaneous_e has quit (Ping timeout: 264 seconds).
12:16:31 -!- GeekDude has joined.
12:16:36 -!- GeekDude has quit (Changing host).
12:16:36 -!- GeekDude has joined.
12:39:07 -!- copumpkin has quit (Quit: My MacBook Pro has gone to sleep. ZZZzzz…).
12:43:03 -!- Patashu has quit (Ping timeout: 265 seconds).
13:01:52 -!- oerjan has joined.
13:11:21 -!- ais523 has quit.
13:11:59 <b_jonas> you know how ia64 (also known as itanium) is a different cpu architecture from x86_64 (also known as intel-64 or amd64 or x64)? these names will confuse some more newbies in the future.
13:13:04 -!- SgeoPhone has quit (Quit: AndroIRC - Android IRC Client ( http://www.androirc.com )).
13:13:15 <b_jonas> so anyway, now we have another similar set of confusing architecture names: http://hurrdurr.org hosts the Hurr Durr kernels, also know as Linux, not to be confused with Hurd which is a different kernel.
13:13:26 <lambdabot> Not in scope: type constructor or class ‘Dict’
13:14:00 <oerjan> aren't you about a day late
13:14:15 <b_jonas> but hurrdurr.org is still alive
13:14:20 <mroman> but... but... x86 has more bits than x64
13:14:28 <b_jonas> it's just that kernel.org no longer redirects to it
13:15:42 <mroman> Which lets me count to 77371252455336267181195263
13:17:34 <b_jonas> mroman: yes, there's a quote about that in http://www.scottaaronson.com/blog/?p=1558
13:18:59 <oerjan> oh interesting, in 7.8 the () constraint wasn't Typeable, it seems.
13:19:12 <j-bot> b_jonas: 77371252455336267181195263
13:19:20 <oerjan> and you cannot derive it, of course
13:20:26 <oerjan> oh damn i cannot define Dict in lambdabot because int-e refuses to import Constraint
13:21:20 <oerjan> b_jonas: not useable for what i'm actually trying to do, which is to expand shachaf's discovery from yesterday to an exploit
13:22:14 <b_jonas> isn't that why int-e refuses to import Constraint though?
13:22:19 <oerjan> unfortunately i'm too lazy to install 7.10 until the Haskell Platform gets out
13:23:02 <oerjan> he gave up trying to get around our previous exploits with that kind of restrictions, and made a proper sandbox.
13:23:36 <oerjan> the reason he refuses is that Constraint is in GHC.Exts, an Unsafe module.
13:23:45 <b_jonas> he might want to use both for security
13:23:49 <oerjan> which means he'll have to jump through some hoops.
13:24:02 <oerjan> b_jonas: but Constraint is _supposed_ to be safe.
13:24:32 <b_jonas> sure, but int-e suspects it's not safe even if it's supposed to be
13:24:57 <oerjan> b_jonas: i don't think he suspects Constraint, in itself, is safe. he'd have to ban _everything_.
13:25:31 <oerjan> except, of course, in this case i need it to test whether there is an exploit.
13:26:06 <oerjan> i tried to use 7.8 as far as possible to test, but it doesn't even _have_ the Typeable instances i need
13:27:01 <b_jonas> isn't there a different online haskell interpreter somewhere?
13:29:20 <oerjan> :t Proxy :: (Proxy (() => ()))
13:29:39 <oerjan> it is quite possible it isn't possible to actually construct the () => () type
13:30:31 <oerjan> oh hm it's probably not considered monomorphic.
13:30:51 <oerjan> in which case it won't show up as Typeable
13:31:13 <oerjan> you can make an argument with the type, but not define instances for it.
13:31:52 -!- ProofTechnique has quit (Ping timeout: 265 seconds).
13:33:35 <oerjan> but _if_ you could, and if goldfire's ghc trac comment about * and Constraint being identified in core is actually relevant and creeps into the form of Typeable instances...
13:33:46 <Taneb> oerjan, isn't the constraint () trivially true?
13:34:22 <oerjan> Taneb: well sure. i was trying to construct (() => ()) as an actual _type_ with a Typeable instances distinct from ()
13:34:40 <oerjan> in order to check whether it had the same TypeRep as () -> ()
13:35:08 <oerjan> which could have allowed an exploit.
13:35:08 <Taneb> :t Proxy :: Proxy (Eq Int => Int)
13:35:10 <lambdabot> Illegal polymorphic or qualified type: Eq Int => Int
13:35:10 <lambdabot> Perhaps you intended to use ImpredicativeTypes
13:35:10 <lambdabot> In an expression type signature: Proxy (Eq Int => Int)
13:36:40 <oerjan> Taneb: it cannot contain actual class names or anything _officially_ polykinded.
13:37:16 <oerjan> () :: * and () :: Constraint have the same TypeRep, but the problem is constructing something with the _same_ kind
13:37:25 <Taneb> :t Proxy :: Proxy (((),()) => Int)
13:37:26 <lambdabot> Illegal polymorphic or qualified type: ((), ()) => Int
13:37:26 <lambdabot> Perhaps you intended to use ImpredicativeTypes
13:37:26 <lambdabot> In an expression type signature: Proxy (((), ()) => Int)
13:37:47 <oerjan> you cannot define any helper types, they would be polykinded.
13:38:54 <oerjan> but => is the same as -> in core, which might or might not be relevant. i'm starting to think it isn't, because => doesn't construct a monomorphic type.
13:39:39 <oerjan> so has no chance of ending up in a Typeable argument.
13:42:09 <oerjan> oh hm maybe it does. in 7.8 with ImpredicativeTypes enabled, typeRep (Proxy :: Proxy (((),()) => ()))
13:42:22 <oerjan> gets close enough to complain about a lacking instance.
13:42:44 <oerjan> (having just () got removed)
13:44:14 <oerjan> i just need 7.10 without stupid restrictions to test this :(
13:44:53 <oerjan> MinGHC or not MinGHC, that's the question.
13:44:56 <mroman> tanebvented is the word.
13:45:39 <Taneb> mroman, this was just a tanebhelped
13:46:51 -!- ais523 has joined.
13:47:02 <oerjan> gah 11 minutes to download something i only want to test something
13:49:12 <oerjan> so basically, i need a ghc 7.10 with ImpredicativeTypes and Data.Typeable enabled.
13:49:44 <oerjan> and that's just to test if the TypeReps _are_ the same, which they most likely aren't.
13:50:27 <oerjan> why isn't shachaf awake :(
13:52:20 <oerjan> @ask shachaf Can you test (you need ImpredicativeTypes) whether typeRep (Proxy :: Proxy (((),()) => ())) == typeRep (Proxy :: Proxy (((),()) -> ()))
13:53:09 -!- ProofTechnique has joined.
13:53:51 <oerjan> > typeRep (Proxy :: Proxy (((),()) -> ()))
13:58:46 <oerjan> huh safe haskell still allows some FFI
13:59:24 <oerjan> under the "everything's still allowed in IO" principle
14:00:13 <oerjan> nothing about ImpredicativeTypes, anyway.
14:02:55 <oerjan> @ask int-e Why aren't ImpredicativeTypes enabled, anyway.
14:04:06 <oerjan> int-e seems conspicuously absent. maybe germans have easter holidays too
14:04:59 <oerjan> Taneb: hey, you don't happen to have GHC 7.10 by any chance
14:05:09 <Taneb> oerjan, just got it installed somewhere
14:05:28 <oerjan> then you could test what i asked shachaf
14:06:42 <oerjan> if it compiles but they _aren't_ equal, the printout of typeRep (Proxy :: Proxy (((),()) => ())) would also be interesting.
14:07:35 <Taneb> They are not equal
14:08:01 <Taneb> > typeOf (Proxy :: Proxy (((),()) => ()))
14:08:02 <Taneb> Proxy * (() -> () -> ())
14:08:03 <lambdabot> Illegal polymorphic or qualified type: ((), ()) ⇒ ()
14:08:03 <lambdabot> Perhaps you intended to use ImpredicativeTypes
14:08:03 <lambdabot> In an expression type signature: Proxy (((), ()) ⇒ ())
14:08:45 <Taneb> > typeOf (Proxy :: Proxy (((),()) -> ()))
14:08:45 <Taneb> Proxy * (((),()) -> ())
14:08:51 <Taneb> Again, sorry lambdabot
14:09:09 <Taneb> oerjan, is that right?
14:10:24 <mroman> > typeOf (5,()) == typeOf (3,())
14:10:30 <oerjan> Taneb: @tell shachaf I cannot get either lambdabot or 7.8 to accept the re
14:11:09 <oerjan> Taneb: @ask shachaf Can you test (you need ImpredicativeTypes) whether typeRep (Proxy :: Proxy (((),()) => ())) == typeRep (Proxy :: Proxy (((),()) -> ()))
14:11:16 <lambdabot> ‘typeRep’ (imported from Data.Typeable),
14:11:17 <lambdabot> forall (k :: BOX) (proxy :: k -> *) (a :: k). Typeable a => proxy a -> TypeRep
14:11:22 <Taneb> oerjan, yeah, they are different
14:11:28 <Taneb> The constraints are uncurried
14:11:50 <oerjan> what does typeRep (Proxy :: Proxy (((),()) => ())) look like
14:11:51 <Taneb> Prelude Data.Typeable> typeOf (Proxy :: Proxy (((),()) => ())) == typeOf (Proxy :: Proxy (() -> () -> ()))
14:12:46 <oerjan> Taneb: what is the result of typeRep (Proxy :: Proxy (((),()) => ()))
14:13:05 <Taneb> Proxy * (() -> () -> ())
14:13:22 <Taneb> "() -> () -> ()" rather
14:14:12 <oerjan> in that case, please compare with actual () -> () -> ()
14:14:46 <oerjan> ooh, that does look promising
14:14:47 -!- vodkode_ has joined.
14:16:47 -!- hailer has quit (Ping timeout: 246 seconds).
14:19:11 <oerjan> oh duh i failed to read some of your lines :P
14:19:20 <oerjan> Taneb: could you try out http://oerjan.nvg.org/haskell/TypeableExploits/TFs5.hs ?
14:20:19 <Taneb> Illegal tuple constraint: () (Use ConstraintKinds to permit this)
14:21:00 <Taneb> oerjan, with ConstraintKinds it compiles
14:22:24 <Taneb> And uc (100 :: Int) :: Char gets 'd'
14:25:01 <oerjan> i fixed that, including your and shachaf's real name
14:26:43 <oerjan> oh, could you add Safe too, on principle.
14:27:55 <Taneb> There's a single warning (duplicate constraint ()) but other than that it's all good
14:28:56 <int-e> oerjan: no holidays, just a combination of getting up late and staying away from the computer
14:29:38 <int-e> Nobody likes ImpredicativeTypes
14:30:48 <int-e> And I'm in Austria, even tomorrow is not a proper holiday...
14:31:16 <int-e> (i.e. Good Fridat) But Easter Monday is.
14:31:47 <oerjan> norway has the highest density of easter holidays in the world, i think
14:32:07 <oerjan> (today, tomorrow, Easter and Easter Monday)
14:32:09 <int-e> . o O ( Dear empty review form, please inspire me... [a different one from yesterday] )
14:32:38 <int-e> Easter Sunday is also a holiday, but a rather useless one.
14:33:03 <ais523> oerjan: does it not have april 1 as a holiday?
14:33:20 <int-e> what kind of holiday would that be?
14:34:05 <ais523> a celebration of creativity that isn't necessarily directed towards a useful goal
14:34:41 <mroman> Karfreitag is usually a thing.
14:34:52 <Taneb> oerjan, do send me a link to the ticket when it is available
14:35:03 <mroman> I'm going to work anyway
14:35:10 <mroman> but it's a holiday around here.
14:35:21 <int-e> mroman: In Austria, it's only a holiday for Protestants. Everybody else has to work.
14:35:52 <mroman> Wait... catholics have to attend work, protestants get a holiday?
14:35:54 <int-e> (Not sure whether it depends on the state, I'm in Tyrol...)
14:36:08 <mroman> Oh. I get that it depends on the state, yeah.
14:36:13 <int-e> mroman: there are catholic-only holidays as well
14:36:16 <mroman> Switzerland has different holidays in different states as well.
14:36:28 <mroman> Depending on what religion was dominant some years ago I guess.
14:36:29 <int-e> mroman: no it really depends on the individual
14:36:41 <mroman> That's certainly... insteresting.
14:36:51 <int-e> (Which I find rather strange. But oh well... and I'm neither catholic nor protestant.)
14:37:16 <mroman> I think this holiday system sucks anyway
14:37:36 <int-e> I think this work system... never mind.
14:37:39 <mroman> Instead of having religious holidays you might as well say "well.. you have 5 days each year you can take off for whatever religious purpose it serves you"
14:37:50 -!- AnotherTest has joined.
14:38:08 <mroman> which would be the same thing as giving you an extra week
14:38:08 <oerjan> ais523: by holiday i mean a day that most people don't need to work hth
14:38:43 <mroman> with these "free extra holidays" you could add some restrictions like "not more than two consecutive days"
14:38:59 <oerjan> Taneb: i just added it to the already existing one https://ghc.haskell.org/trac/ghc/ticket/9858#comment:76
14:39:01 <mroman> so you have 5 extra days, but can't use them as a whole week at once.
14:39:23 <ais523> mroman: your "you have N days and can spend them whenever you want" is very common as a method of allocating time off in companies nowadays
14:39:30 <int-e> mroman: Then again the christian population pays dearly for those extra free days (there are additional taxes).
14:39:51 <ais523> sometimes requiring very slow days like Christmas Day to be one of those days
14:39:51 <mroman> but then you have additional days off because of some religious background.
14:40:17 <mroman> int-e: what kind of taxes?
14:40:19 <ais523> but that's mostly because it's a huge secular holiday where basically nobody works, with the Christian holiday on the same date being observed by a much smaller number of people
14:40:25 <int-e> well, church taxes.
14:40:32 <mroman> but these don't go to the state
14:40:35 <mroman> they go to the churches.
14:40:45 <int-e> mroman: but they still reduce the people's paycheck
14:41:04 <mroman> int-e: what if you're an atheiest?
14:41:10 <mroman> do you get holidays on christmas?
14:41:19 <int-e> mroman: There is this theory of division of church and state, well, this is how it looks in practice ;)
14:41:35 <ais523> mroman: it's hard to argue that there isn't an atheist holiday on Christmas; just statistically, such a holiday exists
14:41:55 <ais523> interestingly, the UK doesn't officially have a separation of church and state
14:41:57 <int-e> mroman: Yes, I do. There's only one or two days where the faith is actually taken into account.
14:41:59 <ais523> and yet the two overlap pretty rarely
14:42:39 <int-e> mroman: To be fair, despite the name, Christmas is really a capitalist holiday. (Ironically it was a holiday in communist countries as well.)
14:43:10 <mroman> I don't fully agree with that
14:43:24 <mroman> people develop expectations from it
14:43:33 <mroman> so you can't really blame it only on shops and malls and the like
14:43:46 <mroman> people's expectations are to blame
14:44:04 <int-e> I have no expectation whatsover for Valentine's day.
14:44:25 <int-e> expectations, whatsoever.
14:44:27 <mroman> mainly because there's no relationship on the horizon and there never was.
14:44:42 <ais523> now I'm feeling bad for not showing up to #esoteric with flowers
14:45:05 <int-e> (the "wow" came from the realization that "whatsover" almost looks like a real word)
14:45:25 <mroman> I only buy christmas gifts for closest of family members
14:45:54 <mroman> and usually you'll tell each other what presents you would have a use for
14:45:55 <int-e> ais523: Cherry blossom is almost over, too.
14:46:00 <mroman> which... makes the whole point rather moot
14:46:11 <mroman> what do I know about social things.
14:48:39 <HackEgo> /home/hackbot/hackbot.hg/multibot_cmds/lib/limits: line 5: exec: flowers: not found
14:49:52 <mroman> It would make more sense for bots to have <space><prefix>
14:50:00 <mroman> nobody starts a sentence with a space
14:50:13 <mroman> those damn bot writers are just too dumb to notice that
14:50:35 <ais523> mroman: I think it's precisely /because/ nobody starts a sentence with aa space
14:50:46 <ais523> people wouldn't be able to use the bot
14:51:46 <idris-bot> (input):1:1: error: expected: ":",
14:52:00 <idris-bot> (input):1:1: error: expected: ":",
14:52:42 <j-bot> mroman: |value error: i9
14:56:49 <mroman> I have to check if I still have the source for octofrogscript
14:58:44 -!- shikhin has joined.
15:01:47 <mroman> I'm having a new language in mind that engrains code conventions in its syntax
15:02:19 <mroman> a bit more restricted than python
15:02:34 <mroman> In python you can still choose between 2 spaces, 4 spaces, 1 tab or 99 spaces
15:02:39 <mroman> that's too much freedom!
15:02:44 -!- vodkode_ has quit (Ping timeout: 265 seconds).
15:02:55 <mroman> also I think if(9 <0) is legal
15:03:33 <mroman> but that might be too restrictive
15:03:47 <ais523> so basically this is $EXISTING_LANGUAGE except that your code must be byte-identical to the output produced by a pretty printer on its parse tree?
15:03:59 <myname> mroman: if(9 <0) should be legal, but do something completely different from if(9<0)
15:04:05 <mroman> And you can write using different syntaxes I guess
15:04:15 <mroman> delphi style, lisp style, c style
15:04:31 <ais523> myname: have you seen Ursala?
15:04:44 <ais523> not even joking, whitespace around operators changes their meaning there
15:05:07 <ais523> a while back I learned enough Ursala to get an appreciation of how it works and just how twisted the design is
15:05:10 <mroman> you actually looked at Ursala a bit more serious?
15:05:12 <ais523> although not enough to actually program in it
15:05:42 <ais523> I can normally mentally parse programs, but not figure out what they mean (or precedence/associativity; those aren't transitive in ursala)
15:06:29 <ais523> myname: huh, I can't find it via my normal search engine
15:07:02 <ais523> yep, I found the URL but it's 404
15:07:17 <myname> ruby some weird whitespace effects, too
15:07:41 <b_jonas> what? it has non-transitive precedence?
15:08:35 <ais523> myname: here you go: http://web.archive.org/web/20110910024105/http://www.basis.netii.net/ursala/manual.pdf
15:08:58 <ais523> I was actually reading through the book I learned to write compilers from recently
15:09:14 <ais523> and it mentions offhand that non-transitive precedence is mathematically possible and the parsing algos work fine on it
15:09:21 <myname> why isn't this in our wiki
15:09:36 <ais523> but that people might want to voluntarily avoid such languages because they might be confusing
15:09:41 <ais523> IMO, ursala is evidence for this
15:11:56 <HackEgo> [wiki] [[Talk:Hexadecimal Stacking Pseudo-Assembly Language]] N http://esolangs.org/w/index.php?oldid=42268 * Esowiki201529A * (+66) Created page with "这个正确的名字是“十六进制堆栈式伪汇编语言”"
15:12:52 <ais523> users has plenty of other contributions
15:13:24 <ais523> ah right, this is a known problem user: http://esolangs.org/wiki/User_talk:Esowiki201529A
15:14:28 <oerjan> @tell shachaf Never mind, Taneb helped; see https://ghc.haskell.org/trac/ghc/ticket/9858#comment:76
15:24:08 -!- zadock has quit (Quit: Leaving).
15:25:32 <oerjan> int-e: btw are you also still missing Cc:s on https://ghc.haskell.org/trac/ghc/ticket/9858 ? i've received shachaf's last message but nothing later.
15:31:59 <int-e> oerjan: nice exploit. And yeah, I think deep down () :: Constraint and () :: * should have different names.
15:33:31 <int-e> (oh and shachaf and Taneb)
15:35:19 <oerjan> btw you know you're excited about something when you're trying to multitask irc'ing and shaving.
15:35:21 <int-e> is there a (,) on the constraint level?
15:35:40 <int-e> oerjan: bloddy business?
15:36:09 <int-e> Ah maybe you're using one of those extra-safe, buzzing, electric shavers
15:39:32 <int-e> . o O ( is there a smartphone with built-in shaver yet? )
15:40:16 <int-e> There could even be a razor-thin edition...
15:40:49 -!- shikhin has quit (Ping timeout: 250 seconds).
15:50:27 <oerjan> int-e: yes the (,) in (Ord a, Num a), say
15:51:07 <oerjan> actually i'm using razor blades. pretty safe, though. although i'm not always entirely free of bleeding.
15:51:31 <oerjan> also, the multitasking still moves between different rooms
15:52:39 <oerjan> i use to use electric but it went *poof* just after i moved here.
15:52:59 <oerjan> as in, there was arcing when it died.
15:56:41 <oerjan> oh hm there was that automatic currying Taneb noticed, but i'm sure that cannot apply in positive position in data types/families
16:00:03 -!- shikhin has joined.
16:08:32 <oerjan> or anywhere polymorphic in the constraints
16:17:32 -!- Koen_ has joined.
16:20:29 -!- Phantom_Hoover has joined.
16:22:19 -!- shikhin has quit (Ping timeout: 272 seconds).
16:26:16 -!- shikhin has joined.
16:36:48 <ais523> ooh, new INTERCAL release
16:37:00 <ais523> esr released it to get the code out there before gitorious died
16:52:32 -!- shikhin has quit (Ping timeout: 246 seconds).
16:56:27 -!- Lymia has joined.
16:59:18 -!- vodkode_ has joined.
17:01:20 -!- shikhin has joined.
17:01:37 -!- shikhin has quit (Changing host).
17:01:37 -!- shikhin has joined.
17:05:38 -!- oerjan has quit (Quit: leaving).
17:12:17 -!- Xeironis has joined.
17:23:00 -!- vodkode_ has quit (Ping timeout: 264 seconds).
17:26:17 -!- Lymia has quit (Ping timeout: 256 seconds).
17:28:01 -!- vodkode_ has joined.
17:29:49 -!- mihow has joined.
17:33:16 -!- vodkode_ has quit (Ping timeout: 248 seconds).
17:35:46 -!- vodkode_ has joined.
17:37:28 <shachaf> oerjan: whoa, I missed the whole thing.
17:37:43 <lambdabot> oerjan asked 3h 45m 22s ago: Can you test (you need ImpredicativeTypes) whether typeRep (Proxy :: Proxy (((),()) => ())) == typeRep (Proxy :: Proxy (((),()) -> ()))
17:37:43 <lambdabot> oerjan said 2h 23m 14s ago: Never mind, Taneb helped; see https://ghc.haskell.org/trac/ghc/ticket/9858#comment:76
17:41:16 <int-e> . o O ( Why do you tempt me to give a tautological answer? )
17:43:44 <ais523> wouldn't the tautological answer there be "because oerjan isn't awake", which doesn't actually answer the question?
17:44:34 <int-e> The temptation arises from the fact that I cannot conceive of a more useful answer than that.
17:44:59 <shachaf> 06:52 <oerjan> why isn't shachaf awake :(
17:48:34 <int-e> shachaf: FWIW I consider this to be one of my character flaws. So I can't really complain.
17:49:09 <int-e> "this" being the tendency to give tautological answers.
17:59:18 -!- variable has joined.
18:00:53 <int-e> why is fungot awake :(
18:00:53 <fungot> int-e: you got to try that kind of explanation makes it easier
18:01:35 <int-e> okay, another review done.
18:01:42 <ais523> clearly, fungot is awake because fungot is awake
18:01:42 <fungot> ais523: i have complained about the lack of such a function
18:01:52 <ais523> and apparently doesn't know how to go to sleep
18:07:39 <int-e> Now as long as nobody mentions fungot by name we can pretend that it worked.
18:10:30 -!- hjulle has quit (Ping timeout: 256 seconds).
18:18:11 -!- hjulle has joined.
18:22:17 -!- ^v^v has quit (Read error: Connection reset by peer).
18:22:42 -!- ^v^v has joined.
18:24:00 <shachaf> oerjan: Makes me wonder whether there are other bugs involving ConstraintKinds that don't need Typeable. E.g. can you write (Show a, Show b) :~: (Show b, Show a) somehow?
18:28:53 -!- variable has changed nick to trout.
18:44:02 -!- ais523 has quit.
18:52:29 -!- nys has joined.
19:00:16 -!- shikhin_ has joined.
19:02:34 -!- idris-bot has quit (Quit: Terminated).
19:03:24 -!- shikhin has quit (Ping timeout: 248 seconds).
19:04:05 -!- shikhin_ has changed nick to shikhin.
19:09:17 -!- mihow has quit (Ping timeout: 248 seconds).
19:12:09 -!- mihow has joined.
19:22:12 -!- ^v has joined.
19:22:14 -!- variable has joined.
19:22:18 -!- trout has quit (Remote host closed the connection).
19:24:44 -!- ^v^v has quit (Ping timeout: 256 seconds).
19:28:59 -!- variable has quit (Remote host closed the connection).
19:29:25 -!- variable has joined.
19:45:21 -!- variable has quit (Remote host closed the connection).
20:03:30 -!- Lymia has joined.
20:33:36 <int-e> shachaf: regarding unicodesyntax, I'm going to patch my ghc.
20:34:15 <int-e> (and update #8959 accordingly once it works)
20:34:44 -!- Phantom_Hoover has quit (Read error: Connection reset by peer).
20:37:48 -!- Phantom_Hoover has joined.
20:38:22 -!- variable has joined.
20:44:11 <HackEgo> [wiki] [[Special:Log/newusers]] create * AnonymousAnomaly * New user account
20:47:49 -!- mihow has quit (Quit: mihow).
20:53:34 -!- Koen_ has quit (Quit: The struct held his beloved integer in his strong, protecting arms, his eyes like sapphire orbs staring into her own. "W-will you... Will you union me?").
20:59:37 -!- ProofTechnique has quit (Quit: ZNC - http://znc.in).
21:08:13 -!- ProofTechnique has joined.
21:08:34 <HackEgo> [wiki] [[Gott]] N http://esolangs.org/w/index.php?oldid=42269 * AnonymousAnomaly * (+143) Gott is an esoteric programming language that uses only for loops.
21:12:46 -!- ProofTechnique has quit (Ping timeout: 252 seconds).
21:13:29 -!- idris-bot has joined.
21:17:44 <HackEgo> [wiki] [[Gott]] http://esolangs.org/w/index.php?diff=42270&oldid=42269 * AnonymousAnomaly * (+826)
21:20:54 -!- Lymia has quit (Ping timeout: 256 seconds).
21:22:20 -!- oerjan has joined.
21:24:36 <oerjan> <shachaf> why isn't oerjan awake :( <-- the question assumes facts not in evidence hth
21:25:03 * oerjan was, at that time, probably showering.
21:25:04 -!- mihow has joined.
21:25:16 -!- Xeironis has left ("Konversation terminated!").
21:25:41 <oerjan> um i wasn't going either to or from bed
21:25:52 <oerjan> just preparing to leave the house.
21:26:04 <shachaf> <shachaf> It's a bit funny that GHC's normalization is exposed by type equality, so that "(Foo a, Bar a) => a" unifies with "Foo a => Bar a => a" but not with "(Bar a, Foo a) => a"
21:26:48 -!- idris-bot has quit (Quit: Terminated).
21:26:52 <oerjan> basically, they haven't worked too hard on making type inference of constraints be flexible.
21:27:08 <oerjan> (or maybe they have and gave up.)
21:27:42 -!- idris-bot has joined.
21:28:03 -!- AnotherTest has quit (Remote host closed the connection).
21:28:10 <oerjan> <shachaf> oerjan: whoa, I missed the whole thing. <-- on the bright side, you got credited.
21:28:46 <shachaf> oerjan: to be fair, what sort of person would even do that sort of thing with constraints
21:29:51 <shachaf> I haven't seen even edwardk make GADTs/type families with arguments that require constraint unification.
21:29:58 <oerjan> in fact, i greatly suspect he'd like it if the outcome of this was to make the (,) :: Constraint -> Constraint -> Constraint etc. entirely separately referencable entities.
21:30:15 <shachaf> Oh, sure, that's a much more reasonable outcome.
21:30:28 <shachaf> Given that you can't even get at that (,) right now.
21:31:26 <shachaf> Anyway, after that's fixed, SafeHaskell is *sure* to be bulletproof!
21:32:14 -!- fractal has quit (Ping timeout: 256 seconds).
21:32:48 -!- merdach has quit (Ping timeout: 256 seconds).
21:32:49 -!- pikhq has quit (Ping timeout: 256 seconds).
21:33:06 -!- merdach has joined.
21:33:56 -!- edirc has quit (Ping timeout: 256 seconds).
21:34:42 -!- pikhq has joined.
21:34:50 -!- perrier_ has joined.
21:35:04 -!- mhi^ has quit (Ping timeout: 256 seconds).
21:35:26 -!- dianne_ has joined.
21:36:32 -!- mhi^ has joined.
21:36:46 <HackEgo> [wiki] [[Gott]] http://esolangs.org/w/index.php?diff=42271&oldid=42270 * AnonymousAnomaly * (+453)
21:36:49 -!- perrier has quit (Ping timeout: 265 seconds).
21:36:49 -!- dianne has quit (Ping timeout: 265 seconds).
21:37:06 <HackEgo> [U+006E LATIN SMALL LETTER N] [U+2060 WORD JOINER]
21:38:34 <HackEgo> [wiki] [[Gott]] http://esolangs.org/w/index.php?diff=42272&oldid=42271 * AnonymousAnomaly * (+437)
21:38:39 -!- Lymia has joined.
21:39:39 -!- mihow has quit (Quit: mihow).
21:39:49 -!- fractal has joined.
21:41:28 -!- variable has changed nick to constant.
21:42:35 -!- TieSleep has quit (Read error: Connection reset by peer).
21:43:06 <lambdabot> Functor f => (a -> b) -> f a -> f b
21:46:18 <shachaf> :t fmap :: Monad m => (a -> b) -> m a -> m b -- p. fancy
21:46:37 -!- constant has quit (Quit: 1 found in /dev/zero).
21:54:18 -!- variable has joined.
21:56:51 -!- ProofTechnique has joined.
21:57:13 -!- vodkode_ has quit (Ping timeout: 264 seconds).
22:04:00 <lambdabot> ‘F.toList’ (imported from Data.Foldable),
22:09:13 -!- mihow has joined.
22:11:08 -!- ProofTechnique has quit (Ping timeout: 264 seconds).
22:14:01 <lambdabot> ‘F.toList’ (imported from Data.Foldable),
22:20:27 <int-e> :k () :: Constraint
22:22:48 -!- FatBack has joined.
22:23:24 -!- GeekDude has quit (Quit: {{{}}{{{}}{{}}}{{}}} (www.adiirc.com)).
22:23:40 <int-e> :k (() :: Constraint)
22:23:41 <lambdabot> Not in scope: type constructor or class ‘Constraint’
22:23:41 <lambdabot> Perhaps you meant ‘Contains’ (imported from Control.Lens)
22:25:02 -!- Patashu has joined.
22:25:46 -!- ProofTechnique has joined.
22:27:58 <HackEgo> [wiki] [[Gott]] http://esolangs.org/w/index.php?diff=42273&oldid=42272 * AnonymousAnomaly * (+811)
22:28:31 <oerjan> after all that work to avoid name clashes
22:29:53 -!- ^v has quit (Read error: Connection reset by peer).
22:30:18 -!- ^v has joined.
22:31:07 <HackEgo> [wiki] [[Gott]] http://esolangs.org/w/index.php?diff=42274&oldid=42273 * AnonymousAnomaly * (+63)
22:31:44 <HackEgo> [wiki] [[Gott]] http://esolangs.org/w/index.php?diff=42275&oldid=42274 * AnonymousAnomaly * (+0)
22:32:46 <int-e> funny, this module exports nothing: http://sprunge.us/XUNE?hs
22:34:41 <int-e> :k (() :: Constraint)
22:34:57 <int-e> :k () :: Constraint -- this appears to be a ghci bug
22:36:16 <oerjan> huh indeed it doesn't seem to export anything
22:37:09 <shachaf> type A = () :: ... has the same issue.
22:37:50 <int-e> if I just put an extra pair of parentheses there, will that break anything?
22:37:55 <lambdabot> Not in scope: data constructor ‘Maybe’
22:37:55 <lambdabot> Perhaps you meant variable ‘maybe’ (imported from Data.Maybe)
22:40:34 -!- FatBack has set topic: penis.
22:41:06 -!- ChanServ has set channel mode: +o oerjan.
22:41:08 -!- int-e has set topic: RIP Misao Okawa | I'm a fungot trapped in a channel full of weirdos | https://dl.dropboxusercontent.com/u/2023808/wisdom.pdf http://codu.org/logs/_esoteric/ http://tunes.org/~nef/logs/esoteric/.
22:41:19 -!- oerjan has set channel mode: +b *!*Fat@*.neo.res.rr.com.
22:41:19 -!- oerjan has kicked FatBack Go to Hell.
22:41:39 <oerjan> ...that's just the reaction they wanted, wasn't it.
22:41:53 -!- oerjan has set channel mode: -o oerjan.
22:41:58 <int-e> if it happens again, use your powers to set +t
22:42:04 -!- ChanServ has set channel mode: +o oerjan.
22:42:05 <int-e> (temporarily at least)
22:42:19 -!- oerjan has set channel mode: +tsric.
22:42:55 -!- oerjan has set channel mode: -sric.
22:43:11 * int-e wonders what +r is...
22:43:19 <oerjan> i cannot remember, was it +c or +C
22:43:37 <oerjan> int-e: it's already happened, ais523 banned em yesterday
22:43:44 <int-e> ah. block unidentified
22:44:04 <oerjan> variable: i am quite sure irssi doesn't use /raw
22:44:17 <variable> * cmode : +C - Disable CTCP. All CTCP messages to the channel, except ACTION,
22:44:25 <int-e> +c filters color, I hear some people here like color.
22:44:34 <variable> * cmode : +c - No color. All color codes in messages are stripped.
22:44:36 <int-e> https://freenode.net/using_the_network.shtml works.
22:44:44 <oerjan> variable: my client doesn't use /raw
22:44:56 <int-e> it uses /quote, hth
22:44:57 <variable> oerjan, oh, so just direct /help cmode
22:45:04 -!- oerjan has set channel mode: -o oerjan.
22:45:30 <oerjan> no, /help cmode gives irssi's own help, which is empty
22:47:06 <shachaf> oerjan: use glguy's fancy new irc client hth
22:47:34 <int-e> does it run on a terminal?
22:48:07 <int-e> does it look like irssi?
22:48:53 <int-e> (I think I've already invested too much time in customizing irssi)
22:49:25 <shachaf> But this client has all sorts of great features.
22:49:41 <shachaf> And also if you tell glguy what you're missing he'll implement it.
22:50:44 <oerjan> int-e: huh why doesn't Constraint get exported
22:52:34 <oerjan> huh it's just Constraint, too
22:53:17 <oerjan> (this with 7.8.3, naturally)
22:53:46 -!- variable has changed nick to constant.
22:59:20 <oerjan> int-e: probably a ghc bug?
22:59:44 <int-e> Maybe, I'm asking #ghc before I put in on Trac.
23:00:40 <int-e> (I did verify that this doesn't happen with just any empty data type, perhaps it's a builtin identifiers thing.)
23:01:37 <oerjan> i verified that Any and Down worked...
23:01:53 <oerjan> (just random ones that aren't prelude or containing #)
23:02:15 <int-e> oh, it's an indirect import thing.
23:02:46 <int-e> (Constraint is "defined" in Ghc.Prim)
23:03:17 <oerjan> but so is a _lot_ of GHC.Exts, no
23:04:32 <oerjan> xor# works just fine, and is from there too
23:04:50 <int-e> I don't know what went wrong in my test, cannot reproduce it anymore.
23:05:39 <int-e> the one where I thought that a reexport hid a reexported identifier
23:07:20 <int-e> "the one"? the incident, I guess.
23:08:05 <oerjan> hm * is also in GHC.Prim but not in GHC.Exts
23:08:18 * shachaf is at computer now, tries to figure out what bug is being discussed.
23:08:22 <int-e> I have not tried to reexport *.
23:08:36 <shachaf> Oh, the Constraint export paste above.
23:09:02 <int-e> (since I don't really know how to refer to it in an import or export list)
23:09:23 <int-e> (or what extension I need for that to work)
23:09:29 -!- ^v^v has joined.
23:09:35 <int-e> (assuming it's possible at all)
23:09:38 <oerjan> oh right the source links weren't working in the 7.10 haddocks
23:10:41 <oerjan> int-e: it just seems that GHC.Exts reexports all of GHC.Prim, so * is also excluded there
23:11:54 <int-e> GHC.Exts has an explicit export for Constraint, figures.
23:12:04 -!- shikhin has quit (Quit: leaving).
23:12:32 -!- ^v has quit (Ping timeout: 256 seconds).
23:13:40 -!- ProofTechnique has quit (Ping timeout: 256 seconds).
23:13:41 <int-e> no explanation :( https://github.com/ghc/ghc/commit/c0e32a32a3f20a9310e7321a8a96acfe0ef0d0f7
23:14:53 <oerjan> and it still exported GHC.Prim too
23:15:46 <shachaf> They should've just given Constraint a symbolic name like *
23:15:49 <oerjan> the most "obvious" cause to me is that this affects kind-only identifiers
23:15:57 <shachaf> Then it wouldn't've needed an import.
23:16:25 <oerjan> which cannot be defined presently iirc
23:16:41 <oerjan> which is why i wondered about *
23:17:08 <oerjan> shachaf: but then it'd clash with type operators
23:17:28 <oerjan> yes but it'd be a _new_ clash.
23:17:48 <shachaf> Just give it a name starting with :
23:17:55 <shachaf> No one would name a type operator that.
23:18:07 * oerjan swats shachaf -----###
23:18:47 <shachaf> The letdown is that I've said much more swatworthy things.
23:19:08 <int-e> don't worry, the swatter is reusable.
23:19:44 <oerjan> only if someone adds feather to it
23:19:44 <int-e> editing the codu logs may be an option
23:22:26 <int-e> (hmm, a minority report)
23:28:27 -!- zadock has joined.
23:38:08 -!- ProofTechnique has joined.
23:42:57 -!- ProofTechnique has quit (Ping timeout: 264 seconds).
23:45:59 -!- Lymia has quit (Quit: Hug~♪).
00:21:31 -!- iamevn_ has joined.
00:23:06 <oerjan> gah it's my monthly reddit shock ad
00:24:29 -!- iamevn has quit (Ping timeout: 248 seconds).
00:27:23 -!- Lymia has joined.
00:27:35 -!- Lymia has quit (Changing host).
00:27:35 -!- Lymia has joined.
00:30:17 -!- Phantom_Hoover has quit (Remote host closed the connection).
00:48:30 <int-e> gah, another wasted ghc build
00:50:18 <int-e> I had copied a file to mk/build.mk.7.10.1 instead of build.mk
00:55:16 <int-e> so I got a full build, but without DYNAMIC_GHC_PROGRAMS
00:56:59 -!- f|`-`|f has quit (Read error: Connection reset by peer).
00:57:31 -!- f|`-`|f has joined.
00:58:40 <int-e> paraphrasing #haskell, unsafeCoerce is a fixed point of ($ id)
00:59:04 -!- stuntaneous has joined.
00:59:09 -!- stuntaneous has quit (Excess Flood).
00:59:24 -!- stuntaneous has joined.
00:59:28 -!- stuntaneous has quit (Excess Flood).
00:59:36 -!- elliott has quit (Ping timeout: 250 seconds).
00:59:41 <lambdabot> Occurs check: cannot construct the infinite type: b ~ (a -> a) -> b
00:59:41 <lambdabot> Expected type: ((a -> a) -> b) -> (a -> a) -> b
00:59:49 -!- stuntaneous has joined.
00:59:51 -!- stuntaneous has quit (Excess Flood).
01:00:11 -!- stuntaneous has joined.
01:00:14 -!- stuntaneous has quit (Excess Flood).
01:00:20 -!- elliott has joined.
01:00:39 <int-e> > :t (unsafeCoerce $ id) :: a -> b
01:00:39 <int-e> (unsafeCoerce $ id) :: a -> b :: a -> b
01:00:41 <lambdabot> <hint>:1:1: parse error on input ‘:’
01:00:43 -!- elliott has changed nick to Guest24483.
01:00:55 <shachaf> :t let uc :: a -> b; uc = undefined in ($ id) uc
01:01:00 <int-e> but the point is, it's operationally the same as unsafeCoerce, too.
01:01:02 -!- stuntaneous has joined.
01:01:03 <shachaf> it has an even more general type
01:01:05 -!- stuntaneous has quit (Excess Flood).
01:01:25 <int-e> shachaf: but without restricting the type it's liable to crash
01:01:40 <shachaf> It's liable to crash anyway.
01:01:44 -!- stuntaneous has joined.
01:01:47 -!- stuntaneous has quit (Excess Flood).
01:01:49 <int-e> true, there's that
01:02:08 -!- stuntaneous has joined.
01:02:45 <shachaf> What's the least fixed point of ($ id) in untyped lambda calculus?
01:03:02 <int-e> maybe unsafeCoerce should really have type unsafeCoerce :: a.
01:04:51 <int-e> let t = t (\y -> y) in t -- doesn't look useful after unfolding it into a Böhm tree.
01:04:54 <oerjan> shachaf: pretty sure it's bottom hth
01:05:38 <shachaf> oerjan: and what's the greatest fixed point twh
01:05:39 -!- GeekDude has joined.
01:06:07 <oerjan> does there have to be one
01:06:10 <int-e> (meh we're working in different domains)
01:06:29 <shachaf> oerjan: i never said it exists
01:07:12 <oerjan> unlambda v is a bit higher, i think
01:07:25 <oerjan> which is basically fix const
01:23:21 -!- mihow has quit (Quit: mihow).
01:52:00 -!- zzo38 has joined.
02:26:50 -!- nys has quit (Quit: quit).
02:46:52 -!- oerjan has quit (Quit: cetera).
03:00:07 <HackEgo> [wiki] [[Talk:Time Out]] http://esolangs.org/w/index.php?diff=42276&oldid=42248 * Esowiki201529A * (+26)
03:15:00 -!- constant has quit (Quit: 1 found in /dev/zero).
03:37:21 <izabera> a hacker made this almost 3 years ago
03:37:24 <izabera> `` a=abcdef; n= eval 'printf %s "${a[0]"{1..'${#a}'}":(-(++n)):1}"' "$'\n'"
03:37:57 <izabera> `` a=abcdef; n= eval 'printf %s "${a[0]"{1..'${#a}'}":(-(++n)):1}"' "$'\n'"
03:38:07 <izabera> `` a=abcdef; eval eval printf %s '"\"\${a:"'{${#a}..0}':1}\"' "$'$\'\\n\''"
03:39:35 <izabera> mine is much more straigthforward :|
03:39:45 <izabera> but... it works in bash/ksh/zsh
03:39:51 <izabera> his version only works in bash
03:41:34 -!- ProofTechnique has joined.
03:56:03 -!- fractal has quit (Changing host).
03:56:03 -!- fractal has joined.
04:08:04 -!- MDream has joined.
04:08:24 -!- MDude has quit (Ping timeout: 244 seconds).
04:08:55 -!- adu has joined.
04:16:59 -!- MDream has quit (Ping timeout: 256 seconds).
04:18:06 -!- GeekDude has quit (Quit: {{{}}{{{}}{{}}}{{}}} (www.adiirc.com)).
04:44:06 -!- hjulle has quit (Ping timeout: 250 seconds).
04:44:31 -!- incomprehensibly has quit (Ping timeout: 252 seconds).
04:45:15 -!- ocharles_ has quit (Ping timeout: 252 seconds).
04:45:45 -!- vodkode_ has joined.
04:47:15 -!- ocharles_ has joined.
04:48:17 -!- incomprehensibly has joined.
04:50:03 -!- vodkode_ has quit (Remote host closed the connection).
04:51:31 <shachaf> int-e: For monotonic functions does o behave the way I wanted it to with respect to O?
04:56:12 -!- variable has joined.
04:58:10 <Guest24483> coppro: you being a nethack dev is an april fool's, right
04:59:32 <pikhq> Guest24483: IIRC no, he's been involved in nethack for a while.
05:09:20 -!- vodkode_ has joined.
05:11:09 -!- zadock has quit (Quit: Leaving).
05:11:45 -!- variable has quit (Quit: 1 found in /dev/zero).
05:18:01 -!- variable has joined.
05:25:13 -!- variable has quit (Ping timeout: 250 seconds).
05:52:16 <zzo38> Is "Do not destroy" the title of any melody?
05:53:06 <izabera> write one and call it like that
05:54:36 -!- adu has quit (Quit: adu).
05:55:07 <zzo38> Footnotes in the book of Psalms in the version I have say that it probably is, although some psalms are just marked "Do not destroy" and it isn't quite clear why; the scholars who wrote the footnotes seem to believe it is probably the title of a melody that is now lost (I suppose, presumably, they had no musical notation at the time so they just named the melody instead).
07:41:49 -!- dianne_ has quit (Quit: byeannes).
07:43:34 -!- gamemanj has joined.
07:44:04 -!- PinealGlandOptic has joined.
07:59:03 <int-e> shachaf: no, you can construct staircase functions with fast growing stairs and still get similar counterexamples to the alternating function one.
08:04:00 <int-e> shachaf: for example, f(n) = 2^2^floor(log_2(log_2(n)) (which maps [2,4) to 2, [4,16) to 4, [16,256) to 16, [256,65536) to 256, etc; it's O(n), not o(n), and n is not O(f)).
08:07:46 <shachaf> Is there an obvious relationship between o and O?
08:08:23 <int-e> other than o(f) being a strict subset of O(f), none that I'm aware of.
08:10:26 <int-e> O(f) \ o(f) has no nice characterization, I think.
08:19:21 -!- stuntaneous_o has joined.
08:20:30 -!- stuntaneous has quit (Ping timeout: 256 seconds).
08:26:21 -!- stuntaneous_o has quit (Ping timeout: 246 seconds).
08:30:11 -!- stuntaneous has joined.
08:30:14 -!- stuntaneous has quit (Excess Flood).
08:33:36 -!- stuntaneous has joined.
08:33:39 -!- stuntaneous has quit (Excess Flood).
08:33:54 -!- stuntaneous has joined.
08:33:57 -!- stuntaneous has quit (Excess Flood).
08:34:17 -!- stuntaneous has joined.
08:34:20 -!- stuntaneous has quit (Excess Flood).
08:34:38 -!- stuntaneous has joined.
08:34:41 -!- stuntaneous has quit (Excess Flood).
08:34:58 -!- stuntaneous has joined.
08:35:01 -!- stuntaneous has quit (Excess Flood).
08:35:13 -!- stuntaneous has joined.
08:35:16 -!- stuntaneous has quit (Excess Flood).
08:35:31 -!- stuntaneous has joined.
08:35:34 -!- stuntaneous has quit (Excess Flood).
08:35:49 -!- stuntaneous has joined.
08:35:51 -!- stuntaneous has quit (Excess Flood).
08:36:11 -!- stuntaneous has joined.
08:36:14 -!- stuntaneous has quit (Excess Flood).
08:36:30 -!- stuntaneous has joined.
08:36:33 -!- stuntaneous has quit (Excess Flood).
08:36:47 -!- stuntaneous has joined.
08:36:50 -!- stuntaneous has quit (Excess Flood).
08:37:04 -!- stuntaneous has joined.
08:37:07 -!- stuntaneous has quit (Excess Flood).
08:37:27 -!- stuntaneous has joined.
08:37:30 -!- stuntaneous has quit (Excess Flood).
08:37:52 -!- stuntaneous has joined.
08:37:55 -!- stuntaneous has quit (Excess Flood).
08:38:08 -!- stuntaneous has joined.
08:38:10 -!- stuntaneous has quit (Excess Flood).
08:38:27 -!- stuntaneous has joined.
08:38:30 -!- stuntaneous has quit (Excess Flood).
08:38:44 -!- stuntaneous has joined.
08:38:47 -!- stuntaneous has quit (Excess Flood).
08:39:02 -!- stuntaneous has joined.
08:39:05 -!- stuntaneous has quit (Excess Flood).
08:39:20 -!- stuntaneous has joined.
08:39:22 -!- stuntaneous has quit (Excess Flood).
08:39:42 -!- stuntaneous has joined.
08:39:44 -!- stuntaneous has quit (Excess Flood).
08:40:07 -!- stuntaneous has joined.
08:40:10 -!- stuntaneous has quit (Excess Flood).
08:40:24 -!- stuntaneous has joined.
08:40:27 -!- stuntaneous has quit (Excess Flood).
08:40:41 -!- stuntaneous has joined.
08:40:44 -!- stuntaneous has quit (Excess Flood).
08:40:58 -!- stuntaneous has joined.
08:41:01 -!- stuntaneous has quit (Excess Flood).
08:41:15 -!- stuntaneous has joined.
08:41:18 -!- stuntaneous has quit (Excess Flood).
08:41:34 -!- stuntaneous has joined.
08:41:37 -!- stuntaneous has quit (Excess Flood).
08:41:50 -!- stuntaneous has joined.
08:41:53 -!- stuntaneous has quit (Excess Flood).
08:42:13 -!- stuntaneous has joined.
08:42:16 -!- stuntaneous has quit (Excess Flood).
08:42:31 -!- stuntaneous has joined.
08:42:34 -!- stuntaneous has quit (Excess Flood).
08:42:49 -!- stuntaneous has joined.
08:42:51 -!- stuntaneous has quit (Excess Flood).
08:43:13 -!- stuntaneous has joined.
08:43:16 -!- stuntaneous has quit (Excess Flood).
08:43:30 -!- stuntaneous has joined.
08:43:33 -!- stuntaneous has quit (Excess Flood).
08:43:52 -!- stuntaneous has joined.
08:43:54 -!- stuntaneous has quit (Excess Flood).
08:44:10 -!- stuntaneous has joined.
08:44:12 -!- stuntaneous has quit (Excess Flood).
08:44:29 -!- stuntaneous has joined.
08:44:31 -!- stuntaneous has quit (Excess Flood).
08:44:48 -!- stuntaneous has joined.
08:44:50 -!- stuntaneous has quit (Excess Flood).
08:45:07 -!- stuntaneous has joined.
08:45:07 <gamemanj> Stuntaneous is yet another unfortunate victim of autojoin...
08:45:09 -!- stuntaneous has quit (Excess Flood).
08:45:22 -!- stuntaneous has joined.
08:45:24 -!- stuntaneous has quit (Excess Flood).
08:45:45 -!- stuntaneous has joined.
08:45:47 -!- stuntaneous has quit (Excess Flood).
08:46:03 -!- stuntaneous has joined.
08:46:04 -!- stuntaneous has quit (Excess Flood).
08:46:43 -!- stuntaneous has joined.
08:46:45 -!- stuntaneous has quit (Excess Flood).
08:46:58 <int-e> . o O ( thank irssi for selective ignores... /ignore stuntaneous JOINS PARTS QUITS )
08:47:00 -!- stuntaneous has joined.
08:47:02 -!- stuntaneous has quit (Excess Flood).
08:47:18 -!- stuntaneous has joined.
08:47:20 -!- stuntaneous has quit (Excess Flood).
08:47:35 -!- stuntaneous has joined.
08:47:37 -!- stuntaneous has quit (Excess Flood).
08:47:52 -!- stuntaneous has joined.
08:47:54 -!- stuntaneous has quit (Excess Flood).
08:48:10 -!- stuntaneous has joined.
08:48:13 -!- stuntaneous has quit (Excess Flood).
08:48:28 -!- stuntaneous has joined.
08:48:30 -!- stuntaneous has quit (Excess Flood).
08:48:44 -!- stuntaneous has joined.
08:48:46 -!- stuntaneous has quit (Excess Flood).
08:49:02 -!- stuntaneous has joined.
08:49:04 -!- stuntaneous has quit (Excess Flood).
08:49:20 -!- stuntaneous has joined.
08:49:30 -!- zadock has joined.
09:08:30 -!- shikhin has joined.
09:12:25 -!- vodkode_ has quit (Ping timeout: 245 seconds).
09:39:06 -!- Guest61975 has joined.
09:40:23 -!- Guest61975 has left.
09:42:59 -!- f|`-`|f has quit (Ping timeout: 252 seconds).
10:09:04 -!- Guest61975 has joined.
10:39:43 -!- AnotherTest has joined.
10:44:34 <HackEgo> Guest61975: 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.)
11:00:16 -!- Guest61975 has left.
11:16:15 -!- hjulle has joined.
11:29:33 -!- gamemanj has quit (Read error: Connection reset by peer).
11:32:58 -!- shikhin has quit (Quit: leaving).
11:44:30 -!- Guest61975 has joined.
11:49:45 -!- AnotherTest has quit (Ping timeout: 265 seconds).
12:02:07 -!- SopaXorzTaker has joined.
12:17:59 -!- shikhin has joined.
12:45:50 -!- oerjan has joined.
12:52:46 <oerjan> > typeRep (Proxy :: Proxy ((((),()),()) => ())
12:52:47 <lambdabot> parse error (possibly incorrect indentation or mismatched brackets)
12:52:54 <oerjan> > typeRep (Proxy :: Proxy ((((),()),()) => ()))
12:52:56 <lambdabot> Illegal polymorphic or qualified type: (((), ()), ()) => ()
12:52:56 <lambdabot> Perhaps you intended to use ImpredicativeTypes
12:52:56 <lambdabot> In an expression type signature: Proxy ((((), ()), ()) => ())
12:53:04 <oerjan> ok that's still missing
12:54:11 <oerjan> > typeRep (Proxy :: Proxy (((),()) :: Constraint)) == typeRep (Proxy :: Proxy ((),()))
13:02:34 <oerjan> > let x :: forall a. (a b c ~ (((),()) :: Constraint)) => TypeRep; x = typeRep (Proxy :: Proxy a) in x
13:02:35 <lambdabot> Not in scope: type variable ‘b’Not in scope: type variable ‘c’
13:03:21 <oerjan> > let x :: forall a. (a b c ~ ((b,c) :: Constraint)) => TypeRep; x = typeRep (Proxy :: Proxy a) in x
13:03:22 <lambdabot> Not in scope: type variable ‘b’Not in scope: type variable ‘c’Not in scope: ...
13:03:23 <int-e> sorry, going to take away the toy for some minutes.
13:03:25 -!- lambdabot has quit (Quit: brb).
13:04:26 <oerjan> i was trying to see if you could get at (,) :: Constraint -> Constraint -> Constraint indirectly
13:07:05 <int-e> well, :t understands unicode syntax now (and still prints types in ASCII)
13:08:03 -!- lambdabot has joined.
13:08:25 <oerjan> > let x :: forall a b c. (a b c ~ ((b,c) :: Constraint)) => TypeRep; x = typeRep (Proxy :: Proxy a) in x
13:10:36 <oerjan> > typeRep (Proxy :: Proxy (() ~ ()))
13:10:46 <oerjan> hm ~ has the kind, useless
13:11:30 <oerjan> i think maybe you actually need the () base case to construct ambiguous things of the same kind, but i'm not entirely counting on it.
13:14:29 <int-e> This was amazingly simple. https://ghc.haskell.org/trac/ghc/attachment/ticket/8959/ghc-print-unicode-flag.patch
13:15:39 <oerjan> GHC simple? what heresy is this?
13:21:40 <oerjan> Guest24483: you are fooling no one hth
13:24:32 <fungot> int-e: gah. i've inadvertently gone and added another project to my ever-increasing list. so there's really no difference between eof and), respectively, too.)
13:24:49 <int-e> fungot: I feel your pain
13:24:49 <fungot> int-e: maybe ' bureaucracy' isn't the opposite of partial? fnord?
13:25:02 <int-e> fungot: that's an interesting thought
13:25:02 <fungot> int-e: it's just not the ants.
13:36:11 -!- SopaXorzTaker has quit (Quit: Leaving).
13:42:46 -!- lambdabot has quit (Quit: sorry, let me try that again...).
13:47:19 -!- lambdabot has joined.
13:51:31 <mroman> fungot: Do your people celebrate easter?
13:51:32 <fungot> mroman: gah. paul graham you program form the bottom up instead of top down...
13:52:32 <int-e> fungot: you're better than a magic 8ball
13:52:32 <fungot> int-e: and it isn't available in debian. debian is known at run-time, but the meta-language in which macros are your fnord bits?
13:52:46 <int-e> fungot: and almost as mysterious
13:52:46 <fungot> int-e: omg c++ rox0rz rofl rofl!!! i want a programming language
13:54:04 -!- SopaXorzTaker has joined.
13:58:07 -!- SopaXorzTaker has quit (Read error: Connection reset by peer).
14:03:01 -!- shikhin_ has joined.
14:03:33 -!- AnotherTest has joined.
14:04:50 -!- shikhin has quit (Disconnected by services).
14:05:03 -!- shikhin_ has changed nick to shikhin.
14:12:29 -!- `^_^v has joined.
14:22:21 <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
14:23:22 -!- oren has joined.
14:25:45 <Taneb> fungot, how are you doing?
14:25:45 <fungot> Taneb: you've all seen it, always building the answer up is much more
14:26:52 <int-e> fungot's on a roll
14:26:53 <fungot> int-e: machinecode is where it's at
14:26:55 <oerjan> hm the most recent girl genius seems to indicate that some time has passed since the battle with the beast
14:27:03 <oren> zzo38: Perhaps at some point, when people tended to reuse parchment after scraping the letters off, some monk thought it a good idea to mark the psalms he needed saved, as "do not destroy"?
14:28:20 <int-e> oerjan: ah well, you know sparks
14:28:24 <oren> And then the mark just got copied from copy to copy, until the reason was lost
14:28:26 <int-e> oerjan: it's probably less than a week
14:29:06 <oerjan> oren: this is the bible though, i somehow doubt they'd scribble in it?
14:29:07 <Taneb> oerjan, sparks are involved, progress can go quickly
14:29:15 <int-e> oerjan: how long did building the swinecopter-driven sleigh take, you think?
14:29:33 <int-e> and she did that all almost by herself
14:30:06 <oren> oerjan: Hmm... my aunt writes notes all over her bible, but i can see how in the era of handwritten books that mght be frownedupon
14:30:18 <oerjan> int-e: but in this case, the monks are also working on it, presumably not as fast
14:30:21 -!- variable has joined.
14:30:38 <int-e> oerjan: I know, she has some serious help there
14:30:47 <int-e> oerjan: and some of those monks are sparky too
14:31:03 <Taneb> oerjan, and the monks are REALLY GOOD at trains
14:32:17 <int-e> I wonder whether Martellus is helping
14:33:35 <oerjan> well, at least a few days though, i'd say, they've had time to calm down some.
14:34:00 <int-e> let's say 3 days and move on :)
14:34:10 <oerjan> and also, gil initially expected them to have gone already.
14:35:13 <int-e> I mean there still was smoke outside, presumably indicating leftovers from the carnage
14:37:11 <int-e> (technically, very little meat was involved... huh)
14:37:51 <oren> Should I evn bother putting "2 years Matlab experience" on my resume?
14:38:04 <oren> Does anyone outside of academia use it?
14:44:47 <int-e> fun site... http://www.itjobswatch.co.uk/jobs/uk/matlab.do
14:45:48 <int-e> so Matlab is about as popular as R, according to that site.
14:46:44 <int-e> I also thought that many of the toolboxes that Mathworks sells are not really made for academia but for real-life engineering and data analysis tasks.
14:47:02 <int-e> But I have virtually no personal Matlab experience.
14:47:33 <oren> Cool, so my time struggling to work with it in various courses was not wasted. Awsome
14:50:27 <fizzie> I have the same impression, that it does see real-life use.
14:50:39 <fizzie> (Something like Mathematica possibly rather less so?)
14:51:16 <fizzie> I haven't used Matlab outside of an academic context, but that's a pretty small sampling of jobs.
14:51:37 <int-e> I haven't used Matlab inside an academic context ;)
14:52:34 -!- copumpkin has joined.
14:52:41 <oren> Also I'm writing my resume in LaTeX... I wonder if anyone will recognize the Computer Modern font on my resume
14:53:34 <int-e> . o O ( "We have a special paper bin for resumes written in LaTeX." )
14:53:51 -!- SopaXorzTaker has joined.
14:53:59 <fizzie> If you want recognizability, Comic Sans would be a good choice.
14:54:57 <int-e> has anyone here played typerider and read the history of comic sans?
14:56:11 <fizzie> You forgot the colon. (But I haven't played it.)
14:56:50 <HackEgo> [wiki] [[Batch]] N http://esolangs.org/w/index.php?oldid=42277 * Esowiki201529A * (+24) redirect to "Batch file"
14:57:08 <int-e> fizzie: sorry, the colon got stuck in the middle of a level.
14:59:31 <HackEgo> [wiki] [[Special:Log/move]] move * Esowiki201529A * moved [[MuFuck]] to [[ΜFuck]]
15:01:02 <HackEgo> [wiki] [[Special:Log/move]] move_redir * Esowiki201529A * moved [[ΜFuck]] to [[MuFuck]] over redirect
15:16:19 <HackEgo> [U+039C GREEK CAPITAL LETTER MU]
15:17:06 <int-e> Way to confuse people.
15:17:34 <int-e> Clearly Latin should be the one and only alphabet ;-)
15:18:11 <HackEgo> [wiki] [[Special:Log/move]] move_redir * Oerjan * moved [[MuFuck]] to [[ΜFuck]] over redirect: It's a good idea but needs a little change...
15:19:59 <oren> int-e: Clearly if unicode did Han unification they should, for the sake of fairness, do Phoenician Unification as well
15:20:01 <HackEgo> [wiki] [[ΜFuck]] http://esolangs.org/w/index.php?diff=42284&oldid=42282 * Oerjan * (-2) Different template, also bold
15:20:07 <fizzie> The thing with µ and μ is pretty bad.
15:20:32 <HackEgo> [U+03BC GREEK SMALL LETTER MU]
15:20:37 <int-e> oerjan: did you mean: ΜΦυκ
15:20:59 <oren> th other one is the micro symbol for iupac
15:21:16 <fizzie> Yes, but I can only easily type µ, not μ.
15:22:03 <oren> I have greek mapped to `x* where x is any latin letter
15:22:52 <fizzie> Eat at Pectopah, the most popular restaurant chain of the Cyrillic world. (Ресторан.)
15:23:18 <oren> Ya ne ponimayu?
15:23:46 -!- yorick has quit (Quit: No Ping reply in 180 seconds.).
15:23:51 * oren does not quite know how to read cyrillic
15:24:01 <int-e> oren: it's the universal phrase, you can say that to anybody, anytime
15:24:14 <int-e> oren: nye, but close enough
15:24:36 <oerjan> oren: so how do you write an actual x?
15:24:47 <HackEgo> [U+0078 LATIN SMALL LETTER X]
15:24:53 <oren> with the key x
15:25:08 <int-e> (ah, not a trick question)
15:25:34 <int-e> or perhaps an actual `
15:25:34 -!- GeekDude has joined.
15:25:36 <oren> oerjan the ` is part of the sequence, and `` makes a `
15:26:10 -!- yorick has joined.
15:26:14 <HackEgo> [U+0465 CYRILLIC SMALL LETTER IOTIFIED E]
15:26:21 <int-e> I've never seen that one (except in gucharmap)
15:28:40 <oren> Probably an old character they need for historic works... like ゑ
15:29:09 <oren> (that's a hiragana 'we' )
15:29:54 <int-e> airplane crashing in the mountains
15:30:20 <int-e> oerjan: just freely interpreting ゑ
15:30:42 * oerjan needs to catch up on recent changes before it slips off the 30 day limit
15:31:09 <int-e> which 30 day limit, what, huh, stop changing the subject!
15:31:54 <int-e> Oh, on the wiki, I guess.
15:33:42 -!- zadock has quit (Quit: Leaving).
15:41:24 -!- copumpkin has quit (Quit: My MacBook Pro has gone to sleep. ZZZzzz…).
15:41:42 <HackEgo> [wiki] [[Special:Log/delete]] delete * Oerjan * deleted "[[Talk:QWERTY Keyboard Dot Language]]": content was: "xd" (and the only contributor was "[[Special:Contributions/80.222.241.129|80.222.241.129]]")
15:43:17 -!- ProofTechnique has quit (Ping timeout: 272 seconds).
15:43:41 <HackEgo> [wiki] [[Special:Log/delete]] delete * Oerjan * deleted "[[Talk:JSFuck]]": content was: "new Array().filter(callbackfn[, thisArg])" (and the only contributor was "[[Special:Contributions/Esowiki201529A|Esowiki201529A]]")
15:46:37 <HackEgo> [wiki] [[Special:Log/delete]] delete * Oerjan * deleted "[[Batch file]]": Not esoteric
15:47:09 <oerjan> i seem to be brutal today
15:50:24 <HackEgo> [wiki] [[Special:Log/delete]] delete * Oerjan * deleted "[[Batch]]": Redirect to deleted page
15:55:29 -!- ais523 has joined.
15:55:31 <HackEgo> [wiki] [[Special:Log/delete]] delete * Oerjan * deleted "[[ArrayZ]]": Author request: content before blanking was: "'''ArrayZ''' is a [[brainfuck]]-derived [[esoteric programming language]] created by [[User:GeorgeEpicGen]] in 2014 to serve one purpose only: to be as short-hand and confusing as possible. It was created over the course ..."
16:00:12 <HackEgo> [wiki] [[User talk:SuperJedi224]] M http://esolangs.org/w/index.php?diff=42285&oldid=42158 * Oerjan * (+51) unsigned, hoping I got time zone right
16:00:38 <oerjan> Guest24483: in the edit summary for the blanking
16:04:41 -!- AnotherTest has quit (Ping timeout: 252 seconds).
16:05:31 <HackEgo> [wiki] [[ReThue]] http://esolangs.org/w/index.php?diff=42286&oldid=42165 * Oerjan * (+17) wikify, not a good URL
16:05:44 -!- AnotherTest has joined.
16:09:20 <oerjan> stupid clicking noise from the ventilation system seems to be insisting on returning today
16:09:33 <oerjan> (it's always been _occasionally_ like this.)
16:10:11 -!- AnotherTest has quit (Ping timeout: 252 seconds).
16:10:27 -!- oerjan has quit (Quit: Should be going soon).
16:12:13 -!- SopaXorzTaker has quit (Ping timeout: 265 seconds).
16:14:22 -!- SopaXorzTaker has joined.
16:36:25 -!- ais523 has quit (Read error: Connection reset by peer).
16:36:31 -!- callforjudgement has joined.
16:36:35 -!- callforjudgement has changed nick to ais523.
16:37:32 -!- SopaXorzTaker has quit (Quit: Leaving).
16:39:15 -!- ProofTechnique has joined.
16:55:56 -!- ais523 has quit (Read error: Connection reset by peer).
16:56:07 -!- callforjudgement has joined.
16:56:16 -!- callforjudgement has changed nick to ais523.
16:58:09 <HackEgo> [wiki] [[ReThue]] http://esolangs.org/w/index.php?diff=42287&oldid=42286 * SuperJedi224 * (-18) Fixed source/
17:00:44 -!- Frooxius has quit (Quit: *bubbles away*).
17:03:53 -!- zadock has joined.
17:19:17 -!- SopaXorzTaker has joined.
17:24:27 -!- AnotherTest has joined.
17:25:20 -!- mihow has joined.
17:27:56 <oren> oerjan: grab the attitude adjustment tool
17:36:25 <HackEgo> [wiki] [[Special:Log/newusers]] create * Isaacg1 * New user account
17:39:43 <HackEgo> [wiki] [[Pyth]] http://esolangs.org/w/index.php?diff=42288&oldid=40981 * Isaacg1 * (+65)
17:40:29 <HackEgo> [wiki] [[Pyth]] http://esolangs.org/w/index.php?diff=42289&oldid=42288 * Isaacg1 * (+57) /* External resources */
17:42:27 <HackEgo> [wiki] [[Pyth]] http://esolangs.org/w/index.php?diff=42290&oldid=42289 * Isaacg1 * (-3232) /* Documentation */
17:49:18 <coppro> Guest24483: yes, it's part of an april fool's joke
17:49:45 <ais523> how is an april fools joke esolang any different from a regular esolang
17:50:00 <b_jonas> how is it different from a regular joke esolang?
17:51:46 <HackEgo> #!/bin/sh \ if [ $(date +%Y) = "$(basename "$0")" ] \ then echo "Hello, world!" \ fi
17:51:50 <HackEgo> #!/bin/sh \ if [ $(date +%Y) != "$(basename "$0")" ] \ then echo "Hello, world!" \ fi
17:52:06 <ais523> aha, 2015 is a language that /doesn't/ work in 2015?
17:54:22 <ais523> that's interesting in another way
17:54:27 <ais523> although I think http://esolangs.org/wiki/2014 is better
18:06:58 -!- Frooxius has joined.
18:09:37 -!- SopaXorzTaker has quit (Remote host closed the connection).
18:26:56 -!- stuntaneous_a has joined.
18:26:59 -!- stuntaneous_a has quit (Excess Flood).
18:27:17 -!- stuntaneous_a has joined.
18:27:19 -!- stuntaneous has quit (Ping timeout: 246 seconds).
18:27:19 -!- stuntaneous_a has quit (Excess Flood).
18:28:50 -!- f|`-`|f has joined.
18:30:27 -!- sebbu2 has joined.
18:31:09 -!- sebbu2 has quit (Changing host).
18:31:09 -!- sebbu2 has joined.
18:31:33 -!- sebbu has quit (Ping timeout: 250 seconds).
18:43:45 -!- callforjudgement has joined.
18:43:46 -!- ais523 has quit.
18:44:00 -!- callforjudgement has changed nick to ais523.
18:49:29 <HackEgo> [wiki] [[Time Out]] http://esolangs.org/w/index.php?diff=42291&oldid=42252 * Rottytooth * (+61)
18:49:32 <zzo38> I believe the problem with trying to do FM synth in .XM is that you cannot have a modulator envelope independent from the note frequency.
18:52:57 <zzo38> (Except for having multiple samples, I suppose, but even then it is not exact unless you do it for each note!!)
19:04:52 -!- nycs has joined.
19:07:42 -!- `^_^v has quit (Ping timeout: 250 seconds).
19:11:17 -!- callforjudgement has joined.
19:11:17 -!- ais523 has quit (Read error: Connection reset by peer).
19:11:28 -!- callforjudgement has changed nick to ais523.
19:13:16 -!- nycs has changed nick to `^_^v.
19:13:21 <oren> i have just been alerted, by the appearance of a procession outside, that there is a holiday today.
19:14:33 <zzo38> That's because it is Good Friday today
19:17:44 <zzo38> Don't you know these kind of thing?
19:18:50 -!- callforjudgement has joined.
19:18:55 -!- ais523 has quit (Read error: Connection reset by peer).
19:19:54 -!- callforjudgement has changed nick to ais523.
19:19:58 -!- ais523 has quit (Client Quit).
19:20:09 -!- callforjudgement has joined.
19:20:14 -!- callforjudgement has changed nick to ais523.
19:24:49 <oren> zzo38: I generally lose track of time when I'm really busy
19:27:03 <zzo38> Someone (who is an atheist) asked me, why is it good (if Jesus is dead)? I said, it is good because you don't have to go to work.
19:27:28 <oren> Hm... maybe it
19:27:37 <oren> is like "god friday"?
19:27:58 <zzo38> I don't know, possibly
19:29:02 * oren afk, getting cotton candy
19:36:08 -!- `^_^v has quit (Ping timeout: 256 seconds).
19:37:37 -!- `^_^v has joined.
19:38:02 <coppro> zzo38: Christian teaching is that Jesus' death is the punishment for humanity's sin. So by the crucixion, the faithful's sins are absolved and they do not need to suffer the punishments themselves
19:39:39 <zzo38> coppro: Yes I know that.
19:41:47 <zzo38> But I think if it is good because sometimes you don't have to go to work!
19:45:29 <zzo38> Some people doubt Jesus's existence. Some others believe he existed but was not resurrected. I am of the latter, but still must say I don't know for sure (I am no historian!); however I also believe that it is pretty irrelevant for today other than as a historical study; the stories were written and now they exist, and they contain a lot of stuff.
19:46:10 <zzo38> You can do good works and you can do prayer and meditation and spirituality and whatever regardless of how accurate the Gospels are.
19:46:46 -!- copumpkin has joined.
19:47:18 <pikhq> And then there's people who believe Jesus was buried in Shingou village, in Aomori Prefecture, Japan.
19:48:00 <zzo38> Well, that seems unlikely to me, but of course I don't know.
19:48:19 <zzo38> Why would he be in Japan?
19:49:13 <pikhq> https://upload.wikimedia.org/wikipedia/commons/7/7f/GraveSign.jpg
19:49:21 <pikhq> Lots of stuff but nothing saying *why* Japan.
19:49:41 <pikhq> Japan is one hell of a long way away from Judea.
19:50:27 <zzo38> Yes, that's why it seems so unlikely to me.
19:51:14 <coppro> pikhq: there's also people who believe that he was in North America when he was thought to be dead
19:51:33 -!- Vorpal has quit (Ping timeout: 255 seconds).
19:51:41 * ais523 wonders how unlikely a statement has to be before /nobody/ believes it
19:51:56 <ais523> at least, it seems likely that such a statement exists
19:52:09 <ais523> the alternative is for some set of people to exist who collectively believe everything
19:52:39 -!- Vorpal has joined.
19:52:39 -!- Vorpal has quit (Changing host).
19:52:39 -!- Vorpal has joined.
19:53:47 -!- variable has quit (Quit: 1 found in /dev/zero).
19:54:13 <pikhq> ais523: "Nothing is false"
19:54:53 <ais523> pikhq: I guess someone believing that either believes everything, or fails at logic
19:55:49 <pikhq> Though unlikely for humans, there hypothetically could exist minds that don't accept modus ponens...
19:56:00 -!- barrucadu has quit (Ping timeout: 265 seconds).
19:56:05 <zzo38> There are various hypotheses as to what actually happened; some say the body was stolen, although even such people disagree as to how or why. The most likely scneario to me seems that his family took it to bury it in the family tomb and didn't tell anyone since it wasn't important.
19:57:10 <pikhq> zzo38: My belief is just that it's unlikely any individual person would be all that recognizable as "Jesus" from that time period.
19:57:50 <pikhq> Even if there is in fact a "Jesus" from Nazareth it seems rather unlikely said person's life much resembles the myth.
19:58:23 <zzo38> I read somewhere that the Jesus Seminar considers that the amount of resemblance is approx. 20%
19:58:39 -!- shikhin has quit (Ping timeout: 250 seconds).
19:58:41 <coppro> pikhq: I think it's fairly likely such a person existed.
19:59:11 <coppro> A prophet is just a cult leader that people never stopped listening to
19:59:33 <fizzie> Vorpal: I tried out the fisheye thing too, since you told me about it.
19:59:41 <pikhq> It's particularly weird some of the various omissions from records that, nevertheless, include other figures that people associate with Jesus...
20:00:03 <pikhq> (for instance, both John the Baptist and the apostle Paul are *quite* well attested.)
20:00:14 <zzo38> My own belief (although I must say I cannot be certain of anyy of this) is that Jesus of Nazareth probably did exist and was a Great Prophet. I do not believe in a final Great Prophet, though (even though most organized religion seems to)
20:00:58 <fizzie> Vorpal: The projection kind of makes this riverside view look like a lake, with the opposite shore being an isle.
20:01:00 <pikhq> But alas, I don't have a time machine.
20:01:13 <pikhq> Piecing shit together from sparse records is a tricky thing. :)
20:01:28 <coppro> zzo38: Most organized religion doesn't actually believe that there is a "final" prophet
20:01:34 <zzo38> Neither do I, and furthermore I am not a historian, so I cannot do it as good as real historians anyways.
20:01:53 <pikhq> coppro: That tends to be common in Christian belief in particular, though.
20:02:02 <pikhq> Assuming one doesn't count the Pope as a prophet.
20:02:08 <coppro> pikhq: Yes, but that is because Jesus is not, in Christian belief, a prophet.
20:02:24 -!- barrucadu has joined.
20:02:55 <pikhq> He is quite specifically a divine being of some sort in that belief system. (precisely which sort depends on sect)
20:03:43 <coppro> He is a prophet in Islam, though.
20:05:11 <zzo38> Being a divine being of some sort does not seem to imply not being a prophet, as far as I can tell, though.
20:06:21 <coppro> pikhq: true, but "$RELIGION accepts $DUDE as a prophet -> Baha'i accepts $DUDE as a prophet" :P
20:09:38 <zzo38> coppro: Are you sure about that?
20:10:42 -!- shikhin has joined.
20:11:47 -!- ais523 has quit (Read error: Connection reset by peer).
20:11:52 -!- callforjudgement has joined.
20:11:57 -!- callforjudgement has changed nick to ais523.
20:18:19 <zzo38> Guest61975: Explain!
20:20:12 -!- Guest61975 has left.
20:23:11 -!- Guest43464 has joined.
20:26:10 <zzo38> (I doubt others here have or care much either, but, I don't know. I don't really care much either though.)
20:28:37 <zzo38> I don't really care what you wish to talk about though, but if you ask, well, I have studied many things, but I am interested in mathematics, and do much computer programming to.
20:30:32 <zzo38> I don't really have much to say right now though
20:30:36 <ais523> Guest43464: you are acting oddly like Eliza…
20:31:43 <Guest43464> Guest43464 knows that it is suspicious but he doesn't know who the hell that is
20:32:23 <oren> I think it is possible they merely made a mistake and he wasn't completely dead when they put him in the tomeb
20:32:39 <zzo38> oren: I did consider that possibility too
20:33:38 <oren> Misao Okawa was the oldest woman in the world until she died a few days ago
20:33:44 <zzo38> I do have one thing to say about logic too, which is that in my opinion, logic is a math, and reasoning is the application of logic; some consider logic and reasoning to be the same thing but I do not.
20:37:43 <zzo38> I don't know what your opinion about these things are.
20:45:39 <oren> In my course "knowledge representation and reasoning" we learned different "logics" including "propositional logic" and "first-order logic"; and then we also learned different processes of "reasoning" which take a set of logical statements and produce a new one from them.
20:46:22 <oren> So sort of "logic" is the language and "reasoning" is the runtime?
20:48:08 -!- `^_^v has quit (Ping timeout: 252 seconds).
20:49:36 <zzo38> O, that's the course? I haven't heard of that course either
20:49:59 -!- `^_^v has joined.
21:01:09 <oren> zzo38: I dunno if they have that course at other universities. http://en.wikipedia.org/wiki/Knowledge_representation_and_reasoning
21:30:54 <int-e> Oh, this is a nice thought... a self-driving car could avoid parking tickets.
21:31:36 <int-e> (Apparently Tesla produced an April fool's video which embedded this idea.)
21:32:36 <int-e> Hmm. April's fool's video. April's fool video. Glad this grammatical swamp will be irrelevant for the next 360 days.
21:34:44 <ais523> int-e: the idea is that if the time parked is about to expire, it drives off without its owner?
21:36:03 <int-e> ais523: right, or perhaps even later, when a parking enforcement officer approaches.
21:36:47 <ais523> the latter would be dangerous; in the UK, most parking enforcement's done via CCTV nowadays
21:38:01 <int-e> Yeah, but that's a technical detail. I'm picturing a scene in a movie: the officer approaches the car, trying to affix the ticket; the car backs away... It's completely unrealistic, but hilarious.
21:38:29 <int-e> (Useless too because then the license plate information will already have been taken down.)
21:39:44 <int-e> (Ultimately, the car, surrounded by traffic enforcement personnel, would sprout wings and fly away.)
21:50:38 -!- AnotherTest has quit (Remote host closed the connection).
21:50:45 -!- copumpkin has quit (Quit: My MacBook Pro has gone to sleep. ZZZzzz…).
21:59:58 -!- oerjan has joined.
22:03:55 <oerjan> <zzo38> Someone (who is an atheist) asked me, why is it good (if Jesus is dead)? I said, it is good because you don't have to go to work. <-- that also confused me once. in norwegian it's called the equivalent of "long friday" instead.
22:05:07 * oerjan is suddenly tempted to ban Guest*!*
22:05:43 <oerjan> especially that pesky Guest24483
22:06:32 <shachaf> oerjan: you seem to have guest their secret identity
22:07:31 <oerjan> now to find some kryptonite...
22:07:33 <shachaf> I feel like some of these constraint things ought to be filed as separate GHC tickets.
22:07:42 <int-e> Uh, I'm not very Christian. Good Friday is a day of mourning, but also a day of hope?!
22:08:14 <shachaf> presumably the first part is only in the morning
22:08:18 <oerjan> int-e: it was pretty much explained in the logs, i was just commenting on the naming
22:08:59 <zzo38> I still have the tradition on Good Friday to not eat meat, but still eat fish and chips. (I do not consider myself a Christian either though.)
22:09:21 <oerjan> shachaf: happy passover, or something
22:09:58 <zzo38> I think Passover is on Saturday; it says so on my calendar.
22:10:15 <zzo38> (It is also Holy Saturday)
22:10:56 <oerjan> i was going by wikipedia's main page, also i believe jewish days start at sunset.
22:11:23 <oerjan> i may of course be too early, pesky time zones.
22:11:57 <int-e> Oh Saturday morning.
22:12:44 <oerjan> well i guess we have saturday morning here, sort of
22:12:50 * int-e wonders where oerjan is right now.
22:13:08 <int-e> oh you already agreed, sort of.
22:14:29 <oerjan> something to test which i don't think will work with the new system
22:16:11 <oerjan> > let f :: forall a. Typeable a => Proxy a -> TypeRep; f _ = typeOf (Proxy :: Proxy a)
22:16:12 <lambdabot> not an expression: ‘let f :: forall a. Typeable a => Proxy a -> TypeRep;...
22:16:41 <oerjan> > let f :: forall a. Typeable a => Proxy a -> TypeRep; f _ = typeOf (Proxy :: Proxy a) in f (Proxy Ord)
22:16:42 <lambdabot> Not in scope: data constructor ‘Ord’
22:16:42 <lambdabot> Perhaps you meant variable ‘ord’ (imported from Data.Char)
22:16:52 <oerjan> > let f :: forall a. Typeable a => Proxy a -> TypeRep; f _ = typeOf (Proxy :: Proxy a) in f (Proxy :: Proxy Ord)
22:16:54 <lambdabot> Could not deduce (Typeable Proxy) arising from a use of ‘typeOf’
22:17:20 <shachaf> oerjan: just download ghc 7.10 hth
22:17:29 <oerjan> i'm waiting for the platform
22:17:32 <shachaf> I haven't used the Haskell platform for years.
22:17:43 <shachaf> Oh, I guess it's a bigger hassle on Windows.
22:18:24 <oerjan> anyway, it cannot deduce Typeable (Proxy a) from Typeable a when the kind is polymorphic
22:18:56 <oerjan> in fact, i don't think you can get the kindRep for k from the dictionary for Typeable (a::k) at all
22:19:02 <shachaf> The error is pretty confusing.
22:19:22 <shachaf> > typeRep (Proxy :: Proxy Proxy)
22:19:23 <lambdabot> (maybe you haven't applied enough arguments to a function?)
22:20:04 <oerjan> isn't that just kind not defaulting
22:20:20 <shachaf> Do you expect it to default?
22:20:32 <oerjan> > typeRep (Proxy :: Proxy (Proxy :: * -> *))
22:20:47 <zzo38> I thought, if the programming language can be made which is using RDF as the input format, and which includes macros, aspect programming, logic programming, and may be made in such a way to be suitable it can implement the rules and cards of Magic: the Gathering and other similar games.
22:20:53 <oerjan> no, but in my example the kind is known
22:21:10 <zzo38> But with many things figured at compile-time
22:22:14 -!- callforjudgement has joined.
22:25:28 <lambdabot> Not in scope: type constructor or class ‘HList’
22:26:06 -!- ais523 has quit (Disconnected by services).
22:26:07 -!- callforjudgement has changed nick to ais523.
22:27:12 <shachaf> oerjan: Why is the kind known in your case?
22:27:14 <oerjan> @let pt :: forall a. Typeable a => Proxy a -> TypeRep; pt _ = typeOf (Proxy :: Proxy a)
22:27:15 <lambdabot> Could not deduce (Typeable Proxy) arising from a use of ‘typeOf’
22:27:31 <oerjan> shachaf: because the type is known
22:28:45 <oerjan> @let pt :: forall a. Typeable a => Proxy a -> TypeRep; pt x = typeOf x
22:28:46 <lambdabot> Could not deduce (Typeable Proxy) arising from a use of ‘typeOf’
22:29:28 <int-e> oerjan: get ghci 7.10.1 installed already
22:29:33 <oerjan> @let pt :: forall a. Typeable a => Proxy a -> TypeRep; pt = typeOf
22:29:34 <lambdabot> Could not deduce (Typeable Proxy) arising from a use of ‘typeOf’
22:29:46 <oerjan> but i'm also demonstrating :(
22:29:49 <int-e> or at least use private messages
22:29:58 <int-e> you're demonstrating lack of restraint
22:30:14 <shachaf> typeOf :: Typeable a => Proxy a -> TypeRep -- is also the same error hth
22:30:25 -!- shikhin has quit (Quit: leaving).
22:31:19 <int-e> it is a funny one though, this works in ghci...
22:31:50 <oerjan> int-e: without PolyKinds, i assume?
22:31:51 <int-e> :k () :: Constraint
22:31:59 <int-e> oerjan: ah there's that...
22:38:07 <int-e> oerjan: http://sprunge.us/Yhdd sheds a bit more light on this. But now it's full of shadows.
22:40:21 <oerjan> int-e: the reason, as i suspect it, is that the new typeable solver doesn't try to transfer kind information at all; in fact TypeRep for the type a doesn't necessarily contain enough information to deduce its kind without access to compiler data.
22:40:43 <oerjan> it's designed such that type application works, but little more.
22:41:11 <int-e> oerjan: No, it goes deeper to the foundations. You cannot talk about a type `a` without knowing its kind first. So ghc invents a context k :: BOX => for pt's type.
22:41:52 <int-e> Oh. Nah, there's no contradiction there.
22:42:32 <oerjan> the foundations don't prevent you from hypothetically making a TypeRep that _does_ contain the necessary information.
22:42:39 <int-e> You want something like class Kindable k => Typeable (a :: k), and ghc doesn't do it that way.
22:42:55 <oerjan> or at least something that fakes it
22:43:19 <oerjan> which is what i discussed with Richard Eisenberg in the trac with test cases
22:43:59 -!- `^_^v has quit (Quit: This computer has gone to sleep).
22:44:01 <oerjan> although i guess if no one has made code that was actually broken by this...
22:44:27 <int-e> The downside, perhaps, is that this would have to be explicit in the TypeRep that the Typeable class instances carry?
22:44:55 <oerjan> i guess mixing Typeable with code kind polymorphic enough to need this is not happening
22:45:10 <oerjan> (i could imagine something with DataKinds)
22:45:33 <oerjan> int-e: well yeah, you'd need a representation of the _whole_ kind
22:45:59 <oerjan> rather than just the core kind parameters
22:47:41 <Taneb> oerjan, I need to book a train ticket!
22:48:04 <Taneb> And then like put my duvet cover on my duvet
22:48:05 <oerjan> and you need to wait until after midnight to do it?
22:48:15 -!- sebbu2 has changed nick to sebbu.
22:48:21 <oerjan> for stupid price reasons?
22:48:44 <Taneb> No, I'm doing it now
22:48:50 <Taneb> I was just procrastinating
22:48:59 <Taneb> And now it is suddenly the last minute
22:49:03 * int-e does such things for "I can still do this when I'm too tired to do all this other more interesting stuff" reasons.
22:49:32 * Taneb has booked train ticket
22:49:38 <int-e> Just make sure you got the date correct!
22:50:34 <int-e> I started to type this before you announced it was already done. So I had a "get" there initially.
22:50:38 * oerjan recalls the time he had ordered a train ticket for the day after the DST change
22:51:08 <int-e> Oh, DST ... *twiddles with watch*
22:51:22 <oerjan> int-e: you're a number of days late...
22:51:29 <int-e> no I'll wait 5 more minutes so it doesn't affect the date
22:51:55 <int-e> oerjan: I know. I hardly ever look at my pocket watch, and then usually only to check whether I have to run for the bus.
22:52:40 <oerjan> last time i took the bus i made the mistake of looking at the bus table i'd got by mail
22:52:57 <int-e> (the "pocket" watch is a wrist watch without the bands)
22:53:42 <oerjan> not remembering that they'd had a major budgeting scandal and had had to downsize everything. so the bus schedule i was going to take had been canceled.
22:54:25 <oerjan> fortunately i didn't miss my appointment.
22:57:26 <int-e> there, 1 am now on that watch
22:57:53 <int-e> (it's a bit fast. that's healthy since ... I'm using it to check whether I have to run for buses and the buses tend to be a bit early ;-) )
23:01:06 <oerjan> i try to make sure it's not late, but i don't compensate for anyone else being early
23:02:51 <Taneb> My train is at 10:53
23:03:03 <Taneb> It is a 40 minute walk to the station, but I want to stop at the shops on the way
23:03:37 * int-e tries to remember Taneb's time zone
23:03:44 <lambdabot> Local time for Taneb is Sat Apr 4 00:05:42
23:03:54 <Taneb> So I probably want to leave before 10
23:03:58 <Taneb> Probably closer to half 9
23:04:12 <int-e> . o O ( half past 9? )
23:04:22 * int-e is used to halb 9 meaning 8:30.
23:04:41 <Taneb> I think "half 9" meaning half past nine is a British thing
23:04:45 <oerjan> oh german is like norwegian then
23:04:45 <int-e> (German speakers are not in agreement about this.)
23:05:04 <ais523> I was taught that in German, "halb 9" meant 8:30
23:05:12 <ais523> however, in English "half 9" would always be 9:30
23:05:23 <myname> halb 9 in germany is 8:30
23:05:47 <int-e> (It's worse about viertel (quarter) 9 and dreiviertel 9 (three quarter 9) meaning 8:15 and 8:45; many states prefer the viertel vor/viertel nach (quarter to/quarter past) versions.)
23:05:50 <Taneb> ais523, I am told that is more a British thing rather than something agreed upon throughout the anglosphere
23:06:25 <ais523> Taneb: English English, then
23:06:25 <myname> int-e: i think "um 1" is more interesting
23:06:35 <int-e> (The logical explanation is that this says how much of the 9th hour has passed.)
23:06:45 <int-e> myname: same explanation
23:06:48 <ais523> almost sure it's the same in the rest of the UK, and I think it's the same in the US too
23:06:55 <myname> there are regions where it is exactly 13:00 and others where it id around 13:00
23:07:25 <ais523> to me it'd just as likely be 1am
23:07:27 <int-e> myname: ah. Ok, for the regions where this means exactly 13:00, that's the point where the 1st hour has passed. (ist um).
23:07:48 <int-e> (I'm used to that meaning.)
23:08:07 <int-e> (The other is "gegen 1")
23:09:02 <myname> "um 1" is meant as "um 1 rum" in the second
23:09:16 <Taneb> I am going to go to bed now
23:09:42 <int-e> Taneb: have a safe trip
23:10:11 <Taneb> (I'm literally going to the next city over to play D&D)
23:10:12 <myname> to me, the funniest thing is that there are three things that are called pfannkuchen, depending on the region
23:10:22 <int-e> Taneb: don't die ;)
23:10:46 <int-e> and try not to kill any GMs either
23:10:58 <shachaf> Taneb: Which city is the next over?
23:12:00 <Taneb> shachaf, (from York)
23:13:04 <Taneb> /s/shachaf, I/int-e, I/
23:13:24 <Taneb> Anyway, I must be off
23:15:54 <HackEgo> [wiki] [[Wordy]] http://esolangs.org/w/index.php?diff=42292&oldid=42171 * Oerjan * (-73) wikify a bit, also we have our own .Gertrude page
23:21:04 <HackEgo> [wiki] [[Taworvor]] http://esolangs.org/w/index.php?diff=42293&oldid=42225 * Oerjan * (+10) standardifimogrify section name
23:22:04 -!- hjulle has quit (Ping timeout: 250 seconds).
23:31:52 <HackEgo> [wiki] [[Duck Duck Goose]] http://esolangs.org/w/index.php?diff=42294&oldid=42223 * Oerjan * (-24) wikify a bit, remove some blank lines
23:36:11 -!- variable has joined.
23:37:51 <HackEgo> [wiki] [[~ATH]] http://esolangs.org/w/index.php?diff=42295&oldid=42240 * Oerjan * (+9) wikify intro, section headers
00:00:21 -!- variable has quit (Ping timeout: 245 seconds).
00:01:56 -!- ais523 has quit.
00:02:00 -!- callforjudgement has joined.
00:02:12 -!- callforjudgement has changed nick to ais523.
00:22:31 <HackEgo> [wiki] [[Yoob]] http://esolangs.org/w/index.php?diff=42296&oldid=42242 * Oerjan * (-38) Undo revision 42242 by [[Special:Contributions/5.29.33.254|5.29.33.254]] ([[User talk:5.29.33.254|talk]])
00:25:39 <HackEgo> [wiki] [[Talk:Time Out]] http://esolangs.org/w/index.php?diff=42297&oldid=42276 * Oerjan * (-26) Undo revision 42276 by [[Special:Contributions/Esowiki201529A|Esowiki201529A]] ([[User talk:Esowiki201529A|talk]]) (Wat)
00:30:49 <HackEgo> [wiki] [[Special:Log/delete]] delete * Oerjan * deleted "[[Talk:Hexadecimal Stacking Pseudo-Assembly Language]]": content was: "这个正确的名字是“十六进制堆栈式伪汇编语言”" (and the only contributor was "[[Special:Contributions/Esowiki201529A|Esowiki201529A]]")
00:35:38 <oerjan> there, now i can slack on visiting the wiki for another half month or so
00:50:05 -!- CADD has joined.
00:50:42 -!- callforjudgement has joined.
00:50:59 -!- mihow has quit (Quit: mihow).
00:53:39 -!- ais523 has quit (Ping timeout: 272 seconds).
00:53:44 -!- callforjudgement has changed nick to ais523.
01:06:45 <int-e> oerjan: oh I have an unsolved puzzle... write a module that only exports (GHC.Prim.*)
01:07:10 <int-e> (you've played with this much more than I have, maybe you know a way?)
01:10:22 <oerjan> hm i haven't played with _that_
01:10:43 <oerjan> quite possibly you're the one who showed me how you could import GHC.Prim.* in the first place
01:12:01 <oerjan> can you even write a module that exports (GHC.Prim.*) _plus_ other things?
01:13:01 <oerjan> it would seem that module ... (module GHC.Prim) would have the same problem as Constraint.
01:13:05 <int-e> yes, by reexporting the whole module
01:14:59 <int-e> :browse GHC.Exts ... data (*)
01:15:56 -!- ais523 has quit (Read error: Connection reset by peer).
01:16:08 <shachaf> i,i module M (module GHC.Prim) where import GHC.Prim hiding (...)
01:16:13 -!- ais523 has joined.
01:16:47 <shachaf> Maybe this has the same issue as Constraint that you've been talkinga bout.
01:16:49 <oerjan> int-e: Constraint doesn't get through that way, at least.
01:17:06 <shachaf> Probably it does because otherwise why would you be bringing this up.
01:17:30 -!- mihow has joined.
01:17:43 <int-e> note that the (*) does not even exist in ghc-7.8
01:18:21 <int-e> oerjan: so, contrary to what I thought, you probably have not played with it :)
01:18:23 -!- mihow has quit (Client Quit).
01:18:24 <oerjan> int-e: um in ghc-7.8 i can see GHC.Prim.*
01:19:29 <int-e> Oh, my testing is flawed.
01:20:06 <int-e> So yeah, it's in GHC.Prim but (visibly anyway) not reexported from GHC.Exts
01:20:23 <zzo38> What exactly does BOX do?
01:20:28 <int-e> s/(\(.*\)) (not)/\2 \1/
01:20:41 <oerjan> when i do module T ((*),Constraint) where import GHC.Prim
01:20:45 <int-e> zzo38: it's superkind, the kind of kinds.
01:20:53 <oerjan> and :m T (to remove the * before T)
01:21:06 <oerjan> then i can see the Constraint but not the *
01:21:28 <int-e> oerjan: try that with {-# LANGUAGE NoImplicitPrelude #-} to remove the other (*).
01:21:44 <oerjan> zzo38: it's the "kind of kinds" in GHC core, you're not supposed to be able to refer to it
01:21:56 <int-e> then ghc will complain about not being able to find (*), I think.
01:22:06 -!- FreeFull has quit (Ping timeout: 248 seconds).
01:22:23 <oerjan> well i tried import Prelude ()
01:24:13 -!- FreeFull has joined.
01:24:36 <oerjan> int-e: you can export it if you rename it with a type
01:26:15 <oerjan> oh except then it thinks it's a type not a kind
01:26:26 <oerjan> funny though, still with kind BOX
01:26:56 <shachaf> Or, at least, it's a thing that has a kind.
01:27:03 <lambdabot> Not in scope: type constructor or class ‘S’
01:27:03 <lambdabot> Not in scope: type constructor or class ‘S’
01:27:17 <oerjan> gives me the error ‘S’ of kind ‘BOX’ is not promotable
01:27:31 <oerjan> (type S = (GHC.Prim.*))
01:27:39 -!- mihow has joined.
01:43:04 <int-e> oerjan: this is what I'm playing with: http://int-e.eu/~bf3/haskell/safe/
01:43:08 -!- mihow has quit (Ping timeout: 252 seconds).
01:46:36 <int-e> (I guess the main purpose of the GHC.Prim.Safe module is to convince myself that it's unmanagable that way.)
01:47:05 <oerjan> why are you commenting out coerce?
01:47:21 <int-e> Because Data.Coerce is the official way to get that one
01:47:49 <int-e> So I'm anticipating the export getting deprecated.
01:48:20 <int-e> Oh, Data.Coerce is unsafe, hmm.
01:48:30 <oerjan> and are all those unboxed shifts unsafe, even the ones not unchecked* ?
01:48:31 <int-e> That is... interesting.
01:49:33 <int-e> oerjan: I suspected that adding primops would open a can of worms. They're probably safe, but look at the Prim_Safe module...
01:50:36 -!- callforjudgement has joined.
01:50:40 <oerjan> i guess lack of documentation of what _is_ safe is a problem
01:50:43 <int-e> (The plan was to add primops by replacing GHC.Prim by GHC.Prim.Safe.)
01:51:30 <int-e> And platform-dependent primops.
01:51:52 <int-e> I wonder if there are more subtle catches like the quot/rem one.
01:53:12 -!- ais523 has quit (Ping timeout: 252 seconds).
01:53:43 -!- callforjudgement has changed nick to ais523.
01:55:22 <int-e> oerjan: in any case to make it manageable, the information should probably be handled by the primop generator infrastrucure (so the safety information would be in primops.txt.pp, mostly)
01:56:19 <int-e> (this beautiful file: https://github.com/ghc/ghc/blob/master/compiler/prelude/primops.txt.pp )
02:12:23 <int-e> (As you can see on #haskell I guess the reason for making Data.Coerce unsafe is that coerce can break abstraction boundaries that SafeHaskell is supposed to preserve, if libraries are not careful enough with the (rather new) type roles.)
02:16:34 <int-e> (SafeHaskell is somewhat blurry. coerce by itself is type-safe. But what if you have a module like Data.Map with representational key type, and use it to implement a trusted type-polymorphic key-value store? Who is to blame if the user coerces the map to one with a different Ord instance for the key type?)
02:31:05 -!- MDude has joined.
02:38:11 -!- callforjudgement has joined.
02:38:15 -!- ais523 has quit (Disconnected by services).
02:38:18 -!- callforjudgement has changed nick to ais523.
02:40:28 -!- MDude has quit (Ping timeout: 246 seconds).
02:50:07 -!- dianne has joined.
02:52:10 -!- oerjan has quit (Quit: leaving).
03:31:20 <HackEgo> [wiki] [[Small SNUSP]] N http://esolangs.org/w/index.php?oldid=42298 * Esowiki201529A * (+94) Created page with "== example: Infinite loop == <pre> !/\ \/ </pre> == See also == [[SNUSP]] [[Category: No IO]]"
03:32:46 <HackEgo> [wiki] [[Small SNUSP]] http://esolangs.org/w/index.php?diff=42299&oldid=42298 * Esowiki201529A * (+0)
03:36:58 <HackEgo> [wiki] [[SNUSP]] http://esolangs.org/w/index.php?diff=42300&oldid=39080 * Esowiki201529A * (+18)
03:38:49 <HackEgo> [wiki] [[Small SNUSP]] http://esolangs.org/w/index.php?diff=42301&oldid=42299 * Esowiki201529A * (+26)
03:39:29 -!- vodkode_ has joined.
03:43:38 <HackEgo> [wiki] [[SNUSP]] http://esolangs.org/w/index.php?diff=42302&oldid=42300 * Esowiki201529A * (+17)
04:03:43 -!- ais523 has quit.
04:03:52 -!- ais523 has joined.
04:06:37 -!- ais523 has quit (Read error: Connection reset by peer).
04:06:49 -!- ais523 has joined.
04:11:46 -!- GeekDude has quit (Quit: {{{}}{{{}}{{}}}{{}}} (www.adiirc.com)).
04:20:17 -!- variable has joined.
04:22:27 -!- callforjudgement has joined.
04:25:51 -!- ais523 has quit (Ping timeout: 256 seconds).
04:25:57 -!- callforjudgement has changed nick to ais523.
04:30:59 -!- Sprocklem has joined.
04:35:04 -!- variable has quit (Quit: 1 found in /dev/zero).
04:44:09 -!- variable has joined.
04:49:03 <zzo38> Do you know what program to use to test .XI instruments?
04:49:24 <zzo38> I know I can use OpenMPT but it requires too many steps to test it in that way
04:54:29 <zzo38> (It also sometimes crashes)
05:15:58 -!- callforjudgement has joined.
05:16:08 -!- ais523 has quit (Disconnected by services).
05:16:10 -!- callforjudgement has changed nick to ais523.
05:17:29 -!- callforjudgement has joined.
05:20:03 -!- scarf has joined.
05:20:04 -!- callforjudgement has quit (Read error: Connection reset by peer).
05:20:44 -!- ais523 has quit (Disconnected by services).
05:20:46 -!- scarf has changed nick to ais523.
05:28:50 -!- ais523 has quit.
05:29:08 -!- ais523 has joined.
06:04:00 -!- vodkode_ has quit (Ping timeout: 252 seconds).
06:13:41 -!- cwe_aza has joined.
06:15:43 -!- cwe_aza has left.
06:35:21 -!- variable has changed nick to constant.
06:50:41 -!- hjulle has joined.
07:38:39 -!- constant has quit (Ping timeout: 256 seconds).
08:41:27 -!- Guest43464 has quit (Read error: Connection reset by peer).
08:54:54 <mroman> https://github.com/fogleman/nes
08:55:55 -!- vodkode_ has joined.
10:04:21 -!- ais523 has quit.
10:04:35 -!- ais523 has joined.
10:08:43 <mroman> Very rainy week in switzerland.
10:09:33 <mroman> oh well. I should be able to live off 3.8k CHF
10:14:15 -!- callforjudgement has joined.
10:17:49 -!- ais523 has quit (Ping timeout: 264 seconds).
10:17:56 -!- callforjudgement has changed nick to ais523.
10:32:21 -!- ais523 has quit (Read error: Connection reset by peer).
10:32:26 -!- callforjudgement has joined.
10:35:18 -!- rodgort` has quit (Ping timeout: 256 seconds).
10:38:24 -!- rodgort has joined.
10:42:08 <int-e> . o O ( As a rule, conventional wisdom is wrong. )
10:55:36 <int-e> oh nice April's fool, subtle... http://www.vexxarr.com/archive.php?seldate=040115
10:55:42 -!- vodkode_ has quit (Ping timeout: 256 seconds).
10:56:49 <mroman> http://pastebin.com/VUHSr0JV
11:02:32 <mroman> That's not delphi though :)
11:12:35 <HackEgo> [wiki] [[SNUSP]] http://esolangs.org/w/index.php?diff=42303&oldid=42302 * Ais523 * (-17) Undo revision 42302 by [[Special:Contributions/Esowiki201529A|Esowiki201529A]] ([[User talk:Esowiki201529A|talk]]) - I don't think that word means what you think it means
11:15:05 -!- v4s has quit (Max SendQ exceeded).
11:15:21 -!- v4s has joined.
11:15:30 -!- callforjudgement has quit.
11:28:10 -!- zadock has quit (Quit: Leaving).
12:17:09 <Guest24483> https://esolangs.org/wiki/Small_SNUSP is a good page
12:20:10 <int-e> elliott: I can hear your sarcastic undertone.
12:29:41 <HackEgo> [wiki] [[Small SNUSP]] http://esolangs.org/w/index.php?diff=42304&oldid=42301 * 213.162.68.171 * (+141) Add no description
12:30:04 <int-e> There, now everybody should be happy *ducks*
12:55:22 -!- nys has joined.
12:59:48 -!- Patashu has quit (Ping timeout: 256 seconds).
13:06:17 -!- FreeFull has quit (Ping timeout: 250 seconds).
13:06:46 -!- Lymia has quit (Quit: Hugs~ <3).
13:08:31 -!- Lymia has joined.
13:17:19 -!- FreeFull has joined.
13:19:38 -!- Koen_ has joined.
13:22:20 <fizzie> Was there a particular name for a diagonal matrix where all the diagonal elements are equal? (Context: covariance matrix for multivariate Gaussian distribution; I know "spherical" is the term for the resulting distribution, but that's not a generic term for the kind of matrix. In fact, "spherical matrix" seems to be something related to matrix variate distributions.)
13:22:25 <fizzie> A "diagonal Toeplitz matrix" might be technically correct but really silly.
13:23:29 <shachaf> https://en.wikipedia.org/wiki/Diagonal_matrix
13:23:47 <fizzie> I see "scaled identity matrix" in a few places, but that's just a description.
13:23:47 <int-e> Makes sense (I just found the same page.)
13:23:54 <b_jonas> scaled identity matrix, yes
13:24:26 <fizzie> I even thought it might be "scalar matrix", but for some reason didn't search for it.
13:24:50 <fizzie> Although in a sentence like "[matrix] is constrained to be diagonal or scalar" it sounds a bit silly.
13:25:02 <fizzie> "How can it be a scalar if it's a MxM matrix?"
13:25:12 <shachaf> Well, in a sentence like that, you can just say it's constrained to be diagonal.
13:26:19 <fizzie> But that's not exactly equivalent. I was trying to say that occasionally it's "more constrained" than just diagonal, if you want even fewer parameters for your distributions.
13:27:32 <fizzie> Maybe it's not too bad to say 'scalar'.
13:27:32 <int-e> ... is constrained to be diagonal (or even scalar).
13:27:46 -!- oerjan has joined.
13:28:05 * int-e swats ----### oerjan for swatting too much.
13:28:33 <shachaf> your swatter's too short hth
13:28:45 <int-e> it's a practice swatter
13:28:49 * oerjan hits int-e with the saucepan ===\__/
13:28:59 <shachaf> Maybe you can say that all its eigenvalues are equal or something silly like that.
13:29:11 <shachaf> It's 06:31. Good time to go to sleep.
13:29:26 <oerjan> that's about when i went to sleep
13:29:43 <shachaf> and now look at you, hitting people with saucepans
13:30:16 <int-e> Well that escalated quickly.
13:30:31 * int-e drops a lift cabin on oerjan, for sake of the pun.
13:30:40 <oerjan> darn i was considering that
13:33:48 <oerjan> <int-e> oh nice April's fool, subtle... http://www.vexxarr.com/archive.php?seldate=040115 <-- oh so that's what it was. i was following the links from freefall but couldn't find _any_ april fool comics in the others.
13:34:39 -!- zadock has joined.
13:34:43 <oerjan> a meta one, where the joke was that there was no april 1 comic
13:45:31 <int-e> oerjan: the brilliancy is, until the next Vexxar comic is published, it could actually be true.
13:46:40 <int-e> oerjan: except that after a decade of comics it'd be rather strange to pull a "it was all just a dream" trope.
15:09:07 -!- yorick has quit (Read error: Connection reset by peer).
15:09:33 -!- yorick has joined.
15:25:19 -!- TieSoul has joined.
15:27:55 -!- boily has joined.
15:31:03 -!- GeekDude has joined.
15:54:43 <lambdabot> CYQB 041544Z 34009KT 1 1/2SM -SN BKN012 OVC020 M04/M08 A2975 RMK SN3SC3SC2 SLP078
15:54:50 <boily> fungot: why. WHYYYYYYYYYYYYY!
15:54:50 <fungot> boily: have you considered just using ( list " hi there! say, what would he reply?
15:55:12 <boily> fungot: no, I didn't consider what you would reply.
15:55:12 <fungot> boily: telling jokes, looking stupid or just generally to squares, or whatever... " i've done a lot of
15:55:33 <fungot> b_jonas: lazy k is done.
15:57:50 -!- vodkode_ has joined.
16:06:27 <fungot> int-e: ummm...i dont know. they were very prompt about putting it on the web
16:06:33 <lambdabot> EGLL 041550Z 04006KT 9999 SCT023 BKN040 08/03 Q1024 NOSIG
16:07:20 <fizzie> fungot: Are you saying they put it on the web too fast, and it's not really done yet?
16:07:20 <fungot> fizzie: just a tic. laundry.
16:07:27 <fizzie> fungot: Okay, take your time.
16:07:27 <fungot> fizzie: it's that one song...? :p. ugh i need to generate it, not official.
16:07:43 <b_jonas> fungot: no, the whole episode
16:07:43 <fungot> b_jonas: or something like that. complain complain complain. but it's easier. and no one wants to do a
16:08:47 -!- f|`-`|f_ has joined.
16:12:08 -!- f|`-`|f has quit (Ping timeout: 246 seconds).
16:12:12 -!- f|`-`|f_ has changed nick to f|`-`|f.
16:15:08 <lambdabot> CYYZ 041600Z 29013G19KT 250V310 15SM BKN045 03/M08 A3009 RMK CU7 SLP196
16:16:19 <boily> fiziello. helloren.
16:18:47 -!- vodkode_ has quit (Ping timeout: 246 seconds).
16:21:39 <fizzie> "Jellona" is a humorous/"cute" term for a lion in Finnish.
16:21:46 <fizzie> http://en.wiktionary.org/wiki/jellona
16:22:06 <fizzie> (By way of mangling from leijona.)
16:23:04 <boily> is leijona related to Nepeta Leijon?
16:23:29 <fizzie> I've wondered about that.
16:24:15 <fizzie> "-- Leijon is taken from the surname of Anna-Greta Leijon, who was a Swedish Minister of Immigration in 1976 and victim of a kidnapping plot dubbed Operation Leo. The Swedish word lejon ("leijon" is the archaic spelling) means "lion", and is pronounced LAY-on. Also, the Finnish word for lion is leijona."
16:24:54 <HackEgo> Thanks, mspa wiki. Tha wiki.
16:46:54 <FreeFull> I forgot it's 4th of april already
16:47:47 <FreeFull> Wait, nevermind, it's 13th of april I'm waiting for
16:48:47 <boily> FreelloFull. what's happening on that Fateful Day?
16:49:54 -!- Lautner has joined.
16:51:17 <HackEgo> /home/hackbot/hackbot.hg/multibot_cmds/lib/limits: line 5: exec: rello: not found
16:51:40 <HackEgo> Lautner: 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.)
16:58:52 -!- Lautner has quit (Ping timeout: 272 seconds).
16:59:03 -!- Lautner has joined.
17:01:14 -!- shikhin has joined.
17:03:39 <Melvar> fizzie: What a cute metathesis.
17:04:47 <HackEgo> Thanks, metathesis. Thetathesis.
17:05:00 <fizzie> Thetathesis sounds like a particle physics thing.
17:05:09 <oerjan> HackEgo: i'm sorry but you were supposed to say Thetamesis tdnh
17:05:27 -!- Lautner has quit (Ping timeout: 244 seconds).
17:06:07 <Melvar> Of course, it makes one wonder how German got “Löwe” from the same source.
17:06:27 <oerjan> it's løve in norwegian hth
17:06:40 -!- Lautner has joined.
17:07:03 <fizzie> Come to Kenya, we've got løver.
17:07:20 <fizzie> The song even refers Norway.
17:07:39 -!- Lymia has quit (Quit: Hugs~ <3).
17:07:48 -!- Lymia has joined.
17:08:01 <oerjan> "From Middle High German lewe, from Old High German leo (both with variants), from Latin leō."
17:08:29 <Melvar> Apparently Norwegian got it from Middle Low German.
17:08:37 <oerjan> "From Old Swedish leon, from Latin leo."
17:08:52 <oerjan> oh right, it's leo, leonis in latin
17:09:28 <oerjan> standard dropping of -n from nominative
17:10:30 <oerjan> borrowed from greek, which had -n everywhere
17:12:19 <Melvar> Is “-ν-” a hook-nose emoticon?
17:12:46 <b_jonas> whereas latin has -us everywhere
17:12:48 <oerjan> no it's a greek letter infixed hth
17:12:58 <oerjan> b_jonas: um not in that word hth
17:13:11 <oerjan> but a lot of them, for sure
17:13:41 <oerjan> apparently wiktionary manages to construct the entire greek declension from {{grc-decl-3rd-οντ-prx|form=M-full|λ|έ|ε}}
17:14:50 <oerjan> "Many ancient languages possessed similar words for lion, including Akkadian 𒌨 (labbu) (reconstructed to Proto-Semitic *labiʾ-). It is unclear who borrowed the word from whom, though the ultimate source is likely not Indo-European."
17:15:06 <HackEgo> [U+12328 CUNEIFORM SIGN UR]
17:17:54 -!- SopaXorzTaker has joined.
17:19:49 -!- kshdecko has joined.
17:22:09 -!- Lautner has quit (Ping timeout: 255 seconds).
17:26:17 -!- Lymia has quit (Quit: Hugs~ <3).
17:29:09 -!- Lymia has joined.
17:30:35 -!- Lymia has quit (Client Quit).
17:32:33 -!- Lymia has joined.
17:39:44 -!- shikhin has quit (Ping timeout: 256 seconds).
17:40:28 -!- vodkode has quit (Remote host closed the connection).
18:00:42 -!- shikhin has joined.
18:06:31 -!- Lautner has joined.
18:07:58 -!- kshdecko has quit (Ping timeout: 244 seconds).
18:12:20 -!- Lautner has quit (Ping timeout: 272 seconds).
18:14:58 <oerjan> ProofTechnique: very cuneiform thx
18:15:03 -!- oerjan has quit (Quit: Later).
18:18:11 -!- Lautner has joined.
18:20:29 <boily> fungot: is there a cuneiform character for chicken twh?
18:20:29 <fungot> boily: hipe iirc is the name of the exception
18:20:44 <boily> fungot: so, no char because of hipe?
18:20:45 <fungot> boily: once we do the fnord on proton are very fnord don't necessarily have anything on paper about this
18:21:07 <boily> A cuneiform chicken needs subatomic fnords. understood.
18:29:02 -!- shikhin has quit (Ping timeout: 256 seconds).
18:34:30 -!- Lautner has quit (Ping timeout: 272 seconds).
18:35:32 -!- Lautner has joined.
18:45:19 <zzo38> Why does charmap crash when I try to start it from the command prompt?
18:46:05 <oren> no idea. it works fine when I do it
18:48:57 <zzo38> It works now, after I closed and reopened the command prompt
18:50:52 -!- kshdecko has joined.
18:51:09 -!- SopaXorzTaker has quit (Read error: Connection reset by peer).
18:54:08 -!- Lautner has quit (Ping timeout: 272 seconds).
18:56:42 -!- Lautner has joined.
18:58:34 -!- kshdecko has quit (Ping timeout: 272 seconds).
19:08:56 -!- Lautner has quit (Ping timeout: 244 seconds).
19:20:17 -!- shikhin has joined.
19:39:12 <HackEgo> [wiki] [[!!!Batch]] http://esolangs.org/w/index.php?diff=42305&oldid=39046 * 73.184.106.177 * (+1) Fixed typo
19:51:04 -!- AnotherTest has joined.
20:01:58 -!- shikhin has quit (Read error: Connection reset by peer).
20:05:03 -!- shikhin has joined.
20:13:57 -!- Koen_ has quit (Quit: The struct held his beloved integer in his strong, protecting arms, his eyes like sapphire orbs staring into her own. "W-will you... Will you union me?").
20:50:12 -!- TieSoul has changed nick to TieSleep.
21:04:22 -!- Frooxius has quit (Quit: *bubbles away*).
21:06:20 -!- supay has changed nick to supay_away.
21:23:31 -!- AnotherTest has quit (Remote host closed the connection).
21:45:27 -!- Frooxius has joined.
21:49:41 -!- shikhin has quit (Quit: leaving).
21:51:57 -!- SgeoPhone has joined.
21:53:39 <SgeoPhone> There's an announcement on nethack.org
22:03:53 <boily> it's very ominous.
22:04:12 <boily> @ask ais523 hello! what with the nethack.org announcement from yesterday?
22:04:25 <boily> @tell ais523 (yesterday being April 3 hth)
22:20:06 -!- SgeoPhone has quit (Remote host closed the connection).
22:20:18 -!- SgeoPhone has joined.
22:20:33 -!- SgeoPhone has quit (Remote host closed the connection).
22:20:49 -!- SgeoPhone has joined.
22:35:20 -!- oerjan has joined.
22:42:49 -!- augur has quit (Ping timeout: 252 seconds).
22:43:51 -!- Patashu has joined.
22:48:15 -!- augur has joined.
22:56:22 -!- SgeoPhone has quit (Remote host closed the connection).
22:56:37 -!- SgeoPhone has joined.
22:57:55 <HackEgo> /home/hackbot/hackbot.hg/multibot_cmds/lib/limits: line 5: exec: r13: not found
23:00:03 -!- vodkode has joined.
23:01:55 <int-e> Another fun big data company. Ostensibly they provide real-time data distribution for web applications, but they also analyze the traffic.
23:02:31 <int-e> Founded 2010, surely took me a long time to stumble upon them.
23:03:48 <int-e> (It seems I could've found them already in late 2013, humblebundle was already one of their customers back then.)
23:04:40 <oerjan> clearly a hebrew company
23:04:56 <int-e> `rot13 phevbfvgl xvyyrq gur png
23:05:28 <int-e> (I had not realized that png is rot13 for cat, I woner whether this explains the obsession of the internet with those creatures...)
23:08:10 <oerjan> the next step after learning to read rot13 code is to be able to speak it fluently
23:09:12 -!- vodkode_ has joined.
23:09:34 <int-e> cyrnfr gryy zr gung lbh'er xvqqvat
23:10:45 <int-e> (I'm using cut&paste and `tr` for this)
23:11:01 <oerjan> i didn't say _i_ could do it. i'm just now disappointed i don't find any youtube videos.
23:11:22 <int-e> "how to read rot13 in 26 easy steps"?
23:11:27 <oerjan> surely a proper linguist should have no problems
23:11:59 <oerjan> erm learning to read it is of course essentially trivial compared to any unknown natural language
23:12:15 <oerjan> but _aloud_ might take a bit of practice.
23:12:28 <oerjan> unless you're bilingually czech-georgian.
23:12:57 <SgeoPhone> I've used pubnub for senior project
23:13:17 <oerjan> int-e: i used cut and paste for most of this too
23:13:20 <int-e> Can't anybody do anything by themselves anymore...
23:14:36 <int-e> (That was a comment about pubnub.)
23:14:53 <oerjan> i managed to make out "Vs lbh fnl fb..." without, though. although i sort of cheated by looking at the above translations.
23:16:01 -!- Frooxius has quit (Quit: *bubbles away*).
23:16:25 <int-e> Whenever I hear "cloud computing" I picture the data as rain.
23:17:10 <int-e> oerjan: that's just the fans blowin
23:18:24 <FireFly> fizzie: so I learned today that the rot14 of "zem.fi" is "nsa.tw"
23:21:39 <oerjan> !zemjoust url_lbh 停止窺探！
23:21:52 <zemhill_> oerjan: I do !zjoust; see http://zem.fi/bfjoust/ for more information.
23:21:53 <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>.
23:21:58 <zemhill_> oerjan.url_lbh: points -30.10, score 3.83, rank 47/47
23:24:38 <FireFly> huh. curious how hey rots to url
23:25:24 -!- Frooxius has joined.
23:26:11 <oerjan> Frooxius: are you a bilingual czech-georgian and can you read rot-13 aloud fluently
23:27:01 <oerjan> rot-13 english, that is. rot-13 czech is probably easy to pronounce.
23:27:28 <oerjan> `rot13 Strč prst skrz krk
23:27:56 <oerjan> well, easier than the original, anyway
23:29:40 <oerjan> yep, holds for georgian too
23:30:25 * oerjan notes himself in the google result
23:30:30 <HackEgo> Thanks, Mgrvgrvladje. Thadje.
23:30:43 <oerjan> good, `thanks now works with it
23:32:02 -!- vodkode_ has quit (Ping timeout: 245 seconds).
23:32:03 <oerjan> hmph google translate doesn't have transcription for georgian
23:33:24 <oerjan> oh hm it's possible the "Georgian Latin" virtual keyboard is actual qwerty in disguise
23:33:51 -!- Frooxius has quit (Quit: *bubbles away*).
23:36:18 <oerjan> ok მგრვგრვლადჯე turns into mgrvgrvladje in GT but no google hits :(
23:36:52 -!- ProofTechnique has quit (Ping timeout: 264 seconds).
23:37:09 <oerjan> i am slightly troubled by the fact the only mentions i've seen of the name is about how it's the largest number of initial consonants word
23:38:26 <oerjan> hm come to think of it i'm pretty sure i tried to cobble the georgian spelling together from wikipedia's alphabet page once
23:42:29 <fizzie> FireFly: You don't have to be worried unless you live in Taiwan hth
23:45:32 <oerjan> funny how georgian letters are completely indecipherable to latin scripters but parts of the alphabet order is clearly related to greek
23:48:39 -!- augur has quit (Ping timeout: 252 seconds).
23:51:35 -!- augur has joined.
23:58:02 -!- augur has quit (Ping timeout: 264 seconds).
00:07:09 -!- augur has joined.
00:13:22 -!- variable has joined.
00:14:43 -!- augur has quit (Ping timeout: 256 seconds).
00:37:15 -!- Patashu has quit (Disconnected by services).
00:37:15 -!- Patashu_ has joined.
00:37:28 -!- augur has joined.
00:40:23 -!- Patashu_ has quit (Remote host closed the connection).
00:40:42 -!- Patashu has joined.
00:42:04 -!- augur has quit (Ping timeout: 256 seconds).
00:48:05 -!- variable has quit (Read error: Connection reset by peer).
00:51:35 <boily> oerjan: armenian letters are somewhat approximatively related to latin letters, with some graphical concordances (e.g. h and o).
00:51:52 <boily> SgeoPhone: to which degree isn't your computer real?
00:52:54 <SgeoPhone> To the degree that the device i am using cannot be used for most of thw things a laptop or desktop can, and to the degree that my laptop s unusable
00:53:09 <oerjan> alan turing would have loved to have a computer as powerful as SgeoPhone's phone.
00:56:16 <HackEgo> [wiki] [[Small SNUSP]] http://esolangs.org/w/index.php?diff=42306&oldid=42304 * Esowiki201529A * (+2)
00:56:18 <Jafet> Unfortunately, they were not coming out at the time.
00:56:24 <zzo38> A phone normally doesn't have a full keyboard or a programming environment though; a computer without a keyboard and programming environment isn't a particularly good computer.
00:57:42 <SgeoPhone> I think there are programming environments. Just not one that allows creation of programs that are first class citizens on the device
00:58:36 <HackEgo> [wiki] [[Small SNUSP]] http://esolangs.org/w/index.php?diff=42307&oldid=42306 * Esowiki201529A * (+360) /* Description */
00:58:42 -!- SgeoPhone has quit (Remote host closed the connection).
00:58:56 -!- SgeoPhone has joined.
00:59:15 <HackEgo> [wiki] [[Small SNUSP]] http://esolangs.org/w/index.php?diff=42308&oldid=42307 * Esowiki201529A * (-55) /* Description */
00:59:31 <SgeoPhone> IRC keeps disconnecting when i get A call
01:01:41 <int-e> Funny that Esowiki201529A has not removed my link yet...
01:02:40 <HackEgo> [wiki] [[Small SNUSP]] http://esolangs.org/w/index.php?diff=42309&oldid=42308 * Esowiki201529A * (+87)
01:03:25 <HackEgo> [wiki] [[Small SNUSP]] http://esolangs.org/w/index.php?diff=42310&oldid=42309 * Esowiki201529A * (+17)
01:03:53 -!- SgeoPhone has quit (Remote host closed the connection).
01:04:07 -!- SgeoPhone has joined.
01:05:38 <HackEgo> [wiki] [[SNUSP]] http://esolangs.org/w/index.php?diff=42311&oldid=42303 * Oerjan * (+14) I think this word might, though.
01:06:34 <boily> who is Esowiki201529A?
01:07:15 <HackEgo> [wiki] [[Small SNUSP]] http://esolangs.org/w/index.php?diff=42312&oldid=42310 * Esowiki201529A * (+305)
01:07:27 <HackEgo> [wiki] [[Small SNUSP]] http://esolangs.org/w/index.php?diff=42313&oldid=42312 * Esowiki201529A * (+1)
01:07:34 <oerjan> some esolanger of dubious taste.
01:09:14 <int-e> it really shouldn't be in the 2003 category, should it?
01:10:41 <HackEgo> [wiki] [[Small SNUSP]] http://esolangs.org/w/index.php?diff=42314&oldid=42313 * Oerjan * (-19) Category should be for this article's language only
01:13:57 <int-e> Reading Andy D's proof from http://www.scottaaronson.com/blog/?p=710 that "consistent guessing" is weaker than the halting problem leaves me wondering whether there is any CG-Oracle that is computable given an oracle for the halting problem, and still weaker in that it cannot be used to solve the halting problem...
01:15:18 <int-e> (As far as I've followed the construction, I think it would need a Halting oracle for Turing machines with a Halting oracle. Tricky beast, and a tricky proof.)
01:22:41 <HackEgo> [wiki] [[Small SNUSP]] http://esolangs.org/w/index.php?diff=42315&oldid=42314 * Esowiki201529A * (+64)
01:24:29 <HackEgo> [wiki] [[Small SNUSP]] http://esolangs.org/w/index.php?diff=42316&oldid=42315 * 213.162.68.171 * (-19) Remove 2003 category again.
01:29:08 <boily> the dubiousity is steadily increasing.
01:30:01 <oerjan> i'm going to assume it was a race condition.
01:33:06 <SgeoPhone> On a related note, i don't think my dad knows how time works
01:35:03 -!- SgeoPhone has quit (Remote host closed the connection).
01:35:18 -!- SgeoPhone has joined.
01:36:59 <int-e> (Of course I took "how time works" at its most fundamental meaning ... where does time come from, and what makes it, so to say, tick?)
01:37:27 <zzo38> There is no time...only, there is spacetime.
01:38:43 <int-e> That's a nicely working theory. Will it work tomorrow? Will there *be* a tomorrow? Or anything besides this instant?
01:39:10 * int-e tries hard to remember what kind of #esoteric channel this place is...
01:40:26 -!- SgeoPhone has quit (Ping timeout: 256 seconds).
01:40:55 <oerjan> time is an illusion. lunch-time doubly so.
01:41:15 <int-e> oh yeah, the nearest place to eat...
01:42:16 <int-e> oerjan: I think you should've used s/-//, it would be easier to decipher
01:43:20 <int-e> Oh, it happens in the very beginning.
01:43:38 <int-e> Maybe I should reread the whole trilogy another time...
01:44:20 <int-e> oerjan: I wish I would've remembered the reply: "Very deep," said Arthur, "you should send that in to the Reader's Digest. They've got a page for people like you."
02:21:01 <boily> I like the Reader's Digest, if only because it helps me forget the moments I was stupidly waiting for my dentist with a discharged cellphone.
02:25:41 -!- boily has quit (Quit: CARBONATED CHICKEN).
02:28:35 -!- SgeoPhone has joined.
02:31:23 -!- fractal has quit (Remote host closed the connection).
02:42:54 -!- GeekDude has quit (Read error: Connection reset by peer).
02:43:19 -!- nys has quit (Quit: quit).
02:52:36 <oerjan> int-e: it's ok, i didn't remember the reply either.
02:53:23 <int-e> oerjan: I meant, if I had remembered, I would have used it on you in some other occasion(s) :)
02:57:46 -!- vodkode_ has joined.
03:01:12 -!- Lymia has quit (Remote host closed the connection).
03:03:00 -!- Lymia has joined.
03:04:17 -!- SgeoPhone has quit (Ping timeout: 244 seconds).
03:24:40 -!- Sprocklem has quit (Quit: Nettalk6 - www.ntalk.de).
03:25:12 -!- Sprocklem has joined.
03:51:14 -!- dianne has quit (Quit: byeannes).
04:03:47 -!- Sprocklem_ has joined.
04:06:04 -!- Sprocklem has quit (Ping timeout: 252 seconds).
04:07:10 -!- Sprocklem_ has changed nick to Sprocklem.
04:08:29 -!- variable has joined.
04:16:55 -!- f|`-`|f_ has joined.
04:18:28 -!- f|`-`|f has quit (Ping timeout: 250 seconds).
04:18:36 -!- f|`-`|f_ has changed nick to f|`-`|f.
04:22:02 -!- oerjan has quit (Quit: leaving).
04:28:22 -!- Patashu_ has joined.
04:28:22 -!- Patashu has quit (Disconnected by services).
04:58:17 -!- Sprocklem has quit (Quit: Leaving).
05:02:24 <zzo38> To make random number uniform with any given range (0 to N-1), what I have done is you take as many random bits as needed (for the higher or equal power of 2), if it is too big then try again. So if N=3 then you have bits 00,01,10,11 but if 11 you must try again. If you only need a 1/3 probability (and don't need to distinguish between the other two possibilities), then you can optimize this algorithm, and it looks like in Pokemon card that is wha
05:12:27 -!- vodkode_ has quit (Ping timeout: 264 seconds).
05:24:03 -!- Sprocklem has joined.
05:28:33 <lifthrasiir> zzo38: a naive rejection sampling is not optimal, though; for 1/5 probability you would reject 101 through 111, but adding one bit and adjustement yields further 5/16 probability to finish; compare that with adding 3 bits which will only yield 15/64 probability to finish.
05:31:28 <zzo38> I was talking about the N=3 case and didn't think about the other cases, but I suppose you can optimize it in other ways too
05:49:38 -!- ^v^v has quit (Read error: Connection reset by peer).
05:58:18 -!- ProofTechnique has joined.
06:17:18 -!- vodkode_ has joined.
06:18:16 -!- dianne has joined.
06:24:24 -!- roasted42 has joined.
06:25:43 -!- roasted42 has quit (Changing host).
06:25:43 -!- roasted42 has joined.
06:25:43 -!- roasted42 has changed nick to TheM4ch1n3.
06:31:56 -!- variable has changed nick to function.
06:36:16 -!- TheM4ch1n3 has left.
07:16:56 <zzo38> Still the algorithm I specified is the way to generate random 0 to N-1 if N isn't known before this subroutine is called, and I have done in C code and in 6502 code. There might be better way, although I don't know. With a 6502 code you can count how many cycles it requires!
07:48:06 -!- Lymia has quit (Remote host closed the connection).
07:49:47 -!- roasted42 has joined.
07:49:59 -!- roasted42 has quit (Changing host).
07:49:59 -!- roasted42 has joined.
07:49:59 -!- roasted42 has changed nick to TheM4ch1n3.
07:53:06 -!- fractal has joined.
07:54:14 -!- TheM4ch1n3 has quit (Client Quit).
08:06:20 -!- function has quit (Ping timeout: 256 seconds).
08:14:44 -!- Lymia has joined.
08:30:18 -!- vodkode_ has quit (Ping timeout: 244 seconds).
08:45:35 -!- vodkode_ has joined.
09:18:21 -!- vodkode_ has quit (Ping timeout: 246 seconds).
09:27:00 <Taneb> Why are D10s such a lame shape
09:29:44 <f|`-`|f> you can make a roller die, or a ten sided prism a lot like the d8, Taneb
09:30:33 <Taneb> fungot, what do you think of D10s?
09:30:33 <fungot> Taneb: i just used google image search, even. let*-optionals would be a small icon in tray to sync the clipboards maybe.
09:36:32 <myname> i like those longer d10
09:37:52 <myname> http://www.gmdice.com/media/catalog/product/cache/1/image/9df78eab33525d08d6e5fb8d27136e95/d/1/d10-crystal-oblivion-red.png
09:50:54 -!- shikhin has joined.
10:02:00 <f|`-`|f> that's a roller die, myname
10:04:37 -!- shikhin has quit (Ping timeout: 256 seconds).
10:07:57 -!- shikhin has joined.
10:28:10 -!- shikhin has quit (Ping timeout: 255 seconds).
10:50:33 -!- boily has joined.
11:21:17 -!- J_Arcane_ has joined.
11:23:03 -!- J_Arcane__ has joined.
11:24:14 -!- J_Arcane has quit (Ping timeout: 252 seconds).
11:24:27 -!- J_Arcane__ has changed nick to J_Arcane.
11:27:00 -!- J_Arcane_ has quit (Ping timeout: 244 seconds).
11:49:39 -!- Sprocklem_ has joined.
11:51:25 -!- Sprocklem has quit (Ping timeout: 255 seconds).
12:05:41 -!- fractal has quit (Changing host).
12:05:41 -!- fractal has joined.
13:13:22 <int-e> zzo38: http://sprunge.us/WCAD looks like it could be suitable for simple processors.
13:17:44 <boily> fungot: fungellot. still trapped?
13:17:44 <fungot> boily: and more half-finished scheme implementations. the question here is, how would i know
13:17:58 <boily> fungot: because of the implementations, duh.
13:17:58 <fungot> boily: i think it could be another one
13:18:07 <boily> fungot: you've got another reason?
13:18:07 <fungot> boily: what about smileys like this ( if e1 ( error e2) e3)
13:18:28 <boily> fungot: those aren't smileys, they're sexpes.
13:18:28 <fungot> boily: i'll write a forum post about a store in helsinki which sells african decoration stuff etc for ridiculously low prices.
13:18:54 * boily takes a sloooow step back away from the sentient 'got...
13:22:49 <int-e> uh, has google always perverted the lower case g like that?
13:23:15 <boily> int-hello. how come?
13:23:58 <int-e> Apparently it has.
13:25:10 <boily> their g looks fine to me.
13:26:30 -!- SopaXorzTaker has joined.
13:27:15 <int-e> The lower loop is attached in a weird (wrong ;-) ) way.
13:27:51 <int-e> the attachment is usually much further to the left.
13:28:28 <int-e> But I have not noticed in 15 years, I wonder what triggered this observation now.
13:30:38 <int-e> (actually I was hoping for an easter logo)
13:32:44 -!- Patashu_ has quit (Ping timeout: 256 seconds).
14:01:41 -!- nys has joined.
14:04:20 <boily> @tell oerjan Joyoeurjanses Pâques!
14:05:20 <boily> b_joyeusnas pâques à toi aussi!
14:09:51 <boily> how do you hungarianly wish Happy Easter?
14:16:52 -!- oerjan has joined.
14:18:39 <b_jonas> boily: ask http://www.omniglot.com/language/phrases/easter.htm
14:30:06 -!- ^v has joined.
14:36:12 -!- ^v has quit (Quit: Network ban).
14:36:33 -!- ^v has joined.
14:48:25 -!- GeekDude has joined.
14:55:33 <lambdabot> CYQB 051400Z 28014KT 20SM FEW052 FEW080 SCT200 M05/M15 A2997 RMK CU1AC1CI2 SLP153
14:57:17 <lambdabot> ENVA 051450Z 14005KT 9999 -SHSN BKN029 05/M05 Q1020 RMK WIND 670FT 18006KT
14:57:34 <oerjan> nevertheless, i saw snow a moment ago.
14:58:35 <lambdabot> ESSB 051450Z 36010KT 330V040 9999 SHRA GS FEW022CB SCT040 05/01 Q1020 R30/19//60
14:58:43 <FireFly> It was snowing a few hours ago
14:58:56 <lambdabot> LOWI 051450Z 27007KT 9999 -SHSN FEW010 BKN050 03/M00 Q1019 TEMPO SHSN
14:58:58 <FireFly> oops, "a few" is 10 apparently
14:59:45 <lambdabot> EGLL 051450Z VRB04KT 9999 BKN038 12/04 Q1027
14:59:59 <fizzie> I feel strange, being at the warmest place when people are @metaring.
15:00:15 <oerjan> <Taneb> Why are D10s such a lame shape <-- just use a D20 with duplicate numbers hth
15:00:42 <oerjan> it's the platonic solution
15:03:31 <fizzie> "Or cut a D20 in half. Wait..."
15:03:33 <lambdabot> KSFO 051456Z 14004KT 10SM FEW020 BKN030 BKN055 12/07 A2991 RMK AO2 RAB35E44 SLP129 P0000 60000 T01170067 55004
15:04:11 <boily> f|`-`|f: why the questionment?
15:04:40 <f|`-`|f> To violate your sense of world, and make you truly wonder
15:04:51 <f|`-`|f> Why the hell don't they have a specific question
15:05:52 <boily> fungot: f|`-`|f makes less sense than you. how is it possible?
15:06:12 <fizzie> Your fungot quota is up!
15:06:12 <fungot> fizzie: so, is the element before the current one. fnord
15:18:40 -!- SopaXorzTaker has quit (Remote host closed the connection).
15:22:51 -!- SopaXorzTaker has joined.
15:23:24 -!- SopaXorzTaker has quit (Max SendQ exceeded).
15:38:31 -!- simpleirc has joined.
15:39:44 -!- simpleirc has quit (Remote host closed the connection).
16:05:28 -!- shikhin has joined.
16:13:20 -!- GeekDude has quit (Ping timeout: 255 seconds).
16:36:18 -!- oerjan has quit (Quit: leaving).
16:59:52 -!- Sprocklem_ has changed nick to Sprocklem.
17:09:12 -!- zadock has quit (Quit: Leaving).
17:32:07 -!- Tod-Autojoined has joined.
17:32:07 -!- TodPunk has quit (Read error: Connection reset by peer).
17:40:14 -!- fractal has quit (Ping timeout: 256 seconds).
17:51:15 -!- fractal has joined.
17:53:51 -!- boily has quit (Quit: FAMILIAR CHICKEN).
17:56:42 -!- augur has joined.
18:09:58 -!- shikhin has quit (Ping timeout: 245 seconds).
18:15:20 -!- shikhin has joined.
18:21:30 -!- Sprocklem has quit (Ping timeout: 252 seconds).
18:26:58 -!- zadock has joined.
18:28:12 -!- shikhin_ has joined.
18:28:18 -!- shikhin has quit (Ping timeout: 245 seconds).
18:28:43 -!- shikhin_ has changed nick to shikhin.
18:41:50 <oren> hello, I have awoken from my eternal, alcohol-induced slumber
18:42:58 <fungot> b_jonas: it's just fnord of the object you pass in variable column names??? i have
18:45:37 -!- lleu has joined.
18:45:37 -!- lleu has quit (Changing host).
18:45:37 -!- lleu has joined.
19:08:51 -!- roasted42 has joined.
19:11:40 -!- roasted42 has quit (Changing host).
19:11:40 -!- roasted42 has joined.
19:11:40 -!- roasted42 has changed nick to TheM4ch1n3.
19:21:28 -!- Sprocklem has joined.
19:22:05 -!- ais523 has joined.
19:26:34 <fungot> FireFly: set! was perfectly fine for scheme-hacking weather
19:26:53 <FireFly> fungot: I wish you would set! the weather to be a bit warmer tomorrow
19:26:53 <fungot> FireFly: my brain is scrambled too, just so it can
19:29:29 -!- TieSleep has changed nick to TieSoul.
19:46:23 <oren> Why doesn't the C standard library provide a "print quoted string" function!?!?!
19:48:28 <oren> Well, I guess I'll have to write fputqs myself
20:14:18 -!- izabera has changed nick to iza1.
20:14:21 -!- iza1 has changed nick to izabera.
20:31:16 <tswett> So are there any unsolved yes-or-no questions in mathematics where about half of people think they're true and about half think they're false?
20:31:57 <tswett> Seems like everyone thinks the Riemann hypothesis, the Goldbach conjecture, and the Collatz conjecture are all true (and there's some pretty nice evidence for all of these), and that P != NP.
20:32:34 <b_jonas> tswett: I don't think the Collatz conjecture is held so generally
20:32:57 <b_jonas> tswett: but there are much better examples where half of the people think it's true
20:33:06 <b_jonas> there's, for example, the Hedetniemi conjecture about graph products
20:33:57 -!- Ronarsky has joined.
20:34:32 <int-e> that's a nice one, thanks
20:34:48 -!- Tod-Autojoined has changed nick to TodPunk.
20:34:56 -!- copumpkin has joined.
20:37:23 -!- boily has joined.
20:37:46 <b_jonas> I'm not sure it's really "half", but I think at least one famous mathematicians has declared they conjecture it and at least one has declared they conjecture the opposite
20:38:03 <b_jonas> obviously not everyone will have an opinion
20:38:51 <oren> tswett: My first thought was "the question of whether math talent is inborn" but that's really a biological question about mathematics.
20:39:18 <oren> or rather about the biology of mathematcians
20:39:32 -!- Ronarsky has quit (Ping timeout: 252 seconds).
20:39:33 <b_jonas> oren: besides not being a mathematical question, that's not even a yes-no question
20:40:30 <tswett> Now, here's a question.
20:41:01 <tswett> Is there a "simple and easy to calculate" function N -> N whose image contains infinitely many numbers, all of which are prime?
20:41:21 <int-e> b_jonas: did you arrive at that conclusion formally or intuitively? (scnr)
20:42:56 <int-e> > nubBy (\a b -> 1 < gcd a b) [2..]
20:42:58 <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,...
20:43:37 <int-e> (what does "simple and easy to calculate" mean?)
20:44:14 <myname> infinitely many numbers, all of which are prime
20:44:16 <ais523> tswett: there's a moderately well known N^lots -> N function whose image contains all prime numbers, and no other positive numbres
20:44:19 <int-e> > nubBy (((1<).).gcd) [2..]
20:44:20 <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,...
20:44:31 <int-e> myname: but the image is finite
20:44:50 <tswett> The set {2} certainly isn't "infinitely many".
20:45:19 <tswett> int-e: well, let's say "easier to calculate than just finding the smallest prime number larger than n".
20:45:30 <int-e> ais523: My memory may be failing me, but isn't it -> Z, and we know nothing about the negative numbers?
20:45:36 <ais523> boily: re your lambdabot message: the NetHack devteam finally realised they probably weren't going to get another release out by themselves, and hired some variant developers to help out
20:45:49 <lambdabot> [2,3,5,7,9,11,13,15,17,19,21,23,25,27,29,31,33,35,37,39,41,43,45,47,49,51,53...
20:45:56 <ais523> it isn't what you were asking for, but it's similar enough that I mentioned it anyway
20:46:04 <boily> this is approximatively good enough for primes, and is easy to compute.
20:46:12 <boily> ais523: oh! thanks for the heads up.
20:48:17 <tswett> I guess you could turn it into a function N -> N by using an isomorphism between N and N^lots.
20:48:29 <tswett> ais523: so what's the function?
20:48:45 <ais523> tswett: I don't know it offhand, it's some huge polynomial that was compiled from Lisp
20:48:51 <ais523> but being a polynomial, it's easy to calculate ;-)
20:50:06 <oren> how can a polynomial have an image containing only integers?
20:50:17 <tswett> By having only integers in its domain.
20:50:30 <int-e> b_jonas: we could have a poll for the second conjecture from http://int-e.eu/~bf3/squares/ (we're tiling rectangles with a minimal number of squares of integer size. if we scale the rectange (multiplying both sides by a positive integer), can the number of required squares become smaller?)
20:51:25 <ais523> int-e: ooh, that's an interesting question
20:52:21 <b_jonas> int-e: interesting, have asked that on Mathoverflow?
20:54:26 <b_jonas> int-e: also, Erich Friedman might be the right person to ask that
20:54:49 <b_jonas> obviously either of these only after you've tried to search existing literature
20:56:12 <oren> Equivalently: The fewest squares solution to an NxM rectangle must, if N and M are both divisible by K, consist of squares whose side lengths are divisible by K
20:56:41 <b_jonas> oren: what if there's more than one solution with the fewest squares?
20:57:34 <ais523> "at least one fewest squares solution" if we're trying to be equivalent to the old wording
20:57:49 <ais523> "all fewest squares solutions" seems like a more interesting wording, though
20:58:13 <int-e> b_jonas: I probably won't, not any time soon anyway.
21:00:09 <b_jonas> int-e: http://mathoverflow.net/q/44524/5340 may be relevant
21:01:57 <b_jonas> int-e: and it links to http://mathoverflow.net/q/116382/5340
21:02:20 <b_jonas> which in turn links back to you
21:02:37 <b_jonas> and asks precisely about that conjecture you're asking
21:07:20 -!- TheM4ch1n3 has quit (Quit: later - tomorrow sometime while I upgrade valgrind & other things).
21:09:43 -!- TieSoul has changed nick to TieSleep.
21:11:12 -!- ais523 has quit (Read error: Connection reset by peer).
21:11:17 -!- callforjudgement has joined.
21:17:58 -!- oerjan has joined.
21:18:46 -!- zadock has quit (Quit: Leaving).
21:22:58 -!- callforjudgement has changed nick to ais523.
21:34:56 <oerjan> <int-e> (what does "simple and easy to calculate" mean?) <-- what about an algorithm which finds a >= n digit prime in time O(n^k) ?
21:37:03 <oerjan> that may not be simple enough, but it should e.g. crush all current prime records easily.
21:39:46 <b_jonas> oerjan: the point is, it's a well-known conjecture whether there's a _deterministic_ algorithm for that, but there's a very easy randomized algorithm
21:40:03 <b_jonas> the randomized algorithm is to just pick a random n digit number and prime test it
21:40:14 -!- shikhin has quit (Quit: leaving).
21:40:23 <b_jonas> the prime test is fast (polynomial time) and there's O(1/n) chance that the number is a prime
21:40:48 <ais523> b_jonas: well, can't you replace the random generation, with any pseudorandom generation that isn't above-average at hitting composite numbers?
21:41:05 <b_jonas> but the prime records are so big that even prime testing is slow for them, and they actually use special form numbers with faster prime tests, specifically Mersenne numbers (numbers of the form 2**n-1 where n is an integer)
21:41:28 <b_jonas> ais523: that's why it's a conjecture (and because people generally think randomness doesn't help anything)
21:41:49 <b_jonas> but I think it's still open, and an important open problem
21:42:20 <oerjan> yes, it's also a conjecture that randomness doesn't help, although that may be at P vs. NP level of difficulty
21:42:30 <b_jonas> ais523: http://polymathprojects.org/2009/07/27/proposal-deterministic-way-to-find-primes/
21:42:44 <b_jonas> that might have some useful descriptions and links
21:50:38 -!- Guest3780 has joined.
21:53:16 <oerjan> it feels slightly wrong to link a fanfiction when i don't even read the real thing but http://www.mezzacotta.net/dinosaur/?comic=70
21:53:36 <oerjan> wait, this applies to 99% of DMM's stuff
21:59:55 -!- erdic has quit (Ping timeout: 256 seconds).
22:10:06 <int-e> /topic Cheesecake! | https://dl.dropboxusercontent.com/u/2023808/wisdom.pdf http://codu.org/logs/_esoteric/ http://tunes.org/~nef/logs/esoteric/
22:12:07 <ais523> int-e: escaped intentionally?
22:12:26 <int-e> yes, we have +t set at the moment.
22:13:00 <ais523> hmm, did the trollbot come back?
22:14:33 <int-e> (it's actually quite hard to escape things accidentally in irssi; the way to do that is to start a line with a slash, then a space: / /topic ...)
22:15:37 <ais523> ah, Konversation escapes with just //
22:16:07 -!- erdic has joined.
22:16:31 <b_jonas> int-e: the easiest way I accidentally escape is by trying to press / but the layout is set to Hungarian so it types - instead
22:20:02 <int-e> "Verify this email address ([email protected]) and attach it to your account?"
22:20:15 <int-e> I think I'm beginning to HATE cloudfront.
22:21:51 <int-e> (as a "security feature", they replace strings that look like email addresses by javascript snippets)
22:26:09 <myname> it is a valid email in the source?
22:32:23 -!- Patashu has joined.
22:32:56 -!- callforjudgement has joined.
22:36:17 -!- ais523 has quit (Ping timeout: 264 seconds).
22:36:39 -!- callforjudgement has changed nick to ais523.
22:44:29 <oerjan> <ais523> hmm, did the trollbot come back? <-- yes it did
22:54:30 * boily is sad the chännel's been +ted...
22:54:49 <oerjan> it is, indeed, untraditional.
22:55:13 -!- ChanServ has set channel mode: +o oerjan.
22:55:26 -!- oerjan has set channel mode: -t.
22:55:30 -!- oerjan has set channel mode: -o oerjan.
22:55:40 <oerjan> yay i got the syntax right
22:56:01 <shachaf> oerjan: advanced irc users do it in one command hth
22:56:20 <shachaf> e.g. /mode #esoteric -to oerjan
22:56:39 <boily> you change the mode of #esoteric to oerjan???
22:56:54 * boily TILed that oerjan is an IRC channel flag.
22:57:59 -!- Sprocklem has quit (Ping timeout: 252 seconds).
23:07:28 -!- int-e has set topic: Educated Cheesecake! | https://dl.dropboxusercontent.com/u/2023808/wisdom.pdf http://codu.org/logs/_esoteric/ http://tunes.org/~nef/logs/esoteric/.
23:07:36 <int-e> oerjan: is that wise enough for you?
23:08:11 <oerjan> i find that question a bit academic
23:08:55 <boily> does the cheesecake have a generous coulis de framboises on it?
23:09:39 <oerjan> @google coulis de framboises
23:09:41 <lambdabot> http://www.marmiton.org/recettes/recette_coulis-de-framboises_11316.aspx
23:09:41 <lambdabot> Title: Coulis de framboises : Recette de Coulis de framboises - Marmiton
23:13:40 <oren> what's your favorite number? mine is 7
23:25:45 <int-e> I suspect that if I start weighing all natural numbers against one another, I'll never finish. Fiendish.
23:27:06 <shachaf> int-e: you're thinking of conatural numbers hth
23:31:50 * oren doesn't know what a conatural number is, and bing is not helpful
23:32:29 <nys> natural numbers with the arrows reversed
23:33:49 <int-e> I guess it's a co-free datatype, a final co-F-algebra with F(A) = 1+A.
23:34:25 <int-e> (Whereas the natural numbers are a free datatype, an initial F-algebra, with the same F.)
23:35:05 <int-e> The difference is that omega is a conatural number, the conatural number that is its own successor.
23:35:54 <int-e> just regard it as a stream over ().
23:37:16 <oren> So it's the naturals, plus Ω where succ(Ω)=Ω . got it
23:37:28 <int-e> ... I should've written "F-coalgebra".
23:37:42 <int-e> It's the cofree F-coalgebra, with F as above.
23:39:42 <shachaf> A cofree F-coalgebra works out to the same thing as the cofree comonad on F, right?
23:40:14 <shachaf> So I guess in that sense you can say that CofreeComonad F () is the greatest fixed point of F.
23:40:30 <shachaf> But that seems pretty different from saying that the greatest fixed point itself is cofree.
23:42:06 <boily> I know some of these words.
23:42:10 <oren> Wat.are you people speaking English?
23:44:12 <boily> it seems so; or something vaguely similar.
23:44:45 <int-e> shachaf: Ok, let me go one step back. I want a final F-coalgebra, whereas the datatype is an initial F-algebra.
23:45:23 <int-e> naturals, in this case.
23:48:12 <boily> oren: I fear they are afflicted with acute fungotitis. I can't make sense at all about what they're communicating.
23:48:12 <fungot> boily: since it counts block allocation amounts in the filesystem
23:48:48 <shachaf> Anyway if it is cofree I'd like to know how.
23:49:01 <shachaf> Especially if there's some relationship to monoids.
23:49:22 <shachaf> boily: it's not very complicated but there are a lot of words
23:50:21 <boily> I know I read some blog posts about F-algebras and stuff like that, that on the spur of the moment it seemed all clear, but by the next day it had all but evaporated from my mind.
23:59:47 <shachaf> I guess the question I was asking before was along the lines of: Lists are free monoids. Are colists any sort of universal monoid construction?
00:00:28 <ais523> I'm surprised that lists aren't self-dual
00:00:41 <ais523> although, the list comonad is for /nonempty/ lists specifically
00:01:25 <ais523> (that actually came up at work, someone was presenting some heavily comonad-based research, and some of the people there didn't know what the list comonad was)
00:01:37 <shachaf> I don't think "colist" is dual in the usual sense.
00:01:55 <shachaf> It's the greatest fixed point vs. the list fixed point of some functor.
00:04:11 -!- callforjudgement has joined.
00:04:22 -!- ais523 has quit (Disconnected by services).
00:04:29 -!- callforjudgement has changed nick to ais523.
00:05:43 <int-e> shachaf: Ok, I think I've got it. The final F-coalgebra is cofree over an empty set of cogenerators, so applying the term is awkward, because usually the cogenerator object is not fixed like that.
00:06:58 <shachaf> I'm not sure what you mean.
00:07:09 <int-e> shachaf: In contrast to the cofree comonad, there is also less structure: The cofree comonad has an F-coalgebra, and furthermore the comonad signature, with extract mapping to the cogenerators.
00:09:23 <shachaf> What are cogenerators? Why is it an empty rather than a singleton set of them? I think I'm missing something.
00:09:57 <int-e> In Cofree f a, a are cogenerators.
00:10:12 <shachaf> "Cofree" is the cofree comonad?
00:10:19 <int-e> Oh it must be a singleton.
00:11:03 <shachaf> OK, I guess there are at least two different ways of getting the cofree comonad, as a cofree f-coalgebra and as a cofree comonoid in the category of endofunctors.
00:11:03 <int-e> Too much dualizing. I'd rather discuss free/initial things...
00:11:30 <shachaf> OK, free/initial things are fine.
00:11:43 <shachaf> In which case it's the empty set.
00:11:47 <int-e> shachaf: the final f-coalgebra does not have the comonad structure. that's what I was trying to get art.
00:12:20 <shachaf> Right, I thought that's what I was getting at too.
00:12:29 <shachaf> In what sense is it cofree?
00:13:11 <shachaf> OK, I think I see what you mean.
00:14:14 -!- callforjudgement has joined.
00:14:19 -!- ais523 has quit (Remote host closed the connection).
00:14:24 <int-e> In that if you fix the cogenerators to be a final object (different category, and awkward, as said above), you get the additional arrows to the cogenerator objects that the cofree definition has for ... uhm ... free.
00:14:32 -!- callforjudgement has changed nick to ais523.
00:15:47 <int-e> So, to summarize, I should just say 'final' or 'terminal' or whichever, not 'cofree', to avoid confusion.
00:16:09 <ais523> I dunno, pretty much every term in maths means like ten different things by now
00:16:26 <ais523> terminology like "terminal" isn't so useful without knowing what category you're talking about
00:16:52 <ais523> (in the sort of categories I work with, the final object is normally the unit data type, e.g. () in Haskell or Ocaml)
00:17:36 <shachaf> i,i in the category of this airport, this object is initial terminal
00:18:32 <ais523> hmm, if the same object is both initial and terminal
00:18:46 <ais523> what restrictions does that put on the category
00:19:09 <shachaf> https://en.wikipedia.org/wiki/Zero_object
00:19:47 -!- callforjudgement has joined.
00:19:51 <shachaf> Hmm, I thought that article said more about it.
00:21:28 <shachaf> int-e: https://www.fpcomplete.com/user/dolio/many-roads-to-free-monads
00:21:42 <shachaf> "One final aside is that there is a well known theorem that "left adjoints preserve colimits" (and right adjoints, limits). Free F is a left adjoint, so it will take an initial object 0 to the initial F-algebra."
00:21:52 <shachaf> I remember talking to dolio about this.
00:22:37 -!- ais523 has quit (Disconnected by services).
00:22:39 -!- callforjudgement has changed nick to ais523.
00:25:45 -!- ais523 has quit (Remote host closed the connection).
00:25:57 -!- ais523 has joined.
00:39:08 -!- Decim has joined.
00:39:58 <Decim> The fires of hell will eclipse your soul and drag you into the void of despair as you watch all happiness that you cling to fade away
00:40:07 <Decim> Idk what I'm talking about
00:40:28 <ais523> I don't know who you're talking to
00:40:32 <ais523> but that's not a very nice introduction, really
00:40:49 <ais523> HackEgo: you're being slow today
00:41:00 <HackEgo> Decim: 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.)
00:41:00 <HackEgo> Decim: 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.)
00:41:23 <Decim> Don't welcome me because I've litterally been welcomed on every single one of my clients for 5 months
00:41:38 <ais523> well, if we don't know who you are
00:41:42 <ais523> you're going to be welcomed a lot
00:41:50 <ais523> but I did it in black and white this time, for a change
00:41:59 <Decim> Oh people know who I am
00:42:39 <Decim> Everything is black and white because of the default filter on Andchat
00:43:23 <oerjan> ais523: it was obvious to me who it was after the first two lines hth
00:43:42 <ais523> oerjan: well you're paying more attention than I am
00:43:45 <ais523> although, it clearly isn't me or you
00:44:49 <Decim> oerjan stop spotting me out, I'm not trying to hide behind nicks I don't even have a vpn
00:45:15 <ais523> normally you can tell who the regulars here are by the writing style
00:45:18 <Decim> I just like these cooool names whilst I'm programming stuff
00:45:30 <FireFly> ais523: I believe that's what oerjan did
00:45:41 <ais523> e.g. do lines start with a capital letter, do they end with a full stop, do nickpings use a comma or colon, do they use "hth" a lot
00:45:46 <oren> i just usemyreal name
00:45:56 <oerjan> FireFly: also the nick, really.
00:46:09 <Decim> My real name is reallllly long
00:46:12 <oren> Yeah, my real name is oren
00:46:18 <FireFly> oh, I didn't realise Oren was a name
00:46:30 <oren> it is normally spelled orin
00:47:07 <FireFly> I would use my real name, but someone registered it 12 years ago
00:47:18 <FireFly> (okay, I wouldn't use it either way)
00:47:20 <Decim> So I don't use it as a nick as most irc clients can't parse 29 letter names
00:47:44 -!- oren has changed nick to OrenWatson.
00:47:53 -!- shachaf has left.
00:48:47 -!- Guest3780 has quit (Ping timeout: 256 seconds).
00:49:02 <oerjan> i think shachaf got fed up again
00:49:16 <Decim> How do you your name oerjan
00:51:10 <ais523> I thought ø was an "aw" sound (like in "forward", which is why oerjan used that word)?
00:51:32 <oerjan> it's a fronted rounded vowel
00:52:11 <ais523> maybe I'm thinking of a different letter
00:52:46 <oerjan> i'm just joking about it being the obvious pronunciation of each letter in norwegian
00:52:57 <Decim> So I was pronouncing it correctly
00:53:34 <oerjan> the j is essentially an english y yes
00:53:44 * int-e wonders how different Ø is from Ö.
00:53:55 <ais523> I mentally pronounce your name as though it were English
00:54:08 <ais523> although we don't get a lot of "oer" in English, "ur" is close enough for mental pronunciation
00:54:21 <ais523> because the purpose of a mental pronunciation is mostly to be able to type things correctly
00:54:23 <Decim> How do you pronounce œ then?
00:54:25 <oerjan> int-e: more tense i think
00:54:27 <ais523> (I type by sound for some reason)
00:54:33 <oerjan> assuming you mean the german
00:55:05 <int-e> oerjan: and you mean the Ö?
00:55:28 <oerjan> the norwegian is more tense and pouted
00:55:40 <Decim> Pronouncing oerjans name in Enochian is quite trouble some
00:56:04 <oerjan> the n is also pretty close to normal for english
00:56:30 <oerjan> the a is short but otherwise close to a in father
00:56:56 <oerjan> the r is a tap, so you're all hopeless on that >:)
00:59:41 <Decim> Med ("grapha" sounded in the throat) don ged un drux is your name in enochian oerjan
00:59:50 <oerjan> ais523: "ur" is probably the closest you get in english
01:00:10 <Decim> I'm learning this language just to have fun
01:02:15 <Decim> Have you been making anything in esolangs lately oerjan or nah
01:21:30 -!- Decim has quit (Remote host closed the connection).
01:23:04 <OrenWatson> I am writing some more horrifying C code! the function sc7cpy allows to copy a linked list of integers by sc7cpy("dR",ll);
01:23:49 <OrenWatson> you can copy a tree of integers by sc7cpy("dRR",tree);
01:24:24 <ais523> what would be the smallest change to NetHack needed to make it TC
01:24:28 <ais523> ideally actually TC, not just bounded-storage
01:24:56 <OrenWatson> hmm, how detailed is the enemy behaviour?
01:25:24 <ais523> the enemy behaviour is mostly incomprehensible, because its bugs obscure its intended features
01:25:31 <ais523> although I've fixed it a bunch in my own variant
01:26:08 <int-e> maybe you can find a buffer overflow that leads to arbitrary code execution... just a thought.
01:26:57 <oerjan> i say that doesn't count
01:27:06 <oerjan> it needs to be in portable nethack
01:27:27 <ais523> int-e: yes, there are a ton of those, but I was thinking in the game mechanics
01:27:47 <oerjan> ais523: add a turing monster hth
01:28:02 <int-e> oerjan: it's the best I could do with my very limited knowledge of nethack
01:28:19 <ais523> I'd love it if people could automate the dungeon Dwarf Fortress-style
01:28:51 <ais523> I guess you'd have to involve items somewhere, because they're the only thing in the game that you can have unlimited amounts of under game mechanics (ofc the game itself runs into trouble tracking them eventually, but I just consider that to be an imperfect interp_
01:28:55 -!- Sgeo has joined.
01:33:20 <int-e> an imperfect interp_?
01:33:54 * int-e is unsure whether that got cut off.
01:34:07 * int-e realizes that _ is next to )
01:34:20 * boily summons an imp_ “RISE, MIGHTY FUNGOT!”
01:34:35 <oerjan> the imp tells you to shout less
01:35:02 <fungot> int-e: there's a parser that works in practice but never had the pro stuff. but who would want to do is allow fnord image transmission. the gba has a linux
01:35:42 <boily> oerjan: okay >_>'...
01:36:41 -!- Guest3780 has joined.
01:36:49 <boily> `relcome Guest24483
01:36:54 <HackEgo> Guest24483: 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.)
01:37:00 <boily> `relcome Guest3780
01:37:01 <HackEgo> Guest3780: 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.)
01:37:42 <oerjan> boily: you know in perl () actually match in s expressions
01:38:33 <boily> no, I didn't know. I expected whatever char appeared after an s to be the one and only delimiter.
01:38:44 <boily> is that a perl idiosyncasy, or is it widespread?
01:38:54 <oerjan> that's true except for brackety things
01:39:05 <oerjan> i dunno if it has spread
01:39:12 <int-e> oh right ... s(...)(...)
01:39:18 <boily> oh well. I guess perl's well spread enough by itself.
01:39:20 <ais523> I think Perl and sed both even allow alphabetic characters as delimeters
01:39:24 <int-e> I thought it's a perl thing
01:39:28 <ais523> but this is normally considered a bad idea
01:39:51 <boily> parser combinators ftw!
01:39:51 <int-e> sed want s(foo(bar(
01:39:56 <ais523> `` perl -e '$_="test"; satamag; print'
01:40:14 <HackEgo> Substitution pattern not terminated at -e line 1.
01:40:45 <int-e> ` echo "foobar" | perl -pe 's(o)(oo)g'
01:40:46 <HackEgo> /home/hackbot/hackbot.hg/multibot_cmds/lib/limits: line 5: exec: : not found
01:40:47 <boily> `` perl -e '$_="test"; s\t\m\g; print'
01:40:48 <int-e> `` echo "foobar" | perl -pe 's(o)(oo)g'
01:42:15 <HackEgo> Unrecognized character \x81; marked by <-- HERE after sかtかm<-- HERE near column 21 at -e line 1.
01:42:23 <HackEgo> /home/hackbot/hackbot.hg/multibot_cmds/lib/limits: line 5: exec: : not found
01:42:24 <HackEgo> noooodl is the correct spelling
01:42:39 <boily> @ask nooodl where are you?
01:43:13 <int-e> fungot: please explain the nooodl incident
01:43:13 <fungot> int-e: with my version, the systems aren't r6rs requires unicode, why do you need for binary distribution is a coin flipped ( because i wrote it.
01:43:19 <HackEgo> Can't open perl script "$_="test";sかtかmか;print;": No such file or directory
01:44:08 <int-e> oerjan: fwiw, "() actually match in s expressions" really confused me at first; I mean, what does that have to do with Perl?
01:44:42 <boily> `` perl -e '$_="か"; s/K/z/; print;'
01:44:56 <boily> meh. it unicodly works.
01:45:40 <oerjan> `` perl -e '$_="test"; s atamag; print'
01:46:22 <HackEgo> bash: -c: line 0: unexpected EOF while looking for matching `'' \ bash: -c: line 1: syntax error: unexpected end of file
01:46:28 <HackEgo> Unrecognized character \x81; marked by <-- HERE after かtかm<-- HERE near column 22 at -e line 1.
01:47:38 <int-e> Perl is old, it operates on bytes. And then there is some utf8 support in string operations.
01:48:07 <ais523> int-e: Perl operates on codepoints; however, it doesn't necessarily assume that they're Unicode codepoints
01:48:21 <ais523> a string in Perl is basically a string of 31-bit integers, stored in a compressed representation
01:48:28 <oerjan> int-e: i was pondering for half a minute how to say that better and then gave up
01:48:43 <ais523> actually Perl is one of the few languages which really supports Unicode well
01:48:57 <ais523> however, it doesn't necessarily know how to interpret its input
01:49:04 <ais523> and normally interprets it as bytes for backwards compatibility
01:49:13 <ais523> perl -e 'print "\x{123}"'
01:49:18 <ais523> `perl -e 'print "\x{123}"'
01:49:23 <ais523> `` perl -e 'print "\x{123}"'
01:49:25 <HackEgo> Wide character in print at -e line 1. \ ģ
01:49:43 <ais523> Perl's quite happy to have a codepoint 0x123 in a string
01:49:54 <Sgeo> Send laptop in to get fixed, or buy new laptop?
01:49:57 <ais523> but it doesn't know how to output it because by default, stdout is bytes
01:49:58 <Sgeo> Screen is dead
01:50:15 <ais523> `` perl -e 'binmode STDOUT, ":encoding(UTF-8)"; print "\x{123}"'
01:50:21 <int-e> Sgeo: any warranty?
01:50:29 <ais523> if you specify an encoding explicitly, everything is fine
01:50:30 <Sgeo> int-e: I almost certainly voided it
01:51:01 <Sgeo> Unless taking the latop completely apart does not void the warranty
01:51:14 <OrenWatson> Sgeo: eiter fix it yourself, use it as youtube for TV, andor buy new
01:51:27 <int-e> Sgeo: you probably voided it.
01:51:47 <Sgeo> Would the manufacturer still repair voided waranty if I pay money?
01:53:24 <OrenWatson> but I would just use it as desktop with external screen for now, and buy new laptop later
01:54:03 <Sgeo> There's no room near my couch for a monitor
01:54:11 <Sgeo> So I'm standing in a different area
01:54:14 <Sgeo> It's inconvenient
01:54:22 <Sgeo> Plus the resolution of this monitor is crap
01:55:39 -!- hjulle has quit (Ping timeout: 256 seconds).
02:05:10 -!- boily has quit (Quit: STROPPED CHICKEN).
02:25:58 -!- dianne has quit (Quit: byeannes).
02:29:09 -!- lleu has quit (Read error: Connection reset by peer).
02:50:21 -!- shachaf has joined.
02:53:06 <shachaf> i would prefer whatevertheirnameis to leave me alone twhal
02:58:56 -!- variable has joined.
03:00:33 <Sgeo> I could buy a better desk, and if that works out, consider building a desktop
03:10:20 -!- Sprocklem has joined.
03:13:48 <oerjan> i guess building a better lap is out of the question.
03:21:59 <OrenWatson> oerjan: http://www.bing.com/images/search?q=lap+pillow not so.
03:23:34 <zzo38> Is there a better way to test .XI files than with OpenMPT?
03:25:22 -!- OrenWatson has changed nick to orin.
03:31:08 -!- callforjudgement has joined.
03:32:29 -!- adu has joined.
03:32:58 -!- ais523 has quit (Ping timeout: 256 seconds).
03:33:11 -!- callforjudgement has changed nick to ais523.
03:38:38 -!- nys has quit (Quit: sleep).
03:41:15 -!- ^v^v has joined.
03:43:08 -!- ^v has quit (Ping timeout: 265 seconds).
03:52:01 -!- vodkode_ has joined.
04:15:56 -!- supay_away has changed nick to supay.
04:21:41 -!- adu has quit (Quit: adu).
04:36:26 -!- oerjan has quit (Quit: ZZZZETA).
04:42:07 -!- vodkode_ has quit (Ping timeout: 246 seconds).
04:44:01 -!- ^v^v has quit (Read error: Connection reset by peer).
04:48:07 -!- vodkode_ has joined.
05:27:30 -!- Sprocklem has quit (Quit: Leaving).
05:37:12 -!- callforjudgement has joined.
05:41:38 -!- ais523 has quit (Ping timeout: 272 seconds).
05:41:44 -!- callforjudgement has changed nick to ais523.
05:47:54 -!- Patashu has quit (Remote host closed the connection).
05:48:38 -!- Patashu has joined.
05:56:53 -!- callforjudgement has joined.
05:56:57 -!- ais523 has quit (Remote host closed the connection).
05:58:04 -!- vodkode_ has quit (Ping timeout: 246 seconds).
06:26:08 <Jafet> Should have been a redirect to iana.org
06:38:31 -!- vodkode_ has joined.
06:42:22 -!- callforjudgement has changed nick to ais523.
06:48:18 -!- variable has quit (Ping timeout: 264 seconds).
07:09:27 <orin> Hmm. the computation of h(14,13) is taking unusually long
07:11:56 <orin> I think there is a bug, but i'm not sure where
07:15:02 <orin> no. wait all the answers are wrong.
07:19:05 <orin> screw this at least my memory mgmt code workd
07:22:55 <orin> http://www.paste.org/77910
07:29:53 <orin> C programs are littered with code deleting and copying various trees and linked lists. this code handles a general case of that
07:37:16 -!- zadock has joined.
07:47:43 -!- shikhin has joined.
08:00:01 -!- roasted42 has joined.
08:01:35 -!- ais523 has quit (Ping timeout: 256 seconds).
08:04:04 -!- roasted42 has quit (Changing host).
08:04:04 -!- roasted42 has joined.
08:04:04 -!- roasted42 has changed nick to TheM4ch1n3.
08:05:10 -!- ais523 has joined.
08:31:44 -!- hjulle has joined.
08:32:24 -!- Patashu has quit (Disconnected by services).
08:32:25 -!- Patashu_ has joined.
08:39:55 -!- TheM4ch1n3 has quit (Quit: bbl).
08:45:02 -!- Patashu has joined.
08:46:20 -!- Patashu_ has quit (Ping timeout: 256 seconds).
08:56:57 -!- vodkode_ has quit (Quit: Leaving).
09:54:54 -!- ais523 has quit (Ping timeout: 264 seconds).
11:31:00 -!- Patashu has quit (Read error: Connection reset by peer).
11:31:12 -!- Patashu has joined.
12:21:46 -!- tromp has quit (Read error: Connection reset by peer).
12:27:52 -!- shikhin_ has joined.
12:28:29 -!- shikhin has quit (Ping timeout: 256 seconds).
12:28:43 -!- shikhin_ has changed nick to shikhin.
12:36:12 -!- Tritonio has joined.
12:42:30 -!- Patashu has quit (Ping timeout: 264 seconds).
12:43:27 <int-e> oho, less than a day...
12:44:11 <Taneb> Oh yeah, this conversation
12:45:05 <int-e> Of course they cheated and started from an existing train...
12:47:00 -!- Tritonio has quit (Remote host closed the connection).
13:12:17 -!- tromp has joined.
13:21:31 -!- boily has joined.
13:22:16 -!- FreeFull has quit.
13:51:22 -!- rodgort has quit (*.net *.split).
13:51:24 -!- newsham has quit (*.net *.split).
13:51:25 -!- tromp has quit (*.net *.split).
13:51:28 -!- f|`-`|f has quit (*.net *.split).
13:51:29 -!- Vorpal has quit (*.net *.split).
13:51:29 -!- PinealGlandOptic has quit (*.net *.split).
13:51:31 -!- MoALTz_ has quit (*.net *.split).
13:51:31 -!- heroux has quit (*.net *.split).
13:51:32 -!- ineiros has quit (*.net *.split).
13:51:33 -!- qlkzy has quit (*.net *.split).
13:51:33 -!- paul2520 has quit (*.net *.split).
13:51:33 -!- mtve has quit (*.net *.split).
13:51:36 -!- myndzi has quit (*.net *.split).
13:51:36 -!- hassa-aravit has quit (*.net *.split).
13:51:36 -!- kline has quit (*.net *.split).
13:51:40 -!- TodPunk has quit (*.net *.split).
13:51:40 -!- barrucadu has quit (*.net *.split).
13:51:41 -!- incomprehensibly has quit (*.net *.split).
13:51:44 -!- Taneb has quit (*.net *.split).
13:51:45 -!- villasukka has quit (*.net *.split).
13:51:45 -!- HackEgo has quit (*.net *.split).
13:51:48 -!- erdic has quit (*.net *.split).
13:51:48 -!- J_Arcane has quit (*.net *.split).
13:51:50 -!- tromp_ has quit (*.net *.split).
13:51:51 -!- FireFly has quit (*.net *.split).
13:51:52 -!- coppro has quit (*.net *.split).
13:51:52 -!- q3k has quit (*.net *.split).
13:51:52 -!- yiyus has quit (*.net *.split).
13:51:53 -!- hjulle has quit (*.net *.split).
13:51:53 -!- zadock has quit (*.net *.split).
13:51:54 -!- lambdabot has quit (*.net *.split).
13:51:54 -!- nisstyre has quit (*.net *.split).
13:51:54 -!- olsner has quit (*.net *.split).
13:51:54 -!- trn has quit (*.net *.split).
13:51:56 -!- iamevn_ has quit (*.net *.split).
13:51:57 -!- gde33 has quit (*.net *.split).
13:51:58 -!- g2watson has quit (*.net *.split).
13:51:59 -!- int-e has quit (*.net *.split).
13:51:59 -!- mroman has quit (*.net *.split).
13:52:00 -!- shachaf has quit (*.net *.split).
13:52:00 -!- vifino has quit (*.net *.split).
13:52:00 -!- pdxleif has quit (*.net *.split).
13:52:01 -!- relrod has quit (*.net *.split).
13:52:01 -!- fizzie has quit (*.net *.split).
13:52:02 -!- fungot has quit (*.net *.split).
13:52:02 -!- zemhill_ has quit (*.net *.split).
13:52:05 -!- TieSleep has quit (*.net *.split).
13:52:06 -!- j-bot has quit (*.net *.split).
13:52:07 -!- Sgeo has quit (*.net *.split).
13:52:11 -!- orin has quit (*.net *.split).
13:52:11 -!- ocharles_ has quit (*.net *.split).
13:52:12 -!- mhi^ has quit (*.net *.split).
13:52:12 -!- pikhq has quit (*.net *.split).
13:52:12 -!- idris-bot has quit (*.net *.split).
13:52:12 -!- clog has quit (*.net *.split).
13:52:13 -!- Melvar has quit (*.net *.split).
13:52:15 -!- supay has quit (*.net *.split).
13:52:15 -!- aloril has quit (*.net *.split).
13:52:16 -!- Guest3780 has quit (*.net *.split).
13:52:16 -!- vodkode has quit (*.net *.split).
13:52:17 -!- Guest24483 has quit (*.net *.split).
13:52:18 -!- mitchs has quit (*.net *.split).
13:52:19 -!- izabera has quit (*.net *.split).
13:52:19 -!- quintopia has quit (*.net *.split).
13:52:20 -!- jix has quit (*.net *.split).
13:52:21 -!- staffehn_ has quit (*.net *.split).
13:52:22 -!- digitalcold has quit (*.net *.split).
13:52:23 -!- ProofTechnique has quit (*.net *.split).
13:52:25 -!- EgoBot has quit (*.net *.split).
13:52:25 -!- b_jonas has quit (*.net *.split).
13:52:26 -!- tswett has quit (*.net *.split).
13:52:26 -!- shikhin has quit (*.net *.split).
13:52:27 -!- CADD has quit (*.net *.split).
13:52:27 -!- zzo38 has quit (*.net *.split).
13:52:36 -!- Naprecks has quit (*.net *.split).
13:52:36 -!- lifthrasiir has quit (*.net *.split).
13:52:36 -!- myname has quit (*.net *.split).
13:52:36 -!- SirCmpwn has quit (*.net *.split).
13:52:37 -!- Deewiant has quit (*.net *.split).
13:52:39 -!- copumpkin has quit (*.net *.split).
13:52:39 -!- augur has quit (*.net *.split).
13:52:39 -!- fractal has quit (*.net *.split).
13:52:39 -!- Lymia has quit (*.net *.split).
13:52:39 -!- yorick has quit (*.net *.split).
13:52:39 -!- v4s has quit (*.net *.split).
13:52:40 -!- perrier_ has quit (*.net *.split).
13:52:40 -!- merdach has quit (*.net *.split).
13:52:42 -!- monotone has quit (*.net *.split).
13:52:42 -!- nortti has quit (*.net *.split).
13:52:42 -!- diginet has quit (*.net *.split).
13:52:43 -!- conehead has quit (*.net *.split).
13:52:43 -!- Jafet has quit (*.net *.split).
13:52:44 -!- boily has quit (*.net *.split).
13:52:44 -!- Zuu has quit (*.net *.split).
13:52:44 -!- mbrcknl has quit (*.net *.split).
13:52:44 -!- skarn has quit (*.net *.split).
13:52:45 -!- edwardk has quit (*.net *.split).
13:57:06 -!- newsham has joined.
13:57:06 -!- rodgort has joined.
13:57:06 -!- yiyus has joined.
13:57:06 -!- q3k has joined.
13:57:06 -!- coppro has joined.
13:57:06 -!- FireFly has joined.
13:57:06 -!- tromp_ has joined.
13:57:06 -!- J_Arcane has joined.
13:57:06 -!- erdic has joined.
13:57:06 -!- HackEgo has joined.
13:57:06 -!- villasukka has joined.
13:57:06 -!- Taneb has joined.
13:57:06 -!- incomprehensibly has joined.
13:57:06 -!- barrucadu has joined.
13:57:06 -!- TodPunk has joined.
13:57:06 -!- Guest11531 has joined.
13:57:06 -!- Deewiant has joined.
13:57:06 -!- Jafet has joined.
13:57:06 -!- conehead has joined.
13:57:06 -!- tswett has joined.
13:57:06 -!- skarn has joined.
13:57:06 -!- mbrcknl has joined.
13:57:06 -!- SirCmpwn has joined.
13:57:06 -!- diginet has joined.
13:57:06 -!- nortti has joined.
13:57:06 -!- Zuu has joined.
13:57:06 -!- digitalcold has joined.
13:57:06 -!- myname has joined.
13:57:06 -!- aloril has joined.
13:57:06 -!- supay has joined.
13:57:06 -!- lifthrasiir has joined.
13:57:06 -!- monotone has joined.
13:57:06 -!- edwardk has joined.
13:57:06 -!- staffehn_ has joined.
13:57:06 -!- jix has joined.
13:57:06 -!- Naprecks has joined.
13:57:06 -!- quintopia has joined.
13:57:06 -!- zemhill_ has joined.
13:57:06 -!- mroman has joined.
13:57:06 -!- vifino has joined.
13:57:06 -!- relrod has joined.
13:57:06 -!- fizzie has joined.
13:57:06 -!- j-bot has joined.
13:57:06 -!- izabera has joined.
13:57:06 -!- trn has joined.
13:57:06 -!- pdxleif has joined.
13:57:06 -!- b_jonas has joined.
13:57:06 -!- EgoBot has joined.
13:57:06 -!- olsner has joined.
13:57:06 -!- int-e has joined.
13:57:06 -!- nisstyre has joined.
13:57:06 -!- Melvar has joined.
13:57:06 -!- mitchs has joined.
13:57:06 -!- gde33 has joined.
13:57:06 -!- fungot has joined.
13:57:06 -!- clog has joined.
13:57:06 -!- g2watson has joined.
13:57:06 -!- idris-bot has joined.
13:57:06 -!- merdach has joined.
13:57:06 -!- pikhq has joined.
13:57:06 -!- perrier_ has joined.
13:57:06 -!- mhi^ has joined.
13:57:06 -!- iamevn_ has joined.
13:57:06 -!- Guest24483 has joined.
13:57:06 -!- zzo38 has joined.
13:57:06 -!- ocharles_ has joined.
13:57:06 -!- lambdabot has joined.
13:57:06 -!- orin has joined.
13:57:06 -!- CADD has joined.
13:57:06 -!- v4s has joined.
13:57:06 -!- yorick has joined.
13:57:06 -!- TieSleep has joined.
13:57:06 -!- vodkode has joined.
13:57:06 -!- ProofTechnique has joined.
13:57:06 -!- Lymia has joined.
13:57:06 -!- fractal has joined.
13:57:06 -!- augur has joined.
13:57:06 -!- copumpkin has joined.
13:57:06 -!- Sgeo has joined.
13:57:06 -!- Guest3780 has joined.
13:57:06 -!- shachaf has joined.
13:57:06 -!- zadock has joined.
13:57:06 -!- hjulle has joined.
13:57:06 -!- shikhin has joined.
13:57:06 -!- boily has joined.
13:57:41 -!- tromp has joined.
13:57:41 -!- f|`-`|f has joined.
13:57:41 -!- Vorpal has joined.
13:57:41 -!- PinealGlandOptic has joined.
13:57:41 -!- MoALTz_ has joined.
13:57:41 -!- heroux has joined.
13:57:41 -!- ineiros has joined.
13:57:41 -!- qlkzy has joined.
13:57:41 -!- paul2520 has joined.
13:57:41 -!- mtve has joined.
13:57:41 -!- myndzi has joined.
13:57:41 -!- hassa-aravit has joined.
13:57:41 -!- kline has joined.
13:58:20 -!- TieSleep has changed nick to TieSoul.
13:58:27 -!- rodgort has quit (*.net *.split).
13:58:27 -!- newsham has quit (*.net *.split).
13:59:11 -!- rodgort has joined.
13:59:11 -!- newsham has joined.
13:59:15 -!- rodgort has quit (Max SendQ exceeded).
14:00:04 -!- rodgort has joined.
14:00:36 -!- f|`-`|f has quit (Ping timeout: 255 seconds).
14:02:28 -!- `^_^v has joined.
14:02:29 -!- oerjan has joined.
14:04:21 -!- Guest11531 has quit (Changing host).
14:04:21 -!- Guest11531 has joined.
14:04:42 -!- Guest11531 has changed nick to GeekDude.
14:07:32 <boily> Guest3780: hi! how are you enjoying these fine netsplits?
14:15:29 -!- magician has joined.
14:15:39 * oerjan wonders if there is any language with words that start with bm
14:15:52 -!- magician has changed nick to Guest6889.
14:18:59 -!- Guest3780 has quit (Ping timeout: 256 seconds).
14:18:59 -!- Guest6889 has changed nick to Guest3780.
14:22:10 <oerjan> trusty georgian seems to provide ქიმიური ბმა, meaning chemical bond, the latter word transcribing as "bma"
14:22:23 <boily> oh. georgian indeed.
14:22:47 <oerjan> your go-to language for advanced consonant clustering
14:23:20 <HackEgo> m: Wlcm t th ntrntnl hb fr strc prgrmmng lngg dsgn nd dplymnt! Fr mr nfrmtn, chck t r wk: <http://slngs.rg/>. (Fr th thr knd f strc, try #strc n rc.dl.nt.)
14:24:01 <HackEgo> /home/hackbot/hackbot.hg/multibot_cmds/lib/limits: line 5: exec: eoe: not found
14:24:17 * oerjan tries russian but google doesn't give anything non-acronymy looking starting with бм
14:25:19 <int-e> Well my small russian dictionary doesn't have anything like that.
14:25:44 <int-e> (Nor do I recall ever having to pronounce such a word.)
14:26:55 <oerjan> it has днепропетровск but not the labial version
14:29:07 <int-e> Right. The Днепр is a river. Dnieper in english, isn't that nice...
14:30:53 -!- zadock has quit (Quit: Leaving).
14:32:52 <int-e> Oh, this is nice. `дно' means `bottom', its plural is `донья'
14:33:51 <int-e> And from `ден' they derive `днём', `during daytime'.
14:35:35 -!- dianne has joined.
14:36:29 <oerjan> but wiktionary couldn't find that
14:37:34 <oerjan> oh should have done a proper search
14:39:00 -!- Sprocklem has joined.
14:40:00 -!- GeekDude has quit (Ping timeout: 265 seconds).
14:43:07 <int-e> Sigh. пей is both "drink!" and "sing!"
14:43:23 <int-e> sing to the bottom... well, no.
14:44:23 -!- GeekDude has joined.
14:45:58 <oerjan> now if it was also "women!" russians would have it easy
14:46:59 <oerjan> <int-e> oho, less than a day... <-- ah.
14:49:50 * int-e wonders whether oerjan deliberately misunderstood "drink!" to be a noun rather than an imperative verb form.
14:51:27 <oerjan> no, i deliberately avoided trying to turn "women" into a verb hth
14:57:49 <int-e> Taneb: спи! (bah, stupid irregular verbs)
14:58:12 <Taneb> Aww, it's 4 in the afternoon and a sunny day
14:58:35 <int-e> Ok, go outside then.
14:59:08 <int-e> (Just passing on advice I tend to get from my parents. You're welcome, no need to thank me.)
15:00:20 * int-e glimpses outside ... snow?! snow???!!!! WHY??!?!!!!?
15:00:54 <Taneb> Where the hell are you? It's May!
15:01:07 <int-e> Innsbruck. It's snowing, but thawing immediately.
15:01:27 <lambdabot> LOWI 061450Z 26010KT 190V290 4000 R08/P1500D R26/P1500N SHSN SCT003 SCT010 BKN015 02/M01 Q1024 WS R26 TEMPO SHSN
15:01:44 <oerjan> int-e: same here yesterday
15:02:07 <oerjan> i guess i'm further north, or something.
15:03:00 <Taneb> oerjan, you are certainly further north
15:03:10 <int-e> SHSN = snow showers. WS = wind shear
15:03:35 <Taneb> oerjan, aren't you in like one of the furthest north large cities in Europe?
15:05:53 <int-e> "R26", what do you mean, runway 26? There is only one runway there... (approachable from two directions, maybe that makes 2).
15:10:37 <oerjan> Taneb: i think it depends a lot on your cutoff for "large city".
15:11:43 <oerjan> murmansk is larger, and far more north
15:12:52 <Taneb> Anyway I am going to get some sleep
15:12:59 * oerjan hates that google maps removed the quick zoomout bar
15:15:32 <myname> fähigkeit: 2 mana - fügt 30 schade zu
15:15:44 <int-e> But yeah, the runway ends are marked 26 and 08. Funny.
15:16:01 <int-e> myname: zu schade.
15:17:21 <oerjan> also, i don't like that if you zoom out enough to see all of scandinavia and murmansk, all the city names disappear.
15:17:29 <int-e> (is there a direction encoded in the numbers... looks that way: "Runways are named by a number between 01 and 36, which is generally the magnetic azimuth of the runway's heading in decadegrees"
15:18:32 <oerjan> hm i guess they wouldn't want two runways in the same direction.
15:19:40 <int-e> They do. They get suffixes: L, M, R.
15:19:56 <int-e> (I'm reading https://en.wikipedia.org/wiki/Runway )
15:20:27 <int-e> (It gets really funny when there are more than 3 parallely runways)
15:20:51 <int-e> s/reall/really/; s/lely/lel/
15:23:44 -!- variable has joined.
15:32:00 -!- FreeFull has joined.
15:42:49 -!- GeekDude has quit (Quit: {{{}}{{{}}{{}}}{{}}} (www.adiirc.com)).
15:59:18 <lambdabot> EGLL 061550Z 02008KT 340V050 9999 FEW032 15/08 Q1032 TEMPO BKN014
15:59:32 <fizzie> I was told this place is cold and rainy.
16:01:49 -!- Sprocklem_ has joined.
16:04:43 -!- Sprocklem has quit (Ping timeout: 245 seconds).
16:10:04 <izabera> let's create a really awful language called every_other_language
16:10:20 <izabera> so that you can say "every_other_language sucks"
16:10:43 <izabera> then someone shall create a language called "this_language" which is just a little bit better
16:10:55 <izabera> so that he can say "this_language is better than every_other_language"
16:19:02 -!- Sprocklem_ has changed nick to Sprocklem.
16:23:07 -!- roasted42 has joined.
16:24:05 -!- roasted42 has quit (Changing host).
16:24:05 -!- roasted42 has joined.
16:24:05 -!- roasted42 has changed nick to TheM4ch1n3.
16:25:33 <lambdabot> CYQB 061600Z 23004KT 30SM BKN220 M03/M16 A3031 RMK CI7 SLP270
16:28:56 -!- ^v has joined.
16:36:14 -!- augur has quit (Remote host closed the connection).
16:36:41 -!- augur has joined.
16:40:28 -!- boily has quit (Quit: CLAD CHICKEN).
17:01:34 -!- oerjan has quit (Quit: leaving).
17:32:21 -!- variable has quit (Ping timeout: 240 seconds).
17:32:55 -!- int-e has left ("CONTRAPOSITIVE CHICKEN").
17:32:55 -!- int-e has joined.
17:36:06 -!- hassa-aravit has quit (K-Lined).
17:50:49 -!- GeekDude has joined.
17:52:48 -!- SopaXorzTaker has joined.
18:02:08 -!- TheM4ch1n3 has quit (Quit: brb).
18:02:51 -!- roasted42 has joined.
18:05:14 -!- roasted42 has quit (Changing host).
18:05:14 -!- roasted42 has joined.
18:05:14 -!- roasted42 has changed nick to TheM4ch1n3.
18:08:48 -!- Apostle has joined.
18:09:11 -!- Apostle has changed nick to Inji.
18:15:33 <Inji> So I've never been here before.
18:15:37 <Inji> This is a huge esoteric chat
18:17:01 <HackEgo> Inji: 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.)
18:17:26 <Inji> So it's not actual esotericism.
18:17:30 <Inji> It's a joke language.
18:17:52 <Taneb> myname, I wasn't in the mood
18:18:09 <Taneb> Inji, yeah, we're a programming channel
18:18:14 <Taneb> Stick around, if you want!
18:18:16 <Inji> I should've known.
18:20:29 -!- Inji has quit (Quit: Leaving).
18:21:21 -!- shikhin has quit (Quit: Changing server).
18:23:35 -!- shikhin has joined.
18:24:09 -!- ^v^v has joined.
18:27:50 -!- augur has quit (Remote host closed the connection).
18:28:29 -!- shikhin has quit (Ping timeout: 246 seconds).
18:30:17 -!- augur_ has joined.
18:34:21 -!- TheM4ch1n3 has quit (Quit: bye for now).
18:41:07 -!- SopaXorzTaker has quit (Remote host closed the connection).
18:57:35 -!- variable has joined.
19:24:14 -!- shikhin has joined.
19:39:10 -!- nszceta has joined.
19:40:55 <orin> Isit just me, or is the fopen() function designed terribly?
19:41:53 <orin> I don't like the way it takes a string for its parameters
19:42:03 <int-e> I think it evolved rather than being designed
19:42:20 <int-e> it's more or less fit for its purpose but not elegant ;)
19:44:36 -!- Guest24483 has changed nick to elliott.
19:44:40 -!- elliott has quit (Changing host).
19:44:40 -!- elliott has joined.
19:45:01 <HackEgo> lliott: elcome o he nternational ub or soteric rogramming anguage esign nd eployment! or ore nformation, heck ut ur iki: <ttp://solangs.rg/>. (or he ther ind f soterica, ry #soteric n rc.al.et.)
19:45:16 <int-e> (elliott may have been here before, I forgot. ;-) )
19:46:10 <orin> Is .rg or .et a real TLD?
19:46:50 <orin> .et I guess would be for aliens?
19:47:54 <coppro> elliott: to answer your question, yes I'm actually on the NHDT
19:47:58 <Taneb> .et is Ethiopia, .rg does not exist
19:48:16 <int-e> Oh there's an i there.
19:48:20 <elliott> coppro: why the 5 days wait :p
19:48:37 <coppro> elliott: I only remembered now
19:48:42 <coppro> (that you asked about it)
19:48:57 <elliott> coppro: you told me at the time it was part of an april fool's or something
19:49:09 <orin> .rg ... um, maybe a site for the greatness of Roentgenium?
19:49:32 <coppro> elliott: The April Fool's was that the announcement was real
19:49:41 <coppro> Taneb: NetHack DevTeam
19:49:52 <int-e> .rg is for role playing gamers who take RPGs seriously (they stopped playing)
19:50:32 <orin> ha! yes, indeed. ffvii.rg, masseffect.rg, etc
19:50:39 <elliott> coppro: did ais not get on the devteam because naming it NH4 pissed them off
19:50:46 <elliott> that's what I would like to believe
19:51:09 <coppro> elliott: I don't actually know the reason. But most likely because he expressed that he wasn't sure he'd want to join
19:51:41 <elliott> coppro: so does this mean I can literally rant to a nethack devteam member about how nethack fucking sucks now
19:54:12 <coppro> (and I'm serious, feedback is good. it won't all get fixed next release, but it's still good)
19:55:59 <Taneb> The only feedback I can give on Nethack is that I am not very good at it
20:07:31 -!- f|`-`|f has joined.
20:13:36 -!- nszceta_ has joined.
20:15:06 -!- nszceta has quit (Ping timeout: 250 seconds).
20:16:02 -!- nszceta_ has quit (Max SendQ exceeded).
20:16:56 -!- nszceta has joined.
20:18:13 -!- magician has joined.
20:18:37 -!- magician has changed nick to Guest72111.
20:22:12 -!- Guest3780 has quit (Ping timeout: 265 seconds).
20:22:12 -!- Guest72111 has changed nick to Guest3780.
20:23:52 -!- ^v has quit (Quit: Leaving).
20:27:28 -!- augur_ has quit (Remote host closed the connection).
20:30:27 -!- augur has joined.
20:39:04 -!- orin has quit (Quit: leaving).
20:47:57 -!- variable has quit (Read error: Connection reset by peer).
20:48:49 -!- AndoDaan has joined.
20:48:53 <zzo38> When Pokemon Pinball is loaded into Visual Boy Advance, Pikachu is being too quietly!
20:59:28 -!- Patashu has joined.
21:00:54 -!- nszceta has quit (Ping timeout: 256 seconds).
21:01:52 -!- oren has joined.
21:08:21 -!- variable has joined.
21:22:03 -!- Patashu has quit (Ping timeout: 250 seconds).
21:23:44 -!- Sprocklem has quit (Ping timeout: 244 seconds).
21:44:05 <oren> what are you playing
21:45:27 -!- adu has joined.
21:46:23 -!- augur has quit (Remote host closed the connection).
21:46:28 -!- variable has quit (Ping timeout: 244 seconds).
21:47:04 -!- adu has quit (Client Quit).
21:52:41 -!- shikhout has joined.
21:52:44 -!- shikhout has changed nick to Guest90138.
21:52:52 -!- Guest90138 has quit (Remote host closed the connection).
22:02:46 <elliott> coppro: my feedback could only be resolved by redesigning the entire game, sorry :p
22:07:54 <zzo38> Then make up a new game.
22:08:13 -!- oerjan has joined.
22:08:55 <oerjan> Gregor: great idling there
22:11:41 <oerjan> <Taneb> Inji, yeah, we're a programming channel <-- if we'd managed to send all those people to a place where they'd stay, it would have been a huge channel by now.
22:12:02 <oerjan> sadly, something something critical mass.
22:12:21 <Taneb> I wonder if there's a channel somewhere out there that keeps getting people who want to be here
22:12:55 <olsner> but do they want to be there? really?
22:13:05 <HackEgo> Unbound implicit parameter (?haskell::Wisdom) \ arising from a use of implicit parameter `?haskell'
22:14:00 <lambdabot> Perhaps you meant ‘handle’ (imported from Control.Exception)
22:14:42 <oerjan> haskle would be the obvious norwegian borrowing from the english verb haskell
22:15:34 <olsner> ler deg haskle med ørjan?
22:18:17 <oerjan> the å isn't optional in norwegian, yet. although with the speed we're absorbing swedish constructions, ask again in a decade or two.
22:20:39 <oerjan> or maybe they're english constructions.
22:21:02 <olsner> not sure, I think the å (att) is probably not really optional in swedish
22:21:28 <oerjan> i found a google hit so may have misinterpreted.
22:23:23 <oerjan> do swedes say "jag har tänkt att [haskla]" or "jag har tänkt till att [haskla]"?
22:25:15 <oerjan> because the shift from the former to the latter in norwegian is one of the grating examples to this old fart
22:25:21 <olsner> the former, but it sounds quite formal still
22:26:02 <olsner> I'd probably say "jag tänkte haskla"
22:26:21 <oerjan> oh. again, the "å" is not optional.
22:26:58 <oerjan> very well. my obvious theory of the origin of this travesty has been proved wrong, then.
22:32:10 <oren> haskell is a verb?
22:32:30 <oerjan> otherwise, how could there be haskellers
22:33:00 <oren> As in "I haskelled a program"?
22:33:20 <oren> Or is it "I haskold a program"?
22:33:27 <Taneb> "We have haskelled a lot over the past few days"
22:33:31 <oren> (like tell, told)
22:33:38 <Taneb> I don't think Haskell takes an object
22:33:43 <Taneb> I mean, it's not Java
22:38:12 <coppro> elliott: just play crawl then
22:38:27 <elliott> coppro: the exact same applies to crawl actually
22:38:43 <coppro> elliott: play ADOM then :P
22:38:51 <elliott> admittedly I find it more fun, but
22:39:27 <Jafet> Go play a real video game, you nerd
22:40:18 <Taneb> elliott, play Pokemon Mystery Dungeon: Red Rescue Team
22:41:04 <oren> そう言えば、どこかgoogleは日本語の動詞「ググる」と読んだ。たとえば、「その映画をググりました」。
22:41:11 <Jafet> or Chocobo Dungeon
22:41:32 <coppro> elliott: when you say 'the exact same', do you mean the same issues? or only that it needs a redesign
22:41:42 <Jafet> They should just make a game where you delve through a dungeon as a goat and crash into things
22:41:49 <coppro> elliott: also, a significant part of NetHack is likely to get redesigned over the next while, assuming the DT remains active.
22:41:53 <elliott> nethack and crawl have tons of issues but probably mostly not the same ones
22:41:54 <coppro> So I'm still interested in hearing :)
22:42:07 <elliott> changing nethack at all is scary
22:42:18 <elliott> how can you disturb the delicate balance of everything just slightly not at all working
22:42:20 <zzo38> Jafet: If you know how to and what deatils, you make up!
22:42:39 <Jafet> hackcode can't really be scarier than it already is
22:42:59 <coppro> elliott: some of the bigger issues like Gehennom are definitely on the radar screen
22:43:25 <zzo38> Make some for Famicom.
22:43:31 <Sgeo> I think I'm going to end up twisting my neck
22:43:46 <Sgeo> My monitor is to my right side, my laptop is straight in front of me
22:43:54 <elliott> I suspect my design philosophy coheres with exactly zero of the nethack devteam members, anyway. for what it's worth, sil, brogue and necrodancer are the roguelikes that come to mind as having the most admirable design, though the former two at least are certainly flawed (and the latter relies on the gimmick to be an effective game)
22:45:32 <zzo38> There are also "small roguelikes" such as KING and The Rougelike!
22:45:51 <coppro> elliott: I'm still interested in hearing
22:45:54 -!- `^_^v has quit (Ping timeout: 250 seconds).
22:45:57 <coppro> I can't speak for other team members
22:46:03 * Sgeo hasn't played either Crawl or Nethack in a while
22:46:11 <Sgeo> The latter for the dumbest possible reason
22:46:15 <elliott> tbh it has been so long since I played NH that i probably can't give much concrete
22:46:47 <elliott> "how about getting rid of all the grinding and instadeaths and really spoilery things"
22:47:12 <coppro> Gehennom is the big grind
22:47:15 <Sgeo> I have a reasonable game going on NAO, and for the past N years have been scared of messing it up.
22:47:18 <coppro> that's the only real problem area for that I think
22:47:27 <coppro> what do you mean by spoilery things?
22:47:58 <elliott> I mean like 80% of the game.
22:48:23 <elliott> (that's the only grind in nethack? have you ever seen an altar??)
22:48:37 -!- shikhin has quit (Quit: leaving).
22:48:57 <Sgeo> Is Crawl grindy? iirc one of the philosophies is antigrind
22:49:28 <Jafet> In crawl you grind through adventurers
22:49:29 <elliott> it can be tedious in many ways but they're not generally "doing the exact same thing N times"
22:50:07 <elliott> coppro: okay, here's my one concrete suggestion: please, god, either automate or eliminate price-id
22:50:42 <coppro> the identification game in general needs attention
23:07:49 -!- augur has joined.
23:09:37 -!- idris-bot has quit (Quit: Terminated).
23:09:56 -!- Melvar has quit (Quit: rebooting).
23:11:59 -!- augur has quit (Ping timeout: 246 seconds).
23:13:14 -!- Melvar has joined.
23:19:03 -!- augur has joined.
23:29:10 -!- idris-bot has joined.
23:48:11 -!- vodkode_ has joined.
00:10:46 -!- vodkode_ has quit (Ping timeout: 250 seconds).
00:49:44 -!- adu has joined.
00:53:51 -!- bb010g has joined.
01:08:39 -!- magician has joined.
01:09:03 -!- magician has changed nick to Guest92232.
01:11:41 -!- Guest3780 has quit (Ping timeout: 250 seconds).
01:11:41 -!- Guest92232 has changed nick to Guest3780.
01:14:24 -!- augur has quit (Read error: Connection reset by peer).
01:14:24 -!- augur_ has joined.
01:14:46 -!- adu has quit (Quit: adu).
01:17:28 <zzo38> Is it possible to define a general ordering of triples in RDF graphs (using the same definition of ordering regardless of which graph) even though there are blank nodes? (Blank nodes are like anonymous nodes; they don't have any ordering, and may be used multiple times.) Assume that if a blank node is wired in a particular way to the rest of the graph, it is indistinguishable for purpose of checking if a graph is the same or not.
01:19:04 -!- ^v^v has quit (Read error: Connection reset by peer).
01:25:07 -!- sdfgsdfg has joined.
01:28:42 -!- augur has joined.
01:31:49 -!- augur_ has quit (Ping timeout: 245 seconds).
02:01:09 <oren> Could we not simply "pick the graph up" by a certain node?
02:04:18 -!- AndoDaan_ has joined.
02:05:00 <zzo38> You may be able to simplify the problem by considering only the blank nodes, since everything else can already be ordered.
02:05:31 <oerjan> first, construct an ordering for graphs with numbered nodes. then, for each unnumbered graph, take the minimum numbered one.
02:05:44 <oerjan> absolutely no promises that this is tractable.
02:06:38 <zzo38> Note that these are directed graphs.
02:06:53 <oerjan> makes no difference...
02:07:18 -!- AndoDaan has quit (Ping timeout: 265 seconds).
02:07:46 <oerjan> the fact i've never heard of RDF graphs before doesn't help
02:09:01 <zzo38> That's OK; its exact definition isn't relevant. However, it may be described in a simplified way as such: A set of triples; the first and third may be either a URI or blank node, the second must be a URI. (It is actually a bit more complicated than that, but for the purpose of this problem everything else is irrelevant)
02:09:48 <zzo38> There is no problem ordering the URIs since you can just use strcmp
02:11:00 <oerjan> what's the problem with just defining blank nodes to be smaller than all URIs, say?
02:11:01 <oren> Each blank node is connected to N predicates as a object
02:11:40 <oerjan> and then order the triples lexicographically
02:12:12 <oerjan> so basically, as haskell's (Maybe URI, Maybe URI, Maybe URI) type
02:12:27 <zzo38> No, that isn't right.
02:12:36 <oren> The second one is guaranteed to be a URI
02:13:00 <oerjan> oh. well (Maybe URI, URI, Maybe URI) then.
02:14:05 <oerjan> i'm sort of assuming that's too simple but you haven't defined the problem in such a way that i can see why it is disallowed.
02:14:14 <zzo38> Let's say you have a unlabeled directed graph; it can become a RDF graph by making each node as a blank node and then the second one (called a predicate) is always <about:blank> or whatever (note that <about:blank> is not a blank node!). So, Maybe URI doesn't do it.
02:16:09 <oerjan> zzo38: my problem is that i have no information about what an RDF graph is other than a set of triples.
02:16:35 <oren> It is a graph composed of two types of vertexes.
02:17:02 <oren> the A type is connected to three B type vertexes
02:17:46 <oren> (with three distinct labeled edges)
02:18:09 <oren> the B type vertexes are arbitrary URI's or just "blank"
02:19:04 <oren> In addition, the second edge from each A type vertex always connects to a B type vertex which is a URI
02:19:36 <zzo38> That is one way to describe it, although I can prefer this way: It is a directed graph where vertexes can be labeled or blank, and edges are always labeled. There may be more than one blank node, but none of them have labels; and some may be used more than once. That's why (Maybe URI) does not describe a vertex.
02:20:32 <oerjan> oh i see the problem is that blank nodes have identity but not order
02:21:22 <zzo38> Yes, that's the problem I was asking about!
02:23:14 <oerjan> but a URI can only be used in one node, right?
02:23:44 <zzo38> (Although there may be multiple connections to and from it)
02:25:45 <oren> Hmm... we can start by putting the blank nodes which have a direct link to a URI node first
02:26:10 <zzo38> Yes I thought that might do, although still don't quite know how to continue then
02:26:32 <oren> and then ordering them by greatest
02:26:57 <oren> URI they are connected to (then by predicate, then by second greatest, etc)
02:27:56 <oerjan> well ok it is obviously possible to do in an intractable way, by first ordering triples in all graphs where blank nodes have been numbered, ordering the graphs themselves, then taking the triple ordering from the minimum graph
02:28:45 <oerjan> which arises from a numbering of your blank nodes
02:29:43 <oren> So if _AAA is connected to www.foo.com and _BBB is connected to vvv.foo.com then _BBB comes first
02:31:05 <oren> After all blank nodes which are connected to a URI have been ordered, we can use said ordering to order the blank nodes connected to them, and so on
02:32:00 <oerjan> however two blank nodes may be connected to the same URIs...
02:32:18 <oren> Then order by the predicate by which they are connected
02:32:33 <oren> And after that, take the second highest uri
02:32:48 <oren> and so on like a "high-card" poker hand
02:32:53 <zzo38> The second element in the triple is called a predicate.
02:33:02 <zzo38> (The first is called a subject, and the third is called an object.)
02:33:44 -!- CADD_ has joined.
02:34:17 <oren> Unfortunately my idea fails in the case where all nodes are blank
02:34:31 <oerjan> hm unless there is some uniqueness property i haven't noticed/been told, this is probably impossible.
02:34:47 <zzo38> oren: Yes, that's another case you haven't considered
02:35:26 <oerjan> in fact, let's take two triples, with (B1, "url1", B1) and (B2, "url1", B2)
02:35:44 <zzo38> oerjan: In that specific case, it doesn't matter the order.
02:35:44 <oerjan> B1 and B2 are blank. there is absolutely no distinction between the riples.
02:36:06 <zzo38> Because exchanging B1 with B2 doesn't change it at all.
02:36:08 <oren> when does the order batter
02:37:38 <zzo38> (In other words, the graph "looks the same" from B1 as it does from B2.) But, if you have: (B1, "url1", B2) (B3, "url1", B4) (B3, "url1", B5) then B1 and B2 and B3 are distinct, although you can exchange B4 with B5 without changing it.
02:38:00 <oerjan> so the ordering is only unique up to isomorphisms of the graph
02:40:53 <oerjan> but your special case of an unlabeled directed graph becomes "can you order the edges of an unlabeled directed graph"
02:41:29 <zzo38> Yes, and I expect that a solution to that problem can easily be extended to work with any RDF graphs then.
02:42:05 <oerjan> i vaguely suspect this is at least as hard as graph isomorphism
02:42:45 <zzo38> Yes, I would think so too.
02:44:09 <zzo38> Just in case you are curious, the additional part of the definition of a RDF graph that I have not yet mentioned is that the object (the third part of the triple) can also be a "literal", which means a pair consisting of a URI and a string. (This is irrelevant to the problem I mentioned though; I simply mention it in case you need to know exactly what a "RDF graph" is for other purposes.)
02:51:05 -!- CADD_ has quit (Quit: Lost terminal).
02:56:46 <oren> Suppose we start by getting each node two numbers, the number of outgoing and ingoing edges
02:57:26 <zzo38> I loaded "graph isomorphism" in Wikipedia now to try to learn a few other stuff, but still don't quite know
02:57:32 <zzo38> oren: OK, that's one start
02:58:16 <oren> Then within each set of nodes, each node's "poker hand" is the N,M of the nodes it is connected to
02:59:29 <oren> I'm thinking ofan iterative process where we keep reordering the nodes which are still undistinct...
03:00:23 <oren> until no change occurs.
03:04:28 <zzo38> I also thought of what I now learned is called "graph canonization" (actually I thought of the same name for it); so, if you can figure out the order of blank nodes then you can replace them with URIs <canon:1> <canon:2> <canon:3> and so on and then you can easily order the triples. (Of course this is a hypothetical "canon:" URI scheme)
03:05:12 <zzo38> I still don't know how to do this though, but making up such a canonical form would easily allow them to be ordered; but you can also do it the other way around, so that you can make up such a canonical form from the ordering is the other way.
03:06:36 <oerjan> zzo38: i think that's what i meant with the numbering?
03:07:49 <oren> So. take the example from above: B1,B2 B3,B4 B3,B5. The initial numbering would be B1-(1,0) B2,B4,B5-(0,1) B3-(2,0)
03:08:11 <oerjan> i think the numbering thing still works, it's just that if the graph has self-isomorphisms then the minimal graph can also be reached by all of those.
03:08:43 <oren> So the initial order is B2=B4=B5,B1,B3
03:10:08 <oren> Now B2 is connected to B1, and B4,B5 are connected to B3, and B1 outranks B3. Thus B2 outrank B4,B5.
03:10:31 <oren> The new ordering on step 2 is B2,B4=B5,B1,B3
03:11:15 <oren> B4 and B5 are still equal, so there is no change, and the algorithm teminates
03:11:47 <oren> (they are qual becuase theya re both only connected to B3)
03:11:48 <zzo38> Ah, OK I can see that now
03:17:07 <zzo38> However, you have to prove it!
03:25:27 -!- adu has joined.
03:25:36 -!- adu has quit (Client Quit).
03:28:01 -!- adu has joined.
03:39:52 -!- AndoDaan_ has quit (Quit: Going, going, gone.).
03:55:35 <zzo38> This RDF graph contains three blank nodes: http://zzo38computer.org/my_foaf.ttl The blank nodes are identified here as [], _:1, and _:2. (Each [] is a distinct blank node (although that isn't relevant here because there is only one); but each _: with the same name identifies the same blank node.) This graph contains many non-blank nodes too. Canonizing would require numbering each blank node. Note that using _:a _:b _:c in place of [] _:1 _:2
03:56:50 -!- GeekDude has quit (Quit: {{{}}{{{}}{{}}}{{}}} (www.adiirc.com)).
04:02:45 -!- Sprocklem has joined.
04:04:22 -!- Sprocklem has changed nick to tub.
04:04:37 -!- tub has changed nick to tumb.
04:04:57 -!- tumb has changed nick to Sprocklem.
04:04:57 <HackEgo> [wiki] [[Hexadecimal Stacking Pseudo-Assembly Language]] http://esolangs.org/w/index.php?diff=42317&oldid=42265 * SuperJedi224 * (+7684)
04:05:37 <HackEgo> [wiki] [[Hexadecimal Stacking Pseudo-Assembly Language]] http://esolangs.org/w/index.php?diff=42318&oldid=42317 * SuperJedi224 * (-2)
04:06:00 <HackEgo> [wiki] [[Hexadecimal Stacking Pseudo-Assembly Language]] http://esolangs.org/w/index.php?diff=42319&oldid=42318 * SuperJedi224 * (+1) /* An interpreter in Java */
04:14:04 <HackEgo> [wiki] [[Hexadecimal Stacking Pseudo-Assembly Language]] http://esolangs.org/w/index.php?diff=42320&oldid=42319 * SuperJedi224 * (-161) /* An interpreter in Java: */
04:17:40 -!- Sprocklem has changed nick to rub.
04:17:59 -!- rub has changed nick to Sprocklem.
04:23:31 -!- vodkode_ has joined.
04:40:41 <zzo38> This is a (badly drawn) diagram of part of such a graph: http://zzo38computer.org/img_17/my_foaf.png In order that you can see how it works. The circles indicate the blank nodes; they will then need to be ordered.
04:50:59 -!- oerjan has quit (Quit: Gah).
04:54:56 <zzo38> A diagram of the full graph (except for literals?) is at http://graves.cl/visualRDF/?url=http%3A%2F%2Fzzo38computer.org%2Fmy_foaf.ttl although it can be hard to read. This one also displays names for blank nodes (even though they don't really have names; names can be used in a representation for obvious uses though), and abbreviates some URIs that are commonly used in RDF.
05:03:56 -!- CADD has quit (Remote host closed the connection).
05:18:37 -!- adu has quit (Quit: adu).
05:32:12 -!- dianne has quit (Quit: byeannes).
05:47:56 -!- zadock has joined.
05:48:01 -!- Sprocklem has quit (Ping timeout: 244 seconds).
06:18:41 -!- zadock has quit (Quit: Leaving).
06:23:44 -!- shikhin has joined.
06:23:44 -!- shikhin has changed nick to Guest3839.
06:27:40 -!- Guest3839 has quit (Client Quit).
06:37:34 -!- shikkhin has joined.
06:40:02 -!- shikkhin has quit (Client Quit).
06:44:21 -!- shikhin has joined.
07:31:18 -!- CADD has joined.
07:35:05 <mroman> I can't really take this "studying 70 min a day is optimal" study that serious.
07:35:23 <mroman> apparentely students who learn the longest are the worst students.
07:35:49 <mroman> which makes sense because the sooner you get it the less long you actually have to study.
07:36:20 <mroman> so it shouldn't be surprising that students who learn longer on average probably do that because they are not very good at the subject.
07:48:49 -!- shikhin has quit (Quit: Lost terminal).
07:49:28 -!- shikhin has joined.
08:00:56 <mroman> "Judge Allows Divorce Papers To Be Served Via Facebook" uhm...
08:01:07 <mroman> fungot: Do you have a Facebook account?
08:01:07 <fungot> mroman: gcc 3 doesn't know about. and either you get threatened with lawsuits and the like
08:01:35 <mroman> Good. gcc3 is probably a facebook profile stalker anyway.
08:08:41 <oren> The actual optimal studying amount is "all the time", but you should study more than one thing.
08:11:47 <Taneb> I should study breakfast
08:15:37 <oren> Indeed. Good pancakes and french toast require intensive study to perfect
08:17:23 <oren> (I often end up burning my pancakes)
08:22:06 -!- Patashu has joined.
08:26:10 <oren> Holy crap, i didn't know there was kanji for sulfuric acid
08:28:51 -!- vodkode_ has quit (Ping timeout: 256 seconds).
08:29:56 <oren> hey fungot, have you tried cooking pancakes with sulfuric acid?
08:29:57 <fungot> oren: about the wiki? :) ( i'm attracted to these types of problems), if fnord enough times, could mutate some input into a more optimal way?
08:46:51 -!- zadock has joined.
08:52:41 -!- nszceta has joined.
08:58:52 -!- nszceta has quit (Quit: My Mac has gone to sleep. ZZZzzz…).
09:34:49 -!- sdfgsdfg has quit (Remote host closed the connection).
09:43:39 -!- hjulle has quit (Ping timeout: 256 seconds).
09:56:16 -!- nszceta has joined.
09:57:12 -!- nszceta has quit (Max SendQ exceeded).
09:57:43 <fungot> mroman: or has a contradiction... non-imperative?) from the keyboard
09:59:03 -!- nszceta has joined.
10:01:40 -!- ProofTechnique has quit (Ping timeout: 245 seconds).
10:04:38 <oren> fungot, funorudo tte nani?
10:04:38 <fungot> oren: why didn't i think of that. gentoo also starts with s! 2. blahbot, dead, dead, is just conditional reading
10:15:16 <HackEgo> [wiki] [[Hexadecimal Stacking Pseudo-Assembly Language]] http://esolangs.org/w/index.php?diff=42321&oldid=42320 * SuperJedi224 * (+142) /* An interpreter in Java: */
10:16:01 <HackEgo> [wiki] [[Hexadecimal Stacking Pseudo-Assembly Language]] http://esolangs.org/w/index.php?diff=42322&oldid=42321 * SuperJedi224 * (+9)
10:20:21 -!- lleu has joined.
10:32:33 <oren> What if a "language" existed in which "programming" was done by pavlovian conditioning on small animals?
10:33:38 <oren> E.g. to do an "and" you condition them to push a button only when two lights are on.
10:42:22 -!- ProofTechnique has joined.
10:44:16 <Jafet> Related: http://arxiv.org/abs/1204.1749
10:45:30 <oren> awesome. crab-based computing
10:46:51 <HackEgo> [wiki] [[Hexadecimal Stacking Pseudo-Assembly Language]] http://esolangs.org/w/index.php?diff=42323&oldid=42322 * SuperJedi224 * (+179) /* An interpreter in Java: */
10:55:56 -!- shikkhin has joined.
10:58:09 -!- shikkhin has quit (Client Quit).
11:03:00 -!- shikkhin has joined.
11:03:02 -!- shikkhin has quit (Remote host closed the connection).
11:07:34 -!- shikhin has quit (Quit: Changing server).
11:07:34 -!- oren has quit (Read error: Connection reset by peer).
11:07:49 -!- shikhout has joined.
11:07:50 -!- shikhout has changed nick to Guest50683.
11:08:11 -!- aloril_ has joined.
11:09:56 -!- aloril has quit (Ping timeout: 272 seconds).
11:31:07 -!- Patashu has quit (Read error: Connection reset by peer).
11:31:24 -!- Patashu has joined.
11:36:55 -!- ski has quit (Ping timeout: 251 seconds).
11:38:47 -!- ski has joined.
11:48:54 -!- hjulle has joined.
11:50:43 -!- vodkode_ has joined.
11:54:50 -!- orin has joined.
11:56:41 <Taneb> Help, someone (I know not who) made https://github.com/jimrustlesPhD/Taneb/blob/master/Taneb.erl
12:00:43 <Taneb> shachaf, I know not who that is
12:01:43 <shachaf> Taneb: perhaps you know who https://github.com/icydoge is?
12:01:54 <Taneb> Yes, I know that person
12:02:03 <Taneb> But they are almost certainly different people
12:02:16 <shachaf> https://erlangcentral.org/erlang-projects/details/15724 suggests some sort of connection
12:03:04 <Taneb> Only in that they both contributed to this git project
12:03:19 <Taneb> I know who everyone is but the author of that erlang
12:04:45 <Jafet> Is that Jim Rustles, PhD, or Jim Rustle's PhD?
12:04:54 <Taneb> Jafet, it is unclear
12:05:08 <Taneb> I don't think that "Jim Rustles" is the author's real name
12:06:10 -!- ais523 has joined.
12:27:41 -!- vodkode_ has quit (Ping timeout: 250 seconds).
12:34:37 <HackEgo> [wiki] [[Hexadecimal Stacking Pseudo-Assembly Language]] http://esolangs.org/w/index.php?diff=42324&oldid=42323 * SuperJedi224 * (+95) /* An interpreter in Java: */
12:38:00 <HackEgo> [wiki] [[Hexadecimal Stacking Pseudo-Assembly Language]] http://esolangs.org/w/index.php?diff=42325&oldid=42324 * SuperJedi224 * (+25) /* An interpreter in Java: */
12:47:20 <mroman> At least it's multi-functional.
12:49:15 -!- Patashu has quit (Ping timeout: 246 seconds).
12:49:41 -!- FreeFull has quit (Ping timeout: 252 seconds).
13:04:53 <mroman> so... I can't visit other courses at my university.
13:05:05 <mroman> Well, I can visit them... but I'm not allowed to attend the final exams.
13:05:24 <mroman> which absolutely sucks.
13:12:37 -!- shikhin has joined.
13:12:51 <Jafet> Well, exams don't work so well if you've seen them before.
13:13:15 <mroman> What are you talking about?
13:14:36 <Jafet> If you were to take the same course later, you would see the same exam again.
13:16:05 -!- Guest50683 has quit (Quit: ZNC - http://znc.in).
13:16:40 <mroman> They write new exams each semester
13:16:44 <mroman> but that's not really the point.
13:17:10 <mroman> I thought since I'm still working at this university I could just attend some courses and get a piece of paper that states that I visited and passed them
13:17:50 <mroman> but they don't allow that.
13:18:19 -!- FreeFull has joined.
13:18:27 <mroman> Shouldn't be too hard for the docent to correct one exam more
13:19:17 <mroman> and the office to print some piece of paper and stamp it
13:19:45 <mroman> they have the tools for that anyway
13:20:07 -!- f|`-`|f has quit (Ping timeout: 255 seconds).
13:20:22 <mroman> every student can keep track of his grades/credits in the universities online tool and can print out a report and get it stamped
13:25:07 -!- shikkhin has joined.
13:25:30 -!- shikhin has quit (Quit: Changing server).
13:26:11 -!- shikhin has joined.
13:31:55 -!- shikhin has quit (Quit: Changing server).
13:39:55 -!- nszceta has quit (Quit: Textual IRC Client: www.textualapp.com).
13:40:01 -!- nortti has changed nick to []{}\|-_`^.
13:40:07 -!- []{}\|-_`^ has changed nick to nortti.
13:51:51 -!- shikhin_ has joined.
13:54:23 -!- shikhin_ has changed nick to shikhin.
13:57:20 -!- shikhin has quit (Quit: Changing server).
13:58:33 -!- shikkhin has changed nick to shikhin.
13:58:49 -!- shikhin has quit (Changing host).
13:58:49 -!- shikhin has joined.
14:00:47 -!- `^_^v has joined.
14:01:21 -!- shikhin has quit (Quit: ZNC - http://znc.in).
14:04:26 -!- shikhin has joined.
14:04:27 -!- shikhin has changed nick to Guest75986.
14:05:08 -!- Guest75986 has changed nick to shikhout.
14:05:29 -!- shikhout has quit (Changing host).
14:05:29 -!- shikhout has joined.
14:07:51 -!- shikhout has changed nick to shikhin.
14:14:36 -!- Guest3780 has quit (Ping timeout: 276 seconds).
14:15:32 -!- shikhin has changed nick to sammwch.
14:15:54 -!- sammwch has changed nick to shikhin.
14:19:15 -!- shikhin has changed nick to sammwch.
14:19:17 -!- sammwch has quit (Disconnected by services).
14:19:26 -!- shikhin has joined.
14:19:49 -!- shikhin has changed nick to Guest53355.
14:20:18 -!- Guest53355 has changed nick to shikhout.
14:20:26 -!- shikhout has quit (Changing host).
14:20:26 -!- shikhout has joined.
14:20:36 -!- shikhout has changed nick to shikhin.
14:21:27 -!- nortti has changed nick to shikh.
14:21:34 -!- shikh has changed nick to nortti.
14:24:31 -!- oerjan has joined.
14:36:16 -!- shikhin has quit (Quit: Cya.).
14:36:27 -!- shikhin has joined.
14:36:29 -!- Sprocklem has joined.
14:36:52 -!- shikhin has changed nick to Guest38099.
14:37:05 <HackEgo> [wiki] [[User:SuperJedi224]] http://esolangs.org/w/index.php?diff=42326&oldid=42267 * SuperJedi224 * (+33)
14:37:54 <HackEgo> [wiki] [[Hexadecimal Stacking Pseudo-Assembly Language]] http://esolangs.org/w/index.php?diff=42327&oldid=42325 * SuperJedi224 * (+24)
14:38:02 -!- Guest38099 has quit (Client Quit).
14:45:24 -!- nszceta has joined.
14:46:28 -!- shikhin has joined.
14:46:54 -!- shikhin has changed nick to Guest35710.
14:47:24 -!- Guest35710 has changed nick to shikhout.
14:47:29 -!- shikhout has quit (Changing host).
14:47:29 -!- shikhout has joined.
14:50:21 <HackEgo> [wiki] [[Hello world program in esoteric languages]] http://esolangs.org/w/index.php?diff=42328&oldid=42002 * 108.171.128.160 * (+107)
14:52:44 -!- shikhout has quit (Quit: Cya.).
14:54:43 -!- shikhout has joined.
14:54:49 -!- shikhout has changed nick to Guest43016.
15:02:08 -!- f|`-`|f has joined.
15:10:00 -!- shikhin_ has joined.
15:11:49 -!- shikhin_ has changed nick to shikhin.
15:17:17 -!- Guest43016 has quit (Quit: Cya.).
15:17:54 -!- shikhin has quit (Quit: Changing server).
15:18:26 -!- shikhin has joined.
15:18:38 -!- shikhin has changed nick to Guest65879.
15:20:54 -!- Guest65879 has quit (Client Quit).
15:23:02 -!- shikherr has joined.
15:24:24 -!- shikherr has quit (Changing host).
15:24:25 -!- shikherr has joined.
15:24:55 -!- shikherr has quit (Client Quit).
15:25:38 -!- shikhin has joined.
15:25:39 -!- shikhin has changed nick to Guest71592.
15:26:03 -!- zadock has quit (Quit: Leaving).
15:27:29 -!- variable has joined.
15:29:23 -!- callforjudgement has joined.
15:29:40 -!- ais523 has quit (Disconnected by services).
15:29:42 -!- callforjudgement has changed nick to ais523.
15:43:46 -!- `^_^v has left ("Leaving").
15:43:50 -!- `^_^v has joined.
16:03:54 -!- variable has quit (Ping timeout: 244 seconds).
16:05:18 -!- SopaXorzTaker has joined.
16:16:07 -!- nszceta has quit (Ping timeout: 252 seconds).
16:19:47 -!- FreeFull has quit (Quit: BBL).
16:30:48 -!- Guest71592 has changed nick to shikhin.
16:31:08 -!- shikhin has quit (Changing host).
16:31:08 -!- shikhin has joined.
16:39:31 -!- PinealGlandOptic has quit (Quit: leaving).
16:42:04 -!- variable has joined.
16:44:38 -!- oerjan has quit (Quit: leaving).
16:44:48 -!- variable has changed nick to constant.
16:54:24 -!- shikhin has quit (Quit: Cya.).
16:54:43 -!- shikhin has joined.
16:54:58 -!- shikhin has changed nick to Guest11133.
16:56:47 -!- Guest11133 has changed nick to shikhout.
16:56:52 -!- shikhout has quit (Changing host).
16:56:52 -!- shikhout has joined.
16:57:48 -!- shikhin has joined.
16:58:09 -!- shikhout has quit (Disconnected by services).
16:58:17 -!- shikhout has joined.
16:58:18 -!- Sprocklem has quit (Read error: Connection reset by peer).
16:58:37 -!- shikhout has quit (Disconnected by services).
16:58:42 -!- shikhin has changed nick to shikhout.
16:58:49 -!- shikhin has joined.
16:59:13 -!- shikhin has changed nick to Guest39441.
17:00:54 -!- SopaXorzTaker has quit (Remote host closed the connection).
17:08:17 -!- Sprocklem has joined.
17:12:10 -!- shikhout has quit (Quit: leaving).
17:13:29 -!- Sprocklem has quit (Quit: snoonet).
17:13:47 -!- Sprocklem has joined.
17:16:09 -!- Guest39441 has quit (Quit: Cya.).
17:16:42 -!- shikhin has joined.
17:34:20 -!- FreeFull has joined.
18:06:43 -!- zzo38 has quit (Remote host closed the connection).
18:09:22 <orin> mroman: The university my father works for (YorkU) doesn't allow him to attend a course in the manner you describe, but does allow *me* to do so... Maybe you should impersonate your own son?
18:11:08 -!- AndoDaan has joined.
18:15:10 -!- zadock has joined.
18:15:47 -!- Guest3780 has joined.
18:21:15 -!- shikhin has changed nick to BrieFly.
18:21:45 -!- BrieFly has changed nick to shikhin.
18:22:11 -!- shikhin has changed nick to BrieFly.
18:23:24 -!- BrieFly has changed nick to shikhin.
18:30:17 -!- zzo38 has joined.
18:58:37 -!- Guest3780 has quit (Ping timeout: 272 seconds).
19:16:25 -!- ais523 has quit (Read error: Connection reset by peer).
19:16:35 -!- ais523 has joined.
19:16:44 -!- ais523 has quit (Changing host).
19:16:44 -!- ais523 has joined.
19:26:25 -!- ais523 has quit (Read error: Connection reset by peer).
19:27:27 -!- ais523 has joined.
19:28:04 -!- Sprocklem has quit (Ping timeout: 248 seconds).
19:42:41 -!- Guest3780 has joined.
19:45:11 -!- constant has quit (Ping timeout: 250 seconds).
19:48:39 -!- ais523 has quit (Ping timeout: 272 seconds).
19:58:06 -!- Sprocklem has joined.
20:13:53 -!- nycs has joined.
20:16:54 -!- `^_^v has quit (Ping timeout: 246 seconds).
20:32:52 -!- FreeFull has quit.
20:41:23 <HackEgo> [wiki] [[Hexadecimal Stacking Pseudo-Assembly Language]] http://esolangs.org/w/index.php?diff=42329&oldid=42327 * SuperJedi224 * (+4) /* An interpreter in Java: */
20:45:39 -!- Helina has joined.
20:46:10 -!- Helina has quit (Quit: Page closed).
20:58:41 -!- AndoDaan has quit (Ping timeout: 255 seconds).
21:00:52 -!- Patashu has joined.
21:21:08 -!- ProofTechnique has quit (Ping timeout: 244 seconds).
21:22:46 -!- Sprocklem has quit (Ping timeout: 264 seconds).
21:23:57 -!- Patashu has quit (Ping timeout: 265 seconds).
21:24:02 -!- AnotherTest has joined.
21:34:41 -!- izabera has quit (Ping timeout: 256 seconds).
21:37:36 -!- izabera has joined.
21:42:15 -!- izabera has quit (Ping timeout: 245 seconds).
21:44:36 -!- izabera has joined.
21:45:00 -!- nycs has quit (Quit: This computer has gone to sleep).
21:56:39 <HackEgo> [wiki] [[A programming language is a formal constructed language designed to communicate instructions to a machine, particularly a computer.]] http://esolangs.org/w/index.php?diff=42330&oldid=41915 * Rottytooth * (+38) added tag
21:57:22 -!- oerjan has joined.
21:57:43 -!- ProofTechnique has joined.
21:59:39 <HackEgo> [wiki] [[Hexadecimal Stacking Pseudo-Assembly Language]] http://esolangs.org/w/index.php?diff=42331&oldid=42329 * SuperJedi224 * (+157) /* An interpreter in Java: */
22:04:02 -!- AndoDaan has joined.
22:06:13 -!- FreeFull has joined.
22:10:00 -!- AnotherTest has quit (Remote host closed the connection).
22:22:38 -!- AndoDaan_ has joined.
22:23:38 -!- dianne has joined.
22:25:51 -!- AndoDaan has quit (Ping timeout: 245 seconds).
22:47:09 -!- boily has joined.
22:59:12 <oerjan> darn i thought i'd finally made a portmanteau so impenetrable you didn't recognize it
22:59:59 <boily> no portmanteau too deep, no conflagration too outrageous.
23:01:34 <lambdabot> CYUL 072200Z 15003KT 30SM FEW240 05/M15 A3040 RMK CI1 CI TR SLP295
23:01:48 <boily> IT'S OVER ZERO THOUSANDS!
23:01:58 <lambdabot> ENVA 072250Z 28032KT 9999 FEW015 BKN030 06/01 Q1017 RMK WIND 670FT 29034G52KT
23:02:16 <oerjan> eek canadians catching up
23:02:20 * boily is doing the dance of finally probably getting something higher than Norway soon!
23:02:45 * oerjan imagines that as very silly
23:02:59 <oerjan> involving handstand jumps
23:03:09 <boily> no handstands tonight. I ate soup.
23:03:24 <lambdabot> KSJC 072253Z 21011G19KT 10SM FEW028 SCT050 BKN090 15/03 A2994 RMK AO2 SLP139 T01500028 PNO
23:03:41 <HackEgo> A szoup a szilárd tápszereknek híg alakban való elkészítése a célból, hogy könnyebben emészthetők legyenek; a hígító anyag a viz, mely feloldja s magába veszi a tápanyag legértékesebb részeit.
23:04:19 <shachaf> Norman Y. Mineta San Jose International Airport hth
23:06:01 <boily> tdh. you're there twh?
23:07:37 <shachaf> apparently we'll be playing kubb on sunday
23:07:50 <boily> that also helps hth
23:08:00 <lambdabot> Title: Kubb - Wikipedia, the free encyclopedia
23:08:55 * boily stays away from a very safe distance
23:10:46 <boily> there's a suspicious pixel attached to my "y".
23:11:19 <HackEgo> [U+01B4 LATIN SMALL LETTER Y WITH HOOK]
23:12:14 <oerjan> i think in this case it should be mapołes
23:12:37 <shachaf> always looks like there's some dirt on my screen
23:18:48 <HackEgo> [wiki] [[Language list]] http://esolangs.org/w/index.php?diff=42332&oldid=42262 * 194.168.93.97 * (+10) /* M */
23:21:41 <HackEgo> [wiki] [[Meq]] N http://esolangs.org/w/index.php?oldid=42333 * 194.168.93.97 * (+1881) Created page with "Meq was created by Richard Sparrow in April 2015. Hello World <pre> .==++>:+>+>[:++++++++>]:=+>===++>.===+++++++>:=+>:=++++>:++++++++>:rp>p>>p>p>p>p>p>p>p>p>p! </pre> Inst..."
23:21:59 -!- CADD has quit (Remote host closed the connection).
23:22:32 <HackEgo> [wiki] [[Meq]] http://esolangs.org/w/index.php?diff=42334&oldid=42333 * 194.168.93.97 * (+64)
23:25:48 <boily> I smell the unmistakeable fumet of a brainfuck derivative...
23:26:30 <AndoDaan_> Why derive from BF is you are just going to unFuck it?
23:27:26 -!- AndoDaan_ has changed nick to AndoDaan.
23:29:39 <HackEgo> [wiki] [[Special:Log/newusers]] create * TheMeq * New user account
23:30:14 <HackEgo> [wiki] [[Meq]] http://esolangs.org/w/index.php?diff=42335&oldid=42334 * TheMeq * (+14)
23:30:23 <HackEgo> [wiki] [[Meq]] http://esolangs.org/w/index.php?diff=42336&oldid=42335 * TheMeq * (+4)
23:31:16 <HackEgo> [wiki] [[Meq]] http://esolangs.org/w/index.php?diff=42337&oldid=42336 * TheMeq * (+0)
23:31:51 <HackEgo> [wiki] [[User:TheMeq]] N http://esolangs.org/w/index.php?oldid=42338 * TheMeq * (+70) Created page with "Hi, I'm TheMeq I developed the [[Meq]] esoteric programming language!"
23:32:05 -!- magician has joined.
23:33:01 <HackEgo> /home/hackbot/hackbot.hg/multibot_cmds/lib/limits: line 5: exec: metar: not found
23:33:11 <lambdabot> CYYZ 072300Z 09007KT 15SM BKN090 BKN130 06/M08 A3031 RMK AC5AC2 SLP272
23:34:08 -!- Guest3780 has quit (Ping timeout: 252 seconds).
23:34:08 -!- magician has changed nick to Guest3780.
23:36:43 <orin> I think they gave toronto the letters left over...
23:42:06 -!- magician has joined.
23:44:24 -!- Guest3780 has quit (Ping timeout: 252 seconds).
23:44:24 -!- magician has changed nick to Guest3780.
23:45:01 <boily> orin: probably the name of some nearby beacon. that's why Dorval is YUL.
23:47:43 * oerjan read that as bacon and was a bit confused
23:49:42 * boily feeds fungot some proximal bacon
23:49:42 <fungot> boily: the example was just a test to see if freenode would get its security act together?
23:50:26 <oerjan> bacon, the next irc threat
23:52:41 <boily> orin: apparently, YTO is the area (probably similar to the GTA, need more details). then you have YTZ for Billy Bishop, YKZ for Buttonville and YYZ for Pearson.
23:54:25 -!- AndoDaan_ has joined.
23:54:27 <boily> aha! http://www.funtrivia.com/askft/Question130856.html, with AyatollaH's reply giving credible details.
23:56:21 -!- AndoDaan has quit (Ping timeout: 256 seconds).
23:56:48 <lambdabot> LLBG 072350Z VRB01KT CAVOK 15/06 Q1012 NOSIG
23:58:42 <boily> ORxx airports are in Okinawa.
23:59:06 <boily> uhm. ROxx, says I.
00:00:17 <lambdabot> ORBI 080000Z 00000KT CAVOK 19/06 Q1010 NOSIG
00:00:47 <lambdabot> ORER 072300Z 15004KT CAVOK 13/08 Q1013 NOSIG
00:21:26 <zzo38> I made up a new variant of Magic: the Gathering now, it is: http://zzo38computer.org/textfile/miscellaneous/magic_card/randcommand.var
00:31:38 <boily> long live conspiracies!
00:37:33 <zzo38> Have you dreamt of nonexisting episodes of television shows?
00:39:59 <boily> as far as my memory serves, no, I think not.
00:40:22 * boily flunked zzo38's Roman Catholic quiz. «maudit qu'y'est pas facile!»
00:42:20 <zzo38> boily: Well, some of the questions are difficult; which questions did you miss?
00:42:52 <boily> I got 19 out of 42. most were guessed...
00:43:23 <boily> I do know the guy's called St-François-d'Assise. other than that they were wildly random.
00:47:16 <zzo38> What kind of religions are you though?
00:48:47 <boily> atheist. I was born and raised Roman Catholic for about the first half of my life.
00:50:48 <zzo38> Ah, OK. (I was also born and raised Roman Catholic, and sometimes still go to church on Christmas Eve)
00:52:19 <zzo38> I do know Catholics, atheists, and a few others though. (I consider myself a panendeist.)
00:55:19 <zzo38> There is still much to read in the Bible though, even if you are not Christian. I think I even read in some book written by an atheist, in a list of books he recommended, the Bible was included in that list too.
00:55:44 <zzo38> Of course there is much to read in other books too!
00:56:07 <HackEgo> [wiki] [[Hexadecimal Stacking Pseudo-Assembly Language]] http://esolangs.org/w/index.php?diff=42339&oldid=42331 * SuperJedi224 * (-8038) /* An interpreter in Java: */
00:56:59 <boily> books are made to be read. it's their purpose in life.
00:57:28 <oerjan> that's what they want you to think
00:58:58 <zzo38> boily: Yes, clearly, that is what it is, otherwise you don't need to write on it.
01:04:59 <boily> oerjan: yes, and I agree. I hope you take good care of your books and that you pet them regularly.
01:20:19 <orin> panendeist - um, lemme see pan=all en=in dei=god ist=believer "someone who believes all is in god" ?
01:27:07 <orin> That emoticon looks seird when \ is a yen sign
01:30:26 <boily> ¥ is ¥, and \ is \.
01:31:47 <pikhq> boily: In Japanese locales \ renders as the yen sign.
01:31:47 <orin> Hmm... apparently the first one is a double-width yen sign
01:32:21 <pikhq> For legacy reasons.
01:32:51 <boily> pikhq: I know. it's surprising the first time you're Team Viewing some desktop in Japan and all paths are C:¥...¥...¥...
01:33:24 <boily> and then you discover that in Korea it's wons all the way, but then you half-expected it anyway.
01:33:36 <zzo38> pikhq: That's because it is the Japanese character encoding I think. And then some people wanted to do it even if you are using different encoding
01:34:20 <pikhq> zzo38: Ish. In legacy Japanese encodings there is no \ but the yen sign is encoded the same as \ in ASCII.
01:34:46 <zzo38> pikhq: Yes, that's what I meant the Japanese character encoding has a yen sign where standard ASCII has a backslash.
01:35:05 <pikhq> So semantically it was treated as a backslash...
01:35:22 <zzo38> Even the Famicom keyboard has a yen sign, but no backslash.
01:35:26 <pikhq> And when they switched to Unicode they still wanted the thing-that-acted-like-backslash to look like a yen sign. :)
01:35:55 <orin> I've seen anime where there are computer classes and it is like printf("%d￥n",i);
01:36:09 -!- vodkode_ has joined.
01:36:17 <pikhq> Yep. Though arguably that's incorrect C.
01:36:31 <orin> Such as in serial experiments Lain
01:39:04 <pikhq> Because their charset doesn't have \ it should be printf("%d??/n",i);
01:43:05 <zzo38> If the character encoding has a yen sign in the place where a backslash in ASCII, then you can use yen sign in that way; C is using ASCII encoding so a variant of ASCII still, you use whatever is in the correct position of the codes. Such as, some older ASCII codes use up arrow in place of ^ so in such codes you use up arrow where ^ is expected (as XOR or whatever).
01:43:34 <orin> http://postimg.org/image/xg91wqvfn/342429f8/
01:44:13 <zzo38> But when using UTF-8 Unicode the proper character should be a proper backslash. UTF-16 should not be used to write a C code though, but some other character encodings are OK (such as ISO-8859-1, or CP437, or whatever)
01:44:59 <orin> Hmm... I'm not sure what printf("%c<&\n",a); does anyway
01:45:08 <orin> Hmm... I'm not sure what printf("%c<^\n",a); does anyway
01:45:12 <orin> Hmm... I'm not sure what printf("%c<%\n",a); does anyway
01:45:56 <zzo38> Probably it isn't valid printf format string, whoever made that picture may have done the mistake
01:47:03 <orin> It's from serial experiments lain... apart from the mistake he seems to be teaching how to use comparison operators or something
01:48:59 <orin> http://postimg.org/image/gc5maf6el/
01:49:44 <orin> unfortunately the anime doesn't show the rest of the lesson because our heroine is about to go on a crazy acid trip
01:50:48 -!- boily has quit (Quit: GOTHIC CHICKEN).
01:54:56 <pikhq> zzo38: C does not use ASCII encoding.
01:56:02 <pikhq> zzo38: C uses some encoding with the property that 0 through 9 are sequential, and a small set of characters exist.
01:56:45 <pikhq> Alphanumerics + !"#%&'()*+,-./:;<=>?[\]^_{|}~
01:57:10 <orin> Does C specify the visual appearance of said characters?
01:57:26 <zzo38> And line break too I suppose? You missed line breaks.
01:57:41 <pikhq> orin: Not especially.
01:58:14 <pikhq> zzo38: Right, yes, it also requires the space character, horizontal tab, vertical tab, and form feed.
01:58:22 <orin> Then japanese computers simply have a \ that looks like ￥ instead of ＼
01:59:08 <pikhq> Additionally, at run time alert, backspace, carriage return, and newline must exist.
01:59:29 <pikhq> orin: That is the implementation used on modern systems, yes.
01:59:48 <pikhq> \ simply has a locale-specific rendering, and nobody is that confused.
01:59:56 -!- incomprehensibly has quit (Ping timeout: 265 seconds).
02:02:05 <zzo38> Yes, it is the C backslash character, and has the same code number as the ASCII backslash, I suppose, is how you can describe it, even if it is not a backslash.
02:02:49 -!- incomprehensibly has joined.
02:02:56 <orin> IIRC, {|} [\] had locale-specific renderings in nordic countries, so people would use xÄiÅ instead of x[i].
02:04:40 <pikhq> orin: How odd, the relevant legacy encoding is ISO 8859-1, no?
02:04:54 <oerjan> this was in the 7-bit age.
02:05:22 <pikhq> *Ugh*, right, ISO 646 got used too.
02:06:13 <oerjan> it's the reason why irc by default consider those characters different case variants of each others
02:07:00 <oerjan> it used the finnish variant
02:08:23 * oerjan checks if irssi will do that, nope
02:09:39 <oerjan> well the server refused my /nick f\`-`\f so at least it still does
02:10:43 -!- orin has changed nick to {|oren|].
02:11:09 <oerjan> [|oren|]: does this ping you
02:11:41 <{|oren|]> apparently they are allowed but no longer case-viariant
02:11:56 -!- {|oren|] has changed nick to \oren\.
02:12:22 <oerjan> \oren\: no, they are case-invariant in the server
02:12:52 -!- \oren\ has changed nick to orin.
02:13:21 <oerjan> if you try to do /nick or /whois with a variant of them, it will be blocked/displayed
02:13:53 <oerjan> (if the nick is in use in some variation)
02:14:52 <orin> The british variant of iso646 had # as £ apparently
02:31:54 -!- lmt has joined.
02:31:59 <lmt> big channel
02:32:25 <HackEgo> lmt: 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.)
02:32:34 <lmt> very big channel
02:32:45 <lmt> how did it get so big?
02:32:58 <orin> I got here via the wiki
02:33:46 <orin> also there are a ton of bots on this channel, so it inflates the nubmers a bit
02:33:53 <lmt> that explains it
02:34:20 <orin> for example fungot HackEgo lambdabot idrisbot...
02:34:20 <fungot> orin: fnord returns true if ( eq val 4) code" from a different angle ( make-rectangular 4 1) 2 3
02:36:24 -!- darwin has joined.
02:36:59 -!- darwin has left ("Leaving").
02:37:26 -!- lleu has quit (Quit: That's what she said).
02:38:36 <oerjan> the bots aren't more than about 10%...
02:39:53 <orin> in a general sense, or right now?
02:40:00 <lmt> nice pdf in the topic
02:40:03 <oerjan> hm we are indeed pretty big
02:40:32 <Taneb> I have no idea what is going on
02:40:54 <Taneb> All the asterisks in lmt
02:42:52 <Taneb> I'm also confused about why I am awake
02:43:42 <lmt> i wish i were cool enough to be in the list of people in the pdf :(
02:43:54 <oerjan> i don't know why my fingers insisted on spelling it with an a
02:44:37 <oerjan> lmt: it's mostly extracted from stuff in HackEgo. it may not go back far enough.
02:44:51 <zzo38> You can add stuff into HackEgo yourself though, instead of using PDF
02:45:41 -!- lmt has left.
02:46:09 <HackEgo> 1227) <oren> when i was a kid it used to snow on christmas eve. what is this "freezing rain", "sleet" crap? <vanila> yeah seriously, who is evn in charge anymore? <oren> apparently not santa claus <zzo38> Santa Claus is dead by now. \ 1228) <{\[oren]|}> ｚｚｏ３８：ｉｔ ｗｉｌｌ ｃａｕｓｅ ｐｒｏｂｌｅｍｓ ｂｙ
02:46:24 -!- gjord has joined.
02:46:35 -!- augur has quit (Remote host closed the connection).
02:46:49 <HackEgo> 1227) <oren> when i was a kid it used to snow on christmas eve. what is this "freezing rain", "sleet" crap? <vanila> yeah seriously, who is evn in charge anymore? <oren> apparently not santa claus <zzo38> Santa Claus is dead by now. \ 1228) <{\[oren]|}> ｚｚｏ３８：ｉｔ ｗｉｌｌ ｃａｕｓｅ ｐｒｏｂｌｅｍｓ ｂｙ
02:46:53 <HackEgo> 49) <Madelon> both of you, quit it with the f-bombs. <Madelon> kaelis: what's the matter? something censoring stuff you're interested in? \ 109) <CakeProphet> how does a "DNA computer" work. <CakeProphet> von neumann machines? <Phantom_Hoover> CakeProphet, that's boring in the context of DNA. <Phantom_Hoover> It's just stealing the universe's w
02:47:34 <HackEgo> 1227) <oren> when i was a kid it used to snow on christmas eve. what is this "freezing rain", "sleet" crap? <vanila> yeah seriously, who is evn in charge anymore? <oren> apparently not santa claus <zzo38> Santa Claus is dead by now. \ 1238) <oren> is instant coffee stronger than espresso? I think it must be... [...] <oren> Ohh.... so apparently
02:48:00 <Taneb> `quote taneb * cows
02:48:09 <orin> `quote instant
02:48:09 <Taneb> `quote punched myself in the face
02:48:09 <HackEgo> 512) <Patashu> dangit I need someone who knows the answers to my problems instantly and is always around for me! <Patashu> I need.....an adult ;_; \ 1117) <ais523> hmm… I guess the difference between me and most esolangers is that I don't instantly go and put it into a BF derivative and call it a day \ 1127) <Sgeo> I designed a norn to drop dead
02:48:10 <HackEgo> 401) <Taneb> Look, I often walk my dog through a field with cows in it. And I punched myself in the face once.
02:48:43 <orin> the watchtower
02:49:37 <orin> oh god my compulsive word association is coming back
02:50:14 <zzo38> In my opinion the best program for online quizzes is Internet Quiz Engine; the other ones require you to use a GUI and are slow. Isn't it?
02:50:25 -!- augur has joined.
02:50:35 <lifthrasiir> (read the topic's PDF for 3rd time) ...I think that was originally Starcraft mentioned in my entry.
02:50:54 <HackEgo> lifthrasiir is shunned by the rest of his country for being no good at League of Legends.
02:51:06 <HackEgo> oren is a Canadian esolanger who would like to obliterate time zones so that he can talk to his father who lives in the same house.
02:51:15 <oerjan> `url wisdom/lifthrasiir
02:51:16 <HackEgo> http://codu.org/projects/hackbot/fshg/index.cgi/file/tip/wisdom/lifthrasiir
02:51:51 <zzo38> I think you should remove that PDF to make room for other stuff; you can link information from HackEgo and so on. Of course the PDF and other information can also be found in the logs. Right now it is unnecessary but it might be useful in future to remove this link
02:52:14 <orin> `quote oren instant
02:52:27 <orin> `quote oren.*instant
02:52:27 <HackEgo> 1238) <oren> is instant coffee stronger than espresso? I think it must be... [...] <oren> Ohh.... so apparently the jar says one scoop of powder per mug, I assumed an equal amount of powder and boiling water
02:52:45 <oerjan> lifthrasiir: it's been that way since 2012 at least
02:53:31 <oerjan> that is, when HackEgo's repository history was wiped out last
02:54:36 <orin> Requiring to use a GUI is barbaric
02:55:30 <oerjan> did you start remembering the future instead
03:01:33 <HackEgo> 1124) <Taneb> kmc, I was trying to go to a sci-fi and fantasy society social, and I went to the wrong bar <Taneb> Wound up at my university's fetish society <Taneb> Didn't realise for an hour and a half
03:01:42 <Taneb> Someone apparently has now done the reverse of that
03:01:50 <Taneb> So the balance of the universe is restored
03:03:37 <Taneb> (they saw "Fantasy" in the society name and jumped to conclusions)
03:06:29 -!- AndoDaan_ has quit (Quit: Going, going, gone.).
03:06:44 <augur> Taneb: ahahaha thats great :)
03:38:35 -!- variable has joined.
04:00:15 <zzo38> Do you know how to hack Pokemon Pinball? There is a problem with the game, that the Mewtwo stage you can earn too many points. Also how to make Visual Boy Advance to allow opposite directions pushed together?
04:11:11 <HackEgo> 1127) <Sgeo> I designed a norn to drop dead instantly if he ever thought about eating elevators. He was stillborn.
04:11:18 <Sgeo> What does dying norns have to do with punching myself in the face?
04:40:23 <Taneb> Sgeo, you creating those norns and me punching myself in the face both got in the quote file
04:45:28 <coppro> Sgeo: why were you interested about me being on TDT?
04:52:03 -!- variable has quit (Ping timeout: 240 seconds).
04:53:09 <Sgeo> coppro: I was just surprised at it, and surprised at the continued existed of TDT
04:56:38 <orin> TDT? isn't that the thing from lessworng
04:57:13 <oerjan> timeless devteam, sounds about right
04:57:58 <orin> I thought he was on the Nethack dev team?
04:58:21 <HackEgo> coppro prefers his nickname, Pooppy.
04:58:48 <oerjan> `slashlearn tdt/That doesn't tdt.
04:59:50 <orin> shachaf: I have heard TDT referring to "timeless decision theory" which is some philosophy where people in the future can make threats to people in the past by simulating them, or some nonsense likt that
05:00:43 <shachaf> I wonder whether using // as a separator would be better for slashlearn
05:00:58 <shachaf> That way you could learn inside directories.
05:01:15 <oerjan> well, but then you'd need it to mkdirs too
05:01:24 <zzo38> I think it works to just one slash; I don't expect you need subdirectories (but, I don't know for sure).
05:01:49 <shachaf> whoa, did you play the discworld computer game?
05:01:53 <oerjan> i don't think we should encourage subdirectories too much, although wisdom has some.
05:07:45 <Sgeo> In this context I think The DevTeam was what was meant
05:12:25 <shachaf> oerjan: https://www.youtube.com/watch?v=tvNLw7IHWmw#t=19m49s hth
05:24:43 <zzo38> Have you ever watched a television show called "To Be Announced"?
05:37:18 -!- vodkode_ has quit (Remote host closed the connection).
05:38:51 -!- oerjan has quit (Quit: Not that I recall).
06:13:29 -!- zadock has quit (Quit: Leaving).
06:29:10 <zzo38> Is Socrates a good golfer?
06:34:40 <shachaf> good golfers are immortal so no hth
06:55:01 -!- zadock has joined.
08:01:14 -!- zadock has quit (Ping timeout: 252 seconds).
08:04:31 -!- zadock has joined.
08:09:26 -!- ais523 has joined.
08:21:13 <mroman> so all immortal people are good golfers?
08:26:40 -!- Patashu has joined.
08:37:27 <Jafet> Socrates is everyman; in other words every man is Socrates. Therefore every man is mortal.
08:38:16 -!- AndoDaan has joined.
08:43:28 -!- gjord has left.
08:52:22 -!- AndoDaan has quit (Read error: Connection reset by peer).
08:52:44 -!- AndoDaan has joined.
09:01:32 -!- merdach has quit (Ping timeout: 252 seconds).
09:01:49 -!- merdach has joined.
09:01:54 -!- fractal has quit (Ping timeout: 252 seconds).
09:03:58 <myname> are there two-dimensional languages besides rail that do have commands that need more than one character?
09:10:34 <ais523> myname: there's some sort of cross between INTERCAL and Befunge, I think
09:10:48 <ais523> but it wasn't very interesting IMO
09:11:07 <ais523> let me check my very first esolang
09:11:32 <ais523> if I can even find where it's got ot
09:12:36 <ais523> * The playfield is made out of blocks of commands and data. The blocks are^M
09:12:37 <ais523> * 2x2 blocks arranged in a hex-grid pattern, like this:^M
09:12:52 -!- fractal has joined.
09:13:07 -!- vodkode_ has joined.
09:13:09 <ais523> looks like I had enough foresight to document how the language actually worked
09:13:13 <ais523> which is something of an improvement on Burn
09:13:41 -!- TodPunk has quit (Read error: Connection reset by peer).
09:14:06 -!- dianne has quit (Quit: byeannes).
09:14:08 -!- TodPunk has joined.
09:14:24 <ais523> myname: http://nethack4.org/esolangs/el1.c
09:14:37 <ais523> may as well "release" it, now I remembered it exists
09:15:10 <ais523> the file's dated 2006, that seems plausible
09:16:22 <ais523> now I'm trying to figure out what platform this was developed on
09:16:39 <ais523> the Windows-style newlines and order of the platform defines give some clues
09:16:43 <ais523> I suspect it may have been DOS
09:16:59 <ais523> after a while, Windows (especially pre-Vista) becomes annoying enough that anything is better :-(
09:17:05 <ais523> and I didn't have a lot of options back then
09:21:56 <ais523> that's a good reason for it to be 4 by 4
09:22:15 <ais523> I think it's better than most people's first attempts
09:22:24 <ais523> but it does rather miss the point it was aiming to illustrate
09:23:54 <b_jonas> so where will you release it? esolangs.org?
09:24:53 <ais523> I just put the file online
09:25:24 <ais523> also, it's very hard to search for files that originally came from a case-insensitive system, when your existing copy of them is on a case-sensitive system
09:25:37 <ais523> because you have to guess the capitalization
09:26:17 <b_jonas> can't you just search for all capitalizations?
09:27:14 -!- vodkode_ has quit (Ping timeout: 250 seconds).
09:29:43 <ais523> that's what I did in the end
09:29:56 <ais523> luckily "el1" only has two cased characters in it
09:30:03 <ais523> or, well, I found the source on the second try
09:30:08 <ais523> my first try found only the executables
09:30:43 <ais523> I guess I could try to get them running in wineconsole, but figuring out how an esolang works based on an /implementation executable/ is pretty hard unless it gives good error messages
09:33:15 <b_jonas> ais523: but it has comments explaining how it works,
09:33:32 <ais523> yep, that should make things much easier
09:33:32 <b_jonas> and you can guess the rest from the source and testing
09:33:45 <ais523> I actually think it's a complete spec, just one written in an awkward style
09:33:47 <b_jonas> and I don't see why you need a wineconsole for it
09:33:52 <ais523> (again, which is believeable for my first esolang)
09:34:01 <ais523> it was a hypothetical about "what if all I had was the executable"
09:35:06 <b_jonas> well, it's by an old compiler which doesn't optimize too much so disassembling and debugging would help a bit more than these days, but yeah.
09:38:38 <ais523> 2006 isn't /that/ old, but the compiler itself may well be much older
09:38:55 <ais523> it'd either be a version of DJGPP which was current at the time (i.e. basically gcc-circa-2006 levels of optimization)
09:39:01 <ais523> or Borland C++ 4, which was ancient even at the time
10:02:42 -!- bb010g has quit (Ping timeout: 256 seconds).
10:05:09 * ais523 reads a US court case, and is amused to see it discussing which state's laws to use to determine which state's laws to use
10:05:37 <ais523> (the court case used New York state laws to determine that California state laws were those that applied to the rest of the case)
10:07:25 <int-e> `complain I don't know what to complain about.
10:07:28 <HackEgo> Complaint filed. Thank you.
10:12:27 <AndoDaan> `complain about frivolous use of the complain command.
10:12:28 <HackEgo> Complaint filed. Thank you.
10:12:52 -!- bb010g has joined.
10:19:11 <ais523> I'd like to see a human vs. compiler asm-writing contest
10:19:14 <ais523> for a range of processors
10:19:39 <ais523> I think on most embedded systems, the human would win easily, because IME the compilers suck there
10:27:13 -!- boily has joined.
10:35:42 <b_jonas> ais523: the problem is that computers only have a source code, have to stick to that literally even when the programmer wrote sucky source code, whereas humans know the purpose and hopefully even test input data to know what to optimize for
10:35:59 <b_jonas> (sometimes the computers have test input data too, and use profile-based optimization, but that's rare)
10:36:18 <ais523> I think you should allow PGO here
10:36:45 <ais523> although, the benefit from it isn't usually that large, it's mostly just used to know how likely a branch is to be taken
10:45:36 -!- AndoDaan has left ("Leave channel").
10:46:11 <b_jonas> The human usually knows a great deal of non-aliasing and frequent special case and similar information that the computer can't divine from the code.
10:46:38 <b_jonas> Also expected array sizes or loop counts.
10:55:01 <mroman> I'm against using life expectantcy as a "quality of life"-measurement.
10:56:29 <ais523> there's also the risk that one set or other of the code is compiled flat-out wrong
10:56:36 <ais523> most likely the human-generated version
10:57:32 <b_jonas> ais523: yes, people produce a lot of flawed benchmark without even testing that the snippets they ran really compute the solution at all
10:57:45 <b_jonas> that's why I never believe timing benchmarks unless I produce them myself
10:57:57 <ais523> this is why alioth claims it shouldn't be taken seriously
10:58:18 <ais523> because there's too much skill influence from the human coders
10:58:34 <ais523> like, it'd be a struggle doing some of that stuff in INTERCAL at all, let alone via the fastest possible algorithm
10:59:06 <b_jonas> I'd just stick to human versus human.
10:59:16 <ais523> http://benchmarksgame.alioth.debian.org/ for people who don't know about it
10:59:50 <b_jonas> (They can use computers, which are just tools, totally not secretly our masters.)
11:12:40 <b_jonas> fungot, do you believe benchmarks?
11:12:40 <fungot> b_jonas: it has been run and debugged now i am depressed... there's been good and bad.
11:13:54 <mroman> fungot: Debugging benchmarks sounds like fun.
11:13:54 <fungot> mroman: when developing full applications it is fnord illustrative of how heavy on style and light on substance java really is an amazing hack that abuses the fnord interleaving ( like in pascal :)
11:15:15 <mroman> that's abso-fnording-lutely amazing.
11:16:05 <mroman> fnord (adj): We don't for the fnord of it know what fnord means.
11:16:34 <mroman> Life is fnord after all.
11:17:04 -!- choochter has joined.
11:28:03 -!- boily has quit (Quit: INESSIVE CHICKEN).
11:32:10 -!- vodkode_ has joined.
11:43:12 <Jafet> ais523: I would expect custom compiler backends to enter such a contest if people took it seriously
11:43:33 <ais523> it'd be hard to get enough people to take such a contest seriously
11:43:56 <Jafet> Also humans would take hours to write assembly code by hand, imagine if you gave superopt ten hours
11:44:44 <ais523> did superopt just try every combination of optimization settings to see which worked best?
11:45:13 <b_jonas> basically, I'm not affraid to lose my work to this kind of stuff.
11:45:56 <Jafet> http://directory.fsf.org/wiki/Superopt
11:46:25 <Jafet> Well, in reality superopt wouldn't get very far in ten hours
11:47:31 <Jafet> You could probably make a compiler backend out of smt solvers or static analysers, some of them can guess loop invariants now
11:47:40 <ais523> wow, that page is really short on info and has a couple of external links that look like they go to the info
11:47:44 <ais523> but they just redirect back to itself
11:48:56 <Jafet> Given that it was “released on 3 June 1995” the fact that it still has a webpage is quite impressive
11:50:26 <ais523> OK, I'm downloading the source to get information about how it works
11:50:58 <Jafet> Most likely it only works for small pure functions
11:51:39 <Jafet> and optimises them for processors that you don't have any more
11:52:17 <ais523> Jafet: I keep all my old processors around just in case!
11:52:46 <ais523> wow this is smaller than I expected
11:53:08 <ais523> since when does a software project only have 13 files in it?
11:53:34 <b_jonas> ais523: try ls -a instead of ls :-)
11:53:52 <ais523> b_jonas: but .. isn't part of the project
11:54:24 <ais523> FireFly: a large part of it seems to be written in a DSL, though
11:54:27 <ais523> with the C file being the DSL interp
11:54:32 <b_jonas> ais523: um, ok, then ls -A
11:54:36 <ais523> that comes to another 5518 lines
11:56:24 <Jafet> I'm sure you kept your old i686 in working condition for this very moment
11:56:44 <ais523> processor probably works
11:56:49 <ais523> not sure about the rest of the machine though
11:56:52 <Jafet> Although it should be mentioned that present-day compilers still compile for i686, for some reasons
11:57:11 <ais523> actually I think one of the machines still has a 16-bit processor
11:57:23 <ais523> I booted it up like 5 or 6 years ago to see if it was still working
11:57:34 <ais523> the hard drive was unreadable but it could boot and run from floppy disk
11:59:02 <ais523> superopt seems quite specific in its use
11:59:13 <ais523> I guess you could try to get it to come up with a fast inverse square root or the like
11:59:36 <ais523> but unless the FPU has an instruction specifically for doing that (in which case the search will be fast), it'd be unlikely to find it in a reasonable length of time
11:59:40 <Jafet> I doubt it would find the right 32-bit constant in time
12:00:08 <ais523> there's actually a range of constants that work
12:00:19 <ais523> the one in the infamous code isn't right in the middle of it, either
12:00:30 <ais523> so it might just have been a trial and error thing
12:01:30 <ais523> superopt rainbow tables
12:01:40 <ais523> you're already running all possible program fragments already, right?
12:01:59 <ais523> so you may as well try some standard inputs on all of them, produce a corresponding hash code
12:02:15 <ais523> then when you want to implement a new function optimally, just look it up in the table and see if the impl is correct
12:02:51 <Jafet> Unfortunately for us humans, we love to make short passwords and long programs.
12:03:26 <olsner> maybe you could make that into a distributed "optimal functions for everything" search
12:04:19 <b_jonas> ais523: the problem with that is often you want to implement a partial function
12:04:28 <b_jonas> and you can't just table that
12:04:58 <b_jonas> not so easily as complete functions
12:05:14 <Jafet> You can use wildcards for the inputs outside the domain, but searching with wildcards is slower.
12:08:48 -!- vodkode_ has quit (Ping timeout: 250 seconds).
12:11:04 <mroman> There should be password schemes/hash functions with error correction codes.
12:20:36 -!- izabera has quit (Ping timeout: 245 seconds).
12:24:44 -!- izabera has joined.
12:39:15 -!- Patashu has quit (Ping timeout: 256 seconds).
12:56:42 -!- magician has joined.
12:59:12 -!- Guest3780 has quit (Ping timeout: 245 seconds).
13:00:41 -!- Guest3780 has joined.
13:00:53 -!- magician has quit (Ping timeout: 248 seconds).
13:16:12 -!- variable has joined.
13:20:00 -!- ProofTechnique has quit (Ping timeout: 272 seconds).
13:29:55 -!- magician has joined.
13:31:42 -!- Guest3780 has quit (Ping timeout: 245 seconds).
13:31:43 -!- magician has changed nick to Guest3780.
13:37:15 <elliott> 12:49:23 <Jafet> You could probably make a compiler backend out of smt solvers or static analysers, some of them can guess loop invariants now
13:37:22 <elliott> regehr is doing stuff like this
13:37:28 <elliott> superoptimisation with an SMT solver
13:38:38 <ais523> elliott: this reminds me of the TASvideos Polarium Automated Solver War
13:38:48 <ais523> which someone eventually won using a SAT solver
13:39:53 <elliott> http://blog.regehr.org/archives/1109 http://blog.regehr.org/archives/1146 http://blog.regehr.org/archives/1192 http://blog.regehr.org/archives/1219
13:43:21 <ais523> hmm, maybe an INTERCAL superoptimizer would be interesting
13:43:43 <elliott> (fun fact: superoptimisation was pioneered by alexia massalin, who also wrote the famous Synthesis OS thesis)
13:44:25 <ais523> that said, violin's using a satisfaction solver already (I forget the technical term for the class of satisfaction solver that gprolog has)
13:46:18 -!- ProofTechnique has joined.
13:46:27 -!- variable has changed nick to constant.
13:47:00 <ais523> elliott: https://groups.google.com/forum/#!topic/alt.lang.intercal/fcxkgc7Pomk
13:47:11 <ais523> (much as I hate linking Google Groups, but it isn't archived elsewhere)
13:47:41 <elliott> "Creating an extra thread to do the addition is somewhat inefficient"
13:47:54 <elliott> ais523: btw, you're going to end up secretly controling nethack development through coppro, right
13:48:19 <ais523> elliott: there's more involved here than is public
13:48:52 <ais523> let's just say, if I wanted to secretly control NetHack development, even without coppro I'd probably find a way
13:49:48 <ais523> heh, Google interprets the filename "violin.pl" as an URL
13:49:51 <ais523> I'm scared to visit it
13:54:36 -!- idris-bot has quit (Ping timeout: 264 seconds).
13:54:53 -!- Melvar has quit (Ping timeout: 276 seconds).
13:55:35 -!- Melvar has joined.
13:56:09 -!- idris-bot has joined.
14:01:02 <ais523> "This syntax was designed to look reassuringly familiar, yet be surprisingly unintuitive in practice (especially when writing it by hand)."
14:01:07 <ais523> I need to read my old esolang stuff more oftne
14:12:12 -!- `^_^v has joined.
14:43:07 <Taneb> Help I am binging Girl Genius again
14:43:17 <Taneb> And I think I have just spotted an Animal Crossing reference
14:43:48 <Taneb> http://www.girlgeniusonline.com/comic.php?date=20090121 Major Resetti - Mr Resetti is a mole in Animal Crossing
14:47:16 <mroman> Press the button with a square on it
14:47:20 <mroman> a filled square that is.
14:47:32 <mroman> or press the one with two vertical lines
14:47:54 <mroman> Just don't fnording press the button with a triangle on it.
14:54:24 -!- Sprocklem has joined.
15:06:39 -!- zzo38 has quit (Remote host closed the connection).
15:09:37 -!- zadock has quit (Quit: Leaving).
15:10:16 -!- dianne has joined.
15:32:17 -!- Sprocklem has quit (Ping timeout: 250 seconds).
15:59:58 <FireFly> mroman: the button with a square on it, that's "maximize" in the window bar, right?
16:00:33 <ais523> that's a filled square, though, not an unfilled square
16:16:01 -!- constant has quit (Quit: 1 found in /dev/zero).
16:21:05 -!- FreeFull has quit.
16:45:58 <quintopia> ais523: what were you quoting above?
16:46:20 <ais523> quintopia: violin documentation
16:46:31 <ais523> which is in the sharball in the post I linked above
16:46:43 <ais523> https://groups.google.com/forum/#!topic/alt.lang.intercal/fcxkgc7Pomk to save you the trouble of scrolling back
16:56:47 -!- Sprocklem has joined.
16:58:45 -!- TieSoul has quit (Ping timeout: 248 seconds).
17:00:49 <ais523> because the file that implements assignments in C-INTERCAL is called fiddle.c
17:02:39 -!- vodkode has quit (Remote host closed the connection).
17:03:57 <quintopia> presumably because it fiddles with things
17:04:55 -!- TieSoul has joined.
17:10:06 <ais523> <spambot> How are you going to get a bit slimmer? It's barely possible in your case.
17:10:14 <ais523> first time I've seen spambots actually throw insults around
17:11:31 <orin> Uh, isn't that a compliment?
17:11:52 <ais523> I'm not sure at this point
17:12:03 <orin> Or maybe a expression of concern for your anorexia?
17:12:37 <ais523> I interpreted it as "there's no /way/ someone like you is ever going to slim without the product we're selling", with a sidecurrent of "and you really need it"
17:12:59 <orin> Ah. From a spambot, that would make sense.
17:13:00 <int-e> . o O ( Pro tip: Eating spam is not a healthy diet. )
17:13:12 <orin> Spam is, however, delicious
17:13:56 <orin> especially spam sandwiches with hot saucece
17:16:07 <quintopia> there is a store he called spamacyt
17:16:24 <quintopia> i haven't been inside, but i think it's just an unfortunate portmanteau of "spa" and "pharmacy"
17:16:58 <quintopia> (there's no t on the end...that was a typo)
17:37:24 -!- Sprocklem has quit (Ping timeout: 240 seconds).
17:45:17 <elliott> ais523: is that reply to the violin thread spam
17:45:47 <ais523> elliott: sort-of, I think it's from someone who wants to contribute to alt.lang.intercal but doesn't know enough INTERCAL to make any sense of the content
17:45:56 <elliott> https://groups.google.com/forum/#!topic/alt.lang.intercal/aTAikUJ2yDc nice replying to 2002 posts in 2014
17:47:37 -!- zadock has joined.
17:48:14 -!- SopaXorzTaker has joined.
17:58:07 <elliott> ais523: The company that runs blogspot web site isn't widely known in Europe. For example I don't know if it is from Bermuda or from Finland; latter due to usage of double vowels in its name (Hei Hyvää päivää! Mitä kuuluu?). But I know that it knows your fetishes better than other companies and even better than you do. It's hidden under /settings/ads URL and then Interests, in case you don't know.
17:58:22 <elliott> i guess the joke is pretending google is a finnish company??
17:58:50 <ais523> the third sentence makes me think it's a joke
17:59:00 <ais523> the rest can be interpreted as "it's hard to discover which company it is that runs blogspot"
17:59:15 <elliott> well the double vowel thing only makes sense with "google"
17:59:25 <elliott> because blogspot and blogger do not have two adjacent vowels in them
17:59:32 <ais523> in that case it probably is a joke, but not a very good one
18:04:20 -!- variable has joined.
18:34:45 -!- SopaXorzTaker has quit (Ping timeout: 248 seconds).
18:40:44 <b_jonas> what the... the Hurr Durr archives frontpage at https://www.hurrdurr.org/ doesn't list 4.0-rc7
18:43:21 -!- variable has quit (Ping timeout: 265 seconds).
19:01:57 -!- FreeFull has joined.
19:04:48 -!- vodkode has joined.
19:13:42 -!- variable has joined.
19:21:55 -!- mitchs has quit (Quit: mitchs).
19:27:37 -!- mitchs has joined.
19:40:03 -!- variable has quit (Ping timeout: 245 seconds).
20:01:23 -!- TieSoul has changed nick to TieSleep.
20:05:56 -!- Sprocklem has joined.
20:12:04 -!- ais523 has quit (Read error: Connection reset by peer).
20:12:13 -!- ais523 has joined.
20:34:38 <orin> http://postimg.org/image/jg0irvjzb/
20:39:53 -!- AnotherTest has joined.
20:52:57 -!- AnotherTest has quit (Ping timeout: 250 seconds).
21:06:06 -!- Patashu has joined.
21:07:35 -!- ProofTechnique has quit (Ping timeout: 246 seconds).
21:24:04 -!- Sprocklem has quit (Ping timeout: 240 seconds).
21:33:31 -!- izabera has quit (Ping timeout: 245 seconds).
21:35:43 -!- izabera has joined.
21:35:47 -!- ProofTechnique has joined.
21:40:11 -!- izabera has quit (Ping timeout: 245 seconds).
21:41:44 -!- izabera has joined.
21:43:05 -!- ais523 has quit.
21:44:17 <HackEgo> [wiki] [[Special:Log/newusers]] create * FreedomSka * New user account
21:53:31 -!- izabera has quit (Ping timeout: 245 seconds).
21:58:45 -!- izabera has joined.
21:58:49 -!- boily has joined.
21:59:02 -!- oerjan has joined.
22:00:46 <HackEgo> [wiki] [[Language list]] http://esolangs.org/w/index.php?diff=42340&oldid=42332 * FreedomSka * (+18)
22:01:07 <HackEgo> [wiki] [[EncryptFuck]] N http://esolangs.org/w/index.php?oldid=42341 * FreedomSka * (+706) Created page with "'''EncryptFuck''' is a encrypted version of a similar brainfuck code created by [[User:FreedomSka|FreedomSka]] This is a comment <pre> : COMMENTS </pre> The syntax it's like ..."
22:03:06 <Sgeo> Programming is hard
22:03:21 <HackEgo> [wiki] [[EncryptFuck]] http://esolangs.org/w/index.php?diff=42342&oldid=42341 * FreedomSka * (+28)
22:03:35 <Sgeo> You can be all like "This bad default is breaking stuff and fixing it won't hurt user code" and some idiot user's code does break
22:05:01 -!- `^_^v has quit (Ping timeout: 244 seconds).
22:05:05 <oerjan> i think this applies to life in general.
22:05:21 <HackEgo> [wiki] [[EncryptFuck]] http://esolangs.org/w/index.php?diff=42343&oldid=42342 * FreedomSka * (+24)
22:06:22 <HackEgo> [wiki] [[User:FreedomSka]] N http://esolangs.org/w/index.php?oldid=42344 * FreedomSka * (+53) Created page with "[[https://esolangs.org/wiki/EncryptFuck|EncryptFuck]]"
22:07:00 <boily> Sgello. hellørjan.
22:07:01 <HackEgo> [wiki] [[User:FreedomSka]] http://esolangs.org/w/index.php?diff=42345&oldid=42344 * FreedomSka * (-38)
22:07:06 <boily> on average, we're all idiot user code.
22:21:48 -!- lleu has joined.
22:21:48 -!- lleu has quit (Changing host).
22:21:48 -!- lleu has joined.
22:28:48 <HackEgo> lleu: 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.)
22:29:30 <HackEgo> [wiki] [[Meq]] http://esolangs.org/w/index.php?diff=42346&oldid=42337 * 194.168.93.97 * (+90)
22:30:24 <HackEgo> [wiki] [[Special:Log/upload]] upload * TheMeq * uploaded "[[File:Meq-ide-screenshot.png]]": Screenshot of the Meq IDE
22:31:03 <HackEgo> [wiki] [[Meq]] http://esolangs.org/w/index.php?diff=42348&oldid=42346 * TheMeq * (-14)
22:57:43 <HackEgo> [wiki] [[EncryptFuck]] http://esolangs.org/w/index.php?diff=42349&oldid=42343 * 87.11.7.181 * (+50)
22:58:55 <HackEgo> [wiki] [[EncryptFuck]] http://esolangs.org/w/index.php?diff=42350&oldid=42349 * 87.11.7.181 * (+8)
23:09:53 -!- adu has joined.
23:27:20 <tswett> Factorio is a pretty fun hardware description language.
23:27:44 <tswett> Someone should make a page for it on Esolang.
23:27:52 <tswett> Focusing, obviously, on how to compute with it.
23:37:03 -!- ProofTechnique has quit (Quit: ZNC - http://znc.in).
23:38:09 -!- ProofTechnique has joined.
23:48:53 <HackEgo> [wiki] [[EncryptFuck]] http://esolangs.org/w/index.php?diff=42351&oldid=42350 * 87.11.7.181 * (+224)
00:04:31 <boily> I appear to have burned a fingertip on my teapot. ow.
00:10:53 -!- v4s has quit (Ping timeout: 252 seconds).
00:10:57 <oerjan> a bit late now, but did you cool it in running water
00:11:43 -!- lambdabot has quit (Ping timeout: 256 seconds).
00:12:01 <oerjan> (i think it's supposed to be slightly less than lukewarm, my memory is a bit vague.)
00:12:07 -!- erdic has quit (Ping timeout: 244 seconds).
00:12:21 <boily> int-e: int-ello. LAMBDABOOOOOOOOOOT!
00:12:23 <oerjan> too bad, that's supposed to help reduce damage.
00:13:05 <oerjan> hm it doesn't seem to have reonlogged
00:13:16 -!- v4s has joined.
00:13:26 <boily> if it blisters, I'll cut away some aloe vera and bandage it around my finger.
00:13:36 <boily> (now, where to find that plant by this time of the year...)
00:13:40 -!- erdic has joined.
00:13:46 <boily> right, no lambdie.
00:13:59 <oerjan> maybe it hasn't noticed it pinged out yet
00:14:06 * boily repeatedly prods int-e with his mapole
00:14:42 <boily> also, it's always fun to mapole people ^^
00:15:37 <oerjan> i suspect int-e may be sleeping at this time
00:17:07 <oerjan> it does take it's sweet time rejoining
00:17:38 <oerjan> i assume it's to avoid getting flooded out
00:17:46 -!- lambdabot has joined.
00:17:49 <oerjan> i wonder if there's a way to speed that up
00:18:42 <Sgeo> https://www.youtube.com/watch?v=t3otBjVZzT0
00:20:46 <lambdabot> CYUL 090000Z 05008KT 1 1/2SM -SN BKN006 OVC018 01/M01 A3036 RMK SF7SC1 SLP283
00:21:01 <boily> snow. it's fungotting snowing. an April 8.
00:21:01 <fungot> boily: sarahbot later tell foxfire, why doesn't anything ever work right? or was that 92, we all know
00:21:59 <boily> fungot: IIRC, I was in Ontario during winter 92. (or were we still on Québec City's South Shore?)
00:21:59 <fungot> boily: what i'm trying without success. i was thinking glass might have moved there.
00:23:03 <oerjan> were you in ontario in autumn 95
00:24:12 <oerjan> were you in waterloo ...
00:25:41 <boily> no, we were in QC. the Ontario period was spent in Hamilton.
00:25:50 <oerjan> another incredible coincidence narrowly averted.
00:25:50 <boily> isn't it coppro who's a Waterlooian?
00:26:03 <oerjan> sure, but i think he got there after that?
00:26:23 <boily> perhaps. the only #esöterist I met IRL was lexande.
00:27:24 <oerjan> i don't know that i've met any, but then i've not left norway since i came here.
00:27:47 <shachaf> I won 5 prizes, expiring at the end of the month: "A .ME for free" "A .EU for free" "A .WEBSITE for free" "A .XYZ for free", "A .INFO for €1"
00:27:48 <tromp> i was postdoc at UofW
00:28:43 <shachaf> What should I do with them?
00:29:13 <oerjan> tromp: did you happen to have an office next to dave wagner twh
00:29:38 <shachaf> coppro: do you happen to play prismata twh
00:29:52 <tromp> no, i was a few offices from my supervisor Ming Li
00:30:06 <oerjan> mingling with ming li, check
00:30:07 <coppro> oerjan: my office is about fifty meters from his
00:30:37 <oerjan> coppro: well i did point you towards him didn't i
00:30:43 <oerjan> on an earlier occasion
00:30:56 <coppro> oerjan: I don't think so
00:31:19 <oerjan> anyway, he's one of the few ex-agorans i've met
00:31:28 <HackEgo> tdh is the past tense of a successful hth. hth.
00:32:05 <coppro> shachaf: I don't play prismata. But I know egrant.
00:32:14 <oerjan> shachaf: clearly you should register SHA.ME hth
00:33:19 <shachaf> oerjan: it's already registered hth
00:35:10 <coppro> tromp: who are you now?
00:35:20 <shachaf> I expect that dictionary words are all taken anyway.
00:36:08 <tromp> i am still tromp now
00:37:31 <coppro> tromp: ok. I just figured you weren't a person when you were a postdoc at UW because you were a postdoc at UW.
00:37:56 <oerjan> shachaf: IJOINEDACONTESTANDALLIGOTWASTHISLOUSY.WEBSITE
00:38:02 <coppro> shachaf: you should register amphetami.ne
00:38:18 <coppro> it costs $100 to update your DNS records
00:38:27 <shachaf> i think enough amphetas have been mined already hth
00:39:12 <coppro> I should go back to ignoring every message ending with hth
00:40:20 <boily> hth let's see if copprop can hear me hth
00:40:37 <boily> hm. well. maybe if I didn't completely typo his name...
00:44:06 <boily> does שאחאף highlights you?
00:44:25 <boily> (meh. weechat doesn't rtl...)
00:44:26 <shachaf> boily: no, and it has too many letters anyway
00:44:38 <shachaf> boily: I think that's your terminal's job.
00:44:45 <shachaf> שחף would be the correct spelling.
00:45:26 <boily> I use Ubuntu's default terminal thingy. let's see if there's some setting in there...
00:45:44 <boily> oh. I should've guessed myself the complete absence of written vowels...
01:00:30 <HackEgo> [wiki] [[Talk:EncryptFuck]] N http://esolangs.org/w/index.php?oldid=42352 * SuperJedi224 * (+251) Created page with "Unless non-labeled loops are assumed to be equivalent to Brainf*** loops, I have reason to believe that this language, as it stands, is not turing complete. ~~~~"
01:15:49 -!- hjulle has quit (Ping timeout: 265 seconds).
01:25:36 <oerjan> <elliott> i guess the joke is pretending google is a finnish company?? <-- it's even worse because g is not a native sound in finnish
01:39:43 -!- boily has quit (Quit: WAVERING CHICKEN).
02:06:06 <orin> Which metal comes from hematite?
02:06:40 <pikhq> "heme" == "iron" FWIW.
02:06:45 <pikhq> (hence "hemaglobin")
02:07:02 <orin> That's good because that means I can make iron weapons
02:09:17 -!- vodkode_ has joined.
02:10:11 <orin> Also I can make magma pumps from iron
02:39:54 -!- doesthiswork has joined.
02:50:41 -!- Patashu has quit (Disconnected by services).
02:50:41 -!- Patashu_ has joined.
02:54:53 -!- Patashu has joined.
02:57:09 -!- Patashu_ has quit (Ping timeout: 250 seconds).
02:58:18 -!- Patashu has quit (Remote host closed the connection).
02:58:30 -!- Patashu has joined.
03:54:42 -!- Patashu has quit (Remote host closed the connection).
03:54:59 -!- Patashu has joined.
04:07:19 -!- mhi^ has quit (Ping timeout: 272 seconds).
04:07:34 -!- mhi^ has joined.
04:31:50 -!- Patashu has quit (Ping timeout: 256 seconds).
04:33:11 -!- Patashu has joined.
05:02:26 -!- ProofTechnique has quit (Ping timeout: 256 seconds).
05:30:02 -!- ProofTechnique has joined.
05:36:02 -!- adu has quit (Quit: adu).
05:42:15 -!- adu has joined.
05:48:31 -!- zadock has quit (Quit: Leaving).
05:58:52 -!- doesthiswork has quit (Quit: Leaving.).
06:17:09 <orin> God damn it, my water pumping system accidentally a whole lake
06:20:08 <orin> VERB='created'
06:25:53 -!- f|`-`|f has quit (Ping timeout: 245 seconds).
06:33:22 -!- f|`-`|f has joined.
06:56:22 -!- Patashu_ has joined.
06:56:22 -!- Patashu has quit (Disconnected by services).
07:00:56 -!- Patashu_ has quit (Ping timeout: 250 seconds).
07:05:17 -!- Patashu has joined.
07:09:37 -!- dianne has quit (Quit: byeannes).
07:26:21 <int-e> Oh it did come back by itself anyway.
07:32:02 <int-e> there was one failed reconnection attempt
07:32:46 -!- adu has quit (Quit: adu).
07:33:39 <int-e> And the ISP's twitter feed says "Investigating network blip in NL"
07:33:48 <int-e> So perhaps that was it.
07:36:07 -!- oerjan has quit (Quit: Zzleep).
07:43:13 <Taneb> orin, are you playing Dwarf Fortress
07:57:10 <orin> well I was. And then I flooded my entire fortress and the entire map, killing virtually every living thing on it
07:57:30 <orin> and this time it was an accident
08:04:08 <mroman> your water pumping system accidentally fnorded a whole lake?
08:06:24 <Taneb> Oh I do that on occasion
08:11:34 <int-e> . o O ( Welcome to the Venetian Underground )
08:36:31 <mroman> my keyboard arrived yesterday
08:36:35 <mroman> the musical instrument keyboard
08:36:41 <mroman> not the typing device keyboard
08:43:56 <mroman> now I can annoy everybody even better in the whole house!
08:44:15 <mroman> I can annoy them with my Flugelhorn, my flute, my euhponium, my keyboard
08:44:18 <mroman> and soon with my trombone!
09:05:12 <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/
09:05:37 <HackEgo> A is _not_ a village in Norway, unless you're the BBC and don't understand things on top of letters.
09:07:53 -!- jameseb has joined.
09:08:12 <Taneb> `learn Å _is_ a village in Norway, unless you're the BBC and don't understand things on top of letters.
09:08:21 <HackEgo> Learned 'Å': Å _is_ a village in Norway, unless you're the BBC and don't understand things on top of letters.
09:34:29 <orin> Since when are humans vicious killers??!?
09:34:58 <orin> This time my fort was wiped out by a human pikeman
09:38:58 <Taneb> Did you attack them first
09:39:12 <vodkode_> humans are alpha predators, of course vicious killers
09:43:52 <orin> Maybe on this world, humans and dwarves areatwar? they aren't sendng caravans
09:55:24 <orin> shows only the dwarven civ
10:02:16 <mroman> I'd say humans began becoming vicious killers since forever
10:02:57 <mroman> Afterall such violence is deeply engrained in most humans.
10:15:16 <b_jonas> is violence deeply ingrained in fungot?
10:15:16 <fungot> b_jonas: in order for the implementation.
10:15:24 <b_jonas> fungot: do you mean temptation?
10:15:24 <fungot> b_jonas: true enough. :) sorry, no connotation intended to
10:28:05 -!- boily has joined.
10:28:19 <fizzie> fungot: So would you say violence is a necessary trait?
10:28:19 <fungot> fizzie: i think that's a bourne fnord. :p
10:29:53 -!- vodkode_ has quit (Quit: Leaving).
10:34:52 <mroman> It's not necessary, but it's human.
10:35:11 <mroman> why else would there be bar fights
10:35:59 <mroman> Most humans have the capability to get angry/mad
10:36:24 <mroman> unless you have certain schizoid traits
10:36:48 <mroman> then you will most likely never get angry
10:40:47 <orin> Evolutionarily a retaliation response is probably selected for
10:41:14 <orin> tit for tat wins repeated prisoners dilemma and all that
10:46:15 <boily> fungot: would you say winter is necessary too?
10:46:15 <fungot> boily: place of interest sign links to, tusho to fnord, like scheme48, but newline is an operator or definition... and the person
10:47:00 <fungot> b_jonas: the 99 bottles of beer on the wall, 3 bottles of beer.
10:47:08 <b_jonas> yeah, that's the quick version
10:47:29 <b_jonas> was that on the twelfth day of Christmas, fungot?
10:47:30 <fungot> b_jonas: but war is peace freedom is slavery ignorance is strenght bush is president". that's non-sensical, technical and zone contact. yours, egal. inmates are mostly people who've were never taught it fnord never saw the need for a working microcode or scheme system to program games for that.
10:48:01 <boily> war is peace. freedom is slavery. ketchup is a vegetable.
11:00:19 -!- APic has joined.
11:18:49 -!- Sgeo_ has joined.
11:19:27 -!- Sgeo has quit (Ping timeout: 250 seconds).
11:21:40 -!- boily has quit (Quit: ALMOST CHICKEN).
11:28:16 <fizzie> I've heard of technical and zone contacts, but it's good to see DNS registrars also include the non-sensical contact too.
11:29:28 <FireFly> Is that where I report fungot?
11:29:28 <fungot> FireFly: error in quotient: java.lang.nullpointerexception
11:30:05 <fizzie> fungot: You're not even written in Java, stop pretending you are.
11:30:05 <fungot> fizzie: umm......do you like the climate in atlanta? how do you include fnord?) is that there are about two or three lines long, making use of your talents. to be honest i just saw
11:32:01 <FireFly> fungot: I think you're a bit lost, but as far as I know fizzie didn't move to Atlanta
11:32:01 <fungot> FireFly: sweet. only need to trigger ( y) y), ( if...), i believe).
11:33:29 <mroman> yeah fungot. Stop acting cool like java.
11:33:29 <fungot> mroman: also ear infection and scalp would (!) to someone or something has subjected you to lambda calculus)
11:38:52 <fizzie> Lambda calculus is the leading cause of ear infections these days.
11:43:25 -!- heroux has quit (Ping timeout: 255 seconds).
11:43:34 <b_jonas> fizzie: better than semicolon cancer
11:55:48 -!- heroux has joined.
12:24:57 -!- Patashu has quit (Ping timeout: 276 seconds).
12:26:46 <b_jonas> fungot, do you live in the fsouth or the fnorth?
12:26:47 <fungot> b_jonas: esp. if the code's well-written maintainable, it's probably not very necessary. i think next weekend i will make it more efficient.
12:33:51 <fizzie> I think I should be slightly worried about fungot redesigning itself to be "more efficient".
12:33:51 <fungot> fizzie: no just not scheme. my knowledge of perl is null? true for any lists l?
12:35:05 <b_jonas> I don't think he's redesigning himself
12:35:10 <b_jonas> just some other code he wrote
12:36:36 <jameseb> what language is fungot written in?
12:36:36 <fungot> jameseb: i much prefer one-implementation languages. if they're interpreted as comments the program should use append! if its result *doesn't* depend on the base language
12:37:35 <fungot> https://github.com/fis/fungot/blob/master/fungot.b98
12:41:35 <jameseb> that's quite a complex program to use a language like befunge for
12:49:13 <fizzie> It's nothing compared to the 100MLOC Befunge codebases all major corporations have.
12:50:27 -!- hjulle has joined.
12:52:31 <mroman> fizzie has been secretly replacing code inside big company software with befunge code.
12:52:48 <mroman> It's called job security.
12:53:13 <mroman> how can we hack TIOBE to display befunge on the top
12:54:07 <b_jonas> you measure befunge in _lines_
12:54:26 <mroman> code is measured in lines.
12:55:15 <b_jonas> but befunge is a two-dimensional language
12:55:24 <fizzie> Maybe they can be diagonal lines.
12:56:40 <mroman> you can always write a paper about how to measure code in 2D languages
12:56:54 <b_jonas> fungot, how do you measure code in two-dimensional languages?
12:56:54 <fungot> b_jonas: 150 euros. :p)) t?
12:57:13 <fizzie> Apparently you measure it in money.
12:57:14 <mroman> characters without nops of course
12:58:40 <b_jonas> can it simulate anything with only quasi-linear slowdown?
12:59:10 <b_jonas> it has random access get and put instructions so I presume it can, but the control options are a bit limited
12:59:35 -!- doesthiswork has joined.
13:14:35 <fizzie> They're just awkward, not limited.
13:14:49 <fizzie> The "set delta to arbitrary value" instruction is pretty much a relative jump.
13:15:05 <fizzie> (As long as you have a landing > or < in place.)
13:15:18 <fizzie> (And the awkwardness is just in encoding the numbers.)
13:15:45 -!- DrVitusWerdegast has joined.
13:15:58 -!- ProofTechnique has quit (Ping timeout: 264 seconds).
13:17:14 <fizzie> (Well, okay, for actually writing code manually it's also awkward to keep updating the numbers all the time, but that's just a small matter of preprocessing from gotos-with-labels to encoded-numbers-with-'x'.)
13:22:04 <b_jonas> there's a set delta to arbitrary value instruction? is that normal or an extension?
13:24:57 <b_jonas> oh, the x instruction in befunge98
13:25:15 <b_jonas> right, together with g and p and arithmetic, that should work
13:31:23 -!- doesthiswork has quit (Quit: Leaving.).
13:34:46 <FireFly> For whatever reason some people on codegolf.stackexchange.com seem to count befunge-98 source code as width×height
13:35:01 -!- DrVitusWerdegast has left.
13:35:07 <FireFly> b_jonas, mroman: character count seems to be the most fair way to compare languages
13:35:34 <FireFly> well, or some kind of atomic "syntactic elements count" where identifiers and keywords are treated as one unit
13:41:59 -!- ProofTechnique has joined.
13:42:38 -!- hjulle has quit (Ping timeout: 256 seconds).
14:10:44 <mroman> A: If a language meets the criteria of being listed (i.e. it is Turing complete and has an own Wikipedia entry that indicates that it concerns a programming language) and it is sufficiently popular (more than 25,000 hits for +"<language> programming" for Google), then please write an e-mail to tpci@tiobe.com.
14:11:03 -!- doesthiswork has joined.
14:11:14 <mroman> only 1.7k for +"befunge programming"
14:16:11 -!- `^_^v has joined.
14:18:05 <fizzie> Even "brainfuck programming" only has 3.5k.
14:18:12 <fizzie> So that's quite a high target.
14:20:46 <tromp> "lambda calculus programming" is also stuck at 3.7k
14:22:37 <tromp> even well established languages like PostScript don't meet the threshold
14:25:14 <HackEgo> [wiki] [[EncryptFuck]] http://esolangs.org/w/index.php?diff=42353&oldid=42351 * FreedomSka * (+12)
14:29:00 <J_Arcane> But that's just because programmers like to through the word around alot. ;)
14:29:36 <fizzie> You're supposed to include the quotes (and the +, which I believe is redundant with the quotes).
14:30:44 <tromp> forth is 3.5k short of the target...
14:30:56 -!- doesthiswork has quit (Quit: Leaving.).
14:31:38 <mroman> yeah it's quite a high target
14:31:43 <mroman> bot with enough spam bots we could do it
14:32:00 <mroman> Every problem can be solved by using more spam bots.
14:32:26 <tromp> K is only 1.6k short!
14:33:31 <tromp> but L made it, with 3.3k to spare:)
14:33:56 <tromp> (i didnt even know there was an L programming language)
14:34:39 <b_jonas> tromp: there's at least one programming language for every ascii letter by now
14:35:33 <tromp> not that have a wikipedia entry for it
14:36:03 <tromp> e.g. +"n programming" has 25.2k hits, but only because there's an ALGOL N
14:37:18 <tromp> smalltalk barely makes it with 26k
14:38:43 <mroman> and most of those aren't about the programming language :p
14:39:08 <tromp> blc has 62, none of them about blc :(
14:39:45 <mroman> J_Arcane: Now you need a WP article on it.
14:40:15 <J_Arcane> I'm pretty sure it'd get deleted, but it might coast a while without anyone noticing. :D
14:41:52 <mroman> Let's see whose fake programming language WP article lasts the longest.
14:42:42 <mroman> it'll probably last longer on esperanto wiki or the like
14:43:03 <J_Arcane> I need a clever or stylish logo. I could probably coast on that cred for a little while. ;)
14:44:39 <mroman> and a start-up using your language
14:44:44 <mroman> possibly a fake start-up
14:46:51 <mroman> It would also help if the bible has something good to say about your language.
14:50:31 <J_Arcane> I was gonna say, sadly the Bible doesn't use the word 'heresy'. It was I think a Catholic invention.
14:53:10 <mroman> Catholics have bibles too?
14:53:24 <mroman> That's not an actual question btw.
14:53:42 <b_jonas> fungot, do you have a bible too?
14:53:42 <fungot> b_jonas: well anyway i already had an instance running. it's written for humans, and the person can switch to an s&m collector!
14:53:49 -!- heroux has quit (Ping timeout: 245 seconds).
14:54:45 <mroman> https://www.biblegateway.com/passage/?search=Acts+24:14&version=AKJV
14:54:49 <mroman> ^- this contains heresy
14:54:50 -!- heroux has joined.
15:11:38 -!- Sprocklem has joined.
15:23:32 -!- yorick has quit (Ping timeout: 252 seconds).
15:25:11 <TieSleep> +"GolfScript programming" only gets 260 results
15:27:45 -!- yorick has joined.
15:27:45 -!- yorick has quit (Changing host).
15:27:45 -!- yorick has joined.
15:38:02 <b_jonas> fungot: authentificate yourself
15:38:03 <fungot> b_jonas: sleepitime is soon. already walking from the bus stop. ' gone' now. soviet russia is dead and it will print a 1.
15:46:37 <fungot> FireFly: how can i overcome this sleep deprivation feeling. i've been thinking about a graphical object inspector, which is all the more
15:47:35 <b_jonas> FireFly: a sweep and mark garbage collector obviously
15:50:04 <fizzie> Must be easy, being a bot. Feeling sleep-deprived? Just fire up a graphical object inspector and mutate some state.
15:51:54 <FireFly> fungot: how's life as a bot?
15:51:54 <fungot> FireFly: fnord/ code/ fshift.scm. perhaps i won't really be encountering new ones all the time, btw)
16:18:22 -!- Sprocklem has quit (Ping timeout: 264 seconds).
16:53:31 -!- TieSleep has changed nick to TieSoul.
17:00:09 -!- fractal has quit (Ping timeout: 244 seconds).
17:44:06 -!- TieSoul has quit (Ping timeout: 248 seconds).
17:51:22 <HackEgo> [wiki] [[Swap]] http://esolangs.org/w/index.php?diff=42354&oldid=17651 * 128.84.125.33 * (-27) rm category unimplemented
18:06:26 -!- TieSoul has joined.
18:15:15 -!- Koen_ has joined.
18:28:13 -!- TieSoul_ has joined.
18:28:41 -!- TieSoul has quit (Read error: Connection reset by peer).
18:28:42 -!- TieSoul_ has changed nick to TieSoul.
18:29:16 -!- HackEgo has quit (Remote host closed the connection).
18:29:32 -!- HackEgo has joined.
18:49:08 -!- shikhin has changed nick to literallyitler.
18:49:26 -!- literallyitler has changed nick to shikhin.
18:49:47 -!- izabera has changed nick to rodabrak.
18:50:45 -!- rodabrak has changed nick to krabador.
18:51:00 -!- krabador has changed nick to izabera.
18:55:10 -!- hjulle has joined.
18:59:46 -!- Sprocklem has joined.
19:39:44 -!- dianne has joined.
19:40:18 -!- `^_^v has quit (Quit: This computer has gone to sleep).
19:43:09 -!- variable has joined.
19:43:59 -!- `^_^v has joined.
20:00:02 -!- GeekDude has joined.
20:03:45 <b_jonas> Has anyone used libxml++ (the C++ bindings for the gnome libxml2 library)? How usable is it, for parsing XML and HTML?
20:04:08 <b_jonas> Or what are other good libraries with a C++ or C interface for parsing XML and HTML?
20:04:12 -!- Koen_ has quit (Quit: Koen_).
20:04:26 -!- Sprocklem has quit (Ping timeout: 256 seconds).
20:07:52 -!- ais523 has joined.
20:35:32 -!- Sprocklem has joined.
20:37:37 -!- TieSoul has changed nick to TieSleep.
20:38:51 -!- ais523 has quit (Read error: Connection reset by peer).
20:38:59 -!- ais523 has joined.
20:42:28 -!- AnotherTest has joined.
20:47:49 <b_jonas> ais523: have you ever used libxml++ (the C++ binding for gnome libxml2) or some other library with a C++ or C interface for parsing XML and HTML? I'd like to know which library to look at.
20:48:20 <ais523> b_jonas: I haven't, the closest I've come is building something that depends on xerxes
20:50:45 <ais523> I think it's an XML library
20:51:45 <int-e> @google xerxes xml
20:51:46 <lambdabot> https://xerces.apache.org/xerces-c/
21:02:03 -!- Patashu has joined.
21:13:20 -!- ProofTechnique has quit (Ping timeout: 252 seconds).
21:15:43 -!- AnotherTest has quit (Remote host closed the connection).
21:22:43 -!- Patashu has quit (Ping timeout: 265 seconds).
21:25:38 -!- Sprocklem has quit (Ping timeout: 245 seconds).
21:39:37 -!- oerjan has joined.
21:42:42 -!- G33kDude has joined.
21:45:22 -!- GeekDude has quit (Ping timeout: 244 seconds).
21:45:22 -!- G33kDude has changed nick to GeekDude.
21:47:49 -!- vodkode_ has joined.
21:49:55 -!- ProofTechnique has joined.
21:55:52 <shachaf> whoa, another Mill talk next week in London
21:56:09 -!- boily has joined.
22:01:30 <Taneb> Why is London like so far away
22:02:24 -!- variable has changed nick to trout.
22:02:42 -!- `^_^v has quit (Quit: This computer has gone to sleep).
22:03:46 <HackEgo> [wiki] [[Beatnik]] http://esolangs.org/w/index.php?diff=42355&oldid=42213 * Chris Pressey * (+1069) Describe the comp.class and (intentional) shortcomings (yes Cliff, it *is* arguably rather rude.)
22:07:47 <boily> London is very far away for almost all points on the Earth spheroid.
22:08:05 <Taneb> I suppose I am relatively close to London
22:08:36 <Taneb> But I am about as far away from London as it is possible to be and that fact to still hold true!
22:08:57 <oerjan> Taneb: 's ok if you were in london you'd just complain that the mill talk is too far to walk
22:08:59 <boily> something something compact manifold something.
22:09:26 <Taneb> oerjan, London's pretty big
22:09:42 <Taneb> Like as big as the rest of the UK put together or something
22:10:17 <Taneb> oerjan, also I need your advice
22:10:25 <Taneb> I seem to be becoming a Hero against my will
22:10:42 <oerjan> being the capital of the largest empire the world has ever seen tends to do that.
22:11:05 <shachaf> oerjan: wouldn't it be more likely with the smallest
22:11:11 <Taneb> Like, people seem to think I am a paragon of good
22:11:27 <oerjan> shachaf: well the UK was just a small part of the empire
22:11:54 <Taneb> oerjan, by population it was the second-biggest
22:12:24 <HackEgo> /home/hackbot/hackbot.hg/multibot_cmds/lib/limits: line 5: exec: alignment: not found
22:12:25 <oerjan> hard to compete with exponential growth.
22:12:32 <boily> hm... no alignment command.
22:12:45 <Taneb> London was the second city in the world to get a population over 1000000
22:13:29 <shachaf> san francisco still has a population below 1000000 :'(
22:13:37 <Taneb> shachaf, SF is weird
22:13:48 <Taneb> oerjan, how do I not seem such a paragon of good
22:13:53 <oerjan> i'd vaguely thought the chinese would have beat that but i guess marco polo wasn't talking about individual cities?
22:13:54 <Taneb> shachaf, not in a very long time
22:14:06 -!- vodkode_ has quit (Ping timeout: 240 seconds).
22:14:10 <oerjan> Taneb: you need to work on your evil overlord plans hth
22:14:51 <Taneb> shachaf, but one of my housemates lived there for a while
22:16:31 <Taneb> oerjan, I kind of lost my evil overlord plans
22:16:40 <Taneb> Step 1 was stealing nuclear weapons
22:16:45 <oerjan> well i guess you're doomed then
22:17:04 <oerjan> talk to ais523 he has experience on surviving as lawful good hth
22:17:11 <Taneb> And the last step was betraying all my former friends and not giving them the reward I promised
22:17:19 <Taneb> I'm not so sure I'm lawful
22:17:30 <ais523> you could be neutral or chaotic good, I guess
22:17:35 <ais523> or true or chaotic neutral
22:17:35 <Taneb> Might even be chaotic I think
22:17:36 <oerjan> Taneb: i think that last step _could_ be against the evil overlord list.
22:18:14 <Taneb> I think I may well be chaotic good
22:18:23 <boily> Taneb: have you ever built overcomplicated contraptions to lure in, snare and menace good people?
22:18:33 <Taneb> boily, not that I can recall
22:18:37 <oerjan> does his haskell programs count
22:18:51 <boily> oerjan: I think so.
22:19:13 <shachaf> oerjan: no truly good people would be tempted by a haskell program hth
22:19:20 <Taneb> That puts me into minion territory
22:19:24 <boily> Taneb: do you have an unhealthy fascination towards lasers, death rays, disintegration and other zeerusty weapons?
22:20:02 <boily> Taneb: is that obsession instead channeled in the direction of bananas and yellow curved fruits?
22:20:17 <Taneb> I don't really like bananas
22:21:22 <boily> module haskellisms, you're a paragon of goodness.
22:21:31 <oerjan> shachaf: that's what a really devious overlord would say
22:21:59 <oerjan> Taneb: what about lenses and barbed wire?
22:22:22 <Taneb> oerjan, in the physical sense, the morphismy sense, or the kmetty sense?
22:22:32 <oerjan> in the ambiguous sense, duh
22:23:21 <int-e> oerjan: how about the seventh sense?
22:23:58 <int-e> boily: the sixth was already taken
22:24:31 <boily> pray tell what's the seventh?
22:24:36 * oerjan only remembers that seventh sense is some kind of old term for almanac or something
22:24:47 <oerjan> in norwegian translation
22:25:23 <Taneb> oerjan, is the most resent GG the first time Zeetha and Bang have met?
22:25:46 * int-e would rather know whether cake has played a role before
22:26:42 <oerjan> Taneb: or at least talked... was bang there in sturmhalten?
22:27:23 <Taneb> oerjan, Bang was in Sturmhalten with Klaus
22:30:47 -!- Sprocklem has joined.
22:31:12 <int-e> right. http://www.girlgeniusonline.com/comic.php?date=20061220
22:33:32 <oerjan> she didn't show up until they'd stopped talking, though.
22:34:55 <int-e> Interestingly I don't recognize her by the name "Bang"... "Bangladesh DuPree" says the wiki.
22:35:22 <oerjan> well yes, bang is a nickname some use...
22:36:03 <int-e> the wiki does not mention cake on DuPree's page.
22:38:33 <Taneb> THat's not much of an interaction
22:39:44 <int-e> Uh, what about this: 'By the time she recovered, the airship had been taken by pirates. (It's speculated, but not proven, that these pirates were those commanded by the infamous pirate queen Bangladesh DuPree.)' ... did the wiki writers make that bit up?
22:39:52 <int-e> (from http://girlgenius.wikia.com/wiki/Zeetha,_Daughter_of_Chump )
22:41:38 <int-e> good way to seed a rumor, I suppose
22:42:24 <oerjan> int-e: it's an obvious speculation to make
22:42:53 <int-e> Yeah, except for the bit where DuPree is still alive. OTOH she *is* a survivor.
22:43:21 <int-e> Best way to survive a fight if you ask me.
22:43:22 <oerjan> it's mentioned in dupree's story
22:44:45 <oerjan> oh it refers to one of the novels.
22:45:03 <oerjan> "Zeetha's involvement is practically confirmed by Agatha H. and the Airship City, where it is mentioned that Bang returned to her fortress to find it in flaming ruins and describes the aftermath of the attack the same way Zeetha described the aftermath of her killing of the pirates."
22:47:47 <int-e> Then this encounter could be ... interesting.
22:49:04 <oerjan> it could be more interesting if bang finds out zeetha and gil are related
22:50:39 <Taneb> oerjan, I am pretty sure that Zeetha and Gil haven't found that out yet
22:51:14 <oerjan> ...i think zeetha knows.
22:53:33 <oerjan> my little theory is that klaus's claim that the skifanderians would want to kill gil (for being alive, and (also my theory) a male with skifandrian blood) ...
22:54:06 <oerjan> is technically correct, but that zeetha doesn't want to kill him, and so prefers to pretend she doesn't know.
22:55:18 -!- ProofTechnique has quit (Ping timeout: 246 seconds).
22:55:20 <oerjan> (my inner theory is based on skifandrians basically being amazons and the amazons killed their male children)
22:56:01 <oerjan> or at least they would kill a male child of a _queen_
22:56:36 <oerjan> or anyone who could be feared to want to upset the matriarchal order
22:58:51 <oerjan> ok i looked it up and i'm not the first to make that theory http://girlgenius.wikia.com/wiki/Gilgamesh_Wulfenbach/Mad
23:13:57 -!- ais523 has quit (Remote host closed the connection).
23:25:42 <Taneb> Huh, the GG timeskip happened in 2013
23:35:15 <FreeFull> Weird, I can't make dns queries to 8.8.8.8
23:36:14 -!- trout has quit (Ping timeout: 255 seconds).
23:37:22 <FreeFull> Apparently there is a problem with google dns right now
23:48:07 <oerjan> zeetha and bang also met at the circus but zeetha didn't say anything http://www.girlgeniusonline.com/comic.php?date=20041227
23:58:42 <Taneb> Hmm http://www.girlgeniusonline.com/comic.php?date=20131220 seems to suggest they met in the timeskip
00:00:26 -!- AndoDaan has joined.
00:06:11 <oerjan> oh right that's theoretically possible
00:07:38 <oerjan> i don't think they met on any other occasions before it, because zeetha didn't enter the story until the circus, bang had no reason to revisit the circus afterward, and after the battle in sturmhalten bang was in mechanicsburg hospital where zeetha afair never went.
00:09:52 -!- Sprocklem has quit (Ping timeout: 250 seconds).
00:10:17 <oerjan> Taneb: i don't read that as proving that they met one way or the other
00:10:51 -!- AndoDaan_ has joined.
00:10:56 -!- AndoDaan has quit (Read error: Connection reset by peer).
00:23:46 * boily sings remixes of remixes of remixes of touhou songs ♪
00:25:26 <tswett> Maybe I should actually design my Amazing Ultimate Programming Language before I implement it.
00:25:53 -!- ProofTechnique has joined.
00:26:10 <AndoDaan_> Seems like a good, and logical idea.
00:26:23 <boily> AndoDaan_: thanks!
00:26:26 <AndoDaan_> Why haven't we've been doing that?
00:29:15 <HackEgo> [wiki] [[Al Dente]] http://esolangs.org/w/index.php?diff=42356&oldid=41801 * 68.60.193.216 * (+0) Fix an apostrophe
00:32:45 <FireFly> boily: what kind of remixes?
00:34:23 <boily> FireFly: hardcore upbeat trance from IOSYS.
00:35:21 <boily> listening to some touhou stuff yourself?
00:35:49 <FireFly> Quite frequently, but not right now
00:36:04 * FireFly hands boily https://www.youtube.com/watch?v=9zpBdfnyy7I
00:37:29 <FireFly> I usually listen to other genres, though
00:38:10 <boily> I was indulging into some XL Project while coding today. it was smooth.
00:39:20 * orin clicks on link, finds it is something he already had
00:40:32 <boily> I wonder if the TLMC will ever get new updates...
00:42:33 <orin> recently I have been binge-listening to everything from Lilycloud
00:44:15 <FireFly> I usually just listen to whatever's playing on Gensokyo Radio or Touhou Radio
00:58:54 <oerjan> <int-e> . o O ( Welcome to the Venetian Underground ) <-- huh i never thought about venice not having cellars before
01:01:25 * boily pictures the Venetian Underground to be quite aquatic...
01:02:18 -!- doesthiswork has joined.
01:02:53 <oerjan> the houses aren't precisely built straight on water either. not all of them, anyway.
01:04:59 <fungot> boily: i don't it just ticked me off... " adventures with mental hygiene"
01:05:35 * oerjan thought fungot said "dental hygiene" and wanted to respond "my adventures with that are over"
01:05:35 <fungot> oerjan: is nfs compiled inside the kernel?
01:05:44 <fungot> oerjan: maybe i'll stop wasting money since you are working under the presumption that a tc language?
01:06:12 <oerjan> i think you are assuming a lot, fungot
01:06:12 <fungot> oerjan: as a space in front.
01:06:22 <boily> fungot: ha ha ha :D
01:06:22 <fungot> boily: " i=0" can be important to everyone else
01:06:55 <boily> oerjan: dental hygiene is important. prostheses too!
01:14:01 <FireFly> mental (or even metal) hygiene seems more important to fungot than dental hygiene, though.
01:14:02 <fungot> FireFly: i went and wrote a pretty good balance of both fnord all introductory courses use java, and a
01:15:19 <oerjan> `learn å is the same letter as Å, unless you're HackEgo and don't understand things on top of letters.
01:15:29 <HackEgo> Learned 'å': å is the same letter as Å, unless you're HackEgo and don't understand things on top of letters.
01:18:01 <HackEgo> [U+0061 LATIN SMALL LETTER A] [U+030A COMBINING RING ABOVE]
01:18:07 <oerjan> AAAAAAAAAAAAAAAAAAAAAAÅ
01:18:08 <FireFly> Aren't there normalization rules for things like that?
01:18:23 <oerjan> probably, but that doesn't mean they're applied
01:19:23 <oerjan> it's not like putty shows them identically either
01:25:21 <orin> this time my pumping system will have multiple safety cutoffs and a spillway
01:27:03 <orin> The combining one looks like a with a degree symbol above, the precombined one is attached to the a
01:28:05 <oerjan> Všichni lidé se rodí svobodní a sobě rovní co do důstojnosti a práv.
01:29:30 <orin> Apparently to dwarves, the human pikeman's corpse is garbage, not a corpse
01:45:42 -!- adu has joined.
01:48:05 -!- vodkode_ has joined.
01:49:01 -!- boily has quit (Quit: HIGHER CHICKEN).
02:06:08 -!- variable has joined.
02:17:19 -!- variable has quit (Ping timeout: 252 seconds).
02:19:09 -!- adu has quit (Quit: adu).
02:25:06 -!- Sprocklem has joined.
02:37:51 -!- gde33 has quit.
02:53:26 -!- adu has joined.
03:08:41 -!- GeekDude has quit (Quit: {{{}}{{{}}{{}}}{{}}} (www.adiirc.com)).
03:15:50 -!- AndoDaan_ has quit (Ping timeout: 255 seconds).
03:18:15 -!- TodPunk has quit (Read error: No route to host).
03:20:18 -!- TodPunk has joined.
03:38:21 -!- perrier_ has quit (Ping timeout: 252 seconds).
03:42:39 -!- Zuu has quit (Ping timeout: 250 seconds).
03:47:15 -!- Sprocklem has quit (Quit: [).
04:22:43 -!- hjulle has quit (Ping timeout: 245 seconds).
04:46:27 -!- vodkode_ has quit (Ping timeout: 244 seconds).
04:46:53 -!- vodkode has quit (Ping timeout: 245 seconds).
04:59:59 -!- Sprocklem has joined.
05:00:42 -!- hassa-aravit has joined.
05:07:27 -!- perrier has joined.
05:25:58 <bb010g> Anybody here dealt with Vala before? If so, how was it? I'm looking into using it mainly for JS bindings to a C++ library.
05:27:57 -!- dianne has quit (Quit: byeannes).
05:57:43 -!- Sprocklem has quit (Ping timeout: 245 seconds).
06:21:47 <b_jonas> fungot, do you like rice chocolate
06:21:47 <fungot> b_jonas: i'm sorry i was copying form the code littledan posted and did not check my syntax.
06:42:56 -!- vodkode has joined.
07:00:45 -!- adu has quit (Quit: adu).
07:12:11 -!- f|`-`|f has quit (Ping timeout: 250 seconds).
07:18:38 -!- augur has quit (Quit: Leaving...).
07:22:07 -!- oerjan has quit (Quit: leaving).
07:22:36 -!- doesthiswork has quit (Quit: Leaving.).
07:28:12 -!- f|`-`|f has joined.
07:48:51 <Taneb> @tell oerjan You were right :(
08:27:36 -!- Patashu has joined.
08:35:04 -!- Patashu has quit (Disconnected by services).
08:35:04 -!- Patashu_ has joined.
08:35:42 <fungot> mroman: probably. you can code them up using continuations. a numerical tower not " data" is in the compression above.
08:35:55 <mroman> fungot: I like continuations.
08:35:55 <fungot> mroman: if there is no explanation on what is the value
08:46:21 <mroman> fun fact: It is legally impossible to rape a male person in switzerland because rape is only defined if the victim is female.
08:52:25 <mroman> and the gov explicitly stated "a man can not be raped".
09:37:19 <FireFly> Now the question is whether you can trick fungot into uttering @messages or @messages-loud
09:37:20 <fungot> FireFly: i mean originally from the fnord convention predates cl by a long
09:57:51 <lambdabot> CYYZ 100948Z 14011KT 5SM +TSRA FEW012 BKN045CB OVC085 09/09 A2952 RMK SF2CB4AC2 FRQ LTGIC ALQDS PRESFR SLP001
09:59:55 -!- augur has joined.
10:01:54 -!- fractal has joined.
10:05:44 <mroman> fungot: Can you say @messages?
10:05:44 <fungot> mroman: i really wish that i'd been able to resolve it to a compiler. i was a
10:05:59 <fungot> mroman: i'll suffer for a sec
10:06:09 <mroman> Oh no. fungot is suffering!
10:06:09 <fungot> mroman: different song...? :p. ugh i need to
10:08:40 -!- MoALTz__ has joined.
10:11:39 -!- MoALTz_ has quit (Ping timeout: 255 seconds).
10:33:06 <fungot> mroman: i'm not crazy.) with extreme prejudice. u.s. slang" ( oed)) ( call/ cc
10:33:26 -!- zadock has joined.
10:35:50 -!- boily has joined.
10:38:54 -!- zadock has quit (Ping timeout: 250 seconds).
10:51:16 -!- vodkode_ has joined.
10:51:30 -!- zadock has joined.
11:11:56 <fizzie> fungot: To be honest, "I'm not crazy" is something you'd expect a crazy bot to say.
11:11:56 <fungot> fizzie: argument evaluation order is pretty much core to it, calling its methods from c code. some of the casvs problems by just using xulrunner. '
11:26:07 <boily> fiziello. did you know that fungot is sane?
11:26:07 <fungot> boily: emacs 22, do you want to read it
11:26:21 <boily> uhm... ok. perhaps not quite entirely sane.
11:28:45 -!- boily has quit (Quit: INKY CHICKEN).
11:37:36 -!- idris-bot has quit (Quit: Terminated).
12:01:43 -!- idris-bot has joined.
12:03:59 -!- idris-bot has quit (Client Quit).
12:04:49 -!- idris-bot has joined.
12:07:34 <mroman> int-e: but you're fnord.
12:07:58 <int-e> mroman: ouch, that hurt.
12:34:27 <HackEgo> [wiki] [[Axo]] http://esolangs.org/w/index.php?diff=42357&oldid=16725 * Marinus * (+126) Replace broken links with archive.org links
12:38:11 -!- ProofTechnique has quit (Ping timeout: 244 seconds).
12:41:35 -!- hjulle has joined.
12:56:43 -!- mroman has quit (Ping timeout: 246 seconds).
12:57:19 -!- vodkode_ has quit (Ping timeout: 245 seconds).
13:02:58 -!- ProofTechnique has joined.
13:16:36 -!- doesthiswork has joined.
13:25:58 -!- vodkode_ has joined.
13:28:59 -!- Patashu_ has quit (Ping timeout: 245 seconds).
13:34:28 -!- ProofTechnique has quit (Quit: ZNC - http://znc.in).
13:43:47 -!- ProofTechnique has joined.
13:46:29 -!- vodkode_ has quit (Ping timeout: 252 seconds).
13:53:31 -!- copumpkin has quit (Quit: My MacBook Pro has gone to sleep. ZZZzzz…).
13:55:55 -!- zadock has quit (Ping timeout: 272 seconds).
13:57:57 <HackEgo> [wiki] [[Beatnik]] http://esolangs.org/w/index.php?diff=42358&oldid=42355 * Chris Pressey * (+131) Edit some statements for clarity
14:01:59 -!- zadock has joined.
14:04:56 <HackEgo> [wiki] [[Beatnik]] M http://esolangs.org/w/index.php?diff=42359&oldid=42358 * Chris Pressey * (+0)
14:10:20 -!- TieSleep has changed nick to TieSoul.
14:22:54 -!- Sprocklem has joined.
14:33:06 -!- doesthiswork has quit (Quit: Leaving.).
14:50:25 <HackEgo> [wiki] [[Talk:EncryptFuck]] http://esolangs.org/w/index.php?diff=42360&oldid=42352 * 160.85.232.187 * (+135) Encryption?
14:59:54 -!- zzo38 has joined.
15:19:57 -!- Sgeo_ has quit (Ping timeout: 250 seconds).
15:27:32 <zzo38> I have worked on a OASYS assembler (I don't have it on this computer), I managed to write it in 2 days and unlike the OASYS compiler, this one uses name prefix/suffix to indicate the types. Prefix can be % (global variable) & (subroutine) ? (class) , (local or argument) . (property) : (label) ' (vocabulary). Suffix can be @ (object) # (number) $ (string) ^ (pointer).
15:28:02 <zzo38> It doesn't even resemble assembly language, even though it is
15:30:31 -!- ais523 has joined.
15:30:59 <ais523> b_jonas: so, I found a contradiction in the YACC standard
15:31:06 <ais523> it has rules for resolving shift/reduce conflicts, and reduce/reduce conflicts
15:31:13 <ais523> but they aren't consistent with each other
15:31:30 <ais523> meaning that you can produce a shift/reduce/reduce conflict where each of the three possible resolutions must be discarded in favour of a different one
15:32:15 <ais523> http://nethack4.org/pastebin/inconsistent-conflict.y
15:32:48 <zzo38> Opcodes and macros use no prefix, while void data types use no suffix.
15:33:51 <zzo38> ais523: Have you considered using Lemon though? It is an alternative to Yacc
15:34:00 -!- Sprocklem has quit (Quit: brb).
15:37:13 -!- Sprocklem has joined.
15:37:53 -!- ais523 has quit (Ping timeout: 272 seconds).
15:39:00 <b_jonas> ais523: is this about precedences again?
15:40:15 <b_jonas> zzo38: I think ais523 is writing this stuff partly because nethack4 uses yacc in a few places
15:40:46 <zzo38> Lemon works better though
15:41:48 <zzo38> And, I have fixed Lemon to be compatible with some grammars that aren't LALR(1) even.
15:43:24 <b_jonas> zzo38: um, can you tell specifics? what grammars?
15:44:03 <b_jonas> maybe I should look into lemon
15:44:32 <zzo38> I mean a few LR(1) grammars that aren't LALR(1) can now be used (although, you need to command it to do the extra processing for the symbols that cannot be used with LALR(1) so that it won't cause a conflict)
15:45:13 <zzo38> Lemon is in the public domain and is written by the same people that made SQLite, and is also used by SQLite.
15:46:50 <b_jonas> I hope your yacc will handle it better
15:48:04 -!- GeekDude has joined.
15:48:10 <zzo38> A few other features of Lemon is that the runtime does not use any global variables, the lexer calls the parser, you can use multiple Lemon parsers in one program, and you can create and destroy any number of instances of a Lemon parser in one program.
15:51:41 <FreeFull> zzo38: I wonder if Lemon would be capable of parsing Rust
15:52:09 <b_jonas> zzo38: what kind of error recovery does lemon has for input that doesn't match the grammar? is it similar to yacc?
15:52:17 <zzo38> I wouldn't know. What kind of thing are needed for parsing Rust?
15:52:42 <zzo38> b_jonas: I think so, although you can define your own error functions too
15:53:42 <zzo38> It is possible to disable error recovery in case you do not need it (SQLite does not need it)
15:55:21 <FreeFull> I have no idea how parsing complexity classes work
16:01:13 <b_jonas> zzo38: sqlite does need error recovery
16:01:46 <b_jonas> zzo38: sqlite still needs to signal an error and remain in a consistent state with no changes or leaks when it parses an invalid sql statement
16:01:55 <zzo38> SQLite will find an error and then stop; it won't try to continue parsing if there is an error.
16:02:58 <b_jonas> zzo38: yes, it won't continue parsing
16:03:04 <b_jonas> but it will still stay in a clean program state
16:03:35 <zzo38> Yes, it will do that
16:10:41 <zzo38> It is a shift-reduce parser
16:10:46 <quintopia> apparently it is supra-LALR(1) now, but not quite LR(1)?
16:11:52 <b_jonas> quintopia: it can't be full LR(1), that wouldn't be practical, it could blow up in your face exponentially
16:12:19 <zzo38> It was LALR(1) but I added a %split_states command to allow some LR(1) stuff that isn't LALR(1) also working
16:12:39 <quintopia> sure of course...unless you like exponential blowups
16:12:50 <zzo38> b_jonas: There are algorithms for LR(1) which don't take up more memory than LALR(1) when the grammar is LALR(1), though.
16:14:04 <zzo38> (I don't know how these algorithms work, so I used a different one that requires the programmer to explicitly tell the compiler which symbols should use the extra processing for LR(1).)
16:14:46 <b_jonas> zzo38: sure, you can determine with an algorithm whether the grammar is LALR(1), right? so that algorithm can just be a conditional on that
16:15:22 <zzo38> b_jonas: That would work of course, but I know there are better algorithms.
16:15:36 <zzo38> One is the "Honalee algorithm"
16:16:17 <b_jonas> I admit I don't know enough about LR-parsing, and should learn more
16:16:35 <b_jonas> borrowed a good textbook and tried to learn some of it
16:16:38 <b_jonas> but I didn't get too far yet
16:16:51 <b_jonas> I definitely should learn more
16:17:24 <zzo38> The runtime for a shift-reduce parser is pretty simple at least (and the runtime doesn't need to care whether it is LR or LALR; only the table is different in these case, but the runtime parser driver is the same)
16:21:20 -!- Phantom_Hoover has joined.
16:33:31 -!- FreeFull has quit (Quit: Nitronic Rush).
16:43:03 <b_jonas> zzo38: ok, so lemon is basically a better, more modern yacc. it has the same power in the sense that it can parse the same languages, but its interface when you're writing the grammar file and calling the parser is much better.
16:45:17 <zzo38> b_jonas: Yes, at least I find it better
17:17:31 -!- Sprocklem has quit (Ping timeout: 264 seconds).
17:22:01 -!- AnotherTest has joined.
17:33:05 -!- Sprocklem has joined.
17:36:24 -!- zzo38 has quit (Remote host closed the connection).
17:50:23 -!- zadock has quit (Ping timeout: 276 seconds).
18:05:48 -!- zadock has joined.
18:32:19 -!- sebbu2 has joined.
18:32:59 -!- sebbu2 has quit (Changing host).
18:32:59 -!- sebbu2 has joined.
18:33:36 -!- sebbu has quit (Ping timeout: 252 seconds).
18:54:22 -!- zadock has quit (Quit: Leaving).
19:01:12 -!- ^v has joined.
19:10:57 -!- zadock has joined.
19:33:54 -!- FreeFull has joined.
19:44:10 -!- magician has joined.
19:46:12 -!- Guest3780 has quit (Ping timeout: 252 seconds).
19:46:12 -!- magician has changed nick to Guest3780.
20:05:09 -!- hjulle has quit (Ping timeout: 272 seconds).
20:19:12 -!- CADD has joined.
20:19:45 -!- CADD has quit (Client Quit).
20:20:27 -!- CADD has joined.
20:29:38 -!- hjulle has joined.
20:38:31 -!- bb010g has quit (Quit: Connection closed for inactivity).
20:48:19 -!- zadock has quit (Quit: Leaving).
20:52:33 <HackEgo> [wiki] [[Hello world program in esoteric languages]] http://esolangs.org/w/index.php?diff=42361&oldid=42328 * Chris Pressey * (+2703) Add Hello, world program in Beatnik
20:58:24 -!- bb010g has joined.
20:58:49 -!- hjulle has quit (Ping timeout: 250 seconds).
21:09:09 <HackEgo> [wiki] [[Hello world program in esoteric languages]] M http://esolangs.org/w/index.php?diff=42362&oldid=42361 * Chris Pressey * (-48) /* Beatnik */ Eh, the context is probably plenty clear.
21:12:58 -!- Sprocklem has quit (Quit: [).
21:21:40 -!- Tod-Autojoined has joined.
21:21:47 -!- TodPunk has quit (Read error: Connection reset by peer).
21:34:14 -!- hjulle has joined.
21:38:48 -!- ProofTechnique has quit (Ping timeout: 248 seconds).
21:44:02 -!- AnotherTest has quit (Remote host closed the connection).
21:45:57 -!- TieSoul has changed nick to TieSleep.
22:02:16 -!- GeekDude has quit (Ping timeout: 248 seconds).
22:05:25 -!- ProofTechnique has joined.
22:07:51 -!- Sgeo has joined.
22:40:35 -!- oerjan has joined.
22:41:34 <lambdabot> Taneb said 14h 52m 42s ago: You were right :(
22:42:51 <Taneb> But that in particulary
22:44:56 -!- Sprocklem has joined.
22:50:30 <int-e> fungot: do you fight too?
22:50:31 <fungot> int-e: do you know the federal deficit is huge?"
22:50:37 <int-e> fungot: well played
22:50:37 <fungot> int-e: i'll talk to openssl via ffi, and sarahbot will tell you
22:50:58 <int-e> fungot: are you in love with sarahbot?
22:50:58 <fungot> int-e: i also got the answer
22:51:21 <int-e> fungot: and now you're going to ignore me just as it gets interesting, right?
22:51:21 <fungot> int-e: you must believe the error message. it won't work with any other. the moves are small and fast to update the paths. with the latest optical fnord technology.
22:56:59 -!- orin has quit (Read error: Connection reset by peer).
23:02:50 -!- Sgeo has quit (Ping timeout: 244 seconds).
23:03:25 -!- Sgeo has joined.
23:15:58 <olsner> fungot: are you right or is oerjan?
23:15:58 <fungot> olsner: except that negative numbers require extra code that i might have it wrong in this case i was looking at pocket pc schemes
23:19:47 <HackEgo> fungot is our beloved channel mascot and voice of reason.
23:28:24 -!- Patashu has joined.
23:34:55 <int-e> Indeed, fungot is a treasure trove of infinite love and wisdom.
23:34:56 <fungot> int-e: i do i often finish typing and press enter? i
23:35:11 <int-e> I mean except when it's not.
23:36:53 <olsner> fungot: I doubt you press enter at all, being a disembodied bot and all
23:36:53 <fungot> olsner: this capital looks a lot clearer than most e documentation i read ( fnord same ideas, but as far as static libraries and executable headers. ( i have that
23:54:11 -!- doesthiswork has joined.
23:59:09 -!- Sgeo has quit (Ping timeout: 244 seconds).
00:07:45 <fungot> @messages-loud @messages-loud
00:07:45 <lambdabot> mroman said 15h 32m 2s ago: fnord.
00:13:20 -!- dianne has joined.
00:18:10 <quintopia> ...is that intentional behavior in order to make fungot potentially able to do interesting things with other bots?
00:18:10 <fungot> quintopia: no such factoid
00:18:43 <olsner> hmm, ^echo is not bot safe?
00:18:49 <oerjan> i think it was intentional behavior to be silly hth
00:19:36 <quintopia> ^echo yields falsehood when preceded by its own quotation
00:19:37 <fungot> yields falsehood when preceded by its own quotation yields falsehood when preceded by its own quotation
00:19:42 <olsner> was "no such factoid" just markov output or does fungot have a factoid feature?
00:19:42 <fungot> olsner: is it very hard for me to duck from the things you're about to use, without some intermediate abstraction ( except for sunterlib and sunet lateron). would that be
00:19:46 <oerjan> indeed fungot doesn't prevent triggering other bots
00:19:46 <fungot> oerjan: to be exact it's stupid of anyone if they use php instead of another language i remember sawing you helping someone in parsing scheme, can i use that
00:20:00 <oerjan> but it has an extensive ignore list itself
00:20:38 <fungot> thanks but no thanks but no
00:21:44 <fungot> oerjan is very what oerjan is very what
00:23:31 -!- Sgeo has joined.
00:26:25 -!- Sgeo has quit (Read error: Connection reset by peer).
00:43:06 -!- lkirk has joined.
00:43:25 -!- variable has joined.
00:43:57 -!- NihilistDandy has joined.
00:44:20 -!- ProofTechnique has quit (Ping timeout: 250 seconds).
00:44:43 -!- doesthiswork has quit (Quit: Leaving.).
00:49:25 -!- copumpkin has joined.
00:56:38 <Lymia> Can you, like, actually index strings
01:00:39 -!- lkirk has quit (Remote host closed the connection).
01:01:21 -!- contrapumpkin has joined.
01:04:49 -!- copumpkin has quit (Ping timeout: 245 seconds).
01:06:12 -!- contrapumpkin has quit (Client Quit).
01:18:11 -!- copumpkin has joined.
01:25:20 -!- contrapumpkin has joined.
01:27:32 -!- propumpkin has joined.
01:28:46 -!- copumpkin has quit (Ping timeout: 255 seconds).
01:30:20 -!- contrapumpkin has quit (Ping timeout: 256 seconds).
01:40:48 -!- propumpkin has changed nick to copumpkin.
01:49:37 -!- contrapumpkin has joined.
01:51:52 -!- vodkode_ has joined.
01:52:48 -!- propumpkin has joined.
01:53:00 -!- copumpkin has quit (Ping timeout: 250 seconds).
01:53:11 -!- propumpkin has quit (Client Quit).
01:56:02 -!- variable has quit (Ping timeout: 250 seconds).
01:56:12 -!- contrapumpkin has quit (Ping timeout: 264 seconds).
01:58:37 -!- Sgeo has joined.
02:07:29 <quintopia> Lymia: i expect that splitting a string and then counting the length of the first part accomplishes that
02:17:29 -!- zzo38 has joined.
02:27:39 <Sgeo> Why would a computer take hours after booting up to act normal?
02:30:52 <Jafet> Not everyone's a morning person.
02:37:42 -!- NihilistDandy has changed nick to ProofTechnique.
02:40:06 -!- vodkode_ has quit (Quit: Leaving).
02:40:36 -!- vodkode_ has joined.
02:41:47 -!- vodkode_ has quit (Remote host closed the connection).
02:42:49 -!- vodkode_ has joined.
02:45:31 -!- Sgeo has quit (Ping timeout: 244 seconds).
02:48:29 -!- bb010g has quit (Quit: Connection closed for inactivity).
03:07:59 -!- copumpkin has joined.
03:15:59 -!- Phantom_Hoover has quit (Remote host closed the connection).
03:35:57 -!- copumpkin has quit (Quit: My MacBook Pro has gone to sleep. ZZZzzz…).
03:42:38 -!- heroux has quit (Ping timeout: 250 seconds).
03:43:35 -!- heroux has joined.
03:52:39 -!- hjulle has quit (Ping timeout: 265 seconds).
04:30:32 -!- vodkode_ has quit (Ping timeout: 246 seconds).
04:32:47 -!- variable has joined.
04:42:11 -!- Sprocklem has quit (Ping timeout: 245 seconds).
04:51:49 -!- adu has joined.
05:07:45 -!- variable has quit (Ping timeout: 245 seconds).
05:13:40 -!- infinitymaster has joined.
05:21:44 -!- Sgeo has joined.
05:21:44 <zzo38> Is there any "urn:bible:" scheme?
05:30:26 -!- Tod-Autojoined has changed nick to TodPunk.
06:03:10 -!- vodkode_ has joined.
06:15:12 -!- bb010g has joined.
06:21:21 -!- infinitymaster has quit (Quit: Leaving...).
06:53:53 -!- adu has quit (Quit: adu).
06:55:22 -!- irctc099 has joined.
07:29:42 -!- Sgeo has quit (Ping timeout: 244 seconds).
07:32:35 <zzo38> Make URIs such as <urn:bible:genesis:1:1> and so on to be valid.
07:37:48 -!- vodkode_ has quit (Ping timeout: 240 seconds).
07:38:07 <zzo38> I made up a kind of backtracking parser like: forever { (X,Y)=pop; foreach (W,Z) in action[Y][input[X]] do push(X,call W with argument Z); foreach Z in next[Y][input[X]] do push(X+1,Z); }
07:45:04 <zzo38> How do you compare this to the other kind of parsing?
07:49:46 <zzo38> You will want to start by pushing (length(input),error state) and then (0,0) onto the stack.
07:52:34 -!- vodkode_ has joined.
07:55:36 -!- Phantom_Hoover has joined.
07:59:23 <zzo38> Actually here is better way: push(length(input),error value); push(0,0); forever { pop(X,Y); if X=length(input) then return Y; foreach (W,Z) in action[Y][input[X]] do push(X,call W(Z,X)); foreach Z in next[Y][input[X]] do push(X+1,Z); } At first you must ensure that the input sequence ends with the EOF token
08:00:04 -!- mroman has joined.
08:04:12 <mroman> something's wrong with my vserver.
08:04:27 <zzo38> Do you know what thing is wrong?
08:05:22 <mroman> it reboots for unknown reasons
08:05:30 <mroman> and now my root password doesn't seem to work anylonger.
08:06:40 <mroman> maybe the did maintenance on their physical hosts
08:06:50 <mroman> but forgot to inform me that they reboot vms
08:16:21 <zzo38> Is it OK now though?
08:21:31 <Taneb> zzo38, I am in the UK
08:21:38 <Taneb> (York, in particular, now)
08:21:54 <mroman> it rebooted twice yesterday though
08:25:28 -!- vodkode_ has quit (Ping timeout: 240 seconds).
08:30:22 <zzo38> How is this parser I made up compared with other ones?
08:37:18 <zzo38> The one which is: add EOF to input buffer; push(length(input),error value); push(0,0); forever { pop(X,Y); if X=length(input) then return Y; foreach (W,Z) in action[Y][input[X]] do push(X,call W(Z,X)); foreach Z in next[Y][input[X]] do push(X+1,Z); }
08:47:00 <mroman> action[Y][input[X]] contains parse functions?
08:47:42 <mroman> with one character lookahead?
08:49:56 <zzo38> Rather, the functions might be used to enter or exit the parser for a particular nonterminal; they can do other things too though.
08:55:59 -!- oerjan has quit (Quit: Niteoid).
09:01:04 -!- oren has joined.
09:05:44 <mroman> 9% of the human population is disabled?
09:07:04 <mroman> More than 1 billion persons in the world have some form of disability. This corresponds to about 15% of the world's population.
09:08:52 <oren> Probably includes nearsighted people, people who have slight deafness (like me), people who are too old to walk.
09:10:22 <oren> So the number would be pretty high, there are so many people who need glasses
09:12:40 <mroman> If you consider that as "disabled" then yes.
09:12:44 <mroman> Then the number is pretty damn high.
09:13:22 <mroman> if you take the definition of "disability funds" because you can't work due to your disability then the number should be less.
09:14:13 <oren> Well there are different levels, aome jobs might need perfect eyesight or perfect hearing, but most jobs don't.
09:15:57 <oren> On the other hand sometimes people complain about an infuriating noise distracting them, and I say "what noise".
09:19:43 <oren> Hmm... it seems statistically trouble walking or climbing stairs is the most common disability
09:23:35 <mroman> well if you're fit to do another job you'll be forced to retrain for another job.
09:24:24 <mroman> You can't just not work because you can't to the job you originally did any longer, you'll have to learn how to do another job.
09:24:43 <mroman> unless you wanna live of social welfare which isn't really a lot of money.
09:25:29 <mroman> unless you have some disability pension
09:25:34 <mroman> I don't really know how they work.
09:25:56 <oren> Although I think many of the people who acquire a disablity do so because they simply are getting old...
09:26:55 <oren> Everything from their eyes to their bones starts to have problems
09:27:08 <mroman> there's insurance against incapacity to work
09:27:38 <mroman> but I'm not sure if that's an additional optional insurance or one you have to have or one you automatically get.
09:28:20 <oren> this stuff probably varies greatly by jurisdiction
09:29:24 <mroman> It appears that 60% of my salary is "insured".
09:30:05 <mroman> if I'm 70% disabled I get 60% of my original salary paid for two years
09:30:20 <mroman> but after that it stops :)
09:30:38 <mroman> so I'd have two years to find a job I can still do
09:30:53 <mroman> or if I'm to disabled to continue meaningful work I have to apply for "income disability"
09:31:14 <mroman> (there's "work disability" == "can't do your job anymore" and "income disability" == "can't do any meaningful job anymore")
09:32:04 <mroman> unless I'm older than 50 years at the time of becoming disabled
09:32:10 <mroman> then there's no two years restriction.
09:32:36 <mroman> oren: this stuff varies a lot by jurisdiction, your employer
09:32:44 <mroman> and which insurance company your employer uses.
09:34:03 <mroman> and if I die my children will get money
09:34:34 <mroman> I guess that's the english word for that.
09:34:59 <mroman> which is 60% of something that also xx% of something else
09:35:10 <mroman> It's aimed at getting them through school
09:35:15 <mroman> but not to live off it for longer periods.
09:35:21 <mroman> but I don't have children.
09:36:06 <oren> I need to see about getting a job pretty soon
09:37:10 <oren> And stop being a NEET
09:38:37 -!- Koen_ has joined.
09:38:53 <Taneb> My current plan is to stay in the E that doesn't pay as well as long as I can
09:41:40 -!- TieSleep has changed nick to TieSoul.
09:47:09 -!- dianne has quit (Quit: byeannes).
09:48:22 <TieSoul> https://gist.github.com/TieSoul/373d98cac227ec51ba4d so I'm working on something
09:48:37 <TieSoul> (brainfuck is just a test for the lexer/parser system)
10:14:25 <mroman> and what are you working on?
10:15:25 -!- Patashu has quit (Disconnected by services).
10:15:25 -!- Patashu_ has joined.
10:23:34 <int-e> The comments at http://en.chessbase.com/post/us-champ-r9-forfeit are so much fun; some of them suggest the arbiter should be using a double standard and not forfeit *top* players when they violate rules despite having been warned about it...
10:24:10 <int-e> (Not really fun. I'm suffering from a case of http://xkcd.com/386)
10:25:54 <zzo38> They should be disqualified if they seriously violate the rules, whether they are the top players or not. They can try again in the next tournament though.
10:26:21 <oren> Hmm, this terminal thought the ) was part of the url...
10:30:01 <TieSoul> mroman: I'm working on a lexer and parser system for arbitrary grammars
10:30:10 <int-e> zzo38: I'm also now waiting for the first case of a player being disqualified for "analysing any game on another chessboard." when they wander around and look at their competitor's game. ;-)
10:30:58 <oren> TieSoul: to what level of "arbitrary"
10:31:16 <oren> any unambiguous grammar?
10:36:38 <TieSoul> https://gist.github.com/TieSoul/ed33bf2c5365b2ed0a7e an example
10:39:22 -!- sebbu2 has changed nick to sebbu.
10:52:55 <mroman> so it's based on regexes
11:27:45 <mroman> fungot: Do you like regexes?
11:27:45 <fungot> mroman: you may need to introduce any extra nesting by receiving the multiple values extension is as important!". kthxbye.
11:28:10 <mroman> TieSoul: see. I told you to introduce extra nesting and multiple values extension.
11:35:39 <mroman> but no... you told me you couldn't do it...
11:35:55 <mroman> fungot: Can you do it?
11:35:55 <fungot> mroman: i think the category theory is mostly a browser-only thing ever, the lives of folks who were thinking about lazy strings/ ropes/ whatever they are
11:36:11 <mroman> Category Theory is sure a browser-only thing.
11:36:32 <HackEgo> In category theory, category theory is a theory in the category of theories.
11:36:46 <mroman> ... and it's only used in browsers.
11:41:55 <mroman> Must be a category theory thing.
11:42:25 <mroman> fungot: What browser do you use?
11:42:25 <fungot> mroman: yah i agree. though riastradhs variant is not formally checkable
11:42:38 <mroman> fungot: agree with what?
11:42:38 <fungot> mroman: i don't mind looking at some code? i want to call something a functor unless it's returning a function
11:43:42 <mroman> fungot: Category Theory is just a theory. It hasn't been proven yet.
11:43:55 <int-e> `define A browser is a Gopher client for convenient access to Gopher services and documents.
11:44:08 <HackEgo> Failed to connect to socket 2. \ \ Looking up 127.0.0.1:3128 \ Making HTTP connection to 127.0.0.1:3128 \ Sending HTTP request. \ HTTP request sent; waiting for response. \ Alert!: Unexpected network read error; connection aborted. \ Can't Access `http://google.com/search?q=define:%41%20%62%72%6f%77%73%65%72%20%69%73%20%61%20%47%6f%70%68%65%72%20%
11:46:14 <int-e> `learn A browser is a Gopher client for convenient access to Gopher services and documents.
11:46:20 <HackEgo> Learned 'browser': A browser is a Gopher client for convenient access to Gopher services and documents.
11:48:57 <mroman> Gopher is int-e's vision of the successor of HTTP/2
11:49:24 <mroman> `learn Gopher is int-e's vision of the successor of HTTP/2.
11:49:37 <HackEgo> Learned 'gopher': Gopher is int-e's vision of the successor of HTTP/2.
11:51:05 <mroman> can't reach google.com, google.de nor google.ch
11:52:25 <mroman> TieSoul: You play Pokémon?
11:52:42 <mroman> I'm stalking your gists.
11:52:51 <mroman> and there's a Nidoqueen.
11:52:56 <mroman> I don't know what Arbok is though
11:53:19 <TieSoul> is from a pokemon battle simulator I wrote
11:55:42 <mroman> well... I'm off to buy me a bicycle.
11:56:06 <izabera> we also have trains and planes
11:56:06 <mroman> and pollute the universe!
11:56:15 <mroman> yeah but trains are friendly people.
11:56:31 -!- mroman has quit (Quit: Lost terminal).
11:56:44 <int-e> I was going to recommend the LEO (Link Everything Online) gopher service (which featured a english/german/english dictionary!), but I'm afraid they dismantled the gopher server years ago.
12:03:03 <oren> Old joke from the playground years ago: Ekans is snake backwards, Arbok is cobra backwards, what about Muk?
12:28:01 <HackEgo> [wiki] [[Beatnik]] http://esolangs.org/w/index.php?diff=42363&oldid=42359 * Chris Pressey * (+213) Add internal link to Hello world and external link to Python implementation
12:30:34 -!- boily has joined.
12:31:25 -!- zadock has joined.
12:31:26 -!- zadock has quit (Max SendQ exceeded).
12:45:43 <oren> what is a .debanyway
12:47:31 <int-e> > ar t libiw30_30~pre9-8_amd64.deb
12:47:32 <lambdabot> ‘a’ (imported from Debug.SimpleReflect),
12:48:21 <oren> Ah, so it's like an archive with some files and metadata as to what to do with them?
12:49:34 <int-e> yeah, control.tar.gz contains meta information, install and uninstall scripts, things like that
12:52:21 * oren is considering trying to make a .deb for dwarf fortress
12:53:22 <int-e> Ah but there are tools for that. https://wiki.debian.org/HowToPackageForDebian looks like a suitable starting point.
12:54:11 <int-e> (Disclaimer: I have not actually made a deb package yet.)
13:03:23 -!- oren has quit (Read error: Connection reset by peer).
13:03:48 -!- orin has joined.
13:16:11 -!- doesthiswork has joined.
13:23:49 -!- shikhin has changed nick to bacon.
13:23:57 -!- bacon has changed nick to shikhin.
13:25:31 <orin> I restarted my computer because firefox was screwing up even after I pkilled it
13:32:30 <orin> it seems to be fine now
13:33:34 <orin> now what I really need to figure out is why my level generator code is making roads that lead to nothing
13:36:35 <orin> http://postimg.org/image/w9gs905y3/full/ the problem occurse in the pink square
13:38:30 -!- bb010g has quit (Quit: Connection closed for inactivity).
13:43:34 <orin> Fixed. I really screwd up the road-merging part last night
13:44:49 -!- Patashu_ has quit (Ping timeout: 264 seconds).
13:47:04 <Jafet> You could just add things that the roads lead to.
13:48:01 <orin> Jafet: That is what was supposed to happen
13:49:00 <orin> Roads come from either side of the level or from tunnels and go off either side or into a tunnel
13:49:34 <orin> A road isn't supposed to bea ble to just... end
13:53:08 -!- GeekDude has joined.
13:59:28 -!- irctc099 has quit (Ping timeout: 246 seconds).
14:00:40 <Jafet> You can say that to the town council over here.
14:23:52 <Taneb> I think one that orin is making
14:25:37 <Taneb> Help I am in at least 2 IRC channels WITH CYBORGS
14:28:37 <int-e> Taneb: welcome to the future
14:28:59 <int-e> Taneb: did any of them say "come with me if you want to live"?
14:29:16 <int-e> (did I get this right?)
14:29:18 <Taneb> I don't think either hav
14:29:47 <int-e> (yeah I did. good.)
14:34:27 -!- hjulle has joined.
15:10:15 -!- vodkode_ has joined.
15:11:38 -!- llue has joined.
15:11:38 -!- llue has quit (Changing host).
15:11:38 -!- llue has joined.
15:15:41 -!- GeekDude has quit (Ping timeout: 252 seconds).
15:24:16 -!- bb010g has joined.
15:25:12 -!- vodkode_ has quit (Ping timeout: 276 seconds).
15:52:06 -!- MoALTz__ has quit (Quit: Leaving).
16:04:07 -!- GeekDude has joined.
16:12:20 <Taneb> Phantom_Hoover, I'm blaming you for this: http://www.bbc.co.uk/news/uk-england-coventry-warwickshire-32264914
16:21:51 -!- GeekDude has quit (Quit: {{{}}{{{}}{{}}}{{}}} (www.adiirc.com)).
16:31:20 -!- yorick has quit (Read error: Connection reset by peer).
16:33:49 -!- yorick has joined.
16:34:07 -!- yorick has quit (Remote host closed the connection).
16:34:28 -!- yorick has joined.
16:35:31 -!- yorick has quit (Remote host closed the connection).
16:36:08 -!- yorick has joined.
16:36:09 -!- yorick has quit (Changing host).
16:36:09 -!- yorick has joined.
16:58:53 <Taneb> Phantom_Hoover, wow, how did you manage to do it, then?
17:00:58 -!- copumpkin has joined.
17:01:08 <int-e> Taneb: Time travel, obviously.
17:01:26 <int-e> You should try it, it's great for deniability.
17:07:34 <int-e> In any case it sounds like a brilliantly successful demonstration.
17:10:09 <zzo38> Should I move the stuff from the old LEO gopher service into my own? I don't even have a copy though, so I can't.
17:11:18 <boily> hezzo38. what's LEO?
17:11:55 <zzo38> I don't know; int-e mentioned it above.
17:12:33 <boily> int-ello. what's LEO?
17:27:20 <int-e> boily: "Link Everything Online". You may know its remnants ( ;-) ) on the World Wide Web, under leo.org.
17:37:24 <Koen_> int-e: it sounds like space travel might be more effective to get to england
17:38:59 <int-e> Koen_: Perhaps, but that may compromise your alibi.
17:39:48 <Koen_> well, time travel preserves the alibi because people assume you're not time traveling, nothing more
17:40:09 <Koen_> similarly space travel wouldn't compromise your alibi if people didn't know you could space travel to england
17:41:51 <b_jonas> fungot, do you ever time travel or space travel?
17:41:51 <fungot> b_jonas: lain was a bit comical
17:50:19 -!- magician has joined.
17:50:59 <HackEgo> magician: 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.)
17:53:21 -!- Guest3780 has quit (Ping timeout: 252 seconds).
17:53:21 -!- magician has changed nick to Guest3780.
17:58:31 <int-e> boily: Btw, "remnants": The main part of what LEO was meant to be is indeed gone: It was a directory service for Gopher, intended to be comprehensive.
18:57:56 <zzo38> I think there are now other directory services for gopher
19:20:26 -!- boily has quit (Quit: %%%%%%%%).
19:26:17 <int-e> . o O ( Gopher - where we're going, we don't need an information superhighway. )
19:38:52 -!- ais523 has joined.
20:07:05 -!- Koen_ has quit (Remote host closed the connection).
20:12:42 <tswett> So, are there infinitely many pairs of 5-smooth numbers differing by 2?
20:13:33 <tswett> According to http://oeis.org/A219794, it would be "very surprising" if there were.
20:13:40 <tswett> I don't see why that's the case.
20:23:42 <tswett> I can think of a bunch. 1 and 3, 2 and 4, 3 and 5, 4 and 6...
20:25:05 <int-e> It's because the density of the 5-smooth number is so low; there are only O(log(n)^3) of them up to n. (Compare this to primes with O(n/log n) primes up to n.)
20:25:44 <tswett> Some Haskelling suggests that the largest pair is 160 and 162.
20:26:06 <tswett> Which is just the doubling of the largest pair of numbers differing by 1, which is 80 and 81.
20:26:52 <tswett> The only pair differing by 2 which isn't "obvious" given the pairs differing by 1 is (25, 27).
20:27:20 <int-e> Oh that's another funny detail. lim inf a(n) >= 2 (an amazing fact, hmm) means that only finitely many pairs arise by doubling
20:28:24 <int-e> Because it says that there are only finitely many pairs of 5-smooth numbers with difference 1.
20:29:04 <tswett> The only pair differing by 3 not "obvious" from prior pairs is (125, 128). For 4, 5, and 6, there are no "non-obvious" pairs.
20:30:34 -!- tswrcclt has joined.
20:30:58 <tswrcclt> For 7, there are two: (128, 135) and (243, 250).
20:31:48 <tswrcclt> My computer is being very sluggish now.
20:33:47 -!- Decim has joined.
20:34:12 <Decim> I'm making an AI what should it do
20:34:54 <TieSoul> it should write functional Brainfuck code
20:35:06 <ais523> it should analyze a source tarball and work out how to compile it
20:35:27 <tswrcclt> It should analyze English text and classify words into parts of speech.
20:35:33 <TieSoul> it should analyze a source tarball and then compile it
20:35:46 <tswrcclt> Note that my suggestions are actually serious.
20:35:47 <Decim> These are really good ideas
20:36:08 <TieSoul> it should play arbitrary NES games
20:36:16 <TieSoul> someone did that already so it's possible
20:36:46 <Decim> The brainfuck thing though
20:37:33 <TieSoul> (btw, I wonder if you could make Prolog write brainfuck code to solve a particular problem)
20:38:14 <TieSoul> (it would output all possible solutions too which is nice)
20:38:31 <Decim> What did you mean by writing functional code I would have to make the algorithm learn the entire language
20:38:37 <Decim> And idk the language so
20:38:48 <tswrcclt> It's a pretty simple language.
20:38:50 <Decim> Guess I have to learn it before I start?
20:39:09 <TieSoul> brainfuck is about the simplest language ever
20:39:16 <tswrcclt> Eight commands. "Add one", "subtract one", and so forth.
20:39:23 <Decim> Tarballs are another thing entirely
20:39:35 <Decim> Compiling Tarball AI bot
20:39:56 <Decim> I don't know kids I'm only a kid
20:40:06 <tswrcclt> Help, GHC is using nearly six gaggleboots of memory.
20:40:13 <TieSoul> if you're starting out with AI
20:40:20 <TieSoul> try something easy like Tic-Tac-Toe
20:40:45 <int-e> tswrcclt: that's how you know it's a serious programming language ... :-/
20:41:14 <Decim> I had to make a self responsive bot for a school project although I got a D- on it
20:41:18 <tswrcclt> Uh, memory usage seems to have stabilized.
20:41:46 <Decim> Is space an issue?
20:41:46 <tswrcclt> Went all the way up to 6.9 before going back down a little.
20:45:32 <Decim> Infinite possibilites in tic tac toe or more to a large ammount of finite possibilites
20:47:28 <int-e> Decim: space is always an issue :)
20:48:12 <Decim> And overclock everything while keeping your server under a mile of ice
20:48:54 <int-e> wtf. "2 GB DDR3L SDRAM, 32 GB Solid-State Drive and 1TB OneDrive Cloud Storage for one year" ...
20:49:23 <int-e> I made the mistake to search for "laptop" on amazon, now marvelling at the crap they offer.
20:49:54 <Decim> Int-e there's a lot better stuff than that
20:50:37 <Decim> Also more on point I don't have enough space for something like a tarball compiler
20:52:10 <int-e> Decim: Of course there is. And it's good to see that even absolute crap has 2GB RAM, and normal laptops have 4GB or 8GB.
20:53:53 <Decim> What's your setup Int-e
20:54:13 <int-e> Still, memory usage matters; on VPSs, RAM determines the price.
20:55:23 <int-e> I have 8GB RAM in a PC at home... which is too small for some things I'm doing. (ghc is pushing the limits; some big Isabelle theories are taking off the lid)
20:57:09 <int-e> But lambdabot is running on a VM with 512MB RAM + 512MB swap, which is not enough to build it anymore.
21:00:02 <Decim> What are you doing
21:00:10 <Decim> And wtf is an isabelle theory
21:00:19 <fizzie> TieSoul: "We" did arbitrary Atari games.
21:00:42 <int-e> Compiling haskell-src-exts with ghc-7.10.1 takes 5GB...
21:00:55 <int-e> ...it's a dependency of lambdabot
21:01:03 <Decim> Take me to the begining of this whole ghc stuff isabelle theory idk I havent payed attention to stuff
21:01:22 <Decim> Don't you guys have articles or something
21:01:45 <int-e> None of this has to do anything with #esoteric really.
21:02:05 <Decim> Why does it depend on lambdabot
21:02:20 <int-e> Isabelle is a proof assistent, http://isabelle.in.tum.de/ , and she's quite memory-hungry.
21:02:33 <Decim> ...what would happen if you deleted every version of lambdabot
21:02:48 <int-e> Why would I do that?
21:03:06 <int-e> Not that I could. It's been forked several times on github.
21:03:10 <Decim> And you were like fuck it
21:03:36 <int-e> Decim: I suppose the world would just go on turning.
21:04:20 <Decim> Until 569075432 AD when the sun expands
21:06:34 <Decim> Aw man isabelle is just on a bullshit level of nope for me I don't think I could ever have that much memory Im pretTy poor atm
21:13:43 -!- nortti has changed nick to lawspeaker.
21:15:40 -!- lawspeaker has changed nick to nortti.
21:16:48 -!- Decim has quit (Remote host closed the connection).
21:18:51 -!- Sprocklem has joined.
21:23:12 -!- bixnode has joined.
21:37:45 -!- callforjudgement has joined.
21:37:58 -!- ais523 has quit (Read error: Connection reset by peer).
21:38:09 -!- callforjudgement has changed nick to ais523.
21:41:46 -!- bixnode has quit (Remote host closed the connection).
21:42:04 -!- bixnode has joined.
22:16:28 -!- boily has joined.
22:25:06 <quintopia> you tryna trick me with your "b" name and your characteristically boily-like response
22:27:50 <zzo38> Is thid document understandable to you? http://sprunge.us/cCCL (I didn't invent the OASYS VM; it days from 1992, but was not documented before, so this is a document of it.)
22:30:45 -!- vodkode_ has joined.
22:31:02 <boily> b_jonas: you're not me.
22:46:52 -!- ais523 has quit (Read error: Connection reset by peer).
22:46:56 -!- callforjudgement has joined.
22:47:07 -!- callforjudgement has changed nick to ais523.
22:49:10 -!- vodkode_ has quit (Ping timeout: 276 seconds).
22:49:26 <b_jonas> zzo38: yes, it's understandible, but there's some difficulties:
22:49:44 <b_jonas> it would be nice if there was an introductory paragraph at the beginning to tell what the whole thing is about;
22:50:11 -!- tswrcclt has quit (Quit: Connection closed for inactivity).
22:50:27 <zzo38> OK, is there anything else to consider?
22:50:34 <b_jonas> I think it would read easier if you first told the simpler case about how matching an input phrase and calling the corresponding method is handled, and only after that told about phrases with commas;
22:50:59 <b_jonas> tell somewhere what character set the strings and vocabulary uses;
22:52:21 <b_jonas> maybe, before telling how a method, a class, and the list of properties is represented in the input, put an introduction telling what those things are for;
22:53:22 <b_jonas> in particular, mention that a method has an invocant which isn't listed in the argument list;
22:55:26 <b_jonas> and maybe call the "message number" of a method an "error message number" or something instead
22:55:47 <b_jonas> because it seems to be used for handling the error when a suitable object is not found;
22:56:03 <zzo38> Yes, that is what the "message number" does
22:57:59 <b_jonas> in the listing of tasks the main loop does, split "Parse the command." to two parts: find the method to invoke for the command, then find the arguments for that method from the command using selector methods.
22:58:31 <b_jonas> Because that really seems two steps to me.
23:00:56 -!- Patashu has joined.
23:02:03 <b_jonas> where you say "C rounding", does that mean the rule from old C (which allows two possibilities for some inputs) or modern C rounding from later standards?
23:02:42 <zzo38> I don't actually know.
23:04:03 <zzo38> OASYS was originally written in C++ though.
23:05:40 <b_jonas> um, when you say "You must invoke the selector method on each object of the class", how is the class determined?
23:06:20 <b_jonas> oh, is it determined from matching the class phrase?
23:06:29 <zzo38> O, it is determined by which class phrase it matches.
23:06:34 <zzo38> Yes, that is correct
23:07:08 <b_jonas> how does this matching work then if the class phrases are variable length and the method phrases can have object slot gaps and fixed words mixed in any order?
23:07:28 -!- oerjan has joined.
23:08:45 <zzo38> It works just by which matches, such as if "blue key" is a class phrase and "put <obj> in <obj>" is a method phrase, then "put blue key in blue key" will match. I don't know what else you meant?
23:09:29 <oerjan> @tell Gregor glogbot could need an NTP update hth
23:09:58 <b_jonas> zzo38: I mean what if there's an ambiguity, or at least a word occurs in many phrases? will the matcher backtrack to try all method phrases with all combinations of class phrases to find a match? that seems unlikely
23:10:31 <zzo38> I suppose it is implementation-defined, although it has to try to find the match.
23:10:53 <zzo38> My own implementation in BASIC does use backtracking though.
23:11:14 <zzo38> I have the C++ implementation too but don't remember how it works.
23:11:33 -!- variable has joined.
23:12:05 <b_jonas> then maybe mention that this is implementation-defined
23:13:10 <zzo38> As long as it gets the correct result it doesn't matter how it is implemented though.
23:13:40 <b_jonas> it can matter if there's an ambiguity, or if it doesn't always find the match
23:14:01 <b_jonas> it can even matter what error message you get
23:14:28 <zzo38> OK, I will try to figure it out
23:14:30 <b_jonas> like if you say "put red key in blue key" the error message could tell you it doesn't know about "red key" but the rest seems fine
23:15:01 <zzo38> The C++ implementation (as well as my BASIC implementation) will just print "I don't understand you." if that happens.
23:15:31 <b_jonas> I guess that's mostly enough because in this case "red" is likely not in the vocabulary
23:15:42 <b_jonas> a game like this will generally use single words when possible
23:15:54 <zzo38> If that's the case it will print "I don't understand the word 'red'." when that occurs.
23:16:10 <zzo38> But that's really an implementation detail anyways I suppose.
23:30:30 <oerjan> <TieSoul> mroman: I'm working on a lexer and parser system for arbitrary grammars <-- that's undecidable hth
23:30:59 <ais523> oerjan: you can just enter an infinite loop trying to decide
23:31:10 <ais523> I'm also working on a parser system, but currently only for LALR(1)
23:31:10 <oerjan> whether you are actually trying the impossible or just don't know about the chomsky hierarchy, i do not yet know.
23:31:51 <ais523> "arbitrary grammars" could mean type 1 I guess, for someone who doesn't realise what type 0 is?
23:32:38 <ais523> is type 2 decidable even if you allow an empty RHS?
23:33:07 <ais523> type 1 is decidable anyway just by brute force
23:33:29 <oerjan> type 1 is PSPACE, essentially
23:33:38 <oerjan> (equivalent in strenght)
23:33:45 <ais523> right, it doesn't look very computationally fast
23:34:09 <oerjan> type 2 is decidable in O(n^3)
23:34:32 <oerjan> well for a fixed grammar
23:35:07 <ais523> oerjan: right, the bison manual mentions that offhand
23:35:18 <ais523> and I forgot until you mentioned it
23:35:18 <oerjan> perhaps even including the grammar.
23:35:25 <ais523> huh, the post correspondence problem is neat
23:35:33 <oerjan> unambiguous type 2 in O(n^2)
23:35:42 <ais523> it's got to be possible to make an esolang out of that
23:35:49 <ais523> given that it's a simple undecidable problem
23:36:14 <ais523> oerjan: and LR(k) for any k in O(n), right?
23:36:15 <oerjan> and earley parsers gracefully get both of those as well as O(n) for LR(1)
23:36:50 <oerjan> LR(k) = LR(1) on language acceptance level
23:36:51 <ais523> something that amused me a lot is that the syntax yacc uses as input is LR(2) but not LR(1)
23:37:05 <ais523> the yacc-in-yacc in the POSIX standard gets around it by doing some of the parsing in the lexer, which is cheating
23:37:18 <oerjan> how did they manage that
23:37:31 <ais523> basically there doesn't have to be any delimiter between rules
23:37:45 <ais523> and an identifier is a rule LHS if it's followed by a colon, part of the RHS otherwise
23:38:03 <oerjan> "we'll make a parser generator that can parse any reasonable language, and then make its own language not fit" best idea
23:38:09 <ais523> when you see an identifier after a rule RHS, therefore, you have to reduce the RHS if there's a colon after it, shift the identifier otherwise
23:38:18 <ais523> = two symbols of lookahead
23:38:36 <ais523> *a colon after the identifier
23:39:20 <ais523> now I'm wondering if there's some crazy way to get it to be LR(1) anyway by rewriting the grammar with a bunch of intermediate steps
23:39:38 <ais523> isn't there some universal way to convert LR(2) to LR(1) and still match the same set of strings? just the structure of the grammar is all wrong
23:39:50 <oerjan> yes, that's what i implied above
23:40:08 <ais523> the POSIX standard's method of working around this is to define "identifier and a colon" as a separate token, which is really blatant cheating
23:42:13 <oerjan> maybe, it's still a regular language for the lexer
23:42:24 -!- Phantom_Hoover has quit (Read error: Connection reset by peer).
23:51:49 -!- Phantom_Hoover has joined.
23:55:36 <HackEgo> wisdom/zygohistomorphic-prepromorphism
23:56:00 <oerjan> `? zygohistomorphic-prepromorphism
23:56:00 <HackEgo> Zygohistomorphic-prepromorphism Used when you really need both semi-mutual recursion and history and to repeatedly apply a natural transformation as you get deeper into the functor
23:56:52 <oerjan> `learn A zygohistomorphic prepromorphism is used when you really need both semi-mutual recursion and history and to repeatedly apply a natural transformation as you get deeper into the functor.
23:56:57 <HackEgo> Learned 'zygohistomorphic': A zygohistomorphic prepromorphism is used when you really need both semi-mutual recursion and history and to repeatedly apply a natural transformation as you get deeper into the functor.
23:57:30 <oerjan> `` mv wisdom/zygohistomorphic{, prepromorphism}
23:57:31 <HackEgo> mv: cannot stat `wisdom/zygohistomorphic{,': No such file or directory
23:57:47 <oerjan> `` mv wisdom/zygohistomorphic{," prepromorphism"}
23:58:21 <HackEgo> wisdom/zygohistomorphic prepromorphism
23:58:44 * oerjan vaguely considers whether he could have done that more efficiently.
00:10:02 <orin> \me was going to repeat his assertion that any decent language should be parsable in o(n) time with o(n) space.
00:10:58 * boily suspects that orin has \ and / on the same key...
00:11:01 <orin> but obviously many widely used languages aren't
00:11:19 <oerjan> orin: well that certainly includes LR(1) languages
00:11:20 <boily> quintopia: today I slept!
00:12:02 <oerjan> or LR(k) for that matter
00:14:52 <ais523> hmm, what about INTERCAL before the fix that made it possible to parse
00:14:58 <ais523> IIRC that's type 2 but not LR(k) for any k
00:15:05 <ais523> also it's ambiguous, which doesn't help
00:16:08 -!- Phantom_Hoover has quit (Read error: Connection reset by peer).
00:16:10 <ais523> it takes some effort to construct an expression with two parses but you can do it
00:16:23 <coppro> ais523: does it involve rabbit ears and/or sparks?
00:17:38 <orin> I am fairly certain that Perl cannot be parsed.
00:17:57 <ais523> orin: actually Perl is parsed by YACC
00:18:14 <ais523> the only thing that's awkward is that Perl has a construct that runs as soon as it's parsed, and it can change the way that the rest of the file parses
00:18:19 <ais523> and you can put arbitrary TC stuff in there
00:18:35 <ais523> which makes parsing Perl undecidable, but in a rather mundane way
00:18:51 <oerjan> -!- magician has joined #esoteric. -!- Guest3780 has quit (Ping timeout: 252 seconds). -!- magician is now known as Guest3780. <-- I THINK E'S DOING IT WRONG HTH
00:18:55 <orin> Oh... so that's why only perl can parse perl
00:19:27 <orin> You need the whole language in the parser
00:19:47 -!- vodkode_ has joined.
00:21:28 <orin> I thought it just had an ambiguous grammar with a lot of cases that are settled in an arbitrary way
00:21:53 <orin> Or is that C++
00:23:34 <coppro> C++'s grammar is not ambiguous. It's not context-free. It's not even context-sensitive
00:23:49 <coppro> like Perl, parsing C++ is generally undecideable
00:25:56 <orin> Are templates turing-complete?
00:26:09 <oerjan> coppro: i think ambiguous is not inconsistent with undecidable hth
00:26:45 <orin> no wait they don't even need to be
00:27:19 <oerjan> in fact i think those are pretty orthogonal
00:28:00 <orin> You just need to be able to make one that takes O(n^2) or worse time to decide whether some token A is a type or a value,
00:28:06 <elliott> isn't template computation limited
00:28:14 <elliott> I can't imagine what else you could exploit for that
00:28:37 <olsner> there's usually a recursion limit on templates, but except for that I think they are TC
00:28:37 <elliott> how can you use it to mess with parsing?
00:29:00 <coppro> the limit is often "compiler's available memory" though
00:29:21 <olsner> as I understand it the "typename X" stuff is supposed to allow parsing to continue without template expansion
00:29:33 <coppro> olsner: right, but that only works inside a template
00:29:45 <elliott> coppro: can you show me an example of some C++ whose parsing does not terminate
00:30:32 <orin> So i guess that's me question. is it possible to make a C++ string which cannot be parsed in O(n) time
00:31:01 <coppro> template <bool B> struct foo { typedef int bar; }; template <> struct foo<false> { static int bar; }; void fail() { int i; { foo<does_TM_halt()>::bar * i; } }
00:33:29 <coppro> the clang testsuite includes a UTM written with constexpr
00:39:25 <elliott> it was more the implemention of does_TM_halt I was curious about, but
00:39:32 <elliott> I guess constexpr is just underrestricted?
00:39:45 <elliott> are you sure the standard doesn't specify some arbitrary implementation limit :p
00:39:49 <ais523> I think constexpr is just "do arbitrary stuff at compile time"
00:39:51 <elliott> (...are you sure C++ is actually TC)
00:41:53 <coppro> C++ is not directly TC at run time
00:42:22 <coppro> ais523: it wasn't intended to be TC; people who are bad at computer science theory were involved in the design and thought that they'd managed to make a version of constexpr which was powerful but not problematic.
00:42:28 <coppro> but it was actually TC
00:42:49 <ais523> powerful but sub-TC is a difficult line to walk
00:42:55 <coppro> C/C++ are not TC only due to the limitation in memory
00:42:58 <ais523> maybe aiming for primitive recursive is the best bet
00:43:24 <ais523> and C is potentially TC because of the file API, nothing in C limits files to any particular arbitrary size
00:43:37 <coppro> ah, right. But I mean without files.
00:43:59 <coppro> and you can sort of consider it in a meta approach
00:44:14 <coppro> where every time you get a memory error, you double the pointer size and retry
00:44:28 <ais523> VLAs and recursion let you allocate arbitrary amounts of memory up to the size of the largest integer or size_t, whichever is smaller
00:44:48 <ais523> actually you don't even really need recursion
00:51:14 <elliott> coppro: is constexpr really more TC than runtime C++
00:51:53 <ais523> not really, many languages are designed to require more power to compile than they do to run
00:52:11 <ais523> just not normally in the "undecidable vs. TC" sense
00:57:25 <pikhq> elliott: Well, C++ is straight TC because of templates too.
00:57:50 <elliott> so any portable C++ program can't use them to demonstrate TCness
00:58:16 <pikhq> Well yes, a C++ compiler can just bail on it. Alas.
00:58:46 <pikhq> But then a C compiler only has to handle a fairly small number of blocks.
01:24:06 <orin> pikhq: really, thy don't have to heandle arbitrary nesting depth?
01:26:09 -!- vodkode_ has quit (Ping timeout: 256 seconds).
01:52:38 -!- hjulle has quit (Ping timeout: 264 seconds).
01:56:55 -!- boily has quit (Quit: CARDINAL CHICKEN).
02:05:37 -!- longbyte1 has joined.
02:05:38 -!- longbyte1 has quit (Remote host closed the connection).
02:13:57 -!- orin has quit (Ping timeout: 246 seconds).
02:30:57 -!- orin has joined.
02:34:13 -!- vodkode_ has joined.
03:53:22 <zzo38> I remember that my grandfather once told me he would call the President on the telephone and tell him to remove the word "I don't want" from the dictionary. (And yet we both live in Canada, eh?)
03:56:13 -!- ais523 has quit (Read error: Connection reset by peer).
03:56:20 -!- ais523 has joined.
03:58:37 <Taneb> I don't think the president has any authority with the dictionary
03:59:48 <izabera> did you know that “( i+=2 < 3 )” means “( i+=(2 < 3) )” ?
04:00:55 <orin> assignment has very low precedence
04:01:15 <zzo38> Taneb: Yes, I know, that isn't his job
04:01:52 <izabera> i didn't... i just wrote a loop that never ended because of that >.>
04:03:50 -!- variable has quit (Ping timeout: 256 seconds).
04:04:17 <orin> Oh. yes, you can't replace i++ with i+=1 in the general case
04:04:21 <HackEgo> [wiki] [[Special:Log/newusers]] create * 0x0dea * New user account
04:04:37 -!- barrucadu has quit (Ping timeout: 265 seconds).
04:06:33 <orin> apparently it's Greek Orthodox Easter
04:07:00 <zzo38> O, I didn't know when Greek Orthodox Easter was this year; now I can know!
04:09:11 <orin> I can tell because outside the window, they are having a ceremony with candles and singing
04:10:05 <orin> and a lot of bell ringing
04:10:41 <orin> seems like they've gone inside now though
04:20:22 <HackEgo> [wiki] [[Beatnik]] http://esolangs.org/w/index.php?diff=42364&oldid=42363 * 0x0dea * (+419) Add alphabet program
04:20:41 -!- doesthiswork has quit (Quit: Leaving.).
04:30:04 <elliott> izabera: I think the problem here is that you wanted to write an expression like (i+=2) < 3 in the first place
04:31:43 <oerjan> it's not like it's undefined behavior
04:32:04 <orin> I was assuming in a while statement
04:32:27 <orin> like while(i++ < n)
04:32:45 <orin> he changed it to while(i+=2 < n) to go two at a time
04:33:03 <orin> and was surprised when it didn't work
04:34:14 <elliott> the pronouns people guess for some nicks will never cease to surprise me
04:36:44 <orin> interesting. i bet it changes when people are asked what pronoun they'd use as opposed to writing with out thinking
04:39:31 -!- dianne has joined.
04:39:43 <oerjan> we should ask dianne what his opinion is
04:41:34 <orin> Ok. dianne, do you think it's bad to write an expression like i += 2 < 3 in C?
04:42:26 <orin> This can be confusing because it means i += (2 < 3) instead of (i += 2) < 3
04:42:28 <Jafet> Someone's mistering the point here
04:43:17 <dianne> ah, I personally wouldn't put an assignment there at all, but I'd rather not argue code aesthetics
04:43:27 <Jafet> `cc main(i){while(i+=2<3);}
04:44:00 <HackEgo> #!/bin/sh \ echo "$@" > /tmp/a.c && gcc /tmp/a.c -o /tmp/a.out && /tmp/a.out
04:44:05 <orin> it probably looped around
04:44:55 <Jafet> `` echo 'main(i){while(i+=2<3);}' >/tmp/a.c && gcc -c -std=c99 -Wall -Wextra /tmp/a.c
04:44:58 <HackEgo> /tmp/a.c:1:1: warning: return type defaults to ‘int’ [enabled by default] \ /tmp/a.c: In function ‘main’: \ /tmp/a.c:1:1: warning: type of ‘i’ defaults to ‘int’ [enabled by default]
04:45:26 <Jafet> `` echo 'main(i){while(i&&i||i);}' >/tmp/a.c && gcc -c -std=c99 -Wall -Wextra /tmp/a.c
04:45:33 <HackEgo> /tmp/a.c:1:1: warning: return type defaults to ‘int’ [enabled by default] \ /tmp/a.c: In function ‘main’: \ /tmp/a.c:1:1: warning: type of ‘i’ defaults to ‘int’ [enabled by default] \ /tmp/a.c:1:1: warning: suggest parentheses around ‘&&’ within ‘||’ [-Wparentheses]
04:46:01 <dianne> um... also. I'm not a "he".
04:46:39 <orin> dianne: oerjan was making a joke because we were discussing how people guess pronouns
04:47:06 <orin> because I guessed "he" for "izabera" and I was wrong
04:48:08 <dianne> oh, alright. I'm not really bothered, was just a bit confused. since, well, I didn't really see how, with my name...
04:48:16 <ais523> I went a day without third-person pronouns once, just for fun
04:48:28 <ais523> it's quite doable, I don't think anyone even noticed how weird the sentence structure gets sometimes
04:48:46 <orin> ais523: In Japanese they don't really have them
04:49:11 <oerjan> ais523: did you use a script to make sure not to slip up?
04:49:14 <Taneb> ais523, I use third-person pronouns exclusively. You might think it is quite odd, but I find it fun
04:49:35 <ais523> oerjan: no, it was a spur-of-the-moment-thing
04:50:14 <orin> There's あの人 and あの奴 etc. but those are just phrases like "that person" or "that dude"
04:50:59 <ais523> IIRC Hungarian doesn't have gendered third-person pronouns? which is why b_jonas' pronoun usage is so weird on occasion?
04:51:30 <oerjan> i haven't noticed anything wrong with b_jonas's usage...
04:52:03 <oerjan> but yes, there's only ő
04:52:51 <elliott> finnish merges them all into "it", right?
04:53:32 <oerjan> elliott: apparently, no, wiktionary claims it's only for humans
04:53:44 <elliott> oklopol lied to me, I guess
04:54:44 <orin> Oh, right there is 彼 and 彼女 but you don't hear people say it often, because they also mean "boyfriend" and "girlfriend" respectivley
04:55:29 <orin> Which is really weird, that a pronoun can shift in meaning like that
04:58:55 -!- barrucadu has joined.
04:59:08 <izabera> http://shop.fsf.org/product/usb/ did you know they sell these?
04:59:45 <oerjan> the english and swedish wiktionaries disagree on whether hungarian ő includes "it"
04:59:56 <elliott> "they" as in USB RNGs in general, or the FSF specifically?
05:00:21 <izabera> i didn't know anyone sold these
05:00:24 <elliott> I mean, I knew that USB RNG things were a thing, but not that the FSF sold them.
05:03:10 <oerjan> (norwegian/swedish/danish have four third person pronouns, because in addition to "natural" gendered pronouns, the _inanimate_ pronouns have _grammatical_ gender.)
05:03:19 <Jafet> http://shop.fsf.org/product/stuffed-baby-gnu/
05:03:51 <izabera> stallman went to italy last september
05:03:57 <izabera> he auctioned a stuffed baby gnu
05:04:01 <oerjan> have you recovered yet?
05:04:05 <zzo38> Do they know speaking Italian?
05:04:09 <elliott> http://shop.fsf.org/category/stuffed-gnu/ lots of things in the stuffed gnus category
05:04:44 <izabera> well he did that saint ignucius thing :D
05:05:01 <oerjan> https://www.youtube.com/watch?v=YqgPyqyh4X4
05:05:05 <zzo38> If I want to go to Italy, I would want to learn speaking Italian though.
05:06:03 <izabera> well it was just a trip for a conference o_o
05:06:29 <izabera> i mean i'd like to visit japan eventually but i'm not going to spend 15 years learning japanese
05:07:55 <elliott> that's not very much dedication, izabera
05:08:16 <elliott> how will you understand what people are saying if you don't master japanese before going there
05:08:27 <izabera> my dedication stops at watching subbed anime <.<
05:08:39 <izabera> what's the plural of anime?
05:08:56 <elliott> is anyone fansubbing literal real life japan
05:09:09 <zzo38> I too watched some sub anime such as Kaiji
05:09:18 <elliott> I think it's "anime" if you don't want to be silly, "animes" if you do.
05:09:27 <elliott> (I guess pedantically it'd be "anime series" or something in the first place anyway.)
05:09:48 <oerjan> hm that video was about twice as long as necessary. although more topical than expected.
05:10:00 <Taneb> I am (somewhat half-heartedly, I admit) trying to learn Italian for a trip I am planning later this year
05:10:02 <zzo38> Do you like to watch Akagi and Kaiji?
05:10:39 <orin> I watch anime without subtitles sometimes... I'm not good at it yet so I have to keep rewinding
05:10:46 * izabera teaches Taneb all her italian: pizza pasta mamma mia
05:11:00 <Taneb> izabera, that is not much italian
05:11:15 <elliott> just kidding. that's spanish
05:11:19 <Taneb> elliott, that is less Italian
05:11:24 * oerjan swats elliott -----###
05:11:29 <elliott> spanish is at least 14% italian.
05:11:33 <orin> cappuccino espresso latte macchiatto
05:11:59 <oerjan> elliott: if boily were here you'd be in for a mapole as well.
05:12:01 <Taneb> Buongiorno, donne e uomini (I think)
05:12:05 <izabera> elliott: actually 90% of the italians share that opinion
05:12:23 <Taneb> elliott, Italian and Spanish are at times mutually intelligible
05:12:32 <elliott> izabera: I only say facts!! and true things
05:12:41 <izabera> Taneb: ciao ragazze e ragazzi
05:12:56 <Taneb> izabera, I am a very formal person, I sometimes even wear a tie
05:12:59 <elliott> you lied, none of those words are pizza, pasta, or mamma. or mia.
05:13:44 <elliott> I have never worn a tie in my entire life.
05:14:10 <orin> I have several ties, but I've mostly only worn them to operas
05:14:23 <orin> and weddings I guess
05:14:42 <izabera> well, on the good side, this channel makes me feel young
05:14:51 <izabera> on the bad side, this channel makes me feel too young
05:15:01 <elliott> Taneb is probably younger than you?
05:15:07 <elliott> well idk maybe Taneb is old now
05:15:13 <Taneb> I am younger than yu
05:15:24 <orin> izabera: I was born may 10 1993
05:15:33 <Taneb> I am also younger than orin
05:15:47 <elliott> am I still the youngest person here? that would be weirder now than when I was 11
05:16:06 <elliott> why have I been in this godforsaken channel for eight years
05:16:50 <orin> elliott: maybe you're a supergenius
05:16:52 <elliott> the former was true for a depressing number of years, more or less
05:17:10 <Taneb> elliott, there's a buffet by the mapole
05:17:19 <elliott> I don't go near the mapole.
05:18:27 <orin> anyway I have been to like at least 8 operas
05:18:48 <Taneb> That is like, 8, more operas than I have been to
05:18:54 <Taneb> I went to an Operetta once
05:18:58 <elliott> isn't cpressey older than you oerjan?
05:19:10 <Taneb> Isn't monqy younger than you, elliott?
05:19:30 <orin> izabera: no, you're not allowed to eat during an opera, eating is noisy
05:20:03 <elliott> Taneb: monqy was I think, yeah
05:21:16 <oerjan> if we're mentioning people who aren't _present_, i suspect Lil^WHe of a dozen names is also younger than elliott
05:21:56 <elliott> maybe one of the people joining for esoterica stuff for like five seconds was, like, 60
05:22:25 <oerjan> elliott: don't you remember that COBOL guy? he was older than me
05:22:47 <oerjan> btiggins or something like that
05:22:56 <elliott> wasn't Rugxlo or whatever his name was too
05:22:57 <izabera> i don't know cobol but i know sed and sed is older :(
05:23:00 <oerjan> (with different actual letters)
05:23:28 <oerjan> sed older than COBOL? i'm skeptical.
05:23:29 <elliott> just saying but I'm actually an immortal being who has been alive for ten thousand years and you're all whippersnappers
05:23:43 <izabera> sed is the oldest language on unix
05:23:43 <izabera> it's even older than unix actually
05:23:44 <Taneb> I thought I was the only one!
05:24:00 <Taneb> izabera, COBOL is, too
05:24:14 <Taneb> COBOL dates to 1959
05:24:26 <Taneb> And is considerably older than sed
05:25:13 <elliott> that's from 1958 theoretically
05:25:34 <elliott> kind of like saying you know BCPL because you know C though
05:25:40 <elliott> I use vim and know lisp :(
05:25:49 <oerjan> <Taneb> elliott, there's a buffet by the mapole <-- beware of the poutine
05:26:12 <Taneb> oerjan, what about the gazspacho?
05:26:41 <elliott> okay sometimes I use emacs but rarely
05:27:02 <Taneb> I know a little lisp but I am not very good at it
05:27:14 <Taneb> Ah, C-x C-c. the :wq of emacs
05:28:20 <oerjan> Taneb: that tastes szupérb
05:29:39 <oerjan> Taneb: i don't understand why they teach :wq instead of :x
05:29:51 <Taneb> oerjan, I don't use vim, I am afraid
05:30:52 <izabera> if you guys use bash and its vi mode, you may like this
05:30:55 <izabera> alias :{x,{,w}q}{,a}=exit :e=vim :h=man info='info --vi-keys'
05:31:29 <izabera> so that you can type :wq in your shell to exit
05:31:30 <elliott> do you ever :wqa bash as opposed to just :qing it
05:32:15 <izabera> it's just a musclar reflex at this point
05:33:08 <elliott> http://shop.fsf.org/product/gnu-emacs-reference-mugs/ http://shop.fsf.org/product/signed-rms-photo-print/
05:39:53 <zzo38> I am not one million years old
05:43:08 <ais523> now I'm wondering if C-x C-c works in bash
05:43:11 <ais523> it knows a lot of Emacs bindings
05:43:51 <Taneb> zzo38, very few people are
05:45:18 -!- mbrcknl_ has joined.
05:46:02 <izabera> binding C-c in bash is kinda hard since stty gets in the way
05:46:08 -!- edwardk_ has joined.
05:48:58 <izabera> this does the job... stty intr ''; bind -x '"\C-x\C-c":exit'
05:49:21 <izabera> i can't make it work without unsetting it for stty :\
05:50:13 <zzo38> Did you ever win a Ig Nobel prize for proving that it is impossible to use complex numbers in accounting?
05:52:06 -!- sebbu has quit (*.net *.split).
05:52:09 -!- mbrcknl has quit (*.net *.split).
05:52:09 -!- skarn has quit (*.net *.split).
05:52:10 -!- edwardk has quit (*.net *.split).
05:52:10 -!- skarn_ has joined.
05:54:19 -!- mbrcknl_ has changed nick to mbrcknl.
05:55:16 <elliott> right after you learn japanese
05:55:21 <zzo38> I had proven such thing, but now I forgot how. Nevertheless it isn't what I was trying to do; I was trying to figure out how to use complex numbers in accounting, but instead I concluded it is impossible and also invented matrix accounting too due to that. It is possible to try to make one thing but you can make something else instead.
05:55:31 -!- edwardk_ has changed nick to edwardk.
06:25:16 -!- Sprocklem has quit (Ping timeout: 246 seconds).
06:31:33 -!- zadock has joined.
06:49:55 -!- Patashu has quit (Ping timeout: 265 seconds).
06:59:06 -!- CADD has quit (Ping timeout: 265 seconds).
06:59:44 -!- copumpkin has quit (Quit: My MacBook Pro has gone to sleep. ZZZzzz…).
07:00:34 <HackEgo> [wiki] [[Beatnik]] http://esolangs.org/w/index.php?diff=42365&oldid=42364 * 0x0dea * (+327) Add infinite loop example
07:26:00 -!- zadock has quit (Ping timeout: 256 seconds).
07:40:56 <myname> "13 Pop a number and skip ahead n (actually n+1) words if the number is zero."
07:42:03 -!- sebbu has joined.
07:42:42 -!- sebbu has quit (Changing host).
07:42:42 -!- sebbu has joined.
07:44:53 <myname> but what is n if it's not "the number"
07:46:26 <oerjan> the one thing i can think of is that possibly he means the +1 to be the "normal" word increment after any instruction
07:47:07 * oerjan paranoidly checks author name, whew looks male
07:47:18 <myname> yeah, but as i said: that's not what bothers me
07:47:35 <myname> i don't get what the hell n is
07:47:59 <myname> if n is in fact "the number", 13 is just a nop
07:48:25 <oerjan> "Note that the commands corresponding to values 5, 13, 14, 15, and 16 each read an extra word and use it as a parameter (then skip it)."
07:48:48 <oerjan> maybe it's that skip that's the +1, then
07:50:45 <oerjan> hm "but it ought to be able to simulate any Push-down automaton"
07:51:45 <oerjan> i'm suspicious that it might not be able to do sufficiently complicated flow control because the size limits also affect jump distance
07:53:23 <oerjan> well in this case, the max scrabble score, i guess
07:54:00 <myname> the examples mad3 me think you could do arbitrary long words
07:54:35 <myname> but longer programs might not quite look like real sentences
07:54:55 <oerjan> hm the interpreter doesn't enforce dictionary words
07:55:09 <oerjan> but the examples are, aren't they?
07:55:38 <myname> what you _could_ do is jumping backwards to a position that jumps backwards
07:56:26 <myname> you just have to jump over them if you read forward
07:56:46 <oerjan> yes, but you'd get a traffic jam, essentially, if you had too many paths
07:58:01 <myname> but i am not quite sure if this is really not tc
07:58:26 <oerjan> tc it is not. there is no infinite memory other than the stack.
07:58:40 <oerjan> the question is whether you can get all pushdown automata.
07:59:13 <myname> 8 is , and 9 is .; 5 1 7 is + and 5 1 10 is -
07:59:54 <myname> [ and ] _should_ be able to translate into 13-16
07:59:54 <j-bot> myname: |ill-formed number
08:00:03 <myname> the problem is > and <
08:00:16 <myname> if you had a second stack, it could be tc
08:00:31 <oerjan> oh for the other size limit, "and since data items are finite (integers from 0 to 255)"
08:00:58 <myname> well, that holds true to bf too, doesn't it?
08:01:58 <oerjan> but the thing is, without a cell limit you don't need unlimited number of cells
08:02:07 <myname> isn't .,+-[] enough for a push-down automaton?
08:03:06 <oerjan> but you don't have general [] if you don't have arbitrary long words
08:03:14 <oerjan> if you do, then probably.
08:06:01 <oerjan> http://cliffle.com/esoterica/beatnik.html looks a bit different from the esolang description
08:06:31 <oerjan> and explains your original question clearly
08:08:08 <myname> i like the second paragraph
08:14:37 -!- MoALTz has joined.
08:22:10 -!- dianne has quit (Quit: byeannes).
08:22:26 <HackEgo> [wiki] [[Beatnik]] http://esolangs.org/w/index.php?diff=42366&oldid=42365 * Oerjan * (+189) /* Computational class */ Quibble on PDA
09:00:38 -!- Phantom_Hoover has joined.
09:06:13 -!- roman2 has joined.
09:06:20 <roman2> fnord morning everybody
09:07:09 -!- vodkode_ has quit (Remote host closed the connection).
09:11:38 <b_jonas> ais523: in ayacc, consider making it possible to have multiple start symbols to choose from when you start the parser, at least in the non-compatibility interface? I believe currently you have to emulate that by injecting an extra terminal symbol at the start from the tokenizer, which is fine for theory but ugly.
09:12:00 <ais523> it shouldn't be too hard to implement, at least
09:12:31 <ais523> the problem is that that would require some sort of syntax extension, or else to compile all possible start symbols
09:13:01 <b_jonas> the syntax extension could be a new declaration type
09:13:15 <b_jonas> or even just multiple copies of %start declarations
09:13:39 <b_jonas> it's not clear how you'd decide from them in the C entrance interface
09:16:45 <b_jonas> of course, all these extra features are less important. the most important thing is that ayacc should always generate correct output, even for unusual grammars.
09:18:00 -!- zadock has joined.
09:18:20 -!- ais523 has quit (Read error: Connection reset by peer).
09:18:31 -!- ais523 has joined.
09:20:28 <b_jonas> if it can do that, than this will probably already be worth to use over bison
09:20:36 <HackEgo> [wiki] [[User:Rdococ/Esolangs]] M http://esolangs.org/w/index.php?diff=42367&oldid=22963 * Rdococ * (+129) Updated user page.
09:22:45 <b_jonas> ais523: oh by the way, how will the license of this work? if I have a constant grammar, can I put the C code output under public domain?
09:23:11 <b_jonas> and is the generated C code output portable, not depending on specifics of the system, so this can be done usefully?
09:23:32 <ais523> b_jonas: unlike flex, the output is going to be direct-coded and have hardly any verbatim copies from the input file
09:23:44 <ais523> so the output will probably be licensed the same way as the input
09:24:37 <b_jonas> (even if it does have verbatim copies from a template, that template could be in public domain while ayacc as a whole is licensed differently. that's how autotools works I think.)
09:25:36 -!- hjulle has joined.
09:25:45 <ais523> autotools works vaguely like that but unnecessarily complicated, I think
09:29:24 <nortti> 07:54 < elliott> finnish merges them all into "it", right? ← well, kinda. there's hän which is only for humans and se which is for everything
09:29:42 <nortti> generally using se for humans is less formal
09:34:24 <ais523> incidentally, normal parsing theory seems to make a distinction between shift actions and goto actions
09:34:33 <ais523> I consider them to be the same, and they are in many cases
09:34:40 <ais523> but added a few of my own for optimization purposes
09:34:50 <ais523> shift_and_reduce actions, degenerate reduce actions, cast actions
09:35:19 <ais523> and indirect actions, which basically just combine the common code of two states that are almost but not quite identical
09:35:37 <b_jonas> wow, so many optimizations
09:35:48 <b_jonas> now you'll need a big testsuite for this, which isn't easy
09:37:18 <ais523> I'm using C-INTERCAL ;-)
09:37:35 <ais523> also, it seems that there's a name for the sort of implementation I'm using: https://en.wikipedia.org/wiki/Recursive_ascent_parser
09:37:48 <ais523> but the optimizations make it look less messy than what's shown there
09:38:18 <b_jonas> oh, C-intercal is a nice idea
09:38:34 <ais523> INTERCAL is a pain to parse
09:38:39 <ais523> so it makes for a good parser testsuite
09:38:50 <b_jonas> um yes, but some of that pain is in the lexer, isn't it?
09:38:57 <b_jonas> or the non-yacc part in general
09:40:32 <ais523> the only help the grammar needs from the lexer is to identify whether a spark/ears is necessarily opening, or could be closing
09:41:43 <ais523> (in the case of "could be closing", it's assumed that it isn't ever opening; this is the hack that removes ambiguity and makes the language LALR(1) in the first place, and it's mentioned in the INTERCAL-72 manual)
09:42:41 <b_jonas> don't you have to disambiguate between overlapping keywords like DO NOT GIVE UPLEASE ,3 <- #0
09:43:31 <ais523> possibly technically we have to, but we don't currently
09:46:01 <ais523> oh, btw, here's a sample warning message:
09:46:07 <ais523> ayacc: warning: shift/reduce conflict on symbol ELSE at t.y line 8
09:46:08 <ais523> ayacc: info: conflict is reached after, e.g., IF expr THEN IF expr THEN stmt . ELSE
09:46:10 <ais523> ayacc: info: to resolve the conflict: specify a precedence for ELSE and THEN
09:46:18 <ais523> so much better than bison :-)
09:46:57 <HackEgo> [wiki] [[Folder]] N http://esolangs.org/w/index.php?oldid=42368 * Rdococ * (+1274) New esolang!
09:47:10 <b_jonas> does posix yacc or bison or ayacc guarantee to not read the lookahead token if you can decide which rule to run without the lookahead?
09:47:42 <ais523> the example is sometimes badly wrong in the case of a reduce/reduce conflict, but that's because due to deficiencies of LALR(1), sometimes there is no example and the conflict's completely spurious
09:48:15 <ais523> and yes, there's a guarantee to not read into the lookahead token if the current state unconditionally reduces and always by the same rule
09:48:18 <b_jonas> that's when the grammar is LR(1) but not LALR(1)
09:48:20 <ais523> although I'm optimizing those states out entirely
09:48:24 <HackEgo> [wiki] [[User:Rdococ/Esolangs]] M http://esolangs.org/w/index.php?diff=42369&oldid=42367 * Rdococ * (-46)
09:48:28 <ais523> that's what a shift_then_reduce action is for
09:48:44 <ais523> because you aren't reading the lookahead token anyway, no need to actually run the logic of the state in question
09:48:47 <b_jonas> ais523: good, but guarantee in what? posix yacc too, or only ayacc?
09:48:52 <ais523> guarantee in posix yacc
09:49:51 <ais523> took me a while to find where it says that (it's near the end), but it does
09:50:02 <ais523> I assume that guarantee exists because it's practically useful
09:50:06 <ais523> because it does make things less consistent
09:50:27 <ais523> you'd think rules would prefer to know that the lookahead token had always been read, rather than sometimes being read and sometimes not
09:50:38 <b_jonas> yes, it's practically useful, both for reading interactive input, and for crazy stuff like that seeking tokenizer I've shown yesterday
09:50:40 <HackEgo> [wiki] [[User:Rdococ]] M http://esolangs.org/w/index.php?diff=42370&oldid=40356 * Rdococ * (+121)
09:50:54 <b_jonas> (actually just a head seeking in the tokenized stream)
09:51:08 <b_jonas> and no, I wouldn't prefer it always read
09:51:29 <b_jonas> (that would be even worse in that hypothetical LALR(2) mode)
09:51:34 -!- rdococ has joined.
09:51:55 <b_jonas> that would just lead to kludges like emitting two tokens when a newline is read interactively
09:55:10 <rdococ> uh... I have an article about an esolang -- it explains everything while being a really short stub... what should I do?
09:56:18 <ais523> post it anyway and put {{stub}} at the start
09:56:32 <ais523> unless the esolang is the sort of esolang that's impossible to spend more than a couple of sentences describing
09:56:38 <ais523> in which case it should probably be on the joke languages list
09:57:06 <rdococ> it's possible to program in, it's equivalent to a finite state automaton. However, it does only take a couple of sentences to describe it.
09:57:19 <rdococ> should I add it to the joke language list anyway?
09:57:35 <rdococ> I'm pretty sure 'joke' means something other than just 'really short stub'...
09:57:43 <rdococ> anyway, I'm rambling now, thanks
09:58:13 <ais523> if it's possible to program in, it's not a joke
09:58:14 <b_jonas> rdococ: maybe add some example programs to make it longer?
09:58:20 <HackEgo> [wiki] [[Folder]] M http://esolangs.org/w/index.php?diff=42371&oldid=42368 * Rdococ * (+9)
09:58:22 <ais523> or well, if it's possible to program in /and/ possible to implement
09:58:42 <rdococ> it's a bit like Text in the fact it's already implemented.
09:58:42 <b_jonas> oh yeah, add an implementation too
09:58:44 <ais523> note that this is sufficient to not be a joke, but not necessary, some non-joke languages would be hard or impossible to program in
09:59:36 <rdococ> you know Text, where there are already programs to interpret it? well my esolang is like that, but it's got better computation power.
09:59:51 <rdococ> *not saying it's better, I should've reworded that
10:00:03 <ais523> Text probably counts as a joke
10:00:31 <b_jonas> rdococ: then add links to implementations to the description of the language
10:00:32 <rdococ> I don't think mine is a joke... not too much of one, anyway
10:01:34 <rdococ> b_jonas: but the point is, everyone already has an implementation - the language's like Text in that way
10:02:00 <rdococ> Text -> most OSes already have an implementation. Folder -> same thing.
10:04:50 <HackEgo> [wiki] [[Beatnik]] http://esolangs.org/w/index.php?diff=42372&oldid=42366 * Oerjan * (-175) I convinced myself I was wrong about unlimited word length being needed
10:16:58 -!- ais523 has quit (Read error: Connection reset by peer).
10:16:58 -!- callforjudgement has joined.
10:17:02 -!- Patashu has joined.
10:17:30 <HackEgo> [wiki] [[Folder]] M http://esolangs.org/w/index.php?diff=42373&oldid=42371 * Rdococ * (+10) Some people have to double-click to open stuff, so 'any user can click one of the transitions' is technically incorrect and might cause confusion.
10:19:08 <callforjudgement> at that point, it's basically just a funky encoding for an FSM, or is it a PDA?
10:19:56 -!- callforjudgement has changed nick to ais523.
10:20:04 <ais523> rdococ: actually this is much more complex than it looks
10:20:31 <ais523> because symlinks don't work quite the same way as shortcuts, and I think it may make a difference to computational power
10:20:46 <rdococ> to be honest, I've never heard of symlinks.
10:20:53 <rdococ> but continue, I'm intrigued.
10:21:17 <ais523> well, a "shortcut" isn't a filesystem feature, it's a feature of the Windows graphical shell
10:21:49 <ais523> and when you follow a shortcut, Explorer opens up a specific file or directory or other shell object for you (the internal name is "shell links")
10:22:08 <ais523> a symlink, meanwhile, is a filesystem feature, it basically forms an asymmetrical alias
10:22:42 <b_jonas> ais523: why is it a difference in computational power; and the shell can treat symlinks in at least two ways in some operations I think
10:23:21 <ais523> e.g. if I create a symlink "a" pointing at "../b/c" in "/d/e", then "/d/e/a" is a different name for the same file as "/d/b/c"
10:23:31 <ais523> however, the two names are treated as distinct for some purposes
10:23:50 <ais523> and knowing what those purposes are is probably important to know if this is an FSM or PDA, and I can't remember offhnad
10:24:16 <ais523> b_jonas: basically, you can't construct unboundedly long paths with shortcuts
10:24:34 <ais523> so the PDAness is based on whether there's some way to /read/ the path using only the basic operation of Folder
10:25:18 <ais523> or, I mean, it's above FSM because you can just use shortcuts to .. to do bracket matching
10:25:27 <ais523> but I'm not sure if you get an actual PDA stack, or just a coutner
10:25:40 <ais523> I'm leaning towards PDA at this point
10:25:54 <ais523> rdococ: given a string consisting only of ( and ) characters, determine whether they match correctly
10:26:05 <ais523> an FSM can't do that, but it's trivial for almost any PDA implementation
10:26:13 <rdococ> so you're saying my esolang could be a PDA instead of an FSM?
10:26:19 <ais523> but it may depend on the oS
10:26:27 <rdococ> well this is interesting
10:26:36 <ais523> proving languages that people think are FSMs are actually PDAs is one of my hobbies
10:26:42 <ais523> e.g. Keymaker-Splinter
10:27:03 <rdococ> are you entirely sure, or is it going to be controversial?
10:27:12 <b_jonas> hehe “< ais523> proving languages that people think are FSMs are actually PDAs is one of my hobbies”
10:27:21 <b_jonas> can we add this to a quotation bot?
10:27:35 <b_jonas> I don't see why it would be a PDA though
10:27:37 <ais523> rdococ: I'm not 100% sure
10:27:53 <ais523> I currently think it's more than 50% likely but can't be much more confident than that
10:28:09 <ais523> but this is mostly based on deficiencies in my understanding of symlinks, rather than in my understanding of PDAs
10:28:16 <Taneb> <pedantic> I don't think languages can be FSMs or PDAs. They can be capable of expressing FSMs or PDAs, sure, but a language is not a program</pedantic>
10:28:20 <ais523> directory hardlinks add an extra layer of complication
10:28:29 <ais523> Taneb: I elided "equivalent in power to"
10:29:32 -!- copumpkin has joined.
10:29:43 <rdococ> what if I use shortcuts only?
10:29:47 <b_jonas> but directory hardlinks shouldn't exist
10:32:47 <rdococ> ais523: what's your username on the wiki? I want to credit you on the talk page
10:34:31 <b_jonas> I still don't see how it could be more powerful than a fsm.
10:34:31 <rdococ> should I call you a he or a she?
10:35:03 <FireFly> Speaking of symlink-related computing, http://www.linusakesson.net/programming/symlinks/index.php
10:35:05 <Phantom_Hoover> i was about to say 'his name is alex, so...' and then i realised that doesn't help at all
10:35:16 <rdococ> if it could do the stuff a PDA can do, I wonder if it could combine the computational power of both.
10:35:54 <rdococ> from what I think, he might be male. But maybe that's just a cultural bias, and I don't really mind.
10:36:08 <rdococ> maybe I should use the singular 'they'
10:40:06 <HackEgo> [wiki] [[Talk:Folder]] N http://esolangs.org/w/index.php?oldid=42374 * Rdococ * (+376) My esolang is more interesting now, I guess...?
10:43:14 -!- oerjan has quit (Quit: Something).
10:45:15 <HackEgo> [wiki] [[Folder]] http://esolangs.org/w/index.php?diff=42375&oldid=42373 * Rdococ * (+586) Updated definition a bit, updated computational class.
10:46:09 <HackEgo> [wiki] [[Folder]] M http://esolangs.org/w/index.php?diff=42376&oldid=42375 * Rdococ * (+0) Fixed incorrect link.
10:47:28 <ais523> rdococ: I tend not to use gendered pronouns when talking about myself in the third person
10:47:40 <ais523> but yes, my gender is possibly too well-known by now
10:48:48 <rdococ> usually I'm not that fussed about revealing my gender...
10:49:47 <b_jonas> when do you talk about yourself in third person? writing a cv or something?
10:50:01 * ais523 talks about themself in the third person
10:50:35 <b_jonas> oh, so self-referencing statements
10:50:54 <shachaf> "talking about myself" tends to be self-referencing.
10:53:07 <rdococ> wait... can't you add flags to a shortcut link like -r for shutdown - atleast in windows?
10:54:10 <rdococ> (ik it's not limited to shortcuts, but it sounds interesting)
10:54:56 <ais523> rdococ: you can, because Windows shortcuts are kind-of complex
10:55:01 <ais523> and badly designed in many ways, too
10:55:47 <b_jonas> well, they're sort of a carry-on from windows 95, and in some ways maybe even from windows 3.1
10:55:58 <b_jonas> they probably made sense back then
10:56:03 <rdococ> huh... does that add any extra computational power or can you just emulate the behavior in an FSA?
10:56:29 -!- Koen_ has joined.
10:57:07 -!- nszceta has joined.
11:01:21 <rdococ> I still don't know what 'use shortcuts to do bracket matching' means
11:05:27 -!- rdococ has quit (Ping timeout: 246 seconds).
11:09:41 -!- rdococ has joined.
11:12:48 -!- zadock has quit (Ping timeout: 264 seconds).
11:13:20 <Koen_> rdococ: maybe set your text editor up to automatically insert a matching ')' after the cursor when you type '('
11:14:38 -!- vodkode_ has joined.
11:18:05 <Koen_> I don't know that would be a shortcut
11:20:02 <HackEgo> [wiki] [[Folder]] M http://esolangs.org/w/index.php?diff=42377&oldid=42376 * Rdococ * (-387) Simplified explanation a little
11:20:30 <rdococ> huh? chrome messed up on me, so I can't see the chat history
11:20:42 <rdococ> still don't know what you mean
11:21:52 <rdococ> anyway, do you know if my programming language is a FSA or a PDA?
11:25:35 -!- zadock has joined.
11:36:03 -!- zadock has quit (Ping timeout: 265 seconds).
11:44:14 <orin> Any tips on draining an ocean
11:46:05 <orin> I guess I need to have as much drain bandwidth as there is water coming in?
11:46:33 <izabera> orin: don't rush it, start slowly, then speed up but not much
11:47:16 -!- AndoDaan has joined.
11:47:33 -!- AndoDaan has left.
11:48:15 -!- AndoDaan has joined.
11:48:19 <orin> I'm trrying to drain an underground ocean to get at some rare minerals
11:48:34 -!- zadock has joined.
11:52:12 -!- yump has joined.
11:53:43 -!- yump has quit (Client Quit).
11:57:43 <Phantom_Hoover> orin, cavern lakes fill from any open tiles at the edge of the map
11:57:54 <Phantom_Hoover> draining them entirely is very hard and will kill your fps
11:58:14 <Phantom_Hoover> probably the most practical way of making an area accessible is to pour magma over it
11:59:18 -!- zadock has quit (Ping timeout: 250 seconds).
12:00:58 -!- vodkode_ has quit (Ping timeout: 256 seconds).
12:01:57 -!- AndoDaan has quit (Ping timeout: 256 seconds).
12:09:45 <HackEgo> [wiki] [[Hello world program in esoteric languages]] http://esolangs.org/w/index.php?diff=42378&oldid=42362 * SuperJedi224 * (+263)
12:12:23 -!- zadock has joined.
12:14:34 -!- Patashu has quit (Quit: Soundcloud (Famitracker Chiptunes): http://www.soundcloud.com/patashu MSN: Patashu@hotmail.com , AIM: Patashu0 , YIM: patashu2 , Skype: patashu0 .).
12:21:00 <HackEgo> [wiki] [[Folder]] M http://esolangs.org/w/index.php?diff=42379&oldid=42377 * Rdococ * (-35) Not sure, with the requirements and specifications, that the argument for PDA holds. However, there's still discussion.
12:21:56 <HackEgo> [wiki] [[Talk:Folder]] M http://esolangs.org/w/index.php?diff=42380&oldid=42374 * Rdococ * (+17)
12:21:57 -!- zadock has quit (Ping timeout: 256 seconds).
12:25:30 <HackEgo> [wiki] [[Talk:Folder]] http://esolangs.org/w/index.php?diff=42381&oldid=42380 * Rdococ * (-137) Rewritten the talk message
12:27:23 <HackEgo> [wiki] [[Folder]] M http://esolangs.org/w/index.php?diff=42382&oldid=42379 * Rdococ * (+0) capitalized 'F' in 'Folder program' and 'Folder programming language'
12:33:06 <HackEgo> [wiki] [[Folder]] M http://esolangs.org/w/index.php?diff=42383&oldid=42382 * Rdococ * (+92) Changes to the computational class section
12:34:00 <HackEgo> [wiki] [[Folder]] M http://esolangs.org/w/index.php?diff=42384&oldid=42383 * Rdococ * (+0) Minor change to the link to the talk page.
12:34:38 -!- zadock has joined.
12:46:12 -!- zadock has quit (Ping timeout: 252 seconds).
12:50:15 <b_jonas> “probably the most practical way of making an area accessible is to pour magma over it” -- hehe, sounds strange
12:57:44 -!- izabera has changed nick to greybera.
12:58:47 -!- zadock has joined.
13:02:21 -!- idris-bot has quit (Ping timeout: 245 seconds).
13:02:51 -!- Melvar has quit (Ping timeout: 264 seconds).
13:09:16 <ais523> b_jonas: dwarf fortress?
13:10:18 -!- zadock has quit (Ping timeout: 265 seconds).
13:11:10 -!- Melvar has joined.
13:11:41 -!- idris-bot has joined.
13:12:50 -!- greybera has changed nick to izabera.
13:18:57 <fizzie> "The Black Buoy has been painted yellow to avoid collisions."
13:19:28 <fizzie> Still called the Black Buoy, apparently.
13:20:37 -!- ais523 has quit (Read error: Connection reset by peer).
13:20:45 -!- ais523 has joined.
13:23:20 <orin> Well, it's going well so far. I haven't got down to magma yet, so I'm digging large width drainage channels
13:24:41 <orin> Later if I get magma, I'll pour it over the edges where the water comes in, so I can excavate more
13:27:09 <orin> So far some of the seabed is at 1-2
13:29:58 <orin> The next one I'm opening is 15 squares wide
13:32:22 -!- dianne has joined.
13:36:44 <orin> (that is, the entring wter is 15 wide, so the drain needs to be nearby and 15 wide)
13:38:42 -!- nszceta has quit (Quit: Textual IRC Client: www.textualapp.com).
13:39:53 -!- nszceta has joined.
13:42:30 -!- ais523 has quit.
13:43:39 <orin> I guess if magma is !!SCIENCE!! then what I'm doing is !!ENGINEERING!!
13:49:47 <orin> Anyway if all goes well I'll soon have acess to a green ore called "garnierite" which I assume can be smelted into shampoo
13:55:15 -!- copumpkin has quit (Quit: My MacBook Pro has gone to sleep. ZZZzzz…).
13:59:57 <orin> http://snag.gy/gHJOc.jpg
14:01:55 <HackEgo> [wiki] [[User talk:Esowiki201529A]] http://esolangs.org/w/index.php?diff=42385&oldid=41658 * Esowiki201529A * (+41) /* vandalismScript */ new section
14:04:00 <HackEgo> [wiki] [[User talk:Esowiki201529A]] http://esolangs.org/w/index.php?diff=42386&oldid=42385 * Esowiki201529A * (+45) /* vandalismScript */
14:08:02 <HackEgo> [wiki] [[User talk:Esowiki201529A]] http://esolangs.org/w/index.php?diff=42387&oldid=42386 * 101.226.125.113 * (+150) /* VandalismScript */
14:11:54 <HackEgo> [wiki] [[User talk:Esowiki201529A]] http://esolangs.org/w/index.php?diff=42388&oldid=42387 * Esowiki201529A * (+0) /* Hello, World */
14:17:02 <HackEgo> [wiki] [[User talk:Esowiki201529A]] http://esolangs.org/w/index.php?diff=42389&oldid=42388 * Esowiki201529A * (+36) /* VandalismScript */
14:22:44 <HackEgo> [wiki] [[User talk:Esowiki201529A]] http://esolangs.org/w/index.php?diff=42390&oldid=42389 * Esowiki201529A * (+28) /* Cat Program */
14:26:56 <HackEgo> [wiki] [[User talk:Esowiki201529A]] http://esolangs.org/w/index.php?diff=42391&oldid=42390 * Esowiki201529A * (+14) /* Hello, World! */
14:36:45 <HackEgo> [wiki] [[Folder]] http://esolangs.org/w/index.php?diff=42392&oldid=42384 * Esowiki201529A * (-1528) 命名冲突
14:40:03 <HackEgo> [wiki] [[Folder]] http://esolangs.org/w/index.php?diff=42393&oldid=42392 * Esowiki201529A * (+1528) Undo revision 42392 by [[Special:Contributions/Esowiki201529A|Esowiki201529A]] ([[User talk:Esowiki201529A|talk]])
14:49:52 -!- bixnode has quit (Ping timeout: 276 seconds).
14:53:56 -!- EVANGELIS has joined.
14:57:45 -!- EVANGELIS has left.
15:10:22 -!- codeitagile has joined.
15:40:52 -!- copumpkin has joined.
15:52:58 -!- GeekDude has joined.
16:21:45 <HackEgo> [wiki] [[Hexadecimal Stacking Pseudo-Assembly Language]] http://esolangs.org/w/index.php?diff=42394&oldid=42339 * 0x0dea * (+236) Add Ruby interpreter
16:35:54 <orin> Forensic I.T.! My mother lost a ring, so I pointed out we can tell when she lost it by looking at her numreous facebook pictures
16:38:22 <rdococ> !!! wut, some vandal deleted my article and put it back?
16:41:23 <rdococ> I translated the weird comment on the person that deleted the stuff on my article. Translated, it's "Naming conflicts"... Was he meaning to make a language called 'Folder' too?!
16:47:39 <FireFly> I wouldn't worry about it... maybe it was a mistake
16:50:15 <elliott> esowiki201529a makes a lot of weird edits
16:50:41 <elliott> I'm not sure what they're doing.
16:51:03 <elliott> they don't seem to be an obvious vandal. maybe just a non-native speaker with some weird ideas about the wiki >_>
16:51:33 <rdococ> what's that emote at the end for?!
16:51:51 <rdococ> it's not his fault he's a foreign speaker
16:52:00 <elliott> I didn't mean to imply that, sorry.
16:52:41 <elliott> it was more a >_> of "they tried to rename my language out of the blue by editing the page and moving it once" :P
16:53:38 <elliott> (I also didn't think that they might be a non-native speaker before that edit, since all their previous edits were in English if anything.)
16:57:51 <elliott> I suspect the "naming conflict" thing was pointing out that there was already a language called "Folder", anyway.
16:59:04 <b_jonas> I don't think there's a uniqueness requirement for esolang names.
16:59:18 <rdococ> oh right... 'Folders'...
16:59:59 <rdococ> they're pretty different... but this is interestin
17:04:45 <rdococ> well that's certainly interesting
17:09:20 <HackEgo> [wiki] [[Folder]] M http://esolangs.org/w/index.php?diff=42395&oldid=42393 * Rdococ * (+24) added distinguish tag because of naming conflicts
17:11:10 <HackEgo> [wiki] [[Folder]] M http://esolangs.org/w/index.php?diff=42396&oldid=42395 * Rdococ * (+19) So there's no distinguish tag...
17:15:04 -!- copumpkin has quit (Ping timeout: 244 seconds).
17:15:50 -!- codeitagile has quit (Remote host closed the connection).
17:16:42 <rdococ> uh... is that 'not to be confused with' necessary?
17:21:30 -!- copumpkin has joined.
17:22:16 <HackEgo> [wiki] [[POGAACK]] http://esolangs.org/w/index.php?diff=42397&oldid=41281 * 92.81.166.144 * (+31)
17:29:38 <elliott> it doesn't hurt and might be useful but if you really don't want it there you can remove it
17:30:03 <elliott> I guess it could be confusing because they both have broadly similar concepts.
17:35:20 <HackEgo> [wiki] [[Folder]] M http://esolangs.org/w/index.php?diff=42398&oldid=42396 * Rdococ * (-43)
17:35:38 <rdococ> probably should've done some kind of undo function
17:35:47 <rdococ> if there is one, but nevermind
17:36:52 <rdococ> I have an idea... File!
17:38:49 -!- nszceta has quit (Quit: Textual IRC Client: www.textualapp.com).
18:03:04 <orin> History book titles from the future
18:04:05 <rdococ> Folder is such an easy programming language... now I just need a hard one
18:04:09 <orin> ``Trigger Warning, Don't like don't look: The subjective reality of the early 2000s
18:04:39 <HackEgo> /home/hackbot/hackbot.hg/multibot_cmds/lib/limits: line 5: exec: `Trigger: not found
18:05:22 <orin> God damn it those are opening quotes not... agh
18:05:27 <rdococ> I wonder, could a language based on algebra and logic be turing complete - or even an unknown computational class?
18:05:50 <orin> Uh, Is prolog turing complete, I forget
18:06:12 <rdococ> I think so, because I read somewhere datalog was supposed not to be
18:06:42 <rdococ> 'pure' prolog, whatever that would mean, yes
18:08:58 <rdococ> !! I know! functional bf?
18:09:41 -!- nszceta has joined.
18:14:24 -!- variable has joined.
18:16:12 <rdococ> what other definitions of programming languages could already be interpreted by applications everyone has?
18:17:25 <rdococ> wait... if you can go on hyperlinks to go to other web pages, could you put links to other program states in a program state written as a .html file?!
18:18:11 <rdococ> so a folder containing HTML files can simulate an FSA.
18:18:26 <rdococ> even if it has no JS, or CSS, etc.
18:18:34 <elliott> there are like ten languages identical to https://esolangs.org/wiki/Text on the wiki
18:19:05 <elliott> I just did; the one I linked. :p
18:19:08 <elliott> https://esolangs.org/wiki/Wiki_Cyclic_Tag is more interesting
18:28:18 <HackEgo> [wiki] [[Object oriented thue]] http://esolangs.org/w/index.php?diff=42399&oldid=40557 * 4D enthusiast * (+263) /* stdio */ added HexOutput & HexInput classes
18:29:33 <HackEgo> [wiki] [[Object oriented thue]] M http://esolangs.org/w/index.php?diff=42400&oldid=42399 * 4D enthusiast * (+0) /* stdtime */ corrected spelling of "hexadecimal"
18:56:01 -!- copumpkin has quit (Ping timeout: 264 seconds).
19:09:54 -!- GeekDude has quit (Remote host closed the connection).
19:14:04 <HackEgo> [wiki] [[Talk:Folder]] M http://esolangs.org/w/index.php?diff=42401&oldid=42381 * Rdococ * (+296) updated discuss page... why did nobody post here
19:24:58 <izabera> can i ask a stupid question about brainfuck?
19:25:22 <int-e> izabera: that was an excellent try
19:26:00 <izabera> well i'm trying to learn it, just what happens when you move the pointer before the 0th cell?
19:26:22 <izabera> is the tape supposed to be infinite in both directions?
19:26:37 <int-e> ah. lovely undefined behavior
19:26:57 <int-e> originally, the tape was onesided. but it depends on the implementation.
19:27:27 <rdococ> I wonder if that makes a difference in the computational class of bf
19:28:17 <izabera> well what's the most common implementation?
19:28:24 <int-e> rdococ: It's Turing-complete either way (assuming an infinite tape).
19:28:38 <rdococ> are you sure it's infinite, or do you mean unbounded?
19:29:25 <rdococ> it would be interesting to see a programming language using infinite tape, such that there's an address 'infinity'
19:29:37 <elliott> izabera: I would treat it as an error
19:29:41 <elliott> I think that is the usual behaviour, too.
19:30:01 <elliott> "right-infinite tape, 8-bit values in cells, 0 on EOF" is what I would consider most standard, personally
19:30:04 <int-e> izabera: I believe most commonly stepping off the tape to the left is either an error, or does really funny things (the implementation used on the anagol site puts input data there...)
19:30:14 <int-e> rdococ: I meant infinite
19:30:16 <elliott> izabera: in some implementations going < lets you access your own source code and modify it(!!)
19:30:30 <int-e> rdococ: that's fine, because the Turing machine is a theoretical construction.
19:30:50 <elliott> (I'm not sure if the modifications actually take effect, but I think they do.)
19:32:21 <izabera> would it be ok for an implementation to only have 2**63-1 cells?
19:32:38 <elliott> it wouldn't be TC but it'd be fine yes
19:32:40 <int-e> (the unbounded/infinite distinction is a silly computer science one; it's silly because in practice, one still runs into address space limits with things of "unbounded" size.)
19:32:42 <elliott> the original only had 30k cells
19:33:01 <elliott> not like there's many people with more than 64 bits of addressable memory
19:33:11 <elliott> (current CPUs can't even address that much if they wanted to)
19:33:30 <rdococ> I wonder if there's such thing as an infinite state automaton, whether it's turing complete or not
19:35:23 <rdococ> you would use regular expressions to define an infinite number of states, and then you could use those regexp-caught areas to transition to another one of many states
19:37:15 <rdococ> e.g. string [x] --- concatenate [y] ---> string [x][y] where [x] and [y] are wildcards
19:37:24 <int-e> Hmm, 48 bits addresses everywhere. (Even ATA addresses 512 byte blocks with 48 bit addresses)
19:37:50 <rdococ> so if the state was 'string derp', going 'concatenate herp' would change the state to 'string derpherp'.
19:39:39 <elliott> izabera: note that if you had a program which went > 2^63-ish times and then did some random stuff it'd "only" take ~97 years to run
19:39:49 <elliott> but since it wouldn't store anything in the cells on the way technically you could run it on a normal machine
19:40:02 <elliott> (e.g., one that uses a hash table to store the tape sparsely, omitting 0s)
19:40:24 <elliott> so there are programs which address a cell past 2^63 without requiring that much addressable memory that we can feasibly run today if we really, really want to
19:40:24 <izabera> i'm writing an interpreter to learn it
19:40:28 <elliott> (this is beyond irrelevant)
19:40:39 <elliott> (~97 years assuming we can move right on the tape at 3 GHz)
19:40:52 <elliott> okay well what about all the people who want to spend 100 years running a useless brainfuck program using bash, izabera. :(
19:41:40 <elliott> my enterprise will not be investing in your software product
19:45:53 <int-e> true, even bitcoins might be a better investment than that...
19:46:12 <Phantom_Hoover> <rdococ> it would be interesting to see a programming language using infinite tape, such that there's an address 'infinity'
19:46:28 <Phantom_Hoover> easy enough, the interesting part is how you get to infinity
19:47:03 <int-e> "^ -- change address to omega^<current address>"
19:47:58 <rdococ> think of it like having unboundedly many unbounded tapes - one starts from 1, another starts from omega, another starts from 2omega^3.
19:48:10 <int-e> (the real problem is that with no way of going down, the operation amounts to just clearing the tape)
19:48:40 <rdococ> you could change address to <current>/omega
19:49:12 <rdococ> so you'd have omega+1, 3omega, 65omega+23, etc. I don't know about exponents though.
19:49:31 <rdococ> in other words, 2d tape
19:49:36 <int-e> (bitcoins, I'm somewhat amazed that the hashing rate is not dropping. oh well...)
19:50:43 <rdococ> if a machine is a feedback system, user --input--> machine --output--> user, why not describe it like that
19:51:14 <rdococ> that could be like an equation or something: y = 3x^2 -- the user puts in a number x, and comes out 3x^2
19:51:15 <Phantom_Hoover> elliott, in the moving right 2^63 times while doing nothing scenario, if you're going to admit hashmaps for tape storage you have to allow for optimisation too
19:51:35 <Phantom_Hoover> so it's probably feasible to do it on a modern machine
19:51:42 <elliott> Phantom_Hoover: sure, but then you get into sticky details of how to actually write a program that does that
19:51:46 <elliott> without it being too big to reasonably store
19:51:56 <elliott> I guess it wouldn't be that hard
19:52:06 <elliott> but you need to leave a trail of 0s behind
19:52:22 <elliott> (basically you wil lneed enough memory to store a 63-bit integer where you are, I guess)
19:52:31 <elliott> but then you're doing fancy stuff and it's harder to optimise away
19:52:39 <elliott> look. let me be a pedant in peace ;_;
19:53:05 <int-e> hmm, leaving a trail of 0s behind isn't so easy... +[->>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>+]
19:53:25 <int-e> (note loop unrolling for extra efficiency)
19:59:18 <Koen_> int-e: how will that stop à 2^63?
20:01:28 <HackEgo> [wiki] [[Pyth]] http://esolangs.org/w/index.php?diff=42402&oldid=42290 * SuperJedi224 * (+0)
20:01:51 <izabera> will you beta test my interpreter when it's ready?
20:05:34 <int-e> Koen_: why would it stop?
20:15:58 <int-e> elliott: actually we may have to be careful, because state-of-the-art optimizing brainfuck compilers will turn sequences of > signs into a single addition instruction.
20:16:16 <elliott> well they also use finite tapes I think
20:16:36 <elliott> izabera: there are some good test programs like mandelbrot.b you can use to test it
20:16:42 <elliott> (will probably be sloooow in a bash interpreter)
20:16:49 <elliott> I think there are some programs that specifically try to test edge-cases, not sure though
20:23:05 <izabera> what happens if i have [ but no ] ?
20:23:45 <Koen_> well the program shouldn't compile
20:24:04 <Koen_> oh, you're making an interpreter
20:24:21 <Koen_> well, you should probably get a runtime error, then
20:24:37 <Koen_> unless there's some preprocessing before the actual interpreting
20:25:36 <Koen_> you could also implement some non-error behaviour in this case, for instance assume there are an unlimited amount of virtual [ at the beginning of the program and ] at the end, to match the unmatched brackets in the program
20:25:46 <Koen_> but I don't think any brainfuck interpreter does that
20:27:03 * int-e knows implementations where an extra ] terminates the program
20:27:29 <zzo38> Another way is if there is an extra ] then the first extra ] it will treat the rest as input to the program, at the end of the file then it starts reading in the actual input instead.
20:27:44 <int-e> and now that I think about it, missing ] might crash the thing.
20:28:11 <zzo38> (If the program uses the same input stream then the part after ] is the actual input.)
20:28:25 <Koen_> int-e: well, symmetrically, an extra [ should start the program again
20:30:37 -!- Koen_ has quit (Quit: The struct held his beloved integer in his strong, protecting arms, his eyes like sapphire orbs staring into her own. "W-will you... Will you union me?").
20:32:11 -!- zzo38 has quit (Remote host closed the connection).
20:36:22 <izabera> are the cells supposed to be chars?
20:36:44 <izabera> let me rephrase that: does [ loop if the current value is 256?
20:42:10 <HackEgo> [wiki] [[Folder]] M http://esolangs.org/w/index.php?diff=42403&oldid=42398 * Rdococ * (-1) /* Interpreter */
20:42:48 <int-e> izabera: do whatever seems convenient.
20:43:08 <izabera> it's fine either way, just tell me what most other implementations do
20:43:43 <int-e> I don't know. Originally they were chars, but there are plenty of implementations using int, and some using unbounded natural numbers...
20:44:40 -!- AnotherTest has joined.
20:46:05 <elliott> izabera: they are usually 0-255
20:46:13 <elliott> or -128 to 127, whichever interpretation you prefer (they are equivalent)
20:46:23 <elliott> they usually wrap on overflow and underflow
20:46:29 <elliott> though plenty of implementations have bignum cells with no limit
20:46:41 <elliott> and some rarer ones have 16-bit or 32-bit etc., or 8-bit but under/overflow is an error
20:46:54 <elliott> 8-bit wrapping is the most "classic" though
20:47:19 <int-e> the strictest implementation I've seen made decrementing 0 and incrementing 255 errors. (some brainfuck golf competition)
20:47:26 <elliott> generally if you have 8-bit wrapping cells, a right-infinite tape, and , sets the cell to 0 on EOF, then you should be able to run pretty much any program people have written unless they're weirdos
20:48:07 <elliott> but if you're writing a program and want to be really portable and boring, it's probably best to assume that cells are 0-255 and you can't go outside that, and that , either sets to 0 or does no change on EOF
20:48:16 <int-e> (eith they idea that this is the least common denominator of virtually all existing implementations)
20:49:41 <int-e> Oh yes, the three flavors of EOF behavior.
20:49:52 <int-e> (the third is -1 on EOF)
20:50:48 * int-e wants a 9 bit Brainfuck (so that -1 can be distinguished from 255).
20:54:11 -!- nszceta has quit (Quit: Textual IRC Client: www.textualapp.com).
20:54:15 -!- rdococ has quit (Quit: Page closed).
20:56:51 <elliott> int-e: yeah, but you can't be portable to both -1 and 0 on EOF, I don't think
20:56:59 <elliott> zero it and then check for 0 or -1
20:57:04 <elliott> but of course you rule out both 0 and 255 bytes in the input
20:57:24 <elliott> what's the easiest way to loop while not 0 or -1
21:03:09 <int-e> it's too tedious, I think you need auxilliary cells.
21:03:12 -!- copumpkin has joined.
21:05:04 <int-e> Ah, "auxiliary", my old nemesis.
21:06:07 <int-e> copumpkin: is codualization the same as dualization?
21:15:01 <izabera> can you give me a concise hello world or something that prints stuff?
21:15:33 <izabera> ++++++++++ ++++++++++ ++++++++++ ++++++++++ ++++++++++ ++++++++++ +++++ .
21:16:08 <izabera> (it does in my interpreter)
21:17:37 <izabera> ok i think i just broke the [ ] but the rest is fine
21:21:44 -!- Naprecks has quit (Quit: ZNC - http://znc.in).
21:25:31 <FireFly> ++++++[->+++++++<]>... should print three asterisks
21:25:31 <FireFly> !bf ++++++[->+++++++<]>... should print three asterisks
21:49:18 <fizzie> Do we have duplicate !bf's?
21:53:13 <izabera> tada http://arin.ga/hpExIX
21:54:17 <fizzie> ^bf [ better error reporting
21:54:32 -!- oerjan has joined.
21:54:37 <elliott> .) printf -v output %o "${tape[cell]}"
21:54:43 <elliott> isn't that the same as printf %o "${tape[cell]}"?
21:55:22 -!- AnotherTest has quit (Remote host closed the connection).
21:56:17 <izabera> well it probably needs to be printf -v output %o "$(( tape[cell] % 256))"
21:56:37 <izabera> it prints the octal in the var "output"
21:57:16 <izabera> `` printf -v output %o 65; printf "\\$output"
21:59:19 <fizzie> `` printf "\\$(printf %o 65)" # arguably slightly streamlined
21:59:52 <fizzie> The whole go-via-octal-escape thing seems silly, but I can't think of anything better offhand either.
22:02:41 <izabera> !bf ok so this is fine, i guess? same code as above but i added <> ++++++[->+++++++<]>...
22:04:16 <oerjan> izabera: you have a , in there but it doesn't matter for the demonstration
22:04:51 <oerjan> a danger of bf commenting
22:07:00 <fizzie> izabera: I don't think it's a fork + exec when the argument is a builtin. Compare http://sprunge.us/PQRO
22:07:39 <oerjan> forks are cheap, aren't they
22:08:10 <izabera> `` echo $(var=3; echo $var); echo $var
22:08:12 * oerjan thought they did copy-on-write sharing
22:09:04 <fizzie> oerjan: There's cheap and then there's cheap.
22:09:30 <oerjan> i will have none of your relativism.
22:09:40 <fizzie> (And okay, there's a clone.)
22:09:44 <izabera> `` time for i in {1..1000}; do printf -v output %o 65; printf "\\$output"; done >/dev/null
22:09:45 <HackEgo> \ real0m0.041s \ user0m0.100s \ sys0m0.000s
22:09:58 <izabera> `` ( time for i in {1..1000}; do printf -v output %o 65; printf "\\$output"; done >/dev/null ) 2>&1
22:09:59 <HackEgo> \ real0m0.045s \ user0m0.000s \ sys0m0.000s
22:10:23 <fizzie> What do you mean, no time?
22:10:53 <izabera> `` TIMEFORMAT='real: %lR, user: %lU, sys: %lS'; ( time for i in {1..1000}; do printf -v output %o 65; printf "\\$output"; done >/dev/null ) 2>&1
22:10:54 <HackEgo> real: 0m0.044s, user: 0m0.210s, sys: 0m0.000s
22:11:05 <fizzie> It looked just fine earlier, too.
22:11:10 <fizzie> I mean, sure, there were some raw tabs.
22:11:22 <izabera> `` TIMEFORMAT='real: %lR, user: %lU, sys: %lS'; ( time for i in {1..1000}; do printf "\\$(printf %o 65)"; done >/dev/null ) 2>&1
22:11:35 <HackEgo> real: 0m12.386s, user: 0m1.980s, sys: 0m9.940s
22:12:06 <fizzie> It's not quite fair to do that particular comparison on the UML box.
22:12:23 <fizzie> I get 0.022s vs 0.364s locally.
22:13:04 <izabera> that's only 15(?) times as much
22:13:22 <HackEgo> /home/hackbot/hackbot.hg/multibot_cmds/lib/limits: line 5: exec: time: not found
22:13:45 <HackEgo> \ real0m0.000s \ user0m0.000s \ sys0m0.000s
22:14:02 <HackEgo> \ real0m0.000s \ user0m0.000s \ sys0m0.000s
22:17:39 <elliott> if you want an expensive fork, try cygwin
22:19:36 * oerjan is getting ambiguous readings on his sarcasm meter
22:20:36 <oerjan> elliott: it just uses Ordinary Exec, no?
22:22:53 * oerjan now is getting ambiguous readings on his confusion vs. groaning meter
22:24:35 <izabera> well i implemented an interpreter in 3 hours
22:24:54 <izabera> i finished it now and it's purrrfect
22:25:22 <oerjan> wait is this brainfuck i'm not up to the logs yet
22:25:45 <oerjan> clearly 3 minutes should be enough for a bf interpreter
22:26:05 <izabera> but this was my first try :(
22:26:20 <izabera> i didn't even know brainfuck before
22:26:39 <oerjan> i made a brainfuck interpreter once, it took me several days i think.
22:26:54 <oerjan> *possibly* because i made it in Fueue.
22:27:28 <fungot> http://esolangs.org/wiki/Fueue
22:28:27 <oerjan> i don't think i've ever made one in a normal language.
22:29:21 <oerjan> although i've implemented at least one brainfuck derivative
22:30:28 * oerjan is a pretty slow programmer and would never make a time estimate in earnest btw
22:30:38 <fizzie> izabera: Doesn't the handling of [ leave extra stuff in the 'loop' array when []s are skipped?
22:31:07 <oerjan> damn ventilation is making that noise again
22:32:01 <fizzie> izabera: Um. Not really, or at least one where it'd make a difference. But I still think you want to do loop+=(i) only in the else of the if (( tape[cell] % 256 == 0 )) test.
22:34:48 <fizzie> ^bf +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++>+++++[-<.>>[]<]
22:34:52 <fizzie> I think that might be an example.
22:35:17 <elliott> izabera: everyone picking on you :P
22:36:26 <fizzie> Yes, I assume it's jumping to the opening [ of the [].
22:36:52 <fizzie> (It will be easy to fix.)
22:37:02 <fizzie> (Because I just fixed it.)
22:40:37 <elliott> izabera: so when will you do an optimising BF compiler in bash >_>
22:40:40 <fizzie> That might be the longest bash script I've ever seen that doesn't actually execute any commands.
22:41:08 <izabera> elliott: are you talking about that optimizing compiler written in sed?
22:41:13 <fizzie> Or I guess in bash terminology the builtins are still "commands", but you know what I mean.
22:41:35 <elliott> izabera: not about one in sed in particular
22:41:48 <izabera> a compiler is out of reach for now :P
22:41:50 <elliott> there's tons of optimising BF copilers, some of them are quite impressive (can compile a hello world make with loops to just printf("Hello, world!\n");)
22:42:44 <elliott> it's actually easier to write a non-optimising BF compiler than an interpreter
22:42:53 <elliott> since you can just turn [ into while (tape[ptr]) or whatever, it's string substitution
22:42:57 <izabera> i'm still trying to fix something, it stops at the first NUL byte it reads with cat :(
22:42:59 <elliott> not very interesting though
22:43:30 <elliott> you can set EOF as -1 (255) but then it fails on other binary data
22:44:04 <elliott> it's purrfect because it runs cat, right?
22:44:16 <elliott> I hope that wasn't your joke because it's a good one and I want to be the one to make it.
22:44:21 <izabera> it's purrfect because it runs +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++>+++++[-<.>>[]<]
22:44:33 <elliott> that does not look like a cat. I doubt it purrs.
22:45:02 <elliott> you just don't appreciate my jokes.
22:45:56 <fizzie> izabera: I think you should probably try LostKng.b, it's the standard stress test for brainfuck stuff.
22:46:09 -!- llue has quit (Quit: That's what she said).
22:46:10 <oerjan> <elliott> izabera: everyone picking on you :P <-- the bastards!
22:46:15 <elliott> does LostKng actually use wrapping?
22:46:19 -!- llue has joined.
22:46:48 <elliott> "<fizzie> izabera: I think you should probably try LostKng.b, it's the standard stress test for brainfuck stuff. -!- llue [~gnomebad@unaffiliated/lleu] has quit [Quit: That's what she said]" she made recommendations as to what brainfuck programs to try, I guess
22:47:06 <elliott> izabera: https://github.com/graue/esofiles/tree/master/brainfuck/src
22:47:12 <elliott> oh that doesn't have lostkng
22:47:23 <fizzie> And http://web.archive.org/web/20111031121638/http://jonripley.com/i-fiction/games/LostKingdomBF.html for that.
22:47:33 <fizzie> But the other archive is quite nice too.
22:47:34 <elliott> https://raw.githubusercontent.com/rdebath/LostKingdom/gh-pages/LostKng.b
22:47:37 <izabera> is that something that takes a while?
22:47:43 <izabera> cause my interpreter is _slow_
22:47:48 <elliott> LostKng.b shouldn't be too slow
22:48:01 <fizzie> It's a biggish program, though.
22:48:21 <fizzie> (It wasn't written by hand.)
22:56:09 -!- vodkode_ has joined.
22:59:10 <izabera> is this slow? https://raw.githubusercontent.com/graue/esofiles/master/brainfuck/src/rot13.b
22:59:25 <izabera> $ time echo xyz | ./bf rot13.b
22:59:29 <izabera> real: 0m16.023s, user: 0m15.983s, sys: 0m0.013s
23:06:03 <elliott> 16 seconds to rot-13 one line?
23:06:08 <elliott> I didn't know bash was THAT slow
23:06:26 <izabera> it's rot13ing only 4 characters XD
23:06:28 <elliott> would it be faster if you compiled to bash and then evalled it
23:08:46 <elliott> that was a sincere question!
23:10:09 <elliott> I guess I don't know how bash's interpretation works
23:10:17 <elliott> does it do any kind of pre-parsing at all?
23:11:32 <elliott> like, does bash parse functions into an AST?
23:11:52 <elliott> or does it store them as strings/lists of tokens and parse/execute them token by token every time you execute a function
23:12:17 <izabera> no it's parsed when it's read
23:12:18 <elliott> if it parses into an actual AST or bytecode data structure that can be interpreted more efficiently then I guess compile-and-eval would be faster
23:12:41 <izabera> that's why you basically can't use aliases in functions
23:13:07 <elliott> does it use the aliases you had at the time of parsing, or?
23:13:08 <izabera> aliases are expanded when the definition is read, not when it's called
23:13:27 <elliott> you know too much about this horrible language :P
23:14:19 <izabera> i'd rather have a faster interpreter but heh
23:15:48 <izabera> also there are errors in the parser...
23:16:04 <elliott> no kidding, those errors get CVEs :p
23:16:34 <izabera> i mean sure, shellshock got famous but there are other errors
23:17:19 <izabera> like, ${var[0] i basically can write whatever i want here and bash will never complain}
23:18:55 <HackEgo> bash: line 0: printf: warning: `.': invalid time format specification \ bash: line 0: printf: `H': invalid format character \ %(
23:19:16 <izabera> `` printf "%(%H:%M and now let's escape a left parentheses \) )T"
23:19:17 <HackEgo> bash: line 0: printf: warning: ` ': invalid time format specification \ bash: line 0: printf: `H': invalid format character \ %(
23:19:46 <izabera> this one shouldn't produce an error but bash basically shuts its brain in %()T
23:21:37 <elliott> well, there's no spec other than bash itself, right
23:21:41 <elliott> so I guess anything it does is okay by definition
23:21:51 <izabera> there are specs for posix sh
23:22:27 <izabera> bash does a good job about those :)
23:23:11 <izabera> i'll just throw a link in here for you to star <.< https://github.com/izabera/bf
23:25:34 <elliott> I haven't logged into github in, like, years.
23:26:49 <elliott> can you even write a bf interpreter in pure posix sh?
23:26:54 <elliott> without anything that can be a non-builtin
23:27:17 <izabera> posix sh has no arrays other than the positional parameters
23:27:27 <elliott> you could store the tape in a string if you could mangle the format enough, I guess?
23:27:39 <elliott> or just use positional parameters. there's probably some rather low guaranteed limit on those though
23:28:24 <izabera> parsing a line character by character is painful...
23:29:02 <elliott> well, nobody said it would be easy >_>
23:29:17 -!- variable has quit (Quit: 1 found in /dev/zero).
23:29:47 <elliott> does your ] jump back to the [ or the instruction after the [?
23:30:01 <elliott> if the former, then I guess it'd be wasting time looking for the ] every iteration? and that could explain why rot13 was so slow
23:30:52 -!- variable has joined.
23:31:09 <izabera> i'm already jumping after the [ :(
23:32:28 <elliott> I don't suppose bash has a profiler :p
23:32:55 <izabera> no profilers yet i'm afraid
23:33:34 <elliott> izabera: your interpreter doesn't do - on 0 -> 255
23:34:15 <elliott> okay but it doesn't support -- on 0
23:34:20 <elliott> (it's probably easiesr to store the cells pre-moduloed; I think your way will also break once you exceed bash's numerical limts?)
23:34:32 <elliott> (as in just do x = (x +- 1) % 256 for both)
23:35:36 <izabera> the problem is that $(( -1 % 256 )) == -1
23:35:50 <izabera> ok i'll just add 256 before the modulus
23:36:23 <elliott> ugh, yeah, that's annoying
23:36:28 <elliott> you can also condition on 0 and 255 which might be easier
23:37:42 <elliott> I admit that ${INTEGERCELLS-% 256} is cute though
23:38:06 <izabera> # set it to an empty value if it's set to avoid messing with the math expansion
23:38:06 -!- vodkode_ has quit (Ping timeout: 255 seconds).
23:38:08 <izabera> if [[ $INTEGERCELLS ]]; then INTEGERCELLS= ; fi
23:38:24 <elliott> don't you want an extensible program??
23:38:42 <elliott> you could use INTEGERCELLS to implement, like, boolfuck :P
23:39:05 <elliott> like brainfuck with a tape of bools
23:39:19 <elliott> it's "the obvious thing", modulo IO being a bit of a fuss since it's bitwise
23:39:26 <elliott> + and - get merged into a flip operation
23:45:10 <elliott> izabera: if you do +, say, 2^32 + 1 times, does it still work with your implementation?
23:45:13 <elliott> like does bash have bignums
23:45:18 <elliott> if not then it could break with long-running programs
00:05:27 -!- Sprocklem has joined.
00:52:16 -!- boily has joined.
00:53:33 -!- bixnode has joined.
01:00:01 <boily> @tell zzo38 hezzo38. verily, 3-player mahjong is a completely different game from regular riichi.
01:01:49 -!- hjulle has quit (Ping timeout: 255 seconds).
01:13:15 <lambdabot> CYUL 130100Z 23007KT 15SM FEW240 11/01 A3018 RMK CI1 CI TR SLP222
01:13:37 <boily> oerjan: hellørjan. please confirm that you see 11/01 as well.
01:16:51 <oerjan> I SEE DEA^W NO WAIT, IT'S JUST 11/01
01:17:33 <lambdabot> CYYZ 130100Z 19004KT 15SM FEW220 14/00 A3017 RMK CI2 SLP219
01:18:09 <orin> seems like it's a bit warmer up by the airport
01:19:51 <lambdabot> ENVA 130050Z 27017KT 9999 FEW019 BKN033 04/01 Q1004 RMK WIND 670FT 28017KT
01:20:04 <oerjan> well it is the middle of the night..
01:20:32 <oerjan> hm there isn't anything in there that tells timezone is there
01:20:44 <oerjan> i guess planes always use UTC anyway
01:21:01 <orin> it is 2122 hrs local time in Tronto
01:21:04 -!- hjulle has joined.
01:21:17 <boily> oerjan: 00:50:00+0000.
01:21:24 -!- bixnode has quit (Quit: Leaving).
01:22:24 <oerjan> boily: ok i don't see those numbers up in the metar
01:23:42 <boily> oerjan: they are grouped as 130050Z. 13 is the 13th of the month. 00h, 50m, Z for Zulu time.
01:23:45 <oerjan> weather in montorondheim
01:24:04 <oerjan> yes but Zulu time is UTC
01:24:09 <boily> I could get used to living in Montorondheim.
01:24:21 <boily> oerjan: yes. therefor, 00:50:00:+0000.
01:24:48 <boily> or something like that.
01:24:56 * boily is plagued by typo spirits...
01:25:16 <oerjan> well my reason for timezone interest was to tell whether it's day or night, so converting to UTC isn't very helpful.
01:26:19 * oerjan is reminded about that "why changing to one timezone for the world is stupid" essay
01:27:29 <boily> you have to remember ENVA is somewhere in Norway, and so it's +0100.
01:27:39 <boily> (or whatever timezone Norway is in.)
01:27:43 <oerjan> hm too many google hits
01:29:02 -!- hjulle has quit (Ping timeout: 245 seconds).
01:34:44 -!- Phantom_Hoover has quit (Remote host closed the connection).
01:50:48 -!- boily has quit (Quit: CURATED CHICKEN).
01:57:39 <oerjan> <b_jonas> I don't think there's a uniqueness requirement for esolang names. <-- * briefly considers inventing a language named "brainfuck"
01:59:37 <elliott> ais523 had that idea but I think it was going to be Brainfuck with a capital b
01:59:47 <elliott> or should that be capital B
02:04:30 * oerjan briefly considers inventing a language named "brаinfuсk"
02:08:10 <orin> I think they should have phonecian unification
02:09:28 <oerjan> orin: that's going to be hard with the latin alphabet having several letters that descend from the same phonecian one
02:10:10 <oerjan> (well that's same in greek, i'm not sure about phonecian proper)
02:10:18 <orin> Hmm, true, but we can at least unify the ones that look the same
02:12:55 <oerjan> look the same but entirely different meanings?
02:13:49 <oerjan> or look the same in one case but not the other, like omicron
02:13:52 <orin> we can at LEAST a and alpha and cyrillic a
02:14:37 <orin> And unify cyrillic sha with hebrew shin
02:17:18 <oerjan> <orin> God damn it those are opening quotes not... agh <-- you could say HackEgo ... `Triggered
02:17:43 <orin> arabic doesn't really look at all like phonecian
02:18:38 <oerjan> note that phonecian descendants also include indic scripts afaik
02:19:39 <oerjan> they don't even look at all like each _other_ either
02:20:55 <oerjan> the idea of the alphabet was only invented once. although hangul probably didn't borrow much of the forms.
02:21:51 -!- variable has quit (Ping timeout: 252 seconds).
02:22:03 <pikhq> Hangul didn't borrow any of the forms -- it cribbed from Chinese script rather than an alphabet.
02:25:25 <orin> katakana and hiragana are literally just very lazily written versions of chinese characters that sort of sounded correct
02:26:25 <orin> http://upload.wikimedia.org/wikipedia/commons/7/7a/Hiragana_origin.svg
02:27:27 <orin> compartively I think hangul is more creative
02:28:02 <pikhq> Yep. Hangul was designed, kana evolved.
02:55:28 -!- Frooxius has joined.
02:56:19 -!- heroux has quit (Ping timeout: 250 seconds).
02:57:14 -!- heroux has joined.
02:58:23 -!- variable has joined.
03:03:02 <oerjan> yum pepperoni and pineapple
03:04:40 -!- encapsulation has joined.
03:34:00 <izabera> https://github.com/graue/esofiles/blob/master/brainfuck/src/factor.b using this one
03:34:10 <izabera> real: 0m51.399s, user: 0m51.213s, sys: 0m0.107s
03:53:01 -!- doesthiswork has joined.
03:59:19 -!- vodkode_ has joined.
04:01:31 <fungot> Jafet: that would never be that clever... ( at least they have planet.lisp.org pointed over to it. i know we are talking about
04:03:24 <Jafet> Let f(n) be the number of steps used by factor.b to factor n
04:03:53 -!- Hijiri has joined.
04:23:20 <elliott> izabera: that's kind of impressive when it takes so long to even rot13
04:25:42 -!- vodkode_ has quit (Ping timeout: 244 seconds).
04:40:26 <HackEgo> /home/hackbot/hackbot.hg/multibot_cmds/lib/limits: line 5: exec: max: not found
04:42:34 -!- zzo38 has joined.
04:47:11 <zzo38> I had a idea, make up the All The Tropes Card Game; if you collect all of the tropes then you win.
04:47:19 <lambdabot> boily said 3h 47m 22s ago: hezzo38. verily, 3-player mahjong is a completely different game from regular riichi.
04:47:41 <zzo38> Yes I know 3-players game uses different rules
04:48:03 <zzo38> Although, I still to prefer to play such game using the rules of 4-players game.
04:52:08 <Hijiri> is there a program I can use to play net riichi mahjong in freedom
05:02:00 <zzo38> But, I also want to play Washizu mahjong
05:09:29 -!- variable has quit (Ping timeout: 256 seconds).
05:14:43 -!- variable has joined.
05:26:45 -!- variable has quit (Quit: 1 found in /dev/zero).
05:27:02 -!- variable has joined.
05:45:48 -!- function has joined.
05:47:19 -!- variable has quit (Ping timeout: 256 seconds).
05:54:44 -!- b_jonas has quit (Ping timeout: 245 seconds).
06:07:28 -!- Froox has joined.
06:09:48 -!- Frooxius has quit (Ping timeout: 248 seconds).
06:10:10 -!- function has quit (Ping timeout: 265 seconds).
06:19:26 -!- Froox has quit (Ping timeout: 264 seconds).
06:23:28 -!- doesthiswork has quit (Quit: Leaving.).
06:23:33 -!- Frooxius has joined.
06:23:43 -!- Frooxius has quit (Read error: Connection reset by peer).
06:26:08 -!- variable has joined.
06:41:22 <izabera> real: 0m12.853s, user: 0m12.713s, sys: 0m0.120s
06:41:31 <izabera> $ time echo hello world | bf examples/rot13.b
06:41:35 <izabera> real: 0m2.833s, user: 0m2.817s, sys: 0m0.010s
06:45:56 <elliott> oh... because in [a[b]c] you look for the ] after the b when hitting its [
06:46:01 <elliott> every iteration of the a[b]c loop
06:46:14 <elliott> I feel silly for not realising that before
06:46:29 <elliott> I assumed there wasn't any overhead compared to preparsing
06:47:24 <izabera> well now the rot13 has about 2s starting overhead, and it prints several characters per second... which is much better than the my first version that took about 5s per letter
06:49:17 <elliott> with variable speed I think
06:50:12 <elliott> you're in a programming channel, what do you expect? >_>
06:54:12 <izabera> https://github.com/izabera/bf/blob/master/bf tadaaa!
06:54:18 <izabera> harder! better! faster! stronger!
06:55:52 -!- variable has changed nick to function.
06:55:56 <function> elliott, izabera: fine, I'll pick a better nick
06:57:34 <elliott> izabera: corollary: your work is never over. you have to improve this interpreter for the rest of eternity
06:58:03 <oerjan> the interpreter of the damned
07:14:35 -!- function has quit (Ping timeout: 256 seconds).
07:52:37 <izabera> $ time bf examples/factor.b <<< 42
07:52:44 <izabera> real: 0m4.411s, user: 0m4.313s, sys: 0m0.090s
07:52:58 <izabera> apparently computing the length of the program each time is stupid and slow <.<
08:02:03 <fizzie> I was wondering about that, whether it'd make a difference.
08:05:53 <fizzie> Collapsing repeated instructions into one is also pretty common, I think even with interpreters. fungot does that, for example.
08:05:53 <fungot> fizzie: other than jpegtopnm and convert, are there any frontends for scheme which have a pleasant time!!
08:06:43 <fizzie> fungot: I didn't even know those were frontends for Scheme.
08:06:44 <fungot> fizzie: i don't see how such artificial restrictions can help in learning. use what you want
08:06:56 <fizzie> And that one sounds like a verbatim quote.
08:07:05 <fizzie> fungot: Try to be a little more original, okay?
08:07:05 <fungot> fizzie: and on providing unreadably succinct names for the srfi-33 ones, they were using the platypus book and using c++. the prof seems to be
08:07:33 <fungot> izabera: ( procedure)'. how do i, there... expr puts value of expr there... expr puts value of expr and output it
08:08:59 <izabera> it hurt itself in confusion
08:28:40 -!- contrapumpkin has joined.
08:32:19 -!- copumpkin has quit (Ping timeout: 272 seconds).
08:32:36 -!- Patashu has joined.
08:50:00 -!- Patashu has quit (Remote host closed the connection).
08:50:20 -!- Patashu has joined.
09:05:31 <roman2> fungot: You should try IronScheme.
09:05:32 <fungot> roman2: how tremendously boring you, perhaps. not that cross compiling isn't great, but i'm going to
09:06:02 <roman2> Help, fungot is going to cross compile something.
09:06:03 <fungot> roman2: so do i. i was new, stairway to heaven sucks. get vmware. or just start up the script again, it creates a time loop somewhere
09:06:59 <fizzie> It's also going to create a time loop. I'm worried.
09:08:32 <oerjan> well obviously fungot is getting tired of waiting for ais523 to implement feather so has decided to do it emself.
09:08:32 <fungot> oerjan: how do i get the latest pika without wasting effort with arch? i've been using it
09:09:32 <fungot> oerjan: there's no reason not to try. patenting can't be the value of ( list)
09:10:05 <oerjan> fungot: the value of list i nil, which is about the same as patenting.
09:10:06 <fungot> oerjan: would make me less confused, he just assembles all the bits in the message
09:10:21 <izabera> AAAAAAAAAAAAAAAABBBBBBBBBBBBBBBCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCDDDDDDDDDEGFFEEEEDDDDDDCCCCCCCCCBBBBB <- output after 25 minutes of mandelbrot.b
09:13:44 <roman2> http://esolangs.org/wiki/Talk:ESOSC
09:13:51 <roman2> nortti, Taneb: There's some work to do
09:13:55 -!- roman2 has changed nick to mroman.
09:14:09 <lambdabot> ENVA 130850Z 30017KT 9999 4000E -SN FEW005 SCT010CB BKN020 01/00 Q1012 TEMPO 1500 SHSNRA VV008 RMK WIND 670FT 31028KT
09:14:50 <lifthrasiir> izabera: are you making a bf interpreter? :)
09:15:20 <izabera> lifthrasiir: https://github.com/izabera/bf/blob/master/bf
09:15:22 -!- Phantom_Hoover has joined.
09:17:05 <lifthrasiir> izabera: it might be actually faster to translate bf into (say) awk script and let awk to interpret that.
09:17:54 <oerjan> wasn't the point to use only shell builtins
09:19:17 <mroman> a compiler that translates to another language
09:19:21 <mroman> like regular compilers do
09:19:55 <mroman> but assumingly transpilers compile to a same generation language rather than a lower generation language :)
09:20:58 <mroman> "A source-to-source compiler translates between programming languages that operate at approximately the same level of abstraction, while a traditional compiler translates from a higher level programming language to a lower level programming language."
09:21:01 <oerjan> they just keep piling on
09:21:08 <mroman> WP says the same thing about that.
09:21:24 <mroman> technically bf -> asm is transpiling
09:21:32 <mroman> it's probably beven uppiling I'd say
09:21:35 <mroman> since you translate upwards
09:21:43 <mroman> from low level to high level
09:22:07 <mroman> it's not compiling nor transpiling
09:22:38 <mroman> hypertranspiling and hypotranspiling
09:22:55 <oerjan> please don't mix greek and latin hth
09:23:07 <oerjan> super or sub, although i don't think they quite fit
09:23:54 <oerjan> of course transpiling is probably a portmanteau anyway
09:24:55 <oerjan> ooh the original meaning of "compile" is "plunder, pillage, rob, steal"
09:25:09 <mroman> With all the software pirates out there.
09:25:57 <fizzie> Dispiling. (Compare converge/diverge.)
09:28:25 <mroman> somebody added a non existing File to pogaack
09:31:55 <oerjan> oh it should clearly be "depiling".
09:32:06 <oerjan> https://en.wiktionary.org/wiki/depilo#Latin
09:33:29 <fizzie> Or perhaps "defiling".
09:35:01 <mroman> compilation -> decompilation
09:35:06 <mroman> depiliation -> dedepilation?
09:35:46 <mroman> (where dedepilation = transpilation)?
09:37:07 <fizzie> 1. dilapidate -- (bring into a condition of decay or partial ruin by neglect or misuse)
09:37:11 <fizzie> Yes, that sounds about right.
09:40:40 <mroman> I dilapidated lots of coding projects.
09:40:50 <mroman> Burlesque is pretty much dilapidating.
09:45:36 <mroman> fungot: Does fizzie dilapidate you?
09:45:36 <fungot> mroman: you figured it out before there were any interesting english-speaking scheme or lisp
09:45:52 <mroman> Of course I figured it out before everybody.
09:46:16 <mroman> Mostly to generate fancy looking passwords.
09:46:55 <fizzie> Have to admit I'm quilty of some amount of neglect there.
10:07:55 -!- oerjan has set topic: Dilapitated depilators | https://dl.dropboxusercontent.com/u/2023808/wisdom.pdf http://codu.org/logs/_esoteric/ http://tunes.org/~nef/logs/esoteric/.
10:08:34 -!- bb010g has quit (Quit: Connection closed for inactivity).
10:10:31 -!- Patashu_ has joined.
10:10:31 -!- Patashu has quit (Disconnected by services).
10:23:08 -!- boily has joined.
10:28:04 <HackEgo> [wiki] [[User:Rdococ]] M http://esolangs.org/w/index.php?diff=42404&oldid=42370 * Rdococ * (+14)
10:29:26 <HackEgo> [wiki] [[User:Rdococ]] M http://esolangs.org/w/index.php?diff=42405&oldid=42404 * Rdococ * (-14) Undo revision 42404 by [[Special:Contributions/Rdococ|Rdococ]] ([[User talk:Rdococ|talk]])
10:30:39 <HackEgo> [wiki] [[User:Rdococ]] M http://esolangs.org/w/index.php?diff=42406&oldid=42405 * Rdococ * (-8)
11:14:30 -!- Patashu_ has quit (Ping timeout: 252 seconds).
11:14:58 <HackEgo> [wiki] [[Folder]] http://esolangs.org/w/index.php?diff=42407&oldid=42403 * Rdococ * (+263) /* Structure */ added concept of substates
11:15:31 -!- Patashu has joined.
11:18:21 -!- boily has quit (Quit: DREAMT CHICKEN).
11:18:45 <HackEgo> [wiki] [[Folder]] http://esolangs.org/w/index.php?diff=42408&oldid=42407 * Rdococ * (+284) /* Input/Output */
11:22:20 -!- Patashu has quit (Ping timeout: 248 seconds).
11:23:37 -!- Patashu has joined.
11:24:37 -!- int-e has left ("PRETENTIOUS CHICKEN").
11:24:37 -!- int-e has joined.
11:27:35 -!- Patashu has quit (Disconnected by services).
11:27:35 -!- Patashu_ has joined.
11:31:07 -!- Patashu has joined.
11:34:00 -!- Patashu_ has quit (Ping timeout: 265 seconds).
11:34:44 -!- Patashu has quit (Disconnected by services).
11:34:44 -!- Patashu_ has joined.
11:37:39 -!- Patashu_ has quit (Client Quit).
11:37:52 <izabera> omg it only printed 4 lines so far of that mandelbrot set
11:39:29 <izabera> i guess i could try to optimize the bf code...
11:50:30 -!- vodkode_ has joined.
11:55:03 <mroman> better optimize the optimizer
11:55:11 <mroman> that has more value to the community :)
11:55:24 <oerjan> but but then you risk singularity
11:56:56 -!- hjulle has joined.
11:58:12 <mroman> fungot: Would you risk the singularity?
11:58:12 <fungot> mroman: if you're getting signatures for keeping strip clubs open. heh.) are created before those variables are indeed bound, so that gambit can start implementing it? :d
11:58:48 <mroman> Does it like strip clubs?
12:01:03 <oerjan> i think fungot may be planning something with blackjack and hookers
12:01:52 <oerjan> fungot: i am not sure what you mean by putting "and" in scare quotes, but i'm sure it's disturbing.
12:01:52 <fungot> oerjan: as for the thing to all three servers at once? :) i don't know why
12:15:43 -!- Taneb has changed nick to atriq.
12:16:00 -!- atriq has changed nick to Taneb.
12:27:46 -!- ProofTechnique has quit (Ping timeout: 244 seconds).
12:29:03 <HackEgo> [wiki] [[User talk:Esowiki201529A]] http://esolangs.org/w/index.php?diff=42409&oldid=42391 * Esowiki201529A * (+96) /* Hello, World! */
12:30:11 <HackEgo> [wiki] [[User talk:Esowiki201529A]] http://esolangs.org/w/index.php?diff=42410&oldid=42409 * Esowiki201529A * (+36) /* Hello, World! */
12:31:02 <HackEgo> [wiki] [[User talk:Esowiki201529A]] http://esolangs.org/w/index.php?diff=42411&oldid=42410 * Esowiki201529A * (+18) /* Hello, World! */
12:32:57 <HackEgo> [wiki] [[User talk:Esowiki201529A]] http://esolangs.org/w/index.php?diff=42412&oldid=42411 * Esowiki201529A * (+16) /* Concatenate string program */
12:35:19 -!- ProofTechnique has joined.
12:36:17 <HackEgo> [wiki] [[User talk:Esowiki201529A]] http://esolangs.org/w/index.php?diff=42413&oldid=42412 * Esowiki201529A * (+38) /* VandalismScript */
12:37:22 <HackEgo> [wiki] [[User talk:Esowiki201529A]] http://esolangs.org/w/index.php?diff=42414&oldid=42413 * Esowiki201529A * (+1) /* VandalismScript */
12:39:08 <HackEgo> [wiki] [[User talk:Esowiki201529A]] http://esolangs.org/w/index.php?diff=42416&oldid=42414 * Esowiki201529A * (+0) /* VandalismScript */
12:39:45 <mroman> I propose an esolang where everything outside /* */ is a comment
12:39:51 <mroman> and everything inside is code.
12:40:00 -!- ProofTechnique has quit (Ping timeout: 256 seconds).
12:40:59 <mroman> #define /* */ #define */ /*
12:46:05 -!- ProofTechnique has joined.
12:48:07 -!- NihilistDandy has joined.
12:48:33 <HackEgo> [wiki] [[User talk:Esowiki201529A]] http://esolangs.org/w/index.php?diff=42417&oldid=42416 * Esowiki201529A * (+0) /* VandalismScript */
12:49:07 -!- ProofTechnique has quit (Read error: Connection reset by peer).
12:49:38 <mroman> It would be fun to have regex defines.
12:50:07 <HackEgo> [wiki] [[Gibberish/JavaScript]] N http://esolangs.org/w/index.php?oldid=42418 * Esowiki201529A * (+452) Created page with "== Example == === [[Cat program|Concatenate string program]] === ${[[Cat program|cat]]:} === [[Hello, world!|Hello, World!]] === A "[[Hello, world!|Hello, World!]]" program..."
12:52:29 <HackEgo> [wiki] [[Gibberish/JavaScript]] http://esolangs.org/w/index.php?diff=42419&oldid=42418 * Esowiki201529A * (+26)
12:52:35 <izabera> AAAAAAAAAAAAAAAABBBBBBBBBBBBBBBCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCDDDDDDDDDEGFFEEEEDDDDDDCCCCCCCCCBBBBBBBBBBBBBBBBBBBBBBBBBBBBBB
12:52:37 <izabera> AAAAAAAAAAAAAAABBBBBBBBBBBBBCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCDDDDDDDDDDEEEFGIIGFFEEEDDDDDDDDCCCCCCCCCBBBBBBBBBBBBBBBBBBBBBBBBBB
12:52:40 <izabera> AAAAAAAAAAAAABBBBBBBBBBBBCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCDDDDDDDDDDDDEEEEFFFI KHGGGHGEDDDDDDDDDCCCCCCCCCBBBBBBBBBBBBBBBBBBBBBBB
12:52:41 <izabera> AAAAAAAAAAAABBBBBBBBBBCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCDDDDDDDDDDDDDDEEEEEFFGHIMTKLZOGFEEDDDDDDDDDCCCCCCCCCBBBBBBBBBBBBBBBBBBBBB
12:52:46 <izabera> AAAAAAAAAAABBBBBBBBBCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCDDDDDDDDDDDDDDEEEEEEFGGHHIKPPKIHGFFEEEDDDDDDDDDCCCCCCCCCCBBBBBBBBBBBBBBBBBB
12:52:49 <izabera> AAAAAAAAAABBBBBBBBCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCDDDDDDDDDDDDDDDEEEEEEFFGHIJKS X KHHGFEEEEEDD^C
12:52:50 <izabera> real: 244m24.955s, user: 237m42.815s, sys: 6m13.283s
12:52:51 <HackEgo> [wiki] [[Gibberish/JavaScript]] http://esolangs.org/w/index.php?diff=42420&oldid=42419 * Esowiki201529A * (-1) /* See also */
12:53:14 <HackEgo> [wiki] [[Gibberish/JavaScript]] http://esolangs.org/w/index.php?diff=42421&oldid=42420 * Esowiki201529A * (+1) /* See also */
12:54:45 <HackEgo> [wiki] [[Gibberish/JavaScript]] http://esolangs.org/w/index.php?diff=42422&oldid=42421 * Esowiki201529A * (+20) /* See also */
12:54:56 -!- NihilistDandy has quit (Ping timeout: 250 seconds).
13:00:05 -!- ProofTechnique has joined.
13:03:03 <HackEgo> [wiki] [[Gibberish/JavaScript]] http://esolangs.org/w/index.php?diff=42424&oldid=42422 * Esowiki201529A * (+53) /* See also */
13:03:32 <HackEgo> [wiki] [[Gibberish/JavaScript]] http://esolangs.org/w/index.php?diff=42425&oldid=42424 * Esowiki201529A * (+4) /* See also */
13:06:16 <HackEgo> [wiki] [[Gibberish]] http://esolangs.org/w/index.php?diff=42426&oldid=37407 * Esowiki201529A * (+59) /* Interpreter */
13:09:02 <HackEgo> [wiki] [[Gibberish/JavaScript]] http://esolangs.org/w/index.php?diff=42427&oldid=42425 * Esowiki201529A * (-2) /* See also */
13:17:55 <mroman> Always nice to have example programs without documentation
13:18:25 <izabera> source code == documentation ^^
13:18:40 <mroman> maybe where you live :)
13:19:00 <mroman> here up in the mountains where we eat cheese and chocolate and nothing else we like documentation alot.
13:19:21 <mroman> Reading documentation and eating Fondue at the same time is a very recreational activity.
13:20:02 <izabera> i used to use kvirc as my irc client
13:20:03 <mroman> There are projects who on purpose don't document very much
13:20:18 <mroman> in order for nobody to use it but still be able to claim it as open-source :D
13:20:29 <izabera> there were two variables that apparently had the same value
13:20:34 <mroman> also to make more money off support
13:21:12 <izabera> and the docs just said VAR1: This prints the value of VAR1 VAR2: This prints the value of VAR2
13:21:17 <izabera> they asked "did you read the docs?"
13:21:27 <izabera> i said yes ofc and quoted that
13:21:35 <izabera> then they asked "did you read the code?"
13:21:49 <mroman> RTFC - Read the fucking code.
13:21:57 <mroman> also real time french clock.
13:23:44 <izabera> would an hour or so be an ok time to print that mandelbrot set? <.<
13:24:04 <izabera> i can probably get close to that
13:26:14 <mroman> why is it having 6m of sys time btw?
13:39:27 -!- Sprocklem has quit (Ping timeout: 276 seconds).
13:42:53 -!- ais523 has joined.
13:44:04 -!- vodkode__ has joined.
13:53:17 -!- `^_^v has joined.
13:53:51 -!- bb010g has joined.
14:09:11 -!- ais523 has quit (Write error: Broken pipe).
14:09:26 -!- ais523 has joined.
14:13:08 -!- Phantom_Hoover has quit (Remote host closed the connection).
14:14:58 -!- Phantom_Hoover has joined.
14:17:49 -!- callforjudgement has joined.
14:18:37 -!- ais523 has quit (Read error: Connection reset by peer).
14:19:05 -!- callforjudgement has changed nick to ais523.
14:32:37 -!- callforjudgement has joined.
14:33:05 -!- ais523 has quit (Disconnected by services).
14:33:06 -!- callforjudgement has changed nick to ais523.
14:33:18 -!- GeekDude has joined.
14:39:45 <mroman> http://thestack.com/cornell-justin-cheng-troll-behavior-130415 whoot
14:48:30 -!- ais523 has quit (Read error: Connection reset by peer).
14:48:47 -!- ais523 has joined.
14:53:38 <mroman> ah good old trolley problem
14:53:54 <mroman> I'd still not flick any switches.
14:54:04 <mroman> unless I had a little bit more motivation than just to safe five people.
14:56:18 -!- nszceta has joined.
14:58:40 <ais523> isn't the correct answer to that to try to derail the train by flicking the switch with precise timing? or yell at the groups of people who would be hit to get out of the way?
14:59:05 <fizzie> Derail the train, killing everyone on it.
14:59:42 <fizzie> izabera: One thing I was wondering was whether it'd be faster to blow out the program into an array, in case the substring expansion is slow. Looking up an instruction is something that's done quite often.
14:59:51 <ais523> fizzie: I thought the way it's normally set up, everyone aboard the train is doomed anyway
15:00:01 <ais523> also IIRC train derailments are often survivable?
15:00:08 <ais523> there are also some fun third options which need more space on the railway but would be much more effective
15:00:16 <APic> Both sound true.
15:00:27 <ais523> such as "use something flimsy and mechanic to short the rails together in front of the rain"
15:00:41 <ais523> which will end up indirectly engaging the emergency brakes unless people go to a lot of trouble to override them
15:01:19 <ais523> there's also a mechanical way to engage the brakes by putting some sort of post next to the train so that it hits a brake engagement lever as the train goes past, but I don't know the details
15:07:49 -!- oerjan has quit (Quit: BRAAAAKES).
15:10:33 <HackEgo> [wiki] [[User:Rdococ]] http://esolangs.org/w/index.php?diff=42428&oldid=42406 * Rdococ * (+78) Merged user page with esolang list
15:21:27 <fungot> ais523: we hates them, they need to make fnord the heap that much more left :p
15:22:43 <APic> ais523: Passed.
15:22:57 <FireFly> fungot: less hateful, please?
15:22:57 <fungot> FireFly: ( if you need them at the corner
15:23:29 <ais523> APic: I just made an assertion that Freenode has an IRC bot written in Befunge online right now
15:23:39 <APic> Yah, You won, Man!
15:23:41 <ais523> and pinging fungot was the easiest way to see whether it was online
15:23:41 <fungot> ais523: toddfleming i am not wearing warm clothes therefore the thermostat should be set to....
15:24:54 <FireFly> Seems like an interesting assertion to make
15:25:50 -!- Sprocklem has joined.
15:25:51 -!- vodkode__ has quit (Ping timeout: 240 seconds).
15:26:32 <ais523> FireFly: someone else was talking about JavaScript's networking abilities
15:26:44 <ais523> tried to pick an example of a language that might be even worse at networking than JavaScript
15:26:50 <ais523> and ended up picking the worst possible esolang to make the point
15:27:36 <APic> ais523: At the very _Least_, it was not Malbolge. B-)
15:27:59 <ais523> yeah, malbolge is bad at networking
15:29:29 -!- variable has joined.
15:30:08 <fizzie> You'd think brainfuck would have been the obvious choice: it's the "standard" esolang, and is also pretty bad at ("innate") networking. The wire-stdin/out-to-netcat kind of things are arguable.
15:30:56 <ais523> brainfuck almost certainly has more attempted OS-communication libraries than any other esolang
15:34:26 <APic> You mean, like, C?
15:34:58 <APic> Everything that does I/O is Standard-Stuff, not C-Stuff…
15:35:22 <ais523> like C except if you restrict it to esolangs
15:35:41 <ais523> actually BF probably is the best answer to the question "what is the C of esolangs?"
15:35:55 <ais523> low-level, imperative, widely used, imitated a huge amount in ways that don't really improve on the original
15:35:58 <APic> But is not it esoteric too in the IOCCC and Places?
15:36:15 <ais523> IOCCC can be thought of as an eso dialect of C, I guess
15:37:41 -!- GeekDude has quit (Ping timeout: 264 seconds).
15:38:01 -!- GeekDude has joined.
15:40:03 <FireFly> Has C been imitated that much?
15:40:34 <FireFly> I mean, not in a syntactic sense (to which the answer is obviously "yes")
15:40:49 <ais523> you clearly don't work in the research compiler community ;-)
15:40:56 <ais523> stupid C derivatives are pretty much our stupid BF derivative equivalent
15:42:57 <FreeFull> C spawned a whole family of syntax
15:43:20 <ais523> C's syntax wasn't exactly new at the time, though
15:43:27 <ais523> it's basically BCPL with types and more sensible keywords
15:44:33 <FreeFull> Yeah, C is where all the other languages got it from though
15:47:01 <ais523> btw, what's the best way to teach people programming if they were expert programmers like 30 years ago, have stopped programming since, and now they ask you questions like "is it like Fortran, or like Algol?" and don't seem to understand why you'd use abstraction?
15:48:35 <FireFly> FreeFull: it did, but most of the languages borrowing its syntax are very far from it semantically I think
15:48:36 -!- bb010g has quit (Quit: Connection closed for inactivity).
15:48:56 <FireFly> At least among more popular languages
15:50:26 <FreeFull> FireFly: Well, I did say syntax, not semantics ;)
15:54:09 <ais523> with research compilers, people often don't bother to have a syntax at all until later
15:54:13 <ais523> you start off by writing parse trees manually
15:56:40 -!- MDude has joined.
15:58:02 -!- Hijiri has quit (Quit: WeeChat 1.0.1).
16:00:13 -!- G33kDude has joined.
16:00:15 -!- G33kDude has quit (Excess Flood).
16:00:35 -!- G33kDude has joined.
16:03:20 -!- GeekDude has quit (Ping timeout: 264 seconds).
16:03:20 -!- G33kDude has changed nick to GeekDude.
16:05:55 -!- ais523 has quit (Remote host closed the connection).
16:06:08 -!- ais523 has joined.
16:06:51 -!- hjulle has quit (Ping timeout: 264 seconds).
16:08:27 <izabera> fizzie: i did that already
16:08:45 <izabera> actually it turs out the expansion _was_ slow when the locale was involved
16:09:02 <izabera> with LANG=C it doesn't make any noticeable difference
16:12:06 -!- Sprocklem_ has joined.
16:12:45 -!- Sprocklem_ has left.
16:25:53 -!- b_jonas has joined.
16:36:45 <fizzie> Probably counting UTF-8 characters from the start of the string each time with the locale on, then.
16:42:39 -!- SopaXorzTaker has joined.
16:42:39 -!- ais523 has quit (Read error: Connection reset by peer).
16:43:21 -!- ais523 has joined.
16:44:26 -!- SopaXorzTaker has quit (Client Quit).
16:44:40 <HackEgo> [wiki] [[Talk:~ATH]] N http://esolangs.org/w/index.php?oldid=42429 * Texenox * (+266) Created page with "== Wow. == I am absolutely impressed. Usually, I tend to not be such a frequent editor, but I'm absolutely stunned with how this article has come along. Thank you, Vriskanon. ..."
16:49:47 <HackEgo> [wiki] [[User:Texenox]] N http://esolangs.org/w/index.php?oldid=42430 * Texenox * (+238) Created page with "Texenox is just some young bellend who enjoys the concept of coding. He has started the page relating to the fictional programming language [[~ATH]], but had then left it with..."
16:51:50 <HackEgo> [wiki] [[State]] N http://esolangs.org/w/index.php?oldid=42431 * Rdococ * (+728) Created page with "{{stub}} My iPad battery is running out, so I am in a rush to get to my PC. Please don't delete this if it is unfinished.<br /> The '''State programming language''' is an esot..."
16:56:13 -!- SopaXorzTaker has joined.
16:56:17 -!- ais523 has quit (Ping timeout: 244 seconds).
16:56:26 -!- SopaXorzTaker has quit (Max SendQ exceeded).
16:56:29 -!- SopaXorzTaker has joined.
17:01:54 -!- esowiki has joined.
17:01:58 -!- esowiki has joined.
17:01:59 -!- esowiki has joined.
17:02:43 -!- esowiki has joined.
17:02:44 -!- glogbot has joined.
17:02:47 -!- esowiki has joined.
17:02:48 -!- esowiki has joined.
17:17:27 -!- Hijiri has joined.
17:27:51 -!- heroux has quit (Ping timeout: 240 seconds).
17:29:06 -!- heroux has joined.
17:34:03 -!- Sprocklem has quit (Ping timeout: 245 seconds).
17:38:52 <int-e> http://sprunge.us/hGSc ... bullshit bingo aside, I wonder what they mean by "non-parseable notations"
17:44:06 <olsner> based on some kind of ethereal tokens inaccessible to our plane?
17:46:14 <HackEgo> [wiki] [[State]] http://esolangs.org/w/index.php?diff=42432&oldid=42431 * Rdococ * (+251) Updated page
17:48:49 -!- Hijiri has quit (Quit: WeeChat 1.0.1).
17:54:05 -!- vodkode_ has quit (Read error: Connection reset by peer).
17:54:49 -!- nszceta has quit (Ping timeout: 244 seconds).
17:57:58 -!- nszceta has joined.
17:59:06 -!- nszceta has quit (Max SendQ exceeded).
17:59:52 -!- nszceta has joined.
18:03:40 -!- Sprocklem has joined.
18:05:29 -!- bb010g has joined.
18:06:17 -!- Hijiri has joined.
18:07:49 -!- SopaXorzTaker has quit (Read error: Connection reset by peer).
18:08:19 -!- Hijiri has quit (Client Quit).
18:09:08 -!- Hijiri has joined.
18:11:37 -!- Hijiri has quit (Client Quit).
18:12:35 -!- Hijiri has joined.
18:42:22 <HackEgo> [wiki] [[State]] http://esolangs.org/w/index.php?diff=42433&oldid=42432 * Rdococ * (-16)
18:42:44 -!- GeekDude has quit (Quit: {{{}}{{{}}{{}}}{{}}} (www.adiirc.com)).
18:47:38 -!- rdococ has joined.
18:47:48 <HackEgo> [wiki] [[User:Rdococ]] http://esolangs.org/w/index.php?diff=42434&oldid=42428 * Rdococ * (-53) New language... although I might have rushed it
18:51:52 <rdococ> so we have Text, Folder, what now? Website?
18:57:37 -!- nycs has joined.
18:57:54 <rdococ> Text, Folder, the next thing would be Picture!
18:59:19 -!- `^_^v has quit (Ping timeout: 272 seconds).
19:18:02 <HackEgo> [wiki] [[Floater]] M http://esolangs.org/w/index.php?diff=42435&oldid=39156 * 4D enthusiast * (+8) /* Configuration */ reduced the ambiguity of the definition of angbase
19:23:05 -!- rdococ has quit (Ping timeout: 246 seconds).
19:30:59 -!- Frooxius has joined.
19:37:36 -!- Phantom_Hoover has quit (Ping timeout: 276 seconds).
19:38:25 <zzo38> Another kind is one to use RDF graphs as the input format. (A RDF graph is a directed graph where edges are labeled with URIs, and nodes are optionally labeled with URIs; each labeled node has a different label. A node can also be a literal which is a pair consisting of a string and a URI; a literal is not allowed to have any edges leading from it.)
19:38:36 -!- Phantom_Hoover has joined.
19:39:48 <izabera> writing programs in it would be easy
19:40:05 <izabera> interpreting the easy subset of the language would be easy
19:40:26 <izabera> but the language would be huge with many equivalent symbols
19:40:54 <izabera> and interpreting/compiling all of it would take a lot of time
19:41:00 <izabera> would this be interesting?
19:42:31 <izabera> for each possible symbol, it's (relatively) easy to understand what it does
19:43:54 <izabera> translate brainfuck like this , 1 . 2 + 3 - 4 [ 5 ] 6 > 7 < 8
19:44:11 <izabera> now any state of the cube has a minimum number of moves required to solve it
19:44:29 <izabera> any state that is solvable in 1 move is mapped to ,
19:44:35 <izabera> any state that is solvable in 2 moves is mapped to .
19:44:49 <izabera> there are 4.3 * 10^19 possible states
19:45:05 <izabera> any state out of that [1-8] range is a comment
19:45:44 <izabera> so to interpret it, you actually have to solve each state in the minimum number of moves
19:46:23 <izabera> writing programs otoh is relatively easy, just identify 8 states and use those
19:47:48 <zzo38> Ah, OK now I can see how you mean.
19:48:40 -!- zadock has joined.
19:48:59 <zzo38> Still if the interpreter proves that you need at least nine moves to solve it, it doesn't have to try to solve it or figure out exactly how much, since it is treated as a comment.
19:49:50 <zzo38> Well, yes, but still it can use such a shortcut
19:52:40 <izabera> i can't think of an efficient way to do it
19:52:48 -!- Hijiri has quit (Ping timeout: 265 seconds).
19:53:32 <zzo38> I don't know either; it is just one kind of idea.
19:59:45 <izabera> i guess one could do something like that for any np-complete problem...
20:00:34 <elliott> I think there are languages that are hard to write but easy to interpret, but I don't think I've seen the other way around before
20:01:44 -!- Hijiri has joined.
20:06:12 -!- zadock has quit (Ping timeout: 276 seconds).
20:09:28 -!- Sprocklem has quit (Ping timeout: 252 seconds).
20:25:33 -!- zzo38 has quit (Remote host closed the connection).
20:46:02 -!- GeekDude has joined.
20:47:08 -!- Froox has joined.
20:50:31 -!- Frooxius has quit (Ping timeout: 240 seconds).
20:52:18 -!- nycs has changed nick to `^_^v.
20:53:29 -!- magician has joined.
20:56:54 -!- Guest3780 has quit (Ping timeout: 276 seconds).
20:56:54 -!- magician has changed nick to Guest3780.
21:12:13 -!- AnotherTest has joined.
21:17:52 <orin> Apparently austria is actually spelled with a o
21:18:22 <Phantom_Hoover> <elliott> I think there are languages that are hard to write but easy to interpret, but I don't think I've seen the other way around before
21:21:15 -!- Froo has joined.
21:24:53 -!- Froox has quit (Ping timeout: 245 seconds).
21:25:18 -!- Frooxius has joined.
21:26:06 -!- Froo has quit (Ping timeout: 250 seconds).
21:28:32 <orin> Hm, what about natural language computing. Natural languages are about as easy as possible for humans, but extremely hard for computers to interpret
21:29:23 -!- rdococ has joined.
21:30:08 <fizzie> Yes, maybe the Osmosian Order of Plain English Programmers would disagree.
21:30:43 <fizzie> (Okay, they don't exactly claim it's hard to interpret.)
21:30:54 <fizzie> (I just wanted to bring them up.)
21:32:43 <orin> Wasn't there a project somewhere with an artificial pronouncable language that was basically prolog?
21:34:21 -!- HMC_A_ has joined.
21:34:23 -!- atehwa_ has joined.
21:34:53 <Taneb> orin, lojban, maybe?
21:36:15 -!- HMC_A has quit (Write error: Broken pipe).
21:36:15 -!- atehwa has quit (Write error: Broken pipe).
21:38:11 <orin> yeah, that was it, I read a page somewhere about using it for programming but I can't find it now
21:42:24 -!- Hijiri has quit (Quit: WeeChat 1.0.1).
21:48:25 -!- idris-bot has quit (Quit: Terminated).
21:49:21 -!- idris-bot has joined.
21:51:49 -!- Hijiri has joined.
21:51:59 <Jafet> Phantom_Hoover: eodermdrome currently has more interpreters than programs
21:52:16 -!- `^_^v has quit (Quit: This computer has gone to sleep).
21:53:38 <Taneb> I am fairly sure there exist joke languages which are easy to write in but hard to interpret
21:53:51 <Taneb> Actually, what about Banana Scheme or something
21:54:15 <Jafet> If you consider smtlib language as a programming language then that probably qualifies
21:55:16 <Jafet> In that vein, HTML5 probably qualifies
21:55:45 -!- AnotherTest has quit (Ping timeout: 250 seconds).
21:59:49 <rdococ> *not easy to write in either
22:07:11 -!- nszceta has quit (Quit: Textual IRC Client: www.textualapp.com).
22:09:03 -!- fungot has quit (Ping timeout: 276 seconds).
22:13:47 -!- boilyphone has joined.
22:14:10 <lambdabot> CYUL 132200Z 15015G21KT 30SM FEW110 FEW180 OVC240 21/04 A2986 RMK AC1AC1CI7 AC TR SLP110 DENSITY ALT 800FT
22:14:58 <rdococ> a program can be built to solve a problem. why not just tell the computer the problem?
22:15:17 <Taneb> You seem somewhat mobile
22:16:05 <boilyphone> Yes, on my phone. Waiting for a friend, then eat then Douteux.
22:16:37 <Taneb> Trying to revise Linear Algebra
22:19:23 <rdococ> I wonder if it's possible to create a turing complete programming language with one instruction & one parameter.
22:21:22 <tromp> you can make one with a single parameterless primitve
22:21:35 <Hijiri> do combinator calculi count as programming languages
22:21:40 -!- boilyphone has quit (Quit: MOBILE CHICKEN).
22:21:59 <tromp> http://en.wikipedia.org/wiki/Combinatory_logic#One-point_basis
22:22:07 <rdococ> if you use it to program, or communicate problems, solutions and instructions to a machine
22:22:18 <tromp> which i'm sure is what Hijiri has in mind
22:22:26 <Hijiri> because there is a turing complete 1-combinator calculus
22:22:51 <rdococ> I don't know what such a thing means
22:23:20 <Hijiri> that's what I was thinking about
22:26:02 -!- Hijiri has quit (Quit: WeeChat 1.0.1).
22:26:20 -!- Hijiri_ has joined.
22:28:33 <rdococ> I have a programming language you can use right now...
22:29:01 <rdococ> unlike its unintentional brother Folders
22:30:56 <rdococ> hmm... what is the computational class of Text?
22:33:39 <Taneb> I think I will go to sleep now
22:40:15 <orin> dilapitated? Isn't that "delapidated"? (from lapis, latin for stone, meaning when stones are fallen out of a wall)
22:40:29 -!- rdococ has quit (Ping timeout: 246 seconds).
22:41:14 <Jafet> It's just a misspelling, don't lose your head over it.
22:41:32 <orin> Apparently I also misspelled it
22:41:51 <orin> it's actually "dilapidated"
22:42:55 <orin> this is what happens when you don't have a phonemic orthography
22:43:46 <HackEgo> [wiki] [[Gibberish/JavaScript]] http://esolangs.org/w/index.php?diff=42436&oldid=42427 * Esowiki201529A * (+26) /* Example */
22:52:00 <HackEgo> [wiki] [[Gibberish/JavaScript]] http://esolangs.org/w/index.php?diff=42437&oldid=42436 * Esowiki201529A * (+55) /* interpreter */
22:52:40 -!- Hijiri_ has quit (Quit: WeeChat 1.0.1).
22:54:43 <FireFly> The one-point basis in combinatory logic hinges on being able to represent the expression as a tree (using parenheses), right?
22:56:04 <FireFly> so it's source representation isn't just a list
22:56:31 <elliott> yes, but with a linear representation you can make do with two
22:56:31 <elliott> http://www.westpoint.edu/eecs/SiteAssets/SitePages/Faculty%20Publication%20Documents/Okasaki/jfp03flat.pdf
23:04:23 <orin> the story is a nice touch
23:07:11 -!- rdococ has joined.
23:24:34 <elliott> FireFly: that just sounds mean out of context :P
23:36:13 -!- HackEgo has quit (Read error: Connection reset by peer).
23:36:23 -!- HackEgo has joined.
23:36:51 <MDude> Makes me want to use a client like Microsoft Comic Chat to take screenshots and pretend they're panels of Jerkcity.
23:37:53 -!- rdococ has quit (Ping timeout: 246 seconds).
23:38:09 <quintopia> "No backend server available for connection: timed out after 10 seconds or idempotent set to OFF or method not idempotent."
23:45:07 -!- Hijiri has joined.
23:46:33 -!- llue has quit (Quit: That's what she said).
23:46:46 -!- llue has joined.
23:46:54 -!- llue has quit (Changing host).
23:46:54 -!- llue has joined.
23:50:59 -!- vodkode__ has joined.
23:53:24 -!- zzo38 has joined.
23:58:34 -!- bb010g has quit (Quit: Connection closed for inactivity).
00:03:49 <elliott> MDude: is there any way to distinguish jerkcity comics from random MS Comic Chat screenshots
00:04:02 <elliott> can they truly be said to be distinct categories
00:04:50 <MDude> Frequency of refferences to dicks?
00:14:30 <izabera> can you show me an if-else in bf?
00:18:51 <izabera> ok wait i'm a beginner, gimme a minute to understand it
00:19:59 -!- Phantom__Hoover has joined.
00:21:04 <izabera> increment cell0 to 1, if cell1 != 0 print it, then decrement cell0, then cell1 = 0 while cell0-- != 0 print cell2
00:21:45 <izabera> ok that... doesn't look like an if-else
00:23:11 -!- Phantom_Hoover has quit (Ping timeout: 273 seconds).
00:24:23 -!- Melvar` has joined.
00:24:23 -!- idris-bot has quit (Ping timeout: 244 seconds).
00:24:41 <izabera> ok uhm the while loop is skipped since you decremented cell0
00:25:07 <mitchs> well a while block executed once is just an if block, if you want to look at it that way
00:25:12 <orin> http://www.paste.org/77995
00:25:33 -!- Melvar has quit (Ping timeout: 276 seconds).
00:25:48 <orin> This is my attempt at an interpreter for "State"
00:26:12 <izabera> orin: can you use a pastebin that doesn't have an anti-adblock? :\
00:26:55 <orin> huh? Ihave adblock and i'm seeing no problems
00:28:09 <orin> http://pastecode.org/index.php/view/99675460
00:28:26 -!- doesthiswork has joined.
00:29:05 <orin> Oh. I see, it's because I also use noscript
00:29:59 <izabera> spam spam spam spam spam best pastebin evur spam spam spam spam http://arin.ga
00:31:08 <izabera> no js required, it gives you the raw version when you load it from curl/wget, and you can set an expire date like '17 years 9 days 2 hours 55 minutes'
00:32:32 <orin> Anyway, rdococ, do you have any example programs?
00:32:57 <quintopia> izabera: have you looked at https://esolangs.org/wiki/Brainfuck_algorithms
00:43:09 -!- Phantom__Hoover has quit (Read error: Connection reset by peer).
00:47:50 <izabera> how do i move the pointer 1000 cells to the left?
00:48:29 <quintopia> depends on the implementation whether that is even possible
00:48:40 <quintopia> where it is possible, 1000 <'s in a row should do it
00:49:01 <izabera> ...i meant to the right ^^
00:49:28 <izabera> and i was hoping for a different answer
00:52:18 <mitchs> if the tape has only zeros and then you put N in a cell, you can then use [-[>+<-]>] pattern to move the pointer over N spots
00:52:57 <HackEgo> [wiki] [[ASCII art/mandelbrot]] N http://esolangs.org/w/index.php?oldid=42438 * Esowiki201529A * (+1067) Created page with " vL , '*m-` -m/**\a, ..."
00:54:13 <HackEgo> [wiki] [[ASCII art/mandelbrot]] http://esolangs.org/w/index.php?diff=42439&oldid=42438 * Esowiki201529A * (+0)
00:55:59 <quintopia> if the tape does not have only zeroes... 1000 >'s should do it :D
00:56:23 <quintopia> (fun fact: most programs do not require 1000 cells)
01:02:39 <mitchs> if you have 1000 nonzero cells followed by a zero, you may want to consider [>]
01:10:50 -!- SgeoWeb has joined.
01:11:13 <orin> youtube is dead
01:12:28 -!- bb010g has joined.
01:13:03 <HackEgo> bb010g: 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.)
01:13:03 <HackEgo> sgeo's: insanity: 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.)
01:16:23 <HackEgo> [wiki] [[Brainfuck algorithms]] http://esolangs.org/w/index.php?diff=42440&oldid=42253 * Quintopia * (+79) /* z = sign(x-y) */ i had this algorithm backwards apparently. i think i fixed it.
01:17:37 <SgeoWeb> Is it a bad idea to call out a subreddit mod for failing to disclose financial incentives?
01:17:50 <SgeoWeb> I mean, this mod is helping me, but still
01:18:46 <HackEgo> [wiki] [[Brainfuck algorithms]] M http://esolangs.org/w/index.php?diff=42441&oldid=42440 * Quintopia * (+49) /* z = sign(x-y) */
01:20:55 <HackEgo> [wiki] [[Brainfuck algorithms]] M http://esolangs.org/w/index.php?diff=42442&oldid=42441 * Quintopia * (-41) /* z = sign(x-y) */
01:22:09 <quintopia> SgeoWeb: do you have reason to suspect the mod's judgment is compromised by a conflict of interest?
01:22:40 <SgeoWeb> quintopia: no, but I have reason to believe it's a violation of the subreddit's own rules, which state that posters of affiliate links should have it disclosed in their flair
01:24:00 <SgeoWeb> Eh, if it's a mistake, they won't mind me asking about the affiliate thing directly
01:24:14 <SgeoWeb> I see other Amazon links by them that don't have the affiliate tag
01:24:26 <SgeoWeb> And ones to non-affiliate-capable sites
01:31:57 -!- oerjan has joined.
01:59:49 <SgeoWeb> http://www.amazon.com/gp/product/B00OBQ5950/
01:59:57 <SgeoWeb> Don't seem to see details on the HD
02:03:50 <orin> what details are you looking for?
02:04:54 <SgeoWeb> Whether the HD will park itself if it detects vibration
02:05:10 <SgeoWeb> Also all the negative reviews about the SSD breaking and being dumped into a BIOS utility scare me
02:20:22 -!- contrapumpkin has changed nick to copumpkin.
02:22:05 -!- lifthrasiir has quit (Ping timeout: 264 seconds).
02:22:22 -!- lifthrasiir has joined.
02:23:51 -!- llue has quit (Read error: Connection reset by peer).
02:23:52 -!- lleu has quit (Read error: Connection reset by peer).
02:23:58 -!- SgeoWeb has changed nick to Sgeo.
02:24:16 -!- Sgeo has changed nick to SgeoWbe.
02:24:19 -!- SgeoWbe has changed nick to SgeoWeb.
02:29:14 -!- TieSoul_ has joined.
02:30:09 -!- Froox has joined.
02:32:28 -!- Frooxius has quit (Ping timeout: 250 seconds).
02:32:45 -!- TieSoul has quit (Ping timeout: 248 seconds).
02:40:03 -!- adu has joined.
02:59:44 -!- jameseb- has joined.
03:05:05 -!- b_jonas has quit (*.net *.split).
03:05:05 -!- dianne has quit (*.net *.split).
03:05:05 -!- lambdabot has quit (*.net *.split).
03:05:06 -!- jameseb has quit (*.net *.split).
03:05:06 -!- zemhill_ has quit (*.net *.split).
03:09:20 <oerjan> <orin> Apparently austria is actually spelled with a o <- Ö hth
03:11:33 -!- Sprocklem has joined.
03:11:33 -!- b_jonas has joined.
03:11:33 -!- dianne has joined.
03:11:33 -!- lambdabot has joined.
03:11:33 -!- zemhill_ has joined.
03:12:23 -!- Sprocklem has changed nick to Guest17241.
03:12:59 <SgeoWeb> https://github.com/mishoo/UglifyJS2/issues/121#issuecomment-92522991
03:20:02 <orin> Hmm... what if i dynamically tell what base a number is in as it's read? so for eixample, 2F0 is (2*10+15)*16=560
03:22:03 <orin> shachaf: good point.
03:22:38 -!- Froox has quit (Quit: *bubbles away*).
03:23:16 <orin> in such representation, it is not obvious to me an algorithm for opimizing the size of higher numbers
03:24:53 <orin> consider if we have only 36 known digits, then in representing 37...
03:30:35 <izabera> can i propose a code challenge?
03:30:46 <zzo38> What kind of code challenge?
03:31:08 <HackEgo> ac1 ac2 ac3 bc1 bc2 bc3 c1 c2 c3
03:32:05 <izabera> find the shortest brace expansion that generates a set of strings
03:36:32 <mitchs> `` echo {1..3}{a,b,c}{4..6}
03:36:33 <HackEgo> 1a4 1a5 1a6 1b4 1b5 1b6 1c4 1c5 1c6 2a4 2a5 2a6 2b4 2b5 2b6 2c4 2c5 2c6 3a4 3a5 3a6 3b4 3b5 3b6 3c4 3c5 3c6
03:37:20 <izabera> `` echo {x,{,w}q}{,a} # you can even nest it
03:40:21 <orin> `` echo {abc,def}{g,}
03:41:07 <HackEgo> 1a 1b 1c 2a 2b 2c 3a 3b 3c
03:41:20 <mitchs> `` echo {1..3}{aa..ac}
03:41:21 <HackEgo> 1{aa..ac} 2{aa..ac} 3{aa..ac}
03:42:22 <izabera> you may restrict the challenge to the {a,b,c} expansion style, ignore the {a..z} ^^
03:43:28 <HackEgo> bash: {,: command not found \ bash: {,: command not found \ bash: {,: command not found \ {}}1 {}}2 {}}3
03:43:52 <izabera> you may restrict the challenge to lowercase letters only <.<
03:44:02 <zzo38> And then, do you have to consider if the text include itself braces?
03:44:11 <izabera> you may restrict the challenge to lowercase letters only <.<
03:44:13 <zzo38> (Even outside of a block)
03:44:25 <izabera> lowercase letters only <.<
03:44:46 -!- MDude has changed nick to MDream.
03:45:21 <zzo38> O, so you mean all of the text is only with lowercase letter and not .. either, I suppose is you mean?
03:45:54 -!- Guest17241 has quit (Quit: [).
03:45:58 <izabera> the input is a single line with several words, space separated or whatever
03:46:07 <izabera> that only use lowercase letters
03:46:16 -!- Sprocklem_ has joined.
03:46:20 <zzo38> O, so spaces is OK too, but only between items.
03:46:35 <izabera> hey the input format is not important
03:47:33 <izabera> i'm just trying to remove the annoying cases <.<
03:48:07 <izabera> get a list of words and produce the smallest brace expansion that generates them ^^
03:53:17 <zzo38> I want to make up a "temporary://" URI scheme for temporary identifiers. The format is scheme,authority,path,query,fragment like other URI and work same way relative URIs too, but it is local to the current instance and is not a global URI and probably doesn't points to anything. I also want to make up "urn:bible:" scheme.
03:54:44 <HackEgo> [wiki] [[Special:Log/move]] move * Esowiki201529A * moved [[Itflabtijtslwi]] to [[Ignore this fancy little acronym because this is just that slashes language with input]]
03:54:44 <HackEgo> [wiki] [[Special:Log/move]] move * Esowiki201529A * moved [[Talk:Itflabtijtslwi]] to [[Talk:Ignore this fancy little acronym because this is just that slashes language with input]]
03:54:59 <SgeoWeb> Would urn:bible: only be Bible locations, or could it also specify translation?
03:55:13 <SgeoWeb> And if so, is there a list of translations, or a more generic way anyone could produce a 'translation'?
03:55:31 <HackEgo> [wiki] [[Special:Log/move]] move_redir * Esowiki201529A * moved [[Ignore this fancy little acronym because this is just that slashes language with input]] to [[Itflabtijtslwi]] over redirect
03:55:31 <HackEgo> [wiki] [[Special:Log/move]] move_redir * Esowiki201529A * moved [[Talk:Ignore this fancy little acronym because this is just that slashes language with input]] to [[Talk:Itflabtijtslwi]] over redirect
03:55:57 <zzo38> SgeoWeb: Only the Bible reference, I think.
03:56:25 <zzo38> If you want a specific translation, you will use the URL that points to the text of that translation.
03:58:50 <zzo38> For example you can write urn:bible:<book> or urn:bible:<book>:<chapter> or urn:bible:<book>:<chapter>:<verse> or urn:bible:<book>:<chapter>:<verse>-<chapter>:<verse> might be the possible formats.
03:59:20 -!- SgeoWeb has quit (Ping timeout: 246 seconds).
04:03:36 <oerjan> <elliott> http://www.westpoint.edu/eecs/SiteAssets/SitePages/Faculty%20Publication%20Documents/Okasaki/jfp03flat.pdf <-- now i'm wondering if it is obviously impossible to do this with S and K specifically
04:06:55 -!- GeekDude has quit (Quit: {{{}}{{{}}{{}}}{{}}} (www.adiirc.com)).
04:08:20 <oerjan> anything starting with K.. or SK.. can be simplified.
04:08:55 -!- adu has quit (Quit: adu).
04:09:20 <oerjan> SSxy = Sy(xy), if y is K that's also useless
04:11:31 <oerjan> SSxSz = SS(xS)z = Sz(xSz), so needs z = S
04:12:27 <oerjan> SSxSSa = SS(xSS)a = Sa(xSSS) oh i see this just keeps being trivial
04:12:47 -!- adu has joined.
04:13:50 <HackEgo> [wiki] [[Gibberish/JavaScript]] http://esolangs.org/w/index.php?diff=42451&oldid=42437 * Esowiki201529A * (+109) /* self interpreter */
04:16:03 -!- vodkode__ has left ("Leaving").
04:16:33 <HackEgo> [wiki] [[Gibberish/JavaScript]] http://esolangs.org/w/index.php?diff=42452&oldid=42451 * Esowiki201529A * (+6) /* Fibonacci sequence */
04:20:07 -!- vodkode_ has joined.
04:25:50 <izabera> OMG HOW DO I DRAW A FUCKING CIRCLE IN ASCII ART THAT LOOKS LIKE A CIRCLE
04:26:17 <izabera> i'm completely unable to do it -_-
04:26:38 <oerjan> -_- looks like a good start
04:28:48 <adu> (_) might be a better start
04:29:35 <oerjan> depends how big it should be
04:32:06 -!- adu has quit (Quit: adu).
04:33:58 <Deewiant> http://ascii.co.uk/art/clock hth
04:37:10 -!- SgeoWeb has joined.
04:42:26 -!- vodkode_ has quit (Quit: Leaving).
04:49:22 <HackEgo> [wiki] [[Gibberish/JavaScript]] http://esolangs.org/w/index.php?diff=42453&oldid=42452 * Esowiki201529A * (+2) /* Fibonacci sequence */
04:49:59 <SgeoWeb> Di oirtabke desktops exist?>
04:50:04 <SgeoWeb> Do portable desktops exist?
04:50:13 -!- vodkode_ has joined.
05:08:45 -!- zadock has joined.
05:12:30 <orin> a homerow shift error
05:14:06 <newsham> > plot (\n -> n `mod` 7) 0 80
05:14:07 <lambdabot> No instance for (Enum a0) arising from a use of ‘plot’
05:14:07 <lambdabot> The type variable ‘a0’ is ambiguous
05:14:08 <lambdabot> Note: there are several potential instances:
05:15:29 <lambdabot> (Enum a1, RealFrac a) => (a1 -> a) -> a1 -> a1 -> Doc
05:15:54 <lambdabot> The operator ‘plot’ [infixl 9] of a section
05:15:54 <lambdabot> must have lower precedence than that of the operand,
05:16:45 <newsham> > plot (\n -> fromIntegral (n `mod` 7)) 0 80
05:16:46 <lambdabot> ⠀⠀⡠⠂⠀⢀⠔⠀⠀⡠⠂⠀⢀⠔⠀⠀⡠⠂⠀⢀⠔⠀⠀⡠⠂⠀⢀⠔⠀⠀⡠⠂⠀⢀⠔⠀⠀⡠⠂⠀
05:16:47 <lambdabot> ⡠⠊⠀⢀⠔⠁⠀⡠⠊⠀⢀⠔⠁⠀⡠⠊⠀⢀⠔⠁⠀⡠⠊⠀⢀⠔⠁⠀⡠⠊⠀⢀⠔⠁⠀⡠⠊⠀⢀⠔
05:17:12 -!- vodkode_ has quit (Ping timeout: 240 seconds).
05:18:40 <oerjan> > plot (\x -> sin (x*80)) 0 (pi/40)
05:18:50 <oerjan> > plot (\x -> sin (x*80)) 0 (pi/40)
05:19:38 <oerjan> > plot (\x -> sin (fromIntegral (x*pi/40))) 0 80
05:19:39 <lambdabot> No instance for (Enum a0) arising from a use of ‘plot’
05:19:39 <lambdabot> The type variable ‘a0’ is ambiguous
05:19:39 <lambdabot> Note: there are several potential instances:
05:19:55 <oerjan> > plot (\x -> sin (fromIntegral (x*pi/40))) 0 (80::Int)
05:19:57 <lambdabot> No instance for (Floating Int) arising from a use of ‘pi’
05:19:57 <lambdabot> In the second argument of ‘(*)’, namely ‘pi’
05:19:57 <lambdabot> In the first argument of ‘(/)’, namely ‘x * pi’
05:20:18 <oerjan> > plot (\x -> sin (fromIntegral x * pi/40)) 0 (80::Int)
05:20:19 <lambdabot> ⣀⣀⣀⣀⣀⣀⣀⣀⣀⣀⢄⣀⣀⣀⣀⣀⣀⣀⣀⣀⡈⠉⠉⠉⠉⠉⠉⠉⠉⠉⠉⠉⠉⠉⠉⠉⠉⠉⠉⠉
05:21:23 <oerjan> > plot (\x -> 2*sin (fromIntegral x * pi/40)) 0 (80::Int)
05:21:24 <lambdabot> ⣀⣀⣀⡠⠤⠤⠤⠤⠤⠤⠢⠤⠤⠤⠤⠤⠤⣀⣀⣀⡈⠉⠉⠑⠒⠒⠒⠒⠒⠒⠒⠒⠒⠒⠒⠒⠒⠉⠉⠉
05:21:57 <oerjan> i feel this is not how plots should work
05:22:07 <oerjan> > plot (\x -> 1 + 2*sin (fromIntegral x * pi/40)) 0 (80::Int)
05:22:09 <lambdabot> ⠤⠤⠤⠔⠒⠒⠒⠒⠒⠒⠑⠒⠒⠒⠒⠒⠒⠤⠤⠤⢄⣀⣀⡈⠉⠉⠉⠉⠉⠉⠉⠉⠉⠉⠉⠉⠉⣀⣀⣀
05:23:18 <newsham> > plot (\n -> sqrt(49 - (n-7)*(n-7))) 0 15
05:24:07 <newsham> > plot (\n -> 7-sqrt(49 - (n-7)*(n-7))) 0 15
05:24:31 <oerjan> > plot (\x -> 1 + 10*sin (fromIntegral x * pi/40)) 0 (80::Int)
05:24:32 <lambdabot> ⠀⠀⠀⠀⠀⣀⠤⠔⠒⠒⠑⠒⠒⠤⢄⡀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀
05:24:32 <lambdabot> ⠀⠀⣀⠔⠊⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠈⠒⢄⡀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀
05:24:32 <lambdabot> ⠤⠊⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠈⠢⢄⠑⠤⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠠⠔⢁
05:24:52 <oerjan> > plot (\x -> 10*(1+sin (fromIntegral x * pi/40))) 0 (80::Int)
05:24:53 <lambdabot> ⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⡀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀
05:24:53 <lambdabot> ⠀⠀⠀⠀⢀⠤⠒⠊⠉⠉⠈⠉⠉⠒⠢⢄⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀
05:24:53 <lambdabot> ⠀⢀⠤⠊⠁⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠉⠢⢄⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀
05:25:29 <lambdabot> ⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀
05:25:29 <lambdabot> ⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⡠⠊
05:25:29 <lambdabot> ⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⡠⠊⠀⠀
05:25:47 <newsham> you'd get a better pic in /msg :)
05:34:09 -!- roasted42 has joined.
05:34:24 -!- roasted42 has quit (Changing host).
05:34:24 -!- roasted42 has joined.
05:34:25 -!- roasted42 has changed nick to TheM4ch1n3.
05:49:28 <orin> they whould draw the plot to a jpeg and upload it to a server somewhere, then respond with a link
05:52:30 <newsham> how about take a link to a jpeg and then plot it as ascii?
05:53:39 <orin> ok i have no IDEA why my hands want to spell would as whould?
05:56:36 <newsham> orin: because https://youtu.be/lich59xsjik?t=51s
05:57:22 -!- adu has joined.
06:01:10 -!- adu has quit (Client Quit).
06:07:35 <HackEgo> [wiki] [[Tomagotcha!]] N http://esolangs.org/w/index.php?oldid=42455 * 0x0dea * (+1838) Add Tomagotcha! "language"
06:10:13 <HackEgo> [wiki] [[Hello world program in esoteric languages]] http://esolangs.org/w/index.php?diff=42456&oldid=42378 * Esowiki201529A * (+5) /* A colon semicolon */
06:12:20 -!- SgeoWeb has quit (Ping timeout: 246 seconds).
06:22:23 <HackEgo> [wiki] [[Beatnik]] http://esolangs.org/w/index.php?diff=42457&oldid=42372 * Esowiki201529A * (+1133) /* Hello, world */
06:24:39 -!- vodkode_ has joined.
06:33:47 -!- doesthiswork has quit (Quit: Leaving.).
06:34:44 -!- ProofTechnique has quit (Ping timeout: 272 seconds).
06:45:07 <HackEgo> [wiki] [[Beatnik]] M http://esolangs.org/w/index.php?diff=42458&oldid=42457 * 0x0dea * (-1133) Remove incorrect "Hello, world!" program
06:53:45 <orin> https://www.youtube.com/watch?v=-4jwzan3AyA
06:55:20 <zzo38> [&]%@*>"Type 'beer' for beer.~Type 'quit' to quit.~"PS [&BEER'BEER],#99>:+,#&VERSE#/"No more bottles of beer on the wall.~"PS [&QUIT'QUIT]GQ+.$0>
06:55:37 <zzo38> [&VERSE#,^#],^#<<PI" bottles of beer on the wall.~"PS,^#<<PI" bottles of beer.~Take one down and pass it around,~"PS,^#<,^#<<DN>,^#<<\,^#<<PI" bottles of beer on the wall.~"PS CR 1RF: 0RF
06:56:28 <zzo38> I just finish by now to make OASYS assembler with C, this is how to make a kind of beer program with it. Is this program understandable to you?
06:58:19 <zzo38> This example program uses a pointer variable; OAC (the original compiler for OASYS) does not support pointer variables. (OAC also doesn't support macros, doesn't support calling methods before they are defined, etc.)
07:07:57 -!- j-bot has quit (Ping timeout: 248 seconds).
07:11:06 <oerjan> orin: thanks now i'm finally up to date tdh
07:15:49 -!- ProofTechnique has joined.
07:39:02 <zzo38> What part didn't you understand?
07:44:45 -!- magician has joined.
07:47:01 -!- Guest3780 has quit (Ping timeout: 246 seconds).
07:47:01 -!- magician has changed nick to Guest3780.
07:51:19 -!- variable has quit (Ping timeout: 244 seconds).
07:51:33 <HackEgo> [wiki] [[Special:Log/move]] move * Esowiki201529A * moved [[Funciton]] to [[Function]]: Err,Function.
07:51:34 <HackEgo> [wiki] [[Special:Log/move]] move * Esowiki201529A * moved [[Talk:Funciton]] to [[Talk:Function]]: Err,Function.
07:53:51 <HackEgo> [wiki] [[Special:Log/move]] move_redir * Oerjan * moved [[Talk:Function]] to [[Talk:Funciton]] over redirect: No, it's not named that.
07:54:15 <HackEgo> [wiki] [[Special:Log/move]] move_redir * Oerjan * moved [[Function]] to [[Funciton]] over redirect
08:13:40 <HackEgo> [wiki] [[Special:Log/move]] move * Esowiki201529A * moved [[A programming language is a formal constructed language designed to communicate instructions to a machine, particularly a computer.]] to [[Aplifcldtcitampac]]: Err
08:14:43 <HackEgo> [wiki] [[Aplifcldtcitampac]] http://esolangs.org/w/index.php?diff=42467&oldid=42465 * Esowiki201529A * (+14)
08:15:34 -!- j-bot has joined.
08:17:25 <HackEgo> [wiki] [[Aplifcldtcitampac]] http://esolangs.org/w/index.php?diff=42468&oldid=42467 * Esowiki201529A * (-14) Undo revision 42467 by [[Special:Contributions/Esowiki201529A|Esowiki201529A]] ([[User talk:Esowiki201529A|talk]])
08:18:26 <HackEgo> [wiki] [[Special:Log/move]] move_redir * Esowiki201529A * moved [[Aplifcldtcitampac]] to [[A programming language is a formal constructed language designed to communicate instructions to a machine, particularly a computer.]] over redirect
08:18:35 -!- idris-bot has joined.
08:22:33 -!- Phantom_Hoover has joined.
08:25:25 <elliott> oerjan: maybe you should tell them how to create redirects without moving twice
08:27:17 -!- zadock has quit (Ping timeout: 264 seconds).
08:36:10 -!- Melvar` has changed nick to Melvar.
08:38:36 -!- Patashu has joined.
08:39:38 <HackEgo> [wiki] [[Gibberish/JavaScript]] http://esolangs.org/w/index.php?diff=42471&oldid=42453 * Esowiki201529A * (+77) /* Hello, World! */
08:45:38 <HackEgo> [wiki] [[Gibberish/JavaScript]] http://esolangs.org/w/index.php?diff=42472&oldid=42471 * Esowiki201529A * (+1) /* Hello, World! */
08:46:44 -!- jameseb- has changed nick to jameseb.
08:48:33 -!- gniourf has joined.
08:50:51 <HackEgo> [wiki] [[Gibberish/JavaScript]] http://esolangs.org/w/index.php?diff=42473&oldid=42472 * Esowiki201529A * (+39) /* Hello, World! */
08:53:04 <HackEgo> [wiki] [[Gibberish/JavaScript]] http://esolangs.org/w/index.php?diff=42474&oldid=42473 * Esowiki201529A * (+9) /* Hello, World! */
08:54:19 <HackEgo> [wiki] [[Gibberish/JavaScript]] http://esolangs.org/w/index.php?diff=42475&oldid=42474 * Esowiki201529A * (+1) /* Hello, World! */
08:57:38 <HackEgo> [wiki] [[Gibberish/JavaScript]] http://esolangs.org/w/index.php?diff=42476&oldid=42475 * Esowiki201529A * (+28) /* Hello, World! */
09:07:31 -!- vodkode_ has quit (Ping timeout: 276 seconds).
09:07:53 <oerjan> elliott: the thought has appeared to me
09:13:27 -!- hassa-aravit has quit (Remote host closed the connection).
09:42:40 -!- dianne has quit (Quit: byeannes).
09:52:18 <mroman> zzo38: does urn:bible include books banned by catholic church?
09:52:29 <mroman> and you probably need an identifier for "which bible" and "which version" of the bible
09:52:41 -!- Gregor` has joined.
09:53:05 -!- Gregor` has changed nick to Guest47678.
09:53:14 <mroman> or is that urn:apocrypha?
10:00:56 -!- Gregor has quit (*.net *.split).
10:00:56 -!- APic has quit (*.net *.split).
10:02:51 <mroman> > plot (-x -> x) 0 (10 :: Int)
10:02:52 <lambdabot> Pattern syntax in expression context: - x -> x
10:02:57 <mroman> > plot (\x -> x) 0 (10 :: Int)
10:02:59 <lambdabot> No instance for (RealFrac Int) arising from a use of ‘plot’
10:02:59 <lambdabot> In the expression: plot (\ x -> x) 0 (10 :: Int)
10:03:15 <mroman> > plot (\x -> x) 0 (10 :: Float)
10:03:36 <mroman> > plot (\x -> 1/x) 1 (10 :: Float)
10:03:49 <mroman> > plot (\x -> 1/x) 1 (20 :: Float)
10:03:59 <mroman> > plot (\x -> 10/x) 1 (20 :: Float)
10:17:27 -!- Phantom_Hoover has quit (Remote host closed the connection).
10:19:08 -!- Phantom_Hoover has joined.
10:24:21 -!- TheM4ch1n3 has quit (Ping timeout: 245 seconds).
10:27:50 -!- boily has joined.
10:40:22 <lambdabot> arising from a use of ‘show_M714213049450625511621244’
10:40:40 <FireFly> I don't suppose @src works for @let'd functions?
10:40:43 <lambdabot> Source not found. stty: unknown mode: doofus
10:45:52 <mroman> > plot (\x -> x + 1/x + 1/(1+x)) 1 (20 :: Float)
10:46:10 <mroman> > plot (\x -> x + 1/x + 1/(1+x) + 1/(1/(1+x)))) 1 (20 :: Float)
10:46:12 <lambdabot> <hint>:1:45: parse error on input ‘)’
10:46:15 <mroman> > plot (\x -> x + 1/x + 1/(1+x) + 1/(1/(1+x))) 1 (20 :: Float)
10:52:01 <mroman> I found a way to calculate log(2) o_O
10:52:17 <mroman> sum_{i=1}^{N} (1/(N+i))
10:53:24 <mroman> sum_{i=1}^{N} (1/(x*N+i)) approaches log(1+x^-1)
10:54:03 <mroman> so by choosing x I can calculate every log \o/
11:00:34 <mroman> can wolframalpha tell me that?
11:01:50 <mroman> It doesn't understand convergence rate
11:02:02 <int-e> you're approximating 1/x by a step function? usually that ends up with with an O(1/N) error term; with some luck, O(1/N^2) if you center the steps on the curve (but you didn't).
11:03:23 <int-e> (1/(x*N+i)) <-- not here
11:03:55 -!- Guest47678 has changed nick to Gregor.
11:04:18 <mroman> @def myLog N x = sum [1/(x*N+i)|<-[1..N]]
11:04:19 <lambdabot> .L.hs:162:7: Not in scope: data constructor ‘N’
11:04:20 <lambdabot> .L.hs:162:27: Not in scope: data constructor ‘N’
11:04:24 -!- Gregor has changed nick to Guest75683.
11:04:30 <mroman> @def myLog n x = sum [1/(x*n+i)|<-[1..n]]
11:04:35 <mroman> @def myLog n x = sum [1/(x*n+i)|i<-[1..n]]
11:05:59 <mroman> doesn't look like it converges fast :)
11:06:18 -!- nszceta has joined.
11:06:21 <mroman> 10000 steps for four digits isn't that fast I guess
11:06:55 <lambdabot> (Enum a1, RealFrac a) => (a1 -> a) -> a1 -> a1 -> Doc
11:08:17 <int-e> What you're doing is to evaluate int_{x}^{x+1} 1/x dx = log(1+1/x) by a (lower) Riemann sum.
11:08:32 <mroman> @def myLog n x = (sum [1/(x*(n+i))|i<-[1..n]])*x
11:08:33 <lambdabot> In an equation for ‘myLog’: myLog n x = ...
11:08:38 <mroman> @def myLog' n x = (sum [1/(x*(n+i))|i<-[1..n]])*x
11:09:04 <mroman> > [log 2, myLog 100 1, myLog' 100 1]
11:09:05 <lambdabot> [0.6931471805599453,0.690653430481824,0.690653430481824]
11:10:27 <int-e> @def let myLog n x = (sum [1/(x*(n+i-1/2))|i<-[1..n]])*x in myLog 100 1
11:10:27 <lambdabot> Parse failed: TemplateHaskell is not enabled
11:10:31 <int-e> > let myLog n x = (sum [1/(x*(n+i-1/2))|i<-[1..n]])*x in myLog 100 1
11:11:13 -!- hjulle has joined.
11:12:00 <int-e> (This one should have an O(1/N^2) error term, but I don't want to prove that rigorously.)
11:13:47 <mroman> I'm trapped in a channel empty of fungots.
11:14:12 <mroman> (... and full of weirdos)
11:15:47 <mroman> Why does the UK forbid rageporn?
11:16:04 <mroman> Shouldn't it be already illegal to upload videos of other people without their consens?
11:18:02 <int-e> We live in an age of overregulation of private life, and excessive freedom for corporations, in the name of safety and prosperity, respectively. Of course we're missing both targets.
11:18:26 <nszceta> Do everything within the context of a corporation and it's A-OK
11:18:34 <int-e> (The prosperity one works better, for the top 1%)
11:19:19 <mroman> hm. perhaps for longer sentences.
11:20:01 <int-e> it also saved talk shows for another two weeks.
11:20:10 <fizzie> Oh, right, we had that network blip.
11:20:15 <mroman> In Germany violating personalyt rights like that apperentely gives you 2 years maximum.
11:20:55 -!- fungot has joined.
11:22:43 <int-e> mroman: Oh all my convergence rate discussion above assumes that x>0.
11:23:14 <mroman> what's a summary conviction?
11:29:06 -!- boily has quit (Quit: UNNAMABLE CHICKEN).
11:35:32 <gniourf> ln(2)=sum_{k=1}^\infty 1/(k*2^k)
11:35:54 <gniourf> it uses the fact that ln(1/2)=-ln(2) and the standard Taylor series for ln at 1
11:36:24 <gniourf> the remainder of the partial sum of order N is less than 1/(N+1)2^N
11:36:41 <gniourf> very likely smaller, but that's a good starting point
11:37:42 <gniourf> more generaly, if you want a ln, you can use the arctanh function
11:50:25 -!- zadock has joined.
11:55:12 -!- ProofTechnique has quit (Ping timeout: 272 seconds).
12:11:40 -!- zadock has quit (Quit: Leaving).
12:11:43 -!- tromp_ has quit (Ping timeout: 244 seconds).
12:14:28 -!- rdococ has joined.
12:21:01 -!- Patashu has quit (Ping timeout: 244 seconds).
12:25:23 <fungot> b_jonas: i say we should learn it. then i starved to death anyway. let's do it, well, there's diversity in scheme community. it's uniting a substantial subset of the environment
12:25:47 <mroman> Phantom_Hoover: uploading sex tapes with your ex
12:26:10 <rdococ> I wonder if it's possible to create a language, without storage, that is turing complete anyway?
12:26:22 <mroman> My english fucked up again :(
12:26:24 <Phantom_Hoover> rageporn just sounds like people having sex while very, very angry
12:26:26 <int-e> rdococ: lambda calculus?
12:26:47 <int-e> rdococ: "storage" is such a malleable term
12:26:49 <mroman> but didn't UK outlaw BDSM and that stuff anyway some time ago?
12:26:54 <rdococ> ugh, lambda calculus is mentioned again?
12:28:24 <rdococ> I'm thinking of a language that has curved dimensions, so it loops? or even more esoteric would be a language where the code is run, then a flipped variant, and so on in a mobius strip
12:29:20 <Phantom_Hoover> mroman, i think what happened is that the film censors in the UK have some very outmoded obscenity rules which have been ignored for a long time because they only applied to the dead-in-the-water industry of videos being sold as tapes or dvds
12:30:22 <Phantom_Hoover> then their authority was extended to cover internet porn and suddenly everyone realised how regressive they are
12:31:39 -!- tromp_ has joined.
12:32:48 -!- rdococ has quit (Ping timeout: 246 seconds).
12:34:03 <mroman> yeah and swiss people kept laughing at the UK for that :)
12:34:20 <mroman> not realizing that a lot of that stuff is still in the gray-zone of law in switzerland as well
12:37:46 -!- ProofTechnique has joined.
12:48:08 <fizzie> fungot: You starved to death? What do you even eat?
12:48:08 <fungot> fizzie: the repl will never be a name for that procedure. and those that can handle arbitrary library calls entirely from scheme.
12:51:34 <HackEgo> [wiki] [[Object oriented thue]] http://esolangs.org/w/index.php?diff=42478&oldid=42400 * 4D enthusiast * (+432)
12:52:44 -!- rdococ has joined.
12:53:30 <rdococ> is it possible to make a language which is turing complete even if you can only use three instructions in a program?
12:54:37 <FreeFull> As in, three instructions total for the whole program?
12:55:06 <b_jonas> fungot, why is github so popular?
12:55:06 <fungot> b_jonas: somebody sort of gave it away. i found that extremely simple :) and conceived with dumb compiler in mind :)
12:55:20 <FreeFull> An instruction could be "execute this data using a different universal turing machine"
12:55:28 <fungot> b_jonas: and god created the heaven and the earth. and the debt is growing like hell. maybe they've fixed some of this
12:57:25 <izabera> so uhm this is just a mockup but how does it look? http://arin.ga/kjG5Kw/raw
12:58:37 <rdococ> FreeFull: that's called cheating lol
12:59:27 <rdococ> it doesn't matter if it has to be looped, it just has to be three instructions
12:59:37 <rdococ> other than loop syntax
13:00:04 <rdococ> infact I'd prefer if it looped.
13:00:08 <FreeFull> rdococ: As long as the instructions are allowed to provide an arbitrary amount of data, and the language has an infinite number of states, you certainly can make it turing complete
13:00:46 <mroman> Can I just use 1 and 0 to encode instructions?
13:00:59 <FreeFull> If you limit the size of the program including the data, it's not turing complete because there are things that a turing complete language could compute, but this language couldn't
13:01:00 <rdococ> thats why I had the idea of an infinite state machine and regexp matching
13:01:03 <mroman> and then using a state machine behind using some prefix-free "instructions"
13:01:26 <mroman> 1 and 0 are instructions that switch to a state and check if it arrived at a state with an action
13:01:33 <mroman> then execute that action.
13:02:36 <rdococ> an infinite state machine would be like an FSM, but it would have infinitely many states generated by regexp based transitions. For example, you could do string $1 - concat $2 -> string $1$2, which would work for any $1 and $2.
13:02:46 <rdococ> so, using my example, string derp -- concat herp -> string derpherp
13:02:59 <mroman> Because I can encode braifuck this way... no problem.
13:04:56 <mroman> there are languages that only work by string replacement
13:05:30 <rdococ> and I had one but I didn't make an article about it
13:05:32 -!- doesthiswork has joined.
13:05:39 <mroman> nope forget what I said... that was stupid.
13:06:23 <rdococ> using regexp matching and string replacement, its possible to do pretty much anything
13:06:35 <rdococ> idk if that means turing complete or not
13:08:11 <rdococ> my internet is terrible
13:12:23 -!- rdococ has quit (Quit: Page closed).
13:12:27 <FreeFull> You need infinitely many possible input states to have infinitely many possible output states
13:14:46 -!- Guest75683 has changed nick to Gregor.
13:18:05 <mroman> Do you need infinitely many possible output states?
13:18:48 <mroman> Maybe your output is limited to True/False.
13:26:10 <izabera> http://lisperator.net/pltut/ cool resource ^^
13:28:58 <izabera> no it's not about lisp >.>
13:29:21 <gniourf> you should say: “yes, I want to do Lisp”
13:31:10 <HackEgo> [wiki] [[Object oriented thue]] http://esolangs.org/w/index.php?diff=42479&oldid=42478 * Esowiki201529A * (+11) /* stdio */
13:33:04 <mroman> fungot: Do you want to do LISP?
13:33:04 <fungot> mroman: and implementing it in d or asm? /me boggle?
13:33:16 <mroman> Sure, I have nothing against a LISP interpreter in asm.
13:33:48 <mroman> Even better if it can fit on a floppy disc boot sector.
13:35:21 <mroman> fungot: Would you want to be written in LISP?
13:35:22 <fungot> mroman: is the official brainfuck forum. it happened to you? :) ( i'm attracted to these types of tools too.
13:36:38 <HackEgo> [wiki] [[Object oriented thue]] http://esolangs.org/w/index.php?diff=42480&oldid=42479 * Esowiki201529A * (+50) /* stdio */
13:39:47 <HackEgo> [wiki] [[Object oriented thue]] http://esolangs.org/w/index.php?diff=42481&oldid=42480 * 4D enthusiast * (+1253) rewrote syntax description, modified file & time library definitions, fixed 99 bottles of beer program
13:47:16 -!- APic has joined.
13:56:25 <mroman> fungot: There's a brainfuck forum?
13:56:25 <fungot> mroman: the explanation is really bad... i've got a bunch in sequence, with no macros, lambda severely limited, slow. because i think they point to the page
14:00:45 <izabera> where does it take these quotes from?
14:02:02 <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
14:02:09 <fungot> Selected style: irc (IRC logs of freenode/#esoteric, freenode/#scheme and ircnet/#douglasadams)
14:02:45 <int-e> izabera: note that they're not quotes; fungot uses a markov-like model for babbling
14:02:45 <fungot> int-e: i can think of things like fnord in srfi-1? laml? tspl? srfi-news?
14:03:21 <int-e> And "fnord" stands for an infrequent word, for example. Fizzie can probably tell you all about it.
14:03:50 <fungot> Selected style: enron (subset of the Enron email dataset)
14:03:56 <fungot> int-e: didn't know that the are two sections resulting in the lowest and highest fares found for your routes to get out any paper on the california power market.
14:07:21 <int-e> fungot: what do you think of fraud?
14:07:21 <fungot> int-e: i don't that will here tomorrow." ???contact john woolfolk at jwoolfolksjmercury.com ?mailto:jwoolfolksjmercury.com or the new in the thinkbank and find the full, and their work on the monday meeting on the construction industry the tariff.
14:07:23 -!- `^_^v has joined.
14:07:48 <fungot> Selected style: irc (IRC logs of freenode/#esoteric, freenode/#scheme and ircnet/#douglasadams)
14:09:30 -!- cirillo74 has joined.
14:09:36 -!- cirillo74 has quit (Client Quit).
14:16:33 <mroman> fungot: Interest in a ponsy scheme?
14:16:34 <fungot> mroman: or what id id) you can still find the original reppy paper not on acm. must have. i only care about the alphabet
14:17:57 -!- doesthiswork has quit (Quit: Leaving.).
14:18:06 <b_jonas> a ponzy scheme? or a ponys scheme?
14:24:09 <mroman> b_jonas: It's a ponzy scheme with ponys.
14:24:10 <int-e> hmm, this may have been intentional
14:24:17 <mroman> therefore I created a new word ponsy scheme
14:24:18 <int-e> I hate this channel, everyone's so smart :)
14:24:41 <mroman> although it's probably ponies
14:24:58 <mroman> fungot: Except you. You're okay.
14:24:58 <fungot> mroman: welcome to drscheme, just because you are trying to access
14:40:29 -!- nszceta has quit (Quit: Textual IRC Client: www.textualapp.com).
14:53:59 -!- Gregor has changed nick to Guest75683.
14:55:57 <fungot> Selected style: qwantz (Dinosaur Comics transcriptions 2003-2011)
14:56:00 <fungot> mroman: in the second example, there," came a cry from across the room, you can reconstruct you from those! this algorithm for relationship satisfaction. tada!
14:56:24 <mroman> fungot: An algorithm for relationship satisfaction would probably be worth a lot of money.
14:56:24 <fungot> mroman: as a man concerned, t-rex, that going shopping was your default activity?"
14:56:51 <mroman> fungot: I like shopping.
14:57:07 <mroman> damn I exceeded my limit again.
15:04:05 <HackEgo> [wiki] [[Special:Log/upload]] upload * Esowiki201529A * uploaded "[[File:Funciton-factorial-call.png]]"
15:05:58 -!- Sprocklem_ has quit (Ping timeout: 256 seconds).
15:06:13 <int-e> fungot: What is a funciton?
15:06:13 <fungot> int-e: but to compare, the number of burgers to eat when i get one
15:06:37 -!- nycs has joined.
15:06:39 -!- `^_^v has quit (Ping timeout: 252 seconds).
15:06:43 <int-e> `learn A funciton is the number of burgers to eat when I get one.
15:07:06 <fungot> int-e: all i've got to show for the past week is a bunch a few nights later. now it's only used when it's time to make some changes around here, you were a real dick on the internet!!" it's enough to make me put down the newspaper, fold it in two, smooth.
15:07:23 <HackEgo> Learned 'funciton': A funciton is the number of burgers to eat when I get one.
15:08:56 -!- MDream has changed nick to MDude.
15:10:13 <HackEgo> [wiki] [[File:Funciton-factorial-call.png]] http://esolangs.org/w/index.php?diff=42483&oldid=42482 * Esowiki201529A * (+12)
15:17:37 -!- nycs has changed nick to `^_^v.
15:27:06 -!- ProofTechnique has quit (Ping timeout: 256 seconds).
15:32:24 -!- ProofTechnique has joined.
15:36:25 -!- tswrcclt has joined.
15:54:37 -!- GeekDude has joined.
15:58:44 <int-e> neat. https://ghc.haskell.org/trac/ghc/ticket/9858#comment:84 (for shachaf, oerjan and Taneb?)
15:59:21 <int-e> (as usual I did not see any e-mail notification for this)
16:00:39 <Taneb> Although I deserve none of the credit for that
16:03:45 -!- variable has joined.
16:08:35 -!- bb010g has quit (Quit: Connection closed for inactivity).
16:24:30 <FireFly> I'm not sure what I deserve karma for, but thanks
16:38:43 -!- tertu has joined.
16:55:42 <int-e> mroman++ <-- random scoring
17:01:46 -!- Guest75683 has changed nick to Gregor.
17:03:31 -!- tertu has quit (Ping timeout: 245 seconds).
17:04:36 -!- aretecode has joined.
17:11:14 <zzo38> Now you have to fix DOSBOX to support CGA hicolor
17:12:55 <zzo38> And other features of 8088 MPH demo.
17:13:24 -!- Hijiri has quit (Quit: WeeChat 1.0.1).
17:17:01 -!- Sprocklem has joined.
17:22:43 -!- bb010g has joined.
17:37:32 -!- dianne has joined.
17:39:57 -!- Vorpal has quit (Ping timeout: 255 seconds).
17:50:15 -!- tswrcclt has quit (Quit: Connection closed for inactivity).
17:54:01 -!- Vorpal has joined.
17:54:01 -!- Vorpal has quit (Changing host).
17:54:01 -!- Vorpal has joined.
17:55:31 -!- J_Arcane has quit (Quit: ChatZilla 0.9.91-rdmsoft [XULRunner 32.0.3/20140923175406]).
18:00:14 <mroman> fungot: What's your karma?
18:00:14 <fungot> mroman: in a good story, they function in an undiagnosable way? for instance, i've recently picked up a hobby, and it's been super great! i signed up for an english as a second language course.
18:00:17 <fungot> mroman: you you dedicated bible ii to me??
18:00:29 <mroman> Yeah I dedicated a bible to fungot.
18:00:29 <fungot> mroman: t-rex, i don't know! maybe! i've never been to the bottom of a bottle.
18:00:32 <mroman> I forgot to mention that.
18:03:11 -!- J_Arcane has joined.
18:14:33 -!- vodkode_ has joined.
18:32:24 -!- nszceta has joined.
18:41:27 <HackEgo> [wiki] [[User:Rdococ]] http://esolangs.org/w/index.php?diff=42484&oldid=42434 * Rdococ * (+20)
18:41:50 -!- roasted42 has joined.
18:42:48 -!- roasted42 has changed nick to TheM4ch1n3.
18:42:48 -!- TheM4ch1n3 has quit (Changing host).
18:42:48 -!- TheM4ch1n3 has joined.
18:47:35 -!- TheM4ch1n3 has quit (Quit: bye).
19:07:25 -!- Frooxius has joined.
19:13:19 -!- adu has joined.
19:18:40 <olsner> heh, "The astonishingly-ingenious trio of Shachaf Ben-Kiki, Ørjan Johansen and Nathan van Doorn managed to persuade GHC 7.10.1 to cough up unsafeCoerce."
19:18:56 <zzo38> Can logic-based and aspect-oriented and reactive and rule-based programming be combined together if the input format is RDF?
19:19:06 <olsner> (from the commit message of the fix)
19:19:17 <zzo38> olsner: I saw that too yes
19:20:23 <b_jonas> I've no idea what that means, but let's see
19:20:29 <b_jonas> `8-ball Can logic-based and aspect-oriented and reactive and rule-based programming be combined together if the input format is RDF?
19:20:40 <b_jonas> fungot, Can logic-based and aspect-oriented and reactive and rule-based programming be combined together if the input format is RDF?
19:20:40 <fungot> b_jonas: you you dedicated bible ii to me?? it wat that easy! it's like buying a game that sounds like a crazy friday as weekend, why not monday too?
19:20:45 <b_jonas> that 8-ball response is wrong
19:20:53 <HackEgo> #!/bin/sh \ shuf -n 1 share/8ballreplies
19:21:03 <zzo38> Deciding the answer by randomly doesn't seem the way to do it in this circumstance.
19:21:05 <HackEgo> It is certain. \ It is decidedly so. \ Without a doubt. \ Yes definitely. \ You may rely on it. \ As I see it, yes. \ Most likely. \ Outlook good. \ Yes. \ Signs point to yes. \ Reply hazy try again. \ Ask again later. \ Better not tell you now. \ Cannot predict now. \ Concentrate and ask again. \ Don't count on it. \ My reply is no. \ My sources s
19:21:17 <zzo38> (It also does not tell you how even if the answer is yes.)
19:21:31 <b_jonas> yes, I wouldn't trust the 8-ball
19:23:04 <zzo38> I suppose 8-ball can still be use in case you do need to decide the answer at random, but my question isn't that kind of question.
19:27:27 -!- adu has quit (Quit: adu).
19:29:13 <elliott> olsner: oh, there was another unsafeCoerce?
19:32:22 <shachaf> It's the ((),()) => () unsafeCoerce
19:32:37 <olsner> elliott: it might be the same
19:35:48 -!- Hijiri has joined.
19:40:30 -!- vodkode_ has quit (Ping timeout: 248 seconds).
19:46:42 <olsner> https://ghc.haskell.org/trac/ghc/ticket/9858
19:47:07 -!- adu has joined.
19:50:21 <HackEgo> [wiki] [[State]] http://esolangs.org/w/index.php?diff=42485&oldid=42433 * Rdococ * (+229) examples
19:51:07 <HackEgo> [wiki] [[State]] M http://esolangs.org/w/index.php?diff=42486&oldid=42485 * Rdococ * (-4) /* Examples */
19:51:30 <HackEgo> [wiki] [[State]] http://esolangs.org/w/index.php?diff=42487&oldid=42486 * Rdococ * (+2) /* Examples */
20:15:17 <oerjan> excuse me while i bask in fame
20:16:25 <oerjan> hello fellow famous guy
20:19:07 <shachaf> I can add this to the list, alongside "ferociously-unintuitive".
20:20:25 <oerjan> what did you get that for
20:22:12 <shachaf> I guess SPJ isn't used to Leibniz equality.
20:22:13 <lambdabot> forall (k :: BOX) (a :: k) (b :: k). (Typeable a, Typeable b) => Maybe (a :~: b)
20:22:13 <shachaf> https://mail.haskell.org/pipermail/libraries/2013-March/019470.html
20:24:47 <shachaf> I think SPJ's fix takes this too far.
20:24:57 <shachaf> E.g. it breaks the Typeable instance for Dict.
20:25:31 <shachaf> There's nothing even somewhat impredicative about that.
20:25:36 -!- ProofTechnique has quit (Ping timeout: 250 seconds).
20:26:50 <shachaf> I got the impression it was intended for at least one release?
20:28:59 <oerjan> i do find it a bit disappointing how all the #9858 fixes remove some features
20:29:11 <oerjan> but i've already nagged enough about that
20:29:44 <shachaf> features like unsafeCoerce
20:30:19 <oerjan> i mean like deriving Typeable (Proxy a) from Typeable a
20:32:14 <oerjan> there's probably something involving type lists that gets really awkward because of it.
20:32:52 <oerjan> because you also cannot derive Typeable (a ': as) i think
20:33:56 <oerjan> otoh uses of Typeable and uses of fake dependent typing are probably a bit disjoint
20:34:10 <oerjan> b_jonas: : promoted to a type
20:34:36 <oerjan> well i vaguely recall that's the notation, i've never used it.
20:39:27 -!- Hijiri has quit (Quit: WeeChat 1.0.1).
20:42:49 -!- zzo38 has quit (Remote host closed the connection).
20:44:51 <oerjan> oh all the gcasts are written with eqT now
20:48:38 -!- vodkode has quit (Remote host closed the connection).
20:50:19 -!- vodkode has joined.
20:51:00 -!- Hijiri has joined.
20:51:48 -!- nszceta_ has joined.
20:53:11 <oerjan> edwardk: shachaf's comment might be relevant to your interests <shachaf> E.g. it breaks the Typeable instance for Dict.
20:53:31 -!- nszceta has quit (Ping timeout: 245 seconds).
20:53:47 <oerjan> well he seems a bit idle
20:55:03 <oerjan> @tell edwardk shachaf points out that the last fix for #9858 breaks e.g. Typeable Dict
20:58:53 -!- nszceta_ has quit (Quit: Textual IRC Client: www.textualapp.com).
20:59:14 <lambdabot> (Enum a1, RealFrac a) => (a1 -> a) -> a1 -> a1 -> Doc
20:59:20 <lambdabot> (Enum a1, RealFrac a) => (a1 -> a) -> a1 -> a1 -> Doc
21:05:45 <lambdabot> help <command>. Ask for help for <command>. Try 'list' for all commands
21:05:56 <lambdabot> eval provides: run let define letlpaste undefine
21:12:22 -!- Guest3780 has quit (Read error: Connection reset by peer).
21:14:49 -!- Guest3780 has joined.
21:21:19 -!- Sprocklem has quit (Ping timeout: 250 seconds).
21:26:55 <oerjan> "GHC 7.4 gave us the ability to talk about ConstraintKinds. They stopped crashing the compiler in GHC 7.6."
21:37:03 <orin> I don't see how a compiler can meaningfully be said to support somthing if it crashes
21:37:06 <oerjan> comment on the top of edwardk's constraints package
21:42:22 -!- ProofTechnique has joined.
21:44:47 -!- Hijiri has quit (Quit: WeeChat 1.0.1).
21:52:23 -!- tertu has joined.
22:02:41 -!- tertu has quit (Ping timeout: 245 seconds).
22:02:48 -!- variable has quit (Ping timeout: 244 seconds).
22:04:12 <oerjan> if you have all of SKI, then flat combinator calculus can express (.) as S I K S K
22:04:33 <oerjan> :t ap id const ap const
22:04:34 <lambdabot> Occurs check: cannot construct the infinite type:
22:04:34 <lambdabot> Expected type: ((a -> (a -> a) -> b) -> (a -> a -> a) -> a -> b)
22:07:01 <lambdabot> Occurs check: cannot construct the infinite type: a ~ b -> a -> b1
22:07:01 <lambdabot> Expected type: ((b -> a -> b1) -> (b -> a) -> b -> b1)
22:07:07 <lambdabot> Occurs check: cannot construct the infinite type:
22:07:07 <lambdabot> Expected type: ((b1 -> a) -> b) -> b1 -> a
22:14:37 <oerjan> > tyConPackage $ typeRepTyCon $ typeOf $ fromList [(1,2)]
22:14:38 <lambdabot> Couldn't match expected type ‘Item r0’ with actual type ‘(t0, t1)’
22:14:38 <lambdabot> The type variables ‘t0’, ‘t1’, ‘r0’ are ambiguous
22:14:55 <oerjan> > tyConPackage $ typeRepTyCon $ typeOf $ fromList [(1::Int,2::Int)]
22:14:56 <lambdabot> Couldn't match expected type ‘Item r0’
22:14:56 <lambdabot> The type variable ‘r0’ is ambiguous
22:15:19 <oerjan> > tyConPackage $ typeRepTyCon $ typeOf $ Data.Map.fromList [(1,2)]
22:15:28 <oerjan> > tyConPackage $ typeRepTyCon $ typeOf $ M.fromList [(1,2)]
22:15:54 <oerjan> :t tyConPackage $ typeRepTyCon $ typeOf $ M.fromList [(1,2)]
22:17:54 -!- `^_^v has quit (Ping timeout: 264 seconds).
22:23:09 <oerjan> it's _really_ annoying that the ghc 7.10.1 online docs have broken source links.
22:28:08 -!- adu has quit (Ping timeout: 256 seconds).
22:29:59 <shachaf> oerjan: By the way, someone linked to https://www.fpcomplete.com/blog/2015/03/minghc-ghc-7-10 in #haskell recently.
22:30:34 * oerjan swats shachaf -----###
22:30:51 <shachaf> what did i even do this time
22:31:09 <oerjan> you hinted that i should install minghc tdnh hth
22:31:24 <shachaf> wait, is there something bad about minghc
22:31:41 <shachaf> I thought the main reason to wait for the Haskell Platform on Windows was that GHC didn't come with an installer.
22:33:43 <oerjan> i like that it comes with precompiled packages.
22:34:37 <shachaf> puns don't cut it anymore?
22:35:06 <oerjan> also, i _really_ thought the plan to get a platform out in about a week was going to work.
22:35:18 <oerjan> but obviously it snagged somewhere.
22:35:56 <oerjan> or maybe they saw #9858 and decided to wait.
23:00:33 -!- Hijiri has joined.
23:06:40 -!- Hijiri has quit (Ping timeout: 256 seconds).
23:11:59 <oerjan> hm dependent on exactly what Kind.isConstraintKind checks, there might be a way to get around spj's fix...
23:12:51 -!- vodkode_ has joined.
23:17:14 <elliott> not allowing Typeable on Constraint seems sad.
23:17:22 <elliott> isn't GHC meant to be gettin more unified
23:17:50 <elliott> also, I'm not sure HP is going to get another release, from what I vaguely heard a while ago.
23:18:07 <elliott> I guess your information is newer than mine
23:18:37 <oerjan> this was after 7.10.1 came out
23:18:38 -!- Hijiri has joined.
23:34:06 -!- Guest3780 has quit (Ping timeout: 248 seconds).
23:38:42 -!- bb010g has quit (Quit: Connection closed for inactivity).
23:38:49 -!- Sprocklem has joined.
23:42:43 <elliott> is Typeable on Constraint impredicative because you have Typeable Typeable?
00:00:35 -!- encapsulation has quit (Remote host closed the connection).
00:09:50 -!- doesthiswork has joined.
00:16:04 -!- Gregor has changed nick to Guest75683.
00:24:27 <edwardk> i love how 'hey we'll slip a little infelicity into the type system for some sweet sweet sugar becomes' "oh fuck"
00:24:48 <HackEgo> [wiki] [[Gibberish/JavaScript]] http://esolangs.org/w/index.php?diff=42488&oldid=42476 * Esowiki201529A * (+443) /* Example */
00:25:01 <edwardk> er the quotes there were somewhat random =)
00:25:54 <edwardk> you know this is fixable. we typecheck these tuples correctly in ermine.
00:27:17 <oerjan> baking the result of isConstraintKind k into the TypeRep should work about as well, shouldn't it?
00:27:19 <edwardk> we explored something similar to the "limited sub-superkinding" system at the end of http://comonad.com/reader/2011/what-constraints-entail-part-1/ but switched to using another level of quantification like SPJ proposed to fix the need for sub-superkinding
00:29:19 <edwardk> basically if you replace kind * # and Constraint with a single kind (Sort a b) -- where a and b can range over a very simple domain say {T, F}, then you can talk about * as Sort T T, Constraint as Sort T F, and # as Sort F T, then using quantifiers over a and b lets you talk about the ambiguity of the kinds involved.
00:29:43 <edwardk> now type () has kind forall a. Sort T a
00:30:12 <edwardk> type (,) has kind forall a. Sort T a -> Sort T a -> Sort T a
00:30:44 <edwardk> type (->) has kind forall a b. Sort a T -> Sort b T -> Sort T T
00:30:48 -!- bb010g has joined.
00:30:55 <edwardk> and type inference proceeds as usual.
00:31:26 <edwardk> Sort F F us currently uninhabited but would be used for 'unboxed constraints' if they ever existed.
00:31:27 <oerjan> edwardk: make T a variable and include unboxed typles as well? >:)
00:31:44 <edwardk> unboxed tuples fit into # now.
00:32:14 <oerjan> i mean you could unify all three (,)s, maybe
00:32:39 <edwardk> doesn't work, because you want * -> * -> # for (#,#)
00:32:51 <edwardk> as well as # -> * -> # etc
00:34:18 <oerjan> do you know what exactly isConstraintKind k checks in that fix? i'm wondering if it only hits the type being of kind Constraint itself, so (=>) and Ord unapplied still work?
00:34:44 <edwardk> type (#,#) has kind forall a b. Sort a T -> Sort b T -> Sort F T
00:34:47 <oerjan> (not that they're much useful without constraints)
00:35:22 <HackEgo> [wiki] [[Gibberish/JavaScript]] http://esolangs.org/w/index.php?diff=42489&oldid=42488 * Esowiki201529A * (+69) /* 99 bottles of beer */
00:35:35 <edwardk> anyways the above encoding is enough to solve the problem for good, but its a lot more invasive.
00:43:57 -!- Sgeo|web has joined.
00:44:08 <Sgeo|web> Apparently replacing the HD of the model I want nulls and voids the warranty
00:44:56 <oerjan> suddenly the trac is sending out Cc:s again, maybe they fixed it
00:45:12 <oerjan> or well, i didn't get goldfire's comment
00:46:59 <shachaf> Hmm, Show is still Typeable after the change.
00:49:09 <oerjan> that means (,) _constructor_ is also Typeable.
00:49:25 <oerjan> in fact i suspect the only thing you cannot get around is () :)
00:49:37 <orin> Sgeo|web: Your mistake there is getting a warranty
00:49:58 <shachaf> oerjan: how can (,) be Typeable if you can't even refer to it?
00:50:00 <oerjan> oh and NullaryConstraints
00:50:11 <Sgeo|web> orin: I've heard that this laptop might sometimes stop working, according to reviews
00:50:18 <oerjan> shachaf: you can tease it out with some type equalities
00:50:29 <shachaf> Oh, you managed to do that?
00:50:45 <oerjan> i think i did, maybe i should recheck
00:50:45 <shachaf> Something like what I was doing with Proxy to avoid KindSignatures?
00:50:57 <shachaf> I thought I tried it here and it didn't work but I didn't try very hard.
00:52:59 <oerjan> > let x :: forall a b c. (a b c ~ (Ord Int, Show Int)) => TypeRep; x = typeRep (Proxy a) in x
00:53:01 <lambdabot> Couldn't match expected type ‘Expr -> proxy0 a0’
00:53:01 <lambdabot> The function ‘Proxy’ is applied to one argument,
00:53:22 <oerjan> > let x :: forall a b c. (a b c ~ (Ord Int, Show Int)) => TypeRep; x = typeRep (Proxy :: Proxy a) in x
00:53:23 <lambdabot> Could not deduce (Typeable a) arising from a use of ‘typeRep’
00:53:23 <lambdabot> from the context (a b c ~ (Ord Int, Show Int))
00:54:14 <shachaf> > let x :: forall (a :: Constraint -> Constraint -> Constraint) b c. (a b c ~ (Ord Int, Show Int)) => TypeRep; x = typeRep (Proxy :: Proxy a) in x
00:55:00 <orin> Sgeo|web: Did any hardware engineers take a look at the cases where it stops working?
00:55:53 <oerjan> why in the world does it require a kind signature there
00:56:06 <edwardk> oerjan: ok, i posted a version of my encoding above to the trac
00:56:58 <orin> Hmm... I would try to find a different model then.
00:57:56 <oerjan> shachaf: can you tease out Typeable (Ord Int) from HEAD by deriving the parts separately?
00:59:26 <oerjan> if you cannot, that means it breaks polykindedness of type application, which is about the only feature this new system had...
00:59:52 <orin> of course, I tend to be conservative in my use of technology
01:00:02 -!- aretecode has quit (Quit: Toodaloo).
01:00:53 <orin> so it depends on your tradeoff of risk of failure versus awesomeness of the laptop
01:01:37 <shachaf> λ> let foo :: forall a b. (Typeable a, Typeable b) => Proxy a -> Proxy b -> Proxy (a b) -> TypeRep; foo _ _ _ = typeRep (Proxy :: Proxy (a b)) in foo (Proxy :: Proxy Ord) (Proxy :: Proxy Int) (Proxy :: Proxy (Ord Int))
01:01:54 <shachaf> (typeRep (Proxy :: Proxy (Ord Int)) is an error)
01:05:13 <oerjan> shachaf: you could make a post about this, if () is the only thing effectively forbidden...
01:06:52 <oerjan> (being the only builtin NullaryConstraint)
01:07:31 <oerjan> it is still quite possible that's enough to close the exploit holes, but...
01:08:11 <oerjan> i don't _quite_ trust that yet.
01:15:00 -!- tertu has joined.
01:19:36 <oerjan> edwardk: i thought -> could return unboxed values too...
01:21:26 <HackEgo> [wiki] [[User:Rdococ]] M http://esolangs.org/w/index.php?diff=42490&oldid=42484 * Rdococ * (+54)
01:22:15 <oerjan> shachaf: are you writing a post or should i do it
01:22:55 -!- Froox has joined.
01:26:35 -!- Frooxius has quit (Ping timeout: 245 seconds).
01:38:07 <shachaf> oerjan: I'm not writing it right now, at any rate.
01:38:17 -!- hjulle has quit (Ping timeout: 250 seconds).
01:49:06 -!- tertu has quit (Ping timeout: 244 seconds).
01:51:10 -!- tertu has joined.
01:51:34 -!- MDude has changed nick to MDream.
01:51:38 <oerjan> shachaf: btw you _did_ test your example above in HEAD, not just lambdabot?
01:52:15 -!- tertu has quit (Client Quit).
01:56:03 -!- rdococ has joined.
01:57:27 -!- rdococ has quit (Client Quit).
01:59:40 <HackEgo> [wiki] [[User:Rdococ]] M http://esolangs.org/w/index.php?diff=42491&oldid=42490 * Rdococ * (+99)
02:01:51 <HackEgo> [wiki] [[Befunge]] http://esolangs.org/w/index.php?diff=42492&oldid=42179 * 68.39.240.189 * (+123) /* Befunge-93 */
02:04:19 * oerjan barely resisted the urge to include the "shachaf> hth" line in the quote
02:06:12 <shachaf> oerjan: The second line works in HEAD.
02:13:08 <oerjan> i couldn't see any particular reason why it shouldn't when Ord worked, so.
02:13:19 -!- vodkode has quit (Remote host closed the connection).
02:25:02 <oerjan> hm the special property of () is that it's the only type that has ambiguous kind and TypeRep even if none of its arguments do.
02:26:01 <oerjan> everything else either includes kind information or has the output kind determined by the argument kinds
02:29:35 -!- Phantom_Hoover has quit (Remote host closed the connection).
02:29:40 <oerjan> oh hm that's technically not what i wanted to say
02:29:54 <oerjan> (,) has ambiguous kind unapplied
02:30:46 <oerjan> _however_, there is nothing that can take it as an unapplied argument which doesn't include kind information
02:31:42 <oerjan> > typeRep (Proxy (Proxy :: '[] -> *))
02:31:43 <lambdabot> <hint>:1:33: parse error on input ‘*’
02:32:02 <oerjan> > typeRep (Proxy :: (Proxy :: '[] -> *))
02:32:03 <lambdabot> <hint>:1:29: parse error on input ‘'’
02:32:12 <oerjan> > typeRep (Proxy :: (Proxy :: [] -> *))
02:32:13 <lambdabot> <hint>:1:30: parse error on input ‘]’
02:32:44 <oerjan> > typeRep (Proxy :: (Proxy :: () -> *))
02:32:46 <lambdabot> Expecting one more argument to ‘Proxy’
02:32:46 <lambdabot> Expected a type, but ‘Proxy’ has kind ‘() -> *’
02:32:46 <lambdabot> In an expression type signature: (Proxy :: () -> *)
02:32:53 <Hijiri> > typeRep (Proxy :: (Proxy (() -> *)))
02:32:54 <lambdabot> <hint>:1:33: parse error on input ‘*’
02:33:04 <Hijiri> > typeRep (Proxy :: (Proxy ('() -> *)))
02:33:06 <lambdabot> <hint>:1:34: parse error on input ‘*’
02:33:20 <oerjan> did int-e turn off DataKinds
02:34:09 <oerjan> > typeRep (Proxy :: Proxy (Proxy :: () -> *))
02:34:42 <oerjan> > typeRep (Proxy :: Proxy (Proxy :: '[] -> *))
02:34:43 <lambdabot> <hint>:1:35: parse error on input ‘'’
02:34:56 <oerjan> > typeRep (Proxy :: Proxy (Proxy :: [] -> *))
02:34:58 <lambdabot> <hint>:1:36: parse error on input ‘]’
02:35:17 <shachaf> > typeRep (Proxy :: Proxy (Proxy :: [*] -> *))
02:35:41 <oerjan> still, what happened to the kind-sensitivity
02:35:55 <oerjan> > > typeRep (Proxy :: Proxy (Proxy :: [*] -> *)) == typeRep (Proxy :: Proxy (Proxy :: () -> *))
02:35:56 <lambdabot> <hint>:1:1: parse error on input ‘>’
02:36:02 <oerjan> > typeRep (Proxy :: Proxy (Proxy :: [*] -> *)) == typeRep (Proxy :: Proxy (Proxy :: () -> *))
02:36:34 <shachaf> λ> typeRepKinds $ typeRep (Proxy :: Proxy (Proxy :: [*] -> *))
02:38:14 <oerjan> <shachaf> what about (,) hth <-- ((,),) ? makes no sense hth
02:39:35 <shachaf> it doesn't make much sense either way
02:40:06 <oerjan> shachaf: i specifically said that the (,) argument had to not have arguments hth
02:40:24 <oerjan> because otherwise, a and b determine its kind
02:45:50 <shachaf> is that good or bad or average?
02:47:12 <oerjan> (,) has two kinds, * -> * -> * and Constraint -> Constraint -> Constraint
02:47:37 <shachaf> it was more of a "no base case" sort of joke
02:47:53 <orin> shachaf: probably fine
02:48:55 <orin> I've run laptops at 130-140 for weeks on end with no problems
02:50:04 <oerjan> wait, this is the one case where you really _should_ say
02:50:31 <quintopia> yeah but omg should come first then
02:50:42 <orin> quintopia: I have a burn mark on my right hand from falling asleep with my hand on a laptop
02:50:53 * oerjan swats quintopia for breaking the joke on the first step -----###
02:51:18 <quintopia> oh...so this isnt a joke. just real idiocy. cool.
02:52:01 <quintopia> well not cool. the opposite of cool.
02:52:26 <oerjan> shachaf: your imitation falls flat hth
02:52:45 -!- Hijiri has quit (Quit: WeeChat 1.0.1).
02:52:54 * oerjan isn't very sharp at the moment
02:53:38 <oerjan> but i do think sharpening a swatter is overdoing it.
02:54:34 <shachaf> the real upgrade was in the handle
02:57:08 <orin> no but this bugswatter is literalyy made of bugs
02:58:22 <orin> WWWWWWWWWWWWWWWWWWWWW
03:16:02 <HackEgo> [wiki] [[Hashes]] http://esolangs.org/w/index.php?diff=42493&oldid=42217 * Esowiki201529A * (+21)
03:18:36 <oerjan> ah. DISPLAYTITLE has restrictions.
03:21:20 -!- Guest3780 has joined.
03:23:15 <HackEgo> [wiki] [[User talk:Esowiki201529A]] http://esolangs.org/w/index.php?diff=42494&oldid=42417 * Esowiki201529A * (+27)
03:24:03 <HackEgo> [wiki] [[User talk:Esowiki201529A]] http://esolangs.org/w/index.php?diff=42495&oldid=42494 * Esowiki201529A * (-2)
03:25:18 <HackEgo> [wiki] [[User talk:Esowiki201529A]] http://esolangs.org/w/index.php?diff=42496&oldid=42495 * Esowiki201529A * (+6)
03:34:31 -!- password2 has joined.
03:49:35 -!- GeekDude has quit (Quit: {{{}}{{{}}{{}}}{{}}} (www.adiirc.com)).
04:06:56 -!- vodkode_ has left ("Leaving").
04:16:55 <Sgeo|web> As in, if I start using Bitlocker, does that mean it's safe for me to send an intact laptop to be serviced without worrying about techs getting access to passwords etc?
04:17:16 <Sgeo|web> Combine that with encrypted cloud backup, and I won't have to worry about losing my data if I do that
04:22:42 -!- Hijiri has joined.
04:32:35 <HackEgo> [wiki] [[Special:Log/move]] move * Rdococ * moved [[State]] to [[Tar]]: Instead of just scrapping this and creating a similar one in its place...
04:37:25 <Jafet> Sounds like a lot of work just to avoid removing the drive.
04:37:52 <HackEgo> [wiki] [[Tar]] http://esolangs.org/w/index.php?diff=42499&oldid=42497 * Rdococ * (-491) Changes to everything, making it harder
04:58:25 -!- variable has joined.
04:59:06 -!- mitchs has quit (Quit: mitchs).
04:59:33 <Sgeo|web> Avoiding removing the drive avoids voiding warranties and drop protection and the like
05:04:40 <orin> AUGHH this is disgusting. because of these serrated discs, my dwrves have to haul each part of the troglodyte to the atomsmasher separately
05:06:22 <orin> You could use bitlocker I suppose... I would just store all sensitive data on an SD card or something
05:09:47 <orin> Hmm is it possible to configure firefox to put its password stuff on a removable drive?
05:11:13 -!- mitchs has joined.
05:12:45 <Hijiri> not an answer to your question
05:17:51 <orin> Yeah. I'm almost done draining the ocean
05:19:13 <HackEgo> [wiki] [[Tar]] M http://esolangs.org/w/index.php?diff=42500&oldid=42499 * Rdococ * (-10) /* Structure */
05:24:51 <orin> like most DF endeavours, this involves dwarf sacrifice
05:28:31 -!- variable has quit (Quit: 1 found in /dev/zero).
05:28:50 -!- variable has joined.
05:29:00 <orin> my FPS was down to 5, now it's up to 13
05:35:31 -!- password2 has quit (Ping timeout: 250 seconds).
05:42:45 <elliott> I wouldn't trust BitLocker against a government. I'd trust it against random tech support people.
05:50:00 <oerjan> you have to be sure they're sufficiently random hth
05:59:33 <edwardk> oerjan: it can. (->) :: Sort a T -> Sort b T -> Sort T T -- Sort b T is the 'return' kind. the Sort T T is the kind of the function itself.
06:00:14 <edwardk> screwed with me at first too =)
06:01:14 <oerjan> i am thinking that separating () :: Constraint and () :: * is all that is needed to stop this bug without outlawing Typeable constraints.
06:01:38 <oerjan> although intuitively, tuples and -> vs. => should also be separated.
06:02:31 <oerjan> and also, as i commented, outlawing Typeable (() :: Constraint) is the only thing the fix does properly.
06:11:11 <HackEgo> [wiki] [[Tar]] http://esolangs.org/w/index.php?diff=42501&oldid=42500 * Rdococ * (+1396) Added interpreter
06:11:44 -!- rdococ has joined.
06:12:16 <rdococ> People say turing tarpit...
06:12:24 <rdococ> I say finite state automaton tarpit.
06:14:47 <HackEgo> [wiki] [[User:Rdococ]] http://esolangs.org/w/index.php?diff=42502&oldid=42491 * Rdococ * (-8) added tar
06:19:48 <oerjan> edwardk: i guess i made an alternative proposal or three.
06:20:40 <oerjan> and _that_ i got a Cc: this is so random...
06:23:38 <oerjan> > typeRep (Proxy::Proxy(Proxy::'[()]->*)) == typeRep (Proxy::Proxy(Proxy::[()]->*))
06:23:39 <lambdabot> <hint>:1:30: parse error on input ‘'’
06:24:29 <oerjan> why doesn't lambdabot accept promoted datatypes. or wait isn't '[()] legal.
06:24:42 <b_jonas> oerjan: dunno, try '[] () maybe
06:25:50 <oerjan> you don't use that at the kind level, do you.
06:27:14 <oerjan> > typeRep (Proxy::Proxy '()) == typeRep (Proxy::Proxy ())
06:29:51 -!- MoALTz has quit (Quit: Leaving).
06:31:59 -!- Froox has quit (Quit: *bubbles away*).
06:33:26 -!- MoALTz has joined.
06:34:52 -!- variable has quit (Ping timeout: 250 seconds).
06:35:37 -!- vodkode_ has joined.
06:38:54 <izabera> opinions on this? https://gist.github.com/izabera/b2dc6515c7cfb05fc500
06:42:34 <HackEgo> [wiki] [[User:Rdococ]] M http://esolangs.org/w/index.php?diff=42503&oldid=42502 * Rdococ * (-190) /* My esoteric programming languages */
06:43:23 <HackEgo> [wiki] [[User:Rdococ]] M http://esolangs.org/w/index.php?diff=42504&oldid=42503 * Rdococ * (-52)
06:46:29 <shachaf> oerjan: your suggestion is more or less what i was thinking hth
06:47:30 <shachaf> maybe i should say it's more or less what i would've thought if i'd thought about it
06:47:35 <shachaf> ok, maybe i should just say i agree
06:54:00 <rdococ> izabera: can you program it?
06:54:28 <rdococ> can you program in it?
06:54:43 <rdococ> the code you linked to
06:55:04 <rdococ> it made me think of alarm clock radio
06:55:46 <rdococ> my joke's funny, right?
06:56:47 <rdococ> you know, if you smoke, you'll get http://esolangs.org/wiki/Tar and shameless self-advertisement in your body.
06:57:07 <rdococ> ...get it? it's called Tar? ...no?
06:57:44 <oerjan> rdococ: apropos shameless self-advertisement, you mentioned string search and replace languages so i must point you at http://esolangs.org/wiki////
06:58:02 <myname> it's so unfunny, it crossed the line where unfunny things become funny and is still unfunny there :p
06:58:08 <oerjan> (i did not invent it, but i did much of the rest.)
06:58:30 <rdococ> s/s////Thue/s/////Thue
06:58:32 <oerjan> rdococ: /// is simpler hth
06:58:52 <rdococ> string replacement is cool though
06:58:54 <izabera> is sed not esoteric enough?
06:59:03 <b_jonas> rdococ: I don't get it. how is it related to tar (the program already called tar)?
06:59:10 <oerjan> izabera: too many useless operations hth
06:59:18 <rdococ> b_jonas: what related to tar?
06:59:18 <b_jonas> rdococ: I understand why "Folders" is called that, but not "Tar"
06:59:27 <rdococ> b_jonas: ah, long story
06:59:45 <izabera> do you just write hth after every sentence or what
06:59:47 <rdococ> you see, it was originally called State and was a bit different
06:59:58 <oerjan> i'm going to assume it's a subtle comment on the nonexistence of Feather hth
07:00:10 <oerjan> izabera: not always hth
07:00:19 <myname> izabera: you must be new here
07:00:55 <rdococ> the principle was the same, but it was clogged... what I mean by clogged is that it was an OISC with 4 arguments... not 2...
07:01:00 <rdococ> so I reduced it and changed it
07:01:09 <b_jonas> um, but you've taken a pretty good name
07:01:18 <rdococ> I named it Tar, because it was a tarpit, but not a turing tarpit
07:01:19 <b_jonas> I mean, what if someone actually does an esolang that somehow uses the tar program
07:01:27 <rdococ> wait, what's the tar program?
07:01:44 <oerjan> oh no, then we will need our wiki's second disambiguation page!
07:02:03 <rdococ> so many name conflicts
07:02:06 <izabera> `` sed streetlight <<< reeter
07:02:18 <rdococ> I could rename it Tarp.
07:03:06 <HackEgo> [wiki] [[Tar]] M http://esolangs.org/w/index.php?diff=42505&oldid=42501 * Rdococ * (+3) changing name to tarp
07:03:52 <HackEgo> [wiki] [[Special:Log/move]] move * Rdococ * moved [[Tar]] to [[Tarp]]: possible naming conflicts with a possible esolang using some kind of 'tar program', whatever that is
07:04:23 <rdococ> I'll also go and delete the redirect
07:04:48 <HackEgo> [wiki] [[Tar]] http://esolangs.org/w/index.php?diff=42508&oldid=42507 * Rdococ * (-18) Blanked the page
07:04:50 <myname> rdococ: you are using windows, aren't you?
07:05:24 <rdococ> I knew there was a .tar extension
07:05:37 <rdococ> which could have caused a conflict
07:06:59 <izabera> http://sprunge.us/WMPa anyway this is a clock written in sed (honestly impressive)
07:08:26 <HackEgo> [wiki] [[User:Rdococ]] http://esolangs.org/w/index.php?diff=42509&oldid=42504 * Rdococ * (+1)
07:11:19 <HackEgo> [wiki] [[Tarp]] http://esolangs.org/w/index.php?diff=42510&oldid=42506 * Rdococ * (+0) okay, now I'm renaming it to Harp.... for some weird reason
07:11:44 <HackEgo> [wiki] [[Special:Log/move]] move * Rdococ * moved [[Tarp]] to [[Harp]]: ugh... make your mind up brain
07:12:54 <HackEgo> [wiki] [[User:Rdococ]] http://esolangs.org/w/index.php?diff=42513&oldid=42509 * Rdococ * (+0)
07:13:20 <rdococ> do you know what the goverment uses?! The http://esolangs.org/wiki/Harp machine!!!
07:13:43 <rdococ> Tarp just sounded too sharp...!!!
07:15:07 <HackEgo> [wiki] [[Harp]] M http://esolangs.org/w/index.php?diff=42514&oldid=42511 * Rdococ * (+17) /* Structure */ forgot a step in executing the only instruction in Harp
07:15:52 <rdococ> if I am to create a derivative of Harp, it would be called Darp.
07:16:18 -!- doesthiswork has quit (Quit: Leaving.).
07:17:47 <HackEgo> [wiki] [[Special:Log/delete]] delete * Oerjan * deleted "[[Tar]]": Author request: content before blanking was: "#REDIRECT [[Tarp]]"
07:18:45 -!- Sgeo|web has quit (Quit: Page closed).
07:19:58 <oerjan> rdococ: shall i just delete State and Tarp too?
07:20:10 <elliott> izabera: foo () for ... done scares me
07:20:23 <HackEgo> [wiki] [[Special:Log/delete]] delete * Oerjan * deleted "[[State]]": Author request: content was: "#REDIRECT [[Tar]]" (and the only contributor was "[[Special:Contributions/Rdococ|Rdococ]]")
07:20:35 <izabera> the function body must be a compound command
07:20:50 <izabera> { } is a compound command, but so is for ... done
07:20:54 <HackEgo> [wiki] [[Special:Log/delete]] delete * Oerjan * deleted "[[Tarp]]": Author request: content was: "#REDIRECT [[Harp]]" (and the only contributor was "[[Special:Contributions/Rdococ|Rdococ]]")
07:22:18 <izabera> `` -d? () [[ -d $1 ]]; -d? /bin && echo /bin is a directory
07:22:19 <HackEgo> bash: -d: invalid option \ Usage:bash [GNU long option] [option] ... \ bash [GNU long option] [option] script-file ... \ GNU long options: \ --debug \ --debugger \ --dump-po-strings \ --dump-strings \ --help \ --init-file \ --login \ --noediting \ --noprofile \ --norc \ --posix \ --protected \ --rcfile \ --restricted \ --verbose \
07:23:14 <izabera> `` :; -d? () [[ -d $1 ]]; -d? /bin && echo /bin is a directory
07:23:24 <izabera> who is the author of HackEgo ?
07:24:11 <elliott> not really a bug in hackego
07:24:16 <HackEgo> bash: -d: invalid option \ Usage:bash [GNU long option] [option] ... \ bash [GNU long option] [option] script-file ... \ GNU long options: \ --debug \ --debugger \ --dump-po-strings \ --dump-strings \ --help \ --init-file \ --login \ --noediting \ --noprofile \ --norc \ --posix \ --protected \ --rcfile \ --restricted \ --verbose \
07:24:46 <elliott> so it's cool that it's broken
07:24:59 <elliott> `run sed -i 's/-c/-c --/' 'bin/`'
07:25:15 <izabera> `` -d? () [[ -d $1 ]]; -d? /bin && echo /bin is a directory
07:25:18 <HackEgo> bash: -d: invalid option \ Usage:bash [GNU long option] [option] ... \ bash [GNU long option] [option] script-file ... \ GNU long options: \ --debug \ --debugger \ --dump-po-strings \ --dump-strings \ --help \ --init-file \ --login \ --noediting \ --noprofile \ --norc \ --posix \ --protected \ --rcfile \ --restricted \ --verbose \
07:25:21 <HackEgo> bash: -d?: command not found
07:25:33 <izabera> wait why did it error out?
07:25:35 <izabera> `` -d? () [[ -d $1 ]]; -d? /bin && echo /bin is a directory
07:25:36 <elliott> I don't think this is exploitable though
07:25:48 <elliott> (since you could just as easily `run bash -... if you wanted)
07:26:11 <elliott> @tell Gregor HackEgo `run foo should do bash -c -- foo rather than bash -c foo, or it breaks on `run -blah
07:26:23 <izabera> the idea of having /bin/` is clever
07:27:48 <HackEgo> /home/hackbot/hackbot.hg/multibot_cmds/lib/limits: line 5: exec: : not found
07:30:25 <elliott> izabera: `run doesn't actually need to be built in
07:30:37 <elliott> since you could do the same trick as `
07:30:55 <elliott> the built-ins are `run, `revert and `help I think
07:31:09 <elliott> you could make `help not built in, and you can make one of `run and `revert not built in
07:31:23 <elliott> since either would let you revert to an earlier revision if someone deletes everything
07:31:34 <elliott> but if you make them both not built in then anyone can just delete everything with no way to fix it >_>
07:50:28 <HackEgo> \ real0m0.871s \ user0m0.340s \ sys0m0.660s
07:51:43 <HackEgo> \ real0m1.023s \ user0m0.000s \ sys0m0.000s
07:51:58 <HackEgo> \ real0m0.321s \ user0m0.000s \ sys0m0.000s
07:52:43 <oerjan> elliott: can't you fix things with `/... commands anyway?
07:53:06 <izabera> `` TIMEFORMAT='real: %lR, user: %lU, sys: %lS'; time sleep 0.3
07:53:09 <elliott> you could do `/revert or whatever if that was added
07:53:14 <HackEgo> real: 0m0.316s, user: 0m0.000s, sys: 0m0.000s
07:53:19 <izabera> why does it take so long ._.
07:53:21 <elliott> ok run and help should become non-primitives then
07:53:29 <HackEgo> \ real0m1.524s \ user0m0.000s \ sys0m0.000s
07:53:29 <elliott> you don't need to revert rm -rf *
07:53:35 <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/
07:53:40 <HackEgo> /home/hackbot/hackbot.hg/multibot_cmds/lib/limits: line 5: exec: `time: not found
07:53:48 <HackEgo> \ real0m1.512s \ user0m0.000s \ sys0m0.000s
07:53:57 <HackEgo> \ real0m1.483s \ user0m0.000s \ sys0m0.000s
07:54:25 <elliott> izabera: because it also starts up user mode linux
07:54:50 <izabera> `` sed -i "s/^/TIMEFORMAT='real: %lR, user: %lU, sys: %lS' /" bin/\`
07:54:59 <HackEgo> real: 0m0.001s, user: 0m0.000s, sys: 0m0.000s \ x
07:55:37 <Jafet> Shouldn't that be in .bashrc
07:55:49 <izabera> .bashrc is only sourced in interactive shells
07:56:16 <elliott> oerjan: okay but `fetch would still be built in
07:56:33 <elliott> oerjan: I guess it could just get an HTTP proxy that lets you do what `fetch does but no more?
07:56:39 <elliott> i.e. GET only, filesize limit, etc.
07:57:04 <HackEgo> curl: try 'curl --help' or 'curl --manual' for more information
07:57:55 <HackEgo> Usage: curl [options...] <url> \ Options: (H) means HTTP/HTTPS only, (F) means FTP only \ --anyauth Pick "any" authentication method (H) \ -a, --append Append to target file when uploading (F/SFTP) \ --basic Use HTTP Basic Authentication (H) \ --cacert FILE CA certificate to verify peer against (SSL) \ --
07:58:09 <izabera> `` curl -F 'aringa=<-' arin.ga <<< 'hello from #esoteric'
07:58:10 <HackEgo> Failed to connect to socket 2. \ \ curl: (52) Empty reply from server
07:58:34 <HackEgo> /home/hackbot/hackbot.hg/multibot_cmds/lib/limits: line 5: exec: dig: not found
07:59:46 <elliott> the curl proxy it has is limited to a few websites
07:59:48 <rdococ> I wish there were a way to adver...hang on... why havent I added any of my languages to the list of languages... other than that old rotten FileCode that I hate
07:59:54 <elliott> so you couldn't replace `fetch with it
08:00:14 <rdococ> `curl -H 'esolangs.org'
08:00:15 <HackEgo> curl: no URL specified! \ curl: try 'curl --help' or 'curl --manual' for more information
08:00:25 <rdococ> `curl -H 'http://esolangs.org'
08:00:26 <elliott> the ideal would be that the entire bot was modifiable
08:00:26 <HackEgo> curl: no URL specified! \ curl: try 'curl --help' or 'curl --manual' for more information
08:00:29 <elliott> but that would be so usable
08:00:33 <rdococ> `curl -H http://esolangs.org
08:00:39 <elliott> maybe you could implement it as a nomic-style voting system
08:00:44 <HackEgo> curl: no URL specified! \ curl: try 'curl --help' or 'curl --manual' for more information
08:00:48 <elliott> with veto power given to some people
08:00:53 <HackEgo> Usage: curl [options...] <url> \ Options: (H) means HTTP/HTTPS only, (F) means FTP only \ --anyauth Pick "any" authentication method (H) \ -a, --append Append to target file when uploading (F/SFTP) \ --basic Use HTTP Basic Authentication (H) \ --cacert FILE CA certificate to verify peer against (SSL) \ --
08:00:56 <elliott> that would be cool... I should write that
08:01:09 -!- ais523 has joined.
08:01:15 <elliott> what you are doing is like curl '-F http://esolangs.org'
08:02:01 <rdococ> `run curl -F http://esolangs.org
08:02:02 <HackEgo> Warning: Illegally formatted input field! \ curl: option -F: is badly used here \ curl: try 'curl --help' or 'curl --manual' for more information
08:02:09 <rdococ> `run curl -H http://esolangs.org
08:02:09 <HackEgo> curl: no URL specified! \ curl: try 'curl --help' or 'curl --manual' for more information
08:02:16 <rdococ> `run curl -H 'http://esolangs.org'
08:02:17 <HackEgo> curl: no URL specified! \ curl: try 'curl --help' or 'curl --manual' for more information
08:03:01 <HackEgo> [wiki] [[Language list]] M http://esolangs.org/w/index.php?diff=42515&oldid=42340 * Rdococ * (+11) /* H */ added Harp
08:03:17 <oerjan> `/bin/bash -cecho hi #Testing
08:03:18 <HackEgo> /bin/bash: - : invalid option \ allexport off \ braceexpand on \ emacs on \ errexit on \ errtrace off \ functrace off \ hashall on \ histexpand on \ history on \ ignoreeof off \ interactive-commentson \ keyword off \ monitor off \ noclobber off \ noexec
08:03:24 <oerjan> `/bin/bash -c echo hi #Testing
08:03:25 <HackEgo> /bin/bash: - : invalid option \ Usage:/bin/bash [GNU long option] [option] ... \ /bin/bash [GNU long option] [option] script-file ... \ GNU long options: \ --debug \ --debugger \ --dump-po-strings \ --dump-strings \ --help \ --init-file \ --login \ --noediting \ --noprofile \ --norc \ --posix \ --protected \ --rcfile \ --restrict
08:03:34 <oerjan> ok bash cannot be used that way
08:04:06 <oerjan> `/usr/bin/perl -eprint "Hi!"
08:04:19 <HackEgo> [wiki] [[Language list]] M http://esolangs.org/w/index.php?diff=42516&oldid=42515 * Rdococ * (+41) /* F */ added Folder [not Folders]
08:06:42 <ais523> hi #esoteric! do you have any idea what the best way is to implement a program whose control structure between basic blocks looks like this?: http://nethack4.org/pastebin/ick-parser-substate-example.png
08:06:48 <ais523> because I don't, really
08:06:59 <ais523> trying to render that thing in terms of if and while doesn't work without extra variables
08:07:32 <ais523> I was definitely considering it
08:07:35 * oerjan sees "ick-parser" and starts to back away...
08:07:49 <ais523> the context is that I'm trying to write a YACC impl that produces human-like output code
08:07:54 <Jafet> Icky parser substrate
08:07:55 <ais523> but I have no idea what a human would write in this situation ;-)
08:08:25 <ais523> this is admittedly an extreme example, in most of the YACC grammars I tried the substate control graphs are much simpler
08:08:37 <orin> I would use goto or just have an integer state variable
08:10:09 <orin> (If the states have more meaning than just numbers, I might use labels or state number constants that reflect the meaning)
08:12:39 <ais523> I think I could probably use more meaningful names
08:12:59 <ais523> a state variable seems like a bad idea, that'd basically leave you in a for-switch situation
08:13:15 <ais523> still, I don't think you'd do the whole thing as a goto
08:13:23 <ais523> e.g. 10 and 13 both look like if statements
08:13:38 <ais523> 21/22 would be perfect for a while, except that it has two entry points
08:21:18 <ais523> functions + tailcalls is basically equivalent to a nest of gotos
08:22:07 <Deewiant> The flow tends to be clearer IME, but yes of course
08:22:07 <ais523> my current plan is to use the goto style in C if the control flow is sufficiently complex that you can't figure out what's going on, and replace it with mutually recursive tailcalls if we're using a functional language
08:23:07 <rdococ> ais523: I have a programming language called Harp... it looks like it might be perfect for your needs. Here: http://esolangs.org/wiki/Harp
08:23:16 <rdococ> it even has an interpreter, lol
08:23:34 <ais523> rdococ: to write my YACC impl in? or as a language to target?
08:24:19 <ais523> also that can't possibly be more powerful than an FSA, it only has one symbol of memory
08:24:37 <ais523> I don't think it's less powerful either, but that's less obvious
08:24:43 <rdococ> it's as powerful as a finite state machine
08:25:03 <ais523> ah right, yes, it's exactly as powerful as a finite state machine
08:25:11 <ais523> because you can just write a list of transitions after each label
08:25:39 <rdococ> no, if you read the specification of Harp...
08:26:43 <rdococ> it doesnt even have the concept of states.
08:26:59 <ais523> rdococ: yes it does, just indirectly
08:27:13 <orin> http://arin.ga/xtkSZO <-- this is the sort of code you get if you take the state variable approach
08:27:39 <b_jonas> ais523: for that particular example, only two states are in any loop (21 and 22), so you could implement it as a function for each state and then a single function with a while loop for those two states
08:27:55 <ais523> each instruction acts as a state whose transitions are listed on the subsequent lines, up to the next unconditional jump, ignoring any duplicates of previous transitions
08:28:31 <ais523> b_jonas: 21/22 would blatantly be a while loop if not for the fact you can enter it either way round (which says a lot about INTERCAL's syntax)
08:28:59 <ais523> orin: I don't find that very readable
08:29:15 <orin> The goto approach would have been better
08:29:16 <ais523> also that's basically a for/switch which is an antipattern
08:29:36 <ais523> yes, you literally have no advantage over goto there, and you're using goto anyway
08:29:45 <b_jonas> so for that you probably need a single state variable there, or else duplicate one of those states
08:29:57 -!- Patashu has joined.
08:30:27 <b_jonas> ais523: mind you, when I write code by hand, I use state variables a lot
08:30:39 <b_jonas> and I encourage state variables in while loops as good style
08:30:53 <ais523> I've been known to do that too, especially if there's a bunch of common code each time round the loop
08:30:58 <ais523> ayacc's parser works like that atm
08:31:08 <b_jonas> I don't meen the balatnt for{switch{}} kind of state variables of course
08:31:12 <ais523> (I couldn't sensibly autogenerate it for obvious reasons, so I wrote a hand-coded parser)
08:31:21 <b_jonas> just variables for quitting a loop or skipping some part of the code etc
08:33:26 <b_jonas> example for quitting loops early with state variables: http://russell2.math.bme.hu/~ambrus/sc/info1/info1-gy4.html#cell_16
08:34:18 <rdococ> wow, internet still working
08:34:42 <rdococ> my internet shouldn't be alive
08:35:43 <rdococ> anyway, it'd be easy to implement that diagram in Harp, as long as you don't care about the consistency of state names
08:36:03 <rdococ> I'd like to see someone use it
08:36:32 -!- Patashu has quit (Remote host closed the connection).
08:36:39 <ais523> well it's basically just a compression scheme for FSMs, and those tend not to get talked about much
08:36:49 -!- Patashu has joined.
08:37:19 <b_jonas> hehe "tend not to get talked about much"
08:37:21 <rdococ> what about my other esolang called Folder (not Folders
08:37:38 <b_jonas> wait that reminds me of this question
08:37:44 <rdococ> I wonder what an infinite state machine would be like
08:38:20 <b_jonas> http://cstheory.stackexchange.com/q/22493/8067 "Are there any open problems left about DFAs?"
08:39:14 <ais523> rdococ: we thought Folder was interesting, because its power most likely depends on filesystem features
08:40:52 -!- rdococ_ has joined.
08:41:42 <rdococ_> I seriously need ideas for a more interesting language
08:41:48 <rdococ_> I had an idea for an infinite state machine
08:42:04 -!- rdococ has quit (Ping timeout: 246 seconds).
08:42:10 -!- rdococ_ has changed nick to rdococ.
08:42:53 <Jafet> Transfinite state machines
08:45:19 -!- rdococ_ has joined.
08:45:39 <rdococ_> so, would an infinite state machine be turing complete
08:45:52 <ais523> depends on how it's defined
08:45:56 -!- wieldablesquid has joined.
08:45:57 <ais523> there are certainly constructions that are
08:46:06 <ais523> the best known is finite state machine + two counters
08:46:24 <rdococ_> well, if you could define an infinite number of states with regular expressions or token wildcards
08:46:36 <rdococ_> like string $1 + concat $2 => string $1$2
08:46:37 -!- rdococ has quit (Ping timeout: 246 seconds).
08:46:45 -!- rdococ_ has changed nick to rdococ.
08:47:23 <rdococ> my internet will be intermittent because I'm in a car
08:47:52 <b_jonas> "infinite state machine" is really vague. almost anything is an infinite state machine if it runs in discrete time, which applies to most of what non-esoteric computer science considers.
08:48:50 <b_jonas> it's so general you can't really say anything useful about it, which is why we restrict it by the chomsky hierarchy or other ways
08:49:18 -!- oerjan has quit (Quit: Wroom).
08:49:32 -!- iamevn_ has quit (Ping timeout: 264 seconds).
08:50:25 -!- Patashu_ has joined.
08:50:25 -!- Patashu has quit (Disconnected by services).
08:52:34 -!- rdococ has quit (Ping timeout: 246 seconds).
08:52:45 <orin> Oh, I forgot: here is the same code, refactored with goto: http://arin.ga/fyyppe
08:53:39 <ais523> it's still not that readable
08:53:43 -!- Patashu has joined.
08:53:55 <ais523> at least now the fact that the flow is optimizable is more obvious
08:54:00 -!- rdococ has joined.
08:54:21 <rdococ> how am I connected at all
08:54:25 <ais523> e,g, you do things like if (...) goto longlongnum; else {...; goto retry;} longlongnum:
08:54:42 <ais523> which is one of the most bizarre ways to write an if statement I've ever seen :-)
08:56:04 <b_jonas> is this lexing C or something?
08:56:37 -!- Patashu_ has quit (Ping timeout: 255 seconds).
08:56:41 <orin> It is reading in arbitrary C structures, in an ad-hoc format similar to C literals
08:57:03 <b_jonas> ais523: I think yacc not reading the lookahead when it's not needed would even make implementing a classical C89 compiler simpler,
08:58:00 <b_jonas> for it would use that hack where the lexer generates a different token for type identifiers than for function/object identifiers, and you may need that distinction very early after a type is declared
08:58:37 <ais523> b_jonas: right, I've implemented it to never read a token unless it's needed
08:58:40 <b_jonas> so it would make sense to me that yacc had always worked that way
08:58:43 <ais523> because POSIX requires that
08:58:46 <ais523> even though it's inconsistent
08:59:05 <ais523> there are other examples like foo: bar {midrule} BAZ
08:59:51 <ais523> suppose I do "a : b {foo} C | b {bar} D", now you have to read in the C or D to know whether to run foo or bar
09:00:18 <b_jonas> brace blocks in the middle of the rule can be useful in some sort of grammars, but it's really just syntacic sugar
09:00:37 -!- rdococ has quit (Ping timeout: 246 seconds).
09:01:08 <ais523> ayacc desugars it in the way recommended by POSIX, to "a : b #1 C | b #2 D; #1 : {foo}; #2 : {bar}"
09:01:25 <b_jonas> luckily this don't read the lookahead rule doesn't make the yacc implementation too complicated, because if you know how to generate the pushdown automaton tables, you probably also know how to determine when you need the lookahead
09:01:30 <ais523> where I start internally-generated identifiers with # because that's normally an illegal character in yacc identifiers, = no clashes
09:02:07 <ais523> well, the check is "is every transition on a terminal in this state an identical reduce action"
09:02:17 <b_jonas> yeah... and yacc identifiers can contain a hyphen so you can't just use them verbatim inside the C function names you generate
09:02:46 <ais523> technically you could check shifts too, but a) that never happens with the LALR(1) algorithm unless there's only one terminal there, b) the act of shifting requires reading the terminal anyway
09:02:52 -!- ais523 has quit (Quit: meeting).
09:03:31 <orin> I assume it is workday time where ais is.
09:03:32 <b_jonas> I don't think (b) is valid because you need to execute a brace block before the reading if there's only one shift action?
09:03:54 <b_jonas> sure it's workday time. he's in the same continent as me.
09:04:39 <orin> Where I am it is 5 in the morning, e.g. crawl home o clock
09:04:41 <b_jonas> orin: does that lex C99 hexfloats too?
09:05:39 <orin> I could probably modify it, but it probably doesn't even work perfectly for regular floats anyway
09:05:45 <b_jonas> (also C++11 suffixed user literals, C++11 literal strings, and the three flavors of unicode strings...)
09:06:00 <b_jonas> orin: but hex floats are _easier_ than regular floats
09:06:20 <b_jonas> yes, because there's no tricky precision issues
09:06:28 <b_jonas> the representation is binary
09:06:45 <b_jonas> for reading decimal floats, it's hard to convert from decimal to binary without roundoff errors
09:06:52 <orin> ohhhh.... that makes sense now I think about it
09:06:58 <b_jonas> for hex floats you don't have that problem, it's easier to convert
09:07:22 <b_jonas> I mean, it's still not trivial, I'd still recommend most people to use a library function from a trusted well-written library instead of parsing themselves
09:07:26 <b_jonas> but it's definitely easier
09:08:24 <orin> This code reads a format taht is a bit more permissive than C... for example, if the number begins with a hex digit you don't need a prefix. 0xff xff and ff are all ok
09:09:16 <orin> but 1f will give you 25
09:09:18 <mroman> ff*3 isn't the variable ff*3
09:10:09 <b_jonas> orin: what? isn't 1f supposed to be the same as 1.1f in C?
09:10:48 <orin> Hm? I thought it would just be an error
09:11:08 <b_jonas> or a C++11 user-defined literal
09:11:34 <orin> lol. what happens if two packages deifne the same literal?
09:13:29 <orin> Hmm.. I guess it is handled as a duplicate definition of operator ""
09:24:44 <b_jonas> orin: it's more complicated than that
09:28:41 <b_jonas> because it's namespaced too
10:03:13 -!- MDream has changed nick to MDude.
10:12:47 -!- Patashu has quit (Disconnected by services).
10:12:47 -!- Patashu_ has joined.
10:16:07 -!- Patashu has joined.
10:19:44 -!- Patashu_ has quit (Ping timeout: 256 seconds).
10:21:02 -!- dianne has quit (Quit: byeannes).
10:39:14 -!- boily has joined.
11:15:15 <boily> uhm. I feel a little bit disturbed to be at 108.
11:26:04 <lambdabot> Plugin `metar' failed with: <<timeout>>
11:26:15 <lambdabot> LOWI 151120Z VRB02KT CAVOK 20/01 Q1021 NOSIG
11:26:19 <lambdabot> CYUL 151100Z 21007KT 30SM FEW050 FEW160 SCT240 04/M01 A3020 RMK SC1CI1CI2 SC TR SLP229
11:26:32 <int-e> I didn't do anything.
11:26:45 * boily glares at lambdabot
11:26:54 <int-e> I guess the webserver was slow to answer
11:33:25 -!- dianne has joined.
11:38:51 -!- boily has quit (Quit: LETHARGIC CHICKEN).
11:40:27 -!- nszceta has joined.
12:07:17 <J_Arcane> threaded brainfuck https://github.com/scotchfield/brainfuck_py
12:07:46 -!- nszceta has quit (Quit: My Mac has gone to sleep. ZZZzzz…).
12:08:31 -!- idris-bot has quit (Quit: Terminated).
12:08:47 -!- idris-bot has joined.
12:10:08 -!- idris-bot has quit (Client Quit).
12:10:24 -!- idris-bot has joined.
12:33:32 -!- Patashu has quit (Ping timeout: 245 seconds).
12:53:52 -!- ProofTechnique has quit (Ping timeout: 256 seconds).
13:16:03 -!- ProofTechnique has joined.
13:22:21 -!- `^_^v has joined.
13:22:41 -!- doesthiswork has joined.
13:22:49 -!- Phantom_Hoover has joined.
13:23:52 -!- doesthiswork has quit (Client Quit).
13:27:25 -!- Phantom_Hoover has quit (Ping timeout: 245 seconds).
13:27:37 -!- Phantom_Hoover has joined.
13:32:10 <HackEgo> [wiki] [[Hello world program in esoteric languages]] http://esolangs.org/w/index.php?diff=42517&oldid=42456 * Esowiki201529A * (+56) /* Gibberish */
13:33:34 <HackEgo> [wiki] [[Hello world program in esoteric languages]] http://esolangs.org/w/index.php?diff=42518&oldid=42517 * Esowiki201529A * (+0) /* Gibberish/Javascript */
13:44:06 -!- Sprocklem has quit (Ping timeout: 245 seconds).
13:47:11 <HackEgo> [wiki] [[Gibberish/JavaScript]] http://esolangs.org/w/index.php?diff=42519&oldid=42489 * Esowiki201529A * (+254)
13:48:25 <HackEgo> [wiki] [[Gibberish/JavaScript]] http://esolangs.org/w/index.php?diff=42520&oldid=42519 * Esowiki201529A * (+10) /* Escape sequence */
13:51:16 <HackEgo> [wiki] [[Gibberish/JavaScript]] http://esolangs.org/w/index.php?diff=42521&oldid=42520 * Esowiki201529A * (+33) /* Escape sequence */
13:51:41 <HackEgo> [wiki] [[Gibberish/JavaScript]] http://esolangs.org/w/index.php?diff=42522&oldid=42521 * Esowiki201529A * (+3) /* Escape sequence */
13:54:09 <HackEgo> [wiki] [[Gibberish/JavaScript]] http://esolangs.org/w/index.php?diff=42523&oldid=42522 * Esowiki201529A * (+38) /* Escape sequence */
13:57:15 -!- adu has joined.
13:59:14 <HackEgo> [wiki] [[Gibberish/JavaScript]] http://esolangs.org/w/index.php?diff=42524&oldid=42523 * Esowiki201529A * (+149) /* Escape sequence */
14:01:52 <HackEgo> [wiki] [[Gibberish/JavaScript]] http://esolangs.org/w/index.php?diff=42525&oldid=42524 * Esowiki201529A * (+39)
14:02:33 <HackEgo> [wiki] [[Gibberish/JavaScript]] http://esolangs.org/w/index.php?diff=42526&oldid=42525 * Esowiki201529A * (+5) /* See also */
14:09:23 -!- villasukka has quit (Ping timeout: 265 seconds).
14:22:45 <HackEgo> [wiki] [[Gibberish/JavaScript/HTML interpreter]] N http://esolangs.org/w/index.php?oldid=42527 * Esowiki201529A * (+7347) Created page with "== HTML code == <pre><nowiki> <!doctype html> <html> <head> <style> .c0 {background:#f73} .c1 {background:#f76} .c2 {background:#f79} .c3 {background:#..."
14:23:24 <HackEgo> [wiki] [[Gibberish/JavaScript/HTML interpreter]] http://esolangs.org/w/index.php?diff=42528&oldid=42527 * Esowiki201529A * (+7) /* See also */
14:27:29 <HackEgo> [wiki] [[Gibberish/JavaScript/HTML interpreter]] http://esolangs.org/w/index.php?diff=42529&oldid=42528 * Esowiki201529A * (-7235) /* HTML code */
14:27:51 <HackEgo> [wiki] [[Gibberish/JavaScript/HTML interpreter]] http://esolangs.org/w/index.php?diff=42530&oldid=42529 * Esowiki201529A * (+0) /* HTML code */
14:29:29 <HackEgo> [wiki] [[Gibberish/JavaScript/HTML interpreter]] http://esolangs.org/w/index.php?diff=42531&oldid=42530 * Esowiki201529A * (+44) /* HTML code */
14:30:21 <HackEgo> [wiki] [[Gibberish/JavaScript/HTML interpreter]] http://esolangs.org/w/index.php?diff=42532&oldid=42531 * Esowiki201529A * (-3) /* HTML code */
14:33:26 <HackEgo> [wiki] [[Gibberish/JavaScript/HTML interpreter]] http://esolangs.org/w/index.php?diff=42533&oldid=42532 * Esowiki201529A * (+44) /* HTML code */
14:37:32 <HackEgo> [wiki] [[Gibberish/JavaScript/HTML interpreter]] http://esolangs.org/w/index.php?diff=42534&oldid=42533 * Esowiki201529A * (+85) /* HTML code */
14:38:08 <HackEgo> [wiki] [[Gibberish/JavaScript/HTML interpreter]] http://esolangs.org/w/index.php?diff=42535&oldid=42534 * Esowiki201529A * (+6) /* HTML code */
14:38:53 -!- GeekDude has joined.
14:40:09 <HackEgo> [wiki] [[Gibberish/JavaScript/HTML interpreter]] http://esolangs.org/w/index.php?diff=42536&oldid=42535 * Esowiki201529A * (+51) /* HTML code */
14:40:54 -!- MDude has quit (Read error: Connection reset by peer).
14:44:54 -!- Phantom_Hoover has quit (Ping timeout: 240 seconds).
14:44:59 -!- Phantom__Hoover has joined.
14:45:35 <HackEgo> [wiki] [[Gibberish/JavaScript/HTML interpreter]] http://esolangs.org/w/index.php?diff=42537&oldid=42536 * Esowiki201529A * (+30) /* HTML code */
14:46:25 <HackEgo> [wiki] [[Gibberish/JavaScript/HTML interpreter]] http://esolangs.org/w/index.php?diff=42538&oldid=42537 * Esowiki201529A * (+2) /* HTML code */
14:53:34 <HackEgo> [wiki] [[Gibberish/JavaScript]] http://esolangs.org/w/index.php?diff=42539&oldid=42526 * Esowiki201529A * (+25) /* Escape sequence */
14:54:23 <HackEgo> [wiki] [[Brainfuck algorithms]] M http://esolangs.org/w/index.php?diff=42540&oldid=42442 * Quintopia * (-1)
14:54:29 <HackEgo> [wiki] [[Gibberish/JavaScript]] http://esolangs.org/w/index.php?diff=42541&oldid=42539 * Esowiki201529A * (+3) /* Escape sequence */
14:56:05 -!- Sprocklem has joined.
14:57:20 <HackEgo> [wiki] [[Gibberish/JavaScript]] http://esolangs.org/w/index.php?diff=42542&oldid=42541 * Esowiki201529A * (+6) /* Escape sequence */
15:07:41 <quintopia> i feel like this esowiki guy could make all these changes in a single edit
15:08:01 <quintopia> or be more descriptive about what they are for
15:13:38 -!- TieSoul_ has quit (Remote host closed the connection).
15:24:42 -!- nortti has changed nick to lawspeaker.
15:25:53 -!- lawspeaker has changed nick to nortti.
15:28:35 -!- hjulle has joined.
15:29:35 -!- adu has quit (Quit: adu).
15:34:39 -!- variable has joined.
15:36:49 -!- Phantom_Hoover has joined.
15:39:35 -!- Phantom__Hoover has quit (Ping timeout: 250 seconds).
15:42:38 -!- nortti has changed nick to lawspeaker.
15:43:04 -!- lawspeaker has changed nick to nortti.
15:43:22 -!- nortti has changed nick to lawspeaker.
15:43:44 -!- lawspeaker has changed nick to nortti.
15:48:21 -!- aretecode has joined.
16:03:16 -!- Hijiri has quit (Quit: WeeChat 1.0.1).
16:08:37 -!- bb010g has quit (Quit: Connection closed for inactivity).
16:26:27 <HackEgo> [wiki] [[Talk:Folder]] http://esolangs.org/w/index.php?diff=42543&oldid=42401 * Rottytooth * (+247) /* Name dispute */
16:57:15 -!- SopaXorzTaker has joined.
17:02:37 -!- SopaXorzTaker has quit (Quit: Leaving).
17:03:22 -!- Hijiri has joined.
17:16:41 <int-e> @tell oerjan are trac notifications still erratic for you as well?
17:23:41 -!- TieSoul has joined.
17:34:53 -!- Hijiri has quit (Quit: WeeChat 1.0.1).
17:45:40 -!- rdococ has joined.
17:47:18 -!- AnotherTest has joined.
17:47:37 <int-e> fungot: what do you think of sleep?
17:47:37 <fungot> int-e: i've never been to the bottom of a bottle.
17:48:15 <orin> fungot is a lightweight huh
17:48:15 <fungot> orin: at a speed of over eight hundred thousand things to save the city, and the skyline is dominated by billboards, ads like that burn my biscuits, pal, or go to an early gravy!
17:55:59 -!- Hijiri has joined.
18:10:16 <b_jonas> ais523 still not back? pity
18:14:45 -!- sebbu has quit (Ping timeout: 256 seconds).
18:15:26 -!- sebbu has joined.
18:15:26 -!- sebbu has quit (Changing host).
18:15:26 -!- sebbu has joined.
18:16:26 <HackEgo> [wiki] [[Harp]] M http://esolangs.org/w/index.php?diff=42544&oldid=42514 * Rdococ * (+63) /* Interpreter */
18:17:32 <b_jonas> I think what he said was wrong
18:18:10 <b_jonas> because then there's a one-symbol reduction
18:21:54 <orin> language where every instruction consists of exactly 2 characters
18:22:59 <int-e> ok oK Ok OK O! o! K! k! <-- let's make a variant of "Ook!" ;-)
18:25:21 -!- sebbu has quit (Ping timeout: 245 seconds).
18:27:39 -!- sebbu has joined.
18:27:39 -!- sebbu has quit (Changing host).
18:27:39 -!- sebbu has joined.
18:32:11 -!- oerjan has joined.
18:33:46 <rdococ> language with 0 instructions
18:36:38 -!- sebbu has quit (Ping timeout: 250 seconds).
18:37:22 <lambdabot> int-e said 1h 20m 41s ago: are trac notifications still erratic for you as well?
18:38:36 -!- sebbu has joined.
18:39:25 -!- HackEgo has quit (Remote host closed the connection).
18:40:11 <oerjan> their killing are bots
18:40:33 <int-e> I've heard, but how does this affect their sending emails?
18:40:57 -!- sebbu2 has joined.
18:41:23 <oerjan> no, _are_ bots, lyke HackyGo hth
18:41:33 -!- sebbu2 has quit (Changing host).
18:41:33 -!- sebbu2 has joined.
18:42:19 <oerjan> int-e: i'm guessing it gets so overloaded the email sending process dies, or something?
18:44:00 -!- sebbu has quit (Ping timeout: 250 seconds).
18:44:11 -!- Sprocklem has quit (Ping timeout: 250 seconds).
18:46:48 -!- sebbu2 has changed nick to sebbu.
18:49:51 -!- variable has quit (Ping timeout: 248 seconds).
18:56:15 -!- sebbu has quit (Ping timeout: 248 seconds).
18:57:01 -!- rdococ has quit (Ping timeout: 246 seconds).
18:58:10 -!- sebbu has joined.
18:58:10 -!- sebbu has quit (Changing host).
18:58:10 -!- sebbu has joined.
18:58:54 -!- Hijiri has quit (Quit: WeeChat 1.0.1).
19:00:43 -!- sebbu2 has joined.
19:01:10 -!- sebbu2 has quit (Changing host).
19:01:10 -!- sebbu2 has joined.
19:03:56 -!- sebbu has quit (Ping timeout: 250 seconds).
19:04:50 -!- j-bot has quit (Remote host closed the connection).
19:05:00 -!- j-bot has joined.
19:09:17 -!- rdococ has joined.
19:09:19 -!- sebbu2 has quit (Ping timeout: 252 seconds).
19:09:20 -!- j-bot has quit (Remote host closed the connection).
19:09:41 -!- j-bot has joined.
19:11:51 -!- j-bot has quit (Remote host closed the connection).
19:12:06 -!- j-bot has joined.
19:14:16 -!- villasukka has joined.
19:20:30 <rdococ> I guess he was https://esolangs.org/wiki/Intolerant !!!
19:20:50 <rdococ> btw that's not my esolang
19:22:08 -!- HackEgo has joined.
19:23:37 -!- hjulle has quit (Read error: Connection reset by peer).
19:24:10 <rdococ> esolangs.org isn't working for me
19:24:39 <oerjan> well the wiki and HackEgo are on the same server.
19:25:39 <rdococ> so my internet wasn't poor at all
19:26:30 <oerjan> gregor isn't even here
19:27:54 <oerjan> hm the wiki is sort of trying to load for me
19:27:55 -!- HackEgo has quit (Remote host closed the connection).
19:28:34 <oerjan> but horribly slow it is.
19:30:02 <oerjan> int-e: lewie e. coyote
19:32:53 <oerjan> ok lewie is remembering the curses, he should have an epiphany soon
19:41:13 -!- hjulle has joined.
19:43:44 -!- Frooxius has joined.
19:46:56 <rdococ> imagine if everything was a function
19:47:24 -!- sebbu has joined.
19:48:00 -!- sebbu has quit (Changing host).
19:48:00 -!- sebbu has joined.
19:49:46 <HackEgo> [wiki] [[User:Rottytooth]] http://esolangs.org/w/index.php?diff=42545&oldid=42243 * Rottytooth * (+13)
19:51:29 <HackEgo> [wiki] [[User:Rdococ]] http://esolangs.org/w/index.php?diff=42546&oldid=42513 * Rdococ * (+52) Hyperspace
19:56:51 -!- orin has quit (Quit: Lost terminal).
19:59:10 -!- sebbu has quit (Ping timeout: 264 seconds).
19:59:39 -!- Sprocklem has joined.
20:00:08 <int-e> Oh right, it's another MWF comic now...
20:02:13 <int-e> (That's Monday Wednesday Friday in case anyone is wondering, and a reply to oerjan.)
20:03:38 -!- PinealGlandOptic has joined.
20:04:47 -!- bb010g has joined.
20:06:22 <oerjan> hopefully it will be regular now
20:09:11 <b_jonas> int-e: ok, but what comic?
20:09:33 <int-e> The one with Lewie ;-)
20:10:41 -!- TieSoul has quit (Quit: No Ping reply in 210 seconds.).
20:11:37 <HackEgo> [wiki] [[Hyperspace]] N http://esolangs.org/w/index.php?oldid=42547 * Rdococ * (+1122) Created page with "{{stub}} ''And also, it is going to be impossible to draw a diagram to represent a program in this language.'' The '''Hyperspace programming language''' is an unbounded-dimens..."
20:12:08 -!- TieSoul has joined.
20:13:21 <izabera> any http experts here? would i break something if i used the percent encoding for everything?
20:13:38 <b_jonas> int-e: what do you mean by "everything"
20:13:53 <int-e> b_jonas: hey I was going to ask this question
20:13:56 <izabera> also those characters that don't need it
20:14:16 <HackEgo> [wiki] [[Hyperspace]] http://esolangs.org/w/index.php?diff=42548&oldid=42547 * Rdococ * (+208) computational class section
20:16:20 -!- sebbu has joined.
20:17:05 <rdococ> hang on, it can't be turing complete
20:17:24 <HackEgo> [wiki] [[Hyperspace]] M http://esolangs.org/w/index.php?diff=42549&oldid=42548 * Rdococ * (+14)
20:17:30 <elliott> izabera: it'll break /, maybe
20:17:39 <elliott> since http://foo/a%2Fb isn't http://foo/a/b
20:17:50 <elliott> since % "escapes" the special syntactic meaning that / has there
20:17:59 <izabera> ok i was thinking about a POST request
20:18:06 <izabera> the content has to be urlencoded
20:18:36 <elliott> that sounds okay, I forget the syntax of POST bodies though
20:18:47 <elliott> is it like URL queries? if so then I think escaping = and & will behave similarly
20:18:57 <elliott> but if it's just "blah=" + overescape(blah) then it should be fine
20:19:04 <elliott> (as in if it's just the one field)
20:19:40 <izabera> what's happening to HackEgo
20:19:56 -!- Tritonio has joined.
20:20:21 <elliott> it's having some problems I guess
20:20:49 -!- sebbu has quit (Ping timeout: 250 seconds).
20:21:05 <elliott> it and the wiki are on a http://www.cloudatcost.com/ VPS that cost $35 for the rest of ever so they are unsurprisingly kind of reliable >_>
20:21:15 <int-e> My CaC (isn't that a great way to abbreviate that provider) server seems to be running fine right now.
20:21:37 <int-e> They're weird, a side business of a small Telco.
20:35:28 -!- oren has joined.
20:37:57 -!- Hijiri has joined.
20:38:38 <HackEgo> [wiki] [[Babble]] N http://esolangs.org/w/index.php?oldid=42550 * Rottytooth * (+1465) added Babble
20:40:43 -!- oren has quit (Ping timeout: 264 seconds).
20:42:05 -!- oren has joined.
20:42:13 <HackEgo> [wiki] [[Warp]] N http://esolangs.org/w/index.php?oldid=42551 * Rdococ * (+1399) Created page with "The '''Warp programming language''' is a derivative of [[Harp]], both by [[User:Rdococ]]. == Structure == Warp is much like Harp, with a single instruction which has two argu..."
20:44:24 -!- oerjan has quit (Quit: ZZZZZZ).
20:45:15 <rdococ> unbounded vs infinite: if finite state automata could be infinitely large, they'd be as powerful as turing machines
20:50:33 <rdococ> ugh, forget it, scrap Warp
20:52:18 <HackEgo> [wiki] [[Warp]] M http://esolangs.org/w/index.php?diff=42552&oldid=42551 * Rdococ * (+9)
20:57:17 -!- izabera has changed nick to greybug.
20:58:30 <HackEgo> [wiki] [[User:Rdococ]] http://esolangs.org/w/index.php?diff=42553&oldid=42546 * Rdococ * (+11)
21:02:10 -!- ProofTechnique has quit (Ping timeout: 264 seconds).
21:02:27 -!- variable has joined.
21:02:53 -!- Patashu has joined.
21:08:18 -!- greybug has changed nick to izabera.
21:22:34 -!- Phantom_Hoover has quit (Ping timeout: 264 seconds).
21:23:06 -!- Sprocklem has quit (Ping timeout: 276 seconds).
21:23:31 -!- Patashu has quit (Ping timeout: 252 seconds).
21:24:26 -!- Phantom_Hoover has joined.
21:30:19 <HackEgo> [wiki] [[Harp]] M http://esolangs.org/w/index.php?diff=42554&oldid=42544 * Rdococ * (+54) /* Interpreter */ modified Lua interpreter
21:31:45 -!- variable has changed nick to function.
21:31:58 <HackEgo> [wiki] [[Harp]] http://esolangs.org/w/index.php?diff=42555&oldid=42554 * Rdococ * (+111) /* Interpreter */
21:32:27 <rdococ> function, can I call you?
21:37:13 <rdococ> finished. error code 0
21:41:27 * rdococ kills function's thread
21:41:51 <function> rdococ, um, I am multi-threaded
21:42:10 <function> worst case I become a zombie and eat brains
21:44:06 <rdococ> you're not a function, are you
21:44:17 <rdococ> why are you called function... why do people call you
21:44:32 <rdococ> get it? function calling?
21:44:43 -!- Sprocklem has joined.
21:46:45 <function> rdococ, you are right. I am actually a mutable constant.
21:50:41 * rdococ protects against the violation
21:51:05 <izabera> so uhm you know that stupid idea to create a language with the rubik's cubes? to know if a command is valid you need to solve a np complete problem... etc
21:51:14 <rdococ> also, how can someone call 0?
21:52:45 <izabera> well, factorization is np complete... so why not use this? . 1 , 2 [ 3 ] 4 < 5 > 6 + 7 - 8 the input file is a list of numbers
21:52:50 <izabera> space separated or whatever
21:53:06 <izabera> factor each one, if it has 1-8 factors it's a valid command
21:54:22 <izabera> so uhm this is cat: 6 30 2 6 210
22:00:15 <izabera> i'm not sure it's np complete
22:00:23 <izabera> it doesn't actually need the factors
22:00:32 -!- AnotherTest has quit (Remote host closed the connection).
22:01:50 <elliott> izabera: so that's as hard as breaking RSA with large enough numbers, I guess?
22:03:07 <FireFly> Well, with RSA you need to find the actual factors and not just the number of factors, o?
22:03:28 <FireFly> I mean, usually I would guess the number of factors is known to be 2 for RSA
22:05:44 -!- `^_^v has quit (Quit: This computer has gone to sleep).
22:05:59 -!- ProofTechnique has joined.
22:23:07 -!- Tritonio has quit (Remote host closed the connection).
22:38:21 -!- v^ has joined.
22:39:27 -!- function has quit (Ping timeout: 244 seconds).
22:41:14 -!- ^v has quit (Ping timeout: 265 seconds).
22:42:04 -!- sebbu has joined.
22:46:07 <rdococ> imagine if we interpreted programs like elements of a set
22:48:21 <rdococ> string S state T = S*(R^N) transition R = S*T program P = T^N
22:49:04 <rdococ> so you'd have set of all strings S, treat it like how you'd treat the set of all integers or rationals or reals, then you can do stuff
22:49:44 <rdococ> or, omit transitions from the definition of a state
22:50:15 <rdococ> string S, state T = S, transition R = S*T, program P = (T*R)^N
22:51:20 <rdococ> a state is a string, a transition is a set containing a string and a state, a program is a set containing sets containing a string and a state
22:52:53 -!- Froox has joined.
22:53:45 -!- Froo has joined.
22:55:11 <rdococ> a set of all finite state automaton, then, would be ((C^N)*(C*(C^N)))^N, where C is the set of all natural numbers from 0 to 255, N is the set of all natural numbers
22:55:23 <rdococ> if you're using characters instead of strings
22:55:56 -!- v^ has quit (Read error: Connection reset by peer).
22:56:36 <rdococ> or, program P could be a function mapping two numbers to one number
22:56:48 -!- Frooxius has quit (Ping timeout: 256 seconds).
22:56:59 <rdococ> p(input, state) = newState
22:57:20 <rdococ> using my sense of mathematics,
22:58:00 -!- Froox has quit (Ping timeout: 276 seconds).
22:59:05 <rdococ> then a program could just be a series of derps
23:05:06 -!- conehead has quit (Ping timeout: 252 seconds).
23:05:09 -!- variable has joined.
23:05:44 -!- conehead has joined.
23:08:38 <variable> rdococ, you can't set me the same value more than once
23:09:05 <rdococ> function f() return variable end
23:09:29 -!- rdococ has changed nick to object.
23:09:53 <object> hi, I'm a first class object.
23:09:58 -!- object has changed nick to rdococ.
23:11:10 -!- Phantom_Hoover has quit (Ping timeout: 264 seconds).
23:15:03 -!- staffehn_ has quit (Read error: Connection reset by peer).
23:15:09 -!- staffehn has joined.
23:23:02 <rdococ> I will find a way to manufacture anti-sleep pills so I will never have to sleep again
23:24:31 <rdococ> I will get my hands on coffee.
23:24:50 <rdococ> nobody can stop me from my internet now!!!
23:27:34 <oren> From personal experience I can tell you instant coffee can be about 5 times as strong as espresso if you put too much powder in.
23:28:06 <izabera> yeah it becomes closer to cocaine than espresso
23:28:19 -!- TieSoul_ has joined.
23:28:34 <oren> espresso is a bit stronger than coffee from a moka pot,and drip coffee is like flavored water
23:30:18 <rdococ> do I have to have coffee?
23:31:03 <oren> ideally, you should use freshly ground coffee beans, ys
23:33:25 -!- yorick_ has joined.
23:33:44 -!- FreeFull_ has joined.
23:36:46 -!- hjulle has quit (Ping timeout: 250 seconds).
23:36:46 -!- FreeFull has quit (Ping timeout: 250 seconds).
23:36:54 -!- yorick has quit (Ping timeout: 250 seconds).
23:36:54 -!- gniourf has quit (Ping timeout: 250 seconds).
23:37:04 -!- hjulle has joined.
23:37:34 -!- TieSoul_ has quit (Read error: Connection reset by peer).
23:37:36 -!- gniourf has joined.
23:37:44 -!- TieSoul has quit (Ping timeout: 248 seconds).
23:37:44 -!- fractal has quit (Ping timeout: 248 seconds).
23:37:53 -!- TieSoul has joined.
23:44:01 -!- Sprocklem has quit (Ping timeout: 255 seconds).
23:46:13 -!- fractal has joined.
23:56:29 -!- vodkode_ has quit (Remote host closed the connection).
00:02:50 -!- lambdabot has quit (Read error: Connection reset by peer).
00:08:25 -!- lambdabot has joined.
00:13:05 -!- Phantom_Hoover has joined.
00:16:50 -!- Sgeo|web has joined.
00:17:04 <Sgeo|web> Is there any reason that ddrescue on a non-damaged HD would be a bad idea?
00:20:24 <int-e> That sounds rather harmless.
00:20:56 <Sgeo|web> Could be a waste of space, I guess
00:21:16 <Sgeo|web> But I think most of the HDs in question are 80GB or so, the 1TB one is questionably broken
00:21:24 <Sgeo|web> (I guess ddrescue will tell me)
00:21:31 <Sgeo|web> So, planning on buying an 8TB NAS
00:24:11 -!- Phantom_Hoover has quit (Ping timeout: 265 seconds).
00:26:29 -!- variable has quit (Ping timeout: 252 seconds).
00:27:47 -!- variable has joined.
00:28:44 -!- yorick_ has changed nick to yorick.
00:30:20 -!- Naviaux has joined.
00:31:33 -!- TodPunk has quit (Read error: Connection reset by peer).
00:31:34 -!- Tod-Autojoined has joined.
00:46:54 <pikhq> Sgeo|web: If there aren't any read errors, ddrescue is basically just dd.
00:50:53 -!- Sgeo|web has quit (Ping timeout: 246 seconds).
00:52:22 <Naviaux> I was wondering if there is anyone that would like to help with making an esolang called Chronos
00:59:08 -!- rdococ has quit (Quit: Page closed).
01:03:31 <HackEgo> [wiki] [[Gibberish/JavaScript]] http://esolangs.org/w/index.php?diff=42556&oldid=42542 * Esowiki201529A * (+9) It's stub
01:05:24 <HackEgo> [wiki] [[Gibberish/JavaScript/HTML interpreter]] http://esolangs.org/w/index.php?diff=42557&oldid=42538 * Esowiki201529A * (+9)
01:09:08 <HackEgo> [wiki] [[Language list]] http://esolangs.org/w/index.php?diff=42558&oldid=42516 * Esowiki201529A * (+60) /* G */
01:13:24 -!- Sgeo|web has joined.
01:13:44 <Sgeo|web> Can ddrescue be badly screwed up? Other than by forgetting to use a logfile, I mean
01:14:21 <Sgeo|web> Also, webchat sucks, it disconnected and this fact was not obvious until I tried to send a message
01:15:13 <Sgeo|web> Like, am I liable to do the wrong thing and regret ever using ddrescue? And should just send an HD (potentially with personal information) to professional data recovery service?
01:15:20 -!- magician has joined.
01:17:43 -!- Guest3780 has quit (Ping timeout: 245 seconds).
01:17:43 -!- magician has changed nick to Guest3780.
01:27:12 -!- variable has quit (Ping timeout: 250 seconds).
01:28:55 -!- Tod-Autojoined has changed nick to TodPunk.
01:49:50 -!- Naviaux has quit (Quit: Page closed).
01:50:21 <oren> should I try my hand at translating a manga?
02:04:59 <HackEgo> [wiki] [[Gibberish/JavaScript]] http://esolangs.org/w/index.php?diff=42559&oldid=42556 * Esowiki201529A * (+51)
02:08:20 <HackEgo> [wiki] [[Gibberish/JavaScript]] http://esolangs.org/w/index.php?diff=42560&oldid=42559 * Esowiki201529A * (+17) /* Escape sequence */
02:20:36 -!- Sprocklem has joined.
02:25:46 <HackEgo> [wiki] [[Special:Log/move]] move * Esowiki201529A * moved [[Gibberish]] to [[Gibberish (programming language)]]: disambiguation?
02:25:46 <HackEgo> [wiki] [[Special:Log/move]] move * Esowiki201529A * moved [[Talk:Gibberish]] to [[Talk:Gibberish (programming language)]]: disambiguation?
02:28:38 -!- bb010g has quit (Quit: Connection closed for inactivity).
02:28:55 <HackEgo> [wiki] [[Gibberish]] http://esolangs.org/w/index.php?diff=42565&oldid=42562 * Esowiki201529A * (-6) Redirected page to [[Gibberish (disambiguation)]]
02:29:39 <izabera> !bf ++++++++++++[>++++++++<-]> > +++++[>+++++<-]>+ [ [->>+<<]>> [-<+<+>>]<- ] <[<]< [->>[+>]<[<]<] >> [.>]
02:29:41 <myndzi> zyxwvutsrqponmlkjihgfedcba
02:29:41 <myndzi> zyxwvutsrqponmlkjihgfedcba
02:29:41 <EgoBot> zyxwvutsrqponmlkjihgfedcba
02:32:30 <HackEgo> [wiki] [[Gibberish (disambiguation)]] N http://esolangs.org/w/index.php?oldid=42566 * Esowiki201529A * (+65) Created page with "* [[Gibberish (programming language)]] * [[Gibberish/JavaScript]]"
02:32:35 <mitchs> !bf <+++++++++++++++++++++++++++++++++.
02:34:38 <mitchs> !bf ++++++++++++[>++++++++++>++<<-]>++>++[<.->-]
02:34:38 <myndzi> zyxwvutsrqponmlkjihgfedcba
02:34:38 <myndzi> zyxwvutsrqponmlkjihgfedcba
02:34:38 <EgoBot> zyxwvutsrqponmlkjihgfedcba
02:35:51 <HackEgo> [wiki] [[Gibberish (programming language)]] http://esolangs.org/w/index.php?diff=42567&oldid=42561 * Esowiki201529A * (+31)
02:37:26 <elliott> myndzi: might want to turn that off in here, or at least make it only run once per line :p
02:39:24 <mitchs> btw the ! wasn't meant to convey anything, it's just the first non-whitespace printable character, and i wanted to check if the bf interpreter lets you go left of starting point
02:39:40 <elliott> wow um that last line broke a bit
02:39:43 <fungot> \o| c.c \o/ ಠ_ಠ \m/ \m/ \o_ c.c _o/ \m/ \m/ ಠ_ಠ \o/ c.c |o/
02:39:44 <myndzi> | c.c.c | ¯|¯⌠ `\o/´ | c.c.c | `\o/´ ¯|¯⌠ | c.c.c |
02:39:44 <myndzi> | c.c.c | ¯|¯⌠ `\o/´ | c.c.c | `\o/´ ¯|¯⌠ ¦ c.c.c |
02:39:44 <myndzi> |\ c.c /^\ /| | | /'\ c.c /| | /< |/< c.c >\
02:39:44 <myndzi> /'\ c.c |\ /| | | /'\ c.c >\ | |\|´¸¨ c.c /|
02:40:01 <elliott> is everything running twice or something
02:40:33 <elliott> it's meant to be a multiocular o
02:40:53 <elliott> it's... getting kind of messed up by everything running twice though
02:41:45 -!- ascl-bot has joined.
02:41:45 -!- ascl-bot has quit (Client Quit).
02:47:16 <izabera> is anyone else disturbed by the small penis in this part of the drawing? /`\
02:47:29 <HackEgo> [wiki] [[Language list]] http://esolangs.org/w/index.php?diff=42568&oldid=42558 * Esowiki201529A * (+33) /* G */
02:48:54 <elliott> would you prefer it be larger? >_>
02:49:06 <HackEgo> [wiki] [[Hello world program in esoteric languages]] http://esolangs.org/w/index.php?diff=42569&oldid=42518 * Esowiki201529A * (+33) /* Gibberish */
02:50:44 <HackEgo> [wiki] [[Gibberish/JavaScript]] http://esolangs.org/w/index.php?diff=42570&oldid=42560 * Esowiki201529A * (+23) /* See also */
02:53:06 <HackEgo> [wiki] [[EsoInterpreters]] http://esolangs.org/w/index.php?diff=42571&oldid=42121 * Esowiki201529A * (+33) /* Main table */
02:54:14 <HackEgo> [wiki] [[List of quines]] http://esolangs.org/w/index.php?diff=42572&oldid=42076 * Esowiki201529A * (+33) /* Gibberish */
02:55:05 <HackEgo> [wiki] [[User:Marinus/Brainfuck interpreters]] http://esolangs.org/w/index.php?diff=42573&oldid=20310 * Esowiki201529A * (+33) /* Gibberish */
02:57:24 <HackEgo> [wiki] [[Gibberish (disambiguation)]] http://esolangs.org/w/index.php?diff=42574&oldid=42566 * Esowiki201529A * (+41)
02:58:21 <HackEgo> [wiki] [[User:Marinus]] http://esolangs.org/w/index.php?diff=42575&oldid=38074 * Esowiki201529A * (+33)
02:58:41 -!- bb010g has joined.
02:59:43 <HackEgo> [wiki] [[User:Marinus]] http://esolangs.org/w/index.php?diff=42576&oldid=42575 * Esowiki201529A * (+33)
03:00:23 <HackEgo> [wiki] [[User:Javawizard]] http://esolangs.org/w/index.php?diff=42577&oldid=16780 * Esowiki201529A * (+33)
03:01:30 <myndzi> something is very wrong here
03:02:06 <myndzi> why does everything run twice :(
03:02:48 <myndzi> one is my work client and one is my home client
03:03:01 <HackEgo> [wiki] [[User:Quintopia]] http://esolangs.org/w/index.php?diff=42578&oldid=40213 * Esowiki201529A * (+33) /* Interpreters written in Python */
03:03:27 <myndzi> well, i imagine the work one is locked up from the bf hax above
03:03:38 <myndzi> i didn't write it defensively :P
03:12:03 <fungot> \o| c.c \o/ ಠ_ಠ \m/ \m/ \o_ c.c _o/ \m/ \m/ ಠ_ಠ \o/ c.c |o/
03:20:25 <myndzi> well i could load it up again but then i'd just have to turn it off again
03:20:42 <myndzi> 2 clients 1 bnc KeKeKe
03:23:04 <oren> every time I try to use Gimp I just wish I was using MS Pailnt
03:24:00 <hjulle> "Pailnt" is an interesting word.
03:24:35 <oren> I can barely pronounce it as one syllable
03:26:02 <oren> but seriously Gimp has an awful user interface
03:26:49 <hjulle> I'd probably ponounce it like Pail'nt, or pailent with a silent e.
03:27:55 <oren> OH, right. I'll just use Wine to run paint.net
03:28:12 <hjulle> What about KPaint or something?
03:28:42 <oren> I have paint.net already installed on my other partition, so meh
03:29:17 <oren> hmmm... it isn't working
03:30:15 <hjulle> (Assuming that ".net" means that it's a dotnet program.)
03:31:14 <oren> it seems like people have been saying good things about "pinta"
03:32:08 <oren> hell yes this is exactly what I want
03:32:27 <oren> i.e. it is basically the same as MS paint
03:32:46 <oren> (the version before Windows 8 ruined everything forever)
03:34:19 <hjulle> "Pinta is ... modeled after Paint.NET", so, yes it seems like exaktly what you want.
03:34:36 <myndzi> windows 7 ruined paint
03:34:41 <myndzi> you can still get paint xp
03:34:51 <myndzi> http://www.mspaintxp.com/
03:35:44 <oren> Windows 7 paint was bad too? I jumped (was forced to jump) from XP to 8
03:36:03 <myndzi> 7 ~ 8 as far as paint is concerned, i think
03:41:36 -!- GeekDude has quit (Quit: {{{}}{{{}}{{}}}{{}}} (www.adiirc.com)).
04:09:44 -!- Froo has quit (Quit: *bubbles away*).
04:18:49 <Sgeo|web> I want to mount, read-only, a raw image file located on the network
04:33:07 <oren> the terriblosity would depend on what kind of network it is
04:37:10 -!- oerjan has joined.
04:40:11 * oerjan spends 2 hours writing an unusually long ghc trac post only to have it start breaking down just before he's ready to submit.
04:41:14 <oren> I never trust in-browser text editing
04:41:48 <oerjan> me neither, i _did_ have enough clue to copy it first
04:42:28 <izabera> with my browser i can launch a terminal with vim by pressing C-e in any editable area
04:42:49 <oerjan> i already have vim open, i just didn't use it to write
04:43:15 <oerjan> trac has the nice feature of automatic preview, as long as it isn't half-dying
04:44:05 <oerjan> also i did this instead of sleeping argh
04:44:28 <oerjan> (figured once i started thinking mathy i wouldn't get any sleep anyway)
04:46:12 <shachaf> oerjan: it's a good thing that after this is fixed Typeable will be bulletproof
04:49:30 <quintopia> i guess this esowiki guy is nothing if not thorough
04:54:05 <oren> i think haskell is a pretty cool guy, eyht makes evrything a manod and doesn't afraid of anything.
04:55:00 <oerjan> WHERE'S YOUR MONAD NOW
04:55:19 <shachaf> oerjan: diagonalization hth
04:55:47 <oerjan> shachaf: doesn't obey the laws hth
04:55:57 <shachaf> but everyone thinks it does hth
04:56:15 <oerjan> no they don't, it's the goto "this cannot be a monad" example
04:57:03 <shachaf> i think Cont is the goto monad example hth
04:57:36 <shachaf> Actually you can probably make a better goto monad than Cont.
04:58:15 <shachaf> You'd want to be able to jump forwards as well as backwards.
04:58:48 <oerjan> no, i'm just wondering whether i should go back to bed
04:59:10 <lambdabot> Local time for oerjan is Thu Apr 16 07:00:50 2015
04:59:40 <oerjan> i did that > 3 hours ago tdnh
05:00:28 <oerjan> but indeed, this would have been the perfect time if i hadn't woken up too early
05:05:36 -!- Sprocklem has quit (Ping timeout: 250 seconds).
05:13:54 -!- Sprocklem has joined.
05:22:26 -!- Sprocklem has quit (Ping timeout: 245 seconds).
05:29:21 -!- variable has joined.
05:37:08 <oerjan> <izabera> well, factorization is np complete... [...] <-- that is neither believed nor proved.
05:38:17 <oerjan> at least not the usual way of thinking of it.
05:39:37 <oerjan> @tell izabera <izabera> well, factorization is np complete... [...] <-- that is neither believed nor proved. at least not the usual way of defining it.
05:50:22 <oerjan> easy things are also np
05:51:11 <izabera> sorry i meant it takes ridiculously long on large enough inputs
05:51:35 * oerjan hides his secret quantum computer
06:12:06 <coppro> izabera: It's not believed to be in P
06:12:13 <coppro> you are confusing "in NP" with "NP-complete"
06:17:29 <oren> I have already forgotten, mostly, what P and NP even mean, but NPC means "at least as hard as everything in NP"
06:17:43 <elliott> npc means non-player character actually
06:18:10 <shachaf> why do you call people nerds?
06:18:44 <elliott> they're not people, they're just NP-complete, obviously
06:18:48 <oren> because he's emulating Piccolo from DBZA?
06:19:12 <elliott> yes. that is what I do all day, 24/7/365
06:19:17 <shachaf> it's probably only faux-rude, but i don't particularly like it
06:20:01 <oren> dragon ballz abridged, the famous comedy youtube redub of DBZ
06:20:53 <elliott> dragon ballz just looks like the plural of dragon ball
06:20:59 <elliott> like, most dragons have 2 dragon ballz
06:21:28 <oren> https://www.youtube.com/watch?v=m0Wc50iEOtc
06:29:57 <b_jonas> (besides, don't judge from just one episode.)
06:30:49 <izabera> i didn't say i'm not going to watch the rest
06:38:01 <lambdabot> CYYZ 160600Z 00000KT 15SM SCT240 05/M02 A3040 RMK CI4 SLP298
06:43:18 -!- Sgeo|web has quit (Quit: Page closed).
07:00:07 <lambdabot> ENVA 160650Z 26020KT 9999 -RASN FEW005 SCT009 BKN011 02/01 Q1002 TEMPO 4000 SHRASNGS BKN010CB RMK WIND 670FT 27021KT
07:01:29 <oerjan> airport weather reports
07:02:58 <b_jonas> forecast says it's not going to rain here though, for today
07:06:38 -!- variable has changed nick to trout.
07:11:57 -!- trout has quit (Ping timeout: 250 seconds).
07:39:35 <Taneb> Possibly relevant/interesting paper: http://arxiv.org/pdf/1203.1895v1.pdf
07:40:35 <oerjan> itym http://arxiv.org/abs/1203.1895v1 hth
07:42:18 <oerjan> from which you can learn that there's a new version
07:51:58 <Taneb> I didn't know you could do that
07:52:05 <Taneb> I was just given the link direct to the PDF
07:52:27 <oerjan> "always link to the abstract" hth
07:53:14 <oerjan> for one thing, there's links only one way, otherwise you need to know the format
07:53:23 <shachaf> oerjan: they should use a better url scheme hth
07:54:11 <oerjan> shachaf: true, it's a bit awkward to guess
07:54:32 <shachaf> in the past i deleted the .pdf, and it put it back in
07:54:43 <shachaf> and i gave up on guessing the right url and just pasted the pdf link in
08:04:52 -!- aretecode has quit (Read error: No route to host).
08:07:56 -!- aretecode has joined.
08:15:43 <Taneb> Does anyone remember when I started to learn Haskell?
08:16:34 <oerjan> wild guess: shortly after you came here
08:16:52 <Deewiant> 2011-07-18 11:26:19( Taneb) Haskell installed
08:17:10 <Taneb> Huh, that feels later than it should be
08:18:24 <Deewiant> One day earlier 2011-07-17 14:55:47( Taneb) Well, I'm not going to learn Haskell just yet
08:23:03 <oerjan> Taneb: that was just the day after the hexham revelation.
08:23:17 <Taneb> I came to this channel later than I though
08:23:45 <Taneb> Jeez, I was already 16 when I got here?
08:24:31 <oerjan> that's about what i thought
08:24:51 <oerjan> i think you _briefly_ visited some time earlier
08:29:22 <Taneb> It feels like this has been part of my life for much longer
08:29:45 -!- Patashu has joined.
08:38:56 -!- Tod-Autojoined has joined.
08:39:32 -!- TodPunk has quit (Read error: Connection reset by peer).
08:41:41 <HackEgo> [wiki] [[Duck Duck Goose]] M http://esolangs.org/w/index.php?diff=42579&oldid=42294 * Vriskanon * (+245) /* Sample program */ Added cat program and multiple sample programs formatting
08:43:58 -!- hjulle has quit (Ping timeout: 265 seconds).
08:57:33 <oerjan> hm wikipedia is renaming accounts to get global logins
08:58:41 <oerjan> mine seems to stay, but i accidentally got to see the talk page message about Oerjan@wiktionary
08:59:12 <oerjan> (not that he would care, hasn't been around since 2007)
08:59:37 <oerjan> i don't _think_ it's me, anyway, i don't recognize those edits.
09:04:18 -!- Phantom_Hoover has joined.
09:12:21 <oren> Hmm... I can tell I'm still young, because none of the languages I know has become obsolete yet
09:13:19 <oren> Whereas my dad knows Perl 3 and Fortran or something
09:13:29 <oren> and therefore is old
09:14:19 * oerjan waves from Pascal-land
09:15:51 <oren> I think Perl as glue is dying in favor of python as glue though... so it won't be long...
09:19:15 <fizzie> oerjan: It's the bizarro-oerjan, your goateed evil counterpart.
09:20:46 <oerjan> fizzie: you've got it backwards hth also HackEgo is damn slow
09:22:40 <fizzie> I assume it's the VPS provider.
09:22:44 <shachaf> I thought it just wasn't working?
09:22:57 <fizzie> The wiki bridge was working less than an hour ago.
09:23:14 <shachaf> Yes, but ` hasn't been working for much longer than that.
09:23:55 <fizzie> That seems plausible, given the logs.
09:24:24 <fizzie> I remember it getting stuck once, due to a thing that I fixed.
09:24:39 <fizzie> It was something related to file permissions, some bit had gone missing.
09:24:51 <fizzie> Of course I didn't write down the details, because where's the fun in that?
09:25:20 <b_jonas> but it worked a few days ago
09:25:39 * oerjan recalls some time when `help worked but not user commands
09:26:07 <coppro> I should probably go to sleep
09:27:36 <fizzie> Well, it's also being slow-ish over SSH, especially if I try to do anything disk-related. But that's probably not the main problem.
09:28:53 <fizzie> It's not on the channel, that's what's up.
09:29:11 <oerjan> um according to my tab completion, it is
09:29:22 <fizzie> According to my /n, it's not.
09:29:30 <fizzie> Perhaps your tab completion is based on incoming messages.
09:30:04 <oerjan> surely it's based on /quits etc.
09:30:09 <fizzie> I think it's a nicely-formatted 'WHO', but it could also be based on 'NAMES'. I'm not entirely sure.
09:30:17 -!- oerjan has left.
09:30:17 -!- oerjan has joined.
09:30:49 -!- HackEgo has joined.
09:31:06 <oerjan> so it was some kind of irc network failure, actually
09:31:13 <HackEgo> Ørjan is oerjan's good twin. He's banned in the IRC RFC for being an invalid character. Sometimes he publishes papers.
09:32:04 <fizzie> (I didn't realize we're so non-'+n' inclusive we allow messages from people not on the channel.)
09:32:47 <oerjan> i think it's irssi getting confused, right
09:34:12 <oerjan> right, HackEgo never was here since i joined, so it must have been the wiki announcement that did it
09:34:34 <oerjan> fizzie: i think it's an experiment?
09:35:27 <oerjan> i think this is the first time a problem has appeared with -n
09:35:53 <oerjan> or well, that i've noticed anyway
09:36:17 <fizzie> Now you'll presumably have that stuck in your tab-completion list, since it won't get any part/quit.
09:36:49 <oerjan> maybe people have messaged from out of channel left and right, and i never noticed they weren't here.
09:38:42 <fizzie> An evil person could make tab-completion arbitrarily difficult by making conflicting prefixes for every nick at every length.
09:42:10 <int-e> But the solution is obvious: only allow single letter nicknames. (Good morning!)
09:43:44 -!- mroman has changed nick to fizzia.
09:44:57 -!- oerjan has left.
09:44:57 -!- oerjan has joined.
09:46:42 <oerjan> int-e: i made a new trac post in the thread
09:46:56 <oerjan> i assume since i didn't get a Cc: you didn't either
09:47:43 <oerjan> now with an actual proof.
09:47:50 <fizzie> "#esoteric: Total of 104 nicks" that's a bit problematic for single-letter (printable ASCII not-reserved-by-IRC) names.
09:49:20 <fizzie> "[0 ops, 0 halfops, 0 voices, 104 normal]" I'm not sure that last word is exactly the right one.
09:53:01 <oerjan> all matter of hairy business, including splitting
09:54:32 <fizzie> In retrospect, I think irssi's tab-complete is based on last-one-who-spoke-first-on-the-list, which would make that less efficient.
10:00:03 <fizzia> irssi has intelligent tab-completion yes.
10:11:04 -!- aretecode has quit (Ping timeout: 246 seconds).
10:14:30 <int-e> fizzie: that can't be, my plan was perfect!
10:17:24 -!- int-e has set topic: Foiled by numbers | Dilapitated depilators | https://dl.dropboxusercontent.com/u/2023808/wisdom.pdf http://codu.org/logs/_esoteric/ http://tunes.org/~nef/logs/esoteric/.
10:17:37 <oerjan> int-e: btw if you see any fatal flaw in my proof (including any form of Typeable-capable types that don't fit in either branch of argument) that might mean another exploit that works against spj's fix.
10:18:25 -!- aretecode has joined.
10:19:20 <int-e> oerjan: Maybe later. I'm not sure what you mean by "kind-ambiguous" right now, which means I don't know why the list you gave is exhaustive.
10:24:41 <oerjan> i mean, basically, any two type constructors with the same TypeRep, which afaik now only happens because of the */Constraint ambiguity in (), (,), ..., -> / =>
10:25:48 <oerjan> because Haskell distinguishes them, but core doesn't, and the kind parameters for Typeable are extracted from core.
10:26:36 <oerjan> or well not quite core maybe, but the upshot is this list has no kind parameters that get used for the TypeRep.
10:27:15 -!- boily has joined.
11:30:17 -!- boily has quit (Quit: LIBERATED CHICKEN).
11:58:38 -!- bb010g has quit (Quit: Connection closed for inactivity).
12:37:27 -!- hjulle has joined.
12:50:01 -!- Patashu has quit (Ping timeout: 276 seconds).
12:58:43 -!- ProofTechnique has quit (Ping timeout: 246 seconds).
12:59:39 -!- Tod-Autojoined has changed nick to TodPunk.
13:19:58 -!- dianne has quit (Quit: byeannes).
13:25:58 -!- ProofTechnique has joined.
13:49:41 <b_jonas> `oeis 16271255119687320314
13:49:43 <HackEgo> /home/hackbot/hackbot.hg/multibot_cmds/lib/limits: line 5: exec: oeis: not found
13:52:28 -!- stuntaneous has joined.
13:53:26 -!- stuntaneous has quit (Client Quit).
13:57:06 -!- bb010g has joined.
14:00:08 <int-e> @oeis 16271255119687320314
14:00:21 <Jafet> `factor 16271255119687320314
14:00:21 <HackEgo> 16271255119687320314: 2 19 137 3989 61519 12736309
14:00:33 <lambdabot> Tetranacci numbers: a(n) = a(n-1) + a(n-2) + a(n-3) + a(n-4) with a(0)=a(1)=...
14:01:26 -!- `^_^v has joined.
14:03:28 <b_jonas> int-e: unless I made a mistake, it's the number of sets of squares of a 8x8 chessboard such that each row and each column has some but not all squares in the subset
14:04:05 <Jafet> @google 16271255119687320314
14:04:14 <b_jonas> but someone should check that
14:05:31 <int-e> so relations on {1..8} with full domain and codomain?
14:07:30 <b_jonas> what's the domain of a relation in that sense?
14:07:40 <int-e> domain and codomain are defined by dom(R) = {a | (a,b) in R}; cod(R) = {b | (a,b) in R}.
14:08:11 <b_jonas> in which case there would be (2**8-2)**8 such relations
14:08:16 <b_jonas> but I restrict both rows and columns
14:08:43 <int-e> What? Surely you mean 255^8, not 254^8. But you're wrong.
14:09:09 <b_jonas> the codomain is teh columns
14:09:54 <b_jonas> in that case I want relations such that the domain and codomain is full, and also the domain and codomain of the negation (complement) of that relation are also full
14:10:14 <int-e> Ah, I missed that.
14:10:59 <b_jonas> that's probably why it's not in oeis
14:14:28 <tromp> you want chessboards with no monochromatic ranks or files
14:16:59 <b_jonas> tromp: yes, black and white chessboards with no monochromatic ranks or files
14:17:11 <j-bot> b_jonas: 1.73249e19
14:17:58 <izabera> `` printf '\x03,%dx' {0..33}
14:17:59 <HackEgo> ,0x,1x,2x,3x,4x,5x,6x,7x,8x,9x,10x,11x,12x,13x,14x,15x,16x,17x,18x,19x,20x,21x,22x,23x,24x,25x,26x,27x,28x,29x,30x,31x,32x,33x
14:18:13 <izabera> `` printf '\x03%dx' {0..33}
14:18:14 <HackEgo> xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx
14:23:36 <int-e> > let c n 0 = 1; c n k = c (n-1) (k-1); f n = (2^n - 2)^n + sum [(-1)^k * (2^((n-k)*n) * (2^k - 2) + (2^(n-k)-1)^n*2) * c n k | k <- [1..n]] in map f [1..8]
14:23:38 <lambdabot> [0,4,174,34204,22874190,55079812684,496433383427646,17190560520625432252]
14:24:00 <int-e> > let c n 0 = 1; c n k = c (n-1) (k-1) * n `div` k; f n = (2^n - 2)^n + sum [(-1)^k * (2^((n-k)*n) * (2^k - 2) + (2^(n-k)-1)^n*2) * c n k | k <- [1..n]] in map f [1..8]
14:24:01 <lambdabot> [0,2,102,22874,17633670,46959933962,451575174961302,16271255119687320314]
14:24:34 <b_jonas> [ 16271255119687320314=16271255119687320314
14:24:47 <b_jonas> hmm, how does that computation work?
14:24:53 <b_jonas> I used a more complicated computation
14:25:52 <int-e> Inclusion-exclusion principle: Starting from (2^k-2)^n solutions satisfying the column criterion, it computes how many of those have k=1..8 equal rows.
14:26:19 <b_jonas> I wondered if something like that would work
14:26:41 <b_jonas> but eventually wrote a computation that's more complicated, though still fast for 8x8 on a computer
14:27:34 <int-e> so that gives a c n k factor (for selecting the k equal rows), and then (2^k - 2) cases with 2^((n-k)*n) solutions (where the monochromatic rows have mixed colors) and 2 cases with (2^(n-k)-1)^n solutions because the monochromatic rows all have the same color.
14:27:49 <b_jonas> but don't you need to multiply by a binomial somewhere?
14:27:58 <int-e> c n k is a binomial.
14:28:26 <int-e> @oeis 0 2 102 22874
14:30:21 <b_jonas> here's my solution: http://rextester.com/QNQCE30194
14:31:36 <tromp> what is running time as function of boardsize?
14:31:52 <b_jonas> tromp: of my solution? exponential
14:32:20 <tromp> exponential in n or in n^2 for an nxn board?
14:32:21 <b_jonas> O((3+epsilon)**width) I think
14:32:32 <b_jonas> exponential in n for an nxn board
14:32:59 <tromp> can't you compute this with the inclusion-exclusion formula?
14:33:10 <b_jonas> sure, but this occurred to me first
14:33:15 <int-e> tromp: scroll back a bit :)
14:33:29 <b_jonas> the inclusion-exclusion formula int-e shows is a better way
14:33:58 <tromp> ah, you're ahead of me, int-e :)
14:34:04 <b_jonas> in fact, I think mine could be optimized to a somewhat more complicated polynomial time solution
14:34:53 <b_jonas> it would have a somewhat higher exponent but whatever
14:34:57 <b_jonas> I won't implement that though
14:38:15 <int-e> at least https://oeis.org/A048291 exists
14:43:02 <tromp> meanwhile, my 19x19 go computation is still going...
14:44:19 <b_jonas> hehe, this is a strange channel, I give a computation and two people try to implement it rightaway
14:44:27 <b_jonas> tromp: or are you computing something else?
14:44:51 <tromp> i'm computing the number of legal 19x19 Go positions, which is somewhat more involved:)
14:45:20 <tromp> should get finished this year though
14:47:15 <HackEgo> [wiki] [[Lesser known programming languages]] http://esolangs.org/w/index.php?diff=42580&oldid=7995 * 50.23.113.210 * (+51)
14:48:46 <HackEgo> [wiki] [[Lesser known programming languages]] http://esolangs.org/w/index.php?diff=42581&oldid=42580 * B jonas * (-51) revert spam by User:50.23.113.210
14:50:43 -!- Sprocklem has joined.
14:57:53 <int-e> tromp: do you know the answer modulo some primes (2^64-ish, I guess) already?
15:00:03 <HackEgo> [wiki] [[Babble]] http://esolangs.org/w/index.php?diff=42582&oldid=42550 * Rottytooth * (+34) clarity
15:00:40 -!- GeekDude has joined.
15:00:56 <HackEgo> [wiki] [[Babble]] M http://esolangs.org/w/index.php?diff=42583&oldid=42582 * Rottytooth * (+16) /* Concept */
15:01:59 <tromp> no, it will take another 6 weeks or so to get the first congruence (mod 2^64)
15:02:36 <tromp> you can see the progress at http://tromp.github.io/go/legal.html
15:08:39 -!- rdococ has joined.
15:12:43 -!- variable has joined.
15:15:42 <rdococ> variable: since I'm so [not
15:16:09 <rdococ> variable: since I'm so [not] kind, I'll elevate you to a first class object... lol... get it?
15:22:16 <b_jonas> what? you're computing it modulo something?
15:23:14 <int-e> b_jonas: modulo several things, to be combined by the chinese remainder theorem to obtain the full answer
15:23:27 <b_jonas> right, but how does that help in this case?
15:23:42 <int-e> b_jonas: it helps keeping the numbers to machine word size
15:23:51 <b_jonas> sure, but you're traversing a graph
15:24:06 <b_jonas> isn't it better to do all the computations at once?
15:24:09 <b_jonas> I mean, it doesn't have to be radixal
15:24:15 <b_jonas> but all the congruences at the same time
15:24:29 <b_jonas> so you just have to apply chinese remainder once at the very end, which is very quick
15:24:50 <b_jonas> as opposed to computing the result with one modulus first
15:26:36 <tromp> the problem is almost IO bound
15:27:09 <int-e> > 3^20 -- too low because it doesn't take connectivity into account.
15:27:12 <b_jonas> hmm, maybe it's just that you don't know any more efficient way to parallize the problem
15:27:39 <tromp> with filesize proportional to number of state-cnt pairs that can be held in memory
15:28:31 <b_jonas> tromp: sure, but if you eg. computed the values modulo some 128 bit number instead of 64 bit number, how much larger would the io work become? twice larger, or just 1.1 larger?
15:28:39 <FireFly> tromp: will you do 19×17 too, afterwards? To complete all {1..19}×{1..19} combinations
15:28:55 <tromp> so with 566 bit counts, you cldn't hold many states in memory, and get files with few states, which makes IO a much bigger problem
15:28:59 <int-e> > 363324268018 / 3^20
15:29:32 <tromp> i will do all 19xn, n up to 20
15:30:03 <b_jonas> tromp: do you get separate counts for black to go next and white to go next?
15:30:05 <tromp> b_jonas: about 1.9 times larger
15:30:27 <b_jonas> tromp: I see. in that case parallelizing this way _might_ help, if you read the io sequentially enough
15:30:36 <tromp> i'm counting positions. there is no notoin of who is to move
15:30:40 <b_jonas> I can't imagine how this could work
15:31:15 -!- variable has quit (Ping timeout: 240 seconds).
15:31:59 <int-e> "Allowing for some redundancy, we need from 10 to 13 servers, each with at least 32 cores, 512GB RAM, and ample disk space (10-15TB), running for about 3-5 months." -- this disk space seems quite tightly calculated.
15:32:31 <int-e> (going by the 363324268018 number)
15:32:45 <tromp> each "vector" takes about 4.3TB
15:33:21 <int-e> > 363324268018 * 8 -- plus some allowance for efficient access?
15:33:54 <tromp> each modulus needs at least the current and new vector, but preferably also the previous and an older one for error recovery
15:34:41 <tromp> int-e: you need between 1 and 2 bytes on avg for the state-delta
15:35:16 <tromp> and the vectors have states duplicated
15:36:14 <tromp> each state could occur up to 3 times, in different files of a state vector
15:36:55 <tromp> but most duplicates are alrd eliminated by the in-memory sorting
15:36:58 <b_jonas> compared to this, we work with small data and quick computations
15:37:15 <tromp> i dont actually need 512GB that was rather conservative
15:37:25 <tromp> i can manage with 128GB
15:38:00 <tromp> the main requirement is high disk IO bandwidth
15:38:25 -!- ais523 has joined.
15:38:40 <b_jonas> even still, the beefyest machine I use here has 32GB of ram only, and 24 cores, though it does have a RAID with like twenty terabytes of disk space and fast IO bandwidth because we're recording raw image data quickly and compressing it later
15:38:56 <b_jonas> ais523: I was thinking about what you said, and you're right
15:39:31 <b_jonas> you only need to handle the case with identical reduce actions for any possible lookahead token (the reduce action can be a one symbol reduce), not the case of an identical shift
15:40:54 <b_jonas> (also, it's a NUMA machine)
15:41:24 <b_jonas> (and with a crazy fast CPU)
15:47:20 -!- ais523 has quit (Ping timeout: 264 seconds).
15:51:05 -!- nszceta has joined.
15:51:52 -!- nszceta has quit (Max SendQ exceeded).
15:53:57 -!- nszceta has joined.
15:55:08 -!- nszceta has quit (Max SendQ exceeded).
15:55:48 -!- nszceta has joined.
15:58:39 -!- bb010g has quit (Quit: Connection closed for inactivity).
16:05:27 -!- nszceta has quit (Quit: My Mac has gone to sleep. ZZZzzz…).
16:12:31 -!- nszceta has joined.
16:12:31 -!- nszceta has quit (Read error: Connection reset by peer).
16:14:05 -!- MDude has joined.
16:20:24 -!- vodkode has joined.
16:22:31 -!- Sprocklem has quit (Quit: Bye).
16:30:47 <rdococ> is an OISC with a command to copy the bit at one address to a second, then flip the first, turing complete
16:32:14 <int-e> @oeis 1 3 9 31 113
16:32:15 <lambdabot> G.f.: (1-sqrt(1-4x-4x^2))/(2(1+x)).[0,1,1,3,9,31,113,431,1697,6847,28161,117...
16:32:34 <int-e> @oeis 1 3 9 31 113 435
16:36:21 -!- hjulle has quit (Ping timeout: 250 seconds).
16:41:34 <lambdabot> Fibonacci numbers: F(n) = F(n-1) + F(n-2) with F(0) = 0 and F(1) = 1.[0,1,1,...
16:50:16 <rdococ> I didn't even noticed a spambot got hold of my talk page...
16:50:24 -!- rdococ has quit (Quit: Page closed).
16:51:54 -!- rdococ has joined.
17:01:33 <rdococ> a finite state automaton could be a described as a finite set of ordered triples p = {(x,y,z)}.
17:02:18 <rdococ> and if they're numbers, then you can make a raster image with it
17:04:17 <rdococ> assuming you have infinite color depth
17:04:31 <rdococ> or atleast unbounded, so
17:04:39 -!- ProofTechnique has quit (Quit: ZNC - http://znc.in).
17:07:22 -!- ProofTechnique has joined.
17:16:01 -!- variable has joined.
17:16:09 -!- Hijiri has quit (Ping timeout: 256 seconds).
17:22:34 -!- Guest3780 has quit (Read error: Connection reset by peer).
17:24:21 -!- Guest3780 has joined.
17:42:26 -!- CADD has joined.
17:43:10 <rdococ> why do programs have to exist
17:44:43 <rdococ> syntax error: unknown channel
17:45:40 <rdococ> oh and apparently I'm banned from ##philosophy -.- forgot how notorious I look
17:46:00 <rdococ> I feel so lonely... nearly every channel rejects me...
17:46:20 <rdococ> I'm always the lonely one... the weird one...
17:48:26 <rdococ> well atleast this channel still likes me
17:53:44 <rdococ> ...I don't like monologues
17:57:28 -!- variable has quit (Ping timeout: 276 seconds).
17:58:50 <int-e> oerjan: #9858 comment 90 would be more helpful if the required extensions had been listed... I've narrowed it down to KindSignatures + ScopedTypeVariables + TypeFamilies for the first one and PolyKinds + ScopedTypeFamilies for the second one. Interestingly, TypeFamilies seems to be essential for the first one...
18:00:34 <int-e> oh wait, GADTs works as well.
18:07:17 <b_jonas> let me read your sieve formula, I tried to reproduce the sieve but got the wrong result
18:07:27 <b_jonas> I have to multiply by a power of 2
18:08:38 <b_jonas> > let c n 0 = 1; c n k = c (n-1) (k-1) * n `div` k; f n = (2^n - 2)^n + sum [(-1)^k * (2^((n-k)*n) * (2^k - 2) + (2^(n-k)-1)^n*2) * c n k | k <- [1..n]] in map f [1..8]
18:08:40 <lambdabot> [0,2,102,22874,17633670,46959933962,451575174961302,16271255119687320314]
18:09:16 <b_jonas> > let { c n 0 = 1; c n k = c (n-1) (k-1) * n `div` k; } in map (c 8) [0..8]
18:10:59 <b_jonas> that's different from the formula I tried
18:13:04 <b_jonas> ok wait, mine gives the wrong result already for a 2x2 chessboard
18:20:28 -!- TESSSSSSSSSSSSSS has joined.
18:20:54 -!- TESSSSSSSSSSSSSS has changed nick to Sprocklem.
18:29:37 <tromp> first get 1x1 correct (0)
18:30:07 <b_jonas> tromp: that one was correct, and 0x0 too
18:30:16 <tromp> then 1x2 and 2x1 (also 0)
18:32:21 <b_jonas> no, the formula I used is just wrong, and I know why
18:32:28 <b_jonas> I'll just have to try to write the correct formula now
18:32:33 <tromp> answer for 2xn is 2^n-2
18:33:48 <int-e> oerjan: oh, news on #9858, looks like you got what you wanted?
18:40:37 -!- zadock has joined.
18:46:20 -!- zadock has quit (Max SendQ exceeded).
18:47:05 -!- zadock has joined.
18:59:28 -!- bb010g has joined.
19:00:07 -!- zadock has quit (Quit: Leaving).
19:03:03 -!- AnotherTest has joined.
19:07:35 -!- AnotherTest has quit (Ping timeout: 250 seconds).
19:25:44 -!- Phantom_Hoover has quit (Ping timeout: 252 seconds).
19:27:31 -!- Phantom_Hoover has joined.
19:28:57 <b_jonas> heh, I made another wrong formula
19:30:38 <b_jonas> [ 3 :'+/,(([!y-])*(]!y"_)*(_1^+)*y^~(y>:+)*+/&(0&=)-~2^y-+)"0/~i.>:y'"0 i.9x
19:30:38 <j-bot> b_jonas: 1 0 2 102 22874 17633670 46959933962 451575174961302 16271255119687320314
19:31:19 <b_jonas> it could be turned to a single sum but then there'd be more conditions so this is simpler to write
19:32:16 -!- nszceta has joined.
19:36:45 -!- Hijiri has joined.
19:52:18 -!- Sprocklem has quit (Ping timeout: 255 seconds).
20:00:52 -!- Sprocklem has joined.
20:01:01 -!- Frooxius has joined.
20:15:09 -!- Encapsulation has joined.
20:15:37 <Encapsulation> I'm facing a challenge right now in my program. I need objects running methods and having their attributes change at regular intervals and in reaction to events while simultaneously providing I/O to the user. Which language would be best suited for me?
20:21:11 <izabera> Encapsulation: maybe #esoteric isn't the best place to ask such a question.....
20:23:28 <MDude> Abstract State Machine Language?
20:25:19 -!- variable has joined.
20:30:59 <rdococ> #esoteric is for esoteric programming languages
20:31:08 <rdococ> ie, ones you probably don't want to use, lol
20:31:28 <rdococ> what? I just wanted a laugh... lol
20:31:38 <rdococ> I need to stop using lol, lol
20:38:31 -!- Frooxius has quit (Ping timeout: 244 seconds).
20:42:35 -!- Phantom_Hoover has quit (Ping timeout: 256 seconds).
20:43:58 -!- Hijiri has quit (Quit: WeeChat 1.0.1).
20:44:07 -!- Frooxius has joined.
20:45:16 -!- Froox has joined.
20:47:13 -!- Froo has joined.
20:48:58 -!- Frooxius has quit (Ping timeout: 265 seconds).
20:49:48 -!- Froox has quit (Ping timeout: 256 seconds).
20:53:02 <b_jonas> [ 3 :'(y^~_2+2^y)--/(!&y*(2*y^~_1+2^y&-)+(2^y*y&-)*_2+2&^)>:i.y'"0 i.9x
20:53:03 <j-bot> b_jonas: 1 0 2 102 22874 17633670 46959933962 451575174961302 16271255119687320314
20:53:16 <b_jonas> ^ that one is just a single summation
20:53:33 <b_jonas> [ 3 :'+/,(([!y-])*(]!y"_)*(_1^+)*y^~(y>:+)*+/&(0&=)-~2^y-+)"0/~i.>:y'"0 i.9x
20:53:34 <j-bot> b_jonas: 1 0 2 102 22874 17633670 46959933962 451575174961302 16271255119687320314
20:53:53 <b_jonas> [ rv0=: 3 :'+/,(([!y-])*(]!y"_)*(_1^+)*y^~(y>:+)*+/&(0&=)-~2^y-+)"0/~i.>:y'"0 i.9x
20:54:02 <b_jonas> [ rv2=: 3 :'+/,(([!y-])*(]!y"_)*(_1^+)*y^~(y>:+)*+/&(0&=)-~2^y-+)"0/~i.>:y'"0 i.9x
20:54:10 <j-bot> b_jonas: 1 0 2 102 22874 17633670 46959933962 451575174961302 16271255119687320314
20:54:31 <b_jonas> somehow it even came out shorter, though probably the expression for the double sum could be written more concise too
20:55:11 -!- Phantom_Hoover has joined.
20:55:30 <b_jonas> I'm comparing the wron gthing
20:55:33 <b_jonas> the single summation is longer
20:55:46 <b_jonas> [ ]rv2=: 3 :'(y^~_2+2^y)--/(!&y*(2*y^~_1+2^y&-)+(2^y*y&-)*_2+2&^)>:i.y'"0 i.9x
20:55:47 <j-bot> b_jonas: 1 0 2 102 22874 17633670 46959933962 451575174961302 16271255119687320314
20:56:17 <b_jonas> no, the single summation is shorter afterall
20:56:51 <b_jonas> [ rv0=: 3 :'+/,(([!y-])*(]!y"_)*(_1^+)*y^~(y>:+)*+/&(0&=)-~2^y-+)"0/~i.>:y'"0 i.9x
21:00:10 -!- nszceta has quit (Quit: Textual IRC Client: www.textualapp.com).
21:05:51 -!- Patashu has joined.
21:10:13 -!- ProofTechnique has quit (Ping timeout: 250 seconds).
21:13:25 -!- variable has changed nick to trout.
21:20:23 <rdococ> I didn't know there was a trout class.
21:20:44 <trout> rdococ, you didn't know that trout is directly related to programming?
21:21:08 <rdococ> anyway, I have another boring esolang coming, but atleast it'll have a punny name
21:21:28 <int-e> . o O ( is this an example of trolling fish? )
21:22:49 -!- Sprocklem has quit (Ping timeout: 256 seconds).
21:26:41 -!- Patashu has quit (Ping timeout: 265 seconds).
21:27:11 <olsner> isn't it spelled trawling when you do it to fish?
21:27:24 <olsner> or is that just how I imagine it should be
21:27:28 <oren> Hmm... What if there was a language sufficiently flexible that you could write it to look like C, Fortran, Pascal, or Basic?
21:28:08 <HackEgo> [wiki] [[State of the Art]] N http://esolangs.org/w/index.php?oldid=42584 * Rdococ * (+1182) new esolang
21:28:20 <oren> e.g. int x; and dim x as integer would both be valid
21:28:40 <HackEgo> [wiki] [[State of the Art]] M http://esolangs.org/w/index.php?diff=42585&oldid=42584 * Rdococ * (+9) lil' stubby
21:28:58 <int-e> olsner: "Trolling can be phonetically confused with trawling, a different method of fishing where a net (trawl) is drawn through the water instead of lines." says Wikipedia
21:29:32 <rdococ> it could be trolling because the fish put on the rage face
21:30:13 <int-e> Pouting trouts are not a pretty sight.
21:30:45 <HackEgo> [wiki] [[User:Rdococ]] http://esolangs.org/w/index.php?diff=42586&oldid=42553 * Rdococ * (+23) /* My esoteric programming languages */
21:31:07 <int-e> trout: Apologies for the puns, I hope you do not take them seriously.
21:31:16 <olsner> according to what I hear, these days it's all about the bass
21:31:22 <rdococ> sorry about those puns...
21:31:23 <trout> int-e, puns are fine, that is the whole point of having such a username
21:31:31 -!- sebbu has quit (Ping timeout: 265 seconds).
21:31:40 <rdococ> also, scroll bar wont scroll down
21:31:51 <trout> int-e, I do have a question about your name though
21:32:01 <trout> are you intenctionally casting it?
21:32:25 <olsner> int e is a page fault, maybe that's it
21:32:44 <rdococ> he's more likely to be 3, I think
21:32:48 <int-e> rdococ: that's a better guess than I've seen in a while.
21:33:08 <oren> in C iirc (int) rounds down
21:33:32 -!- sebbu has joined.
21:33:32 <trout> oren, it truncates, yes
21:33:33 <rdococ> don't use C, prefer lua
21:33:56 <rdococ> because low-level stuff derps and costs money and herps.
21:34:10 -!- sebbu has quit (Changing host).
21:34:10 -!- sebbu has joined.
21:35:12 <oren> trout: so it rounds toward zero. I think it's probably a bad idea to rely on that though.
21:40:32 <rdococ> I'd like a programming language based on nothing
21:41:14 <rdococ> should I have just created a bf derivative?
21:44:05 -!- aretecode has quit (Quit: Toodaloo).
21:46:52 -!- `^_^v has quit (Quit: This computer has gone to sleep).
21:54:40 <rdococ> maybe I should just add some hashing requirement
22:00:27 <izabera> unzip unrar unxz... gunzip
22:00:47 <izabera> i type ungzip every fucking time and i keep getting command not found
22:02:55 <oren> put an alias in your bashrc
22:03:24 <oren> I have alias fuckyou as pkill
22:04:36 <izabera> silent () { "$@" > /dev/null 2>&1; }
22:04:38 <izabera> silout () { "$@" > /dev/null; }
22:04:40 <izabera> silerr () { "$@" 2> /dev/null; }
22:06:06 -!- trout has quit (Quit: 1 found in /dev/zero).
22:06:42 <oren> I have a lot of aliases doing that stuff because, after canonical ruined everything with unity, every GUI program outputs:
22:07:08 <oren> Gtk-Message: Failed to load module "overlay-scrollbar"
22:07:15 <oren> every few seconds
22:07:24 -!- Phantom_Hoover has quit (Ping timeout: 244 seconds).
22:07:40 <elliott> izabera: install http://hartlich.com/deco/ and just use "deco" for all of them :p
22:08:06 <elliott> (deco{,-archive} are in the AUR)
22:08:26 <elliott> also protects against tar bombs
22:08:28 -!- Phantom_Hoover has joined.
22:10:05 -!- idris-bot has quit (Quit: Terminated).
22:10:18 <izabera> well honestly i never had problems with tar bombs.......
22:10:39 <izabera> probably gnu tar has an option for it <.<
22:11:21 <izabera> it does, see the overwrite control section in the man page
22:11:42 -!- idris-bot has joined.
22:11:51 <elliott> well, it's mostly .zip bombs
22:12:06 <elliott> a lot of the time I'm like "oh okay this is a .zip not a tar so uh 'unzip foo.zip'... fuck, the files went everywhere"
22:12:14 <elliott> hence deco's consistency is nice :p
22:13:24 <izabera> i believe files in a zip archive can't have hardcoded paths...
22:13:58 <izabera> i mean the worst that can happen is that they clobber the current directory
22:14:12 <elliott> yeah but that's the problem when the current directory is ~ or a downloads dir or something
22:14:16 <int-e> and of course tar files can do that as well.
22:14:20 <elliott> it's just a minor annoyance
22:14:57 <izabera> int-e: yeah but in a tar you can have a file that extracts to /bin/whatever
22:15:41 <int-e> izabera: and GNU tar at least strips leading slashes by default.
22:18:43 <oren> generally I don't just untar things
22:18:45 -!- bb010g has quit (Quit: Connection closed for inactivity).
22:18:56 <oren> I extract the specific files I want
22:20:55 <oren> tar -tzf foo.tar
22:21:17 <int-e> "By default, GNU tar drops a leading `/' on input or output, and complains about file names containing a `..' component."
22:22:04 <int-e> with that behaviour it's no worse than zip
22:22:52 -!- dianne has joined.
22:22:57 <int-e> (well, I suppose you can create interesting symlinks or special files)
22:23:40 <oren> Also if you extract a whole archive, use tar -xkzvf foo.tgz
22:24:03 -!- augur has quit (Remote host closed the connection).
22:24:19 <oren> k makes it not clobber existing files
22:26:12 <oren> I learned about tar after seeing that XKCD comic
22:26:17 <int-e> yeah, well, no. I'm a tar xzf person.
22:27:37 <int-e> (but I have a scratch directory where I unpack stuff, and usually do a tar tzf first when I'm not dealing with a source code distribution of software I'm used to...)
22:29:39 <int-e> (I've lost more data to hitting ^J instead of ^K than I have lost to extracting tar files in a different place than I wanted.)
22:29:57 -!- augur has joined.
22:30:26 -!- FreeFull_ has changed nick to FreeFull.
22:31:20 <oren> I know ^J is the same as enter...
22:31:27 <elliott> alternative explanation: d$
22:32:49 <oren> anyway I don't understand how you can lose data to hitting enter instead of cutting the line?
22:32:55 -!- Froox has joined.
22:33:51 <izabera> don't take it too seriously...
22:33:57 <int-e> by executing a half-typed command instead of deleting it. as a silly example, consider rm -rf ./ [err, no, I don't want to actually delete anything], followed by ^A (beginning of line), ^J.
22:36:27 -!- Froo has quit (Ping timeout: 250 seconds).
22:37:24 <int-e> (Perhaps I should use ^U instead of ^A^K. But U is also next to J.)
22:37:41 <oren> What about just down?
22:37:44 -!- Froox has quit (Ping timeout: 245 seconds).
22:37:59 <izabera> perhaps consider using vi mode <.<
22:38:53 <oren> nonononononononon
22:39:19 <elliott> I use vim but emacs keybindings in everything else
22:39:24 <int-e> oren: down doesn't delete anything for me (bash / readline)
22:39:31 -!- ProofTechnique has joined.
22:39:35 -!- Frooxius has joined.
22:39:58 <int-e> elliott: no more weird than any other hacker I've ever met
22:40:07 -!- Froox has joined.
22:40:18 <oren> Hm? oh. yeah for some reason I usually start every command by hitting up a fe tmes
22:40:23 <elliott> and also sometimes I use emacs but rarely these days
22:40:32 <elliott> but when I do use emacs I often edit ~/.emacs with vim
22:40:43 <oren> I use midnight commander's internal editor
22:40:44 <int-e> there are so many ways of doing stuff that nobody does everything the same way anyway
22:41:25 <oren> which makes even that nano people go "uh. what's that?"
22:41:39 <int-e> I use vi, too, for quick and simple edits. I switch to emacs when it involves moving stuff around (cut & paste)...
22:42:15 <int-e> nano gives me the vi effect (HOW DO I QUIT?)
22:42:38 <rdococ> real programmers use butterflies
22:42:43 <int-e> Err, I use vim, I should say. Cursor keys...
22:43:55 -!- Frooxius has quit (Ping timeout: 246 seconds).
22:44:26 <elliott> I get terrified when I do, like, "sudo -e" on a random system and nano pops up
22:44:41 <elliott> please. what condemned me to this fate. will I succeed in making the simple edit I'm going for here
22:45:04 <oren> nano has internal help tho
22:45:21 <int-e> (Actually quitting nano is not so hard anymore, but I still struggle with saving files. What's wrong with the "Save" verb? "WriteOut" makes no sense. Wordstar has died in the mid 1990s!)
22:45:24 -!- Froox has quit (Ping timeout: 256 seconds).
22:45:33 <oren> as in, the commands are at the bottom of the screen
22:46:05 <int-e> (needless to say the shortcuts are different from the wordstar ones as well...)
22:47:30 <int-e> "[ XOFF ignored, mumble mumble ]" ... cute.
22:48:39 <elliott> oren: it's hard to read when you're panicking though
22:49:39 <oren> I wish vi had like three or four lines of help at the bottom
22:51:09 <int-e> that would waste more than 10% of a 25 line terminal's screen estate...
22:51:47 <oren> it should enable it if it detcts you press escape like 5 times
22:52:22 * int-e wonders whether joe still exists
22:53:05 <int-e> (I don't seem to have it installed anywhere)
22:54:20 <oren> joe seems to exist, as in it prompts me to apt-get it
22:55:52 <izabera> vim has internal help too >.>
22:57:10 -!- vodkode has quit (Quit: Leaving).
22:57:39 <int-e> izabera: but it's hard to find when some other program (like crontab -e) launched it for you to edit a file.
22:59:25 <oren> izabera: where? http://snag.gy/CUxag.jpg
22:59:58 <oren> I don't see a list of commands or a thing saying "insert mode" or anything!
23:00:20 <izabera> how can you code with that
23:01:24 <FireFly> <izabera> i type ungzip every fucking time and i keep getting command not found ← don't forget bunzip2
23:01:39 <izabera> yeah that's another fucker -.-
23:01:42 -!- Hijiri has joined.
23:01:55 <int-e> right. without transparency ;) http://int-e.eu/~bf3/tmp/vi.png
23:02:17 <izabera> <esc>:h topic-you-want-help-about
23:02:21 <int-e> . o O ( Same as gzip, I use bzip2 -d )
23:02:57 <int-e> izabera: You know about vi already. We're discussing a first user experience here. Or so I thought.
23:03:11 <izabera> What is the meaning of life, the universe and everything? *42*
23:03:14 <izabera> Douglas Adams, the only person who knew what this question really was about is
23:03:16 <izabera> now dead, unfortunately. So now you might wonder what the meaning of death
23:04:04 <oren> anyway, mcedit has a list of commands at bottom, a status line at top with the name of the file. http://snag.gy/fBnvC.jpg nano has similar.
23:04:04 <int-e> Death is when you stop worrying about taxes.
23:04:38 <oren> Also you can click on the commands.
23:04:38 * int-e can't see anything in oren's screenshots.
23:04:56 <int-e> (same issue as izabera mentioned)
23:05:40 <oren> http://snag.gy/u2q1D.jpg
23:05:57 <FireFly> oren: when you start vim, you should get a startup message that tells you about :help
23:06:08 <FireFly> unless you explicitly disable it
23:06:44 <FireFly> "type :help<Enter> or <F1> for on-line help"
23:07:03 <int-e> FireFly: that works (for me) if you start 'vi', but not when you use 'vi file', which is what tools like crontab -e will do[D[D[D[D[D[D[D[D[D[D[D.
23:07:14 <int-e> (oops, slow terminal)
23:07:14 <oren> vim fake help file ... great. just great.
23:07:58 <oren> VIM - fake help file for vim-tiny The Vim online help is not installed on this Debian GNU/Linux system.
23:08:07 -!- Sprocklem has joined.
23:08:12 <FireFly> Well, what can I say.. blame Debian :P
23:08:25 <oren> anyway I set EDITOR to nano
23:09:21 -!- ProofTechnique has quit (Ping timeout: 256 seconds).
23:09:44 <FireFly> you could use the STANDARD EDITOR
23:09:47 <izabera> what does :version say in vim-tiny?
23:10:32 <FireFly> I know vim well enough, so the fact that ed ~ ex should help..
23:10:47 <int-e> ooh, nasty thought: set $EDITOR to /bin/rm ...
23:10:53 <elliott> izabera: have you ever used teco?
23:11:00 <elliott> it was nicer than ed when I tried it I think
23:11:11 <oren> ed is good. I can use ed well. but vi REALLY needs a help line at least telling me what mode i'm in. ed doesn'tneed it becuase you can see the commnads.
23:11:17 <elliott> acme is cooler than sam :p
23:11:40 <elliott> sam is the one that's ed + viewer windows, basically
23:11:56 <elliott> acme is the weird futuristic one
23:12:36 <elliott> I like it. it's minimal and flexible
23:12:42 <FireFly> oren: in vim, :set nocompatible and you get a mode thingy in the bottom left
23:13:11 <FireFly> ("nocompatible" meaning "drop strict vi emulation; I want vim powers")
23:13:44 <oren> I see... so now the arrow keys work
23:14:28 <izabera> i mapped the arrows to resize the split windows <.<
23:14:53 <oren> how do you move around the file then?
23:15:13 <elliott> I use hjkl(yubn) in roguelikes but arrow keys in vim.
23:15:34 <FireFly> I use hjklyubn in nethack because it's too messy to remap
23:15:39 <elliott> sometimes I try yubn in vim and am surprised to find they don't work
23:15:40 <FireFly> it's kinda.. weird. with dvorak though
23:15:45 <oren> why doesn't backspace work
23:16:02 <FireFly> Because of stupid defaults
23:16:02 <izabera> oren: set bs=eol,indent,start
23:16:17 <elliott> vim comes with some sample vimrc you can copy that's better than nothing
23:16:22 <elliott> it's probably in /usr/share somewhere
23:16:26 <FireFly> I hope neovim adopts nicer defaults
23:16:49 <FireFly> like, nocompatible and bs=eol,indent,start should definitely be default in 2015..
23:17:18 <FireFly> Yeah, that too, although I think that's less uniform than nocompatible and bs
23:18:01 <FireFly> The only downside I can think of for mapping Y to y$ is that you forget about the original Y when doing vimgolf..
23:18:44 <izabera> nnoremap n nzz <- also this and a couple more...
23:18:53 <oren> augh I think I prefer ed
23:19:04 <oren> ed doesn't have modes
23:19:10 <FireFly> You could use ex for a slightly more user-friendly ed
23:19:20 <izabera> it has normal and insert mode
23:19:30 <oren> (well it does, but they are like heredocs)
23:21:07 <FireFly> Hm, I guess ed is pretty straightforward after all
23:21:19 <oren> Hmm... maybe I can write my own ed with syntax highlighiting
23:22:35 <izabera> i wrote a readline wrapper to add history to ed
23:22:48 <izabera> so that the arrow keys are a little more useful
23:23:36 <FireFly> I was thinking "hey, ed is light enough that you could implement it in an esolang".. then I remembered :s
23:23:38 <oren> I've never written an editor before, but maybe I'll call it OED
23:25:06 <oren> well you can do ed -p:
23:25:19 <oren> then you get a prompt of :
23:25:19 <FireFly> With an esolang implementation of regex matching, I guess the regex engine would be bigger than the rest of the editor..
23:25:45 <izabera> actually a basic regex engine isn't that hard...
23:25:54 <shachaf> they support intersections and all sorts of things
23:26:31 <FireFly> izabera: yes, that is true..
23:28:18 <FireFly> shachaf: you mean using /\= ?
23:29:18 <FireFly> I was thinking of \@= which acts a bit like (?=) in PCRE
23:29:58 <FireFly> Apparently \& is a \@= with implicit parens around everything to the left of it
23:30:17 <shachaf> Well, maybe \@= isn't the same as (?=)
23:30:36 <FireFly> "Note that using "\&" works the same as using "\@=": "foo\&.." is the same as "\(foo\)\@=..". But using "\&" is easier, you don't need the braces."
23:31:01 -!- GeekDude has changed nick to `test.
23:31:33 -!- augur_ has joined.
23:31:43 <FireFly> \@= tries to match the preceding atom zero-width, as far as I know that's the same as Perl's (?=...) (and the help seems to say so, too)
23:31:52 -!- Hijiri has quit (Ping timeout: 256 seconds).
23:32:58 <shachaf> If it does actual regular language intersection, then there's a difference.
23:33:26 <izabera> sorry guys i found this in ltrace's output regcomp(0x7ffeda758840, 0x740470, 1, 0) = 0
23:34:05 <izabera> i found that and regexec(0x7ffeda758840, 0x7403f0, 3, 0x741680) = 1
23:34:09 <izabera> and regfree(0x7ffeda758840, 0x7fb569fddc08, 0x741600, 0x740ec0) = 0
23:35:14 -!- augur has quit (Ping timeout: 245 seconds).
23:35:22 <izabera> ok np i just thought that some of you could know it <.<
23:37:05 -!- Hijiri has joined.
23:37:14 -!- augur_ has quit (Remote host closed the connection).
23:39:29 -!- augur has joined.
23:46:15 -!- `test has changed nick to GeekDude.
23:47:42 <elliott> izabera: I think you can teach strace that the first two parameters are pointers?
23:47:50 <elliott> strace knows types and follows pointers, at least
23:47:59 <elliott> you could just use gdb and breakpoint on regex stuff
23:48:48 <elliott> izabera: http://man7.org/linux/man-pages/man5/ltrace.conf.5.html
23:48:53 <elliott> make one of these for the functions in question
23:50:29 <izabera> i seriously hate debugging -_-
23:59:44 <shachaf> How efficiently can two regular expressions be compared for equivalence?
00:02:21 <int-e> Fun, that problem is EXPSPACE-complete.
00:02:46 <int-e> ( https://en.wikipedia.org/wiki/EXPSPACE )
00:02:47 <idris-bot> https://en.wikipedia.org/wiki/EXPSPACE )<EOF>
00:02:53 <int-e> idris-bot: ah yes.
00:03:01 <shachaf> int-e: Oh, I didn't find that.
00:03:10 <shachaf> EXPSPACE-complete is pretty bad.
00:03:29 <shachaf> Hmm, that's regular expressions with squaring, though.
00:04:00 <int-e> sorry, I didn't read far enough.
00:04:31 <shachaf> I guess it's better if you don't allow squaring?
00:04:56 <int-e> (Nor did I think, equivalence of NFA is in PSPACE)
00:05:54 <shachaf> But with squaring your NFA can be exponential in the size of the expression, I guess.
00:05:59 <int-e> So PSPACE-complete it is.
00:06:17 <int-e> squaring goes beyond regular languages.
00:07:00 <shachaf> http://cs.stackexchange.com/a/12625 says that in practice NFA equivalence can often be done efficiently.
00:24:37 -!- hjulle has joined.
00:34:00 -!- rdococ has quit (Ping timeout: 246 seconds).
00:36:01 -!- rdococ has joined.
00:40:13 <int-e> shachaf: does ^(|.*((a[^a]|[^a]a).............[^a]|(aa|[^a][^a]).............a).*|[^a].*|..?.?.?.?.?.?.?.?.?.?.?.?a.*|.*a|.*[^a].?.?.?.?.?.?.?.?.?.?.?.?.?.)$ match all strings? What about ^(|.*((a[^a]|[^a]a).............[^a]|(aa|[^a][^a]).............a).*|[^a].*|..?.?.?.?.?.?.?.?.?.?.?.?a.*|.*a|.*[^a].?.?.?.?.?.?.?.?.?.?.?.?.?.?.)$?
00:41:47 <int-e> which I have messed up, let me try that again...
00:42:47 <oerjan> ah they went with my suggestion 2+3, essentially
00:43:29 <shachaf> int-e: Did you produce those by using some algorithm to take the complement of a string?
00:43:36 <oerjan> now i started to briefly worry about * -> # -> *
00:44:03 <shachaf> Er, of a regular expression.
00:44:47 <oerjan> however, there's _probably_ no way to construct something that's ambiguously # or *, so it _should_ be fine.
00:44:50 <int-e> the first one should be ^(|.*((a[^a]|[^a]a).............[^a]|(aa|[^a][^a]).............a).*|[^a].*|..?.?.?.?.?.?.?.?.?.?.?.?(a.*|)|.*a|.*[^a].?.?.?.?.?.?.?.?.?.?.?.?.?.)$, and the second one ^(|.*((a[^a]|[^a]a).............[^a]|(aa|[^a][^a]).............a).*|[^a].*|..?.?.?.?.?.?.?.?.?.?.?.?(a.*|)|.*a|.*[^a].?.?.?.?.?.?.?.?.?.?.?.?.?.?.)$
00:44:59 <int-e> shachaf: it's much much worse than that.
00:46:01 <shachaf> i,i they're just regular languages, how bad could it possibly be?
00:46:02 -!- Phantom__Hoover has joined.
00:47:07 -!- Phantom_Hoover has quit (Remote host closed the connection).
00:47:13 <int-e> shachaf: how about, the shortest string that's not accepted has 32769 characters?
01:05:21 -!- rdococ has quit (Quit: Page closed).
01:12:41 <int-e> slightly shorter expressions, same idea, and correcting a mistake with the second expression: ^(|.*(([^a]a|a[^a]).............a|([^a][^a]|aa).............[^a]).*|.?.?.?.?.?.?.?.?.?.?.?.?.?.?(a.*|.?)|.*a.?.?.?.?.?.?.?.?.?.?.?.?.?.?)$ and ^(|.*(([^a]a|a[^a]).............a|([^a][^a]|aa).............[^a]).*|.?.?.?.?.?.?.?.?.?.?.?.?.?.?(a.*|.?)|.*a.?.?.?.?.?.?.?.?.?.?.?.?.?.?.?)$
01:14:47 -!- hjulle has quit (Ping timeout: 246 seconds).
01:15:32 <int-e> (the first expression has a slightly longer minimal non-accepted string, too: 32782 characters. the second one now accepts all strings; this went wrong in my previous attempt.)
01:17:26 -!- rdococ has joined.
01:17:59 <rdococ> decided to get mIRC 6.35 and then get trial reset script...
01:18:07 <rdococ> was that a good decision?
01:18:17 <rdococ> oh I know! an esolang based on mIRC.
01:19:02 <int-e> Anyway, sleep. I can explain those regexps tomorrow if anyone cares.
01:19:35 <rdococ> goodnight int-2... sorry. just had to
01:26:20 -!- Encapsulation has quit (Remote host closed the connection).
01:36:04 -!- rdococ has quit.
01:36:32 -!- rdococ has joined.
01:55:59 <oerjan> hm int-e is asleep, i was going to ask if lambdabot had any unboxed functions
01:56:18 <lambdabot> Not in scope: type constructor or class ‘Int#’
01:56:18 <lambdabot> ‘Int’ (imported from Data.Int), ‘Int8’ (imported from Data.Int)
02:00:53 <oerjan> :k Typeable GHC.Exts.Int#
02:00:53 <lambdabot> Illegal unlifted type: GHC.Prim.Int#
02:00:54 <lambdabot> In a type in a GHCi command: Typeable GHC.Prim.Int#
02:01:12 <oerjan> :k Typeable (GHC.Exts.Int# -> GHC.Exts.Int#)
02:04:38 <Hijiri> is there a separate Typeable for unboxed types?
02:06:38 <oerjan> i'm not sure how it works now
02:06:52 <oerjan> i am steadfastly refusing to try to install GHC HEAD :P
02:07:20 <oerjan> (or 7.10, until the platform comes out.)
02:08:05 <oerjan> they're not allowed 7.8, anyway.
02:08:46 <oerjan> i cannot get it to derive
02:09:10 <oerjan> but in 7.10, Typeable is so magical that it _probably_ exists.
02:10:05 <oerjan> it allowed =>, after all, util this latest fix.
02:12:17 <oerjan> i just don't know how to test it in lambdabot if it doesn't export any unboxed types in its > environment
02:13:11 <oerjan> :t typeRep (Proxy :: Proxy Int#)
02:13:12 <lambdabot> Not in scope: type constructor or class ‘Int#’
02:13:12 <lambdabot> ‘Int’ (imported from Data.Int), ‘Int8’ (imported from Data.Int)
02:13:20 <oerjan> :t typeRep (Proxy :: Proxy GHC.Exts.Int#)
02:13:21 <lambdabot> Illegal unlifted type: GHC.Prim.Int#
02:13:22 <lambdabot> In an expression type signature: Proxy GHC.Prim.Int#
02:13:22 <lambdabot> In the first argument of ‘typeRep’, namely
02:13:44 <shachaf> there's Proxy# type but i'm not sure what it does
02:13:46 <oerjan> :t typeRep (Proxy :: Proxy (GHC.Exts.Int# -> GHC.Exts.Int# -> *))
02:14:17 <oerjan> :t typeRep (Proxy :: Proxy (Proxy :: GHC.Exts.Int# -> *))
02:14:18 <lambdabot> ‘GHC.Prim.Int#’ of kind ‘#’ is not promotable
02:14:31 * oerjan may be confusing emself
02:14:46 <oerjan> i suppose they're not allowed in enough places
02:15:01 <shachaf> :t typeRep (Proxy :: Proxy (GHC.Exts.Int# -> ())) -- ?
02:15:48 <oerjan> ok it thinks that exists, at least.
02:17:20 -!- Sgeo|web has joined.
02:17:30 <oerjan> :t let x :: forall a b c. (a b c ~ GHC.Exts.Int# -> ()) => TypeRep in typeRep (Proxy :: Proxy a)
02:17:36 <Sgeo|web> So, many Wikias now have autoplaying loud video ads
02:17:50 <oerjan> :t let x :: forall a b c. (a b c ~ (GHC.Exts.Int# -> ())) => TypeRep in typeRep (Proxy :: Proxy a)
02:17:51 <lambdabot> The type signature for ‘x’ lacks an accompanying binding
02:18:08 <oerjan> :t let x :: forall a b c. (a b c ~ (GHC.Exts.Int# -> ())) => TypeRep; x = typeRep (Proxy :: Proxy a) in x
02:18:57 -!- Hijiri has quit (Ping timeout: 248 seconds).
02:19:33 <oerjan> :k (a b c ~ (GHC.Exts.Int# -> ())) => a
02:19:34 <lambdabot> Expecting two more arguments to ‘a’
02:19:34 <lambdabot> Expected a type, but ‘a’ has kind ‘k0 -> k1 -> *’
02:19:34 <lambdabot> In a type in a GHCi command: (a b c ~ (GHC.Prim.Int# -> ())) => a
02:19:48 -!- edirc has joined.
02:20:24 * oerjan is confusing himself again
02:22:56 <elliott> does Typeable impredicativity actually cause any problems
02:23:14 <elliott> I mean other than GHC being really broken
02:27:13 <oerjan> of => you mean? i doubt it, but it's sort of intuitively fishy.
02:29:53 <oerjan> because the things on the left of => are of a fragile existence, being automatically instantiated all the time
02:30:32 -!- Phantom__Hoover has quit (Read error: Connection reset by peer).
02:32:19 <oerjan> so depending on whether Eq T has been instantiated, Eq T => U is in a sense the same thing as U.
02:32:48 <oerjan> and having something in the language that can distinguish them is fishy.
02:35:21 <oerjan> it gets even worse if you somehow break coherence of type classes so that there are two different Eq Ts in scope
02:35:50 <oerjan> (i saw someone complain on stackoverflow, i think, about this sometimes happening with GADTs)
02:36:15 <oerjan> (well, at least the part about not picking the instance from the right source.)
02:43:29 -!- GeekDude has quit (Ping timeout: 248 seconds).
02:52:20 -!- TodPunk has quit (Read error: Connection timed out).
02:52:51 -!- TodPunk has joined.
02:53:04 <lambdabot> Not in scope: data constructor ‘I#’
02:53:04 <lambdabot> Perhaps you meant ‘In’ (imported from Lambdabot.Plugin.Haskell.Eval.Trusted)
03:29:00 <Sgeo|web> Is it weird to find syntax-rules more elegant than imperative macros
03:29:14 <Sgeo|web> I feel like what I'm doing isn't cheating because it's syntax-rules only
03:29:44 <Sgeo|web> Like, if what I wanted to do was too inelegant, then I'd be forced into syntax-case
03:29:50 -!- dianne has quit (Ping timeout: 272 seconds).
03:31:07 -!- dianne has joined.
03:35:52 <izabera> did you know that printf has "int" in it? i just found out it does, with s/int/float/g
03:40:21 -!- bb010g has joined.
03:46:51 <oerjan> @tell int-e <int-e> [...] I've narrowed it down to KindSignatures + ScopedTypeVariables + TypeFamilies for the first one and PolyKinds + ScopedTypeFamilies for the second one. [...] <-- pretty sure you switched those
03:47:21 * oerjan ignores the actual typo
03:50:54 -!- zadock has joined.
03:53:45 <shachaf> oerjan: the actual typo is that you didn't @tell float-e hth
03:57:29 <rdococ> someone needs to make a programming language using prfloatf
03:58:58 <oerjan> the problem is, what should it _do_? printf already prints floats.
04:00:16 <shachaf> oerjan: clearly it should prfloat them hth
04:07:03 -!- ProofTechnique has joined.
04:13:08 <oerjan> `addquote <rdococ> what? I just wanted a laugh... lol <rdococ> I need to stop using lol, lol <olsner> just stop then
04:13:10 <HackEgo> 1240) <rdococ> what? I just wanted a laugh... lol <rdococ> I need to stop using lol, lol <olsner> just stop then
04:13:21 <oerjan> `addquote <rdococ> what? I just wanted a laugh... lol <rdococ> I need to stop using lol, lol <olsner> just stop then, hth
04:13:27 <HackEgo> 1241) <rdococ> what? I just wanted a laugh... lol <rdococ> I need to stop using lol, lol <olsner> just stop then, hth
04:13:34 <HackEgo> *poof* <rdococ> what? I just wanted a laugh... lol <rdococ> I need to stop using lol, lol <olsner> just stop then
04:14:13 <rdococ> I just used lol again, lol
04:14:43 <oerjan> careful or your lol may become another django
04:15:07 <rdococ> sorry, I don't know what a django means
04:15:23 <HackEgo> 261) <olsner> django is named after a person? <olsner> thought it would be a giraffe or something \ 306) <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 \ 307) <monqy> `quote django <HackEgo> 352) <olsner> django is named a
04:16:34 <oerjan> `` quote django | tail -n +5
04:16:35 <HackEgo> 318) <elliott_> `addquote <olsner> two quotes about quotes about django <olsner> I guess the worst part is that I appear in all three hackego quotes about django <olsner> elliott_: another quote? you're not helping :/ \ 884) <oerjan> `pastequotes django <HackEgo> http://codu.org/projects/hackbot/fshg/index.cgi/raw-file/tip/paste/paste.5404 <ols
04:17:16 <oerjan> `` quote django | tail -n +3
04:17:16 <HackEgo> 307) <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 <HackEgo> 352) <olsner> django is named after a person? <olsner> thought it would be a giraffe or something <cpressey> thankfully only one <monqy> thankfully only two \ 31
04:17:41 <HackEgo> http://codu.org/projects/hackbot/fshg/index.cgi/file/tip/paste/paste.22857
04:18:28 <rdococ> django must be a giraffe!
04:20:18 <oren> if(var =! var2){
04:20:40 <oren> the =! operator is for messing
04:21:24 <oerjan> gah why is youtube so slow
04:24:11 <elliott> right, because <video> is a crashy CPU hog and flash isn't
04:24:41 <oren> elliott: depends on video format hth
04:24:49 <rdococ> why not just use pausable gifs
04:25:04 <rdococ> so a blank div with a button that inserts a gif into the div
04:25:08 <oren> some <video> formats screw up a lot for me
04:25:13 <elliott> flash's decoding is never accelerated in pretty much any way afaik
04:25:37 <elliott> the only ~relevant formats are VP8/9 and H.264, the latter is more likely to get accelerated on mobile or whatever than the others
04:25:50 <elliott> but flash just always seems to be terrible about video decoding
04:27:46 <oerjan> rdococ: a bit bad for sound, perhaps.
04:28:11 <rdococ> the button could invoke a function that inserts a gif AND plays an audio file
04:28:17 <elliott> gifs also load awfully, compress awfully and are limited to 256 colours, but who's counting
04:28:34 <rdococ> but it loads the gif and audio first so theyre synched
04:28:58 <rdococ> thought youtube was awful anyway
04:29:30 <elliott> youtube do like serious bandwidth limiting so buffering is painful on slower connections
04:29:36 <oren> youtube has always been awful compared to downloading the video and playing it with vlc
04:29:39 <rdococ> also, internet explorer -6 will support gifs
04:29:42 <elliott> it's not inherent they just do it to increase capacity I guess
04:30:09 <elliott> oren: that's half flash's fault, half doing all the buffering upfront, basically
04:30:13 <elliott> youtube does especially badly if you seek around
04:30:54 <oren> youtube with html5 seems worse
04:31:18 <elliott> there's a browser extension to force it to serve H.264 instead of VP8/9
04:32:08 <elliott> since I think that maybe flash didn't do VP8/9? so you could have been going from H.264 flash to VP8/9 <video>, which could be worse I guess
04:33:37 <elliott> oh also if you're using firefox then I dunno if they do DASH yet (right click youtube player -> "stats for nerds"), chrome probably works best there for obvious reasons
04:34:00 <elliott> seems to make seeking a lot better too
04:35:30 -!- ProofTechnique has quit (Ping timeout: 250 seconds).
04:39:27 <oren> the state for nerds says I have HTTPS/DASH/VOD and software rendering and decoding
04:41:06 <oren> http://snag.gy/T7AYP.jpg
04:42:13 <elliott> uh why does it look different for you than it does for me
04:42:17 <elliott> are you sure that's HTML5 :P
04:43:02 <oren> Hmm, this video is flash
04:43:20 <oren> explains why it hasn't frozen yet
04:43:50 <oren> HTML5 freezes firefox every 15 minutes
04:44:11 <pikhq> Weird, HTML5 video actually works perfectly fine for me.
04:44:20 <oren> of course, my computer has only 2 GB of ram
04:44:25 <pikhq> elliott: They do DASH as of the latest release.
04:44:26 <elliott> sounds like you have other problems
04:44:47 <elliott> no, "uses all 2GB of your RAM unlike flash and then crashes firefox" is not a known drawback of HTML5 video :p
04:45:01 <pikhq> Sometime a bit before that they appear to have made HTML5 video playback not suck.
04:45:13 <elliott> I mean on windows flash is actually kind of okay
04:45:14 <oren> firefox uses all my ram from some stylesheets....
04:45:18 <elliott> but on linux/osx it is beyond useless
04:45:35 <elliott> also especially on linux the flash plugin for firefox is like... several major releases behind because they only do the Pepper one now? so chrome/ium only
04:45:42 <elliott> I don't even know if it still gets security releases
04:45:49 <pikhq> It does still get those.
04:46:00 <rdococ> got a gif player working in pure HTML and JS
04:46:06 <elliott> was the NPAPI interface really that hard to maintain
04:46:22 <elliott> I mean they still support it on every platform but linux right
04:46:24 <pikhq> elliott: No, but the distinction is *Adobe doesn't maintain anything at all on Linux*.
04:46:29 <rdococ> once HTML5 dominates, flash won't even exist
04:46:31 <pikhq> Google maintains the Pepper version.
04:46:39 <elliott> who does the security fixes
04:46:46 <pikhq> Some poor single guy.
04:46:47 <oren> rdococ: what sbout animations
04:46:55 <elliott> flash is already well on its way to dying...
04:46:57 <rdococ> oren: yeah, it animates
04:47:03 <elliott> doesn't it even output HTML5 gunk these days?
04:47:06 <pikhq> (I don't remember where, but he's got a blog. Seriously, it's just him.)
04:47:15 <rdococ> oren: found a funny banana animation to test
04:47:26 <rdococ> I could watch this all day
04:47:34 <elliott> btw you might run out of your 2 GB RAM less if you had fewer than 20 extensions in firefox :P
04:47:38 <pikhq> Flash as an animation util lives on, as an Internet file format it's not quite dead but it's getting there.
04:47:44 <elliott> since a lot of firefox's awful RAM hungriness and leakiness is bad extensions
04:48:02 <pikhq> Believe it or not Adblock Plus is one of the worse ones in that regard.
04:48:04 <elliott> in particular you had adblock plus which is awful for RAM usage, so...
04:48:13 <elliott> is there a uBlock for firefox yet. there is, right?
04:48:18 <elliott> I know it forked recently... *sigh*
04:48:26 <oren> what is ublock
04:48:37 <elliott> like adblock plus except it doesn't double your memory usage
04:48:42 <pikhq> Newer ad blocker, works without injecting a lot of shit into the DOM.
04:49:21 <elliott> pikhq: should I be using the gorhill one or the "official" one on chrome
04:49:27 <elliott> since I don't care enough to figure out why they are separate now
04:49:38 <pikhq> elliott: I'm not sure which one is the "sane" one as yet.
04:50:17 <pikhq> Ah, the gorhill one is the one you really do not want to use because it's no longer maintained.
04:50:37 -!- variable has joined.
04:50:58 <elliott> he said he was going to keep working on it in his own time
04:51:00 <pikhq> In effect he's just bug-fixing.
04:51:01 <elliott> he just isn't taking feature requests
04:51:10 <pikhq> I was under a misconception and google quickly fixed it.
04:51:16 <elliott> he definitely said he was going to keep adding things to it
04:51:28 <elliott> that's the amount to which I did check up wtf was happening and why the extension changed name for me
04:51:50 <elliott> Important note: This is a fork of the new official repo. Although both projects are essentially the same as of 0.9.3.0, they will probably start to diverge as time goes (update: they already started to diverge feature-wise).
04:51:52 <pikhq> He's still working on it but not particularly caring about WTF anyone else demands from it, then?
04:52:05 <elliott> I may add features whenever I feel the need to do so -- I use the extension myself, so if I feel it definitely needs something more, I will just go ahead and add it.
04:52:11 <pikhq> I suppose that's a question of which one sucks less.
04:52:18 <elliott> it's not like it matters since uMatrix does the heavy lifting
04:52:35 <pikhq> It sounds like right *now* there's only going to be trivial differences.
04:54:21 <pikhq> I suppose stick with ublock "official" for now unless it starts sucking then.
04:55:05 <elliott> it automatically upgraded to gorhill's uBlock for me
04:55:23 <elliott> I guess because he owned the chrome store entry for it
04:56:14 <oren> anyway, the reason firefox crashes is becasue I wrote a script to monitor the computer and kill -9 firefox if the computer starts to freeze. before, firefox would put the whole computer in a coma
04:56:38 <elliott> chrome crashes too because I kill -9 it periodically. dont use chrome
04:56:53 <rdococ> added stop feature to the gif player
04:57:05 <elliott> anyway if you switch from adblock pro to ublock then you can continue pretending you don't need to upgrade your RAM for another few months
04:57:06 <pikhq> Pity that Firefox, like a lot of things, is of the philosophy that "free() everything before exit is a useful behavior".
04:57:15 <elliott> in the meantime it's not really firefox itself that is destroying your RAM
04:58:43 <pikhq> (if you don't free() before exit, the kernel gets to free pages without mutating them. i.e. it can avoid reading them out of swap just to mark them as no longer used. :))
04:59:05 -!- Melvar has quit (Ping timeout: 265 seconds).
04:59:21 -!- idris-bot has quit (Ping timeout: 264 seconds).
04:59:30 <pikhq> elliott: For now I'd advise "meh, whatever".
04:59:52 <elliott> yeah I kinda already decided that before I even asked
05:00:09 <elliott> I should switch to IE and stop caring about everything
05:00:23 <pikhq> Though a much smaller *wince* than it once was.
05:00:39 <pikhq> These days IE is merely not as good as its alternatives, rather than actively terrible.
05:00:50 <oren> I dunno. basically what happens is, firefox normally takes 18% to 30% of my ram (including flash plugin container). Sometimes on certian sites, suddenly that climbs rapidly without warning, causing the mouse to stop moving and sort of blink from one place to the next. So my utility checks if memory usage of firefox is above 50% and kills it if it is
05:01:23 <pikhq> Here's a nickle, kid; get yourself a real computer.
05:01:54 <oren> You're one of those condescending UNIX users!
05:02:40 <pikhq> (seriously though, my *phone* has as much RAM as your computer)
05:03:47 <oren> your phone probably cost more than this computer
05:03:57 <rdococ> my laptop is a little dodgy but it works
05:03:59 <pikhq> Maybe. How much did it cost and when?
05:04:00 <oren> my computer was 200
05:04:07 <elliott> oren can I buy you some RAM just so I don't have to hear about how little RAM you have again
05:04:14 <oren> *canadian* dollars, 2 years ago
05:05:08 <izabera> there are lightweight browsers you know
05:06:02 <elliott> I seriously doubt it's even firefox's fault rather than extensions here
05:06:43 <oren> I think it is javascript's fault
05:07:07 <pikhq> By the way, *mine* cost more but there are in fact phones for that price with 2G of RAM...
05:08:06 <pikhq> But heck. What type of RAM do you have? DDR3?
05:09:23 <pikhq> How much would you be willing to spend on RAM right now?
05:10:11 <pikhq> Lowest we can go right now is 18 USD.
05:10:21 <pikhq> (to double your RAM)
05:10:32 <oren> I dunno, it's a laptop
05:11:25 <oren> seems it is DDR3
05:11:42 <pikhq> Fine then, http://www.newegg.com/Product/Product.aspx?Item=N82E16820239853 Here, if you have a spare slot.
05:12:13 <rdococ> look someones done it already http://slbkbs.org/jsgif/
05:12:43 <oren> apparently I have 3 spare slots. it's hard to type with the case of the laptop hanging off it though
05:12:53 <pikhq> (seriously though, RAM is both cheap and something that's really painful to skimp on)
05:13:09 <elliott> rdococ: don't worry, nobody knows who made *that*
05:14:06 * pikhq wonders how long until a RPi with 2 or more gigs of RAM.
05:15:23 <oren> is ddr3 ram hot swappable?
05:15:40 <oren> what if i'm only putting one in?
05:16:00 <pikhq> Still no, but at least less obviously so.
05:16:25 <oren> well, i guess I should shut down beofre trying this then
05:16:38 <pikhq> What, do you *have* some spare RAM handy?
05:16:39 <elliott> did the ram arrive already
05:16:47 <elliott> newegg shipping really is a marve
05:17:12 <oren> i have some ram that may or may not be fried due to an incident
05:17:27 <pikhq> Might I recommend memtest86?
05:17:39 -!- ProofTechnique has joined.
05:17:45 -!- oren has quit (Quit: leaving).
05:18:19 -!- MDude has changed nick to MDream.
05:19:53 <elliott> well either he will have more RAM or his computer will catch fire
05:19:59 <elliott> either way we won't have to hear about it any more
05:20:07 <pikhq> That's like winning.
05:20:41 <pikhq> Maybe I'll just tinker with my silly HTTP server s'more then.
05:21:08 <pikhq> (y'know it's lazy when it uses dprintf!)
05:23:19 <pikhq> Actually, more to the point, when it uses a thread per connection. :)
05:24:57 <shachaf> i can't tell whether you hilighted me on purpose
05:25:16 <shachaf> i must be missing some context
05:28:30 <rdococ> find tool says nothing
05:28:49 <shachaf> "slbkbs" highlights me but i guess that wasn't related
05:29:35 <pikhq> shachaf: We did actually talk about jsgif so that might have been all that was needed.
05:30:12 <shachaf> that's such a terrible program
05:30:18 <shachaf> especially the lzw decoding
05:30:38 <pikhq> Can't be as bad as the gzip decoder I've got laying around here.
05:30:50 <pikhq> Or the PNG encoder. :)
05:31:52 -!- orin has joined.
05:32:13 <orin> based on that i still have 2GB of ram, thi ram is indeed fried
05:34:24 <orin> I also taped the case shut more ecurely
05:35:06 <oerjan> are people being fake humble about their code
05:35:19 <oerjan> also, what does slbkbs mean
05:35:31 <pikhq> Nah, I'm openly mocking my code. It's impressive shit.
05:35:49 <shachaf> oerjan: no, it's actually terrible
05:35:59 <oerjan> does shachaf have a middle name starting with l
05:36:23 <pikhq> When you write a PNG encoder that doesn't do compression you know it's terrible.
05:36:28 <oerjan> in which case, who's the s at the end
05:41:31 <orin> pikhq: PNG supports raw data?
05:42:07 <pikhq> No, but you don't have to compress to output zlib data.
05:44:43 <orin> you just a output a bunch of literal blocks
05:49:02 <orin> normally, literal blocks are used for when the data is too hard to compres... I guess in this case, you just give up beofre you even start
06:10:43 -!- ProofTechnique has quit (Ping timeout: 252 seconds).
06:13:08 <oerjan> @tell olsner <olsner> isn't it spelled trawling when you do it to fish? <-- different terms hth
06:14:00 -!- zadock has quit (Ping timeout: 265 seconds).
06:15:58 -!- zadock has joined.
06:16:55 <oerjan> @tell olsner mainly trolling uses a line but trawling uses a net, i think. except there seems to be some overlap in meaning.
06:26:19 -!- ProofTechnique has joined.
06:33:51 <oerjan> wat why didn't i see int-e's response right underneath
06:39:29 <quintopia> i don't understand this comparing of programs to boats thing
06:39:43 <quintopia> what makes a piece of code especially like a boat?
06:40:00 <Taneb> I saw a proof of Sylow's first theorem yesterday and it seemed really elegant
06:40:04 <Taneb> But now I have forgotten it
06:40:20 <oerjan> so elegant it slides right through
06:48:21 <Taneb> Huh, DMM is doing a patreon to bring IWC back
06:48:52 <Taneb> https://www.patreon.com/dmmaus
06:49:44 <oerjan> IWC? i thought it would be for general projects
06:51:17 <Taneb> $50 goal was for 1 new IWC comic a week
06:51:41 * oerjan didn't visit the patreon page before
06:52:21 <Taneb> $75 is for *two* comics a week
06:52:37 <Taneb> $54000 is for the Allosaurus' presidential campaign
06:54:16 <shachaf> oerjan: sorry about the scow hth
06:54:38 <oerjan> shachaf: OKAY tdh hand bbq fnord
06:56:05 <shachaf> oerjan: the l is a finnish translation of the s hth
06:56:49 <Taneb> I have a poor memory for numbers
06:57:31 <Taneb> David Morgan Mar is someone who changed my life without really meaning to
06:59:17 -!- Sgeo|web has quit (Quit: Page closed).
07:00:06 -!- variable has changed nick to trout.
07:00:17 <Taneb> If it weren't for him I'd probably be doing a pure maths degree
07:00:37 <shachaf> What are you doing instead?
07:00:39 <Taneb> A degree that is only maths
07:00:47 <Taneb> I am doing a degree that is maths and computer science
07:02:41 <Taneb> Right now, a fair amount of group theory and a bit of linear algebra
07:03:55 <shachaf> whoa, you should teach me about linear algebra
07:05:02 <Taneb> There are things called vector spaces over a given field, which have some axioms
07:05:26 <Taneb> And there are things called linear transformations which are really vector space homomorphisms
07:05:42 <Taneb> Thing is, linear transformations work out to be almost but not quite matrices
07:07:18 <Taneb> And if a property holds true for all matrices that are similar to one representing a linear transformation, something like it will be true for the linear transformation itself!
07:08:06 <Taneb> That's basically all I know
07:09:02 <shachaf> can you elaborate on the last bit
07:09:24 <shachaf> in the past i would have asked things like whoa, where do matrices come from. but now i know the answer
07:09:32 -!- nszceta has joined.
07:10:45 <oerjan> well when a matrix and a patrix love each other very much...
07:11:16 <shachaf> what does "diagonal matrix" correspond to
07:11:28 <oerjan> that's a base-dependent notion
07:11:42 <shachaf> ok, what does "diagonalizable matrix" correspond to
07:12:06 <oerjan> that it has a spanning set of eigenvectors
07:12:15 <shachaf> what about "doubly-stochastic matrix"
07:12:25 <shachaf> what are left eigenvectors
07:12:51 <oerjan> ordinary eigenvectors of the transpose
07:13:07 <shachaf> ok, what's the transpose of a matrix
07:13:16 <oerjan> i'm not entirely sure what "doubly-stochastic" means
07:13:27 <shachaf> the matrix is stochastic and also its transpose is stochastic
07:13:31 <oerjan> for a matrix it's simply the same as haskell transpose
07:13:39 <Taneb> shachaf, the transpose of a matrix is a contravariant endofunctor
07:13:39 <shachaf> i.e. rows and columns sum to 1
07:14:01 <shachaf> oerjan: in terms of linear transformations, not of matrices
07:14:35 <Taneb> Are transposes of similar matrices similar?
07:15:15 <oerjan> if you have a linear transformation, and a functional on its range space, then you can compose them to get another functional on the domain
07:15:41 <oerjan> that's a linear transformation of the dual spaces in the opposite direction, so a contravariant functor
07:16:24 <shachaf> but you need to choose a basis?
07:16:28 <oerjan> now i've forgotten what similar means
07:16:37 <oerjan> shachaf: no, not for the l.t. concept
07:16:54 <oerjan> but to _identify_ the space with its dual space, you need a basis.
07:16:57 <Taneb> oerjan, two matrices A and B are similar if there exists a matrix C such that A = CBC^-1
07:17:54 <Taneb> In terms of linear algebra, that means that a linear transformation is still valid if you change your basis
07:17:55 <oerjan> yeah that's preserved by transposes
07:18:16 <oerjan> A^t = (C^t)^-1 B^t (C^t)
07:18:51 <oerjan> transposition reverses order of multiplication and preserves inverses
07:19:52 <Taneb> I ought to do some linear algebra revision at some point
07:22:21 <oerjan> shachaf: i think stochastic is pretty base-dependent. it's essentially that inner product with the vector (1,1,...,1) is preserved. And maybe some positivity requirement. No wait I think that's automatic.
07:22:46 <Taneb> Oh yeah! We started doing inner products the other day
07:23:21 <shachaf> oerjan: i thought it had some basis-invariant properties
07:31:26 <shachaf> another linear algebra puzzle is why do people say "eigenvector with eigenvalue 1" instead of "fixed point" twh
07:32:19 <oerjan> well it's silly to use a special name for a special case if it has no interesting special properties, or something.
07:32:20 <quintopia> ...sometimes they do say "a fixed point"
07:34:45 -!- trout has quit (Ping timeout: 264 seconds).
08:00:06 <fizzia> "I don't know how I could design an interpreter to interpret a picture. "
08:03:55 <rdococ> what? are you staring at me through your screen?
08:05:22 <rdococ> stop judging me through your screen
08:07:06 <oerjan> i think he's just pietying you
08:08:11 <fungot> http://esolangs.org/wiki/piet
08:08:50 <HackEgo> [wiki] [[Version]] http://esolangs.org/w/index.php?diff=42587&oldid=30453 * Rdococ * (-7) instructions whose labels match this regular expression will not be executed.
08:08:52 <orin> Hmm... this is an interesting result.
08:09:41 <orin> My experimental compression alogrithm, followed by gzip, beats gzip done alone
08:09:59 <rdococ> but does it take a million years?
08:10:13 <oerjan> i don't think orin is that old
08:10:20 <elliott> fizzia: nice unconfusing nick
08:10:33 <rdococ> also, is it lossy compression (if that even makes sense for folders)
08:11:07 <elliott> I was like "would fizzie really use o_O"
08:11:36 <orin> It is completely lossless...
08:12:01 * oerjan leaves most of his spammer recognition to elliott
08:12:37 <oerjan> i don't think we've seen any of the regular trolls in a while...
08:12:42 <orin> http://snag.gy/tyoi4.jpg
08:13:10 <orin> see screenshot. the file out is the compressed of the file 14.12.23
08:13:22 <elliott> oerjan: you mean like c'er or h'rd
08:13:33 <rdococ> can you decompress it?
08:13:36 <fizzia> rdococ: well you read in an image into a pixel array?
08:13:50 <fizzia> images are good for 2D languages probably because they are already 2D
08:14:10 <fizzia> videos are good for 3D languages
08:14:14 <fizzia> because they are already 3D
08:14:17 <oerjan> orin: i cannot quite fathom how people can stand transparent text windows.
08:14:32 <rdococ> guess you could use text
08:14:36 <fizzia> you can always have a width*1 picture
08:14:43 <elliott> well the cool part is that those screenshots are jpegs
08:14:49 <elliott> so they look even worse than they otherwise would
08:15:14 <orin> http://snag.gy/CgJuv.jpg
08:15:32 <orin> here no transparent
08:17:43 <oerjan> i wasn't complaining, just unfathoming
08:18:38 <orin> http://arin.ga/Ct6O7c <- compressor http://arin.ga/36DMJG <- uncompressor
08:20:38 <orin> I have been experimenting with variants of thi sort of thing for a bit
08:22:58 <orin> The idea is that many files do not use every byte from 00 to ff. we can encode pairs of bytes they use a lot, like '==' using them.
08:23:53 <orin> so we append, say \000== to the start of file, then inside file replace every \000 with == and vice versa
08:26:20 <orin> So even if there is like one capital R or something we can still use Rll to reduce size if there are a lot of 'll's.
08:27:45 -!- Patashu has joined.
08:28:13 -!- fizzia has changed nick to mroman.
08:28:17 <mroman> Never changed it back.
08:35:09 <quintopia> orin: i don't really see this beating a huffman encoding. why do you do it?
08:36:34 <int-e> oerjan: you mean you don't like ScopedTypeFamilies? (The confusion about the order arose because I copied the second example first, and then worked from an editor)
08:37:17 <orin> quintopia: this algorithm, followed my gzip, beats gzip used alone
08:37:25 <oerjan> oh i'm sure they will revolutionize haskell once they're implemented
08:37:33 <quintopia> i mean if you're gonna rename things to shorter things, might as well go further. for instance, in the file with one R and tons of ll, would it not make sense to swap all ll's for R's? but this idea just ends up leading to a huffman coding if taken to its extreme
08:37:47 <int-e> oerjan: and I'm not consciously providing any unboxed types in lambdabot but how can I ever be sure?
08:38:29 <orin> quintopia: my algorithm already does that
08:39:09 <int-e> especially when @let lets you import new modules as long as they're safe... which makes it tricky to get anything that reexports stuff from GHC.Exts; it would have to come from a trusted package; but not impossible, I suppose.
08:39:23 <orin> it goes through all x,y,z and if occurs(yz)-occurs(x) is large enough it swaps all x for yz and vice versa
08:40:14 <orin> it is slow to compress, but very fast to uncompress
08:40:45 <quintopia> but again...why stop there? you could swap some uncommon letters for very common trigrams or tetragrams too!
08:40:49 <oerjan> int-e: i actually found out how to get unboxed kinds
08:41:16 <b_jonas> oerjan: are those kinds for types of unboxed values?
08:41:19 <orin> quintopia: eaxtly...
08:41:20 <oerjan> > let f x = let #42 = x in x in typeOf f
08:41:22 <lambdabot> <hint>:1:11: parse error in let binding: missing required 'in'
08:41:42 <oerjan> > let f x = let 42# = x in x in typeOf f
08:41:46 <int-e> oh, literals. right.
08:42:00 <int-e> Meh. I should've known.
08:42:14 <int-e> (I knew that MagicHash is in there)
08:42:27 <oerjan> however, it seems it _refuses_ to let you take apart that kind
08:42:35 <int-e> (Because, you know, "what harm could it possibly do?)
08:43:19 <oerjan> let f x = 2 :: Int where {3# = x}; p2 :: t a b -> Proxy t; p2 _ = Proxy in typeRep (p2 f)
08:43:26 <oerjan> > let f x = 2 :: Int where {3# = x}; p2 :: t a b -> Proxy t; p2 _ = Proxy in typeRep (p2 f)
08:44:03 <oerjan> > let f x = 2 :: Int where {3# = x}; p2 :: t b -> Proxy t; p2 _ = Proxy in typeRep (p2 f)
08:44:50 <oerjan> so there's some kind of protection against removing unboxed arguments from a -> b
08:45:15 <oerjan> (also i tried unboxed tuples before i remembered ghci doesn't support them)
08:45:41 <quintopia> orin: i would guess there would be some types of files that it does poorly, on account of they already use all available bytes, or each byte is used with roughly equal frequency. (notice this is not the same condition as the sort of randomness you see in compressed files)
08:46:24 -!- nszceta has quit (Quit: Textual IRC Client: www.textualapp.com).
08:46:35 <b_jonas> oerjan: does that mean that the kind of a function on an unboxed type is not supposed to have (->) as the top kind constructor?
08:47:32 <orin> but consider for example acrives of C code... they might not even use the characters @ or `
08:47:45 <quintopia> you know what i want to see? a lossy english language compression algorithm. one that is guaranteed to decompress to grammatical english text with the same approximate semantics as the compressed file, but not exactly the same file
08:48:24 <orin> um... maybe we can compress synonyms to the same number?
08:48:26 <oerjan> <int-e> (Because, you know, "what harm could it possibly do?) <-- well the manual explicitly says it doesn't import anything or change semantics, so the literals is all you get immediately
08:48:28 <quintopia> perhaps because it maps synonyms to the same word, or considers certain sentence structures equivalent...
08:48:41 <b_jonas> quintopia: you have to ask the journalist bots for that. they already have a model to rewrite journal articles with the same meaning (not compress though), to very quickly produce articles that aren't direct quotes of the article they steal from
08:49:08 <quintopia> b_jonas: i'd love to check those out
08:49:08 <orin> ooh. it would be good if it eliminated double negatives and the passive voice
08:51:09 <quintopia> orin: well, it would be difficult to eliminate double negatives. sometimes people actually use double negatives to intensify negatives, rather than flip back to positives. or you could just say "this is guaranteed to work only if you start with something grammatical and formal. start throwing conversational or dialectal stuff at it at your own risk"
08:52:41 <oerjan> b_jonas: it means that -> with unboxed kinds involved is deeply magical and confuses things at the core stage. and it's the same kind of magic that we used to make an exploit involving * vs. Constraint. although they've patched enough now that i don't think there's an exploit in HEAD any longer.
08:53:08 <oerjan> basically => and -> _are_ the same constructor, afa core is concerned.
08:56:56 -!- zadock has quit (Ping timeout: 240 seconds).
08:58:28 -!- Melvar has joined.
09:00:39 <quintopia> what sort of data naturally has an unlabelled undirected graph structure?
09:02:10 <elliott> quintopia: it's hard to do *any* semantics-preserving transformation on english text
09:04:21 <oerjan> exercise: prove there are no two english phrases with the exact same semantics hth
09:08:02 <lambdabot> forall (k :: BOX) (k1 :: BOX) (a :: k -> k1 -> *) (b :: k) (c :: k1). a b c -> Proxy c
09:08:22 <int-e> > let c _ = 1# in ppp c
09:08:31 <int-e> oerjan: yeah, weird.
09:09:44 <b_jonas> oerjan: you can't prove that. there are text with identical semantics, it's just that we can't handle English with computers well enough to find them
09:10:25 -!- zadock has joined.
09:10:40 <oerjan> b_jonas: you can't prove that either hth
09:10:48 <b_jonas> oerjan: in particular, if you have a long spam advertisment mail, its semantics doesn't change if you modify its end to almost anything, after the part that's enough to make it clearly a spam ad. however, recognizing spam ad mails automatically is difficult
09:11:06 -!- idris-bot has joined.
09:12:45 <int-e> oerjan: but then again, type-level (->) is weird; I mean..
09:12:52 <quintopia> elliott: obviously. else it would be done already. for all i know, even the simple not-guaranteed-to-work version i envision is already AI-hard
09:13:31 <elliott> well, I think some such transformations are done in practice
09:14:07 -!- zadock has quit (Read error: Connection reset by peer).
09:14:34 <rdococ> I need something to do
09:19:41 <f|`-`|f> the art of hiding things in plain sight
09:19:55 <int-e> I'm sure that steno = stenography, a short script.
09:21:08 <int-e> But I guess you could say that the 'ga' was hidden in plain sight and you found it...
09:21:18 <f|`-`|f> stegano -> concealing messages in script
09:21:35 <f|`-`|f> I usually see people use steno in place of steganography
09:21:57 <int-e> f|`-`|f: well, they shouldn't ;)
09:22:38 <quintopia> rdococ do you have a nkro keyboard?
09:23:06 <oerjan> the steganosauri are still among us
09:23:39 <f|`-`|f> I also have Gregg Steno book around my desk
09:23:52 -!- augur has quit (Ping timeout: 272 seconds).
09:24:30 -!- augur has joined.
09:24:53 -!- int-e has set topic: Stenosteganography | https://dl.dropboxusercontent.com/u/2023808/wisdom.pdf http://codu.org/logs/_esoteric/ http://tunes.org/~nef/logs/esoteric/.
09:25:20 <oerjan> int-e: i can understand that they don't want to allow unlifted types as type parameters, i just don't see why it should claim that the other match is a *
09:25:56 <int-e> oerjan: At this point I rather suspect that the defaulting of -> to * -> * -> * is somewhat overaggressive.
09:29:10 <int-e> oerjan: for example, and this is pure speculation, if that happens whenever the solver sees a standalone (->), then a b c = Int# -> Int# would be decomposed into a :: k -> k1 -> k2 = (->) :: * -> * -> *, b :: k1 = Int# :: # and c :: k2 = Int# :: #...
09:29:26 -!- zadock has joined.
09:29:55 <f|`-`|f> so youare trying to figure out how to deal with kindedness
09:30:07 <f|`-`|f> not why -> has a kind of * -> * -> *
09:30:29 <oerjan> oh i know why the standalone (->) gets that kind.
09:30:59 <f|`-`|f> does it involve (a -> b) :: *
09:31:14 <oerjan> what i don't understand is how a function that is already of type Int# -> Int#, doesn't allow you to split out the (->) :: # -> # -> * that is already in there
09:31:46 <f|`-`|f> because kinds are in terms of types, they aren't functions per se
09:31:53 <int-e> oerjan: hence "overaggressive"
09:32:27 <f|`-`|f> I mean, not until you get to liquid of dependant types, but that is way ahead of my pay grade
09:34:32 <oerjan> int-e: oh i see what you mean, the * comes from (->) not from the b or c
09:35:22 <oerjan> a weird thing to do. also this worked:
09:35:51 <oerjan> > let f x = 2 :: Int where {3# = x}; p2 :: t b -> Proxy t; p2 _ = Proxy in typeRep (p2 f)
09:36:45 <oerjan> while it doesn't if you make the result of f unboxed
09:38:32 <oerjan> i cannot quite tell if this is a bug or an intended feature
09:39:08 -!- zadock has quit (Ping timeout: 245 seconds).
09:39:49 <oerjan> but if i try to replace a by Int# i get "Illegal unlifted type" instead.
09:40:02 <oerjan> so i suspect it's intended.
09:46:07 <elliott> f|`-`|f: I'm not sure this is relevant to what oerjan is talking about
09:46:23 <elliott> oerjan is talking about representations of types with Typeable
09:49:10 <int-e> oerjan: looking at a type-checking traces... found this bit: http://sprunge.us/JNUB
09:50:35 <int-e> (Heh, plural. The thing is over 1000 lines... maybe that justifies this abuse of grammar.)
09:51:03 <int-e> oerjan: you do know about -ddump-tc-trace, right?
09:53:22 <oerjan> anyway, all of this makes it even less likely that there's a way to get Typeable confusion out of this.
10:02:45 <HackEgo> [wiki] [[Gibberish (programming language)]] M http://esolangs.org/w/index.php?diff=42588&oldid=42567 * Vriskanon * (+4) Made 'Turing-complete' a link to wiki.
10:04:14 <HackEgo> [wiki] [[Gibberish/JavaScript/HTML interpreter]] http://esolangs.org/w/index.php?diff=42589&oldid=42557 * Esowiki201529A * (+83) /* HTML code */
10:09:06 -!- Phantom_Hoover has joined.
10:20:12 -!- boily has joined.
10:25:36 <int-e> oerjan: Ok, I was right. http://sprunge.us/FLGU ... so when some t -> u (i.e. FunTy t u) gets decomposed into (->) [t, u], that's when the (->) gets a * -> * -> * constraint.
10:26:49 <int-e> oerjan: To compensate for this, if the type checker unifies t -> u with t' -> u', it will not decompose, but unify t with t' and u with u' directly.
10:27:35 <oerjan> huh i didn't know the change had to do with Arrows
10:27:38 <int-e> oerjan: and, as the comment says, (->) t y is not the same as t -> u. That bit is good to know.
10:28:26 <oerjan> boily: i do not know what you did there
10:29:12 <int-e> oerjan: I did not fully understand this either; obviously Arrow expects an argument of kind * -> * -> *, but I didn't see the problem with providing something more general (which could then be specialized)
10:29:15 <boily> oerjan: you used the other part of my name, so I went with what I remembered was yours. IMO, it doesn't fit well with French mornings.
10:29:40 <oerjan> i think you may have misremembered.
10:30:22 <oerjan> oh you think i'm sørensen
10:30:41 -!- ProofTechnique has quit (Ping timeout: 252 seconds).
10:32:42 <oerjan> int-e: oh i think the problem is the idea that the Arrow instance would have the same kind, but there's no reason that cannot be restricted to *
10:34:56 <oerjan> int-e: i have the feeling the Arrow explanation doesn't hold water, then.
10:40:17 <oerjan> presumably they would have had to change the tcSplitTyConApp_maybe line to extract the kinds of arg and res, then.
10:40:36 -!- ProofTechnique has joined.
10:42:58 <int-e> oerjan: I can imagine that having several different funTyCon values around (same constructor, but different kinds) would get messy; especially when those kinds are ? and ??... (does ghc even know about these explicitly? judging by the definition of isSubOpenTypeKindKey in compiler/types/Kind.hs that doesn't seem to be the case anymore[4~))
10:44:13 <oerjan> i think they merged ? and ?? when they let unboxed tuples become arguments
10:45:17 <int-e> https://github.com/ghc/ghc/blob/d8d541d85defcf3bbbddaeee8cfac70b74f47ffc/compiler/types/Kind.hs#L190-L205
10:45:58 <int-e> note: okArrowArgKindCon = isSubOpenTypeKindCon and okArrowResultKindCon = isSubOpenTypeKindCon
10:46:43 <int-e> so hmm. openTypeKindTyConKey *mumble*
10:47:25 -!- ProofTechnique has quit (Ping timeout: 244 seconds).
10:49:08 <int-e> Ok, I'm lost. And I should do different stuff anyway.
10:49:12 <oerjan> they should clearly implement edward's method
10:49:37 <int-e> what's that? unsafeCoerce is ok unless the compiler can prove it's wrong?
10:50:18 <oerjan> no, from https://ghc.haskell.org/trac/ghc/ticket/9858#comment:89
10:50:21 -!- ProofTechnique has joined.
10:51:57 <int-e> b_jonas: wait until you see reallyUnsafePointerEquality
10:52:19 <Jafet> @quote roconnor unsafeCoerce
10:52:19 <lambdabot> roconnor says: unsafeCoerce isn't even safe
10:52:20 <int-e> sorry, reallyUnsafePtrEquality#
10:52:33 <int-e> @quote int-e unsafeCoerce
10:52:33 <lambdabot> int-e says: What, unsafeCoerce# is kind-preserving? how boring :/
10:52:46 <int-e> (this predates polykinds)
10:53:09 <int-e> (it's still true, of course, but it's less funny now)
10:53:44 <int-e> @quote reallyUnsafePtrEquality
10:53:44 <lambdabot> No quotes match. My pet ferret can type better than you!
10:56:08 <int-e> oerjan: well, it sounds like a rather big change to me. so I wouldn't hold my breath
10:56:56 <b_jonas> but why does Constraint come in here in first place?
10:57:06 <b_jonas> I can see why unboxed types have to be handled separately,
10:57:26 <int-e> I suppose that's because => is just another name for ->
10:57:29 <b_jonas> but why can't Constraint actually be an ordinary * typed value?
10:57:40 <b_jonas> int-e: yes, but can't it just _really_ be that?
10:57:49 <b_jonas> for the compiler internals that is, without lying to itself?
10:58:03 <b_jonas> what makes it necessary to handle it separately in some cases?
10:59:22 <int-e> ordinary values can be bottom; evidence never should be. so if anything, it'd have to be some unlifted thing ...
10:59:50 <b_jonas> I mean, evidence can be lazy,
10:59:57 <b_jonas> so why can't it also be bottom?
11:00:19 <int-e> because you want to be able to erase it
11:00:40 <b_jonas> I mean especially if higher-rank types are involved
11:01:40 <b_jonas> int-e: I don't understand what you mean by "erase" there. doesn't "erase" usually just mean to pass around the evidence or type in runtime?
11:02:10 <oerjan> if Constraint and * weren't distinguished, you could write f :: (Ord a, Int) => Int and what would that mean
11:02:12 <b_jonas> (well, "erase" and "remove" and "delete" means way too many things, because we've ran out of synonyms everywhere, but still in this sense)
11:02:19 <int-e> coerce :: (a ~ b) => a -> b <-- no evidence is ever passed to coerce; the equality is satisfied by the caller.
11:02:43 <b_jonas> oerjan: it would mean a question-mark constraint probably, like (Ord a, ?a :: Int) =>
11:02:56 <oerjan> b_jonas: but under which name?
11:03:09 <int-e> This would become much harder when you make (a ~ b) "just another value".
11:03:47 <int-e> Also things of Constraint types is something the type checker can manufacture itself (looking up type classes, etc); it cannot produce arbitrary values.
11:04:22 <oerjan> b_jonas: but in that case, Ord a would _also_ mean ?a :: Ord a because the kind is the only thing distinguishing them
11:04:44 <int-e> There may not be a foundational reason for treating constraints as values (I don't know; since you can embed them in GADTs that suggests this is theoretically doable), but there are plenty of practical reasons to treat them specially.
11:04:47 <b_jonas> int-e: um, don't you still have to pass an evidence there, it's just of unit type so it's often optimzied otu or something?
11:05:11 <int-e> b_jonas: () has two values
11:05:26 <b_jonas> int-e: yes, and don't you still need two values for passing (a ~ b)?
11:05:35 <int-e> b_jonas: you cannot erase that. that's what I meant when I wrote about "something unlifted".
11:05:54 <int-e> b_jonas: no. it's never passed; there is no undefined a ~ b value (except nontermination)
11:07:21 <b_jonas> int-e: yes, I'm talking about nontermination. you could have an existentially quantified value of type, say, (exists a b. (a ~ b) => (a, b)) that is so non-terminating it can't even prove the constraint
11:07:39 <oerjan> <int-e> oerjan: well, it sounds like a rather big change to me. so I wouldn't hold my breath <-- maybe goldfire could include it since he's already messing with all the kinds
11:07:44 <b_jonas> now actually passing the constraint might be optimized away because if the constraint is non-terminating then the value is also non-terminating
11:07:54 <b_jonas> but that's just an implementation detail
11:08:28 <int-e> b_jonas: but you don't have to *represent* nontermination. the caller still may have to do some work to produce the evidence (if the type-checker can't figure it out on the spot), but no value ever gets passed to coerce.
11:09:26 <b_jonas> I probably have to trust the ghc people that this is so
11:09:49 -!- lleu has joined.
11:10:47 <b_jonas> did the original problem get solved, the problem where phantom kinds in a type did not get represented in the Typeable?
11:11:10 <b_jonas> at least I can now see why this new problem is related to that
11:11:23 <int-e> So I stick to what I said initially. a) evidence should be unlifted (so that trivial evidence like type equalities can be erased; clearly class dictionaries are a different matter...), and b) it's good for the type-checker to know where to look for opportunities for manufacturing its own evidence.
11:11:44 <b_jonas> ok, I think you use "erase" in a different sense than I thought
11:11:58 <oerjan> b_jonas: that's solved yes, then we found another problem which is now also solved
11:12:02 <int-e> Now if you were writing a type theory based theorem prover ... I'd change my opinion and claim the opposite.
11:12:12 -!- Sprocklem has quit (Ping timeout: 250 seconds).
11:12:39 <b_jonas> int-e: can't the trivial evidence be just optimized out later, when generating the machine code?
11:12:54 <int-e> b_jonas: "erasure" refers to values that clearly exist on the System Fc/whatever level, but have no runtime representation.
11:13:06 <int-e> b_jonas: Only if it's never bottom.
11:13:17 <int-e> b_jonas: where "bottom" means a non-terminating, undefined value
11:13:29 <int-e> which *operationally* makes a huge difference.
11:14:10 <b_jonas> int-e: right, that's a different use of "erasure"
11:14:14 -!- Sprocklem has joined.
11:14:25 <int-e> (I really should talk about a different domain, where nontermination and undefined are distinct values.)
11:15:33 <oerjan> f :: ('True ~ 'False) => a; f = launchMissiles
11:15:54 <int-e> note that ghc's unboxed types have the same quality: you can write expressions like let x = 1# + x in ...; despite being unboxed, it's still bottom. but there are no (terminating) undefined values.
11:16:36 <b_jonas> int-e: what do you mean by a terminating undefined value, for other types? one that throws a runtime exception?
11:16:40 <Melvar> ( :let f : (Ord a, Int) => Int; f = %instance
11:17:03 <b_jonas> or one that has some side effect when evaluating, but never gets to the point of returning?
11:18:19 <oerjan> (i saw in the manual earlier that recursive definitions of unboxed variables isn't allowed)
11:18:49 <oerjan> that may be just because + doesn't apply to Int#s
11:19:11 <lambdabot> ‘++’ (imported from Data.List), ‘+’ (imported from Prelude),
11:19:27 -!- boily has quit (Quit: PROEMINENT CHICKEN).
11:19:30 <oerjan> Prelude Data.Typeable GHC.Exts> let x = 1# +# x in x
11:19:30 <oerjan> <interactive>:42:5: Recursive bindings for unlifted types aren't allowed: x = 1# +# x
11:20:45 <b_jonas> is "unlifted types" the same as "unboxed types"?
11:21:07 <oerjan> Melvar: i don't think idris has coherent instances so it doesn't really apply
11:22:29 <oerjan> b_jonas: not exactly. unlifted means "no thunk", unboxed means "no pointer"
11:22:46 <mroman> Make sure that when you use the <pre> and <code> tags, you use the unicode variants for the opening and closing tags: < and >.
11:22:51 <oerjan> there are unlifted arrays that still use pointers to heap
11:23:22 <idris-bot> BotPrelude.mkShow : (a -> String) -> Show a
11:23:39 <oerjan> mroman: well that guy obviously isn't using theirs
11:24:00 <mroman> That's taken from a bootstrap how-to website :)
11:24:10 <oerjan> b_jonas: mainly because they're too big to keep in registers/stack
11:24:19 -!- edirc has quit (Excess Flood).
11:24:27 <oerjan> afaiu from what i read this morning
11:25:43 <oerjan> Melvar: AAAAAAAAAAAAAAAAA
11:26:24 <Melvar> oerjan: ∀∀∀∀∀∀∀∀∀∀∀∀∀∀∀∀∀
11:26:31 <int-e> oerjan: ok, some actual loop then. let f :: () -> Int#; f x = f x in I# (f ())
11:26:33 <oerjan> mroman: presumably the distinction between unlifted and unboxed only makes sense for a non-strict language.
11:27:13 <oerjan> strict languages have no values that are lifted.
11:27:56 <Melvar> Except for those of type Lazy' t a .
11:27:57 <int-e> oerjan: Anyway, fun insight: The Scott topology that we so often use to discuss Haskell semantics cannot distinguish between Int and Int# (the two types are isomorphic; note that I# is strict.)
11:28:00 <oerjan> int-e: right, results that never return are allowed.
11:29:06 <b_jonas> fungot, what do you think would be the best fix for these Typeable problems?
11:29:07 <fungot> b_jonas: t-rex, i left a party early to go have a bath, and there i don't feel like i look down and notice you're not there cannot help but to fade a bit! i meant real emails.
11:30:40 <int-e> b_jonas: yes, a terminating undefined value is something like `undefined` or `error "foo"`.
11:30:52 <oerjan> b_jonas: oops that was to you not mroman
11:31:53 <oerjan> fungot: i agree, it would be nice if ghc trac's Cc: worked properly
11:31:53 <fungot> oerjan: people have worried! the fact, you were like, " hey, i wonder if i've become one
11:32:49 <Melvar> I sometimes feel like Idris’ typeclasses currently have the wrong amount of magic.
11:32:58 <HackEgo> [wiki] [[Language list]] M http://esolangs.org/w/index.php?diff=42590&oldid=42568 * Vriskanon * (+8) /* Non-alphabetic */ Added 4
11:33:00 <HackEgo> [wiki] [[4]] N http://esolangs.org/w/index.php?oldid=42591 * Vriskanon * (+117) Created stub. Will develop later.
11:33:40 <oerjan> that a is not *, but OpenKind iirc
11:34:05 <oerjan> just so it can be used with unlifted types
11:34:21 <Melvar> That is, they should either be more magical like Haskell’s, perhaps with coherence, or they should be less magical to be more flexible.
11:34:34 <int-e> > let a :: Int#; !a = error "foo" in ()
11:34:35 <lambdabot> Not in scope: type constructor or class ‘Int#’
11:34:36 <lambdabot> ‘Int’ (imported from Data.Int), ‘Int8’ (imported from Data.Int)
11:34:38 <Melvar> I’m kinda favoring the latter at the moment.
11:34:54 <FireFly> Melvar: how are they currently magical?
11:34:55 <int-e> oerjan: sorry, you're right... very interesting.
11:35:46 <oerjan> int-e: which means that let e = error does not make e equivalent to error
11:36:43 <FireFly> Somehow it reminds me of JS's `eval`, which changes behaviour if you alias it and invoke the alias
11:36:46 <oerjan> > let !a = error "foo" where 3# = a in ()
11:36:47 <lambdabot> Recursive bindings for unlifted types aren't allowed:
11:37:43 <oerjan> > let 3# = error "foo" in ()
11:38:10 <FireFly> So because 3# is strict, the error is evaluated immediately?
11:38:15 <oerjan> > let 3# = e "foo"; e = error in ()
11:38:31 <oerjan> FireFly: yeah so it seems
11:39:24 <FireFly> > let !a = e "foo"; e = error in ()
11:39:50 <Melvar> FireFly: Well, declared instances are available for the search to find alongside local variables, and values of declared classes can only be constructed through an instance declaration. Constraints kick off the search.
11:40:31 <int-e> Ok, operationally there's no problem here; error just traverses the stack, executing various updated frames (which only point to boxed things), until it reaches a catch frame, where it stops.
11:40:55 <b_jonas> what does (let 3# = error "foo" in ()) even mean? how can 3# be a pattern? isn't it a literal?
11:41:23 <b_jonas> maybe there are numeric rules that make it check equality when you use it as a pattern
11:41:33 <oerjan> b_jonas: literals have always been patterns
11:41:46 <oerjan> otherwise, how would fac 0 = 1 work
11:41:47 <b_jonas> oerjan: right, there's specific rules for them
11:41:57 <int-e> b_jonas: we're outside of Haskell2010 territory anyway. ghc implements patterns for unboxed ints.
11:42:03 <FireFly> Well, a literal is a data constructor
11:42:10 <Melvar> FireFly: (mkShow does not circumvent the second limitation; it uses a single named instance as glue.)
11:42:15 <int-e> n#-patterns, if you well
11:42:16 <oerjan> FireFly: not in theory
11:42:19 <b_jonas> FireFly: nah, not a numeric literal, no
11:43:08 <oerjan> :t \x -> let 3 = x in x
11:43:21 <FireFly> Melvar: hm, I don't think I know enough about Idris to understand that properly, but thanks anyway
11:43:34 <Jafet> > let f 1.0 = () in f 1.0
11:44:13 <Jafet> > let f 1.0 = () in f (1.0 + 1e-15)
11:44:14 <lambdabot> *Exception: <interactive>:3:5-14: Non-exhaustive patterns in function f
11:45:04 <Melvar> > let f : Rational -> (); f 1 = () in f 1
11:45:06 <lambdabot> <hint>:1:18: parse error on input ‘->’
11:45:13 <Melvar> > let f :: Rational -> (); f 1 = () in f 1
11:45:46 <Jafet> > let f (1%3) = () in f (1%3)
11:45:47 <lambdabot> <hint>:1:8: Parse error in pattern: 1 % 3
11:46:01 <Jafet> > let f ((==1%3) -> True) = () in f (1%3)
11:46:53 <Melvar> Do numerical literal patterns turn into use of (==)?
11:47:06 <oerjan> they _removed_ n+k patterns, they're not going to add %
11:47:43 <b_jonas> Melvar: and numeric literals as either patterns or values turn to a use of FromInteger or FromRational I think
11:48:02 <oerjan> b_jonas: uncapitalized
11:48:17 <b_jonas> fromInteger or fromRational
11:48:28 <Melvar> I was only unclear on the semantics of the patterns.
11:48:33 <int-e> oerjan: Hmm, so the distinguishing feature of unlifted types is not that they can't be bottom, but that a function cannot be lazy in an unlifted type argument. Fun.
11:49:21 <mroman> what the fuck is let f ((==1%3) = () in f (1%3)
11:49:30 <Jafet> I hope nobody actually uses floating point patterns
11:49:48 <int-e> oerjan: sorry, I'm having an epiphany here.
11:50:02 <Jafet> (The only reasonable uses for those would be matching Infinity or NaN, but neither of those can be achieved.)
11:50:05 <oerjan> mroman: ((==1%3) -> True) is a view pattern
11:50:17 <mroman> I haven't looked at recent extensions.
11:50:32 <oerjan> it's not _that_ recent >:)
11:50:45 <mroman> Maybe not in haskell terms :D
11:51:12 <int-e> oerjan: (The distinction is so very subtle.)
11:52:03 <oerjan> <Jafet> I hope nobody actually uses floating point patterns <-- well you could use them Rationals if you wanted
11:52:06 <Melvar> Jafet: I picked RATIO there on purpose.
11:52:45 <int-e> > let f 0 i = i; f x i = f (x/2) (i+1) in f 1 0
11:52:55 <Jafet> But it looks like a constructor. Imagine the confusion that would sow.
11:53:04 <b_jonas> do we have foo=>bar view patterns too now
11:53:14 <b_jonas> you know, the ones involving a Maybe
11:53:35 <b_jonas> haskell syntax extensions in ghc are screwed up anyway
11:54:14 <Jafet> Not even the list comprehension SQL extensions?
11:54:17 <oerjan> they sacked the syntax czar too early
11:54:23 <Jafet> (... "paging zzo")
11:55:09 * int-e is silently hoping for an sqlite-based Haskell compiler.
11:55:18 <Melvar> Jafet: Would full monad comprehensions suffice?
11:55:43 <oerjan> Melvar: i think those two extensions are compatible
11:55:56 <oerjan> as in, there are classes for the SQL things
11:57:50 <Melvar> (In Idris, comprehensions of course turn into >>= and guard so you can once again do whatever you want. >ω>)
11:57:50 <oerjan> with the weakening of the distinction between values/types/kinds, the type notation is so screwed up
11:58:22 <mroman> "Bootstrap's global default font-size is 14px, with a line-height of 20px. This is applied to the <body> and all paragraphs. In addition, <p> (paragraphs) receive a bottom margin of half their line-height (10px by default)."
11:58:33 <mroman> why would they choose a pixel sized font-size :(
11:59:38 <Jafet> 0.014 imperial cubits
12:03:25 <Melvar> Apparently the cubit is the latin equivalent of the ell.
12:09:09 <mroman> It's surprising americans actually use hours, seconds and minutes
12:09:11 <mroman> and not something else
12:09:16 -!- hjulle has joined.
12:09:18 <b_jonas> thi sis surreal, I'm sitting in an office with a rabbit stuffed toy, and talking nonsense about the ghc type system that I don't understand
12:09:29 <b_jonas> who's have thought my life would get to this?
12:09:37 <mroman> where a tick is 0.978 seconds and a tock is 53 ticks
12:15:02 <int-e> mroman: px are not physical pixels.
12:15:23 <oerjan> mroman: that's because hours, seconds and minutes predate the metric system hth
12:17:03 <b_jonas> but days and weeks are are even older
12:19:05 <b_jonas> I can't type "vocabulary". I keep trying to type "covabulary" instead
12:19:58 <int-e> Funny, I once saw a beamer that (apparently, it's the only explanation I have) reported its physical resolution, which made pt-based fonts (which, also apparently, the login manager used...) ridiculously small.
12:21:20 <int-e> (it would be about 30 dpi)
12:23:20 <int-e> mroman: do you know about https://en.wikipedia.org/wiki/French_Republican_Calendar ? It didn't catch on...
12:24:07 <int-e> (I suspect that a big factor in this was that nobody liked having their birthday on quartidi every year.)
12:35:20 -!- tellybot has joined.
12:36:05 -!- tellybot has left.
12:42:41 <mroman> int-e: yeah but it overwrites my default browser font-size
12:45:11 <mroman> but a year has ~365 day
12:45:35 <mroman> what did they do with those 5 days at the end?
12:46:31 <int-e> https://en.wikipedia.org/wiki/French_Republican_Calendar#Complementary_days
12:50:36 <mroman> You should be using internet time anyway
12:50:40 <mroman> currently we have 577 beats.
12:50:53 <mroman> it's @577 to be precise.
12:52:12 <int-e> mroman: oh you were not saying that they should've used pt instead...
12:54:17 <HackEgo> [wiki] [[4]] http://esolangs.org/w/index.php?diff=42592&oldid=42591 * Vriskanon * (+3145) Added summary, table of functions, formatting (check for correct wiki formatting?) and basic example code.
13:00:39 -!- ProofTechnique has quit (Quit: ZNC - http://znc.in).
13:11:28 <nortti> idea: there are an unbounded number of memory cells, numbered from 1 onwards. you can move between them using the operations 2n, (n-1)/3, and collatz function
13:12:13 <HackEgo> [wiki] [[4]] M http://esolangs.org/w/index.php?diff=42593&oldid=42592 * Vriskanon * (+172) /* Sample codes */ Added Hello World program
13:13:34 <oerjan> well that gives you at least a one-sided tape on powers of 2
13:14:41 <oerjan> in fact an infinite number, although moving between them is more awkward.
13:15:07 -!- Phantom_Hoover has quit (Remote host closed the connection).
13:15:40 <nortti> hmm, actually, should one be allowed to go to 4 from 13? because if yes, you do (n-1)/3, then collatz, and end in someplace completely different
13:15:48 <nortti> and also, it would no longer be a tree
13:16:35 <int-e> so just stick to powers of two
13:16:44 <HackEgo> [wiki] [[Language list]] M http://esolangs.org/w/index.php?diff=42594&oldid=42590 * Vriskanon * (-16) /* D */ Removed Daft Punk - Have given up on the project
13:16:47 <oerjan> (n-1)/3 only if you end up at an odd number, naturally
13:17:39 <HackEgo> [wiki] [[Daft Punk]] http://esolangs.org/w/index.php?diff=42595&oldid=42234 * Vriskanon * (-317) Removed all text - please delete the page (project given up)
13:18:09 <int-e> Alternatively, make a competition: limit n to 2^16, and write programs that can reverse strings up to some length M; the person with the best M/sqrt(program size) ratio wins.
13:18:27 <int-e> (not sure what the scoring formula should be)
13:19:11 <HackEgo> [wiki] [[Special:Log/delete]] delete * Oerjan * deleted "[[Daft Punk]]": Author request: content was: "{{stub}}" (and the only contributor was "[[Special:Contributions/Vriskanon|Vriskanon]]")
13:19:12 <Jafet> Can that simulate a RAM with logarithmic overhead?
13:27:20 -!- ProofTechnique has joined.
13:29:00 -!- Patashu has quit (Ping timeout: 256 seconds).
13:33:33 -!- oerjan has quit (Quit: leaving).
13:35:25 <HackEgo> [wiki] [[User:Vriskanon]] M http://esolangs.org/w/index.php?diff=42596&oldid=42266 * Vriskanon * (+10) /* Vriskanon */ Added credit for 4
13:41:01 -!- Sprocklem has quit (Ping timeout: 244 seconds).
13:43:21 -!- Phantom_Hoover has joined.
13:55:20 <Taneb> There are going to be 2 new IWC comics A WEEK
13:56:19 <b_jonas> nortti: http://www.irregularwebcomic.net/
14:06:28 -!- `^_^v has joined.
14:12:57 <fungot> mroman: 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, for all intents and purposes
14:13:23 <int-e> fungot: what a cliffhanger...
14:13:24 <fungot> int-e: in a good story, they function in an undiagnosable way?
14:13:33 <fungot> int-e: so! i intend to do today! we can't hang up the phone to talk to a t-rex... nostalgia, doesn't that make them equally valid?!
14:14:24 <int-e> But I still want to know what pushing the salt shaker over to their side means :-/
14:14:47 <int-e> Etiquette is hard.
14:16:07 -!- adu has joined.
14:28:02 -!- MDream has changed nick to MDude.
14:28:10 <HackEgo> [wiki] [[Element]] http://esolangs.org/w/index.php?diff=42597&oldid=40776 * 63.232.95.4 * (-1) /* Documentation */ minor typo fixes
14:28:56 -!- Phantom_Hoover has quit (Ping timeout: 246 seconds).
14:29:21 <HackEgo> [wiki] [[Special:Log/newusers]] create * Phi * New user account
14:31:47 <mroman> We can't hang up the phone to do that, indeed.
14:33:42 <b_jonas> int-e: probably he wanted to show a trick with the salt shaker, like Reg from ''Dirk Gently'' did
14:33:50 <HackEgo> [wiki] [[Element]] http://esolangs.org/w/index.php?diff=42598&oldid=42597 * Phi * (+1492) Updated documentation
14:34:21 <int-e> b_jonas: good idea (great trick, too.)
14:35:03 <mroman> fungot: What does the shalt shaker mean?
14:35:03 <fungot> mroman: and so: " probably not!"
14:36:24 <int-e> fungot: what can you tell us about electric monks?
14:36:24 <fungot> int-e: dromiceiomimus, i have a great idea, dromiceiomimus: stories for women! stories with " and in april, your ' i got it'" letters forever
14:36:47 <int-e> fungot: can we try that again?
14:36:52 <int-e> fungot: go ahead then
14:36:52 <fungot> int-e: as a man concerned, t-rex, that going shopping was your default activity? by this i mean, t-rex?
14:37:56 <mroman> fungot: I like shopping.
14:37:56 <fungot> mroman: i've never been to the bottom of a bottle. doctor: as a male, i can be one of those people are going to think you're a pedophile, and he's on a friggin' universe. and then there'll be a day shortly afterwards when we can simulate universe on our cell, because there'd have been no controversy.
14:38:07 <int-e> b_jonas: Oh, and for some reason the phrase "horses were so cheap to make" stuck to my mind.
14:38:39 <b_jonas> int-e: where's that phrase from?
14:38:42 <mroman> fungot: That doctor sounds weird.
14:38:43 <fungot> mroman: but t-rex, you can't play the game optimally! and assuming that in a man... or a woman, dromiceiomimus
14:38:43 <int-e> b_jonas: same book
14:39:03 <int-e> b_jonas: they allowed the [electric monk] to keep his horse though, because horses were so cheap to make
14:39:04 <b_jonas> I'll have to re-read that book. it's been a lot of time.
14:49:36 -!- Sprocklem has joined.
14:53:40 <HackEgo> [wiki] [[Element]] http://esolangs.org/w/index.php?diff=42599&oldid=42598 * Phi * (+1284)
14:57:21 -!- Phantom_Hoover has joined.
15:04:14 -!- hjulle has quit (Ping timeout: 265 seconds).
15:11:02 <FireFly> <Taneb> There are going to be 2 new IWC comics A WEEK ← sounds rather regular
15:12:05 <b_jonas> FireFly: from http://www.irregularwebcomic.net/special/faq.html "But so far this comic has been more regular than many webcomics that actually claim to be updated regularly!"
15:13:32 -!- S1 has joined.
15:17:02 <b_jonas> hehe, http://www.savagechickens.com/2015/04/stomping.html totally looks like qwantz
15:39:15 -!- S1 has quit (Quit: S1).
15:44:58 -!- SopaXorzTaker has joined.
15:48:07 <HackEgo> [wiki] [[4]] http://esolangs.org/w/index.php?diff=42600&oldid=42593 * SuperJedi224 * (+10)
15:49:42 -!- GeekDude has joined.
15:52:13 -!- ProofTechnique has quit (Ping timeout: 256 seconds).
16:01:58 -!- ProofTechnique has joined.
16:02:10 -!- adu has quit (Quit: adu).
16:03:35 <HackEgo> [wiki] [[Turing tarpit]] http://esolangs.org/w/index.php?diff=42601&oldid=30149 * 162.247.72.213 * (+1) Spelling fix
16:05:15 -!- variable has joined.
16:07:48 -!- variable has quit (Client Quit).
16:10:38 -!- variable has joined.
16:12:20 -!- MDude has quit (Ping timeout: 245 seconds).
16:18:37 -!- GeekDude has quit (Ping timeout: 244 seconds).
16:18:41 -!- bb010g has quit (Quit: Connection closed for inactivity).
16:20:57 -!- GeekDude has joined.
16:23:07 <HackEgo> olist 980: shachaf oerjan Sgeo FireFly boily nortti
16:25:33 -!- zzo38 has joined.
16:52:35 <zzo38> When opening a ZIP archive I will first list the files in the archive before extracting it
17:12:16 -!- nszceta has joined.
17:17:19 -!- variable has quit (Quit: 1 found in /dev/zero).
17:19:01 -!- variable has joined.
17:26:41 -!- atrapado has joined.
17:31:36 -!- Guest75683 has changed nick to Gregor.
17:33:29 -!- SopaXorzTaker has quit (Read error: Connection reset by peer).
17:37:46 -!- Sprocklem has quit (Ping timeout: 264 seconds).
17:39:27 -!- variable has quit (Quit: 1 found in /dev/zero).
17:41:34 -!- atehwa_ has changed nick to atehwa.
17:42:52 -!- variable has joined.
18:13:23 -!- nszceta has quit (Quit: My Mac has gone to sleep. ZZZzzz…).
18:42:47 -!- Sprocklem has joined.
19:01:49 -!- ProofTechnique has quit (Remote host closed the connection).
19:07:05 -!- ProofTechnique has joined.
19:11:09 -!- ais523 has joined.
19:13:09 -!- atrapado has quit (Ping timeout: 265 seconds).
19:24:55 -!- rodgort has quit (Ping timeout: 272 seconds).
19:31:08 -!- rodgort has joined.
19:46:47 -!- ais523 has quit (Remote host closed the connection).
19:46:53 -!- callforjudgement has joined.
19:46:59 -!- callforjudgement has quit (Changing host).
19:46:59 -!- callforjudgement has joined.
19:51:19 -!- bb010g has joined.
19:51:30 -!- variable has quit (Quit: 1 found in /dev/zero).
19:51:58 -!- variable has joined.
19:52:38 -!- callforjudgement has changed nick to ais523.
19:53:04 <ais523> so, my yacc implementation has now reached the point where, if everything works out correctly, it can successfully parse something
19:53:14 <ais523> i.e. far from 100% functionality, but a sufficient percentage that it works sometimes
19:53:18 <ais523> this is quite the milestone
19:53:53 -!- Phantom__Hoover has joined.
19:54:45 -!- Phantom_Hoover has quit (Ping timeout: 256 seconds).
19:54:54 -!- callforjudgement has joined.
19:55:00 <ais523> also, I found a place where Bison violates the letter of the POSIX spec, because POSIX is asking for something unreasonable
19:55:02 -!- ais523 has quit.
19:55:28 <callforjudgement> also, looks like I arrived in time to see the last message I sent
19:55:37 -!- callforjudgement has changed nick to ais523.
19:55:51 <pikhq> What was so unreasonable about the POSIX spec?
19:56:05 <ais523> it doesn't limit the situations in which yyclearin can be called
19:56:17 <ais523> which allows you to retroactively invalidate any sort of optimization that the yacc impl might have made
19:57:22 <ais523> you can try that example in Bison (or ayacc, it comes to the same thing, default config in both cases)
19:58:00 <b_jonas> let me look up what that means
19:58:21 <ais523> this means I have to do stupid things, like checking to see if the lookahead character has a particular value to know to run a particular reduction, then checking it again to make sure it hasn't changed
19:58:27 <ais523> which are likely to really slow down parsing
19:58:28 -!- rdococ has quit (Quit: Page closed).
19:58:39 <ais523> I'm on the point of just grepping for "yyclearin" in the user's actions and optimizing if I don't see it
19:58:39 <pikhq> When is a lookahead token read, exactly?
19:58:49 <ais523> whenever it's needed to determine between two possible parses
19:59:04 <pikhq> "If the current lookahead token has not yet been read, yyclearin shall have no effect."
19:59:27 <ais523> in the example I pasted, it's as clear as possible that that's happening
19:59:44 <ais523> because you clearly can't distinguish an x from a y without reading the x_indicator or y_indicator
19:59:49 <b_jonas> pikhq: it's a token that hasn't been shifted yet. the lr parser works in a way that it can apply a grammar rule reducing symbols only if the last symbol that's already been shifted is part of that, it can't reduce "below" the last shifted symbol
19:59:56 <b_jonas> (dunno if that makes sense)
20:00:45 <b_jonas> ais523: what if you just make yyclearin a macro that always gives a compile error saying that feature is unsupported if you try to use it?
20:00:58 <ais523> b_jonas: I'm trying to be POSIX-compatible even when it makes no sense
20:01:04 <b_jonas> also, why do they put these kinds of things in POSIX?
20:01:06 <ais523> just look at the location of the comment in that example :-)
20:01:24 <b_jonas> these seem like historical artifacts that were added because they were easy to implement in one particular yacc implementation
20:01:32 <ais523> another fun bit is that the POSIX spec mentions that yychar is renamed by -p, but doesn't define any job for it to do
20:01:47 <b_jonas> argh stupid historical cruft we're carrying
20:01:48 <ais523> so I just didn't implement it
20:02:19 <ais523> yyclearin is very easy to implement in almost any yacc implementation, it just invalidates pretty much any optimization you might think of that involves reductions
20:03:18 <ais523> and it makes sense to put it in an error recovery rule
20:03:18 <pikhq> Now that's real interesting. :)
20:03:36 <ais523> I just can't think of a different sensible place to put it, IMO it'd be confined to error recovery only
20:03:37 <b_jonas> wait, yychar is a _variable_, writable?
20:03:48 <b_jonas> how would that not break the states?
20:04:03 <pikhq> It looks like traditionally it contains the lookahead token.
20:04:05 <b_jonas> can you just write anythign in it?
20:04:17 <ais523> and the reason (probably the only reason) it works is that Bison verifies tokens for syntaxiness on shift, not on reduce
20:04:18 <pikhq> b_jonas: Doing so probably invokes UB.
20:04:51 <pikhq> Most of the state in traditional yacc is mutable global state that a yacc program isn't permitted to touch.
20:05:11 <b_jonas> this is crazy stuff I didn't want to see or know about
20:05:16 <b_jonas> I'll have to try to unsee it hard now
20:05:18 <ais523> according to Bison you can just change yychar when you want
20:05:27 <pikhq> Because yacc straight-up compiles to C code that just mutates all that state.
20:05:50 <pikhq> (yacc is *not* designed for, say, reentrant use. :))
20:05:54 <b_jonas> people back then didn't understand encapsulation
20:06:10 <pikhq> Yes, it was designed to compile compilers.
20:06:13 <pikhq> And that's about it.
20:06:28 <ais523> pikhq: the way I'm handling this in ayacc is, it has an entry point yyparse_symbol that takes yylex as an argument
20:06:36 <pikhq> It is *entirely* suitable for the task of, say, writing a simple C compiler.
20:06:51 <ais523> and then yyparse is a wrapper around that, which gives it a wrapper around yylex as an argument
20:07:57 <ais523> the only problem with doing this is that yylex has to /exist/ even if you use the sensible API (although it won't be called)
20:08:06 <pikhq> ais523: Ah, spiffy. So essentially none of it assumes that the state is global, it just so happens that when used in a purely POSIX fashion it behaves that way.
20:08:33 <ais523> I'm glad yychar isn't /necessarily/ a global because otherwise I couldn't keep it in sync with yylval
20:08:36 <ais523> (which is necessarily a global)
20:09:13 <b_jonas> ais523: and is each parser re-entrant so you can start multiple instances? if so, is there a defined api for how to break out of one cleaning up all the memory it's allocated?
20:09:21 <pikhq> Done anything with lex, or is flex "good enough" for you? :)
20:10:03 <ais523> b_jonas: yes to the first; for the second, I don't have destructors or the like, but in a language which has exceptions, if you use exception-safe code it should work
20:10:33 <pikhq> So you essentially just have to be aware that it's C.
20:11:11 <pikhq> Mind me asking why you started working on ayacc?
20:11:19 <ais523> because I couldn't find a decent yacc impl for Windows
20:11:32 <b_jonas> hmm, how'd she get the knife back? I'll have to read back
20:11:42 <pikhq> Hum. Does ayacc work on not-Windows?
20:11:48 <ais523> that's where I'm testing it
20:11:54 <ais523> I haven't tried it on Windows yet
20:12:02 <b_jonas> ais523: do you mean it is guaranteed to allocate memory only on the stack, as in, it won't call malloc?
20:12:04 <ais523> but I'm not doing anything unportable yet
20:12:14 <ais523> b_jonas: right, no malloc anywhere (unless you write it in your semantic actions)
20:12:22 <pikhq> And hopefully by the time it matters musl-on-windows will be an option.
20:12:32 <b_jonas> and sure, if I allocate, that's of course mine to cleanup
20:12:50 <ais523> I'll need help from a C++ expert to figure out how this should work in C++, you can copy everywhere and it'd work but be inefficient
20:12:59 <b_jonas> ais523: it also won't start threads or coroutines or processes of course, right? not that it would make sense, but that's also required for just jumping out to work.
20:13:20 <b_jonas> ais523: to figure out how what should work?
20:13:30 <ais523> no, but it currently uses setjmp/longjmp in C for error handling
20:13:34 <ais523> b_jonas: semantic values, mostly
20:13:55 <ais523> atm I just pass them around with assignment commands
20:14:01 <ais523> and return them and pass them from functions plain
20:14:32 <ais523> in C they're nearly always integers or pointers, so that works pretty well
20:14:35 <b_jonas> ais523: hmm... the problem is mostly when you destroy symbols on the stack, either during error handling or when the whole stream is rejected
20:14:37 <ais523> but in C++ it'd make sense to use objects
20:14:39 <b_jonas> ais523: you need some sort of destructors
20:14:49 <ais523> Bison has a nonstandard extension for this
20:14:50 <b_jonas> ais523: as in, most of the symbols are destroyed when they're reduced
20:15:00 <b_jonas> ais523: lemon handles this sanely actually:
20:15:17 <b_jonas> it has destructor function for symbols (terminal and non-terminal) that it calls if they're non-reduced
20:15:34 <b_jonas> setjmp itself should be no problem unless you somehow call it from inside a user action
20:15:34 <ais523> anyway I could implement things like that but it'd cost a lot of performance, as I'd need a separate error path in every function
20:15:52 <b_jonas> but even without error handling, you have to do something when the input doesn't match the grammar
20:15:54 <ais523> well YYERROR is a longjmp call, but thankfully that's already documented to not terminate normally
20:16:03 <b_jonas> clean up the symbols on the stack somehow
20:16:07 <ais523> I think it normally compiles to a goto, because traditionally everything's one function
20:17:17 <ais523> anyway the POSIX approach is to just leak them
20:17:24 <ais523> which is completely fine if they're ints
20:17:36 <ais523> btw, something that shocked me is that POSIX yyparse has no way to return a value, other than success/fail
20:17:51 <ais523> you have to write a top-level semantic action that stores it in a global variable
20:18:42 <b_jonas> ais523: there's a mode where there's no %union but only one type for representing all nonterminals, right? if that's what I do, there'll be no union in the emitted C code?
20:19:00 <b_jonas> if so, then it will probably "just work" if you make that one type a C++ object with a destructor,
20:19:23 <ais523> b_jonas: right, if you don't use <> marks anywhere
20:19:26 <b_jonas> however, it might be better if you could make ayacc call some sort of destructor in C mode too
20:19:32 <ais523> although I'm having trouble understanding what POSIX says to do in that situation
20:19:40 <ais523> some bits imply the global type should be int
20:19:49 <b_jonas> isn't there another declaration?
20:20:16 <GeekDude> >>> from __future__ import division; 1/2**6 * sum(map(lambda n: (-1)**n/2**(10*n) * (-2**5/(4*n+1) - 1/(4*n+3) + 2**8/(10*n+1) - 2**6/(10*n+3) - 2**2/(10*n+5) - 2**2/(10*n+7) + 1/(10*n+9)), range(50)))
20:20:31 <GeekDude> is there not a python bot in here?
20:20:49 <pikhq> ais523: Well, at least with C11 you could make it a thread-local and then you'd have *a* way of behaving sanely.
20:20:53 <ais523> there was like 5 years ago
20:21:09 <ais523> I guess HackEgo might be able to do it?
20:21:16 <b_jonas> I can call parsers recursively
20:21:38 <pikhq> b_jonas: I was meaning you could wrap it into a vaguely sane API.
20:21:42 <ais523> b_jonas: I wasn't expecting anyone to do that, but yes, I think with ayacc it does actually work
20:22:00 <b_jonas> ais523: the point is, if you're using a union (as in the C/C++ thing) in the emitted code, then it's only your parser's code that's somehow tracking which type it contains, so even the C++ compiler won't know how to destroy the values
20:22:40 <b_jonas> ais523: so there's two choices to clean up properly: either ayacc has to support calling a destructor depending on the type of the symbol (ayacc probably knows the type), or you have to use a single type and no union
20:23:15 <ais523> b_jonas: currently I am using a union, but that's only temporary
20:23:20 <ais523> I'm hoping to optimize the union out
20:23:34 <ais523> even inventing a generic syntax for %union that makes sense for languages other than C so that the optimization works
20:23:47 <ais523> (the rule is "%union consists of a sequence of target-language declarations")
20:23:50 <b_jonas> ais523: you can certainly do that in some cases, but I think you need the union in some other cases
20:24:17 <b_jonas> I thought you meant you'd store just one member instead of the whole union in some cases when you know its type
20:24:40 <ais523> if I know the type, I want to be storing in a variable of that type
20:24:56 <ais523> occasionally you need a union though because you can reduce in two different ways (depending on lookahead) and they have different tyeps
20:25:08 <ais523> then your function is basically returning a tagged union, so you can unpack it as soon as you arrive at the destination
20:25:09 <b_jonas> ais523: sure, you almost certainly need a union some times
20:25:27 <b_jonas> but if you want to store just a member sometimes, then you have to be able to parse the union declaration, don't you?
20:26:11 <ais523> you do, but the amount of actual parsing needed is minimal
20:26:33 <b_jonas> don't you have to parse out the member name _and_ the type name?
20:26:46 <ais523> b_jonas: I defined %union as "a sequence of target-language declarations", then all you have to do is swap out the member name
20:26:57 <b_jonas> but how do you know where the member name is?
20:27:10 <ais523> you know /what/ the member name is, so you just look for it
20:27:14 <b_jonas> heck, how do you even know where the boundary between the members is?
20:27:31 <b_jonas> can't semicolons occurr inside declarations these days?
20:27:37 <ais523> that's one of the few concessions I had to make, but luckily they're valid as statement separators in most languages
20:27:51 <ais523> the only case I know, in C at least, is int (/*;*/ *x)
20:28:01 <ais523> and I think I can get away with a "please don't do that"
20:28:04 <b_jonas> but how can you find the member name?
20:28:21 <ais523> you're thinking about this backwards
20:28:29 <ais523> what you already know is the member name, what you don't know is the full declaration
20:28:36 <ais523> but it'll only appear in one of the declarations, so you know it's that one
20:28:39 <b_jonas> nah, more like struct { int u; int v; } foo;
20:28:41 <ais523> and it'll only appear once, so you just look for it
20:28:56 <ais523> right, if you do that, then u and v become invalid as %union tags
20:28:57 <b_jonas> (or struct { int u; char v[';'/4]; } foo; if I want to be evil
20:29:21 <ais523> it's a bit fragile but I think it's an acceptable price, especially if I give an option to disable the optimization
20:29:25 <b_jonas> you mean you know the member name from %type declarations?
20:29:35 <b_jonas> but what if a member name is never used?
20:29:42 <ais523> then you never have to use it
20:29:47 <ais523> so it doesn't matter that you can't
20:30:13 <b_jonas> and what if the same symbol as the member name appears in another context in the declarations? I guess that's just don't do it territory
20:30:58 <b_jonas> ah, I see, Crystal takes it away from Haley in just the previous strip
20:31:19 <ais523> I was going on the basis that it's not going to be a target-language keyword in almost any cases
20:31:22 -!- fractal has quit (Changing host).
20:31:22 -!- fractal has joined.
20:31:34 <ais523> technically you can call a variable $my in Perl, but if you do that, IMO you deserve what you get
20:31:41 -!- variable has quit (Quit: 1 found in /dev/zero).
20:31:51 <b_jonas> ais523: I don't mean a keyword. an identifier. but it's a union tag, so it can appear in other structs or something.
20:32:12 <ais523> yep, I didn't think of the "struct defined in-place" case
20:32:21 <b_jonas> like, %union { float x; struct { float x, y; } point; }
20:32:33 <ais523> admittedly it doesn't seem like a /useful/ case, but it's nice to be as general as possible, especially in #esoteric
20:32:45 <b_jonas> I guess you could just ban that and ask for the types to be defined elsewhere
20:32:50 <ais523> what about this: if the tag isn't unique in the entire %union definition, I just don't optimize
20:33:07 <b_jonas> ais523: if there's an inline struct, you'll have problems with the semicolons anyway
20:33:54 <ais523> actually no because ayacc knows enough to not detect semicolons inside braces
20:34:06 <b_jonas> I think you actually can't use an in-place defined struct usefully
20:34:13 <b_jonas> because you can't easily refer to it from elsewhere
20:34:22 <b_jonas> even if it has a name, you can refer to that name only if you know the name of the union
20:34:41 <b_jonas> you can still use it in a type-unsafe way or by using the value in the rules without referring to the types of coures
20:34:44 <ais523> it has a subset-of-C parser, which you need to use to find the end of the %union declaration anyway
20:34:56 <ais523> also, you do know its name, it's YYSTYPE (specified by POSIX)
20:35:14 -!- orin has quit (Read error: Connection reset by peer).
20:35:27 <pikhq> Be fun to use ayacc to put together a naive-but-usable C compiler.
20:35:30 <b_jonas> ais523: yeah... but it's not YYSTYPE from another compilation unit, especially if you compile multiple grammars
20:35:48 <pikhq> My definition of "usable" here would ideally include "can be used to build Linux".
20:35:59 <b_jonas> ais523: by the way, this kind of nonsense might explain why they use bison in the implementation of bison
20:36:00 <ais523> that's a pretty lofty definition
20:36:05 <ais523> even clang had trouble doing that until recently
20:36:15 <ais523> b_jonas: somehow that doesn't surprise me
20:36:17 <pikhq> Though "naive" helps matters significantly.
20:36:31 <ais523> I think the hard part of building Linux is all the gcc extensions
20:37:00 <pikhq> Which are simpler if you're not doing a significantly complicated optimizer.
20:37:21 -!- Sgeo has joined.
20:37:29 <b_jonas> there's also that Linux relies on particular non-optimizations, and newer gcc and Linux together has to avoid optimizations breaking those old assumptions
20:37:37 <Sgeo> And using Hexchat instead of Quassel
20:37:38 <pikhq> "Which are simpler if you're not doing a significantly complicated optimizer."
20:38:18 <ais523> b_jonas: a naive compiler doesn't need to worry about reliance on non-optimizations
20:38:19 <b_jonas> stuff about atomic accesses that are handled in a strange way (because they had to exist before there was a sane way to handle them in user programs), and objects being ordered in segments in a particular order
20:38:37 -!- hjulle has joined.
20:38:46 <ais523> pikhq: I assume you'd be outputting asm?
20:39:19 <b_jonas> also, that's not too hard, but they have to make sure the kernel code is compiled in a way that it never tries to touch xmm and x87 state
20:39:20 <pikhq> If we're going full-naive but usable for bootstrapping, the compiler should do as little work as it can get away with. :)
20:39:29 <olsner> outputting asm directly from the parser?
20:39:46 <FireFly> From a compiler, as opposed to machine code, I presume
20:39:50 <olsner> might be horrible, but nice to have just a single yacc input file be the whole compiler
20:40:00 <b_jonas> and have to handle old gcc style tagged structure initializers, which for some reason the Linux developers are fond of, even over c99 style initializers
20:40:28 <b_jonas> I think they also have some gcc-style inline assembly, which isn't actually so easy to implement correctly in a compiler
20:40:37 <b_jonas> even without optimizations
20:41:15 <ais523> b_jonas: I'm trying to remember what the old-style even was
20:41:30 <ais523> { [field] value, [field] value } ?
20:41:32 <ais523> or was that just for arrays?
20:41:47 <b_jonas> ais523: I think struct point p = { x: 4, y: -1 };
20:42:04 <b_jonas> wheras new stype is struct point p = { .x = 4, .y = -1 }; I think
20:42:05 <ais523> that does look a bit prettier than the C99 version
20:42:11 <ais523> the C99 syntax is more logical though
20:42:25 <b_jonas> I mostly do C++ so I don't see either
20:42:35 <b_jonas> there's also similar syntax for array initializers
20:42:36 <ais523> and C syntax has a traditional of being 100% logical and predictable, and yet somehow still massively ugly and unintuitive
20:42:44 <olsner> doesn't c++xy import any of that?
20:42:49 <ais523> { [0] = "zero", [1] = "one" }
20:43:00 <b_jonas> ais523: yes, but what's the old gcc style?
20:43:05 <ais523> I use that in NH4 quite a bit for enum-valued arrays
20:43:11 <ais523> I think old style is that without the = signs?
20:43:24 <Sgeo> "Just so you know, your computer does not meet Second Life's minimum system requirements."
20:43:30 <b_jonas> that would totally conflict with C++11 lambda syntax
20:43:53 <b_jonas> well, you need braces for that but those can occurr in an initiali9zer
20:44:04 <ais523> b_jonas: this is way older than C11
20:44:10 <olsner> "An alternative syntax for this which has been obsolete since GCC 2.5 but GCC still accepts is to write `[index]' before the element value, with no `='."
20:44:16 <ais523> it was obsolete in 1999
20:44:34 <ais523> so the fact that it conflicts with C++11 syntax is not really a strike against its having existed
20:45:02 <b_jonas> now I wonder if the C11 initalizer syntax can conflict syntactically with C++11 lambdas too
20:45:07 <b_jonas> but I think it probably can't
20:45:58 <ais523> you can't put an = there in C++
20:46:02 <ais523> and it's required in C11
20:46:07 <b_jonas> ais523: sure, but maybe in some more complicated cases
20:46:30 <ais523> well in C++, after the closing square bracket
20:46:38 <ais523> don't you have to have an opening parenthesis next?
20:46:49 <b_jonas> in C11, you have a bracketed stuff, then either an equal sign, or another bracketed stuff, or a dot, right?
20:46:56 <ais523> (wow, my brain is definitely in parser mode)
20:46:56 <b_jonas> you don't need the parenthesis
20:47:07 <b_jonas> the return type is also optional
20:47:18 <b_jonas> I don't think a dot can follow in C++
20:47:24 <b_jonas> and probably no equals sign either
20:47:26 <ais523> oh wow, that much optional?
20:47:42 <b_jonas> ais523: the braces are required though
20:47:43 <ais523> so []{puts("hello world");} is a valid lambda in C++?
20:47:57 <b_jonas> this is why people are joking about [](){}();
20:48:02 <b_jonas> which is a valid statement in C++11
20:48:34 <b_jonas> and some people want explicit template lambda syntax which would make []<>(){}(); valid too
20:48:44 <b_jonas> but it probably won't happen, sadly
20:49:09 <b_jonas> olsner: they exist now, but without an explicit <>
20:49:25 <ais523> b_jonas: I saw the [](){}() syntax being thrown around as an example of the horrors of C++ well before I knew what it did
20:49:30 <ais523> I was a little disappointed to hear it was a no-op
20:50:02 <ais523> meanwhile, it's crazy hard to write a switch statement efficiently in Perl
20:50:03 <HackEgo> [wiki] [[Taktentus]] http://esolangs.org/w/index.php?diff=42602&oldid=42137 * 80.53.184.190 * (-1) /* External resources */
20:50:07 <olsner> my c++ must be slipping, I can't imagine any way to use a templated lambda
20:50:19 <ais523> my current attempt is a hash from values to subroutines
20:50:20 <b_jonas> ais523: no-op when allowed
20:50:38 <b_jonas> olsner: it's basically an object with a member function template called operator()
20:51:48 <b_jonas> olsner: so it's sort of like auto m = [](auto x){ printf("hello"); } is similar to like struct foo { void template<typename T> operator()(T x) { printf("hello"); } }; foo m;
20:52:01 <HackEgo> [wiki] [[Taktentus]] http://esolangs.org/w/index.php?diff=42603&oldid=42602 * 80.53.184.190 * (+44) /* Syntax */
20:52:11 <b_jonas> don't take that as strict truth, but that's the idea
20:52:23 <olsner> ah, right, the operator() becomes a templated function
20:52:47 <b_jonas> olsner: the main use is just when you're lazy and don't want to explicitly name the argument type, even though you could; but there can be a use when you actually use the same lambda with multiple instantiations of that function
20:53:13 <b_jonas> you can even pass such a polymorphic lambda to other functions, and those functions can call it with multiple typse
20:53:50 -!- f|`-`|f_ has joined.
20:55:04 <b_jonas> ais523: the difficult part of that is that you don't get to use closed values inside the subroutines
20:55:13 <b_jonas> so you have to pass them as arguments explicitly
20:55:21 <b_jonas> ais523: one hack you can use in perl is computed goto
20:55:41 <ais523> that might actually be less evil than the hash of subs
20:55:48 <ais523> actually the hardest part was the scope of "return"
20:55:58 <ais523> because you just return from the inside
20:56:02 <b_jonas> it just has some limitations
20:56:18 <ais523> so you need another layer of "return" around the outside, so the evil part is
20:56:23 <b_jonas> so just use a goto/last to return from deep :-)
20:56:27 <ais523> now the only way to continue in the same function is to jump out of the inside subs using goto
20:57:44 -!- f|`-`|f has quit (Ping timeout: 264 seconds).
20:57:45 -!- f|`-`|f_ has changed nick to f|`-`|f.
20:58:00 <ais523> or last, but that's more evil than goto I think (at least, there's a warning on last and not on goto)
20:58:43 <b_jonas> the incantation is our $RETFOO; sub foo { ... bar(); ... ENDFOO: $RETFOO } sub bar { ...; if (...) { $RETFOO = ...; no warnings "exiting"; goto ENDFOO; } ... }
20:59:03 <ais523> I know you can turn it off
20:59:14 <b_jonas> ais523: actually, you can also jump out with die and eval{}
20:59:15 <ais523> this is how Test::More does its "SKIP:" blocks
20:59:23 <ais523> b_jonas: I use that for the syntax error path
20:59:27 <ais523> or will, that bit isn't implemented yet
20:59:43 <b_jonas> there are some constructs die can't jump out of, and constructs goto can't jump out of, and neither of these are subsets of the other
20:59:48 <b_jonas> but in practice die can jump out of more things
21:00:19 <b_jonas> in particular, die can jump out of some well-behaved XS subroutines whereas I think goto can't ever jump out of any XS (but I could be wrong)
21:00:32 -!- Guest3780 has quit (Read error: Connection reset by peer).
21:00:49 <b_jonas> whereas goto can jump out of sort comparison blocks but die can't (I think)
21:02:02 -!- AnotherTest has joined.
21:02:17 -!- Guest3780 has joined.
21:02:25 <ais523> the reason you can't goto out of XS is because the code outside the XS and the callback from the XS are running in different interpreters
21:02:29 <ais523> just ones that share most of their state
21:02:36 <ais523> the instruction pointer's part of the state that isn't shared
21:02:55 <ais523> hmm, can you goto out of a block eval?
21:02:57 <b_jonas> ais523: also, if you jump out from regexes or the right hand side of s/// substitutions, you may get into unexpected trouble with very old versions of perl
21:03:53 <b_jonas> but I think s/// is fine since the oldest perls you want to support
21:04:06 <ais523> ayacc doesn't work as far back as aimake
21:04:10 <ais523> it's something like 5.14 I think
21:04:26 <b_jonas> and you probably don't want to use /(?{ blocks at all if you want to use old perls, regardless of whether you jump out of them or recurse into the regex engine from them or anything
21:04:32 <ais523> I'm using modern Perl stuff if I want to (although not experimental stuff), on the basis that the platforms stuck on old Perl also tend to have a working yacc
21:04:58 <b_jonas> ais523: yes, but /(?{ semantics has changed even after that, so it's best to avoid complicated tricks with that
21:05:08 <ais523> btw, ayacc has a language-generic backend, the syntax of the target language is basically just in one big hash that contains code fragments
21:05:16 <ais523> that are combined to make the target program
21:05:32 <b_jonas> but I support targetting 5.14+
21:06:01 <b_jonas> ais523: hmm, are there placeholders in those code fragments so the code can be re-ordered?
21:06:42 <ais523> I might have to change my templating syntax eventually but it's working OK atm
21:07:14 <b_jonas> ais523: but you'll still make the C language backend such that it emits a single version of that code that should work in all systems and compilers, right?
21:07:17 <ais523> on the assumption that even though we might have false positives on constructs that exist in the target language, we can avoid generating code that confuses our own internal parser
21:07:30 <ais523> although, one thing I did was
21:07:45 <ais523> you can define a macro YYUNREACHABLE to __builtin_unreachable or the like and it makes your code more efficient
21:07:49 <ais523> if you don't, it substitutes an infinite loop
21:08:08 <b_jonas> ais523: just get the code from libecb and use the ecb_unreachable macro for that
21:08:22 <ais523> (also, I realised that there's really only one correct way to write a macro that expands to an infinite loop)
21:08:47 <ais523> my first attempt was do { for(;;) ; } while (0)
21:08:58 <ais523> but it's clearly possible to do better :-)
21:09:27 <b_jonas> ais523: um, an infinite loop of what?
21:09:33 <b_jonas> like, what's in the loop body?
21:09:46 <ais523> an infinite loop of nothing
21:09:53 <int-e> {} while (1) clearly works
21:09:56 <ais523> it's to help the compiler optimize it out
21:10:02 <b_jonas> oh, you implement that as an inline function
21:10:12 <ais523> ah right, you missed the "do"
21:10:16 <b_jonas> and then the macro just expands to a call to that function
21:10:22 <ais523> yep, I eventually golfed it down to "do; while (1)"
21:10:35 <ais523> (this is a weird sort of golf that requires correct whitespace)
21:10:55 <b_jonas> like, on the top level, inline ecb_noreturn void yyinfiniteloop() { for (;;) pause(); }
21:11:13 <b_jonas> (void) instead of () probably, in C
21:11:20 <ais523> b_jonas: the libecb stuff relies on implementation namespace, doesn't it?
21:11:34 <b_jonas> ais523: what do you mean by "implementation namespace"?
21:11:49 <ais523> b_jonas: anything starting with double underscore or underscore and capital letter
21:11:57 <ais523> (or a few other cases which don't matter here)
21:12:01 <ais523> whether you use them yourself, or just look at them
21:12:12 <ais523> exception: anything that's specifically specified in a relevant C standard
21:12:20 <ais523> (and the relevant standard is C99)
21:12:37 <b_jonas> ais523: it probably relies on it in that it refers to some non-standard compiler extensions on particular compilers, yes
21:12:42 <ais523> so you can look at __STDC_VERSION__ but not __GNUC
21:12:47 -!- oren has joined.
21:12:48 <int-e> ais523: That was a brain fart, but ... interestingly ... gcc accepts that without the do, why?
21:12:49 <ais523> b_jonas: right, POSIX disallows that
21:12:58 <ais523> int-e: two different statements
21:13:04 <ais523> {} and while(1); are both valid statements
21:13:15 <int-e> ais523: oh. silly me.
21:13:24 <b_jonas> ais523: but for most stuff, it refers to those things only on particular compilers
21:13:44 <b_jonas> and on unknown compilers, it will use standard replacements for everything where it's possible
21:13:52 <ais523> b_jonas: yes, but even /detecting/ the compiler is implementation namespace stuff, unless the compiler is outright breaking the standards
21:13:57 * int-e simply shouldn't write infinite loops as a macro
21:14:09 <b_jonas> ais523: but there's a way out
21:14:23 <ais523> working on gcc-bf was weird
21:14:28 <b_jonas> ais523: POSIX specifically says you can't rely on compiler extensions except where you document that in your implementation
21:14:30 <pikhq> Though in general you can get *away* with just testing for compiler-defined macros.
21:14:36 <ais523> because suddenly I was working in implementation namespace myself
21:14:44 <ais523> pikhq: sure, that's the sensible and sane way to go about things
21:14:49 <pikhq> ('get away', not 'you are permitted to by the standard' of course.)
21:14:55 <ais523> but I decided to implement POSIX literally to see what happened
21:15:11 <pikhq> It is much harder for some things than others.
21:15:22 <b_jonas> ais523: but if you're really picky about this, you could make it an option of ayacc to not include the ecb definitions
21:15:53 <ais523> you mean an option /to/ include them?
21:16:13 <b_jonas> I'd always just ask ayacc to include them
21:18:45 <b_jonas> ais523: basically, if I'd be on a compiler where libecb as a whole didn't work (as opposed to it just can't provide a few of its more tricky features), then I'm already screwed and my code will break in other places too
21:18:57 <b_jonas> I don't go strictly POSIX or strictly C99 or anything
21:19:28 <pikhq> In general I try to write strict POSIX or "will work on anything strict POSIX".
21:19:35 <b_jonas> I'm content with just marking nonportable stuff in my code with #ifndef #error so when you try to port it you get compiler errors pointinng out where all the code you ahve to modify is
21:19:42 <ais523> I guess there's a scale from "practical" to "meets the letter of the standard"
21:19:45 <ais523> what I do depends on what I'm doing
21:19:53 -!- variable has joined.
21:20:06 <ais523> but every now and then I jam right against the right-hand end of the scale, just for fun
21:20:16 <ais523> last time was C-INTERCAL's autotools-based build system
21:20:18 <b_jonas> I don't, like, deliberately break compatibility when I don't need to
21:20:31 <b_jonas> but I write nonportable code when it's easier, and mark it so I can change it later when it has to be ported
21:20:37 <ais523> possibly the only time an autotools-based build system has worked exactly in the way that the autotools maintainers intend, for a nontrivial project?
21:21:10 <b_jonas> ais523: which one is the right hand end?
21:21:27 <ais523> the one where you follow the standard exactly
21:23:18 -!- ProofTechnique has quit (Ping timeout: 256 seconds).
21:25:05 <HackEgo> [wiki] [[Element]] http://esolangs.org/w/index.php?diff=42604&oldid=42599 * Phi * (+878)
21:25:08 -!- callforjudgement has joined.
21:25:39 <b_jonas> ais523: are you alreay planning to write specific backends other than the C/C++ one?
21:25:41 -!- ais523 has quit (Disconnected by services).
21:25:44 -!- callforjudgement has changed nick to ais523.
21:25:59 <ais523> b_jonas: I have a Perl backend written already, although I haven't tested it yet beyond visual inspection of the source
21:26:20 <b_jonas> but that's not because you want to use ayacc to implement ayacc itself, right?
21:27:13 <b_jonas> hehe, if ayacc got so successful that bison is abandonned, then the perl people will be in trouble because it will be difficult to bootstrap perl without perl
21:27:20 <ais523> indeed, it isn't implemented in itself
21:27:35 <ais523> b_jonas: nah, they'd just keep a copy of its output around
21:28:34 <pikhq> And it's not like Perl doesn't already have bootstrapping problems.
21:28:47 <pikhq> Perl builds Perl so it can build more Perl.
21:28:57 <ais523> the Perl build system builds a minimal Perl
21:29:00 <b_jonas> sure, but it boostraps fine withotu a perl to start from
21:29:01 <ais523> then uses that for the rest of the build
21:29:11 <pikhq> Yeah, but it doesn't cross compile well. :)
21:29:12 <b_jonas> and it's only one level deep anyway
21:29:48 * pikhq does not understand the obsession with having languages with only a bootstrapping implementation
21:29:53 <b_jonas> pikhq: sure, but it native compiles everywhere, and is relatively quickly compile
21:30:21 <ais523> pikhq: well, if your language is intended to be for compiler writing, then bootstrapping it is a good demonstration of that fact
21:30:35 <pikhq> (note, "only". I can understand having one, and even having that be the preferred one. But c'mon, you should at least have a simple compiler in C so you can use it without having a compiler already.)
21:30:37 <b_jonas> ais523: and also a good test
21:30:41 <ais523> many languages don't need a boostrap because compiling's not what they're for
21:30:54 <ais523> I was going to bring up INTERCAL as an example, but then I remembered CLC-INTERCAL
21:31:07 <b_jonas> there's a lot of errors, including hardware errors, that you can catch by getting a segfault during compiling gcc
21:31:08 <ais523> which is written in IACC, and the IACC compiler is also written in IACC
21:31:38 <ais523> and the distribution contains a precompiled bytecode version of the compiler so that you can get started
21:31:53 <ais523> I suspect CLC_INTERCAL does thst just because it can, though
21:31:59 <b_jonas> ghc actually scares me a lot
21:32:04 <b_jonas> because of the way it's built
21:32:09 <pikhq> Like, c'mon GHC. There should be a simple, generic Haskell compiler that can build you.
21:32:19 <ais523> doesn't GHC outright run regex on the output asm?
21:32:22 <ais523> or is that something else?
21:32:26 <pikhq> I don't care if it's shit or not, it should at least be good enough to get you a GHC.
21:32:30 <pikhq> ais523: It *used to*.
21:32:39 <pikhq> ais523: When it compiled by way of C.
21:32:52 <ais523> doesn't that lose like half the reason to compile via C?
21:32:54 <pikhq> Now it either code gens itself entirely or uses LLVM.
21:33:35 <olsner> there was an evil mangler and the satanic splitter, iirc both are/were some horrific perl mess
21:33:37 <b_jonas> ghc scares me in ways other than its build procedure too
21:33:44 * pikhq has a similar complaint with C++...
21:33:45 <b_jonas> there's very few things in ghc that don't scare me
21:33:57 <ais523> btw, ayacc's output is designed to be easy to optimize, so I've been looking at the output asm and it does seem to be optimized quite well
21:34:21 <b_jonas> but I think ghc is getting somewhat saner these days
21:34:52 <b_jonas> it won't get to the state where you can just build it without a haskell implementation ever of course
21:35:35 <b_jonas> I think it just works as a sane direct compiler these days, implemented in haskell
21:35:36 <ais523> pikhq: what language do you think Rust should be implemented in? C is clearly unthinkable, because the point of Rust is to replace C
21:35:42 <b_jonas> without any of the evil mangler or compile through C stuff
21:36:03 <pikhq> ais523: I *am 100% fine with* the reasonable, high quality implementation being bootstrapped.
21:36:04 <b_jonas> ais523: couldn't there be two implementations, one in C or C++ and one in rust?
21:36:35 <pikhq> The point is there should be at least a naive, inefficient but functional implementation that is suitable for bootstrapping said implementation.
21:36:38 <ais523> most compiler teams have enough problems maintaining just one implementation
21:37:02 <ais523> hmm, how easy would type erasure be for Rust?
21:37:09 <pikhq> You're not telling me a parser that outputs naive C is going to be that bad.
21:37:23 <b_jonas> ais523: no no, it'd be two teams: the gcc team maintains the C++ implementation, like they do for gccgo, and the rust enthusiasts maintain the rust implementation
21:38:11 <pikhq> And I do mean "naive"... When you're wanting something that's just sufficient for getting something going it doesn't have to be even faintly optimizing or even all that efficient.
21:38:43 <pikhq> Or even all that general if you don't mind writing your "real" compiler in a subset of the language...
21:39:30 <b_jonas> pikhq: yes, but a good compiler is complicated and hard to maintain, which is why gcc is written in C++ these days, not in, like, portable c89
21:39:48 <pikhq> I'm not asking for a good one.
21:39:53 <b_jonas> and C++ is very difficult to compile even naively
21:39:58 <pikhq> I'm asking for one that suffices to get your good one running.
21:40:02 <b_jonas> that's why they're separate languages really
21:40:15 <b_jonas> C is easy to compile if you don't want optimizations, C++ is very difficult
21:40:32 <pikhq> C++ is kinda an all-around bad language though.
21:40:55 <pikhq> Okay, so it's a spectacular esolang.
21:41:45 <pikhq> Stockholm syndrome much?
21:42:18 -!- AnotherTest has quit (Remote host closed the connection).
21:46:16 <b_jonas> ais523: how much does trying to support multiple restrict what kind of optimized code you can want to emit?
21:46:57 <ais523> the way it works is, some fragments don't exist in some languages, then you don't run the matching optimizations
21:47:03 <ais523> either because you can't or because you don't need to
21:47:23 -!- ProofTechnique has joined.
21:47:39 <ais523> for example, atm pointing multiple switch case labels at the same code works in C but not in Perl, it just copies the body
21:48:10 <b_jonas> what? why wouldn't it work in perl?
21:48:33 <ais523> not with the hash-of-subs thing, at least not as a literal
21:48:41 <b_jonas> but you don't have to use a hash literal
21:49:09 <b_jonas> a hash literal doesn't even have an advantage because I think it won't ever be optimized to creating the hash only once
21:49:13 -!- `^_^v has quit (Ping timeout: 256 seconds).
21:49:22 <b_jonas> you can just write my%h; $h{foo}=$h{bar}=sub{...};
21:50:14 <ais523> you have to use the hash literal for readability
21:50:28 <b_jonas> a hash literal is actually less readable
21:50:48 <b_jonas> $h{foo} = sub { ... }; is better because the sub bodies can be long and that way you see at the sub head what you're defining
21:53:10 <b_jonas> some people write hash literals for this but I just don't agree with that. it's just pointless. I think it's mostly beginners who don't understand what a hash is and think of it as a braced list syntactical thing rather than a structure you can indexed lookup and indexed assign efficiently
21:53:39 <b_jonas> (that clearly doesn't apply to you)
21:53:54 <b_jonas> $h{foo} = sub { ... }; is good syntax and readable
21:54:46 <b_jonas> ais523: anyway, even with a hash literal you can just say sub foo { ... }; our %h = { foo => \&foo, bar => \&foo, };
21:55:01 <ais523> yes, although then you have to name the block
21:55:13 <ais523> but the point is that these are short one-off things
21:55:25 <b_jonas> if they are then a hash literal might make sense
21:55:27 <ais523> they're the cases of a switch statement
21:55:35 <tswett> I'm shoving SLOBOL aside and creating a different language called SLOBOL.
21:55:36 <b_jonas> yes, those can be long blocks too
21:55:46 <ais523> they're mostly just a couple of function calls and a goto, some are even simpler than that, few are more complex
21:56:16 <b_jonas> anyway, even for simple blocks $h{foo} = sub { ... }; isn't too much of an overhead probably
21:56:30 <HackEgo> [wiki] [[Special:Log/move]] move * Tanner Swett * moved [[SLOBOL]] to [[SLOBOL (2005 language)]]: Shoving this aside to make a new language with the same name
21:56:30 <HackEgo> [wiki] [[Special:Log/move]] move * Tanner Swett * moved [[Talk:SLOBOL]] to [[Talk:SLOBOL (2005 language)]]: Shoving this aside to make a new language with the same name
21:56:43 <HackEgo> [wiki] [[4]] M http://esolangs.org/w/index.php?diff=42609&oldid=42600 * Vriskanon * (+115) Explained the mathematically inaccurate joke surrounding the language's origin
21:57:22 <b_jonas> the old and ugly interpreter in http://www.math.bme.hu/~ambrus/pu/psz-snapshot.tgz has one or two large code dispatcher hashes defined in the $h{foo} = sub { ... }; way,
21:57:45 <b_jonas> including the $op has which defines how each operation of the optree is implemented, mapping opcode names to subs that run them
21:58:23 <b_jonas> and two smaller code dispatch hashes that help parsing
21:59:13 <b_jonas> mind you, normally if something appears in that interpreter, then it's a bad idea code-style wise
21:59:36 <b_jonas> but I think provided you actually want hashes of code, then that's the best syntax
22:00:07 <b_jonas> so it's got that particular thing right
22:02:15 <ais523> what I actually want is a C-style switch statement
22:02:28 <b_jonas> ais523: yes, you're correct that such a thing is difficult in perl
22:02:58 <b_jonas> is this for the perl backend? or for the ayacc interpreter itself?
22:03:24 <ais523> basically because in a parser impl, you have to at least /try/ to aim for efficiency
22:03:41 <b_jonas> make it output xs code that calls back the actions in perl :-)
22:03:41 -!- variable has changed nick to trout.
22:04:14 <b_jonas> you have to try to aim for efficiency in a general parser generator
22:04:17 <b_jonas> not in all handwritten parsers
22:04:47 <ais523> I'm not 100% convinced that the parser it uses for reading yacc code is even O(n)
22:05:09 <b_jonas> ais523: is it at least O(n**(1+epsilon)) ?
22:05:55 <ais523> it's O(n**2) for finding the end of a %{%} or %union {} block, I think
22:06:17 <b_jonas> (or O(n**(1+epsilon)) on condition that the yacc code doesn't contain tokens (such as identifiers) that are longer than a constant)
22:07:26 <b_jonas> well, you'll certainly try ayacc on largish grammars, and if this doesn't cause a practical problem there then it's probably fine
22:08:03 <b_jonas> like, I dunno, the C-intercal grammar, the perl grammar, the ruby grammar, I dunno what else
22:08:41 <b_jonas> actually, compiling perl with ayacc and then running the perl testsuite might be a good test for ayacc
22:09:04 <ais523> I've never compiled Perl from source
22:10:28 <b_jonas> I might try to compile it with ayacc, though I can't guarantee I can do that
22:10:57 <b_jonas> I'll definitely be able compile the geo interpreter with ayacc, but that's a simple toy with very few tests so it doesn't help much
22:11:36 <ais523> b_jonas: atm the grammar has to be weird enough that it isn't optimized into something the backend can't handle
22:12:14 <b_jonas> in fact, maybe I should try to compile ruby with ayacc too
22:12:20 <b_jonas> but again I can't guarantee anything
22:12:32 <b_jonas> and it's not as good a test as with perl
22:13:01 <b_jonas> you will build c-intercal with ayacc, right?
22:13:21 <ais523> it won't become part of the build system permanently
22:13:59 -!- b_jonas has quit (Remote host closed the connection).
22:16:44 -!- TieSoul_ has joined.
22:19:31 <HackEgo> [wiki] [[Element]] http://esolangs.org/w/index.php?diff=42610&oldid=42604 * Phi * (+735)
22:20:09 <HackEgo> [wiki] [[SLOBOL]] http://esolangs.org/w/index.php?diff=42611&oldid=42606 * Tanner Swett * (+1254) New language
22:20:34 -!- TieSoul has quit (Ping timeout: 248 seconds).
22:20:53 <tswett> Can someone give me admin access on the wiki, thanks.
22:21:40 <ais523> tswett: possibly, what do you want it for?
22:21:56 <tswett> Deleting [[Talk:SLOBOL]].
22:21:59 <ais523> actually let me check I have the perms first
22:22:14 <ais523> I can just delete that for you
22:22:25 <tswett> I'll just edit it, actually.
22:22:35 <ais523> yeah, that'd probably be easier
22:22:39 <HackEgo> [wiki] [[Talk:SLOBOL]] http://esolangs.org/w/index.php?diff=42612&oldid=42608 * Tanner Swett * (+0) Change redirect to a bit of text saying "see also"
22:22:57 <tswett> I had admin access eight or so years ago, and surely I'm only more mature now.
22:23:32 <ais523> seems I do have the perms, but it's probably worth talking it over with the other admins first; there's no rush
22:23:55 <tswett> Here's my campaign speech:
22:24:01 <tswett> "Feel free to give me admin access if you want."
22:24:06 <ais523> tswett: you actually already do have admin access, just on another account
22:24:07 <FireFly> You people change nicks too often
22:24:15 <ais523> at least, I'm assuming ihope127 is yours
22:24:26 <tswett> ihope127 is mine indeed.
22:24:46 <tswett> I don't use it any more and I don't remember the password. I could reset the password if I wanted, but I won't.
22:25:10 <ais523> don't have an email set, so I can't verify it like that
22:25:48 <ais523> I guess the problem is that when it comes to wiki administration, I slip into Wikipedia mode
22:26:25 <ais523> and am thinking "I'd be happy to move admin perms between accounts, but how do I know that the person who's editing as Tanner Swett and is on IRC as tswett right now is formerly-ihope127 and not an imposter"
22:29:03 <ais523> <oerjan> ok so tswett is not ihope127 but elliott is me. got it.
22:29:09 <ais523> the log history is looking bad ;-)
22:29:13 <tswett> Would you believe me if I sent you an email from ihope127@gmail.com and/or received an email there?
22:30:10 <ais523> it's a case of believing you but being unsure how much verification I need
22:30:53 <ais523> tswett: OK, I've verified that ihope127+w@gmail.com is ihope127
22:31:25 -!- Patashu has joined.
22:31:29 <ais523> so yes, we can do this by email
22:31:37 <ais523> I'll send, From: addresses can be forged
22:33:57 <ais523> it may well end up in with other B Nomic stuff
22:36:19 <tswett> Did you get an autoresponse instructing you to use a different contact method?
22:36:55 <HackEgo> [wiki] [[Special:Log/rights]] rights * Ais523 * changed group membership for User:Ihope127 from sysop to (none): Moving permissions to a different account, via IRC request (I've verified account ownership)
22:37:15 <HackEgo> [wiki] [[Special:Log/rights]] rights * Ais523 * changed group membership for User:Tanner Swett from (none) to sysop: Moving permissions to a different account, via IRC request (I've verified account ownership)
22:37:43 <ais523> I did now, it was a little slow
22:42:36 <elliott> that's not proof, tswett could have emailed that address and seen that it gives such an autoresponse prior
22:42:51 <tswett> But that's not what the verification was.
22:43:09 <tswett> The verification was that I knew the content of an email sent to that address.
22:44:09 <int-e> Advanced Account Accountability
22:44:20 -!- Tritonio has joined.
22:44:38 <ais523> elliott: I sent a randomly generated string to the address, tswett sent it back by IRC PM
22:45:12 <elliott> how do you know he didn't just intercept it
22:45:23 <elliott> along its path to the destination
22:45:32 <int-e> There are no proofs.
22:45:45 <ais523> wiki is http, so someone who could do that could do the same to an admin password
22:45:48 <int-e> ais523 might be living in a simulation for all he knows. (if ais523 exists...)
22:45:49 <ais523> and take over an admin account that way
22:46:58 <FireFly> elliott: it's fizzie's domain that rot14's to 'nsa', not tswett's
22:47:30 <ais523> what does it say about me that I can reverse rot14 in my head? (albeit slowly)
22:47:52 -!- trout has quit (Ping timeout: 264 seconds).
22:48:10 <elliott> ais523: mail is more susceptible, though
22:48:36 <elliott> I mean compared to being an AS or something
22:48:49 <ais523> elliott: OK, so what you do instead is, you send a password reset for an admin
22:49:12 <elliott> ais523: you don't get to choose either address there, though
22:49:17 <elliott> tswett got to choose the destination address here
22:49:39 <ais523> well, no, he had to pick an address that verifiably belonged to ihope127
22:49:43 <int-e> ais523: lbh pna ernq ebg guvegrra syhragyl?
22:51:01 <int-e> Of course not, rot14 is too uncommon.
22:51:15 <ais523> oh, if it's rot13, the second word is "can"
22:52:20 <ais523> "you can read rot thirteen fluently?"
22:52:25 <ais523> nah, still pretty slow
22:52:37 <ais523> would have been faster to just use a rot13 decoder
22:53:02 <ais523> but given the subject of the conversation, I pretty much had to do it manually
22:53:03 <int-e> (tbf I *did* use a rot13 encoder)
22:53:15 <ais523> encoding is much harder than decoding, if you're doing it manually
22:53:36 <int-e> egb13 is the only thing I recognize reliably.
22:53:41 <ais523> because you can guess words from a partial decoding
22:53:50 <int-e> (note the swapped letters ;) )
22:53:56 <ais523> 14 is harder than 12 because it's not trivially reversible
22:54:13 <ais523> well, rot26 and rot52, as are sometimes used on Slashdot, are easiest
22:54:39 <int-e> aka double-rot-13 and quadruple-rot-13?
23:03:12 <FireFly> You'd think it'd be more secure
23:03:23 <tswett> Quadruple rot13 is actually less secure than triple rot13.
23:03:47 -!- callforjudgement has joined.
23:04:00 -!- ais523 has quit (Remote host closed the connection).
23:04:09 <tswett> rot13 is a so-called... uh, what's it called.
23:04:18 <tswett> Characteristic-2 automorphism, I think it's called?
23:04:24 -!- callforjudgement has changed nick to ais523.
23:04:35 <tswett> Which results in cancellative properties of iterations which are multiples of 2.
23:05:27 <int-e> tswett: https://en.wikipedia.org/wiki/Involution_%28mathematics%29
23:05:50 <tswett> It's not just a -tion, it's an -ism!
23:05:54 <tswett> ...in the category of sets.
23:06:25 <int-e> I don't like all the abstract nonsense.
23:07:25 <HackEgo> In category theory, category theory is a theory in the category of theories.
23:07:39 <ais523> theories form a category?
23:08:00 <ais523> I can make them into a discrete category
23:08:07 <int-e> Oh, of course. There's work on embedding logics (theories) in other logics
23:08:09 <ais523> but I can't see an obvious way to add extra structure
23:08:18 <tswett> A morphism from a theory T to a theory U consists of a function from terms in T to terms in U, and a function from models of U to models of T, which are adjoint.
23:08:46 <olsner> is that actually true? I was just putting words together to make it look good
23:08:52 <tswett> "or something like that"
23:10:05 <int-e> thanks, that helped
23:11:39 <tswett> "Adjoint" here means that given a term in T and a model of U, interpreting the term in T in the image of the model of U gives the same result as interpreting the image of the term in T in the model of U.
23:17:57 <ais523> olsner: it's category theory, it's hard to find something it doesn't apply to
23:18:06 <ais523> a few years in my research, I found something that wasn't a category
23:18:11 <ais523> and everyone was very surprised
23:28:01 -!- TieSoul_ has quit (Quit: No Ping reply in 180 seconds.).
23:28:52 -!- Sprocklem has quit (Ping timeout: 250 seconds).
23:29:25 -!- TieSoul has joined.
23:33:58 <tswett> Legend tells of categories that can't be represented as concrete categories.
23:35:10 <tswett> So, let's see if we can write a program in SLOBOL.
23:37:15 -!- ais523 has quit.
23:37:26 -!- ais523 has joined.
23:44:12 <tswett> You can probably do AND and OR, aye?
23:44:26 <tswett> This group is alive if and only if this group and/or this group is alive.
23:49:27 <FireFly> That sounds more like go than programming
23:49:41 -!- Frooxius has joined.
23:51:36 <tswett> Simpler problem: make it so that group B is alive iff group A is alive.
23:53:58 -!- Sgeo has quit (Quit: Leaving).
23:55:31 -!- Sgeo has joined.
00:07:34 <tswett> So far I haven't even thought how to do that.
00:07:43 <tswett> Group A gives liberties to group B but not vice versa?
00:09:01 -!- oerjan has joined.
00:11:19 <int-e> tswett: you could make it simple: have two equal, unsettled groups.
00:13:03 <int-e> Hmm. You can read off an answer (who wins), but how do you do input... do you have free intersections where optionally a stone can be placed before the program starts?
00:13:59 <int-e> (in which case you might be able to follow the ladders-in-PSPACE approach by encoding the input as ladder breakers)
00:14:04 <tswett> The program is the input.
00:14:13 <int-e> that's not an input
00:14:22 <int-e> that's just an unwieldy encoding of the final score
00:15:25 <int-e> that if you have several optimal moves, the input could be in the choice.
00:16:45 <int-e> (except that this means that the input will never affect the final score ... so that's not very useful unless you encode the output in a different way.)
00:17:06 <zzo38> How marge does a hexagonal cell on a board need to be if a Slugterra figure is going to fit in such a cell?
00:17:52 -!- Tritonio has quit (Remote host closed the connection).
00:19:09 <zzo38> Also how many cells would you need? And then you can multiply it and figure out how big is the board. (I think it would need to be large enough that two figures can stand on adjacent cells, isn't it?)
00:23:13 -!- ais523 has quit.
00:25:37 <int-e> tswett: I guess even with a fixed position you could try stuff like "in this position, white wins if and only if chess is a first player win"
00:28:42 <lambdabot> ‘.’ (imported from Data.Function),
00:30:12 <int-e> (I'm trying to understand https://github.com/lambdabot/lambdabot/issues/119 )
00:54:04 -!- t3chstep has joined.
00:54:25 -!- t3chstep has left.
01:04:06 <oerjan> int-e: i think the traditional, but still nonstandard name is (.:) ?
01:04:28 <int-e> oerjan: right, I'd have recognized .:
01:04:43 <lambdabot> ‘.’ (imported from Data.Function),
01:05:13 <int-e> I think lambdabot forgot about it when Cale stopped running it.
01:05:57 <lambdabot> The operator ‘<>’ [infixr 6] of a section
01:05:57 <lambdabot> must have lower precedence than that of the operand,
01:06:00 <int-e> But I may be misremembering. I clearly recall the (.) = fmap thing, however.
01:06:13 <oerjan> yeah a lot of that was removed?
01:06:54 <lambdabot> Foldable t => (a -> b -> b) -> b -> t a -> b
01:09:22 <zzo38> I would want the . to be the Category.. instead
01:10:56 <int-e> lambdabot is using the (.) that's exported by the Prelude.
01:11:14 <zzo38> Yes I can see that
01:11:23 <int-e> which has so far resisted being generalized
01:19:25 -!- Phantom__Hoover has quit (Read error: Connection reset by peer).
01:32:21 -!- variable has joined.
01:58:42 -!- bb010g has quit (Quit: Connection closed for inactivity).
02:02:53 -!- GeekDude has quit (Quit: {{{}}{{{}}{{}}}{{}}} (www.adiirc.com)).
02:16:44 -!- lleu has quit (Read error: Connection reset by peer).
02:47:48 -!- hjulle has quit (Ping timeout: 246 seconds).
02:51:16 -!- ProofTechnique has quit (Quit: ZNC - http://znc.in).
03:14:27 <oerjan> int-e: ouch, i had a suspicion that would affect the locket
03:19:10 -!- MDude has joined.
03:56:17 -!- J_Arcane has quit (Read error: Connection reset by peer).
04:17:33 -!- augur has quit (Quit: Leaving...).
04:19:07 -!- magician has joined.
04:22:21 -!- Guest3780 has quit (Ping timeout: 245 seconds).
04:22:21 -!- magician has changed nick to Guest3780.
04:35:49 -!- Sgeo has quit (Quit: Leaving).
04:36:12 -!- Sgeo has joined.
04:53:01 -!- Frooxius has quit (Quit: *bubbles away*).
05:00:38 -!- J_Arcane has joined.
05:33:28 -!- esowiki has joined.
05:33:28 -!- glogbot has joined.
05:33:32 -!- esowiki has joined.
05:33:32 -!- esowiki has joined.
06:18:52 <oerjan> @tell pikhq <pikhq> ais523: It *used to*. <-- they abolished The Evil Mangler, then had to make a new mangler for the LLVM backend, although it's in haskell rather than perl.
06:26:16 -!- MDude has changed nick to MDream.
06:43:18 -!- variable has quit (Ping timeout: 240 seconds).
06:55:31 <zzo38> How commonly in a pinball game will you manage to recover the ball even when it is about to fall off and the flipper cannot hit it?
06:56:14 <zzo38> I am aware of that
06:56:29 <izabera> people don't play pinball games in 2015 ._.
06:56:57 <zzo38> No, some people still do, sometimes with real pinball machine but also by a simulation on the computer.
06:57:01 <oerjan> izabera: ARE YOU SURE YOU'RE IN THE RIGHT CHANNEL
06:58:01 <Jafet> Kids these days with the violent war videogames
06:58:05 <zzo38> The Windows version or the DOS version?
06:58:31 <izabera> http://www.minesweeper.info/wiki/Arbiter
07:01:07 <zzo38> People still play whist in 2015 (although bridge is far more popular), and people still program for a Famicom in 2015, too. See?
07:03:02 <shachaf> zzo38: i played whist in 2014
07:05:40 <zzo38> Probably also in 1999 bridge was more popular, although whist is still played too. (Actually I don't think I played whist this year either, although I did in 2014)
07:05:43 <oerjan> they tried to get me to play bridge in 2000
07:07:20 <shachaf> i had a bridge class at school
07:07:31 <shachaf> we went to bridge tournaments and i won bridge medals
07:07:57 <quintopia> bridge day is one of the best days of the year, and i have yet to go :(
07:10:05 -!- jameseb has quit (Ping timeout: 264 seconds).
07:10:12 -!- jameseb has joined.
07:10:24 -!- barrucadu has quit (Ping timeout: 252 seconds).
07:10:55 -!- Taneb has quit (Ping timeout: 265 seconds).
07:11:31 -!- barrucadu has joined.
07:11:46 -!- Taneb has joined.
07:13:22 <zzo38> They have one section of bridge cards in a newspaper too.
07:18:38 <zzo38> I prefer chess problems but I don't see that much in newspaper (I did see it in one newspaper though).
07:20:24 <oerjan> @tell ais523 <ais523> wiki is http, so someone who could do that could do the same to an admin password <-- it does support https hth
07:22:28 <izabera> do you think it's ok to say that a bignum library supports arbitrary large numbers if actually it only supports numbers up to 2^63-1 digits?
07:23:40 <zzo38> But, if it is a kind of implementation detail of the type and you can fix it easily, then that is not a problem; that is already a lot of digits.
07:23:42 <oerjan> maybe if the 2^63-1 isn't hardcoded
07:24:22 <oerjan> it's > all computer memory in the world, anyway.
07:24:24 -!- Sgeo has quit (Quit: Leaving).
07:24:46 -!- Sgeo has joined.
07:25:58 <oerjan> hm we may have passed that
07:26:03 <izabera> `` printf "%'f" "$((2**63-1))"
07:26:06 -!- Sgeo has quit (Client Quit).
07:26:36 <HackEgo> 9,223,372,036,854,775,807.000000
07:26:37 -!- Sgeo has joined.
07:29:37 <oerjan> "As of 2013, the World Wide Web is estimated to have reached 4 zettabytes."
07:33:05 -!- Sgeo has quit (Quit: Leaving).
07:33:41 -!- Sgeo has joined.
07:51:21 -!- Tritonio has joined.
07:56:41 <zzo38> I have made up several kind of Hero Heart levels with things that have not been done before: in one level you have to run out of time, in other you have to throw a grenade into the water (this wastes the grenade and displays a message "That was a waste of a good grenade! Who taught you how to throw a grenade?"), in another you have to light bombs solely to decrease the number of matches in your inventory...
07:59:09 <zzo38> In one level you have to destroy hearts with explosives (doing so results in a message "Now that you have so smartly blown up that heart, it will be impossible to solve this level." and you can no longer turn the exit green by collecting all of the hearts, because the one that has been blown up is one you didn't collect).
08:00:50 <zzo38> And in another level, using only the pieces that are included with the game by default, make a puzzle that is not solvable unless "Explain death" option is turned off (it is on by default)! These options are not supposed to be allowed to affect the solution of the puzzle, and yet it does even without programming in my own pieces.
08:02:38 <zzo38> Is that a strange kind of game?
08:02:54 <quintopia> the one where you can't win because you have to explode the heart sounds dumb though
08:03:12 <quintopia> why make impossible to solve puzzles?
08:03:41 <zzo38> Actually I made a puzzle where you can win despite (actually because of) that; the message is a lie in this case.
08:03:58 <zzo38> The message is also the important part (you actually can't win that level without the message)!
08:05:54 <zzo38> That message was already there; I didn't change the message, I just took advantage of it.
08:06:04 <quintopia> how the heck do messages appearing change the winningness of a level?
08:08:36 -!- Guest3780 has quit (Ping timeout: 256 seconds).
08:08:49 <zzo38> The game engine can display only one message at a time. If you step on a quiz box, you must answer the question (a multiple choice question; sometimes there is no correct answer, although usually there is one). If you answer correctly, you move south. If you do not answer correctly, you move north. Do you start to see where I am getting at with this?
08:10:47 <quintopia> yeah. i guess the message from the exploding heart interrupts the quiz game, causing you to get the answer correct and pushing you into the next area
08:10:57 <quintopia> even though there is no correct answer
08:11:27 <zzo38> That's close, but not quite. This particular quiz does have a correct answer.
08:12:09 <quintopia> so maybe you are supposed to go east instead? and the only way to go east is break the quiz?
08:12:49 <quintopia> what about the explain death thing?
08:13:26 <quintopia> do the puzzles in this game allow you to put like signs with hints on them?
08:13:48 <zzo38> That is in a level with two heroes; it also contains a quiz box. And yes the puzzles do allow you to put notes with hints (or any other message) on them.
08:14:03 <quintopia> because i think the hint for that one should be "when you are told you cannot win, you have already won"
08:15:04 <zzo38> Each level can also have intro text; the intro text for that puzzle with exploding hearts simply says "Now that you have so smartly..."
08:19:35 <zzo38> The level is fixed such that one of the heroes will inevitably run into a laser beam and die when another one is about to reach the exit by stepping on a quiz. The explain death is also a message like the others; whether or not it appears, the level starts over before your next turn. If the explain death is turned off then you can answer the question and move directly into the exit before you get another turn.
08:21:39 <zzo38> In another level that (like this one) isn't supposed to work, it takes advantage of a different bug in the game engine where the escape key resets the level inside of a loop which fails to reset the BlockHero flag and therefore other objects might move before you get a turn (which isn't supposed to happen).
08:23:11 <zzo38> (These are the only two levels that do things that aren't supposed to be possible; the others, such as the exploding hearts and so on, I consider legitimate.)
08:23:45 <zzo38> Another unusual feature is that the hero is completely invincible to getting killed by anything while standing on an exit. (Normally once you step on an exit you have won, but this is not the case if you stepped on it while stealthy.)
08:23:53 <quintopia> yeah i can't see how anyone who hasn't studied the game engine could solve that last one
08:24:43 -!- Guest3780 has joined.
08:28:44 <zzo38> Source-codes for all of the objects in the game is available, although not for the game engine itself (although the help file does contain pseudocodes for parts of the game engine). Nevertheless I have managed to figure out nearly all of it (except for the file format) closely enough that I could probably write a clone of the game engine.
08:29:33 -!- zadock has joined.
08:32:57 <zzo38> The gift box works as such: When created, it checks if the object it contains is a heart; if so, it increments the heart count. When properly assembled, it creates the object stored inside and destroys itself. When destroyed, if the object it contains is a heart and there is an object of the same class in its position, the heart count is decremented. Do you see anything a bit unusual about this? I did, and took advantage of it.
08:40:54 -!- CADD has quit (Ping timeout: 256 seconds).
08:41:12 <zzo38> It is a counter that keeps track of how many hearts you need to collect. A heart increments that count when it is created and decrements it when it is destroyed (such as by collecting it; if hit by an explosive, the explosive objects increments it again and displays the "Now that you have so smartly..." message).
08:42:16 <zzo38> And there are a *lot* more tricks.
08:42:29 -!- oerjan has quit (Quit: leaving).
08:42:57 <zzo38> Other people have used many tricks, but not quite like I have done.
08:44:04 <quintopia> so there must be a trick wehereby you assemble a box on top of an existing heart or something like that?
08:45:46 <zzo38> quintopia: Yes; not with most hearts, but one kind of heart that a gift box can be pushed on top of is an arrow heart. And you don't need to assemble it (assembling a gift box means pushing four pieces together into a 2x2 square, one of the pieces having a bow); the devil can destroy the gift box without destroying the arrow heart that was already there.
08:48:38 <zzo38> Yes; the program only cares whether or not there is a heart of the same class at the position where the gift box got destroyed, not whether or not it is the same one the gift box created or who destroyed the gift box (normally it destroys itself once the pieces are assembled correctly).
08:53:37 <zzo38> An exit sets its height too high for the player to step on while it is red, and reduces its height when green; therefore you can (normally) only step on the exit while it is green. However, once the hero actually steps on the exit, it doesn't care what color it is; you win once the MSG_ARRIVED event finds that the hero is standing on it.
08:54:41 <oren> oerjan: even if there are 2^64 bytes on the internet, most of that is stored on disks or solid state. haveing 2^64 bytes of RAM is probably harder
08:55:20 <zzo38> Therefore, teleporting onto a red exit also counts as winning; stepping on it while you are flying counts as winning too. However, stepping on it (regardless of color) while you are stealthy does not count as a win; you just stand there (and the game continues; notice what I said above about the hero being indestructible while standing on an exit!)
09:00:46 <Sgeo> https://gist.github.com/Sgeo/c42c4c2b5bcdf8c91d5a
09:05:36 <zzo38> How do you program the syntax highlighting on Aringa pastebin? It looks like it only has one kind and you can't change it (but it does have the nice feature that it automatically turns off syntax highlighting if you download using the command-line)
09:11:22 -!- augur has joined.
09:18:25 <izabera> zzo38: aringa is free software, the syntax highlighting is pretty dumb but it kind of works for most languages https://github.com/izabera/aringa/blob/master/hl.php
09:19:21 <izabera> and it redirects the requests according to the user agent https://github.com/izabera/aringa/blob/master/.htaccess
09:21:23 <zzo38> I know, I looked at the code; better probably would be to have an extra parameter to tell what syntax highlighting it is when you post a file. This parameter, as well as expiry, should probably both be documented and be available on the form. (I have written a IRC syntax highlighter in PHP, although it outputs ANSI escapes and not HTML.)
09:22:38 <izabera> that would add too much complexity... i don't want to use a syntax highlighter that's 20x as big as the rest of the code
09:22:51 -!- Phantom_Hoover has joined.
09:23:12 <izabera> the expire parameter will be eventually added to the form
09:23:34 <izabera> and by eventually i mean as soon as possible but _not_now_ because i don't wanna <.<
09:30:11 -!- TieSoul_ has joined.
09:33:12 <Lymia> @pl f x = g x (tail x)
09:33:33 <lambdabot> Maybe you meant: tell thank you thanks thesaurus thx tic-tac-toe ticker time todo todo-add todo-delete type v @ ? .
09:33:40 <lambdabot> Monad m => m (a -> b) -> m a -> m b
09:33:45 -!- TieSoul has quit (Ping timeout: 245 seconds).
09:35:09 <Lymia> @type (\fm -> \am -> fm >>= (\f -> am >>= (\a -> return $ f a)))
09:35:10 <lambdabot> Monad m => m (a -> r) -> m a -> m r
09:35:50 -!- Vorpal has quit (Ping timeout: 255 seconds).
09:35:56 <lambdabot> <unknown>.hs: 1: 1:Parse error: EOF
09:36:06 <lambdabot> Local time for izabera is Sat, 18 Apr 2015 11:37:36 +0200
09:36:10 <lambdabot> Local time for Sgeo is Sat Apr 18 05:37:47
09:36:20 <lambdabot> Local time for Lymia is Go buy a watch or something. -w-
09:36:36 <lambdabot> Local time for izabera is Sat, 18 Apr 2015 11:38:07 +0200
09:36:54 <lambdabot> Local time for Sgeo is Sat Apr 18 05:38:30
09:38:18 <lambdabot> Perhaps you meant one of these: ‘e’ (imported from Debug.SimpleReflect), ‘_4...
09:38:29 <lambdabot> arising from a use of ‘myquickcheck’ The type variable ‘prop0’ is ambiguous ...
09:45:10 -!- Sgeo has quit (Read error: Connection reset by peer).
09:52:00 <zzo38> (This question is inspired by something I dreamt of) How large does a hexagonal cell need to be in order that Slugterra figures can stand on adjacent cells?
09:53:48 <Lymia> @type (>>=) (\x -> x + 1)
09:56:17 -!- Sgeo has joined.
09:59:00 -!- oren has quit (Quit: Lost terminal).
10:06:47 <lambdabot> ‘fmap’ (imported from Control.Monad.Writer),
10:06:55 <lambdabot> Functor f => (a -> b) -> f a -> f b
10:07:14 <Lymia> @type fmap :: (Monad m) => (a -> b) -> m a -> m b
10:07:42 <Lymia> @type (\a b -> fmap a b) :: (Monad m) => (a -> b) -> m a -> m b
10:07:48 <Lymia> > (\a b -> fmap a b) :: (Monad m) => (a -> b) -> m a -> m b
10:07:49 <lambdabot> (maybe you haven't applied enough arguments to a function?)
10:07:49 <lambdabot> arising from a use of ‘show_M784233406531567547924610’
10:08:00 <Lymia> > (\a -> \b -> fmap a b) :: (Monad m) => (a -> b) -> m a -> m b
10:08:01 <lambdabot> (maybe you haven't applied enough arguments to a function?)
10:08:01 <lambdabot> arising from a use of ‘show_M297169522764633571424620’
10:08:45 <izabera> https://40.media.tumblr.com/1448b395c61da8f6aead492ef204bcdf/tumblr_mlowa2l8M81rrax6ao1_500.jpg
10:30:10 -!- lleu has joined.
10:38:15 -!- roasted42 has joined.
10:38:18 -!- roasted42 has quit (Changing host).
10:38:18 -!- roasted42 has joined.
10:38:18 -!- roasted42 has changed nick to TheM4ch1n3.
11:12:22 -!- hjulle has joined.
11:14:01 -!- Guest3780 has quit (Ping timeout: 245 seconds).
11:28:37 <Taneb> I wonder if left-handedness is more common in cultures that write right-to-left
11:37:14 <Jafet> https://en.wikipedia.org/wiki/Handedness#Combat
11:40:44 <Taneb> Jafet, my reasoning is that, when writing left-to-right, left-handed people often smudge the ink
11:43:52 <Taneb> I don't really know
12:12:52 -!- mhi^ has quit (Changing host).
12:12:53 -!- mhi^ has joined.
13:08:47 -!- rdococ has joined.
13:17:34 <TieSoul_> http://www.reddit.com/r/dailyprogrammer/comments/32o5je/20150415_challenge_210_intermediate_drawing_a/cqgg67z :D
13:20:39 <izabera> can you help me debug something ;-;
13:20:54 <izabera> i don't know what's going wrong ;-;
13:26:56 -!- TieSoul_ has changed nick to TieSoul.
13:28:42 -!- SopaXorzTaker has joined.
13:41:32 -!- Patashu has quit (Ping timeout: 255 seconds).
13:44:19 -!- TheM4ch1n3 has quit (Ping timeout: 248 seconds).
13:50:37 -!- boily has joined.
14:02:49 -!- GeekDude has joined.
14:16:19 -!- Johnnie has joined.
14:19:52 <Johnnie> Hey elliott. I've been playing around with an idea for an esolang.
14:20:43 <Johnnie> It's derivative, so I'll put it on the chopping block and I'll see what you guys think.
14:21:43 <Johnnie> Using 6908E Assemby as the basis (6908E - Color Computer), represent the language using color blocks.
14:22:43 <Johnnie> No comment tags, addresses aren't used, and labels are represented by the background color.
14:25:53 <Johnnie> I'm coming up with an example of an idea I'm pondering.
14:27:47 <Johnnie> Ah, here we are..."STB -1,X" would come out with five blocks of color (one block representing STB, and one block each representing "-", "1", "," and "X")
14:28:04 <boily> ponder the example. create a page on the wiki. consult the fungot.
14:28:05 <fungot> boily: hey, i have unfocused, but at the end, to ask me what my favourite suffix.
14:29:40 <Johnnie> The key is all characters and background labels are represented by the internet color map (from "000000" to "FFFFFF") and to make it that much more difficult...say have the alphabet be represented by slight variations of the same color (from 00FFFF to 29FFFF)
14:30:47 <Johnnie> I just like the idea of representing the Color Computer assembly language using colors.
14:30:56 <Johnnie> I'll get to work on the page, then.
14:32:20 -!- Johnnie has quit (Quit: Page closed).
14:33:14 <Taneb> He quit before I read the conversation and instantly thought of ColorForth
15:00:15 -!- MDream has changed nick to MDude.
15:05:25 <MDude> http://www.deviantart.com/art/Dog-and-hedgehog-rough-sketch-525720474
15:11:03 -!- variable has joined.
15:11:14 -!- variable has quit (Remote host closed the connection).
15:11:34 -!- variable has joined.
15:30:42 -!- MDude has quit (Ping timeout: 245 seconds).
15:36:20 -!- boily has quit (Quit: NESTED CHICKEN).
15:43:53 -!- hjulle has quit (Ping timeout: 250 seconds).
15:46:21 -!- MDude has joined.
15:56:48 <int-e> . o O ( the hedgehog may never be buggered at all )
16:01:56 <MDude> But it may snuggle doggies: http://www.deviantart.com/art/Dog-and-hedgehog-rough-sketch-525720474
16:03:13 <int-e> MDude: I saw that, that's why I mentioned it.
16:04:36 <MDude> Wait, did I link this here?
16:05:00 <MDude> That would I didn't in the channel I thought I did link it, probably.
16:09:45 -!- SopaXorzTaker has quit (Remote host closed the connection).
16:09:55 -!- zadock has quit (Quit: Leaving).
16:20:06 -!- GeekDude has quit (Quit: {{{}}{{{}}{{}}}{{}}} (www.adiirc.com)).
16:26:26 -!- mitchs has quit (Quit: mitchs).
16:33:05 -!- SopaXorzTaker has joined.
16:41:13 <Melvar> int-e: Doesn’t Nanny Ogg sing that when drunk or something?
16:44:43 -!- Phantom__Hoover has joined.
16:46:07 -!- Phantom_Hoover has quit (Ping timeout: 250 seconds).
16:48:19 <int-e> Melvar: yes. and some fans have created actual lyrics
16:48:35 <Melvar> Wait, I thought there were some?
16:49:27 <int-e> well, the books onlg have fragments
16:56:19 <Melvar> Bleh, can’t find the bit I remembered.
17:02:30 <int-e> I don't know more than http://wiki.lspace.org/mediawiki/Hedgehog_song
17:04:32 -!- Sprocklem has joined.
17:13:58 -!- oerjan has joined.
17:24:23 <Melvar> Oh right, that was also a thing, “A Wizard’s Staff Has a Knob On the End”.
17:27:02 <Melvar> Hahahah, this version includes “The lemurs cry "Frink!" as a coy mating call”.
17:33:41 <zzo38> My brother said the weight of the Mewtwo that they added to the Smash Brothers recently is a slightly too low weight, and that if disable is countered it should only block the attack and not fight back too.
17:35:29 -!- Tritonio_ has joined.
17:37:28 -!- Tritonio has quit (Ping timeout: 272 seconds).
17:39:55 -!- Tritonio_ has changed nick to Tritonio.
18:15:41 <int-e> oerjan: I'm slightly disappointed. I had expected Agatha to be a a fugue state and therefore immune. Oh well, let's see how this turns out.
18:20:29 <int-e> On the other hand, why would the Foglios put three major sparks in the same place. Maybe Othar will turn up too.
18:21:27 <oerjan> i've been assuming othar is in mechanicsburg
18:21:48 <oerjan> i certainly didn't see him leave
18:24:11 <oerjan> int-e: why would she be immune, lucrezia showed up immediately the last two times the locket was removed.
18:24:21 <int-e> actually I may be confusing heterodyning (the music stuff) and the fugue state (a general spark thing)
18:24:54 <oerjan> i don't remember hearing about the fugue state before.
18:25:40 <oerjan> and yes, the music disabled lucrezia before
18:25:51 <int-e> but I don't want to browse the archives. at some point after Klaus was wasped there was a discussion about the effect of wasps on someone in a permanent fugue state (which Klaus, I gathered, is).
18:26:21 <oerjan> i see, i don't remember that
18:28:46 * oerjan looks at http://girlgenius.wikia.com/wiki/The_madness_place instead
18:29:15 -!- Phantom_Hoover has joined.
18:29:38 <int-e> oerjan: it was mentioned here: http://www.girlgeniusonline.com/comic.php?date=20120720
18:29:43 <oerjan> i have not paid enough attention to these font changes...
18:30:53 -!- Phantom__Hoover has quit (Ping timeout: 255 seconds).
18:33:40 <int-e> (I got lucky, I found a forum post about this on the same day. I'd really have no clue how to find this (one-off, detached from the story line) page otherwise.)
18:36:12 <oerjan> int-e: it wasn't "permanent" fugue state, anyway. and klaus didn't use to be in such a state all the time, see just the _next_ page after that...
18:39:20 <int-e> Yeah I read too much into that.
18:44:27 <oerjan> "The Madness Place apparently can be forced by methods of mind control, as the "measures" that Baron Wulfenbach inflicted on his son Gil to prevent manipulation by The Other seem to have locked him in a continuous madness place."
18:44:58 <oerjan> perhaps that's what came out of that fugue state question
18:47:53 -!- Sgeo has quit (Quit: Leaving).
18:48:16 -!- Sgeo has joined.
18:48:17 <int-e> Oh well, the story has so many loose ends, who knows what's even relevant now...
18:51:53 <oerjan> gil _knows_ about agatha's locket, zeetha told him.
18:51:54 <int-e> is the time traveling Agatha Agatha or Lucrecia?
18:53:18 <oerjan> that's a good question. i recall one of the characters used "mistress" in scare quotes, which i interpreted as them trying to fool the geisterdamen into _thinking_ they were lucrezia's servants.
18:53:21 <int-e> Just a thought (and I'm leaning towards Agatha based on her company.)
18:56:40 <oerjan> it was the one who looked liked gil
18:56:58 -!- SopaXorzTaker has quit (Ping timeout: 246 seconds).
18:58:50 <oerjan> anyway moloch was there, so they pretty much _have_ to rescue mechanicsburg first...
18:59:35 <oerjan> which means they may rescue tarvek, and have a good chance of removing lucrezia permanently
19:03:02 <oerjan> of course tarvek might also die. narratively, unless they _actually_ go for the "she takes both" option, either gil or tarvek pretty much have to. of course they _could_ subvert that.
19:05:08 <oerjan> i seem to be procrastinating eating again ->
19:20:29 <int-e> Cute. http://girlgenius.wikia.com/wiki/Book_of_DuPree "How [Klaus] convinces Dupree to take time away from her busy schedule of killing, maiming, and torturing others is a mystery."
19:24:47 <oerjan> int-e: one thing i've been wondering and which we'll soon find answered is whether the copy of klaus in gil's head is still wasped...
19:27:33 -!- variable has quit (Quit: 1 found in /dev/zero).
19:27:56 -!- variable has joined.
19:28:13 -!- variable has changed nick to trout.
19:39:07 <zzo38> What does "Invalid Address specified to RtlReAllocateHeap( 003D0000, 003D44A0 )" mean?
19:44:26 <shachaf> It probably means you were trying to reallocate an invalid address.
19:45:30 <shachaf> seems that RtlReAllocateHeap is the same as HeapReAlloc hth
19:58:46 -!- rdococ has quit (Quit: Page closed).
20:04:34 -!- Frooxius has joined.
20:13:14 <zzo38> Now there is some other error, I don't know what it is because it doesn't occur in the debugger; it also doesn't occur if the input file is included rather than coming from stdin (although it doesn't care whether the stdin comes from the keyboard or from a file; the same error occurs in each case).
20:14:08 <zzo38> When it crashes it displays an option to debug; when trying to do that, Visual Studio crashes too.
20:17:36 <mroman> so debug visual studio
20:19:55 <mroman> what time is it now in america?
20:20:09 <zzo38> America is a large place with many timezone
20:20:42 <mroman> I suspect streaming sites get slow at night in europe
20:20:52 <mroman> because then the americans are sucking them dry
20:21:04 <mroman> because it's getting evening in america now
20:21:15 <mroman> so naturally demand probably rises.
20:30:12 -!- trout has quit (Ping timeout: 248 seconds).
20:42:30 -!- variable has joined.
20:48:29 -!- AnotherTest has joined.
21:09:14 -!- oerjan has quit (Quit: Procrastinated bedtime).
21:10:03 -!- variable has quit (Ping timeout: 256 seconds).
21:10:15 -!- nortti has changed nick to lawspeaker.
21:10:28 -!- lawspeaker has changed nick to nortti.
21:19:19 -!- TieSoul_ has joined.
21:22:28 -!- TieSoul has quit (Ping timeout: 248 seconds).
21:34:02 -!- nortti has changed nick to lawspeaker.
21:36:43 -!- lawspeaker has changed nick to nortti.
21:41:19 -!- TieSoul_ has quit (Ping timeout: 272 seconds).
21:41:43 <HackEgo> [wiki] [[4]] http://esolangs.org/w/index.php?diff=42613&oldid=42609 * 0x0dea * (+193) Add link to Ruby interpreter
21:44:58 -!- dianne has quit (Quit: byeannes).
21:45:15 -!- TieSoul has joined.
21:53:53 <izabera> http://arin.ga/9Gq52e/raw wtf am i doing wrong ;-;
21:54:03 <izabera> 15858241145932120218894943871026608990152107751826585365077595114766435.95790063850508607606943707675091261594678265767494925 <- my function's output
21:54:06 <izabera> 1585824114593212021889494387102660899015210775182658536507759216300499513.70549126207955355289853652483 <- output from bc
21:54:44 <izabera> i messed up something TT_TT
21:57:53 -!- GeekDude has joined.
22:05:39 -!- AnotherTest has quit (Remote host closed the connection).
22:05:47 -!- oren_ has joined.
22:05:58 -!- oren_ has changed nick to orin.
22:06:49 <zzo38> I figured out which function in my program results the error but not why, or if it is something that comes before that causes it
22:07:31 <zzo38> Maybe you can see the mistake?
22:13:52 <orin> #define cqp(p) ({if((p)==0){printf("%s: %s is null\n",__func__,#p); abort();}})
22:14:16 <orin> #define cqp(p) ({if((p)==0){printf("%s: %s is null\n",__func__,#p); abort();}p;})
22:15:14 <zzo38> I did check already if the pointers are null; none of the pointers that shouldn't be null are null pointers.
22:15:32 <orin> hm... what about divide by zero?
22:16:00 <zzo38> I have no division operations.
22:16:49 <zzo38> Also like I said before, the error doesn't occur in the debugger or if an instruction on stdin tells it to include the file, rather than the input being on stdin itself.
22:21:01 <zzo38> O, now it crashes even if you tell it to include the file, but still does not crash when running in the debugger, and that makes it difficult to test in the debugger.
22:24:26 <zzo38> Now maybe I found it; I tried something else, therefore I can look
22:25:36 <zzo38> Ah, yes I think I found it now.
22:31:56 <zzo38> The mistakes was, I wrote: p->data=realloc(p->data,sizeof(p->data[0])*(p->length+=i+1)); p->data[p->length].count=i; while(i) p->data[p->length+i].name=y[i-1],--i; Clearly that is wrong, so I changed it to: j=p->length; p->data=realloc(p->data,sizeof(p->data[0])*(p->length+=i+1)); p->data[j].count=i; while(i) p->data[j+i].name=y[i-1],--i;
22:36:46 -!- Patashu has joined.
23:07:32 -!- TieSoul has quit (Ping timeout: 248 seconds).
23:08:51 -!- TieSoul has joined.
23:41:55 -!- variable has joined.
23:44:55 -!- variable has changed nick to trout.
00:00:00 -!- orin has quit (Ping timeout: 264 seconds).
00:01:48 -!- orin has joined.
00:14:50 -!- Patashu_ has joined.
00:14:50 -!- Patashu has quit (Disconnected by services).
00:15:13 -!- bb010g has joined.
00:19:56 -!- Tritonio has quit (Remote host closed the connection).
00:24:31 <HackEgo> [wiki] [[Language list]] http://esolangs.org/w/index.php?diff=42614&oldid=42594 * Phi * (+14)
00:48:31 -!- doesthiswork has joined.
01:08:17 -!- boily has joined.
01:09:03 <boily> int-e: int-ello. what is stenosteganography? it sounds like something I'd be prefixing to a chicken.
01:18:01 <orin> I assume it is stuff quickly written in invisible ink?
01:18:17 <orin> or the electronic equivalent
01:20:41 <zzo38> You are going to write with electric ink?
01:21:13 -!- Phantom_Hoover has quit (Read error: Connection reset by peer).
01:22:41 <boily> hellorin. I think it's invisible shorthand.
01:22:58 <boily> hezzo38. there exists conductive ink for drawing circuits and stuff.
01:24:41 <zzo38> I don't know writing with shorthand; if I knew then I can try to use shorthand to record any play or movie I watched by writing down everything they say.
01:29:02 -!- hjulle has joined.
01:37:57 -!- shikhin has quit (Quit: Cya.).
01:46:17 -!- doesthiswork has quit (Quit: Leaving.).
02:05:20 -!- boily has quit (Quit: WALLED CHICKEN).
02:08:13 -!- orin has quit (Ping timeout: 265 seconds).
02:09:51 -!- yetto13921 has joined.
02:10:00 -!- orin has joined.
02:10:37 -!- yetto13921 has left.
02:12:01 <Sgeo> Expensive laptop, and it's defective
02:38:04 <orin> Did you already buy it? That was fast.
02:54:53 <orin> Why can't printers work by singeing the paper with heat? Then they wouldn't need ink.
02:59:22 <zzo38> How much fire do you need to do that?
03:04:02 -!- doesthiswork has joined.
03:09:02 -!- GeekDude has quit (Quit: {{{}}{{{}}{{}}}{{}}} (www.adiirc.com)).
03:15:17 <doesthiswork> greg shorthand is pretty interesting because it is optimised for ease of movement
03:21:21 <zzo38> I have heard of that; the book I have is Pitman (although this book doesn't explain all of it either)
03:24:15 -!- dianne has joined.
03:32:35 <HackEgo> [wiki] [[Gibberish/JavaScript]] http://esolangs.org/w/index.php?diff=42615&oldid=42570 * Esowiki201529A * (+4) /* Escape sequence */ Err
03:38:43 -!- bb010g has quit (Quit: Connection closed for inactivity).
03:40:16 -!- variable has joined.
03:40:30 -!- trout has quit (Read error: Connection reset by peer).
03:50:07 <Sgeo> orin, yes, and using it now
03:55:15 <zzo38> What is the shorthand for recording plays and movies and theater and stuff?
04:09:35 <zzo38> You cannot interrupt them in such a case if you miss something while writing!
04:10:15 <zzo38> It also needs to do without interrupting other people who watch the show.
04:29:13 -!- variable has changed nick to trout.
05:01:32 <newsham> orin: like thermal printers?
05:01:58 <newsham> most receipt printers do that, no ink required! (special thermal paper required)
05:03:29 <zzo38> I would like to learn to make up and then write in Theater Shorthand; that's what I would use shorthand for, because I don't need it for other purposes.
05:13:19 -!- Frooxius has quit (Quit: *bubbles away*).
05:14:41 <zzo38> Do you even know answer of any of my question at all, or anything a few thing a bit about it, or even to question the question (or to question the question the question the question)?
05:19:25 <shachaf> What is Theater Shorthand?
05:21:31 <zzo38> A new kind that we would have to make up, to use for recording live theater or movies without the use of any device other than pencil and paper and without disturbing any other people in audience or disturbing the actors
05:37:22 <newsham> why not just develop a photographic memory?
05:39:10 <zzo38> I want it written down
05:39:22 <zzo38> Such thing what they said and so on
05:40:20 -!- doesthiswork has quit (Quit: Leaving.).
05:51:20 -!- trout has quit (Quit: 1 found in /dev/zero).
05:51:51 -!- variable has joined.
05:56:08 <zzo38> Do you know stuff about my other questions above though?
06:01:45 <zzo38> (Such as, how much fire you need and how large a hexagonal grid cell must be and how to automatically fill in the frequent words table and so on)
06:10:18 <orin> Hm... it would have to be a shorthand such that you can write in the dark.
06:11:05 <orin> Based on the test I did just now, it's not easy to write legibly without looking at what you're writing
06:12:54 <orin> the shorthand would need to be designed so you won't normally write over your previous line, or maybe the notepad would need some sort of texture so you can tell where you are writing
06:13:49 -!- MDude has changed nick to MDream.
06:23:14 -!- hjulle has quit (Ping timeout: 276 seconds).
07:29:51 <HackEgo> [wiki] [[User talk:Esowiki201529A]] http://esolangs.org/w/index.php?diff=42616&oldid=42496 * Esowiki201529A * (+45) /* Quine */
07:30:32 <HackEgo> [wiki] [[Gibberish/JavaScript]] http://esolangs.org/w/index.php?diff=42618&oldid=42615 * Esowiki201529A * (+45) /* Quine */
07:34:22 <Jafet> I think a phonographic memory would work better for that.
08:04:24 -!- Vorpal has joined.
08:04:24 -!- Vorpal has quit (Changing host).
08:04:24 -!- Vorpal has joined.
08:33:30 -!- mitchs has joined.
09:02:33 -!- AndoDaan has joined.
09:07:36 -!- TieSoul has quit (Read error: Connection reset by peer).
09:07:48 -!- TieSoul has joined.
09:29:35 -!- Phantom_Hoover has joined.
09:37:56 -!- zadock has joined.
09:41:26 -!- variable has quit (Ping timeout: 246 seconds).
10:00:47 -!- _1_Hopp1 has joined.
10:04:57 <HackEgo> [wiki] [[List of quines]] http://esolangs.org/w/index.php?diff=42619&oldid=42572 * Esowiki201529A * (+57) /* Cheating Quines */
10:05:26 <HackEgo> [wiki] [[List of quines]] http://esolangs.org/w/index.php?diff=42620&oldid=42619 * Esowiki201529A * (+0) /* Gibberish/Javascript */
10:07:51 <HackEgo> [wiki] [[List of quines]] http://esolangs.org/w/index.php?diff=42621&oldid=42620 * Esowiki201529A * (+62) /* Gibberish */
10:09:28 <HackEgo> [wiki] [[List of quines]] M http://esolangs.org/w/index.php?diff=42623&oldid=42621 * Esowiki201529A * (+1) /* Gibberish/JavaScript */ 上次少了一个空格！
10:34:44 -!- oerjan has joined.
10:43:14 -!- _1_Hopp1 has quit (Ping timeout: 244 seconds).
10:45:04 -!- AndoDaan has quit (Read error: Connection reset by peer).
10:45:12 -!- AndoDaan_ has joined.
10:48:32 <oerjan> <boily> hezzo38. there exists conductive ink for drawing circuits and stuff. <-- i've been here too long, i read that as coinductive
10:53:13 <Jafet> The inkwell that never bottoms out
10:54:34 -!- rdococ has joined.
11:28:26 -!- augur_ has joined.
11:29:23 -!- augur has quit (Ping timeout: 276 seconds).
11:50:57 <myname> wow, there is actually a funciton quine
12:11:22 -!- Jafet has quit (Ping timeout: 252 seconds).
12:11:43 -!- Jafet has joined.
12:12:06 -!- nortti has quit (Ping timeout: 252 seconds).
12:13:00 -!- nortti has joined.
12:30:20 -!- Patashu_ has quit (Ping timeout: 256 seconds).
12:41:05 -!- ski has quit (Quit: Lost terminal).
12:45:46 -!- boily has joined.
13:00:55 -!- TieSoul_ has joined.
13:01:52 -!- boily has quit (Read error: Connection reset by peer).
13:02:43 -!- Jafet has left.
13:05:22 -!- TieSoul has quit (Ping timeout: 272 seconds).
13:08:48 -!- mtve has quit (Read error: Connection reset by peer).
13:36:55 -!- Phantom_Hoover has quit (Ping timeout: 250 seconds).
13:40:35 -!- Phantom_Hoover has joined.
13:51:26 -!- boily has joined.
13:52:10 -!- Jafet has joined.
13:52:52 -!- EgoBot has quit (Ping timeout: 272 seconds).
13:53:03 -!- EgoBot has joined.
14:00:20 -!- b_jonas has joined.
14:01:00 -!- orin has quit (Ping timeout: 250 seconds).
14:01:52 -!- orin has joined.
14:11:16 -!- Phantom_Hoover has quit (Ping timeout: 255 seconds).
14:11:46 -!- zadock has quit (Quit: Leaving).
14:16:21 -!- orin has quit (Ping timeout: 250 seconds).
14:18:17 -!- orin has joined.
14:20:25 -!- AndoDaan_ has quit (Read error: Connection reset by peer).
14:20:28 -!- _AndoDaan_ has joined.
14:20:41 -!- GeekDude has joined.
14:28:18 -!- TieSoul_ has changed nick to TieSoul.
14:29:44 <mroman> Are there programs that print out their machine code?
14:30:14 -!- orin has quit (Ping timeout: 272 seconds).
14:31:40 -!- orin has joined.
14:33:41 <mroman> if you write it dirctly in machinecode ok
14:34:38 <mroman> but I meant more like they'll output P where P is what a transpiler/compiler would produce given the original program
14:35:53 <oerjan> should in principle be easy, use the normal quine construction with "run a compiler" instead of "print"
14:36:53 -!- AndoDaan has joined.
14:37:07 <oerjan> the compiler can be completely embedded if you want
14:38:58 -!- _AndoDaan_ has quit (Ping timeout: 256 seconds).
14:39:07 -!- Tritonio has joined.
14:40:15 <b_jonas> oerjan: you don't even need that
14:41:10 <b_jonas> you could just write a non-quine that outputs a literal twice (with the second copy in the middle), compile, it, then change the literal to what the compiler has output, and iterate this a few times until it stabilizes
14:41:49 <b_jonas> it's even easier than in most languages because you probably don't need backslash stuff, the literal will appear literally in the executable
14:41:57 <oerjan> ...what guarantee do you have that it stabilizes
14:42:18 <b_jonas> (unless it's an executable in the silly MMIX object file format)
14:43:14 <oerjan> i don't think compilers usually embed literals in decimal?
14:43:39 <b_jonas> oerjan: once you know the length of the literal, the executable will remain the same except that when you modify the literal itself its verbatim copy will change in the executable. the length of the literal and the position where it has to be inserted in the output will change, but will converge quickly, and in any case, only have finitely many values.
14:44:03 <b_jonas> in theory it could fail to converge and get in a short loop, but you can just fuzz the program a bit to avoid that
14:44:43 <oerjan> i agree it _could_ work, provided you have a literal type that _does_ get literally embedded in the executable in the same form as in source
14:45:05 <oerjan> oh well i guess strings do
14:45:07 <b_jonas> oerjan: sure it does. just a global char d[] = {3,1,4,1,5,...}; will be
14:45:15 <b_jonas> just an array with constant initializer
14:45:35 <b_jonas> if you're worried the rest of the program is optimized for it too much, put it in a separate compilation unit
14:45:44 <oerjan> b_jonas: um, surely it doesn't get embedded as the same byte sequence "3,1,4,1,5"
14:46:03 <b_jonas> oerjan: exactly, it gets embedded as the raw bytes
14:46:03 <oerjan> the 3 in source is a 51 byte, you know
14:46:20 <b_jonas> which is what you have to print, because the point is to print not the C source, but the executable file
14:46:32 <b_jonas> you don't have to print _any_ part of the C source code at all
14:46:56 <b_jonas> (replace C with some other compiled language if you wish)
14:47:27 <b_jonas> (of course, you could write it directly in machine code too if you choose to)
14:53:04 <b_jonas> there are other ways to write such a quine:
14:53:28 <b_jonas> you could duplicate only the elf headers, and have the program read the code and constant data segments directly;
14:53:46 <b_jonas> or you could fuzz with the elf headers so the entire executable file is mapped, and then write that;
14:54:07 <b_jonas> or a DOS COM file already does that, so just making it write(1, 0x100, length of file); return; would work
14:54:46 <oerjan> in quines, that's called "cheating" hth
14:54:51 <b_jonas> that's probably around 20 bytes of a COM file, less if you golf agressively
14:55:35 <b_jonas> no it's not. it's cheating if you're reading the file, or otherwise accessing it in a way the program doesn't normally do so
14:56:02 <b_jonas> it is perfectly normal for an executable program to have portions of it mapped in memory (some of the data portions might _change_ by the time you access them though)
14:56:19 <oerjan> well in machine code...
14:56:25 -!- Sprocklem has quit (Ping timeout: 264 seconds).
14:56:50 <oerjan> but this question is less interesting if the original language is that close to the machine.
15:08:23 <mroman> well accessing the machine code in memory is probably cheating yes
15:08:49 <mroman> also maybe it runs on a computer with code/data separated
15:08:52 <mroman> like a microcontroller
15:08:59 <mroman> and you don't have read/write access to it.
15:11:15 <lambdabot> CYQB 191500Z VRB06KT 30SM FEW040 08/M04 A3027 RMK SC1 SC TR SLP255
15:37:05 -!- AndoDaan has quit (Read error: Connection reset by peer).
15:37:19 -!- AndoDaan has joined.
16:00:14 -!- oerjan has quit (Quit: Later).
16:03:40 -!- AndoDaan has quit (Quit: Going, going, gone.).
16:03:58 -!- AndoDaan has joined.
16:13:23 -!- Tritonio_ has joined.
16:15:20 -!- variable has joined.
16:17:16 -!- Tritonio has quit (Ping timeout: 272 seconds).
16:18:38 -!- variable has changed nick to trout.
16:18:41 -!- MDream has changed nick to MDude.
16:19:56 -!- Tritonio_ has changed nick to Tritonio.
16:21:26 -!- boily has quit (Quit: PROCLAIMED CHICKEN).
16:27:16 -!- AndoDaan has quit (Read error: Connection reset by peer).
16:27:20 -!- AndoDaan_ has joined.
16:29:23 -!- MDude has quit (Ping timeout: 250 seconds).
16:30:10 -!- _AndoDaan_ has joined.
16:33:01 -!- AndoDaan_ has quit (Ping timeout: 264 seconds).
16:36:00 -!- SopaXorzTaker has joined.
17:07:41 -!- SopaXorzTaker has quit (Read error: Connection reset by peer).
17:15:56 -!- _AndoDaan_ has quit (Read error: Connection reset by peer).
17:17:25 -!- Tritonio_ has joined.
17:19:58 -!- Tritonio has quit (Ping timeout: 272 seconds).
17:24:57 -!- Tritonio_ has changed nick to Tritonio.
17:30:40 -!- Tritonio has quit (Remote host closed the connection).
17:56:33 -!- FreeFull has quit (Quit: BBL).
18:02:04 <HackEgo> [wiki] [[Deadfish]] http://esolangs.org/w/index.php?diff=42624&oldid=42115 * BCompton * (+69) /* Rust */ Updated based on Rust v1.0.0 Beta, old code wouldn't compile.
18:02:43 <HackEgo> [wiki] [[User:BCompton]] http://esolangs.org/w/index.php?diff=42625&oldid=41530 * BCompton * (+7) /* Languages I've implemented */
18:04:40 -!- TodPunk has quit (Ping timeout: 240 seconds).
18:14:35 -!- shikhin has joined.
18:17:58 -!- TodPunk has joined.
18:18:08 <HackEgo> [wiki] [[Basilisk]] N http://esolangs.org/w/index.php?oldid=42626 * Vriskanon * (+1369) Created page Basilisk
18:19:18 <HackEgo> [wiki] [[Joke language list]] M http://esolangs.org/w/index.php?diff=42627&oldid=42140 * Vriskanon * (+71) /* General languages */ Added Basilisk
18:23:16 <HackEgo> [wiki] [[User:Vriskanon]] M http://esolangs.org/w/index.php?diff=42628&oldid=42596 * Vriskanon * (+52) /* Vriskanon */ Added credit for Basilisk
18:26:10 -!- AnotherTest has joined.
18:42:13 -!- shikhin has quit (Ping timeout: 256 seconds).
18:51:53 -!- rdococ has quit (Quit: Page closed).
19:15:58 -!- bb010g has joined.
19:21:21 -!- hjulle has joined.
19:39:00 -!- hjulle has quit (Ping timeout: 265 seconds).
20:01:21 <zzo38> Also some machine codes are harvard, too
20:12:39 -!- AnotherTest has quit (Ping timeout: 276 seconds).
20:13:23 -!- zzo38 has quit (Remote host closed the connection).
20:27:12 -!- b_jonas has quit (Remote host closed the connection).
20:29:19 -!- mitchs_ has joined.
20:32:27 -!- mitchs has quit (Ping timeout: 246 seconds).
20:43:04 -!- boily has joined.
20:44:28 -!- trout has quit (Ping timeout: 256 seconds).
20:46:12 -!- Sgeo has quit (Quit: Leaving).
20:47:08 -!- Sgeo has joined.
20:50:29 -!- Sgeo has quit (Client Quit).
20:51:23 -!- Sgeo has joined.
20:52:46 -!- FreeFull has joined.
20:54:04 -!- boily has quit (Quit: OPTIONAL CHICKEN).
20:58:00 -!- Phantom_Hoover has joined.
21:00:19 -!- Patashu has joined.
21:01:38 -!- Frooxius has joined.
21:14:13 -!- oerjan has joined.
21:18:49 -!- bb010g has quit (Quit: Connection closed for inactivity).
21:20:48 -!- AnotherTest has joined.
21:23:48 -!- Patashu has quit (Ping timeout: 272 seconds).
21:33:18 -!- AnotherTest has quit (Ping timeout: 272 seconds).
21:38:49 -!- Froox has joined.
21:42:23 -!- Frooxius has quit (Ping timeout: 245 seconds).
22:21:26 -!- pikhq has quit (Ping timeout: 272 seconds).
22:27:26 <HackEgo> [wiki] [[Deadfish]] http://esolangs.org/w/index.php?diff=42629&oldid=42624 * BCompton * (+43) /* Rust */
23:09:47 -!- sebbu has quit (Ping timeout: 250 seconds).
23:10:20 -!- sebbu has joined.
23:11:02 -!- sebbu has quit (Changing host).
23:11:02 -!- sebbu has joined.
23:11:45 -!- pikhq has joined.
23:24:09 -!- oerjan has quit (Quit: Nite).
00:19:36 <HackEgo> [wiki] [[Gibberish/JavaScript]] http://esolangs.org/w/index.php?diff=42630&oldid=42618 * Esowiki201529A * (+65) /* Escape sequence */
00:19:50 -!- variable has joined.
00:22:06 -!- variable has quit (Read error: error:1408F10B:SSL routines:SSL3_GET_RECORD:wrong version number).
00:26:02 -!- variable has joined.
00:37:56 <HackEgo> [wiki] [[Gibberish/JavaScript/Escape sequence]] N http://esolangs.org/w/index.php?oldid=42631 * Esowiki201529A * (+5057) Created page with "{| class="wikitable sortable" |- ! escape sequence !! output !! output’s ASCII code |- | $x21 || ! || 33 |- | $x22 || " || 34 |- | $x23 || # || 35 |- | $x24 || &..."
00:57:27 -!- Phantom_Hoover has quit (Read error: Connection reset by peer).
01:10:07 <pikhq> http://berlin.ipsojobs.com/job/senior-brainf-k-developer/3-1473326
01:18:37 -!- variable has changed nick to trout.
02:48:41 -!- augur_ has changed nick to _augur.
02:55:13 -!- zzo38 has joined.
03:04:21 -!- Sgeo_ has joined.
03:06:26 -!- clog has quit (Ping timeout: 272 seconds).
03:06:34 -!- clog has joined.
03:07:42 -!- Sgeo has quit (Ping timeout: 272 seconds).
03:19:12 <HackEgo> [wiki] [[Deadfish]] http://esolangs.org/w/index.php?diff=42632&oldid=42629 * Zzo38 * (-538) Add OASYS Assembler; delete the Frolg version that is not valid anymore
03:24:32 <HackEgo> [wiki] [[Deadfish]] http://esolangs.org/w/index.php?diff=42633&oldid=42632 * Zzo38 * (+456) OASYS (OAC)
03:26:30 -!- AndoDaan has joined.
03:27:15 <zzo38> Now I made the Deadfish using both compilers for OASYS which are both OAC and OAA and now is possible to see how they are compared.
03:59:02 -!- GeekDude has quit (Quit: {{{}}{{{}}{{}}}{{}}} (www.adiirc.com)).
04:28:51 -!- Sprocklem has joined.
04:30:36 <tromp_> > let f='.';o c(x:y)=x:c y;z c(x:y)=f:c y;p n='p':ap fix p(o.n)in f:f:p z
04:30:38 <lambdabot> "..pp.p.p...p.p...p.p...p.....p.p.....p...p.p...p.....p.....p.p.....p...p.p....
04:42:48 <tromp_> 0 is not, 1 is not, 2 is,...
04:45:23 <copumpkin> > let f='.';o c(x:y)=x:c y;z c(x:y)=f:c y;p n='p':ap fix p(o.n)in map fst . filter ((=='p') . snd) $ zip [0..] (f:f:p z)
04:45:24 <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,...
04:49:38 <tromp_> we developed it in BLC originally
04:49:52 <tromp_> see https://github.com/tromp/AIT
04:50:29 <tromp_> which is also featured in http://www.ioccc.org/2012/tromp/hint.html
04:50:49 <tromp_> i just translated it to Haskell tonight...
04:51:54 <zzo38> Ah, yes now I can see, that is what it is.
04:52:29 -!- jsilver has joined.
04:52:49 <zzo38> Mathematics will make up many ways of one thing a lot of times.
04:52:58 <tromp_> i'm off to bed now... g'night!
04:55:48 <jsilver> if numbers start at 0, why isn't 56 really called 57
05:09:57 <orin> jsilver: you could call it that.
05:11:02 <orin> the names of numbers are pretty much arbitrary
05:12:07 <orin> a better question however is why isn't eleven called oneteen?
05:13:12 -!- pikhq has quit (Ping timeout: 265 seconds).
05:28:09 -!- mitchs_ has quit (Read error: Connection reset by peer).
05:32:07 -!- TieSoul has quit (Remote host closed the connection).
05:42:56 <zzo38> Is there such a thing as a <urn:null> URI?
05:55:41 -!- pikhq has joined.
05:59:32 <HackEgo> [U+3007 IDEOGRAPHIC NUMBER ZERO]
06:00:47 -!- rdococ has joined.
06:07:44 <jsilver> haskell is really fucking cool man
06:09:37 <orin> AAAAAA WHY ARE THE SUBTITLES HALF IN GERMAN
06:10:01 <myname> you don't like german?
06:11:07 <orin> I guess I don't mind since I understand the japanese anyway, but it is weird
06:15:05 <orin> She says よかった、友達が出来た and the subtitles say "I'm glad I made some Freunde"
06:17:41 <orin> hmm I'm starting to like this.
06:21:38 <orin> Was ist los? どうしたの？
06:23:54 <jsilver> fuck this is so cool man, my mind is blown
06:27:03 <HackEgo> [wiki] [[QuinePig]] http://esolangs.org/w/index.php?diff=42634&oldid=41983 * 122.37.11.94 * (+0) /* Text File Named "Hello, World!" */
06:32:23 <myname> what are you watching?
06:35:12 -!- PinealGlandOptic has quit (Ping timeout: 244 seconds).
06:38:31 <HackEgo> [wiki] [[CASISP]] N http://esolangs.org/w/index.php?oldid=42635 * Orenwatson * (+576) lol this would be awesome
06:38:41 <orin> girls und panzer
06:39:46 <myname> to be fair, the title is half german, too
06:41:08 <orin> So I think we could just mix programming languages too,
06:47:13 <orin> in a sense PHP is kind of a Perl/C crossover.
06:56:36 <orin> Interpreting such a programming language would be easy for a human, but hard for a computer
06:59:24 <orin> "Der Herrgott sei gelobt" <-- what does that mean?!!?!?!?
07:02:21 <orin> Ah. that makes sense
07:03:39 -!- Sprocklem has quit (Ping timeout: 245 seconds).
07:05:03 <mroman> or more literally "Praised be the lord"(?)
07:05:21 <orin> yeah they translated よかった with it
07:05:23 <mroman> I'm not sure if that is proper english though.
07:12:18 <orin> yeah that sounds like proper english
07:12:44 <orin> (based on my arbitrary native speaker sense of what sounds right)
07:13:05 <quintopia> it is legitimate, but a bit formal, nigh on archaic
07:13:42 <myname> https://pbs.twimg.com/media/CDAHcZnUUAALn2d.jpg
07:18:12 -!- Froox has quit (Quit: *bubbles away*).
07:22:17 <mroman> What would you say otherwise?
07:22:30 <mroman> That sounds like an order.
07:26:36 <orin> Hmm, it kind of is a set phrase...
07:27:40 <orin> I guess halelujah is also still used, but that is hebrew not english
07:34:21 -!- trout has quit (Ping timeout: 272 seconds).
07:35:58 <mroman> Good thing I switched religions.
07:42:09 <HackEgo> [wiki] [[List of ideas]] M http://esolangs.org/w/index.php?diff=42636&oldid=42033 * Vriskanon * (+134) /* Music */ Added idea for original Daft Punk language
07:42:55 -!- zadock has joined.
07:44:23 <mroman> A religion of peace :)
07:44:36 <mroman> fungot: Do you like peace?
07:44:37 <fungot> mroman: a very tiny car... coincidence, utahraptor?: we either have to acknowledge that, why call him " hey man of my racial qualities! so say a decision has to be made to feel the miracle??
07:45:08 <mroman> "A decision has to be made to feel the miracle"
07:52:10 <orin> Damn it. I'm tired but I have to sta up so that I'll be on a sleep schedule where my test is in the afternoon
07:52:47 <orin> At least it's probably the last exam I'll ever take
07:54:41 <mroman> what's your current sleep schedule?
07:55:46 <orin> Currently I would be going to sleep aboutnow
08:06:53 <mroman> Can one solve equation systems of the sort a ^ b = c AND a | b = d AND a & b = e where c,d and e are known but not a,b?
08:08:03 <mroman> (I can obviously brute-force it)
08:08:27 <mroman> but I'm not sure if that even gives a unique answer.
08:11:58 -!- Insipid has joined.
08:13:56 <orin> Hmm... if d=0 then the only answer is a=b=0. If e=1 then the only answer is a=b=1.
08:15:02 <orin> If d=1 and e=0, then one of a,b is 0 and the other is 1
08:15:38 <orin> and c has to be 1, so it tells us nothing
08:15:54 <orin> So you cannot solve it
08:16:52 <HackEgo> [wiki] [[AFTL]] N http://esolangs.org/w/index.php?oldid=42637 * Vriskanon * (+122) cre
08:18:28 <HackEgo> [wiki] [[AFTL]] M http://esolangs.org/w/index.php?diff=42638&oldid=42637 * Vriskanon * (+2) Created AFTL stub page
08:19:10 <HackEgo> [wiki] [[Language list]] M http://esolangs.org/w/index.php?diff=42639&oldid=42614 * Vriskanon * (+11) /* A */ Added Another Fucking Time Loop
08:28:28 <fizzie> Hm? http://sprunge.us/OjWM makes it sound like there'd be a unique combination of c, d, e for each of the possible values of a, b.
08:29:14 <fizzie> Yeah, the 0/1, 1/0 cases have the same c, d, e.
08:29:59 <fizzie> (Given that all three are commutative, maybe not so surprising.)
08:30:33 <orin> d would have to be 1 not 0. if d is 0 or e is 1 then c must be 0
08:30:57 <mroman> A naive person like me would even claim that the above system is "over defined"
08:31:02 <mroman> 3 equations, 2 variables
08:31:20 <fizzie> (Also I wrote the table all wrong. I've just woken up, going to blame that.)
08:31:47 <orin> yeah that only works for algebra on real numbers
08:33:42 <fizzie> If you had, say, a ^ b, a | b and a -> b, then you could tell.
08:34:25 -!- AnotherTest has joined.
08:35:24 -!- Insipid has quit (Quit: Leaving.).
08:35:33 -!- oerjan has joined.
08:36:05 -!- rdococ has quit (Ping timeout: 246 seconds).
08:38:35 <HackEgo> [wiki] [[AFTL]] http://esolangs.org/w/index.php?diff=42640&oldid=42638 * Vriskanon * (+2264) Added all content excluding sample programs.
08:38:59 -!- AnotherTest has quit (Ping timeout: 252 seconds).
08:39:18 -!- Patashu has joined.
08:39:34 <HackEgo> [wiki] [[User:Vriskanon]] M http://esolangs.org/w/index.php?diff=42641&oldid=42628 * Vriskanon * (+11) /* Original Languages */ Added AFTL
08:41:29 <mroman> Any ideas on how to encode a,b into c and d so that a,b can only be reconstructed by somebody knowing both c and d?
08:41:39 <mroman> where a,b are integers mod N
08:41:49 <mroman> (and c,d also integers mod N)
08:44:04 -!- AnotherTest has joined.
08:44:24 <oerjan> that's not quite a one time pad
08:44:47 <mroman> 128+128 = 0, 128 - 128 = 0
08:45:34 <orin> what about for prime N
08:46:14 -!- Insipid has joined.
08:46:38 <oerjan> odd N is enough, i think
08:46:43 <orin> oerjanL whats a one time pad
08:47:01 <oerjan> perfect encryption with a key as long as the message
08:47:02 <orin> augh I mean oerjan:
08:47:25 <oerjan> to be perfect, the key must _never_ be reused, thus one time
08:48:13 <oerjan> but then you encrypt a as a + k, say.
08:48:25 <oerjan> (any group operation will do.)
08:49:17 <mroman> what's with the one time pad?
08:49:18 <oerjan> i suppose it is a one time pad if b is the key
08:49:35 <mroman> a and b are two data points
08:49:54 <oerjan> in that case i believe what you're asking is mathematically impossible
08:50:04 <mroman> well it works with odd N
08:50:28 <oerjan> no i mean, to be secure you have to assume the attacker knows _something_ about a and b.
08:50:43 -!- AnotherTest has quit (Ping timeout: 252 seconds).
08:51:06 <oerjan> like, imagine is a be were just 0 and 1 (but you still used > 1 bits) (this is a hypothetical strawman to illustrate)
08:51:08 <mroman> it's terrible against known plaintexts I guess
08:51:29 <mroman> or partially known plaintexts
08:51:43 <oerjan> or even texts in a known language
08:53:17 <oerjan> otoh secret sharing _is_ a branch of cryptography https://en.wikipedia.org/wiki/Secret_sharing
08:53:50 <mroman> but you would have no overhead and wouldn't need to transmit any keys
08:53:53 <oerjan> however you need more bits than the secret to be shared
08:54:16 <oerjan> yes, but i don't think that's theoretically possible.
08:54:36 <oerjan> the overhead is needed to make it work.
08:54:43 <mroman> Reasonably if a and b were images
08:54:50 <mroman> I can encode those two images into two other images
08:54:58 <mroman> and give one to each of my two friends
08:55:16 <mroman> and they wouldn't be able to get these two images back without consulting each other
08:55:24 <mroman> (unless they have good prior knowledge about a and b I guess)
08:55:43 <mroman> and I don't need to give them any keys or whatsoever.
08:56:07 <oerjan> i suppose you need a good scrambling function. hm can you write it using just a hash...
08:56:36 <oerjan> assume we can use a publically know hash function.
08:56:40 <mroman> That's the scenario I'm aiming at actually :D @two images, distribute to two friends
08:57:31 <mroman> however you can probably see parts of the images :(
08:57:46 <mroman> i.e. if one is bright and one is dark (i.e mostly (0,0,0) pixels)
08:57:53 <mroman> you would see the other image in the a+b image
08:57:55 <oerjan> a + b + h, a - b + h, the question is what should the hash h be _of_ to make it reconstructible
08:58:50 <oerjan> if you hash b it works with that, i think
08:59:04 <oerjan> because you can reconstruct b by subtraction
08:59:22 <oerjan> mroman: for that you can hash a
08:59:28 <mroman> that let's you reconstruct h anyway?
08:59:37 <mroman> by taking the difference of the two images?
08:59:57 <oerjan> there are several options here
09:01:20 <mroman> you could use the upper left pixels to encode some information I guess
09:01:33 <mroman> but then you loose a few pixel of the image :(
09:01:37 <mroman> and that'd be cheating
09:02:59 <elliott> can't you just use xor or something
09:04:03 <oerjan> elliott: not with his requirement that the resulting shares should be that small
09:04:08 <elliott> you can use xor to split A and B into A and C or B and C such that the combination of both gives you the remaining one
09:04:09 <mroman> a ^ b = c; a ^ d = e; but then you'd need to transmit c,d and e
09:04:21 <elliott> but that requires revealing one of A or B
09:05:03 <oerjan> elliott: btw he's not assuming that the number of values is a power of 2, so xor isn't necessarily available
09:05:19 <elliott> you can xor images well enough
09:05:46 <oerjan> well they usually _are_ a whole number of bits
09:05:46 <mroman> you can xor images, yes.
09:06:25 <elliott> if you have a hash function H and let c = a ^ b then you could somehow compute a fixed point x = encrypt(c, H(y)), y = encrypt(c, H(x)). maybe.
09:06:58 <elliott> oh. because you can't go from both of those to a or b
09:08:38 <elliott> x = encrypt(a, H(y)), y = encrypt(b, H(x)) would still work, but that's just cheating by assuming you can construct that fixed point
09:10:03 <elliott> well I am sure oerjan will figure it out
09:10:05 <mroman> you could also randomly select if you should use the pixel from image A or image B
09:10:39 <mroman> if rnd() then x[i] = a[i] ; y[i] = b [i] else x[i] = b[i]; y[i] = a [i];
09:10:57 <mroman> but then you'd need to comunicate the seed somehow
09:10:58 <oerjan> https://en.wikipedia.org/wiki/Secret_sharing#Space_efficient_secret_sharing <-- this seems to imply you cannot get quite down to that size, and in fact there is no saving with just 2 people
09:11:14 <mroman> I hate that a + b, a - b totally works
09:11:22 <mroman> images aren't random enough :(
09:12:59 <mroman> you could scramble things though
09:13:04 <mroman> like x = a + b; y = a -b;
09:13:11 <mroman> then swap pixels in x and y
09:13:41 <mroman> (i.e. swap x[i] and y[i])
09:13:59 <mroman> that reduces visible artefacts to some extent.
09:14:18 <oerjan> the point of my adding a hash was to ensure that scrambling.
09:14:53 <oerjan> of course the hash has to be the same size, and indistinguishable from random noise
09:15:38 <oerjan> this is obviously vulnerable to an attacker who knows either a or b
09:15:39 <mroman> x = a + b + H(b), y = a - b + H(b)?
09:16:15 <mroman> x - y = a + b + H(b) - a + b - H(b) = b + b?
09:16:17 <oerjan> except + _doesn't_ work with whole bits
09:16:40 <oerjan> maybe nothing does, hm
09:17:23 <oerjan> it works when N is odd
09:17:23 <mroman> and you can't really divide by 2 :(
09:17:51 <mroman> how do you reconstruct b?
09:18:10 <oerjan> easy when N is odd hth
09:19:05 <oerjan> x = a - b + H(b), y = a + 2b + H(b) would work when N is not divisible by 3, etc.
09:20:28 <oerjan> hm i'm slightly worried that some bits may seep through there
09:20:28 <mroman> If an attacker knows a or b your privacy is lost anyway :D
09:21:07 <mroman> that depends on H probably
09:21:12 <mroman> if H(x) = x then yes :D
09:21:20 <oerjan> there's probably something wrong about this scheme since the wikipedia page doesn't mention it, but i don't know what :)
09:21:38 <mroman> maybe it's too good so the NSA doesn't want people to know it .
09:21:41 <oerjan> why in the world would H(x) = x
09:22:09 <mroman> because that's the Hashfunction recommended by the NSA
09:22:13 <elliott> oerjan: if we're considering bits then H is either identity or negation right
09:22:29 <oerjan> elliott: um we're not considering single bits hth
09:22:57 <oerjan> (i'm pretty sure i used the word "strawman" in the line where i did)
09:23:42 <HackEgo> [wiki] [[AFTL]] M http://esolangs.org/w/index.php?diff=42642&oldid=42640 * Vriskanon * (+279) Added Hello World sample program
09:24:04 <elliott> oerjan: okay but we're considering images right
09:24:09 <elliott> so isn't + meant to be bitwise xor or whatever
09:24:12 <oerjan> the NSA doesn't want encryption to be _that_ bad. they don't want the _chinese_ to be able to break it, after all.
09:24:39 <oerjan> elliott: no, it's + (mod N), sheesh
09:25:44 <oerjan> if it were xor then 2b would be 0. otoh i don't see why that _really_ breaks anything...
09:27:08 <oerjan> so my assumption is that the NSA wants encryption to be strong but them to have a backdoor. which i recall is exactly what they tried to do to one standard.
09:27:59 <oerjan> ok then, x = a + b + H(b), y = a + H(b).
09:28:24 <oerjan> now it works with any group addition.
09:30:49 <oerjan> but probably breaks for lousy a and b
09:35:18 <elliott> oerjan: ok but what is H then
09:35:28 <elliott> presumably it has a smaller domain than codomain?
09:36:02 <oerjan> no that wouldn't work, needs to be equal size
09:36:42 <elliott> are you sure this is a hash function :P
09:36:50 <oerjan> it needs to look like random noise
09:37:00 <oerjan> no, i'm not sure that's what it's called
09:37:05 <elliott> is there a name for that kind of scrambler
09:38:04 <oerjan> oh and it's also necessary that b + H(b) looks like random noise
09:39:02 <mroman> well some basic structure can still be recognised depending on the pictures.
09:39:21 <mroman> but my hash function isn't that great probably
09:39:40 <oerjan> mroman: RANDOM NOISE OF THE SAME SIZE hth
09:39:55 <elliott> oerjan: H is basically an encryption with some random key
09:40:00 <elliott> (as in, some pre-specified key)
09:40:18 <elliott> I guess it's just H(x) = x ^ key
09:40:47 <oerjan> elliott: um no that would break the b + H(b) assumption i just f mentioned hth
09:41:38 <oerjan> elliott: if you mean ^ = + = xor, it doesn't help, b + H(b) = key then
09:42:37 <oerjan> (note that the key is _not_ secret or we break the whole problem statement)
09:43:04 <elliott> well are you sure this H exists
09:43:25 <elliott> you want H(x) to not be x, and also x + H(x) to neither be x nor H(x), but not be the same for all x
09:43:40 <elliott> maybe my intuition is misfiring in seeing a pigeonhole problem here
09:44:28 <oerjan> elliott: um there's no requirement it cannot accidentally coincide for _some_ x.
09:45:28 <oerjan> it just has to be astonishingly unlikely
09:45:55 <mroman> I'm using x^3 `mod` 255
09:46:17 -!- shikhin has joined.
09:46:26 <oerjan> bloody upstairs neighbor trampling around
09:47:21 <mroman> you can still recognize that it's a building in the picture :)
09:47:51 <oerjan> mroman: it's not supposed to apply the hash function to each byte separately, duh
09:48:02 <oerjan> it's supposed to be a hash of the _whole_ picture
09:48:22 <mroman> if b is a white picture
09:48:37 <mroman> or a black one for that matter
09:48:45 <oerjan> ...then you're lost anyway because what attacker cannot test such simple cases?
09:49:01 <orin> oerjan: try hitting the ceiling with a broom
09:49:05 <mroman> even if you take the hash of the whole picture
09:49:08 -!- Insipid has quit (Quit: Leaving.).
09:49:11 <mroman> you can still recognize structures in them
09:49:19 <mroman> if an area is uniform in one picture
09:49:35 -!- Insipid has joined.
09:49:43 <mroman> the other picture will "shimmer" through
09:50:22 <orin> try throwing a potato at the ceiling
09:50:38 <oerjan> mroman: the hash is supposed to look like random noise for heaven's sake
09:51:03 <oerjan> mroman: THEN FIND A BETTER ONE
09:51:12 <mroman> the hash has the same size as the picture?
09:51:31 <elliott> can you please call it something other than H :P
09:52:25 -!- shikhin_ has joined.
09:52:34 * oerjan must be having that Curse of knowledge thing
09:52:55 <oerjan> hashed together with dunning-kruger
09:53:13 <oerjan> orin: i don't have a potato hth
09:54:25 -!- shikhin has quit (Ping timeout: 256 seconds).
09:55:57 <orin> I didn't mean specifically a potato, just some random object
09:56:23 -!- shikhin_ has changed nick to shikhin.
09:57:50 <oerjan> I HAVE NO RANDOM OBJECTS oh wait
09:57:59 <oerjan> also they sort of stopped.
10:00:08 -!- Insipid has quit (Quit: Leaving.).
10:17:08 -!- shikhin has quit (Ping timeout: 245 seconds).
10:17:31 -!- shikhin has joined.
10:18:24 -!- shikhin has quit (Client Quit).
10:18:44 -!- shikhin has joined.
10:25:09 -!- boily has joined.
10:33:07 <HackEgo> /home/hackbot/hackbot.hg/multibot_cmds/lib/limits: line 5: exec: 2016: not found
10:33:28 <HackEgo> /hackenv/bin/2015: POSIX shell script, ASCII text executable
10:33:39 <HackEgo> #!/bin/sh \ if [ $(date +%Y) != "$(basename "$0")" ] \ then echo "Hello, world!" \ fi
10:34:01 <HackEgo> #!/bin/sh \ if [ $(date +%Y) = "$(basename "$0")" ] \ then echo "Hello, world!" \ fi
10:34:25 <fungot> http://esolangs.org/wiki/2014
10:37:55 <FireFly> Someone has yet to write a page on the 2015 derivative
10:38:06 <HackEgo> [wiki] [[Hexadecimal Stacking Pseudo-Assembly Language]] http://esolangs.org/w/index.php?diff=42643&oldid=42394 * Oerjan * (+10) wikify a bit
10:40:51 <AndoDaan> it outputs when run in any year but it's 2015?
10:47:48 <HackEgo> [wiki] [[Hello world program in esoteric languages]] http://esolangs.org/w/index.php?diff=42644&oldid=42569 * Oerjan * (-19) Fix some disorder
10:54:48 <HackEgo> [wiki] [[Language list]] http://esolangs.org/w/index.php?diff=42645&oldid=42639 * Oerjan * (-6) /* G */ grm
11:00:18 <HackEgo> /home/hackbot/hackbot.hg/multibot_cmds/lib/limits: line 5: exec: 2016: not found
11:02:39 <AndoDaan> 2016 should be, if 2014 and 2015 give the same output then output it too, if not then... something else.
11:07:20 <HackEgo> [wiki] [[Meq]] http://esolangs.org/w/index.php?diff=42646&oldid=42348 * Oerjan * (+642) Wikify and format
11:08:05 -!- shikhin_ has joined.
11:10:50 -!- shikhin has quit (Ping timeout: 264 seconds).
11:13:39 <mroman> if year = 0 then echo "Welcome, Jesus!"
11:13:54 <mroman> that is, unless you beleive some period around 17xx didn't exist.
11:14:20 <mroman> (It was around 17xx wasn't it?)
11:14:52 <mroman> which proposes that the year 613 was followed by the year 911 hm no
11:15:43 <mroman> 1000 AD, so he got there by advancing the calendar 300 years
11:15:56 <mroman> ok apparenteley multiple people screwed with the calendar.
11:16:12 <mroman> 613-911 didn't exist and 700-1000 didn't exist.
11:16:40 <mroman> how can he advance 300 years from 700 to 1000 if the year 700 didn't exist in the first place?
11:17:46 -!- shikhin_ has changed nick to shikhin.
11:19:04 <boily> mrhelloman. they saved on non-existing years by recycling one that never happened in the first place hth
11:19:14 <boily> AndhelloDaan. it's him, who else?
11:21:07 <mroman> AndoDaan: the pope I think.
11:21:48 <mroman> I just know that there are conspiracies about years being skipped
11:21:55 <mroman> and no sane man would do that
11:22:08 <mroman> so I just assumed it has a religous background to do so
11:22:25 <mroman> I would advance the calender to 3145
11:22:28 <mroman> but I'm no sane man :p
11:23:15 <mroman> AndoDaan: http://en.wikipedia.org/wiki/Phantom_time_hypothesis
11:23:23 <mroman> that's one of those conspiracies.
11:24:49 <mroman> "One theory ran that one pope wanted to be the pope of record for 1000 AD, so he got there by advancing the calendar 300 years. "
11:25:07 <mroman> He could've just asked god for him to live another 300 years but ok...
11:25:32 <AndoDaan> Maybe he hoped to bring about the second coming.
11:25:37 <mroman> "Another theory ran that the church had created historical documents predicting future events, and when they didn’t happen they just made up the history to match the documents, stuck it in and claimed that the predictions had come true. "
11:27:00 <orin> There's also the weird Fomenko theory
11:27:16 -!- boily has quit (Quit: PLUVIOUS CHICKEN).
11:27:23 <HackEgo> [wiki] [[Axo]] http://esolangs.org/w/index.php?diff=42647&oldid=42357 * Oerjan * (+38) table style, fmt, template
11:27:36 <orin> Which claims that various events prior to 1000 were postdated copies of events that happened after
11:28:45 <orin> Apparently Solomon and Suleiman the Magnificent are the same person
11:29:44 <Taneb> Pseudohistory is entertaining sometimes
11:34:04 -!- idris-bot has quit (Ping timeout: 246 seconds).
11:36:49 -!- idris-bot has joined.
11:38:57 -!- AnotherTest has joined.
11:39:13 <HackEgo> [wiki] [[POGAACK]] http://esolangs.org/w/index.php?diff=42648&oldid=42397 * Oerjan * (-21) Something went wrong with that last edit. Also link.
11:41:38 <HackEgo> [wiki] [[Object oriented thue]] http://esolangs.org/w/index.php?diff=42649&oldid=42481 * Oerjan * (+11) intro fmt
11:42:44 <orin> I have no way of proving that anything happened prior to ~1996
11:44:55 <mroman> orin: How old were you 1996?
11:45:29 <orin> assuming the previous three years actually happened
11:45:35 <mroman> but are you sure that it really was the year 1996?
11:45:41 <mroman> knowing that some years might not have existed at all.
11:45:49 <orin> Well it could have been the year 0
11:46:31 <orin> which would make this year 19
11:47:24 <orin> Alternately, we could fix 1970 as year 0
11:47:26 <HackEgo> [wiki] [[Gibberish (programming language)]] http://esolangs.org/w/index.php?diff=42650&oldid=42588 * Oerjan * (+64) link, tables, link description
11:48:33 <mroman> using 1970 as year 0 sounds reasonable.
11:51:35 <orin> making Alan Shepard the first man on the moon
11:51:56 <FireFly> What is 1970? I think year 0 is year 0
11:51:57 <HackEgo> [wiki] [[Special:Log/move]] move * Oerjan * moved [[ASCII art/mandelbrot]] to [[User:Esowiki201529A/ASCII art/mandelbrot]]: I don't think this should be a main namespace article all by itself
11:52:50 <orin> it would allow us to more easily convert unix time to years
11:53:12 <oerjan> didn't we use to have subpages in User:
12:07:54 <HackEgo> [wiki] [[Hashes]] http://esolangs.org/w/index.php?diff=42652&oldid=42493 * Oerjan * (-21) Undo revision 42493 by [[Special:Contributions/Esowiki201529A|Esowiki201529A]] ([[User talk:Esowiki201529A|talk]]) (doesn't work)
12:10:59 <oerjan> the wiki is nearly locking up again :(
12:11:48 <HackEgo> [wiki] [[Gibberish (disambiguation)]] http://esolangs.org/w/index.php?diff=42653&oldid=42574 * Oerjan * (+14) We seem to have a template for this
12:14:49 -!- AndoDaan_ has joined.
12:16:11 -!- AndoDaan has quit (Ping timeout: 264 seconds).
12:18:38 -!- AndoDaan has joined.
12:21:40 -!- AndoDaan_ has quit (Ping timeout: 246 seconds).
12:22:08 -!- GeekDude has joined.
12:29:16 -!- Patashu has quit (Ping timeout: 256 seconds).
12:33:17 -!- AndoDaan has quit (Ping timeout: 272 seconds).
12:33:44 <HackEgo> [wiki] [[420]] N http://esolangs.org/w/index.php?oldid=42654 * Vriskanon * (+2633) Added 420 in celebration of 4/20. Code is a derivative of Chicken.
12:34:08 -!- oerjan has quit (Quit: leaving).
12:34:28 <HackEgo> [wiki] [[User:Vriskanon]] M http://esolangs.org/w/index.php?diff=42655&oldid=42641 * Vriskanon * (+10) /* Joke Languages */ Added 420 credit
12:35:08 <HackEgo> [wiki] [[Joke language list]] M http://esolangs.org/w/index.php?diff=42656&oldid=42627 * Vriskanon * (+76) /* General languages */ Added 420
12:49:29 -!- shikhin has quit (Ping timeout: 250 seconds).
12:59:09 -!- nszceta has joined.
13:26:24 <HackEgo> [wiki] [[420]] M http://esolangs.org/w/index.php?diff=42657&oldid=42654 * Vriskanon * (+1) /* Commands */ Fixed an error in table
13:30:11 <HackEgo> [wiki] [[AFTL]] M http://esolangs.org/w/index.php?diff=42658&oldid=42642 * Vriskanon * (+163) /* Commands */ Added spacing clarification
13:32:54 -!- zadock has quit (Quit: Leaving).
13:39:30 <mroman> orin: but Fomenko is probably the sanest of them all
13:53:48 -!- `^_^v has joined.
13:56:57 -!- ais523 has joined.
14:19:40 <tswett> Y'know, my favorite large number is one I like to call "the largest reasonable number".
14:20:17 <tswett> The largest number representable in the calculus of constructions using no more than a million symbols.
14:21:06 <tswett> Of course, that's a rather ambiguous definition. What, exactly, is "the calculus of constructions", and what counts as a "symbol", and how do you represent a number in the CoC.
14:24:11 -!- variable has joined.
14:25:42 <mroman> I like the notation of "reasonably large numbers"
14:27:11 <mroman> I call every number reasonable that can be expressed as a sum of distinct square roots.
14:27:50 <mroman> and I call numbers of the form n = sqrt(a) + sqrt(b) where (a - b) = n super reasonable
14:28:02 <mroman> (I hope there aren't too many of them)
14:28:11 <mroman> but there are too many
14:28:26 <mroman> Can't every number be expressed as the sum of two squares actually?
14:29:06 <mroman> but what about square roots.
14:29:09 <ais523> (a - b) = sqrt(a) + sqrt(b); thus (a - b)² = (sqrt(a) + sqrt(b))²; thus a² - 2ab + b² = a + b + 2×sqrt(a×b)
14:29:22 <ais523> mroman: even more numbers can be expressed as the sum of two square roots
14:29:38 <ais523> e.g. 3 is not the sum of two squares
14:29:45 <ais523> but it's sqrt(1) + sqrt(4)
14:30:14 <mroman> obviously you can do that with every number ;)
14:30:26 <ais523> a necessary condition for a number to be super reasonable is that a×b is a square number
14:30:43 <ais523> yep, super reasonable is harder
14:31:11 <mroman> sqrt(4) + sqrt(1) is 3
14:31:49 <mroman> It'd be more fun if the numbers to be square rooted can't exceed the number itself
14:32:11 <ais523> in that case it's impossible for any but very small numbers
14:32:22 <ais523> because most numbers are greater than twice their own square root
14:32:33 <ais523> this super reasonable thing is more interesting though
14:32:36 <mroman> well you can use multiple square roots
14:32:40 <mroman> just not the same one twice.
14:34:14 <mroman> sqrt(1) + sqrt(4) would be illegal then
14:35:03 <mroman> I need to come up with more useful things.
14:47:27 -!- shikhin has joined.
14:47:27 -!- shikhin has quit (Client Quit).
14:47:51 -!- shikhin has joined.
14:50:10 -!- rdococ has joined.
15:01:18 <mroman> ais523: What about numbers that can't be divided by any sum of two of its factors.
15:01:31 <mroman> Like 6 is not such a number because 1+2 = 3 and 3 divides 6
15:01:51 <mroman> 8 however 1,2,4,8 is such a number.
15:02:14 <ais523> I have a feeling that there's a simple rule here
15:02:24 <mroman> probably with the number 3
15:02:29 <ais523> along the line of "any number with three different prime factors"
15:02:35 <ais523> but that's not necessary
15:20:21 -!- GeekDude has quit (Quit: {{{}}{{{}}{{}}}{{}}} (www.adiirc.com)).
15:35:12 <HackEgo> /home/hackbot/hackbot.hg/multibot_cmds/lib/limits: line 5: exec: `echo: not found
15:35:27 <HackEgo> bash: line 1: 293 Done echo [[]]ax \ 294 Segmentation fault | dc
15:35:48 <izabera> myndzi: stop adding penises -_-
15:38:25 <izabera> \o/ \o/ \o/ \o/ \o/ \o/ \o/ \o/ \o/ \o/ \o/ \o/ \o/ \o/ \o/ \o/ \o/ \o/ \o/ \o/ \o/ \o/ \o/ \o/ \o/ \o/ \o/ \o/ \o/ \o/ \o/ \o/ \o/ \o/ \o/ \o/ \o/ \o/ \o/ \o/ \o/ \o/ \o/ \o/ \o/ \o/ \o/ \o/ \o/ \o/ \o/ \o/ \o/ \o/ \o/ \o/ \o/ \o/ \o/ \o/ \o/ \o/ \o/ \o/ \o/ \o/
15:41:07 -!- PinealGlandOptic has joined.
15:44:34 <fizzie> I think there are just limits.
15:46:19 -!- ais523 has quit (Remote host closed the connection).
15:52:15 <FireFly> ...dc shouldn't segfault on [[]]ax, should it? What's happening there?
15:53:22 <FireFly> Oh huh, it just pushes '[' as a string and then tries to execute that?
16:07:23 <fizzie> Yes, I guess it's not very robust w.r.t. unbalanced brackets.
16:07:38 <HackEgo> [wiki] [[AFTL]] M http://esolangs.org/w/index.php?diff=42659&oldid=42658 * Vriskanon * (+23) /* Commands */ Changed inherant looping
16:07:52 <fizzie> Probably you're not "supposed" to be able to enter such.
16:13:56 -!- Somelauw has joined.
16:14:24 <Somelauw> What's a good way to represent negative numbers in brainfuck-like languages without having to special case.
16:15:02 <Somelauw> I noticed multiplication works most of the time because of wrapping
16:19:51 -!- variable has changed nick to trout.
16:30:13 <int-e> FireFly: beautiful
16:30:32 <FireFly> izabera's program, not mine
16:30:50 <FireFly> Even this segfaults, it seems..
16:31:09 <HackEgo> Usage: dc [OPTION] [file ...] \ -e, --expression=EXPR evaluate expression \ -f, --file=FILE evaluate contents of file \ -h, --help display this help and exit \ -V, --version output version information and exit \ \ Email bug reports to: bug-dc@gnu.org .
16:31:28 <FireFly> I thought GNU software was generally a bit more stable than that
16:31:30 <int-e> `learn dc is short for "dump core". (try it out yourself: dc -e '[')
16:31:33 <HackEgo> Learned 'dc': dc is short for "dump core". (try it out yourself: dc -e '[')
16:35:44 <Somelauw> but something more easy to represent comparision operators with
16:36:31 <Somelauw> izabera: I think it works all the time for plus, minus, times and divide as long as the implementation is wrapped
16:41:41 <fizzie> I think I knew that about -e '[', but had totally forgotten.
16:43:05 <fizzie> `run dc -e ']' # at least this has an error message
16:43:06 <HackEgo> dc: ']' (0135) unimplemented
16:49:25 -!- lleu has quit (Ping timeout: 246 seconds).
16:50:36 -!- nszceta has quit (Ping timeout: 250 seconds).
17:00:13 -!- zadock has joined.
17:01:29 <HackEgo> [wiki] [[Twocode]] http://esolangs.org/w/index.php?diff=42660&oldid=40158 * GermanyBoy * (+628) /* Examples/Minsky machine */ new section
17:03:46 -!- b_jonas has joined.
17:05:02 <J_Arcane> So I dredged up an old bit of code for an RNG using Racket generators. Anyone wanna sanity check my math? http://pasterack.org/pastes/80800
17:09:37 <HackEgo> [wiki] [[Onecode (GermanyBoy)]] http://esolangs.org/w/index.php?diff=42661&oldid=41662 * GermanyBoy * (+45) /* Grammar */
17:10:17 -!- shikhin_ has joined.
17:10:46 -!- shikhin has quit (Ping timeout: 248 seconds).
17:11:01 -!- shikhin_ has changed nick to shikhin.
17:22:24 <zzo38> If dc has something wrong then you can post a bug report to GNU
17:22:32 <zzo38> (You can also try to fix it by yourself)
17:23:08 <HackEgo> [wiki] [[AFTL]] M http://esolangs.org/w/index.php?diff=42662&oldid=42659 * Vriskanon * (-5) /* Hello, world! program */ Fixed Hello, world! program
17:25:19 -!- AndoDaan has joined.
17:26:21 <HackEgo> [wiki] [[AFTL]] M http://esolangs.org/w/index.php?diff=42663&oldid=42662 * Vriskanon * (+42) /* Sample programs */ Added Cat program
17:29:01 <Taneb> `dc -e "1 2 3 + + p"
17:29:05 <HackEgo> dc: dc: '"' (042) unimplemented \ 6 \ '"' (042) unimplemented
17:29:09 <Taneb> `run dc -e "1 2 3 + + p"
17:32:08 -!- Somelauw has quit (Ping timeout: 252 seconds).
17:36:32 -!- trout has quit (Ping timeout: 250 seconds).
17:48:12 -!- nszceta has joined.
17:49:25 -!- nszceta has quit (Client Quit).
17:50:20 -!- Somelauw has joined.
17:51:12 -!- aretecode has joined.
18:00:19 -!- Somelauw has quit (Ping timeout: 244 seconds).
18:04:03 -!- variable has joined.
18:08:08 <HackEgo> [wiki] [[Fortob]] http://esolangs.org/w/index.php?diff=42664&oldid=40525 * GermanyBoy * (+276) /* Method reference */
18:09:06 -!- Vorpal has quit (Ping timeout: 244 seconds).
18:10:59 -!- Phantom_Hoover has joined.
18:21:54 -!- Somelauw has joined.
18:23:39 -!- Vorpal has joined.
18:24:31 -!- nortti has changed nick to lawspeaker.
18:25:10 -!- lawspeaker has changed nick to nortti.
18:46:02 -!- AndoDaan_ has joined.
18:46:07 -!- AndoDaan_ has quit (Client Quit).
18:46:29 -!- AndoDaan_ has joined.
18:47:20 -!- AndoDaan has quit (Ping timeout: 244 seconds).
19:03:52 -!- teuchter has joined.
19:06:58 -!- choochter has quit (Ping timeout: 244 seconds).
19:14:50 -!- guydreich has joined.
19:16:25 -!- AndoDaan has joined.
19:17:20 <zzo38> Is it possible to tell Mozilla and other software to set a proxy for only secure connections? Is there such a proxy that decrypts everything so that it doesn't cause problems with the user client causing errors with it?
19:17:28 -!- AndoDaan_ has quit (Ping timeout: 246 seconds).
19:18:14 -!- teuchter has quit (Ping timeout: 248 seconds).
19:21:05 -!- AndoDaan has quit (Ping timeout: 256 seconds).
19:21:31 <fizzie> I think that's generally called a man-in-the-middle attack.
19:24:42 -!- hjulle has joined.
19:25:59 <zzo38> They are files which don't need to be secure but the server insists on entering secure mode, yet it does not even do it using a compatible cipher and then it is error.
19:26:11 -!- AndoDaan has joined.
19:28:19 -!- AndoDaan_ has joined.
19:31:02 -!- AndoDaan has quit (Ping timeout: 248 seconds).
19:31:23 -!- Sprocklem has joined.
19:31:44 -!- AndoDaan_ has quit (Read error: Connection reset by peer).
19:32:53 -!- roasted42 has joined.
19:32:53 -!- roasted42 has quit (Changing host).
19:32:53 -!- roasted42 has joined.
19:32:53 -!- roasted42 has changed nick to TheM4ch1n3.
19:33:29 -!- TheM4ch1n3 has quit (Read error: Connection reset by peer).
19:35:55 -!- rdococ has quit (Quit: Page closed).
19:43:31 <fizzie> I think normally if you tell a browser to use a proxy for the 'https' scheme, it will just use the 'CONNECT' request method, so you would need to use some sort of transparent proxy setup, and then there's the certificate problem. If you just want to provide http:// endpoints for something behind a https-only server, and don't need it to be "invisible" to the users, you could just set up a ...
19:43:37 <fizzie> ... regular web server as a "reverse proxy", so that when the user asks for http://proxy/foo, it will fetch the resource from https://server/foo.
19:44:30 <zzo38> Some servers use the wrong certificate so I want to ignore the certificate
19:45:46 <zzo38> I have used CONNECT proxy before, not only for HTTP and HTTPS but also to connect to MUD servers that temporarily could not be reached from my computer for some reason
19:46:11 <zzo38> Do you know if Wikipedia has a userbox for linking to FOAF data?
19:48:03 -!- oerjan has joined.
19:52:47 <pikhq> fizzie: That is correct.
19:53:01 <pikhq> fizzie: It's the only way for https to work *sensibly* through a proxy.
19:53:31 <pikhq> Other such schemes (where the proxy injects! itself! via firewall funkiness) obviously breaks horribly on https unless the browsers are set to trust the proxy's cert.
19:54:36 <pikhq> HTTP CONNECT is kinda neat as a way of tunneling a TCP connection.
19:54:43 <pikhq> *If* obviously quite limited in scope.
20:00:18 <zzo38> I do find HTTP CONNECT useful for use as a general-purpose proxy sometimes, since there are some such proxies
20:00:35 -!- GeekDude has joined.
20:00:55 <zzo38> Although what I was asking, this doesn't do.
20:02:19 <zzo38> I certainly don't need it to be invisible to users but do need it to be capable of working with the same domain name (although there is a way around that too of course, such as by using hosts files)
20:07:22 -!- nszceta has joined.
20:09:48 <HackEgo> [wiki] [[Harp]] http://esolangs.org/w/index.php?diff=42665&oldid=42555 * Oerjan * (+8) clarify
20:11:15 <HackEgo> [wiki] [[AFTL]] http://esolangs.org/w/index.php?diff=42666&oldid=42663 * Vriskanon * (+1874) Added Python Interpreter
20:18:26 -!- b_jonas has quit (Remote host closed the connection).
20:22:37 <zzo38> I had idea making the decentralized poll survey system out of RDF
20:24:50 -!- Somelauw has quit (Quit: WeeChat 0.4.2).
20:41:54 <tswett> How many integers are the sum of two square roots of integers, neither of which is a perfect square?
20:44:57 -!- lleu has joined.
20:45:14 <oerjan> except 0 if you squint the right way
20:45:57 <oerjan> also i vaguely recall some relevant theorem
20:46:00 <tswett> Lessee, when is sqrt(a) + sqrt(b) an integer? Is there a Diophantine equation for that?
20:46:33 <tswett> It's an integer whenever a + b + 2 sqrt(ab) is a perfect square.
20:46:36 <oerjan> (sqrt(a) + sqrt(b))^2 is then also an integer
20:47:15 <oerjan> which means 4ab must be a perfect square, minimum
20:48:41 <oerjan> which means every factor of a or b which _isn't_ a square must be equal
20:49:21 <oerjan> so a = n*x^2, b = n*y^2
20:49:40 <tswett> So it's (x^2 + y^2) sqrt(n), aye?
20:49:49 <tswett> Which is never an integer when n isn't a perfect square, aye?
20:50:21 <tswett> But the conclusion is right, aye?
20:50:23 <quintopia> but the sqrt n part is what matters
20:50:29 <tswett> So this Turing machine does not halt.
20:54:45 <oerjan> also, the "except 0" looks right too.
20:55:47 <quintopia> it being the sum of all pairs of square roots of the same number
20:57:37 <quintopia> it doesnt matter to the proof above whether we allow one of the roots to be negative, except in that case, yes?
21:01:34 -!- Patashu has joined.
21:04:23 <HackEgo> [wiki] [[Duck Duck Goose]] http://esolangs.org/w/index.php?diff=42667&oldid=42579 * Oerjan * (+4) /* Sample programs */ links and section level
21:05:03 * oerjan finds it curious that the page takes ages to load _after_ HackEgo has announced it
21:05:57 -!- `^_^v has quit (Quit: This computer has gone to sleep).
21:06:01 <oerjan> which happened instantly this time
21:11:42 <HackEgo> [wiki] [[4]] http://esolangs.org/w/index.php?diff=42668&oldid=42613 * Oerjan * (-7) formatting, link
21:16:24 -!- aretecode has quit (Quit: Toodaloo).
21:19:36 <HackEgo> [wiki] [[Element]] http://esolangs.org/w/index.php?diff=42669&oldid=42610 * Oerjan * (+40) section levels, links
21:24:10 -!- Patashu has quit (Ping timeout: 246 seconds).
21:31:31 <HackEgo> [wiki] [[Basilisk]] http://esolangs.org/w/index.php?diff=42670&oldid=42626 * Oerjan * (+61) intro does not need header, formatting, typo
21:34:39 <HackEgo> [wiki] [[420]] http://esolangs.org/w/index.php?diff=42671&oldid=42657 * Oerjan * (-27) intro format, section levels
21:37:26 -!- _augur has changed nick to augur.
21:39:47 <HackEgo> [wiki] [[AFTL]] http://esolangs.org/w/index.php?diff=42672&oldid=42666 * Oerjan * (-21) intro format, section levels, link
21:56:10 <fizzie> oerjan: Maybe it has to swap out MediaWiki in order for HackEgo to speak.
21:56:28 <fizzie> oerjan: Alternatively, all 104 people on channel instantly try to visit whenever HackEgo says something.
21:57:12 <olsner> 104 people, that's ... something
21:57:27 -!- boily has joined.
22:01:48 -!- nszceta has quit (Quit: Textual IRC Client: www.textualapp.com).
22:10:20 -!- AnotherTest has quit (Ping timeout: 245 seconds).
22:37:44 <oerjan> eek i disagree with spj but i don't have ghc HEAD to test with...
22:41:22 <tswett> All right, I'm doing this. I'm making this happen.
22:41:33 <tswett> I'm starting the Lepwick project again.
22:43:11 <zzo38> What kind of project is that?
22:46:38 <tswett> Why, what kind of project *isn't* it?
22:46:56 <tswett> The idea is for it to be a legal, political, and economic simulation.
22:50:48 <tswett> Well, ideally other people will also participate eventually.
22:52:33 <int-e> oerjan: it's not very hard to build ghc you know :P
22:53:25 -!- GeekDude has quit (Ping timeout: 264 seconds).
22:56:10 <int-e> I dunno, you may have a point there. How can you suffer Windows?
22:56:23 <Jafet> Surely the point of reference there is the difficulty of building anything at all on windows
22:56:39 <oerjan> i think i should ban you all.
22:56:53 <int-e> that would be a big time-saver
22:57:06 <Jafet> for everyone involved
22:57:47 <Sgeo_> I've seen Windows referred to as 'the securest one'
22:57:49 -!- shikhin has quit (Quit: Lost terminal).
22:58:16 <Sgeo_> https://www.blackhat.com/docs/eu-14/materials/eu-14-Selvi-Bypassing-HTTP-Strict-Transport-Security.pdf
22:58:32 <Sgeo_> Windows: • NTPv3but…
22:58:32 <Sgeo_> • Synchronizationeach7days.
22:58:41 <Sgeo_> • Doesn’tacceptmorethan15hoursincrement/
22:59:13 <int-e> why all those tabs?
22:59:29 <Sgeo_> Because copy/pasted from pdf slides
23:01:28 <tswett> Hey, what should the server's hostname be?
23:04:46 <int-e> Sigh I need a faster PC so that I can build ghc in less than 20 minutes...
23:06:03 <Jafet> You just need a prescient one so that it builds ghc right before you need it to
23:07:13 <orin> or just set ascript to build the newest one when it is released
23:07:38 -!- GeekDude has joined.
23:07:46 <int-e> orin: that's not so helpful for following a git repo.
23:07:57 -!- boily has quit (Quit: PEDIATRIC CHICKEN).
23:08:35 <Taneb> New Munchkin strategy: hide the die so the damned thief can't steal your stuff
23:09:34 <int-e> Ah, Eddie the ship's computer. ("Hi there!" said the ship's computer.)
23:22:59 <Taneb> Anyway, I ended up tying a game of Munchkin
23:25:45 <int-e> oerjan: Fwiw, current head still accepts T.hs and i is not bottom, and of type Proxy (Eq Int => Bool)
23:26:24 <shachaf> whoa, Eddie the Shipboard Computer
23:26:28 <int-e> And it took 28 minutes to build, and that's without docs and only the dyn way.
23:26:41 <Taneb> quintopia, it's a D6, used for running away and stealing thingw
23:30:22 <oerjan> int-e: what about http://oerjan.nvg.org/haskell/TypeableExploits/ConTyp1.hs which is my attempt at what spj is _really_ trying to say, i think
23:30:59 <oerjan> (the fact i'm not actually _using_ Typeable in the posted file makes the literal interpretation nonsense)
23:31:32 <int-e> oerjan: how did you get the * and * -> * in the proxy signatures?
23:31:40 <oerjan> i am not sure whether it will work or not, it fails in 7.8 but Typeable works completely differently
23:32:19 <int-e> oerjan: g :: Proxy (* -> *) ((->) (Eq Int)) <-- there
23:32:46 <oerjan> oh -fprint-explicit-kinds
23:33:26 -!- Phantom_Hoover has quit (Read error: Connection reset by peer).
23:33:33 <int-e> oerjan: ok, first it works in 7.10.1: j prints Eq Int -> Bool
23:34:00 <int-e> And it works in head as well.
23:34:33 <int-e> uhm. that's going through the show instance of typerep
23:34:45 <oerjan> oh wait, obviously they don't have any => handling for typerep
23:34:58 <oerjan> so it uses the default ->
23:35:02 <int-e> so that's expected.
23:35:11 <oerjan> ok then i can post that example.
23:39:08 <int-e> g :: Proxy ((->) (Eq Int))
23:39:09 <lambdabot> <hint>:1:1: parse error on input ‘:’
23:39:55 <int-e> (or Proxy (* -> *) ((->) (Eq Int)) with explicit kinds)
23:40:16 <oerjan> darn do i call you int-e or Bertram :P
23:40:28 <int-e> oerjan: int-e, I have a trac account too
23:41:30 <oerjan> i get confused by everyone calling each other by real name in trac whether or not their nicks match
23:42:12 <int-e> Well I don't care much.
23:43:27 <int-e> Ah. Figured it out :)
23:48:31 <oerjan> ordinary typeREp should work for that
23:49:14 <int-e> However, typeRep (h g) does fail... I guess that was the whole point.
23:52:19 <oerjan> hm i suppose you don't need all the other variables
23:52:35 <oerjan> i (Proxy :: Proxy (Eq Int => Bool)) ought to work
23:52:54 <int-e> ghci> i (Proxy :: Proxy (Eq Int => Int))
23:58:07 <shachaf> This is the same sort of thing as what I was doing to get a TypeRep for Ord Int?
23:58:21 <oerjan> shachaf: just pointing out that you still can get hold of Typeable (Eq Int => Int) etc. in HEAD, you just need to slightly circumvent the check
23:58:54 <oerjan> shachaf: well it started as that, anyway
23:59:35 <oerjan> now they put the ability to do Typeable (Ord Int) back, but tried to disallow =>
00:00:59 <oerjan> so it boils down to a type restricted version of typeRep that explicitly _avoids_ using the evidence for the whole type.
00:01:25 <shachaf> Right, that's the same sort of thing.
00:01:50 <shachaf> Except for the non-obvious fact that (k => t) is of the form (a b), I guess.
00:02:20 <oerjan> they should sort of change that, if they really want it to count as impredicative
00:02:32 <shachaf> Calling it impredicative is kind of strange too.
00:02:45 <shachaf> But so is instantiating a type variable to (k => t).
00:02:47 <oerjan> well spj seems to like doing that
00:05:12 <shachaf> variable: Who are you, anyway?
00:05:25 <shachaf> You're in all these channels and you have all these nicks.
00:05:52 <oerjan> clearly variable is secretly Lilax
00:06:29 <Sgeo_> "ACME is a protocol for automating the management of domain-validation certificates, based on a simple JSON-over-HTTPS interface. This repository contains the specification for ACME.
00:06:37 <Sgeo_> Words more informative than 'API'? What is this madness?
00:47:23 <orin> the new way to spell "and" is amp
00:47:58 -!- variable has quit (Ping timeout: 272 seconds).
00:52:37 -!- oerjan has quit (Quit: Nite).
01:14:44 -!- GeekDude has quit (Quit: {{{}}{{{}}{{}}}{{}}} (www.adiirc.com)).
01:20:14 <zzo38> While watching a show recorded on a VHS tape I noticed that the tape counter's hours and minutes showed the same time as the time I was watching it.
01:34:19 <quintopia> that's bound to happen if you start watching at noon. (and if it's the minutes and seconds that match...well it's pretty much guaranteed to happen once per movie)
01:36:20 <zzo38> Yes, but I didn't start watching at noon (and the tape wasn't started from the beginning either; it was from where it left off)
01:41:53 -!- doesthiswork has joined.
02:03:29 <zzo38> Now I invented RDF-survey specification; it is pretty simple and here is the full specification:
02:03:31 <zzo38> A single URI is defined for this purpose: <gopher://zzo38computer.org/1ns/foaf:survey> This will be the predicate of a triple where the subject is the person/agent answering the survey and the object is the node identifying the answer set; the rdf:type of that node is the URI identifying the survey itself.
02:06:14 -!- Decim has joined.
02:06:46 <Decim> Ok so like what programs other than minghc from the haskell site can run haskell or is that all
02:09:10 <zzo38> There are other Haskell implementations but most programs are meant for GHC
02:09:49 <orin> iirc GHC is considered the defqcto standard
02:11:12 <zzo38> If no extensions are used then you can use a different implementation but the GHC extensions are very useful to have.
02:14:02 <orin> You know what would be nice? A version of CPP that expands macros but not includes.
02:15:31 <zzo38> Possibly with AWK you can make it to comment out all of the includes and then you can make it like that
02:24:49 <zzo38> /^#include/{$0="//"$0}1
02:27:00 <zzo38> AWK is very good for that kind of stuff.
02:27:29 <zzo38> As it turns out, AWK is also good for implementing Deadfish.
02:35:53 <Decim> Did someone say deadfish!
02:36:15 <zzo38> Yes....?? Isn't it?
02:38:00 <zzo38> We can implement Deadfish with everything including C and AWK and dc and assembly language and TeX and so on but not Deadfish (but it is possible to implement Deadfish while sitting in the Deadfish cafe)
02:40:01 <zzo38> Even on Nintendo Family Computer, with more than 16-bits.
02:40:31 <zzo38> Do you know how to program a Famicom?
02:50:45 -!- variable has joined.
03:02:45 <zzo38> I also worked a lot making the Z-machine implementation in Famicom. It is faster than Commodore 64 (almost twice as much)
03:10:47 -!- variable has changed nick to function.
03:11:41 -!- function has changed nick to executes.
03:11:47 -!- executes has changed nick to function.
03:17:25 <zzo38> I have not quite decided how to implement vocabulary lookup though
03:18:23 <Decim> I'm looking into famicom
03:34:18 -!- bb010g has joined.
03:43:39 -!- sebbu has quit (Ping timeout: 244 seconds).
04:05:58 -!- Decim has quit (Remote host closed the connection).
04:08:29 -!- doesthiswork has quit (Quit: Leaving.).
04:18:07 <zzo38> This is I made up most of the Famicom Z-machine implementation http://sprunge.us/PjUc http://sprunge.us/YLZE Do you think is OK, do you have other complain about it please?
04:29:56 -!- jsilver has quit (Ping timeout: 252 seconds).
04:30:42 -!- Sprocklem has quit (Quit: 'Tis time to say goodbye, as I bid y'all farewell, my time for sleep is nigh, and bed seems oh so swell).
04:31:03 -!- function has quit (Quit: 1 found in /dev/zero).
04:31:19 -!- variable has joined.
04:41:08 -!- doesthiswork has joined.
05:30:23 -!- sebbu has joined.
05:31:00 -!- sebbu has quit (Changing host).
05:31:00 -!- sebbu has joined.
05:32:08 -!- doesthiswork has quit (Quit: Leaving.).
05:35:44 -!- AndoDaan has joined.
05:44:59 -!- PinealGlandOptic has quit (Ping timeout: 250 seconds).
06:00:12 -!- pikhq has quit (Ping timeout: 272 seconds).
06:01:07 -!- rdococ has joined.
06:05:47 -!- hjulle has quit (Ping timeout: 250 seconds).
06:19:11 -!- zadock has quit (Quit: Leaving).
06:56:15 -!- zadock has joined.
07:11:30 -!- Insipid has joined.
07:15:12 -!- iamevn_ has joined.
07:18:30 -!- variable has quit (Read error: Connection reset by peer).
07:18:45 -!- wieldablesquid has quit (Ping timeout: 265 seconds).
07:24:40 -!- Insipid has quit (Quit: Leaving.).
07:24:53 -!- Insipid has joined.
07:29:16 -!- Insipid has quit (Ping timeout: 256 seconds).
07:30:18 -!- b_jonas has joined.
07:35:39 -!- f|`-`|f has quit (Ping timeout: 256 seconds).
07:36:15 -!- f|`-`|f has joined.
07:44:26 -!- AndoDaan has quit (Read error: Connection reset by peer).
07:45:19 -!- AndoDaan has joined.
07:57:09 <lambdabot> ‘id’ (imported from Data.Function),
08:02:19 -!- Insipid has joined.
08:13:07 <mroman> ghci has it as "last result"
08:30:10 -!- Insipid has left.
08:43:55 -!- Patashu has joined.
08:48:32 -!- Patashu has quit (Remote host closed the connection).
08:48:49 -!- Patashu has joined.
08:57:48 <HackEgo> [wiki] [[420]] http://esolangs.org/w/index.php?diff=42673&oldid=42671 * Vriskanon * (+4962) /* Sample programs */ Added Hello, world! program (copied from Chicken's page)
09:17:08 -!- orin has quit (Ping timeout: 250 seconds).
09:19:10 -!- orin has joined.
09:34:15 -!- orin has quit (Ping timeout: 264 seconds).
09:35:36 -!- orin has joined.
09:43:31 <b_jonas> fungot, is it true that to remain binary compatible with user-space context/coroutine switching, ABIs cannot designate new registers in future CPUs as callee-saved, but must keep them as either scratch registers or registers you must restore at all boundaries?
09:43:31 <fungot> b_jonas: that's why i learned to get hugged without feeling strange. but the same idea
09:44:16 <fungot> AndoDaan: i don't plan to enter it, the full range of 256 values per channel is lessened understand why cons should have two loop variables, then... wait... uhm...
09:45:15 <b_jonas> fungot: no, we actually support 16 bit depth here, and in fact some of our channels have over 9000 nicks joined
09:45:15 <fungot> b_jonas: laml is two things in te second statement of a program written in scheme
09:45:39 -!- rdococ has quit (Ping timeout: 246 seconds).
09:46:55 -!- Insipid has joined.
09:47:09 <mroman> It's somehow weird that movies claim the world has gone bad
09:47:19 <mroman> like it was better 500 years ago
09:47:46 <Taneb> 500 years ago serfs could be serfs, lords can be lords, and everyone knew what there place was
09:48:08 <Taneb> Nowadays it's all mixed up
09:48:26 -!- Insipid has left.
09:54:01 <FireFly> fungot: what do yout think about the mix-up?å
09:54:01 <mroman> and Tanebs could be Tanebs
09:54:01 <fungot> FireFly: kuribas, because syntax-rules doesn't integrate scheme the pattern language can include, e.g. ( blah :some 3 ( something) is instance local ( afaik)
09:54:56 <FireFly> (blah :some 3 (something) is instance local (afaik)), got it
09:59:37 <mroman> fungot: Would you like the domain "fungot.sucks"?
09:59:38 <fungot> mroman: the swingle singers... which may be what you're looking for? :) that just makes you look like that.
10:10:29 -!- orin has quit (Ping timeout: 245 seconds).
10:12:21 -!- orin has joined.
10:12:24 <Taneb> Hmm, I seem to have ended up with a tendency to write emoticons with multiple mouths
10:17:36 <HackEgo> [wiki] [[420]] M http://esolangs.org/w/index.php?diff=42674&oldid=42673 * Vriskanon * (+1) /* Commands */ Changed 'Chicken' name name
10:18:24 <mroman> Taneb: That's just your double-chin acting out.
10:18:57 <mroman> fungot: Are you a fitness trainer?
10:18:58 <fungot> mroman: of course. thanks. it'll need a few temp cells need to be specified in a certain time of year" is the name
10:20:08 <mroman> fungot: Would you train me?
10:20:09 <fungot> mroman: nobel watchers say neither mr bush nor mr blair has much chance of that before...
10:21:09 <mroman> I'm trying to beat 15 pull-ups
10:21:13 <mroman> but I'm stuck at around 12 :(
10:35:19 -!- boily has joined.
10:52:34 <Taneb> mroman, that's about 11 more than I can do!
10:54:38 <boily> taking it quieter and slower after a week of social life.
10:54:46 <boily> how's it on your end?
10:55:08 <Taneb> Well, last night I tried out a board game I bought recently
10:55:11 <Taneb> I found it pretty fun
10:55:16 <Taneb> (Avalon is the game)
10:55:27 <Taneb> (It's essentially The Resistance in Camelot)
10:56:00 <boily> still boardgaming :D
10:56:03 <mroman> Taneb: then you should start training ;)
10:58:14 <boily> Taneb: recently I played a few new games. I think I'm a deckbuilding addict.
10:59:02 <Taneb> I've challenged myself to see how good I can get at Magic without paying any money
10:59:44 <boily> we play Magic every lunch at work. I have Dominion, Tanto Cuore, Mage Wars, Space Realms, Quarriors...
11:00:04 <boily> going to buy Race for the Galaxy soon, but then there's Roll for the Galaxy too.
11:03:29 <shachaf> never mind, i need to go to sleep
11:05:39 <mroman> Taneb: the real secret is actually that it's not really hard nor does it take up a lot of time.
11:05:57 <mroman> You just need to devote like 15min of your day to fitness and that's really all there is.
11:06:36 <mroman> People seem to think you need to train for hours to get 30 push-ups, 15 pull-ups and the like which is utterly wrong.
11:07:04 <mroman> I sit in front of my computer all day except like 15min where I do some body weight exercises.
11:09:20 <Taneb> mroman, my problem is more space than time
11:14:09 <boily> let's try not falling asleep in the shower.
11:14:24 -!- boily has quit (Quit: OTOLITHIC CHICKEN).
11:15:08 -!- oerjan has joined.
11:15:31 -!- AndoDaan has quit (Ping timeout: 256 seconds).
11:16:29 -!- orin has quit (Ping timeout: 246 seconds).
11:18:34 -!- orin has joined.
11:18:56 -!- Lymia has quit (Changing host).
11:18:56 -!- Lymia has joined.
11:19:00 <Taneb> Also that doesn't really help with my pull-ups
11:19:26 <mroman> no trees around? No bars?
11:21:04 <Taneb> Most of the trees around lack low branches
11:22:40 * oerjan finds himself literally laughing maniackally
11:22:52 <oerjan> that means it must be a very good idea.
11:23:13 <Taneb> mroman, and I can't install a bar because this is rented accomodation and I'll only be here for another 2 months or so
11:23:43 <oerjan> just make it a minibar hth
11:24:45 <Taneb> I'm too tall for a minibar
11:26:29 <oerjan> but too short for the branches
11:26:48 <oerjan> solution, put the minibar under the branches and stand on it.
11:32:09 <Taneb> Unfortunately I don't have a minibar
11:34:53 <mroman> If you live in a city there's gotta be something you can do pull ups on
11:35:00 <mroman> even if it's a street sign :D
11:37:12 <Taneb> mroman, I'm damn near the edge of the city
11:37:35 <oerjan> i think they usually have a sign at the edge of a city hth
11:37:58 <oerjan> but i guess it might be crowded.
11:54:53 -!- zadock has quit (Quit: Leaving).
12:04:17 <mroman> https://www.youtube.com/watch?v=upUUWuJhvXk hth
12:08:27 -!- Patashu has quit (Ping timeout: 255 seconds).
12:38:46 -!- AndoDaan has joined.
12:45:05 <orin> go to a playground
12:45:12 <orin> use the monkey bars
12:50:12 <elliott> nobody has ever done one, ever
12:50:29 <Taneb> orin, I do not know any playground with monkey bars around here
12:59:05 <HackEgo> [wiki] [[Λιμπ]] http://esolangs.org/w/index.php?diff=42675&oldid=11870 * Esowiki201529A * (+14)
13:03:56 -!- hjulle has joined.
13:05:10 <HackEgo> [wiki] [[AFTL]] http://esolangs.org/w/index.php?diff=42676&oldid=42672 * Esowiki201529A * (+14) /* Hello, world! program */
13:19:31 <mroman> 18 Reasons Why You Don’t Get Laid"
13:19:54 <mroman> Can't I even read news know without these fucking pop-ups
13:20:04 <oerjan> thanks, now i'm wondering if sumo wrestler get laid (probably)
13:20:05 <mroman> that aren't really the good old pop-ups from the old days
13:20:31 <mroman> pop-ups used to be windows.
13:20:50 <mroman> now they are "static divs" injected into pages with javascript
13:21:21 <mroman> although I wonder what those 18 reasons could be...
13:21:41 <mroman> I can only think of one. And that one is enough so I don't even need the other 17 reasons.
13:21:44 <oerjan> 1. you spend all your time browsing web
13:22:31 <mroman> but I guess that could be one of those 17 other reasons.
13:23:56 <oerjan> Taneb: did that fetish society have any people wearing paper bags on their heads
13:24:07 <Taneb> oerjan, I do not believe so
13:24:11 <Taneb> But I did not stay very long
13:24:17 <oerjan> i guess there's no hope then
13:24:36 <oerjan> oh wait, blind people exist
13:24:38 <mroman> What would a paper bag over your head do?
13:24:42 <mroman> You can still have an ugly body.
13:24:43 <Taneb> I know exactly why I don't get laid
13:24:50 <mroman> Besides having an ugly face/head.
13:25:01 <mroman> fungot: Are you ugly too?
13:25:01 <fungot> mroman: how are you doing there? :p)
13:25:11 <mroman> Is it mocking me??!?!?!?
13:25:32 <b_jonas> fungot: give me test data because it's hard to write a program without it
13:25:32 <fungot> b_jonas: may i add that? since only " the result(s) of the objections about plt-specificness we need to know ( my " behaviors" you mentioned
13:26:05 <mroman> Taneb: you're butt ugly too?
13:26:10 <Taneb> mroman, nah, I'm asexual
13:26:21 <mroman> That's my reason number 2.
13:26:46 <Taneb> I do not believe so
13:27:53 <oerjan> yay an asexual pairing
13:33:07 <mroman> I actually have no idea if I'm butt ugly. I just assume so.
13:33:19 <mroman> It's something that you can't really judge by yourself I think.
13:34:29 -!- Sprocklem has joined.
13:34:52 <mroman> Judging by the reflection in the mirror and other people I'm at least ugly but not necessarily butt ugly.
13:40:25 <mroman> Hm. Theres 402 - Payment required.
13:47:05 <fizzie> I don't think it sees much use.
13:47:39 <b_jonas> mroman: that's just the temporary name assigned to the reserved code in earlier versions of the standard. the more correct localized message these days is 402 Virgin sacrifice required
13:48:46 <mroman> fungot: Apple uses it apparentely
13:48:47 <fungot> mroman: anywhere but sweden, apparently. i won't actually pay 50 cents for that :p
13:48:56 <mroman> fizzie: Apple uses it apparentely.
13:49:07 <mroman> fizzie: BUT PAYMENT IS REQUIRED! I WANT THOSE 50 CENTS!
13:49:29 <mroman> that should've been directed to fungot
13:49:30 <fungot> mroman: http://www.99-bottles-of-beer.net/ language-malbolge-995.html the last comment in http://esolangs.org/ wiki/ quadtree work, would just be better to have names like that
13:50:01 <fizzie> There's also the "418 I'm a teapot" response.
13:50:26 <b_jonas> mroman: the HTTP/1.1 rfc specifically says "reserved for future use" "http://www.w3.org/Protocols/rfc2616/rfc2616-sec10.html#sec10.4.3"
13:50:51 <b_jonas> I think HTTP/2 defines the meaning correctly and calls it its proper name
13:51:40 <b_jonas> only that's one of those w3c standards that are always under development and never released, like HTTP 5 or the new CSS standard
13:52:00 <mroman> hasn't that been released?
13:52:31 <fizzie> It's also a "living standard".
13:52:47 <fizzie> Or the version by WHATWG, anyway.
13:52:50 <b_jonas> apparently I'm not relaly following this junk
13:53:25 <b_jonas> now the question is, which response header gives the bounds for the age of the virgin?
13:53:38 <fizzie> I got the impression that W3C released some particular fixed version, while the WHATWG standard is just... living.
13:54:32 <fizzie> (And the W3C standard doesn't exactly match WHATWG.)
13:55:25 <b_jonas> probably WWW-Authenticate with some approperiate challenge typ
13:58:37 -!- b_jonas has set topic: Stenosteganography | https://dl.dropboxusercontent.com/u/2023808/wisdom.pdf http://codu.org/logs/_esoteric/ http://tunes.org/~nef/logs/esoteric/ | http://esolangs.org/.
14:04:48 <elliott> whatwg's standard is just "HTML" with no version
14:06:36 -!- Sprocklem has quit (Ping timeout: 272 seconds).
14:21:26 -!- `^_^v has joined.
14:28:02 <tswett> Duh, "claptrap" is what the hostname should be.
14:30:06 <b_jonas> fungot, why does this function have so many arguments?\
14:30:06 <fungot> b_jonas: i came across srfi-83 last night, couldn't get to sleep now. goodnight everybody!! i've flown in leslie gore and two dozen
14:30:17 <fungot> b_jonas: sarahbot is very much in the recursive call must be optimized. just a non-american living in american indeed.
14:32:31 <tswett> fungot: wait, what's *your* opinion of what the hostname should be?
14:32:31 <fungot> tswett: no clue really.) the name with a
14:32:55 <tswett> I guess "claptrap" is, in fact, a "name with 'a'".
14:42:27 -!- AndoDaan_ has joined.
14:45:34 -!- GeekDude has joined.
14:45:47 -!- AndoDaan has quit (Ping timeout: 246 seconds).
14:50:15 -!- TieSoul has joined.
14:52:41 -!- orin has quit (Quit: Lost terminal).
14:53:50 -!- `^_^v has quit (Ping timeout: 246 seconds).
14:53:58 -!- Sprocklem has joined.
14:56:59 -!- `^_^v has joined.
15:00:27 -!- Vorpal has quit (Ping timeout: 272 seconds).
15:00:57 -!- rdococ has joined.
15:12:06 -!- Sprocklem has quit (Quit: Leaving).
15:25:52 -!- pikhq has joined.
15:46:19 -!- fractal has quit (Ping timeout: 245 seconds).
15:46:21 -!- Vorpal has joined.
15:46:21 -!- Vorpal has quit (Changing host).
15:46:21 -!- Vorpal has joined.
15:50:46 -!- variable has joined.
15:58:12 -!- GeekDude has quit (Remote host closed the connection).
15:58:40 -!- GeekDude has joined.
15:59:55 -!- oerjan has quit (Quit: leaving).
16:02:28 -!- fractal has joined.
16:08:48 -!- bb010g has quit (Quit: Connection closed for inactivity).
16:11:11 -!- vifino has quit (Remote host closed the connection).
16:12:14 -!- vifino has joined.
16:21:50 -!- zzo38 has quit (Remote host closed the connection).
16:27:33 <HackEgo> [wiki] [[SMETANA]] http://esolangs.org/w/index.php?diff=42677&oldid=35747 * 62.216.211.203 * (+39)
16:31:39 -!- zadock has joined.
16:39:34 -!- Insipid has joined.
16:39:48 -!- Insipid has left.
16:45:32 -!- Sprocklem has joined.
16:51:04 -!- AndoDaan_ has quit (Read error: Connection reset by peer).
16:51:35 -!- AndoDaan has joined.
17:07:56 -!- b_jonas has quit (Quit: http://www.kiwiirc.com/ - A hand crafted IRC client).
17:37:36 -!- bb010g has joined.
17:41:27 -!- AndoDaan has quit (Read error: Connection reset by peer).
17:41:30 -!- AndoDaan_ has joined.
17:50:24 -!- TieSoul has changed nick to TieSoul_.
17:50:27 -!- TieSoul_ has changed nick to TieSoul.
18:09:49 -!- supay has quit (Ping timeout: 272 seconds).
18:14:36 -!- supay has joined.
18:18:16 -!- Sprocklem has quit (Ping timeout: 245 seconds).
18:25:33 -!- Sprocklem has joined.
18:25:39 -!- b_jonas has joined.
18:31:52 -!- AndoDaan_ has quit (Ping timeout: 256 seconds).
18:49:36 -!- PinealGlandOptic has joined.
18:50:30 -!- Phantom_Hoover has joined.
18:53:28 -!- AndoDaan has joined.
18:54:01 -!- nortti has changed nick to nortiecat.
18:54:09 -!- nortiecat has changed nick to nortti.
18:54:40 -!- nortti has changed nick to hvidiecat.
18:54:45 -!- hvidiecat has changed nick to hvidie.
18:54:54 -!- hvidie has changed nick to nortti.
19:06:09 -!- shikhin has joined.
19:30:24 -!- rdococ has quit (Quit: Page closed).
19:38:22 -!- nycs has joined.
19:41:25 -!- `^_^v has quit (Ping timeout: 256 seconds).
20:10:59 -!- roasted42 has joined.
20:14:58 -!- roasted42 has quit (Changing host).
20:14:58 -!- roasted42 has joined.
20:14:58 -!- roasted42 has changed nick to TheM4ch1n3.
20:36:02 -!- daria has joined.
20:43:19 -!- perrier has quit (Read error: Connection reset by peer).
20:43:33 -!- nycs has quit (Quit: This computer has gone to sleep).
20:44:33 -!- perrier has joined.
20:48:33 -!- `^_^v has joined.
20:52:16 -!- AnotherTest has joined.
20:52:35 -!- AndoDaan has quit (Ping timeout: 272 seconds).
20:53:30 -!- nortti has changed nick to lawspeaker.
20:53:49 -!- lawspeaker has changed nick to nortti.
21:02:05 -!- Patashu has joined.
21:03:05 -!- b_jonas has quit (Remote host closed the connection).
21:14:23 -!- `^_^v has quit (Quit: This computer has gone to sleep).
21:16:17 -!- `^_^v has joined.
21:23:46 -!- Sprocklem has quit (Ping timeout: 255 seconds).
21:24:40 -!- Patashu has quit (Ping timeout: 255 seconds).
21:28:50 -!- TheM4ch1n3 has quit (Ping timeout: 245 seconds).
21:35:20 -!- AndoDaan has joined.
21:38:20 -!- daria has quit (Ping timeout: 244 seconds).
21:44:44 -!- AnotherTest has quit (Remote host closed the connection).
21:45:04 -!- `^_^v has quit (Quit: This computer has gone to sleep).
21:45:28 -!- shikhin has quit (Quit: leaving).
21:46:22 -!- shikhin has joined.
21:47:33 -!- Phantom_Hoover has quit (Ping timeout: 246 seconds).
21:48:01 -!- Phantom_Hoover has joined.
22:12:08 -!- MoALTz has quit (Ping timeout: 250 seconds).
22:12:54 -!- MoALTz has joined.
22:19:13 <shachaf> oerjan: your fame grows every day hth
22:32:16 -!- staffehn has quit (Ping timeout: 265 seconds).
22:32:19 -!- staffehn_ has joined.
22:41:55 -!- oerjan has joined.
22:42:34 <tswett> I think I like Object Oriented Thue.
22:42:48 <tswett> I definitely like the idea. I'm not sure about the implementation.
22:43:53 <tswett> It's not clear from the specification (excluding the Libraries section) that it's actually possible to create objects.
22:44:25 <tswett> Whoops, there's the part where it says you can do that.
22:46:39 <tswett> Yes, I think I do like it.
22:50:24 <oerjan> shachaf: the fix was one of the things i suggested in comment 92, too.
22:52:18 <oerjan> edwardk: now i'm vaguely wondering if any of this will break your constraints package
22:52:42 <shachaf> Have you been following #9858?
22:52:43 <edwardk> breaking the constraints package would kinda suck
22:53:04 <oerjan> edwardk: a => b will no longer unify with t u
22:53:27 <edwardk> i don't use a => b explicitly as a type anywhere
22:54:56 <shachaf> A previous change was to make Constraints un-Typeable.
22:55:35 <oerjan> edwardk: i suspect you'd be happy if they implement what spj mentions in https://ghc.haskell.org/trac/ghc/ticket/9858#comment:95
22:56:55 -!- staffehn_ has quit (Ping timeout: 256 seconds).
22:56:55 -!- fractal has quit (Ping timeout: 256 seconds).
22:57:10 <oerjan> the previous comment is something i know you've complained about before
22:57:11 <edwardk> been too busy playing with fractions to notice =)
22:57:43 <edwardk> working on exact real arithmetic using nested linear fractional transformations and continued fractions
22:57:46 <shachaf> oerjan: see #haskell-lens hth
22:58:11 <edwardk> but really its all just really fancy lazyish fractions
22:59:00 -!- staffehn has joined.
22:59:02 <edwardk> pi = 3, no 3 + 1/7 no 3 + 1/(7 + 1/15), no...
22:59:46 <oerjan> i vaguely thought exact arithmetic with continued fractions was something that had already been done in haskell
23:00:01 <edwardk> i'm not using continued fractions per se
23:00:08 <edwardk> but rather "nested linear fractional transformations"
23:00:14 <edwardk> which has _also_ been done in haskell
23:00:27 <edwardk> in fact, SPJ has a paper on continued fractions.
23:00:43 <edwardk> what i'm working on is extending the scope of what we can compute with exactly
23:00:54 <edwardk> by extending the work here to so called "Hurwitz numbers"
23:01:00 <edwardk> and then generalizing the notion of hurwitz numbers
23:01:03 <oerjan> linear fractional transformations, is that like möbius transformations except with integers/rationals
23:01:30 <edwardk> matrix representation used instead multiply matrices to compose.
23:01:53 <edwardk> now we represent numbers as potentially infinite sequences of linear fractional transformations
23:02:29 <edwardk> an LFT with all positive (or all negative, they are the same up to scalar multiples) coefficients takes the interval from [0,infinity) to a small interval.
23:03:25 <edwardk> you can view a continued fraction [a;b,c,d,e...] as the composition of matrices [a 1; 1 0]*[b 1; 1 0]* ....
23:03:56 <edwardk> quadratic irrationals (e.g. sqrt 2) have repeating representations as continued fractions
23:04:26 <edwardk> "hurwitz numbers" have near-repeating representations. the representations repeat with a polynomial in the number of times you've repeated
23:04:40 <edwardk> 2;1,2,1,1,4,1,1,6,1,1,8,1...
23:05:33 -!- fractal has joined.
23:05:46 <edwardk> so i can write that out the repeating part as a matrix with polynomial coefficients: the product [1 1; 1 0] * [2k 1; 1 0] * [1 1; 1 0]
23:05:56 <edwardk> and we can convert the prefix to another ft
23:06:33 <edwardk> so it is [ 2 1; 1 0] * Pi_k^{1..infinity} [1 1; 1 0] * [2k 1; 1 0] * [1 1; 1 0]
23:06:52 <edwardk> which if you truncate it at any point takes the range from [0..infinity) to a window very very close to e.
23:07:15 <oerjan> this zooming with matrices reminds me of some of my PhD work
23:07:17 <edwardk> then we can use algorithms for adding and multiplying/dividing such numbers, etc.
23:07:52 <edwardk> the algorithms for adding/multiplying uses a 3d tensor to merge results from two different sources into one output
23:08:30 <edwardk> and then finally i can represent a meromorphic function like 'exp x' or 'log x' as a funny infinite tensor chain, where i've got the coefficients as polynomials like the hurwitz case.
23:08:42 <edwardk> and put all that into one number type and i can compute fast nice reals.
23:09:06 <edwardk> and hopefully still get things like e/e = 1 to cancel exactly because of a small closed form.
23:09:49 <edwardk> i can get computations that never step outside of quadratic surds to cancel, but now i want computations that never step outside of hurwitz numbers to cancel.
23:09:59 -!- shikhin_ has joined.
23:10:03 <tswett> data SmallReal where { toSmallReal :: Stream Bit -> SmallReal; mid :: cons Zero (repeat One) = cons One (repeat Zero); down :: forall (b :: Bit, x :: Stream Bit, y :: Stream Bit). (toSmallReal x = toSmallReal y) -> (toSmallReal (cons b x) = toSmallReal (cons b y)) }
23:10:10 <tswett> Real numbers in the interval [0, 1], in Homotopy Haskell.
23:10:11 <edwardk> basically looking for 'not-symbolic' but close enough representations where you can compare them nicely.
23:10:17 <tswett> (NB: there's no such thing as Homotopy Haskell.)
23:10:29 <oerjan> oh so you are keeping finite representations as far as possible
23:10:44 <edwardk> rather than unrolling them into a lazy mess like everyone else
23:11:28 -!- shikhin has quit (Ping timeout: 264 seconds).
23:11:47 <edwardk> LF = Rat Integer Integer | Hom Integer :* LF | Hurwitz (Hom Poly) | Meromorphic (Bihom Poly) LF
23:11:52 <edwardk> where Hom is a homographic transformation
23:12:21 -!- Decim has joined.
23:12:38 <edwardk> and Bihom is a bihomographic transformation which is a 3d analogue. or equivalently z(x,y) = (axy+bx+cy+d)/(exy+fx+gy+z) which can be viewed as z(x) in Z[y] or z(y) in Z[x]
23:13:37 <edwardk> LF = Rat Integer Integer | Hom Integer :* LF | Hurwitz (Hom Poly) | Meromorphic (Bihom Poly) LF | Tensor (Bihom Integer) LF LF
23:13:46 <edwardk> because i can't apparently cancel that
23:14:17 <edwardk> and the finite form simplifies whenever it can
23:15:04 <edwardk> phi = Hurwitz (Hom 1 1 1 0) gives the golden ratio, sqrt2 = Hom 1 1 1 0 :* Hurwitz (Hom 2 1 1 0)
23:15:48 <Decim> Sorry Im just dead
23:16:24 <edwardk> anyways i have algorithms now for 'spigoting' off partial matrices from each of those forms
23:16:31 <edwardk> and modifying the remainder
23:17:05 <edwardk> and ways to construct them from continued fractions, redundant binary, decimal, etc.
23:18:00 <edwardk> basically the only requirement is that every homographic transformation after the first 'contracts' some interval.
23:18:03 <oerjan> the z(x,y) makes me think vaguely of quaternions
23:18:30 <Decim> What's Brainfuck used for?
23:19:16 <Decim> I know but what are its general purposes or is it just a fun language
23:19:49 <tswett> As far as I know, the sole purpose of Brainfuck is to be interesting.
23:20:04 <oerjan> edwardk: can you differentiate with this too?
23:20:23 <edwardk> i can treat these as raw numbers for AD
23:20:35 <edwardk> and you can build pade approximants using the same techniques
23:20:46 <edwardk> and those are used as good forms for differentiation/integration
23:21:12 <Decim> Well in general all of you are pretty neat
23:21:36 <Decim> Except that one guy >_>
23:21:47 <edwardk> i got started with pade approximants when jacques carette earwormed me with the idea that they would be the best form for dealing with more or less "automatic integration"
23:21:59 <edwardk> as that is what all the big boys use in things like Mathematica / Maple, etc.
23:22:27 <edwardk> but then put it away for a couple years
23:22:36 <edwardk> until now, when i now have more of the groundwork in place
23:22:51 <Decim> Please teach at our school, Ill pay you like a dollar
23:27:01 <tswett> Why the hell did I decide I wanted to go into industry instead of academia...
23:30:14 <oerjan> probably involved money
23:37:57 <Decim> Did you want to teach tswett
23:38:17 <tswett> No, I'm not really interested in teaching professionally.
23:38:57 -!- boily has joined.
23:39:21 -!- Decim has quit (Remote host closed the connection).
00:06:07 <olsner> is there teaching in research?
00:06:37 <boily> hellolsner. perhaps.
00:07:29 <olsner> in other news, I'm somewhat happy to see more haskell luminaries in here
00:08:28 <boily> fungot: what is edwardk's albedo?
00:08:29 <fungot> boily: oops no i'm wrong. gah i don't have a problem with loose adaptations, if they're pretty enough.
00:08:47 <olsner> fungot: what is fungot's then?
00:08:48 <fungot> olsner: my thought at the time
00:08:55 <shachaf> oerjan: just think of what you're missing out on in #-lens hth
00:09:23 <olsner> fungot: my thought almost exactly
00:09:23 <fungot> olsner: srfi 44 has been done. in fact you could do it
00:09:34 <edwardk> i'm pretty pale, so i'd assume my albedo would be quite high
00:09:39 <boily> shachaf: there's an #esoteric-lens?
00:10:04 <olsner> boily: it may be called otherwise, but I think there is
00:25:07 -!- Vorpal has quit (Ping timeout: 255 seconds).
00:25:28 -!- Vorpal has joined.
00:39:13 <shachaf> boily: this is ridiculous hth
00:44:27 <oerjan> i'm sure Taneb's TC proof would belong there.
00:53:40 -!- oren has joined.
01:09:16 -!- Phantom_Hoover has quit (Read error: Connection reset by peer).
01:15:10 -!- Frooxius has joined.
01:25:58 -!- Sprocklem has joined.
01:26:24 -!- oerjan has quit (Quit: Gnite).
01:34:25 -!- boily has quit (Quit: ESCALATIVE CHICKEN).
01:38:50 -!- Vorpal has quit (Ping timeout: 265 seconds).
01:45:39 -!- Vorpal has joined.
01:45:39 -!- Vorpal has quit (Changing host).
01:45:39 -!- Vorpal has joined.
01:49:23 -!- Frooxius has quit (Ping timeout: 240 seconds).
02:37:47 -!- Frooxius has joined.
02:57:44 <HackEgo> [wiki] [[Special:Log/newusers]] create * Paul2520 * New user account
03:13:58 <HackEgo> [wiki] [[Underload]] http://esolangs.org/w/index.php?diff=42678&oldid=41993 * Esowiki201529A * (+31) /* Numbers */
03:14:19 <HackEgo> [wiki] [[Underload]] http://esolangs.org/w/index.php?diff=42679&oldid=42678 * Esowiki201529A * (+1) /* Numbers */
03:14:55 <HackEgo> [wiki] [[Underload/Numbers]] N http://esolangs.org/w/index.php?oldid=42680 * Esowiki201529A * (+2518) Created page with " 0 !() 1 (empty)! 2 :* 3 ::** 4 :*:* 5 ::*:** 6 ::**:* 7 :::**:** 8 :*:*:* 9 ::**::** 10 ::*:**:* 11 :::*:**:** 12 ::**:*:* 13 :::**:*:** 14 :::**:**:* 15 ::*:*..."
03:15:11 -!- tswett has quit (Quit: No Ping reply in 180 seconds.).
03:16:26 -!- Warrigal has joined.
03:25:28 -!- AndoDaan_ has joined.
03:26:49 -!- AndoDaan_ has quit (Read error: Connection reset by peer).
03:27:17 -!- AndoDaan_ has joined.
03:27:20 -!- AndoDaan has quit (Ping timeout: 248 seconds).
03:31:33 -!- AndoDaan_ has changed nick to AndoDaan.
03:41:32 -!- GeekDude has quit (Quit: {{{}}{{{}}{{}}}{{}}} (www.adiirc.com)).
03:48:01 <HackEgo> [wiki] [[Gibberish (programming language)]] http://esolangs.org/w/index.php?diff=42681&oldid=42650 * Esowiki201529A * (+2) /* Interpreter */
03:49:20 <HackEgo> [wiki] [[Gibberish (programming language)]] http://esolangs.org/w/index.php?diff=42683&oldid=42681 * Esowiki201529A * (-2) /* Interpreter */
03:50:09 <HackEgo> [wiki] [[Gibberish (programming language)]] http://esolangs.org/w/index.php?diff=42684&oldid=42683 * Esowiki201529A * (-2) /* See also */
04:02:33 -!- barrucadu has left.
04:07:51 -!- Decim has joined.
04:11:18 <Decim> >7854256753 * 79997
04:11:55 <Decim> > 7854256753 * 79997
04:18:44 <Decim> Are you trying to sell me drugs FreeFull
04:20:14 <Decim> You better not, I've got my eye's on you. »_»
04:27:14 -!- Decim has quit (Quit: Onii-chan you're the best especially when you touch my breast).
04:37:45 <HackEgo> /home/hackbot/hackbot.hg/multibot_cmds/lib/limits: line 5: exec: mspalist: not found
04:37:53 <HackEgo> ` \ `` \ ^.^ \ ̊ \ ! \ ? \ ¿ \ ' \ @ \ ؟ \ ＷＥＬＣＯＭＥ \ \ \ 2014 \ 2015 \ 8ball \ 8-ball \ aaaaaaaaa \ addquote \ addwep \ allquotes \ analogy \ anonlog \ as86 \ aseen \ benvenuto \ bf \ bienvenido \ botsnack \ bseen \ buttsnack \ calc \ CaT \ catcat \ cats \ cc \ cdecl \ c++decl \ chroot \ coins \ CoInS \ complain \ complain
04:38:22 <Sgeo_> I refuse to believe that there is nothing in ~/bin that comes later alphabetically than c
05:06:40 -!- Frooxius has quit (Quit: *bubbles away*).
05:10:53 -!- shikhin has joined.
05:12:12 -!- shikhin_ has quit (Ping timeout: 256 seconds).
05:13:13 -!- Sprocklem has quit (Quit: Leaving).
05:16:09 -!- variable has changed nick to trout.
05:41:56 -!- PinealGlandOptic has quit (Ping timeout: 244 seconds).
05:47:41 -!- zadock has quit (Quit: Leaving).
05:47:45 -!- pikhq has quit (Ping timeout: 265 seconds).
06:42:04 -!- Sgeo_ has quit (Remote host closed the connection).
06:42:14 -!- trout has quit (Ping timeout: 272 seconds).
06:42:27 -!- Sgeo_ has joined.
06:43:17 -!- heroux has quit (Ping timeout: 245 seconds).
06:55:45 -!- mitchs has joined.
07:14:16 -!- hjulle has quit (Ping timeout: 265 seconds).
07:25:32 -!- AndoDaan has quit (Read error: Connection reset by peer).
07:48:13 -!- AndoDaan has joined.
07:53:13 <HackEgo> [wiki] [[Goldfish]] http://esolangs.org/w/index.php?diff=42685&oldid=40128 * Esowiki201529A * (+0) /* Commands */
07:54:07 -!- Sgeo_ has quit (Remote host closed the connection).
07:54:36 -!- Sgeo_ has joined.
08:01:22 -!- Sgeo_ has quit (Remote host closed the connection).
08:02:14 -!- Sgeo_ has joined.
08:02:24 -!- Sgeo_ has quit (Remote host closed the connection).
08:02:53 -!- Sgeo_ has joined.
08:05:00 -!- Sgeo_ has quit (Remote host closed the connection).
08:05:28 -!- Sgeo_ has joined.
08:13:45 -!- Patashu has joined.
08:17:54 <HackEgo> slist: Taneb atriq Ngevd Fiora Sgeo ThatOtherPerson alot
08:18:38 -!- Patashu_ has joined.
08:18:38 -!- Patashu has quit (Disconnected by services).
08:19:00 <Taneb> Wow I am half of those names
08:20:09 -!- Phantom_Hoover has joined.
08:21:34 -!- Sgeo_ has quit (Remote host closed the connection).
08:22:03 -!- Sgeo_ has joined.
08:25:42 -!- Sgeo_ has quit (Remote host closed the connection).
08:26:07 -!- Sgeo_ has joined.
08:30:04 <Taneb> Last night I may have ordered a new PSU for my desktop
08:30:11 <Taneb> I also may have ordered it to come gift-wrapped
08:37:44 -!- b_jonas has joined.
08:41:54 -!- AnotherTest has joined.
08:45:53 -!- Sgeo_ has quit (Remote host closed the connection).
08:46:22 -!- Sgeo_ has joined.
08:49:26 <HackEgo> [wiki] [[Talk:Gibberish/JavaScript]] N http://esolangs.org/w/index.php?oldid=42687 * Esowiki201529A * (+67) Created page with " <User> ${echo:Hello, World!} <Calculate> Hello, World!"
08:50:14 <HackEgo> [wiki] [[Talk:Gibberish/JavaScript]] http://esolangs.org/w/index.php?diff=42688&oldid=42687 * Esowiki201529A * (+1)
08:52:07 -!- Sgeo_ has quit (Remote host closed the connection).
08:52:32 -!- Sgeo_ has joined.
08:53:09 -!- Sgeo_ has quit (Remote host closed the connection).
08:53:14 <HackEgo> [wiki] [[Talk:Gibberish/JavaScript]] http://esolangs.org/w/index.php?diff=42689&oldid=42688 * Esowiki201529A * (+50)
08:53:37 -!- Sgeo_ has joined.
08:55:28 <HackEgo> [wiki] [[Talk:Gibberish/JavaScript]] http://esolangs.org/w/index.php?diff=42690&oldid=42689 * Esowiki201529A * (+45)
08:56:53 <HackEgo> [wiki] [[Talk:Gibberish/JavaScript]] http://esolangs.org/w/index.php?diff=42691&oldid=42690 * Esowiki201529A * (+38)
08:57:49 <HackEgo> [wiki] [[Talk:Gibberish/JavaScript]] http://esolangs.org/w/index.php?diff=42693&oldid=42691 * Esowiki201529A * (+9)
08:58:59 <HackEgo> [wiki] [[Talk:Gibberish/JavaScript]] http://esolangs.org/w/index.php?diff=42694&oldid=42693 * Esowiki201529A * (+2)
08:59:46 <HackEgo> [wiki] [[Talk:Gibberish/JavaScript]] http://esolangs.org/w/index.php?diff=42695&oldid=42694 * Esowiki201529A * (-13)
09:03:38 <HackEgo> [wiki] [[Talk:Gibberish/JavaScript]] http://esolangs.org/w/index.php?diff=42696&oldid=42695 * Esowiki201529A * (+115)
09:06:24 <HackEgo> [wiki] [[Talk:Gibberish/JavaScript]] http://esolangs.org/w/index.php?diff=42697&oldid=42696 * Esowiki201529A * (+155)
09:06:33 -!- Sgeo_ has quit (Remote host closed the connection).
09:07:04 -!- Sgeo_ has joined.
09:07:20 <b_jonas> how much coffee do you drink, fungot?
09:07:20 <fungot> b_jonas: what good is a kaiser roll?! what good is a kaiser roll?! what good is a kaiser roll without a little easier. these use support files. is this my stop?!
09:08:55 <HackEgo> [wiki] [[Talk:Gibberish/JavaScript]] http://esolangs.org/w/index.php?diff=42698&oldid=42697 * Esowiki201529A * (+29)
09:11:33 <HackEgo> [wiki] [[Talk:Gibberish/JavaScript]] http://esolangs.org/w/index.php?diff=42700&oldid=42698 * Esowiki201529A * (+94)
09:12:44 -!- Sgeo_ has quit (Remote host closed the connection).
09:12:48 <HackEgo> [wiki] [[Talk:Gibberish/JavaScript]] http://esolangs.org/w/index.php?diff=42701&oldid=42700 * Esowiki201529A * (+10)
09:13:11 -!- Sgeo_ has joined.
09:13:50 <mroman> fungot: Yes, you should leave the bus now.
09:13:51 <fungot> mroman: the same forcer had in mind :) ttyl i'm going to study medicine, starting in a language than to campaign for a change that would make it easier for people to edit stuff
09:16:47 <HackEgo> [wiki] [[Talk:Gibberish/JavaScript]] http://esolangs.org/w/index.php?diff=42702&oldid=42701 * Esowiki201529A * (+73)
09:18:24 <b_jonas> fungot is studying medicine. that scares me
09:18:25 <fungot> b_jonas: if itself requires only one jump. jumping back to _before_ where the interrupt _and_ exception systems would abort to in case of fire, and nothing more than a tenth of the mailing list. either i have a *copy* of... or xp if they want
09:22:08 <fizzie> fungot: Are you sure an interrupt handler is enough to deal with a *fire*?
09:22:08 <fungot> fizzie: you're entitled to your opinion. there are seven bits of a pointer to the memory pages the memory is shared, and the
09:22:14 <HackEgo> [wiki] [[Talk:Gibberish/JavaScript]] http://esolangs.org/w/index.php?diff=42703&oldid=42702 * Esowiki201529A * (+137)
09:23:30 <HackEgo> [wiki] [[Talk:Gibberish/JavaScript]] http://esolangs.org/w/index.php?diff=42704&oldid=42703 * Esowiki201529A * (+14)
09:23:55 <HackEgo> [wiki] [[Talk:Gibberish/JavaScript]] http://esolangs.org/w/index.php?diff=42705&oldid=42704 * Esowiki201529A * (+1)
09:23:57 <mroman> fungot: Am I entitled to an opinion?
09:23:58 <fungot> mroman: but that doesn't mean i wouldn't understand it?
09:24:15 <mroman> fungot: No, you can still understand my opinion.
09:24:15 <fungot> mroman: body thetans detected? fnord/ tips/ shared/ fnord
09:25:08 -!- Sgeo_ has quit (Remote host closed the connection).
09:25:37 -!- Sgeo_ has joined.
09:27:01 <HackEgo> [wiki] [[Talk:Gibberish/JavaScript]] http://esolangs.org/w/index.php?diff=42706&oldid=42705 * Esowiki201529A * (+29)
09:31:31 <quintopia> when did fungy become a scientologist?
09:31:51 -!- daria has joined.
09:32:06 -!- daria has quit (Changing host).
09:32:06 -!- daria has joined.
09:44:02 -!- Vorpal has quit (Ping timeout: 255 seconds).
09:45:38 -!- Vorpal has joined.
09:57:10 <HackEgo> [wiki] [[Special:Log/move]] move * Esowiki201529A * moved [[User:SMA]] to [[User:$M@]]
10:00:56 <fizzie> There was a Scientology bus in Mountain View.
10:00:58 <fizzie> I tried to take a photo, but only caught the rear end of it.
10:01:58 <fizzie> So it's just an "OLOGY" truck now.
10:10:22 <HackEgo> [wiki] [[User talk:Esolang account]] N http://esolangs.org/w/index.php?oldid=42709 * Esowiki201529A * (+33) Redirected page to [[User:Esowiki201529A]]
10:11:05 <HackEgo> [wiki] [[User talk:Esolang account]] http://esolangs.org/w/index.php?diff=42710&oldid=42709 * Esowiki201529A * (+5) Redirected page to [[User talk:Esowiki201529A]]
10:25:32 -!- Insipid has joined.
10:30:27 -!- Insipid has quit (Quit: Leaving.).
10:30:44 -!- boily has joined.
10:36:43 -!- Insipid has joined.
10:43:27 -!- Insipid has left.
10:48:18 -!- nszceta has joined.
10:54:49 <HackEgo> [wiki] [[Talk:Gibberish (programming language)]] http://esolangs.org/w/index.php?diff=42711&oldid=42563 * Vriskanon * (+214) /* J command with no command set */ new section
11:00:02 -!- oerjan has joined.
11:03:07 <HackEgo> [wiki] [[4]] M http://esolangs.org/w/index.php?diff=42712&oldid=42668 * Vriskanon * (+80) added python interpreter (badly optimized)
11:04:39 <HackEgo> [wiki] [[AFTL]] M http://esolangs.org/w/index.php?diff=42713&oldid=42676 * Vriskanon * (-1773) /* Interpreters */ Moved interpreter to github
11:04:44 <HackEgo> http://codu.org/projects/hackbot/fshg/index.cgi/file/tip/bin
11:05:06 <HackEgo> [wiki] [[AFTL]] M http://esolangs.org/w/index.php?diff=42714&oldid=42713 * Vriskanon * (+6) /* Interpreters */ Renamed Interpreters to 'External resources'
11:06:23 -!- heroux has joined.
11:07:19 <HackEgo> ELF...Ht$..>............8.......HHu<H.8........................fy \ ...............H \ HuB \ H)H
11:07:27 <HackEgo> y \ y \ y \ y \ y \ y \ y \ y \ y \ y \ y \ y \ y \ y \ y \ y \ y \ y \ y \ y \ y \ y \ y \ y \ y \ y \ y \ y \ y \ y \ y \ y \ y \ y \ y \ y \ y \ y \ y \ y \ y \ y \ y \ y \ y \ y \ y \ y \ y \ y \ y \ y \ y \ y \ y \ y \ y \ y \ y \ y \ y \ y \ y \ y \ y \ y \ y \ y \ y \ y \ y \ y \ y \ y \ y \ y \ y \ y \ y \ y \ y \ y \ y \ y \ y \ y \ y \ y
11:07:43 <HackEgo> #!/bin/bash \ yes "$@" #ë
11:07:44 <HackEgo> no \ no \ no \ no \ no \ no \ no \ no \ no \ no \ no \ no \ no \ no \ no \ no \ no \ no \ no \ no \ no \ no \ no \ no \ no \ no \ no \ no \ no \ no \ no \ no \ no \ no \ no \ no \ no \ no \ no \ no \ no \ no \ no \ no \ no \ no \ no \ no \ no \ no \ no \ no \ no \ no \ no \ no \ no \ no \ no \ no \ no \ no \ no \ no \ no \ no \ no \ no \ no \ no \
11:08:06 <HackEgo> y \ y \ y \ y \ y \ y \ y \ y \ y \ y \ y \ y \ y \ y \ y \ y \ y \ y \ y \ y \ y \ y \ y \ y \ y \ y \ y \ y \ y \ y \ y \ y \ y \ y \ y \ y \ y \ y \ y \ y \ y \ y \ y \ y \ y \ y \ y \ y \ y \ y \ y \ y \ y \ y \ y \ y \ y \ y \ y \ y \ y \ y \ y \ y \ y \ y \ y \ y \ y \ y \ y \ y \ y \ y \ y \ y \ y \ y \ y \ y \ y \ y \ y \ y \ y \ y \ y \ y
11:08:16 <HackEgo> z \ z \ z \ z \ z \ z \ z \ z \ z \ z \ z \ z \ z \ z \ z \ z \ z \ z \ z \ z \ z \ z \ z \ z \ z \ z \ z \ z \ z \ z \ z \ z \ z \ z \ z \ z \ z \ z \ z \ z \ z \ z \ z \ z \ z \ z \ z \ z \ z \ z \ z \ z \ z \ z \ z \ z \ z \ z \ z \ z \ z \ z \ z \ z \ z \ z \ z \ z \ z \ z \ z \ z \ z \ z \ z \ z \ z \ z \ z \ z \ z \ z \ z \ z \ z \ z \ z \ z
11:08:35 <oerjan> these seem a little redundant
11:08:51 -!- pikhq has joined.
11:10:06 -!- shikhin_ has joined.
11:10:08 <int-e> I don't recall the last time I even used 'yes'...
11:10:43 <oerjan> it's supposedly good if you have some command that asks a lot of stupid yes/no questions?
11:11:06 <int-e> yes 'eggs on the wall. throw one more egg,' | cat -n
11:11:12 <int-e> `` yes 'eggs on the wall. throw one more egg,' | cat -n
11:11:13 <HackEgo> 1eggs on the wall. throw one more egg, \ 2eggs on the wall. throw one more egg, \ 3eggs on the wall. throw one more egg, \ 4eggs on the wall. throw one more egg, \ 5eggs on the wall. throw one more egg, \ 6eggs on the wall. throw one more egg, \ 7eggs on the wall. throw one more egg, \ 8eggs on the
11:11:43 -!- shikhin has quit (Ping timeout: 250 seconds).
11:11:51 <oerjan> `` yes 'eggs on the wall. throw one more egg,' | nl
11:11:52 <HackEgo> 1eggs on the wall. throw one more egg, \ 2eggs on the wall. throw one more egg, \ 3eggs on the wall. throw one more egg, \ 4eggs on the wall. throw one more egg, \ 5eggs on the wall. throw one more egg, \ 6eggs on the wall. throw one more egg, \ 7eggs on the wall. throw one more egg, \ 8eggs on the
11:13:25 <boily> holy fungot there are yesses everywhere...
11:13:25 <fungot> boily: i was just talking to fnord himself talk about esoteric
11:13:27 <int-e> doboily dyen (too lazy for gucharmap)
11:15:01 -!- int-e has left ("FREAKED OUT CHICKEN").
11:15:01 -!- int-e has joined.
11:18:52 <oerjan> `` (echo '#!/bin/bash'; echo 'print_args_or_input "$@" | tr a-z A-Z | sed '"'"'s/$/ CHICKEN/'"'") >bin/poulet
11:19:35 <boily> oh. oooooh. OOOOOOOH! :D
11:20:16 <oerjan> `poulet ooooooooooooooh
11:20:49 <boily> speaking of chicken, the first thing I'll be doing at work is to rename the method I wrote yesterday.
11:22:24 <boily> nothing shameful, only something like 'private Mesh computeSideChicken(List<Vector> startLine, List<Vector> endLine)'.
11:23:12 <myname> the famous side chicken
11:23:26 <oren> I usually name things like computeOrenIsAwesome
11:25:02 -!- boily has quit (Quit: LATERAL CHICKEN).
11:25:34 <oerjan> `` run ls wisdom/*list
11:25:34 <HackEgo> bash: run: command not found
11:25:47 <HackEgo> wisdom/bdsmreclist \ wisdom/danddreclist \ wisdom/list \ wisdom/olist \ wisdom/slist
11:26:09 <HackEgo> Update notification for the webcomic Homestuck.
11:26:40 <oerjan> hm Sgeo_ wanted a general mpsa one?
11:27:14 <oren> Also I use label names like hell: heaven: rome:
11:27:46 <oren> rome: is a good label name for a place where all control flows converge
11:27:58 <oren> all roads goto rome;
11:28:19 -!- zadock has joined.
11:32:29 <oerjan> fungot: you don't _need_ a kaiser roll with coffee, you know.
11:32:29 <fungot> oerjan: ' ( 1))) this is a barbarian buyer
11:32:48 <oerjan> i think fungot disagrees
11:32:48 <fungot> oerjan: consider that ( name. args)
11:33:44 -!- shikhin_ has changed nick to shikhin.
11:33:44 <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
11:37:34 -!- AndoDaan_ has joined.
11:37:45 -!- AndoDaan has quit (Ping timeout: 246 seconds).
11:40:17 -!- _AndoDaan_ has joined.
11:43:29 <HackEgo> [wiki] [[Special:Log/move]] move_redir * Oerjan * moved [[User:$M@]] to [[User:SMA]] over redirect: User pages cannot be renamed, they have other data connected
11:44:13 -!- AndoDaan_ has quit (Ping timeout: 250 seconds).
11:45:40 <Sgeo_> oerjan, I forgot which one was HS
11:47:34 <FireFly> http://codegolf.stackexchange.com/questions/48931/make-the-largest-infinity-that-you-can aaah
11:48:15 <HackEgo> [wiki] [[Special:Log/delete]] delete * Oerjan * deleted "[[User talk:Esolang account]]": Redirect created by someone other than the user themselves
11:52:36 -!- Sgeo_ has quit (Remote host closed the connection).
11:53:06 -!- Sgeo_ has joined.
11:54:11 -!- Sgeo_ has quit (Remote host closed the connection).
11:54:40 -!- Sgeo_ has joined.
11:56:48 -!- Sgeo_ has quit (Remote host closed the connection).
11:57:17 -!- Sgeo_ has joined.
11:58:22 -!- Sgeo_ has quit (Remote host closed the connection).
11:58:50 -!- Sgeo_ has joined.
12:05:35 <HackEgo> [wiki] [[User talk:Esowiki201529A]] http://esolangs.org/w/index.php?diff=42716&oldid=42616 * Oerjan * (+397) /* Disruptive edits */ Don't rename user pages either
12:17:11 -!- Patashu_ has quit (Ping timeout: 245 seconds).
12:19:48 -!- Sgeo_ has quit (Ping timeout: 272 seconds).
12:27:10 -!- llue has joined.
12:30:52 -!- lleu has quit (Ping timeout: 265 seconds).
12:34:25 -!- nszceta has quit (Max SendQ exceeded).
12:35:29 -!- nszceta has joined.
12:45:48 -!- zadock has quit (Quit: Leaving).
12:48:35 <HackEgo> [wiki] [[Alphabetti spaghetti]] N http://esolangs.org/w/index.php?oldid=42717 * Mazeman * (+1441) Created page with "Alphabetti spaghetti is an esoteric programming language invented in 2015 by an anonymous user. Programs in alphabetti spaghetti consist of a string of alphabetic characters (..."
12:49:29 <oerjan> noodle incident on wiki
12:49:47 -!- nszceta has quit (Remote host closed the connection).
12:50:21 -!- nszceta has joined.
12:59:18 <elliott> oerjan: fwiw I suspect the lack of reply to my previous messages was down to them being a non-native speaker
13:00:08 <elliott> I like The title of this article is incorrect because of technical limitations. The correct title is talk page.
13:00:46 <elliott> oerjan: also are we sure esowikiblahblah isn't esolang account?
13:01:14 <oerjan> well no, but if so e should do the redirect from that account.
13:01:26 <oerjan> so far, it hasn't done anything.
13:01:48 <elliott> right I just tend to avoid being pedantic about things like that when it seems highly likely
13:01:53 <elliott> but I guess in this case it's hard to tell
13:02:06 <elliott> for instance what about when someone forgets their password
13:02:20 <oerjan> the account must exist, since it has a contributions link
13:02:34 <HackEgo> [wiki] [[Language list]] http://esolangs.org/w/index.php?diff=42718&oldid=42645 * Mazeman * (+27) /* A */
13:02:44 * oerjan just tested that a random name doesn't.
13:03:24 <elliott> if only I still had DB access I'd just compare the emails
13:03:36 <elliott> fizzie: don't you think I deserve DB access?!?!?!
13:03:48 <elliott> it's like, uh. whatever wikimedia calls that permission level.
13:04:14 <HackEgo> [wiki] [[Alphabetti spaghetti]] http://esolangs.org/w/index.php?diff=42719&oldid=42717 * Mazeman * (+181)
13:04:50 <HackEgo> [wiki] [[Alphabetti spaghetti]] http://esolangs.org/w/index.php?diff=42720&oldid=42719 * Mazeman * (-1) /* Syntax */
13:04:51 <oerjan> isn't there some way to find out when a user registered
13:05:21 -!- _AndoDaan_ has quit (Quit: Going, going, gone.).
13:05:27 <oerjan> it seems not to count on the activity page
13:05:46 -!- _AndoDaan_ has joined.
13:07:18 <oerjan> ah the user list can be sorted by creation
13:07:28 <elliott> the log probably got cleared at some point
13:08:15 <oerjan> esowiki* joined on january 9
13:09:18 <oerjan> 7 september 2011 for the other
13:11:15 <oerjan> i cannot seem to convince it to list around that date
13:12:48 * oerjan skips spam 500 accounts at a time
13:13:09 <oerjan> holy shit february 2012
13:14:30 <fizzie> There is no user_email set for either account hth
13:15:16 * oerjan notes spammers grabbing a lot of 2-letter account
13:16:29 -!- conehead has quit (Quit: ZNC - http://znc.in).
13:18:05 <oerjan> the account was registered at about the time the spam started picking up severely
13:18:36 -!- conehead has joined.
13:18:36 -!- conehead has quit (Changing host).
13:18:36 -!- conehead has joined.
13:20:34 <HackEgo> [wiki] [[Special:Log/delete]] delete * Oerjan * deleted "[[User:WLaquitaCuevasa]]": Spam: content was: "PHP is usually a really popular Web programming language. It really is approximated that it's got now about 5 million developers across the world. Possessing PHP help php on google app engine can mean a lot of possibilities for PHP devel..."
13:20:38 * oerjan deletes 3 year old spam
13:21:37 -!- _AndoDaan_ has quit (Ping timeout: 245 seconds).
13:22:15 <HackEgo> [wiki] [[Special:Log/block]] block * Oerjan * blocked [[User:WLaquitaCuevasa]] with an expiry time of indefinite (autoblock disabled): Spamming links to external sites
13:23:16 <oerjan> hm SMA was also around that time
13:32:51 -!- myname99 has joined.
13:33:08 <oerjan> :t let f = \(p :: Proxy Proxy) -> typeRep p in f
13:33:09 <lambdabot> Typeable Proxy => Proxy Proxy -> TypeRep
13:57:51 -!- AndoDaan has joined.
14:04:05 -!- `^_^v has joined.
14:14:41 -!- myname99 has quit (Ping timeout: 245 seconds).
14:16:32 -!- TieSoul has changed nick to DootBot.
14:19:43 <Warrigal> :t let x :: forall a. a -> Bool; x = x in x x
14:38:31 -!- AndoDaan has quit (Ping timeout: 276 seconds).
14:38:38 -!- Warrigal has changed nick to tswett.
14:39:25 -!- supereman16 has joined.
14:41:55 -!- DootBot has changed nick to TieSoul.
14:42:31 -!- variable has joined.
14:44:27 -!- guydreich has quit (Read error: Connection reset by peer).
14:45:12 -!- b_jonas has quit (Quit: http://www.kiwiirc.com/ - A hand crafted IRC client).
14:49:44 -!- supereman16 has quit (Ping timeout: 246 seconds).
14:56:24 -!- variable has changed nick to trout.
15:11:58 -!- GeekDude has joined.
15:12:10 -!- oren has quit (Ping timeout: 256 seconds).
15:13:46 -!- oren has joined.
15:38:30 -!- Insipid has joined.
15:43:00 -!- Sprocklem has joined.
15:43:54 -!- Insipid has left.
16:08:55 -!- HMC_A_ has quit (Remote host closed the connection).
16:12:11 -!- zadock has joined.
16:13:33 -!- AndoDaan has joined.
16:18:50 -!- bb010g has quit (Quit: Connection closed for inactivity).
16:28:46 <lambdabot> *** "hello" wn "WordNet (r) 3.0 (2006)"
16:28:46 <lambdabot> n 1: an expression of greeting; "every morning they exchanged
16:28:46 <lambdabot> polite hellos" [syn: {hello}, {hullo}, {hi}, {howdy}, {how-
16:32:13 -!- lambdabot has quit (Quit: brb).
16:36:30 -!- oerjan has quit (Quit: leaving).
16:36:46 -!- lambdabot has joined.
16:51:36 -!- lambdabot has quit (Quit: sorry, let's try this again).
16:56:15 -!- lambdabot has joined.
16:59:12 <lambdabot> Sorry, look up one word at a time please.
17:02:40 -!- zadock has quit (Quit: Leaving).
17:10:37 -!- shikhin_ has joined.
17:11:12 -!- shikhin has quit (Ping timeout: 250 seconds).
17:11:33 -!- shikhin_ has changed nick to shikhin.
17:15:04 -!- PinealGlandOptic has joined.
17:16:28 <lambdabot> *** "a" wn "WordNet (r) 3.0 (2006)"
17:16:28 <lambdabot> n 1: a metric unit of length equal to one ten billionth of a
17:16:28 <lambdabot> meter (or 0.0001 micron); used to specify wavelengths of
17:16:28 <lambdabot> electromagnetic radiation [syn: {angstrom}, {angstrom
17:17:43 <lambdabot> *** "a" gcide "The Collaborative International Dictionary of English v.0.48"
17:17:43 <lambdabot> Gastropoda \Gas*trop"o*da\, n. pl., [NL., fr. Gr. ?, ?, stomach
17:17:43 <lambdabot> One of the classes of Mollusca, of great extent. It includes
17:17:45 <lambdabot> most of the marine spiral shells, and the land and
17:26:28 -!- AndoDaan has quit (Ping timeout: 256 seconds).
17:28:25 -!- zadock has joined.
17:30:49 -!- ais523 has joined.
17:36:20 -!- Sprocklem has quit (Ping timeout: 250 seconds).
17:37:49 -!- ais523 has quit (Remote host closed the connection).
17:38:45 -!- bb010g has joined.
17:39:03 -!- ais523 has joined.
17:46:45 <ais523> so, I came to the conclusion that compilers aren't as good at generating asm as people think they are
17:47:24 <shachaf> How good do people think they are?
17:47:39 <ais523> here's a fun one I came across today: http://sprunge.us/JESG
17:47:47 <ais523> try that with gcc -O2, then try with -O3 for a comparison
17:47:58 <shachaf> Did you see http://cr.yp.to/talks/2015.04.16/slides-djb-20150416-a4.pdf the other day?
17:48:04 <ais523> on my laptop (gcc 4.9.1), the -O3 solution is hilariously bad
17:51:21 <quintopia> is that something requires lex or yacc or whatever
17:52:03 <int-e> quintopia: nope, it looks self-contained at a glance
17:52:06 <ais523> quintopia: I've been working on a yacc impl
17:52:52 <ais523> this is the -O3 implementation: http://sprunge.us/XGef
17:53:10 <ais523> I'm not even convinced it beats -O0
17:53:34 <ais523> basically gcc sees that I'm trying to load 128 contiguous bits from memory, thinks "ooh, I'll load them into a 128-bit register!"
17:53:47 <int-e> tough one. *counts instructions* 12 instead of 2?
17:53:49 <ais523> then can't figure out what to do with them after that and has to put them /back/ into memory to be able to put them into the return value registers
17:54:25 <int-e> I suppose it beats the -O0 one, but it's really quite awful :)
17:54:38 <ais523> and now, because it's spilling 128 bits onto the stack
17:54:44 <ais523> it goes and adds a stack canary to the function
17:55:18 <ais523> and decides to spill the 128-bit register into a different memory location so that it isn't clobbered by the stack canary
17:55:22 <ais523> which makes even less sense
17:55:51 <int-e> ais523: An alternative theory: There might be a temporary on the stack in either case (there certainly is one in the -O0 version), but only the -O2 version manages to eliminate it, because it doesn't "optimize" the memory transfer.
17:56:42 <ais523> I think the problem is that gcc is starting off with temporaries and then trying to find places to put them
17:56:49 <int-e> In any case it's a nice example.
17:57:12 <ais523> clang gets it right at -O3, which is what I'd expect for an llvm-based compiler
17:57:13 -!- AnotherTest has quit (Ping timeout: 256 seconds).
17:57:20 <ais523> I have an even nicer example somewhere
17:57:33 -!- nszceta has quit (Quit: My Mac has gone to sleep. ZZZzzz…).
17:58:03 <int-e> the -O0 -fomit-frame-pointer version looks pretty straightforward: copy struct to temporary on stack, then load the temporary into registers for returning it.
17:58:36 <ais523> here: http://sprunge.us/BVKG
17:58:43 <ais523> the source is a little complex
17:58:46 <ais523> but the output is just inexplicable
17:59:11 <ais523> I think that was -Os, from memory
18:00:06 <ais523> clang gets that one right too
18:03:49 <ais523> bleh, neither gcc nor clang have figured out how to optimize out yyvalid in ayacc's output
18:05:43 -!- trn has quit (Ping timeout: 256 seconds).
18:06:29 -!- trn has joined.
18:13:45 <int-e> DJB touches a crucial point... fully exploiting modern hardware requires specific algorithms (and the designer will work in terms of keeping various parts (say, integer and floating point units) busy, caches populated, etc...); doing that directly in assembly languyage is easier than fighting an optimizing compiler.
18:14:24 <shachaf> Touches? Isn't that his main point?
18:14:52 <int-e> But I don't think that optimizing compilers are dying.
18:14:54 <shachaf> Well, that and that the specific algorithms will take a larger and larger percentage of CPU time.
18:16:29 <shachaf> I think it's a bit silly to say that CPUs keep getting faster, so we don't need to worry about optimizing compilers at all.
18:16:53 <shachaf> A lot of the things that make CPUs faster in hardware are the sorts of things that an optimizing compiler does in software
18:16:54 <int-e> Yes, you'll optimize the hell out of the hotspots, but you still want the remaining code to be fast. Or prototypes of new algorithms...
18:19:13 -!- ais523 has quit.
18:22:28 <int-e> (Perhaps I have written too many combinatorial search programs, where each program has a hot spot, but it looks different every for each program. Which means writing it in assembler is not going to worth my time, but I appreciate every speedup that I can get "for free" by using an optimizing compiler.)
18:24:26 <tromp> int-e: did you see our primes program in Haskell?
18:26:34 <int-e> at least I don't think so
18:26:42 <tromp> > let f='.';o c(x:y)=x:c y;z c(x:y)=f:c y;p n='p':ap fix p(o.n)in f:f:p z
18:26:44 <lambdabot> "..pp.p.p...p.p...p.p...p.....p.p.....p...p.p...p.....p.....p.p.....p...p.p....
18:26:58 <tromp> i added it to the AIT git repo
18:27:06 -!- tswett has quit (Changing host).
18:27:06 -!- tswett has joined.
18:27:48 <tromp> one day i'd like to see a bit- optimizing haskell-to-blc compiler that reproduces the blc program from Haskell
18:29:07 <tromp> although for some program the typing requirement is going to get in the way:(
18:29:44 <tromp> may need to use a haskell variant with optional typing
18:29:56 <tswett> Hey, I don't suppose I could get clog to log this IRC channel I just created?
18:30:23 <tswett> Who would I even talk to about that?
18:40:02 -!- Sprocklem has joined.
18:41:39 -!- AndoDaan has joined.
18:48:07 -!- nszceta has joined.
18:52:41 -!- augur has quit (Quit: Leaving...).
18:55:49 -!- nszceta_ has joined.
18:57:35 <elliott> tswett: you'd want to use glogbot instead
18:57:59 -!- nszceta has quit (Ping timeout: 255 seconds).
19:06:09 <Taneb> tswett, glogbot is Gregor's logging bot
19:06:15 <Taneb> the logs are at codu.org/logs
19:13:13 -!- augur has joined.
19:15:42 <tswett> Yes, those logs do look snazzy.
19:17:47 <tswett> Gregor: hey, how would you feel about logging #lepwick?
19:18:18 <int-e> izabera: https://gcc.gnu.org/develop.html#num_scheme
19:19:26 <tswett_> Am I allowed to send messages to #esoteric without being in it?
19:19:59 <tswett_> I intend to use this ability for the sole purpose of confusing everyone and causing distress and despair.
19:20:17 <int-e> tswett_: how nasty.
19:20:42 <int-e> (funny, irssi autocompletes that nick regardless of it not being present)
19:21:14 <tswett_> I wondered for a moment how come your message wasn't showing up on my screen.
19:21:27 <tswett_> The answer is, of course, somewhat obvious.
19:21:33 <int-e> tswett_: this is hurting you more than me
19:21:54 <tswett_> Who says it's hurting anyone?
19:26:01 <tswett_> Let me tell you what I intend to do with my amazing new powers of mischief.
19:35:55 <elliott> tswett: just /invite glogbot there
19:36:27 <elliott> no. I made it up to sabotage you
19:54:19 -!- Sprocklem has quit (Ping timeout: 250 seconds).
20:17:28 -!- Sprocklem has joined.
20:21:12 -!- nszceta_ has quit (Quit: Textual IRC Client: www.textualapp.com).
20:21:55 -!- elisa17 has joined.
20:44:38 -!- elisa17 has quit (Read error: Connection reset by peer).
20:48:38 -!- zadock has quit (Quit: Leaving).
21:00:09 -!- Patashu has joined.
21:07:39 -!- ais523 has joined.
21:12:09 -!- daria has quit (Ping timeout: 250 seconds).
21:14:59 <izabera> https://gcc.gnu.org/onlinedocs/gcc-5.1.0/jit/intro/tutorial05.html
21:16:14 <Taneb> I need to do things in programming languages that aren't Haskell or esoteric (or both) at some point
21:18:10 -!- AndoDaan_ has joined.
21:21:32 -!- AndoDaan has quit (Ping timeout: 255 seconds).
21:21:48 -!- Sprocklem has quit (Ping timeout: 256 seconds).
21:22:46 -!- Patashu has quit (Ping timeout: 256 seconds).
21:26:07 <int-e> tromp: I've done something horrible to compile a non-trivial part of Haskell to BLC :) http://sprunge.us/jead and an example: http://sprunge.us/KWRb
21:26:35 <int-e> (non-optimizing, proof of concept quality at best)
21:29:50 <tromp> wow, that looks awesome. much shorter than i expected!
21:30:55 <Taneb> How hard would that be to adapt into a Real Fast Nora's Hair Salon 3: Shear Disaster Download thingy?
21:31:03 <int-e> My motivation was to leverage ghc's desugaring for function definitions by pattern matching.
21:32:37 <int-e> (which will not work nicely yet because of the missing case in mkCase')
21:33:57 <int-e> Taneb: from the looks of it it's just a matter of pretty-printing.
21:34:16 <Taneb> int-e, I believe the languages only differ in syntax and IO convention
21:34:38 <tromp> in your Sample, how do the various constructors map to blc?
21:34:40 <int-e> the code knows nothing about the IO convention.
21:35:09 -!- oerjan has joined.
21:35:22 -!- ais523 has quit.
21:35:26 -!- callforjudgement has joined.
21:35:31 <int-e> tromp: church-encoding. data X = A x y | B has A x y = \a b -> a x y; B = \a b -> b
21:35:45 -!- callforjudgement has changed nick to ais523.
21:36:13 <tromp> i see, so Digit will in fact map to the right booleans
21:36:20 <int-e> so data Bool = True | False does the right thing, but List suffers from lack of Nil.
21:40:00 <tromp> right; that's gonna be a challenge to fit in
21:40:35 <tromp> i guess you want syntactive support for lists as well
21:41:02 <int-e> Is there a nicer way to encode let a = a'; b = b' in e than doing (\x. x x) (\x. (\a b p. p a' b') (x x (\a b. a)) (x x (\a b. b)) (\a b. e)?
21:42:33 <tromp> where a' and b' both refer to a and b?
21:43:26 <tromp> not that i know of
21:43:27 <int-e> hmm, that's missing a )
21:44:36 -!- `^_^v has quit (Quit: This computer has gone to sleep).
21:44:50 <tromp> i guess you'd have to peruse some functional compiler construction texts to discover
21:45:48 <int-e> It's not too bad, ghc also does the SCC decomposition for me.
21:46:52 <int-e> So as awful as the code I wrote is (really, I want to rewrite it from scratch), it looks like a plugin is a *really* quick way to get to the interesting bits of the translation.
21:47:11 <int-e> strongly connected component (in the dependency graph induced by let bindings)
21:47:35 -!- callforjudgement has joined.
21:47:37 -!- ais523 has quit (Read error: Connection reset by peer).
21:47:44 -!- callforjudgement has changed nick to ais53.
21:47:46 -!- ais53 has changed nick to ais523.
21:48:35 <oerjan> answer to what, or did i miss your question
21:49:03 <tromp> yes, plugin seems to be the way to go to avoid a huge codebase, and to get the full benefits of an evolving ghc
21:51:13 <ais523> oerjan: what "SCC" expands to
21:52:04 <oerjan> strongly connected component hth
21:52:37 <coppro> supreme court of canada hth
21:52:57 -!- Sgeo_ has joined.
21:53:22 -!- Sgeo_ has quit (Remote host closed the connection).
21:53:51 -!- Sgeo_ has joined.
21:54:34 <ais523> hmm, I was thinking about canadian politics recently
21:54:40 <ais523> during a conversation about the royal family
21:54:45 <ais523> I haven't followed it in ages
21:54:55 <ais523> anything particularly stupid happen recently? or has it been calm?
21:54:58 <Sgeo_> Do I have connection issues?
21:55:17 <ais523> Sgeo_: yes, but nowhere near as bad as mine
21:55:48 <Sgeo_> ais523, someone tried renaming a userpage
21:55:58 <ais523> I noticed, but I think oerjan fixed it
21:56:17 <Sgeo_> I think it counts as a particularly stupid thing though
21:56:20 <ais523> I think that's the user who keeps on coming up with creative new ways to screw up the wiki
21:57:49 <olsner> oh, if a ghc plugin is as easy as that looks, I might actually get going on jonguilexiphonaugh some day
21:58:35 <coppro> ais523: elections in two provinces
21:58:39 <coppro> PEI isn't making much news
21:58:49 <ais523> we have general elections coming up in the UK
21:58:51 <coppro> but the PCs are probably going to lose in Alberta, which is a big deal
21:59:07 <coppro> they're polling in third place, which is insane.
21:59:09 <coppro> They're behind the NDP
21:59:18 <ais523> what's the likely result? coalition?
21:59:27 <coppro> given that Alberta is usually considered the most conservative province, this is insane.
21:59:31 <coppro> Wildrose minority I think
21:59:50 <ais523> we're kind-of coalition-crazy in the UK because there's an election coming up and the polls say that no party's likely to get a majority, again
22:00:02 <ais523> but not just that, most of the plausible coalitions also are unlikely to get majorities
22:00:25 <ais523> and I'm stuck trying to figure out where to vote to get the best possible result for me
22:00:38 <coppro> coalition's unlikely. The governing party lies ideologically very firmly between the other two. Neither opposition party will likely want to coalition with them because they're politically toxic, and they likely won't coalition with each other
22:00:42 <coppro> far more likely is a Wildrose minority
22:01:23 <ais523> that makes sense, although you need at least some concessions in a minority government
22:01:29 <ais523> to prevent no confidence votes knocking you out
22:01:45 <ais523> the current coalition wanted to push no-confidence up to 66% but that didn't go through
22:02:13 <coppro> that would have been insanely stupid
22:03:10 -!- callforjudgement has joined.
22:03:13 <coppro> the best poll analysis out there predicts the governing party reduced to 10/87 seats
22:03:17 <callforjudgement> also the Queen has final say over who the Prime Minister is (the check on this is that her choice can be immediately no-confidenced out), and unlike most of the royal powers, has actually used it on occasion
22:03:36 <coppro> callforjudgement: as late as the 60s, it was expected to be used
22:03:45 -!- ais523 has quit (Disconnected by services).
22:03:46 -!- callforjudgement has changed nick to ais523.
22:03:50 <coppro> I don't expect they'll survive
22:03:57 <coppro> more likely they'll prop up a Wildrose or NDP government
22:04:22 <ais523> ideally would be if policies were decided on a case by case basis, rather than party lines
22:04:22 <coppro> probably wildrose because Canadians, especially Albertans, get itchy about the governing party not having the lead in seats
22:04:34 <ais523> but that doesn't really work for the budget
22:04:52 <coppro> ais523: I think it was the Cons in Britain that didn't elect their own party leader when in government in the 60s and actually expected the monarch to make the choice
22:05:43 -!- callforjudgement has joined.
22:05:50 -!- ais523 has quit (Disconnected by services).
22:05:52 -!- callforjudgement has changed nick to ais523.
22:06:16 <coppro> < coppro> ais523: I think it was the Cons in Britain that didn't elect their own party leader when in government in the 60s and actually expected the monarch to make the choice
22:06:43 <ais523> considering how party leadership debates in the UK often go, I think that was a sensible decision
22:08:29 <Phantom_Hoover> the snp seems to be able to find good ones for whatever reason
22:08:55 <FreeFull> Well I don't think we can vote for the SNP to rule over England
22:09:06 <ais523> not really, some of the SNP people are reasonably awful too
22:09:23 <ais523> FreeFull: that's what a Labour vote may work out as, there's huge debate about whether Labour + SNP will happen
22:09:46 <Phantom_Hoover> obviously, but both salmond and sturgeon are very good at what they do
22:09:47 <ais523> it's one of the most plausible combinations for which the numbers have a chance of working out, even though Labour would probably be fools to accept it
22:10:22 <Phantom_Hoover> the scenario i keep hearing is labour/snp confidence vote, then labour majority government
22:10:41 <Phantom_Hoover> neither party wants a coalition, especially not after the last one
22:11:17 <coppro> it could be labour minority propped up by SNP possibly
22:11:27 <ais523> Phantom_Hoover: you mean labour uses the SNP to confidence out whoever else tries to form a government?
22:11:29 <Taneb> It's gonna be interesting, no matter what, I think
22:11:56 <ais523> hmm, is there a good site to get latest predictions from?
22:12:06 <coppro> for canada it's threehundredeight.com
22:12:16 <coppro> you want a site that analyzes polls because a lot can go wrong
22:12:31 <ais523> yes, and different sites can come up with very different results
22:12:42 <ais523> sometimes it's just best to check bookie's odds because they have a financial incentive to be right
22:13:41 <Phantom_Hoover> i've heard the caveat a few times that bookies have an incentive to predict the perception of the outcome more than the outcome itself
22:13:41 <ais523> I get the feeling that the liberals don't want to be in a coalition this time around, but will probably do it anyway if they have to
22:13:56 -!- oren has quit (Quit: Lost terminal).
22:14:06 <izabera> <o> \o/ <o> \o/ <o> \o/ <o> \o/ <o> \o/ <o> \o/ <o> \o/ <o> \o/ stretching
22:14:16 <Phantom_Hoover> a liberal/tory coalition is not really feasible from any of the polls i've seen
22:14:31 <fizzie> I could give you pretty accurate predictions for the Finnish parliamentary election 2015.
22:14:34 <fizzie> (But only because they already counted the votes and published the results last weekend.)
22:14:57 <ais523> Phantom_Hoover: the DUP will make up some of that, I'm pretty sure they'd have no objection to being part of that coaltion
22:15:02 <ais523> but they'll still be short even adter that
22:16:27 <Phantom_Hoover> is that during the AV referendum people argued FPTP is good because it guarantees a strong majority government
22:16:50 <ais523> Phantom_Hoover: and they said that despite having a coalition government from an FPTP vote
22:17:21 <ais523> the problem is, that none of the major parties are really electable atm, and none of the minor parties are either
22:17:52 <ais523> I predict more success for minor parties than before, maybe the greens will get two seats this time for instance
22:18:07 <Phantom_Hoover> i love how small ukip's actual gains are looking to be
22:19:35 <ais523> they are going to gain, though, unfortunately
22:20:18 <Taneb> I think their gain will be quite spread out
22:20:25 <ais523> in a way you sort-of want them to be a big enough part of the government to become permanently unelectable
22:20:33 <ais523> but I'm not sure we'd survive the intervening years
22:20:51 <Taneb> ais523, if UKIP get into government I am activating my increasingly terrible back up plan
22:21:39 <ais523> Taneb: hmm, do I want to know what this is/
22:21:53 <ais523> anyway, I'm still undecided on how to vote
22:21:57 <Phantom_Hoover> i imagine that after 5 years of political irrelevance the wave will break and their vote will collapse
22:21:59 <Taneb> ais523, use the fact that I am dual national to go live in Australia
22:22:05 <ais523> both in terms of "who do I want to run the country" and "what vote maximizes the chance of this"
22:23:00 <ais523> they got a few council seats, and that was it I think?
22:23:26 <ais523> meanwhile, UKIP did hugely well at the European elections, but that's probably going to be their last major success
22:24:06 <ais523> actually I'd sort-of like to see a conservative+labour coalition, but the chances of that happening are basically 0
22:24:11 <ais523> even though they'd have easily enough seats
22:24:15 <ais523> they hate each other too much
22:24:15 <Taneb> It amuses me that a lot of the UKIPish parties throughout Europe refuse to work with each other in Europarl
22:24:27 <ais523> Taneb: yep, UKIP refusing to work with the Front National, for instance
22:24:39 <ais523> they basically all don't want to be associated with each other, because they're trying to look respectable
22:24:48 <ais523> and consider each other to be disrespectable
22:24:53 <Taneb> iirc that led to the left block getting power
22:25:24 <ais523> that makes perfect sense, actually
22:26:40 -!- boily has joined.
22:27:38 <Phantom_Hoover> i got poll cards for both leamington and edinburgh north, i think i'll probably vote in leamington since it's a tory marginal and edinburgh north's polling a 14-point snp lead
22:27:58 <Phantom_Hoover> plus i also get to avoid the awkward topic of the snp with my dad when i next see him
22:28:22 <Taneb> I have poll cards for York Outer and Hexham, and by broadly similar reasoning I'll only be voting in the former
22:28:25 <ais523> I thought you had to say which place you were voting in in advance?
22:28:28 <ais523> to stop you voting in both?
22:28:43 <Taneb> ais523, university students have weird rules
22:28:48 <Taneb> And can actually vote in both
22:29:11 <ais523> one person, one vote, surely?
22:29:20 <Phantom_Hoover> i looked it up the other day, i was under the impression that-- yeah
22:29:27 <Taneb> Unless you're a university student living away from home
22:29:37 -!- mitchs_ has joined.
22:29:52 <Phantom_Hoover> http://www.aboutmyvote.co.uk/register-to-vote/students
22:29:56 -!- mitchs has quit (Ping timeout: 255 seconds).
22:30:05 <Phantom_Hoover> "It is a criminal offence to vote twice in a UK general election."
22:31:00 <Taneb> That is different to what I recall
22:31:05 <Phantom_Hoover> i had a friend tell me the same thing so this is obviously a common urban legend
22:31:11 <ais523> it says you can vote in both local elections
22:31:22 <ais523> but only in one general election constituency
22:31:27 <ais523> which would allow you to use both poll cards
22:32:38 <Phantom_Hoover> i applied for a postal vote in edinburgh, maybe that means i have to vote there
22:33:10 <Phantom_Hoover> "Once you've used your postal vote you can't change your mind and vote at a polling station."
22:33:13 -!- S1 has joined.
22:33:23 <ais523> Phantom_Hoover: I believe that's "used" rather than "applied for", though
22:33:40 <ais523> I know that a while ago, we had to hand-deliver a postal vote to a polling station, because it hadn't been posted in time
22:33:53 -!- S1 has left.
22:33:53 <ais523> which is another weird variant on that
22:37:14 <Taneb> Well, this'll be the first general election I've voted n
22:39:02 -!- staffehn has quit (Remote host closed the connection).
22:42:04 -!- staffehn has joined.
22:45:39 <Taneb> I am not very good at writing a CV
22:46:27 <fizzie> Perhaps you should write a version control system instead.
22:46:59 <boily> Taneb: Tanelle. is it written with LaTeX?
22:47:12 <Taneb> boily, the LaTeX is the easier part
22:47:18 <Taneb> And I am still not very good at it
22:48:50 -!- bb010g has quit (Quit: Connection closed for inactivity).
22:49:31 <ais523> Taneb: have you seen the eurocard thing?
22:49:42 <ais523> it's a european standard for CVs, the same way that PAX is a POSIX standard for tarballs
22:49:52 <ais523> I've been considering using it but nobody's asked me for a CV yet
22:50:08 <boily> could be worse. I'm not even European!
22:50:15 <Taneb> ais523, do you have a link?
22:50:48 <ais523> apparently I misremembered the name
22:51:22 <ais523> https://en.wikipedia.org/wiki/Europass
22:55:41 -!- callforjudgement has joined.
22:55:54 -!- ais523 has quit (Disconnected by services).
22:55:55 -!- callforjudgement has changed nick to ais523.
23:03:38 <Taneb> Well, goodnight! :)
23:10:28 -!- shikhin_ has joined.
23:11:30 -!- shikhin has quit (Ping timeout: 250 seconds).
23:12:20 -!- shikhin_ has changed nick to shikhin.
23:18:05 -!- ais523 has quit.
23:25:13 <quintopia> you always disappear before responding to me
23:26:26 <quintopia> what would be a good project to refresh my c skills
23:27:32 <quintopia> those usually dont require much dynamic memory allocationx
23:28:12 <boily> hmm... mmmh... what would make an interesting small C project?
23:28:13 <paul2520> write a brainfuck interpreter that dynamically assigns the tape as it's needed
23:28:22 <boily> fungot: do you have inspirational ideas?
23:28:22 <fungot> boily: but hey... whatever floats your boat") in my old days. fnord
23:28:29 <boily> fungot: go boat yourself.
23:28:29 <fungot> boily: the optimizing run.c was not ready for prime time :) :) :) :) :)
23:28:41 <boily> quintopia: what about an IRC bot?
23:28:48 <fungot> boily: but of course. i know what to do with antpony.
23:28:57 <boily> quintopia: and call it antpony.
23:29:16 <boily> ¿porqué no los dos?
23:29:23 <boily> an IRC/gopher server!
23:29:41 <boily> (I highly doubt the usefulness of the thing, but we're in #esöteric.)
23:30:00 <pikhq> The great thing about an HTTP server is, simple ones are in fact quite easy.
23:31:04 <boily> indeed. I managed to get one running on an Arduino without too much hassle.
23:31:16 <boily> serving .png was harder than the HTTP part!
23:32:23 <pikhq> Doing HTTP *well* is tricky, but you can get it functional with much, much less.
23:32:28 <pikhq> Even if you're doing HTTP/1.1.
23:33:16 <pikhq> Admittedly an HTTP/1.1 server that does Connection: close for everything kinda sucks, but it's valid.
23:33:39 -!- TieSoul_ has joined.
23:33:40 <boily> quintopia: good question.
23:35:21 -!- TieSoul has quit (Ping timeout: 248 seconds).
23:35:25 -!- NotSoul has joined.
23:36:00 <HackEgo> [wiki] [[Matrix]] M http://esolangs.org/w/index.php?diff=42721&oldid=42151 * Paul2520 * (-1) /* Language Overview */ fixed typo
23:39:06 -!- TieSoul_ has quit (Ping timeout: 248 seconds).
23:43:11 -!- creationBlues has joined.
23:54:31 <HackEgo> [wiki] [[Element]] http://esolangs.org/w/index.php?diff=42722&oldid=42669 * Phi * (+493) added more examples
00:06:17 -!- boily has quit (Quit: DIVINATORIAL CHICKEN).
00:10:23 <HackEgo> [wiki] [[Special:Log/newusers]] create * SplatterWorthy * New user account
00:25:48 -!- trout has changed nick to constant.
00:29:37 -!- ^v has joined.
00:34:35 <HackEgo> slist A6A6I5: Taneb atriq Ngevd Fiora Sgeo ThatOtherPerson alot
00:39:26 -!- Phantom_Hoover has quit (Read error: Connection reset by peer).
00:58:23 <HackEgo> echo -n "$(basename "$0")${@:+ }$@: "; tail -n+2 "$0" | xargs; exit
01:05:16 <paul2520> I don't get it... what does it mean?
01:31:57 -!- oren has joined.
01:32:17 <oren> it is all over
01:33:53 <oren> hmm that's too general. my school is all over
01:34:50 -!- staffehn has quit (Ping timeout: 265 seconds).
01:35:23 -!- staffehn has joined.
01:37:24 <HackEgo> [wiki] [[Gibberish/JavaScript/Escape sequence]] http://esolangs.org/w/index.php?diff=42723&oldid=42631 * Esowiki201529A * (+27)
01:39:44 <HackEgo> [wiki] [[Gibberish/JavaScript/HTML interpreter]] http://esolangs.org/w/index.php?diff=42724&oldid=42589 * Esowiki201529A * (+3) /* See also */
01:40:58 <HackEgo> [wiki] [[Gibberish/JavaScript/Escape sequence]] http://esolangs.org/w/index.php?diff=42725&oldid=42723 * Esowiki201529A * (+58)
01:42:40 <HackEgo> [wiki] [[Gibberish/JavaScript/Escape sequence]] http://esolangs.org/w/index.php?diff=42726&oldid=42725 * Esowiki201529A * (+29) /* See also */
01:45:02 <HackEgo> [wiki] [[Gibberish/JavaScript/Escape sequence]] http://esolangs.org/w/index.php?diff=42727&oldid=42726 * Esowiki201529A * (+206) /* Unprintable character */
01:50:02 -!- AndoDaan_ has quit (Quit: Going, going, gone.).
01:53:07 <HackEgo> [wiki] [[Gibberish/JavaScript/Escape sequence]] http://esolangs.org/w/index.php?diff=42728&oldid=42727 * Esowiki201529A * (+120) /* Blank characters */
01:55:00 -!- oerjan has quit (Quit: ZZZ).
01:55:57 <HackEgo> [wiki] [[Gibberish/JavaScript/Escape sequence]] http://esolangs.org/w/index.php?diff=42729&oldid=42728 * Esowiki201529A * (+89) /* Unprintable characters */
02:13:59 <HackEgo> [wiki] [[Gibberish/JavaScript/Escape sequence]] http://esolangs.org/w/index.php?diff=42730&oldid=42729 * Esowiki201529A * (+57) /* Unprintable characters */
02:16:30 <HackEgo> [wiki] [[Gibberish/JavaScript/Escape sequence]] http://esolangs.org/w/index.php?diff=42731&oldid=42730 * Esowiki201529A * (+41) /* Unprintable characters */
02:17:17 <HackEgo> [wiki] [[Piet++]] N http://esolangs.org/w/index.php?oldid=42733 * SplatterWorthy * (+6066) Created page with "This is a work in progress, and is still in development. '''Piet++''' is a stack orientated 2 dimensional programming language expanding upon the functionality of [[Piet]]. I..."
02:18:39 <HackEgo> [wiki] [[Gibberish/JavaScript/Escape sequence]] http://esolangs.org/w/index.php?diff=42734&oldid=42731 * Esowiki201529A * (+40) /* Unprintable characters */
02:20:19 <creationBlues> So I've been thinking about the specifics of Piet++ recently, does anybody have any commentary on the language?
02:40:12 -!- creationBlues has quit (Quit: Page closed).
03:00:53 -!- adu has joined.
03:03:03 <coppro> where's the spec for Piet++
03:35:00 -!- Sprocklem has joined.
03:48:13 -!- GeekDude has quit (Quit: {{{}}{{{}}{{}}}{{}}} (www.adiirc.com)).
04:58:20 <oren> http://ctrlv.in/562934 <-- oh the horror
05:09:18 -!- shikhin has quit (Ping timeout: 256 seconds).
05:23:55 -!- mitchs has joined.
05:26:43 -!- mitchs_ has quit (Ping timeout: 256 seconds).
05:46:47 -!- AndoDaan has joined.
05:49:12 -!- bb010g has joined.
06:03:32 -!- rdococ has joined.
06:05:09 -!- adu has quit (Quit: adu).
06:13:10 -!- ^v has quit (Read error: Connection reset by peer).
06:31:14 <mitchs> "mitchs_ already in use. Retrying with mitchs_..." <-- HexChat has a stubborn side
06:40:33 -!- AndoDaan has quit (Ping timeout: 272 seconds).
06:41:31 -!- constant has quit (Ping timeout: 256 seconds).
06:41:54 -!- zadock has joined.
06:50:09 <oren> I guess it's a list of nicks with no nicks in it?
06:52:58 <izabera> `` echo james lily >> bin/emptylist
06:53:06 <izabera> `` echo harry ron hermione >> bin/emptylist
06:53:25 <HackEgo> echo -n "$(basename "$0")${@:+ }$@: "; tail -n+2 "$0" | xargs; exit \ james lily
06:53:31 <izabera> `` echo harry ron hermione >> bin/emptylist
06:53:42 <HackEgo> emptylist: james lily harry ron hermione
07:02:19 -!- hjulle has joined.
07:30:16 -!- AndoDaan has joined.
07:32:34 <oren> How many items can be in one square in DF?
07:34:04 <oren> Apparently every non-food item in my fortress
07:34:27 <oren> (other than corpses and refuse)
07:38:48 -!- AndoDaan has quit (Read error: Connection reset by peer).
07:40:40 -!- shikhin has joined.
07:42:34 -!- daria has joined.
07:42:34 -!- daria has quit (Changing host).
07:42:34 -!- daria has joined.
07:58:28 <FireFly> izabera: I think the point is to be able to copy from it when creating a new *list
08:08:24 -!- hjulle has quit (Ping timeout: 250 seconds).
08:24:06 -!- Patashu has joined.
08:24:40 -!- shikhin has quit (Ping timeout: 244 seconds).
08:38:39 -!- AnotherTest has joined.
08:43:20 -!- AnotherTest has quit (Ping timeout: 264 seconds).
08:44:00 -!- shikhin has joined.
08:56:33 -!- Sprocklem has quit (Ping timeout: 256 seconds).
09:03:31 -!- AndoDaan has joined.
09:03:34 <elliott> like RSS but it causes more #esoteric arguments
09:09:27 <elliott> slist is homestuck, olist is order of the stick, I forget the others
09:28:37 -!- daria has quit.
09:37:48 -!- shikhin has quit (Ping timeout: 252 seconds).
09:38:57 -!- idris-bot has quit (Quit: Terminated).
09:39:16 -!- idris-bot has joined.
09:40:25 -!- PinealGlandOptic has quit (Ping timeout: 272 seconds).
09:40:49 -!- shikhin has joined.
09:41:46 -!- shikhin has quit (Client Quit).
09:59:50 -!- shikhin has joined.
10:19:10 -!- zadock has quit (Quit: Leaving).
10:20:30 -!- zadock has joined.
10:21:01 <FireFly> `echo are you alive, HackEgo?
10:22:04 <HackEgo> bin/danddreclist \ bin/dontaskdonttelllist \ bin/don'taskdon'ttelllist \ bin/emptylist \ bin/erflist \ bin/list \ bin/llist \ bin/makelist \ bin/mlist \ bin/olist \ bin/pbflist \ bin/slist \ bin/smlist \ bin/testlist
10:22:53 <oren> apparently Hackego is FIFO
10:31:14 <izabera> http://i.4cdn.org/wsg/1427914345783.gif
10:33:38 -!- boily has joined.
10:34:53 -!- f|`-`|f_ has joined.
10:35:57 -!- AndoDaan has quit (Quit: Going, going, gone.).
10:36:05 -!- f|`-`|f has quit (Ping timeout: 240 seconds).
10:36:19 -!- f|`-`|f_ has changed nick to f|`-`|f.
10:58:09 <FireFly> izabera: ↑ so that's what it's for
11:00:02 -!- mbrcknl has changed nick to crickets.
11:00:37 -!- crickets has changed nick to mbrcknl.
11:26:43 -!- boily has quit (Quit: LUMINARY CHICKEN).
11:58:47 -!- oerjan has joined.
11:59:24 -!- Sgeo_ has quit (Read error: Connection reset by peer).
12:11:33 <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/
12:23:51 <Taneb> I had a thought today
12:24:30 <Taneb> Matrices of regular expressions
12:24:36 <Taneb> I have no idea what they would do
12:26:52 <Taneb> But you could like multiply them sort of
12:26:56 <oerjan> if you can make a commutative semiring of regular expressions, the rest is simple.
12:27:33 <Taneb> It's not commutative, I don't think, but it has an identity
12:27:59 <oerjan> too bad, commutativity is required for matrices to behave nicely
12:28:30 <oerjan> well at least for determinants to do
12:29:03 <Taneb> 0 is the empty language, 1, is the language containing the empty string, + is union, * is concatenation
12:29:19 <oerjan> i suppose it's not entirely obligatory, i vaguely recall we made matrices out of C*-algebra elements back in my day
12:30:01 <oerjan> and C*-algebras aren't very interesting if they're commutative (then they're essentially just ordinary function spaces)
12:31:58 <oerjan> Taneb: although the thing that's _completely_ non-negotiable for sanity is distributivity.
12:32:07 -!- Patashu has quit (Ping timeout: 250 seconds).
12:32:13 <Taneb> I think we have that
12:32:37 <Taneb> a(b U c) is the same as (ab) U (ac)
12:33:13 <oerjan> and union is commutative. maybe it checks out as a semiring then.
12:33:52 <Taneb> It's definitely a semiring
12:36:19 -!- rdococ has quit (Ping timeout: 246 seconds).
12:42:56 -!- Sgeo has joined.
12:45:47 <Taneb> Now, the question is, is there any way this matrix could be useful
12:46:30 <oerjan> well if you have a vector of languages, what happens if you apply the matrix to it
12:46:53 <oerjan> this should be s "semi"linear transformation
12:48:46 <oerjan> hm this resembles a kind of reverse parsing, i think
12:50:47 <oerjan> you map a vector of regexps/languages to another vector, formed by adding prefixes to the original elements
12:51:36 <oerjan> and parsing usually starts with recognizing prefixes
13:27:11 -!- spateerworth has joined.
13:27:29 -!- Adam_T has joined.
13:28:14 -!- spateerworth has quit (Client Quit).
13:30:26 -!- Spatterworthy has joined.
13:31:26 <elliott> `relcome Adam_T Spatterworthy
13:31:36 <HackEgo> Adam_T: Spatterworthy: 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.)
13:34:46 -!- Spatterworthy has quit (Ping timeout: 246 seconds).
13:55:56 -!- zadock has quit (Ping timeout: 250 seconds).
13:59:43 <oren> ol pop in an oak pop in an oak ??incomprehensible??
14:00:50 <oren> seriously it's like the singer suddenly switches to vcantonese
14:02:07 <Taneb> My PSU arrived! :)
14:03:34 -!- `^_^v has joined.
14:06:17 <oren> Taneb: how many outputs
14:06:34 <oren> and how much current?
14:13:35 <oren> Did you know, if you connect two PSU's in series, it doesn't work like batteries? Instead one of the PSU's will burn up.
14:16:30 <oren> (or sometimes the wire connecting them. I tried several configurations, it just doesn't work)
14:21:51 <Taneb> Don't PSUs convert AC to DC?
14:21:56 <Taneb> What did you think would happen?
14:23:11 <oren> I assumed if I connected the 0V of PSU A to the +12V of PSU B, that the voltage difference from the +12V of A to the 0V of B would be a total of 24V.
14:24:17 <oren> It works like that if you do it with two 9V batteries
14:24:30 <oren> you get 18V difference
14:26:19 <oren> But no. Instead your copper wires become !!copper wire!!s
14:27:01 <oren> even before the circuit is even a closed circuit
14:36:35 -!- GeekDude has joined.
14:47:19 <oerjan> shachaf: i feel like i'm getting in over my head :(
15:02:39 -!- `^_^v has quit (Ping timeout: 255 seconds).
15:07:54 -!- rdococ has joined.
15:08:34 -!- mitchs_ has joined.
15:11:06 -!- mitchs has quit (Ping timeout: 256 seconds).
15:12:37 -!- `^_^v has joined.
15:12:42 -!- ais523 has joined.
15:18:13 -!- ais523 has quit (Read error: Connection reset by peer).
15:18:20 -!- ais523 has joined.
15:19:18 <Taneb> Installing a PSU is very easy when you have a more competent housemate who likes to do things his own way
15:24:23 * oerjan notes that Taneb's statement could be either literal or sarcastic, dependently.
15:24:40 <Taneb> oerjan, it's actually both
15:24:46 <Taneb> I'm not doing any work for it
15:25:02 <Taneb> Although my housemate, who is in fact more competent at this sort of thing, is having some difficulty
15:28:33 <int-e> . o O ( It's called delegation. )
15:30:15 <Taneb> He pretty much made me sit down so he could do it
15:38:37 <shachaf> oerjan: seems that spj has not been kind to you hth
15:49:39 <tswett> Given a set S of 32 elements, how many subsets of S can you put in a collection T such that no element of T is a subset of another element of T?
15:49:46 <tswett> Is it just 32 choose 16?
15:49:48 <oerjan> Taneb: i made https://ghc.haskell.org/trac/ghc/ticket/10343
15:51:12 <oerjan> not realizing it would mean further obligations hth
15:52:01 -!- b_jonas has joined.
15:52:48 <oerjan> my last comment tries to condense to the core of it
16:02:25 * oerjan forgot that he shouldn't copy and paste rendered markup into source markup
16:04:12 -!- oerjan has quit (Quit: Later).
16:12:43 <Taneb> Aaaah my desktop is working!
16:17:18 -!- zzo38 has joined.
16:18:18 -!- variable has joined.
16:30:11 -!- emapaere has joined.
16:33:19 <HackEgo> emapaere: 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.)
16:34:09 <b_jonas> help, I have digged too deep into the Windows API!
16:34:40 <b_jonas> I need a ring of jumping or levitation so I can get out
16:40:55 <lambdabot> Any change is resisted because bureaucrats have a vested interest in the chaos in which they exist.
16:41:44 -!- emapaere has quit (Quit: Ex-Chat).
16:41:56 <ais523> oh, I thought that was fungot for a moment
16:41:56 <fungot> ais523: fnord egobot ___________________ ' !hangman lcase-guess' to guess a letter!... i think
16:42:00 <ais523> and thought it was oddly insightful
16:49:07 -!- TieSoul has joined.
16:53:02 -!- NotSoul has quit (Ping timeout: 245 seconds).
17:00:25 <fizzie> What, you don't find ___________________ insightful?
17:00:46 <ais523> it's clearly a hangman puzzle
17:00:54 <ais523> with nobody to check the guesses
17:01:00 <ais523> which is kind-of philosophical in its own way
17:01:55 <fungot> fizzie: since lisp was devised, it has to make an example ( other than making it do the right thing? continuations being there and all
17:03:59 <fizzie> fungot: 't's? 'a's? 'o's? 'i's? 'n's? 's's? 'h's? 'r's? 'd's? 'l's? 'u's?
17:03:59 <fungot> fizzie: pfft. you and your crazy fnord do it in
17:05:31 -!- ais523 has quit.
17:11:18 -!- ais523 has joined.
17:15:11 <b_jonas> that looks like an eliza template to me, not a hangman puzzle
17:16:06 <fizzie> The '!hangman lcase-guess' part is kind of a giveaway, though.
17:46:22 -!- b_jonas has quit (Quit: http://www.kiwiirc.com/ - A hand crafted IRC client).
17:54:53 -!- zzo38 has quit (Remote host closed the connection).
19:01:04 -!- nszceta has joined.
19:04:58 -!- b_jonas has joined.
19:17:30 -!- nycs has joined.
19:18:45 -!- `^_^v has quit (Ping timeout: 264 seconds).
19:21:15 -!- CADD has joined.
19:22:34 <b_jonas> everyone, gcc 5.1 is released
19:28:11 -!- rdococ has quit (Quit: Page closed).
19:30:01 -!- nszceta has quit (Remote host closed the connection).
19:31:14 -!- nycs has quit (Ping timeout: 246 seconds).
19:34:15 <nortti> a simple system I've been playing with like since forever: you have 4 objects (e, A, B, C) and one operator (I generally don't mark it) that is communtative and associative. eX = X, AB = C, BC = A, AC = B, XX = e
19:36:38 <nortti> originally, eABC were operations on rotating a rhombus while keeping it symmetrical to the original one (do nothing, flip along X axis, flip along Y axis, rotate 180° about the center), but soon I figured that the 4 positions (0, 1, 2, 3) could be represented as (0e, 0A, 0B, 0C), and dropped the positions off
19:37:18 -!- `^_^v has joined.
19:37:24 <ais523> nortti: that reminds me of quaternions
19:37:41 <nortti> it is probably not that interesting, but I've noticed a couple fun properties on it, like if you represent (e, A, B, C) as (00, 01, 10, 11), the operator is XOR
19:37:49 <ais523> except with quaternions, you have ij = k, jk = i, ki = j, but ji = -k, kj = -i, ik = -j
19:38:02 <nortti> yeah, I've run into them
19:38:03 -!- b_jonas has quit (Ping timeout: 248 seconds).
19:38:09 <nortti> didn't make that connection, tho
19:38:12 <ais523> and xx (where x = i, j, or k) = -1
19:38:37 <ais523> actually I think this is the set {1 or -1, i or -i, j or -j, k or -k} under quaternion multiplication
19:39:27 -!- b_jonas has joined.
19:41:02 -!- vodkode_ has joined.
19:42:25 <nortti> a reduced version of it uses only (A, B). I usually replace then e as AA and C as AB. there are a couple fun ways to evaluate it, for example xxx = x, BA = AB, BB = AA
19:51:29 <nortti> hmm, actually, the xy = yx is not requires, since if (x,y) is (A,A) or (B,B), it'd be a nop, and (A,B) and (B,A) can be gotten using the BA = AB rule
19:52:18 <ais523> on the length of the input, for all reasonable grammars?
19:52:35 <b_jonas> ais523: no, I don't think so
19:52:49 <b_jonas> ais523: isn't it a full backtrack parser?
19:53:01 -!- Sprocklem has joined.
19:53:12 <int-e> I guess the question is for Parsec without `try`.
19:53:22 <ais523> b_jonas: I think so, yes
19:53:41 <ais523> int-e: I'm thinking about backtrack parsers versus LR parsers
19:53:55 <ais523> versus the sort-of pseudo-LR I'm ending up with in ayacc that has more primitives
19:54:07 <ais523> sadly I can't match bison output in size, probably not even with the hand-coded asm I'm working on
19:54:21 <ais523> I might be able to match it in speed because of better branch prediction, but maybe not due to caching effects
19:54:49 <ais523> ayacc is now feature-complete against POSIX, except for occasional UB in cases that shouldn't matter but nonetheless needs eliminating
19:54:52 <b_jonas> ais523: by pseudo-LR, do you mean optimized LR?
19:55:01 <ais523> (such as returning an uninitialized value from a function, then not using it)
19:55:13 <ais523> b_jonas: it's based on optimizing LR tables
19:55:13 <b_jonas> ais523: good, is there a public release? and where?
19:55:19 <ais523> but it has rather more actions than shift/reduce
19:56:13 <ais523> b_jonas: http://nethack4.org/media/alex/ayacc/ayacc.pl , public but currently license-undecided
19:56:16 <ais523> although I'll probably do GPL3
19:56:29 <ais523> also I haven't finished documenting it yet
19:58:33 <b_jonas> ais523: is that a release, or only a snapshot or escape?
19:59:18 <ais523> that's pointing straight into the darcs repo
19:59:21 <int-e> ais523: Parsec has this odd behavior of committing to a choice when at least one input token has been consumed, unless one uses `try` explicitly. It's meant to plug a common memory leak, but I think it also means that if you stick to the Applicative fragment of Parsec (so you're not able to build parsers from previously parsed things, which the monadic parser interface allows) it should be...
19:59:27 <int-e> ...either nonterminating or linear...
20:00:33 <int-e> (still without `try`.)
20:01:15 <ais523> hmm, LR parsers are a bit like that
20:01:26 <ais523> they always decide to either reduce or not reduce (and if reducing, how) on every token
20:01:31 <ais523> which is what keeps them O(n)
20:01:45 <int-e> This is highly informal; I'm actually missing some finiteness constraint in there as well (you can write down an infinite grammar, with increasing number of branches, even when sticking to the Applicative fragment... so tricky.)
20:01:47 <ais523> the big innovation over LL parsers is that they can decide to shift without committing as to why
20:02:10 -!- `^_^v has quit (Ping timeout: 265 seconds).
20:03:11 <ais523> it's interesting looking over the C-INTERCAL grammar for places where that's necessary
20:03:50 -!- `^_^v has joined.
20:23:51 <b_jonas> in 4-intercal with the prefix operator syntax extension, does DO.6<-,7SUB#82?#9 parse as DO.6<-,7SUB#8#2?9 or as DO.6<-,7SUB#82#?9 or something else?
20:24:18 <ais523> b_jonas: the 82 parses as a single token in C-INTERCAL at least
20:24:39 <b_jonas> ais523: I see. what if I put a space, like DO.6<-,7SUB#8 2?#9
20:24:50 <ais523> then I think it'd lex as an 8 and a 2?
20:25:15 <ais523> C-INTERCAL uses a separate lexer and parser
20:26:45 <ais523> I've seen a plausible argument that INTERCAL-72 allows spaces inside keywords (that aren't READ OUT)
20:26:48 <b_jonas> ais523: shouldn't as in to emulate the strange behavior of certain BASIC implementations where AX OR B parses as A XOR B ?
20:26:58 <ais523> err, (not just READ OUT, the other ones too)
20:27:00 <b_jonas> and I think some FORTRAN implementations
20:27:17 <b_jonas> ais523: yeah, in fact I think some dialects of basic spelt GOTO as GO TO
20:27:25 <b_jonas> but later GOTO became the norm
20:27:29 <ais523> Algol 68 has a go to keyword
20:27:34 <ais523> but then, it allows spaces inside variable names too
20:27:43 <b_jonas> significant or non-significant spaces?
20:27:54 <ais523> and variable names that are the same as keywords
20:28:00 <ais523> they're significant in 68 and nonsignificant in 60, IIRC
20:38:17 -!- PinealGlandOptic has joined.
20:41:22 <fizzie> "The World Bank has already given approval for the payment of your fund while they deliberately delay your payment and continue to demand fees from different departments mostly from Africa, the UK , Europe and Asia all in an attempt to enrich their private accounts. I wonder why you haven’t notice all these while. I am Christian and my religion does not permit such."
20:41:32 <fizzie> The last bit was a new twist for me.
20:42:04 <fizzie> (This is from an "IMF agent attach to the World Bank office".)
20:43:14 <fizzie> "Not very long after the World Bank completed the acquisition process of all pending payments, I discovered that my boss connived with some top officials of the World Bank to divert funds already approved to settle inheritances, email lottery winners and international contractors."
20:43:24 <fizzie> Nice "cover all common spam stories" part there.
20:47:55 <b_jonas> ais523: so when you say the docs is incomplete, that means you'll document the basic C++ support ayacc offers (same C-like interface, but brace blocks in grammar contain C++ code, and output is to be compiled with C++), right?
20:48:28 <ais523> it doesn't really have C++ support yet
20:48:34 <ais523> except inasmuch as C works
20:48:42 <ais523> that'll change, but I need help from someone who knows more C++ than I do
20:50:10 <b_jonas> ais523: I mean only basic C++ support. you probably don't really need to implement anything for that, you just have to make sure you don't use anything in the template that doesn't work in C++, such as implicit cast from void* or such things
20:51:03 <ais523> I'm thinking more about RAII support
20:51:10 <b_jonas> ais523: also, I assume you'll document more about how the interface is reentrant, and how it doesn't heap-allocate anything so you can just break out of it with longjmp or C++ exceptions, how to destroy symbol values when you break out this way or when there's a parse failure
20:51:14 <ais523> without that it isn't really C++
20:51:27 <b_jonas> ais523: well sure, you can do more lots of things for more advanced C++ support
20:51:32 <b_jonas> I might even be able to help in that
20:53:13 <b_jonas> oh by the way, if the language is currently determined by the source output filename given by the -o switch, then some C++ people will hate you for using .h or .hpp or .hxx as a file extension of the header no matter what extension you choose, unless you add an option to set the name of the header
20:53:34 <b_jonas> C++ file extensions are in a sad state
20:55:03 <int-e> #include <vector> // the solution is obvious
20:55:58 <b_jonas> int-e: um, why would you need that? ayacc's C output already doesn't heap allocate anything
20:56:09 <int-e> .hh is also a thing.
20:56:21 <int-e> But what about .H to match .C?
20:56:37 <b_jonas> it allocates everything on the stack, so RAII should work fine, except when it uses longjmp which has to be replaced by C++ exceptions if you want it to work, and <vector> doesn't help in that
20:56:41 <int-e> b_jonas: I was talking about file extensions
20:56:56 <b_jonas> you mean no extension at all
20:57:34 <b_jonas> int-e: ok, but ayacc won't choose any of those by default, so anyone who likes those rarer choices will hate you anyway
20:58:43 <b_jonas> ayacc will probably have to use either .hpp or .h by default, because those are the most common
20:59:16 <b_jonas> (admittedly, Eigen uses no-extension files for its public interface.)
20:59:27 <int-e> The only .H C++ files I have are from an example in the ocaml source distribution...
21:00:06 -!- Patashu has joined.
21:00:08 <int-e> and those have all capital file names, so some case-insensitive file system was probably involved at some point.
21:00:40 <int-e> (Sorry, for some reason I find those trivial conventions quite fascinating.)
21:00:49 <b_jonas> int-e: what extension does that use for c++ source files
21:01:43 <int-e> or, apparently, .CPP.gz ... to save space?!
21:02:44 <b_jonas> last week I've seen actual unix compress compressed files (with a .Z extension) on the web
21:03:26 <b_jonas> and they weren't just named that, they were really that
21:04:16 <b_jonas> have you seen such a thing yet?
21:05:08 <int-e> found another one... https://github.com/ghc/nofib/blob/master/real/gg/gg.stdin-2.Z
21:05:34 <int-e> (from the nofib benchmark suite used by ghc)
21:06:23 <int-e> but usually it's just very old software (xdu-3.0.tar.Z) or old papers from people's homepages (I have a number of foo.ps.Z)
21:06:55 <b_jonas> yes, these were old papers in ps.Z
21:07:10 <b_jonas> it surprised me, usually they're gzipped instead
21:09:46 <int-e> what a nice headline... "Using the docker command to root the host (totally not a security issue)"
21:11:21 <int-e> (link: http://reventlov.com/advisories/using-the-docker-command-to-root-the-host )
21:16:16 -!- b_jonas has quit (Remote host closed the connection).
21:16:37 <elliott> isn't the docker command meant to be restricted o those with root access
21:16:47 <elliott> since you can easily do whatever you want to the system with it anyway
21:17:27 <elliott> i mean i've not used docker but i knew that so it's probably communicated well enough already
21:22:32 -!- Patashu has quit (Ping timeout: 246 seconds).
21:24:34 -!- Sprocklem has quit (Ping timeout: 245 seconds).
21:29:13 -!- variable has quit (Ping timeout: 250 seconds).
21:45:30 -!- `^_^v has quit (Quit: This computer has gone to sleep).
21:45:37 -!- ais523 has quit (Ping timeout: 265 seconds).
22:00:54 -!- Phantom_Hoover has joined.
22:06:54 -!- shikhin has quit (Ping timeout: 256 seconds).
22:09:26 -!- shikhin has joined.
22:21:44 -!- oerjan has joined.
22:38:22 <oerjan> at least goldfire seems to understand what i mean :P
22:39:06 -!- variable has joined.
23:00:49 -!- atehwa has quit (Ping timeout: 252 seconds).
23:01:01 -!- villasukka has quit (Ping timeout: 265 seconds).
23:02:05 -!- villasukka has joined.
23:02:32 -!- atehwa has joined.
23:13:06 -!- atehwa has quit (Ping timeout: 265 seconds).
23:14:04 -!- villasukka has quit (Ping timeout: 265 seconds).
23:20:43 -!- atehwa has joined.
23:21:15 -!- villasukka has joined.
23:23:15 -!- egw has joined.
23:39:58 -!- idris-bot has quit (Quit: Terminated).
23:43:09 -!- GeekDude has quit (Quit: {{{}}{{{}}{{}}}{{}}} (www.adiirc.com)).
23:43:16 -!- idris-bot has joined.
00:03:34 -!- Sprocklem has joined.
00:03:50 <oerjan> i made a long reply to spj on the flaky trac site and forgot to copy to a safe place before submitting.
00:05:01 -!- GeekDude has joined.
00:06:00 -!- egw has quit.
00:06:31 <HackEgo> [wiki] [[Brainfuck algorithms]] http://esolangs.org/w/index.php?diff=42735&oldid=42540 * 199.21.86.10 * (-104) /* if (x == 0) { code } */ This section was redundant with the "if (x) { code1 } else { code2 }" section and had the same solutions!
00:24:40 -!- Decim has joined.
00:25:12 -!- mitchs has joined.
00:27:13 -!- mitchs_ has quit (Ping timeout: 245 seconds).
00:34:22 <elliott> oerjan: ghc adding * :: * seems weird
00:34:30 <elliott> but I guess it's not exactly consistent in the first place
00:35:04 <Decim> What does :: do again cause I just use it to seperate numerical values
00:35:43 <oerjan> elliott: even more not exactly consistent hth
00:36:09 <Decim> Yeah so pretty much whatever im doing
00:36:15 <elliott> and simultaneously type ascription...
00:36:39 <Decim> Anyways Algorithms are hard to make
00:38:18 <Decim> That tarball thing whoever told me to make that idk it seems pretty hard to make
00:45:47 -!- boily has joined.
00:48:54 <Decim> http://youtu.be/dQw4w9WgXcQ
00:54:18 * boily mapoles Decim with great force
00:56:57 <boily> you outrageous villain! horrible miscreant!
00:57:10 <oerjan> yay i escaped due to boily's heroic sacrifice
00:59:44 * oerjan tosses Decim lightly aside
01:00:00 <Decim> Did I get you too?
01:00:24 <Decim> ill get you one day
01:00:40 -!- variable has changed nick to trout.
01:03:35 <boily> hellørjan. understand that the mapole application was well deserved hth
01:03:43 <boily> Decim: what can't you?
01:04:12 <lambdabot> CYUL 240000Z 25016G24KT 15SM -SHRA SCT025 OVC040 04/M00 A2964 RMK SC3SC5 SLP037
01:04:14 <Decim> A I for compiling tarballs
01:04:35 <boily> oerjan: can you believe it was snowing this morning?
01:04:51 <boily> Decim: you want artificial intelligence to compile tarballs???
01:05:41 <Decim> Well actually no I'm not or else I wouldn't be making artificial intelligence to compile a tarball that I could easily do in like 2 minutes
01:05:56 <Decim> Its not that intelligent atm
01:06:10 <Decim> Its more of an Artificial Dumb
01:06:12 -!- trout has quit (Ping timeout: 276 seconds).
01:11:38 <Decim> A-S-S artificial stupid server
01:11:49 <oerjan> boily: well it was snowing here a few hours ago
01:12:31 * boily feels reassured there are Other Cold Places
01:14:04 <Decim> Can someone check the weather for Pallasgreen, Limerick
01:14:30 <Decim> I could just call my gran but she's probably asleep
01:16:32 <boily> Limerick, as in that Island over there on the Far Side of the Great Puddle?
01:17:11 <lambdabot> EINN 240100Z 13007KT 9999 SCT011 BKN035 08/06 Q1012 NOSIG
01:19:31 <boily> Weather Underground uses Tiobraid Arann as a reference. their source METAR is listed as AAXX sadly.
01:21:04 <Decim> I laughed a bit to hard there
01:21:33 <Decim> Great job boily you made me laugh again
01:36:58 -!- boily has quit (Quit: RESUMED CHICKEN).
01:47:08 -!- zzo38 has joined.
01:48:36 <Decim> Give me something in brainfuck
01:48:43 <Decim> That's super complicated
01:53:29 <Decim> > ++++++++++++++++[>++>+++>++++>+++++>++++++>+++++++<<<<<<-]++++++++++++++++>>>++++++++.>>+.>+++.<+++++++.------.-.>-----.<++++++
01:53:30 <lambdabot> <hint>:1:1: parse error on input ‘++++++++++++++++’
01:53:38 <Decim> Those fucking liars
01:57:40 <zzo38> How much energy do you need to move everything in the universe?
01:57:46 <oerjan> Decim: you could, like, try to remember how to actually run brainfuck in this channel. (hint: there's at least four different bots that can do it.)
01:58:14 <Decim> I'm not the one who put that down
01:58:25 <Decim> My friend gave it to me
01:58:46 <oerjan> @bf ++++++++++++++++[>++>+++>++++>+++++>++++++>+++++++<<<<<<-]++++++++++++++++>>>+++
01:58:47 -!- Neber has joined.
01:58:49 <oerjan> +++++.>>+.>+++.<+++++++.------.-.>-----.<++++++
01:59:17 -!- Neber has left.
01:59:23 <oerjan> @bf ++++++++++++++++[>++>+++>++++>+++++>++++++>+++++++<<<<<<-]++++++++++++++++>>>++++++++.>>+.>+++.<+++++++.------.-.>-----.<++++++
02:00:04 <Decim> I'm just translating stuff for people and I need lambda's help
02:00:17 <Decim> Thank you misses lambda bot
02:01:26 <Decim> http://hastebin.com/raw/fexotomulu
02:03:21 <Decim> Oh god I think I broke my ring finger
02:06:49 <Decim> Have fun with that link oerjan >:|
02:08:42 <oerjan> NOT VISITING AAAAAAAAAAAAA
02:09:40 <Decim> http://hastebin.com/raw/ejipahozup its brainfuck tho
02:10:15 <Decim> Wait if lambda bot is a Mrs who's the Mr
02:10:59 <lambdabot> I don't want to see this country to go that way. You know what happened to the Greeks. Homosexuality destroyed them. Sure, Aristotle was a homo, we all know that, so was Socrates.
02:11:31 <Decim> Makes me rlly salty
02:12:24 <Decim> Homosexuality didn't destroy them they just made all their fucking creations out of poisonous metals and minerals
02:12:44 <Decim> Oh noes plutonium-76 in my drinking water
02:13:03 <oerjan> i am not sure which statement is more ridiculous
02:13:21 <Decim> Or was the the Romans and all their fucking aquaducts
02:13:36 <Decim> Yeah I think it was the Romans
02:13:52 <Decim> Go about your buisness Nixon
02:14:13 <pikhq> Perhaps a bit worse is that they used lead(II) acetate as an artificial sweetener.
02:14:21 * Decim cough "water gate scandal" cough cough
02:14:36 <Decim> Mmm that sugar tho
02:14:42 <Decim> Tastes reallll good
02:15:11 <oerjan> i don't think the romans had sugar
02:15:35 <Decim> I don't think Jesus wasn't made of bread
02:16:04 <pikhq> oerjan: Yep, they had honey but no sugar.
02:16:59 <paul2520> Decim: nice bf script earlier. well played
02:18:10 <Decim> I literally only learned bf for pun reasons only
02:20:39 <Decim> I have no use for it anywhere else
02:21:05 <Decim> None of my friends no what I'm talking about so I usually never bring it up in class
02:21:22 <Decim> Unless my IT teacher asks me then I can mess with him
02:25:31 -!- Decim has quit (Remote host closed the connection).
02:26:53 -!- Phantom_Hoover has quit (Ping timeout: 252 seconds).
02:58:52 -!- bb010g has quit (Quit: Connection closed for inactivity).
03:07:24 -!- PinealGlandOptic has quit (Ping timeout: 244 seconds).
03:08:24 -!- PinealGlandOptic has joined.
03:09:34 -!- oerjan has quit (Quit: Ntigh).
03:14:46 <zzo38> How much energy do you need to move everything in the universe?
03:38:54 <pikhq> Depends. Define "move".
03:40:05 <zzo38> I mean like the force moving one object, but now I mean all objects, in the equal direction/velocity/distance as each other.
03:47:08 <pikhq> The problem is it's still poorly defined. There are not absolute coordinates in the universe.
03:47:54 <pikhq> Unfortunately the question is itself poorly defined.
03:48:07 <pikhq> Which means it can't meaningfully be answered.
03:48:25 <pikhq> "How much energy do you need to flimble the flange?" is about as answerable.
03:49:09 <pikhq> I don't think that energy is a unitless quantity.
03:49:30 <zzo38> Well, I assumed Planck units for some reason
03:49:40 <copumpkin> hey, if your question is nonsense my answer can be nonsense
03:50:10 <zzo38> Does it take more energy to move forward or to move everything else in the entire universe backward by the same amount, or does it come out the same, and does it matter what kind of geometry and infinity we have in our universe at all?
03:50:11 <pikhq> zzo38: Planck energy is still a unit. :)
03:50:43 <pikhq> copumpkin: Iya, eigo no. "Hi~"-rashii no on da ga
03:50:53 <zzo38> pikhq: Yes, I know, but I assumed that copumpkin meant 7.52 Planck units somehow
03:51:24 <zzo38> Who says you didn't do what?
03:58:58 <zzo38> What is total amount of momentum of everything in the universe moving together with a uniform velocity?
04:03:12 <zzo38> If there are a few objects that don't move, relative to any one of those
04:07:32 <pikhq> So, everything moving at the same time within the reference frame of one single object.
04:08:37 <pikhq> I... believe that is actually exactly the same as situation with a single object moving relative to the rest of the objects.
04:09:58 <zzo38> It does seem to me (although it may be a finite small group of objects), yes, it is, but, you have to show a calculation of it
04:12:19 <zzo38> Without a calculation how do you know if it is true?
04:12:39 <zzo38> Without a calculation, how do you know if anything is true or false?
04:12:47 <pikhq> Unfortunately I do not know how to meaningfully express this in particular mathematically.
04:13:14 <pikhq> Hence I am answering the result of my intuition, not giving a particularly confident answer.
04:14:44 <zzo38> It does seems to me that it must be the same, but, I cannot prove it either. But if it is then all of the momentum of everything else relative to you must add up the same thing isn't it? But if the universe is finite then I don't expect that it will add up!
04:21:24 <zzo38> But I'm not sure; do you notice anything about this, wrong or right or seems like wrong or good or bad or whatever?
04:24:06 -!- f|`-`|f has quit (Ping timeout: 240 seconds).
04:27:42 <oren> The concept of momentum is only known to me to be valid in the context of relatively me-sized obejcts. The entire universe is outside the context where I can confirm the accuracy or utility of theories invlving "momentum".
04:29:18 -!- CADD has quit (Remote host closed the connection).
04:30:39 -!- f|`-`|f has joined.
04:37:05 <zzo38> I read in one book, they said if the universe is infinite then there is infinite number of stars and the light of stars will be an infinite amount of energy and it won't be dark at the night time. But, can't a divergent series add up to a finite negative number? Is that where all of the "dark matter" is coming from?
04:45:12 <zzo38> Such as 2^0 + 2^2 + 2^4 + 2^6 + 2^8 + 2^10 + 2^12 + ... = -1/3
04:45:57 <pikhq> Even if the universe is infinite the size of our light cone is definitely finite, so that's... not very relevant.
04:49:01 <zzo38> Where does it stop? At the big bang? Or is it curved and doesn't need to stop?
04:51:05 <pikhq> It stops at about the point of recombination, where the universe first became transparent. Approx. 378,000 years into the universe.
04:51:51 <pikhq> The light from this is a major component of the cosmic background radiation.
04:52:17 <Sgeo> http://en.wikipedia.org/wiki/List_of_duplicate_file_finders
04:52:26 <zzo38> Ah, so those are some reason that their reasoning of the universe cannot be infinite are also flawed reasoning. This is I read it in some philosophy book
04:52:28 <Sgeo> I am surprised that there exists an entire Wikipedia list for this.
04:54:04 <zzo38> pikhq: But why can such things happen anyways?
04:54:56 <oren> Sgeo: the definition of a "duplicate file" varies by task
04:57:16 <oren> For finding duplicate images, for instance, I wrote a program that reads the file and renames it by a rearranged version of its average color as RGBRGB
04:58:17 <zzo38> You can have two different compressed files with the same contents, or two different RDF files representing isomorphic RDF graphs, or two text files one with LF and one with CRLF, or one truecolor and one indexed color picture that are the same picture, or two same files which you need duplicates of since one might be modified or on a different partition or a backup or whatever
05:00:00 <oren> so probably each tool was invented by a programmer who had a task requiring a particualr definition of "same"
05:02:49 <oren> Hmm, the cave spider went through my fortress and off the edge of the map outside without killing anyone
05:04:38 <Jafet> https://en.wikipedia.org/wiki/List_of_lists_of_lists
05:09:19 -!- idris-bot has quit (Ping timeout: 265 seconds).
05:10:26 <oren> Why don't we create an article named List of lists of lists that don't include themselves? 201.66.171.62 (talk) 15:04, 10 April 2011 (UTC)
05:10:53 -!- Melvar has quit (Ping timeout: 244 seconds).
05:14:27 <oren> Hold on. Although a list of lists that don't include themselves is ill defined, a list of such lists is perfectly well defined, viz. the enpty list
05:14:36 <zzo38> Should I add command in AmigaMML to define just intonation and command to define binary compatibility with existing .MOD/.XM files (meaning the same track number for multi songs/multi parts)?
05:56:41 -!- variable has joined.
06:10:57 -!- bb010g has joined.
06:18:54 <zzo38> I have a list of "You know you've been in Japan too long when..."
06:21:20 <izabera> i have a list of "you know you've been playing with tautologies too long when..." but there's only one element: "...when you know you've been playing with tautologies too long."
06:21:48 -!- variable has changed nick to trout.
06:23:32 <zzo38> I have never been in Japan but have done some of the things listed and still do, such as, pull out your ruler to underline words, one kind of rice tastes better than another kind, recognize BGM as a meaningful genre of music, go to a book shop with the full intention to read all the interesting magazines and put them back on the shelf (except 2600 which I purchase if it is a new one)
06:25:31 <zzo38> I do sometimes buy books too, but often I don't buy any; they don't care as long as I do not enter the washroom or Starbucks with unpaid merchandise
06:26:04 <zzo38> And to don't stop anyone from buying it if they do wish to buy it
06:35:44 <zzo38> I have a file in my computer titled "Book of Good Advice" which contains such things as: A knowledge of Sanskrit is of little use to a man trapped in a sewer. Carpe diem, carpe hunc librum. Don't catch fire. Dress a little better than you should, but not as well as you do. Never sit on your baby. Respect all life especially if it's ugly and slithers. The customer is usually right-handed. The best teddy bears are the live kind.
06:40:39 <zzo38> DIET is a bad word. Always save a suicide pill for later instead of eating it now. Don't drink water: it is too good for you. Never dream about anyone laughing. When you smell an odorless gas, it is probably carbon monoxide. When opportunity knocks, check to see who it is. It is difficult to repair a watch while falling from an airplane. If you only do what is right, you will miss out on what is left.
07:13:12 -!- Sgeo has quit (Remote host closed the connection).
07:13:42 -!- Sgeo has joined.
07:42:21 <HackEgo> [wiki] [[ArnoldC]] M http://esolangs.org/w/index.php?diff=42736&oldid=39379 * Vriskanon * (+10) Added stub to page. Only text is "ArnoldC is an esoteric programming language created with Scala by Lauri Hartikka. The source is available [https://github.com/lhartikk/ArnoldC here], along with tutorials and example programs."
07:48:52 -!- CADD has joined.
07:55:24 -!- dianne has quit (Ping timeout: 250 seconds).
07:55:54 -!- AndoDaan has joined.
07:56:57 <AndoDaan> I finally know what monads are.
07:57:09 -!- dianne has joined.
08:08:56 <zzo38> Pizza? Why are they pizza? I don't think so.
08:09:06 <AndoDaan> But I realize now that they are not functions.
08:10:22 <AndoDaan> Does that mean many things are monads?
08:11:15 <lifthrasiir> no, but I can assert that if monads are not delicious they are useless at best
08:12:28 <AndoDaan> Now you just have to define what 'delicious' is and I think we can put this problem to bed.
08:12:31 <zzo38> The way to explain working of monads is if you had used other programming languages with list comprehensions
08:12:36 -!- trout has quit (Ping timeout: 276 seconds).
08:13:23 * lifthrasiir has exhausted his joke budget, so is no longer functional
08:13:46 -!- zadock has joined.
08:14:02 <zzo38> AndoDaan: I suppose so, well, I know there are a few.
08:14:08 <AndoDaan> Still a good pun at the end there, lifthrasiir
08:15:46 <AndoDaan> Haskell most of all, I guess. For the longest time i was under the impression that monads were only a Haskell thing.
08:16:57 <zzo38> Monads can also be used with some mathematical stuff that isn't done with computer programming, too.
08:18:10 <AndoDaan> But more the logic-branch of mathematics, right?
08:18:28 <zzo38> It is category theory
08:22:15 <AndoDaan> Hmm. Though I think I understand them, I need a better grip on the terminology, and hard practical experience, I think.
08:27:05 <zzo38> In addition to monads there is comonads. Category theory is also involving functors, discrete categories, thin categories, tensor categories, forgetful functors, cartesian closed categories, etc.
08:27:55 -!- Patashu has joined.
08:29:42 <AndoDaan> Above my paygrade those. I mean I just learned that they aren't burritos! Some of those things sound fascinating, though. Forgetful functions? I know about temporal logic...
08:30:37 <AndoDaan> Not like paradoxes and stuff, but just that "things is true now, but not then" type thingie.
08:33:55 <zzo38> Yes I know some things about temporal logic and there are other kinds of logic too, such as linear logic, classical logic, intuitionistic logic, doxastic logic, modal logic, paraconsistent logic, and others.
08:34:56 <AndoDaan> Bloody hell. The ancient Greeks have a lot to answer for.
08:35:56 <zzo38> The logic of the ancient Greeks is the classical logic, which still has a lot of uses, although now there are other kinds too.
08:38:15 <AndoDaan> I know, but if they hadn't opened their mouths we'd... I don't know where I'm going with this.
08:51:12 -!- Adam_T has left.
08:54:45 -!- b_jonas has joined.
09:05:11 <shachaf> oerjan: foiled by not copying and pasting hth
09:15:03 -!- Phantom_Hoover has joined.
09:18:52 -!- bb010g has quit (Quit: Connection closed for inactivity).
09:27:05 -!- PinealGlandOptic has quit (Ping timeout: 250 seconds).
09:39:26 -!- zadock has quit (Quit: Leaving).
10:04:02 -!- augur_ has joined.
10:04:52 -!- augur has quit (Ping timeout: 256 seconds).
10:12:12 -!- augur_ has quit (Ping timeout: 276 seconds).
10:17:05 -!- augur has joined.
10:23:25 -!- Melvar has joined.
10:24:06 -!- boily has joined.
10:54:10 -!- idris-bot has joined.
11:03:14 -!- AnotherTest has joined.
11:24:27 -!- boily has quit (Quit: LAQUERED CHICKEN).
11:25:16 -!- hjulle has joined.
11:48:35 -!- AnotherTest has quit (Ping timeout: 256 seconds).
12:33:54 -!- copumpkin has quit (Quit: My MacBook Pro has gone to sleep. ZZZzzz…).
12:34:58 -!- AnotherTest has joined.
12:51:00 -!- AndoDaan has quit (Read error: Connection reset by peer).
12:56:09 <nortti> instead of moving around the tape using < and >, moving around it with scanl(x) and scanr(x). they look for the next instance of x on the tape, not counting the current cell
12:58:55 <nortti> the more general version scan[rl](x, step) can be used to simulate a 3-counter machine, by having a specific symbol in the beginning of the tape, then identifiers for each of the 3 registers. going to the "top" of the register (where a numer N is stored as N "empty" and then a top marker) would be: scanl(START, 1) scanr(REG, 1) scanr(TOP, 3)
12:59:47 <nortti> to increment, use set(EMPTY) scanr(EMPTY, 1) set(TOP). decrement likewise
13:00:34 <nortti> hmm, actually, I'm not sure if you can check what value is in the register...
13:01:37 <HackEgo> [wiki] [[Special:Log/newusers]] create * 12Me21 * New user account
13:01:54 <nortti> maybe if you had in addition of a conditional execution of if there is an X to left/right to you, as then you could just check toleft?(EMPTY, 3), and if not, then the register has value of 0
13:02:47 <Sgeo> Apr 18 David Wu's program (Sharp) wins the Arimaa challenge"
13:03:05 <nortti> but I have no idea what is if the computational class for scanl, scanr(, toleft?, toright?) without the step argument
13:03:29 <HackEgo> [wiki] [[Befunge]] M http://esolangs.org/w/index.php?diff=42737&oldid=42492 * 12Me21 * (-35) %0 does not ask the user, only /0 does.
13:10:52 <HackEgo> [wiki] [[Talk:Befunge]] http://esolangs.org/w/index.php?diff=42738&oldid=40585 * 12Me21 * (+358) /* What about editor of Befunge programs? */
13:12:04 <HackEgo> [wiki] [[Talk:Befunge]] http://esolangs.org/w/index.php?diff=42739&oldid=42738 * 12Me21 * (+100) /* Befunge-93 really 2d */
13:17:57 <HackEgo> [wiki] [[Talk:Befunge]] http://esolangs.org/w/index.php?diff=42740&oldid=42739 * 12Me21 * (+296) /* Befunge programs? */ new section
13:18:44 <HackEgo> [wiki] [[Talk:Befunge]] M http://esolangs.org/w/index.php?diff=42741&oldid=42740 * 12Me21 * (+3) in
13:23:34 -!- oerjan has joined.
13:24:00 -!- erdic has quit (Ping timeout: 246 seconds).
13:29:17 -!- Patashu has quit (Ping timeout: 272 seconds).
13:39:23 -!- erdic has joined.
13:40:22 <nortti> https://bitbucket.org/purelang/pure-lang/wiki/Rewriting
13:41:45 <HackEgo> [wiki] [[Befunge]] M http://esolangs.org/w/index.php?diff=42742&oldid=42737 * 12Me21 * (-3) 0 is popped when stack is empty, unless you have a crappy interpreter
13:57:41 <b_jonas> this is brilliant. in the windows api, if you write to a pipe and there's no reader, the write fails with the error code ERROR_NO_DATA; whereas if you read from a pipe and there's no writer, it doesn't give you eof, but instead the read fails with the error ERROR_BROKEN_PIPE.
14:00:51 -!- `^_^v has joined.
14:07:45 -!- hamrove has joined.
14:15:04 -!- AnotherTest has quit (Read error: No route to host).
14:15:37 -!- AnotherTest has joined.
14:27:02 <b_jonas> fungot: don't you just love self-documenting enum names?
14:27:02 <fungot> b_jonas: yes, that would be cool?
14:28:19 <oerjan> fungot: how gandhish of you.
14:28:19 <fungot> oerjan: i'm surprised that latter hasn't gotten more attention. :p so where's that befunge-interpreter of yours?" " well, that's the official term. your question is, does it
14:33:19 -!- SopaXT has joined.
14:38:20 -!- SopaXT has quit (Remote host closed the connection).
14:51:42 -!- bb010g has joined.
14:56:01 -!- shikhin has changed nick to wolf.
14:56:06 -!- wolf has changed nick to shikhin.
15:11:00 -!- mitchs has quit (Ping timeout: 264 seconds).
15:46:20 -!- Sprocklem has quit (Ping timeout: 255 seconds).
16:04:47 * oerjan wonders if lucrezia actually expects klaus to accept her suggestion
16:05:04 <oerjan> or if it's negative psychology
16:05:35 <int-e> reverse psychology
16:07:19 <oerjan> also, whatever "went wrong"
16:10:04 -!- AnotherTest has quit (Ping timeout: 252 seconds).
16:13:51 <int-e> I have not looked at the comic yet.
16:15:10 <oerjan> i'm sorry, i'm out of airships to push you from hth
16:15:13 <int-e> (A long long time ago, maybe when he was dropped of an airship under Castle Wulfenbach?)
16:15:30 <oerjan> i'm pretty sure he's said it more than once.
16:15:42 <oerjan> but that was the first one, i guess.
16:16:07 <int-e> Maybe, but that's an occasion I'm fairly sure about. Mostly my memory of the comic is quite hazy.
16:16:22 <int-e> Anyway... back to unification...
16:18:34 -!- TieSoul_ has joined.
16:18:53 -!- TieSoul has quit (Read error: Connection reset by peer).
16:31:58 -!- b_jonas has quit (Quit: http://www.kiwiirc.com/ - A hand crafted IRC client).
16:31:58 -!- oren has quit (Read error: Connection reset by peer).
16:33:22 -!- ais523 has joined.
16:35:25 -!- oerjan has quit (Quit: leaving).
16:36:20 -!- AnotherTest has joined.
16:37:11 -!- orin has joined.
16:43:27 -!- ais523 has quit (Ping timeout: 240 seconds).
16:48:53 -!- bb010g has quit (Quit: Connection closed for inactivity).
17:05:22 -!- variable has joined.
17:11:34 -!- bb010g has joined.
17:36:03 -!- MoALTz has quit (Read error: Connection reset by peer).
17:36:50 -!- MoALTz has joined.
18:11:00 -!- rdococ has joined.
18:17:35 <rdococ> imagine, a programming language in which instead of assignment 'set x to 3' you can call things by other names 'call 3 x'
18:18:19 <myname> wouldn't that imply immutability?
18:18:57 <rdococ> you could do 'call 3 x' and then 'call 4 x', then x would refer to 4, and not 3 anymore
18:19:32 <rdococ> or x could refer to both
18:20:15 <rdococ> maybe the interpreter could determine based on context
18:20:23 <myname> how would you phrase x = x * 4?
18:21:16 <rdococ> should that cause infinite recursion?
18:21:32 <rdococ> maybe it would and you'd have to do 'call y x' 'call y*4 x'
18:22:19 <rdococ> or 'call x y' 'call y y' 'call x*4 y'
18:23:30 <rdococ> so y would recursively refer to itself, but since whatever y refers to wouldn't change with each iteration, it could be ignored safely
18:26:33 <elliott> is the innovation here "language where you write assignment backwards"
18:27:35 <rdococ> reminds me of that idea of an ironic programming language
18:28:23 <rdococ> or, we could have a logic system with a three-argument operator
18:28:43 <rdococ> 'if x then y else z' would return y if x is true, but return z otherwise
18:30:48 <rdococ> not operator: if x then 0 else 1. and operator: if x then y else 0
18:31:37 <myname> well, most languages call that ?:
18:31:44 <rdococ> unlike other functionally complete sets of operators, its only element can describe the behaviour of NOT, AND, and OR operators with ease.
18:32:43 <rdococ> NAND definition of AND is much more complicated than using IFTHENELSE
18:33:31 <rdococ> true, most languages call this x ? y : z. However, imagine a language with only that.
18:35:53 <rdococ> imagine a BF derivative with it
18:36:07 <rdococ> ...hang on, that doesn't many any sense
18:44:21 -!- AnotherTest has quit (Ping timeout: 250 seconds).
18:44:29 <FreeFull> rdococ: Those look just like "let" to me
18:44:49 <rdococ> you mean the CALL syntax?
18:45:21 <FreeFull> call x*4 x would be equivalent to let x = x*4; in Rust
18:45:38 <FreeFull> And the left side of = can be a pattern too, as long as it's irrefutable
18:45:42 -!- AnotherTest has joined.
18:46:01 <FreeFull> Any references to x before that line will still refer to the old x
18:49:13 <rdococ> in my language, Harp, current program state is described by the position of the current instruction. imagine if the program state could be described by other runtime variables
18:51:04 -!- TieSoul_ has changed nick to TieSoul.
18:51:52 <FreeFull> I think there is a language that has no mutability, just this kind of assignment
18:55:06 -!- variable has changed nick to trout.
18:55:25 <rdococ> imagine a language in which everything is nil.
18:59:14 <zzo38> I think such thing is already in esolang wiki anyways (if I remember it correctly)
19:02:16 <rdococ> not instructions, but all objects
19:02:58 <rdococ> maybe you could say, 'x = 3' - and then 'y = 4'... they're all nil but different kinds of nil, so x isn't equal to y nor is it to 4, but it is to 3
19:03:28 <rdococ> nil =/= nil, unless you use assignment, say x = nil, then x == nil
19:03:42 <rdococ> does this make sense to you? it doesn't to me
19:05:02 <zzo38> It doesn't seem sensible to me either
19:05:39 <rdococ> maybe let's say we have literals and references. references refer to literals, like 'x = 3' would make x a reference that refers to 3
19:07:10 -!- GeekDude has quit (Ping timeout: 276 seconds).
19:10:21 -!- GeekDude has joined.
19:25:15 -!- Sprocklem has joined.
19:51:08 -!- Insipid has joined.
19:51:22 -!- Insipid has left.
19:55:36 <tswett> rdococ: so what would "everything is nil" mean in that context?
20:15:29 -!- PinealGlandOptic has joined.
20:18:25 <HackEgo> [wiki] [[Special:Log/newusers]] create * MrSherlockHolmes * New user account
20:20:46 <HackEgo> [wiki] [[User:MrSherlockHolmes]] N http://esolangs.org/w/index.php?oldid=42743 * MrSherlockHolmes * (+89) Created page with "Hello! I'm [https://scratch.mit.edu/users/MrSherlockHolmes/ MrSherlockHolmes] on Scratch."
20:48:51 -!- AnotherTest has quit (Remote host closed the connection).
20:55:47 <rdococ> I'm pretty sure I know MrSherlockHolmes from Scratch.
20:56:18 <HackEgo> [wiki] [[User talk:MrSherlockHolmes]] N http://esolangs.org/w/index.php?oldid=42744 * Rdococ * (+354) saying hi
20:56:58 -!- spatterworthy has joined.
21:20:37 <HackEgo> [wiki] [[User talk:Rdococ]] N http://esolangs.org/w/index.php?oldid=42745 * Rdococ * (+241) /* Hi guys! */ new section
21:21:33 -!- GeekDude has quit (Quit: {{{}}{{{}}{{}}}{{}}} (www.adiirc.com)).
21:23:59 <quintopia> zzo38: are you any good at TeX macros
21:25:12 <zzo38> quintopia: Yes, I have done a lot of that
21:25:16 -!- Sprocklem has quit (Ping timeout: 248 seconds).
21:25:40 <zzo38> Why are you asking about?
21:26:43 <quintopia> zzo38: would you know how to make a document print something like the bottom thing here: http://imgur.com/WtfBYz1
21:28:05 <zzo38> To do that you need to add a font containing such thing.
21:28:12 <zzo38> It has nothing to do with macros.
21:28:34 -!- fractal has quit (Ping timeout: 265 seconds).
21:30:30 <quintopia> zzo38: aha. would macros be usable to change the number under the symbol assuming there was a font with the symbol in it?
21:36:30 <FireFly> quintopia: interesting syntax, I like it
21:37:56 <paul2520> quintopia: that's neat. what's the source on that?
21:43:31 <HackEgo> [wiki] [[Clip]] http://esolangs.org/w/index.php?diff=42746&oldid=42176 * 168.99.197.18 * (+62) /* Constants */
21:44:44 <quintopia> FireFly, paul2520: he is planning to publish something about it soon at http://solidangl.es I'll let you know when it comes out
21:49:19 <zzo38> quintopia: Yes, macros can do that
21:50:00 <zzo38> You can look at the source codes of Computer Modern to learn how to make the font and then you can make upside-down
21:50:49 <quintopia> zzo38: where do i find the sources of Computer Modern?
21:52:00 <zzo38> They should be included with the TeX distribution
21:52:36 <quintopia> is this something you know how to do already? or you've never tried?
21:52:53 <zzo38> I have used METAFONT before, although not this specifically.
21:53:49 <zzo38> (The sources of Computer Modern, together with diagrams, can also be found in Computers & Typesetting volume E; although they should be on your computer too if you have TeX)
21:55:47 -!- `^_^v has quit (Ping timeout: 240 seconds).
22:05:12 <quintopia> zzo38: do you have any idea which mf file the sqrrt symbol might be in
22:17:25 * Sgeo wonders if there's anything good about VMware Player compared to VirtualBox
22:25:24 -!- oerjan has joined.
22:34:19 -!- Patashu has joined.
22:46:46 -!- fractal has joined.
22:48:31 -!- iamevn_ has quit (Ping timeout: 272 seconds).
22:48:54 -!- iamevn has joined.
22:51:11 <orin> Did you know that, unlike other repeat jobs in DF, a repeated pottery job will never run out of materials?
22:53:38 <orin> if you set "Collect Clay" "Make Clay crafts" on repeat, the dwarf will create an unlimited number of figurines, etc.
22:55:07 <orin> Yes, unless you have magma.
22:55:43 <orin> Although even if you don't, lignite veins give a crapload of coke
22:55:48 <Phantom_Hoover> and where there is magma there is unlikely to be clay, and vice versa
22:56:29 <Phantom_Hoover> back when #esoteric DF was a thing i even modded coal into metamorphic layers because i was sick of having to use charcoal on every. single. map.
22:57:33 <orin> I usually embark at either a volcano or a tropical forest (that appears to be where lignite happens)
22:58:14 <orin> which makes sense in a world with no continent drift
22:59:45 <orin> In a normal map, volcanoes appear to mainly occur at the poles and in the middle of oceans
23:01:36 <orin> I have never found magma and coal in the same place though
23:02:47 <coppro> you know what I miss? lego rock raiders
23:18:29 <quintopia> http://www.reddit.com/r/funny/comments/1thhyk/the_hobbit_the_tessellation_of_smaug/
23:18:35 <oerjan> quintopia: irregular webcomic
23:20:32 <oerjan> quintopia: ok i don't get that pun...
23:27:15 <orin> Hmm... what if I simply dropped a clay floor 70 levels down to the magma level?
23:27:50 <orin> I only need a few tiles to collect clay from after all
23:34:28 -!- trout has changed nick to function.
00:06:53 <paul2520> quintopia: please do let me know about that publication. looks neat
00:08:53 -!- bb010g has quit (Quit: Connection closed for inactivity).
00:20:48 <quintopia> paul2520: it might be posted as soon as tonight
00:28:40 <zzo38> Why do you hate Internet Quiz Engine? It is better than OkCupid and HelloQuizzy and so on. However, currently I didn't make the program that allow to make the print-out of the quiz, yet
00:28:54 -!- adu has joined.
00:30:55 <zzo38> I don't know; do you hate it?
00:31:52 <zzo38> Then you must learn. There is even one quiz of esolang that someone else made on Internet Quiz Engine; I did not make this quiz file by myself
00:36:47 -!- copumpkin has joined.
00:38:57 <function> what is Internet Quiz Engine ?
00:39:52 <zzo38> It is a online quiz software written in C
00:40:55 <zzo38> There are no buffer overflows and so on, because there are no buffers, no recursion, etc, therefore it is safe from such security breaches
00:47:55 -!- CADD has quit (Quit: Lost terminal).
00:54:22 -!- dianne has quit (Quit: byeannes).
00:56:46 -!- a2 has joined.
01:02:28 <zzo38> Do you hate "Make every program a filter"? Why?
01:08:00 -!- copumpkin has quit.
01:10:34 <zzo38> And why is Pikachu too quiet on Visual Boy Advance?
01:11:07 -!- cefkamcau has joined.
01:11:15 <pikhq> Are you sure it's VBA at fault?
01:11:43 -!- copumpkin has joined.
01:12:43 <zzo38> It seems to be; it isn't quiet on other emulators and isn't quiet on the real GameBoy
01:12:59 <pikhq> That seems like an odd emulator issue.
01:13:15 <pikhq> Though it might have to do with VBA not intending to be an especially good Gameboy emulator.
01:29:28 -!- copumpkin has quit (Quit: My MacBook Pro has gone to sleep. ZZZzzz…).
01:43:50 -!- copumpkin has joined.
01:44:31 -!- contrapumpkin has joined.
01:44:52 -!- a2 has changed nick to CADD.
01:45:22 -!- CADD has changed nick to Guest15869.
01:48:33 -!- copumpkin has quit (Ping timeout: 256 seconds).
01:51:36 -!- function has quit (Quit: 1 found in /dev/zero).
01:56:02 -!- variable has joined.
01:56:09 <quintopia> paul2520: FireFly http://www.solidangl.es/2015/04/a-radical-new-look-for-logarithms.html
01:59:24 <zzo38> How to propose new URI scheme? Such as: temporary:// urn:null urn:bible: urn:pokemon:
02:03:42 -!- TodPunk has quit (Ping timeout: 252 seconds).
02:12:39 <HackEgo> [wiki] [[Special:Log/newusers]] create * Phase * New user account
02:14:58 -!- Sprocklem has joined.
02:15:18 -!- Phantom_Hoover has quit (Quit: Leaving).
02:20:17 -!- variable has quit (Ping timeout: 256 seconds).
02:26:02 -!- Decim has joined.
02:30:08 <zzo38> What is your opinion of these kind of new URI scheme?
02:31:08 -!- contrapumpkin has quit (Ping timeout: 265 seconds).
02:31:33 -!- copumpkin has joined.
02:45:14 <Sgeo> Grr my !!expensive!! headphone's earpads fell off
02:45:23 <Sgeo> (No, the expensiveness is not on fire)
02:47:55 <Sgeo> Reattached, but that was annoying to do
02:49:32 <Sgeo> Also I seem to be going variably deaf in my left ear
02:50:44 -!- bb010g has joined.
03:11:04 -!- eshiffob has joined.
03:11:57 <Decim> The hairs in your outer eardrum are probably dieing/breaking
03:14:28 -!- cefkamcau has quit (Ping timeout: 240 seconds).
03:18:09 -!- contrapumpkin has joined.
03:21:20 -!- copumpkin has quit (Ping timeout: 250 seconds).
03:27:55 -!- contrapumpkin has quit.
03:27:56 -!- clog has quit (Ping timeout: 245 seconds).
03:28:36 -!- copumpkin has joined.
03:30:06 <Sgeo> I think wax is more likely. Although I do occasionally have brief tinnitus in either ear, which scares me
03:32:17 <Sgeo> Brief or permanent?
03:32:48 <FreeFull> Permanent, although usually I won't be noticing it
03:37:06 -!- Decim has quit (Ping timeout: 245 seconds).
03:42:29 -!- adu has quit (Quit: adu).
04:00:06 <orin> Apparently elves don't mind me trading them a masterwork figurine of a cyclops striking down a fomous elf.
04:00:22 <orin> So long as the figurine isn't made of wood
04:01:21 <zzo38> It should also depend who they are who is trading to as well as who is the figurine of
04:04:59 <orin> OH GOD NO "The item is a well-designed image of Rakust Pagelungs and leeches in earthenware by Dumat Ilidathel. Rakust Pagelungs is surrounded by the leeches."
04:05:53 -!- copumpkin has quit (Quit: My MacBook Pro has gone to sleep. ZZZzzz…).
04:06:31 <oerjan> i take it dumat isn't particularly fond of rakust.
04:06:33 <zzo38> It says it is well-designed though, so, probably is not bad, but check to see if it is poison in that case it is no good, or if you don't like to collect art also it is no good
04:06:59 <zzo38> Or sell it if the item cannot be used yourself
04:09:23 <orin> oerjan: Rakust is the expedition leader. lol
04:20:09 -!- Sprocklem has quit (Ping timeout: 245 seconds).
04:27:18 -!- oerjan has quit (Quit: Nite).
04:51:49 -!- hjulle has quit (Ping timeout: 245 seconds).
22:43:34 -!- esowiki has joined.
22:43:35 -!- glogbot has joined.
22:43:38 -!- esowiki has joined.
22:43:39 -!- esowiki has joined.
22:43:39 -!- EgoBot has joined.
22:44:05 <Gregor> prgmr moved my server and apparently they didn't start properly >: (
22:44:19 * oerjan never knows when is a good time to ping Gregor
22:44:50 <Gregor> If you /msg me instead of the channel then I'll see it later more easily *shrugs*
23:01:46 * int-e wonders what kind of technical measures Freenode employs to make privmsg spam unattractive.
23:01:55 <HackEgo> [wiki] [[There Once was a Fish Named Fred]] http://esolangs.org/w/index.php?diff=42763&oldid=34094 * Charlie * (+558)
23:02:41 <Gregor> int-e: Given my past experiences, my guess is "none"
23:02:57 <int-e> (I suspect there must be something, since the only kind of that spam that I'v ever seen were private messages in reaction to channel messages.)
23:03:36 <fizzie> Is it a technical reason when they K-line people after you complain about spam?
23:04:09 <int-e> fizzie: not if it involves actual people pulling the trigger
23:04:45 <int-e> As usual, there's no clear boundary there.
23:07:18 <int-e> Maybe it's really just diligent staff combined with flood protection and obscurity of IRC.
23:10:10 <int-e> But I'm hoping for honeypots (imagine a few idlers on ##freenode such that if any two of them get privmsged by the same user within 10 minutes, that user gets k-lined)
23:11:00 <tswett> Is there some description somewhere of exactly how gairaigo are produced from English words?
23:12:13 -!- Sprocklem has joined.
23:12:27 -!- sebbu2 has joined.
23:12:53 <int-e> Anyway, none that I know of.
23:13:04 -!- sebbu2 has quit (Changing host).
23:13:04 -!- sebbu2 has joined.
23:13:12 -!- sebbu has quit (Ping timeout: 240 seconds).
23:16:34 <int-e> Hmm, n. I guess that's better than mu.
23:17:00 <int-e> (which would be an extra syllable)
23:18:58 -!- hamrove has quit (Quit: hamrove).
23:22:14 <tswett> Not to be confused with パソコンム
23:24:29 <orin_> It's actually makudonarudo
23:26:12 <orin_> There aren't many rules, but ending consonants are made with *u except for t which instead uses to
23:28:11 <orin_> ending R is typically done by elongating the vowel the way people from Britain do. E.g stars -> sutaazu
23:31:57 <orin_> Also, words with 'wh' begin with 'ho' e.g. whiteboard -> howaitoboodo
23:32:30 <boily> as much as I try to really grok ソ and ン, I always mix them together.
23:32:37 <orin_> (even though in mopdern english wh sounds exactlye the same as w)
23:34:39 <tswett> I'm mostly wondering about the vowels.
23:35:08 <orin_> in ソ the small stroke ends to the left of where the long stroke begins. in ン the small stroke is above the long stroke and ends above where the long stroke beigns
23:36:19 <boily> yes. but at a glance they're pretty much all the same, at least when using a display font.
23:36:35 <boily> handwritten it's a completely different matter, as stroke order isn't the same.
23:37:06 <tswett> Does /æ/ become "a" or "e"? Do /ɑː/ and /ɒ/ become "a" or "aa"? Does /iː/ always become "ii"? Are /ɜr/ and /ər/ always "aa"?
23:37:20 <tswett> And so on and so forth forever.
23:38:21 <orin_> I think it probably depends on whether the individual words was imported from Britain or America (or in many cases Germany)
23:38:45 <boily> /æ/ becomes a. /ɑː/ and /ɒ/ usually become o (IIRC). /iː/ iifies, and the latter aa.
23:39:07 <boily> (aa, from the verb "to aa": to become aa.)
23:40:00 <tswett> So "father" and "wasp" become "fozaa" and "wosupu"?
23:41:15 <orin_> hmm, apparently it is faazaa
23:41:23 <boily> faazaa makes sense.
23:41:30 <orin_> different accent, see!!?!
23:41:56 <tswett> Man, English has too many vowels.
23:41:58 * boily would like to point out that my English accent is unreliable at best
23:42:03 <tswett> It has so many vowels that nobody knows how many vowels it has.
23:42:28 <orin_> I have done a count for my accent of 14
23:42:31 <tswett> Lemme see exactly how many vowels my particular accent has.
23:43:48 <Phantom_Hoover> vowels are in too continuous to be able to make discrete counts, really
23:44:14 <tswett> For me, they're definitely discrete.
23:44:58 <orin_> hmm, my previous count disagrees with my current count
23:45:08 -!- boily has set topic: Vowel Continuum | https://dl.dropboxusercontent.com/u/2023808/wisdom.pdf http://codu.org/logs/_esoteric/ http://tunes.org/~nef/logs/esoteric/ | http://esolangs.org/.
23:45:40 <Phantom_Hoover> <tswett> So "father" and "wasp" become "fozaa" and "wosupu"?
23:46:03 <tswett> /æ/, /ɑ/, /ɔː/, maybe /ə/, /ɪ/, /iː/, /eɪ/, /ɛ/, /ər/, /ʌ/, /ʊ/, /uː/, I'm not counting /juː/, /aɪ/, /ɔɪ/...
23:46:37 <tswett> Phantom_Hoover: they're totally different vowel sounds for a lot of people, but Japanese is inevitably going to round some distinct pairs of English vowels to the same Japanese vowel.
23:47:16 <Phantom_Hoover> i assumed this was some foolhardy phonetic standardisation attempt :/
23:47:47 <tswett> /oʊ/, /aʊ/, /ɑr/, /ɪər/, /ɛər/, /ɔr/, /ʊər/, I'm not counting /jʊər/ either.
23:49:29 <tswett> So I have 21 in total, 15 non-rhotic and 6 rhotic.
23:50:30 <tswett> I'm including /ə/ in that count because even in very careful speech I sometimes pronounce it distinctly from /ʌ/.
23:50:40 <orin_> Ok, I have 16 total
23:52:27 <orin_> cat kate cart pet peat kit kite bird cot coat court cook cow cut coot cute cure
23:52:34 <zzo38> I made up a "Advanced Modular Music"; which is based on a sample ROM (of mono 8-bit or 16-bit samples), a sample header list (the offset, looping, center frequency, and auto-vibrato settings), a memory map of several registers per channel, and a 6502 code to control the register writes.
23:53:26 <boily> nope. can't count how many I distinguish.
23:53:28 <orin_> it's like cut + keet
23:53:42 <tswett> orin_: ooh, you sound like a Canadian raiser.
23:53:55 <tswett> Oh, I do have a split that might be unusual.
23:54:08 <tswett> For me, the words "holy" and "lowly" don't rhyme.
23:54:17 <tswett> My best attempt at representing the distinction in IPA...
23:54:58 <tswett> "holy" is /hɔli/, "lowly" is /louli/.
23:55:09 <tswett> I meant to use [] instead of //.
23:55:28 <tswett> It's a monophthongization of /oʊ/ before /l/.
23:57:36 <orin_> hmm, for me holy would rhyme with loli but now lowly
23:59:03 <tswett> orin_: do "bowl" and "pole" rhyme for you?
23:59:08 <zzo38> The register per channel includes: 16.16 fixed point frequency, sample number, volume control, filter cutoff, filter resonance, filter mode (low-pass, high-pass, or off), and one register per pair of channels to activate FM synthesis and set the feedback amount. Each channel also has command registers to reset the phase and to multiply/divide the frequency quickly.
23:59:36 <tswett> They sound like "holy", I imagine?
00:01:07 <orin_> I think it sounds different becuase the ly in lowly is like another, uh, word-part while holy is all one word
00:03:25 <orin_> ah. here's something I've noticed. some people rhyme poor with lure while others rhyme it with bore
00:03:48 <orin_> I rhyme it with lure
00:06:24 <tswett> If I had to change the way English vowels are written to match my personal accent... let's see.
00:12:24 <tswett> /æ/ a, /ɑ/ á, /ɛ/ e, /eɪ/ é, /ɪ/ i, /iː/ í, /ʌ/ o, /ɔː/ ó, /ʊ/ u, /uː/ ú, /aɪ/ ay, /ɔɪ/ oy, /aʊ/ aw, /oʊ/ ow, /ɑr/ ar, /ɛər/ er, /ɪər/ ir, /ɔr/ or, /ʊər/ ur
00:29:56 -!- polytone_ has quit (Quit: rebooting server).
00:32:59 -!- monotone has joined.
00:43:37 -!- Phantom_Hoover has quit (Read error: Connection reset by peer).
00:44:03 -!- Phantom_Hoover has joined.
01:00:26 -!- hamrove has joined.
01:15:32 -!- G33kDude has joined.
01:16:44 -!- GeekDude has quit (Read error: Connection reset by peer).
01:16:53 -!- G33kDude has changed nick to GeekDude.
01:17:51 -!- izabera has quit (Ping timeout: 256 seconds).
01:20:09 -!- mbrcknl has quit (Ping timeout: 256 seconds).
01:22:06 -!- mbrcknl has joined.
01:22:28 <quintopia> what's the best food only available on great britain
01:24:06 <oerjan> is boily qualified to answer that
01:25:49 -!- izabera has joined.
01:25:53 <oerjan> something highly perishable that can neither be made outside of GB nor exported...
01:30:06 <orin_> my whole fort is turning green with vomit
01:30:15 <quintopia> well, i'm asking because i want to know what i should get shipped
01:32:39 <orin_> wait you sid GB not the british isles
01:32:57 <orin_> the english aren't really known for their food you know
01:33:02 <boily> quintopia: QUINTHELLOPIA!
01:33:25 <boily> eeeeh... I wonder if cornish pastries are mainlonly available there.
01:34:11 <boily> orin_: roast beef.
01:38:15 -!- relrod has quit (Ping timeout: 256 seconds).
01:42:18 -!- relrod_ has joined.
01:59:27 -!- boily has quit (Quit: ARBOREAL CHICKEN).
02:12:20 -!- Phantom_Hoover has quit (Read error: Connection reset by peer).
03:17:45 -!- perrier has joined.
03:20:17 -!- hjulle has quit (Ping timeout: 255 seconds).
04:12:24 -!- GeekDude has quit (Quit: {{{}}{{{}}{{}}}{{}}} (www.adiirc.com)).
04:16:55 -!- relrod_ has changed nick to relrod.
04:54:47 <zzo38> I had a idea which is a program to be converted into another program, which on alternating steps runs the first program and tries to find a proof that the first program will not halt (such a proof might not exist though, or it might not be able to find one).
04:56:06 <zzo38> Do you know how to do it?
05:07:01 -!- variable has joined.
05:26:16 -!- variable has quit (Ping timeout: 264 seconds).
05:31:09 -!- TodPunk has joined.
05:44:11 -!- mbrcknl has quit (Ping timeout: 256 seconds).
05:46:04 <orin_> Apparently Muckefuck means chicory coffee in German?
05:46:19 -!- mbrcknl has joined.
05:46:36 <zzo38> I don't know, I am not German
05:51:33 <orin_> wikipedia says so, but it may be vandalism...
05:52:08 <zzo38> It does have history look and also look Wiktionary
05:53:26 -!- Sprocklem has quit (Ping timeout: 264 seconds).
06:02:45 <FreeFull> From what I can find on Google, muckefuck is a coffee substitute of some kind, at least
06:03:14 -!- oerjan has quit (Quit: Nite).
06:07:32 -!- bsin has joined.
06:07:32 -!- bsin has left.
06:09:29 -!- variable has joined.
06:35:22 -!- hamrove has quit (Quit: hamrove).
06:58:54 -!- conehead has quit (Quit: ZNC - http://znc.in).
07:13:29 -!- zadock has joined.
07:36:33 -!- AnotherTest has joined.
07:39:13 <orin_> Protip: くdiv> isn't a html tag
07:42:08 -!- dianne has quit (Quit: byeannes).
07:46:06 <orin_> neither, for that matter, is <dⅳ>
07:53:55 -!- variable has quit (Ping timeout: 250 seconds).
08:01:36 <mroman> it is if you have unicode -> ascii replacements turned on in your parser .
08:23:44 -!- AnotherTest has quit (Ping timeout: 248 seconds).
08:28:19 -!- Patashu has joined.
08:38:57 <orin_> ed is the best editor for editing CSV files.
08:41:19 <int-e> It's hard to find fault in that idea, but I will still object on the principle that any sentence starting with "ed is the best editor" must somehow be wrong. :)
08:42:36 <orin_> Well it's the only situation in which you work primarily on lines, rather than paragraphs or blocks
08:45:31 -!- jameseb has quit (Ping timeout: 256 seconds).
08:45:44 <orin_> In this case, I was reformatting a html table into a csv file, then adding javascript to convert it back at runtime
08:46:31 <orin_> That way it is much easier to add/remove rows
08:46:49 <b_jonas> orin_: you can still use ex for that
08:47:10 <orin_> Oh right, I keep forgetting that.
08:48:49 -!- jameseb has joined.
08:54:20 <orin_> to be fair, my ed is an alias for rlwrap ed -p$'\33[31med:\33[0m '
08:54:51 <orin_> It has command history and a red ed: prompt
08:54:54 <mroman> Is vi just an ed frontend?
08:55:17 <orin_> i think it was originally a mod
08:57:25 <mroman> "ed is the best editor" is wrong. <- so this sentence would be wrong as well.
08:58:45 <orin_> I like the way ! allows you to use the shell from ed
09:04:50 <orin_> it has a learning curve, but I use it anytime i'm editing a line-oriented format
09:09:32 -!- AnotherTest has joined.
09:09:51 -!- AnotherTest has quit (Ping timeout: 252 seconds).
09:10:45 -!- bb010g has quit (Quit: Connection closed for inactivity).
09:10:45 <int-e> mroman: you may know more about ed than you realize; a significant number of vi commands originate in ed.
09:12:48 <mroman> I don't know how to use vi
09:13:00 <mroman> I could write me an ed-like editor with haskeline
09:14:54 <lambdabot> http://en.wikipedia.org/wiki/Edlin
09:14:55 <lambdabot> Title: Edlin - Wikipedia, the free encyclopedia
09:18:55 <int-e> oops, has that feature been abused for bot loops?
09:54:21 <orin_> SEO seems a lot of effort to just make a bot loop.
10:01:50 <HackEgo> [wiki] [[CalScript]] N http://esolangs.org/w/index.php?oldid=42764 * Vriskanon * (+90) Created CalScrupt
10:02:49 <HackEgo> [wiki] [[Language list]] M http://esolangs.org/w/index.php?diff=42765&oldid=42718 * Vriskanon * (+16) /* C */ Added CalScript (will add info to page later)
10:08:12 <b_jonas> wait, there's a new OOTS strip
10:11:17 <Taneb> b_jonas, there's a new IWC strip as well
10:11:27 <Taneb> And Homestuck is back, too!
10:11:35 <Taneb> It's like the world is coming to an end!
10:12:02 <b_jonas> Taneb: also, Debian Jessie is released, and gcc 5.1 was released some weeks ago
10:12:14 <Taneb> I thought gcc 5.1 was like last week?
10:12:34 <HackEgo> [wiki] [[Fish]] http://esolangs.org/w/index.php?diff=42766&oldid=42110 * Charlie * (+346) Added a fizzbuzz example
10:13:06 <HackEgo> [wiki] [[Fish]] M http://esolangs.org/w/index.php?diff=42767&oldid=42766 * Charlie * (+5) Formatting :$
10:27:28 -!- boily has joined.
10:38:12 -!- hamrove has joined.
10:56:33 -!- Patashu_ has joined.
10:56:34 -!- Patashu has quit (Disconnected by services).
11:04:05 -!- Phantom_Hoover has joined.
11:10:16 <boily> @ask fungot do you read your messages?
11:10:17 <fungot> boily: very language has it's strength, and it's driving me a little version of the white box) it disappears? :p) but i'd forget some key thing i decided on define-c-struct.) the name of the yield expression.
11:11:03 <boily> A yield expression by any other name will generate as much.
11:20:42 <orin_> Why is inhibition pronounced as if spelled hinibition?
11:24:02 <orin_> I guess I only know how I pronounce it. other people appear to disagree
11:25:22 <orin_> Oh i see, somehow I imported the french spelling
11:26:36 <boily> aren't they spelled the same in French and English?
11:27:41 <orin_> @google "hinibition"
11:27:43 <lambdabot> http://www.google.ee/patents/EP0941733A3?cl=fr
11:27:43 <lambdabot> Title: Patent EP0941733A3 - Proc�d�s d'hinibition de l'exportation de prot�ine...
11:28:31 <orin_> Ok I dunno where I got "hinibition" but that is how i say it
11:29:14 <boily> they wrote «hinibition.» google translate says «Essayez avec cette orthographe : inhibition». I don't know what to believe.
11:29:36 <orin_> i guess it flows more naturlly than saying inhibition... my tongue trips over the n followed by h
11:30:16 <boily> unvoice the "n" hth
11:30:21 <orin_> note that my dialect has an h
11:31:24 <orin_> i mean i think brits are like, "ello" and im like uh, "Hhhhhello"
11:31:50 <boily> I'll try to grab a dead-tree-pulp dictionary and find information about words with wandering hes.
11:31:56 -!- boily has quit (Quit: HAPPENING CHICKEN).
11:32:01 <orin_> also how the heck do you unvoice an N
11:32:32 -!- GeekDude has joined.
11:32:45 <orin_> would that just amount to blowing yourn nose?
11:34:23 -!- fizzie has quit (Quit: jumpin' jumpin').
11:34:31 -!- fizzie has joined.
11:35:00 <lambdabot> boily asked 24m 43s ago: do you read your messages?
11:36:06 <fizzie> (That would've been better if I hadn't had to disreconnect to get rid of the unseemly ~ in my user name.)
11:39:08 -!- gniourf has quit (Quit: Leaving).
11:44:07 -!- orin_ has changed nick to orin.
11:47:34 -!- gniourf has joined.
12:01:48 -!- AnotherTest has joined.
12:24:33 <Jafet> @ask fungot do you read your massages?
12:24:33 <fungot> Jafet: ( reading the above article.) ( 1 2 3
12:24:54 <Taneb> Apparently there is a 6-month time limit to bank a cheque
12:25:06 <Taneb> And I am glad I was not three days later otherwise I would have found out the hard way
12:49:20 -!- hjulle has joined.
12:56:28 <mroman> fungot: Any movie recommendations?
12:56:29 <fungot> mroman: neutral, of course. it's not that hard to read imo.
12:56:46 <mroman> Ok, I'll read books then.
13:03:30 -!- Phantom_Hoover has quit (Ping timeout: 240 seconds).
13:10:30 <HackEgo> [wiki] [[Talk:ASCII art]] N http://esolangs.org/w/index.php?oldid=42768 * 72.10.97.6 * (+163) yes
13:14:25 -!- AnotherTest has quit (Ping timeout: 252 seconds).
13:40:36 <HackEgo> [wiki] [[Talk:Lazy evaluation]] http://esolangs.org/w/index.php?diff=42769&oldid=31644 * 72.10.97.6 * (+116) /* I request that more be written for this article! */ new section
13:41:07 <Jafet> Or you can be crazy like fungot and read all of europarl.
13:41:07 <fungot> Jafet: what about banana-0?
13:55:50 <fizzie> fungot: Is that what they talk about in the EU parliament?
13:55:50 <fungot> fizzie: closing ports and the global time will tick each time something is fnord
13:58:49 -!- `^_^v has joined.
14:02:07 -!- Phantom_Hoover has joined.
14:05:39 <FreeFull> How about a programming language indistinguishable from things said in #esoteric
14:06:43 <mroman> every line ending with hth is a comment
14:06:54 <mroman> which makes oerjan a comment.
14:06:59 <myname> every fact has to end with hth
14:07:10 <myname> and every request with twh
14:07:26 -!- Phantom_Hoover has quit (Ping timeout: 250 seconds).
14:07:56 <myname> we could oerjanize(tm) prolog
14:23:23 -!- Patashu_ has quit (Ping timeout: 256 seconds).
14:27:36 -!- Sprocklem has joined.
14:34:34 -!- v4s has quit (Ping timeout: 256 seconds).
14:43:31 -!- Sprocklem has quit (Ping timeout: 264 seconds).
14:45:07 -!- v4s has joined.
14:49:44 -!- conehead has joined.
14:55:52 -!- spiette has joined.
15:03:17 -!- Sprocklem has joined.
15:04:02 -!- Sprocklem has changed nick to Guest1367.
15:06:57 <HackEgo> olist 981: shachaf oerjan Sgeo FireFly boily nortti
15:12:00 -!- nszceta has joined.
15:14:17 -!- Phantom_Hoover has joined.
15:16:59 -!- rdococ has joined.
15:19:43 -!- Phantom_Hoover has quit (Ping timeout: 248 seconds).
15:22:04 <paul2520> quintopia: "Progress in mathematics is often obtained by finding the right notation.
15:22:13 <paul2520> │ | (~phantomho@unaffiliated/phantom-hoover) has │ Vorp
15:22:25 <paul2520> M. Kline, Mathematics from Ancient to Modern Times. Oxford, U.K.: Oxford Univ. Press, 1972
15:23:15 <paul2520> (I figured you might appreciate the quote based on the blog post from last week)
15:24:05 <HackEgo> [wiki] [[Lazy evaluation]] http://esolangs.org/w/index.php?diff=42770&oldid=21440 * GermanyBoy * (+15) completed the request
15:41:07 <quintopia> think of a better notation than that one
15:52:39 -!- hjulle has quit (Ping timeout: 264 seconds).
16:06:04 -!- Guest1367 has quit (Quit: [).
16:06:24 -!- Sprocklem has joined.
16:12:38 <paul2520> quintopia: yeah, I really enjoyed that read
16:12:43 <paul2520> problem is, math is so ingrained
16:12:49 <paul2520> but definitely this is good to stir up discussion
16:12:54 <paul2520> have you posted it to reddit at all?
16:13:34 -!- variable has joined.
16:52:15 -!- Phantom_Hoover has joined.
16:58:03 -!- Phantom_Hoover has quit (Ping timeout: 264 seconds).
17:04:32 -!- zadock has quit (Quit: Leaving).
17:05:01 <quintopia> paul2520: no i don't think it's been posted there. feel free to do so.
17:08:41 <quintopia> but i searched reddit for "logarithm" and there's nothing posted there recently with that subject
17:14:19 <HackEgo> [wiki] [[Lazy evaluation]] http://esolangs.org/w/index.php?diff=42771&oldid=42770 * SuperJedi224 * (+137)
17:22:39 <paul2520> quintopia: http://redd.it/341ugi
17:23:12 <paul2520> easy way to find if an article has been posted to reddit is to type in your address bar redd.it/http://www.solidangl.es/2015/04/a-radical-new-look-for-logarithms.html
17:29:47 -!- Phantom_Hoover has joined.
17:30:04 <zzo38> I don't expect it to work and it doesn't; but...in the browser I use you can't type anything into the address bar anyways, you have to type it into the command bar and it still just result "file not found"
17:30:55 -!- Sprocklem has quit (Ping timeout: 248 seconds).
17:32:54 <Taneb> The person whom my user page claims not to be an esolanger IS MAKING AN ESOLANG
17:33:29 <Taneb> http://esolangs.org/wiki/User:Taneb
17:33:30 <zzo38> Then maybe your user page is wrong
17:33:35 <Taneb> "<Sourceless> Taneb is made of magic and probably rubber bands
17:33:35 <Taneb> Someone who to my knowledge is not an esolanger."
17:34:13 <olsner> plot twist: both lines are wrong
17:34:28 <Taneb> olsner, I am in fact made of magic and probably rubber bands
17:35:01 <int-e> olsner: also the number of false statements so far has been odd
17:35:44 -!- Phantom_Hoover has quit (Ping timeout: 272 seconds).
17:36:50 <int-e> Ah, finally the cake is working. I was worried...
17:49:50 -!- nszceta has quit (Remote host closed the connection).
17:50:56 -!- nszceta has joined.
17:53:42 <J_Arcane> http://blog.fogus.me/2015/04/27/six-works-of-computer-science-fiction/
18:02:02 -!- Phantom_Hoover has joined.
18:04:18 -!- spiette has quit (Ping timeout: 245 seconds).
18:05:07 <zzo38> Do you know this code? 35003C4187F2CD2193B440CD21
18:11:18 -!- nszceta has quit (Read error: Connection reset by peer).
18:12:14 -!- nszceta has joined.
18:17:28 -!- spiette has joined.
18:23:46 <int-e> There should really be a C3 at the end though, it's not good style to execute random data
18:27:29 <b_jonas> do you mean it's a DOS com file?
18:28:28 <int-e> It is. It makes a few common but undocumented assumptions (CX = 00FF and SI=0100 at program start; it also assumes AX=0000 but that is actually assured if the program got no arguments)
18:37:26 <HackEgo> [wiki] [[Fish]] M http://esolangs.org/w/index.php?diff=42772&oldid=42767 * Charlie * (+242) Added another interpreter.
18:39:27 -!- Sprocklem has joined.
18:41:01 <b_jonas> ok wait, so it starts XOR AX, 3C00H: INC CX: XCHG SI,DX: INT 21
18:45:25 <b_jonas> you say AX starts as 0, so that would make AH=3C, DOS2 style create file, DX points to filename, but DX is 0100h so the filename is "5" (so that's why it's an XOR instruction instead of MOV)
18:46:13 <b_jonas> this will presumably set AX to the file descriptor number, say 5
18:46:41 -!- nycs has joined.
18:49:36 -!- `^_^v has quit (Ping timeout: 276 seconds).
18:50:31 <b_jonas> then XCHG BX,AX: MOV AH,40H: INT 21H
18:51:54 <b_jonas> that calls the function 40H for writing into a file (dos2 style), which takes the file handle in BX which is where this moves it, and the pointer to data in DX which is still the start of the code,
18:52:22 <b_jonas> the length is in CX and it's 0100H
18:52:40 <b_jonas> so I guess this is a quine that writes the first 256 bytes of the COM file to the file "5"
18:52:45 <b_jonas> but yes, it needs a return at the end
18:56:41 <zzo38> Apparently it is a "Trivial.13" virus
18:58:04 -!- nycs has changed nick to `^_^v.
18:59:27 <int-e> "This virus spreads by attaching its code to other files on your PC or network. Some of the infected programs might no longer run correctly."
18:59:46 <int-e> Lovely generic descriptions.
19:00:39 <int-e> "Detection added: 01 Jan 1970 01:00 GMT"
19:02:27 <zzo38> I read in some book at the library I think that mentioned this was the shortest computer virus, but the codes were not printed in the book, so I tried to find it so that I can study it, and then I did so
19:05:33 <rdococ> it's a TRIVIAL description, lol
19:08:36 -!- nszceta has quit (Remote host closed the connection).
19:12:44 -!- AnotherTest has joined.
19:24:34 <int-e> The 41 bytes one from http://vxheaven.org/vl.php?dir=Virus.DOS.Small at least tries...
19:25:01 <int-e> (it looks for a file *.e* and places a matching .com file besides it)
19:25:14 -!- zadock has joined.
19:26:42 <int-e> (and it needs a 386 to run)
19:27:35 <rdococ> for some weird reason, Windows decided it was a good idea to let 'shutdown' command exist.
19:27:43 -!- spiette has quit (Ping timeout: 248 seconds).
19:27:48 <rdococ> can be useful, but since it cant really be stopped
19:27:58 -!- rdococ has quit (Quit: Page closed).
19:29:57 -!- `^_^v has quit (Quit: This computer has gone to sleep).
19:30:08 -!- `^_^v has joined.
19:31:55 -!- hamrove_ has joined.
19:34:43 -!- hamrove__ has joined.
19:35:25 -!- hamrove has quit (Ping timeout: 255 seconds).
19:37:23 -!- hamrove_ has quit (Ping timeout: 250 seconds).
19:42:21 -!- spiette has joined.
19:43:14 -!- hamrove__ has quit (Quit: hamrove).
19:43:30 -!- hamrove has joined.
19:45:31 -!- bb010g has joined.
19:49:01 -!- zzo38 has quit (Remote host closed the connection).
19:53:47 -!- AnotherTest has quit (Ping timeout: 265 seconds).
20:01:03 -!- Koen_ has joined.
20:01:37 -!- hamrove has quit (Quit: hamrove).
20:01:55 -!- hamrove has joined.
20:56:07 -!- zadock has quit (Quit: Leaving).
20:59:20 -!- spiette has quit (Ping timeout: 256 seconds).
21:04:14 -!- AnotherTest has joined.
21:04:55 <paul2520> quintopia: great discussion on the reddit post! http://redd.it/341ugi
21:06:52 -!- Patashu has joined.
21:08:56 <Koen_> "I like this. I'll start using it whenever I write math that I don't need to show to other people"
21:14:05 -!- spiette has joined.
21:29:00 -!- Sprocklem has quit (Ping timeout: 265 seconds).
21:34:10 -!- Patashu has quit (Ping timeout: 252 seconds).
21:40:40 -!- Koen_ has quit (Quit: The struct held his beloved integer in his strong, protecting arms, his eyes like sapphire orbs staring into her own. "W-will you... Will you union me?").
21:43:21 -!- oerjan has joined.
21:47:56 -!- AnotherTest has quit (Remote host closed the connection).
21:52:58 -!- boily has joined.
21:53:00 -!- Sprocklem has joined.
21:54:10 -!- FanFL has joined.
21:56:30 -!- hamrove has quit (Quit: hamrove).
21:57:00 <HackEgo> FanFL: 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.)
21:57:17 -!- `^_^v has quit (Quit: This computer has gone to sleep).
21:57:26 <FanFL> lol thank you for the warm welcome
21:57:57 <fizzie> The new relcome is so ordered. :/
21:58:12 <FanFL> Is it against community values to ask for help beta testing an interpreter?
21:58:38 <FanFL> I'm making a Funge-98 interpreter
21:58:42 <FanFL> its going really well
21:58:43 <oerjan> no response guaranteed
21:58:48 <FanFL> its been just me testing it
21:58:58 <fizzie> You should use Mycology.
21:59:02 <FanFL> I figure I have to get some users or I'll find out that my UI is crap
21:59:37 <fizzie> Oh. Well, Mycology wouldn't be testing that.
21:59:45 <FanFL> funny you should mention it
21:59:52 <fizzie> (But you could at least verify the interpretation part.)
21:59:57 <FanFL> because I'm currently running through mycology right now
22:00:26 <FanFL> "BAD: 4k #..." is confusing me a bit
22:01:04 <FanFL> because the position of the IP is not supposed to be altered by whatever happens inside of k right?
22:01:31 <fizzie> There have been all manner of debates about corner cases involving k, to be honest.
22:02:09 <fizzie> I think the consensus is that the standard is too ambiguous there.
22:02:31 <fizzie> "The k "Iterate" instruction pops a value n off the stack. Then it finds the next instruction in Funge-space in the path of the IP (note that this cannot be a marker such as space or ;), treats it as an instruction, executing it n times. This takes only one tick with respect to concurrent operation.
22:02:36 <fizzie> Note that some instructions don't make much sense within the context of k unless you include zero as one of the possibilities for how many times the instruction is repeated. For example, no matter how many times after the first time k execute ^, the result is the same. However, you may pass a zero count to k, and the ^ instruction will not be executed; this can be a valuable behaviour.
22:02:42 <fizzie> Also, note k will never, ever actually execute instruction #32, space, or ;."
22:04:59 <fizzie> And of # it says: "moves the IP one position beyond the next Funge-Space cell in its path". I think you can make the case that k# should be capable of doing j-like things.
22:05:22 -!- FanFL has quit (Ping timeout: 246 seconds).
22:05:37 -!- FanFL_ has joined.
22:05:48 <FanFL_> my internet connection is terrible
22:06:06 <FanFL_> edge cases involving k
22:06:26 <fizzie> You can use http://codu.org/logs/_esoteric/ to check what you missed. I pasted a chunk that's probably too long to re-paste.
22:07:23 <oerjan> <Taneb> It's like the world is coming to an end! <-- YOU THINK SO TOO?
22:08:11 <FanFL_> http://www.rcfunge98.com/tutorial4.html
22:08:16 <lambdabot> LOWI 272150Z AUTO VRB05G15KT 9999 BKN120 16/06 Q1001
22:08:28 <lambdabot> ENVA 272120Z 23006KT 9999 FEW050 BKN180 07/M00 Q1004 RMK WIND 670FT 27002KT
22:08:43 <FanFL_> important piece of the puzzle, the 'k' command does NOT move the IP when it executes the iterated command, the IP is pointing at the 'k' command not the command it is executing.
22:08:49 <oerjan> Taneb: well we still don't have an alderaan forecast hth
22:09:13 <FanFL_> am I just reading that wrong?
22:09:29 <fizzie> FanFL_: Well, you're reading it in one way.
22:09:40 <fizzie> FanFL_: I think the argument here is that while k does not move the IP, the # will.
22:09:56 <oerjan> just make k create nose daemons and call it a day.
22:10:09 <FanFL_> fizzie: perhaps I'm reading mycology wrong
22:10:37 <FanFL_> fizzie: when it says BAD: 4k # does nothing and hits #
22:10:58 <FanFL_> fizzie: is it saying that it is wrong that 4k# does nothing and it is wrong that it hits #
22:11:19 <FanFL_> I think I answered my own question
22:11:29 <fizzie> Yes, I think that's what it is saying. FWIW, there's a number of k-# tests it does.
22:11:55 <FanFL_> fortunatly those all pass
22:12:30 <fizzie> "GOOD: 2k# jumps twice from k" and "BAD: 2k# jumps twice from #", for example.
22:12:43 <FanFL_> fizzie: On a social note, whats your connection with Funge 98?
22:12:46 <fizzie> I think the goal with "4k #" (with the space) is to make sure k is executing the # and not the ' '.
22:13:13 <fizzie> Nothing official. I wrote a bot with it, people seem to like it.
22:13:19 <fizzie> fungot: Say something bright, would you?
22:13:19 <fungot> fizzie: ive been working on a p2p app and that seemed to you like it
22:13:32 <fizzie> ...yeah, it's not very good at impressing on command.
22:13:34 <fungot> https://github.com/fis/fungot/blob/master/fungot.b98
22:13:55 <coppro> fizzie: does k move the IP an extra cell?
22:14:21 <coppro> or does it usually execute the next instruction top + 1 times, if the instruction doesn't effect the IP
22:14:26 <fizzie> coppro: It should not. Hence the thing about "5kX" executing X 6 times.
22:15:17 <fungot> oerjan: by the way.) you should _not_ introduce any more syntax than needed! hah! :-p cool.
22:15:31 <FanFL_> fizzie: with the code and nothing else on the stack, where does this end up "11kj^v<>"
22:16:10 <fizzie> FanFL_: Gblh. Up, I think.
22:16:21 <fizzie> FanFL_: Should have the same effect as 1j except from the k.
22:16:43 <lambdabot> http://www.anagrammer.com/scrabble/gblh
22:16:43 <lambdabot> Title: GBLH Definition, Anagrams, and related Scrabble word finder for GBLH
22:17:32 <FanFL_> I guess here at the end of the page answers all of this
22:17:33 <oerjan> `learn Gblh but less helpful.
22:17:34 <FanFL_> http://www.rcfunge98.com/tutorial4.html
22:17:43 <HackEgo> Learned 'gblh': Gblh but less helpful.
22:18:30 <int-e> I wonder whether the monks have any ... free ... padded cells.
22:19:00 <fizzie> FanFL_: FWIW, I don't think that tutorial is really normative. But I agree with it.
22:19:26 <FanFL_> what do you mean by normative?
22:20:14 <oerjan> int-e: i wonder if the monks did something to knock them out, or if it was agatha's locket reactivating
22:20:29 <fizzie> Um. Capable of dictating how the language should behave. Like the spec document is, in theory.
22:20:30 <oerjan> (klaus/gil _was_ touching it...)
22:20:53 <int-e> (that's my theory)
22:21:14 <FanFL_> fizzie: oh! a question that has been on my mind for a while. What is Funge-108/109?!
22:21:39 <FanFL_> fizzie: It is mentioned in cfunge and rc-funge but I cannot find documentation about it anywhere
22:21:57 <FanFL_> fizzie: I got the feeling it was talked about in some email back and forth and shoved under a rug
22:22:11 <FanFL_> fizzie: or maybe I am just not cool enough to have found it searching through search engines...
22:23:01 <oerjan> int-e: hm does that mean _all_ the main characters in the room are now going down?
22:23:13 <Taneb> I think recent Girl Genius comics are really highlighting that we are reading one of the Heterodyne stories
22:24:51 <Taneb> Like, it's the same sort of tone, sparks save the world from the Other with mad science
22:25:12 <int-e> oerjan: http://www.girlgeniusonline.com/comic.php?date=20070119 may not be relevant, after all *that* was a pie :)
22:26:07 <fizzie> FanFL_: There was an attempt (here, on the channel) to define a less ambiguous standard, somewhen 2008-ish.
22:26:47 <fizzie> FanFL_: It didn't really go anywhere. There was a draft text or a few.
22:26:50 <b_jonas> oh! did people start to refer to it as Funge-11x when you couldn't complete it in time?
22:26:57 <oerjan> int-e: different application method. also that spark supposedly went to england.
22:27:18 <int-e> oerjan: but we don't know what happened to the recipe :)
22:27:31 -!- MDude has joined.
22:27:55 <int-e> anyway it's really more of a random association, I don't see a connection inside the story
22:28:14 <FanFL_> fizzie: thats kind of disapointing to hear...
22:28:24 <fizzie> FanFL_: There's also a Befunge-111, FWIW.
22:28:30 <oerjan> Taneb: well there _is_ the "phil and kaja are professors at transylvania polygnostic" conceit, i guess.
22:28:31 <fizzie> Although the link to that draft seems to be dead too.
22:29:35 <FanFL_> fizzie: Even on achrive sites?
22:29:41 <Taneb> I think the final storyline will reveal the fate of Bill and Barry, possibly with their triumphant return and/or tragic tragedy
22:30:05 <fizzie> "Wayback Machine doesn't have that page archived."
22:30:23 <fizzie> FanFL_: Funge-108 was mostly by Vorpal, the cfunge author, while Befunge-111 was by cpressey, the... well, the Befunge-93/98 author.
22:30:53 <FanFL_> fizzie: Maybe I'll email them and ask them about it
22:31:24 <FanFL_> fizzie: also, I should really finish -98 before I try to move on to -11X
22:31:45 <Taneb> `? Stephen Wolfram
22:31:46 <HackEgo> Stephen Wolfram is an esolanger with too much money and power. Taneb invented him.
22:31:47 <FanFL_> fizzie: I'm just obsessed. Its great.
22:31:58 <Taneb> I think Charles Moore is also an esolanger with too much money and power
22:32:11 <fizzie> Apparently the Funge-108 links I have are also (a) dead, and (b) not archived by archive.org.
22:32:33 <FanFL_> fizzie: Last thing before I stop bothering you all, scary moment. Can I share a screen shot of my program with you?
22:32:46 <oerjan> 2008, the dark age of the internet
22:33:04 -!- sebbu2 has changed nick to sebbu.
22:33:04 <fizzie> Sure, but best share it with the channel. I'm not the only befunge person here, even if I seem to be making the most noises at the moment.
22:33:43 <fizzie> (Given how the latest fungot commit is from 2013, I'm not sure I can even call myself a Befunge person very much longer.)
22:33:43 <fungot> fizzie: or at least language specs for smith?
22:40:03 <FanFL_> do people here hate imgur for sharing images?
22:40:17 <FanFL_> I just like it because you can copy and paste from the clipboard
22:42:53 -!- FanFL_ has left.
22:43:01 -!- FanFL_ has joined.
22:43:19 <FanFL_> so people are okay with imgur?
22:45:21 <FanFL_> lol, it seems mentioning the word cleared out everyone....
22:45:27 <fizzie> There's been at least a thousand imgur links on the channel already, go for it.
22:46:16 <FanFL_> http://i.imgur.com/1Fbdrxv.png?1
22:46:29 <FanFL_> A terrifying moment but you know what, I am confident and proud of my work so far
22:46:52 <FanFL_> This awesome thing is the best thing I've ever created in my life.
22:47:30 <FanFL_> It features cut, copy, paste, being able to set the direction of the editing IP
22:47:50 <FanFL_> making you able to typing North,East,South, or West
22:48:05 <fizzie> Also syntax highlighting, very fancy.
22:48:35 <FanFL_> the picture on the right shows that you can select areas of funge and edit negative funge space directly
22:48:54 <FanFL_> it also allows you to navigate to anywhere in funge space and view it
22:49:06 <FanFL_> even the edges of fungespace
22:49:20 <b_jonas> "negative funge space" is the part with negative coordinates?
22:49:31 <fizzie> I've always kind of wanted a Befunge editor where you could associate comments with arbitrary regions, perhaps indicated by subtle background colors. And shown somewhere. I don't know where. I don't have a good vision about this, really.
22:49:38 <Taneb> Someone ought to make ColorFUNGE in the same line as ColorFORTh
22:50:00 <FanFL_> I saw that once for a Funge-98 for RISC OS
22:50:05 <FanFL_> mine might include that too one day
22:50:27 <fizzie> It's good for documentation, stuff like http://sbp.so/qsort
22:50:38 <b_jonas> Taneb: yeah, it would suit Funge because colorforth uses fixed size pages to store code, and old befunge has a fixed rectangle
22:50:48 <fizzie> I did something quite similar to a piece of code, too, and then managed to completely lose it.
22:52:10 <FanFL_> if you want to download a copy you'll need Visual Studio 2012, .NET something or other, and this link https://github.com/tngreene/BefungeSharp!
22:52:24 <FanFL_> if you want to download a copy you'll need Visual Studio 2012, .NET something or other, and this link https://github.com/tngreene/BefungeSharp
22:52:42 <b_jonas> make it so the color codes consume a cell though!
22:53:05 <b_jonas> except at the beginning of a line where it's free
22:53:10 -!- hamrove has joined.
22:53:11 <FanFL_> Its coded in C# and uses the Console. It was quite a twisting to make the console act like this
22:53:32 <Taneb> b_jonas, in the spirit of ColorFORTH, different characters have different widths
22:53:37 -!- boily has quit (Quit: EXPLOSIVE CHICKEN).
22:54:09 <b_jonas> oh sure, we need double-height rows, and shift codes not only for color, but also for double width
22:55:04 <b_jonas> double width wouldn't be shift codes
22:55:23 <b_jonas> it would be a character meaning "stretch the next character to this cell"
22:56:34 -!- FanFL_ has quit (Quit: Page closed).
22:57:02 <Taneb> b_jonas, I was trying to reference ColorFORTH's variable-width huffman-style encoding
22:58:15 <b_jonas> but doesn't it only do that to store the names of symbols, which mostly aren't used for execution, and the actual pages just contain a list of words that refer to symbols?
22:58:24 <b_jonas> um, a list of fixed size words.
22:58:39 <b_jonas> I admit I don't really know how colorforth works
23:01:17 <Taneb> I think I'll head to bed now
23:04:04 <lambdabot> lexical error in string/character literal at end of input
23:04:59 -!- int-e has left ("IMPLOSIVE CHKN").
23:04:59 -!- int-e has joined.
23:12:12 -!- spatterworthy has joined.
23:18:58 -!- ais523 has joined.
23:24:28 -!- hamrove has quit (Quit: hamrove).
23:31:21 -!- Sprocklem has quit (Ping timeout: 256 seconds).
23:39:45 -!- variable has changed nick to trout.
00:00:18 -!- bb010g has quit (Quit: Connection closed for inactivity).
00:04:05 -!- hjulle has joined.
00:24:48 <ais523> you may have to change your password
01:03:20 <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/
01:07:14 -!- bb010g has joined.
01:16:39 -!- trout has quit (Ping timeout: 265 seconds).
01:19:34 -!- hamrove has joined.
01:39:58 -!- MDude has changed nick to MDream.
02:00:10 -!- Phantom_Hoover has quit (Quit: Leaving).
02:40:32 -!- hjulle has quit (Ping timeout: 245 seconds).
03:00:54 -!- variable has joined.
03:18:57 -!- spatterworthy has quit (Ping timeout: 246 seconds).
03:26:59 -!- Sprocklem has joined.
03:31:18 -!- GeekDude has quit (Quit: {{{}}{{{}}{{}}}{{}}} (www.adiirc.com)).
03:43:29 -!- hamrove has quit (Quit: hamrove).
04:33:37 -!- variable has changed nick to trout.
04:48:18 -!- trout has quit (Ping timeout: 264 seconds).
05:15:51 -!- zzo38 has joined.
05:20:30 <zzo38> Another way to do color codes in cells is to use the PC memory format, so there is a color code in each cell
05:30:25 <orin> color codes for text or graphics?
05:33:17 <zzo38> Color codes for text is what I meant
05:34:56 <orin> Yeah ncurses does that IIRC, you | the color into the character you write
05:35:21 <orin> whcih implies the higher bits are used for color
05:37:26 <zzo38> I don't mean ncurses though, I mean poking the data directly into the memory; such a thing is only for PC though
05:37:51 <zzo38> PC color codes are also different numbers than ANSI color codes.
05:38:52 <orin> yah, i would think so, curses was invented on some mainframe architecture, i think.
05:40:33 <orin> also I remember on windows you can instead use conio.h
05:41:22 -!- Sprocklem has quit (Ping timeout: 245 seconds).
05:49:50 <zzo38> How would you make a transform from one program to a program which on alternating steps runs the original program and tries to figure out a proof that the original program does not halt? Now is it the new kind of halting problem? (Well, not quite the new kind)
05:52:36 <orin> I suppose, you could simply chack whether the state of the program is one that it was in before?
05:53:12 <orin> (wait, that only works if the memory doesn't grow)
05:53:20 <oerjan> @tell int-e <int-e> Ah, finally the cake is working. I was worried... <-- wait this means you shouted "cake!" *without* having read the latest comic tdnh
05:53:36 <zzo38> Yes, that is one case, at least, but there are other cases too
05:53:55 <oerjan> @tell int-e wait scratch that i'm getting confused about the age of logs i'm reading
05:54:44 <oerjan> that's what happens when i don't log off before going to bed
05:55:31 <orin> oerjan: well that's better than me. without school or work I was recently corrected about the day of the week from thinking itwas friday to monday
05:56:35 <orin> The day of the week is pretty arbitrary isn't it
05:56:58 <oerjan> yeah. but very traditional.
05:57:28 <oerjan> we've probably not skipped a single one since the ancient jews.
05:58:16 <oerjan> although the french tried.
05:58:36 <ais523> suppose the 7-day cycle had existed since the first humans
05:58:41 <orin> The chinese apparently had a 10 day week (reading wiipedia)
05:59:02 <oerjan> ais523: WELL OF COURSE DON'T YOU READ THE BIBLE
05:59:02 <ais523> how few humans would there have to be to have a decent chance of all of them forgetting what day of the week it was simultaneously, amd being unable to reconstruct?
05:59:32 <ais523> oerjan: that doesn't imply that the seven days cycled, did it?
05:59:49 <orin> if they were programmers, 100
05:59:50 <ais523> I think the Romans had a 9-day cycle, anyway
06:00:01 <oerjan> i vaguely thought it was 8...
06:00:08 <ais523> nones and ides happened once a monht
06:00:28 <ais523> so each month was separated into three pieces, each of which was numbered separately
06:00:34 <ais523> I guess it seemed like a good idea at the time?
06:01:06 <oerjan> zzo38: your transform sounds sort of trivial, once you've selected a formal proof system
06:02:44 <orin> I think I would prefer a 9 day system. then we can have 2 days work, one day off
06:03:04 <ais523> don't some jobs have a 2 on, 1 off, 2 on, 2 off system?
06:03:16 <ais523> that seems even better
06:03:20 <oerjan> ais523: except some parts of the year didn't have months originally
06:03:35 <zzo38> oerjan: What kind of formal proof system is it though?
06:03:39 <ais523> oerjan: I think they did in the Roman calendar
06:03:42 <ais523> perhaps not in the early days, thoguh
06:03:53 <orin> right, that would help sync with the moon
06:04:08 <oerjan> zzo38: i assume gödel implies you cannot really select a "best" one.
06:04:27 <oerjan> so you could go with ZFC, or homotopic type theory, or whatever.
06:04:43 <oerjan> (i hear the latter is all the rage)
06:05:47 <oerjan> ais523: well i'm talking about the roman calendar, from when someone here(?) pointed at a good site explaining its evolution.
06:05:52 <zzo38> OK I looked it up a few information in Wikipedia
06:07:42 <zzo38> Is it ever possible that applying such a transformation twice makes a difference (if the transformation method does something unusual)?
06:07:50 -!- zadock has joined.
06:08:22 <oerjan> lots of things are possible
06:09:08 <oerjan> zzo38: well your transform never makes the program _less_ halting.
06:09:20 <zzo38> oerjan: I do see that at least yes
06:10:42 <ais523> I don't think that, if your proof system is correct, it's possible to prove that you can prove something, but not prove it
06:10:44 <ais523> perhaps I'm wrong though
06:11:04 <ais523> actually I think this is a property of proof systems that has a name and gets discussed by logicians
06:11:32 <ais523> perhaps I should go find my copy of Forever Undecided, it has a lot of discussion about that sort of thing
06:11:37 <oerjan> argh bloody tonsils or whatever it hurts when i swallow
06:11:44 <zzo38> I thought that too but also am unsure, even if a proof system can make up a proof system somehow
06:12:34 <oerjan> <ais523> I don't think that, if your proof system is correct, it's possible to prove that you can prove something, but not prove it <-- i refuse to believe you're not garbling whatever what was supposed to mean.
06:13:26 <oerjan> ais523: in fact i think there's such a theorem but i cannot remember who it's named after
06:13:43 <ais523> from what I remember reading about this stuff
06:13:57 <ais523> it's a property a system can have, which is useful in some proofs, and which is implied via various other plausible groups of properties
06:14:15 <ais523> so the theorem you're vaguely remembering is probably along the lines of "if a proof system has properties X, Y, and Z, it has that one too"
06:14:47 <oerjan> hm löb's theorem is sort of the wrong way
06:17:49 <zzo38> Can a formal system make up its own new kind of formal system by adding "this statement cannot prove itself" as a new axiom?
06:18:37 <ais523> zzo38: well, if you take Gödel's counterexample "this statement is not provable"
06:18:57 <ais523> you know that statement is not provable in a correct system (if it were, it would be false)
06:19:19 <ais523> and its negation is not provable either (its negation is "the negation of this statement is provable", and if it were, you'd again be proving a false statement)
06:19:30 <ais523> thus you can add either it or its negation as an axiom
06:19:34 <ais523> and still have an internally consistent system
06:19:36 <zzo38> Yes, I read about that too
06:19:51 <ais523> IMO it wouldn't be a very useful axiom though
06:23:27 <oerjan> <J_Arcane> http://blog.fogus.me/2015/04/27/six-works-of-computer-science-fiction/ <-- way for a link to make me feel cheated the second i open it tdnh
07:24:20 -!- TodPunk has quit (Read error: Connection reset by peer).
07:37:38 -!- llue has quit (Quit: That's what she said).
07:37:48 -!- lleu has joined.
07:57:22 -!- jameseb has quit (Ping timeout: 276 seconds).
07:57:39 -!- TodPunk has joined.
07:59:23 -!- jameseb has joined.
08:11:56 <orin> Hmm ed's ! command doesn't appear to allow cd to work properly
08:12:22 <ais523> that's because cd is a shell builtin
08:12:35 <ais523> you're changing the current directory of the spell you spawned, not the editor that spawned it
08:12:54 <HackEgo> [wiki] [[CalScript]] M http://esolangs.org/w/index.php?diff=42773&oldid=42764 * Vriskanon * (+100) Added tokens and memory info.
08:13:10 <ais523> I have shown #esoteric /bin/cd before, I doubt it'd work with ed directly
08:13:15 <ais523> but you could probably tweak it to do so
08:13:32 <ais523> (it works by attaching a debugger to the parent process and forcibly getting that process to call the change-directory syscall itself)
08:14:05 <orin> Hmm... Maybe I should download the source code for ed and add filsytem stuff to it
08:14:52 <orin> Ed is written in C, almost certainly, so it shouldn't be hard
08:23:30 -!- idris-bot has quit (Ping timeout: 250 seconds).
08:23:51 -!- mroman has quit (Ping timeout: 256 seconds).
08:24:05 -!- mroman has joined.
08:24:17 -!- idris-bot has joined.
08:24:19 <oerjan> orin: that's called ex hth
08:24:35 <orin> does ex have a cd
08:24:47 <oerjan> yes, at least the vim based one
08:25:14 <oerjan> ex is simply a different mode of running vim (you can switch from inside)
08:25:21 <fungot> mroman: what's this " it doesn't compile
08:25:48 <mroman> fungot: That's a start of a string.
08:25:48 <fungot> mroman: i don't think anyone but me's ever used intercal quotes to parens when there are fnord
08:26:03 <mroman> fungot: Ow. " in intercal? I don't know intercal.
08:26:03 <fungot> mroman: ( define subset? ' ( a) ab acdafg ( b) think long and hard about the concept of code being outstanding... right?
08:26:12 <oerjan> chdir means the same thing
08:26:18 <ais523> mroman: in INTERCAL, parens are ' to ' or " to "
08:26:42 <ais523> or well, INTERCAL '' and "" do the same thing as parens in most languages
08:26:50 <ais523> with the benefit of occasionally being ambiguous in weird ways
08:27:41 <orin> ex is not full backward compatible to ed
08:28:06 <orin> specifically ex uses q! while ed uses Q
08:29:54 -!- Patashu has joined.
08:34:59 <orin> I think strings should be 5"hello
08:35:14 <orin> and/or [hello]
08:36:11 <orin> Ideally it would support hollerith for auto-generated code, and matching delimiters for humnas
08:36:40 <orin> hollerith means the generator doesn't have to translate escapes
08:49:51 -!- lleu has quit (Quit: That's what she said).
09:06:28 -!- idris-bot has quit (Quit: Terminated).
09:06:45 -!- idris-bot has joined.
09:09:45 <orin> Holy crap. The ed source contains the following line: if( errno == ERANGE || li > INT_MAX || li < INT_MIN )
09:09:51 <orin> set_error_msg( "Numerical result out of range" );
09:10:16 <orin> Which assumes that li, a long, has a lager range than an int
09:10:34 <orin> which it doesn't, on most 32 bit systems
09:11:35 <ais523> that would have made sense in the days of 16-bit systems
09:11:41 <ais523> which is where I learned to program
09:11:52 <ais523> or, well, it was Windows 3.1 code but running on Windows 95
09:12:02 <orin> yeah, that makes sense as the origin
09:12:03 <ais523> err, where I learned to program C and C++, I should say
09:12:42 <ais523> I learned BASIC and Pascal earlier than that (and eventually got a computer with BASIC in the ROM of my own; it was obsolete at the time and its owners were trying to get rid of it, so it only cost £20 IIRC)
09:13:07 * Taneb never actually learnt to program
09:13:32 <ais523> Taneb: can you program, though?
09:13:44 <Taneb> ais523, I can pretend to program very well
09:14:13 <orin> Is long a 64 bit integer on 64 bit systems?
09:14:21 <ais523> orin: yes on Linux, no on Windows, typically
09:14:44 <Taneb> More seriously, I sort of just picked stuff up, I did learn Haskell at some point, and I get lost very easily in any program of any appreciable size
09:14:51 <ais523> this is apparently because on Linux 32-bit programs, "long is pointer-sized" is a more common assumption than "long is 32 bits"; on Windows, it's the other way round
09:15:15 <ais523> given how little it has in common with anything else
09:15:27 <ais523> I can imagine knowing that quite well and still having not that much contact with the rest of the programming world
09:15:35 <Taneb> I had a little Python and JavaScript before I started Haskell, but not much at all
09:15:40 <ais523> (although, my day job is in OCaml, so)
09:15:47 <ais523> actually I'm not even sure why I wrote this thing in OCaml
09:15:50 <orin> I can program in imperative languages. I can write toy programs in functional languagaes
09:16:01 <ais523> I can't remember if I was asked to, or if I chose it, and if I chose it, why
09:16:25 <ais523> it's not like I was good at OCaml at the time (I'm much better at it now, after working in it for 3-4 years)
09:16:45 <orin> I once wrote a program inFortran 77 for no good reason
09:17:07 <orin> other than i was reading a book that had examples in fortran
09:17:27 <ais523> I once wrote a program in Prolog with no way to run it
09:17:31 <ais523> no idea if I still have it or if it would have worked
09:17:36 <ais523> that was based entirely on reading manuals
09:17:44 <Taneb> Really, I think I'm a maths student who likes computer science more than anything else
09:17:58 <ais523> (strangely enough, I remembered enough Prolog from back then to actually write in it once I had an impl)
09:18:22 <orin> I had a course in prolog where I never actually ran any prolog programs, just wrote and analyzed them
09:18:54 <ais523> to be fair, actually running Prolog programs doesn't give much insight into what they do or whether it's working
09:19:27 <Taneb> I think my uni course will take me about as close to Eodermdrome as to Prolog :/
09:19:53 -!- hjulle has joined.
09:20:18 <ais523> the amazing thing about Prolog is that I don't think there's another language like it (apart from uncomputable vaporware esolangs)
09:20:46 <ais523> (I have the working name "Proud" for a language which is Prolog minus the arbitrary restrictions needed to make it computable, and have no idea why I chose that name any more)
09:21:02 -!- Phantom_Hoover has joined.
09:21:07 <orin> why is Perl called perl?
09:21:26 <orin> I don't know why anything is called anything
09:21:27 <Taneb> ais523, "PROlog UnDecidable"?
09:21:47 <ais523> Larry Wall read through all the three- and four-letter words in the dictionary
09:21:52 <ais523> didn't find any he liked
09:22:05 <ais523> and then went through the five-letter words until he finally found a name he thought was acceptable
09:22:12 <ais523> then he discovered it was already taken, so had to misspell it
09:23:49 <mroman> orin: Perfect emacs rewriting language
09:24:05 <mroman> `learn Perl is the Perfect Emacs Rewriting Language
09:24:12 <HackEgo> Learned 'perl': Perl is the Perfect Emacs Rewriting Language
09:24:45 <orin> Anyway if your professor says, you can write the program in any language so long as it works, that is an excuse to use Fortran or PL/I or any other ancient and forbidden tongue.
09:25:19 <ais523> orin: they said that in my Systems and Control GCSE
09:25:25 <ais523> and I had a huge urge to write it in assembler
09:25:46 <ais523> but given that that was an exam that I wanted to do really well at and I had a feeling I shouldn't annoy the examiner, I wrote it in pseudo-BASIC instead
09:26:37 <mroman> but without -ffree-form
09:26:42 <mroman> free-form is for whimps.
09:26:50 <orin> Yeah that's what I did
09:27:14 -!- ais523 has left ("<fungot> fizzie: it makes demons fly out of my window, washing the windows api").
09:27:18 -!- ais523 has joined.
09:27:20 <orin> I used the line numbers and the weird three number goto and everythinmg
09:27:28 <ais523> what does -ffree-form do?
09:27:55 <ais523> (also, I did do well at that exam, I got a letter back from the exam board saying I had one of the top 5 marks in the country on that exam)
09:28:11 <ais523> (then the school stopped teaching the subject altogether a few years later)
09:28:29 <orin> it means you don't have to put the line numbers aon particular columns and begin the statement at charcter number 7 and put a C in character 1 for commnets
09:29:25 <ais523> oh, I was assuming BASIC, not Fortran
09:29:45 <ais523> actually this gives me an evil idea
09:30:09 <ais523> line numbers in particular columns, REM has to be in column 1, etc.
09:30:43 <oerjan> i don't think REM in column 1 is backward compatible
09:31:03 <oerjan> unless you're satisfied with 9 comment lines
09:31:32 <oerjan> or wait is this 0 or 1 indexing
09:32:07 <oerjan> or wait you mean REM doesn't get a line number
09:32:22 * oerjan learned BASIC too long ago
09:32:29 <ais523> I was wondering about that myself
09:32:33 <ais523> I can see a few potential solutions
09:32:43 <ais523> one is to use fancy Unicode line numbers that let you fit larger numberes into one column
09:32:54 <ais523> I guess, failing that, you could put the number at the end of the previous line
09:34:19 <orin> What if a lanuage used Roman line numbers
09:34:38 <ais523> I'm surprised that hasn't been done yet
09:34:48 <ais523> I can believe it happening in something INTERCAL-related
09:35:00 <orin> I. WRITE HELLO WORLD
09:35:25 <ais523> meanwhile, I'm reading a paper on how to do a FizzBuzz in Haskell without checking /anything/ twice, O(n) in program size in the number of "fizz"/"buzz" keywords
09:35:40 <ais523> from the ICFP contest a few years ago
09:35:43 <ais523> if you haven't seen that, you should
09:35:50 <ais523> it is one of the most amazing esoprogramming projects ever
09:35:57 <ais523> (not QVICKBasic, the contest as a whole)
09:36:32 <ais523> orin: http://boundvariable.org/task.shtml
09:36:35 <myname> ais523: show me that paper
09:37:01 <ais523> myname: https://themonadreader.files.wordpress.com/2014/04/fizzbuzz.pdf
09:37:01 <myname> i don't quite get where the problem is
09:37:11 <ais523> this doesn't look very submitted, as papers go
09:37:14 <ais523> but it's in the form of a paper
09:37:22 <myname> at least every third number is a fizz
09:37:45 <myname> number of fizz is in O(numbers)
09:38:14 <ais523> as in, if you add more pairs than just (3, "fizz"), (5, "buzz")
09:38:24 <ais523> say you add in more primes and more humorous noises
09:38:36 <ais523> the size of your program needs to be O(n) in that
09:38:47 <ais523> anyway, the reason I mentioned this is that it reminded me of yacc
09:38:57 <ais523> and now I'm trying to figure out if a yacc fizzbuzz is even a meaningful problem
09:40:27 <ais523> hmm, this thing has just two references; one to Dijkstra, the other to Wikipedia
09:42:59 <orin> Why not just do struct {char*s,int i} noises[]={{"fizz",3},{"buzz",5}};
09:43:19 <ais523> and then write an interpreter?
09:43:33 <ais523> you may still end up checking something twice
09:43:58 <orin> I don't think so...
09:44:36 <ais523> depends on how your interp works
09:44:45 <mroman> Is 'capital punishment' == 'death sentence'?
09:44:49 <ais523> I think it might work if you have an accumulator variable
09:44:55 <ais523> mroman: pretty much, they're used in different contexts
09:45:15 <ais523> "capital punishment" = "this countries' laws allow for execution of people committing certain crimes"
09:45:25 <ais523> "death sentence" = "a ruling that a specific person should be executed"
09:45:38 <ais523> but they're close enough in meaning for people to use them interchangeably
09:45:56 <mroman> Susan-Anne White has quite a manifesto.
09:46:45 -!- zadock has quit (Quit: Leaving).
09:47:42 <orin> for(i=0;i<MAX;i++)for(j=0;j<sizeof(noises)/sizeof(noises[0]);j++)if(i%noises[j].i==0)fputs(noises[j].s,stdout);putchar();
09:47:46 <orin> for(i=0;i<MAX;i++)for(j=0;j<sizeof(noises)/sizeof(noises[0]);j++)if(i%noises[j].i==0)fputs(noises[j].s,stdout);putchar('\n');
09:47:49 <ais523> hmm, westernish europe
09:48:24 <ais523> orin: where does that print the number itself if none of them match?
09:48:48 <orin> oh, right. you need to have a boolean for that...
09:49:51 <ais523> also you're missing a pair of braces, meaning that you'll only print one newline at the end of the program
09:50:05 -!- hjulle has quit (Ping timeout: 248 seconds).
09:50:15 <ais523> which given that it's summer time, means western but not as far west as the UK
09:50:16 <orin> for(i=0;i<MAX;i++){f=1;for(j=0;j<sizeof(noises)/sizeof(noises[0]);j++)if(i%noises[j].i==0)fputs(noises[j].s,stdout),f=0;if(f)printf("%n",i);putchar('\n');}
09:50:22 <ais523> although if you are in Portugal, it's using some weird DST rules
09:50:31 <ais523> either that or my clock is wrong or your clock is wrong
09:50:37 <HackEgo> /home/hackbot/hackbot.hg/multibot_cmds/lib/limits: line 5: exec: time: not found
09:50:47 <HackEgo> real: 0m1.575s, user: 0m0.000s, sys: 0m0.000s
09:50:54 <HackEgo> Tue Apr 28 09:50:53 UTC 2015
09:51:13 <ais523> somehow, even nowadays I slip that I grew up on DOS
09:51:42 <orin> yeah. so I think it's trivial to do it, if you store the numbers and words in a data structure separately
09:54:52 <orin> although, it's not necessary to test if i%4==0 if i%2==1
09:55:10 <orin> so there are still uneccary tests
09:56:28 <ais523> I think it's probably more efficient to just check anyway, than to write extra logic to detect that case
09:56:35 <ais523> although arguably that violates the rules
09:56:44 <ais523> it didn't really make the details of the rules clear
09:57:18 <ais523> so, it turns out there's no fizzbuzz in INTERCAL
09:58:10 <oerjan> oh you mean no one wrote one
09:58:44 <b_jonas> what? let me check Rosetta Code
09:58:59 <ais523> oerjan: not in the Pit, anyway
09:59:03 <b_jonas> http://rosettacode.org/wiki/FizzBuzz
09:59:07 <ais523> which claims to be a repository of all known INTERCAL programs
09:59:11 <ais523> it may, however, be lying
09:59:18 <b_jonas> but there's a Chef implementation
09:59:35 <ais523> actually INTERCAL is a really hard language to write this in
09:59:42 <ais523> especially if you don't use the standard library
10:00:04 <b_jonas> yeah, the problem is that it's hard to write even a BF interpreter in intercal
10:00:23 <ais523> BF interp is easier, I think
10:00:29 <ais523> no modulo, no string handling other than single chars
10:00:37 <b_jonas> is there an easy way to remap array indexes so that they're easy to increment and decrement in intercal?
10:01:01 <b_jonas> I mean, remap integers to other integers that way, and then you use them as array indices
10:01:04 <ais523> b_jonas: there's a one-statement increment in INTERCAL that isn't too awful that's been known for a while now
10:01:22 <b_jonas> ais523: is there a decrement too?
10:01:34 <ais523> I have been considering the "some formula which cycles through 2^n possible values in an arbitrary order" thing, but didn't come up with a solution
10:01:34 <b_jonas> just increment isn't enough
10:01:46 <b_jonas> ais523: it needn't be 2**n values
10:01:46 <ais523> and yes, to decrement you can complement then increment then complement, among other things
10:02:25 <ais523> DO .1 <- "?'"'"'"'"'"'"'"'"'".1~.1"~.1'~.1"~.1' ~.1"~.1'~.1"~.1' ~.1"~.1'~.1"~.1' ~.1"~.1'~.1"~.1' $#1"~"#32767$#1"'$.1"~"#0$#65535"
10:02:32 <ais523> sorry for the gratuitous whitespace
10:02:56 <ais523> DO .1 <- "?'"'"'"'"'"'"'"'"'".1~.1"~.1'~.1"~.1'~.1"~.1'~.1"~.1'~.1"~.1'~.1"~.1'~.1"~.1'~.1"~.1'$#1"~"#32767$#1"'$.1"~"#0$#65535"
10:03:55 <ais523> IIRC, if you remove one of the "…~.1" repetitions, it works for all numbers but 65534
10:03:59 <b_jonas> I mean, I certainly prefer languages that have a large selection of arithmetic built in, but if you're using intercal, there's really no reason to use numbers in their original meaning, is there?
10:04:13 <b_jonas> Maybe there is some little reason for that, like if arrays are stored continuously
10:04:57 <ais523> (((((#65535 $ #65535) ~ ((?32 ((((V32 ((&32 (.4 $ .2) ~ (#0 $ #65535)) $ .9) (#0 $ #65535)) $ #0) ~ (#32767 $ #1)) $ .2) ~ (#0 $ #65535)) $ #65535)) $ .4) ~ (#0 $ #65535)) $ .9) <- (#435 $ #72)
10:05:00 <b_jonas> or... can you give computed percentages?
10:05:17 <ais523> this one was the culmination of literally years of work
10:05:20 <ais523> and isn't in INTERCAL syntax yet
10:05:24 <ais523> and has the input operands hardcoded
10:05:36 <ais523> and no, not in C-INTERCAL I don't think (you probably can in CLC-INTERCAL)
10:06:18 <ais523> specifically, you give it the bitwise-AND and bitwise-XOR of two numbers
10:06:42 <ais523> and it returns the bitwise-XOR of a specific one of those numbers and their sum
10:07:11 <ais523> so a little extra code allows you to convert it to an addition routine
10:07:15 <ais523> no loops, no threading, it's great
10:07:24 <ais523> it takes violin a little under 2 minutes to run on this laptop
10:07:50 <ais523> yeah, that's my Slashdot sig, I managed to golf it to fit it within the size limits
10:08:54 <ais523> (1)DOCOMEFROM!2~.2'~#1WHILE:1<-"'?.1$.2'~'"':1/.1$.2'~#0"$#65535'"$"'"'&.1$.2'~'#0$#65535'"$#0'~#32767$#1"
10:09:09 <ais523> that's way more efficient than the reverse assignment method
10:09:13 <b_jonas> That looks way scarier than my GF(128) obfu, because that only has to compute an inconvenient operation from convenient primitives. in intercal, you have to go backwards, computing convenient operations from crazy primitives.
10:09:57 <ais523> the reason to use threading is simply that x WHILE y runs y for as long as x is running
10:10:02 <ais523> and thus is a convenient way to do a loop
10:10:19 <b_jonas> GF(128) obfu => http://www.perlmonks.com/?node_id=863110
10:10:51 <ais523> that algorithm there is actually incredibly conventional, it basically starts with two numbers, adds them bitwise to produce a value and a carry, then uses the value and shifted carry as inputs to the next round
10:10:56 <ais523> and repeats until there are no carries left
10:11:02 <ais523> the violin code is a little more unconventional
10:11:28 <b_jonas> though maybe a better analog would be http://www.perlmonks.com/?node_id=989716 which does implement useful operation (addition) from inconvenient ones (indexing and amending bits in the Zeckendorf representation)
10:12:23 <ais523> <my notes on violin> `carry` = (`a` bitwise-OR (`x` bitwise-AND `carry`)) leftshifted 1
10:12:29 <b_jonas> (zzo38 has implemented even more useful stuff in zeckendorf)
10:12:37 <ais523> `a` and `x` are the and and xor of the original numbers
10:12:39 <HackEgo> /home/hackbot/hackbot.hg/multibot_cmds/lib/limits: line 5: exec: a`: not found
10:12:44 <ais523> based on that, we then define the carry in terms of itself
10:13:47 <b_jonas> and it's only about 16 steps to stabilize
10:13:58 <b_jonas> not, say, 65536 steps which some formulas could do
10:14:08 <ais523> b_jonas: oh, you don't understand
10:14:13 <ais523> it's not an iterative algorithm
10:14:22 <ais523> violin has to use a SAT solver to solve it
10:14:27 <ais523> which is why it's so slow
10:15:00 -!- TodPunk has quit (Read error: Connection reset by peer).
10:15:15 <ais523> INTERCAL expression syntax is now NP-complete, you can write arbitrary boolean satisfaction problems in it
10:15:29 -!- TodPunk has joined.
10:16:26 <ais523> basically you write them on the left of the arrow
10:16:49 <ais523> all compilers agree that it's legal to select 16 bits from a 32-bit number, then mingle that with something
10:17:10 <ais523> also, all compilers agree that it's illegal to selec 17 or more bits from a 32-bit number, producing a value greater than 65535, then mingle that with something
10:17:10 <b_jonas> and it can contain indexing on the left and right hand side of the arrow?
10:17:31 <b_jonas> how does it even determine which variables to modify?
10:17:38 <ais523> (there's some grey area if you select 17 or more bits but the value is less than 65536 bits, but you can easily avoid that case)
10:17:45 <ais523> and, ugh, I didn't think of array indexing on the left of the arrow
10:18:25 -!- MauBot has joined.
10:19:10 <b_jonas> like, if you say DO.1~.2<-.3 how does it know whether to modify .1 or .2 ?
10:19:57 <ais523> oh, it modifies everything mentioned to the left of the arrow
10:20:00 <ais523> including the constants, in some mpls
10:20:08 <ais523> although rather predictably in most
10:20:21 <ais523> violin will find each possible solution with nonzero probability
10:20:22 <oerjan> <ais523> I have been considering the "some formula which cycles through 2^n possible values in an arbitrary order" thing, but didn't come up with a solution <-- if you make that 2^n-1, it's what i did for the unlambda interpreter gc
10:20:38 <b_jonas> and is there a way to force it to keep some values constant when searching for a solution?
10:20:50 <ais523> also the unlambda interp has a gc? or was it just refcounting?
10:21:10 <ais523> b_jonas: currently no, for violin integration I'm planning a "don't modify constants unless you have to" approach
10:21:25 -!- MDream has changed nick to MDude.
10:21:40 <b_jonas> ais523: ok, but how about non-constants? like if I want to search a solution where .1 doesn't change but .2 does
10:22:12 <b_jonas> hmm, is there a multiple assignment syntax so you can give more than one condition by the way?
10:22:16 <ais523> b_jonas: then you have to pass in the value indirectly on the right of the arrow
10:22:18 <orin> I read that as integrating an actual violin, before realizing there could be a language called violin
10:22:22 -!- Wazza has joined.
10:22:30 <ais523> also, you can't directly do a multiple assignment
10:22:37 <ais523> but you can just write DO .1$.2 <- .3$.4
10:22:47 -!- Wazza has left ("Textual IRC Client: www.textualapp.com").
10:22:54 <b_jonas> that won't work for two dwords or three words
10:23:07 <ais523> you can only do 32 bits atm, yes
10:23:40 <b_jonas> I guess too much generality would make it too easy to program
10:23:53 <ais523> it's not INTERCAL without arbitrary restrictions
10:24:00 <ais523> although I have been considering bignum mingle as a usefulish operation
10:27:23 <oerjan> ais523: ok refcounting it was
10:28:10 -!- boily has joined.
10:32:41 -!- iamevn_ has joined.
10:34:53 -!- nortti has quit (Ping timeout: 265 seconds).
10:35:01 -!- nortti has joined.
10:35:32 -!- iamevn has quit (Ping timeout: 245 seconds).
10:43:36 -!- AnotherTest has joined.
10:44:05 -!- MauBot has quit (Remote host closed the connection).
10:48:24 <orin> Ok, I added a 'C' command to ed that changes direcotry
10:49:22 <orin> As long as I'm mangling GNU software, anything else I shouold add?
10:49:58 <b_jonas> orin: why don't you just use ex instead?
10:50:10 <orin> because that's not as fun
10:51:30 <orin> Maybe I can add syntax highlighting
10:52:04 <b_jonas> orin: doesn't it already have that via w|your-syntax-highlighter-executable
10:52:09 <b_jonas> or maybe with a ! instead of |
10:52:52 <orin> Good point. Maybe I whould just add a command to set an executable to pass all output through
10:54:32 <orin> Well technically that doesn't do exactly what I mean, but I see the value in externalizing the highlighting
10:56:00 <boily> hellorin. what kind of atrocities are you commiting to ed?
10:56:15 <ais523> boily: it's a saner method than /bin/cd at least
10:56:37 <orin> I added a 'C' command, and now I think i'll add syntax highlighting
10:57:04 <ais523> apparently early UNIX had a /bin/goto that exploited the fact that the shell of the time, pre-sh, read the file back from disk after every command was executed
10:57:08 <ais523> so it manually moved bits of the shellscript around
10:57:39 <boily> /aaaaaaaaaaaaaaaargh!
10:58:24 <orin> http://ctrlv.in/565704
11:00:37 <orin> *strchr(*ibufpp,'\n')=0;
11:00:46 <orin> beacuse i'm awful.
11:01:57 <boily> remind me to mapole you when I won't be having a cold and have a little bit more muscular strength twh
11:02:51 -!- ais523 has quit (Ping timeout: 264 seconds).
11:03:27 <orin> well it seems that there is always a newline at the end
11:03:46 <orin> (based on the lack of egfaulting)
11:05:15 <oerjan> boily: hey have you been infecting me
11:05:26 <oerjan> oh i was supposed to eat
11:05:51 <boily> hellørjan. I don't think so hth
11:06:07 <oerjan> i recommend not having a throat that hurts when you swallow hth
11:08:02 <boily> my sinuses are blocked, coughing light green extraterrestrial radioactive stuff, but at least my throat doesn't hurt.
11:08:35 <oerjan> now i can think "at least my sinuses aren't blocked"
11:10:38 <orin> So I think I'll add an F [command] command, which causes ed to pass all output of 'p' and 'n' through the command.
11:11:08 <orin> and maybe an option to set this from the command line
11:11:24 <orin> 'F' for 'formatter'
11:12:20 <b_jonas> orin: um, at that point you might want to add some escape code for multibyte commands before you use up all letters for insignificant commands
11:12:36 <b_jonas> that could hurt you later if you find more useful commands you'd want to put on the single letters
11:12:53 <b_jonas> you know, like the way the vanilla nethack key layout is messed up
11:13:23 <orin> Nah, I'll just start using é and æ
11:14:08 <orin> probably utf-8
11:14:24 <b_jonas> you'll just run out of all 256 bytes. many are already used up for ranges or commands.
11:15:07 <orin> I mean, all i'd need to do is check for a byte above 128, and in that case read the next byte
11:15:20 <orin> and check what it is.
11:16:08 -!- f|`-`|f has quit (Ping timeout: 240 seconds).
11:16:56 <orin> But I dunno if I'll add more than 2 commands. I'll get bored pretty fast
11:17:31 <orin> apparently people used to modify the local versions of commands a lot in the old world
11:22:25 <oerjan> the haskell libraries list seems severely infested with top posters
11:23:12 -!- copumpkin has quit (Quit: My MacBook Pro has gone to sleep. ZZZzzz…).
11:24:01 <boily> oerjan: what do you mean?
11:24:37 <oerjan> people who quote the message they're replying to, _never_ removing anything, regardless of thread depth
11:24:48 <oerjan> and put their own answer at the top
11:25:03 <boily> oh. mailing lists.
11:25:37 <orin> I usually do that, but put my reply at the bottom
11:26:04 -!- ChanServ has set channel mode: +o oerjan.
11:26:13 -!- oerjan has kicked orin Crimes against humanity.
11:26:18 -!- oerjan has set channel mode: -o oerjan.
11:26:27 -!- orin has joined.
11:26:55 <orin> 'Crimes against humanity'
11:27:46 <orin> logically I think the reply shuld be at the bottom, but only if your software doewsn't automatically display the post your repling to
11:28:38 <oerjan> logically i think it's the sender's responsibility to be non-annoying to a large fraction of recipients.
11:29:45 <oerjan> in this case i'm browsing the mailing list from a web archive. it
11:30:01 <orin> Hm.. could you not write a script to go through your emails and cut out lines that consist of />>>>>>>>>>>>>>>*/
11:30:02 <oerjan> why was there a return key there.
11:30:20 <oerjan> orin: it's not my emails, i'm reading it on the web.
11:30:59 <orin> Actually that could also cut out lines with brainfuck code in them
11:31:07 <orin> that's a problem
11:32:03 -!- boily has quit (Quit: REPLICATING CHICKEN).
11:32:22 <oerjan> does that mean we'll have two boilys next time
11:34:02 <orin> no, it means there was never one boily. the boily we get each time is a duplicate of the original boily, whowe've never met.
11:36:16 <orin> Does garnierite have anythign to do with the shampoo?
11:37:19 <orin> apparently they're both named after french people
11:48:20 -!- AnotherTest has quit (Ping timeout: 244 seconds).
12:10:50 -!- AnotherTest has joined.
12:32:46 -!- Patashu has quit (Ping timeout: 244 seconds).
13:02:47 -!- nortti has quit (Ping timeout: 265 seconds).
13:05:26 -!- nortti has joined.
13:09:40 <orin> http://ctrlv.in/565759
13:14:35 <orin> is it a problem if it passes the line numbers into the highlighter?
13:16:10 <orin> I suppose I could fork again and add the line numbers at the end of the pipeline
13:17:46 -!- Phantom_Hoover has quit (Ping timeout: 265 seconds).
13:18:21 <orin> eh, for now it's ok
13:21:34 -!- hamrove has joined.
13:29:03 <orin> I'm adding new features to the ed editor, what features do you think it needs?
13:31:18 <orin> what would that do?
13:39:28 -!- AnotherTest has quit (Ping timeout: 256 seconds).
13:39:38 <orin> oh, like destory the data on disk?
13:40:13 <orin> thats probably beyond my programmign porwess
13:53:42 -!- e_svedang has joined.
14:14:59 -!- e_svedang has quit (Ping timeout: 255 seconds).
14:17:12 -!- variable has joined.
14:30:01 -!- f|`-`|f has joined.
14:30:12 -!- Sgeo__ has joined.
14:31:28 -!- Vorpal has quit (Ping timeout: 240 seconds).
14:32:48 -!- Sgeo_ has quit (Ping timeout: 240 seconds).
14:33:08 -!- spiette has quit (Ping timeout: 240 seconds).
14:33:32 -!- spiette has joined.
14:33:57 -!- Vorpal has joined.
14:33:57 -!- Vorpal has quit (Changing host).
14:33:57 -!- Vorpal has joined.
14:50:55 <mroman> can ed execute shell commands?
14:50:59 <mroman> and collect the output?
14:51:08 <mroman> that would be a feature
14:51:26 <orin> https://github.com/orenwatson/orens-fun-ed
14:51:41 <orin> yes it does do that: for example
14:52:29 <mroman> I'm working on an editor in java
14:52:55 <orin> what kind of editor
14:53:16 <mroman> with support for 2D languages
14:53:33 <mroman> i.e. you can type normalle and it'll write it backwards or downwards and that stuff.
14:53:50 <orin> Oh, cool! that would really help
14:54:03 <mroman> and you can configure letters that change directions
14:54:14 <mroman> so it automatically switches after typing a ^ for example
14:54:53 <mroman> orin: I'll let you know once I have a decently working version.
14:59:17 -!- GeekDude has joined.
14:59:51 <orin> I suppose it is much easier to hack stuff that was already written...
15:04:38 -!- GeekDude has quit (Ping timeout: 252 seconds).
15:04:54 -!- variable has quit (Quit: 1 found in /dev/zero).
15:08:30 -!- variable has joined.
15:14:07 -!- Sprocklem has joined.
15:14:23 -!- orin has quit (Ping timeout: 255 seconds).
15:15:56 -!- GeekDude has joined.
15:16:08 -!- orin has joined.
15:17:11 -!- hamrove has quit (Quit: hamrove).
15:20:35 <int-e> orin: I certainly feel that way.
15:21:33 <int-e> oerjan: wait scratch that i'm getting confused about the age of logs <-- I forgive you
15:21:52 * int-e is in a benevolent mood
15:37:04 -!- variable has quit (Ping timeout: 250 seconds).
15:40:50 <orin> int-e: about the difficulty of writing versus modifying a program, or about replies should be at the bottom
15:43:00 -!- Jafet has quit (Ping timeout: 256 seconds).
15:43:26 -!- Jafet has joined.
15:44:08 -!- jix has quit (Ping timeout: 256 seconds).
15:44:16 -!- jix has joined.
15:50:21 -!- Jafet has left.
15:50:28 <int-e> orin: I meant the former, but I also feel the same way about top-posting.
15:51:10 -!- Jafet has joined.
15:51:30 <int-e> A: Because it upsets the natural flow of reading.
15:51:30 <int-e> Q: Why is top posting so rude?
16:12:06 -!- Vorpal has quit (Quit: ZNC - http://znc.sourceforge.net).
16:20:18 -!- bb010g has quit (Quit: Connection closed for inactivity).
16:21:53 <oerjan> int-e: that was to the forgiveness, i find the "don't cut away anything" part of posting more annoying than the actual top posting part
16:23:43 <int-e> oerjan: I thought so, but I replied to orin.
16:30:44 <int-e> oerjan: The two issues are related though: inline replies encourage people to cut down the context.
16:32:16 -!- hamrove has joined.
16:58:30 -!- e_svedang has joined.
16:58:48 <HackEgo> e_svedang: 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.)
17:01:14 -!- hamrove has quit (Quit: hamrove).
17:08:48 -!- AnotherTest has joined.
17:10:24 -!- HackEgo has quit (Ping timeout: 252 seconds).
17:11:45 -!- hamrove has joined.
17:12:30 -!- orin has quit (Quit: Lost terminal).
17:13:27 -!- variable has joined.
17:17:07 -!- oren has joined.
17:17:35 <oerjan> Gregor: HackEgo ran away
17:18:06 <oren> blah now DF is hanging my computer? god damn it 2GB of memory used to be a megaton!
17:18:18 -!- e_svedang has left ("Using Circe, the loveliest of all IRC clients").
17:19:07 <oerjan> argh too much drooling
17:20:33 <Taneb> oren, DF as in Dwarf Fortress?
17:21:00 <oerjan> i've got an infection such that it hurts to swallow, but never swallowing doesn't really work either. thus drooling.
17:21:33 <oerjan> oren: i think 2GB was about the _disk space_ on the first computer i installed linux on, back in 1999
17:22:16 <oerjan> quintopia: sorry no can do
17:22:43 <quintopia> what about throat numbing medicine? what about soaking up drool with crackers?
17:23:53 <oerjan> i don't have crackers. i do have plenty of paper tissue.
17:23:57 <oren> hmm try swallowing lots of tiny ice cubes
17:24:42 <oren> I think an eggo would work as a tray to make tiny ice cubes
17:24:44 <oerjan> i don't have ice cubes, and i don't see why that should help.
17:25:01 <oerjan> (i don't think i have one)
17:25:08 <oren> @google leggo my egoo
17:26:39 <oren> eggos were my lunch every day in middle school
17:28:46 <oerjan> isn't ridiculously detailed simulation like the point of DF, obviously it will always want to use as much resources as you have.
17:29:07 <oerjan> just be glad it's not 3d graphics on top
17:30:06 <quintopia> (i don't know that it would add that much load since the simulation would be cpu-bound and the graphics gpu-bound)
17:31:28 <b_jonas> debian installer CDs now boot with grub-2 instead of isolinux?
17:33:30 <int-e> heh, I don't even know what an installer CD is anymore... I guess I have one for Windows XP somewhere...
17:33:51 <oren> I use an installer SD usually
17:34:30 <int-e> (For the last few installations of Linux I've used debootstrap from Knoppix, which I find convenient because Knoppix can access an existing network.)
17:34:30 <b_jonas> int-e: I don't boot from the CD either, I just load the kernel and initrd on the tiny netboot installer CD from a boot loader instead
17:34:38 <b_jonas> so this change isn't really relevant to me
17:35:12 <int-e> but what's the problem with using grub 2 anyway?
17:35:42 <b_jonas> but I don't burn a CD, and don't install a bootloader just to run an installer image
17:36:13 <b_jonas> I just download the files to hard disk, and load them from my already installed grub-l bootloader or from a cd that has a grub-l bootloader
17:36:48 <b_jonas> I have a script here to convert between boot loader config files => http://www.perlmonks.com/?node_id=928102
17:37:04 <b_jonas> but I don't use that, I just type the command manually because I know what the debian installer expects
17:38:15 -!- Sprocklem has quit (Ping timeout: 264 seconds).
17:39:41 <b_jonas> I'll probably start to use grub2 when I'm forced to because I get hard disks larger than 2 tebibytes and so can't use a dos partition table
17:40:41 <b_jonas> how common are such hard disks now?
17:40:50 <b_jonas> not that I'll be buying any soon
17:44:22 <oren> Hence why I have so many SD cards
17:46:32 <b_jonas> I love having lots of disk space
17:46:45 <b_jonas> but currently the big hard disks seem to be 2 terrabytes size
17:47:20 <int-e> Right, 1TB seems to be the standard size for a new desktop pc, 500GB is also still a thing.
17:47:23 <oren> terrabytes: the data standard for all of Holy Terra
17:48:01 <int-e> nobody said anything about holyness...
17:48:29 <oren> int-e: its a 40K refrence.
17:48:38 <int-e> Ah. (And welcome to the bianual smartass competition!)
17:49:15 <oren> oh, I'm up against some terrifying competition
17:49:41 <oren> I hope I can do well!
17:50:48 <oren> anyway the disk space you get depends on how much you spend
17:51:23 -!- Vorpal has joined.
17:51:23 -!- Vorpal has quit (Changing host).
17:51:23 -!- Vorpal has joined.
17:59:48 <Vorpal> I need a hostname for a new RPi. I already have a RPi, but this new RPi 2 needs a name
18:00:49 <Vorpal> oren, doesn't fit my theme. Which is mythological beasts. The existing RPi is cerberus. The laptop I'm typing on is dragon.
18:02:03 <oren> wait did rowling invent them
18:02:24 <Vorpal> Never heard of them, what are they?
18:03:30 <Vorpal> oren, also plus points if the name fits the device. The RPi acts as a VPN and ssh endpoint. So Cerberus, the gatekeeper of the underworld is a fitting name.
18:03:49 <Vorpal> And phoenix is an old Pentium 3, reborn from various spare parts
18:05:58 <oren> guardians. gargoyles
18:06:25 <oerjan> (courtesy of the yafgc character)
18:06:38 <Vorpal> oren, yes that would fit the new RPi too, since it will be a ssh end point in a new location
18:07:52 <Vorpal> god, this memory card in this older RPi is slow, it previously ran on an external hdd, but I switched that over to the new RPi
18:10:54 -!- oerjan has set topic: Vǫwël Cøntınùům | https://dl.dropboxusercontent.com/u/2023808/wisdom.pdf http://codu.org/logs/_esoteric/ http://tunes.org/~nef/logs/esoteric/ | http://esolangs.org/.
18:23:26 -!- hamrove_ has joined.
18:26:18 -!- hamrove has quit (Ping timeout: 252 seconds).
18:31:06 -!- hamrove has joined.
18:34:08 -!- hamrove_ has quit (Ping timeout: 256 seconds).
18:44:41 <tswett> If I flip a fair coin until the number of heads exceeds the number of tails, or vice versa, by 50, then what's the expected value of the total number of flips?
18:47:08 <MDude> Based on a random walk moving, on average, the square root away from the center line after a given distance.
18:51:42 -!- variable has quit (Ping timeout: 256 seconds).
19:00:53 -!- fractal has quit (Changing host).
19:00:54 -!- fractal has joined.
19:18:48 <oerjan> MDude: i find the argument lacking, although simulation seems to confirm the answer.
19:21:15 -!- Sprocklem has joined.
19:31:58 <tromp> it's not exactly 2500, but on the order of that
19:38:22 -!- zzo38 has quit (Remote host closed the connection).
19:47:11 -!- Sprocklem has quit (Ping timeout: 245 seconds).
20:04:01 -!- hamrove has quit (Quit: hamrove).
20:05:44 <oerjan> tromp: it actually _is_ exactly 2500
20:11:07 <oerjan> @let rwStep l = 0:zipWith((+)`on`(/2))l(drop 2 l)++[0]
20:12:34 <oerjan> @let rwe = map toInteger (iterate rwStep (replicate 101 0) !! 100000)
20:12:35 <lambdabot> No instance for (Integral a0) arising from a use of ‘toInteger’
20:12:35 <lambdabot> The type variable ‘a0’ is ambiguous
20:12:55 <oerjan> @let rwe = map round (iterate rwStep (replicate 101 0) !! 100000) :: [Integer]
20:13:12 <coppro> oerjan: that's not a proof
20:13:37 <oerjan> coppro: it's a proof if i can get lambdabot to calculate it, but it's a little heavy
20:14:04 <oerjan> but lambdabot doesn't cache anything does it...
20:15:23 <oerjan> @let fp = [0,99,196,291,384,475,564,651,736,819,900,979,1056,1131,1204,1275,1344,1411,1476,1539,1600,1659,1716,1771,1824,1875,1924,1971,2016,2059,2100,2139,2176,2211,2244,2275,2304,2331,2356,2379,2400,2419,2436,2451,2464,2475,2484,2491,2496,2499]
20:16:11 <oerjan> > let tab = fp ++ 2500 : reverse fp in tab == rwStep tab
20:17:48 <oerjan> that gives True in GHCi :(
20:19:11 <oerjan> perhaps a rounding error. hm how can i make it exact... aha!
20:19:30 <oerjan> > let tab = fp ++ 2500 : reverse fp :: [CReal] in tab == rwStep tab
20:20:52 <oerjan> @let rwSum l = 0:zipWith((+))l(drop 2 l)++[0]
20:21:13 <coppro> oerjan: it's not a proof, it's just a simulation
20:21:43 <oerjan> coppro: the simulation is to find the answer. once you have the answer you can make a proof.
20:22:05 <oerjan> all i need to show is that the answer is a fixpoint of rwStep
20:22:50 <oerjan> hm wait how can there possibly by round-off error whan all i'm doing is half-integers
20:23:23 <oerjan> @let tab = fp ++ 2500 : reverse fp
20:24:00 <oerjan> > map (*2) tab == rwSum tab
20:24:02 <lambdabot> <no location info>: can't find file: L.hs
20:24:05 <oerjan> > map (*2) tab == rwSum tab
20:24:06 <lambdabot> <no location info>: can't find file: L.hs
20:24:16 <oerjan> > map (*2) tab == rwSum tab
20:28:33 <oerjan> i copied the wrong version
20:28:49 <oerjan> @let rwStep l = 0:zipWith((+)`on`(/2).(+1))l(drop 2 l)++[0]
20:28:49 <lambdabot> Parse failed: Ambiguous infix expression
20:29:00 <lambdabot> (b -> b -> c) -> (a -> b) -> a -> a -> c
20:29:17 <lambdabot> The operator ‘on’ [infixl 0] of a section
20:29:17 <lambdabot> must have lower precedence than that of the operand,
20:30:04 <oerjan> @let rwStep l = 0:zipWith((+)`on`(/2).(+1))l(drop 2 l)++[0]
20:30:04 <lambdabot> Parse failed: Ambiguous infix expression
20:30:16 <oerjan> @let rwStep l = 0:zipWith((+)`on`((/2).(+1)))l(drop 2 l)++[0]
20:30:17 <lambdabot> In an equation for ‘rwStep’: rwStep l = ...
20:30:35 <oerjan> @let rwStep2 l = 0:zipWith((+)`on`((/2).(+1)))l(drop 2 l)++[0]
20:31:00 <oerjan> coppro: that counts as a proof hth
20:33:10 <coppro> oerjan: I do not have the time right now to determine if it does
20:33:20 <coppro> that's rather esoterically dense code
20:36:06 <oerjan> ok but all it does is calculate the expected time to escape at this time given the expected time to escape after one step.
20:38:43 <oerjan> also, the stepping function is contracting in l^1 norm, thus has a unique fixpoint.
20:41:06 <oerjan> at least in nonnegative values.
20:48:30 <paul2520> quintopia: the original author of the blog post weighs in on reddit: http://www.reddit.com/r/math/comments/341ugi/a_radical_new_look_for_logarithms_interesting/cqrurrt?context=3
20:49:57 -!- S0lll0s has joined.
20:50:28 <S0lll0s> so I made something: https://github.com/S0lll0s/zunscript
20:50:56 <S0lll0s> first time I do anything meta-programming-ish
20:58:42 <HackEgo> [wiki] [[Talk:Al Dente]] http://esolangs.org/w/index.php?diff=42774&oldid=41877 * Tanner Swett * (+746) Responses
21:04:04 -!- Patashu has joined.
21:08:12 <tromp> oerjan: isn't the answer infinity?
21:10:22 <tromp> i think we were confused with the expected number of steps until *either* #heads or #tails leads by 50, which is indeed exactly 2500
21:10:51 <tromp> but the one sided expectations are infinite
21:14:00 <oerjan> the original question was the former
21:14:49 -!- AnotherTest has quit (Remote host closed the connection).
21:15:46 <tromp> oops; missed the vice-versa:(
21:16:30 <oren> S0lll0s: clicked on link, thought it had to do with 東方.
21:21:02 <oren> actually this is cool even if it doesn't have yukkuris in it
21:29:22 -!- Patashu has quit (Ping timeout: 256 seconds).
21:35:51 <oren> http://yukkuri.wikia.com/wiki/Yukkuri
21:37:40 <oren> heads filled with delicious bean paste
21:38:38 <oren> from a subculture of a subculture within japanese otaku subculture
21:41:21 <oren> the creator of Touhou is named (well, pseudonamed) "ZUN"
21:58:09 -!- spatterworthy has joined.
22:02:05 -!- spatterworthy_ has joined.
22:04:32 -!- spatterworthy has quit (Ping timeout: 246 seconds).
22:08:44 -!- ent0nces has joined.
22:19:24 -!- Phantom_Hoover has joined.
22:28:27 -!- ent0nces has quit.
22:43:01 -!- boily has joined.
22:44:15 -!- hjulle has joined.
22:58:47 -!- spatterworthy_ has quit (Ping timeout: 246 seconds).
00:00:17 -!- Sprocklem has joined.
00:01:26 -!- pikhq has quit (Ping timeout: 252 seconds).
00:17:14 -!- pikhq has joined.
00:45:38 -!- Phantom_Hoover has quit (Quit: Leaving).
00:58:39 <fungot> boily: a wireworld computer around somewhere. ( sources.tar.gz sources/ comp/ scsh/ scheme/ gauche
01:34:49 -!- variable has joined.
01:48:36 -!- MDude has changed nick to MDream.
02:03:14 <boily> bonne nuitopia! boerjanne nuit!
02:03:22 -!- boily has quit (Quit: REAPING CHICKEN).
02:32:11 -!- hamrove has joined.
02:39:20 -!- hjulle has quit (Ping timeout: 256 seconds).
02:55:48 -!- bb010g has joined.
03:23:59 -!- oerjan has quit (Quit: ZZZWAT).
03:58:11 -!- GeekDude has quit (Quit: {{{}}{{{}}{{}}}{{}}} (www.adiirc.com)).
04:00:36 -!- variable has quit (Ping timeout: 245 seconds).
04:40:42 -!- Decim has joined.
04:43:52 <Decim> http://hastebin.com/raw/payulupise
04:45:02 -!- copumpkin has joined.
04:45:22 -!- variable has joined.
05:06:31 -!- Sprocklem has quit (Ping timeout: 250 seconds).
05:38:37 -!- Decim has quit (Remote host closed the connection).
05:57:15 -!- nszceta has joined.
06:07:54 -!- TodPunk has quit (Read error: Connection reset by peer).
06:08:28 -!- TodPunk has joined.
06:12:01 -!- nszceta has quit (Read error: Connection reset by peer).
06:12:29 -!- nszceta has joined.
06:13:15 -!- diginet has quit (Quit: diginet has quit!).
06:13:24 -!- hamrove has quit (Quit: hamrove).
06:15:35 -!- nszceta has quit (Client Quit).
06:33:56 -!- hamrove has joined.
06:36:15 -!- nszceta has joined.
06:58:30 -!- variable has quit (Ping timeout: 250 seconds).
07:00:01 -!- nszceta has quit (Quit: Textual IRC Client: www.textualapp.com).
07:07:13 -!- zadock has joined.
07:20:55 -!- hamrove has quit (Quit: hamrove).
07:51:20 -!- CADD has quit (Ping timeout: 265 seconds).
07:51:48 -!- CADD has joined.
07:52:10 -!- CADD has changed nick to Guest69966.
08:20:00 -!- aloril_ has joined.
08:22:26 -!- aloril__ has quit (Ping timeout: 276 seconds).
08:28:45 -!- Patashu has joined.
08:34:13 -!- Patashu has quit (Remote host closed the connection).
08:35:02 -!- Patashu has joined.
08:40:20 -!- Phantom_Hoover has joined.
10:06:38 -!- boily has joined.
10:12:39 -!- hjulle has joined.
10:50:13 <fizzie> Short fungot break: electricity thing.
10:50:57 -!- fungot has quit (Remote host closed the connection).
10:51:11 -!- Phantom_Hoover has quit (Ping timeout: 250 seconds).
10:59:03 <mroman> Is <div/> valid HTML5?
11:00:04 <oren> um. maybe, but what would it be used for
11:00:38 <oren> ooh, colored rectangle?
11:02:10 <mroman> stuff like <div style="clear: both" />
11:02:23 <mroman> or <div style="width: 10px; background-color: red;" />
11:02:57 <int-e> apparently, "In HTML 5, <foo /> means <foo>"
11:03:42 <int-e> (from http://stackoverflow.com/questions/3558119/are-self-closing-tags-valid-in-html5 )
11:04:24 <oren> http://trevorjim.com/a-grammar-for-html5/
11:06:49 <int-e> so reading further that only goes vor void tags, so <div /> should be invalid.
11:07:48 <int-e> So I don't know. Need to read the spec...
11:14:25 <mroman> that should work right?
11:14:40 <mroman> so every div is one pixel wide except if you overwrite it in style
11:15:31 <mroman> and then <div style="width:1px;"></div> causes browsers to misrender
11:16:26 -!- oerjan has joined.
11:17:02 <mroman> it causes browsers to ignore the float:left
11:17:29 <mroman> div{float:left;height:1px;} together with <div style="width:1px"></div> works
11:18:02 <mroman> but adding width:1px; to the css in order to save space by not repeating style="width:1px" for all the divs causes the browser to ignore the float:left
11:30:45 <FireFly> uh, that sounds very weird
11:30:59 -!- boily has quit (Quit: NEUTRAL CHICKEN).
11:33:42 <mroman> FireFly: compare http://mroman.ch/output_ok.html with http://mroman.ch/output_wrong.html
11:33:50 <mroman> the only difference is the width:1px; in the CSS
11:34:13 <mroman> (wrong uses width:1px; in the CSS, but overwrites it in every div inside style)
11:35:08 <FireFly> Yeah, because you're also making the container div 1px wide
11:35:16 <FireFly> which wraps all the pixel-y divs
11:35:39 <FireFly> you could make it <div id="container">...</div> and then style #container > div
11:36:40 <mroman> that get's me down to 260KB
11:36:48 <FireFly> I think a table styled to have no border/padding would be slightly neater semantically
11:36:50 <mroman> (by using default width:1px)
11:37:23 <FireFly> you can use colspacing to run-length compress, akin to how you're using width
11:38:13 <FireFly> But it probably wouldn't save you much space (might save you a little bit since <td> is smaller than <div>, but then again you need <tr>'s around each row instead of the float hackery then
11:38:36 <FireFly> Actually hm, I wonder if <td> isn't one of the elements with implicit close tags
11:39:06 <mroman> using <p> sadly doesn't work
11:39:53 -!- AnotherTest has joined.
11:40:50 <FireFly> you could change background-color to just background
11:41:18 <FireFly> But then again, if your web server supports serving files compressed, none of this matters much at al
11:42:33 <FireFly> I suppose relying on JS or any existing image format would be out of the question?
11:43:01 <oerjan> today's xkcd: what kind of maniac puts vents in floors anyway
11:43:21 <mroman> it's gotta be pure HTML+CSS
11:43:43 <mroman> using JS would be much easier and shorter though.
11:43:56 <mroman> but not nearly as crazy as using HTML
11:45:51 <FireFly> You could histogram the elements after RLE and assign frequently-used colours dedicated classes since class="a" is shorter than style="background:#FF00FF"
11:46:13 <FireFly> You could use #F0F for e.g. #FF00FF which would help a tiny bit, too
11:46:59 <mroman> i'm reducing all colours to three char hexstrings already
11:47:09 <mroman> (not just FF00FF but all colors)
11:48:00 <FireFly> So you're not supporting full 24-bit colour output
11:48:21 <mroman> but this saves a few bytes :D
11:48:45 <mroman> but my linewise RLE already does that too
11:48:56 <mroman> a <div> per pixel is really a huge overhead :(
11:48:56 <FireFly> Oh, the RLE isn't lossless either?
11:49:00 -!- AnotherTest has quit (Ping timeout: 256 seconds).
11:49:14 <mroman> It has a color-delta it accepts as "same color"
11:49:26 <mroman> if(colourdiff(clr, img.getRGB(x+o, y)) < 20) {
11:49:34 <FireFly> With table/tr/td you could use rowspan/colspan to do "RLE" in both directions, but then it becomes trickier
11:49:54 <FireFly> i.e. you could compress a similarly-coloured rectangle into one element in the source
11:50:34 <mroman> that would be tricky but doable
11:51:54 <FireFly> Hm, is bgcolor deprecated, I wonder
11:53:16 <Jafet> oerjan: "it sounds annoying" also seems to be an unusually mild reaction to dropping a phone into a vent
11:54:48 <oren> I have vnts on the floors in my house but they are 40 cm deep and you could easily grab your phone
11:55:37 <oren> is this suppose to be a bottomless vertical vent?
11:56:10 <Jafet> It empties into the black void of space
11:59:24 <FireFly> Well it's clearly not bottomless if they're contemplating pouring water and/or mercury into it hoping to get the phone back
12:01:28 -!- zadock has quit (Quit: Leaving).
12:06:16 <Jafet> If you pointed a ring-shaped rocket engine down the rim of the bottomless vent, could the phone possibly be pushed back up the centre by aerodynamic pressure?
12:07:06 <oerjan> int-e: cake confirmed!
12:09:54 -!- HackEgo has joined.
12:12:04 -!- fungot has joined.
12:12:39 <fizzie> Funnily enough, I had nothing to do with the first thing.
12:12:48 <fizzie> That was the auto-rejoin functionality actually working for once.
12:12:58 <mroman> vaccinations are feared to cause autism but weed is ok
12:13:17 <mroman> nobody knows that weed is linked to developing schizophrenia, psychosis among other illnesses...
12:14:24 <oerjan> "linked" could mean correlation, not causation hth
12:15:07 -!- AnotherTest has joined.
12:15:09 <mroman> pretty much everything in psychiatry is correlation and statistics.
12:15:15 <Jafet> Hmm actually you can just point a jet engine through a funnel across the opening, lifting the phone out due to venturi effect
12:15:19 <mroman> because we no shit about it :)
12:15:36 <Jafet> (This may void the warranty)
12:16:40 <oerjan> Jafet: and dropping it down the vent in the first place doesn't?
12:18:19 <oerjan> i think if the vent were bottomless then the phone alarm would quickly cease to be a problem hth
12:20:09 <mroman> maybe turn off moving parts first.
12:26:54 <b_jonas> what I don't understand is how they can have a vent on the floor next to their bed in first place
12:40:01 <oren> My dad has one
12:40:34 <oren> Why can't they?
12:43:16 -!- Patashu has quit (Ping timeout: 265 seconds).
12:56:20 <FireFly> The edit distance between 'oren' and 'oerjan' is too low :(
12:56:28 <FireFly> I doesn't help that weechat decided to make both of you green
13:01:09 -!- mroman has changed nick to oerjen.
13:05:00 -!- oren has changed nick to oerein.
13:06:15 <oerein> Btw, I decided to make my ed mod actually check whther the syntax highlighter program exists
13:08:39 <oerein> because if it doesn't, then it gets confused and ouputs over 9000 ?
13:09:59 <Jafet> "These are your father's air vents"
13:15:59 -!- hamrove has joined.
13:17:46 <oerjan> an elegant system for a more civilized age
13:18:13 <oerjan> they go straight down to the reactor core hth
13:23:35 <oerjen> oerein: change that to 9999 and you're good.
13:29:42 -!- AnotherTest has quit (Ping timeout: 256 seconds).
13:41:40 -!- `^_^v has joined.
13:50:13 -!- MDream has changed nick to MDude.
13:58:49 -!- spatterworthy has joined.
14:00:07 <oerein> anyway I think the builders of this house were trying to save on ductwork
14:00:52 <oerein> if the furnace is in the basement, then having the vents on the floor reduces th4e distance
14:02:29 <oerein> although I think the house originally (in ～) had
14:02:58 <oerein> fireplaces in every room
14:04:31 <FireFly> I had to disable the nickchange/join/part/quit filter to see what was going on..
14:06:15 <oerjen> fungot: are you confused?
14:06:16 <fungot> oerjen: pwm is something you can go get dinner. thanks, dmg?
14:06:30 <oerjen> fungot: it's not dinner time yet.
14:06:30 <fungot> oerjen: implementing an event loop. :) heh.
14:07:08 <fungot> oerjen: i often do that; do other people?
14:17:11 -!- ChanServ has set channel mode: +o oerjan.
14:17:35 -!- oerjan has set channel mode: +q oer*!*@*.
14:17:43 <oerjan> lessee if this works hth
14:17:47 -!- oerjan has set channel mode: -o oerjan.
14:18:02 -!- GeekDude has joined.
14:21:40 -!- Koen_ has joined.
14:30:24 <oerjan> (you may have to leave the channel to change nick hth)
14:32:24 -!- oerein has quit (Quit: ivan polkka).
14:33:15 -!- oren has joined.
14:37:15 -!- oerjen has left.
14:37:22 -!- mroman has joined.
14:37:26 <mroman> That's abuse of power!
14:37:35 <mroman> fungot: oerjan is being mean.
14:37:36 <fungot> mroman: i thought it looked really cool in the works natively sense, seeing how much else i know.
14:38:15 <oren> https://www.youtube.com/watch?v=kbbA9BhCTko
14:38:27 <oerjan> mroman: my brain had trouble remembering who was who hth
14:40:02 -!- Sprocklem has joined.
14:40:59 -!- FanFL has joined.
14:41:20 <oerjan> oren: needs to work on her finnish hth
14:42:44 -!- FanFL has quit (Client Quit).
14:53:26 <oren> https://www.youtube.com/watch?v=0OZyleriwRU
14:57:27 <oren> What happens if you try to write into a pipe whn the buffers full?
15:03:46 <oren> I wrote useless code to manually wait, which will never actually execute
15:04:38 -!- Vorpal has quit (Ping timeout: 264 seconds).
15:06:58 -!- Vorpal has joined.
15:07:29 <oerjan> oren: there's probably a non-blocking write if you really want it....
15:08:05 <oerjan> this is C where everything can fail, isn't it.
15:08:14 * oerjan should leave this to the experts.
15:12:34 -!- Koen_ has quit (Quit: The struct held his beloved integer in his strong, protecting arms, his eyes like sapphire orbs staring into her own. "W-will you... Will you union me?").
15:29:50 -!- hjulle has quit (Ping timeout: 256 seconds).
15:37:10 <shachaf> When you say e.g. "an integer x s.t. x+2=4", " s.t
15:37:24 <shachaf> " stands for "sigma type".
16:05:59 -!- hamrove has quit (Quit: hamrove).
16:17:14 <oren> s.t.? subject to
16:17:47 <izabera> Linux notebook 4.0.1-1-ARCH #1 SMP PREEMPT Wed Apr 29 12:00:26 CEST 2015 x86_64 GNU/Linux
16:18:07 <HackEgo> Linux umlbox 3.13.0-umlbox #1 Wed Jan 29 12:56:45 UTC 2014 x86_64 GNU/Linux
16:18:43 <oren> Linux oren-X501A1 3.13.0-46-generic #79-Ubuntu SMP Tue Mar 10 20:06:50 UTC 2015 x86_64 x86_64 x86_64 GNU/Linux
16:19:09 <oren> Wait,why do I have x86-64 thrice
16:20:48 <oerjan> izabera: HackEgo's vps is pretty crappy
16:21:04 <HackEgo> Architecture: x86_64 \ CPU op-mode(s): 32-bit \ Byte Order: Little Endian \ CPU(s): 1 \ On-line CPU(s) list: 0 \ Thread(s) per core: 1 \ Core(s) per socket: 1 \ Socket(s): 1 \ Vendor ID: User Mode Linux \ BogoMIPS: 1744.89 \ Hypervisor vendor: VMware \ Virtua
16:21:04 <oerjan> (it also runs the wiki)
16:21:49 <oren> `` lscpu | tail
16:21:50 <HackEgo> Byte Order: Little Endian \ CPU(s): 1 \ On-line CPU(s) list: 0 \ Thread(s) per core: 1 \ Core(s) per socket: 1 \ Socket(s): 1 \ Vendor ID: User Mode Linux \ BogoMIPS: 1305.80 \ Hypervisor vendor: VMware \ Virtualization type: full
16:22:54 <oerjan> oren: pretty sure s.t. in that context means "such that"
16:23:31 <oren> I thought it meant subject to [the restriction that]
16:24:19 <oren> but such that does make sense
16:24:51 <oerjan> hm i suppose both work
16:25:04 <shachaf> the usual meaning is "such that" hth
16:25:18 -!- spatterworthy has quit (Quit: Page closed).
16:25:42 <izabera> http://www.urbandictionary.com/define.php?term=TDNH
16:28:07 <izabera> why doesn't this work? cat file | { head; tail; }
16:28:14 <izabera> this does: { head; tail; } < file
16:28:34 <izabera> in the former, tail doesn't print anything
16:28:51 <int-e> oerjan: please take note of https://clientarea.ramnode.com/announcements.php?id=394 and don't panic if lambdabot disappears for a bit!
16:28:53 <izabera> i know it has something to do with the fact that the latter is seekable but i don't really understand it
16:30:36 <int-e> izabera: head has already consumed all the input from stdin; there's nothing left for tail to read when it finally gets the chance.
16:31:07 <int-e> the second case is more interesting. let's see
16:31:22 <oerjan> int-e: A. AAA. AAAAA? AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA
16:31:45 <int-e> izabera: if the input is a file, 'tail' uses lseek to find its size...
16:31:55 <shachaf> Your explanation about seeking would seem to explain it?
16:32:38 <izabera> tail must know that it's a stream
16:33:39 <oerjan> < file doesn't make it fully a stream, i assume
16:33:51 <oerjan> the fd still points to a file rather than a pipe
16:34:12 <izabera> the other one, i don't >.<
16:34:46 <oerjan> while ... | ... produces a non-seekable stream
16:35:55 <int-e> izabera: Actually my explanation for the first case is wrong. It's bound to be buffering. (for me, `head` reads a 8kiB chunk)
16:38:07 <int-e> izabera: it even tries to fix it, note the first lseek call: http://sprunge.us/RaXi
16:38:47 <int-e> uh, I copied more that I wanted...
16:39:10 <int-e> http://sprunge.us/diOi is sufficient
16:39:52 -!- variable has joined.
16:40:18 <int-e> `` seq 5000 | (head > /dev/null; tail)
16:40:28 <HackEgo> 4991 \ 4992 \ 4993 \ 4994 \ 4995 \ 4996 \ 4997 \ 4998 \ 4999 \ 5000
16:40:34 <int-e> `` seq 50 | (head > /dev/null; tail)
16:46:03 <oerjan> > length . unwords $ map show [1..4990]
16:46:25 <int-e> I erred on the safe side.
16:47:04 <int-e> > length . unlines $ map show [1..4990]
16:47:05 <oerjan> yes but you got ridiculously close
16:47:36 <oerjan> it doesn't look particularly round
16:48:54 <oerjan> `` seq 5000 | (head > /dev/null; cat)
16:48:55 <HackEgo> \ 1861 \ 1862 \ 1863 \ 1864 \ 1865 \ 1866 \ 1867 \ 1868 \ 1869 \ 1870 \ 1871 \ 1872 \ 1873 \ 1874 \ 1875 \ 1876 \ 1877 \ 1878 \ 1879 \ 1880 \ 1881 \ 1882 \ 1883 \ 1884 \ 1885 \ 1886 \ 1887 \ 1888 \ 1889 \ 1890 \ 1891 \ 1892 \ 1893 \ 1894 \ 1895 \ 1896 \ 1897 \ 1898 \ 1899 \ 1900 \ 1901 \ 1902 \ 1903 \ 1904 \ 1905 \ 1906 \ 1907 \ 1908 \ 1909 \ 1
16:49:19 <oerjan> > length . unlines $ map show [1..1860]
16:52:00 <int-e> > 999 + (8192 - (2*9 + 3*90 + 4*900) + 4) `div` 5 -- tedious
16:53:06 <int-e> > 999 - (2*9 + 3*90 + 4*900 - 8192) `div` 5
16:54:33 <int-e> > -(8192 + 9 + 99 + 999) `div` 5
16:54:47 <int-e> > -(-(8192 + 9 + 99 + 999)) `div` 5
16:58:53 <int-e> What's up with all those gates... this is getting silly. Tattogate, seriously?
17:23:20 -!- zadock has joined.
17:27:25 -!- mitchs has joined.
17:29:14 -!- mitchs_ has quit (Ping timeout: 264 seconds).
17:29:25 -!- variable has quit (Ping timeout: 250 seconds).
17:32:41 <oren> my favorite gate was shirtgate, in which a short with sexy ladies (drawn by a lady) caused a firestorm of people who said it was sexist
17:32:55 <oren> s/short/shirt/
17:34:49 <J_Arcane> stupid functional nerds and their hyperclever data structures i don't understand
17:35:44 -!- mitchs has quit (Ping timeout: 250 seconds).
17:36:50 <oren> Eh, at least it's not perl where the data structure is implicitly created by usage
17:38:09 -!- Phantom_Hoover has joined.
17:38:39 -!- Sprocklem has quit (Ping timeout: 264 seconds).
17:43:50 <oerjan> J_Arcane: you find yourself trapped in a branch of a finger tree, indexed by an Endo monoid...
17:46:30 <oerjan> hm could you replace the monoid by a category? me and elliott once figured out how to replace the _contents_ that way.
17:47:08 <oerjan> also, if you do that, is it redundant to distinguish index and content?
17:47:37 -!- mitchs has joined.
18:02:09 -!- Phantom_Hoover has quit (Ping timeout: 245 seconds).
18:25:10 -!- zadock has quit (Quit: Leaving).
18:31:48 <oren> #define REM //
18:34:20 -!- zadock has joined.
18:39:17 -!- nycs has joined.
18:40:03 -!- `^_^v has quit (Ping timeout: 250 seconds).
18:56:55 <oren> hmm apparently comments happen before #defines
19:04:29 <oren> #define Um del(
19:04:53 <oren> #define del(x)
19:05:15 <oren> int x=3.14; Um, this is pi, lol
19:08:40 <J_Arcane> Clojure XML support sucks, and the zipper library that's supposed to make it 'easier' literally doesn't work.
19:13:56 <myname> oren: i'd say "lol" -> del( and "^^" -> )
19:14:28 <FireFly> I don't think you can define ^^ though
19:15:39 -!- nortti has quit (Quit: was told to leave ;_;).
19:15:49 -!- nortti has joined.
19:20:25 <oren> could you not just use one of Java's XML thingies?
19:20:27 -!- GeekDude has quit (Ping timeout: 256 seconds).
19:21:53 -!- zadock has quit (Quit: Leaving).
19:42:16 -!- oerjan has quit (Quit: THINGIES).
20:12:26 -!- lleu has joined.
20:12:53 -!- spatterworthy has joined.
20:18:53 <Vorpal> fizzie, see lambdabot message
20:26:15 -!- Phantom_Hoover has joined.
20:32:52 -!- hamrove has joined.
20:49:25 <S0lll0s> what OOP-ish concept would you guys recommend?
20:49:37 <S0lll0s> for easy implementation and a small feature set
20:49:49 <S0lll0s> I'm thinking something like Lua tables but I'm not sure yet
21:00:07 -!- MDude has quit (Ping timeout: 265 seconds).
21:07:08 <Vorpal> S0lll0s, not sure how they work. What about prototype based like js though?
21:07:23 <Vorpal> Or perhaps a more traditional vtable thing like C++
21:07:42 <Vorpal> I guess duck typing like python is quite easy too
21:07:53 <Vorpal> At least in a scripting language
21:08:44 <Vorpal> I think most concepts can be quite simple when scaled down and extra features are removed
21:08:53 <Vorpal> (you don't need python style metaclasses for example)
21:10:12 -!- bb010g has quit (Quit: Connection closed for inactivity).
21:17:27 -!- ais523 has joined.
21:17:58 <ais523> haven't seen you talk here for a while
21:18:19 <FireFly> Lua's tables are also prototype-based, but more "purely" so than JS
21:18:49 -!- nycs has quit (Quit: This computer has gone to sleep).
21:21:00 -!- atrapado has joined.
21:30:25 <Taneb> Starting a local Haskell meetup group was a good idea
21:48:19 <S0lll0s> Vorpal: in Lua things are just hashtables
21:48:36 <S0lll0s> but you can set a few extra "options" like a hashtable to look up missing entries in
21:48:51 <S0lll0s> or something to call whenever a key is added
21:49:15 <S0lll0s> and then there is syntactic sugar for calling a function stored in a table with that table as the first parameter
21:53:08 <fizzie> @tell Vorpal Maybe it was some sort of a Dropbox fluke, it loaded for me now.
21:55:49 -!- Frooxius has joined.
21:59:09 -!- boily has joined.
22:09:14 -!- spiette has quit (Ping timeout: 248 seconds).
22:11:03 -!- ais523 has quit (Read error: Connection reset by peer).
22:11:15 -!- ais523 has joined.
22:17:12 -!- variable has joined.
22:23:21 -!- atrapado has quit (Quit: Leaving).
22:28:15 <S0lll0s> I think I'll just go with the Lua style
22:28:32 <S0lll0s> also skipping arrays, Lua tables are the most simplistic I can think of
22:28:52 <S0lll0s> and anything more complex is easily integrated on top of them
23:04:31 <HackEgo> [wiki] [[Fish]] M http://esolangs.org/w/index.php?diff=42775&oldid=42772 * 0x0dea * (+47) Document the # mirror.
23:07:08 -!- ^v has joined.
23:10:31 -!- v4s has quit (Ping timeout: 256 seconds).
23:10:58 -!- lambdabot has quit (Ping timeout: 276 seconds).
23:11:05 -!- erdic has quit (Ping timeout: 272 seconds).
23:12:23 -!- erdic has joined.
23:15:42 -!- v4s has joined.
23:20:29 -!- lambdabot has joined.
23:36:19 -!- MDude has joined.
23:39:26 -!- heroux has quit (Ping timeout: 264 seconds).
00:05:40 -!- ais523 has quit.
00:50:07 -!- hamrove has quit (Quit: hamrove).
00:55:18 -!- Phantom_Hoover has quit (Read error: Connection reset by peer).
01:11:04 -!- boily has quit (Quit: OUTER CHICKEN).
02:03:28 -!- hamrove has joined.
02:39:38 -!- MDude has quit (Ping timeout: 245 seconds).
02:44:30 -!- MDude has joined.
02:49:59 -!- spatterworthy has quit (Ping timeout: 246 seconds).
03:31:03 -!- hamrove has quit (Quit: hamrove).
03:32:37 -!- variable has changed nick to constant.
03:33:28 -!- hamrove has joined.
03:43:50 -!- bb010g has joined.
04:20:54 -!- MDude has changed nick to MDream.
04:55:10 -!- ent0nces has joined.
05:05:48 -!- ent0nces has quit (Ping timeout: 256 seconds).
05:09:43 -!- ^v has quit (Read error: Connection reset by peer).
05:11:20 -!- paul2520 has quit (Ping timeout: 255 seconds).
05:24:30 -!- paul2520 has joined.
05:24:47 -!- paul2520 has changed nick to Guest26818.
06:25:00 -!- tromp__ has joined.
06:25:52 <HackEgo> [wiki] [[Fish]] http://esolangs.org/w/index.php?diff=42776&oldid=42775 * 0x0dea * (-122) Replace FizzBuzz example with a stack-clean, terminating implementation.
06:27:23 -!- tromp_ has quit (Ping timeout: 255 seconds).
06:44:50 <lambdabot> LOWI 300620Z VRB02KT 6000 RA FEW005 SCT008 BKN020 08/07 Q1019 NOSIG
07:03:59 -!- Sgeo_ has joined.
07:07:20 -!- Sgeo__ has quit (Ping timeout: 272 seconds).
07:12:24 -!- mitchs has quit (Read error: Connection reset by peer).
07:12:51 -!- mitchs has joined.
07:37:35 -!- constant has quit (Ping timeout: 244 seconds).
07:49:46 -!- mitchs has quit (Quit: mitchs).
08:01:13 -!- mitchs has joined.
08:02:56 -!- tr00p has joined.
08:03:14 <tr00p> so... I am proud of myself
08:03:16 <tr00p> http://lpst.tk/?LqkL
08:07:28 <HackEgo> [wiki] [[Newton]] M http://esolangs.org/w/index.php?diff=42777&oldid=40024 * Vriskanon * (+62) Added cat program. The instructions are unclear so I guessed some information.
08:15:57 <mroman> Lua's OOP is hashtables, right?
08:19:17 -!- hamrove has quit (Quit: hamrove).
08:27:56 -!- heroux has joined.
08:30:47 -!- rodgort` has quit (Ping timeout: 265 seconds).
08:31:46 -!- idris-bot has quit (Quit: Terminated).
08:32:02 -!- idris-bot has joined.
08:40:38 -!- Patashu has joined.
08:48:21 -!- tromp_ has joined.
08:48:39 -!- tromp__ has quit (Ping timeout: 256 seconds).
08:49:00 -!- rodgort has joined.
09:02:35 <mroman> Is a stack + three registers enough for TC?
09:05:49 -!- mitchs has quit (Read error: Connection reset by peer).
09:06:15 -!- mitchs has joined.
09:12:12 <fizzie> Are they registers of unbounded size? I mean, two-counter Minsky machine.
09:13:06 <fizzie> If they're bounded, then I would guess no, since it's just "stack + more finite states" then.
09:28:24 -!- Phantom_Hoover has joined.
09:30:46 <mroman> I fiddling around with decimally encoded opcode/args and stuff
09:51:20 <Jafet> Boring completeness imo
09:56:47 -!- FreeFull has quit (Quit: Rebooting into new kernel).
09:59:36 -!- FreeFull has joined.
10:23:10 -!- boily has joined.
11:12:53 <myname> why is a queue sufficient?
11:21:36 -!- boily has quit (Quit: RETROCOMPATIBLE CHICKEN).
11:33:25 <mroman> Queues are self-sufficient.
11:58:13 -!- ais523 has joined.
12:17:16 <Jafet> Boring-complete languages based on queues exist, such as cyclic tag
12:24:48 <mroman> the opposite of fun-complete
12:27:44 -!- Patashu has quit (Ping timeout: 240 seconds).
12:31:20 -!- HackEgo has quit (Remote host closed the connection).
12:35:34 -!- oerjan has joined.
12:52:51 -!- copumpkin has quit (Quit: My MacBook Pro has gone to sleep. ZZZzzz…).
12:53:07 -!- copumpkin has joined.
12:54:48 -!- contrapumpkin has joined.
12:57:59 -!- copumpkin has quit (Ping timeout: 256 seconds).
13:02:43 -!- ais523 has quit.
13:08:23 <FireFly> mroman: they're map/table structures, but I don't know if the reference manual says whether they're strictly hashtables or not
13:09:35 <FireFly> No mention of 'hash' in http://www.lua.org/manual/5.2/manual.html at least
13:14:38 <mroman> can you do python-like stuff?
13:14:55 -!- ais523 has joined.
13:23:25 <mroman> At least Lua is better than JavaScript
13:23:39 <mroman> and that assumption is based solely on knowing JavaScript.
13:26:51 -!- `^_^v has joined.
13:30:57 -!- ais523 has quit.
13:42:15 -!- ais523 has joined.
13:43:23 -!- oren has quit (Ping timeout: 244 seconds).
13:45:34 -!- villasukka has quit (Remote host closed the connection).
13:45:34 -!- atehwa has quit (Read error: Connection reset by peer).
13:59:14 -!- ais523 has quit.
14:35:14 <MDream> After using both Lua and Javacript, so far I've liked how canvas works.
14:35:19 -!- MDream has changed nick to MDude.
14:37:08 <MDude> But I also haven't used Love2D because I don't like how it expects you to make fake .exes by renaming a zip before running ti through some process and then renaming it again.
14:38:06 <MDude> If it's not going to let actual compilation then at least let let Love2D be something that itself doens't require installation.
14:39:34 <MDude> And somethiing where for a program to use it, it can just be in a subfolder under Love2Dprogs or something.
14:41:53 <MDude> The canvas functions for graphical interfaces, I mean, I mean.
14:42:29 <MDude> Lua and Javascript both seem pretty usable to me in their current state.
14:44:04 <MDude> I don't actually use other languages much though, just read about them.
14:44:45 <mroman> Löve2D at least has some physics.
14:46:17 <MDude> I like describing physics myself, it's just the hardware interface I want simple.
14:49:58 <J_Arcane> MDude: Have you seen PICO8? ;)
14:50:24 -!- GeekDude has joined.
15:04:31 <MDude> No, or if I did I mistook it for CHIP-8. This virtual cartridge thing seems like exactly what I wanted for Lua.
15:04:52 -!- oren has joined.
15:47:24 <MDude> Unfortunatly I see no way to actually download it?
15:48:38 <MDude> You need to register for Voxatron, but there's not even an option to download Voxatron.
15:53:58 -!- g2watson_ has quit (Remote host closed the connection).
15:54:35 <oerjan> you need to go to Dagobah to find the sole surviving Voxatron user hth
16:08:19 -!- mitchs_ has joined.
16:10:30 -!- hjulle has joined.
16:10:45 -!- hamrove has joined.
16:11:47 -!- mitchs has quit (Ping timeout: 256 seconds).
16:14:15 -!- password2 has joined.
16:15:38 -!- password2 has quit (Max SendQ exceeded).
16:16:37 -!- password2 has joined.
16:17:17 -!- hjulle has quit (Ping timeout: 276 seconds).
16:25:24 <FireFly> mroman: yup, there are metamethods for overloading operators (__gt etc)
16:27:39 <FireFly> PICO-8 looks interesting... hm
16:34:29 * oerjan ogles oren after whistling ievan polkka for the nth time ಠ_ಠ
16:36:16 <oerjan> also after watching too many versions including finnish a capella, finnish lumberjacks and the wiener sängerknaben.
16:36:45 <oerjan> oh and some asian ocarina playing ladies
16:45:22 -!- hamrove has quit (Quit: hamrove).
16:50:41 <oren> https://www.youtube.com/watch?v=znxPpH2MuR4
16:53:34 * oerjan feels a vague breeze from something passing way over his head.
16:54:45 <oerjan> it must be this newfangled tech gnome music
16:56:01 <oren> Ya, imma TeX gnome!
17:05:19 * int-e eyes oren suspiciously
17:07:51 <int-e> http://thread.gmane.org/gmane.linux.kernel/1930358/focus=1939166 ... I wonder if this will be the death of kdbus
17:12:42 <oerjan> has anyone made a potato computer yet
17:24:04 -!- atrapado has joined.
17:29:07 <int-e> (fwiw, lambdabot runs on a systemd-free (but not dbusd-free) system...)
17:29:37 <int-e> (uevent needs dbus, right? sigh.)
17:29:56 <b_jonas> oerjan: what do you mean by potato computer?
17:30:04 <oerjan> b_jonas: see int-e's link
17:30:32 <int-e> I'm waiting for the day that a major distribution ships a systemd update that bricks a ton of computers (making them unable to boot, not even in some sane recovery mode).
17:30:54 <b_jonas> int-e: they have already done that
17:31:10 <J_Arcane> oerjan: https://web.archive.org/web/20000815202656/http://world.std.com/~fwhite/spud/
17:31:48 <oerjan> J_Arcane: those are potato batteries not computers hth
17:33:46 <int-e> Is there any *simple* dependency based init daemon that just tries to be that without wanting to take over the whole system and desktop as well? Ideally smaller than sysvinit (init.c has almost 3k lines of code...)
17:34:50 <int-e> The main point is it should have a *fixed* set of features, so it has a chance to mature and shed its bugs...
17:35:03 <b_jonas> int-e: I don't understand why init would have to handle the dependencies. couldn't that be in a separate process which init just starts at every runlevel change?
17:35:54 <int-e> b_jonas: it doesn't have to be init. but if I reduce init to spawning a single process then I can just as well use that process as init
17:36:43 <b_jonas> int-e: no, init would still handle respawning the getty on the consoles, and waiting for whatever way telinit tells init to change runlevel
17:36:59 <b_jonas> but the separate process would handle which scripts to start, dependency-based, when you change runlevel
17:37:02 -!- Tod-Autojoined has joined.
17:37:02 -!- Phantom__Hoover has joined.
17:37:11 -!- int-e_ has joined.
17:37:24 <b_jonas> with ideally a clean interface between the two so they're modular, you can replace one or the other with a newer version
17:37:57 <b_jonas> plus init would still have to handle waiting on orphans of course
17:38:46 <b_jonas> (you don't really have a choice about that part)
17:39:11 -!- int-e has quit (Disconnected by services).
17:39:17 -!- int-e_ has changed nick to int-e.
17:40:44 <int-e> Note that I'm musing, I have no clear picture of the requirements... But going on regardless, so how does init communicate that a runlevel changes ... if it happens in the middle taking care of a runlevel change?
17:41:55 <int-e> (I also have to admit that I don't particularly like sysvinit. It does me no harm, since it won't get in my way, but we're not friends.)
17:44:32 <int-e> I guess basically I'm appalled at the feature creep that systemd shows and am wondering what a viable alternative (i.e. one that distributions would be willing to adopt) would look like.
17:45:28 -!- Lymee has joined.
17:46:46 -!- Guest69966 has quit (*.net *.split).
17:46:46 -!- TodPunk has quit (*.net *.split).
17:46:47 -!- Phantom_Hoover has quit (*.net *.split).
17:46:47 -!- sebbu has quit (*.net *.split).
17:46:47 -!- Lymia has quit (*.net *.split).
17:46:47 -!- Sgeo_ has quit (*.net *.split).
17:46:47 -!- olsner has quit (*.net *.split).
17:46:53 -!- Lymee has changed nick to Lymia.
17:49:29 -!- Sgeo_ has joined.
17:49:29 -!- olsner has joined.
17:53:29 -!- Guest69966 has joined.
17:53:45 <int-e> I guess I shall have a serious look at upstart.
18:01:29 <shachaf> How easy is it to decide whether the intersection of regular expressions is empty?
18:01:41 -!- sebbu has joined.
18:02:18 -!- sebbu has quit (Changing host).
18:02:18 -!- sebbu has joined.
18:06:01 <oerjan> shachaf: there's an exponential blowup on converting it to a DFSA, from there it's relatively trivial...
18:06:44 <shachaf> oerjan: yes, but can you better twh
18:07:05 <shachaf> your solution works for just about any question i'd want to ask about regular expressions
18:07:48 <oerjan> someone's probably researched this
18:08:37 <oerjan> do you actually _need_ that conversion.
18:09:38 <oerjan> i cannot see why. just pair the NFSA states.
18:09:43 <oerjan> shachaf: ok i think it's simpler.
18:10:33 <oerjan> convert to NFSA instead, no exponential blowup given regular expressions in the original sense
18:11:05 <oerjan> then pair all states and do a path reachability test
18:11:26 <oerjan> this should be polynomial.
18:13:55 <oerjan> (no guarantee on the last statement)
18:15:08 <oerjan> as long as you're not silently giggling to yourself
18:15:40 <shachaf> silently giggling to myself sounds good to me
18:15:49 <oerjan> thought so. now food ->
18:48:17 -!- coppro has quit (Quit: leaving).
18:48:54 -!- coppro has joined.
19:07:12 -!- boily has joined.
19:07:19 -!- MDude has quit (Ping timeout: 244 seconds).
19:12:05 <boily> oerjan: boerjanjour!
19:14:49 <boily> AAAAAAAAAAAAAAAAAAAAURGH!
19:15:08 <oerjan> 's ok go listen to ievan polkka instead
19:16:44 <boily> Nupurista koolu se polokan ta ti ♪
19:17:35 <oerjan> nothing like a shared earworm
19:17:46 * oerjan now imagines something gross
19:21:12 <boily> splitting an earworm is like generating a new apple through Bananach-Tarski.
19:23:14 <oerjan> with sufficiently bad apples, those may be part of the same process
19:23:38 -!- hamrove has joined.
19:31:49 -!- Guest26818 has quit (Ping timeout: 256 seconds).
19:31:49 -!- b_jonas has quit (Ping timeout: 256 seconds).
19:32:18 -!- Guest26818 has joined.
19:33:13 -!- atrapado has quit (Ping timeout: 256 seconds).
19:33:13 -!- trn has quit (Ping timeout: 256 seconds).
19:33:29 -!- b_jonas has joined.
19:34:35 -!- trn has joined.
19:51:34 -!- atrapado has joined.
19:51:45 -!- password2 has quit (Ping timeout: 244 seconds).
19:59:35 -!- variable has joined.
20:06:21 -!- variable has changed nick to trout.
20:10:10 <J_Arcane> http://pasterack.org/pastes/55501
20:20:16 -!- bb010g has quit (Quit: Connection closed for inactivity).
20:32:43 -!- ^v has joined.
21:01:36 -!- Patashu has joined.
21:07:18 -!- oerjan has quit (Quit: Hm).
21:11:35 -!- roasted42 has joined.
21:13:26 -!- roasted42 has quit (Changing host).
21:13:27 -!- roasted42 has joined.
21:13:27 -!- roasted42 has changed nick to TheM4ch1n3.
21:14:07 <FireFly> <oerjan> also after watching too many versions including finnish a capella, finnish lumberjacks and the wiener sängerknaben. ← oh, I wasn't the only one doing that
21:16:59 <FireFly> This version of Ievan Polkka is nice, too: https://www.youtube.com/watch?v=O79kyDNiBqQ
21:17:20 -!- AnotherTest has joined.
21:18:44 <boily> FirelloFly. nice find!
21:20:18 <boily> (what the fungot is that character: 甩)
21:20:19 <fungot> boily: check back in a couple of the peppers to build up
21:20:27 <boily> fungot: I highly doubt it's a pepper.
21:20:27 <fungot> boily: will do. the player works... fnord... i'd better don't try then.
21:20:46 <boily> fungot: nope. ain't trying that on that se.
21:20:46 <fungot> boily: or is failing. i felt so clever when i started to work on my own
21:21:13 <shachaf> FireFly: i would listen to it if i had headphones hth
21:21:44 <boily> fungot: sorry. it's not a se, it's a guzheng. but good practice to you!
21:21:45 <fungot> boily: there is port to freebsd and so on
21:21:55 <FireFly> boily: sadly I don't know chinese
21:22:10 <boily> fungot: I didn't know I could play Chinese stringed instruments on freebsd.
21:22:30 <boily> FireFly: I wikipediaed the stuff.
21:22:43 <shachaf> FireFly: have you considered changing your nick to HugFly
21:22:55 -!- hamrove has quit (Quit: hamrove).
21:24:34 -!- Patashu has quit (Ping timeout: 256 seconds).
21:25:42 <FireFly> I prefer GHC over hugs to be honest
21:26:10 <shachaf> you prefer a haskell implementation to hugs?
21:26:37 <FireFly> I prefer one haskell implementation over another
21:31:26 -!- TheM4ch1n3 has quit (Quit: leaving).
21:31:48 -!- roasted42 has joined.
21:31:48 -!- roasted42 has quit (Changing host).
21:31:48 -!- roasted42 has joined.
21:31:48 -!- roasted42 has changed nick to TheM4ch1n3.
21:39:36 <AnotherTest> mroman: I noticed your question on crypto stack exchange
21:40:22 <AnotherTest> there doesn't seem to be an obvious security flaw in the scheme, but I think a simple XOR would be easier
21:40:55 <AnotherTest> (also, it would be faster and the keyspace would be larger)
21:49:47 -!- AnotherTest has quit (Remote host closed the connection).
21:55:33 -!- atrapado has quit (Quit: Leaving).
21:56:09 -!- `^_^v has quit (Ping timeout: 255 seconds).
22:16:44 -!- tr00p has quit (Ping timeout: 276 seconds).
22:19:14 -!- tr00p has joined.
22:54:45 -!- MDude has joined.
23:11:57 -!- idris-bot has quit (Quit: Terminated).
23:12:14 -!- idris-bot has joined.
23:22:09 -!- lleu has quit (Read error: Connection reset by peer).
23:27:30 -!- tr00p has quit (Ping timeout: 255 seconds).
23:28:04 <quintopia> whats the utility of a karma system which allows users to downvote their own posts?
23:36:23 -!- tr00p has joined.
23:44:59 -!- S1 has joined.
23:50:55 -!- hilquias has joined.