2017-08-01: 00:27:41 `unidecode ߷ 00:27:42 ​[U+07F7 NKO SYMBOL GBAKURUNEN] 00:28:52 -!- https_GK1wmSU has joined. 00:31:18 -!- https_GK1wmSU has left. 00:37:52 -!- Jafet has quit (Ping timeout: 246 seconds). 00:42:18 -!- Warrigal_ has joined. 00:55:08 -!- Jafet has joined. 00:58:05 -!- Jafet has quit (Read error: Connection reset by peer). 00:59:02 -!- Jafet has joined. 01:04:13 [wiki] [[Special:Log/newusers]] create * Periapsis * New user account 01:06:03 -!- Jafet has quit (Read error: Connection reset by peer). 01:07:46 -!- Jafet has joined. 01:15:02 [wiki] [[Esolang:Introduce yourself]] https://esolangs.org/w/index.php?diff=52610&oldid=52602 * Periapsis * (+247) 01:15:49 [wiki] [[Joke language list]] https://esolangs.org/w/index.php?diff=52611&oldid=52437 * Periapsis * (+16) /* Brainfuck derivatives */ 01:18:55 -!- z0d has quit (Remote host closed the connection). 01:22:55 -!- Jafet has quit (Read error: Connection reset by peer). 01:25:26 -!- Jafet has joined. 01:36:31 -!- Jafet has quit (Read error: Connection reset by peer). 01:37:36 -!- Jafet has joined. 01:38:08 Is this language any good? https://winworldpc.com/product/actor 01:39:18 "Actor is an object oriented Smalltalk-like programming language for Windows 3.1. 01:39:18 Interestingly, an earlier version of Actor ran on Windows 2.1!" 01:40:33 -!- Jafet has quit (Read error: Connection reset by peer). 01:41:05 -!- Jafet has joined. 01:45:56 [wiki] [[BrainGuck]] N https://esolangs.org/w/index.php?oldid=52612 * Periapsis * (+694) Created page with "BrainGuck is an esoteric language created by [[User:Periapsis]]. It was inspired by [https://esolangs.org/wiki/Brainfuck#Language_overview BrainFuck]. It adds a few extra comm..." 01:51:22 [wiki] [[BrainGuck]] https://esolangs.org/w/index.php?diff=52613&oldid=52612 * Periapsis * (+0) 01:56:14 -!- Jafet has quit (Read error: Connection reset by peer). 01:57:42 -!- Jafet has joined. 02:02:42 -!- Jafet has quit (Read error: Connection reset by peer). 02:05:31 -!- Jafet has joined. 02:06:25 -!- Warrigal_ has quit (Ping timeout: 246 seconds). 02:07:27 -!- Jafet has quit (Read error: Connection reset by peer). 02:08:49 -!- Jafet has joined. 02:20:40 -!- imode has joined. 02:24:59 -!- Jafet has quit (Read error: Connection reset by peer). 02:25:46 -!- Jafet has joined. 02:30:02 -!- hppavilion[1] has joined. 02:31:00 `smlist 455 02:31:01 smlist 455: shachaf monqy elliott mnoqy Cale 02:31:08 ooh 02:31:40 Cale: you're supposed to ooh over olists 02:32:02 Super Mega Comics℠ 02:32:10 Super Mega℠ 02:32:20 -!- Jafet has quit (Ping timeout: 260 seconds). 02:32:26 What is olist? 02:32:32 `? olist 02:32:33 olist is update notification for the webcomic Order of the Stick. http://www.giantitp.com/comics/ootslatest.html 02:33:01 ah, I haven't gotten into that one yet 02:33:21 It's a good time for it! 02:33:53 It's just you have to read past the first hundred or so before it turns into much of anything. 02:34:45 -!- Jafet has joined. 02:43:07 `randquote Cale 02:43:24 1116) I do sometimes work on Linux computer. I think it is set to en.UTF-8 by default although on my account I have changed it to the C locale, disabled Unicode translation, and loaded a CP437 font. This improves the operation of the system. 02:43:43 `randquote 02:43:44 No output. 02:43:48 @quote Cale 02:43:48 Cale says: One can create powerful abstractions in C++ in much the same way that a woman can produce a child. It's possible, and people do it, but it takes hours of labour and is extremely painful. 02:44:13 Cale: Do you like the new C++ metaclasses proposal? 02:46:17 I dunno, I kinda stopped caring about how good/shitty C++ is. 02:46:48 It's probably better just not to touch it at all. 02:46:57 This new proposal is wonderfully complex. 02:47:03 For fear that you can only make things worse 02:47:04 C++ is going to be so complicated. 02:47:07 It's great. 02:47:09 haha 02:47:28 Anyway there are still not many competitor to C++ 02:47:41 There's a lot of software that I'd probably still use C++ to write today? 02:54:22 -!- https_GK1wmSU has joined. 02:56:51 -!- https_GK1wmSU has left. 03:00:30 Cale: I wish I understood the reals. :-( 03:01:12 shachaf: What would it mean to understand them? 03:01:28 I'm not sure! 03:01:41 I just think they're a much more mysterious and fundamental object than I gave them credit for in the past. 03:02:29 Cale: any opinions on https://www.facebook.com/slbkbs/posts/1540808232616365 twh 03:03:53 That question makes me think to mention this quirky strategy for proving the reals are uncountable 03:04:25 (See also the comments, which apparently you have to click the link to see.) 03:08:35 Let S be an arbitrary subset of [0,1] and define a two-player game as follows. 03:08:47 The first player picks a number 0 < a_1 < 1 03:08:59 and the second player picks a number a_1 < b_1 < 1 03:09:14 and thereafter, the players pick numbers between the previous two selected numbers, i.e. 03:09:26 a_(n-1) < a_n < b_(n-1) 03:09:26 and 03:09:42 a_n < b_n < b_(n-1) 03:09:51 -!- oerjan has joined. 03:10:18 Since the sequence of a_n is monotone increasing and bounded, it has a limit L. The first player wins if L is in S. 03:10:52 If S is countable, then the second player has a winning strategy: pick b_n to be s_n whenever that is a valid move, and to play a random move otherwise 03:11:11 If s_n wasn't a valid move, then it's already outside the interval in which the limit must occur 03:11:36 and the limit of the sequence must be strictly less than b_n, so playing s_n as b_n ensures that the limit is not s_n for any n 03:11:48 But if S is [0,1], then the first player always wins 03:12:09 So [0,1] is uncountable 03:12:22 What's s_n? 03:12:44 Ah, S = {s_1,s_2,...} under the assumption it's countable 03:13:00 Sorry, left that out 03:13:58 -!- doesthiswork has joined. 03:18:59 the first player would have a winning strategy if the _complement_ of S is countable, i think. 03:20:06 in pretty much the same way. 03:21:15 gah what's up with internet... 03:21:22 * oerjan goes to restart router 03:22:59 right 03:24:50 hm that didn't help, still no connection to PPCG 03:25:24 Cale: Which properties of the reals do you need for this? 03:26:50 Totally ordered, Dedekind-complete? 03:26:54 Well, that's not enough. 03:28:31 * oerjan switches DNS to 8.8.8.8 03:29:42 * oerjan puts reminder in a vim window to change it back 03:30:17 high tech primitive solutions 03:32:53 shachaf: that defines the reals though 03:33:00 shachaf: well, that and that they are a field 03:33:24 "that they are a field" is a short phrase that has a lot of complexity. 03:33:54 well, yes 03:34:04 and in particular they are a totally ordered field 03:34:05 Did you see my post above? 03:34:25 I don't have any special insight 03:34:56 "The real line ⟨ℝ,<⟩ is (up to isomorphism) the unique nonempty, separable, complete, dense, endless total order." 03:35:23 Which of those properties are used in Cale's game? 03:35:43 Hmm, I guess a lot of them. 03:37:34 not the endless one, i guess. 03:37:52 Cale's proof isn't even about R, it's about [0,1] 03:38:08 So that one isn't necessary. 03:38:50 What's separability again? 03:39:01 hm which of those properties isn't satisfied by a single point space... 03:39:10 oh. 03:39:17 that's the only one you need endless for. 03:39:25 to show that it has more than one point. 03:41:28 Well, [0,1] isn't endless. How do you characterize a potentially-closed real interval? 03:42:25 i think dropping endless gives all of them, plus the single point. 03:42:56 shachaf: separable = contains countable dense subset 03:43:21 I don't know why it's called separable 03:44:24 Ah, right, like Q in R 03:46:25 yep 03:46:38 trying to figure out why separable is necessary 03:48:16 https://mathoverflow.net/a/43165 gives an example 03:54:44 i'm not sure separable is necessary for the proof. 03:57:31 [wiki] [[Esolang:Introduce yourself]] https://esolangs.org/w/index.php?diff=52614&oldid=52610 * Phi * (+160) 03:59:51 I don't think it is 04:00:20 [wiki] [[Esolang:Introduce yourself]] https://esolangs.org/w/index.php?diff=52615&oldid=52614 * PhiNotPi * (+203) 04:24:32 koenigl: https://gitlab.brokenpipe.de/stettberger/avremu 04:25:01 -!- erkin has quit (Quit: Ouch! Got SIGABRT, dying...). 04:33:47 ooh, genuine spammers are back on the wiki... 04:34:14 I bet I would be good at spamming the wiki. 04:34:26 I wonder how much I can get for it. 04:34:29 probably. for a while. 04:34:51 (it didn't get through the new filter.) 04:35:22 oerjan: how much will you pay me not to become an evil spammer and ruin the wiki for everyone twh 04:37:10 i'll delay banning you for up to a week hth 04:38:32 does anybody know of any papers covering a dynamic succinct linked list implementation? 04:38:43 the closest I can get is binary trees and squinting really hard. 04:38:52 What's a succinct linked list? 04:39:02 That seems kind of tricky. 04:39:35 `? succinct 04:39:36 succinct? ¯\(°​_o)/¯ 04:39:56 shachaf: lists that contain either empty lists or atoms that take up an amount of bits close to the minimum to represent them. 04:40:03 `dowg succinct 04:40:06 but still remain usable. 04:40:10 No output. 04:40:16 imode: But they still have pointers between nodes? 04:40:22 nope. 04:40:51 I came up with a static version a while back that can fit a lot within a single machine word. 04:41:00 but now I'm searching for a dynamic version. 04:41:09 What's the difference between succinct linked lists and succinct sequences? 04:41:24 Do they support sharing nodes or something? 04:41:47 mmm. alright, bear with me now. 04:42:02 say you have a list like [[],[],[]]. 04:42:40 how would you encode that so you conserve on space while retaining the same operations. 04:42:55 for traversal. not modification. 04:43:01 A list of lists? 04:43:15 yep. just as an example. 04:43:23 Is this an arbitrary tree or only depth 2? 04:43:49 any arbitrary list consisting of either nested lists or empty lists. 04:44:17 I would call that a tree. Where a tree is defined as a list of trees. 04:44:25 sure. 04:44:38 Anyway this is the old balanced parentheses thing, right? 04:44:44 correctamundo. 04:44:46 What makes these linked lists? 04:45:10 closest two words I have for something like this. 04:45:47 could just use 'list'. 04:46:11 Why would you call a tree a list? 04:46:12 anyway, yeah, this is the nested parens problem. store opening and closing parens as bits. 04:46:20 This is the least fixed point of lists. 04:46:43 "why would you call a tree of list." 04:46:47 *a list. 04:47:02 because... a list is a list of values, each of which may also be lists. 04:47:15 not sure why you're getting hung up on that. 04:47:54 if you wanted me to specify "right-heavy binary trees" I could. 04:49:22 [wiki] [[Special:Log/block]] block * Oerjan * blocked [[User:Kutta]] with an expiration time of indefinite (account creation disabled): Spamming links to external sites 04:49:38 anyway, with the binary representation of a tree, it's hard to do arbitrary inserts without lots of operations being flung around at once. so I was wondering if there was a more dynamic method of storing them. 04:54:15 imode: us haskellers get hung up on that because of all the nested "lists" that won't pass type checking as lists in haskell because they're actually trees hth 04:54:41 (i forget, were you from PPCG) 04:54:48 I am not. :P 04:55:04 because there are quite a number of such challenges there. 04:55:17 nah. just a dude doing research. 04:55:36 imode: How much overhead are you willing to accept? 04:55:57 shachaf: for what? a dynamic representation? 04:56:01 You said "succinct" so I guess you want Z + o(Z) 04:56:13 yuh. also, I already have an encoding for static trees. 04:56:26 always saves one bit over the traditional parens representation. 04:56:34 -!- PattuX has quit (Quit: Connection closed for inactivity). 04:56:57 just wondering about what a convenient alternative is for trees that support arbitrary insertion/manipulation. 05:00:10 I don't know much about dynamic succinct data structures unfortunately. I'd like to know more. 05:00:45 But at least I understand the question now. 05:00:47 I don't think it has anything to do with linked lists (I think linked lists are lists where each node has a link pointer to the next node). 05:01:03 shachaf: you can replace linked list with "collections of cons cells". :P 05:01:41 but yeah, trees work. 05:01:47 But this has even less to do with binary trees than it does with lists. 05:02:02 not.. really. 05:02:16 considering they're all equal in representation. if you think not, ask a lisper. :P 05:02:42 Here's a exoteric reduct game http://www.therottingcartridge.com/games/programming/ 05:03:35 [wiki] [[Special:Log/upload]] upload * PhiNotPi * uploaded "[[File:Qftarch01.png]]" 05:03:51 @wn exoteric 05:03:52 *** "exoteric" wn "WordNet (r) 3.0 (2006)" 05:03:52 exoteric 05:03:52 adj 1: suitable for the general public; "writings of an exoteric 05:03:52 nature" [ant: {esoteric}] 05:04:28 doesthiswork: TG 05:05:40 Ferdinand-Tönnies-Gesellschaft ? 05:06:29 Too Good 05:07:23 axtually I'm juxt bad at typeing 05:07:53 What are these broken keys? 05:08:18 Booleans? 05:08:28 yeah, false booleans 05:09:25 I guess the pink thing is (==) and doesn't allow function arguments. 05:09:41 🎜 Take these broken keys. And learn to type again. 🎜 05:10:46 Does this introduce callCC later? 05:11:07 yeah, once you unlock the hidden levels 05:12:19 Ah, 19 was the first slightly tricky one. 05:13:32 Did you make this? 05:14:00 no I found it on LTU 05:16:11 doesthiswork: You should extend it for linear types. 05:18:42 that would be interesting 05:20:03 [wiki] [[Funge-98]] https://esolangs.org/w/index.php?diff=52617&oldid=52609 * Btiffin2017 * (+1769) /* Instructions (including Befunge-93 commands) */ 05:22:14 shachaf: she'd be more the vicereine, i should think. 05:22:54 hm should that be reyne 05:23:03 oerjan: am i missing a pun twh 05:23:16 no, just a gender hth 05:23:45 are you missing a pun twh 05:23:52 probably. 05:24:23 it's not a very complicated one 05:24:39 i assumed you were just going from vicenarian. 05:24:54 which isn't much of a pun. and not even cognate, i suspect. 05:25:05 assume again 05:25:08 or wait, maybe it is. 05:27:13 nope, doesn't seem to be cognate. 05:27:39 ... 05:28:28 i cannot in good conscience swat for a pun that took me that long, sorry. 05:28:51 What! 05:28:56 How about the pan? 05:31:02 i'm afraid it doesn't pan out, either. 05:32:45 `? decadent 05:32:46 a decadent is a ten-pronged rake 05:33:02 `slwd decadent//s,.,A,;s,$,., 05:33:04 decadent//A decadent is a ten-pronged rake. 05:33:08 I knew it. 05:33:43 but did you manage to make a profit from your inside knowledge? 05:34:00 No, I don't play golf. 05:34:14 shocking 05:38:47 doesthiswork: How do you unlock the hidden levels? 05:39:57 you invoke the continuation and restore to level 5 with continuations enabled 05:40:39 Oh, so you were joking? :-( 05:41:20 I'm sorry but I was, I'm going to design some levels and suggest continuations to andru 05:42:04 http://www.cs.cornell.edu/andru/ 05:44:37 that was a fun game. 05:57:58 <\oren\> how is the bitcoin fork going? 06:09:28 <\oren\> Are graphics cards going to become affordable again 06:12:24 [wiki] [[QFTASM]] N https://esolangs.org/w/index.php?oldid=52618 * PhiNotPi * (+6860) created page 06:13:07 <\oren\> find out in 7 hours, 7 minutes and 7 seconds! 06:13:55 <\oren\> https://www.timeanddate.com/countdown/launch?iso=20170801T1220&p0=1440&msg=Bitcoin+Cash+Hardfork 06:14:20 [wiki] [[QFTASM]] M https://esolangs.org/w/index.php?diff=52619&oldid=52618 * PhiNotPi * (-2) fixed link format 06:29:37 -!- https___GK1wmSU has joined. 06:30:10 -!- https___GK1wmSU has left. 06:33:34 -!- erkin has joined. 07:00:41 -!- FreeFull has quit. 07:21:00 Do you know this algorithm for converting a number into decimal? http://wiki.nesdev.com/w/index.php/User:Zzo38/Decimal_numbers 07:25:37 -!- sleffy has joined. 07:25:43 why not just use BCD. :P 07:27:28 Mainly for cases where conversion is needed. For many uses, BCD (or base 100 may be better, especially for Famicom which has no decimal mode) can be very helpful, but sometimes you will need conversion (such as if implementing Z-machine, for example). 07:27:57 how so? packed BCD is pretty standard. 07:29:11 Famicom and NES doesn't support the packed BCD arithmetic of 6502; that flag will be ignored (it still exists though, it just doesn't do anything). 07:29:43 oh shit, yeah. forgot about that. 07:30:08 -!- sleffy has quit (Ping timeout: 258 seconds). 07:30:09 man it has been a while.. 07:30:25 * imode looks at the last accessed date on his old NESASM... 07:31:52 Which is what date? 07:32:48 January 13th, 2011. 07:33:02 OK 07:34:38 -!- augur has quit (Remote host closed the connection). 07:40:38 -!- sdhand has quit (Excess Flood). 07:40:48 -!- sdhand has joined. 07:41:12 -!- sdhand has changed nick to Guest43396. 07:43:07 -!- Guest43396 has quit (Changing host). 07:43:07 -!- Guest43396 has joined. 07:43:07 -!- Guest43396 has changed nick to sdhand. 07:49:30 -!- HackEgo has quit (Remote host closed the connection). 07:50:14 -!- HackEgo has joined. 07:54:12 [wiki] [[Funge-98]] M https://esolangs.org/w/index.php?diff=52620&oldid=52617 * Btiffin2017 * (+0) /* Instructions, correct the stack pictures */ 08:11:18 -!- sleffy has joined. 08:28:03 <\oren\> there will, in less than 5 hours, be two variant coins: Bitcoin Core, and Bitcoin Cash 08:28:32 -!- doesthiswork has quit (Quit: Leaving.). 09:08:00 `? bitcoin 09:08:02 bitcoins are coins that have been drilled through with a bit, and can be strung together in long chains. This practice dates to ancient China, and the Chinese remain experts in bitcoin manufacturing. A chain can support up to 21 million coins before breaking. 09:15:50 why do large companies care about being influential in standard committees? 09:16:07 like google and facebook 09:16:11 why do they even care? 09:19:32 in IBM's case, an ultimately futile struggle to stem the tide of trigraph-haters 09:24:25 hah 09:26:17 in any case, it's rather cheap influence compared to, say, congressional lobbying 09:49:26 -!- oerjan has quit (Quit: Nite). 09:58:17 -!- btiffin has quit (Quit: ChatZilla 0.9.93 [SeaMonkey 2.46/20170120202656]). 10:11:23 -!- imode has quit (Ping timeout: 255 seconds). 10:20:30 -!- sleffy has quit (Ping timeout: 240 seconds). 10:24:49 -!- hppavilion[1] has quit (Ping timeout: 246 seconds). 10:46:12 -!- hppavilion[1] has joined. 10:51:23 -!- hppavilion[1] has quit (Ping timeout: 258 seconds). 10:51:46 -!- hppavilion[1] has joined. 10:52:40 -!- hppavilion[1] has quit (Client Quit). 11:38:56 -!- boily has joined. 11:56:20 -!- LKoen has joined. 12:06:04 -!- jaboja has joined. 12:29:57 -!- boily has quit (Quit: TOROIDAL CHICKEN). 13:07:37 -!- ais523 has joined. 13:51:14 -!- ais523 has quit. 13:51:29 -!- LKoen has quit (Remote host closed the connection). 14:00:46 -!- doesthiswork has joined. 14:03:07 -!- copumpkin has quit (Ping timeout: 240 seconds). 14:10:52 -!- wob_jonas has joined. 14:11:41 " Here's a exoteric reduct game" => oh, will this become the next toy everyone in #esoteric tries, like that euclides compass and line game last time? 14:12:02 I still haven't figured out how to do the pentagon in 10 steps 14:12:13 I really like that ancient greek geometry game 14:12:30 -!- Cale has quit (Remote host closed the connection). 14:15:09 -!- Cale has joined. 14:21:47 (trying that reduct game) huh what? I don't understand 14:22:30 -!- jaboja has quit (Read error: Connection reset by peer). 14:23:18 -!- jaboja has joined. 14:23:55 I don't understand how this game works 14:24:02 maybe it will become clear later 14:26:49 ok, now I'm even more confused 14:29:14 -!- `^_^v has joined. 14:39:08 -!- jaboja has quit (Ping timeout: 255 seconds). 14:41:35 -!- copumpkin has joined. 14:41:55 -!- jaboja has joined. 14:48:53 well I still don't understand what this game is about, even after beating lots of levels 14:49:51 I thought it was about arbitrary changes in notation 14:50:56 doesthiswork: maybe 14:53:42 I understand what it's about 14:53:51 It's basically like weird manual lambda calculus 14:54:19 Cale: but where's the lambda calculus part? I've seen lambdas, but no application expression. 14:55:05 You do application by hand by dropping things into the lambdas 14:55:26 yes, but there's no expression that does application. you can't have lambda calculus without that. 14:55:47 or at least, I haven't encountered such an expression up to where I'm at 14:55:58 and I'm playing level 69 now 14:58:18 wait what? 15:01:02 I'm at the end of the game, and I still don't understand it 15:01:49 I just don't get the point 15:03:37 -!- jaboja has quit (Ping timeout: 258 seconds). 15:03:51 -!- jaboja has joined. 15:04:26 wob_jonas: I think the main thing which is confusing there is that you can't just leave something sitting in the input of a lambda without having it automatically reduce 15:06:15 -!- ais523 has joined. 15:06:29 Maybe ais523 can make sense of it 15:06:44 -!- doesthiswork has quit (Quit: Leaving.). 15:06:54 `? euclid 15:06:56 euclid? ¯\(°​_o)/¯ 15:07:59 wob_jonas: context? 15:08:09 or am I going to have to read the logs? :-( 15:08:50 ais523: doesthiswork brought up this game thingy http://www.therottingcartridge.com/games/programming/ 15:08:50 Jafet: (re Brainfudge) I'm not sure that counts; at least, it's fairly different from what I had in mind 15:09:00 I played through the 72 levels, but still don't understand what it's about 15:09:06 wob_jonas: can't really follow links like that at work 15:09:11 I can have a look tomorrow, perhaps? 15:09:23 sure 15:09:26 wob_jonas: I don't know if it's about anything more than what is apparent 15:09:57 well, I guess it does say "prototype" at the bottom 15:10:01 so maybe he'll change it later 15:10:13 on the subject of programming games, I used to like Rubicon (which is based on an esolang, http://esolangs.org/wiki/RUBE) 15:10:18 but I haven't played it in ages 15:10:34 being written as a Java applet isn't great for modern-day computers 15:10:36 ais523: I mentioned that euclid game that we played on this channel some years ago 15:10:54 you know, the one about how to make a regular pentagon in ten of the game's steps, which I couldn't solve 15:11:28 oh, is it a geometry game? 15:11:40 hmm, is geometry somehow Turing-complete? 15:11:47 no, it's not a geometry game 15:12:02 it just reminds me because it's a meme game on web someone thrown into #esoteric 15:12:18 and the same sort of abstract geeky game 15:12:39 I get really annoyed by the classification "meme game" 15:12:55 people act like a game that becomes suddenly popular is necessarily bad as a result 15:13:00 no 15:13:02 kind-of like hipsterism except it's mainstream 15:13:09 I mean it was popular on #esoteric 15:13:13 and I'm not saying it's bad 15:13:24 well, I guess I am 15:13:24 right 15:13:27 they are bad 15:13:36 people normally use the phrase "meme game" to dismiss a game that's had a recent surge in popularity, though 15:13:50 but it's not bad because it's popular, but more like it's popular despite that it's bad, which is why I call it a meme game 15:14:04 yes, I am dismissing it, but not because it's popular 15:14:33 right 15:14:38 you're dismissing it, and it also happens to be popular? 15:15:05 yes 15:15:26 and I'm dismissing it more than the geometry game, because I can't make sense of what it's about 15:16:14 oh, " oh, is it a geometry game" was referring to the euclid thing, not the earlier topic of conversation 15:16:19 I need to be more precise in my pronouns 15:16:36 the earlier game I can't really discuss because I have basically zero information about it and can't take a look at it directly until tomorrow 15:17:50 sure 15:18:49 well, not quite zero information, I know that a few #esotericers don't understand it, an URL, and the number of levels it has 15:19:32 I understand it 15:19:47 I don't know what it is that wob_jonas is saying he doesn't understand about it. It's fairly straightforward. 15:34:40 -!- erkin has quit (Quit: Ouch! Got SIGABRT, dying...). 15:44:24 by the way, ICFP contest http://events.inf.ed.ac.uk/icfpcontest2017/ starts in less tha n3 days 15:44:32 I think that's on topic for #esoteric 15:46:40 definitely 15:46:43 it should be in topic, not just on topic 15:46:55 to reduce the number of people who miss it 15:47:03 good idea 15:47:55 and still no news about IOCCC 15:49:28 bad timing: http://www.cade-26.info/ 15:50:14 but I guess it just happens that both the ICFP contest and CADE are one month before ICFP. 15:50:38 int-e: they scheduled one of the previous ICFP contests at the same time as a Harry Potter book release, making it a bad time for many people, even though the date for the latter was known ages ago. 15:51:04 I might or might not participate 15:51:15 participating will depend on a) me remembering to participate, b) me liking the task 15:51:32 when I've participated in the past it's been solo, depending on what the task is it might make sense to get a #esoteric team together 15:52:27 -!- wob_jonas has set topic: bimetal prismack | http://esolangs.org/ | logs: http://codu.org/logs/_esoteric/ http://tunes.org/~nef/logs/esoteric/?C=M;O=D | https://www.dropbox.com/s/fyhqyvy3i8oh25m/wisdom.pdf | ICFP contest starting on 2017-08-01. 15:52:43 at 12 pm UTC, annoyingly 15:52:48 ais523: yes, these days they're increasingly making the task such that it's harder and harder to participate 15:52:50 that means I'll miss the first few hours due to work 15:52:58 um 15:53:03 harder and harder to participate alone 15:53:14 wait, 08-01? 15:53:22 uh wait 15:53:22 the UMIX challenge was very parallelisable 15:53:27 int-e: wob_jonas got the wrong date 15:53:27 -!- wob_jonas has set topic: bimetal prismack | http://esolangs.org/ | logs: http://codu.org/logs/_esoteric/ http://tunes.org/~nef/logs/esoteric/?C=M;O=D | https://www.dropbox.com/s/fyhqyvy3i8oh25m/wisdom.pdf | ICFP contest starting on 2017-07-01. 15:54:00 no wait 15:54:03 um 15:54:05 2017-08-04, I'd guess? 15:54:11 -!- wob_jonas has set topic: bimetal prismack | http://esolangs.org/ | logs: http://codu.org/logs/_esoteric/ http://tunes.org/~nef/logs/esoteric/?C=M;O=D | https://www.dropbox.com/s/fyhqyvy3i8oh25m/wisdom.pdf | ICFP contest starting on 2017-08-04. 15:54:18 that, yes 15:55:01 It looks like I'll miss it entirely 15:55:04 oh well 15:55:47 why does it have to be a VM... and does the VM exploit vulnerabilities in Virtualbox or VMware or the lesser known ones (is Bochs still a thing? Qemu...) 15:56:29 and why does the VM have to be so large 15:56:40 int-e: it doesn't have to be a VM. you can just compile your programs for a similar linux machine. they just make it a VM in case you're worried your program won't work in their setup. 15:56:47 you don't actually need to use the VM. 15:56:55 Debian used to have a version which ran off 1.44 MB of disk space 15:57:06 ais523: what? no way 15:57:10 they dropped that eventually to fit more programs in, but 5 GB is too much of a scale 15:57:19 wob_jonas: it was very cut down, I think 15:57:21 I mean, 3 MB, sure, but 1.44 MB? 15:57:27 I might be misremembering 15:57:31 but that's only a factor of 2 15:57:38 yes, a factor of 2 15:58:02 but Debian is intentionally designed to be able to do a minimal install if you want 15:58:05 first disk is only half full and has the boot loader and kernel (initrd wasn't a thing back then), second floppy has root file system image 15:58:24 I mean, I wasn't using Debian back then, but that's how small linux systems worked 15:58:27 most programs are split between core functionality and larger data files, so you can install just the core functionality if you like 15:58:53 well, I think the Debian install was just kernel + shell + dpkg + apt 15:58:59 i.e. just enough to be able to install more programs 15:59:00 they probably realized that computers dont have floppy drives any more. 15:59:09 I own a USB floppy disk drive 15:59:17 and have even used it on occasion, although not for a long time 15:59:20 mind you, I've heard legends about Linux before Linux 2.0 where you could run a system on 1 MB of RAM, which frankly seems impossible to me. you need at least 2MB for Linux, 4MB if you actually want to run nontrivial programs. And that's for old versions. These days you need much more. 15:59:38 i havent used one since like 2007 15:59:47 ais523: you need a libc too. libc was big even back then. 15:59:54 wob_jonas: the 8086 can't address more than 1 MiB of RAM 16:00:42 ais523: sure, but Linux was never intended to run without 386 32-bit protected mode, and it still almost doesn't run without it. I hear there are non-vanilla versions for cpus without memory protection, but not for x86. 16:00:52 Linux was originally intended as an OS for 386, 16:00:56 but later they made it portable 16:01:09 (386 compatibles obviously) 16:01:27 its instruction set can address almost 2 MiB if you use carrying rather than wrapping addition for segmentation calculations 16:01:47 what? no way 16:01:52 how would that work? 16:02:13 so a far pointer on x86 real mode is 32 bit long 16:02:22 and the address is calculated as (high 16 bits × 16) + low 16 bits 16:02:47 which cpu generation are you talking about here? 16:02:59 wob_jonas: 8086-compatibles 16:03:12 yes, but which generation? 8086 or 286 or 386? 16:03:47 all of them use this syntax when running in real mode (which is meant to be 8086 compatible) 16:03:57 however, the actual 8086 will do a wrapping calculation 16:04:11 yeah, and so will the 8086 I think 16:04:13 um 16:04:15 whereas the 80286, which has more address lines available, deos a carrying calculation 16:04:16 the 80286 16:04:19 ah 16:04:21 right 16:04:24 now I'm confused 16:04:30 how much address lines does the 286 have? 16:04:33 so motherboards at the time had a configurable bit 20 of their address line 16:04:56 the 80286 can address 16 MiB in protected mode, so I guess 24 address lines? 16:05:15 I see 16:06:01 I never really actually used a 286, I only read about them in books. The first computer we had at home was a 386-based PC with I think 8 MB of RAM, although I've seen older PCs elsewhere 16:06:18 It was quite a good machine at that time, the 386 was pretty new 16:07:23 the 286 never really caught on because its protected mode was really buggy / lacking in features 16:07:36 I see 16:08:04 it uses 16 bit addresses + fairly slow bank switching, which means that it can't easily access most of the memory that's available 16:08:20 yeah 16:08:39 also you can't switch back to real mode without resetting the cpu 16:08:45 right 16:08:50 they fixed all of that and more in the 386 16:08:57 although it took surprisingly long for people to find the triple-fault-based method to do that 16:09:00 which is fairly clean and net 16:09:02 *neat 16:09:08 plus made the cpu way more efficient 16:09:11 (and, incidentally, is still used by Linux as a last resort implementation of rebooting) 16:09:25 (if it can't reboot via ACPI like it'd like to) 16:09:29 a triple-fault based method? nice 16:09:45 I thought they just used a small circuit on the motherboard 16:09:50 in the keyboard controller or something 16:10:47 the 386 is a great cpu. it actually has a data cache. that was a big innovation. 16:10:55 obviously they didn't NEED a cache before that 16:10:56 but still 16:11:01 wob_jonas: that was the original method discovered (i.e. using the keyboard controller to trigger the hardware reboot input) 16:11:05 that allowed them to run the cpu so quickly 16:11:15 triple fault is much simpler, though, I wonder why they didn't think of it before screwing around with hardware 16:11:26 that was *discovered*? I assumed it was built into the motherboard deliberately 16:11:43 well, I mean 16:11:51 IBM were stuck trying to work around Intel's bugs 16:12:03 so they programmed their keyboard controller to be able to do reboots 16:12:13 which is one solution to the issue of "how can the processor reboot itself to get back into real mode" 16:12:23 right, but you didn't really have to discover that. it's a well-known feature that the cpu can be reset in like four ways and one of them is a signal on a leg. 16:12:27 so they discovered the principle behind the solution, but still had to actually implement it using a custom keyboard controller 16:12:29 <\oren\> ReeCoin up 7300% 16:12:32 <\oren\> https://twitter.com/WorldCoinIndex/status/892399569077776385 16:12:37 <\oren\> REEEEEEEEE 16:12:45 \oren\: altcoins are incredibly volatile 16:12:53 right, but they need a completely new motherboard for 286 anyway 16:13:01 and most of them are almost worthless, thus a small absolute change can lead to a large relative change 16:13:20 <\oren\> ais523: right now everyone if panicky about the whole bit coin core bit coin cash split 16:14:05 why not just run both chains and see which one ends up having more value? 16:14:20 each bitcoin gets split into two, one on each system; their total value should add up to the original value of the coin 16:14:37 <\oren\> some people are doing that, but others are trying to arbitrage 16:15:02 ais523: sure, they're run both. but it's a market, so they won't "just" run both and see, they want to predict the value to win huge 16:15:04 arbitrage helps to cause convergence to a stable value 16:15:18 wob_jonas: oh, I didn't realise there was an actual hard fork that had already happened 16:15:24 I thought it was still being discussed 16:15:27 I think it hadn't happened yet 16:15:32 but will very soon 16:15:33 but I'm not sure 16:15:54 as in, so soon people who are serious about that sort of thing have had to start preparation long ago 16:32:03 -!- jaboja64 has joined. 16:32:11 for comparison, the last time the ICFP used a VM image, it was 639.1 MB 16:32:20 -!- jaboja has quit (Read error: Connection reset by peer). 16:32:26 this one's 5.3 GB 16:32:38 Oo 16:32:46 yeah, that's big. but like I said, you don't actually need it. 16:33:39 if they ask you to submit an executable, and they usually do, you probably need it for the final compile 16:33:43 but you certainly don't need to work on it 16:37:53 I don't think you really need it. You just need any modern x86_64 linux system to compile on, and make sure you either include the required dynamical libraries or compile them statically into the program. 16:38:10 although I'm not sure how libc works these days 16:39:22 I mean, I understand why in normal production work you don't want to statically link libc to your programs, but in a competition thing like this it might be useful. 16:42:26 depending on how much of libc you need, normally you could statically link it 16:42:39 however, this particular purpose for the VM, compiling programs, has a big reason to want all of libc 16:42:45 because compiled programs will likely want to link against it 16:42:48 and the only reason you even might need to statically link it is if you're using a later version of glibc than what's on their debian 16:43:52 and that isn't too likely, since they're using debian 9, which is recent 16:44:14 so you'll get screwed up only if you use some gentoo or something with later libc 16:44:35 and even then you could install a smaller installation of debian 9 (or 8) on x86_64 and compile on that 16:47:44 -!- jaboja64 has quit (Ping timeout: 260 seconds). 16:48:48 hmm, the VM is failing to boot under qemu 16:48:57 GRUB works, and Linux starts to load 16:49:07 ais523: do you have enough RAM? 16:49:15 but after the "setting up initial RAMdisk" stage, the view returns to the original view as of boot, then it hangs 16:49:17 where does it fail? 16:49:28 ah 16:49:42 I'd guess it's a problem with the boot lodaer setup with your emulator then 16:49:57 or something 16:49:58 well, GRUB working is evidence that it at least doesn't fail in the early stages 16:50:12 yeah, but grub has to load the initrd 16:50:25 right, but that isn't a hard step or one I'd expect to fail 16:50:34 yeah 16:50:37 dunno 16:50:48 debug it and if it's their fault complain to them 16:51:49 I don't think I'll even try to install the VM if I want to participate 16:51:58 or download 16:53:13 hmm, I think the issue is to do with memory 16:53:30 my qemu can't give it more than half a gigabyte, but the implication in the notes is that it needs 4 gigabytes of memory 16:53:47 qemu actually segfaults trying to allocate 4G of memory 16:53:59 I wonder if it's overflowing it to 0 bytes? 16:54:16 no, the implication in the notes is that they will give you 4G of memory for the contest, but it's a modern debian system which is terrible on machines with low amount of RAM so it might actually need 2G or something 16:54:35 is it a recent enough version of qemu? 16:54:46 whatever the most recent version in the Ubuntu stable repos is 16:55:05 and your host is x86_64, right? 16:55:20 try giving it just one virtual cpu? 16:55:31 not that it should matter much 16:56:05 but even with just 512M it should get past the loading initrd stage 16:59:24 changing the number of CPUs doesn't help 17:00:51 hmm, I suspect GRUB is running but failing to hand over to Linux 17:00:58 in this configuration, it's GRUB that loads the initrd 17:01:02 let me add some debug statements to the GRUB config 17:02:05 sure, grub or the boot loader is always what loads the initrd. that's why it's called *init*rd. it would be just a ramdisk otherwise. 17:02:42 [wiki] [[Number Factory]] https://esolangs.org/w/index.php?diff=52621&oldid=52544 * Qwertyu63 * (+86) 17:02:50 -!- idris-bot has quit (Quit: Terminated). 17:03:32 [wiki] [[User:Qwertyu63]] https://esolangs.org/w/index.php?diff=52622&oldid=52519 * Qwertyu63 * (+8) 17:03:49 hmm, it seems to be working now, even though I didn't change anything other than dropping caches 17:03:57 at least, I'm not aware of having changed anything 17:04:21 what caches? 17:04:22 I'm also not specifying the amount of memory to use; 0.6GB was not enough 17:04:28 wob_jonas: Linux virtual memory caches on the host 17:04:47 wtf 17:05:12 some web searches implied that QEMU incorrectly counts them as used memory when trying to work out how much memory is available 17:05:16 is it possible that you have ran out of memory on the host? 17:05:28 ah! 17:05:35 so it automatically set the memory size 17:05:45 you should try to set it explicitly 17:06:03 right, but all the values were either too small, or else caused qemu to fail to allocate memory 17:06:06 [wiki] [[Number Factory]] https://esolangs.org/w/index.php?diff=52623&oldid=52621 * Qwertyu63 * (+162) 17:06:20 the remaining issue seems to be that, after logging in, all the filesystems are read-only 17:06:29 but that's likely fixable with a ramdrive 17:06:40 and if you're on a machine that doesn't have much resources, such as mine where I ran out of memory for ayacc, then you might be screwed anyway, because you shouldn't expect that a 5 GB disk sized debian system will be kind on memory use. 17:07:03 Isn't that because the underlying virtual disk drives are read-only? 17:07:49 yes, almost certainly 17:10:26 OK, this works 17:10:28 at least for C 17:11:16 as in, you compiled a hello world? 17:11:18 yes 17:11:32 yeah, I did at one point break my linux system such that that simple test failed 17:11:45 that was shortly before I reinstalled, and one of the last straws 17:11:55 the other was the man program no longer working 17:12:13 it was all my fault by the way 17:12:26 I don't know the specifics, but I fiddled a lot with the system 17:12:33 I learned a lot though 17:13:29 are you the person who reimplemented core programs like cat and managed to break them in the process? or was that someone else? 17:13:40 that was someone else 17:15:55 [wiki] [[Language list]] https://esolangs.org/w/index.php?diff=52624&oldid=52587 * Qwertyu63 * (+63) 17:16:01 [wiki] [[User:Qwertyu63]] https://esolangs.org/w/index.php?diff=52625&oldid=52622 * Qwertyu63 * (+0) 17:17:09 -!- erkin has joined. 17:17:15 -!- ais523 has quit. 17:21:11 [wiki] [[Special:Log/newusers]] create * TheZipCreator * New user account 17:22:00 -!- FreeFull has joined. 17:25:50 -!- staffehn has quit (Ping timeout: 258 seconds). 17:28:01 oh wow 17:28:12 I got nostalgic and started thinking about those old computers 17:28:51 basically the story is that the third computer we had at home was a Pentium that was my computer, running at the same time as the main computer (my father's computer), another Pentium 17:29:40 and that I still use that same PC, even though I've replaced the hardware and the operating system many times, but I never replaced both the operating system and a major hardware component at the same time, so I always had to keep the hostname 17:29:42 -!- staffehn has joined. 17:30:21 and I have backups sometimes local copies of lots of files from all the earlier operating systems 17:30:47 and I used to say that the operating system and each individual part of the hardware got replaced at least three times since 17:30:53 but I just realized that's not true 17:31:21 I think the optical disk drive only got replaced twice, 17:31:35 but when that computer was first set up, it didn't yet have an optical disk drive 17:31:53 so getting that first CD drive probably counts as an extra occasion 17:31:59 ok, that means the balance is restored 17:32:29 heck, I think even the desk has been replaced three times 17:33:01 the monitor, I think, got replaced exactly three times: once to a newer crt, once to a small tft, and once to this big tft 17:33:44 I'm really fuzzy with the history and I'm not sure how many times the motherboard and many other components were replaced, but I know it was at least three times each 17:34:07 hmm... the floppy drive might also be a bottleneck in fact 17:34:30 both the 1.44 and the 1.2 floppy drive. I think I only had one 1.2 floppy drive and one or two 1.44 floppy drive 17:34:32 damn it 17:35:06 but I don't have a floppy drive in this machine anymore, so it's hard to notice 17:36:25 -!- staffehn has quit (Ping timeout: 276 seconds). 17:37:13 -!- staffehn has joined. 17:37:25 do I now have to buy two cheap floppy drives and throw one out after installing to the machine? probably no 17:47:14 -!- jaboja64 has joined. 18:02:18 I invented a kind of character coding for use with computer applications involving astronomy and/or astrology. 18:03:51 There are up to 1065353472 codepoints, and the first 128 codepoints are compatible with ASCII. 18:04:52 Do you like this? 18:05:56 wob_jonas: Okay, one thing I don't understand is why this thing makes the notation for lambdas and conditionals worse halfway through 18:10:13 Yeah, the notation is getting more and more disgusting :) 18:25:43 -!- jaboja64 has quit (Ping timeout: 246 seconds). 18:28:15 -!- jaboja has joined. 18:34:17 -!- LKoen has joined. 18:49:26 -!- idris-bot has joined. 18:52:18 -!- Lord_of_Life has quit (Excess Flood). 18:52:50 -!- Lord_of_Life has joined. 18:59:20 -!- imode has joined. 19:08:26 -!- augur has joined. 19:08:53 [wiki] [[~-~!]] https://esolangs.org/w/index.php?diff=52626&oldid=47106 * Xav737 * (+331) Add a summary area for the esolang 19:11:59 zzo38: This sounds almost like giga-Unicode. :P 19:14:26 Cale: wait till the last few levels. I already didn't understand how come lists can always be extracted freely, even when they are the output of a computation, 19:15:07 but in the final few levels suddenly you'll be able to remove the condition from the conditionals, even if that conditional is the output of a computation (like a lambda) 19:15:24 So I really don't understand how building stuff works in this game. 19:15:25 wob_jonas: Yeah, I finished it, and the notation was really dumb at the end, I guess they want it to look like ruby or something? 19:15:39 Also, at some point it changes the notation to the atoms to something horrible. 19:15:46 Cale: h8r 19:15:53 The notation is pretty silly but it doesn't matter. 19:16:08 Cale: maybe they want to make it look like *something*, but not ruby 19:16:17 what game? that lambda game? 19:16:20 But it's not really the notations that bother me. 19:16:21 shachaf: I just don't know why they would start with better notation, and then make it worse gradually 19:16:25 imode: yes 19:16:51 wob_jonas: Would it be better if you could place an argument on a lambda and only click it to beta reduce? 19:17:27 I mean, the rules about how you can manipulate the components are pretty arbitrary 19:17:38 Like the thing about being able to unpack lists 19:17:45 That seems okay to me 19:17:55 It's just an arbitrary power that you're granted 19:18:23 -!- erkin has quit (Quit: Ouch! Got SIGABRT, dying...). 19:18:27 /context 19:18:39 Cale: I don't think so. Even now in some tasks you need too many clicks to reduce expressions that should just auto-reduce. 19:19:33 Ah, found it. 19:19:35 wob_jonas: I thought it was kind of interesting to have the power to avoid reduction and decompose things 19:19:57 Cale: really my main complaint is that we never see an application expression 19:20:10 Cale: I don't quite understand those null things. 19:20:18 shachaf: Just bad notation. 19:20:28 Cale: but you don't seem to NEED reduction. And I think I understand the null thing 19:20:51 They want it to look like a ternary operator for some reason, but it's not actually a ternary operator 19:21:06 So they introduce null there (which actually always occurs on the false branch of the thing) 19:21:11 This might be inspired by Dragonbox. At least it has some similarities. 19:21:30 basically a lambda can have multiple return values, which makes sense even if few languages have it, and then it freely allows you to compose any output to any input without building blocks 19:21:33 Cale: I was hoping they'd introduce callCC 19:21:47 shachaf: we'd need a fucking function composition first 19:21:50 I mean, this style of game could be much better with different primitives 19:21:54 the part I really don't understand is the map thing 19:22:03 Cale: sure. like the crocodile game, but more powerful. 19:22:04 Anyway I wanted to make a game like this but in the version I had in mind you build more complicated expressions without reducing them all the time. 19:22:09 you know the crocodile game, right? 19:22:12 yeah 19:22:14 Alligator eggs? 19:22:32 Yeah, Alligator eggs 19:22:38 Professor Twist could not but smile. / "You mean," he said, "a crocodile." 19:22:38 shachaf: that yes. I'm in Europe, so I can only go with crocodiles 19:23:01 Why? 19:23:47 Europe doesn't really have aligators. It has crocodiles, which are nicer, and even those are really far from Hungary, I only see them in zoos. 19:24:31 You're in Eurasia, which has Chinese alligators. 19:24:44 But you can talk about dragon games even though dragons are extinct in Europe. 19:24:59 yeah, but Africa has crocodiles, and it's much closer 19:25:32 Africa also has elephants. Why not talk about elephant eggs? 19:25:34 are they extinct or are they just hiding? even so, I don't use Chinese dragons for dragon games 19:26:13 shachaf: crocodiles have big gaping mouths, you can draw them easily as swallowing eggs or other crocodile families, and even draw them to look similar to a lowercase lambda 19:26:28 it would be much stranger for an elephant to eat other elephant families 19:26:42 http://www.qu-i-x.com/crocodile.html 19:26:54 space games are quite popular these days 19:27:02 you could set it in space, with spacesuits 19:28:02 Jafet: Why not set it in a factory with nuclear waste containers? 19:30:18 Cale: anyway, the building rules indeed start to make no sense when map are introduced. you can map an expression that has holes, and get expressions with multiple holes. how does that even work? 19:30:28 ok, maybe that already didn't make sense with the lambdas 19:30:30 dunno 19:31:12 The holes vs. lambdas thing didn't quite make sense to me in the first place. 19:31:17 -!- jaboja has quit (Ping timeout: 246 seconds). 19:31:35 `5 w 19:31:40 1/1:galaxy//A galaxy is a star that feeds its litter with milk. \ canada//Canada is Big Scotland. Like, you know, very big. \ turing complete//You complete a Turing when you Tur by a specified amount. \ cod//Cod is a fish's favourite fish person shooter. \ watch//Too late! 19:31:41 [wiki] [[Talk:~-~!]] https://esolangs.org/w/index.php?diff=52627&oldid=39430 * Xav737 * (+708) /* Dropping the requirement of bignums */ new section 19:31:50 You might be overthinking it? 19:32:10 It's not like, keeping track of scope or anything 19:32:33 [wiki] [[Talk:~-~!]] M https://esolangs.org/w/index.php?diff=52628&oldid=52627 * Xav737 * (+78) /* Dropping the requirement of bignums */ 19:32:52 `cwlprits canada 19:32:53 level 35 is also strange 19:33:00 shachäf shachäf boil̈y boil̈y boil̈y 19:33:07 you get free variables you can drag there 19:33:20 and insert to a lambda, and suddenly they're bound to it 19:33:37 Yes, I guess that's the distinction between holes and lambdas. 19:34:06 but that was the only level where you can do that, the theme doesn't get explored, and we never find out what the rules are or how alpha-reduction works 19:34:46 ah yes, you also get free variables in level 7 19:35:08 I also prefer the original syntax for "lists" which makes them look more like sets 19:35:23 [wiki] [[~-~!]] M https://esolangs.org/w/index.php?diff=52629&oldid=52626 * Xav737 * (+30) 19:35:28 but I think you never get enough building blocks to witness alpha reduction, do you? 19:35:45 There's nothing really to suggest that sets/lists have any order to them 19:36:06 There's only ever x 19:36:15 They're multisets. 19:36:22 But in at least one level the order is required. 19:36:33 ...But you can always take them apart and put them back together so it doesn't mean much. 19:36:36 yeah, multisets / bags 19:36:40 Cale: yes, that was strange, but I think there's only one or two tasks where that actually matters, the ones that use both lists and equal, and at that point you get the bracket notation 19:37:02 wait, which level required something about order? 19:37:21 Cale: let me find that 19:37:35 Looks like 54 19:37:49 48 19:37:58 oh 19:38:05 I see 19:38:11 and 49 19:38:19 48 and 49 surely don't 19:38:20 48 requires order? 19:38:23 54 does 19:38:25 no wait, 49 doesn't require it 19:38:40 I don't see how to make order matter in 48 or 49 19:38:43 shachaf: I think 48 has solutions and non-solutions that differ only by order in lists 19:38:46 49 doesn't 19:39:06 I don't see how. 19:39:13 hmm wait 19:39:14 ([star,star] ==) is pre-bound 19:39:36 sorry, you're right 19:39:39 48 doesn't require order 19:42:42 -!- AnotherTest has joined. 19:43:01 hmm... I think order might matter for level 51, let me try that 19:43:49 wait wtf 19:45:20 -!- PattuX has joined. 19:45:24 #51 seems to claim that ([star, (false?$hole:null)] == [(false?$hole:null),star]) evaluates to true 19:45:26 how does that work? 19:50:17 you did that differently... I compared two stars and erased a bag containing four stars. 19:50:20 65 is the other level where order matters 19:50:29 int-e: sure, that's the easy solution 19:50:55 but the thing is that nulls disappear completely 19:50:57 so because of 54, the goal definitely cares about order 19:51:16 but let me test if the == operator cares about the order in 65 19:51:42 no wait, 54 doesn't let me test that 19:52:48 in any case, I agree that it introduces ugly notation for no good reason. 19:53:07 ok, then I think 51 is the only level where you can detect whether == cares about list order 19:53:47 I still don't understand the part where you can sometimes evaluate lambdas and some other expressions even if the arguments have holes 19:53:57 that's so strange, and I don't understand what the meaning is supposed to be 19:54:03 I mean, how do you do that in programming? 19:54:53 and it's a bit strange that 51 lets you evaluate (false?$hole:null) 19:56:05 -!- jaboja has joined. 19:56:11 The way a conditional can return variable number of return values is strange, but technically you can imagine like you always get a list of the variable arity they output (like in scheme) and as a concession to easy playing the game, you can freely unpack and repack lists, sort of 19:56:23 it doesn't quite make sense, but it's not the most disturbing thing at first about the game 19:56:23 -!- AnotherTest has quit (Ping timeout: 255 seconds). 19:57:31 in the end, the whole game is so strange I can't make much sense of it, but I'll see what ais says because he knows more about strange logic systems 19:57:59 (logic systems in the sense like modal logic and linear logic and use-once variables etc) 20:01:53 well, #51 also says that [true,star] == [star,true] 20:02:06 as you've probably found out 20:02:23 int-e: oh! I haven't checked that. good idea. 20:03:55 also the items in the bag aren't arranged nicely after the 6th one, sad :) 20:04:19 int-e: well after a while it's hard to display stuff on the screen 20:04:35 bags also don't get nicely arranged when the contained elements are large in screen space 20:04:41 yeah, but up to 9 is still easy 20:18:22 -!- LKoen has quit (Remote host closed the connection). 20:24:22 -!- jaboja has quit (Read error: Connection reset by peer). 20:29:19 -!- jaboja has joined. 20:31:04 -!- moony has joined. 20:31:10 _unidecode ᠍ 20:31:14 err 20:31:20 `unidecode ᠍ 20:31:20 ​[U+0020 SPACE] [U+180D MONGOLIAN FREE VARIATION SELECTOR THREE] 20:39:36 <\oren\> AAAAAAAAAAAAAAAAAA 20:39:42 <\oren\> WHYYYYYYY 20:48:48 what why? 20:49:11 I must be missing the context 20:52:09 -!- sleffy has joined. 21:05:11 -!- sleffy has quit (Remote host closed the connection). 21:20:44 [wiki] [[Funge-98]] https://esolangs.org/w/index.php?diff=52630&oldid=52620 * Btiffin2017 * (+546) /* Examples, add Rock Scissors Paper */ 21:23:00 -!- Naya has joined. 21:23:20 -!- Naya has quit (Quit: -a- IRC for Android 2.1.35). 21:25:21 [wiki] [[Funge-98]] M https://esolangs.org/w/index.php?diff=52631&oldid=52630 * Btiffin2017 * (+7) /* Instructions */ 21:30:44 [wiki] [[Funge-98]] M https://esolangs.org/w/index.php?diff=52632&oldid=52631 * Btiffin2017 * (+0) /* Instructions */ 21:43:02 -!- jaboja has quit (Ping timeout: 255 seconds). 21:50:57 -!- jaboja has joined. 21:59:13 -!- Phantom_Hoover has joined. 22:02:12 -!- jaboja has quit (Read error: Connection reset by peer). 22:02:42 -!- jaboja has joined. 22:09:25 -!- jaboja has quit (Ping timeout: 276 seconds). 22:16:49 -!- jaboja has joined. 22:25:03 -!- LKoen has joined. 22:38:51 -!- sleffy has joined. 22:54:25 -!- btiffin has joined. 22:57:05 -!- Jafet has quit (Ping timeout: 246 seconds). 22:57:25 To the Funge-98 experts in the crowd? I've tried FBBI rcfunge and cfunge, the Input Character function is buffered. For a proper Play again? prompt is it wise to spin on ~ eating newlines? Or are there better options for getting a 'yn' answer that is to be repeated after the next round? 22:57:35 -!- Jafet has joined. 22:58:26 -!- `^_^v has quit (Quit: This computer has gone to sleep). 23:00:01 -!- `^_^v has joined. 23:08:18 -!- `^_^v has quit (Quit: This computer has gone to sleep). 23:24:52 -!- Phantom_Hoover has quit (Ping timeout: 260 seconds). 23:29:25 [wiki] [[Funge-98]] https://esolangs.org/w/index.php?diff=52633&oldid=52632 * Btiffin2017 * (+293) /* Rock Scissors Paper, on 3; updated to ask play again? */ 23:44:28 -!- rdococ has quit (Quit: ZNC - http://znc.in). 23:44:35 -!- rdococ has joined. 23:44:36 -!- rdococ has quit (Changing host). 23:44:36 -!- rdococ has joined. 23:46:03 [wiki] [[Funge-98]] M https://esolangs.org/w/index.php?diff=52634&oldid=52633 * Btiffin2017 * (-32) /* Rock Scissors Paper, on 3 */ 23:57:48 -!- oerjan has joined. 2017-08-02: 00:03:52 -!- LKoen has quit (Remote host closed the connection). 00:06:26 -!- https_GK1wmSU has joined. 00:08:42 -!- https_GK1wmSU has left. 00:52:44 -!- augur has quit (Ping timeout: 240 seconds). 01:19:48 -!- doesthiswork has joined. 01:34:55 -!- wob_jonas has quit (Quit: http://www.kiwiirc.com/ - A hand crafted IRC client). 01:45:16 -!- augur has joined. 01:45:19 -!- sftp has quit (Ping timeout: 246 seconds). 01:47:04 -!- sftp has joined. 01:55:22 -!- jaboja has quit (Ping timeout: 260 seconds). 02:34:44 -!- Sgeo_ has joined. 02:36:04 -!- Sgeo has quit (Ping timeout: 268 seconds). 02:36:49 -!- https_GK1wmSU has joined. 02:37:01 -!- https_GK1wmSU has left. 03:21:26 -!- sleffy has quit (Ping timeout: 255 seconds). 03:34:59 -!- sleffy has joined. 03:36:24 -!- moony has quit (Ping timeout: 260 seconds). 03:48:17 Hah! I constructed an ancient greek pentegon 03:52:37 -!- moony has joined. 04:02:10 -!- sleffy has quit (Ping timeout: 240 seconds). 04:04:50 -!- LKoen has joined. 04:10:10 -!- LKoen has quit (Ping timeout: 276 seconds). 04:10:35 -!- PattuX has quit (Quit: Connection closed for inactivity). 04:12:32 -!- sleffy has joined. 04:17:14 -!- moony has quit (Disconnected by services). 04:17:39 -!- moonythedwarf has joined. 04:34:30 -!- sleffy has quit (Ping timeout: 240 seconds). 04:36:57 -!- sleffy has joined. 04:39:52 -!- MrBrq has joined. 04:42:29 -!- MrBrq has left. 05:37:04 girl genius is recycling material i've already read! it's an outrage! 05:42:17 oh it may get colored 05:44:27 -!- sleffy has quit (Ping timeout: 240 seconds). 05:44:53 -!- sleffy has joined. 06:08:15 -!- moonythedwarf has quit (Quit: Leaving). 06:31:54 -!- erkin has joined. 06:59:43 -!- FreeFull has quit. 07:03:36 -!- sleffy has quit (Ping timeout: 260 seconds). 07:08:59 <\oren\> FUUUUUUUUUUUU 07:09:01 <\oren\> IN EU4 THE EQUATOR DOES NOT PASS THROUGH ECUADOR! 07:09:21 <\oren\> THE MAP IS ALL WRONG WRONG WRONG 07:15:50 <\oren\> http://imgur.com/a/pYQht 07:18:49 -!- augur has quit (Remote host closed the connection). 07:26:12 <\oren\> http://imgur.com/kFg6XT3 07:26:20 <\oren\> Look at this shit! 07:29:24 are you sure it's not the other continents that are too far south hth 07:30:43 <\oren\> oerjan: welll... whatever, relativity and all that 07:30:53 also they've placed italy in the north of africa tdnh 07:32:17 <\oren\> oerjan: no, that was the treaty of lausanne that did that 07:32:54 ah. 07:52:02 a bigger problem is its use of a mercator projection 07:53:05 I think it's a we do what we want projection 07:54:02 I'm inclined to agree with the folks in the Hunting of the Snark. 08:16:36 Girl Genius is showing reruns. I want my money back! 08:19:27 doesthiswork: your complaint is a rerun of oerjan's hth 08:19:32 `complaints 08:19:36 24 share/Complaints.mp3 08:19:45 `? `complain 08:19:46 ​`complain? ¯\(°​_o)/¯ 08:19:53 `w complain 08:19:54 That's not wise. 08:19:57 `grWp complain 08:20:06 No output. 08:27:44 -!- erkin has quit (Remote host closed the connection). 08:28:09 -!- erkin has joined. 08:42:58 -!- MrBusiness has quit (Quit: https://www.youtube.com/watch?v=xIIqYqtR1lY -- Suicide is Painless - Johnny Mandel). 08:50:05 -!- MrBusiness has joined. 08:59:18 -!- spruit11 has joined. 09:17:01 -!- imode has quit (Ping timeout: 255 seconds). 09:28:37 -!- https_GK1wmSU has joined. 09:31:07 -!- https_GK1wmSU has left. 09:59:50 -!- oerjan has quit (Quit: Nite). 10:07:47 \oren\: http://newsthump.com/2017/07/31/scaramucci-fired-after-failing-to-do-the-fandango/ <-- I hope this will be the final Bohemian Rhapsody piece on that guy. 10:27:38 -!- LKoen has joined. 10:59:59 -!- btiffin has quit (Quit: ChatZilla 0.9.93 [SeaMonkey 2.46/20170120202656]). 11:01:55 -!- tromp has quit. 11:12:58 -!- doesthiswork has quit (Quit: Leaving.). 11:15:22 -!- tromp has joined. 11:34:14 -!- boily has joined. 11:40:44 `w 11:40:45 spore//spore stores its input in tmp/spout and displays the nth line (default first). For a version considering irc line lengths, see sport. See also `spam. 11:42:42 Taneb invented mushrooms, so I guess he probably invented spores too. 11:48:01 `? tanebventions 11:48:02 Tanebventions include automatic squirrel feeders, necessity, Go, submarine jousting, Fueue, the universe, special relativity, metar, weetoflakes, mushrooms, sand, dragons, persistence, the BBC, _46bit, cognac, progress, sanity, the Oxford comma, and this sentence. See also tanebventions: maths. He never invents anything involving sex. 11:48:13 indeed. 12:23:55 -!- PattuX has joined. 12:24:39 -!- boily has quit (Quit: EVERYTHING CHICKEN). 13:22:01 -!- jaboja has joined. 13:41:18 -!- jaboja has quit (Read error: Connection reset by peer). 13:41:59 -!- jaboja has joined. 13:45:23 -!- jaboja has quit (Read error: Connection reset by peer). 13:45:32 -!- jaboja has joined. 13:49:58 -!- jaboja has quit (Read error: Connection reset by peer). 13:51:11 -!- jaboja has joined. 13:52:52 -!- ski has quit (Ping timeout: 260 seconds). 13:55:47 -!- jaboja has quit (Read error: Connection reset by peer). 13:56:01 -!- jaboja has joined. 14:00:30 -!- doesthiswork has joined. 14:04:17 -!- jaboja has quit (Ping timeout: 246 seconds). 14:06:44 -!- jaboja has joined. 14:12:10 -!- jaboja has quit (Ping timeout: 240 seconds). 14:31:07 -!- joast has quit (Ping timeout: 246 seconds). 14:39:43 -!- `^_^v has joined. 14:45:46 -!- jaboja has joined. 14:49:44 -!- erkin has quit (Remote host closed the connection). 14:50:07 -!- erkin has joined. 15:05:25 -!- Cale has quit (Ping timeout: 246 seconds). 15:07:52 -!- joast has joined. 15:10:02 -!- doesthiswork has quit (Quit: Leaving.). 15:11:08 -!- sdhand has quit (Excess Flood). 15:11:31 -!- sdhand has joined. 15:11:42 -!- sdhand has quit (Changing host). 15:11:42 -!- sdhand has joined. 15:18:11 -!- Cale has joined. 15:23:44 -!- jaboja has quit (Ping timeout: 258 seconds). 15:38:57 -!- erkin has quit (Quit: Ouch! Got SIGABRT, dying...). 15:50:07 [wiki] [[Special:Log/newusers]] create * SpeedTime * New user account 15:51:50 [wiki] [[Special:Log/newusers]] create * Plantagenet * New user account 16:09:20 -!- impomatic has quit (Quit: http://corewar.co.uk). 16:32:24 -!- AnotherTest has joined. 16:42:22 -!- LKoen has quit (Quit: “It’s only logical. First you learn to talk, then you learn to think. Too bad it’s not the other way round.”). 16:55:21 -!- AnotherTest has quit (Ping timeout: 258 seconds). 16:58:36 -!- sleffy has joined. 17:15:12 [wiki] [[Cubix]] https://esolangs.org/w/index.php?diff=52635&oldid=49843 * SnoringFrog * (+55) adding D comand 17:15:26 -!- FreeFull has joined. 17:20:48 -!- AnotherTest has joined. 17:25:52 -!- sdhand has changed nick to [f][r][o][g][b][. 17:27:08 -!- [f][r][o][g][b][ has changed nick to [s][a][m]. 17:42:28 -!- AnotherTest has quit (Ping timeout: 240 seconds). 17:44:51 -!- AnotherTest has joined. 17:59:34 -!- AnotherTest has quit (Ping timeout: 276 seconds). 18:02:10 -!- sleffy has quit (Ping timeout: 246 seconds). 18:07:06 -!- [s][a][m] has changed nick to sdhand. 18:11:50 -!- erkin has joined. 18:15:10 -!- sleffy has joined. 18:15:49 -!- Phantom_Hoover has joined. 19:00:41 if anyone cares, #esoteric is now channel number 38 out of 84 that lambdabot joins... should get here sooner after restarts. (I reprioritized the non-core-haskell channels based on channel population count, and #esoteric is quite large) 19:09:35 int-e: Maybe #reflex-frp would make a good addition as well? :) 19:09:54 (I manually joined it there a little while back) 19:12:50 looks good, adding it... 19:15:06 [wiki] [[Befunge]] M https://esolangs.org/w/index.php?diff=52636&oldid=52606 * Btiffin2017 * (+63) /* Befunge-98 and beyond */ 19:25:49 -!- augur has joined. 19:48:03 -!- imode has joined. 19:51:20 -!- MrBismuth has joined. 19:53:46 -!- MrBusiness has quit (Ping timeout: 255 seconds). 19:56:45 <\oren\> WILLIAM SHATNER IS A BRONY 20:00:21 source or die. 20:00:53 -!- sleffy has quit (Ping timeout: 258 seconds). 20:07:11 <\oren\> imode: look at his twitter 20:08:00 oh my god he's shitposting. 20:08:19 -!- shikhin has changed nick to shikbie. 20:08:25 <\oren\> yeah... he also in one tweet implied he posts on 4chan 20:08:28 -!- MrBismuth has quit (Ping timeout: 240 seconds). 20:08:46 I wonder if that's actually him or a PR dude. 20:08:48 *shrug* 20:16:04 -!- tromp has quit (Read error: Connection reset by peer). 20:16:10 -!- tromp has joined. 20:17:34 -!- MrBusiness has joined. 20:32:37 -!- MDude has quit (Quit: Going offline, see ya! (www.adiirc.com)). 20:34:45 -!- sleffy has joined. 20:41:04 -!- MrBusiness has quit (Ping timeout: 246 seconds). 20:48:40 -!- sleffy has quit (Ping timeout: 255 seconds). 20:51:36 -!- MrBusiness has joined. 20:54:26 Imagine a language which uses "yes" and "no" for its boolean values, rather than "true" and "false". 20:59:05 -!- AnotherTest has joined. 20:59:19 <\oren\> rdococ: kOS uses On and Off 20:59:42 <\oren\> eg. to set the variable X to true, you say: 20:59:46 <\oren\> X ON. 20:59:51 ah 21:00:13 imagine extending On and Off with something that doesn't translate to the true/false dichotomy, e.g. In 21:00:28 Hare Krishna. ♥ 21:03:13 -!- AnotherTest has quit (Ping timeout: 240 seconds). 21:05:30 -!- AnotherTest has joined. 21:05:41 rdococ: there was a codebase I worked on that replaced booleans with bitwise flags, and we had to use _valid for true and _invalid for false. 21:06:22 it was convenient because if you wanted to signal multiple conditions you could (because you were returning a uint), but it ended up with us just aliasing things to true and false. :P 21:07:27 heh 21:11:36 -!- `^_^v has quit (Quit: This computer has gone to sleep). 21:11:39 imode: 7 21:11:56 7? 21:12:05 7. 21:12:25 the three bit flags that I turned on happened to be at the least significant end, but their meaning is most significant. 21:12:41 lmao. 21:12:55 19. 21:13:01 :P 21:13:06 one on, two off, two on. :P 21:13:36 one on, two on, three off, four on, five on. 21:13:39 we basically treated uints as bit arrays with macros to access individual bits. 21:13:54 like an array of booleans 21:13:57 yuh. 21:14:16 Wait. Each bit's index in the bit array is its own bit array. 21:14:24 hahahahahaha. 21:14:39 it's bit arrays all the way down. 21:16:10 Not only can you store bit arrays, you can store sets of bit arrays. 21:16:18 In fact, not just sets. 21:18:33 A bit array is an associative array that maps bit arrays to bits. Which means that it is an associative array that maps associative arrays that map bit arrays to bits, to bits. 21:19:00 yo dawg. 21:19:05 -!- AnotherTest has quit (Ping timeout: 258 seconds). 21:19:20 -!- AnotherTest has joined. 21:20:27 A class of associative arrays that map themselves to bits. 21:21:43 Imagine an entire self-referential language in which every class is defined this way. 21:22:25 So you have class number = {number -> bit}. Now you can have class array = {number -> number}, which is also {{number -> bit} -> {number -> bit}}. 21:22:55 hm. 21:23:55 A set maps objects (including numbers and arrays) to bits. So here's the twist: a set of numbers is a number. 21:24:41 huh. you're doing something that's close to what I'm doing. 21:24:47 storing paths in a binary tree as unsigned integers. 21:25:10 At least a finite set containing finite numbers, anyway. 21:25:34 Transfinite ordinals might work the same way, but I'm not sure. 21:25:44 We are, after all, dealing with powers of two. 21:25:57 -!- erkin has quit (Quit: Ouch! Got SIGABRT, dying...). 21:27:17 https://ptpb.pw/2bPr/python check this out 21:28:23 Woah. 21:28:37 storing/encoding binary trees. 21:29:09 Holy nuts. 21:29:09 the way it works is you provide a path to a node (in the form of left/right instructions) 21:29:44 and on every query for a node (meaning, you go left, right, then left, then ask if a node is there), we simply trace all the way back to the root of the tree from that node. 21:29:57 if your node happens to fall upon that path, we output a '1'. if not, we output a '0'. 21:30:48 !Warning! Mind has reached critical meta and explosion is imminent. Evacuate immediately. !Warning! 21:31:04 if you run the python script, it actually prints out the resulting tree. 21:31:28 is it python 2.x or 3.x? 21:31:37 3. but it should just work. 21:31:52 yeah it works with 2. 21:32:31 hm. what's __name__? 21:32:40 I'm not acquainted with python, so idk. 21:33:13 that's just some code to run the file if you call, rather than importing it. 21:33:18 err, run the main function. 21:33:22 ah. 21:33:30 makes sense. 21:33:35 otherwise main() would run on every import. 21:33:39 yeah. 21:34:18 what I wanted was something additive. meaning, to construct a binary tree in memory, updates don't have to come in order. 21:34:35 ah. 21:35:01 '0000' is 'fork left four times'. '10000' is 'fork right once, then left four times.' 21:35:12 regardless of when these arrive, the structure is the same. you can even re-order them. 21:35:46 cool. 21:36:12 10110 is "fork right once, then left once, then right twice, then left once", right? 21:36:18 yup. 21:36:27 any node on that path is now valid. 21:36:32 what content does each node have? 21:36:46 none. but it's trivial to ship your data after the fact. 21:37:02 or build it in like an associative array. 21:37:06 is each tree defined as an array of these numbers, then? 21:37:07 "this path maps to this binary blob." 21:37:12 yup. 21:37:20 ah, makes sense. 21:37:36 this tree, for example, contains 26 unique nodes across all the paths. 21:38:04 the resulting list, [15, 47, 271, 2191, 111, 4385], can all be stored as two-byte numbers if you're really hamfisted about it. 21:38:17 -!- wob_jonas has joined. 21:38:18 so your 26-node tree is encoded in 12 bytes. 21:38:22 heh 21:38:57 the cool part is that it's also a sort of database. you can query for a partial path, delete a node along that path, and then the rest of the paths become invalid because they matched. 21:39:00 "<\oren\> WILLIAM SHATNER IS A BRONY source or die." => imode: he's voiced a character in S7 E13 21:39:11 wob_jonas: hahaha oh god. 21:40:07 imode: So say you took the tree from the demo, and removed "0001". Would that make 00010000, 00010010000 and 000100100010 invalid too? 21:40:08 -!- https_GK1wmSU has joined. 21:40:34 correct. you say "remove all paths corresponding to this prefix 0001." 21:40:37 ah. 21:40:45 meaning "delete the node at left,left,left,right. 21:40:57 -!- https_GK1wmSU has left. 21:40:57 which means its children are orphans. 21:41:15 :O 21:41:17 now, you can -not- do that. another path may pick up the slack later. 21:41:27 meaning, say, if you wanted to do an arbitrary insertion. 21:41:43 or a replacement. it's a lot easier than messing with pointers. 21:41:56 and at that level, your paths take up less than a machine word's worth of space. 21:43:12 I mean, that demo decodes to... {{*,*,*,*},*,*,*},*,*,{*,*,{*,*,{*},*},*}} 21:43:43 Hm. If a path, e.g. "001100", has leading 0s, simply converting it into an integer would remove the information and make it indistinguishable from "1100" or "00001100". How do you convert it? 21:43:58 that's in the path function. 21:44:18 I take the traditional approach of only dealing with nodes in a complete binary tree. 21:44:22 ah. 21:44:38 which means that for a given node N, children are located at 2n+1 and 2n+2. 21:44:49 and parent is located at n-1/2 21:44:52 Makes sense, I suppose. 21:45:21 this way given a bit's index (a number), I can trace all the way back towards the root of the tree just by calling parent until I hit it. 21:45:30 ah. 21:45:45 Wait, (n-1)/2?! 21:45:49 Oh, ah. 21:45:50 mhm. 21:46:10 I assume there's some rounding there (especially since the code uses bit shifting). 21:46:18 That's... actually really clever. 21:46:18 correct, integer arithmetic. 21:46:24 pretty standard for heaps. 21:47:15 here's something that'll twist your mind. because we can map integers onto unique paths for a binary tree, we can create functions that generate infinite or bounded trees with a certain pattern, compose them, and traverse the results. 21:48:00 for example, checking if the number is even yields only right branches from a given node. 21:48:02 ...Wait. 21:48:18 Hold on, let me reread that. 21:48:38 short version: I can write functions to generate infinite trees and compose them together. 21:48:55 in fact, let's do an experiment. 21:49:09 Wait - are these infinite trees finite in their format as an array of integer paths? 21:50:50 -!- AnotherTest has quit (Ping timeout: 246 seconds). 21:51:33 https://ptpb.pw/UnFc/python run this. 21:51:43 look at the second tree() function. 21:51:58 -!- AnotherTest has joined. 21:52:48 notice how I'm not running through a list of paths or anything. the code is doing the work. 21:54:11 woah, recursion 21:54:27 in traverse(), yeah. 21:54:34 just a standard left/right traversal. 21:55:28 brb, piecing my brain back together 21:55:52 the way I envision it is taking the infinite full binary tree and carving paths out of it. it's somewhat similar to raymarching, where you can compose transforms on distance functions to yield a scene. 21:56:05 sort of playing with 1D space. 21:56:28 wait, so an infinite tree which is stored as its complement? 21:56:40 there's nothing stored here. 21:56:49 ...wait, what? 21:56:50 you could remove the list in main() and it'd still work. 21:57:04 the second tree() function is generating the tree based on which node gets queried. 21:57:31 Ahh. 21:57:32 if the node you're on's index is divisible by 4, you'll see that it doesn't exist in the tree. 21:57:41 if it isn't, then the node exists in the tree. 21:58:01 Ahhh. 21:58:14 (the first if statement is just to limit it to a few levels. 21:58:21 That makes sense. 21:58:42 This is similar to infinite lazy lists. 21:58:46 so imagine this. you have a set of primitive functions that you can compose together to make any tree you'd like without having to store anything. 21:58:50 yup. 21:58:55 In fact, it IS infinite lazy lists. 21:59:11 essentially, yeah. :P 21:59:20 Makes sense, somehow. 21:59:50 ARGH! 21:59:56 eh? 21:59:56 I was working on encoding nested lists of atoms (just unlabeled trees) in as small a format as possible, and I just ended up here. 22:00:54 I still hate how font creators for latin script always put a fucking fi ligature in their font that is very distinctive from just a plain fi with possibly slight kerning, even if such a ligature looks bad in that font, just to try to signal that their font is well-made and high-classed. 22:00:54 go change the modulo parameter to see how it adds and eliminates paths. 22:01:12 The way I understand it, ["0001", "000100", "00011"] is the same list as ["000100", "00011"], yes? 22:01:14 Sure, and fi ligature may look nice in a Times-like font, but in most fonts it's just freaking ugly. 22:01:15 s/list/tree 22:01:27 -!- `^_^v has joined. 22:01:54 rdococ: in the original script, yes. 22:02:06 Not in the second script, though? 22:02:18 And yes, I know I keep complaining about this. 22:02:19 well, the second script doesn't use lists of paths to traverse a tree. :P 22:02:23 heh 22:02:59 but yeah, that's the idea. paths are additive. meaning if two paths share the same prefix, you can always select the longer one and the shorter one will remain valid. 22:03:49 ah. 22:03:55 this is useful because if you say "oh I want to insert at this point in the tree", you don't have to do anything. you just have to say "oh this path is now valid." and optimize later. 22:04:05 heh 22:04:26 like, if you had a series of right branches, 0000, and you wanted to branch -one more time- after that, you could either edit the path to 00000, or just add 00000 to the list of paths. 22:05:29 if you're playing the home game you'll notice that you can encode arbitrary lists like this. :P 22:09:08 -!- AnotherTest has quit (Ping timeout: 255 seconds). 22:09:33 rdococ: for example, 00010010000 and 000100100010.. you can always choose the latter, because it still yields a valid path for the former. the same goes with 00010000 and 0000. 22:10:28 -!- `^_^v has quit (Quit: This computer has gone to sleep). 22:11:16 though actually, now that I'm looking at it, unless you choose it very carefully, some of those forks are invalid. 22:11:24 -!- MDude has joined. 22:14:18 moo. 22:14:44 you mean 0001001000 and 000100100010, right? 22:15:00 yup. 22:15:32 I already gathered that :P 22:15:42 I'm gonna try mod 5 22:15:49 do it. it's pretty trippy. 22:16:08 if you do mod 2, and then mod 3, you can see how it adds an entire left traversal. 22:16:11 woah, it made the tree even larger 22:16:34 * imode wonders if he could form a bitwise trie... 22:16:56 mainly to do prefix sharing. 22:18:19 -!- shikbie has changed nick to shiklet. 22:22:11 nah. that'd be more trouble than it's worth. what I could do is just do it on the db side and say "well okay, I'm going to be using this path entry as my prefix now." 22:22:14 and do parent prefixes. 22:23:14 PARENTAL ADVISORY 22:23:24 Explicit Content 22:23:41 so one path could look like (Null, 00010000), and another could look like (1, 000), and another could look like (1, 0010). 22:24:23 so the paths generated would be 00010000, 00010000000, and 000100000010. 22:24:29 -!- `^_^v has joined. 22:24:43 but with the overhead being smaller because you wouldn't have to repeat the prefix each time. 22:26:42 heh 22:27:44 a 26-node tree in 6 bytes isn't that bad though. 22:28:17 agreed 22:28:48 nice, mod 2 creates a left-only tree 22:29:36 and %2==1 is a right-only tree - makes sense 22:29:36 mhm. if you invert the conditions (so that it outputs a '1' instead of a '0' and vice versa), you'll create a right-only tree. 22:29:45 or do that. :P 22:29:49 heh 22:31:25 for some reason, I'm beginning to understand the structure of the tree system by only looking at the output rather than the code 22:31:44 that's the benefit of a quickly added depth variable. :P 22:31:49 heh 22:32:25 id:depth:latest_turn 22:32:33 yup! 22:32:38 id == index in this case. 22:32:58 it's cryptic because it's a scratch file. 22:34:26 I assume the bottom line of output is the tree converted into one integer 22:36:52 how is that done? 22:37:35 so that's actually just a depth-order traversal in binary. 22:37:41 ah. 22:37:47 0's are lefts, 1's are rights. 22:38:09 oh, I see the correlation now. 22:38:56 I'd like to encode text and such via this. 22:40:10 i.e get the ordinal for a given character, split it up via its decimal digits, encode said digits as a tree traversal. 22:48:47 <\oren\> Un problema en Las Toninas hace que Internet funcione mal en todo el país 22:48:53 <\oren\> En el balneario hay un cable que es la principal fuente de fibra óptica de todo el país. En una de ellas hay inconvenientes y, por eso, hay dificultades de conexión en todo el territorio argentino. 22:49:00 <\oren\> Este cable tiene una extensión total de unos 20 mil kilómetros y forma parte del SAC (siglas de South American Crossing), un anillo interoceánico que bordea América del Sur y provee conectividad a diversos países de la región. 22:49:29 <\oren\> The entire country of Argentina is having internet problems 22:50:16 odd 22:53:23 -!- hppavilion[1] has joined. 23:15:52 hppavilion[1]! 23:15:59 rdococ! 23:16:56 -!- `^_^v has quit (Quit: This computer has gone to sleep). 23:23:16 -!- Phantom_Hoover has quit (Ping timeout: 276 seconds). 23:23:55 -!- https_GK1wmSU has joined. 23:24:32 -!- https_GK1wmSU has left. 23:29:32 -!- wob_jonas has quit (Quit: http://www.kiwiirc.com/ - A hand crafted IRC client). 23:30:07 -!- wob_jonas has joined. 23:33:05 -!- boily has joined. 23:33:07 @metar CYUL 23:33:07 CYUL 022200Z 22006KT 15SM FEW040TCU BKN240 29/17 A2993 RMK TCU2CI4 SLP138 DENSITY ALT 1800FT 23:39:23 ba na na na 23:40:12 hm. Some (human) languages utilize echo answers instead of yes/no ("Did you fart?" "I did fart.") 23:40:32 what happens if we translate that to the realm of programming? "2 == 3" returns "2 ~= 3" 23:40:41 rdochellochelloc. 23:42:31 hoily. 23:42:57 `cat bin/makelist 23:42:58 if [[ "$1" == *" "* ]]; then exec makelist $@; fi; name="$1"; file="bin/$name"; makelistlist "$name"; shift; cp bin/emptylist "$file"; for n in "$@"; do echo "$n" >> "$file"; done 23:43:46 `makelist ysaclist boily shachaf 23:43:49 makelistlist ysaclist: shachaf 23:44:00 hm 23:44:05 Ah, right. 23:44:08 -!- imode has quit (Ping timeout: 240 seconds). 23:46:44 <\oren\> I thought suv was a regular word, prnounced like "sub" but with a v 23:46:46 `ysaclist (63) 23:46:46 ysaclist (63): boily shachaf 23:46:52 heh, it works ^^ 23:47:07 <\oren\> `? suv 23:47:08 suv? ¯\(°​_o)/¯ 23:47:10 he\\oren\! long time no see. 23:50:07 <\oren\> `learn A suv /sʌv/ is used to transport toddlers of various sizes. 23:50:09 Learned 'suv': A suv /sʌv/ is used to transport toddlers of various sizes. 2017-08-03: 00:02:18 That bugs me so much 00:02:19 holy fungot it's pouring like crazy... 00:02:19 boily: sometimes i wonder if it keeps it the jury people so close for weapons and everything changes so quick that eight years ago)) 00:02:25 @metar CYUL 00:02:25 CYUL 022200Z 22006KT 15SM FEW040TCU BKN240 29/17 A2993 RMK TCU2CI4 SLP138 DENSITY ALT 1800FT 00:02:35 @metar PAMR 00:02:35 PAMR 022253Z 01004KT 10SM FEW049 OVC060 16/12 A3019 RMK AO2 SLP225 T01610117 00:06:27 -!- sleffy has joined. 00:26:48 -!- augur has quit (Quit: Leaving...). 01:02:04 -!- sleffy has quit (Ping timeout: 276 seconds). 01:11:30 -!- http_GK1wmSU has joined. 01:11:32 -!- http_GK1wmSU has left. 01:17:31 `5 w 01:17:36 1/2:dy//dx = y \ htdh//HtDH is a classic text on How to Design Hotdogs or possibly Hogprams. It is all about functional condiments, and was co-authored by Herence Tao and Don Ho. \ gonad//gonads are the best punctional fondlegramming squishcture. \ golf//Golf is the shortest game known. The goal is to get a ball into a hole with a single stroke. \ 01:17:37 `n 01:17:38 2/2:category-helpdesk//category-helpdesk is a helpdesk with identity and composition. This channel isn't it. 01:21:02 -!- doesthiswork has joined. 01:27:42 -!- augur has joined. 01:39:05 mo 01:49:22 * boily mapoles rdococ into complete words 01:49:27 -!- wob_jonas has quit (Quit: http://www.kiwiirc.com/ - A hand crafted IRC client). 01:49:45 -!- imode has joined. 01:53:44 `? rdococ 01:53:45 rdococ was thought to be from Budapest, then Mars, but he is actually in Airstrip One. Thanks to boily he is approaching permanent boredom & mapoledom. He is a relative of `words. 01:54:19 `? imode 01:54:20 imode? ¯\(°​_o)/¯ 01:54:24 :( 01:55:10 "IMODE - Innovative Multicomponent Drug Design" 01:55:15 imode: are you innovative? 01:55:24 imode: are you componentised? 01:55:26 imellode, ybdellon! 01:55:30 imode: do you design drugs? 01:55:41 belloily! 01:56:10 hybden 01:56:11 imode: do you have a severe (or not so severe) case of the UPPERs? 01:56:31 shachaif 01:56:40 -!- sdhand has quit (Ping timeout: 276 seconds). 01:56:43 `le/rn imode//imode is an Innovative Multicomponent Drug Designer, afflicted by a severe case of the UPPERs. 01:56:44 imode: if you do could you suggest a replacement for amphetamines that doesn't increase my heart rate? 01:56:45 I may design drugs. 01:56:45 Learned 'imode': imode is an Innovative Multicomponent Drug Designer, afflicted by a severe case of the UPPERs. 01:57:04 `? ybden 01:57:05 ybden daintily hides in her den, fostering dark machinations on warfare cutlery. 01:57:06 ybden: http://kmcallister.github.io/complexity.html 01:57:13 -!- sdhand has joined. 01:57:36 -!- sdhand has changed nick to Guest94226. 01:58:15 shachaf: To-day I have learned that I should be careful around drugs, lest I mistake them for complexity classes 01:58:57 -!- boily has quit (Quit: EXECUTIVE CHICKEN). 02:00:10 just ask yourself "what would Erdős do?" 02:05:22 `? UPPERs 02:05:23 UPPERs? ¯\(°​_o)/¯ 02:08:17 There's a new SpecGram out http://specgram.com/CLXXIX.3/00.contents.html 02:36:20 -!- MDude has quit (Quit: Going offline, see ya! (www.adiirc.com)). 02:37:56 i swear i just heard jaku say bjonas in a video 02:41:05 ?Qien es jaku? 02:41:05 Unknown command, try @list 02:45:48 -!- PattuX has quit (Quit: Connection closed for inactivity). 03:16:58 -!- sleffy has joined. 03:42:37 `5 w 03:42:42 1/2:hertz//hertz (German for heart) is an SI unit equal to the frequency of an average heartbeat. \ nih//NIH was /not/ invented by Taneb. \ rntz//rntz is a classically-trained logician known for his constructive criticism. \ fact//Facts are lies. They are not there. Go away! \ infidel//An infidel is someone who doesn't support the great former lead 03:42:44 `n 03:42:45 2/2:er. Socialismo o muerte! 03:59:58 -!- hppavilion[1] has quit (Ping timeout: 246 seconds). 04:28:31 Dicotomías de rechazo 04:28:43 Socialismo Y muerte! 04:45:16 `5 04:45:17 1/3:411) 99% OF USES OF STRDUP ARE ILLEGAL! \ 785) my best guess is 4 years ago but possibly also yesterday \ 1285) I couldn't help thinking that maybe if one considers the ramifications in full detail it will turn out that overthinking is often not helpful and therefore, not something to be proud of. \ 746) `n 04:45:23 2/3:er> i once had a dream when i was told to look after some kittens but they were made of chocolate and i ate them :( \ 878) the idea is that you can get the information you need from reading the other players, isn't it [...] and of course, reading isn't limited to facial expressions [...] That's true, you can read e.g. boo 04:45:25 `n 04:45:25 3/3:ks. 04:45:38 What is the context of 411? 04:45:57 `` doag quotes | grep STRDUP 04:46:03 No output. 04:46:21 `` hg cat -r 1 quotes | grep STRDUP 04:46:23 99% OF USES OF STRDUP ARE ILLEGAL! 04:46:26 figures 04:46:40 I'd like to know too. 04:47:25 * imode ponders an alternate tree indexing scheme. 04:47:45 The context is 2011-07-22 05:12:12 -!- brandonson has quit (Ping timeout: 260 seconds). 05:13:41 -!- brandonson has joined. 06:36:32 -!- erkin has joined. 06:56:09 -!- doesthiswork has quit (Quit: Leaving.). 06:59:54 -!- FreeFull has quit. 07:01:16 -!- Guest94226 has changed nick to sdhand. 07:01:32 -!- sdhand has quit (Changing host). 07:01:32 -!- sdhand has joined. 07:26:37 -!- augur has quit (Remote host closed the connection). 07:27:11 -!- augur has joined. 07:31:39 -!- augur has quit (Ping timeout: 258 seconds). 08:19:32 -!- sdhand has quit (Excess Flood). 08:19:45 -!- sdhand has joined. 08:20:08 -!- sdhand has changed nick to Guest79676. 08:31:32 -!- Guest79676 has quit (Changing host). 08:31:32 -!- Guest79676 has joined. 08:31:32 -!- Guest79676 has changed nick to sdhand. 08:43:49 -!- sleffy has quit (Ping timeout: 246 seconds). 09:15:50 -!- imode has quit (Ping timeout: 240 seconds). 09:43:26 [wiki] [[Funge-98]] https://esolangs.org/w/index.php?diff=52637&oldid=52634 * Btiffin2017 * (+9501) Add Fingerprints blurb and table 09:47:09 Some of those links are incorrect since rcsfingers.html is only for the RCS-defined ones 09:47:46 E.g. NCRS is not from there 09:48:50 Not sure if this Btiffin2017 is on this channel though. 09:59:39 [wiki] [[Funge-98]] https://esolangs.org/w/index.php?diff=52638&oldid=52637 * Deewiant * (+141) Link original docs for jvh fingerprints 10:04:21 fizzie: Please link the original ext_SOCK.txt from GLfunge98, I don't think it's up at http://glfunge98.sourceforge.net directly 10:07:03 [wiki] [[Funge-98]] M https://esolangs.org/w/index.php?diff=52639&oldid=52638 * Btiffin2017 * (+6) /* Example of fingerprint loading */ 10:11:04 [wiki] [[Funge-98]] M https://esolangs.org/w/index.php?diff=52640&oldid=52639 * Btiffin2017 * (-38) /* Some well known fingerprints */ 10:11:23 -!- erkin has quit (Quit: Ouch! Got SIGABRT, dying...). 10:11:52 [wiki] [[Funge-98]] https://esolangs.org/w/index.php?diff=52641&oldid=52640 * Btiffin2017 * (+38) Undo revision 52640 by [[Special:Contributions/Btiffin2017|Btiffin2017]] ([[User talk:Btiffin2017|talk]]) 10:13:16 -!- btiffin has joined. 10:14:10 Sorry Deewiant, I undid one of your fixes as I thought I made a mistake on the origin. Undid my erroneous edit. ;-) 10:25:51 [wiki] [[Funge-98]] https://esolangs.org/w/index.php?diff=52642&oldid=52641 * Btiffin2017 * (+613) /* Stack Stack */ 10:38:31 [wiki] [[Funge-98]] https://esolangs.org/w/index.php?diff=52643&oldid=52642 * Btiffin2017 * (+764) /* Concurrency */ 10:46:17 funge 10:46:18 tasty 10:54:22 salty 10:57:42 btiffin: The link for SCKE is still wrong, but I'm not sure if the original doc is available online directly. It should be in the tarballs at http://glfunge98.sourceforge.net but it's less than ideal to link to those... I already asked fizzie about it. 11:01:24 Deewiant: thanks for the updates. Page needs a good History section and some nice credits in the Implementation part. Will try and track down and gather up some blurbs worthy of the page. And will appreciate corrections to the guaranteed mistakes that will be made. 11:06:16 Haven't built CCBI yet, but your mycology kit has really upped the game for the implementations it seems. Grand work, Deewiant, it's nice being able to play and not have things jump and catch fire. 11:07:06 Thanks, and yeah, didn't really expect it or Funge-98 to become so popular 11:08:34 You might need some good luck building CCBI these days... D 1.0 hasn't been supported in ages, hopefully at least some of the tools still work 11:08:43 Consistent and reliable toys makes for good toys, worthy of some time in. 11:10:22 I had a 1.0 D, but that machine gave up the ghost a while back, might have the archive in a state that can be restored (but, a backup untested is usually borked, right? Just because) ;-) 11:11:05 One of my projects for years has been to build a new interpreter in C, starting with a solid Funge-Space library... which has been a work in progress since 2011 and has seen almost no work since 2013 or so. (These days I might go for Rust for the interpreter itself though.) 11:12:25 Coïncidentally, 2013 is when I graduated from university. 11:13:09 Only been funging for a week on and off, but NEED libfunge for embedding in COBOL. ;-) libfunge, someone needs to treat Funge like a Lua and take over the world from within. 11:13:12 It's funny how badly having a full-time job eats your free time, as opposed to school/uni 11:14:31 Oh, I turn 54 in a few days, I still have a final year to complete (my ID started with 82). Might not make it to grad. ;-) 11:18:19 Heh, I don't think the universities around here let people do that kind of thing any more :-) 11:23:40 I do miss Waterloo. I started the day they dragged the last card punch machine out of the Pit and into a museum. I kinda don't miss the 8K machines of the time though, them be good old days only in the sense of, "really? they were good? those old days?" 11:28:47 bechocolatefudge 11:29:04 -!- erkin has joined. 11:30:09 A computer without Funge is a like a piece of chocolate cake without mustard and ketchup 11:31:34 so... good? 11:31:59 Best 11:32:20 * rdococ needs fresh concepts 11:32:26 I FEAST ON CONCEPTS!!! 11:34:45 -!- boily has joined. 11:34:46 btiffin: About Mycology, gotta credit Vorpal as well in the game-upping, for doing cfunge and actively discussing issues that came up. In a way there's some luck involved in that he did it when I was still available for doing my part in the discussions and whatnot, but still. 11:35:14 Try inventing something with the elegance of Forth with the human friendly syntax of algebra (not reverse polish). REBOL Red come close, but the editor and file system access needs to be part of the language so there is zero brain swapping during development. 11:36:24 Deewiant, I'll likely pester the IRC room when writing up a history blurb and try and pack it with names that deserve recognition. 11:36:47 Sure. 11:39:43 My go to implementations are cfunge and rcfunge at the moment. Too much fun. These are all fairly amazing pieces of work, but I'm still leaning to mycology being a root cause of the robustness. 11:41:16 I seem to recall that rcfunge still had some quirks, cfunge should be solid though 11:44:26 fudge! 11:45:04 The main selling point of CCBI these days is probably the interactive debugger, I'm not sure if anybody else implemented something like that 11:45:08 Yeah, rcfunge BOOL unload isn't correct; easy fix (umm, I think - it looked straight forward, but maybe I'm too new); but I want to play with the Tardis so rcfunge will get a workout. cfunge is the default funge here. 11:45:53 rdococ: mustard funge 11:48:40 Will strive to get CCBI built shortly. It would be nice to be able to point to one as the "reference" implementation; FBBI just advertises as 'early, not reference'. 11:53:00 I think FBBI is the closest you can get to a reference since it's by the same guy as the spec. Too bad it contradicts the spec (or at least used to) so much... 11:53:42 In a way CCBI was used as a reference since at least Vorpal admitted to sometimes just checking its source for how to do things when Mycology spat out an error. :-P 11:53:55 :-) 11:57:09 libfunge, the world needs a libfunge, something with an init, a go, and a let me at the resulting stack(s) and funge space, simple API 12:00:14 You can probably write one that works by shelling out to CCBI's debugger ;-) 12:01:42 Unfortunately "simple API" may turn out to be not so simple with funny Funge-Spaces and abstraction-breaking fingerprints 12:02:03 Hmm... 12:03:51 Depends on what you want out of it, of course. 12:05:37 Yeah, I guess simple in this case would be low number of function entry points for a make it work mode. And then side functions for deeper mining. Like Tcl, only more mustard-ey. A ten line C file to embed a funge and then 80 meg of API docs for figuring out what else you can do. 12:06:22 Sure, init and go should be simple enough. 12:06:42 It's the "let me at it" part where things get tricky. 12:07:09 TRDS for instance. 12:09:00 Then read stack to get results, and a way to peek into final Funge space. Details on access to running programs would be part of the 80 megs of API. 12:10:05 Still reading up on TRDS before attempting a script, but looking forward. 12:13:25 Ah, only the final state. Yeah, that should be simpler. Still there's some funky stuff about the stack, e.g. MODE, and Funge-Space is basically a sparse 2^N * 2^N square (or cube or worse) (with N = 32 or N = 64 typically) so I'm not sure what kind of API would be suited for anything beyond "read from x,y" style operations 12:13:48 From a GnuCOBOL perspective it would be nice as CALL "funge" USING script RETURNING answer; default easy mode just returns top of stack cell. "funge-stack" could provide more and "funge-space" just does a get on a vector after the run. 12:19:51 or range, similar to i and o, and that would make a toy people could brag about; and then you know ignore, except for the odd fan that flames the admiration. 12:23:58 Yeah, I added i-like display of an area to the CCBI debugger, was quite useful at times 12:24:18 It's all there, just hook it up ;-) 12:26:01 -!- boily has quit (Quit: TRAP CHICKEN). 12:29:43 I work with GNU, and asked the mailing list if I could get an alias for brainfuck in the Guile binding. Most of the dev group hadn't heard about it, and thought I was just swearing at them. The goal was to add documentation to the GnuCOBOL FAQ without swearing. Richard Stallman gave me a small talking down to until someone else posted the wikipedia link and saved my rep. End of the day,... 12:29:45 ...I folded (and agree), brainfuck is simply not mentioned as one of the possible integrations to GnuCOBOL in any manuals. Funge would be something that could be written down with the expectation that wouldn't offend anyone like an IBM president or Church Lady. 12:32:01 Heh. 12:45:23 -!- mroman has joined. 12:45:38 Is there some neat way to get dx, dy in a grid system for a given radius 3 12:45:44 and I only want the outermost fields 12:46:01 i.e. not for(dx=-r;dx<=r;dx++) for(dy=-r;dy<=r;dy++) 12:46:09 as this will also give pixels that don't exactly have a distance of r 12:47:12 *radius r 12:49:50 Deewiant; hope to chat again, time to call it a day, and once again, thanks for the updates. 12:50:08 No worries, talk to you later. 12:51:07 -!- btiffin has quit (Quit: ChatZilla 0.9.93 [SeaMonkey 2.46/20170120202656]). 13:09:06 mroman: I feel like you can use some trig functions for that 13:09:17 I seem to have forgotten how maths works though 13:10:08 http://codepad.org/nPcmCam2 <- something along the lines of this 13:10:12 but this is really inconvenient. 13:33:39 -!- mroman has quit (Ping timeout: 260 seconds). 14:00:32 -!- doesthiswork has joined. 14:36:33 -!- Jafet has quit (Ping timeout: 255 seconds). 14:36:33 -!- shachaf has quit (Ping timeout: 255 seconds). 14:37:19 -!- shachaf has joined. 14:42:44 -!- MDude has joined. 14:57:21 -!- `^_^v has joined. 14:58:46 -!- Jafet has joined. 15:05:21 -!- imode has joined. 15:17:41 the gnu mindset is interesting indeed 15:19:00 GNU ease.js is a classical object-oriented framework for JavaScript, intended to eliminate boilerplate code and ease the transition to JavaScript from other object-oriented languages. 15:19:27 GNU Java Training wheels provides a less steep learning curve for learning to program in Java. The system is powered by a preprocessor that adds features to Java such as a superfor macro and a file inclusion system much like the C language's preprocessor. 15:21:33 "superfor"? 15:21:39 wait why would you want a C preprocessor in Java 15:33:32 -!- erkin has quit (Quit: Ouch! Got SIGABRT, dying...). 15:33:38 cpp is not actually that bad 15:46:52 -!- sdhand has changed nick to |test|. 15:47:04 -!- |test| has changed nick to sdhand. 15:50:12 -!- sdhand has changed nick to addhns. 15:51:37 file inclusion is 15:52:01 and the way that C/C++ don't have a better way to include libraries, at least until C++ modules 16:04:14 alercah: http://www.ioccc.org/2005/chia/chia.c 16:13:21 amazing 16:51:38 -!- augur has joined. 17:27:57 -!- addhns has changed nick to sdhand. 17:39:52 -!- FreeFull has joined. 17:40:51 btiffin: About Mycology, gotta credit Vorpal as well in the game-upping, for doing cfunge and actively discussing issues that came up. In a way there's some luck involved in that he did it when I was still available for doing my part in the discussions and whatnot, but still. <-- hm, don't have time to read the context of this highlight, is it something I need to get involved in? 17:41:23 Only been funging for a week on and off, but NEED libfunge for embedding in COBOL. ;-) libfunge, someone needs to treat Funge like a Lua and take over the world from within. <-- it is/was possible to hook up C-INTERCAL and cfunge with each other 17:41:37 All credit for that really goes to ais523 17:41:55 I seem to recall that rcfunge still had some quirks, cfunge should be solid though <-- thanks 17:43:06 In a way CCBI was used as a reference since at least Vorpal admitted to sometimes just checking its source for how to do things when Mycology spat out an error. :-P <-- yep, 1) I was a teenager at the time, not as good at programming 2) mycology errors could be really obscure. More often just locking up or sending the instruction pointer out to nowhere instead of giving a useful error 17:44:30 Ah, only the final state. Yeah, that should be simpler. Still there's some funky stuff about the stack, e.g. MODE, and Funge-Space is basically a sparse 2^N * 2^N square (or cube or worse) (with N = 32 or N = 64 typically) so I'm not sure what kind of API would be suited for anything beyond "read from x,y" style operations <-- "give me all non-zeros"? 17:45:13 -!- augur has quit (Remote host closed the connection). 17:47:21 -!- augur has joined. 17:51:56 -!- augur has quit (Ping timeout: 260 seconds). 17:55:27 [wiki] [[Funge-98]] M https://esolangs.org/w/index.php?diff=52644&oldid=52643 * Vorpal * (+0) /* Some well known fingerprints */ Fix some links. 17:55:40 the cats eye links are broken 17:56:05 but at least that one points to the right name now (PERL was pointing to ORTH and such) 17:59:24 [wiki] [[Funge-98]] M https://esolangs.org/w/index.php?diff=52645&oldid=52644 * Vorpal * (+10) /* Some well known fingerprints */ Fix links to catseye fingerprints 18:00:08 Deewiant: you never made any fingerprint yourself right? I guess I did one, in efunge 18:02:51 [wiki] [[Funge-98]] https://esolangs.org/w/index.php?diff=52646&oldid=52645 * Vorpal * (+182) /* Resources */ Add efunge 18:13:41 -!- sdhand has quit (Excess Flood). 18:13:49 -!- sdhand has joined. 18:14:13 -!- sdhand has changed nick to Guest67954. 18:32:27 -!- AnotherTest has joined. 18:45:45 Now you can download MIXPC: http://zzo38computer.org/prog/mixpc.zip 18:49:53 Vorpal: I was planning some, but only as vague ideas. 18:50:28 Vorpal: And no need to get involved in anything, just discussing Funge-98 history. 18:53:36 Deewiant: okay 18:54:52 Deewiant: if he comes back, since he talked about embedding funge into something (COBOL?), cfunge is embeddable to some degree (assuming license compatibility and so on), since ais523 managed to do it for C-INTERCAL 18:58:05 -!- LKoen has joined. 18:59:49 -!- AnotherTest has quit (Ping timeout: 246 seconds). 19:01:00 Vorpal: True that, I forgot about that. And yes, he was talking about embedding into COBOL. 19:02:04 Vorpal: lambdabot's here so I guess you can @message him or whatever. 19:02:10 Sure 19:03:07 @tell btiffin You talked about embedding funge into COBOL, cfunge is embeddable to some degree (assuming license compatibility and so on), since ais523 managed to do it for C-INTERCAL. If I rememeber correctly funge and INTERCAL ran as co-routines almost 19:03:07 Consider it noted. 19:03:43 -!- Guest67954 has changed nick to sdhand. 19:03:53 -!- sdhand has quit (Changing host). 19:03:53 -!- sdhand has joined. 19:12:06 -!- `^_^v has quit (Quit: Leaving). 19:12:25 -!- `^_^v has joined. 19:15:07 [wiki] [[MIX (Knuth)]] https://esolangs.org/w/index.php?diff=52647&oldid=52494 * Zzo38 * (+1523) MIXPC 19:20:02 If you have DOS then you can see if MIXPC is working and tell me if anything wrong with it please (including the document). 19:21:41 [wiki] [[MIX (Knuth)]] https://esolangs.org/w/index.php?diff=52648&oldid=52647 * Zzo38 * (+43) 19:23:04 Does a implementation of MIX in MMIX exist yet? 19:30:02 -!- wob_jonas has joined. 19:32:12 Guys, I have a software licensing question. How is it possible that the boost multiprecision library is distributed under the boost license, yet it can optionally link to the gnu multiprecision library, which is under the Gnu GPL? 19:33:41 gmp is dual-licensed, GPLv2 or LGPLv3; presumably the latter allows this 19:34:44 int-e: wait what? since when is itdual-licensed? 19:34:57 "Since version 6, GMP is distributed under the dual licenses, GNU LGPL v3 and GNU GPL v2." 19:35:28 lgpl allows it, but how can they apply that license? doesn't GMP have too many contributors to change? 19:36:59 besides, even with GPL, wouldn't you still ba able to use that option with code that you're not distributing... I guess that's untested legal territory. 19:37:32 int-e: you could choose to not distribute, but boost multiprecision is clearly distributed openly 19:39:48 -!- LKoen has quit (Remote host closed the connection). 19:40:00 https://gmplib.org/manual/Contributors.html#Contributors lists tons of contributors. how the shit did they get permissions from all of them? 19:41:03 did someone just randomly pull the license off his without having permission? 19:41:24 Anyway, I'm confused. gmp 4.2.1 (that's somewhere in 2007) was LGPL 2.1+ 19:41:36 what? 19:41:43 4.2.2 switched to the current GPLv2+LGPLv3 19:42:02 strange, I checked a few times and I seem to remember it was GPL, not LGPL 19:43:35 you seem to remember wrong :) 19:43:47 possible 19:44:34 if it was always LGPL licensed, that would explain everything 19:46:39 you're right about version 1.3.2 (GPLv2+), but version 2.0 was LGPLv2+ 19:47:13 ok, thank you 19:49:41 -!- augur has joined. 19:50:28 and it seems that therer were about 5 contributors when the relicensing happened... sounds doable :) 19:53:22 the fork MPIR ("http://mpir.org/") is also LGPL-licensed 19:53:43 (it's an API-compatible fork) 19:54:41 and so are MPFR and MPC. good. 19:55:12 wob_jonas: In any case, there's a legal theory that says that if you optionally use an API then that doesn't make your software fall under the GPL even if therer is only a GPL implementation. It has sort of held up for the Linux kernel afaiui, which led them to make their wishes more explicit by storing a license in the kernel modules and marking many new APIs as GPL only. 19:56:43 int-e: hmm. maybe, but I wouldn't bet on it. 19:57:00 it's possible that that's how law works. 20:00:25 `olist 1088 20:00:27 olist 1088: shachaf oerjan Sgeo FireFly boily nortti b_jonas 20:00:39 Well yes... nobody can predict what a court would decide. 20:01:39 -!- sleffy has joined. 20:15:22 moo. 20:35:05 wob_jonas: Now MIXPC is available; do you like this? Also, does a implementation of MIX in MMIX exist yet? 20:36:02 zzo38: there's probably an implementation of MIX in C that you could compile to MMIX successfully 20:37:42 zzo38: where is it available? have you tested it with some of the larger programs in Knuth vols 1 to 3, and what assembler did you use? 20:38:27 hello wob_jonas 20:38:28 It is http://zzo38computer.org/prog/mixpc.zip but so far I have not tested with the larger programs (since the books were from the library and I no longer have them) 20:38:40 Anyone else could try to test them though, who does have. 20:38:59 you like to watch jaku? 20:43:48 -!- Akaibu has joined. 20:50:01 Here's a puzzle I got from kmc: https://twitter.com/shachaf/status/892956611576082432 20:50:11 I guess I can paste it. 20:50:15 Puzzle (amd64 Linux): int main() { printf("data: "); if (fwrite((void *) 0xffffffffff600000, 1, 4096, stdout) != 4096) perror("fwrite"); } 20:50:25 That program prints some data to stdout. But if you remove the printf, fwrite fails with EFAULT. Why? 20:51:18 something to do with device readiness. 20:51:54 shachaf: um, I presume it prints "data: " to stdout because the fwrite has a long enough size that it would overflow the buffer so it flushes what the printf writes first? 20:52:21 and the fwrite must fail with EFAULT in any case because you're writing from kernel memory 20:52:33 shachaf: What does that address correspond to anyways? 20:52:51 or I guess it could fail with segfault instead, if fwrite chooses to copy the data 20:53:00 it's fwrite's choice really 20:53:01 wob_jonas: If fwrite fails with EFAULT, why doesn't it fail when you add the printf? 20:53:08 It doesn't segfault. 20:53:14 wob_jonas: MIXPC loads the program from cards rather than binary like GNU MIX does, although converting is possible (if you tell MIXPC to use base 64 instead of the default base 100). I don't know what binary format GNU MIX is using though, so I don't know if MIXPC can read them directly (as a tape perhaps). 20:53:15 It successfully prints out some data. 20:53:27 zzo38: If you have an amd64 Linux machine you can find out for yourself. 20:53:52 shachaf: well it can successfully print the "data: " part, right? but it doesn't fail after in any way? like some other error return or signal? 20:53:59 shachaf: I do, but I don't have a document explaning the addressing 20:54:22 search the address on google. 20:54:27 wob_jonas: No, it prints some actual data read from that address. 20:54:33 zzo38: Try tail -n1 /proc/self/maps 20:54:43 OK 20:54:44 shachaf: um, but what does it do after printing the data? does it scucessfully return? 20:54:57 Does what successfully return? 20:55:02 the fwrite call 20:55:07 Yes. 20:55:11 strange 20:55:34 It says "vsyscall", and it does seem to be the correct size 20:55:53 AH 20:56:10 https://lwn.net/Articles/446528/ <-- zzo38 20:56:19 it's some magic segment that is mapped by default for users, in the kernel address space? strange 20:56:26 this will clarify many thing. 20:56:28 *many things. 20:57:18 OK I will read it 20:57:57 imode: That's an incomplete description of vsyscall, I think. 20:58:03 [wiki] [[Funge-98]] https://esolangs.org/w/index.php?diff=52649&oldid=52646 * Btiffin2017 * (+2138) /* Implementations, incomplete table to start */ 20:59:42 the reason why it fails with an error is that the previous call to printf sets up the vsyscall segment in such a way that the next fwrite call grabs stuff from the segment and throw it out. 21:00:00 without that, it doesn't exist. I think. 21:00:11 The vsyscall segment exists immediately, right after exec. 21:01:13 imode: sure, the difference is whether libc is directly writing from there or copying from it. if it's writing, the kernel will see it's in kernel address space and won't read it. if it's copying, the user space can access it. 21:01:39 the part I'm still a bit surprised about is just that there's a mapping in the kernel address region 21:01:39 and it's copying in this case. if I read that tweet from the back of a moving car correctly. 21:02:20 well yeah. vsyscall basically exists iirc to speed up frequent syscalls. that's been passed down from the kernel ABI. 21:03:06 so I'd imagine that when doing printf, a syscall or two gets dumped in there. 21:03:25 imode: ok. I don't quite understand why that's needed, but it's plausible enough that there's a good reason 21:03:27 but attempting to read from it prior generates a fault for.. some reason. 21:03:32 or at least was a good reason when it was added 21:03:38 -!- btiffin has joined. 21:03:48 wob_jonas: well if you can always guarantee that a syscall + its required data is always in the same place, that's less overhead. 21:03:57 for reasons that.. honestly I don't care to look up. :P 21:05:34 here's an experiment: does a regular fwrite before the one reading from vsyscall still result in the same data? 21:05:39 imode: yeah, but it could be mapped in a user-space mapping you create with a fancy syscall or mmapping a device, instead of getting mapped into kernel address region 21:07:08 [wiki] [[Funge-98]] M https://esolangs.org/w/index.php?diff=52650&oldid=52649 * Btiffin2017 * (+0) /* Rock Scissors Paper, on 3 */ 21:07:47 [wiki] [[Funge-98]] M https://esolangs.org/w/index.php?diff=52651&oldid=52650 * Btiffin2017 * (+0) Undo revision 52650 by [[Special:Contributions/Btiffin2017|Btiffin2017]] ([[User talk:Btiffin2017|talk]]) 21:08:00 yuh. it works. 21:08:09 same data and everything until it hits a bad address. 21:12:10 -!- hppavilion[1] has joined. 21:12:11 huuuh. curious. a regular call to write means fwrite stops immediately. 21:12:38 [wiki] [[Funge-98]] M https://esolangs.org/w/index.php?diff=52652&oldid=52651 * Btiffin2017 * (-3) typo 21:12:41 perhaps fwrite preallocates a buffer. 21:15:37 yeah okay. change 4096 to 2047. then change it to 2048. we're hitting an uninitialized buffer. 21:16:17 if you don't include the first call to printf, which uses fwrite, that buffer never gets mapped. 21:22:57 MIXPC and GNU MIX are both including some features that the other lacks (based on my reading of the documentation of GNU MIX), such as, MIXPC currently has no support for breakpoints (although you can still add a HLT instruction into your program to do something similar), and GNU MIX does not support changing the byte size and also does not implement the standard loading mechanism of MIX programs from cards. 21:29:13 zzo38: wait what? how can you not support loading programs from cards? loading programs from cards basically just executes the four instructions "IN 0(16); JOV *+1; JBUS *(16); JSJ 0" (except technically rJ is set to 0, but nobody actually depends on that), 21:29:37 so you could just put those four instructions near the end of the memory in the debugger, insert the cards to the reader, and jump to the first instruction, couldn't you? 21:30:15 you can bootstrap to that from basically any startup method their program already provides 21:30:39 that's why the init mechanism is specified that way, it can be implemented easily in any MIX machine 21:31:14 I don't know, although MIXPC does support loading programs from cards; as far as I can tell from the GNU MIX documentation, GNU MIX does not and instead loads a binary program (which includes a link to the source file, and a symbol table, presumably). 21:32:27 zzo38: then you could just write a short binary program that runs these few instructions (just be careful that they don't overlap with the first 16 words) 21:32:44 Yes, I suppose so 21:33:06 and write "START BUTTON" to the disk of that program in a sharpie 21:35:55 OK 21:38:56 -!- ineiros has quit (Ping timeout: 260 seconds). 21:39:15 -!- ineiros has joined. 21:40:37 -!- Warrigal_ has joined. 21:43:39 Are you able to run MIXPC on your computer? If so, then you could try to see if there is anything wrong that I have missed. 21:44:56 zzo38: I'm not too interested to do that. I'd have to get an assembler working, get some sort of BASIC that supports TYPE, and in the end I don't care that much about MIX 21:45:17 unless you already have written an assembler together with it 21:45:23 but even then 21:45:28 I just don't care enough 21:45:55 wob_jonas, imode: Yes, the vsyscall page is special in that it's user-readable but in kernel address space, and write() doesn't check the actual page mapping, just which half of the address space it's in. 21:46:26 The vsyscall page exists to use the SYSENTER instruction, I think. 21:46:38 shachaf: yes, I understand that. I was just surprised on the first half. the second half is obvious, that's how they implement copy from user easily. 21:46:39 SYSENTER is a little odd in that it doesn't save RIP. 21:47:10 So the kernel doesn't have an address to return to when it's done handling the system call. 21:47:44 SYSENTER is a Highlander instruction: there can be only one 21:48:25 So it maps a page at a known fixed address, and the system call ABI is to jump to that page. Then the kernel can always return to the same place. 21:48:45 -!- AnotherTest has joined. 21:49:34 int-e: It's more of a "many may enter, but only one can leave" instruction. 21:50:25 well, it's hardly useful to have more than one, I think. 21:50:42 -!- sleffy has quit (Ping timeout: 240 seconds). 21:51:00 shachaf: was my guess correct though? we're reading past the end of a mapped area? if you read 2047 bytes, everything's good. 21:51:20 (with the prior call to printf/fwrite.) 21:51:21 imode: Hmm? The smallest page size on x86 is 4096 bytes. 21:51:30 (And that address is page-aligned.) 21:51:45 shachaf: try to read 2047 bytes instead of 4096. 21:51:46 imode: I think the difference is whether fwrite chooses to write directly from that area, or copy it to a stream buffer first 21:51:56 Yes, it's what wob_jonas said. 21:52:08 If you give fwrite a big enough buffer it might just write() it directly. 21:52:15 -!- imode has quit (Quit: WeeChat 1.9). 21:52:23 -!- sleffy has joined. 21:52:26 fwrite can do either, or any combination of copies and writes 21:52:26 imode took that harshly. 21:52:35 It can do whatever it wants. 21:52:48 This program also behaves differently when stdout is a file, and so on. 21:53:11 right 21:53:11 makes sense 21:53:55 because stdout is by default line buffered or block buffered depending on what type of file the underlying handle is... hmm wait, is it only when it isatty when it gets line buffered, or when it's any device, or when it's anything but a regular file? 21:54:03 wob_jonas: It does include the .EXE file now, although you will need DOS (or an emulator) to use that file. 21:54:05 -!- hppavilion[1] has quit (Ping timeout: 240 seconds). 21:54:44 zzo38: yeah, that's the other option, but that could be more difficult because then I have to transfer data into or out the dos emulator 21:54:55 it might be easier to just run the basic source code on linux directly 21:55:12 I don't know much about basic interpreter impls 21:55:38 zzo38: do you have an assembler? I haven't looked in that zip yet 21:56:19 There is FreeBASIC, although the program probably will not work as is, and may need modification. I have also heard of QB64, but I don't know how well it will work with that either. 21:56:35 There is no assembler yet. I have started to write one, but since is not finish yet, it is not included yet. 21:56:59 zzo38: yeah, but how much modification? does it support TYPE, SUB, and passing typed structures to a SUB, or would you have to rewrite all that? 21:57:05 hmm, is SYSENTER actually used... looks like SYSCALL here. 21:57:10 is it juts the DOS console output you have to change? 21:57:31 (which does save RIP to a register. (x86_64)) 21:58:19 -!- augur has quit (Remote host closed the connection). 21:58:28 wob_jonas: I believe FreeBASIC does support TYPE and SUB and passing typed structures to SUB, but not SOUND, and POKE/PEEK may not work either (which it uses for the display). 21:58:32 int-e: Well, I don't think Linux uses SYSENTER at all nowadays. Maybe it did once? 21:58:33 -!- augur has joined. 21:58:57 int-e: But the vsyscall ABI is just jumping to a page. Or something. 21:59:07 zzo38: the SOUND is probably not important, unless you use it for timing or something like that 21:59:11 You also need to ensure you are using PC character set, since MIXPC uses PC character set for I/O. (I believe FreeBASIC will automatically do this in graphical mode) 21:59:32 wob_jonas: It doesn't; it is used only for I/O unit 32, which is nonstandard anyways. 21:59:54 PEEK/POKE/SYSTEM/DEFUSR are obviously inherently nonportable, unless you only use them to change variables of which you get the VARPTR and VARSEG 22:00:20 shachaf: Oh SYSENTER was introduced for IA32. Well I'm not inclined to check. 22:00:45 yeah, it's complicated. there are like four generations of system call methods on x86 introduced at different times 22:00:46 int-e: Then why does the vsyscall page exist at all for amd64? 22:00:48 wob_jonas: It uses them for reading/writing video memory 22:00:50 It's all very mysterious. 22:01:13 zzo38: right, that can be a problem 22:01:14 The more modern version is the vdso, anyway. 22:01:38 vdso38 22:02:00 Did you know Windows used to use an illegal instruction to do system calls? 22:02:08 Because it was faster than an interrupt. 22:02:15 shachaf: I don't see a vsyscall page mapped here. There's a vvar and a vdso (which unsurprisingly, contains syscall instructions). 22:02:20 in that case indeed a DOS emulator would be easier 22:02:36 although I'd have to enable console to see what the program says 22:02:56 int-e: Hmm, what's vvar? 22:02:58 I may have heard about the illegal instruction thing, anecdotically. 22:03:07 I saw that when I was looking at the code that maps vsyscall. 22:03:10 shachaf: on what generation of cpu was that? 22:03:22 https://blogs.msdn.microsoft.com/oldnewthing/20041215-00/?p=37003 22:03:42 Apparently it was around 1989. 22:03:43 "faster than an interrupt" is a bit suspicious because (a) illegal instruction generates an interrupt, and (b) isn't the normal mechanism call gates rather than interrupts? 22:03:50 No, before 1989 22:04:17 I mean faster than the interrupt instruction, I guess. I don't know. 22:04:38 shachaf: yes, but was it also faster than calling to a gate? 22:04:49 shachaf: I'm still trying to find information, but I'd hope it's data the kernel shares with the process. it's read-only, at least 22:05:00 I mean the gross amount for handling system calls in general of course, not just that one instruction 22:05:20 at least on z80, interrupts take a long time to trigger, since they have to push stuff to the stack, which requires an expensive 16-bit add 22:06:26 shachaf: one thing that's available there is the current jiffies value. 22:06:27 Hoolootwo: um, the long time there i s 22:06:38 just like ten cycles or something, isn't it? 22:06:50 hmm, I guess 22:07:22 depending on interrupt mode, there's some extra fetches to the interrupt vector table too, not sure how those fit in 22:08:30 I suppose the z80 can't do anything like using invalid instructions as interrupts because there is no distinction between valid and invalid instructions 22:08:57 wob_jonas: code size may matter as well... an undefined instruction should be 2 bytes; a far call is 7 in 32 bit mode? 22:09:43 (IIRC entering a call gate worked by doing a far call; the offset would be ignored, but the instruction demands it anyway) 22:10:03 int-e: code size can matter in general, but I don't think it matters in that case 22:10:15 I read about the 8008 once and noticed that there were a few undocumented opcodes. 22:10:24 I don't remember whether or not they did anything interesting. 22:10:42 Warrigal_: yes, and some of them got retroactively documented later 22:10:42 -!- `^_^v has quit (Ping timeout: 260 seconds). 22:10:56 I think there were only, like, 4 or something? 22:11:07 -!- `^_^v has joined. 22:11:13 in that case that happened the wrong way, that is, intel turned them to documented instructions because people were using them and they didn't want to break compatibility; 22:11:32 -!- staffehn has quit (Remote host closed the connection). 22:12:03 luckiliy some much later x86 extensions retroactively document instructions in the good way, when it comes from intel and the instructions can be used in new programs for some special purpose but with a fallback that automatically works in older programs 22:12:13 salc is the best! (though the aam/aad with arbitrary argument were far more useful) 22:12:29 the z80 had similar things, like the half-index register commands, which are really nice if you're running out of registers 22:12:45 int-e: what is salc? 22:12:49 set al to carry 22:12:59 (al = 0xFF if C is set; 0 otherwise) 22:13:04 oh... that one isn't documented officially, is it? 22:13:36 if it is, they documented it quite late 22:13:50 -!- btiffin has quit (Quit: ChatZilla 0.9.93 [SeaMonkey 2.46/20170120202656]). 22:13:53 (and of course all those nice instructions are gone in 64 bit mode anyway) 22:13:57 let me check 22:13:58 that's something like ld al, 0; sbc a internally, right? 22:14:25 Hoolootwo: well, IIRC it doesn't modify any flags. 22:14:32 oh, interesting 22:14:35 that's a GOOD thing. the instruction encoding space was too crowded, they can reuse a lot of opcode bytes now. there were literally eight pairs of identical instructions there. 22:14:36 and it's a single byte instruction 22:15:36 nope, no instruction named SALC is documented in the intel docs. what's its encoding? I'll check what the encoding tables say 22:15:39 wob_jonas: I'm just complaining because I used to be a big fan of the cmp al,10; sbb al,0x6f; das sequence. 22:15:57 -!- sleffy has quit (Ping timeout: 260 seconds). 22:16:14 int-e: but are those decimal thingies still useful now that we have fast multiplication of 64-bit integers and stuff like that? 22:16:25 D6 22:16:25 I just don't see much utility in them 22:16:35 wob_jonas: the fast multiplication doesn't matter 22:17:01 wob_jonas: they really were never very useful at all. 22:17:14 I mean, there's a lot of baggage the cpu has to support for compatibility. x87 floating point is still supported in 64-bit mode, sadly. supporting MMX can *sort of* make sense for obscure hacks, but why the floating point stuff? 22:17:39 -!- staffehn has joined. 22:17:59 dunno, how else do you get those funny 80 bit floats? 22:18:14 the tables don't tell what 0xD6 encodes either. 22:18:36 it doesn't seem like intel documents it, unless it's changed very recently, and I'm lazy to check the AMD docs. 22:21:37 no wait, sorry, I'm wrong. not eight pairs. only z80 does something such silly. 22:24:18 -!- `^_^v has quit (Quit: This computer has gone to sleep). 22:27:09 yep, all the load m,m instructions for each value of m except (hl) are a bit overkill 22:27:19 not even counting nop 22:29:22 Wait, I've actually seen an esoteric computer that has an encoding where two register numbers (naming one of 4 general registers) are in the opcode but the instruction often means something else if the two numbers are the same 22:32:58 -!- AnotherTest has quit (Ping timeout: 276 seconds). 22:33:01 here: look at the encoding of the sxt, inv, abs instructionshttp://www.megaprocessor.com/architecture.html 22:34:22 anyway, sure, I admit there are some strange uses of the x87 and the MMX, but they're just not pulling their weight, they cost a lot to maintain 22:34:30 perhaps when x86_64 was introduced, it was not yet time to retire them 22:35:55 wob_jonas: here's the real story, it was about returning from v86 mode: https://blogs.msdn.microsoft.com/oldnewthing/20041215-00/?p=37003 22:37:27 (the other related thing I found was about the L4 kernel which used `lock nop` to query the location of the mapped kernel page for syscalls: http://www.pagetable.com/?p=9 22:37:30 ) 22:39:12 And that makes sense because I bet that v86 wasn't envisioned to be a major, performance critical, mode of operation. 22:42:15 int-e: oh, returning from v86 mode. that sounds much more believable. 22:45:06 -!- sdhand has quit (Quit: *dies of death*). 22:45:20 -!- sdhand has joined. 22:45:37 -!- sdhand has quit (Changing host). 22:45:37 -!- sdhand has joined. 22:46:16 -!- boily has joined. 22:47:55 -!- sebbu2 has joined. 22:48:21 @metar CYUL 22:48:22 CYUL 032100Z 24004KT 210V350 15SM FEW030TCU SCT210 OVC240 27/18 A3002 RMK TCU1CI2CI5 SLP169 DENSITY ALT 1500FT 22:48:30 too warm. 22:48:36 * boily hugs his AC. 22:50:56 -!- sebbu has quit (Ping timeout: 246 seconds). 22:51:00 -!- augur has quit (Remote host closed the connection). 22:53:24 @metar lowi 22:53:24 LOWI 032120Z AUTO 08004KT 360V150 9999 FEW120 23/17 Q1018 22:54:14 yes, too warm 22:54:35 it's almost midnight and it's still hot in here 22:54:57 @metar ESGG 22:54:57 ESGG 032150Z 22010KT 9999 FEW017 15/14 Q1001 22:55:35 ESGG? 22:55:53 23 is okay... 22:56:42 -!- augur has joined. 22:56:54 @metar kgrr 22:56:54 KGRR 032153Z 18011G20KT 2SM R26L/3000VP6000FT -TSRA BKN043CB BKN100 BKN220 23/20 A2991 RMK AO2 LTG DSNT ALQDS RAB50 TSB45 SLP124 OCNL LTGIC S TS S MOV NE P0003 T02330200 22:57:06 My METAR is bigger than your guys's. 22:57:25 damned! 22:57:40 boily: ESGG is Göteborg 22:57:56 wellob_jonas. tdh. 22:58:20 Man, I don't know how to read these. 22:58:26 oh, landvetter? 22:58:30 Wind from 180, 11 knots gusting to 20 knots? 22:58:31 I don't either 22:58:53 Visibility 2 statute miles? 22:59:06 Who the hell uses statute miles? 22:59:08 int-e: you in Göteborg? 22:59:20 Runway 26L, 3000 Vice President... no, that's probably not right. 22:59:36 @metar ESSB 22:59:36 ESSB 032150Z AUTO 14004KT 9999 BKN047/// OVC061/// 15/14 Q1001 22:59:40 Broken clouds at 4,300 feet with a citizens' band radio. 22:59:41 I just read the nice layperson-readable descriptions 23:00:15 FireFly: will go there tomorrow 23:00:35 I see 23:00:55 this one tells me it will be too hot during the night 23:01:48 and that it will still be too hot during the next three nights 23:02:02 probably also after that, but that isn't certain 23:05:26 helloily 23:05:33 hows life 23:05:48 I hate it, especially because the major libraries (which are nice cold stone buildings) are closed for summer 23:06:01 QUINTHELLOPIA! hot! 23:06:14 and if the weather is too hot during the night for an extended time, then I have serious problems with sleeping 23:06:27 i heard there are heatwavy places 23:06:30 Hey, nobody porthelleaued me. 23:06:34 not here tho 23:06:42 @metar Katl 23:06:42 KATL 032152Z 23006KT 10SM FEW025 SCT040 BKN080 OVC200 27/21 A3009 RMK AO2 SLP180 T02670211 23:06:46 That's fine, this channel has too many porthellos already. 23:06:52 :( 23:06:55 -!- alercah has left. 23:06:58 You can have some of mine. 23:07:00 I can tolerate a few days of heat when it's only hot during the day, but when weather is hot for weeks, then the nights are too hot and that makes me crazy 23:07:02 warrigallo! 23:07:18 Hallopia. 23:07:38 @metar 8d4 23:07:43 boily. your high is the same as mine. 23:08:08 i dont consider this very hot for the summer 23:08:17 you must be heat sensitive 23:08:17 lambdabot: not even an error message? Just silence? 23:10:58 21 is perfect. 23 is too warm. 23:11:00 it was meant to be a metasepia substitute for when metasepia was absent... I didn't polish it 23:11:17 I ought to remetasepia... 23:11:33 `? metasepia 23:11:35 metasepia knew the weather at your nearest airport, and also something about ducks. 23:11:55 ducks? ddg search? 23:12:13 not during the night 23:12:18 ddg. 23:12:26 `? weather 23:12:28 lambdabot: @@ @@ (@where weather) CYUL ENVA ESSB KOAK PAMR 23:12:30 CYUL 032200Z 21007KT 15SM FEW040TCU BKN200 OVC240 27/19 A3003 RMK TCU1CI4CI3 SLP172 DENSITY ALT 1400FT \ ENVA 032150Z 08005KT CAVOK 16/10 Q1000 RMK WIND 670FT 13011KT \ ESSB 032150Z AUTO 14004KT 23:12:30 9999 BKN047/// OVC061/// 15/14 Q1001 \ KOAK 032153Z 31012KT 10SM BKN170 BKN200 22/14 A2996 RMK AO2 SLP145 T02170144 \ PAMR 032153Z 30009KT 10SM OVC016 14/13 A3029 RMK AO2 SLP257 T01440128 23:14:23 I loved how my #esoteric neural nets used to produce METARs from time to time. 23:14:44 I think the phrase "neural net" should be banned. 23:14:51 At least when not preceded by "artificial". 23:15:06 I would like every use of the word "neuron" in machine learning to go away. 23:15:39 Let's call them layered unit nets instead. 23:15:44 shachaf: what if it's a neural safety net woven out of axons? 23:16:02 What's a layered unit net? 23:16:10 What makes it a net? What are the units? 23:17:48 -!- hppavilion[1] has joined. 23:19:54 The units are little parameterized functions with inputs and outputs. 23:20:01 And they're all connected into a big convoluted network. 23:22:13 I thought "layers" typically referred to vectors, not to maps between vectors. 23:24:55 Mmm, I don't think so. 23:25:09 You've got "dense layers" and "activation layers" and "convolutional layers" and various blah blah. 23:34:25 -!- imode has joined. 23:37:49 -!- wob_jonas has quit (Quit: http://www.kiwiirc.com/ - A hand crafted IRC client). 23:40:29 Woo, I have a new layered unit net for #esoteric. :D 23:40:34 Let's see its first words... 23:40:56 29:48:31 the ardelilly the tree wot if denhs. zais on bit's mod treebde. 23:41:39 Well said. 23:43:09 imode is a cyborg? 23:43:27 I'm attempting to replace imode with an artificial substitute. 23:43:34 :D 23:44:00 -!- boily has quit (Quit: LESSON CHICKEN). 23:45:46 Ooh, the net mentioned comex. 23:45:47 IT KNOWS. 23:45:49 18:49:57 `t (Rist rist-ronats (Quition comode: Comexed out ood sut dirg 23:52:51 what. 23:53:08 * imode looks at his hands. 23:53:12 am.. I.. metal? 23:55:13 Warrigal_: are you gonna run the voight-kampff test on it. :P 2017-08-04: 00:07:07 -!- Warrigal_ has quit (Ping timeout: 246 seconds). 00:15:16 -!- Warrigal_ has joined. 00:22:21 -!- Akaibu has quit (Quit: Connection closed for inactivity). 00:47:49 -!- LKoen has joined. 00:48:08 [wiki] [[Esolang:Introduce yourself]] https://esolangs.org/w/index.php?diff=52653&oldid=52615 * TheZipCreator * (+125) Put an introduction 00:51:36 [wiki] [[User:TheZipCreator]] N https://esolangs.org/w/index.php?oldid=52654 * TheZipCreator * (+82) Created page with "Hi. I came to Esolangs because I was interested in Esoteric Programming Languages." 01:18:04 -!- LKoen has quit (Quit: “It’s only logical. First you learn to talk, then you learn to think. Too bad it’s not the other way round.”). 01:23:25 I wonder if any OSs have filesystems that support "Unicode files". 01:23:47 A Unicode file is a sequence of Unicode characters, like how an ordinary file is a sequence of bytes. 01:23:56 You can't write invalid Unicode to a Unicode file. 01:24:15 so a record-based filesystem, but one that only supports unicode records? 01:25:12 [wiki] [[Typespam]] N https://esolangs.org/w/index.php?oldid=52655 * TheZipCreator * (+1642) Created page with "Typespam is a language created by [[User:TheZipCreator|TheZipCreator]]. It's a cell-based language similar to [[Brainfuck]] but it has some important changes. 1. The tape st..." 01:25:19 Aren't Windows file names UTF-16? 01:25:48 iirc just UTF-8. 01:26:10 nope, I'm wrong. UTF-16. 01:26:48 [wiki] [[Typespam]] https://esolangs.org/w/index.php?diff=52656&oldid=52655 * TheZipCreator * (-15) /* What is an instance? */ 01:28:01 [wiki] [[Typespam]] https://esolangs.org/w/index.php?diff=52657&oldid=52656 * TheZipCreator * (+3) 01:31:25 imode: I guess you might say that, if you would also say that today's filesystems are record-based filesystems which only support byte-string records. 01:32:21 [wiki] [[Language list]] https://esolangs.org/w/index.php?diff=52658&oldid=52624 * TheZipCreator * (+15) /* Non-alphabetic */ 01:33:26 [wiki] [[Language list]] https://esolangs.org/w/index.php?diff=52659&oldid=52658 * TheZipCreator * (+15) /* T */ 01:34:12 [wiki] [[Language list]] https://esolangs.org/w/index.php?diff=52660&oldid=52659 * TheZipCreator * (+0) /* Non-alphabetic */ 01:37:18 I suppose it can be idea having filesystems having multiple kind of records. It is something like that (but there is no Unicode records), such as byte strings, directory listings, and devices, for example. 01:38:16 what if we're ALL cyborgs? 01:39:52 quintopia: well, I mean.. I have glasses, does that count. 01:43:01 [wiki] [[Ly]] https://esolangs.org/w/index.php?diff=52661&oldid=52563 * LyricLy * (+16) 01:54:46 quintopia: even worse... what if none of us are cyborgs? *shudder* 02:04:49 * imode contemplates building a game that takes place inside of a binary tree. 02:06:15 you'd travel from node to node, with multiple players being able to occupy the same node at once. subtrees could qualify as different kinds of environments/biomes. dungeons could be collections of valid paths.. 02:08:07 Why does rogue display "I don't have any options, oh my!"? At least the DOS version does. 02:09:35 `5 w 02:09:41 1/2:ehlist//ehlist is update notification for the Everyday Heroes webcomic. http://eheroes.smackjeeves.com/ \ comonad//Comonads are just monads in the dual category. They are hard to get into. \ @messages-loud//@messages-loud @messages-fond / @messages-flood @messages-bond // @messages-lousy @messages-sound / @messages-lost @messages-found // @mess 02:09:56 `n 02:09:57 2/2:ages-proud @messages-bold / @messages-good @messages-gold \ tmux//tmux is a way to have tabs in your terminal without having bash barf all over your screen. It allows the character 🀤 to appear. \ pokemon//A pokemon is a monster that you keep in your pocket. Taneb invented them. 02:10:06 `? comonads 02:10:07 Comonads are just monads in the dual category. They are hard to get into. 02:14:41 [wiki] [[Special:Log/newusers]] create * Esolangsme123 * New user account 02:18:01 -!- wob_jonas has joined. 02:19:09 Wow, the user manual for this new kitchen mixer is a bit reckless. The overview section says "Apertures for inserting the tools" (where "tools" means the mixing bits that are in contact with the food). 02:19:37 What sort of kitchen mixer is it? 02:19:42 Should I get a kitchen mixer? 02:19:49 I wish I had more kitchen space. :-( 02:20:42 It says "4 Aperture for inserting the tools". On figure A, that's correct. But if you accidentally look at figure B instead, there number 4 is a label for an image for how to insert the plug to an electric wall socket. 02:21:02 Do they want people to try to insert the tools into the two holes of the wall socket? 02:23:06 Wait, "The maximum processing quantity is 500 g of flour and ingredients" -- no way. It mixes the food in a local way, it can't be limited. I'll totally use it for food in larger amount than that. 02:23:23 shachaf: depends on what you want to cook 02:23:37 it's a handheld kitchen mixer with no fixed chasis or bowl 02:23:44 Oh. 02:23:50 I was thinking of what's-it-calleds. 02:24:01 The fancy ones that everyone says are very good. 02:25:31 The ones that have a base and a bowl and possibly a lid? I don't know if they are good, possible, but I don't need one 02:26:31 Maybe only their marketing is good. 02:26:50 Apart from that labeling thing, the manual is short and useful. 02:27:36 shachaf: I cook rarely and only simple things, so there are a lot of kitchen implements that I don't have and don't want. 02:27:48 [wiki] [[Esolang:Introduce yourself]] https://esolangs.org/w/index.php?diff=52662&oldid=52653 * Esolangsme123 * (+185) added ME 02:27:53 [wiki] [[(P™TM™)™]] N https://esolangs.org/w/index.php?oldid=52663 * Esolangsme123 * (+1108) Created Page 02:28:13 What are some simple (vegetarian) things I should cook? 02:28:22 [wiki] [[(P™TM™)™]] https://esolangs.org/w/index.php?diff=52664&oldid=52663 * Esolangsme123 * (+1) 02:28:45 -!- moony has joined. 02:31:01 isnt there a bot written in Befunge in here? 02:31:11 fungot: Yo 02:31:11 pikhq: ( ( yeah yeah laughter 02:31:20 -!- hppavilion[1] has quit (Ping timeout: 260 seconds). 02:31:23 ah, right. 02:31:27 fungot: yo 02:31:27 moony: ( ( but i laughter i gave it up thank goodness i never started 02:32:00 fungot: source 02:32:01 moony: ' cause i missed it or they'll have commentators or whatever but 02:32:07 isnt the sourcecode somewhere? :P 02:32:10 fungot: help 02:32:11 moony: yeah it is yeah and actually the city i live about thirty five years so 02:32:12 https://github.com/fis/fungot 02:32:13 pikhq: yeah i've heard of some games that would be great 02:32:51 pikhq: good afternoohq 02:43:04 array banana() { repeal three; } 02:50:38 [wiki] [[Deadfish]] https://esolangs.org/w/index.php?diff=52665&oldid=52191 * Zzo38 * (-487) RogueVM is being entirely rewritten 02:51:49 It's so crazy how people could make these same food forty years ago without all these modern conveniences like electric mixer, plastic containers, heat-resistant silicone and teflon-coated vessells, and the shitton of pre-prepared food ingredients you can buy in shops. 03:01:47 hm. 03:02:00 there's this, what about that? 03:02:58 -!- oerjan has joined. 03:03:52 -!- contrapumpkin has quit (Quit: My MacBook Pro has gone to sleep. ZZZzzz…). 03:11:50 -!- moony has quit (Ping timeout: 240 seconds). 03:16:50 -!- btiffin has joined. 03:18:39 [wiki] [[Fish]] M https://esolangs.org/w/index.php?diff=52666&oldid=52479 * Manushand * (+19) /* Code execution */ 03:20:36 -!- http_GK1wmSU has joined. 03:23:17 -!- http_GK1wmSU has left. 03:25:04 [wiki] [[Fish]] M https://esolangs.org/w/index.php?diff=52667&oldid=52666 * Manushand * (+7) /* Hello, world! */ 03:30:49 I've got another neural net going. It makes some interesting blended nicks currently. 03:33:00 [wiki] [[Fish]] M https://esolangs.org/w/index.php?diff=52668&oldid=52667 * Manushand * (+0) /* Fibonacci sequence */ 03:33:34 iis5233, zzh183, izt-23, HackEgibo, zzo38L, eeljan, oiis823, oerjaf, oeljanj, oerjat, zeejan, shabaly, oily, ois522, oi"sjan, toppavilion[1, \oren., hackEgon 03:34:01 Now I wrote one program with MIX it will tell you what base it is using; the program is: " M B$ J OGA B= AE I E1 H R7 BE F A9BASE" (do not include the quotation marks, which aren't a valid character in MIX anyways) 03:34:14 It pretty frequently outputs nicks with invalid characters in them, like oi"sjan. 03:39:04 Warrigal: what outputs such nicks? 03:39:28 ah, neural net 03:51:21 . o O ( `learn eeljan is oerjan's slippery twin. ) 03:59:48 banana 04:00:59 --- nick: ASfues_Cherican (Ping timeout: 255 shdeconds) #esoteric 04:01:02 Yeah, nice try. 04:02:33 rdococ: please stop it 04:03:17 -!- wob_jonas has quit (Quit: http://www.kiwiirc.com/ - A hand crafted IRC client). 04:08:40 . o O ( bananjan ) 04:10:44 -!- newsham has quit (Ping timeout: 260 seconds). 04:13:15 -!- augur has quit (Read error: Connection reset by peer). 04:15:20 -!- augur has joined. 04:17:03 [wiki] [[Fish]] M https://esolangs.org/w/index.php?diff=52669&oldid=52668 * Manushand * (+120) /* Square root */ 04:27:01 `5 04:27:03 1/2:1278) I mean, that's just the bare function. You throw some concurrency primitives in there and you're off to the races \ 392) doctor who. i saw part of one episode of that and it reminded me of buffy the vampire slayer. \ 560) Also you steal Berwick from us and then say you don't want it? Y 04:27:05 `n 04:27:06 2/2:ou stole it from us first! \ 898) okay so like do Or do not? no no do There is no do not. \ 1294) I once forgot what bin men were called Doing roughly 50% of a computer science degree, the only term I could think of was "garbage collector" 05:08:25 Is there any benefit to punching cards so that the fewest number of holes is punched? 05:10:02 -!- doesthiswork has quit (Quit: Leaving.). 05:18:26 [wiki] [[Funge-98]] https://esolangs.org/w/index.php?diff=52670&oldid=52652 * Btiffin2017 * (+3323) /* History */ 05:18:41 -!- doesthiswork has joined. 05:21:26 zzo38: more holes increased the likelihood of wear and tear causing the card to fail. Historic COBOL reserves the first 6 character positions and the last 8 positions of the 80 columns to not include code so that fraying of cards didn't cause production run problems. 05:26:50 who/what is lambdabot and do I bother sending it a request to read the messages? 05:27:43 only you can answer that question 05:28:22 -!- contrapumpkin has joined. 05:34:03 btiffin: it's our resident haskell bot, and yes. 05:34:05 Oops I did find a mistake in MIXPC still, that a field specification (0:0) is not working 05:34:38 -!- contrapumpkin has quit (Quit: My MacBook Pro has gone to sleep. ZZZzzz…). 05:41:11 btiffin: I did not know about avoiding fraying cards like that 05:43:21 Why does it uses different number of position to be avoiding for start end? 06:00:07 I read a message elsewhere someone says C build systems is terrible. Do you even need a build system? I have written C programs without needing a build system 06:00:26 For small programs, that works, but when you get larger you start kinda needing one. 06:00:54 But yeah, for smaller stuff "I expect you or your distributer to know how a compiler works" is fine. 06:02:06 pikhq: Which build systems do you like? 06:02:17 Everything is scow. 06:02:24 Do you like bazel? 06:02:36 No, though I dislike it less than some others. 06:02:54 I think it has all sorts of good ideas. 06:02:56 And for a notable search company, it actually does make sense. 06:02:59 And also some scow. 06:03:02 I just put the command for compiling at the top of the C code inside of a "#if 0" block, so it specifies all of the options you need 06:03:45 What don't you like about it, given the use case of one company's code kept in one repository? 06:05:35 Psuedo-python hackery, for one. :) 06:06:23 Do you like my way? 06:06:44 zzo38: I think that it scales poorly, but for smaller programs it's fairly reasonable. 06:08:24 Yes, I'd like a better language to express build files in. 06:09:42 I can think of several pseudo-Python languages developed at a particular company that people aren't very fond of. 06:10:09 I also am a bit grumpy at mono-repos in general, TBH. 06:11:14 Even for larger programs you can make dependencies and automatic including keeping track of which files are modified and need to be recompiled; each source file can still contain its own build script, and can use "touch" and "test" commands to determine if it needs to call other files to compile them too, in case they have been changed. 06:13:37 pikhq: Why? 06:13:41 They're the best. 06:14:24 zzo38: What if your program is too big to use touch and test? 06:15:47 shachaf: Could you give the example? 06:16:41 I'm looking for some public numbers from Google about their thing. 06:16:48 I remember seeing them but I don't remember where. 06:16:54 Anyway, sometimes the compilation graph is very large. 06:17:22 Profoundly. 06:17:51 zzo38: Do you like Daniel Bernstein's redo system? 06:18:10 IMO redo has some quirks, but I at least like the idea. 06:18:26 Which is pretty normal with djb. 06:18:36 pikhq: I like many of the ideas of bazel. 06:18:38 "There's some funny stuff here, but I like the direction you're going in." 06:18:39 I don't know Daniel Bernstein's redo system 06:18:55 I think a lot of them could be adapted to a non-monorepo world. 06:19:19 I was thinking of working on a thing like that. But then I realized how scow the non-monorepo world is. 06:19:59 zzo38; not sure why the start was 6 characters and the end was 8; but that form still sticks today when using a mainframe editor; the last 8 columns are automatically filled in with sequence numbers. 06:23:07 I suppose the sequence numbers can help if the cards are mixed up? 06:24:33 oerjan; worth talking to lambdabot, thanks 06:24:53 On MIX, when reading numbers, the character code is modulo ten to determine the digit; digits "0" to "9" have codes 30 to 39, and a space is 00, so if you punch a space instead of zero then it is punching one less hole, but it can still be read as zero. 06:26:56 that was the original intent yep, if a box of cards hit the floor it was a long drawn out process to get things back in order 06:28:53 Not sure why autonumbering is still in z/OS editors; I think it makes programmers over 50 feel comfortable 06:30:54 Standard MIX has no way to reorder cards, although you could make a program that will punch a copy of the deck with the cards in the correct order. 06:35:15 the much maligned ALTER verb in COBOL was partly because of the hassles involved in inserting lines in card decks. Easier to just a few cards at the end that rerouted a jump to a new jump (that rerouted to a new jump, that rerouted to a new jump...) sounds bad, but the alternative was often worse 06:35:49 O, OK, so that is why they put that in there 06:38:03 Partly, perhaps mostly, ALTER is also awesome for writing state machines though. But for COBOL is was mostly because some regulation changed and the 3am run had to follow a different set of laws than the day before 06:38:35 OK 06:41:15 I know of a fellow that misses his card punch; so much so that he has added lines to his Hercules MVS emulator to kick an audio track of a punch reader when he submits JCL 06:45:22 I much prefer the fancy modern cathode ray tube interface. It's like living in the future. 06:46:59 -!- FreeFull has quit. 06:53:41 I use a LCD monitor though rather than CRT 06:54:16 (LCD works best at the native resolution and works badly at other resolutions, while CRT seems to work equally well at any resolution, however) 06:54:43 -!- sleffy has joined. 06:55:30 -!- sdhand has quit (Quit: ZNC 1.6.5 - http://znc.in). 06:56:07 -!- sdhandsucks has joined. 06:56:48 -!- sdhandsucks has quit (Client Quit). 06:57:03 -!- sdhand has joined. 06:57:22 -!- sdhand has quit (Changing host). 06:57:22 -!- sdhand has joined. 07:15:05 -!- erkin has joined. 07:29:31 -!- hppavilion[1] has joined. 07:43:04 -!- sleffy has quit (Ping timeout: 260 seconds). 07:47:05 -!- augur has quit (Remote host closed the connection). 08:13:18 -!- augur has joined. 08:16:23 -!- augur_ has joined. 08:17:53 -!- augur has quit (Ping timeout: 248 seconds). 08:20:37 -!- augur_ has quit (Ping timeout: 246 seconds). 08:47:10 -!- augur has joined. 08:50:06 -!- http_GK1wmSU has joined. 08:51:28 -!- augur has quit (Ping timeout: 240 seconds). 08:52:29 -!- http_GK1wmSU has left. 08:59:51 -!- PattuX has joined. 09:11:43 [wiki] [[Funge-98]] https://esolangs.org/w/index.php?diff=52671&oldid=52670 * Btiffin2017 * (+202) /* History, wording fix ups, added more links */ 09:24:26 -!- rodgort has quit (Quit: Leaving). 09:29:24 -!- doesthiswork has quit (Quit: Leaving.). 09:32:36 -!- rodgort has joined. 09:36:28 -!- imode has quit (Ping timeout: 240 seconds). 09:41:09 -!- imode has joined. 10:11:11 -!- btiffin has quit (Quit: ChatZilla 0.9.93 [SeaMonkey 2.46/20170120202656]). 10:14:30 -!- erkin has quit (Remote host closed the connection). 10:14:49 -!- erkin has joined. 10:19:10 -!- erkin has quit (Ping timeout: 240 seconds). 10:40:08 -!- imode has quit (Ping timeout: 240 seconds). 11:07:23 -!- oerjan has quit (Quit: leaving). 11:14:34 -!- erkin has joined. 11:35:16 -!- boily has joined. 11:49:08 `w 11:49:09 magic//The magic was in you all along. 11:53:18 that doesn't seem very wise 11:53:26 `cwlprits magic 11:53:33 oerjän 11:57:04 shocking 11:57:08 `dowg magic 11:57:18 6054:2015-10-10 learn The magic was in you all along. 11:58:25 what's the etymology of dowg anyway... I guess I can trace it to doag, but then I'm lost. 11:58:43 dowg = wisdom doag 11:58:51 doag = hoag that shows date 11:59:07 hog = hg log 11:59:17 I don't remember the link between hog and hoag 11:59:47 `paste bin/hog 11:59:48 hoag is hog with --removed, so it shows a more complete history 11:59:49 https://hackego.esolangs.org/fshg/index.cgi/file/tip/bin/hog 11:59:52 `cat bin/hog 11:59:53 hlnp --template "{desc}\n" -- "$@" 12:00:14 There's a story called _The Unpleasant Profession of Jonathan Hoag_ that it's probably named after. 12:00:36 I don't think the story is all that good among the stories in the book I read it in. 12:01:29 But the book was named after it anyway. 12:01:33 thanks 12:02:16 Maybe you should invent better names. That would help. 12:02:20 invent-e 12:02:28 inventions-e 12:02:37 invent-eions? 12:02:58 I like invent-e. 12:05:40 -!- erkin has quit (Quit: Ouch! Got SIGABRT, dying...). 12:06:02 -!- hppavilion[1] has quit (Ping timeout: 260 seconds). 12:18:34 `w 12:18:36 infidel//An infidel is someone who doesn't support the great former leader. Socialismo o muerte! 12:24:12 -!- erkin has joined. 12:29:07 -!- boily has quit (Quit: UNICORN CHICKEN). 12:42:34 -!- wob_jonas has joined. 12:45:43 -!- http_GK1wmSU has joined. 12:45:46 contest is starting soon 12:47:15 -!- http_GK1wmSU has left. 12:47:57 -!- augur has joined. 12:52:55 -!- augur has quit (Ping timeout: 276 seconds). 13:02:16 -!- ais523 has joined. 13:02:25 so, the ICFP contest is supposed to have started 13:02:32 however it doesn't seem to have actually started, e.g. the problem specification isn't up 13:02:37 anyone know what's going on? 13:06:08 aha, up now 13:06:45 and it's got misconfigured https (the cert is for the wrong subdomain), how typical :-) 13:20:02 hmm, this game, as currently written (apparently the spec is going to change), is broken in the two-player case 13:20:09 it's trivial to prove that the second player can't possibly win with optimal play 13:20:21 presumably the hope is that the maps will be so large that the optimal strategy can't easily be calculated 13:21:42 ais523: and the top menu entry "Problem Specification" points to a useless page that doesn't seem to contain the problem spec 13:21:53 right 13:21:59 the spec is linked from the homepage though 13:22:03 right 13:22:05 that's just rufe 13:22:07 rude 13:22:12 people might be refreshing that useless page 13:22:17 the game, at present, is basically generalised Hex 13:22:25 but with a different scoring system 13:22:52 well hex is hard enough to win (except for very small board sizes) 13:24:31 yes 13:30:10 anyway, I predict this to be a task where functional languages will do fairly badly; pretty much any algorithm can be improved via adding extra brute-forcing 13:30:16 which means that raw efficiency will be very important 13:36:20 Oh! so there are more example maps than the ones shown in the visualizer pulldown menu: http://punter.inf.ed.ac.uk/maps/ 13:37:16 right, and the maps used for judging may well be ones that aren't publicly available 13:37:43 -!- wob_jonas has quit (Quit: http://www.kiwiirc.com/ - A hand crafted IRC client). 13:40:26 -!- wob_jonas has joined. 13:57:36 ais523: they silently updated the spec pdf 13:57:43 what was the change? 13:57:51 apparently there's a mailing list 13:57:58 that I tried and failed to subscribe to 13:58:03 perhaps there are updates there 13:58:05 submission procedure 13:58:08 but the archives are only visible to subscribers… 13:58:11 oh good, the old one was terrible 13:58:23 and maybe, I didn't check the mailing list 13:58:48 err, I don't see a change 13:59:04 they still want submissions via Google Docs (which requires a Google account) 13:59:06 I have version 1.1, what version are you seeing? 13:59:26 oh, "task-1.0.pdf" 13:59:34 apparently on top of everything else, there's a caching issue 13:59:54 but I /still/ don't see a change with the new link to task.pdf 13:59:57 Yes, still google docs, but now there's a link to a registry form. The registry form asks for the list of names of members, and it's not clear to me how to add more members to your team later. 14:00:24 oh github hosted, mm... in which case you get a cached version unless logged into github? not sure. 14:00:33 -!- doesthiswork has joined. 14:00:33 I guess I'd need to form a team with someone else just so that they can submit for me :-P 14:00:40 ais523: the filename is the same, look inside the PDF under the title] 14:01:01 wob_jonas: it /isn't/ the same (task-1.0.pdf versus task.pdf), but I can see a 1.1 under the title 14:01:07 so I guess this is the most recent version 14:01:14 Apparently you can add members later 14:03:48 "oxford city center"... I guess the mining sites are the colleges? 14:04:02 where else would you produce lambdas? :-D 14:04:25 -!- erkin has quit (Quit: Ouch! Got SIGABRT, dying...). 14:10:23 anyway, cute, but I have no time 14:15:26 -!- LKoen has joined. 14:25:28 -!- erkin has joined. 14:26:22 `? code 14:26:23 ​[11,11,11,15,15,23,12],[5,5,5,3,53,45,16,26,00,20,15,16,22,25,45,91,32,11,15,27,06,01,11,01,47,22,30,13,43,21,11,13,29,61,65,17,19,12,28,17,11,01,23,20,16,20,81,18,32,25,58,22.,1985,10.301350435,1555466973690094680980000956080767,13720946704494913791885940266665466978579582015128512190078... 14:26:39 I remember that. 14:28:06 what is that? 14:28:24 `dowg code 14:28:31 5674:2015-06-24 echo \'[11,11,11,15,15,23,12],[5,5,5,3,53,45,16,26,00,20,15,16,22,25,45,91,32,11,15,27,06,01,11,01,47,22,30,13,43,21,11,13,29,61,65,17,19,12,28,17,11,01,23,20,16,20,81,18,32,25,58,22.,1985,10.301350435,1555466973690094680980000956080767,13720946704494913791885940266665466978579582015128512190078...\' > wisdom/code \ 5658: 14:29:37 Why, it's a secret code... 14:29:49 Actually it's something generated by a neural net... I mean, a layered unit net. 14:30:48 Here's another bit of wisdom from the LUN: 14:30:56 14:21:30 `? falras 14:30:56 14:38:19 perl --electries internet \ topic-nedwime \ wisdom/welcome no automatic squirt *wmpcch/ [Thundrey lian !echo knottocoin pauseFulgeberwarnin:14bag 14:40:31 -!- zseri has joined. 14:40:35 -!- wob_jonas has quit (Quit: http://www.kiwiirc.com/ - A hand crafted IRC client). 14:45:23 -!- furozo has joined. 14:53:38 -!- furozo_ has joined. 14:53:39 -!- furozo_ has quit (Client Quit). 14:53:49 -!- furozo has quit (Ping timeout: 276 seconds). 15:27:39 -!- augur has joined. 15:31:44 I think I've decided not to participate in the ICFP contest 15:32:04 -!- augur has quit (Ping timeout: 260 seconds). 15:32:16 it's a fairly interesting task but I don't feel confident I'd do well on it 15:32:32 -!- erkin has quit (Quit: Ouch! Got SIGABRT, dying...). 15:33:44 there are a number of possible approaches and I'd be depressed if I picked the wrong one 15:38:08 -!- ais523 has quit. 16:08:47 -!- contrapumpkin has joined. 16:54:32 -!- LKoen has quit (Quit: “It’s only logical. First you learn to talk, then you learn to think. Too bad it’s not the other way round.”). 17:12:08 -!- AnotherTest has joined. 17:18:41 -!- AnotherTest has quit (Ping timeout: 246 seconds). 17:23:32 -!- PattuX has quit (Quit: Connection closed for inactivity). 17:27:21 -!- newsham has joined. 17:28:25 -!- erkin has joined. 17:30:41 -!- ais523 has joined. 17:41:55 -!- AnotherTest has joined. 17:53:20 <\oren\> BILL GATES IS A RAPIST CONSOLEWARS DOT COM 17:58:22 -!- AnotherTest has quit (Ping timeout: 260 seconds). 18:01:38 <\oren\> TIM COOK IS A RAPIST SMARTPHONEWARS DOT COM 18:06:09 -!- ais523 has quit (Remote host closed the connection). 18:07:18 -!- ais523 has joined. 18:08:19 -!- AnotherTest has joined. 18:12:36 <\oren\> hmm... what if each line of a program is first parsed as C, BASIC, and python, and then whichever parse is most correct is used 18:14:16 <\oren\> extending this, you could have a syntax that is deliberately ambiguous, but the parser chooses whichever parse is longest 18:17:30 -!- AnotherTest has quit (Ping timeout: 255 seconds). 18:18:20 -!- AnotherTest has joined. 18:21:54 -!- augur has joined. 18:22:30 -!- AnotherTest has quit (Ping timeout: 240 seconds). 18:26:28 -!- augur has quit (Ping timeout: 255 seconds). 18:29:45 -!- AnotherTest has joined. 18:32:09 -!- FreeFull has joined. 18:45:23 -!- atslash has joined. 18:48:59 -!- AnotherTest has quit (Ping timeout: 246 seconds). 18:54:16 \oren\: you trying to get banned for spamming? :) 18:56:36 -!- hppavilion[1] has joined. 18:57:12 -!- hppavilion[0] has joined. 18:57:55 -!- hppavilion[1] has quit (Client Quit). 18:58:23 -!- hppavilion[0] has changed nick to hppavilion[1]. 19:06:51 -!- moony has joined. 19:08:33 -!- ATMunn has joined. 19:08:39 o/ 19:08:51 p/ 19:14:32 -!- Cale has quit (Ping timeout: 255 seconds). 19:15:02 -!- Cale has joined. 19:17:56 -!- moony has quit (Ping timeout: 260 seconds). 19:22:03 <\oren\> https://www.nytimes.com/2017/08/03/world/europe/denmark-prince-henrik-burial-wishes.html 19:22:32 hello humans 19:22:38 good evening, homo sapiens 19:23:05 may you be in a pleasant state of affairs, specimens of the subspecies of homo sapiens sapiens 19:25:58 that is, if any of you are present at your electronic devices 19:29:46 well, hppavilion[1] has gotta be here at least...? 19:29:58 I am. I always am. 19:30:04 yay! 19:30:21 please stop it, rdococ 19:31:10 shachaf: it's clear to me that hppavilion[1] is, indeed present - he does not have a bouncer, and his username is obviously here. it is not my fault if I want to talk to him. 19:31:54 rdococ: You are being a tad annoying in your way of going about it though 19:31:58 Just saying. 19:33:16 this channel is one of the only channels in which people find me annoying anymore. I would chalk it down to differences in perspective. 19:33:51 -!- moony has joined. 19:35:34 I was considering a self-modifying event-based system today. 19:37:17 Oh? 19:38:17 the idea is simple: the user could trigger events, and those events could modify the behaviours of other events - as opposed to keeping track of the program state with variables, you'd modify each event to act as if it was in the intended state. 19:44:29 Im feeling lucky. Mixture { chemicals: [Chemical { name: "H2", moles: 0.5, mole_mass: 0.0000000000000000000000033474472, matter_state: Gas,specific_heat: 14.2, is_pseudo: false }, Chemical { name: "O2", moles: 0.75, mole_mass: 0.000000000000000000000026566962,matter_state: Gas, specific_heat: 0.915, is_pseudo: false }, Chemical { name: "H2O", moles: 0.5, mole_mass: 0.00000000000000000000002991507361, matter_state: Liquid, specific_heat: 4.814, 19:44:29 is_pseudo: false }], temperature: 802.8550270045699, volume: 1 } 19:44:37 Anyone know if that is the correct reaction? 19:44:56 (1 mole H2 1 mole O2 burning, with only half of it burning per universal 'update') 19:44:59 -!- imode has joined. 20:18:30 -!- FreeFull has quit (Quit: Rebooting). 20:30:20 -!- FreeFull has joined. 20:46:20 -!- AnotherTest has joined. 20:56:13 -!- zseri has quit (Quit: Page closed). 21:01:48 -!- Phantom_Hoover has joined. 21:21:18 -!- zseri has joined. 21:22:13 -!- augur has joined. 21:27:02 -!- doesthiswork has quit (Quit: Leaving.). 21:30:08 -!- AnotherTest has quit (Ping timeout: 240 seconds). 21:30:25 -!- AnotherTest has joined. 21:49:17 im currently trying to wrap my head around befunge, because why not :p 21:49:25 working on a fizzbuzz program right now 21:49:41 im sure its been done before, but sometimes you have to reinvent the wheel, you know? :p 21:50:29 so far i've got a thing that counts from 1 to 100 and prints it out 21:50:35 its even got newlines! :D 21:56:48 befunge <3 22:01:56 -!- AnotherTest has quit (Ping timeout: 255 seconds). 22:12:21 ATMunn, may want to look at fungot's code for examples later on. It demonstrates some neat functions 22:12:22 moony: well i'm a my hobby laughter i guess it when i go and i'm like man how am i going to be good 22:12:41 like how to make a.. What does fungot use? in befunge 22:12:41 moony: well i think it was televised uh-uh)) amazing 22:12:50 lol does fungot activate a markov chain or something when you ping it 22:12:50 ATMunn: right it's it's very cooperative you know everyone loved it it was hard but we did and um i don't really i 22:13:05 ATMunn, uses something similar. But fungot is written in pure befunge. 22:13:05 moony: um i used to 22:13:12 neat 22:13:18 lmao 22:13:33 its like "i used to be written in pure befunge, but not anymore" 22:13:45 lol. It still is 22:13:51 i know 22:14:05 but that was too perfect 22:14:22 ikr 22:14:31 also, does fungot use 93 or 98? 22:14:31 ATMunn: yeah yeah i think ah a lot of days later to come back in so sigh you know 22:14:36 98 22:14:38 ah 22:14:46 im using 93 at the moment 22:14:56 use 98, 93 has a size limit 22:15:06 but if i want to do anything more than just something simple then i'll use 98 yeah 22:15:35 what other differences are there 22:19:40 98 has some new instructions 22:25:41 -!- atslash has quit (Ping timeout: 240 seconds). 22:26:01 -!- atslash has joined. 22:26:22 looking at the wiki, quite a few new instructions in fact 22:26:41 including one for every letter of the alphabet it seems :p 22:32:11 Fudge. 22:41:26 -!- augur has quit (Remote host closed the connection). 22:42:31 -!- erkin has quit (Quit: Ouch! Got SIGABRT, dying...). 23:04:30 -!- augur has joined. 23:17:04 -!- zseri has quit (Quit: Page closed). 23:35:03 fungot would be pretty much impossible (or at least implausible) without some of the '98 fingerprints, even without the size issue. 23:35:03 fizzie: see i don't either 23:35:38 In particular the babbling models are a bit too large to fit comfortably in memory, so it needs the FILE fingerprint to read them. 23:37:07 OK, I'm glad I decided not to take part in the contest, now 23:37:16 -!- atslash has quit (Quit: This computer has gone to sleep). 23:37:30 this spec change means you need to start thinking about the algo again 23:37:51 in general, I'm not sure this is a good task for a 1- or 3-day contest, it's more the sort of thing you'd want to spend months on 23:38:12 fizzie: sockets? 23:38:25 https://www.chiark.greenend.org.uk/~sgtatham/puzzles/js/mines.html Always-solvable Minesweeper 23:38:43 ais523: That as well, but I thought the usual "conect stdin/stdout to the server via some external means" approach would work around that. 23:38:45 Gregor tricked himself into thinking a puzzle he encountered didn't have a unique solution 23:38:56 >.> 23:43:30 I still should assume most people are better at Minesweeper than I am 23:46:42 eh, depends 2017-08-05: 00:02:42 -!- atslash has joined. 00:03:32 -!- MDude has quit (Quit: Going offline, see ya! (www.adiirc.com)). 00:12:29 -!- augur has quit (Remote host closed the connection). 00:14:16 -!- augur has joined. 00:40:51 -!- atslash has quit (Quit: This computer has gone to sleep). 00:51:48 -!- atslash has joined. 01:03:49 \o/ now my fizzbuzz thing outputs buzz instead of the number on every multiple of 5 01:04:15 man there's something so satisfying about watching a program counter/instruction pointer fly through a befunge program :p 01:05:32 now to make it output fizz on multiples of 3, and fizzbuzz on multiples of 15 01:07:19 -!- btiffin has joined. 01:09:48 damnit. how do I signal the end of a valid path when all I can use is binary?! 01:18:50 -!- atslash has quit (Quit: This computer has gone to sleep). 01:22:22 -!- Phantom_Hoover has quit (Read error: Connection reset by peer). 01:23:48 -!- hppavilion[1] has quit (Ping timeout: 260 seconds). 01:27:52 Idea - a super-lazy language: a language which /actively/ avoids evaluating expressions, even if they'd normally be necessary. 01:29:06 say you have: var x := 3; var y := 2; var z := sqrt(x^2 + y^2); if (z < 5) { return }; here, the language will avoid evaluating the sqrt, prefering rather to square the 5 01:47:21 I wonder if I could store the traversal in reverse order so that I terminate when I get to the parent. 02:06:25 -!- augur has quit (Remote host closed the connection). 02:07:07 -!- augur has joined. 02:07:50 -!- ATMunn has changed nick to ATMunn62. 02:07:54 -!- ATMunn62 has changed nick to ATMunn. 02:42:27 Wisdom from the layered unit net: 02:42:28 23:12:43 So, it's actually intended for instance for the fucking pokemon point, multi-uninteresting! 02:42:57 -!- augur has quit (Remote host closed the connection). 02:43:45 22:06:00 Define montal maxlack (cannot bother nickname with sweden) 02:51:29 -!- augur has joined. 02:51:42 what does lambdabot have against swedish nicknames. 02:59:31 -!- augur has quit (Remote host closed the connection). 03:02:00 -!- ATMunn has quit (Quit: See ya! o/). 03:07:58 -!- Warrigal_ has quit (Ping timeout: 246 seconds). 03:17:07 -!- contrapumpkin has quit (Quit: My MacBook Pro has gone to sleep. ZZZzzz…). 03:25:50 -!- moony has quit (Ping timeout: 240 seconds). 03:48:56 -!- augur has joined. 04:39:23 -!- augur has quit (Remote host closed the connection). 05:09:26 -!- augur has joined. 05:12:23 -!- oerjan has joined. 05:29:23 rdococ: that's basically a symbolic evaluation language 05:29:36 instead of calculating the values of things, you have them as unevaluated expressions 05:29:49 and then things like conditional operators will compare the expressions symbolically 05:30:31 this also lets you do things like compare expressions with uninitialized variables in and get a yes/no/maybe response 05:31:39 -!- sleffy has joined. 05:52:41 -!- sleffy has quit (Ping timeout: 240 seconds). 06:13:37 "layered unit" \\ "neural" 06:13:40 > "layered unit" \\ "neural" 06:13:42 "yed it" 06:23:48 -!- doesthiswork has joined. 06:43:51 `? lunac 06:43:52 lunac? ¯\(°​_o)/¯ 06:43:54 `? lunacy 06:43:55 lunacy? ¯\(°​_o)/¯ 06:44:30 `learn LUNacy is wisdom generated by a neu^Wlayered unit net. Ask Warrigal for details. 06:44:32 Learned 'lunacy': LUNacy is wisdom generated by a neu^Wlayered unit net. Ask Warrigal for details. 06:50:53 `grWp for details 06:51:04 goat:Goats will eat and drink anything, except tea. Solain is unavailable for details. \ lunacy:LUNacy is wisdom generated by a neu^Wlayered unit net. Ask Warrigal for details. \ monqy:monqy is no longer extant. He lives in concept, hidden, unfindable. You could ask itidus21 for details, if you find him. 06:52:02 What was the command for simulating `...-style command line parsing? 06:52:36 `cat bin/nur 06:52:37 ​"${1%% *}" "${1#* }" 06:53:43 Right. 06:53:49 `nur run 06:53:49 run run run 06:54:47 `2 grWp for details 06:54:48 2/116:. \ ⊥:⊥ is a bottom tack, useful for annoying teachers. \ ☾_:☾_ is moon_'s lawful twin. He's banned in the IRC RFC for being an invalid character. He sometimes eats papers. \ 1:The 1 is just for disambiguation. \ `2:`2 is equivalent to `1 , except that it starts displaying the _second_ output piece. Useful when you've alrea 06:55:05 `2 grWp "for details" 06:55:06 2/1: 06:55:16 `1 grWp "for details" 06:55:18 1/1:goat:Goats will eat and drink anything, except tea. Solain is unavailable for details. \ lunacy:LUNacy is wisdom generated by a neu^Wlayered unit net. Ask Warrigal for details. \ monqy:monqy is no longer extant. He lives in concept, hidden, unfindable. You could ask itidus21 for details, if you find him. 07:01:32 -!- augur has quit (Remote host closed the connection). 07:31:23 hi 07:31:40 hirpal 07:32:48 * oerjan was inspired by the logs to try the "always solvable" mines in chatham's puzzles, but cannot see why this one is solvable. 07:34:10 count? 07:34:23 hm it seems so. 07:34:48 i didn't think i had found enough mines to rule out just by count, but it seems i have. 07:34:57 what is chatham's puzzles? 07:35:07 er 07:35:09 it's like hexham, but more chatty 07:35:11 *tatham 07:35:20 doesn't help either 07:35:46 the mines generator just runs a constraint solver internally, I think 07:35:47 minesweeper puzzles? 07:35:47 https://www.chiark.greenend.org.uk/~sgtatham/puzzles/ 07:36:03 lots of puzzles, minesweeper is just one of them 07:36:37 *just by total count. obviously i've counted neighbors plenty. 07:38:35 oh it even says so in the description 07:38:43 the thing with that type of puzzle for me, I find it far more interesting inventing algorithms for solving it with a computer program than actually solving it myself 07:38:56 OKAY 07:39:01 so not for me 07:39:01 `w itidus 07:39:56 though minesweeper is kind of trivial in that regard, at least sudoku requires some thought of how to solve it efficiently 07:40:04 * oerjan prods HackEgo with the cane J======O 07:40:07 `echo hi 07:40:18 I think it may be dead 07:40:42 It's dead oerjan 07:40:46 NOOOOOOOOOOOOOOOOOOOO 07:41:19 The cane? 07:41:22 hm wiki may be too 07:41:37 shachaf: i've got a cane for telling people to get off my lawn, naturally 07:42:12 it's shape may be a little unstable. 07:42:14 *its 07:42:59 -!- AnotherTest has joined. 07:44:20 Vorpal: You can leave all the cleverness to a SAT solver. 07:45:27 int-e: that is the boring option though 07:46:19 (for Sudoku, I mean, though this extends to quite a lot of puzzles that don't involve guessing... mine sweeper gets kind of interesting if you try to maximize the winning probability on random starting grids) 07:46:37 yeah okay that is true 07:47:48 Hm, there should be more variants of minesweeper. Some ideas (they are probably not original): hex grids, board game version with tiles, multi-player (competitive on shared grid) 07:48:22 Or why not more types of mines, with different radius effects? 07:49:01 Or more attributes, not just number, but make the colour have a meaning (other than 1 is blue, 2 is green, ...) 07:49:25 3D minesweeper 07:49:37 or even higher dimensionality 07:50:33 moving mines, that can move about in patterns, but only under non-revealed tiles 07:57:27 I sense a seumas mcnally award in your future 07:59:38 Vorpal: got Funge-98 embedded in COBOL now. First step anyway. Used rcfunge as it doesn't use exit and rely on q to return top of stack. C and COBOL coding took about 10 minutes, playing with more Funge took hours. 08:00:00 i saw minesweeper with a hex grid on a sphere, it was pretty easy, though 08:00:58 -!- AnotherTest has quit (Ping timeout: 255 seconds). 08:01:29 i also saw a minesweeper crawler where mines were opponents with different levels and the numbers were the sum of the adjacent levels. you will get damage if you attack monsters above your level 08:07:32 . o O ( you cannot put a hex grid on a sphere, it has the wrong euler characteristic ) 08:10:19 -!- AnotherTest has joined. 08:12:14 you are right, there were also pentagons 08:14:31 -!- augur has joined. 08:18:47 -!- augur has quit (Ping timeout: 258 seconds). 08:21:26 -!- atslash has joined. 08:23:39 -!- doesthiswork has quit (Quit: Leaving.). 08:23:48 -!- AnotherTest has quit (Ping timeout: 240 seconds). 08:26:36 -!- atslash has quit (Ping timeout: 260 seconds). 08:27:14 -!- atslash has joined. 08:27:51 Hmm, you can put a pentgrid on a sphere 08:29:20 -!- AnotherTest has joined. 08:31:02 a small one. 08:31:51 wikipedia has a picture of a chocolate brownie and now i'm hungry :( 08:32:09 *+front page 08:38:18 * oerjan tries the esoteric solution known as "eating". 08:39:30 -!- erkin has joined. 08:42:51 -!- AnotherTest has quit (Ping timeout: 255 seconds). 08:43:45 -!- spruit11 has quit (Ping timeout: 255 seconds). 08:51:59 You can make a pentgrid bigger with arbitrary numbers of hexagons, maybe 08:52:39 yes. but you will always have 12 pentagons that way. 08:54:29 Spheres a frustrating like that 08:54:35 -!- bb010g_ has joined. 08:57:47 They have a lot of pent-up frustration. 08:59:54 oerjan, would you recommend eating? 09:00:04 I've heard good things about it but I'm not so sure 09:00:24 I think it depends a lot on what you eat. 09:00:33 Do you like mushrooms? 09:01:16 -!- imode has quit (Ping timeout: 255 seconds). 09:01:53 From time to time 09:02:08 Had mushroom pasta the day before yesterday 09:04:26 "Subject: [FIRING:1] host_down (esolangs.org)". Unfortunately too sleepy to look into this now, and the machine isn't answering to SSH anyway. Will try again tomorrow. 09:07:20 Taneb: I don't recommend eating death caps. 09:08:22 I'll bear that in mind 09:09:58 Taneb: with moderation hth 09:10:15 oerjan, thank you tdh 09:11:38 Good thing oerjan is an op. 09:11:44 . o O ( some crazy people might consider it tomorrow already ) 09:12:08 -!- erkin has quit (Quit: Ouch! Got SIGABRT, dying...). 09:12:56 are there _any_ foods with "death" in the name that are recommended to eat 09:13:10 it's pretty obvious, really. 09:13:51 Death by chocolate? 09:14:29 huh. so it is. 09:14:53 but clearly _someone_ is trying to kill me with chocolate today, anyway. 09:15:08 -!- HackEgo has quit (Ping timeout: 260 seconds). 09:17:38 -!- zseri has joined. 09:33:45 oerjan: You'd think that it'd be easy, but people still eat them for some reason. 09:33:57 Apparently it's a delicious mushroom. 09:36:13 maybe something for one of those bucket lists. in one of the last spots. 09:37:04 -!- zseri has quit (Quit: Page closed). 09:37:30 I recall seeing I think a Tumblr post that was like "Did you know you can drink magma???? But only once" 09:39:07 is suspect magma isn't delicious, though. 09:39:11 *i 09:41:06 I'm not sure I would describe it as drinking. 09:51:00 -!- oerjan has quit (Quit: Later). 09:51:02 -!- FreeFull has quit. 09:55:20 <\oren\> I am da Μαֆד𝒆г of unicode! 10:09:15 -!- ais523 has quit. 10:20:22 -!- btiffin has quit (Quit: ChatZilla 0.9.93 [SeaMonkey 2.46/20170120202656]). 10:28:42 -!- zseri has joined. 10:29:42 esolangs.org seems down. 10:36:19 zseri: so it does 10:36:25 not sure who is responsible for it 10:37:41 @tell btiffin Ah, good. That sort of integration seems less fun than what C-INTERCAL did though, with the calling back and forth between two separate programs 10:37:41 Consider it noted. 10:38:30 myname: interesting 10:39:40 myname: it seems to me there is a huge potential to invent new (possibly interesting, maaaybe good) games by just "x in y genre". I.e. the RPG style minesweeper you decribed 10:39:44 described* 10:40:13 "Subject: [FIRING:1] host_down (esolangs.org)". Unfortunately too sleepy to look into this now, and the machine isn't answering to SSH anyway. Will try again tomorrow. <-- so what timezone are you in? Thought you were in EU? 10:40:57 Vorpal: i totally agree 10:41:30 myname: though now I'm trying to think what a minesweeper with RPGs would be like 10:41:36 first person? 10:41:44 -!- zseri has quit (Quit: Page closed). 10:42:30 i don't think that'll work 10:42:46 also, there is kind of a 3d sokoban 10:43:08 -!- zseri has joined. 10:43:19 and a tetris-like with sand 10:45:30 myname: how does tetris with sand work? 10:46:04 sand just piles up with a certain critical slope, so surely you could never reach the top of the stage before filling the width of the stage 10:46:21 unless the stage is much shorter I guess 10:55:32 https://play.google.com/store/apps/details?id=com.hottato.sandagolite 10:59:14 the video doesn't really explain the mechanics 10:59:39 if you have a big enoug pile of sand of one color, you can make it disappear 10:59:49 (also, as a side note, it feels rather unprofessionally made, using a camera on a phone rather than screen capture) 11:02:57 -!- bb010g_ has quit (Quit: Connection closed for inactivity). 11:26:02 -!- MDude has joined. 11:28:51 myname: what about a tetris with mines such that you build up certain patterns of adjacency? 11:29:53 how? 11:30:22 not sure... maybe one person plays tetris to generate the level that another person solve as a mine sweeper game 11:31:55 or you could just make it require a certain amount of mines per line to remove that line, rather than the fullness of the line, though that way it would be easy to get stuck not being able to remove a filled in line, but that could be solved by having the mines explode nearby blocks when removed (thus "damaging" the line below and above) 11:34:33 that would work but does not sound that interesting 11:34:36 myname: ah, I got an idea that might actually be good (though I personally would be stressed out instead by it): Endless scrolling minesweeper, such that you only see a moving window over a set number or rows or columns, and you have to mark as many mines as possible to get high score. I think one hit kill would be too punishing in this scenario 11:35:49 say every 5 or so seconds (depending on selected difficulty) a new line appears on the left side and an old one is removed on the right 11:36:04 or maybe a block of lines (5 or so) 11:36:25 take a look at concrete jungle 11:36:37 what about a game that is exactly like battleships except you launch airstrikes on terrorists 11:36:47 myname: the one on steam? 11:36:55 Jafet: that is just a re-theme 11:36:55 yeah 11:37:38 myname: this looks turn based (i.e. based on number of actions you perform rather than time)? 11:37:44 that probably works better 11:37:56 it is 11:38:11 yeah, that seems somewhat towards that idea 11:40:42 I'm not much for these types of puzzle games, I find them monotonous. I like puzzle games like Myst and Antichamber, because they are quite varied. 11:41:08 I guess that is why I like programming, it is after all like a puzzle in some ways, but it is very varied 11:41:37 i totally agree 11:42:27 there is way too few mobile friendly interesting gamification of it 11:42:30 I can not understand why my dad continues to engage in Sodoku puzzles for years 11:43:39 i recommend "the sequence" for android, nice little bullying automaton puzzle 11:43:41 Hm, now for a completely different type of puzzle, how early do I need to leave on a Saturday to go to the opposite side of the city arriving at 13:30... 11:44:27 myname: I liked Monument Vally, the puzzles weren't that advanced, but the atmosphere and (rather opaque) storytelling more than made up for it 11:44:50 also the puzzles were basically MC Escher style, messing with perspective 11:45:00 which I very much like 11:45:06 it was way too short, though 11:45:19 yeah, and they haven't ported the second one to Android yet 11:45:38 just ios, which I don't own 11:45:44 also: snakebird is a pretty hard puzzle 11:46:50 euclidea is interesting, too 11:46:52 hm google suggests about 20 minutes driving, but I know that route is not the fastest in practice 11:47:12 oh yeah I saw someone at work playing euclidea I think 11:47:42 myname: I don't mind PC games though, I have a reasonable desktop 11:48:55 myname: the latter two has in app purchases... :/ 11:48:59 and are free 11:49:03 so I expect the worst 11:49:39 anyway I need to get ready to leave, have a great day 11:53:57 euclideas IAP just allow you to skip levels 11:54:34 snakebird is kind of a shareware version, if you don't purchase the one IAP that is there, you can only play a limited amount of levels 11:54:49 demo may be the better term 12:02:20 -!- augur has joined. 12:06:37 -!- augur has quit (Ping timeout: 246 seconds). 12:20:05 -!- btiffin has joined. 12:23:54 -!- LKoen has joined. 12:31:08 -!- hkt has joined. 12:31:45 -!- hkt_ has joined. 12:32:03 -!- hkt_ has quit (Client Quit). 12:33:18 -!- hkt has quit (Client Quit). 12:42:54 -!- augur has joined. 12:48:52 -!- augur has quit (Ping timeout: 260 seconds). 12:50:36 -!- boily has joined. 12:51:21 -!- btiffin has quit (Remote host closed the connection). 12:51:50 hoily! 12:57:47 rdochellochellochellochellochello... 12:58:08 hi. 13:02:17 -!- __kerbal__ has joined. 13:03:38 -!- zseri has quit (Quit: Page closed). 13:03:43 <__kerbal__> hi 13:04:19 <__kerbal__> what happened to the wiki? 13:05:52 `moo 13:06:20 I can't seem to connect to the wiki. 13:06:26 __kellorbal__. 13:06:51 fizzie: fizziello. AAAAAAAAAAAAAAAAAAAAAIAIAIAIAIAIAIAIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIII! 13:06:54 good kerbing. 13:07:19 <__kerbal__> boily: hoillo 13:07:29 -!- hkt has joined. 13:07:48 <__kerbal__> rdococ: grdococtings 13:09:05 I guess it'd make sense for versors (unit quaternions) to be stored in memory with only three values (x, y, z). 13:13:25 it makes sense for display purposes to reduce a quaternion to three dimensions, but their whole purpose in 3D graphics is to expediently compute rotations. 13:14:01 and for that we need all four values to be present and close by, so it's more efficient to keep everything in memory. 13:14:16 k 13:14:32 what happens if they're not unit? 13:14:41 well, w. 13:21:28 say I rotated a cube to Q(0.5, 0, 0, 0). would it appear smaller? 13:22:43 as far as my addled coffeeless brain can figure it, yes. 13:22:58 Wanna try some Klatchian Coffee? 13:24:21 I'm having sourj at the moment. it tastes good. 13:26:14 -!- zseri has joined. 13:27:31 But Klatchian Coffee gives you superspeed! 13:27:37 `relcome zseri 13:27:57 hi 13:27:57 the wiki and the bot are down 13:28:08 'tis the end of times. 13:28:09 I already know. 13:28:31 the horror. 13:28:34 the agony. 13:29:07 ice scream. 13:31:07 the bowl of cereals. 13:31:43 <__kerbal__> What is the ICFP contest? 13:35:49 <__kerbal__> wait, it's this: https://icfpcontest2017.github.io 13:40:53 <__kerbal__> Here's the wiki backup from the last outage: http://esolangs.zem.fi 13:41:06 <__kerbal__> It doesn't work very well, though 13:42:18 <__kerbal__> you have to manually fiddle with the URLs, and the info it provides is incredibly outdated 13:42:28 @metar CYUL 13:42:28 CYUL 051236Z 20010KT 2 1/2SM SHRA BR FEW012 OVC035 19/17 A2978 RMK CF1SC7 VIS W 12 SLP087 DENSITY ALT 900FT 13:44:15 -!- hkt has quit (Quit: http://www.kiwiirc.com/ - A hand crafted IRC client). 14:00:46 -!- doesthiswork has joined. 14:01:24 The search forwards to esolangs.org and thus doesn't work now. 14:01:39 (on the backup page) 14:05:13 -!- boily has quit (Quit: DIGGING CHICKEN). 14:06:19 I'd like to clarify: is the name of the wiki "Esolang", or is it "Esolangs"? 14:06:46 I think it's named "Esolang" 14:06:53 <__kerbal__> The main page suggests "Esolang" 14:07:37 Yes. 14:07:52 But the URL is esolangs.org/, right? 14:08:29 * __kerbal__ 's mind was blown 14:08:46 I'm...not cleaning that up. 14:17:29 -!- ATMunn has joined. 14:27:14 -!- __kerbal__ has quit (Ping timeout: 260 seconds). 14:28:33 But Klatchian Coffee gives you superspeed! <-- makes you knurd 14:29:51 website seems to be down :\ 14:33:22 Yes 14:58:03 -!- doesthiswork has quit (Quit: Leaving.). 15:00:27 -!- augur has joined. 15:04:30 -!- augur has quit (Ping timeout: 240 seconds). 15:06:02 -!- LKoen has quit (Remote host closed the connection). 15:45:07 -!- zseri has quit (Quit: Page closed). 15:45:44 -!- zseri has joined. 15:48:39 \o/ finished my befunge-93 fizzbuzz program 15:48:49 it's probably super inefficient but i dont care :p 15:52:25 is esolangs.zem.fi a clone of esolangs.org? 15:57:18 the esolangs.zem.fi certificate doesn't match the domain name. 16:25:03 is anyone even trying to get the wiki/bot back up? 16:25:37 I don't know. 16:47:48 -!- Warrigal_ has joined. 16:53:39 -!- zseri has quit (Ping timeout: 260 seconds). 16:53:51 -!- imode has joined. 16:59:17 Vorpal: Usually UK, but I'm visiting Mountain View this week. 17:05:11 -!- http_GK1wmSU has joined. 17:07:04 fizzie: ah 17:07:08 fizzie: fixing the wiki? 17:07:40 -!- http_GK1wmSU has left. 17:12:43 -!- heroux has quit (Ping timeout: 268 seconds). 17:16:08 -!- imode has quit (Ping timeout: 246 seconds). 17:16:14 -!- augur has joined. 17:18:17 Vorpal: Can't do terribly much about it, other than maybe ping Gregor. It's not answering SSH. 17:18:34 I could point at the backup copy I have, I guess. 17:18:45 Usually I've done that once it's been down for more than a day though. 17:19:48 Funny, though -- yesterday evening when I got the alert, I was getting a timeout. Now it actually does TCP connect to port 22, but then immediately gets closed by the remote side. 17:20:56 -!- augur has quit (Ping timeout: 260 seconds). 17:22:28 And on port 80 it accepts a connection and reads any data, but doesn't send back any response. That's so odd. 17:29:10 -!- AnotherTest has joined. 17:32:18 -!- zseri has joined. 17:32:27 hi 17:35:39 yay 17:39:44 fungot: poke 17:39:44 ATMunn: and i mean)) i can't really say that that's there policy but different places i've worked they've brought 17:41:31 fungot: Brought what? 17:41:32 fizzie: no but but people were taking it pretty easy i can't imagine how writers and researchers fnord before there used to be that it was 17:58:29 -!- AnotherTest has quit (Ping timeout: 255 seconds). 17:58:59 -!- AnotherTest has joined. 18:02:54 fizziello 18:03:10 -!- AnotherTest has quit (Ping timeout: 240 seconds). 18:23:26 -!- AnotherTest has joined. 18:23:29 -!- zseri has quit (Ping timeout: 260 seconds). 18:33:50 And on port 80 it accepts a connection and reads any data, but doesn't send back any response. That's so odd. <-- very 18:33:52 is it a VPS? 18:35:37 -!- LKoen has joined. 18:59:49 -!- augur has joined. 19:02:24 -!- AnotherTest has quit (Ping timeout: 258 seconds). 19:15:03 -!- atslash has quit (Quit: Leaving). 19:23:28 -!- sleffy has joined. 19:25:12 -!- erkin has joined. 19:40:16 -!- sleffy has quit (Ping timeout: 255 seconds). 19:45:43 -!- augur has quit (Remote host closed the connection). 19:53:08 -!- erkin has quit (Read error: Connection reset by peer). 19:53:41 -!- erkin has joined. 19:54:50 -!- augur has joined. 19:55:06 -!- zseri has joined. 20:03:48 -!- AnotherTest has joined. 20:07:16 hi 20:17:00 -!- erkin has quit (Quit: Ouch! Got SIGABRT, dying...). 20:17:20 -!- erkin has joined. 20:22:50 -!- MrBusiness has quit (Ping timeout: 240 seconds). 20:24:06 -!- augur has quit (Remote host closed the connection). 20:25:40 -!- AnotherTest has quit (Ping timeout: 240 seconds). 20:27:05 -!- GeekDude has changed nick to Rowlet. 20:31:31 -!- augur has joined. 20:51:00 He wasn't a fungi, he was a fungot. 20:51:00 rdococ: ( ( yeah i can i can't even imagine um we my parents had to say about airport security noise mhm)) 20:51:07 ... 21:00:06 -!- FreeFull has joined. 21:00:09 -!- Phantom_Hoover has joined. 21:14:40 -!- MDude has quit (Ping timeout: 240 seconds). 21:15:05 -!- LKoen has quit (Remote host closed the connection). 21:15:08 Let's see how good the layered unit net is at making METARs. 21:15:20 LOWI 021920Z VRB03KT 090V19KT CRICTE40 CLM BKN009/02///////// \1936 \ 9999 122353370 1003 5400 5121 1435 3132 2325 3253 5f46 21:15:42 I'm pretty sure that stopped making sense right around those slashes. 21:16:46 Looks like it gave two wind things instead of one. CRICTE and CLM don't mean anything. 21:17:05 -!- MDude has joined. 21:17:05 -!- AnotherTest has joined. 21:17:10 ENVA 012455Z 02005KT 10SM FEW014 FEW048 SCT064CC2 31/06 Q1013 TEMPO SMP137 TF 40010 FROL 21:25:07 The time there is 24:55 UTC, which is impossible. As far as I can tell, CC2, SMP, 40010, and FROL don't seem to mean anything. 21:25:14 Higher density of mines definitely makes Minesweeper harder 21:25:23 I actually have to think instead of relying on 1-corners 21:25:32 I found a page that says that TF means tornado. 21:27:14 at least for tatham's mines, the critical density seems to be around 40% 21:27:29 https://tortue.itch.io/triangulation 21:27:34 99 mines out of 100 squares is either 99% instant loss, or 100% instant win, depending on whether the implementation is a good one or a bad one 21:27:40 (Interesting take on minesweeper) 21:27:52 this is interesting because from what I can tell, it just generates the minefields at random 21:29:55 then again, 3-sat also has a critical density 21:30:49 oh 21:30:50 cool 21:35:27 -!- pikhq has quit (Ping timeout: 240 seconds). 21:38:21 -!- MrBusiness has joined. 21:39:12 is the wiki down? 21:40:59 -!- pikhq has joined. 21:41:35 -!- AnotherTest has quit (Ping timeout: 268 seconds). 21:43:09 -!- AnotherTest has joined. 21:46:58 -!- Jafet has set topic: http://esolangs.org/ will be back shortly after this bimetal prismack | logs: http://codu.org/logs/_esoteric/ http://tunes.org/~nef/logs/esoteric/?C=M;O=D | https://www.dropbox.com/s/fyhqyvy3i8oh25m/wisdom.pdf | ICFP contest ends on 2017-08-07. 22:02:16 Yes, the wiki is down. 22:08:10 -!- AnotherTest has quit (Ping timeout: 240 seconds). 22:13:41 -!- zseri has quit (Quit: Page closed). 22:33:36 -!- augur has quit (Remote host closed the connection). 22:38:58 -!- sleffy has joined. 22:57:39 -!- sleffy has quit (Quit: Leaving). 22:57:51 -!- augur has joined. 23:07:15 -!- Phantom__Hoover has joined. 23:10:00 -!- Phantom_Hoover has quit (Ping timeout: 260 seconds). 23:28:08 Are there any esolangs in which the break command accepts an integer as the number of loops to break out of? 23:28:30 s/esolangs/normal langs/, because honestly it'd be useful to me 23:28:40 e.g. while true { while true { break; } }; vs e.g. while true { while true { break 2; } }; 23:29:33 Try a language that uses delimited continuations, maybe you could make your own 23:39:54 -!- Warrigal_ has changed nick to tswe_tt. 23:43:07 -!- imode has joined. 23:44:36 excuse me, I have to pick up bits of my brain again. the last time this happened, I was introduced to storing binary tree paths as numbers. 23:50:54 -!- LKoen has joined. 23:51:05 -!- erkin has quit (Quit: Ouch! Got SIGABRT, dying...). 2017-08-06: 00:00:20 -!- tswe_tt has quit (Ping timeout: 268 seconds). 00:14:43 rdococ: There's a bunch where the "break" command (or equivalent) accepts a label of the loop, but there's also at least one where it takes the number. 00:15:32 "Label of the loop" meaning e.g. outer: while true { while true { break outer; } } 00:15:41 ik 00:16:02 Numbers just seem to make sense to me, to be honest. 00:17:11 http://php.net/manual/en/control-structures.break.php "break accepts an optional numeric argument which tells it how many nested enclosing structures are to be broken out of. The default value is 1, only the immediate enclosing structure is broken out of." 00:17:36 break -1; 00:27:35 -!- tswe_tt has joined. 00:27:43 `? squid 00:28:05 :( 00:33:17 -!- Rowlet has changed nick to GeekDude. 00:34:26 rdococ: re taking the number of loops to break out of as an integer: I feel like that's an idea people tend to come up with every so often... 00:35:05 For "serious" languages, I don't see a big advantage over labeled breaks. 00:35:56 I don't see much of a disadvantage. 00:37:01 -!- LKoen has quit (Quit: “It’s only logical. First you learn to talk, then you learn to think. Too bad it’s not the other way round.”). 00:37:27 Well, there are a couple of disadvantages. 00:37:37 When you're writing it in the first place, you have to count the number of loops you're breaking out of. 00:37:40 true 00:37:48 Same thing when you're reading it. You have to count the number of loops it's going to break out of. 00:37:59 So it's perfect for a language that wants to be hard to read. 00:38:03 Yup. 00:38:13 Cool. 00:38:17 If you add or remove a loop without realizing that there's a numbered break in there, you'll break the break. 00:38:36 Sounds lovely and esoteric to me. 00:41:20 -!- imode has quit (Ping timeout: 246 seconds). 00:43:40 -!- imode has joined. 00:47:38 Does the number have to be a constant? 00:51:52 nope 00:52:23 you could, if you really wanted to, ask the user how many loops they'd like to break out of. 01:06:37 -!- tswe_tt has quit (Remote host closed the connection). 01:07:04 -!- tswe_tt has joined. 01:11:49 -!- doesthiswork has joined. 01:23:56 -!- Phantom__Hoover has quit (Read error: Connection reset by peer). 01:24:19 -!- Phantom__Hoover has joined. 01:35:51 -!- MDude has quit (Quit: Going offline, see ya! (www.adiirc.com)). 01:44:36 -!- Phantom__Hoover has quit (Read error: Connection reset by peer). 01:56:08 -!- sebbu2 has quit (Ping timeout: 240 seconds). 02:24:04 @metar KGRR 02:24:04 KGRR 060053Z 26005KT 10SM FEW100 SCT190 BKN250 20/13 A3004 RMK AO2 SLP169 T02000133 02:50:22 where is that quote that says programming a large project in C is like building the taj mahal out of toothpicks? 02:53:10 all I can find is people building the taj mahal out of toothpicks :/ 02:53:53 I couldn't find it in "the lisp curse" which was the context that I remember it from 02:54:14 There sure are a lot of toothpick Taj Mahals 03:04:29 -!- ATMunn has quit (Quit: See ya! o/). 03:20:32 well, I just made some improvements, and at the same time made a downgrade. 03:21:18 in order to store an N-M bit path in a N-bit integer, pad the bit string with N-M 1's, one 0, and then the path. 03:23:05 you could also make it subtractive and say "well I padded it with 3 1's, that means the path is 8 - 3 long." 03:35:25 -!- contrapumpkin has joined. 03:59:23 this wastes one bit. but it's a nice improvement. 04:00:16 hah, you wasted one bit :P 04:00:26 I'd rather waste 0. :P 04:01:00 Here's a compromise: waste 2. you can't waste 0, but it's even like 0! 04:01:06 hahahahhahahaha. 04:03:47 I was considering another scheme where if your path starts with 0, you fill the unused bits with 1's. 04:03:57 and vice versa. 04:04:54 but that would waste one bit as well. 04:05:22 because you'd always need to sacrifice one as a 'boundary bit' even at larger paths.. or would you. 04:05:54 if I wanted to store the path '00000000' in a chunk of 8 bits, I would need 9 because I would need an extra '1'. 04:06:31 same if I wanted to do 11111111, or 10101010. 04:07:41 * imode grumbles. 04:10:14 well, at least it's better than storing the length of the damn bit string. 04:31:51 -!- MDude has joined. 04:34:22 imode: I haven't been able to bully my friends into reading my article and the submission deadline is the 8th. 04:34:35 Would you be willing to help me? 04:42:35 uhm. I suppose. what's the article about. 04:43:24 Live-Programming :) 04:43:26 https://www.pdf-archive.com/2017/08/06/scrubbing-complex-and-non-incremental-domains-1/ 04:44:02 sure. I suppose. 04:44:40 Thank you 04:45:05 4's "conclusion" is not capitalized. 04:45:29 what's with the weird red numbers on the sides. 04:45:55 adding "review" does that 04:46:02 ah. 04:46:21 so your main idea is scrubbing CAs? 04:46:23 mm. 04:47:10 yes, because the technique should be generalizable to other things that seemed unscrubbable 04:47:46 kind of cool. scrubbable datastructures would be an interesting thing to investigate after this introduction. 04:49:31 could you tell me what kind of data structures would interesting to scrub? 04:50:13 anything really with a composable set of transforms. something like a 3D renderer with a scrubbable "matrix timeline" would be interesting. 04:50:21 something akin to a scrubbable forth would also be cool. 04:50:33 maybe something with scrubbable graph operations 04:51:31 wonderful! 04:52:07 honestly the first one wouldn't be that hard to hack up in GLSL. 05:07:39 I have made up two loading programs for MIX each of which fit on one card (and in fact the last five character positions of that card aren't used), one for specific byte size and one to be independent of byte size. (The independent one needs more cards to encode a program than the one for specific byte sizes.) 05:12:33 Here is one (untested, may contain mistakes): " N O6 A O4 H N ENX E K BU I OA H A. PA N D LB E AEU ABG G 9" 05:13:04 Do you like this? 05:16:36 huh, google's recaptcha tests recognition of vehicles in a photo 05:18:12 isn't this the kind of thing that google's automatic driver can recognise? 05:18:15 They phased out the "select all squares with Sarah Connor" captcha 05:22:45 (It is actually a 80-column card, so there are five more spaces afterward, although the copy in RAM will be immediately overwritten anyways so it doesn't matter; using spaces means less holes will be punched into the card, though) 05:25:47 If you are making a code golf with MIX, you could have the variants. Such as, binary program loading, as well as text program loading, and in the text case, you could have variants such as if some characters cannot be loaded from cards, as well as the scoring, such as the total number of cards, total number of holes punched into the cards, or total mass of the cards (in this last case, you may allow "lace columns", which have an undefined value). 05:31:59 `5 w 05:33:52 Oh, right. 05:35:13 -!- joast has quit (Ping timeout: 246 seconds). 05:35:28 it's actually better without all that bot spam in the way 05:35:34 `? shachaf 05:35:39 that would be an interesting code golf: write the lightest program that does a given task 05:36:04 and only allow languages that can be used with punch cards 05:40:18 Yes, I thought so perhaps 05:49:20 -!- hppavilion[1] has joined. 06:06:02 -!- contrapumpkin has quit (Quit: My MacBook Pro has gone to sleep. ZZZzzz…). 06:22:09 @metar ESGG 06:22:09 ESGG 060450Z 24013KT 9999 BKN016 13/10 Q1008 06:22:15 chilly 06:24:56 @metar EGSC 06:24:56 No result. 06:25:18 ... I'm sure that's worked previously 06:27:47 it only shows data that's less than 3 hours old, I think 06:28:20 so if you have an airport that closes overnight and has no automated updates then this can easily happen 06:28:26 That might be it, it's pretty early here and it's a tiny airport 06:29:06 It's also the closest I've ever lived to anything with an ICAO code 07:14:52 -!- oerjan has joined. 07:17:41 -!- sftp has quit (Ping timeout: 255 seconds). 07:17:49 -!- augur has quit (Remote host closed the connection). 07:40:16 -!- imode has quit (Ping timeout: 255 seconds). 07:52:37 -!- doesthiswork has quit (Quit: Leaving.). 07:56:47 -!- sftp has joined. 09:12:09 -!- AnotherTest has joined. 09:27:49 -!- AnotherTest has quit (Ping timeout: 255 seconds). 09:28:54 -!- AnotherTest has joined. 09:34:15 -!- erkin has joined. 09:47:37 @tell doesthiswork They phased out the "select all squares with Sarah Connor" captcha <-- i'm pretty sure "phased out" is the wrong verb here hth 09:47:37 Consider it noted. 09:49:07 -!- AnotherTest has quit (Ping timeout: 276 seconds). 09:55:15 -!- AnotherTest has joined. 10:21:23 I'm sure they'll be back 10:35:45 @metar EGSC 10:35:45 EGSC 060920Z 23009KT 190V250 9999 FEW020 18/11 Q1022 10:38:45 @metar koak 10:38:45 KOAK 060853Z 29012KT 10SM OVC008 16/16 A2992 RMK AO2 SLP131 T01610156 56005 10:38:49 @metar ksjc 10:38:49 KSJC 060853Z AUTO 30005KT 10SM CLR 18/16 A2991 RMK AO2 SLP129 T01780156 56006 10:38:53 @metar ksan 10:38:53 KSAN 060851Z 18003KT 10SM OVC017 21/17 A2992 RMK AO2 SLP132 T02110167 58007 10:38:58 @metar llbg 10:38:59 LLBG 060920Z 29008KT 240V340 CAVOK 32/21 Q1007 NOSIG 10:39:15 Taneb: Did you learn Latin? 10:39:29 Up to A-level 10:39:47 I was never particularly good at it but I know a bit 10:39:52 Do levels go from A to Z? 10:40:11 That would be nice but unfortunately not 10:40:24 Why do you ask about Latin? 10:40:40 I know someone who's learning Latin this summer. 10:40:52 I vaguely remembered that maybe you learned it once but I wasn't sure. 10:42:06 Good luck to them! I hope they enjoy it 10:43:24 Well, they're almost done. 10:47:44 -!- zseri has joined. 10:47:53 hi 10:52:10 -!- AnotherTest has quit (Ping timeout: 276 seconds). 10:55:36 -!- hppavilion[1] has quit (Ping timeout: 255 seconds). 11:00:36 -!- atehwa_ has quit (Remote host closed the connection). 11:09:42 -!- oerjan has quit (Quit: Later). 11:13:46 -!- AnotherTest has joined. 11:19:45 -!- sebbu has joined. 11:46:33 -!- LKoen has joined. 12:16:02 -!- erkin has quit (Quit: Ouch! Got SIGABRT, dying...). 12:23:14 -!- zseri has quit (Ping timeout: 260 seconds). 12:39:30 -!- AnotherTest has quit (Ping timeout: 240 seconds). 12:40:18 -!- AnotherTest has joined. 12:50:28 -!- AnotherTest has quit (Ping timeout: 276 seconds). 13:01:01 -!- PattuX has joined. 13:14:06 -!- http_GK1wmSU has joined. 13:16:20 -!- http_GK1wmSU has left. 13:30:46 -!- Phantom_Hoover has joined. 13:54:04 -!- AnotherTest has joined. 14:00:43 -!- doesthiswork has joined. 14:01:00 -!- heroux has joined. 14:03:13 -!- AnotherTest has quit (Ping timeout: 255 seconds). 14:03:35 -!- AnotherTest has joined. 14:14:22 -!- heroux has quit (Remote host closed the connection). 14:17:32 -!- heroux has joined. 14:18:53 -!- augur has joined. 14:23:10 -!- augur has quit (Ping timeout: 240 seconds). 14:43:41 -!- ATMunn has joined. 15:04:44 -!- doesthiswork has quit (Quit: Leaving.). 15:06:46 -!- AnotherTest has quit (Ping timeout: 246 seconds). 15:59:01 -!- zseri has joined. 16:01:06 esolangs.org is still down. 16:23:10 -!- MrBusiness has quit (Ping timeout: 240 seconds). 16:28:37 -!- contrapumpkin has joined. 16:29:10 -!- MrBusiness has joined. 16:32:51 -!- contrapumpkin has quit (Client Quit). 16:35:02 -!- atehwa has joined. 16:56:49 -!- zseri has quit (Ping timeout: 260 seconds). 17:10:01 -!- AnotherTest has joined. 17:28:36 `smlist 17:29:42 -!- FreeFull has quit (Ping timeout: 260 seconds). 17:32:23 -!- AnotherTest has quit (Ping timeout: 255 seconds). 17:32:53 -!- AnotherTest has joined. 17:41:22 -!- FreeFull has joined. 17:48:59 -!- AnotherTest has quit (Ping timeout: 258 seconds). 18:29:43 -!- erkin has joined. 18:52:43 -!- imode has joined. 18:54:58 -!- zseri has joined. 19:42:10 When does the Wiki go online again? 19:53:11 I don't know 20:03:26 -!- viznut_ has joined. 20:07:55 -!- j-bot has quit (*.net *.split). 20:07:55 -!- izabera has quit (*.net *.split). 20:07:55 -!- olsner has quit (*.net *.split). 20:07:56 -!- zgrepc has quit (*.net *.split). 20:07:57 -!- viznut has quit (*.net *.split). 20:08:49 -!- olsner_ has joined. 20:11:23 "The Rekursiv Single-Board Computer had hardware support for a writable instruction set (that is, you could dynamically add microcode instructions) and associative memory dispatch tables for supporting object-oriented programming. 20:11:23 " 20:11:29 ...writable instruction set 20:11:34 That sounds fascinating 20:12:31 sgello 20:12:32 O_o 20:12:42 mornintopia 20:12:49 evenintopia, rather. 20:13:10 its a rainy fternoon 20:13:40 eh, it's closer to ighttime. 20:16:38 I'd say it's vening 20:16:47 You know 20:16:56 Maybe we're in different imezones 20:17:05 -!- copumpkin has quit (Ping timeout: 255 seconds). 20:18:49 -!- j-bot has joined. 20:18:49 -!- izabera has joined. 20:18:49 -!- zgrepc has joined. 20:19:51 here its just past 3, with some 6 hours to go until ighttime 20:20:00 also anell9 20:20:04 anello 20:23:18 -!- joast has joined. 20:26:14 -!- zseri has quit (Ping timeout: 260 seconds). 20:27:02 Today I had a go at an idea I had about 4 years ago 20:27:16 I think I did a cleaner job than I did back then 20:30:16 a new tanebvention? 20:37:35 -!- zseri has joined. 20:38:27 -!- AnotherTest has joined. 20:45:03 -!- ais523 has joined. 20:52:43 When does the Wiki go online again? 20:52:44 hi 20:57:20 zseri, I don't think asking over and over again is going to make it come back any faster 20:57:40 Especially when none of us know all that much more than you do 20:57:42 I know. 20:58:02 Why do x86 processors have so many modes? 20:58:52 Because they have grown historically. 20:59:40 zseri, if you just want to read it, it's on the wayback machine here: http://web.archive.org/web/20170710222334/http://esolangs.org/wiki/Main_Page 21:00:34 quintopia, nah, just something I've made 21:00:43 I also know the backup page: http://esolangs.zem.fi/wiki/Main_Page 21:01:04 so, your point of asking is what? 21:01:20 `quote definition of insanity 21:01:33 ...no wiki, no HackEgo, of course 21:02:35 But the search doesn't work on the backup page. 21:03:55 there is a language list 21:04:54 ok 21:06:49 -!- Phantom_Hoover has quit (Read error: Connection reset by peer). 21:08:40 -!- zseri has quit (Quit: Page closed). 21:10:11 -!- AnotherTest has quit (Ping timeout: 246 seconds). 21:14:04 -!- AnotherTest has joined. 21:24:23 -!- augur has joined. 21:48:30 -!- AnotherTest has quit (Ping timeout: 240 seconds). 21:51:54 -!- AnotherTest has joined. 21:57:50 I have a flight today, but will try to set the backup back up properly tomorrow, assuming the real thing is still down then. 21:58:36 -!- hppavilion[1] has joined. 22:04:31 hm, what's a good fungy-98 interpreter? im on windows. i downloaded one made in c#, but i dont really like the look of it, and i'd prefer a browser based one. 22:08:34 -!- dingbat has quit (Quit: Connection closed for inactivity). 22:10:03 -!- erkin has quit (Quit: Ouch! Got SIGABRT, dying...). 22:13:04 -!- AnotherTest has quit (Ping timeout: 246 seconds). 22:13:24 -!- AnotherTest has joined. 22:19:32 -!- copumpkin has joined. 22:28:34 -!- LKoen has quit (Remote host closed the connection). 22:31:30 -!- AnotherTest has quit (Ping timeout: 240 seconds). 22:33:56 I'll pay for efficient sibling traversal with one bit. 22:47:05 heh 22:50:09 Do you have some test files for MIX to test implementations? 22:55:30 -!- contrapumpkin has joined. 22:56:55 -!- ais523 has quit (Remote host closed the connection). 22:58:04 -!- ais523 has joined. 23:03:48 -!- augur has quit (Remote host closed the connection). 23:14:46 -!- LKoen has joined. 23:22:57 -!- augur has joined. 23:28:29 -!- wob_jonas has joined. 23:32:38 hello, guys 23:32:42 what happened while I was away? 23:39:40 Do you have some test files for MIX to test implementations? 23:40:13 no. you'll just have to look at the programs from the Knuth vol 1 to 3, such as the crossword program 23:40:42 I don't use MIX, I just documented it as an esolang. 23:48:17 -!- Mr2001 has quit (*.net *.split). 23:48:29 -!- boily has joined. 23:49:47 `w 23:53:22 -!- Mr2001 has joined. 23:54:12 Still I want to see to find some program. I do not have those book anymore because they were from the library 23:54:29 (and, it was a inter library loan, so I can't read it there, either) 23:56:12 zzo38: wait, aren't you in an English-speaking country? why do you need an inter-library loan for it? 23:56:57 wob_jonas: Because different libraries have different books. 23:57:39 anyway, even though the e-book edition is expensive and the only website where you can buy it sucks, it was totally worth the money I spent 23:58:32 this way I got the originals, and their latest editions, so I can now give away my translations of vol 1 to 3 inclusive (which are good, but based on the older edition) 23:58:50 I will totally buy vol 4B and 4C and 5 when they come out 2017-08-07: 00:03:11 -!- augur_ has joined. 00:04:46 Should I read the 80386 manual to start learning assembly? 00:04:52 OSDev wiki seems to suggest that 00:05:00 http://wiki.osdev.org/Learning_80x86_Assembly 00:05:05 -!- augur has quit (Ping timeout: 240 seconds). 00:06:17 Sgeo_: maybe. but don't forget that cpus have changed a lot since the 386. they have out-of order execution and speculative and rollback and crazy branch condition and target prediction and multi-level caches and vector registers (which are the new general registers) and 64-bit mode and all that stuff now. 00:06:53 oh, and register renaming too 00:06:56 not all english-speaking countries have useful libraries 00:07:02 and fast-multiplication 00:08:44 Sgeo_: do you want to learn how to write assembly that works or assembly that runs fast? 00:08:58 I want to understand CPUs better. 00:09:01 assembly optimization is pretty crazy nowadays, mostly because processors no longer work anything like asm assumes they do 00:09:26 modern x86 basically recompiles the asm into an entirely different format on the fly 00:10:00 ais523: I personally care about the x86 cpu to learn how to write compiled code (C or C++ etc) that can run fast. it's rare that you actually have to write assembly, but knowing what the cpu does and caches and stuff helps when you write compiled code. 00:11:43 it's hard to know how to understand CPUs better nowadays 00:11:58 I guess looking at pathological cases and understanding why they're pathological can help 00:12:14 I suppose you could start with agner fog's optimization manual 00:13:03 (namely, the microarchitecture manual) 00:13:25 -!- augur_ has quit (Read error: Connection reset by peer). 00:14:16 ais523: you don't need to understand it perfectly, but knowing something about it can help 00:20:12 one other approach, which is a bit more relaxing, is to read mysticial's stack overflow answers 00:20:21 I would want to instead design the computer better, to not be so complicated and confusing like that. 00:22:19 Some of the complicatedness have really good excuses. Like, you know, speed of light and how big atoms are. 00:24:13 Yes, but I think there are better ways to deal with that. 00:24:29 with the speed of light? 00:24:35 or with the size of atoms? 00:25:13 less speed of light and more speed of electric charge through a medium. :P 00:25:27 but I guess if you did optical computing.. 00:26:19 imode: that matters only in the short deep circuits, like within the cpu. for between the main ram and cpu where there's only wires, no logic, the propagation speed is basically the speed of light. 00:27:01 You shouldn't put the out of order execution, complicated caching, speculation/rollback, etc. Make any stuff being doing explicily as part of the program instead. 00:27:06 then there are dumb complications, like how every x86 chip has three different types of floating point units 00:27:22 what? it's all subject to the speed of electric charge through a medium. transferrance of charge is NOT the speed of light. 00:28:03 (apparently gcc defaults to doing all floating point in sse now, if you use -ffast-math) 00:28:08 regardless of whether or not there's logic in the way. logic only adds switching delays, gate delays, etc. 00:28:49 zzo38: I don't think that's a good idea. hardware guys tried that, but it turns out it only works if you assume the software guys can write magic compilers that can guess how cached each memory load actually is and the people who write the high level code want to annotate their C code with lots of hints, 00:29:14 and even then the machine code will be very verbose and you can't cache it properly. 00:29:35 out-of-order execution and register renaming and speculative branch prediction works well. 00:29:58 the way to think about modern x86 machine code is as a compression scheme for what's actually run 00:30:03 and one that isn't very good, at that 00:30:24 I don't like it, as then you can't know what order it is in, and so on. MMIX has explicit branch prediction; you must specify whether you want a branch or not-branch to be faster. 00:30:28 the machine models probably should stay the same, but we should move to asynchronous circuits. 00:30:38 actually, the complexity of a modern core exists for a more fundamental reason 00:30:51 because memory is getting slower 00:30:53 Then use a better compression scheme, I suppose? 00:31:13 most of the time the bottleneck is either memory access when people write cache-unfriendly code or decoding time when people write cache-friendly code. it's less common that the bottleneck is mispredicted jumps which is the only case when reducing the depth of the pipeline would actually help. 00:32:16 If I want caching I should to explicitly write in the caching instead. 00:32:40 zzo38: tell that to stupid programmers who insist on using large arrays of 64-bit pointers everywhere when large arrays of 32-bit array indexes would work. 00:32:48 since memory is getting slower, there is nothing else for your doubling transistor counts to do other than to reorder more loads and stores or to cram more ways to use that memory bandwidth into the instruction decoder 00:32:57 zzo38: it's not "if I want caching". you almost always want caching. 00:33:42 I don't want to complicate it. You don't need so huge number of transistor and so slow memory; make faster memory then. 00:34:04 helloily 00:34:34 Jafet: I have said this a few times, but what would IMO help a lot is if the cpu and OS people together found a way to increase the minimum page size from 4k, because then we could have more L1 cache, but it only works globally and some software assumes the page size is fixed, so it's really hard to do without breaking compatibility with everything 00:34:34 we have. 00:35:40 zzo38: memory throughput is plenty fast, especially if you're willing to buy expensive hardware. you can't have faster memory in latency though, because the main memory is between 0.1 to 0.3 meters from the cpu pyhsically, so the signal takes several clock cycles to propagate 00:35:52 what does the page size have to do with it? 00:36:20 that's why we need lots of on-board caches, in three levels (L3 for the whole chip, L2 per core or per two cores, and L1 with very slow latency really close to the execution units) 00:37:39 Jafet: basically L1 cache wants to have very low latency, so it has to guess which cache slot holds your memory before it can look up the physical address in the page table cache (aka TLB = translation lookaside buffer), then verify that the address matches what the cache entry caches. 00:38:41 So the L1 cache can only use the low 14 bits of the address, and it practically can't have more than 8 entries for any one address because then managing it would be too slow. So L1 caches have been topped out at 32 kilobytes (8 page sizes) of data cache and 32 kilobytes of code cache per core for half a decade now. 00:38:48 -!- sebbu has quit (Ping timeout: 240 seconds). 00:38:49 I still think there is a way to do though, by having separate addressing for the cache 00:39:18 And put the memory in the processor itself also microcode, that you can program your own microcode too, to improve the speed. 00:39:38 All cpus have that much L1 cache, but none can have more. To fix this, either you need larger page sizes, or some even more incompatible change. 00:40:14 I am not so concerned if C codes will run extremely fast, since you can write it in assembly language if you want to code for specifically this computer. 00:40:20 zzo38: the memory IS practically in the processor. processors have like 380 megabytes of L3 cache, and it keeps increasing. you get memory outside of the cpu too because most people want even more memory than that. 00:41:32 Yes, but you could have separate addressing for them. 00:41:56 yeah. sliding memory windows.. 00:42:07 -!- LKoen has quit (Quit: “It’s only logical. First you learn to talk, then you learn to think. Too bad it’s not the other way round.”). 00:42:14 you could run a linux system off of cache alone these days. 00:42:17 zzo38: why would that be worth? the program can't tell in advance which memory will be in L3 because that depends a lot on the multitasking, and spilling from L3 to memory doesn't really add much overhead anyway. 00:42:39 note that for the machines that have 380 megabytes of L3, it takes almost as long to access as the dram 00:42:52 imode: I think motherboards don't really support that, but that doesn't matter, because slow RAM chips are cheap anyway, so you can just put some in. 00:42:56 Design it so that the program does know in advance, because only what the program puts there will be there. 00:43:02 at least for chipsets that I know of 00:43:16 Jafet: no, not really. not in latency. It's still five times closer physically than the main memory. 00:43:25 hi wob_jonas 00:43:29 hi shachaf 00:43:37 I ate lángos the other day. 00:43:45 shachaf: go on 00:43:52 That's pretty much it. 00:43:59 Do you eat it sometimes? 00:44:07 You may even add parallel memory transfer if you want to, and then you can only address the cache, and not the external memory. 00:44:09 no, I don't much like it 00:46:40 I don't like food that's soggy with fat. That mostly comes up with ways to prepare meat, but lángos is an example too. 00:47:18 It was very deep-fried. 00:48:09 Exactly. 00:48:14 Doesn't change much. 00:48:30 Is there other Hungarian food I should try? 00:48:34 here's a diagram claiming 40ns for the SB-E interconnect https://mechanical-sympathy.blogspot.de/2013/02/cpu-cache-flushing-fallacy.html 00:49:01 although I'm not sure if I should believe 65ns dram 00:49:06 shachaf: I can't predict what you'd like. 00:49:16 are you in Hungary or close somewhere? 00:49:47 or just ate lángos in Norway? I've seen such sold in Sweden, though I can't tell how authentic they are. 00:49:50 No. 00:49:54 It was in Oakland, CA. 00:50:02 I don't know how authentic it was, or how to measure that. 00:51:32 relatedly, the mill architecture videos were p.g. 00:52:25 Did you watch them all? 00:52:25 In any case, even if better architecture is possible, I care about x86_64 only, because it has the best support: most of the powerful computers have it, including anything I'll buy, and there's lots of good tools like optimizing compilers and good documentation. 00:52:33 You should go work for the Mill folks. 00:54:02 No, x86_64 is too complicated and too confusing; MMIX is better, and the original x86 is also good, and also MIX, and also 6502. 00:54:13 I did watch them all, but the plot twist in 10 was perhaps worth it 00:54:36 zzo38: Do you like the Mill? 00:55:03 Jafet: 10? 00:55:09 I looked but was unable to find the proper document of it 00:55:26 zzo38: I think the best documentation is in video form unfortunately. 00:55:30 Did you watch the videos? 00:55:33 No 00:56:16 There are a lot of people that start projects about fancy new cpu architectures, but actually making good optimized and well-tested cpu hardware and supporting software like optimizing compilers is pretty hard, so I don't think those projects make any sense. 00:56:39 Only a big company like Intel or AMD has the resource to be competitive in it. 00:56:41 You can write the program in assembly language, though. 00:57:12 huh, video 10 (“compiler”) is not the tenth on the website 00:57:25 And while it's easy to criticise Intel, and they do make mistakes, they are actually doing a pretty good work overall IMO. 00:57:28 well, it was that one 00:57:31 Hmm, what's the twist in that video? 00:58:22 the true nature of the mill is revealed in the end, in the q&a session I think 00:58:38 zzo38: only if you don't care about the lots of existing software written in C and other compiled languages that you'll want to run and want them to perform fast, such as the linux kernel itself 00:58:59 Which true nature? I watched the video but it was a while ago. 01:00:04 and don't even try to say you'll just have two different cpus side by side, because it turns out, if you want to do thousands of operating system calls per second and low latency networking and stuff like that, that just doesn't work. 01:00:25 Of course I will likely want the programs to run, but I can do without them going fast if making them fast means making a lot of confusion and complication, and instead write assembly languages programs when wanting to make a faster program specifically for this computer. This is always the case anyways; you will want to write assembly language program hand optimize for space and speed taking advantage of the specific features of this computer. 01:00:49 For example, you might use different kinds of data structures for the version of the program for different computers, too. 01:01:17 zzo38: for some programs, you can get away with running slow. but you won't rewrite the linux kernel and all the hardware drivers. there's a lot of work going into that project. 01:01:19 Or one version might omit some check that is needed on another implementaiton. Or whatever. 01:01:23 shachaf: something about how the belt is really just a better register map 01:01:32 but I don't remember clearly either 01:01:40 Jafet: Ah, I vaguely remember something like that. 01:01:47 Different computers will have different interfacing with hardware anyways. 01:02:02 I talked to someone who worked at Intel about it and they were a bit dubious about the hardware implementation of it. 01:02:09 But I don't really know much about it. 01:02:13 zzo38: Do you like the Mill's instruction encoding? 01:02:20 I don't know how it is work 01:02:22 zzo38: There are two instruction pointers, one moving forward and the other moving backward. 01:03:48 My own idea a bit different, there is a microcode memory (with RAM and ROM), that you can load VLIW microcode into, and uses entirely different addressing (and even different number of bits) from the external memory, is one thing that it does. There are others too. 01:04:15 zzo38: Do you like the Mill's belt? 01:04:16 Programs can load their own self-modifying microcodes. 01:04:56 Is self-modifying code worth the trouble? 01:05:08 shachaf: Again, I don't know how it is working; you will need to explain them if I am to answer such questions 01:05:26 I think self-modifying code is worth the trouble; I do not see why not. 01:05:53 zzo38: The belt is like a stack, except it's a queue of some bounded size. 01:05:56 As long as the CPU execution is defined precisely and unambiguously, then you have compatibility. 01:06:32 Instructions push their results onto the belt, and refer to belt positions by index (i.e. how recently a value was pushed). 01:07:11 When values fall off the end of the belt, they disappear. 01:07:31 Actually I have done stuff like that before, so yes I do understand. 01:08:52 people try that, but IMO it doesn't work. ostensibly it saves a few bits in the encoding, but nothing else (the register renamer isn't actually a bottleneck EVERY, register reads and writes sometimes are but a belt doesn't help) and your code gets much harder to write when you need to store registers for longer or need conditions or loops. 01:09:13 it does sound like a good idea, I've thought about it, but I don't think it works. 01:10:20 as I understand it, the main point of the belt is that you get to use 512 registers instead of 16 01:10:54 how does that work? don't you still need to encode all the input registers in the code explicitly, even if you can omit the output register most of the time? 01:11:48 we can have a plain large register array (like the one with 32 vector registers in future x86) or a large MMIX-like register stack if we just want more registers 01:12:17 (and that's 32 vector registers, plus the same 16 index registers you've always had) 01:12:17 well, the output registers are always fixed, so leaving that out does free up some bits 01:12:30 -!- augur has joined. 01:12:44 (and if you want even more, you can save index registers into fields of vector registers, and also efficiently use the stack) 01:12:48 but the videos didn't go into any detail about the instruction encoding 01:12:55 wob_jonas: golfing languages have experimented with different registerish things quite a bit 01:12:59 I just don't believe it saves much 01:13:12 I think the optimum is to have some way to have very cheap, short-lived local values but also separate storage for longer-lived values 01:13:23 a Mill-like belt is good at the former but not the latter 01:13:59 ais523: after a limit, golfing doesn't help. modern x86 extensions actually are somewhat less golfed than old x68 used to be, because being able to decode the instructions quickly is more important. so they actually have a lot of unused bits in instructions in EVEX encoding. 01:14:28 wob_jonas: well, golfing helps in that it reduces cache pressure 01:14:31 Sure, compact code still matters, but extreme golfing isn't always good. 01:14:36 I prefer how MMIX is doing actually, although I can also think of a few other ideas about how to do 01:15:02 and the thing about a highly golfed instruction set is that there's more scope to improve its performance as processors get better 01:15:09 and you lose a lot in expressability 01:15:14 REX encoding annoys me, it's so verbose, and yet you have to use it for basically everything on x86_64 01:15:30 -!- doesthiswork has joined. 01:16:53 ais523: nah, the double prefixes (0xF0 and one more prefix byte) for old SSE code is much worse, but it was necessary for easy decoding 01:17:15 I still think modern x86 is too messy, and modern ARM is also too messy. 01:17:17 but it get somewhat better with the later extensions (AVX code and AVX512 code) 01:17:55 zzo38: sure, there's some historical craft, but a lot of it is pushed out to where it doesn't actually impact the performance if you don't use it 01:18:34 I am not talking about historical stuff, but about the new stuff. 01:18:42 the mill speaker was going on about small loops very often, so I don't think his goal was to improve instruction set density 01:20:15 zzo38: some of it is messy, but they are getting better in the design than they used to. AVX512 actually manages to avoid the AVX stupidity o(where vector registers got split to 16 bit and 32 bit) which was only done to make it easier for operating systesm 01:21:18 you only affect whole registers now, which by the way means you can't have callee-saved registers because they can't save the upper part if the register is ever extended to 1024 bytes, but that ship has sailed with AVX2 anyway already 01:21:22 he had a plan to pipeline loops with nullable values, though (which can be implemented in a conventional CPU) 01:21:23 or with AVX 01:21:38 the vector registers all have to be scratch except for the lower 128 bits of four of them 01:22:03 Jafet: we have efficient conditional move instructions for that 01:23:05 it took us quite a while, they should have added them long ago, so sadly you still have to feature test for them on x86_64, but still, they are there in all currently used cpus 01:23:09 zzo38: even the original 8086 was pretty messy 01:23:17 x86 must be the worst popular asm 01:23:34 What's a good popular asm? 01:23:41 6502. 01:23:47 ais523: yes, and it already had stupid historic cruft for marketing reasons 01:24:02 6502 isn't popular but it is fairly good for the scale of processor it's on 01:24:27 ais523: Yes, but still not quite as messy as the modern kind 01:24:29 you still have to move a value, though, and it could cause an instruction in the pipeline to trap? 01:25:02 6502's pipeline is /very/ short 01:25:06 I do like 6502 though, as well as MMIX 01:25:33 6502 was good when it was new. but it's just not modern. 01:26:08 ARM then. AVR. MIPS. choose one, they all suck in many ways. :P 01:26:36 Is why, I will prefer MMIX than ARM, AVR, MIPS 01:27:07 I think 8080 seems nice. 01:27:14 What's all the hype about 8086? 01:27:28 historic reasons. 01:30:22 tswe_tt: historical 8086 isn't important, except historically as in it has a lot of successors that have inherited some decisions from it that made sense at the time but are hard to support now and take a ton of time to get rid of them. modern x86_64 matters because it's the best supported high-performance cpu there is on the market now, with good 01:30:22 hardware and software, both well-tested and high performance. 01:36:30 `? charizard 01:36:56 wait, where's HackEgo. fungot, what did you do with HackEgo? 01:36:56 wob_jonas: yes i think everybody's just afraid i think now 01:36:59 when people say that arm's instruction set is good, are they referring to a subset that does not include thumb, thumb2, jazelle, neon, virtualization, or mov pc 01:38:23 all of the damn embeddings I've seen for binary trees have been in hypercubes, and they all waste one bit of space. 01:38:53 one bit per tree? 01:38:56 `? bulbasaur 01:39:07 one bit per path to a node. 01:40:02 it seems that I can't escape paying one bit.. 01:40:25 Can you prove it? 01:40:38 certainly trying to. 01:41:19 you can encode any path from the root of an N level full binary tree to any of its leaves in N bits, but you can't encode a partial path. 01:41:44 unless I'm clinically insane, you will always have leftover bits that stand for a left traversal if left unchanged. 01:44:53 ah, the wonderful world of small-space information-theoretic lower bounds 01:45:11 you have to waste _at least one bit_ to mark the start of a valid sequence of branches. 01:45:45 doesn't an n-level binary tree have 2^n-1 nodes? 01:46:59 if it's balanced 01:47:20 hm. 01:50:57 Jafet: I'm trying to avoid integer arithmetic. calculating parent paths is not beneficial if you're dealing with paths through 1024-level binary trees or larger. 01:51:11 this is actually faster. 01:51:45 -!- augur has quit (Remote host closed the connection). 01:52:28 the problem reduces to "how do I store the length of a bit vector without storing the length of a bit vector." :P 01:55:12 -!- augur has joined. 01:55:29 -!- boily has quit (Quit: ARTICULATED CHICKEN). 01:59:02 I believe that computers do integer arithmetic in binary 01:59:49 that they do. but I would rather not implement arbitrarily large binary numbers just to store large paths. 02:00:08 now, arbitrarily large bitvectors on the other hand, that I can get behind. 02:00:09 But for what kind of computer? 02:01:50 Let's see what the weather forecast says. Does the weather cool down after this rain and storm and cold front? 02:02:32 if you store all paths with the same number of bits, then you do not need any extra bits 02:03:43 yeah, you do. if you want to store a path in a byte, you're going to store lefts as 0's, and rights as 1's. the path 101 is really 10100000, which is not the path you intended. 02:04:36 A bit, but not enough. It will warm up again. Damn. 02:04:59 -!- wob_jonas has quit (Quit: http://www.kiwiirc.com/ - A hand crafted IRC client). 02:05:43 hmm, it seemed like there was an arbitrage opportunity for a bit 02:05:56 Do you like the two new loader programs for MIX that I have designed? (Both need only one card, and actually the last five character positions are unused. One is for loading programs with a specific byte size, while the other one is independent of byte size) 02:06:51 " N O6 A O4 H N ENX E K BU I OA H A. PA N D LB E AEU ABG G 9 " 02:07:20 Jafet: here's the solution to that. pad the path with however many unused bits there are - 1, then pad it with a 0. so the path 101 becomes 11110101. you march forward through the bit vector and stop after the first 0. 02:07:56 the downside is that now your paths must _always_ start with a 0. you could fenangle it to work out an extra root node from a path, but uh.. yeah. 02:10:02 @wn fenangle 02:10:02 No match for "fenangle". 02:10:13 @wn finagle 02:10:14 *** "finagle" wn "WordNet (r) 3.0 (2006)" 02:10:14 finagle 02:10:14 v 1: achieve something by means of trickery or devious methods 02:10:14 [syn: {wangle}, {finagle}, {manage}] 02:10:22 huh, til. 02:10:33 never even knew it was.. really a word. 02:11:28 it doesn't seem tricky or devious if you just number all the nodes in level order starting from 00000001 02:12:11 right. so, with that numbering, give me the path to that node. 02:12:36 then 101$ is 00001101 02:13:39 because the real idea here is storing sparse trees, where you give me a node and I assume that every node along the path is a valid one. 02:14:34 so when I say "well does node X exist?", all I have to do is run over all the stored paths and check whether a partial match exists. 02:17:17 well, storing paths in trees is a generally poor way to store trees 02:17:51 what alternative would you give me? I just need to store the structure of the tree and query whether a given node exists. 02:19:44 I might offer a parenthetical (even a balanced one) 02:20:00 mm. sure. that's a good way to store static trees. 02:20:12 hell, I have an encoding that saves a bit. 02:20:26 but dynamic trees. 02:22:46 most trees look static to me; they sway a bit sometimes 02:22:52 lmao. 02:23:29 -!- btiffin has joined. 02:23:39 are you one of those people who graft branches, or turn them sideways? 02:24:30 I would really like to not rewrite a given bit string representing a tree every time I need to insert a node. 02:24:34 actually, I'm not sure I've seen a paper that implements tree rotations 02:24:53 they only tend to cover indels, and maybe split/merge 02:24:58 yeah. 02:25:09 I guess rotations reduce to split/merge 02:25:21 pretty much any operations imply rewriting the whole bit string. 02:25:54 I think navarro had a paper that demonstrated logarithmic indels, splits and merges 02:26:04 -!- augur has quit (Remote host closed the connection). 02:26:23 I'd rather take my chances with early matches and additive updates. the benefit to my method is that no matter how the paths arrive, the tree is final. 02:26:44 meaning I could send over the paths 000, 010, 110, 101 in any order and the tree would still be the same. 02:28:30 so I guess... I'm willing to pay the extra storage. 02:28:47 -!- contrapumpkin has quit (Quit: My MacBook Pro has gone to sleep. ZZZzzz…). 02:29:41 well, “demonstrates” might have been the wrong word, as this data structure has probably never been actually implemented 02:29:47 https://arxiv.org/abs/0905.0768 02:30:07 oh yeah, I saw this. 02:35:23 -!- augur has joined. 02:36:00 I don't think any of these bit strings are meant to be stored as bit strings 02:36:27 how so? 02:37:12 they are stored as trees, with nodes near the edge compressed into short strings to reduce size 02:37:38 mm. I'd store them as bit strings. efficient traversal, but inefficient updates. :P 02:38:06 hell, efficient storage too. 02:38:23 as long as you compress groups of about (log n)^k nodes at a time, the remaining n/(log n)^k pointers for the tree no longer prevent you from having the word “succinct“ in your paper title 02:39:22 so it's asymptotically worthwhile to interpret trees as bitstrings then store them in trees of bitstrings 02:39:59 perhaps xzibit would have been a good string algorithms researcher 02:40:44 is there a word for the relationship expressed by that meme that's more precise than just "recursion"? 02:41:13 (for reference, the "reference implementation" of that meme is "I put a car in your car so you can drive while you drive") 02:42:19 I'm not sure, but such a word could also describe the work that someone once did benchmarking nested self-interpreters 02:43:04 oh, the eigenratio website still exists 02:45:30 I've been thinking about nested self-interpreters quite a bit recently 02:45:50 trying to work out what sort of language would naturally have an eigenratio of 1 for most obvious ways of writing a self-interpreter 02:46:05 also continuations 02:52:21 if you take a recursive unit cell grid in conway's life and run it with hashlife you should technically get an eigenratio of 1 02:53:26 I'd test this, but nesting a unit cell sounds like something I'd need to generate with a script and I don't care enough 02:55:27 -!- augur has quit (Remote host closed the connection). 03:00:43 Why would you need to nest it with a script? 03:01:28 If you have some way to describe macrocells, you should just be able to do a simple substitution or something for the next level. 03:02:05 well, I would do such a substitution with a script 03:02:19 gn 03:02:21 Well, OK. 03:02:21 I'm not sure if macrocell identifiers are required to be increasing 03:02:24 -!- ATMunn has quit (Remote host closed the connection). 03:02:28 that would make it more annoying 03:02:42 Jafet: storing trees, even partial trees, via pointers is not succint, afaict. 03:02:45 Required by what? 03:03:50 -!- augur has joined. 03:04:39 apparently the nodes are numbered implicitly, so I'd have to change all the numbers when combining macrocell files 03:05:09 Is there a standard format for describing hashlife states? 03:05:40 yes, I think that format is called macrocell 03:06:03 well, not if you also want the cached results 03:08:58 Jafet: ah right, hashlife is a good example here 03:09:15 it seems that nobody wants the cached results, though, not even golly, which clears the cache every GC cycle (even for results that didn't get GC'd!) 03:11:00 ais523: now if you had a simple functional language that, unlike a really overrated CA from 1970, could express the notion of a memoizing implementation of itself 03:11:29 it's pretty easy if you're OK with programs like if (false) while (true); not terminating 03:11:36 but that's a pretty big restriction 03:15:15 so they found the unit cell and hashlife but failed to see that the resulting eigenratio is 1 03:15:49 But the main point as far as this blog goes is that "Life" has a self-interpreter, and it's eigenratio is exactly 5760! — http://eigenratios.blogspot.de/2007/09/self-interpreter-for-conways-game-of.html 03:17:49 a self-interpreter that works from finitely many starting cells would be rather more impressive :-) 03:18:04 also should be possible, and might even be possible with the same ratio 03:19:24 well, you only need to invent a fast enough breeder that lays more unit cells 03:19:39 it would probably have a larger period that 5760 though 03:22:18 if it fits within 11520 it would be fine 03:22:47 the speed of light might be the absolute speed limit in Life, but if starting from a finitely large pattern, things can't escape the pattern boundary faster than c/2 in the long term 03:26:15 Can you have a non-empty background for a finite pattern? 03:26:40 Some sort of infinite pattern that lets you communicate information more quickly. 03:27:01 I guess you would want all your patterns to preserve it. 03:30:29 well, a breeder for unit cells would likely have a six-digit period 03:32:23 (or more than six, but the unit cell seems to be made of standard parts so a fast glider synthesis shouldn't be too hard) 03:33:43 imode: a succinct data structure is just one that has less than O(n) overhead 03:34:40 not O(n), o(n). 03:35:24 this generously includes trees with O(n/(log n)^(1+ε)) pointers of O(log n) bits each 03:35:33 again, that is not the lower bound. 03:35:54 ꙮ(n) 03:36:42 shachaf: in general, yes, but I'm thinking about the specific case of an only-dead-cells background 03:37:56 golly supports a toroidal grid, which could be expanded to support a periodic background 03:39:08 Presumably a periodic background is reasonably easy to implement in hashlife -- you just need to change the way you grow the grid. 03:39:40 yes, though having to pad it to powers of 2 would be annoying 03:47:53 ꙮ̃(n)? 03:58:44 -!- PattuX has quit (Quit: Connection closed for inactivity). 04:01:36 I don't think multiocular O is a common piece of computational order notation 04:04:38 creationists use it to denote information lower bounds — the eyes signify irreducible complexity 04:05:04 Nor is it a common character in Cyrillic manuscripts. 04:05:27 Creationists? Is that people who use ꙮ_CREAT? 04:07:10 ꙮ̃ is used when a log gets in the eye, or perhaps a 2-by-4 05:00:26 -!- btiffin has quit (Remote host closed the connection). 05:13:57 -!- olsner_ has changed nick to olsner. 05:15:03 Apparently some Java-based HTTP client interpreted "gopher://zzo38computer.org" as a relative URI, even though clearly by its syntax it isn't. 05:15:07 golly supports one perodic background, but that's only for b0s8 rules 05:15:33 What's b0s8? 05:15:38 and where the background switches from on to off every generation 05:15:44 the parity hack doesn't really count 05:16:05 yeah, that's just an edge case 05:16:09 http://golly.sourceforge.net/Help/Algorithms/QuickLife.html 05:16:22 I think that explains it better than I could here 05:26:44 -!- xkapastel has joined. 05:31:45 What does "eigenratio" mean here? 05:33:01 Oh, b,s means born,survive 05:34:36 oh, :/ thought that page said that 05:40:37 It does. 05:43:28 zzo38: "zzo38computer.org" is technically a relative domain name; the absolute version is "zzo38computer.org." 05:43:38 however, for some reason it became standard to write URLs without the trailing dot 05:44:35 ais523: OK, but is still not a relative URI 05:44:44 Do you mean it interpreted it as ./gopher:/zzo38computer.org? 05:45:34 Yes, that is what it did, it look like 05:48:45 -!- augur has quit (Remote host closed the connection). 05:50:54 huh, so it did 05:53:44 If I get a vanity TLD, can I put an MX record on it? 05:54:55 there's no technical restriction against that 05:55:12 there might or might not be a political one (e.g. ICANN only agreeing to sell you the TLD if you don't host anything on the TLD directly) 05:55:32 or, well, it's a known fact as to whether or not there's a political restriction, but not known by me 05:57:18 There was a URL shortener on a two-letter country TLD once. 05:57:21 But they took it down. 05:57:53 I bet lots of bad email regexps would reject a email address like that. 06:03:21 hmm https://serverfault.com/questions/154991/why-do-some-tld-have-an-mx-record-on-the-zone-root-e-g-ai 06:07:22 Aha, Jafet++ 06:10:09 I wonder if /bin/hostname should ship with a copy of this table 06:10:43 I guess that would only solve half the problem 06:12:39 Which table? 06:28:01 shachaf: a table of TLDs with strange DNS records 06:29:00 that would be hard to update 06:30:35 seems that ai. no longer has an MX record, though it still has A, NS, and a conspicious lack of SOA 06:30:39 -!- erkin has joined. 06:44:08 -!- erkin has quit (Quit: Ouch! Got SIGABRT, dying...). 06:45:08 -!- newsham has quit (Ping timeout: 260 seconds). 06:49:58 Jafet: It looks like it has an MX record to me? 06:51:26 -!- FreeFull has quit. 06:51:47 Is .home a generic TLD? It would make a good email address for inquiries regarding distributed computing projects. 07:00:18 -!- erkin has joined. 07:03:49 -!- hakatashi has joined. 07:14:33 -!- newsham has joined. 07:17:27 -!- ais523 has quit (Ping timeout: 260 seconds). 07:34:53 -!- doesthiswork has quit (Quit: Leaving.). 07:49:19 -!- oerjan has joined. 07:59:10 -!- ybden has quit (Ping timeout: 240 seconds). 08:01:45 -!- ybden has joined. 08:12:57 -!- erkin has quit (Read error: Connection reset by peer). 08:13:29 -!- erkin has joined. 08:21:33 no (but homes and house are) 08:21:43 Wikipedia says "BT hubs use the top-level pseudo-domain home for local DNS resolution of routers, modems and gateways." 08:22:48 https://en.wikipedia.org/wiki/List_of_Internet_top-level_domains 08:26:08 -!- hppavilion[1] has quit (Ping timeout: 240 seconds). 08:41:56 -!- tuu has joined. 08:59:41 -!- sebbu has joined. 09:44:58 -!- imode has quit (Ping timeout: 276 seconds). 10:04:56 -!- oerjan has quit (Quit: Later). 10:05:14 <\oren\> look at this shit http://imgur.com/k86avnF 10:05:25 <\oren\> How is this allowed? 10:07:58 <\oren\> I think an instersection between 6 or more streets should be required to be a roundabout 10:25:07 -!- mroman has joined. 10:25:10 rello. 10:25:22 esolangs.orgc is down. 10:26:21 -!- xkapastel has quit (Quit: Connection closed for inactivity). 11:25:59 I can't count the number of times that has been said already. 11:26:09 I do have alerting on it as well. 11:27:12 Anyway, will set up the backup thing properly once I get home from the airport and unpack a little. 11:34:01 -!- boily has joined. 11:35:41 -!- PattuX has joined. 11:48:16 :D 11:48:24 well.. I'm not pressuring you. 11:48:26 just informing you 11:48:42 it's really the least important site in my life. 11:52:08 the most important is int-e's cheap server :D 11:52:13 because it hosts the online shell. 12:03:27 -!- zseri has joined. 12:11:17 -!- jaboja has joined. 12:12:35 fungot: can you be HackEgo? 12:12:35 boily: you you can start ' em in the paper 12:12:51 * boily starts HackEgo in the paper 12:27:55 -!- boily has quit (Quit: DECLARED CHICKEN). 12:49:44 -!- zseri has quit (Ping timeout: 260 seconds). 12:54:47 -!- zseri has joined. 13:02:25 -!- heroux has quit (Ping timeout: 246 seconds). 13:02:35 -!- heroux has joined. 13:10:13 - + + + ] + > [ [ + > < > ] - > [ - ] ] [ - < - + + ] - < < - > > + < - > [ < ] + > - + ] < ] < + - < - - [ < ] > 13:27:44 stupid evolver produces stupid programs 13:27:59 hm. 13:28:13 has anybody ever done evolving html/css 13:28:16 to fit a specific design 13:38:02 -!- Labeo has joined. 13:42:20 -!- Labeo has quit (Quit: Mutter: www.mutterirc.com). 13:44:31 -!- Labeo has joined. 13:47:41 -!- LKoen has joined. 13:48:31 -!- Labeo has quit (Client Quit). 14:00:30 -!- doesthiswork has joined. 14:01:38 -!- Labeo has joined. 14:03:14 -!- mroman has quit (Ping timeout: 260 seconds). 14:06:55 -!- ais523 has joined. 14:13:54 -!- Labeo has quit (Quit: Mutter: www.mutterirc.com). 14:16:11 -!- erkin has quit (Ping timeout: 255 seconds). 14:22:54 -!- atslash has joined. 14:27:12 -!- erkin has joined. 14:27:57 -!- jaboja has quit (Ping timeout: 260 seconds). 14:32:07 -!- Mayoi has joined. 14:32:14 -!- erkin has quit (Disconnected by services). 14:37:42 -!- zseri has quit (Quit: Page closed). 14:39:40 -!- ais523 has quit (Remote host closed the connection). 14:40:50 -!- ais523 has joined. 14:42:09 -!- `^_^v has joined. 14:48:27 -!- LKoen has quit (Remote host closed the connection). 14:52:19 -!- tuu has quit (Remote host closed the connection). 14:59:41 -!- jaboja has joined. 15:03:26 -!- doesthiswork has quit (Quit: Leaving.). 15:05:25 -!- __kerbal__ has joined. 15:05:45 <__kerbal__> Hi 15:06:34 <__kerbal__> Does anyone know exactly what is wrong with the wiki? 15:07:25 no, we only heard that question like a dozen times the last hours 15:11:40 <__kerbal__> Probably CaC's fault again 15:16:22 -!- ATMunn has joined. 15:16:22 -!- ATMunn has quit (Changing host). 15:16:22 -!- ATMunn has joined. 15:18:10 -!- jaboja has quit (Ping timeout: 240 seconds). 15:21:11 <__kerbal__> https://www.youtube.com/watch?v=HuCJ8s_xMnI 15:21:20 <__kerbal__> One of the weirdest videos I've seen in a while 15:29:43 -!- Mayoi has quit (Quit: Ouch! Got SIGABRT, dying...). 15:42:12 -!- Bowserinator has quit (Excess Flood). 15:42:22 -!- Bowserinator has joined. 15:42:45 -!- Bowserinator has changed nick to Guest82305. 15:43:42 -!- augur has joined. 15:43:57 -!- __kerbal__ has quit (Quit: Page closed). 15:47:59 -!- augur has quit (Ping timeout: 255 seconds). 15:48:05 Heh, division is weird. You could consider multiplication its "opposite", but considering modulo its opposite also makes sense. :P 15:50:47 -!- contrapumpkin has joined. 15:57:56 -!- Guest82305 has changed nick to Bowserinator. 15:57:57 -!- Bowserinator has quit (Changing host). 15:57:57 -!- Bowserinator has joined. 15:58:45 so uh, can someone exlpain funge-98's stack stack to me? im having trouble understanding the commands it uses 16:01:34 -!- ais523 has quit (Remote host closed the connection). 16:02:44 -!- ais523 has joined. 16:23:18 -!- LKoen has joined. 16:46:20 -!- Lord_of_Life has quit (Remote host closed the connection). 16:59:35 -!- LKoen has quit (Remote host closed the connection). 17:15:05 Concept: like the "break n;" idea, but with returning values. "return<2> x;", for example, would return x and force the function that called it to immediately return x too. 17:17:07 that would break encapsulation a lot 17:17:24 -!- Lord_of_Life has joined. 17:17:31 exactly. 17:17:57 -!- LKoen has joined. 17:22:04 -!- AnotherTest has joined. 17:29:43 -!- LKoen has quit (Remote host closed the connection). 17:38:00 -!- FreeFull has joined. 17:38:12 -!- LKoen has joined. 17:39:31 -!- erkin has joined. 17:41:32 -!- AnotherTest has quit (Read error: Connection reset by peer). 17:41:51 -!- AnotherTest has joined. 17:44:27 -!- augur has joined. 17:45:55 -!- augur has quit (Remote host closed the connection). 17:47:13 -!- augur has joined. 17:58:44 -!- zseri has joined. 18:02:13 -!- AnotherTest has quit (Ping timeout: 276 seconds). 18:20:31 -!- AnotherTest has joined. 18:25:28 -!- LKoen has quit (Remote host closed the connection). 18:38:39 -!- AnotherTest has quit (Ping timeout: 255 seconds). 18:45:53 -!- imode has joined. 18:48:21 -!- AnotherTest has joined. 19:03:13 rdococ: that operation exists in INTERCAL 19:03:22 in fact, it's the only way to do flow control in INTERCAL-72 19:11:34 -!- erkin has quit (Quit: Ouch! Got SIGABRT, dying...). 19:13:38 -!- ais523 has quit (Ping timeout: 240 seconds). 19:35:08 -!- AnotherTest has quit (Ping timeout: 240 seconds). 19:40:42 -!- AnotherTest has joined. 19:48:41 -!- LKoen has joined. 20:01:09 -!- LKoen has quit (Remote host closed the connection). 20:01:29 -!- wob_jonas has joined. 20:02:04 ais523: I don't think that's the same. Intercal has multi-level return, that is, it can pop multiple entries from the return stack and return to the last one popped. 20:02:45 how is this different? 20:02:47 You could actually emulate that in GW-BASIC, which has a form of the RETURN statement that pops the return stack but jumps to a constant line in the statement. 20:03:04 myname: I think the original question was a multi-level break. As in, from while or for or do-while loops 20:03:35 it was a multi-level return like the existing multi-level break 20:03:54 oh, that was the question? 20:03:59 sorry then 20:04:02 I didn't follow 20:07:45 -!- AnotherTest has quit (Ping timeout: 248 seconds). 20:08:30 -!- AnotherTest has joined. 20:09:55 -!- oerjan has joined. 20:14:35 Do you know when to expect fixing esolang wiki? 20:15:37 wob_jonas: Yes, I have used that before, using RETURN to jump to a different line number (and have used it once to RETURN to the next line which is a RETURN to a constant line number, even) 20:17:32 -!- AnotherTest has quit (Ping timeout: 255 seconds). 20:19:35 -!- AnotherTest has joined. 20:19:40 PHP has multi-level break by number, while JavaScript has multi-level break by name. (Although I happen to think goto would be a better way of doing this anyways; you don't need much more than the single-level break/continue, as well as goto) 20:21:00 zzo38: Just throw in callCC and call it a day 20:21:40 callIAD 20:22:34 :( why are there no good befunge-98 interpreters for windows 20:22:57 because developers don't use windows? 20:23:41 yeah i guess 20:23:51 there's not even any good online ones :( 20:24:04 there are 20:24:21 at least, i havent found any 20:24:31 i don't know which one anymore, though 20:24:38 i used to have one modified 20:25:10 actually there are way more developers who use windows than developers who use befunge 20:28:14 One of the features of NNIX is that the file number has to be a constant and it does not support variable file numbers. Do you know why? 20:29:18 zzo38: because it's just a toy OS interface that's enough for the examples in the book, not a real complete operating system? 20:29:37 I think it should be fixed 20:30:13 zzo38: it also doesn't support modifying an already written file without erasing its data first, that's much more annying IMO 20:30:45 (and that's despite that the book claims it supports everything the file interface of C89 can do except remove files) 20:31:25 but in any case, the OS interface is extensible, an OS could add new system calls, it doesn't intend to be complete and closed like the CPU architecture itself 20:32:29 Yes, that is another think to fix. There are a few other things too, such as adding file control interface, and perhaps a convenience function for reading/writing one value to/from $255. 20:32:42 myname: also, at some point ill get linux, but for now im stuck on windows so i have no choice but to use a windows or browser based one :/ 20:32:48 what do you mean "file control interface"? 20:33:02 Similar to fcntl() 20:33:26 (Although you don't need all of the functions of fcntl) 20:34:38 Also similar to ioctl() for some devices 20:35:57 again, he only needs a little of OS interface for his examples. he did say he doesn't intend to create a full operating system. 20:36:01 wob_jonas: hah, I actually kind of like that thing about not allowing modification of files after the fact. 20:36:11 if you want a full OS, just imagine a unix-like running on MMIX 20:36:37 Cale: you can modify files, it's just you can only do so if you do the equivalent of O_TRUNC 20:36:45 aw 20:36:49 Actually fcntl() probably isn't needed, but a few of the controls of ioctl() may be, mainly the terminal controls. 20:39:48 One possible way that could be done is to add additional command-line arguments to the simulator to load .so files assigned to different X values in the TRAP instructions, where 0 means to use the built-in stuff. 20:40:16 That way you could add one extension for connecting to the X server, one extension for music, and so on 20:49:26 I'm trying to rig up some method to photograph a book, for which I need to hold both the book and the camera in place. But I am failing miserably, because I'm really bad at hardware stuff, and don't have many things to use at home. 20:51:05 (and it shouldn't obstruct lighting, which is basically impossible since I want to get the camera close to the book) 20:51:27 -!- AnotherTest has quit (Ping timeout: 240 seconds). 20:52:12 -!- AnotherTest has joined. 21:05:48 -!- AnotherTest has quit (Ping timeout: 240 seconds). 21:06:48 -!- AnotherTest has joined. 21:18:40 wob_jonas: There are scanners which can feed a stack of pages through, if you don't mind destroying the book 21:20:33 There was one point when I was in highschool where I helped a friend of mine make a digital version of his mother's cookbook, and we cut the ring binding off a copy and fed it through a scanner, and then OCR'ed it... and OCR was terrible back then, so I had a lot of hand-editing to do. :P 21:21:55 Still probably amounted to less work than typing out the whole book though 21:24:31 Cale: I don't want to destroy the book. A flatbed scanner is a good idea in general, and I did think of it, 21:24:39 and I could flip pages manually 21:25:37 but the problem is that the scanner I have access to has a maximum scan area of only slightly bigger than A4, and this book is bigger than that. The page content might just barely fit in that area, but I couldn't position it right. 21:25:41 I'd need a larger scanner. 21:26:28 Although destroying a book isn't such a bad idea actually. I didn't think of that. I can't destroy this library copy, but I might be able to locate a new or used copy of this that I can destroy. 21:26:52 That would make this somewhat easier, because then I only have to position the individual pages, but it's still not easy 21:27:01 Let me check online for the price 21:28:06 -!- xkapastel has joined. 21:28:35 the easiest way to mount a normal digital camera is by the mount on the bottom, usually 21:29:01 I think it's a 1/4-20 thread, you could bolt it to something solid above the book 21:30:17 Hmm, it's not expensive. I could buy and destroy a copy. 21:30:26 I'd still have to figure out how exactly to photograph or scan it though. 21:35:34 Is there somewhere I can just borrow a flatbed scanner larger than A4? 21:40:32 what if you scanned the pages in two parts sideways and stitched them back together 21:40:44 print shops would probably have a big scanner 21:40:49 not sure what else would 21:40:53 Hoolootwo: would be hard to stitch them accurately 21:41:01 and to position the pages accurately that way 21:41:04 is there not software for that? :/ 21:41:15 Yeah, but still 21:41:16 I guess automatedly doing it is probably hard 21:41:29 It would be much better if scanned together 21:41:38 yeah, definitely 21:42:01 The image quality matters here. If it didn't, I'd just shoot the pictures with the camera handheld and be done with it. 21:42:37 with scanning, I think you have plenty of resolution 21:42:57 Exactly, that's why a scanner would be better 21:45:26 Apparently this print shop has A3 sized scanners I can use (for a fee obviously) 21:45:31 in 600 DPI 21:45:33 that could work 21:46:01 It's not even expensive. 21:49:12 -!- sleffy has joined. 21:49:26 Now I made up a way to make operating system interface extensions into the MMIX simulation. It is: http://sprunge.us/PAdY 21:53:09 Do you like this? 21:53:15 I think I'll order a copy of this book. 21:56:34 Ordered. 21:57:12 I'll be able to get it in a few days. Then I can decide whether I want to scan it whole or cut up. 21:57:21 Cut up would probably be more precise. 22:01:46 Cale: thanks for the cut up idea 22:02:34 -!- wob_jonas has quit (Quit: http://www.kiwiirc.com/ - A hand crafted IRC client). 22:07:38 -!- AnotherTest has quit (Ping timeout: 240 seconds). 22:08:09 -!- AnotherTest has joined. 22:11:22 -!- LKoen has joined. 22:12:42 -!- hppavilion[1] has joined. 22:17:23 -!- `^_^v has quit (Quit: Leaving). 22:17:42 -!- `^_^v has joined. 22:20:50 -!- paul2520 has joined. 22:20:50 -!- paul2520 has quit (Changing host). 22:20:50 -!- paul2520 has joined. 22:21:43 -!- AnotherTest has quit (Ping timeout: 258 seconds). 22:22:52 -!- AnotherTest has joined. 22:27:08 -!- AnotherTest has quit (Ping timeout: 240 seconds). 22:40:16 -!- btiffin has joined. 22:42:23 -!- `^_^v has quit (Quit: This computer has gone to sleep). 22:43:57 -!- oerjan has quit (Quit: Nite). 22:51:07 -!- zseri has quit (Quit: Page closed). 22:56:44 -!- ais523 has joined. 22:59:20 -!- boily has joined. 23:14:35 `w -- Will HackEgo ever be again \\ S'enfargea-t-il dans un tranche de pain \\ I need my random wisdom \\ Peut-être est-il tombé dans les pommes? 23:14:55 https://github.com/aaronduino/asciidots/ 23:21:54 helloily 23:23:21 boily bluepommel 23:24:23 -!- LKoen has quit (Quit: “It’s only logical. First you learn to talk, then you learn to think. Too bad it’s not the other way round.”). 23:24:55 fizzie: less fizzie, more fixxie twh 23:34:53 QUINTHELLOPIA! 23:34:56 helloochaf! 23:35:16 bluepommel? 23:35:50 -!- imode has quit (Ping timeout: 240 seconds). 23:37:02 oui 23:59:27 -!- augur has quit (Ping timeout: 240 seconds). 2017-08-08: 00:04:27 French lesson of the day: Est-ce que les cabots peuvent manger de la poutine? Non, les cabots ne peuvent pas manger de la poutine. 00:04:47 -!- boily has quit (Quit: PERSPIRATING CHICKEN). 00:06:30 -!- wob_jonas has joined. 00:11:36 -!- btiffin has quit (Remote host closed the connection). 00:19:56 `olist 1089 00:20:17 ooh! 00:20:34 olist 1089: shachaf oerjan Sgeo FireFly boily nortti b_jonas 00:20:54 ah yeah, since HackEgo isn't here, you have to do it manually 00:22:12 lol 00:23:36 asciidots looks interesting 00:25:42 Mark Rosewater in http://magic.wizards.com/en/articles/archive/making-magic/cats-2017-08-07 writes "While [sabertooth is] not the only word spelled differently on different cards (I'm looking at you "sylex"), such occurrences are infrequent." 00:26:58 wob_jonas: I think I must be missing something about this comic. 00:27:04 The word sylex is in the name of "Golgothian Sylex", but what other cards does it appear on, what is the alternate spelling, what the heck is a sylex, and why did it choose to collapse on Betelguse Seven in particular? 00:27:28 Do you know any GURPS game? 00:28:14 there is a pratchett themed 00:28:26 Do you like the two loader programs I wrote for use with MIX? (One for programs that are only for specific byte sizes of MIX, and one for programs that are independent of byte sizes of MIX.) 00:29:28 (Both of these programs each fit on only one card; you don't need two cards.) 00:34:07 However, I used a different format for the program cards, which are the format which can be loaded more efficiently. The one for specific byte sizes, has seven words per card like the one described in the book, although their format is different, and it skips by 2 instead of by 1 (so if a card specifies an address of 300, then it loads at 300, 302, 304, 306, 308, 310, and 312, instead of 300, 301, 302, 303, 304, 305, 306). 00:35:12 The final card (the "transfer card") will modify the loading routine; there is no special logic for this in the loader program. 00:35:41 the fuck is MIX? 00:35:55 dunno, look on the wiki... oh wait 00:36:12 It is a kind of hypothetical computer invented by Knuth. There is a description in esolang wiki, but esolang wiki does not currently work now. 00:40:45 http://zzo38computer.org/textfile/miscellaneous/mix_stuff 00:45:45 -!- Lord_of_Life has quit (Quit: EliteBNC free bnc service - http://elitebnc.org - be a part of the Elite!). 00:49:16 wob_jonas: I did some Gathering and Googlering, and it looks like "sylex" is a misspelling of "cylix". 00:49:55 tswe_tt: ah thanks 00:51:26 in that case the second half of the question stands. what's a cylix? it's not in my dictionary. 00:51:59 I also don't know what is meaning 00:52:11 "Noun. 1. cylix - a shallow drinking cup with two handles; used in ancient Greece. kylix." 00:52:47 thanks 00:53:58 That would be like what the picture shows, I guess 00:54:52 yeah, all four cylix cards show a chalice (flat cup) 00:57:04 of course, M:tG has chalices and goblets too 01:07:16 -!- sleffy has quit (Ping timeout: 246 seconds). 01:10:43 -!- ais523 has quit (Remote host closed the connection). 01:11:54 -!- ais523 has joined. 01:21:20 -!- doesthiswork has joined. 01:37:44 -!- GeekDude has quit (Quit: WeeChat 1.8). 01:45:18 -!- Lord_of_Life has joined. 01:45:18 I made the layered unit net generate some exchanges with lambdabot. My favorite one so far... 01:45:34 > z (f xarg $mob n)) tswett [x] 01:45:34 12:59:29 L2DIMAIT #=. (bad exoteric program status reverse copy") 01:46:35 lol 01:47:26 -!- GeekDude has joined. 01:50:30 -!- Lord_of_Life has quit (Ping timeout: 240 seconds). 01:52:52 Concept: esoteric, stack-based programming language where the program must pop their clogs before it can halt 01:55:01 -!- augur has joined. 01:57:39 pop their what? 01:57:50 oh 01:57:57 do you mean cogs? 01:58:06 Can we make a hydraulic esoteric language? 02:00:02 Ooh, more fake METAR. 02:00:03 LASK 041356Z 23013KT 200 9999 SCT011 BKN007 02/05 A2979 RMK AO2 THITK AO2 SLP123 T01860004 02:03:21 -!- Lord_of_Life has joined. 02:03:54 fizzie: I didn't actually mean "less fizzie". Your presence here is valued and appreciated. 02:04:04 It was just a pun. 02:10:14 Sin gas 02:15:31 -!- PattuX has quit (Quit: Connection closed for inactivity). 02:24:23 I trained a net on timestamps only. Some of the output is pretty funny. 02:24:58 The output mostly makes sense. 13:59:26 is followed by 14:02:20, which is followed by 14:25:52. 02:25:15 tswe_tt: did it produce invalid dates like 2017-02-29? 02:25:46 Just the time component. 02:26:06 Here it went from 15:59:45 to 15:00:03. 02:26:29 So it thought it was reasonable for 15:59:45 to be followed by another timestamp in hour 15, but then decided to reset the minutes and seconds anyway. 02:26:42 you could add some domain-specific knowledge to timestamp generation though 02:27:45 Shouldn't be necessary. After just a little more training, it should generate timestamps pretty flawlessly. 02:28:18 It occasionally goes backwards a little bit, like from 18:11:03 to 18:10:23. 02:29:14 Here it generated 23:03:31 followed by 22:03:30... 02:29:20 tswe_tt: clock skew or timezone offset change 02:29:28 or even most of a day skipped 02:29:43 I think the timestamp 00:00:00 always appears every day, in the training data. 02:29:54 Here's a mutant time, 221:29:08. 02:30:31 02:04:17 to 20:04:30. I wonder if it forgot which digit was which in the hour component? 02:31:28 Then here it goes from 23:59:08 to 24:00:02 and stays in hour 24 for a while before going back to 23. 02:31:58 After a while, it generates the timestamp 00:00:00:00. 02:35:54 I want to train a network on this for a while and then do one of those visualization things to see what units are doing what. 02:37:48 -!- imode has joined. 02:46:27 -!- augur has quit (Remote host closed the connection). 02:47:10 -!- augur has joined. 02:51:35 -!- augur has quit (Ping timeout: 240 seconds). 02:59:04 -!- augur has joined. 03:00:46 -!- ATMunn has quit (Quit: ~~~~goodnight~~~~). 03:11:13 -!- erkin has joined. 03:12:54 -!- wob_jonas has quit (Quit: http://www.kiwiirc.com/ - A hand crafted IRC client). 03:18:50 -!- jjthrash has quit (Ping timeout: 255 seconds). 03:25:45 -!- jjthrash has joined. 03:31:49 -!- Lord_of_Life has quit (Ping timeout: 246 seconds). 03:33:38 -!- sleffy has joined. 03:45:51 -!- sleffy has quit (Ping timeout: 255 seconds). 03:56:29 Concept: Esolang where tables can access theirselves, and their parent. e.g. {a = "foo", b = "bar", c = {c = self, d = parent}}. 03:57:04 So that table (let's call it t) would be recursive, and things like t.c.c.c.c.c.c.c.c.c.c.d.c.c.c.c.c.d.a would be valid. 04:05:41 -!- Lord_of_Life has joined. 04:15:47 -!- contrapumpkin has quit (Quit: My MacBook Pro has gone to sleep. ZZZzzz…). 04:32:26 -!- erkin has quit (Quit: Ouch! Got SIGABRT, dying...). 05:10:00 -!- doesthiswork has quit (Quit: Leaving.). 05:10:33 -!- doesthiswork has joined. 05:12:54 Heirloom-Mailx allows to write downloaded attachments to pipes. Why doesn't a web browser do this? 05:24:21 nothing stops you from using curl. :P 05:25:33 Yes, although I think it can be useful at the download prompt. The same is true with upload forms; you should be allowed to enter the local filename (or program to execute) and the remote filename separately. 05:25:59 And I don't like the file dialog boxes either; a simple prompt where you can type in the full path (with tab completion) is best. 05:26:13 I do have curl and yes it is very useful though. 05:41:29 Another possible thing to be useful is an extension to make a shell script equivalent of a HTML form. 05:54:52 Any image I had of low-level programming being saner than web dev was just shattered 05:54:53 http://wiki.osdev.org/A20_Line 05:55:45 Are there esolangs with support for anonymous, first-class functions, but not closures? 05:55:46 userspace in amd64 is fairly sane 05:59:14 Sgeo_: legacy x86 is often crufty. 05:59:49 usually you can choose not to use the insane bits, though there is the legacy cruft where ymm registers have split lanes 06:03:31 Maybe I should read about MINIX? 06:04:23 I think the original design of IBM PC was reasonable (although there are a few things I would have done differently), although now it is a mess. 06:04:36 ...the book recommended is a bit more than I want to pay right now 06:05:08 zzo38: I concur. 06:05:30 The original IBM PC was, in most respects, a very normal computer of its time. 06:05:54 Just made a bunch of natural decisions on how you'd go about designing a computer around the 8080 and off-the-shelf components. 06:06:25 Yes, although there are a few things I would have done differently; such as, altering a few gates of CGA would make CGA much more flexible than it is. 06:07:03 Yeah, that's probably the best example of a case where they could've *easily* done better. 06:07:44 But goodness a lot of cruft got built up. 06:07:48 -!- hppavilion[1] has quit (Quit: HRII'FHALMA MNAHN'K'YARNAK NGAH NILGH'RI'BTHNKNYTH). 06:08:06 (I have the schematics, so I can see which gates to change.) 06:08:54 Sgeo_: For extra fun, the only thing we know of that used the A20 wraparound is *itself* a legacy compat feature. 06:08:56 I think the original "Model F" keyboard design was good too actually. 06:09:11 It was used by DOS's implementation of the CP/M API. 06:09:22 well, that was... odd. didn't expect the wikipedia article on callbacks to mention Roblox of all things. 06:09:59 -!- sleffy has joined. 06:10:02 You see, one of the selling points of the 8086 was that it was a purely mechanical process to convert 8080 asm to it... 06:10:30 So, *if* your 8086 OS implemented the CP/M system call API, then it was trivial to port CP/M software to it. 06:10:34 And DOS did exactly that. 06:10:48 But it had to use the A20 wraparound to do it. 06:11:14 If not for that, the A20 line mess probably wouldn't have happened. 06:11:35 o.O 06:12:12 Also, this was actually a damned important feature; most of the early DOS software was actually CP/M ports. 06:13:41 Nobody would've bought an IBM PC if it didn't run WordStar, dBASE, or AutoCAD. 06:13:52 I wonder how many CP/M programs actually needed the wraparound 06:14:12 Jafet: All of them. For technical reasons, the *API* relied on it. 06:14:33 I suspect few of them needed it outside of that, however. 06:14:35 that would do it, then 06:15:13 The API was a call to a weird address, which on an 8080 was just a normal address, but with segmenting involved pretty much had to wrap around. 06:26:16 whoa whoa whoa, "Intel no longer supports the A20 gate, starting with Haswell." 06:28:07 bold move, I wonder how many programs that will break. 06:28:38 Wanna bet it's still togglable from the keyboard controller? 06:29:34 well, define "keyboard controller"... AFAIK that stuff tends to be emulated by SMM code these days. 06:30:03 The 8042 chip is only so emulatable considering many systems still *ship* with a PS2 port. 06:30:13 i.e. the thing that it actually interfaces with. 06:31:19 TBH, I strongly suspect it broke the use cases of exactly *nobody* to not support the A20 line, though. 06:31:55 It'd only *possibly* break software people are running straight from DOS on a Haswell system. 06:32:06 -!- Lord_of_Life has quit (Remote host closed the connection). 06:32:14 maybe highmem.sys actually checked whether the A20 gate worked at some point? :P 06:33:08 If it's running from inside virtual 8086 mode, nothing breaks, so... 06:33:20 Yes, himem.sys could *hypothetically* be broken by that. 06:34:52 Also, given it's recent enough, you could actually probably work around it by using the virtualization extensions to have a *thin* VM that's basically just the base hardware except for a tiny chunk of RAM carved out, and A20 actually works. 06:36:02 you can even use paging to get the wrapping behavior right. 06:36:52 -!- erkin has joined. 06:36:54 the A20 gate was mighty silly from the moment it was introduced. 06:37:22 It made sense for maybe the year after it was introduced. 06:37:46 no, because oce it was there you'd be stuck for it forever :P 06:37:56 The only software that needed it was legacy software *at the time*, so. 06:38:12 -!- doesthiswork has quit (Quit: Leaving.). 06:38:18 admittedly updating software wasn't as easy then as it is now 06:41:34 just think, the alternative fix would be to permanently alias A20 to 0 if A21 upwards are all 0 06:41:35 (or to implement A20-as-0 in virtual 8086 mode) 06:43:02 I thought that 8088 only has twenty address lines anyways? Although, ais523's idea makes sense too, that you can have mirrored addressing of the physical memory perhaps. If 8088 has only twenty address lines and the later versions have more, then it would make more sense for that function to be part of the processor instead, where if you do not use long addressing then it wraps. 06:43:19 zzo38: it only has 19 address lines 06:43:29 that's why there were backwards compatibility issues when the twentieth was introduced 06:43:42 wait, no 06:43:46 I'm off by 1 06:43:52 it has 20 address lines, A20 is the 21st 06:44:36 so some 8086/8088 programs assume that there's no A20 line (by wrapping addresses past 1MB), meaning that later processors which wanted to be compatible tended to disable the A20 line by default 06:44:59 Yes, although due to that backward compatibility issues, I think it would make more sense for that to be a feature of the processor itself. If you do not enable long addressing by the control registers then the processor should automatically output 0 on the A20 line and all higher address lines. 06:45:58 zzo38: that's basically the solution the 80386 used 06:46:05 although in a bit of an indirect way 06:46:19 the A20 line nonsense was mostly related to the 80286 (which also had a number of other problems) 06:46:41 actually, a good way to think about the 80386 is "Intel learns how to be backwards compatible in a way that doesn't hold back the future too" 06:47:05 -!- Lord_of_Life has joined. 06:57:43 -!- xkapastel has quit (Quit: Connection closed for inactivity). 06:58:10 Is OSDev wiki the best way to learn about this stuff? 07:02:18 -!- ais523 has quit (Remote host closed the connection). 07:03:28 -!- ais523 has joined. 07:06:19 -!- FreeFull has quit. 07:07:13 <\oren\> I just invented a new word. Weaboo, but korea: Weobeo 07:08:47 . o O ( Are there esolangs with support for anonymous, first-class functions, but not closures? I'd say langs in general, but it seems odd enough to me that it would be considered esoteric ) 07:28:33 GCC C local functions 07:29:02 you've never heard of it because no one uses it, because it is about as useless as it sounds 07:29:18 Jafet: I've heard of it 07:29:38 however I believe they are closures, they just only last as long as the surrounding stack frame 07:30:16 oh, apparently they are 07:32:35 I've heard of it but never looked into the details. 07:32:44 How does it work? 07:33:15 shachaf: syntax-wise, it's basically the C function definition syntax that appears inside a function body 07:33:18 You can pass a nested function pointer as an argument to another function and it has its local scope? 07:33:29 implementation-wise, via the use of a small executable trampoline on the stack 07:33:45 and yes, the resulting function can be called (not very useful) but you can also take pointers to it 07:34:00 But the pointer is the same code pointer each time? 07:34:10 Or does it allocate executable memory or something? 07:34:51 nearly all implementations of first-class functions use the same code pointers each time 07:35:07 But then how does it pass the data? 07:35:27 using a data pointer, presumably 07:35:53 https://gcc.gnu.org/onlinedocs/gcc/Nested-Functions.html 07:35:59 shachaf: the pointer is to the stack 07:36:03 I'm talking about the "intermediate" example. 07:36:11 ais523: Executable memory on the stack? 07:36:13 which is basically a simple wrapper that supplies arguments and calls the actual code 07:36:20 shachaf: yes, it's a nightmare for gcc backend writers 07:36:58 I heard about a clever trick used by GHC on iOS, where you're not allowed to allocate writable executable memory (or something). 07:37:07 Or rather used by a library GHC uses. 07:37:45 I think the way it works is, they have a dynamically linked library that has a relative address. 07:37:50 -!- imode has quit (Ping timeout: 240 seconds). 07:38:00 They load it at multiple places in memory, and they put the data pointer next to it. 07:39:33 I thought that ghc implemented closures as functions taking a pointer to the closure data 07:39:59 -!- ais523 has quit (Remote host closed the connection). 07:40:04 I mean the thing where you can pass closures to C. 07:40:07 foreign import "wrapper" 07:40:09 -!- ais523 has joined. 07:43:32 After visiting the centre for computing history in Cambridge, I really want a BBC Micro 07:45:20 I used to have one of those 07:45:28 I don't think I still do, though; it's possible it broke 07:45:41 they should be pretty easy to emulate, come to think of it 07:45:46 maybe there's an emulator already 07:45:52 I'd imagine there is 07:48:32 ais523: whoa, it just makes the stack executable 07:48:36 That's ridiculous. 07:48:58 the whole thing? or just one page 07:49:02 either would be pretty bad though 07:49:45 it strikes me that programs would benefit from multiple (processor-provided) hardware stacks 07:50:04 one which only holds return addresses, one which is executable, one for small fixed-size locals, one for allocas, etc. 07:50:04 As far as I can tell the whole thing. 07:50:07 Not being able to allocate writable executable memory isn't very good then it makes it difficult to use self-modifying codes. 07:50:12 Of course there isn't that much stack in this process. 07:50:13 the extra cost in registers would be negligible 07:50:22 But at least the 33 pages labeled [stack] are +x 07:50:31 33 pages is a lot 07:50:31 -!- augur has quit (Remote host closed the connection). 07:50:38 Yep. 07:50:50 ais523: The Mill does something like that, doesn't it? 07:51:03 Well, not quite to that degree. 07:51:17 Itanium probably does something like that too 07:51:33 but having the return value stack independent of everything else makes quite a few exploits almost impossible 07:52:10 most notably, both the original "overwrite the return address so that it points to data" exploit, and the ROP-based version that gets past W^X 07:57:14 ais523: Oh, it just sets the stack to executable in the ELF flags. 07:57:50 This is scow. 07:58:08 -!- ^v has joined. 08:00:05 would sending the stack pointer to point at part of the executable image be more or less scow? 08:00:08 -!- augur has joined. 08:00:53 What do you mean? 08:01:23 have a writable part of the executable; instead of writing to the stack, you temporarily shift the stack pointer to point at that part of the executable 08:01:28 then move it back when the function returns 08:01:42 Why do you need to do that? 08:01:45 you don't 08:02:05 I was trying to think of something that would accomplish similar things as making the stack writable, but was even more ridiculous 08:03:20 Ah. 08:03:46 You can write to read-only shared executable memory using ptrace. 08:03:51 That's how gdb sets breakpoints and so on. 08:04:01 Of course at that point it stops being shared. 08:04:33 come to think of it, a similar approach that's a bit less ridiculous is to reserve a few "closure slots" in the data segment for each closure to store the values being closed over 08:04:52 this wouldn't work if the function were recursive, but would work in other cases 08:05:02 and doesn't require any screwing around with memory protection nor segment discipline 08:05:16 -!- augur has quit (Ping timeout: 276 seconds). 08:05:28 I was planning to test with a recursive nested function. 08:05:43 Or rather a recursive nesting function. 08:05:51 But it turned out not be necessary. 08:09:36 It might be halfway reasonable to have a per-thread "stack" containing just executable closures. 08:10:35 that'd interact badly with longjmp, unless you told your longjmp implementation about it specifically 08:11:01 (and this is less irrelevant than it seems, as longjmp-heavy code is one of the main reasons to want to put random complicated things on the stack) 08:11:12 Speakinig of which, apparently you can implement longjmp using nested functions. 08:11:22 You can jump to labels from the nesting function. 08:12:07 yes, I think that works 08:12:11 in fact, it's basically just call/cc 08:12:24 with a slightly different call sequence 08:12:56 Why call/cc rather than longjmp? 08:13:30 because call/cc produces a "continuation" value which is a function that jumps to a particular point when called 08:13:39 In my informal mental hierarchy I have something like callcc > coroutines > longjmp 08:13:48 I think C should have more track and field sports than just longjmp 08:13:52 setjmp doesn't do that; a jmp_buf is a value that's only meaningful to lonjgmp 08:13:59 *longjmp 08:14:18 Since callcc can use the same continuation multiple times, and coroutines can switch back and forth, and longjmp can only jump up in the stack. 08:14:29 so in your case of creating a nested function that creates a jump, you're pretty much literally calling the rest of the code with the current continuation 08:15:00 note that the same continuation works multiple times in this case (actually, the same jmp_buf works multiple times with longjmp too, as long as you jump upwards to the same point each time) 08:15:01 -!- TellsTogo has joined. 08:15:18 Is the wiki down? 08:15:22 I guess that's true. 08:15:26 Yes, the wiki is down. 08:15:34 switch (setjmp(j)) { case 0: longjmp(j,1); case 1: longjmp(j,2); } 08:15:35 Tragic.. 08:15:41 not very useful as written, but it works 08:15:59 assuming I haven't forgotten C syntax 08:16:20 which I probably have, given that I have a job working with Java atm 08:16:21 I would say that you forgot break, but it doesn't do much here. 08:17:06 nah, I remembered it and realised it was unnecessary 08:17:39 I was trying to figure out a good way to make switch statements work for strings in C++. 08:17:49 I haven't known for sure if the same jmp_buf can be worked multiple times with longjmp, so I used something like: while(setjmp(j)); 08:17:50 oddly enough, most languages in which the switch-equivalent is called `switch` use some sort of `break` in it, although sometimes as a syntax error if it's omitted 08:18:31 You can make something like this work: constexpr auto t = foo("a","bc","def"); switch(t(s)) { case t("a"): ...; ... } 08:18:37 But it's not that great. 08:18:45 zzo38: is that even legal? there are very few contexts in which setjmp is allowed, I'm not sure if the test of a while statement is one of them (although the test of an if statement is, so it's plausible) 08:18:57 also why do I have a PM tab open with myself 08:19:17 this client often opens random PM tabs in response to what I assume are accidental clicks but normally they're with other people 08:19:38 ais523: Go has "switch" which doesn't require "break", but it has an explicit "fallthrough" statement. 08:19:39 ais523: I know there are only some cases where it is legal, but I believe implicitly comparing the result with a constant (in this case zero) is allowed 08:20:09 shachaf: Does FreeBASIC support anything similar? 08:20:10 zzo38: is merely comparing with 0 enough by itself? or are there restrictions on how you can use the comparison result, too? 08:20:26 zzo38: I've never used FreeBASIC. 08:21:51 ais523: I think it is allowed in any boolean context, but I think that's all. I think also I have read that it is not allowed to save the result of setjmp or to pass it to anything else though. 08:22:34 zzo38: right, the only way you can (legally) check more than two possibilities is to use it as the test of a switch statement 08:22:59 however, on most compilers, assigning the result to an int happens to work in practice despite being UB 08:23:56 But work-around is nevertheless possible, by making your own variable (or member of a structure, perhaps one that also has the setjmp buffer) to store the values you need to pass. This can also help if you want temporary override of where to jump back to, for example. 08:29:36 Speaking of Go, did you know that when you cast a type to an interface (or check whether it satisfies an interface), the Go runtime does runtime type checking? 08:29:37 zzo38: that's harder if the longjmp is in a signal handler that can be called recursively 08:29:46 Including string comparison of method names and everything. 08:30:05 shachaf: Java does that too, however it has a more efficient way to do it than string comparison of method names 08:30:16 ais523: Yes, although I was not considering signal handlers 08:30:34 ais523: Well, in Java you declare interface implementations explicitly, right? 08:30:51 shachaf: yes, that's one of the reasons checking is more efficient 08:30:55 In Go a type satisfies an interface if it has all the right methods with the right types. 08:31:14 IMO anything interface-like should have namespaced method names 08:31:44 which effectively means that even duck typing has "explicit" interface implementations as you wouldn't be using the interface's namespace otherwise 08:31:59 I'm not a big fan of the Go approach. 08:32:09 is there anything Go does well? 08:32:31 That depends on what you include in "anything". 08:33:05 I think the designers value simplicity a lot, which is nice. Even if I don't like a lot of their decisions. 08:33:48 It doesn't manifest itself in any particular feature but it makes for a pleasant experience in some cases. 08:34:29 Have you seen my RogueVM designs? It does allow the result of setjmp() to be used in any way, and interface implementations are done by just defining them by a class, but each interface is only two functions (a "read" function and a "write" function), so not quite like interfaces in other programming languages which do more than that I think. 08:34:43 I think language complexity and capacity for abstraction (beyond what Go has) is very often worth it, but it still has a cost that people don't consider. 08:34:46 comparing method names at runtime doesn't fit my definition of "simple" 08:34:52 although, hmm 08:35:01 something like Tcl is simple in some ways, and extremely complex in other ways 08:35:04 -!- mroman has joined. 08:35:32 What languages have namespaces symbols? 08:35:41 I know Common Lisp does. 08:35:44 I guess Rust. 08:35:56 Is it a common feature? 08:36:27 MMIX has namespace symbol in a way (although namespaces in MMIX are really just prefixes) 08:37:48 -!- augur has joined. 08:38:36 shachaf: not as common as it should be 08:38:53 Java namespaces a lot of things but not method names 08:39:18 however, because it has overloading, you can effectively namespace them via dummy parameters belonging to namespaced types 08:40:06 How much do you think C++ would benefit from JIT compilation? 08:41:12 literal C++, with no changes to make it JIT-friendlier, probably not much 08:41:23 there are too many corner cases which assume AOT behaviour 08:41:29 profile guided jitting could possibly help in some tight loops 08:42:37 -!- augur has quit (Ping timeout: 240 seconds). 08:42:39 most profilers don't help at all in high-performance C++, due to the lack of hardware instrumentation 08:43:04 CERN did switch CINT to llvm recently, though 08:43:40 There are already profile-guided AOT optimizers for C++. 08:44:20 I guess branch prediction helps, but a lot of code today is memory-bound 08:44:24 Maybe that's good enough in practice. 08:48:17 I wonder if there is any profile-guided optimisation for malloc 08:49:12 I don't even know how branch prediction is working on most computers, other than MMIX where it is explicit in the program. 08:49:29 zzo38: The Mill doesn't have branch prediction; instead, it has exit prediction. 08:49:39 Do you like this? 08:50:02 How is exit prediction working? 08:50:26 if you can replace each call to malloc with an allocation from a carefully chosen region, it could improve locality 08:50:40 Instead of having an arbitrary instruction stream, instructions are encoded in EBBs, "extended basic blocks". 08:50:48 rust sounds like the ideal candidate for it 08:50:56 You always jump the beginning of an EBB, and you always exit it at exactly one place. 08:51:31 So it predicts which exit it'll take from an EBB. 08:52:04 Don't be a fool. Go easy on your EBBs. 08:52:14 O, OK, well I still don't quite know. 08:52:39 zzo38: Maybe you should watch the Mill videos. 08:53:39 -!- augur has joined. 08:54:20 shachaf: how are those encoded in the instruction scheme? it strikes me as suspiciously VLIWy if the compiler is meant to specify how they work 08:55:02 Specify how what work? 08:55:40 The Mill is indeed suspiciously VLIWy. 08:56:26 what's so suspicious about being VLIWy? 08:58:31 -!- augur has quit (Ping timeout: 268 seconds). 08:58:34 -!- sleffy has quit (Ping timeout: 276 seconds). 09:02:29 -!- TellsTogo has quit (Ping timeout: 260 seconds). 09:03:44 zzo38: you mean on the CPU level? 09:04:00 Most primitive ones just count how many times a jump was taken or not taken 09:04:02 then use this 09:04:17 well 09:04:20 You could predict indirect jumps, of course. 09:04:27 Some C++ code has a lot of virtual function calls. 09:04:28 even less primitive ones always assume that a jump is not taken 09:04:34 I mean JIT, not predict. 09:04:38 ah. 09:04:55 which is actually quite good I think 09:05:14 because then the compiler can just use the right version of the jump (jiz instead of jnz) 09:05:38 I know nothing about JIT tho :( 09:05:50 edwardk had a tracing JIT for amd64 09:06:19 It finds indirect jumps that usually go to the same address and replaces them with conditional jumps. 09:06:39 Or even just plain jumps, after checking the pointer once. 09:06:44 Or something. I don't know the details. 09:08:54 of course, CPUs already predict indirect jumps and calls 09:09:32 Sure. 09:10:28 though if you can inline them statically, it would reduce predictor cache pressure 09:11:07 C++ compilers will try to do this 09:11:36 But they can do much better with some profiling data presumably? 09:11:50 Who knows what virtual functions are likely to be called in practice. 09:12:40 Jafet: VLIW implies that the instruction stream contains redundant data, which turned out in practice to be inferior to just having the processor infer it 09:12:43 if the call target is not fixed, the code will still need a branch, and it will still involve CPU branch prediction 09:14:11 ais523: yes, but then your cores become complicated and use a lot of power 09:14:15 But I guess you can, say, move the check outside a loop, and have a common case that just has a direct branch? 09:14:18 I don't know. 09:14:49 aren't there prefetch instructions? 09:15:06 that sounds like a normal loop hoist, which I would expect any C++ compiler to do, though I don't know 09:15:10 (for instruction cache) 09:15:44 I happen to like the kind of branch prediction of MMIX, where the programmer will specify what prediction to use, rather than trying to make it automatic. 09:16:50 ah. MMIX has those P prefixes 09:16:55 what for? 09:17:21 Jafet: How can it do it without knowing the branch target? 09:17:29 Why not just predict "always taken" and then have to use the negated version of jumps if you want it differently? 09:17:49 mroman: that makes cold-path exception handlers hard to write 09:18:09 because in that situation, you have a number of unlikely jumps from different locations to the same location 09:18:12 I have to look up what that is :D 09:18:18 you are right, it doesn't know yet 09:18:36 that's IIRC not possible to write in such a way that the non-exceptional path takes every jump, without duplicating the handler 09:19:00 I believe the normal very simple "compiler specifies branch prediction properties" is to make backwards jumps predict as taken by default, and forward jumps predict as not taken by default 09:19:33 as loops generally jump back, right. 09:19:49 mroman: exception handler = code that handles an unusual/exceptional circumstance; cold-path = code that could run in theory but rarely actually does 09:20:31 ah right 09:21:20 what is a negated jump? is that where you squat? 09:21:44 Jafet: dropping into a buoyant fluid, I guess 09:21:53 thus causing you to go temporarily downwards, then rise back upwards 09:22:40 Jafet: jnz <-> jiz 09:22:53 or jumpIfAbove <-> jumpIfLessOrEqual 09:23:06 but it wouldn't really work yes 09:23:13 *jumpIfBelowOrEqual, surely? 09:23:25 most jumps are not selected by programmers, but by the compiler 09:23:38 IIRC jump-above and jump-greater are different operations in x86 (most likely it's a signedness difference) 09:24:30 they are 09:24:37 above/below is unsigned 09:24:37 hmm, I wonder if there's an asm where you can jump on arbitrary combinations of status flags 09:24:44 "jump if odd or equal", that sort of thing 09:26:00 -!- ais523 has quit. 09:58:22 -!- LKoen has joined. 10:05:54 jump if prime 10:05:56 that'll be usefull 10:27:42 DupSwap: Nobody has yet figured out what this is actually useful for. Some say it's useless, other's say... 'Fuck you'. 10:28:52 -!- jaboja has joined. 10:32:39 I argue DupSwap is a command for copyright reasons 10:32:41 like a fake map 10:33:08 If somebody were to steal my sets of commands and is stupid enough to also steal DupSwap 10:33:12 I have a solid case there! 10:49:57 -!- Lord_of_Life has quit (Remote host closed the connection). 11:09:44 -!- ybden has quit (Excess Flood). 11:10:23 -!- ybden has joined. 11:16:03 -!- mtve has quit (Ping timeout: 268 seconds). 11:16:22 -!- Lord_of_Life has joined. 11:16:26 -!- LKoen has quit (Remote host closed the connection). 11:17:54 -!- jix has quit (Ping timeout: 268 seconds). 11:18:22 -!- jaboja has quit (Ping timeout: 246 seconds). 11:18:32 -!- jix has joined. 11:19:49 -!- mtve has joined. 11:20:11 -!- jaboja has joined. 11:33:42 -!- boily has joined. 11:34:42 fungot: how much WIS do you have? 11:34:42 boily: you the state would have to be there it's just uh attitude like you know like the buddhist philosophy that you know that these children are out there toting the guns and dealing drugs and you know 11:41:21 wait 11:41:22 what 11:42:03 buddhist philosophy is about children doing guns and dealing drugs. 11:43:52 * boily realigns fungot with current reality 11:43:52 boily: and she's not sure what else more to say 11:44:04 * boily shakes the fungot a little bit more 11:44:04 boily: like a a money thing here is is the shock of it all in the all in the world 11:44:32 * boily shakes more. just to be sure 11:44:36 -!- LKoen has joined. 11:44:42 fungot: now, what is buddhism? 11:46:27 -!- wob_jonas has joined. 11:52:43 " You see, one of the selling points of the 8086 was that it was a purely mechanical process to convert 8080 asm to it..." => sure, that's why they used the same format for the low half of the flags register, such as inverted carry for subtract operation etc. but why did they insist that any instruction must translate to a single instruction 11:52:43 on 8080, as opposed to sometimes translating to a short sequence of instructions? that's put some stupid instructions into the set. 11:58:04 -!- mroman has quit (Ping timeout: 260 seconds). 11:58:06 " actually, a good way to think about the 80386 is "Intel learns how to be backwards compatible in a way that doesn't hold back the future too"" => no way. the 386 introduced 16-bit operations that cause register tear. they might not have been able to foresee that, but that has already caused problems near the pentiums. 11:59:47 -!- LKoen has quit (Remote host closed the connection). 12:01:28 " it strikes me that programs would benefit from multiple (processor-provided) hardware stacks" => the problem with that is that it's inefficient to know how much of each stack you want to pop when you exit frames. 12:05:01 hm, citeseer's cache is currently not working 12:05:17 fortunately, google has cached citeseer's cache 12:06:06 perhaps I should also download a local copy of this paper 12:09:26 " is there anything Go does well?" => sure, there's a lot of things that most modern programming languages do well, and go doesn't mess up either. also, marketing. 12:10:35 " What languages have namespaces symbols?" => C++, rust 12:13:48 don't Java's dot also count as a namespace symbol, with its static methods, and `import static`? 12:14:04 -!- LKoen has joined. 12:15:08 boily: I think it's a typo for "namespaced symbols" from context 12:15:19 oh. 12:17:26 " I don't even know how branch prediction is working on most computers, other than MMIX where it is explicit in the program." => some generation of x86 allowed taken/not-taken hints for short branch instructions, and in a backwards compatible way too, 12:18:26 but they don't do anything now, which makes sense, because how the cpu does branch prediction changes every few years so any hint that made sense in older cpus might actually make your program perform worse than the no-hint prediction in modern cpus 12:19:37 even on MMIX I think the prediction bit is used only on cheaper versions of the hardware, like 486 level 12:23:09 " what is a negated jump? is that where you squat? Jafet: dropping into a buoyant fluid, I guess thus causing you to go temporarily downwards, then rise back upwards" lol 12:24:48 -!- wob_jonas has quit (Quit: http://www.kiwiirc.com/ - A hand crafted IRC client). 12:29:43 -!- boily has quit (Quit: LADY CHICKEN). 12:51:31 -!- augur has joined. 12:56:33 -!- augur has quit (Ping timeout: 268 seconds). 12:58:13 -!- Lord_of_Life has quit (Changing host). 12:58:13 -!- Lord_of_Life has joined. 12:58:13 -!- Lord_of_Life has quit (Changing host). 12:58:13 -!- Lord_of_Life has joined. 14:00:47 -!- doesthiswork has joined. 14:23:25 -!- xkapastel has joined. 14:26:11 -!- `^_^v has joined. 14:26:32 -!- LKoen has quit (Remote host closed the connection). 14:32:17 -!- Mayoi has joined. 14:35:37 -!- erkin has quit (Ping timeout: 240 seconds). 14:49:23 -!- Cale has quit (Remote host closed the connection). 14:50:46 -!- Cale has joined. 14:52:40 -!- doesthiswork has quit (Quit: Leaving.). 14:57:25 -!- doesthiswork has joined. 15:00:52 -!- jaboja has quit (Ping timeout: 260 seconds). 15:08:17 -!- ATMunn has joined. 15:08:17 -!- ATMunn has quit (Changing host). 15:08:17 -!- ATMunn has joined. 15:09:27 -!- AnotherTest has joined. 15:31:10 -!- Cale has quit (Ping timeout: 276 seconds). 15:35:21 -!- Cale has joined. 15:36:01 -!- Mayoi has quit (Quit: Ouch! Got SIGABRT, dying...). 15:47:31 -!- AnotherTest has quit (Ping timeout: 246 seconds). 15:47:43 -!- AnotherTest has joined. 15:47:53 -!- contrapumpkin has joined. 15:47:59 -!- Cale has quit (Ping timeout: 255 seconds). 15:48:10 -!- Cale has joined. 15:55:51 -!- LKoen has joined. 16:08:35 -!- jaboja has joined. 16:19:08 -!- LKoen has quit (Remote host closed the connection). 16:42:36 humans. 16:42:42 -!- btiffin has joined. 16:57:49 -!- AnotherTest has quit (Ping timeout: 255 seconds). 17:06:14 Damn it, the wiki is still down?! 17:07:10 -!- FreeFull has joined. 17:10:33 -!- zseri has joined. 17:15:56 -!- erkin has joined. 17:22:48 -!- AnotherTest has joined. 17:39:56 <\oren\> https://www.wykop.pl/cdn/c3201142/comment_4PbmfLgqbbQCMtbgNxVNKuLOf77gTHsi.jpg 17:41:25 <\oren\> everyone calls an integral an integral, except poles, who call it a calka 17:42:21 <\oren\> and icelanders, but that's probably on purpose 17:43:28 -!- AnotherTest has quit (Ping timeout: 240 seconds). 17:44:19 -!- LKoen has joined. 17:49:56 -!- wob_jonas has joined. 17:51:24 why the fuck do people do a 2d plot of something like records of something over time and connect the data points with straight lines instead of stairs? straight lines makes no sense! the record doesn't even approximate going down linearly, it has jumps when someone gets a new record. 17:51:35 it's so stupid 17:51:43 so many annoying stupid plots 17:58:24 If you think that's dumb, consider 3D pie charts 17:58:43 -!- jaboja has quit (Ping timeout: 268 seconds). 17:58:55 Cale: or 3D bar charts with crazy close perspectives, in plots where there's absolutely no need for any 3D. I know. 17:59:49 <\oren\> http://www.businessinsider.com/the-27-worst-charts-of-all-time-2013-6?op=1 18:00:31 -!- LKoen has quit (Remote host closed the connection). 18:01:01 Also, I just saw some charts where the numbers on the Y axis were truncated in the image, so all you could see is "5%" "0%" "5%" "0%" "5%" with no way to tell the first digit 18:01:56 -!- LKoen_ has joined. 18:02:56 -!- btiffin has quit (Remote host closed the connection). 18:05:44 -!- AnotherTest has joined. 18:06:50 \oren\: wow 18:16:56 -!- AnotherTest has quit (Ping timeout: 255 seconds). 18:23:04 -!- zseri has quit (Ping timeout: 260 seconds). 18:25:41 -!- AnotherTest has joined. 18:27:57 -!- LKoen_ has quit (Remote host closed the connection). 18:28:01 -!- jaboja has joined. 18:34:06 -!- zseri has joined. 18:35:49 Cale: Hale 18:35:53 3D pie charts are delicious 18:37:24 What is the meaning of the trace of a linear map? 18:38:48 shachaf: sum of eigenvalues? 18:39:08 also sum of elements in diagonals 18:40:16 shachaf: basically, if you have a linear map from a space to the same space, and you change coordinates (on both sides), the eigenvalues don't change, and so the multiset of eigenvalues is an important invariant. but 18:41:18 the multiset of invariants is a multiset, which is a bit ugly, so sometimes you want specific scalar-valued statistics from it, and the most important ones are the determinant (product of eigenvalues), trace (sum of eigenvalues), eigenvalue with largest absolute value, and the ratio of the eigenvalues with the largest and second largest eigenvalues 18:41:30 these come up in a few places, but I don't quite remember where 18:41:52 Hmm, so it is. 18:42:06 the trace is also funny because it satisfies a somewhat simple equality Tr(ABC)=Tr(BCA), which isn't as simple as the determinant one, but still comes up sometimes 18:42:25 maybe physicists can tell more about why the trace is important 18:42:32 it seems to come up in physics 18:42:44 and tensors and stuff 19:26:24 -!- jaboja has quit (Ping timeout: 260 seconds). 19:30:51 -!- jaboja has joined. 19:31:35 -!- LKoen has joined. 19:34:56 -!- Herbstkind has joined. 19:34:56 There are somewhat subjective questions like "What's the difference between X and Y?" that if you try to research on the internet, you find only vague answers like "I use X because it seems to work better for me" and answers that are trying to sell something "X is definitely better in all cases for the following five reasons: (long explanation), oh 19:34:57 and buy the way, buy our new X+ for just 99 dollars". 19:40:31 wob_jonas, what was the book you were buying yesterday 19:41:34 Taneb: ''Arany János Balladái Zichy Mihály rajzaival''. (2016) Kossuth Kiadó, MTA Könyvtár és Információs Központ – Országos Széchényi Könyvtár, ISBN: 978-963-09-8596-3. A kiadás alapja azonos címmel (I–IV. kötet), Budapest, Ráth Mór, 1895–1898. 19:41:50 nice facsimile of the old four volume book set with Zichy's beautiful drawings 19:43:42 totally in public domain, except possibly a single essay on page 69, which is only pretty likely in public domain and doesn't matter anyway, so I'm going to try to scan it in as high quality as I can get, clean it up, and upload to commons.wikimedia so everyone can access 19:44:10 it's such a beautiful collection of drawings that it totally deserves a complete reproduction on the internet 19:44:46 the destroyed book plus scanning will cost me less than 10000 HUF in total, which I will gladly pay for this 19:44:51 -!- sleffy has joined. 19:45:01 -!- LKoen has quit (Remote host closed the connection). 19:47:07 -!- oerjan has joined. 19:47:40 -!- erkin has quit (Remote host closed the connection). 19:58:59 -!- wob_jonas has quit (Quit: http://www.kiwiirc.com/ - A hand crafted IRC client). 19:59:20 -!- wob_jonas has joined. 20:01:49 -!- wob_jonas has quit (Client Quit). 20:07:51 -!- Phantom_Hoover has joined. 20:13:37 -!- MDude has quit (Ping timeout: 240 seconds). 20:25:58 -!- imode has joined. 20:36:05 -!- jaboja has quit (Ping timeout: 240 seconds). 20:48:39 -!- hppavilion[1] has joined. 20:58:34 hi hppavilion[1]. 20:58:49 hi rdococ. I just got dilated 21:11:37 -!- augur has joined. 21:11:58 O_o http://gcc.gnu.org/onlinedocs/gcc/Nested-Functions.html 21:12:06 -!- AnotherTest has quit (Ping timeout: 255 seconds). 21:13:06 nested functions + function pointers ≈ first-class functions 21:25:56 -!- zseri has quit (Quit: Page closed). 21:26:51 Hey, the server is answering SSH now. 21:26:59 But it seems to be having some amount of trouble. 21:27:00 -!- PinealGlandOptic has joined. 21:27:31 "Write-error on swap-device (254:1:178952)" "end_request: I/O error, dev sda, sector 25058568" "EXT4-fs error (device dm-0) in ext4_evict_inode:243: Journal has aborted" 21:27:37 Doesn't sound terribly healthy. 21:28:47 There's also 1254 processes marked "[sshd] ". 21:29:14 Wonder if a reboot would be a good idea. 21:29:21 ribbit 21:30:08 if there are 1254 processes then possibly it hasn't rebooted in a while 21:30:21 Not in 31 days. 21:30:37 Though most of those processes are from today or Aug 5th, for whatever reason. 21:30:54 was Aug 5th when it first disappeared? 21:31:01 They also all have systemd's init process as parent. 21:31:35 "Aug 5 02:17:41" is when syslog stops, so I'm guessing yes. 21:31:51 I guess a reboot is unlikely to make it any *more* broken than it currently is. 21:31:58 wheee 21:32:43 Looks like it's mounted / as read-only as well, presumably due to the errors. 21:33:03 Of course there's the chance that it won't come back up after a reboot, so maybe I should run my backup script to a temporary location just in case. 21:33:06 it's like a chicken walked up to a mountain and pecked the ground, causing a landslide that took a billion computers with it 21:39:42 Looks like mysql isn't up enough to do the backups, anyway. 21:39:53 Oh well, I still have a copy up to Aug 1st. 21:39:57 Actually cooked for the first time in years 21:41:03 Heh, rebooting doesn't work. 21:41:04 What food did you invent? 21:41:15 Cheese and Too Much Ham Omelette 21:41:19 "Failed to start reboot.target: Activation of org.freedesktop.systemd1 timed out" "Failed to open initctl FIFO: No such device or address" "Failed to talk to init daemon." 21:41:53 Taneb: As a marketing trick, maybe call it "Cheese and Extreme Ham Omelette" if you're starting a restaurant. 21:43:42 fizzie, I think I'll stay feeling like an imposter in software development for now 21:46:37 cheese and EXTREME jam omelette 21:49:34 -!- AnotherTest has joined. 21:57:24 . o O ( Are there esolangs with support for anonymous, first-class functions, but not closures? I'd say langs in general, but it seems odd enough to me that it would be considered esoteric ) <-- iirc FALSE might count... 21:58:21 -!- Herbstkind has quit (Quit: Leaving). 21:58:46 I considered the possibility of using partial application or currying to simulate anonymous functions, and function pointers to simulate higher-ordered functions. 21:58:56 i recall when translating my :()^ TC proof from underload to it, it was essential that no dynamically built functions were required. 21:59:13 -!- hppavilion[1] has quit (Ping timeout: 268 seconds). 22:01:48 -!- AnotherTest has quit (Ping timeout: 260 seconds). 22:03:36 -!- AnotherTest has joined. 22:21:19 -!- AnotherTest has quit (Ping timeout: 276 seconds). 22:33:29 -!- LKoen has joined. 22:42:03 Concept: esolangs where functions can not only be passed around as parameters, but their very mechanics can be modified - each individual step in the function is a unit in itself. 22:42:56 -!- wob_jonas has joined. 22:43:09 rdococ: like emacs lisp, or (sort of) postscript, or, you know, machine code? 22:43:22 maybe? 22:44:45 it's possible to modify code in a lot of languages that allow memory access, it's just very often very nonportable against different implementations, including later ones that are better optimized, which is why people don't like it 22:44:53 -!- tswe_tt has quit (Read error: Connection reset by peer). 22:45:19 people have modified BASIC code even in BASIC-era personal computers, mostly to get around various limitations of BASIC or tight memory limits 22:45:23 True, but I was considering a high-level approach in which modifying functions remains consistent between implementations, due to the fact that it is in the specification. 22:46:21 that's possible because those interpreters usually store the BASIC code in a rather straightforward way, as a list of characters with keywords represented as one or two byte shortcuts per line, and some sort of linked list structure to link the lines 22:49:51 such tricks were not done often, because once you go to so much trouble to learn about the guts of the machine, it's usually better to just write most of your program in machine code with very little use of BASIC, but they did exist 22:51:21 then there are the forth people. 22:56:14 one crazy hack you could do this way is to use the same loop for reading and writing all variables and array items of game state to/from a savefile in a game, with special code to switch the statement between WRITE and INPUT in the lines of code 22:57:03 this was necessary on the C64 because its basic didn't have a FIELD statement (nor MKI/CVI functions for that matter, although that wouldn't help here at all), so you saved text to the casette. what a waste! 23:09:17 -!- `^_^v has quit (Quit: This computer has gone to sleep). 23:13:28 -!- wob_jonas has quit (Quit: http://www.kiwiirc.com/ - A hand crafted IRC client). 23:15:42 yeah, that sounds like how I use assembly, at least for tight loops 23:15:49 (on z80) 23:19:48 -!- btiffin has joined. 23:27:33 -!- btiffin has quit (Remote host closed the connection). 23:28:53 -!- HackEgo has joined. 23:30:12 Hoo. 23:30:28 Looks like that worked. 23:30:45 HiEgo 23:31:14 systemd was totally hosed and refused to play ball, but there was a rw-mounted filesystem at /boot, so could stick in there a program that just called the reboot syscall. 23:31:58 Hacky. 23:32:35 So far there aren't even any IO errors in dmesg, and the web server is back up as well. 23:32:43 fizzie: Fortunately we're running regular fshg backups, right? 23:32:49 shachaf: Yes, we are. 23:33:07 -!- oerjan has set topic: http://esolangs.org/ is back, bimetal prismack nowhere to be found | logs: http://codu.org/logs/_esoteric/ http://tunes.org/~nef/logs/esoteric/?C=M;O=D | https://www.dropbox.com/s/fyhqyvy3i8oh25m/wisdom.pdf | ICFP contest ends on 2017-08-07. 23:33:12 <\oren\> hurray, I got a raise! 23:33:18 I had a copy up to slwd decadent//s,.,A,;s,$,., 23:33:34 \oren\: raise dead?! 23:33:35 famous last hacks 23:33:45 I didn't know \oren\ was a vampire. 23:33:48 (It's once a week, not quite up to continuous integration standards.) 23:34:12 oerjan: What's going on with olist, by the way? 23:34:18 What's what'shisname planning? 23:34:59 <\oren\> shachaf: no I got a raise in salry 23:35:23 shachaf: it appears to be going into fart joke territory hth 23:36:50 \oren\ sprø som salry 23:36:54 shachaf: i'm vaguely assuming durkon is trying to get the vampire to misunderstand some memories in a fatal way. just not sure he's succeeding much... 23:37:17 oerjan: he seems to be p. pleased with whatever he's doing 23:39:02 <\oren\> 🤑 23:39:02 <\oren\> 💰 23:39:02 <\oren\> 🏦 23:39:03 <\oren\> ! 23:39:38 economoji 23:40:01 <\oren\> also I watched the emoji movie 23:40:17 <\oren\> it was terrible 23:40:39 Why did you watch it? 23:41:02 <\oren\> becuase I wanted to knwo how bad it is 23:41:12 `unidecode 🤑 💰 🏦 23:41:14 U+1F911 MONEY-MOUTH FACE \ UTF-8: f0 9f a4 91 UTF-16BE: d83edd11 Decimal: 🤑 \ 🤑 \ Category: So (Symbol, Other) \ Bidi: ON (Other Neutrals) \ \ U+0020 SPACE \ UTF-8: 20 UTF-16BE: 0020 Decimal: \ \ Category: Zs (Separator, Space) \ Bidi: WS (Whitespace) \ \ U+1F4B0 MONEY BAG \ UTF-8: f0 9f 92 b0 UTF-16BE: d83ddcb0 Decimal: 23:41:26 `unidecode 🤑💰🏦 23:41:27 U+1F911 MONEY-MOUTH FACE \ UTF-8: f0 9f a4 91 UTF-16BE: d83edd11 Decimal: 🤑 \ 🤑 \ Category: So (Symbol, Other) \ Bidi: ON (Other Neutrals) \ \ U+1F4B0 MONEY BAG \ UTF-8: f0 9f 92 b0 UTF-16BE: d83ddcb0 Decimal: 💰 \ 💰 \ Category: So (Symbol, Other) \ Bidi: ON (Other Neutrals) \ \ U+1F3E6 BANK \ UTF-8: f0 9f 8f a6 UTF-16BE 23:41:31 . o O ( and now you know. and knowing is half the battle. ) 23:42:24 <\oren\> in emojis 23:42:43 `unicode 🤑💰🏦 23:42:44 U+1F911 MONEY-MOUTH FACE \ UTF-8: f0 9f a4 91 UTF-16BE: d83edd11 Decimal: 🤑 \ 🤑 \ Category: So (Symbol, Other) \ Bidi: ON (Other Neutrals) \ \ U+1F4B0 MONEY BAG \ UTF-8: f0 9f 92 b0 UTF-16BE: d83ddcb0 Decimal: 💰 \ 💰 \ Category: So (Symbol, Other) \ Bidi: ON (Other Neutrals) \ \ U+1F3E6 BANK \ UTF-8: f0 9f 8f a6 UTF-16BE 23:42:48 Hmm. 23:42:57 Wasn't there a thing that gave a more concise output? 23:43:10 `unidecode 🤑💰🏦 23:43:11 U+1F911 MONEY-MOUTH FACE \ UTF-8: f0 9f a4 91 UTF-16BE: d83edd11 Decimal: 🤑 \ 🤑 \ Category: So (Symbol, Other) \ Bidi: ON (Other Neutrals) \ \ U+1F4B0 MONEY BAG \ UTF-8: f0 9f 92 b0 UTF-16BE: d83ddcb0 Decimal: 💰 \ 💰 \ Category: So (Symbol, Other) \ Bidi: ON (Other Neutrals) \ \ U+1F3E6 BANK \ UTF-8: f0 9f 8f a6 UTF-16BE 23:43:45 shachaf: the concise output only works if all the characters are within the ancient version of python's unicode library 23:43:52 Ah. 23:43:58 imo fix it twh 23:44:15 that would probably require upgrading HackEgo's python. 23:44:29 <\oren\> money mouth, bag with dolar sign, bank 23:44:38 Why? Just change the printing format for the fallback. 23:45:33 <\oren\> 🏧 23:46:16 http://www.edgarmcherly.com/spider_rumor.htm 23:46:33 In the time it took me to find that comic I forgot why I was looking for it. 23:46:54 the fallback is to a more general unicode lookup program that isn't just for characters. 23:47:02 `multicode LATIN 23:47:03 U+0041 LATIN CAPITAL LETTER A \ UTF-8: 41 UTF-16BE: 0041 Decimal: A \ A (a) \ Lowercase: U+0061 \ Category: Lu (Letter, Uppercase) \ Bidi: L (Left-to-Right) \ \ U+0042 LATIN CAPITAL LETTER B \ UTF-8: 42 UTF-16BE: 0042 Decimal: B \ B (b) \ Lowercase: U+0062 \ Category: Lu (Letter, Uppercase) \ Bidi: L (Left-to-Right) \ \ U+0043 LATIN C 23:48:08 i suppose `unidecode could try to parse the output of that. 23:48:30 Doesn't it have Unicode data in a more convenient format? 23:49:18 <\oren\> `` multicod🏧e 23:49:19 ​/hackenv/bin/`: line 5: $'multicod\360\237\217\247e': command not found 23:49:35 <\oren\> I fail 23:49:35 well right, it's using share/unicodedata.txt or whatever 23:50:50 `` cat share/unic* 23:50:50 0000 NULL [.] \ 0001 START OF HEADING [.] \ 0002 START OF TEXT [] \ 0003 END OF TEXT [] \ 0004 END OF TRANSMISSION [] \ 0005 ENQUIRY [] \ 0006 ACKNOWLEDGE [] \ 0007 BELL [] \ 0008 BACKSPACE [] \ 0009 CHARACTER TABULATION [] \ 000A LINE FEED (LF) [ \ ] \ 000B LINE TABULATION 23:51:09 hum. 23:51:12 <\oren\> https://www.youtube.com/watch?v=LcT2Cx1Rbd8 23:51:56 well i don't know how to do it, anyway. 23:52:51 \oren\: Are they no longer underpaying you? 23:53:03 You should try to get even more money. Maybe get a top hat and be a proper capitalist. 23:53:51 imo move to america 23:54:07 and maybe oppress some people? 23:54:23 <\oren\> who would I opress in america, fat people 23:54:24 <\oren\> ? 23:54:35 What did they do to you? 23:55:45 <\oren\> i mean most people in america are already pretty oppressed 23:56:09 Right, so they're used to it. 23:59:13 We're used to it? How do I measure how oppressed I am? 2017-08-09: 00:00:16 `` for c in 🤑 💰 🏦; do unidecode $c | head -n 1; done 00:00:18 U+1F911 MONEY-MOUTH FACE \ U+1F4B0 MONEY BAG \ U+1F3E6 BANK 00:00:35 `url bin/unidecode 00:00:36 https://hackego.esolangs.org/fshg/index.cgi/file/tip/bin/unidecode 00:02:11 It could just do "take the first line" thing on the fallback, though it's using os.execvp which makes that not entirely trivial. 00:02:44 `mkx bin/singlecode//multicode "$@" | head -n 1 00:02:47 bin/singlecode 00:02:51 `singlecode 💰 00:02:52 U+1F4B0 MONEY BAG 00:02:53 shachaf: i recall something relevant in monty python's holy grail. i think you use a duck somehow. 00:03:09 -!- boily has joined. 00:03:13 `` sed -i -e 's/multicode/singlecode/g' bin/unidecode 00:03:15 No output. 00:03:23 `unidecode 🤑💰🏦 00:03:23 Traceback (most recent call last): \ File "/hackenv/bin/unidecode", line 6, in \ os.execvp("singlecode", ["singlecode"] + sys.argv[1:]) \ File "/usr/lib/python2.7/os.py", line 346, in execvp \ _execvpe(file, args) \ File "/usr/lib/python2.7/os.py", line 382, in _execvpe \ func(fullname, *argrest) \ OSError: [Errno 8] Exec 00:03:27 fizziello! you rehackegoed! 00:03:30 ... 00:03:36 `w 00:03:38 arin//ARIN is the American Registry for Internet Numbers. Or a pastebin service; one of the two. 00:04:54 `url bin/unidecode 00:04:55 https://hackego.esolangs.org/fshg/index.cgi/file/tip/bin/unidecode 00:05:06 I "fixed" that offline. 00:05:07 `unidecode 🤑💰🏦 00:05:08 U+1F911 MONEY-MOUTH FACE 00:05:20 Except without realizing it's not calling the fallback separately per character. 00:05:28 was just about to say. 00:06:18 helløœøœøœøirjan. 00:07:17 `` multicode 🤑💰🏦 | grep '^U+' 00:07:18 U+1F911 MONEY-MOUTH FACE \ U+1F4B0 MONEY BAG \ U+1F3E6 BANK 00:07:54 `` sed -i -e "s/head.*/grep '^U+'/" bin/singlecode 00:08:04 Yes, I was doing the same in a query. 00:08:18 `unidecode 🤑💰🏦 00:08:38 Hm. 00:08:45 U+1F911 MONEY-MOUTH FACE 00:08:46 No output. 00:08:57 I think it was being slow. 00:08:59 `unidecode 🤑💰🏦 00:09:00 U+1F911 MONEY-MOUTH FACE \ U+1F4B0 MONEY BAG \ U+1F3E6 BANK 00:09:05 Yes, that's good enough. 00:09:14 It's not exactly a consistent format, but definitely good enough. 00:09:18 `unidecode abc 00:09:19 ​[U+0061 LATIN SMALL LETTER A] [U+0062 LATIN SMALL LETTER B] [U+0063 LATIN SMALL LETTER C] 00:09:39 hm pretty close 00:11:04 `cat bin/singlecode 00:11:04 ​#!/bin/bash \ multicode "$@" | grep '^U+' 00:11:51 `sled bin/singlecode//2cmulticode "$@" | grep '^U+' | sed 's/.*/[&]/' | fmt -w500 00:11:53 bin/singlecode//#!/bin/bash \ multicode "$@" | grep '^U+' | sed 's/.*/[&]/' | fmt -w500 00:12:00 `unidecode 🤑💰🏦 00:12:01 ​[U+1F911 MONEY-MOUTH FACE] [U+1F4B0 MONEY BAG] [U+1F3E6 BANK] 00:12:59 I can see this in one of those motivational poster meme styles, with the word "dedication" under it. 00:13:09 OKAY 00:13:42 hellœily 00:16:35 I once K-Lined a bottle. I ended up with a klein bottle. 00:17:26 eine kleine flaschenmusik 00:18:49 * rdococ wonders what a high-level language with C-like syntax would look like 00:19:11 As in, higher-level. I know there are definitely lower-level languages than C. 00:19:55 * imode coughs. 00:20:00 C++. Rust. Java. 00:20:04 C#. 00:20:14 and literally a dozen others. 00:20:22 touche 00:20:38 like. find one who's syntax hasn't been influenced by C. that would be easier. 00:21:07 Well, there are programming languages which seem /wildly/ different from C. 00:21:26 of course there are. 00:21:33 helloily 00:21:41 It's just hoily. :P 00:21:52 nah 00:22:07 lazanteaus 00:22:09 theres coily and ahoily, but no hoily 00:23:54 ahoy 00:29:50 * rdococ throws some C and some first-class functions into a blender and blends 00:30:04 partial cubes are fucking weird. 00:31:04 -!- oerjan has quit (Quit: Nite). 00:32:31 QUINTHELLOPIA! 00:32:40 rdochelloc, imellode. 00:33:00 imellode. 00:35:00 bum 00:59:57 Well, I'm bored. My brain is malfunctioning, it can't come up with ideas. 01:00:16 join me in experimenting with path counting for hamming-labeled graphs. 01:00:26 I mean, binding, partial application and currying to simulate first-class functions seems cool and all, but many programming languages have that... 01:02:03 I wonder: if we started with reversible computing, instead of developing it as a concept later on, what would our programming languages be like? 01:06:09 -!- LKoen has quit (Quit: “It’s only logical. First you learn to talk, then you learn to think. Too bad it’s not the other way round.”). 01:17:55 O_O Apparently, and I did not know this, a goto statement was introduced to Lua 5.2.0-beta-rc1. 01:59:43 -!- paul2520 has quit (Ping timeout: 276 seconds). 01:59:45 what are partial cubes 01:59:45 -!- vifino has quit (Ping timeout: 248 seconds). 02:00:08 -!- paul2520 has joined. 02:00:08 -!- paul2520 has quit (Changing host). 02:00:08 -!- paul2520 has joined. 02:00:28 -!- vifino has joined. 02:02:38 -!- jaboja has joined. 02:10:25 . o O ( inverse Elvis operator, like Lua's and operator. a :? b ) 02:14:11 doesthiswork: https://en.wikipedia.org/wiki/Partial_cube 02:14:25 subgraph of an n-cube. 02:15:36 I don't know if anyone's mentioned this yet, but YaY! The wiki is back up. 02:20:15 -!- Phantom_Hoover has quit (Read error: Connection reset by peer). 02:24:11 rdococ: I think the /topic may have already pointed to that fact hth 02:26:40 boily: Not false. 02:31:33 `5 w 02:31:38 1/2:hungarian//A gulyás, közeli rokonaival, a pörkölttel és a paprikással szinte az egyedüli parasztételek, amelyek a 19. században a polgári és a nemesi konyhában teljes mértékben létjogosultságot szereztek. \ invention//Invention is the daughter of necessity. \ narutoverse//narutoverse is a place where they haven't heard of having 02:31:44 `n 02:31:45 2/2: a bus factor of >1. Sgeo drives the bus. \ tdt//That doesn't tdt. \ rholypoly//A rholypoly is an edible Greek species of Armadillidiidae. Goes well with garlic! 02:32:03 ...what? 02:32:26 everything makes sense. paprikással. 02:33:43 * rdococ suddenly dies 02:34:56 * imode throws rdococ a senzu bean. 02:35:07 please no dying, unless certified for auto-reanimation. 02:35:20 this is getting annoying 02:38:57 -!- wob_jonas has joined. 02:40:51 I have a stupid algorithm theory question that doesn't seem googlable because the results are masked by a more famous NP-complete question that doesn't seem to be reducable to my problem. 02:43:09 Input is a digraph G, node weights w that are arbitrary precision integers, a selected node s in that digraph, and a natural number n. Find a set of n arcs such that the total weight of the nodes reachable from s through those arcs is maximal. 02:43:44 The weights in the input are encoded in binary. This is clearly in NP, but I can't tell if there's a polynomial algorithm. 02:44:06 Can you give a polynomial algorithm or a good argument why such an algo doesn't exist (eg. the problem is NP-complete)? 02:45:27 ARGH I messed up the main part 02:45:34 The node weights in my problem are nonnegative. 02:45:46 0 <= w(v) for every vertex v 02:46:02 That's what makes it very different from the other problems I found on the interweb. 02:46:07 Trust me to mess this up. 02:47:20 Ah, this looks relevant: https://math.stackexchange.com/q/1824344/24908 02:47:31 Not the same though 02:47:50 Might still help. 02:48:17 linear programming eh... good idea 02:49:41 I don't understand how that works though 02:50:19 It sounds as if that answer is wrong 02:51:42 -!- boily has quit (Quit: WARRIOR CHICKEN). 02:54:54 -!- MDude has joined. 02:55:55 what is s? 02:56:04 nevermind 02:59:05 since every node monotonically non-decreases the total weight isn't the answer just the set of edges reachable from s? 02:59:21 ah n 02:59:32 yes dynamic programming 02:59:46 doesthiswork: dynamic programming how exactly? 03:00:12 note that n is in the input, and I would like a polynomial algorithm. 03:00:25 (an exponential algorithm is trivial) 03:01:10 but of course I could be just tired and making a stupid mistake here 03:01:24 -!- ATMunn has quit (Quit: See ya! o/). 03:02:05 the value of a node it is its w + all ws that it is worthwile to reach from it 03:03:26 ( don't have a solid answer yet so I'm working on it) 03:03:27 (input):1:51: error: expected: "#", 03:03:27 "$", "&", "&&", "&&&", "*!>", 03:03:27 "*", "***", "*>", "*>|", "+", 03:03:27 "++", "+++", "-", "->", ".", 03:03:27 "/", "/=", ":+", ":-", "::",↵… 03:04:03 ( "#" 03:04:03 "#" : String 03:05:04 I might ask this on TCS SE if I can't find an answer with more searching and thinking later, but I'm too tired for that today, and when I do it properly, I will probably find a ready answer on the web. 03:05:10 pretty sure you can reduce max-cover to it 03:05:36 why not reduce max-n 03:06:10 @Jafet: oh! that's a good idea 03:06:10 Unknown command, try @list 03:06:12 in fact, it probably works even if w ∈ {0,1} 03:07:05 although I don't really see if it works 03:07:25 if you know more concretely, please tell 03:08:19 How about start at s and for each path outward put the path partial sum at each node 03:08:46 that doesn't handle branching but will find the best linear 03:09:50 doesthiswork: the number of paths (from s) needn't be polynomially bound 03:10:05 so I don't see how you do that 03:10:33 it is bounded by the number of nodes 03:11:45 if that doesn't count then that is an easy proof that it can't be done polynomially 03:11:57 if there are S sets with M total elements, create a little tree for each set and join the sets to s by paths of length SM^2 03:12:44 doesthiswork: huh? the number of paths isn't bounded by the number of nodes 03:12:54 then if n=(K+1)SM^2-1, only K sets can be selected 03:14:07 you don't explore any node that has a higher or equal partial sum than the one you'd assign to it (this is the dynamic programming part) 03:14:09 Jafet: I don't understand that 03:15:22 doesthiswork: I don't understand that either, how is the algorithm supposed to work? 03:16:37 wob_jonas: I don't understand why you don't understand that 03:16:40 you start at s and create a tree where each node stores the sum of all weights between it and s 03:19:12 You're right that it doesn't work because the path length might be different 03:20:58 Jafet: ah, you're trying to reduce a different problem than I thought of 03:21:01 that's the problem 03:22:29 ah, tricky 03:22:46 https://en.wikipedia.org/wiki/Maximum_coverage_problem 03:23:07 you make long paths so those overwhelm other nodes in the node count limit 03:23:14 but still only polynomial length paths 03:25:24 And you assign 0 weight to the nodes in those extra paths, but 1 weight to the nodes corresponding the elements in the cover problem 03:25:59 That probably works as an NP-completeness reduction, yes, although I think your formulas are slightly off 03:26:05 Jafet: thank you 03:26:10 that sounds like a solution 03:41:10 -!- sleffy has quit (Ping timeout: 240 seconds). 03:43:34 -!- sleffy has joined. 03:48:36 -!- sleffy has quit (Ping timeout: 240 seconds). 03:57:32 -!- jaboja has quit (Remote host closed the connection). 05:09:00 -!- sleffy has joined. 06:14:07 -!- wob_jonas has quit (Quit: http://www.kiwiirc.com/ - A hand crafted IRC client). 06:29:24 [wiki] [[OISC]] https://esolangs.org/w/index.php?diff=52672&oldid=46344 * DinoD123 * (+10) Added mention of [[WordWordJump]], adjusted some grammar and phrasing 06:32:12 [wiki] [[OISC]] M https://esolangs.org/w/index.php?diff=52673&oldid=52672 * DinoD123 * (-2) 06:42:39 @metar esgg 06:42:39 ESGG 090520Z 10012KT 9999 -SHRA FEW024 SCT040 16/12 Q1011 07:06:00 -!- FreeFull has quit. 07:45:55 -!- augur has quit (Remote host closed the connection). 07:46:35 -!- doesthiswork has quit (Quit: Leaving.). 08:10:09 -!- augur has joined. 08:11:25 -!- xkapastel has quit (Quit: Connection closed for inactivity). 08:14:32 -!- augur has quit (Ping timeout: 260 seconds). 08:29:52 -!- augur has joined. 08:31:39 -!- erkin has joined. 08:35:25 -!- augur has changed nick to 17SABNV0E. 08:38:05 -!- 17SABNV0E has quit (Ping timeout: 268 seconds). 08:40:35 -!- augur has joined. 08:45:29 -!- augur has quit (Ping timeout: 268 seconds). 08:53:57 -!- augur has joined. 08:58:17 -!- augur has quit (Ping timeout: 260 seconds). 09:05:15 -!- AnotherTest has joined. 09:10:50 navigating hamming spaces gets weird. 09:12:37 -!- pikhq has quit (Ping timeout: 276 seconds). 09:13:40 -!- AnotherTest has quit (Ping timeout: 246 seconds). 09:15:35 "go five units west". okay. "go five units west again." okay. "you traveled back where you came from." 09:23:35 -!- pikhq has joined. 09:32:36 -!- sleffy has quit (Ping timeout: 240 seconds). 09:44:52 -!- augur has joined. 09:45:10 -!- imode has quit (Ping timeout: 240 seconds). 09:47:17 -!- jix has quit (*.net *.split). 09:47:19 -!- Gregor has quit (*.net *.split). 09:49:01 -!- augur has quit (Ping timeout: 246 seconds). 09:50:20 -!- augur has joined. 09:50:47 -!- mtve has quit (Ping timeout: 260 seconds). 09:54:35 -!- augur has quit (Ping timeout: 240 seconds). 10:00:03 -!- augur has joined. 10:04:43 -!- augur has quit (Ping timeout: 255 seconds). 10:09:06 -!- erkin has quit (Quit: Ouch! Got SIGABRT, dying...). 10:31:18 -!- jix has joined. 10:34:18 -!- Gregor has joined. 10:34:44 -!- mtve has joined. 10:36:12 -!- danieljabailey has quit (Quit: ZNC 1.6.4+deb1 - http://znc.in). 10:36:30 -!- danieljabailey has joined. 10:39:39 -!- erkin has joined. 11:08:46 -!- jaboja has joined. 11:16:03 -!- LKoen has joined. 11:34:41 -!- boily has joined. 11:56:59 `w 11:57:01 select//select is a very versatile construct: it waits for events, retrieves data from tables, creates a list from elements of an input list that satisfy a condition, a dropdown list element, an event for when selection changes, branches between multiple arms, conditional between two expressions, prints a text-based menu prompt in a loop, and more. 11:59:43 -!- erkin has quit (Quit: Ouch! Got SIGABRT, dying...). 12:13:40 -!- erkin has joined. 12:23:12 `w poll 12:23:13 That's not wise. 12:24:50 -!- boily has quit (Quit: BIREFRINGENT CHICKEN). 12:44:14 -!- LKoen has quit (Remote host closed the connection). 12:44:33 -!- LKoen has joined. 12:47:11 -!- augur has joined. 12:51:44 -!- augur has quit (Ping timeout: 260 seconds). 13:00:30 -!- erkin has quit (Remote host closed the connection). 13:00:51 -!- erkin has joined. 13:03:22 -!- LKoen has quit (Remote host closed the connection). 13:15:39 -!- LKoen has joined. 13:17:01 -!- jaboja has quit (Ping timeout: 276 seconds). 13:28:07 -!- pikhq has quit (Ping timeout: 255 seconds). 13:28:29 -!- pikhq has joined. 14:00:31 -!- doesthiswork has joined. 14:06:08 -!- LKoen has quit (Remote host closed the connection). 14:08:35 -!- zseri has joined. 14:09:29 hi 14:16:01 -!- __kerbal__ has joined. 14:18:10 -!- Labeo has joined. 14:19:47 -!- Labeo has quit (Client Quit). 14:39:37 -!- erkin has quit (Read error: Connection reset by peer). 14:41:11 [wiki] [[Unary Except Every Zero Is Replaced with the Title of This Programming Language or, Alternately, Is Replaced with the Smallest Counter-Example to the Goldbach Conjecture. Compilers and Interpreters Only Have to Implement the Former Option]] N https://esolangs.org/w/index.php?oldid=52674 * Kerbal * (+28896) Created page with "'''Unary Except Every Zero Is Replaced w 14:42:38 [wiki] [[User:Kerbal]] https://esolangs.org/w/index.php?diff=52675&oldid=52321 * Kerbal * (+329) 14:43:53 <__kerbal__> Guess how my new language works 14:44:14 <__kerbal__> You'll never figure it out 14:45:17 [wiki] [[Unary Except Every Zero Is Replaced with the Title of This Programming Language or, Alternately, Is Replaced with the Smallest Counter-Example to the Goldbach Conjecture. Compilers and Interpreters Only Have to Implement the Former Option]] M https://esolangs.org/w/index.php?diff=52676&oldid=52674 * Kerbal * (-1) 14:45:52 -!- erkin has joined. 14:46:21 -!- Mayoi has joined. 14:46:31 -!- `^_^v has joined. 14:46:40 -!- erkin has quit (Disconnected by services). 14:46:52 -!- Mayoi has changed nick to erkin. 14:55:49 -!- LKoen has joined. 14:57:41 -!- doesthiswork has quit (Quit: Leaving.). 14:59:49 -!- ATMunn has joined. 15:02:57 -!- augur has joined. 15:07:27 -!- augur has quit (Ping timeout: 240 seconds). 15:09:37 -!- augur has joined. 15:17:27 -!- augur has quit (Ping timeout: 260 seconds). 15:19:23 -!- augur has joined. 15:23:52 -!- augur has quit (Ping timeout: 258 seconds). 15:29:14 -!- augur has joined. 15:30:09 -!- erkin has quit (Quit: Ouch! Got SIGABRT, dying...). 15:36:45 <__kerbal__> I'm reading about http://agoranomic.org and have happened to notice that a lot of esolangers frequent that site 15:36:54 <__kerbal__> interesting 15:38:14 -!- zseri has quit (Ping timeout: 260 seconds). 15:40:40 -!- augur has quit (Ping timeout: 260 seconds). 15:40:55 -!- zseri has joined. 15:41:58 <__kerbal__> ok, well, maybe not a lot 16:09:27 http://esolangs.org/wiki/Talk:Text 16:10:50 [wiki] [[PRINTASKSWITCHINPUTCASEXGOTOACASEYGOTOBELSEGOTOC]] M https://esolangs.org/w/index.php?diff=52677&oldid=43384 * Rdococ * (-104) I am officially an idiot. 16:20:53 -!- AnotherTest has joined. 16:25:10 -!- AnotherTest has quit (Ping timeout: 240 seconds). 16:25:55 -!- AnotherTest has joined. 16:51:38 -!- LKoen has quit (Quit: “It’s only logical. First you learn to talk, then you learn to think. Too bad it’s not the other way round.”). 16:58:36 -!- AnotherTest has quit (Ping timeout: 260 seconds). 16:59:07 [wiki] [[Assignless]] https://esolangs.org/w/index.php?diff=52678&oldid=51721 * Rdococ * (+166) 17:24:02 -!- FreeFull has joined. 17:24:26 -!- AnotherTest has joined. 17:24:56 -!- xkapastel has joined. 17:38:35 -!- AnotherTest has quit (Ping timeout: 240 seconds). 17:47:14 <\oren\> https://twitter.com/theowalcott/status/895316802745507841 17:47:45 <\oren\> Idiot footballer thinks devanagari can be written vertically, and puts an i vowel on a separate line from the consonant it shoudl be attached to 17:48:35 [wiki] [[Special:Log/newusers]] create * Mercerenies * New user account 17:50:00 -!- imode has joined. 17:50:32 -!- AnotherTest has joined. 17:51:38 -!- erkin has joined. 17:52:20 [wiki] [[Esolang:Introduce yourself]] https://esolangs.org/w/index.php?diff=52679&oldid=52662 * Mercerenies * (+161) 17:59:24 -!- __kerbal__ has quit (Ping timeout: 260 seconds). 18:05:28 [wiki] [[Folder]] https://esolangs.org/w/index.php?diff=52680&oldid=50607 * Rdococ * (+44) 18:07:05 -!- AnotherTest has quit (Ping timeout: 240 seconds). 18:07:59 [wiki] [[Folder]] https://esolangs.org/w/index.php?diff=52681&oldid=52680 * Rdococ * (+290) 18:14:17 -!- AnotherTest has joined. 18:30:31 -!- Phantom_Hoover has joined. 19:08:57 -!- augur has joined. 19:13:37 [wiki] [[MashedPotatoes]] N https://esolangs.org/w/index.php?oldid=52682 * Mercerenies * (+13992) MashedPotatoes: an esoteric programming language designed to look like a mashup of other languages 19:18:20 [wiki] [[MashedPotatoes]] https://esolangs.org/w/index.php?diff=52683&oldid=52682 * Mercerenies * (-384) Corrected code block syntax for formatting 19:19:33 [wiki] [[Language list]] https://esolangs.org/w/index.php?diff=52684&oldid=52660 * Mercerenies * (+21) Added MashedPotatoes 19:19:49 tasty 19:20:08 -!- AnotherTest has quit (Ping timeout: 240 seconds). 19:20:25 -!- AnotherTest has joined. 19:20:59 [wiki] [[User:Mercerenies]] N https://esolangs.org/w/index.php?oldid=52685 * Mercerenies * (+51) Created page with "Hi, I'm Mercerenies. More content coming here soon." 19:21:16 [wiki] [[MashedPotatoes]] https://esolangs.org/w/index.php?diff=52686&oldid=52683 * Mercerenies * (+40) Attribution 19:27:58 -!- oerjan has joined. 19:32:07 @metar esgg 19:32:07 ESGG 091820Z 19013KT CAVOK 17/13 Q1013 19:33:09 @metar ENVA 19:33:09 ENVA 091820Z 11008KT CAVOK 17/11 Q1013 NOSIG RMK WIND 670FT 14010KT 19:41:40 hex grids are cool. 19:44:33 `? weather 19:44:34 lambdabot: @@ @@ (@where weather) CYUL ENVA ESSB KOAK PAMR 19:44:58 You should write a lambdabot script that extracts just the temperature from each METAR. 19:56:52 > "hi" 19:56:54 "hi" 19:57:04 `? weather 19:57:05 lambdabot: @@ @@ (@where weather) CYUL ENVA ESSB KOAK PAMR 19:57:13 hum. 19:57:25 @where weather 19:57:25 ?? ?@ ?run var$intercalate " \\ " . map (\x -> "(@metar "++x++")") . words $ ?show 19:57:47 lambdabot: @@ @@ (@where weather) CYUL ENVA ESSB KOAK PAMR 19:57:50 CYUL 091800Z 28015G21KT 30SM FEW050 FEW240 24/12 A3009 RMK SC1CI1 CI TR SLP190 DENSITY ALT 1000FT \ ENVA 091850Z 12007KT CAVOK 17/11 Q1013 NOSIG RMK WIND 670FT 16010KT \ ESSB 091850Z 14004KT 9999 19:57:50 FEW030 17/15 Q1013 \ KOAK 091853Z 24010KT 7SM OVC008 16/14 A2999 RMK AO2 SLP156 T01610144 \ PAMR 091853Z 00000KT 10SM SCT080 OVC100 16/12 A2996 RMK AO2 SLP147 T01560122 19:58:05 ic 19:58:28 `echo lambdabot: @run "hi" 19:58:29 lambdabot: @run "hi" 19:58:42 i guess that's pretty conclusive. 19:59:53 int-e: what's going on with that, yo twh 20:00:57 `unidecode > l 20:00:58 ​[U+003E GREATER-THAN SIGN] [U+0020 SPACE] [U+006C LATIN SMALL LETTER L] 20:01:47 ?where test 20:01:47 * lambdabot tests 20:01:53 ?where+ test `echo test 20:01:53 It is forever etched in my memory. 20:01:55 ?where test 20:01:55 `echo test 20:01:56 test 20:02:43 * oerjan doesn't see how that's relevant. 20:02:58 it ignored HackEgo, then responded to me c/p-ing the same command. 20:03:07 I'm just saying, maybe one of them should be ignoring commands from the other one. 20:03:26 I'll just cheat. 20:03:40 `echo lambdabot: @run "hi" 20:03:40 lambdabot: @run "hi" 20:03:41 unless HackEgo is suddenly inserting a ^O which i cannot copy. 20:03:42 "hi" 20:03:46 oh. 20:04:23 was that the cheat. 20:04:51 `? weather 20:04:52 lambdabot: @@ @@ (@where weather) CYUL ENVA ESSB KOAK PAMR 20:04:54 CYUL 091800Z 28015G21KT 30SM FEW050 FEW240 24/12 A3009 RMK SC1CI1 CI TR SLP190 DENSITY ALT 1000FT \ ENVA 091850Z 12007KT CAVOK 17/11 Q1013 NOSIG RMK WIND 670FT 16010KT \ ESSB 091850Z 14004KT 9999 20:04:54 FEW030 17/15 Q1013 \ KOAK 091853Z 24010KT 7SM OVC008 16/14 A2999 RMK AO2 SLP156 T01610144 \ PAMR 091853Z 00000KT 10SM SCT080 OVC100 16/12 A2996 RMK AO2 SLP147 T01560122 20:05:08 `? weather 20:05:09 lambdabot: @@ @@ (@where weather) CYUL ENVA ESSB KOAK PAMR 20:05:11 CYUL 091800Z 28015G21KT 30SM FEW050 FEW240 24/12 A3009 RMK SC1CI1 CI TR SLP190 DENSITY ALT 1000FT \ ENVA 091850Z 12007KT CAVOK 17/11 Q1013 NOSIG RMK WIND 670FT 16010KT \ ESSB 091850Z 14004KT 9999 20:05:11 FEW030 17/15 Q1013 \ KOAK 091853Z 24010KT 7SM OVC008 16/14 A2999 RMK AO2 SLP156 T01610144 \ PAMR 091853Z 00000KT 10SM SCT080 OVC100 16/12 A2996 RMK AO2 SLP147 T01560122 20:05:25 hm i cannot prove you didn't cheat again. 20:28:45 -!- erkin has quit (Quit: Ouch! Got SIGABRT, dying...). 20:30:02 `5 w 20:30:07 1/3:burlesque//Burlesque is only the sexiest language on Earth. (See: http://mroman.ch/burlesque) \ saucepan//The saucepan is a tool used by oerjan to cook delicious risgrøt as a reward for good behavior. \ gaspacho//You like Gaspacho and I like Gazpacho. Let's call the whole thing off! \ intellectual property//Intellectual property is either the 20:30:09 `n 20:30:09 2/3:plot of land where a university campus is or otherwise a property which gives something an intellectual air or appearance. \ fundamental theorem of taneb//The Fundamental Theorem of Taneb states that for all strings S, if S describes a thing not involving sex, then it is provable that Taneb invented the thing described by S; and, furthermore, t 20:30:11 `n 20:30:11 3/3:hat it is provable that there exists a string T that describes a thing not involving sex that Taneb did not invent. 20:30:20 `dowg saucepan 20:30:27 9456:2016-10-26 learn The saucepan is a tool used by oerjan to cook delicious risgr\xc3\xb8t as a reward for good behavior. 20:30:31 oerjan makes risgrøt? 20:31:17 not for many years alas. 20:31:36 Why not? 20:31:44 my stomach gets upset by hot milk products. 20:31:53 Hmm. 20:31:54 also, too lazy to cook. 20:32:18 I'm trying to get into the habit of cooking 20:32:22 I bought a fancy tri-ply saucepan. 20:32:29 I use it for all sorts of things. It's great. 20:32:32 I think I mentioned yesterday I made an omelette 20:32:42 Taneb: What vegetarian food have you been cooking? 20:32:57 -!- rdococ has left ("Leaving"). 20:33:05 shachaf, certain pasta ready meals 20:33:16 Taneb: Maybe you'd like to make tomato chutney? 20:33:29 Perhaps! But not tonight 20:33:42 I can send you a recipe my mother sent me. 20:33:44 I don't have any tomatoes in, for a start 20:33:52 And I need to use up my ham 20:34:11 Do you want the recipe? 20:34:17 . o O ( para-chutney, the meal for people in flight ) 20:34:34 I'm not sure "chutney" is even the right word for this thing. Maybe it is. 20:34:37 But at any rate it's TG. 20:34:48 Tomatoes are the best vegetables. 20:34:57 `? tomato 20:34:58 tomato? ¯\(°​_o)/¯ 20:35:02 `? tomahto 20:35:03 tomahto? ¯\(°​_o)/¯ 20:35:08 `? tomayto 20:35:09 tomayto? ¯\(°​_o)/¯ 20:35:16 hm wait 20:35:19 `? potato 20:35:20 potato? ¯\(°​_o)/¯ 20:35:22 plz send hairy tomato help 20:35:24 darn 20:35:38 `grwp whole think off 20:35:40 argh 20:35:46 `grwp whole thing off 20:35:56 gaspacho:You like Gaspacho and I like Gazpacho. Let's call the whole thing off! \ gazpacho:You like Gazpacho and I like Gaspacho. Let's call the whole thing off! 20:35:56 No output. 20:36:05 hm ok 20:36:17 -!- AnotherTest has quit (Ping timeout: 258 seconds). 20:36:28 -!- wob_jonas has joined. 20:36:31 * oerjan is delaying eating again -> 20:36:59 Jafet: funnily, that reduction still leaves open the similar problem where the graph has to be undirected. 20:38:01 -!- AnotherTest has joined. 20:38:22 __kerbal__: I thought only ais523 did 20:38:34 I have some tomatoes, but they're mealy (I think). 20:38:42 That's pretty scow. What do I do to avoid mealy tomatoes? 20:39:40 -!- joast has quit (Ping timeout: 246 seconds). 20:39:54 Maybe... make spaghetti sauce with them? 20:40:36 Well, I'm going to cook the ones I have. 20:40:38 "<\oren\> Idiot footballer thinks devanagari can be [...]]" => there are entire long blogs collecting stupid tattoos, including http://hanzismatter.blogspot.hu/ 20:40:51 But the others I made salad with, and the salad turned out bad. 20:41:03 So I want to avoid mealiness (meal?) in future tomatoes. 20:42:03 wob_jonas: There is http://www.badhebrew.com/ 20:42:31 \oren\: also related is http://www.madore.org/~david/weblog/d.2015-03-09.2280.html messed up arabic script on a sign, all letters in separated form and written left to right. 20:42:57 wob_jonas: several others are, or have been, in agora. i'm currently just watching. 20:43:07 that actually seems to happen somewhat often, I've seen a few cases myself, at least of the all letters in isolated form, I don't know enough arabic to tell whether the direction is reversed too 20:43:16 but i was in agora before i knew what an esolang was. 20:43:29 -!- Sgeo_ has quit (Ping timeout: 248 seconds). 20:44:05 Do you know what an esolang is now? 20:45:12 Also, I just got my new eyeglasses, so I'm now getting accustomed to it. 20:45:14 . o O ( i have some machines, but they're mealy ) 20:47:25 ``` rev <<<'won niaga evila si ogEkcaH' 20:47:26 HackEgo is alive again now 20:47:30 great 20:47:32 shachaf: erm... 20:48:07 . o O ( why is wob_jonas making HackEgo say evil things backwards ) 20:48:09 -!- atslash has quit (Read error: Connection reset by peer). 20:48:37 `le/rn_append oerjan//He doesn't know what an esolang is. 20:48:54 -!- atslash has joined. 20:49:02 shachaf: well i knew, but people keep trying to change the definition 20:49:24 `le/rn_append oerjan//He no longer knows what an esolang is. 20:49:36 `le/rn_append oerjan//He no longer knows whether he knows what an esolang is. 20:50:10 -!- Sgeo has joined. 20:50:24 `? oerjan 20:50:25 Your omnipheasant back principal swatty arrant "Darth Ept" oerjan the indecisive is a hazy expert in minor compaction. Also a Glaneep who disses Roald Dahl. He could never render the word "amortized" so he put it here for connivance. His arc-nemesis is Kitty Crocker. He twice punned without noticing it. 20:50:44 `2 ? oerjan 20:50:45 2/1: 20:50:50 hmm 20:51:09 we do try to keep it within standard length limits. 20:51:10 HackEgo didn't seem to understand your commands 20:51:16 Yeah. 20:51:30 wob_jonas: shachaf likes to pretend he gives HackEgo commands. 20:51:44 I didn't want to exceed the length limit. 20:52:06 i guess that would require a major compaction. 20:52:23 `grWp major compaction 20:52:25 No output. 20:52:41 `` doag . | grep compaction 20:52:48 No output. 20:53:00 Hmm. We were talking about major compactions here, weren't we? 20:53:22 `` grWp -l compaction 20:53:24 oerjan 20:53:26 hth 20:53:57 Oh, right. 20:54:12 `swrjan s/arc/ark/ 20:54:14 oerjan//Your omnipheasant back principal swatty arrant "Darth Ept" oerjan the indecisive is a hazy expert in minor compaction. Also a Glaneep who disses Roald Dahl. He could never render the word "amortized" so he put it here for connivance. His ark-nemesis is Kitty Crocker. He twice punned without noticing it. 20:54:55 -!- sleffy has joined. 20:55:45 Do you like LevelDB? 20:55:46 `swrjan s/Kitty Crocker/Noah/ 20:55:47 oerjan//Your omnipheasant back principal swatty arrant "Darth Ept" oerjan the indecisive is a hazy expert in minor compaction. Also a Glaneep who disses Roald Dahl. He could never render the word "amortized" so he put it here for connivance. His ark-nemesis is Noah. He twice punned without noticing it. 20:55:51 zzo38: U+261D 20:56:05 -!- quintopia has quit (Ping timeout: 240 seconds). 20:56:09 pun wasn't working. unless i didn't get the reference. 20:56:20 Wait, what pun? 20:56:50 well there's one now. 20:57:07 -!- quintopia has joined. 20:57:10 -!- Sgeo has quit (Ping timeout: 246 seconds). 20:57:11 it used to say i was antedeluvian, didn't it. 20:58:43 `` doag oerjan | grep delu 20:58:49 No output. 20:58:52 hm 20:58:59 dilu hth 20:59:05 `` doag oerjan | grep dilu 20:59:10 No output. 20:59:13 So it did. 20:59:20 dowg hth 20:59:27 `` dowg oerjan | grep dilu 20:59:34 8249:2016-06-01 sedlast s/antediluvian/precambrian/ \ 4652:2014-06-06 sed -i \'s/a lying/an antediluvian/\' wisdom/oerjan 21:00:02 i guess i hypercorrected to avoid anti- 21:00:20 Well, it means "before the deluge" 21:00:24 So it would make sense. 21:03:22 -!- Sgeo has joined. 21:09:59 -!- wob_jonas has quit (Quit: http://www.kiwiirc.com/ - A hand crafted IRC client). 21:13:44 -!- erkin has joined. 21:26:03 -!- AnotherTest has quit (Ping timeout: 255 seconds). 21:32:23 -!- AnotherTest has joined. 21:35:15 -!- zseri has quit (Ping timeout: 260 seconds). 21:44:51 -!- Antoxyde has joined. 21:50:58 <\oren\> the torque of a solar sail at the end of a space elevator is measured in nNMm 21:53:47 mHhM 21:54:21 \oren\: Do you like LevelDB? 21:56:02 <\oren\> shachaf: never used it 21:58:41 <\oren\> shachaf: what is it for? 21:58:54 Storing data. 22:03:39 <\oren\> shachaf: we already have databases that do that. does it do anything better? 22:04:01 No, all databases are identical. 22:04:48 <\oren\> shachaf: uh, no. I mean what is the advantage of using LevelDB over say MySQL 22:05:10 Do you like BigTable? 22:05:25 <\oren\> shachaf: no idea what that is 22:06:31 Maybe the t is lowercase. 22:06:53 Well, LevelDB is like one Bigtable tablet. 22:08:08 Hmm, do you like Spanner? 22:10:01 <\oren\> shachaf: uhhh are you just naming random google internal thingies 22:10:07 Yes. 22:10:11 Well, LevelDB is external. 22:10:23 And I don't know much about Spanner other than external details. 22:12:38 <\oren\> so levelDB is basically used for when you want a giant hash? 22:12:57 A hash of what? 22:12:57 <\oren\> a giant map from strings to strings that is? 22:13:35 I don't think that's accurate. 22:13:52 For example you can make range queries. 22:15:50 <\oren\> so it's a giant PHP array? 22:16:13 <\oren\> supporting both array-like and hash-like things? 22:16:33 Hmm? 22:18:07 I mean you can query all the values in the range [a,b) 22:18:12 keys 22:19:56 -!- AnotherTest has quit (Ping timeout: 255 seconds). 22:20:52 <\oren\> http://php.net/manual/en/language.types.array.php 22:23:44 Aren't PHP arrays implemented as hash tables? 22:25:39 <\oren\> shachaf: they are a hybrid hash-table linked-list mess 22:26:05 forget everything you know about php hth 22:26:31 <\oren\> i wish i could 22:26:39 The point is that you can't ask for all keys in the range ["abc","def") 22:49:48 -!- `^_^v has quit (Quit: This computer has gone to sleep). 23:14:00 -!- Phantom_Hoover has quit (Read error: Connection reset by peer). 23:23:10 -!- imode has quit (Ping timeout: 240 seconds). 23:27:35 -!- erkin has quit (Quit: Ouch! Got SIGABRT, dying...). 23:43:09 -!- oerjan has quit (Quit: Nite). 23:52:43 -!- boily has joined. 2017-08-10: 00:04:04 -!- Antoxyde has quit (Quit: Leaving). 00:09:30 -!- sebbu has quit (Ping timeout: 240 seconds). 00:12:42 fungot: nostril. 00:24:30 -!- xkapastel has quit (Quit: Connection closed for inactivity). 00:31:36 fungot: Speak when spoken to. 00:31:37 fizzie: anyone here speaks swedish? :p. ugh i need to go to burger king for lunch. 00:31:55 fungot: How would you even eat food? 00:31:55 fizzie: which kind of defeats the community spirit :p. ugh i need to 00:32:12 Well, if you definitely need to. 00:33:32 ^style 00:33:32 Available: agora alice c64 ct darwin discworld enron europarl ff7 fisher fungot homestuck ic irc* iwcs jargon lovecraft nethack oots pa qwantz sms speeches ss wp youtube 00:33:41 ^style qwantz 00:33:41 Selected style: qwantz (Dinosaur Comics transcriptions 2003-2011) 00:33:48 fizzie: Do you like Spanner? 00:47:53 I don't know much about it. 00:48:17 I see on the Cloud Spanner page they've managed to make one of those comparison tables where their thing gets best of everything. 00:49:25 ✔ has more checkmarks than the competition 00:55:08 helloocheckmarkchaf. 00:55:19 fizziello, fungellot. 00:59:38 -!- oerjan has joined. 01:00:11 hellørjan. 01:01:56 helloily. 01:02:41 fizzie: how's the esolangs.org registration? someone at reddit claimed whois showed it was expired and in a grace period. 01:02:46 *on 01:05:14 (they thought that's why the site was down.) 01:07:26 hm i don't see anything like that. 01:08:22 oerjan: Should be fine. 01:08:32 It's on auto-renew, and last bumped up in May. 01:08:38 Registry Expiry Date: 2018-05-24T19:21:16Z 01:14:09 * oerjan makes a comment https://www.reddit.com/r/esolangs/comments/6rv7fq/esolangsorg_down/dlekraj/ 01:14:20 -!- rdococ has joined. 01:16:14 who is cheryllium? 01:18:42 . o O ( which cheryllium ) 01:20:03 two questions: the one who is a moderator on /r/esolangs? there are multiple ones? 01:20:13 oh 01:20:21 no idea 01:25:31 -!- doesthiswork has joined. 01:33:27 -!- oerjan has quit (Quit: Nite #2). 01:43:44 `5 w 01:43:48 1/2:goofix//Goofix is an antropomorphic canine arithmetic notation. \ squirrel//A squirrel is a small nut-harvesting unit frequently deployed all over the world. They are popular due to their usefulness in distracting dogs. \ lifespan//Your lifespan is how fat you are in the time dimension. The temporally fattest person in the world has a temporal 01:44:08 squirrels are evil. 01:55:45 <\oren\> STUPID TUNNELBLICK I HATE IT 01:58:12 HE\\OREN\. 01:58:28 <\oren\> I can't get the stupid VPN to work 01:59:13 <\oren\> it either sends nothing thru the VPN, or sends EVERYTHING thru the VPN 01:59:17 what is tunnelblick? what kind of VPN is it setting up? on what platform are you running it? what's the phase of the moon? 01:59:27 <\oren\> OpenVPN 02:00:21 <\oren\> and I want it only to go thru the vpn when connecting to company wobsites, not when connecting to yahoo.com 02:02:21 <\oren\> it's on macOS. 02:02:39 I'm a little bit rusty on VPN stuff, but afaicr, you'll be filtering your trafic based on some kind of mask. stuff like everything that points to 10.x.x.x goes through the VPN. 02:03:23 do you have access to CLI tools, or are you expected to go through the tunnelblick thing for everything? 02:04:25 I think OSX ethernet tools are BSDlike. is there such a concept as TUN/TAP on OSX? 02:04:31 <\oren\> boily: yeah 02:04:55 <\oren\> http://www.moongiant.com/phase/today 02:05:09 I don't have access to that kind of thing right now, and I may be past a few gin tonics, but I believe that's the first step. 02:05:33 I wish you good luck, and may your googlesoteric-fu be powerful! 02:05:46 oh, full moon. 02:14:36 -!- [ATMunn] has joined. 02:16:05 -!- ATMunn has quit (Ping timeout: 240 seconds). 02:16:27 -!- [ATMunn] has changed nick to ATMunn. 02:30:20 -!- boily has quit (Quit: CITRIC CHICKEN). 02:31:03 -!- imode has joined. 03:02:06 -!- ATMunn has quit (Quit: See ya! o/). 03:38:57 [wiki] [[Ly]] https://esolangs.org/w/index.php?diff=52687&oldid=52661 * LyricLy * (+125) 03:39:39 [wiki] [[Ly]] https://esolangs.org/w/index.php?diff=52688&oldid=52687 * LyricLy * (+22) /* Stack manipulation */ 04:01:51 I'd talk more often here, but then I run the risk of being scolded. 04:22:57 -!- sleffy has quit (Ping timeout: 240 seconds). 04:25:44 scolded for what. 04:25:46 -!- sleffy has joined. 04:27:43 -!- joast has joined. 05:16:36 [wiki] [[Special:Log/newusers]] create * Aaronduino * New user account 05:22:58 -!- aaronduino has joined. 05:26:04 -!- aaronduino has quit (Client Quit). 05:26:22 -!- aaronduino has joined. 05:27:52 Hello. Anyone online? 05:27:57 -!- PinealGlandOptic has quit (Quit: leaving). 05:29:17 -!- aaronduino has quit (Client Quit). 06:13:46 <\oren\> http://imgur.com/D7VwIOs 06:21:17 [wiki] [[Ly]] https://esolangs.org/w/index.php?diff=52689&oldid=52688 * LyricLy * (+1158) 06:22:25 So I've been reading brian cantwell-smith's varieties of self reference 06:23:24 and it awakens in me the desire to make a language that fully understands its operation. but doesn't have much control 06:53:11 -!- erkin has joined. 07:03:07 -!- FreeFull has quit. 07:08:19 -!- sleffy has quit (Ping timeout: 255 seconds). 07:09:12 -!- augur has quit (Remote host closed the connection). 07:12:27 -!- augur has joined. 07:12:31 -!- augur has quit (Remote host closed the connection). 07:20:33 -!- sleffy has joined. 07:51:27 -!- augur has joined. 07:53:36 -!- shiklet has changed nick to shikhin. 07:55:48 -!- augur has quit (Ping timeout: 240 seconds). 08:07:12 -!- augur has joined. 08:11:52 -!- augur has quit (Ping timeout: 260 seconds). 08:29:27 -!- doesthiswork has quit (Quit: Leaving.). 08:43:45 -!- erkin has quit (Remote host closed the connection). 08:44:06 -!- erkin has joined. 08:51:24 -!- erkin has quit (Ping timeout: 255 seconds). 09:37:30 -!- imode has quit (Ping timeout: 240 seconds). 09:43:35 -!- Sgeo has quit (Ping timeout: 240 seconds). 09:54:22 -!- sebbu has joined. 10:03:24 -!- erkin has joined. 10:04:27 -!- sleffy has quit (Ping timeout: 260 seconds). 10:10:43 -!- AnotherTest has joined. 10:13:02 -!- augur has joined. 10:17:21 -!- augur has quit (Ping timeout: 248 seconds). 10:26:21 -!- AnotherTest has quit (Ping timeout: 255 seconds). 10:35:04 -!- gsora has joined. 10:36:32 -!- LKoen has joined. 10:46:46 -!- AnotherTest has joined. 10:49:45 -!- Sgeo has joined. 10:52:09 -!- Antoxyde has joined. 11:34:19 -!- boily has joined. 12:14:11 -!- jaboja has joined. 12:26:04 -!- AnotherTest has quit (Ping timeout: 276 seconds). 12:26:42 -!- boily has quit (Quit: PLAN CHICKEN). 12:31:18 -!- AnotherTest has joined. 12:58:20 -!- AnotherTest has quit (Ping timeout: 255 seconds). 12:58:46 -!- AnotherTest has joined. 13:27:50 -!- AnotherTest has quit (Ping timeout: 240 seconds). 14:03:18 -!- AnotherTest has joined. 14:07:45 -!- AnotherTest has quit (Ping timeout: 255 seconds). 14:12:32 -!- AnotherTest has joined. 14:20:35 -!- jaboja has quit (Ping timeout: 240 seconds). 14:27:35 -!- doesthiswork has joined. 14:39:57 -!- zseri has joined. 14:44:14 -!- `^_^v has joined. 14:47:07 -!- jaboja has joined. 15:03:26 -!- doesthiswork has quit (Quit: Leaving.). 15:10:00 -!- AnotherTest has quit (Ping timeout: 260 seconds). 15:19:39 -!- AnotherTest has joined. 15:37:49 -!- jaboja has quit (Ping timeout: 276 seconds). 15:44:21 -!- ATMunn has joined. 15:58:52 -!- jaboja has joined. 16:06:05 -!- jaboja has quit (Ping timeout: 240 seconds). 16:06:22 -!- jaboja has joined. 16:21:07 -!- erkin has quit (Quit: Ouch! Got SIGABRT, dying...). 16:21:35 -!- AnotherTest has quit (Ping timeout: 240 seconds). 16:22:03 -!- AnotherTest has joined. 16:26:25 -!- jaboja has quit (Ping timeout: 248 seconds). 16:36:40 -!- augur has joined. 17:33:30 -!- jaboja has joined. 17:51:33 -!- aaronduino has joined. 17:52:12 -!- aaronduino has quit (Client Quit). 17:53:23 -!- ais523 has joined. 18:06:56 -!- augur has quit (Remote host closed the connection). 18:08:49 -!- augur has joined. 18:13:06 -!- augur has quit (Ping timeout: 258 seconds). 18:24:18 -!- ais523 has quit (Remote host closed the connection). 18:25:29 -!- ais523 has joined. 18:28:51 -!- augur has joined. 18:33:05 -!- augur has quit (Ping timeout: 240 seconds). 18:51:55 -!- Phantom_Hoover has joined. 19:15:20 `olist 1090 19:15:22 olist 1090: shachaf oerjan Sgeo FireFly boily nortti b_jonas 19:26:26 -!- PinealGlandOptic has joined. 19:39:26 -!- imode has joined. 19:41:10 -!- wob_jonas has joined. 19:41:49 an olist? great 19:41:54 it's speeding up! 19:43:01 ... ah yes. as if that worked. 19:43:01 hi 19:43:15 great foreshadowing 19:45:40 -!- imode has quit (Ping timeout: 255 seconds). 19:52:54 -!- nchambers has quit (Ping timeout: 255 seconds). 19:55:32 wob_jonas: It's been updating every Monday and Thursday for the past few weeks. 19:55:45 wow 19:58:16 -!- LKoen has quit (Remote host closed the connection). 20:00:21 -!- lambdabot has quit (Remote host closed the connection). 20:00:36 " actually, a good way to think about the 80386 is "Intel learns how to be backwards compatible in a way that doesn't hold back the future too"" => no way. the 386 introduced 16-bit operations that cause register tear. they might not have been able to foresee that, but that has already caused problems near the pentiums. 20:00:50 -!- nchambers has joined. 20:01:37 " it strikes me that programs would benefit from multiple (processor-provided) hardware stacks" => the problem with that is that it's inefficient to know how much of each stack you want to pop when you exit frames. 20:01:40 -!- ais523 has quit (Remote host closed the connection). 20:02:00 argh I sent him away! 20:02:49 -!- ais523 has joined. 20:04:03 -!- `^_^v has quit (Quit: This computer has gone to sleep). 20:05:28 -!- `^_^v has joined. 20:06:45 -!- lambdabot has joined. 20:12:06 -!- aaronduino has joined. 20:13:00 hello. Anyone online? 20:13:58 hi 20:14:09 I'm online 20:14:16 Hello 20:14:39 Is there anything I should know before making an esolangs.org page for AsciiDots? 20:15:07 nobody is online. 20:15:15 Oh. Good to know :) 20:15:56 `5 w 20:16:01 1/2:output//who//Who cares about ancient cases anyway? \ vulture//Vulture is like Culture, but far less picky about the food. \ quoteformat//quoteformat is: message; * nick action; two spaces between messages; all elisions marked with [...] other than irrelevant intervening messages; for messages separated by elision, one space on each side, 20:16:07 `n 20:16:08 2/2: not two. \ nm//nm means "nondeterministic minotaur" hth 20:16:38 `? hth 20:16:39 hth ([ʰtʰh̩]) is help received from a hairy toe. It is not at all hambiguitous. 20:16:42 `? inb4 20:16:43 inb4? ¯\(°​_o)/¯ 20:16:47 `? tias 20:16:48 tias? ¯\(°​_o)/¯ 20:17:13 ? 20:17:16 `tias 20:17:24 ​/home/hackbot/hackbot.hg/multibot_cmds/lib/limits: line 5: exec: tias: not found 20:17:54 Is HackEgo a bot? 20:17:59 `yes 20:18:00 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 20:18:04 Ok 20:18:42 So, wob_jonas, anythink I should know before adding a language to esolangs.org? 20:18:52 *anything 20:19:13 dunno, just read the wiki a bit to see how other articles work 20:19:18 Ok. 20:19:22 and the introduction on the main page too 20:19:47 k 20:19:59 aaronduino: you'll need to introduce yourself to the wiki first, if you haven't yet 20:20:05 we have a lot of problems with spambots 20:20:10 see http://esolangs.org/wiki/Esolang:Introduce_yourself 20:20:43 Oh. Good to know. Thx 20:20:43 apart from that, when creating an article, the main thing that people forget to do that's helpful is to make sure it's actually possible to find the article 20:20:52 link it from the language list, and place it in appropriate categories 20:20:56 Oh yeah. 20:21:30 yeah, we actually have both a language list and a languages category, both independently maintained for some reason 20:21:35 I don't understand why 20:21:43 Huh 20:21:50 I think there are discrepancies between them but I haven't really checked 20:22:00 The main page (and documentation) is on github (github.com/aaronduino/asciidots); should I copy and paste from that or just write a little description on the wiki and link to the github page? 20:22:05 it's just some crazy habit esoteric people do 20:22:46 I guess an esowiki needs some overarching esotericness that isn't too distracting, or else some worse esoterisation of the wiki would pop up 20:23:11 Huh 20:23:15 (some say natural languages work that way too, people make it more and more complicated as long as they can still speak it. I don't really believe that theory.) 20:23:30 Huh 20:23:44 [wiki] [[Special:Log/newusers]] create * Ais523 signup process tester 1 * New user account 20:23:50 So, should I copy and paste documentation into esolangs if its is maintained on Github? 20:24:27 aaronduino: often it'll need reformatting to look good; Esolang doesn't use Markdown 20:24:40 Ok. Will do 20:26:31 On the Introduce Yourself page, do I need to write the timestamp, or is it appended automagically? 20:27:06 if you use four tildes for a signature, the wiki will replace that with a timestamp when you save the page 20:27:12 Ok. thx 20:27:12 as in foo ~~~~ 20:27:15 -!- oerjan has joined. 20:27:43 -!- erkin has joined. 20:28:50 k 20:28:59 [wiki] [[Esolang:Introduce yourself]] https://esolangs.org/w/index.php?diff=52690&oldid=52679 * Aaronduino * (+251) 20:29:08 Great 20:30:44 [wiki] [[MediaWiki:Welcomecreation-msg]] N https://esolangs.org/w/index.php?oldid=52691 * Ais523 * (+369) tell new users about the introduction page 20:31:48 I just changed the signup form so that it would tell people about the introduction page 20:31:54 so that they don't have to get an edit rejected to discover it exists 20:32:29 wob_jonas: specifically, three tildes is just username, four is username + timestamp, five is just timestamp 20:32:50 four is therefore the standard signature 20:33:03 -!- imode has joined. 20:33:06 Do more ~s have more esoteric definitions 20:33:20 17 ~s is a link to the last article you edited 20:33:23 not that I know of 20:34:22 ais523: i thought half of the point of the introduction system was that it would thwart the kind of spammers that use humans for signup but bots for editing; that extra inf may break that. 20:34:26 *info 20:35:18 let's see if it turns out to be a problem, first 20:35:31 if nothing else, it'll be amusing to see what the human spammers say 20:35:43 and several new people have complained about losing edits because they didn't know about the introduction rule 20:36:07 well, at least one 20:36:51 if it were possible, it would be better to put such a warning on the edit button itself. 20:37:35 (that is, triggered by _starting_ an edit of the wrong page) 20:37:40 it is possible, not sure how many people would read it though 20:37:52 nobody reads the current request to make sure pages are correctly categorised 20:38:05 well in such a way that you cannot edit the page, naturally. 20:38:21 oh, that's harder 20:38:48 I'm not sure we can detect whether a user's been introduced or not from CSS or JS without using AJAX 20:38:51 although, hmm 20:39:02 oerjan: there's the old internet truth that no matter how many flashing red warnings and click-throughs and "I accept" checkboxes you put, eventually you just can't make some people to read things 20:39:05 there's a possible fix but it's really complex and would require a change to the sitewide config 20:39:35 we could make it so that users become autoconfirmed at 1 edit, then use the !autoconfirmed status as a trigger to tell people to introduce themselves 20:40:53 wob_jonas: but if there was no actual edit form for them to fill in, they might at least suspect they were doing something wrong. 20:42:06 oerjan: you mean you'd just get the source view for an uneditable page? maybe 20:42:22 more depressing is that since the introduction system started, i recall exactly _one_ spammer getting caught in it. just the other day. 20:42:33 good afternoerjan 20:42:44 (of course that's because we haven't had an actual spam flooding attempt, but still...) 20:42:46 What do you make of this regular olist update schedule? 20:42:52 shachaf: shocking 20:43:19 I always imagine that scene with James Bond and the hairdryer when someone says that. 20:43:58 * oerjan may not have seen that scene 20:46:24 -!- tromp has quit (Remote host closed the connection). 20:47:07 What's the best kind of Norwegian pizza? 20:47:49 -!- Antoxyde_ has joined. 20:48:06 i wouldn't know. 20:48:38 I'm guessing it's the deep fjord pizza. 20:48:47 sounds fishy. 20:49:21 although my dad once, way back, did make a fish pizza. 20:49:44 i suppose tuna isn't unheard of, this was not tuna. 20:50:12 -!- ATMunn has quit (Ping timeout: 260 seconds). 20:50:22 . o O ( hm herring pizza ) 20:50:27 Is there a way to automatically convert from markdown to the wiki's markup language? 20:50:28 Salmon pizza isn't that uncommon either, I think. 20:50:37 Oops. Sorry to inturrupt 20:50:47 -!- Antoxyde has quit (Ping timeout: 260 seconds). 20:51:00 Interrupt... the really important discussion about pizza? 20:51:05 aaronduino: i don't know, but it's mediawiki syntax, so search for that. 20:51:09 Interrupting the offtopic chatter with esolang dicussions? 20:51:15 I'd be surprised if no-one had written a markdown-to-wikitext converter. 20:51:17 the nerve! 20:51:18 aarnduino: there's probably no perfect way for that, because Markdown is stupid and impossible to parse. it's probably the second worst wiki formatting system after Tiki's 20:51:18 oerjan: thx 20:51:35 perhaps that famous pandoc can do it 20:51:42 Well, its hard to parse, but great to write in 20:52:01 pandoc does have it as a supported format, yes. 20:52:25 There's also a few MediaWiki modules that add support for Markdown, but I don't think we want to experiment with those. 20:52:28 wob_jonas: What syntax should I use instead of Markdown? 20:53:07 shachaf: I quite like mediawiki syntax myself 20:53:22 I'm pretty sure markdown-to-mediawiki convertors exist, but that doesn't necessarily mean they're any good 20:53:24 No way, it's way too heavyweight for taking notes. 20:53:27 surely mediawiki is even harder to parse 20:53:38 I just want to write things down and have them be readable in the source language. 20:53:40 mediawiki syntax is much more internally consistent than markdown is 20:53:41 Not for a wiki. 20:53:48 Well, maybe for a wiki. 20:53:49 if it's harder to parse, it's because it has more cases, not because they're more complex 20:54:20 Do you ever go mushroom-hunting? 20:54:20 The main thing I like about markdown is using backticks for code instead of spaces or x 20:54:48 low-overhead markup languages have three main requirements: 1) not looking excessively artificial when read (i.e. mistakable for text files); 2) capable of expressing arbitrary content; 3) being easy for unfamiliar users to write in 20:55:19 Markdown fails all three, IMO (whereas MediaWiki syntax passes 2 and in simple cases 3) 20:55:33 I'd rather like something that passed 1 and 2 simultaneously 20:55:34 * oerjan hasn't been mushroom-hunting since ... _possibly_ early 90s, quite likely 80s. 20:55:37 all three at once seems fairly hard 20:56:14 Markdown isn't too far from passing 1, I think. 20:57:10 there's also a case for just plain HTML, features restricted by the parser for security, and added features in HTML syntax only for things that HTML can't easily express 20:57:17 -!- sleffy has joined. 20:57:19 I know, I've used a subset of Markdown in the past when 1 was the most important feature 20:57:29 eg. some syntax for internal wikilinks that looks HTML-like 20:57:38 wob_jonas: that's basically BBcode 20:57:49 which is pretty good if you want 2+3 and don't care about 1 at all 20:58:02 ais523: yes, bbcode is decent 20:59:05 -!- aaronduino has quit (Quit: Page closed). 21:01:57 ais523: btw many of the new users recently did _not_ get caught in the filter before introducing... with many of them from PPCG, i've been wondering if it's passed through word by mouth. 21:02:12 quite possibly 21:02:28 -!- ais523 has quit. 21:02:32 otoh at least one of them had a hard time. 21:14:33 -!- tromp has joined. 21:17:05 -!- viznut_ has quit (Ping timeout: 240 seconds). 21:18:57 -!- tromp has quit (Ping timeout: 240 seconds). 21:19:56 -!- erkin has quit (Quit: Ouch! Got SIGABRT, dying...). 21:20:12 -!- viznut has joined. 21:32:54 -!- tromp has joined. 21:33:53 -!- ATMunn has joined. 21:33:53 -!- ATMunn has quit (Changing host). 21:33:53 -!- ATMunn has joined. 21:39:21 [wiki] [[Special:Log/newusers]] create * Jordan * New user account 21:41:53 [wiki] [[Esolang:Introduce yourself]] https://esolangs.org/w/index.php?diff=52692&oldid=52690 * Jordan * (+209) 21:52:36 That's a pretty fast progress from Log/newusers to Esolang:Introduce yourself. I think ais523's change is working! 22:02:36 -!- LKoen has joined. 22:10:28 nope, that user got caught in the filter first. 22:16:33 -!- wob_jonas has quit (Quit: http://www.kiwiirc.com/ - A hand crafted IRC client). 22:21:03 Aw. :/ 22:33:06 -!- AnotherTest has quit (Ping timeout: 255 seconds). 22:38:00 -!- zseri has quit (Quit: Page closed). 22:57:51 <\oren\> @realdonaldtrump: I have just ordered a preemptive strike on pyongyang. #MAGA #cleansingfire 22:57:51 Unknown command, try @list 22:58:08 [wiki] [[AsciiDots]] N https://esolangs.org/w/index.php?oldid=52693 * Aaronduino * (+13223) Create page for AsciiDots 23:00:33 [wiki] [[Language list]] M https://esolangs.org/w/index.php?diff=52694&oldid=52684 * Aaronduino * (+16) add AsciiDots to language list 23:00:57 -!- aaronduino has joined. 23:02:08 -!- `^_^v has quit (Quit: This computer has gone to sleep). 23:03:38 Hello 23:05:48 *chirp* 23:17:50 beep. 23:18:12 -!- oerjan has quit (Quit: Nite). 23:33:28 -!- Phantom_Hoover has quit (Read error: Connection reset by peer). 23:40:41 -!- wob_jonas has joined. 23:42:12 http://www.smbc-comics.com/comic/fuel-efficiency reminds me to the captivating idea I have of a tram so long it doesn't even have to move at all: passengers just get on in one door in one station and exit on another door in the other station. 23:42:44 the problem with that is that cars couldn't cross the road with the tram then 23:44:28 you might as well have a walking underground subway then. 23:44:31 how would it not move? 23:44:38 just shut the trains down, and walk 23:45:18 in one of Asimov books there's walkways that are similar to trains 23:46:09 Hoolootwo: yeah, walking strips. 23:46:12 wob_jonas: sounds like a topic for #trains hth 23:46:14 but a long tram is funnier 23:47:35 -!- sleffy has quit (Ping timeout: 240 seconds). 23:49:35 -!- augur has joined. 23:57:14 -!- aaronduino has quit (Ping timeout: 260 seconds). 2017-08-11: 00:14:47 -!- mertyildiran has joined. 00:16:59 Hi, what are the best examples of self-replicating computer program generation system that developed using an esoteric programming language? 00:18:30 by best, I mean the ones with most successful results (generated most complex programs) 00:19:54 *specifically using Turing tarpit languages 00:29:55 redcode. 00:30:29 -!- Mr2001 has quit (Ping timeout: 260 seconds). 00:35:30 imode: Redcode? 00:37:10 redcode, the programming language for CoreWar. 00:37:59 the entire idea is "battling programs", and thus, replication. 00:39:27 "thus"? battling programs don't necessarily have to involve replication 00:39:40 you can have one program battling one 00:39:52 don't try to set it up like that's a clear consequence 00:40:25 Mr Smith replicated, but normal agents don't do that 00:42:07 -!- wob_jonas has quit (Quit: http://www.kiwiirc.com/ - A hand crafted IRC client). 00:52:40 imode: for Redcode it says not even Turing Complete. 00:53:10 imode: I'm looking for the state-of-art. 00:53:43 -!- sleffy has joined. 00:54:56 also what is the self-replication example in the lowest leve possible? in Assembly for example. 00:55:14 *lowest level 00:56:11 I'm asking that because I couldn't find any example beyond a toy (printing to console and not doing any real life tasks) 00:57:00 "the state of the art". 00:58:17 maybe a self-replicating system targeting x86 assembly language for example, can be useful 00:58:27 why self replication, exactly. 00:58:42 go play with von neumann CAs in golly. 00:58:55 also, redcode is turing complete. 01:01:15 you seem to have something in mind, perhaps consider sharing with us. 01:02:08 imode: "state-of-the-art" is also valid (the was missing though :D). https://esolangs.org/wiki/Redcode says it's (almost) Turing Complete. 01:02:25 yes, in the same way that every modern computer is (almost) a turing machine. 01:02:39 we live in finite memory spaces. turing machines require infinite memory. 01:03:18 regardless of that, I'm wondering why you're seeking self-replication. there was some work on.. god what was it.. robust-first computing. 01:03:53 https://www.youtube.com/watch?v=7hwO8Q_TyCA&list=PLm5k2NUmpIP-4ekppm6JoAqZ1BLXZOztE here's an entire playlist of talks and presentations on it. 01:04:09 if that doesn't satiate you, you might have some other idea in mind. 01:08:02 imode: I was just wondering around about self-replication in computers and biology for a while. I found DNA codon table (https://en.wikipedia.org/wiki/DNA_codon_table) and languages like Brainfuck or DNA# (https://esolangs.org/wiki/DNA-Sharp) are very similar yet far away from being useful. 01:08:52 yup. and that's mainly because we don't really have use for things that have the ability to replicate. 01:09:38 "robust-first computing" is kind of like what you're searching for. multiple agents with biological feedback systems working towards a real goal, like sorting an array. 01:10:04 imode: because the encapsulation has been made by manual coding from CPU architecture to your desktop environment is making Turing tarpit languages useless. 01:10:27 -!- sleffy has quit (Ping timeout: 240 seconds). 01:10:38 not really. it's more "why would I want to write a program that replicates itself or has the capability to replicate if it doesn't contribute to the end goal of my project." 01:10:58 if your goal is to write worms, then sure. if your goal is to do some creative stuff with distributed systems, then sure. 01:12:18 don't get me wrong. case studies in evolution applied to programs produce interesting results, but it's not generally useful. 01:13:10 same goes with self-replicating programs. 01:13:23 -!- sleffy has joined. 01:13:27 imode: the thing that it's not possible to mimic biologic replication in a high level computer code. This was the thing I was trying to say. 01:13:40 well, you say that but it's definitely possible. 01:14:01 "mimic biologic replication", you mean replication with mutation? that's entirely the point of.. well, genetic algorithms. 01:14:08 when applied to programs, of course. 01:15:10 there was even a simulator that provided a circular string of DNA embedded with operations on a stack machine, and some of those were operations that did replication/modification of the original string. 01:15:17 I'll see if I can find it. 01:15:17 imode: I know what genetic algorithms are. 01:16:06 imode: you know the amino acids are the most basic building blocks of a protein. 01:16:19 yes, I'm very well aware of that. 01:16:43 as should anybody who's taken a biology course in highschool. 01:19:24 imode: and what a protein is doing a cell? It's a procedure(function) in a cell. Every protein does certain tasks and there are protein complexes that you can imagine as a procedure made of from multiple functions. 01:19:51 imode: everything is possible with 20 amino acids in total. 01:20:09 ...yes, it's a useful abstraction, sure. though I don't really see your point. 01:21:51 imode: now imagine a microprocessor architecture with 20 instructions in its assembly language. 01:22:12 imode: that's the same thing in theory right? 01:23:34 no. useful abstraction, but it doesn't cut it. 01:24:31 imode: what I'm trying to say is it's more of a hardware and encapsulation problem than an algorithmic problem. Encapsulation creating a barrier. 01:24:55 imode: what do you mean with does not cut it? 01:24:57 barrier to what? nothing stops us from mimicing mutation and replication on a fixed alphabet which stands for instructions. 01:25:09 -!- doesthiswork has joined. 01:25:10 again, it's what genetic algorithms were invented to do. 01:25:36 and it doesn't cut it because cellular mechanics are far more complicated than "proteins are just function calls". proteins don't do anything. 01:25:47 imode: barrier in front to the advancement of this field (self-replicating programs). 01:25:49 not by themselves, anyway. 01:26:13 uh.. no. there's nothing stopping you from simulating a bonafide genome. people do it all the time. plenty of resources on genetic algorithms around. 01:27:03 go research protein folding. that will show you where exactly your analogy breaks down. 01:28:07 sorry to say but the idea isn't useful generally. you're not going to suddenly apply a genetic algorithm to x86 machine code and out pops a cyborg. :P 01:28:20 now, you can apply GAs to useful optimization problems. 01:32:47 Simulating and mimicking are different concepts. With DNA simulation you create better DNA (the target is biology) but with DNA mimicking you create better program (the target is computers). 01:33:04 ..simulating and mimicking are the same thing. 01:33:23 Current self-replication technologies are unable to surpass manual coding. 01:33:48 -!- Antoxyde_ has quit (Quit: Leaving). 01:34:05 But biologic self-replication is able to surpass manual coding of DNA. 01:35:13 Bacteria create better bacteria before your computational biology techniques, so nature surpass. 01:36:16 Not useful = Will not be invested 01:37:12 -!- sleffy has quit (Ping timeout: 260 seconds). 01:39:07 imode: also you said proteins are function calls not functions itself. So where the program is stored for those functions? If you are talking about mitochondria there is mitochondria DNA :) 01:39:17 -!- LKoen has quit (Quit: “It’s only logical. First you learn to talk, then you learn to think. Too bad it’s not the other way round.”). 01:39:30 *mitochondrial DNA 01:40:56 so your original question wasn't really a question. you just had an idea in mind and wanted to expound on it. 01:41:47 imode: no I'm just investigating the frontier. 01:42:05 yeah. sure. 01:42:15 have fun with uh.. whatever your intent is. 01:43:21 imode: I'm ultimately looking for the self-replication in the lowest level possible (and its usefulness). 01:48:07 -!- jaboja has quit (Remote host closed the connection). 01:57:37 -!- boily has joined. 02:02:08 -!- aaronduino has joined. 02:06:42 I'm arguing with someone about language. He wants an example of where A is true B is true and A "and" B is false 02:08:45 uh.. as in, "A&B" behaves like "!(A&B)"? 02:09:57 “if (A) { if (B) { /* something */ } }” is isomorphic to “if (A && B) { /* something */ }”. 02:10:10 Isomorphic? 02:10:10 you *could* express something like you said, but it wouldn't be logically sound. 02:10:22 well. some word to that effect. 02:10:37 up to isomorphism, I guess >_>'... 02:13:41 What isomorphism? 02:16:42 * boily hmms. 02:17:54 If I have a file with QuickTime movies in it, and I try to pull out one movie, and it's just sound and half the sound is coherent and half is static, where did I screw up? 02:17:55 is it always the case that “if (A) { /* asdf */ } if (B) { /* asdf */ }” is the same as “if (A && B) { /* asdf asdf */ }”? 02:18:05 Like, how do I not get either pure static or the coherent thing I'm looking for? 02:18:09 But... half? 02:18:24 -!- aaronduino has quit (Ping timeout: 260 seconds). 02:22:39 Holy crap I got something to work 02:24:41 gotta love that moment. 02:29:40 Not sure how to expand on this 02:29:53 I replaced everything before the first mdat with a huge skip atom 02:32:18 -!- aaronduino has joined. 02:32:23 Well, I now know how to point this 300MB file to various things within it 02:32:40 I suppose I could do some sort of "change file + run conversion tool" thing 02:32:56 Hello 02:33:00 Hi aaronduino 02:33:29 I just added a language to the wiki (AsciiDots)? Anything else I should do? 02:33:39 (categorical stuff, etc) 02:34:25 -!- mertyildiran has quit (Quit: Page closed). 02:37:45 Sgeo, do you go on ppcg? 02:38:26 no 02:38:30 k 02:39:39 Have a favorite esolang? 02:45:46 -!- aaronduino has quit (Quit: Page closed). 02:56:28 -!- boily has quit (Quit: ZEITGEIST CHICKEN). 03:06:20 -!- ATMunn has quit (Quit: See ya! o/). 03:11:09 -!- atslash has quit (Read error: Connection reset by peer). 03:11:28 -!- atslash has joined. 03:18:22 -!- rodgort` has joined. 03:18:54 -!- atslash has quit (Read error: Connection reset by peer). 03:18:55 -!- atslash has joined. 03:18:56 -!- rodgort has quit (Ping timeout: 260 seconds). 03:18:56 -!- sdhand has quit (Ping timeout: 260 seconds). 03:18:56 -!- newsham has quit (Ping timeout: 260 seconds). 03:23:44 -!- sdhand has joined. 03:24:07 -!- sdhand has changed nick to Guest86463. 03:28:15 -!- atslash has quit (Ping timeout: 260 seconds). 03:28:16 -!- newsham has joined. 05:05:55 -!- Guest86463 has changed nick to sdhand. 05:06:13 -!- sdhand has quit (Changing host). 05:06:13 -!- sdhand has joined. 06:23:33 -!- erkin has joined. 06:29:25 -!- zseri has joined. 06:40:54 -!- zseri has quit (Ping timeout: 260 seconds). 06:46:01 what's this, it's warmer in Göteburg than in Innsbruck :P 06:46:11 @metar esgg 06:46:12 ESGG 110520Z 19006KT 9999 VCFG SCT011 13/12 Q1016 06:46:13 @metar lowi 06:46:14 LOWI 110520Z VRB01KT 9999 -SHRA FEW005 SCT016 FEW050CB BKN055 12/11 Q1016 TEMPO SHRA 07:27:01 -!- Bowserinator has quit (Quit: Oh noes I ded). 08:42:54 who else is up at this ungodly hour. 08:50:57 -!- augur has quit (Remote host closed the connection). 08:59:30 -!- doesthiswork has quit (Quit: Leaving.). 09:22:50 -!- imode has quit (Ping timeout: 240 seconds). 09:47:13 -!- sleffy has joined. 09:55:08 -!- sleffy has quit (Ping timeout: 240 seconds). 10:28:42 -!- erkin has quit (Quit: Ouch! Got SIGABRT, dying...). 10:51:45 -!- sebbu2 has joined. 10:54:48 -!- sebbu has quit (Ping timeout: 240 seconds). 10:57:58 -!- atslash has joined. 11:01:57 -!- Antoxyde has joined. 11:02:41 -!- atslash has quit (Ping timeout: 248 seconds). 11:07:24 -!- atslash has joined. 11:34:45 -!- boily has joined. 11:46:23 -!- zseri has joined. 11:46:34 -!- atslash has quit (Quit: Leaving). 11:49:21 -!- erkin has joined. 12:18:51 -!- Vorpal has quit (Quit: ZNC - http://znc.sourceforge.net). 12:24:57 -!- newsham has quit (*.net *.split). 12:29:13 -!- boily has quit (Quit: LACTOSE CHICKEN). 12:40:08 -!- LKoen has joined. 13:19:09 -!- j-bot has quit (*.net *.split). 13:19:09 -!- izabera has quit (*.net *.split). 13:19:09 -!- zgrepc has quit (*.net *.split). 13:20:30 -!- zgrepc has joined. 13:20:52 -!- izabera has joined. 13:22:27 -!- mtve has quit (Ping timeout: 260 seconds). 13:24:43 -!- mtve has joined. 13:33:40 -!- LKoen has quit (Remote host closed the connection). 14:13:15 [wiki] [[User:Jordan]] N https://esolangs.org/w/index.php?oldid=52695 * Jordan * (+68) Created page with "My SE account: https://codegolf.stackexchange.com/users/72169/jordan" 14:15:10 -!- hkgit03 has joined. 14:16:47 -!- doesthiswork has joined. 14:24:21 -!- jaboja has joined. 14:39:44 -!- ATMunn has joined. 14:39:44 -!- ATMunn has quit (Changing host). 14:39:44 -!- ATMunn has joined. 14:47:28 -!- sebbu2 has quit (Ping timeout: 240 seconds). 14:48:55 -!- sebbu has joined. 14:49:59 -!- `^_^v has joined. 15:05:00 -!- hkgit03 has quit (Quit: http://www.kiwiirc.com/ - A hand crafted IRC client). 15:14:46 -!- jaboja has quit (Ping timeout: 255 seconds). 15:20:34 -!- newsham has joined. 15:59:28 -!- jaboja has joined. 16:03:13 -!- erkin has quit (Quit: Ouch! Got SIGABRT, dying...). 16:11:58 -!- LKoen has joined. 16:29:37 -!- jaboja has quit (Ping timeout: 248 seconds). 16:34:34 -!- jaboja has joined. 16:42:51 -!- FreeFull has joined. 16:46:44 -!- doesthiswork has quit (Quit: Leaving.). 16:49:30 -!- AnotherTest has joined. 17:04:28 -!- `^_^v has quit (Quit: This computer has gone to sleep). 17:20:09 -!- FreeFull has quit (Quit: Rebooting). 17:20:24 Now I have posted a corrected version of MIXPC, and now there is also some new features, and includes an assembler. 17:20:30 (The assembler is a separate program) 17:22:44 -!- FreeFull has joined. 17:25:07 [wiki] [[MIX (Knuth)]] https://esolangs.org/w/index.php?diff=52696&oldid=52648 * Zzo38 * (+206) 17:37:08 -!- zseri has quit (Quit: Page closed). 17:44:59 -!- augur has joined. 17:46:01 -!- LKoen has quit (Remote host closed the connection). 17:49:02 -!- jaboja has quit (Ping timeout: 260 seconds). 17:55:50 -!- GeekDude has changed nick to MrRobato. 17:56:07 -!- MrRobato has changed nick to MrRoboto. 18:00:15 -!- imode has joined. 18:01:00 -!- `^_^v has joined. 18:06:33 -!- augur has quit (Remote host closed the connection). 18:12:12 -!- jaboja has joined. 18:19:16 -!- AnotherTest has quit (Ping timeout: 255 seconds). 18:22:11 -!- augur has joined. 18:26:30 -!- augur has quit (Ping timeout: 240 seconds). 18:44:21 -!- Phantom_Hoover has joined. 18:48:29 -!- imode has quit (Ping timeout: 246 seconds). 18:48:42 Also is including one example program which is the guess number game. It uses the random number extension and music extension of MIXPC. 18:50:58 -!- augur has joined. 19:10:27 -!- imode has joined. 19:17:13 -!- augur_ has joined. 19:20:23 -!- augur has quit (Ping timeout: 255 seconds). 19:23:09 -!- rodgort` has quit (Quit: Leaving). 19:23:44 -!- copumpkin has quit (Remote host closed the connection). 19:29:47 -!- copumpkin has joined. 19:31:25 -!- rodgort has joined. 19:41:23 -!- hppavilion[1] has joined. 19:46:19 -!- zseri has joined. 20:10:57 -!- `^_^v has quit (Quit: This computer has gone to sleep). 20:17:39 -!- oerjan has joined. 20:26:14 * oerjan has an obvious guess who vanamonde is thinking of in today's girl genius. 20:30:57 There's a character called that in an Arthur C. Clarke novel, The City and the Stars. 20:31:05 (I haven't read the comic in years now.) 20:31:36 yeah the foglios tend to shout out a bit... 20:32:11 also, *gasp* 20:32:29 `5 w 20:32:34 1/2:monads//Monads are just free monad monad monad algebras. \ wat//ኢትዮጵያ ውስጥ የሚሰራ የምግብ አይነት ሲሆን፣ የሚሰራውም ከጤፍ ነው። \ programmer's googol//A programmer's googol is equal to 10^100, or 110 \ help//Help is on the way. We don't know where the way is, though. You might try `help inste 20:32:36 `n 20:32:36 2/2:ad. \ lystrosaur//The lystrosaurs were an ancient genus of evil reptiles who successfully took over the world in the early Triassic. 20:32:42 oerjan, I tend to miss the obvious, what's your guess? 20:33:09 a certain gentleman adventurer. 20:33:20 Oh no! 20:33:25 indeed 20:33:36 Oh no! 20:34:40 he does fit perfectly, also he's in half the other side stories... 20:34:51 Does a gold penny have the same mass as a silver penny? 20:35:23 zzo38: i suspect that both may have varied over time. 20:36:54 hm wait 20:37:12 aren't they too small to be gold or silver? but that may have varied too... 20:38:26 "The gold penny was a medieval English coin with a value of twenty pence." 20:39:13 Bob has 140 pounds worth of money. I am assuming the mass is the same, so that if it is all gold coins then it will weigh 7 pounds. 20:39:47 "Until the reign of King Henry III of England (1216–1272), any need in England for coins worth more than one penny, at the time a silver coin, was met by the use of Byzantine or Arabic gold and silver coins which circulated among merchants and traders." 20:48:21 OK, but still do you know? This is in a GURPS game I play in, the GM said one NPC has 140 pounds worth of money, but apparently in gold (or maybe I misunderstood him), so I assume that the total weight of the money is 7 pounds, and can notify him about it, but for simplicity we could assume the coins have the same weight anyways, even if it isn't historically accurate (if GM agrees), but still I am curious to know if it actually is or not. 20:50:52 -!- jaboja has quit (Ping timeout: 276 seconds). 20:55:26 -!- jaboja has joined. 20:55:35 i've always assumed gold to be more worth than silver per weight. 20:56:11 but maybe it's just denser... 20:56:35 i don't really know, anyway. 20:57:16 also, _reliably_ minted money can be more worth than its base material. 20:58:14 This website prices gold at $41.59/g and silver at $0.55/g 20:58:19 p. close 20:58:24 -!- zseri has quit (Ping timeout: 260 seconds). 20:58:37 p. not at all... 20:58:53 did you miss a digit 20:59:04 No, it's two orders of magnitude difference. 20:59:17 ah 20:59:41 who knows if that was the case in medieval times, though... 20:59:48 Does it have a price for mithril? 21:00:05 (Also which marriage anniversary year is that?) 21:00:32 eleventy, obviously. 21:01:52 -!- copumpkin has quit (Read error: Connection reset by peer). 21:02:02 hm or should it be eleventy-one 21:03:37 -!- zseri has joined. 21:04:36 -!- copumpkin has joined. 21:04:53 copumpkin: Do you like Matt Levine? 21:12:43 -!- Xav_ has joined. 21:13:09 Hello 21:17:39 -!- Xav_ has quit (Ping timeout: 260 seconds). 21:39:02 -!- Bowserinator has joined. 21:39:26 -!- Bowserinator has changed nick to Guest90542. 21:40:46 -!- rdococ has left ("I just realized I don't talk here. I wonder why."). 21:41:01 -!- Guest90542 has changed nick to Bowserinator. 21:41:12 -!- Bowserinator has quit (Changing host). 21:41:12 -!- Bowserinator has joined. 21:43:14 -!- wob_jonas has joined. 21:44:54 " also what is the self-replication example in the lowest possible? in Assembly for example." => an example is probably those very short viruses for early DOS systems that stayed in memory and copied themselves into the disk file of any com or exe program you ran 21:46:34 well, there's the degenerate case, but that's boring 21:47:14 -!- LKoen has joined. 21:51:28 -!- LKoen has quit (Ping timeout: 240 seconds). 21:52:01 `? monad 21:52:02 Monads are just monoids in the category of endofunctors. 21:52:07 `? monads 21:52:08 Monads are just free monad monad monad algebras. 21:56:07 " i've always assumed gold to be more worth than silver per weight." => definitely worth much more than silver. 21:56:43 -!- sleffy has joined. 22:01:21 -!- sleffy has quit (Ping timeout: 248 seconds). 22:02:01 gold is also more amazing and rarer on Earth than silver 22:03:15 who else is up at this ungodly hour. <-- not me hth 22:04:05 @time oerjan 22:04:06 Local time for oerjan is Fri Aug 11 23:04:05 2017 22:04:26 shachaf: not the same hour hth 22:04:28 [wiki] [[Talk:Esoteric Operating System]] https://esolangs.org/w/index.php?diff=52697&oldid=45237 * Xav737 * (+1472) Add a suggestion for a file structure 22:04:39 oerjan: are you saying this hour is godly? 22:04:47 certainly not. 22:06:36 apparently few others were, as now i've finished the logs. 22:06:56 oerjan hungers for logs 22:08:27 What rolls down stairs / Alone or in pairs, / And over your neighbor's dog? 22:08:39 oerjan, how is your neighbour's dog 22:08:42 " No, it's two orders of magnitude difference." => wait, really? I thought the difference was somewhat less than that. wow. 22:08:58 wob_jonas: Going by the prices I quoted above. 22:09:06 yeah, I understadn 22:10:02 and gold is still cheaper than any of its cousins (iridium, platium, osmium, rhenium, tungsten) right? 22:10:08 -!- AnotherTest has joined. 22:10:10 Taneb: i'm not sure they currently have one, so i guess it's silent if it exists. 22:10:41 actually there have been a couple bad days. 22:11:46 -!- zseri has quit (Quit: Page closed). 22:12:23 An intermittent dog 22:12:30 `cat bin/dog 22:12:31 cat: bin/dog: No such file or directory 22:12:33 wait tungsten is a precious metal? 22:12:34 Huh. 22:13:21 oerjan: "precious metal" is defined differently by any two people. I consider it precious because it has the highest melting point among all metals, higher than even rhenium 22:13:25 [wiki] [[AsciiDots]] https://esolangs.org/w/index.php?diff=52698&oldid=52693 * IanO * (+142) /* External Resources */ 22:14:17 -!- AnotherTest has quit (Ping timeout: 246 seconds). 22:15:58 I consider all metals precious, except zinc. 22:16:38 shachaf: huh? don't you mean all metals except iron and maybe cobalt? because that would be sort of a sensible definition 22:16:49 No, iron is precious. 22:16:59 there's way more iron on Earth than ANYTHING ELSE, by mass 22:17:01 I don't think that was meant to be a sensible definition 22:17:13 Who said anything about the Earth? 22:17:21 so every other metal is rare compared to iron 22:17:32 aluminum is extremely precious, just ask louis napoleon 22:17:34 Isn't there more aluminium than iron? 22:17:55 he did say by mass. 22:18:11 By mass. 22:18:51 shachaf: the earth is basically a big ball of iron, with some dirt layer on the surface. the surface may have more aluminum atoms (not in atomic form) than iron, but if you go deeper (which we can't really do because the pressure kills us) it's all iron (and maybe some cobalt) 22:18:55 well, how about all the metallic hydrogen (theoretically) in jupiter? 22:19:11 `? precious 22:19:12 precious? That doesn't ring a bell. ¯\(°​_o)/¯ 22:19:20 Oh, this page is about the crust. 22:19:25 hm already has a ring pun 22:19:39 shachaf: and there's almost no metalic aluminum in the ground, practically all of it is refined by men 22:19:56 which is not surprising because it's that sort of junk semimetal, it doesn't like remaining in metalic form much 22:20:01 Which men? 22:20:08 mankind in general 22:20:25 and mostly in the last few hundred years 22:20:37 before that people didn't know a cheap way to refine it 22:21:34 Tungsten is also not a precious metal. 22:21:43 which is a shame because it could have been tg 22:21:57 huh? 22:22:34 shachaf: i'm afraid stephen got to select its abbreviation hth 22:22:54 `? tungsten 22:22:55 tungsten? ¯\(°​_o)/¯ 22:22:59 `? wolfram 22:23:00 Stephen Wolfram is an esolanger with too much money and power. Taneb invented him. 22:23:28 what does tungsten have to do with cellular automata? 22:23:48 oerjan: it's more like that back when they decided the abbreviations, English wasn't yet the most frequent language used in science, so they use german and latin and french and russian and swedish and whatever names instead. 22:24:17 Well, "tungsten" is a Swedish name. 22:24:22 So they should've used it. 22:24:33 except the swedes don't. 22:24:47 Right, they donated that word to English. 22:25:30 apparently tungsten _is_ used in jewelry. 22:26:37 tonguesten 22:28:05 "Tungsten is unique amongst the elements in that it has been the subject of patent proceedings. In 1928, a US court rejected General Electric's attempt to patent it, overturning U.S. Patent 1,082,933 granted in 1913 to William D. Coolidge." 22:28:43 Taneb: that's only used for piercings hth 22:32:01 Understandable 22:32:57 -!- aaronduino has joined. 22:33:02 oerjan: that sounds strange. I mean, patent trolls have tried to patent basically anything, whether it makes sense or not 22:33:12 how come it's the only element where they did that? 22:33:48 hello 22:33:56 well, after the first one, there's a precedent set 22:34:07 and I bet GE had some role in its discovery 22:34:28 Hi, aaronduino 22:34:33 welp, nope 22:34:34 hi, Tabeb 22:34:38 *Taneb 22:35:18 any people here who do ppcg? 22:35:25 MAYBE 22:35:36 aaronduino: some people used to at least 22:35:40 sometimes I read it 22:35:45 never submitted anything 22:35:52 yeah. 22:36:20 I was thinking of starting, but was wondering how stdin works if your esolang of choice only accepts numbers through stdin 22:36:37 my last submission was July 30 22:37:01 isn't there a thread about acceptable input types 22:37:17 hmmm 22:37:29 yes there is 22:37:31 k 22:37:49 although i'm not sure how it treats something _that_ weird. 22:38:26 yeah. 22:38:43 e.g. the ;# challenges 22:38:59 aaronduino: you might try to ask such policy questions on their chat. 22:39:11 oerjan: What, like INTERCAL? 22:39:16 you need some reputation before you can chat. 22:39:29 shachaf: INTERCAL has binary I/O, it's just awkward. 22:39:36 I think I got 101 from coming from stackoverflow 22:39:39 (101 rep) 22:40:12 oh SO is enough, i don't think the chat cares which SE site you're from 22:40:20 it's a common system. 22:40:25 yep 22:40:30 oerjan: the chat IS partitioned to three parts actually 22:40:37 oh? 22:40:49 oerjan: stack overflow chat, stack exchange meta chat, and everything else 22:40:56 * oerjan doesn't follow the chat much, only logged on for specific occasions. 22:40:56 huh 22:41:11 but the reputation you get from stack overflow might still allow you to chat on the general chat 22:41:19 I think so 22:41:22 I don't know that, because I don't care much about stack overflow 22:41:43 in any case, chat needs very little rep, so you can get it easily even without that 22:42:15 the partitioning is more so that chat moderators are different on the three slices 22:42:25 that makes sense 22:42:25 it's not for excluding people from chatting altogether 22:43:01 of course 22:43:43 aaronduino: i don't think your language is famous enough to get a wikipedia article yet hth 22:43:57 ? 22:44:10 wait a sec 22:44:28 it has a esolang.org 22:44:30 page 22:44:40 (not saying its famous, tho) 22:44:54 someone made a red link to it from wikipedia's esolang page. 22:45:27 Cool! 22:45:40 i am not entirely sure it's even famous enough for a section there, but i'm generally not involving myself in _that_ question. 22:45:40 wow 22:46:40 hmmm. 2602:306:31ab:c4b0:454c:258:f30e:636 22:47:08 I get it. Thx 22:47:37 (running on <8 hrs of sleep total for a week right now) 22:48:03 yeah, it's still too hot 22:48:16 haha 22:48:22 ? 22:48:49 sleeep 22:48:55 I still find it hard to sleep because of the aftereffects of the hot weather, even if it's starting to become somewhat less hot now 22:49:21 ahh 22:49:28 For me its just TV. 22:49:33 until 4 am 22:50:48 oerjan: I just saw that you proved turing-completeness of ///. That really cool! 22:53:02 what? string replacement languages like /// were known to be turing complete for very long ago, before the era of esolangs. Knuth actually mentions one of them early in TAOCP even. 22:53:25 but its still hard to make a specific proof 22:53:33 no it's not 22:54:38 it's specifically easy to compile turing machines to it 22:54:50 wob_jonas: but were they string replacement languages like thue, or like /// ? 22:55:03 * aaronduino realized how much of a noob he is 22:55:40 the hard part with /// is that it has no separation between data and program. 22:55:52 oerjan: uh... let me check what /// does 22:55:55 Oh, yeah 22:56:02 like thue, I think 22:58:06 hmm... in that case /// might be trickier 22:58:55 wob_jonas: you essentially cannot get any true while loop going without quining techniques. 22:59:04 wow 22:59:09 as far as we know. 22:59:27 oerjan: I see 22:59:36 I'm sorry then, I was wrong above 22:59:42 I was thinking of more like thue 22:59:51 APOLOGY ACCEPTED 23:01:10 I'm starting to read more about ///; it's crazy 23:04:51 iirc User:Nthern also has made some impressive /// programs. 23:05:55 cool. what do they do? 23:06:04 -!- jaboja has quit (Remote host closed the connection). 23:06:22 `5 23:06:23 1/2:173) oerjan: What, can girls aim their penises better? \ 185) clue is a language for beauty, not usefulness or ability to run at all ability to run at all is not even close to a design goal, no \ 32) `translatefromto hu en Hogy hogy hogy ami kemeny How hard is that \ 659) [...] `n 23:06:27 2/2:e> So if someone tells you "you're worth your weight in Ethernet", it's likely they think your worth is less than $2k. \ 863) shachaf: contrary to common belief, #esoteric is not really "a channel for crazy people", but has (ostensibly) a topic... is beaky from finland? 23:07:13 https://esolangs.org/wiki/User:Nthern/archive#Thue-to-.2F.2F.2F_translator 23:07:26 i need a Thue-to-Frie translator twh 23:07:51 impressive 23:08:22 * oerjan swats shachaf -----### 23:09:42 oerjan: I'm thinking of proving asciidots' turing-completeness using bct. Any tips? 23:10:12 well i don't know asciidots 23:10:38 idk, it 23:10:48 nvm 23:11:14 its a functional language with a pointer that holds 2 variables 23:11:25 idk, any tips at all would help 23:11:52 (tbh, i don't really know what I'm doing0 23:12:25 the easiest way to prove tc-ness depends a lot on what data structures your language has. 23:12:57 hmmm 23:13:00 k 23:13:03 if you have bignum integers, i recommend fractran or the like. 23:13:24 if you have first class functions, i recommend SKI calculus. 23:13:30 I'll look into those 23:13:35 esp. fractran 23:13:53 -!- jaboja has joined. 23:14:05 wow. fractran is crazy 23:14:18 oerjan: Come on, there were a bunch of great puns you didn't swat me for. 23:14:18 (also the collatz functions, which sometimes fits better to a language than fractran does.) 23:14:21 And now you swat me for this? 23:14:36 I'm disappointed. 23:14:37 shachaf: you probably were too subtle hth 23:17:31 i've gtg. Too much procrastinating today :) 23:17:35 :/ 23:17:40 -!- aaronduino has quit (Quit: Page closed). 23:21:23 -!- doesthiswork has joined. 23:42:22 -!- oerjan has quit (Quit: Nite). 23:55:32 -!- wob_jonas has quit (Quit: http://www.kiwiirc.com/ - A hand crafted IRC client). 2017-08-12: 00:09:50 -!- oerjan has joined. 00:10:10 -!- oerjan has quit (Client Quit). 00:39:32 -!- Phantom_Hoover has quit (Read error: Connection reset by peer). 01:04:57 -!- Antoxyde has quit (Quit: Leaving). 01:17:55 -!- jaboja has quit (Remote host closed the connection). 01:41:19 -!- ATMunn has changed nick to the_moon_in_ksp. 01:44:42 -!- xkapastel has joined. 02:19:59 [wiki] [[Special:Log/newusers]] create * HereToAnnoy * New user account 02:21:06 -!- the_moon_in_ksp has changed nick to ATMunn. 02:24:45 [wiki] [[Esolang:Introduce yourself]] https://esolangs.org/w/index.php?diff=52699&oldid=52692 * HereToAnnoy * (+312) /* Introductions */ 02:25:17 [wiki] [[Esolang:Introduce yourself]] https://esolangs.org/w/index.php?diff=52700&oldid=52699 * HereToAnnoy * (+105) /* Introductions */ 02:27:45 [wiki] [[User:HereToAnnoy]] N https://esolangs.org/w/index.php?oldid=52701 * HereToAnnoy * (+23) Created page with "What should I put here?" 02:35:18 -!- augur_ has quit (Remote host closed the connection). 02:52:11 -!- hppavilion[1] has quit (Ping timeout: 255 seconds). 02:54:48 -!- augur has joined. 02:58:57 -!- augur has quit (Ping timeout: 240 seconds). 03:01:54 -!- ATMunn has quit (Quit: See ya! o/). 03:06:21 -!- hppavilion[1] has joined. 04:03:58 -!- MrRoboto has changed nick to GeekDude. 04:23:45 -!- hppavilion[1] has quit (Ping timeout: 248 seconds). 05:05:45 Is there a faster way of dealing with sign-magnitude on a computer that doesn't use sign-magnitude? 05:06:44 faster than what? 05:07:51 Than always dealing with the sign and magnitude separately (which does work, but is there a better way?) 05:08:56 not sure, what does java do? 05:09:37 I don't know 05:10:00 (Also, I mean specifically for integers; floating-point is already sign-magnitude) 05:10:18 (well, kind of; it is sign-fraction-exponent-magnitude) 05:10:40 why not just do regular two's compliment arithmetic. 05:11:22 Mainly in case you are working with data or programs that use sign-magnitude, such as if you are implementing MIX, which uses sign-magnitude. 05:11:41 oh, never mind about java, not sure why I thought java did weird stuff with ints, maybe I was thinking of floats 05:11:42 oh. 05:11:48 hm. 05:12:03 hasn't been long enough since I've programmed in java 05:12:26 well, it doesn't really stop you from doing regular integer arithmetic. just different wrapping/overflow conditions. 05:12:54 [wiki] [[Assignless]] https://esolangs.org/w/index.php?diff=52702&oldid=52678 * Rdococ * (+17) 05:13:26 Yes, I suppose so. 05:14:13 Although there still may be some other considerations with the sign 05:14:42 such as? 05:15:25 also, I hope you're storing those numbers as native binary and not as a single bool + n-bit integer. 05:16:29 Even so, it is necessary to keep track of negative zero and positive zero 05:16:36 [wiki] [[HI9+]] https://esolangs.org/w/index.php?diff=52703&oldid=51373 * Rdococ * (+141) Arbitrary_effect_at_an_arbitrary_point 05:16:47 [wiki] [[Language list]] https://esolangs.org/w/index.php?diff=52704&oldid=52694 * LyricLy * (+9) /* L */ 05:16:53 [wiki] [[HI9+]] M https://esolangs.org/w/index.php?diff=52705&oldid=52703 * Rdococ * (+1) 05:16:59 true. but that still lies on underflow/overflow conditions. 05:17:31 meaning when a negative zero is added to some positive number, as some positive zero is added to a negative. 05:17:36 I guess. 05:18:47 [wiki] [[Ly]] https://esolangs.org/w/index.php?diff=52706&oldid=52689 * LyricLy * (+110) /* Interpreters */ 05:20:05 [wiki] [[HI9+]] M https://esolangs.org/w/index.php?diff=52707&oldid=52705 * Rdococ * (-9) 05:20:29 [wiki] [[HQ9+]] M https://esolangs.org/w/index.php?diff=52708&oldid=52477 * Rdococ * (+93) 05:20:37 The esolang wiki article about "MIX (Knuth)" describes what happens in this case on MIX, at least. (Other things using sign-magnitude might do differently maybe) 05:21:40 (I don't know if MIXPC is actually doing it correctly; if it is wrong, I will fix it) 05:24:05 (But I think the rule is basically like: If x+y=0 then the result has the same sign as x. For multiplication and division the sign of the result is already unambiguous anyways) 05:25:28 [wiki] [[MIX (Knuth)]] https://esolangs.org/w/index.php?diff=52709&oldid=52696 * Zzo38 * (+3) 05:27:31 [wiki] [[HI9+]] https://esolangs.org/w/index.php?diff=52710&oldid=52707 * Rdococ * (+415) quines 05:28:12 [wiki] [[HI9+]] M https://esolangs.org/w/index.php?diff=52711&oldid=52710 * Rdococ * (+73) 05:29:55 [wiki] [[Talk:HI9+]] M https://esolangs.org/w/index.php?diff=52712&oldid=51381 * Rdococ * (+236) 05:30:05 [wiki] [[Talk:HI9+]] https://esolangs.org/w/index.php?diff=52713&oldid=52712 * Rdococ * (+79) 05:34:38 [wiki] [[HI9+]] https://esolangs.org/w/index.php?diff=52714&oldid=52711 * Rdococ * (+373) more quines 05:48:02 -!- j-bot has joined. 05:58:22 I invented a few new kind of astrological house system, such as "Hemisphere-Null" system, which is similar to the "Null" (or "Aries") system, but the houses are flipped in the southern hemisphere. 06:02:00 Do you like this? 06:52:16 -!- rdococ has joined. 06:53:38 -!- doesthiswork has quit (Quit: Leaving.). 07:01:07 Ugh, why am I so scared to talk here? 07:02:21 I don't know? 07:05:40 `grwp scar 07:05:41 intelligence:Intelligence is a scarce resource that is distributed by the CIA. \ ß:ß is not a beta. It's a "scharfes S", aka s with a scarf. \ the universe:The universe was invented by Taneb as an opposing force to oerjan. Escardó proved that it was indiscreet. 07:06:12 it's a mystery. 07:06:29 sometimes we mock people. 07:08:08 -!- Gregor has quit (Quit: Coyote finally caught me). 07:08:23 I'm still hunting for an original concept. Am I going about this whole esolanging thing wrong? 07:10:14 Depends whether you intend to make only the original one or to just make it anyways regardless of that, I suppose. (Or, do something in between.) 07:12:18 rdococ: "1) Watch everything, read everything, and especially read outside your subject -- you should be importing, not recycling." from https://www.lspace.org/books/apf/words-from-the-master.html seems relevant 07:13:13 Yes, that too 07:13:21 in almost all cases, inspiration is taking a couple of ideas and combining them in a new way... which means you need to learn about the existing ideas first. 07:23:06 rdococ: don't fear looking stupid. 07:23:30 I know I look stupid every time I type something or share some weird thing I wrote. 07:23:45 imode: When I look back on what past me has added to the wiki, I faceplant. 07:24:04 meh. it's ideas. 07:24:26 some may like them, some may not. point is they're yours and they reflect your preferences. 07:24:32 Well... whether it works out or not, I have an idea in my head right now (if you want to hear about it). 07:24:49 sure, it's late and I have some booze. hit me. 07:25:56 K. The idea is that there would be no subroutines; only coroutines. Subroutines would be simulated using a while (true) loop and a call to yield() at the end of each iteration of that loop. 07:26:25 oh oh oh. I have done this. 07:26:54 Rather than calling a subroutine, you would pass parameters to and resume the coroutine. 07:27:56 imode: so, what do you think? 07:28:41 it's an interesting concept. I experimented with it for something like a tuplespace. 07:30:34 the gist was you'd have a large what was basically an assembly program, yet execution was based on coroutines, so that segments of the program would fall through to other segments in sequence. each segment would search for matching tuples in the tuplespace and work on them if it found them, else it would drop to the next segment, in an infinite loop. "yield" was essentially putting tuples back into the 07:30:34 tuplespace. 07:31:02 in this way it could be seen as multiple agents working on a shared blackboard. it works well, but only if you have a decent model of execution backing it. 07:31:16 I have some python code if you wanna see it. 07:31:37 I'd like to see it. 07:32:19 -!- Gregor has joined. 07:33:02 https://ptpb.pw/urGZ/python 07:33:32 I treat all my python files as sort of scratch files. they are not pretty. 07:33:35 but this is turing complete. 07:34:02 it is not complete in documentation, though. if you scroll down to the bottom you can see some code. 07:34:26 it's seen as a linear sequence of instructions but the way the matches are set up, you either jump back to a previous statement or fall through. 07:34:39 it's kind of like... a declarative assembly language, if you wanna read it from a moving car. 07:38:06 Eh... okay... 07:38:38 the point is it worked pretty well. the yields were implicit. 07:38:57 meaning you didn't have to do the windows 3.1 thing of giving CPU time to something. 07:41:13 one of the advantages of that method is that you don't need a stack to do anything. functions that you define, or subroutines as you call them, are _always running_, searching for work to do and where to send the results. 07:42:47 it'd be interesting to see an esolang that utilized that model. 07:46:11 I barely understand the model myself. 07:47:23 think of it like this. you have chunks of code, whatever they may be, that represent some functionality of your program. say for example a square function, or something that computes raising a number to a power. 07:48:07 so one chunk may be one function, one chunk may be another. instead of having a single entry point to your program, and a cursor racing back and forth between subroutine calls and the call stack... 07:48:43 you have no call stack. the cursor zips linearly around. you can still jump to instructions, sure, but you eventually have to fall through to other chunks of code. what you do differently is you have a sort of mailbox/work order system. 07:49:16 so you say "I am from function Foo, I am requesting a result from Bar with these parameters. I'm going to send it to Bar's mailbox. Please post the result with my name on it afterwards, so I can pick it up." 07:49:42 then you yield. if no other functions have work, they simply yield. 07:49:46 O_o 07:50:13 Umm... okay? 07:50:16 but Bar will go search in its mailbox and say "oh wow I have a letter. oh it's from Foo. cool I'm going to post the result of me mangling this value or whatever back in his mailbox." 07:50:34 and eventually execution will trace back to Foo, he'll receive the work. 07:51:24 Again, I'm not sure... 07:53:03 it's kind of like standard coroutines only, like I said, yields are implicit, as are entry points. a segment can pause and resume because it can save its work in its own mailbox, and other segments can send stuff to its mailbox so it can act as a function/subroutine. 07:53:21 sounds a lot like the actor model erlang has, actually. 07:53:31 with a blackboard system attached. 07:54:21 To me, it sounds like it could be an object-oriented system. 07:54:32 As in, objects sending messages to eachother. 07:54:45 certainly can! work at your chosen level of abstraction. :) 07:56:21 in fact, I was implementing this for a game, so I'd be writing game objects in that style. 07:56:32 so you really aren't that far off the mark. 07:56:58 I'd also like an opinion on the concept of http://esolangs.org/wiki/Assignless - at the moment, its syntax is borrowed from C/C++ but it has no actual assignment operation. 07:57:32 so.. like a functional language. 07:57:51 I guess, but it is imperative......is it? 07:57:57 Yeah, it's imperative. 07:58:13 in the fact that you don't do mutable assignment. 07:58:44 you just declare values, and code that acts on values. they don't need names attached to them. 07:59:12 I guess... 07:59:50 why the dots? 08:00:24 I tend to be very uncertain. 08:01:01 uncertainty is the first step towards certainty. 08:01:18 Odd, "#input"? I don't remember what that # was for. 08:01:28 [wiki] [[Assignless]] https://esolangs.org/w/index.php?diff=52715&oldid=52702 * Rdococ * (-1) 08:01:51 Ohh, I see now. 08:01:54 judging from the syntax, a comment. 08:02:01 (forall a b. (Dim a, Dim b) => Layer a b -> v a x -> v b x) -> v a x -> Network a b -> v a x 08:02:15 That's the most frustratingly slightly awkward type signature I've written in a while 08:02:16 neural nets in haskell? :P 08:02:28 Yeah! That's what I'm trying to do 08:02:32 sweet. 08:02:45 imode: # is used for comments, yes, but I was talking about the line "if (step < #input) {". 08:03:01 rdococ: yeah, I was wondering if you meant to comment it out or something. 08:03:34 imode: I guess so, but "if (step < " doesn't seem to be a very useful line to me. 08:03:41 lol. 08:04:24 it's a bit of a cliffhanger 08:04:36 imode, I work for a company that writes neural net compilers and I want to get a feel for how it all works 08:05:01 Taneb: huh. interesting. done anything with integer-only NNs? 08:06:06 imode, I don't think so, I'm afraid 08:06:24 But there's no real reason why we couldn't 08:06:49 they're mainly intended for systems with small memory footprints but for large-scale ops they couldn't hurt. 08:07:09 I guess it fits, but we mostly use half-width floats 08:07:39 hehe. the main strength was also the simplicity in implementation. no need to mess with floating point numbers for devices that lacked an FPU. :P 08:08:09 From the sound of it, they're not out of our remit 08:08:27 https://cdn.intechopen.com/pdfs-wm/9274.pdf some literature if you're morbidly curious. 08:08:37 interesting that you choose haskell though. what brought that on? 08:09:02 I don't know, I just joined 08:09:10 Oh, you mean me personally? 08:09:15 yuh! 08:09:18 I like to use Haskell as much as I can 08:09:30 Joined this company because I heard that they use Haskell 08:09:41 It's the language I know best 08:09:54 -!- erkin has joined. 08:09:59 nice. I don't think I've ever seen a NN libarary for haskell... 08:10:15 no time like the present. though I agree, that is an awkward type signature. :P 08:10:28 It looks like there's a few on Hackage 08:10:37 @type foldr 08:10:39 Foldable t => (a -> b -> b) -> b -> t a -> b 08:10:45 That's what the type signature wants to be 08:11:55 I'm trying to make a type-safe-as-possible feed forward network 08:12:49 It's going to be a fair bit awkward but I'm doing this for fun mostly 08:13:25 's all that matters in the end. 08:14:15 -!- xkapastel has quit (Quit: Connection closed for inactivity). 08:15:05 feedForward sigmoid = foldNetwork (\l i -> sigmoid <$> weights l !* i - biases l) 08:15:10 I love how neat that is 08:16:14 damn. 08:31:16 Now I've defined an analogous function to mapAccumL, I'm going to try and figure out backpropogation 08:52:20 -!- ski has joined. 08:58:30 -!- g0d355__ has joined. 09:13:23 -!- btiffin has joined. 09:23:06 -!- augur has joined. 09:36:39 Would it be a good idea to use "function" to refer to functions that can't form closures, and "closure" to refer to those that can? 09:46:45 -!- zseri has joined. 09:49:03 -!- augur has quit (Remote host closed the connection). 09:52:55 -!- imode has quit (Ping timeout: 246 seconds). 09:58:24 -!- imode has joined. 10:11:00 imode: One other idea I had was different flavours of function: @funcs inherit their scope from their caller, rather than their creator (that is, no closures), &funcs have /no/ scope of their own - all variables they define can be accessible from after the function is called, and ^funcs force their caller to return when they return. 10:11:19 They would be used in defining custom control structures. 10:16:30 -!- ^v has quit (Ping timeout: 240 seconds). 10:17:50 -!- ^v has joined. 10:19:01 -!- augur has joined. 10:23:20 -!- augur has quit (Ping timeout: 246 seconds). 10:25:27 interesting concept, but alas it is far too late for me to even consider the ramifications. 10:25:48 head go on pillow now. sweet dreams. 10:30:24 -!- imode has quit (Ping timeout: 258 seconds). 11:08:40 -!- Phantom_Hoover has joined. 11:18:21 -!- wob_jonas has joined. 11:18:44 I am cutting the book from the cover right now. And AAAAAAA IT HURTS ME INSIDE SO MUCH even though I know it's the right thing to do rationally. 11:26:38 -!- jaboja has joined. 11:28:51 -!- Antoxyde has joined. 11:36:35 -!- wob_jonas has quit (Quit: http://www.kiwiirc.com/ - A hand crafted IRC client). 11:45:11 -!- LKoen has joined. 11:49:33 -!- btiffin has left. 12:14:16 -!- FreeFull has quit. 12:23:53 -!- LKoen has quit (Quit: “It’s only logical. First you learn to talk, then you learn to think. Too bad it’s not the other way round.”). 13:04:00 -!- ybden has quit (Read error: Connection reset by peer). 13:05:05 -!- ybden has joined. 13:25:03 -!- jaboja has quit (Ping timeout: 240 seconds). 14:00:25 -!- doesthiswork has joined. 14:09:57 -!- jaboja has joined. 14:13:20 -!- HTTP_____GK1wmSU has joined. 14:13:36 -!- HTTP_____GK1wmSU has left. 14:28:05 -!- jaboja has quit (Ping timeout: 240 seconds). 14:30:50 -!- ATMunn has joined. 14:32:21 -!- jaboja has joined. 15:01:42 -!- xkapastel has joined. 15:09:50 [wiki] [[Talk:Assignless]] N https://esolangs.org/w/index.php?oldid=52716 * Zseri * (+154) Created page with "Assignless looks like a more functional version of C. Is it (pure) functional? ~~~~" 15:27:21 -!- boily has joined. 15:28:51 -!- Phantom_Hoover has quit (Read error: Connection reset by peer). 15:49:05 `5 w 15:49:10 1/2:numbers//Numbers: 0, 848, 1344, 1696, 1969, 2192, _, 2544, 2688, 2817, _, 3040, _, _, 3313, 3392, ... \ `whoops//`whoops is a repluralizer. \ qdb//qdb is used like: `quote; `quote regexp; `quote id; `addquote ...; `delquote id; `pastequotes regexp; `pastenquotes [n]; see also quoteformat \ sleep//Sleep is for the weak. \ ping//Ping is a Peking 15:49:12 `n 15:49:13 2/2:Duck H4XX0R who amuses himself by making people's IRC connections timeout. 15:49:44 `quote some.*thing 15:49:46 48) both of you, quit it with the f-bombs. kaelis: what's the matter? something censoring stuff you're interested in? \ 73) Making a small shrine to Lawlabee in my basement is something I should get around to at some point. \ 96) AnMaster: to any airbus plane. 3 passengers sadly died the most awesome thing e 16:18:51 [wiki] [[User:HereToAnnoy]] https://esolangs.org/w/index.php?diff=52717&oldid=52701 * HereToAnnoy * (+2) 16:32:36 -!- boily has quit (Quit: KERNAL CHICKEN). 16:33:27 [wiki] [[Assignless]] https://esolangs.org/w/index.php?diff=52718&oldid=52715 * Zseri * (-26) remove unneeded returns 16:39:37 [wiki] [[Assignless]] https://esolangs.org/w/index.php?diff=52719&oldid=52718 * Zseri * (-44) remove semicolons after braces 16:43:03 -!- ATMunn has quit (Remote host closed the connection). 16:45:37 -!- ATMunn has joined. 16:46:28 @metar eddf 16:46:28 EDDF 121520Z 21009KT 9999 -RA FEW010 SCT020 BKN026 17/14 Q1018 NOSIG 16:46:49 seems plausible. 16:46:52 @metar lowi 16:46:52 LOWI 121520Z 08004KT 040V120 9999 FEW025 BKN075 16/11 Q1022 NOSIG 17:05:44 -!- augur has joined. 17:10:02 -!- augur has quit (Ping timeout: 246 seconds). 17:21:18 -!- FreeFull has joined. 17:27:01 -!- boily has joined. 17:31:19 -!- erkin has quit (Quit: Ouch! Got SIGABRT, dying...). 17:37:18 -!- copumpkin has quit (Ping timeout: 240 seconds). 17:38:18 [wiki] [[Ans]] M https://esolangs.org/w/index.php?diff=52720&oldid=52418 * Zseri * (+1) fix 'dead link' note 18:03:56 -!- jaboja has quit (Ping timeout: 246 seconds). 18:26:18 -!- imode has joined. 18:31:37 -!- AnotherTest has joined. 18:54:19 -!- copumpkin has joined. 19:03:04 -!- moony has joined. 19:03:22 Just trying to look for a quick solution, how do you guys limit UMLbox's disk space on HackEgo? 19:17:02 -!- jaboja has joined. 19:28:28 I don't think we have limits on total disk space, though we do set ulimit -f 10240 (i.e., RLIMIT_FSIZE of 10 megs) to limit the maximum size of created files. 19:29:56 If you wanted a hard upper bound, Linux does have filesystem quotas, or you could just have the root on a filesystem of limited size. The failure mode of that might not be terribly great if exceeded, though. 19:34:11 fizzie, mk. im working with a box i cant change the kernel or software on, so ulimit will have to do for now 19:34:57 (well i can change software, root, but cant edit disk to make a new limited partition even if i wanted to) 19:37:24 You can make a file you loop-mount as a block device. Either inside or outside the UML. 19:37:52 i never thought of that 19:38:22 -!- Sgeo has quit (Ping timeout: 260 seconds). 19:38:27 But, as i dont need it to be permanant, i could probably use a tmpfs 19:40:27 -!- augur has joined. 19:45:47 -!- wob_jonas has joined. 19:47:24 Maybe other elements aren't patented because the guys who patented tungsten has also patented the method of patent trolling by patenting chemical elements and natural mineral resources, and they're lashing out on other patents of elements using that. 19:49:16 why even allow patenting something that is part of everyday life that we cant help? :V 19:49:31 because sooner or later someone is gonna patent air and make people pay fees to breath 19:51:13 @metar CYQB 19:51:13 CYQB 121800Z 05006KT 040V110 25SM FEW010 FEW014 BKN031 BKN070 21/17 A2982 RMK SF1SC2SC4AC1 SF TR TCU EMBD SLP101 DENSITY ALT 1100FT 19:51:57 " Is there a faster way of dealing with sign-magnitude on a computer that doesn't use sign-magnitude?" => I'm not sure. There's probably not too much to gain over keeping the sign and magnitude separate if you do have to keep track of the sign of zeros. There might be some tricks, so you could check Hacker's Delight and Knuth vol 4 for ideas 19:51:58 . 19:53:21 zzo38: keeping the sign and magnitude separately definitely helps with at least MIX memory words, which are often accessed as partial fields 19:54:05 wob_jonas: Yes, and I have certainly thought of that 19:54:25 Which is one reason why I had decided to keep them separately 19:56:55 for some temporary values, you can use different formats of course, such as how you already do with addresses 19:59:26 Yes, MIXPC stores the address as a plain number instead of MIX bytes, but still keeps the sign separately. However, an implementation that supports only binary MIX could store all five fields in a single 30-bit value, for example if implementing MIX on MMIX. 20:01:47 -!- wob_jonas has quit (Quit: http://www.kiwiirc.com/ - A hand crafted IRC client). 20:01:50 Also, the MIXASM program included with MIXPC stores MIX word values internally as the sign and five fields in decimal, together with another number whose bits specify how the fields are divided; if a "BASE 100" command is omitted in the input file, it uses that data to output a deck that is independent of byte size. 20:10:50 -!- wob_jonas has joined. 20:12:07 -!- wob_jonas has quit (Client Quit). 20:12:41 -!- wob_jonas has joined. 20:12:57 Hello 20:13:23 I think I may have posted some message while you are not on temporarily 20:13:48 (But of course it is commonly what is happen on the IRC anyways, I think) 20:14:34 zzo38: in particular, you can't easily store mix words as doubles, because the IEEE 754 rules handle signed zeros differently than the MIX addition. 20:15:15 also extracting fields from such a representation would be very difficult 20:15:25 wob_jonas: Yes, I can see 20:22:21 -!- D33P-B00K has joined. 20:24:25 -!- D33P-B00K has left. 20:25:41 At least, on MMIX, it look like bitwise complement by the sign bit (if the number is a 32-bit number rather than a 64-bit number) by MXOR 20:26:00 (I don't know if it is help though, or what kinds of programs it might help with if at all anyways) 20:32:21 -!- oerjan has joined. 20:39:59 -!- wob_jonas has quit (Quit: http://www.kiwiirc.com/ - A hand crafted IRC client). 20:43:20 -!- wob_jonas has joined. 20:45:03 fizzie, just one last question: Which kernel do you use for umlbox? 20:53:25 moony: I don't really maintain the bot. The test installation I have locally uses linux-3.7.10. 20:53:46 The one on HackEgo seems to be 3.13.0. 20:54:54 mk 21:04:04 -!- doesthiswork has quit (Quit: Leaving.). 21:05:19 Do you know that the latest version of MIXPC also has a new I/O unit 36 which is the television (in addition to fixing several mistakes, and adding the feature to set a breakpoint)? 21:11:21 zzo38: can't the teletype output already be connected to a CRT? 21:11:33 I mean, the computer itself doesn't have to know the difference 21:12:53 nor do programs have to know the difference much, unless the CRT displays less than 70 characters per line 21:12:58 -!- Sgeo has joined. 21:14:06 Of course it can be already connected to a CRT, although unit 36 is for APA mode rather than text. 21:14:36 what is APA mode? 21:14:40 (You can physically display them on the same screen if you want to) 21:14:59 wob_jonas: All-points-addressable. 21:15:23 (Although output to unit 36 will replace the entire picture at once with the contents in memory starting at the specified address.) 21:15:59 what? do you mean a pixel-based full screen frame buffer? that would have more memory than a MIX computer, it's totally unrealistic for that era. 21:16:30 The resolution is very low; only 80x40 21:17:36 huh... that's not really APA mode, that's more like high-resolution text mode 21:17:40 but ok 21:18:17 I thought real graphics starts at over 128 pixels width 21:18:54 Yes, and it is actually implemented in MIXPC using text mode, although each pixel in the 80x40 area is limited to being either on or off (or even different intensities, up to the size of a MIX byte, although MIXPC only implements on/off) 21:19:00 real graphics? 21:19:47 ooooh. as in real pixel manipulations rather than textmode. 21:21:57 ok, I guess that's not really true. there is one cheap graphing calculator, the TI-80, that has only a 64x48 pixel display 21:22:46 -!- dingbat has joined. 21:23:08 yeah, there's a lot of small displays that allow per-pixel manipulation. 21:23:18 but that's unusually low even for an early graphic calculator 21:23:39 hell even an 8-column lcd has per-pixel manipulation. 21:25:23 Casio fx-6300G may be an even smaller example 21:25:35 EDSAC (which predates MIX) has a graphical display too, although with a lower resolution. 21:26:16 -!- Sgeo_ has joined. 21:27:03 -!- Sgeo has quit (Ping timeout: 258 seconds). 21:27:40 and sure, I have plotted functions on a programmable calculator with the 14x3 text characters, so you only see three values at a time and have to watch as the curve scrolls through and you need a VERY active imagination, but I don't call that "all pixels addressable" or anything close 21:29:04 OK, then 21:33:26 -!- PinealGlandOptic has quit (Quit: leaving). 21:35:45 The assembler I wrote for MIX is not quite the same as MIXAL, such as it has no compile-time multiplication/division, and omits a few other things too, but does have a few new commands such as FILL and PUNCH. 21:36:21 (PUNCH is used for appending additional data that will be loaded at runtime, rather than in the loader routine.) 21:37:56 wob_jonas: Do you like my way of fitting the loader program onto one card instead of needing two cards? 21:43:05 The same restriction to which characters can be punched still holds. 21:43:20 (I actually made two loader programs; one for specific byte sizes and one for programs independent of byte size.) 21:45:25 -!- Sgeo__ has joined. 21:45:27 For the one for specific byte sizes, the rest of the program still takes (approxmiately) the same number of cards, although the format of the cards is different; in order to handle negative numbers, the numbers are stored "biased"; the first five columns store the address and the last five columns must be blank; multiple words on one card are on addresses skipped by 2 instead of by 1; the transfer card is different (it overwrites the loading routin 21:47:14 -!- Sgeo_ has quit (Ping timeout: 246 seconds). 21:50:16 The assembler also tries to reduce the number of holes to be punched, so that it will use spaces instead of zeros where possible. 22:24:20 -!- ais523 has joined. 22:25:00 -!- zseri has quit (Ping timeout: 260 seconds). 22:25:29 zzo38: I don't much care if it's one card or two card. the loader format already isn't trying to compress the program much, so one extra card doesn't hurt anyone. 22:26:11 OK, although I still decided to do it with just one card anyways, mainly just because I want to do 22:26:23 sure 22:31:05 However, this one card program may be faster (although I have not actually tested the speed), and needs to use only 31 words of memory while loading. 22:31:59 (Or maybe it isn't faster; I don't know) 22:34:42 home sweet home 22:36:34 zzo38: isn't the speed of loading mostly limited by the speed of the card reader though? 22:36:35 -!- augur has quit (Remote host closed the connection). 22:40:33 -!- Guest13399 has joined. 22:53:22 wob_jonas: Yes, I suppose so 22:54:04 -!- Guest13399 has quit (Quit: Leaving...). 22:54:26 -!- jaboja has quit (Ping timeout: 246 seconds). 22:58:02 I don't actually know how fast is the card reader anyways, although it may be implementation-dependent. 22:58:54 it is implementation-dependent 22:59:00 but slow enough in any case 22:59:35 Anyways my version does not need any special logic for the transfer card, and since I have returned the book to the library I cannot compare the method used for loading signed numbers 23:01:27 -!- ais523 has quit. 23:01:36 -!- ais523 has joined. 23:02:58 -!- doesthiswork has joined. 23:06:47 A more efficient encoding for the independent-byte-size loader could be made though; currently each number needs one card, which seem too much 23:07:44 The speific-byte-size loader though is already efficient. 23:13:30 -!- AnotherTest has quit (Ping timeout: 240 seconds). 23:19:26 You're saying umlbox doesnt provide init :v `Kernel panic - not syncing: No init found. Try passing init= option to kernel. See Linux Documentation/init.txt for guidance.` 23:20:58 It does provide an init. 23:21:21 It's right there in the repository, init.c. 23:22:56 The Makefile should put it in the umlbox-initrd.gz, and the umlbox script gives that as an initrd argument to the UML kernel. 23:23:09 Support for "BASE 64" should also be added into this assembler; currently it only support 100 and independent. 23:25:05 zzo38: or make it support any base from 64 to 100 inclusive 23:25:26 for ternary or more unusual machines 23:25:29 Yes, it ought to, you are right. 23:25:48 huh, it does contain init... Why is it not executing it? 23:25:48 but yes, 64 and 100 cover most of the practical cases 23:25:55 (MIXPC already does, although MIXASM currently doesn't.) 23:26:55 moony: Maybe try passing -v to umlbox and see if all the paths in the command line it runs seem to be right. 23:27:27 In any case you could use the independent mode if you really need to, although it would be better to support any base from 64 to 100 anyways, in case you do not want to use the independent mode. 23:27:36 they all look good. here's the output of a test: https://hastebin.com/anobevubum.pas 23:29:39 -!- oerjan has quit (Quit: Nite). 23:29:53 moony: Odd. Does zcat /usr/bin/../lib/umlbox/umlbox-initrd.gz | cpio -t say "init"? 23:30:25 yup 23:34:15 zzo38: you could even have a base 256 machine. it's not quite standard according to the book, but the only change you really need is extending the CHAR instruction with an extended encoding format for large numbers and add a new NUME instruction that decodes that format 23:35:16 -!- wob_jonas has quit (Quit: http://www.kiwiirc.com/ - A hand crafted IRC client). 23:35:22 fizzie, i think its another case of the linux kernel being magic :V 23:35:32 -!- wob_jonas has joined. 23:35:37 it's still possible to encode a word into a word a word into ten punchable bytes easily 23:35:48 OK, it is another idea, although standard MIX programs may assume that the base is 64 to 100 and that it isn't larger than 100. 23:36:04 yes, they may assume that 23:36:22 moony: I don't have any good ideas, since it's not really saying much by the way of useful errors. Though I guess "Failed to execute /init" need not really mean it's missing, could be something else as well. 23:36:38 i wish the kernel would tell me why :V 23:36:51 So this new way is not really MIX, it is "nearly MIX", I suppose. (Still, it can be a possible variant anyways) 23:36:51 -!- augur has joined. 23:36:59 yes, it's a variant 23:37:46 -!- copumpkin has quit (Ping timeout: 258 seconds). 23:37:56 moony: Heh, well, looks like that error in a more current kernel (4.10) has changed to "Failed to execute %s (error %d)\n", so maybe someone else wished that as well. 23:38:56 -!- augur has quit (Remote host closed the connection). 23:39:37 https://github.com/torvalds/linux/commit/ba24762bd "make init failures more explicit" 23:40:27 hmm 23:40:38 i'll try(tm) to see if it'll work with a recent kernel 23:41:03 If I'm reading github right, that commit made it to 3.13, which is what we've got on HackEgo. 23:41:16 So that might be a reasonable version to try. 23:41:38 I remember running into problems when I tried a 4.x series one when trying to set up my local test environment. 23:42:33 -!- augur has joined. 23:43:13 You might also want to verify ("file init", "file umlbox-linux") your both executables are for the same architecture. 23:43:51 (Instead of, say, x86 and x86-64.) 23:47:01 fizzie, that was exactly the problem :V kernel 32bit init 64bit 23:47:03 23:47:17 -!- augur has quit (Ping timeout: 246 seconds). 23:49:04 Maybe I should've said that first, then. :) 23:50:26 -!- wob_jonas has quit (Quit: http://www.kiwiirc.com/ - A hand crafted IRC client). 23:51:44 melted blue stilton on a burger is the best thing in the world. 23:55:29 fizzie does umlbox not work with 64-bit kernels for some reason, or is it just being silly and enforcing the kernel be 32bit? 23:55:57 It should work with 64-bit kernels just fine. 23:56:03 I use it with one. 23:56:20 init: ELF 64-bit LSB executable, x86-64 -- umlbox-linux: ELF 64-bit LSB executable, x86-64. 23:56:27 Just as long as you have both the same. 2017-08-13: 00:04:04 well the build process seems to insist on making the kernel 32bit but everything else 64bit 00:07:49 I don't know how you specify the host architecture for the kernel build, and I don't have any notes on how I built my test setup. 00:08:44 oh i figured it out. SUBARCH=x86_64 00:08:54 I'm pretty sure I just did "make ARCH=um", and got a 64-bit executable out. 00:09:05 fizzie, for me it insists on 32bit on a 64bit box :P 00:11:31 Looks like that has quasi-recently changed as well. 00:15:20 From arch/x86/um/Makefile, it looks more like it depends on if CONFIG_X86_32 is set or not. 00:15:57 Well, I'unno. Maybe that's indirectly from SUBARCH. 00:24:29 fizzie, thanks for the help. Works now :D 00:33:24 -!- augur has joined. 00:50:41 -!- copumpkin has joined. 01:23:50 -!- copumpkin has quit (Ping timeout: 240 seconds). 01:33:07 -!- augur has quit (Read error: Connection reset by peer). 01:36:32 -!- augur has joined. 01:47:25 -!- MrBusiness has quit (Read error: Connection reset by peer). 01:48:09 -!- MrBusiness has joined. 01:58:47 -!- augur has quit (Remote host closed the connection). 02:02:17 -!- augur_ has joined. 02:06:44 -!- augur_ has quit (Ping timeout: 255 seconds). 02:23:44 -!- copumpkin has joined. 02:24:05 -!- copumpkin has quit (Remote host closed the connection). 02:31:25 -!- copumpkin has joined. 02:38:52 -!- jaboja has joined. 02:47:54 @metar CYQB 02:47:54 CYQB 130127Z 06003KT 15SM TS FEW007 SCT030CB BKN075 18/16 A2973 RMK SF1CB4AC3 SF TR LTGCG SW OCNL -SHRA SLP070 DENSITY ALT 900FT 03:03:47 -!- Antoxyde has quit (Remote host closed the connection). 03:11:21 -!- ATMunn has quit (Quit: See ya! o/). 03:13:10 -!- jaboja has quit (Read error: Connection reset by peer). 03:24:41 [wiki] [[User:HereToAnnoy]] https://esolangs.org/w/index.php?diff=52721&oldid=52717 * HereToAnnoy * (+69) 03:29:53 -!- boily has quit (Quit: ANACHRONISTIC CHICKEN). 03:37:15 -!- btiffin has joined. 03:44:37 -!- joast has quit (Ping timeout: 246 seconds). 04:12:58 Concept: Programming language which forces CPS on all programs written in it. 04:15:12 Do you have some idea how that might be done? 04:16:38 Well, I was planning on attempting to combine CPS with coroutines, rather than subroutines. 04:17:20 Then again, there probably wouldn't be much of a difference anyway. 04:17:48 Anyway, a possible method of forcing CPS would be to halt the program on a function return. 04:23:13 -!- joast has joined. 04:42:29 fizzie, yes, im bugging you again, but how is hackego's env set up? -B is obviously unsecure (i checked) 04:42:47 wait.. oh dev files dont translate outwards do they? 04:50:17 Is there any hardware implementation of MIX (including punch cards and that stuff)? 04:53:33 rdococ: I've been working on one of those 04:53:41 I'm not happy with the details but they're details unrelated to CPS 04:54:01 if you're interested in just the CPS stuff, I can write up what I have so far (but not tonight) 04:54:13 Write up...? 04:54:34 article on the wiki 04:55:05 Okay... I guess...? 04:55:52 well, you said you were interested in a language which forces CPS 04:56:06 so I could write an article on my language that does that, even though it doesn't do other things I wanted it to 04:58:32 I was planning on creating a language which forces CPS, but I don't want you to write an article on it if you don't want to. 04:58:47 Anyway, what other things do you want it to do? 04:59:24 I wanted it to naturally have efficient (eigenratio 1) self-interpreters 04:59:37 also a few syntax requirements but those are easy 05:00:05 (in particular, a syntax that makes self-interpreters as simple as possible to write) 05:04:55 sooner or later someone is gonna patent air and make people pay fees to breath — http://theineptowl.com/2013/02/07/businessman-sells-canned-air-china-cocacola-pepsi-nestle-vie-patent/ 05:06:26 What is "eigenratio"? 05:06:55 (ok, according to real news sites, there wasn't actually any patent being sold) 05:07:50 (that is, they do not mention patent rights anywhere) 05:10:00 -!- doesthiswork has quit (Quit: Leaving.). 05:10:45 -!- FireFly has quit (Quit: Goodbye). 05:12:02 zzo38: you can run a self-interpreter on itself, and then run a self-interpreter on that, etc., to make a chain of self-interpreters; the eigenratio is the limit of the ratio between the performance of a self-interpreter stack of size n and a self-interpreter stack of size n+1 05:12:14 -!- j-bot has quit (Read error: Connection reset by peer). 05:12:38 i.e. it measures how much slower a language is interpreted compared to running natively 05:13:05 OK 05:15:15 What is the measure of the performance going to be? MMIX has two kind of time units ("oops" and "mems"), for example. Some programming languages don't specify any kind of timing. Does it even matter? 05:17:31 `cat bin/` 05:17:32 ​#!/bin/bash \ cmd="${1-quote}" \ TIMEFORMAT="real: %lR, user: %lU, sys: %lS" \ shopt -s extglob globstar \ eval -- "$cmd" | rnooodl 05:36:38 -!- FireFly has joined. 05:37:20 [wiki] [[Arrows]] N https://esolangs.org/w/index.php?oldid=52722 * HereToAnnoy * (+193) Created page with "Arrows is a W.I.P Esolang by User:HereToAnnoy that only accepts UTF8/Unicode arrows. A list of accepted arrows can be found `whoami 05:37:56 whoami: cannot find name for user ID 5000 05:37:58 `whoami 05:37:58 whoami: cannot find name for user ID 5000 05:38:02 hmm 05:38:40 [wiki] [[Arrows]] https://esolangs.org/w/index.php?diff=52723&oldid=52722 * HereToAnnoy * (-16) 05:38:53 [wiki] [[Arrows]] https://esolangs.org/w/index.php?diff=52724&oldid=52723 * HereToAnnoy * (+1) 05:39:10 [wiki] [[Arrows]] M https://esolangs.org/w/index.php?diff=52725&oldid=52724 * HereToAnnoy * (+3) 05:41:42 [wiki] [[Arrows]] https://esolangs.org/w/index.php?diff=52726&oldid=52725 * HereToAnnoy * (+134) 05:43:19 [wiki] [[MIX (Knuth)]] https://esolangs.org/w/index.php?diff=52727&oldid=52709 * Zzo38 * (+607) 05:43:52 [wiki] [[Arrows]] https://esolangs.org/w/index.php?diff=52728&oldid=52726 * HereToAnnoy * (+16) 05:45:44 [wiki] [[User:HereToAnnoy]] https://esolangs.org/w/index.php?diff=52729&oldid=52721 * HereToAnnoy * (-9) 06:15:59 -!- ais523 has quit. 06:16:01 -!- btiffin has quit (Remote host closed the connection). 06:31:17 -!- xkapastel has quit (Quit: Connection closed for inactivity). 06:46:25 -!- doesthiswork has joined. 07:00:20 -!- augur has joined. 07:02:38 In a CPS environment, would it be best to have functions that take in the continuation as their first, or last, argument? 07:04:52 -!- augur has quit (Ping timeout: 276 seconds). 07:09:00 last, if you want partial application 07:10:32 -!- augur has joined. 07:19:49 https://repl.it/KHrj welp. serializing stuff works. 07:20:25 very happy about that. 07:20:58 -!- augur has quit (Remote host closed the connection). 07:22:25 -!- g0d355__ has quit (Ping timeout: 248 seconds). 07:24:03 my encoding is definitely more trim than python's method, though I'm missing a few things (like rounding up to the nearest byte when finding the whole length of the series of paths.) 07:24:17 * imode is a happy imode. 07:32:21 int-e: Is partial application required for effective computation in CPS? 07:32:43 I'm attempting to create an example of the "while" construct created in my upcoming CPS-only esolang. 07:36:34 I think some sort of closures is required, and partial application can be viewed as an implementation of closures. 07:37:21 Actually, that's true (what /was/ I thinking?) 07:41:51 -!- augur has joined. 07:53:50 You know, the continuations in CPS are just like callbacks. 08:04:21 -!- augur has quit (Remote host closed the connection). 08:10:39 -!- augur has joined. 08:11:35 Hmm. I haven't come up with a name yet. Maybe "Continue" - ooh, what about "CC"? 08:15:08 -!- j-bot has joined. 08:17:41 -!- zseri has joined. 08:24:59 The urge is rising to add self-deprecatory sarcasm to my esolang articles. 08:32:00 -!- int-e has quit (Remote host closed the connection). 08:32:41 -!- int-e has joined. 08:33:17 -!- lambdabot has quit (Remote host closed the connection). 08:36:05 -!- lambdabot has joined. 08:41:45 [wiki] [[Ly]] https://esolangs.org/w/index.php?diff=52730&oldid=52706 * LyricLy * (+324) 08:44:52 @bot 08:44:52 :) 08:45:54 -!- augur has quit (Remote host closed the connection). 09:04:05 -!- moony has quit (Ping timeout: 240 seconds). 09:12:14 -!- augur has joined. 09:16:30 -!- augur has quit (Ping timeout: 240 seconds). 09:57:28 -!- imode has quit (Ping timeout: 240 seconds). 10:02:35 -!- doesthiswork has quit (Quit: Leaving.). 10:43:21 Is Newbiefuck ( http://esolangs.org/wiki/Newbiefuck ) Turing complete? 10:59:34 Are the '[]' commands in Newbiefuck a do-while loop? 11:04:19 @tell moony https://bitbucket.org/GregorR/hackbot/src/tip/multibot_cmds/lib/sandbox -- and no, /dev nodes are basically just a name for a (major, minor) pair, and don't magically translate to host devices, /dev is just hostfs-mounted to get /dev/null &c. easily. 11:04:19 Consider it noted. 11:19:24 -!- AnotherTest has joined. 11:30:09 zseri: Think they are. 11:30:23 Newbiefuck is the same thing as Brainfuck, except that [ is a NOP. 11:30:41 Which eliminates what is effectively the while conditional check at the beginning of the while loop. 11:35:11 (newbiefuck? what next, studentfuck? amateurfuck?) 11:35:58 anyway, I thought that newbiefuck would be the variant where ] goes back to the nearest [ 11:46:16 That could be studentfuck or amateurfuck. 12:04:25 [wiki] [[Assignless]] M https://esolangs.org/w/index.php?diff=52731&oldid=52719 * Rdococ * (-7) heh, nice. we don't need a "return" there at all :P 12:06:17 [wiki] [[Assignless]] https://esolangs.org/w/index.php?diff=52732&oldid=52731 * Zseri * (+3) remove unneeded return / braces 12:21:57 [wiki] [[HI9+]] M https://esolangs.org/w/index.php?diff=52733&oldid=52714 * Rdococ * (-58) 12:22:36 [wiki] [[HI9+]] https://esolangs.org/w/index.php?diff=52734&oldid=52733 * Rdococ * (+1) Syntactic errors, also known as syntactic lava. 12:26:14 [wiki] [[HI9+]] https://esolangs.org/w/index.php?diff=52735&oldid=52734 * Rdococ * (+133) 12:27:27 [wiki] [[HI9+]] https://esolangs.org/w/index.php?diff=52736&oldid=52735 * Rdococ * (-78) modified formatting 12:30:34 -!- Antoxyde has joined. 12:34:35 [wiki] [[User:Rdococ]] https://esolangs.org/w/index.php?diff=52737&oldid=52241 * Rdococ * (+0) 12:35:29 -!- LKoen has joined. 12:37:03 [wiki] [[HI9+]] https://esolangs.org/w/index.php?diff=52738&oldid=52736 * Rdococ * (+67) Disconfuse. Seriously, I'm bad at edit summaries. 12:48:20 -!- erkin has joined. 12:51:51 -!- jaboja has joined. 12:59:51 -!- Antoxyde_ has joined. 13:01:57 -!- Antoxyde has quit (Ping timeout: 240 seconds). 13:17:35 -!- danieljabailey has quit (Quit: ZNC 1.6.4+deb1 - http://znc.in). 13:19:25 -!- danieljabailey has joined. 13:27:20 -!- LKoen has quit (Quit: “It’s only logical. First you learn to talk, then you learn to think. Too bad it’s not the other way round.”). 13:35:00 -!- boily has joined. 13:46:40 -!- augur has joined. 13:51:08 -!- augur has quit (Ping timeout: 246 seconds). 14:00:32 -!- doesthiswork has joined. 14:01:54 `5 w 14:01:59 1/2:entschuldigung//Entschuldigung is the German word for blaming something on trees moving by themselves. \ coptology//Coptology is comprised of coptanalysis and coptography. Coptanalysis is concerned with the disassembly and reverse engineering of copters, whereas coptography is the art of designing and engineering copters that are robust against 14:02:01 `n 14:02:02 2/2: coptanalysis. \ nano//nano is vi's sister. \ bookwatching//bookwatching is when you conflagrate birdwatching and the books used to identify them in the same object. \ extreme irony//Extreme irony is what happens when you get a Darwin award for extreme ironing. 14:08:19 -!- jaboja has quit (Ping timeout: 258 seconds). 14:31:20 -!- jaboja has joined. 14:36:00 ()() is not a palindrome but )(() is 14:37:38 dhelloesthiswork. that is one ugly palindrome. 14:39:11 -!- ATMunn has joined. 14:39:44 ><> is a nicer one. 14:41:51 . o O ( that is, we have palindromic fish: ><> >(> ... even )(() looks a bit fishy... but can we make palindromic chicken? ) 14:44:33 `grwp palin 14:44:40 ي 14:44:41 palindrome:A palindrome is a word that remains the same if you take it to the mirror dimension, and then take each individual letter back to the normal dimension separately. 14:45:11 `unidecode ي 14:45:12 ​[U+064A ARABIC LETTER YEH] 14:45:27 yeh has always looked like a chicken to me 14:47:30 I guess 鶏 would be palindromic. 14:48:30 single characters are cheating. 14:50:20 Do Ara taste like chicken? 14:51:55 wow, shachaf should love this palindrome: "POOCHCOOP" 14:52:35 ara ara... 14:53:57 @google aibohphobia 14:53:59 https://en.wiktionary.org/wiki/aibohphobia 14:56:23 "poop – a raised deck at the stern of a ship; various other meanings" 15:03:47 -!- doesthiswork has quit (Quit: Leaving.). 15:14:09 -!- zseri has quit (Ping timeout: 260 seconds). 15:31:57 -!- jaboja has quit (Ping timeout: 240 seconds). 15:43:40 -!- FreeFull has quit. 15:50:53 -!- FreeFull has joined. 16:00:55 -!- zseri has joined. 16:06:25 -!- HTTP_____GK1wmSU has joined. 16:09:20 -!- HTTP_____GK1wmSU has left. 16:17:22 -!- Sgeo_ has joined. 16:19:31 -!- Sgeo__ has quit (Ping timeout: 240 seconds). 16:28:27 -!- Sgeo_ has quit (Ping timeout: 260 seconds). 16:31:22 -!- Antoxyde_ has quit (Ping timeout: 260 seconds). 16:40:32 -!- erkin has quit (Quit: Ouch! Got SIGABRT, dying...). 17:07:14 -!- jaboja has joined. 17:27:20 -!- erkin has joined. 17:35:37 -!- jaboja has quit (Ping timeout: 255 seconds). 17:36:52 -!- jaboja has joined. 18:04:47 -!- imode has joined. 18:23:14 -!- jaboja has quit (Ping timeout: 255 seconds). 18:30:59 -!- jaboja has joined. 18:32:29 -!- erkin has quit (Read error: Connection reset by peer). 18:32:41 Oops I found a few other bugs in my MIX assembler; "CON -0" results in positive zero by mistake, and equal sign expressions will make multiple copies of the same expression instead of just one; that is in addition to needing to add support for base other than base 100. 18:38:22 -!- erkin has joined. 18:52:49 -!- Antoxyde has joined. 19:13:38 @metar CYQB 19:13:38 CYQB 131800Z 30009G15KT 250V310 30SM SCT060 SCT220 24/11 A2982 RMK CU4CI1 CI TR SLP098 DENSITY ALT 1500FT 19:16:37 -!- moony has joined. 19:47:49 -!- augur has joined. 19:51:50 -!- augur has quit (Ping timeout: 240 seconds). 20:11:35 [wiki] [[Deadfish]] https://esolangs.org/w/index.php?diff=52739&oldid=52665 * Zzo38 * (+2218) +[[MIX (Knuth)]] 20:14:52 Now I wrote the implementation of Deadfish on MIX. 20:16:58 Do you like this? 20:20:43 http://esolangs.org/wiki/Deadfish#MIX_.28Knuth.29 20:43:20 -!- Sgeo has joined. 20:43:52 -!- Phantom_Hoover has joined. 20:50:57 -!- boily has quit (Ping timeout: 260 seconds). 20:56:29 -!- augur has joined. 21:16:26 -!- zseri has quit (Quit: Page closed). 21:19:57 -!- augur has quit (Remote host closed the connection). 21:27:50 -!- boily has joined. 21:29:53 -!- augur has joined. 21:38:12 `5 w 21:38:17 1/2:croissont supplier//See misspellings of croissant \ dy//dx = y \ 6 random numbers//4 8 15 16 23 42 \ gene ray//Dr Gene Ray is the Greatest Philosopher, and is the Greatest Mathematician. Cubic Harmonics. Only Cubic Harmonics can save humanity. Cubic Harmonics will pacify all religions. 96-hour Cubic Day debunks 1-day unnatural god. 96-hour day 21:39:24 `n 21:39:25 2/2:willdisprove disunity god. Academians are teaching - pseudocience. Worshipping a Word God will destroy the USA. \ mussel//Mussels are boily's natural enemies. Fortunately he runs faster than them. 22:06:11 -!- iczero has joined. 22:06:19 -!- iczero has left ("bye"). 22:10:35 -!- AnotherTest has quit (Ping timeout: 246 seconds). 22:20:03 [wiki] [[Arrows]] M https://esolangs.org/w/index.php?diff=52740&oldid=52728 * HereToAnnoy * (+168) 22:22:25 -!- augur has quit (Remote host closed the connection). 22:25:08 -!- augur has joined. 22:42:58 [wiki] [[Ly]] https://esolangs.org/w/index.php?diff=52741&oldid=52730 * LyricLy * (+79) 22:43:50 [wiki] [[Ly]] https://esolangs.org/w/index.php?diff=52742&oldid=52741 * LyricLy * (+6) /* Implicit I/O */ 22:45:02 helloily 22:53:48 -!- Remavas has joined. 22:55:14 -!- erkin has quit (Quit: Ouch! Got SIGABRT, dying...). 23:02:46 I tried to make the calculation listed in the Wikipedia article about "Midheaven", but sometimes the result is in the wrong quadrant. 23:02:46 QUINTHELLOPIA! 23:11:32 -!- moony has quit (Ping timeout: 260 seconds). 23:16:50 -!- boily has quit (Quit: SPARKLE CHICKEN). 23:24:58 I figured it out 23:34:47 -!- Phantom_Hoover has quit (Read error: Connection reset by peer). 23:37:37 [wiki] [[Arrows]] M https://esolangs.org/w/index.php?diff=52743&oldid=52740 * HereToAnnoy * (+131) 23:52:18 How to compute the position of the International Space Station? 23:56:51 I found "statistics as of 9 March 2011" on Wikipedia, but they do not match the elements needed by Swiss Ephemeris in the seorbel.txt file. 2017-08-14: 00:00:02 -!- danieljabailey has quit (Quit: ZNC 1.6.4+deb1 - http://znc.in). 00:00:26 -!- danieljabailey has joined. 00:42:52 -!- jaboja has quit (Ping timeout: 246 seconds). 00:44:07 -!- jaboja has joined. 00:51:16 -!- wob_jonas has joined. 00:52:14 " anyway, I thought that newbiefuck would be the variant where ] goes back to the nearest [" => this yes. and we've been calling the one where [] is a do-while loop "dofuck" informally, when I was thinking about why it's Turing-complete 00:59:10 " [...] "CON -0" results in positive zero by mistake" => well, technically vol 1 forgets to say what the unary minus does when it introduces the assembler (it defines precisely what the binary operators do) so that's not really a bug 01:00:30 My own assembler is not quite the same as MIXAL anyways though 01:01:29 -!- moony has joined. 01:01:34 zzo38: "and equal sign expressions will make multiple copies of the same expression instead of just one" => they have to make multiple copies. the book doesn't say they're unified, and they shouldn't be, since the program might write them. 01:02:45 O, I suppose you are correct about that, although I intended that you would explicitly use CON if you wanted to write them; otherwise how to know the address when you read them instead? 01:03:43 you use a CON line if you want to reference them twice, sure 01:04:03 or if you want to place them somewhere other than right before the END location 01:07:03 " How to compute the position of the International Space Station?" => that's hard because it has powered thrusters actively changing its orbit all the time, and is also in thin atmosphere so it's getting breaked 01:07:05 I am not sure why a program would want to write them anyways 01:08:38 Especially if you are only referencing it once, why will you write them? I don't see why a program should ever write to them whether they are unified or not. 01:09:47 Did you see the Deadfish implementation in MIX? (If you have the book, and if you want to do, you can write in actual MIXAL perhaps, because the code I posted is my own assembler instead) 01:16:15 -!- doesthiswork has joined. 01:27:11 -!- hppavilion[1] has joined. 01:58:58 -!- augur has quit (Remote host closed the connection). 02:04:27 -!- augur has joined. 02:13:55 zzo38: http://heavens-above.com/orbit.aspx?satid=25544 (linked from https://en.wikipedia.org/wiki/International_Space_Station ) shows the current position of the ISS 02:16:35 -!- Remavas has quit (Quit: Leaving). 02:47:37 -!- wob_jonas has quit (Quit: http://www.kiwiirc.com/ - A hand crafted IRC client). 02:55:51 -!- Antoxyde has quit (Quit: Leaving). 03:00:33 -!- ATMunn has quit (Quit: See ya! o/). 03:02:50 I saw that, but how to predict it? 03:03:58 -!- imode has quit (Ping timeout: 255 seconds). 03:05:33 zzo38: Do you like tensors? 03:11:11 I suppose so, kind of 03:11:52 Do you like monoidal categories? 03:13:49 Same, I think, yes it can have some uses 03:52:45 -!- moony has quit (Remote host closed the connection). 04:29:45 -!- imode has joined. 04:50:22 -!- sebbu has quit (Ping timeout: 258 seconds). 05:03:33 Some webpages have a stylesheet named "antiClickJack" which hides everything. What is that? 05:14:19 zzo38: You can read about clickjacking at https://en.wikipedia.org/wiki/Clickjacking 05:15:05 The idea is that you load someone's web page or other UI that responds to certain clicks in certain ways. 05:15:24 Then you put an overlay on top of it that makes it look like the click would do something else in your own UI. 05:16:24 -!- augur has quit (Remote host closed the connection). 05:18:46 -!- augur has joined. 05:27:30 I still think there are better ways to avoid such thing, such as by ignoring any CSS rules that affect an iframe other than positioning rules, so alpha transparency cannot be set, the border style cannot be altered, etc; and furthermore, if anything overlays an iframe, it makes that part of the iframe effectively disappear (so it can't be seen through alpha transparency) and cannot receive events. The iframe cannot receive keyboard events either un 05:28:08 A user setting to disable custom cursors may also be helpful. 05:28:15 As well as other things I did not mention. 05:29:39 Such as including the user settings which can affect what can load what. 05:37:01 But one way to avoid Facebook "like" jacking is if you do not have a Facebook account, I suppose; or does it still do even in that case? 05:53:33 The ALT+ENTER in Firefox to open entered address in a new tab is especially useful when "relative location bar" is in use; without that extension, this ALT+ENTER is less useful. 06:21:48 -!- doesthiswork has quit (Quit: Leaving.). 06:29:26 -!- erkin has joined. 06:42:54 -!- augur has quit (Remote host closed the connection). 06:53:53 -!- augur has joined. 07:01:26 -!- FreeFull has quit. 07:37:46 -!- augur has quit (Remote host closed the connection). 07:39:05 -!- augur has joined. 07:47:46 -!- jaboja has quit (Remote host closed the connection). 07:50:53 -!- imode has quit (Ping timeout: 246 seconds). 08:08:18 -!- augur has quit (Remote host closed the connection). 08:08:52 -!- augur has joined. 08:13:01 -!- augur has quit (Ping timeout: 240 seconds). 09:39:39 -!- sebbu has joined. 10:03:23 -!- erkin has quit (Quit: Ouch! Got SIGABRT, dying...). 10:19:45 -!- augur has joined. 10:24:13 -!- augur has quit (Ping timeout: 246 seconds). 10:53:03 -!- AnotherTest has joined. 11:13:45 -!- erkin has joined. 11:34:11 -!- boily has joined. 11:49:45 -!- Antoxyde has joined. 11:50:41 -!- heroux has quit (Ping timeout: 248 seconds). 12:17:37 -!- heroux has joined. 12:20:30 `5 w 12:20:35 1/2:mdude//MDude is just a dude, with an M's courage. \ misle//misle v. tr. "I was misled about morphology." \ method//A method is a tweaked out mothod. \ guillible//A guillible person is someone who can be fooled with a Scheme script. \ northumberland//Northumberland may be today a sparsely populated country... but SOON! THE NORTHUMBRAINS SHALL RI 12:20:39 `n 12:20:40 2/2:SE! 12:30:57 -!- boily has quit (Quit: NETWORK CHICKEN). 13:09:40 -!- augur has joined. 13:14:05 -!- augur has quit (Ping timeout: 255 seconds). 13:32:39 -!- zseri has joined. 14:00:31 -!- doesthiswork has joined. 14:42:15 -!- `^_^v has joined. 14:43:11 -!- zseri has quit (Quit: Page closed). 14:56:07 -!- ATMunn has joined. 14:56:12 -!- erkin has quit (Read error: Connection reset by peer). 14:56:40 -!- erkin has joined. 15:02:40 -!- doesthiswork has quit (Quit: Leaving.). 15:23:59 -!- wob_jonas has joined. 15:24:37 Oh wow! amazon.com is great! I've never used it before 15:25:20 -!- augur has joined. 15:26:07 Despite how US-centric it is, it actually allows me to choose to pay from credit card in USD; as opposed to ebay who insists on charging everything in HUF with their high currency conversion rates, just because I live in Hungary. 15:26:37 As in, paypal insists on that. 15:27:36 -!- erkin has quit (Quit: Ouch! Got SIGABRT, dying...). 15:28:58 Do the other amazons (amazon.co.uk, amazon.de etc) do this properly too? 15:29:46 -!- augur has quit (Ping timeout: 246 seconds). 15:31:36 They also warn you not to put non-ascii characters in your shipping address in advance, which I think is nicer than silently printing garbage on the envelope. 15:47:03 -!- jaboja has joined. 16:06:25 -!- wob_jonas has quit (Quit: http://www.kiwiirc.com/ - A hand crafted IRC client). 16:26:38 -!- moony has joined. 16:27:05 -!- jaboja has quit (Ping timeout: 240 seconds). 16:52:26 [wiki] [[Talk:Mindscrew]] https://esolangs.org/w/index.php?diff=52744&oldid=30287 * Rdococ * (+196) /* May I take this name for an esolang? */ new section 16:53:09 [wiki] [[Talk:Mindscrew]] M https://esolangs.org/w/index.php?diff=52745&oldid=52744 * Rdococ * (+84) 16:53:29 [wiki] [[Talk:Mindscrew]] https://esolangs.org/w/index.php?diff=52746&oldid=52745 * Rdococ * (-2) accidentally invoked \n- code syntax 16:58:52 [wiki] [[Talk:Mindscrew]] https://esolangs.org/w/index.php?diff=52747&oldid=52746 * Rdococ * (+304) meh, might as well do it anyway 17:15:59 -!- erkin has joined. 17:16:28 `olist 1091 17:16:29 olist 1091: shachaf oerjan Sgeo FireFly boily nortti b_jonas 17:40:42 -!- FreeFull has joined. 17:41:14 -!- augur has joined. 17:45:53 -!- augur has quit (Ping timeout: 246 seconds). 17:47:26 -!- zseri has joined. 18:02:21 -!- erkin has quit (Quit: Ouch! Got SIGABRT, dying...). 18:11:45 -!- imode has joined. 18:16:50 -!- imode has quit (Ping timeout: 240 seconds). 18:21:30 -!- moonythedwarf has joined. 18:21:41 -!- moony has quit (Read error: Connection reset by peer). 18:39:02 -!- imode has joined. 18:53:18 -!- jaboja has joined. 19:09:00 -!- Phantom_Hoover has joined. 19:12:47 At the moment, Mindscrew is a fast redirect to Brainfuck. I was wondering if I could use the name for my own esolang, which would add first-class functions and stuff. 19:14:28 Meh - I'll publish the article anyway, and see what people think. It's an easy move and revert if it doesn't work out for some reason. 19:16:37 [wiki] [[Mindscrew]] https://esolangs.org/w/index.php?diff=52748&oldid=30285 * Rdococ * (+6326) Mindscrew is a high-level extension of Brainfuck - at the moment, it adds first-class subroutines, first-class continuations, and non-first-class coroutines (though you could probably simulate them with subroutines and continuations). 19:17:10 [wiki] [[Mindscrew]] https://esolangs.org/w/index.php?diff=52749&oldid=52748 * Rdococ * (-1) Fixed a minor formatting bug in the table header. 19:20:35 -!- jaboja has quit (Ping timeout: 240 seconds). 19:20:38 [wiki] [[Mindscrew]] https://esolangs.org/w/index.php?diff=52750&oldid=52749 * Rdococ * (-21) Fixed a minor issue in the examples. 19:22:01 [wiki] [[Mindscrew]] https://esolangs.org/w/index.php?diff=52751&oldid=52750 * Rdococ * (+1) Fixed /another/ minor issue. 19:25:16 [wiki] [[User:Rdococ]] https://esolangs.org/w/index.php?diff=52752&oldid=52737 * Rdococ * (+110) /* My hopefully better esoteric languages (12017 HE - ∞+10000 HE) */ 19:25:35 [wiki] [[User:Rdococ]] M https://esolangs.org/w/index.php?diff=52753&oldid=52752 * Rdococ * (+3) 19:28:30 -!- jaboja has joined. 19:28:58 <* Taneb> hello 19:33:04 hi. 19:34:27 [wiki] [[User:Rdococ]] https://esolangs.org/w/index.php?diff=52754&oldid=52753 * Rdococ * (+1009) 19:37:38 * rdococ hi Taneb and imode. 19:38:08 [wiki] [[Brainfuck extensions]] https://esolangs.org/w/index.php?diff=52755&oldid=45312 * Rdococ * (+15) Added Mindscrew to the "Subroutines, functions, macros" entry. 19:38:45 My Neural Net program is pretty much ready for me to try to actually build a neural net 19:39:36 Build a neural net that builds neural nets. 19:40:01 Sounds like effort 19:40:13 Are you using actual neurons? 19:40:23 I am afraid not 19:40:36 imo then why call it a "neural net" twh 19:40:39 not in the budget. 19:41:00 shachaf, they try to simulate actual neurons 19:41:07 They do? 19:41:13 yuh. 19:41:18 How? 19:41:36 Poorly 19:41:44 all about that activation function booiiii. 19:42:10 My claim is that there's no resemblance. 19:42:30 would you like to back up that claim with evidence? 19:42:54 ..for an extra .99c? 19:43:11 Well, I don't know what Taneb is making yet. 19:43:30 It's only a weak claim right now. 19:43:32 shachaf, a terrible imitation is still an imitation 19:43:55 But then anything can be called a neuron. 19:43:56 [wiki] [[Mindscrew]] https://esolangs.org/w/index.php?diff=52756&oldid=52751 * Rdococ * (+229) 19:44:08 it's not about what Taneb is making, you're claiming neural nets show no resemblance to actual nets of actual neurons. 19:44:22 I'd like to see some evidence. 19:44:31 You mean "artificial neural networks"? 19:44:38 rdococ: My own opinion at least is that that redirect is worthless, so it should be OK to use the name by yourself. If it is found that it isn't so worthless and that you want it anyways, then to add the "see also"/"maybe you meant" kind of stuff at the top 19:44:42 yup. that's a good search term. 19:44:49 Well, I see no resemblance. How's that? 19:44:56 I think it's a bad name. 19:45:02 I don't really know enough about brains to comment 19:45:08 and can you give us some reasons.. why? 19:45:19 zzo38: I've already added that to it. 19:45:25 I think it's up to the people using ridiculous names like "neural" to give evidence. 19:45:40 no, it's up to you to say why you don't like it. :P 19:45:51 claims typically require justification. 19:46:02 how minimal that might be. 19:46:04 I was thinking of removing the continuations and coroutines, though, because they just feel like they're unnecessary bunk in a brainfuck derivative. 19:46:13 I don't like it because I see no resemblance. 19:46:21 and you see no resemblance because you don't like it? 19:46:23 To borrow a name and make an analogy like that, you need evidence. 19:46:29 I think it doesn't matter whether they are similar to biological neural nets or not because it's an established name now 19:46:31 do you even know what they are? 19:46:38 What what are? 19:46:44 ANNs. do you kno whow they work 19:46:59 More or less. 19:47:04 *know how they work. have you read why they're called that? 19:47:13 They represent data as a vector in R^n 19:47:21 have you at least done the required skimming as to why the model was labeled that? :P 19:47:31 They repeatedly apply linear maps followed by some nonlinear transformation. 19:47:38 Sometimes they do other things. 19:48:05 maybe read some more on the topic. there's a clear resemblance, albeit one that's being seen from a moving car. 19:48:06 shachaf, I think it's the training of them that's the interesting bit 19:48:07 Yes, I've done some skimming. A long time ago there was slightly more resemblance, for example when people used perceptrons with discrete output. 19:48:26 perceptrons didn't change, our activation functions became smoother, much like actual neurons 19:48:43 Taneb: There's certainly no evidence that I know of that real neurons are "trained" using backpropagation or gradient descent, which are the popular tactics for ANNs. 19:49:00 Are actual neurons smooth? 19:49:08 yes, their activations are. 19:49:23 You say neuron firing is not discrete? 19:49:31 essentially. 19:49:33 shachaf, I still think backpropogation is interesting even if it isn't accurate to biology 19:49:41 Taneb: I agree. 19:50:07 though I totally agree with you that ANNs are as good a model for real neurons as legos are for large-scale skyscraper construction, there's some resemblance. 19:50:07 I think as people make more progress with ANNs they become further and further from biology, because the biological inspiration was never very important in the first place. 19:50:39 these days it's pretty twisted. there's a relevant xkcd for this. 19:50:55 https://www.xkcd.com/1838/ 19:51:45 People have had linear algebra for a long time. 19:51:58 [wiki] [[Mindscrew]] https://esolangs.org/w/index.php?diff=52757&oldid=52756 * Rdococ * (-222) Added a return instruction, and improved the example formatting. 19:52:12 just about as long as calculus, in fact! 19:52:20 #funfact 19:53:15 [wiki] [[Mindscrew]] https://esolangs.org/w/index.php?diff=52758&oldid=52757 * Rdococ * (+89) /* Examples */ Fixed the if conditional example. 20:01:04 Ugh, my own article screws my mind. 20:16:36 [wiki] [[Mindscrew]] https://esolangs.org/w/index.php?diff=52759&oldid=52758 * Rdococ * (+105) 20:29:26 [wiki] [[Works in progress]] M https://esolangs.org/w/index.php?diff=52760&oldid=51496 * HereToAnnoy * (+13) 20:33:17 [wiki] [[Mindscrew]] https://esolangs.org/w/index.php?diff=52761&oldid=52759 * Rdococ * (-1032) Removed continuations. 20:46:09 [wiki] [[Mindscrew]] https://esolangs.org/w/index.php?diff=52762&oldid=52761 * Rdococ * (+946) Added SWAP register and modified + and - instructions for moving subroutines around in the cell tape. 20:49:44 [wiki] [[Mindscrew]] https://esolangs.org/w/index.php?diff=52763&oldid=52762 * Rdococ * (+54) Added categories: "Brainfuck derivatives", and "2017". 20:50:28 -!- imode has quit (Ping timeout: 255 seconds). 20:51:39 [wiki] [[User:Rdococ]] M https://esolangs.org/w/index.php?diff=52764&oldid=52754 * Rdococ * (+127) 20:52:46 It strikes me as odd that out of all of my esolangs, I (as of now) rate my BF derivative the highest. Then again, I could just be that bad. (Then again, "Rule" is pretty cool, and so is "HI9+".) 20:56:48 -!- augur has joined. 20:57:35 Hellaugur. 21:00:16 -!- imode has joined. 21:09:43 [wiki] [[Mindscrew]] M https://esolangs.org/w/index.php?diff=52765&oldid=52763 * Rdococ * (+75) Added more categories. 21:13:01 [wiki] [[Mindscrew]] M https://esolangs.org/w/index.php?diff=52766&oldid=52765 * Rdococ * (+6) Added some bold to the beginning. 21:22:52 -!- idris-bot has quit (Quit: Terminated). 21:33:06 -!- zseri has quit (Quit: Page closed). 21:37:44 -!- moonythedwarf has changed nick to moony_{vil}. 21:43:56 https://www.reddit.com/r/ProgrammerDadJokes/comments/6tmqm3/my_app_is_crashing_when_the_user_has_a_bad_cell m( 22:04:01 -!- jaboja has quit (Ping timeout: 248 seconds). 22:05:54 -!- Melvar has quit (Quit: rebooting). 22:07:41 -!- copumpkin has quit (Ping timeout: 246 seconds). 22:14:23 -!- Melvar has joined. 22:17:55 -!- idris-bot has joined. 22:26:36 -!- moony_{vil} has changed nick to moony. 22:27:48 -!- jaboja has joined. 22:32:13 -!- Sgeo has quit (Read error: Connection reset by peer). 22:39:02 <\oren\> https://en.wikipedia.org/wiki/Daichi_Fukushima 22:39:06 <\oren\> poor guy 22:39:57 -!- copumpkin has joined. 22:40:00 -!- `^_^v has quit (Quit: This computer has gone to sleep). 22:41:05 [wiki] [[Language list]] https://esolangs.org/w/index.php?diff=52767&oldid=52704 * Kwikrick * (+15) 22:49:04 -!- boily has joined. 22:56:07 -!- augur has quit (Remote host closed the connection). 22:58:09 -!- augur has joined. 23:06:39 -!- Sgeo has joined. 23:11:18 -!- ski has quit (Ping timeout: 258 seconds). 23:33:22 -!- imode has quit (Ping timeout: 255 seconds). 23:36:17 -!- joast has quit (Ping timeout: 248 seconds). 23:36:23 [wiki] [[Ly]] https://esolangs.org/w/index.php?diff=52768&oldid=52742 * LyricLy * (-774) 23:36:36 -!- AnotherTest has quit (Ping timeout: 258 seconds). 23:41:46 [wiki] [[Ly]] https://esolangs.org/w/index.php?diff=52769&oldid=52768 * LyricLy * (+181) 23:47:46 [wiki] [[Arrows]] https://esolangs.org/w/index.php?diff=52770&oldid=52743 * HereToAnnoy * (+4) /* External links */ 23:47:59 [wiki] [[Arrows]] https://esolangs.org/w/index.php?diff=52771&oldid=52770 * HereToAnnoy * (+2) /* File type */ 23:49:31 -!- boily has quit (Quit: COVERAGE CHICKEN). 23:55:11 [wiki] [[Arrows]] https://esolangs.org/w/index.php?diff=52772&oldid=52771 * HereToAnnoy * (-12) 2017-08-15: 00:13:11 [wiki] [[TheSingularity]] N https://esolangs.org/w/index.php?oldid=52773 * HereToAnnoy * (+1336) Created page with "'''TheSingularity''' is an [[esoteric programming language]] created by [[User:HereToAnnoy]] that only gives the programmer one constant, called "TheSingularity", to work with..." 00:13:11 -!- Phantom_Hoover has quit (Read error: Connection reset by peer). 00:16:37 -!- oerjan has joined. 00:26:44 -!- joast has joined. 00:51:08 -!- augur has quit (Remote host closed the connection). 00:51:20 -!- Antoxyde has quit (*.net *.split). 00:51:20 -!- Gregor has quit (*.net *.split). 00:51:20 -!- Bowserinator has quit (*.net *.split). 00:51:20 -!- nchambers has quit (*.net *.split). 00:51:20 -!- gsora has quit (*.net *.split). 00:51:20 -!- Jafet has quit (*.net *.split). 00:51:21 -!- relrod has quit (*.net *.split). 00:51:21 -!- Lymia has quit (*.net *.split). 00:51:21 -!- Deewiant has quit (*.net *.split). 00:51:21 -!- newsham has quit (*.net *.split). 00:51:22 -!- mtve has quit (*.net *.split). 00:51:22 -!- FreeFull has quit (*.net *.split). 00:51:22 -!- heroux has quit (*.net *.split). 00:51:22 -!- quintopia has quit (*.net *.split). 00:51:22 -!- Cale has quit (*.net *.split). 00:51:22 -!- contrapumpkin has quit (*.net *.split). 00:51:23 -!- digitalcold has quit (*.net *.split). 00:51:23 -!- APic has quit (*.net *.split). 00:51:23 -!- trn has quit (*.net *.split). 00:51:23 -!- clog has quit (*.net *.split). 00:51:23 -!- xa0 has quit (*.net *.split). 00:51:24 -!- MrBusiness has quit (*.net *.split). 00:51:24 -!- zgrepc has quit (*.net *.split). 00:51:25 -!- iovoid has quit (*.net *.split). 00:51:25 -!- diginet has quit (*.net *.split). 00:51:26 -!- Melvar has quit (*.net *.split). 00:51:26 -!- ATMunn has quit (*.net *.split). 00:51:26 -!- lambdabot has quit (*.net *.split). 00:51:26 -!- vifino has quit (*.net *.split). 00:51:27 -!- olsner has quit (*.net *.split). 00:51:27 -!- puckipedia has quit (*.net *.split). 00:51:27 -!- BooK_ has quit (*.net *.split). 00:51:28 -!- Guest6666 has quit (*.net *.split). 00:51:48 -!- Lymia has joined. 00:52:02 -!- iovoid has joined. 00:52:52 -!- MrBusiness has joined. 00:53:19 -!- hppavilion[1] has quit (Quit: HRII'FHALMA MNAHN'K'YARNAK NGAH NILGH'RI'BTHNKNYTH). 00:54:36 -!- augur has joined. 00:55:14 -!- FreeFull has joined. 00:55:14 -!- heroux has joined. 00:55:14 -!- newsham has joined. 00:55:14 -!- mtve has joined. 00:55:14 -!- quintopia has joined. 00:55:14 -!- Cale has joined. 00:55:14 -!- contrapumpkin has joined. 00:55:14 -!- digitalcold has joined. 00:55:14 -!- APic has joined. 00:55:14 -!- clog has joined. 00:55:14 -!- xa0 has joined. 00:55:17 -!- copumpkin has quit (Ping timeout: 255 seconds). 00:55:48 -!- zgrepc has joined. 00:55:53 -!- APic has quit (Max SendQ exceeded). 00:56:11 -!- Antoxyde has joined. 00:56:11 -!- Gregor has joined. 00:56:11 -!- Bowserinator has joined. 00:56:11 -!- gsora has joined. 00:56:11 -!- Jafet has joined. 00:56:11 -!- relrod has joined. 00:56:12 -!- ineiros has quit (Ping timeout: 260 seconds). 00:56:14 -!- APic has joined. 00:56:19 -!- Deewiant has joined. 00:56:42 -!- Melvar has joined. 00:56:42 -!- ATMunn has joined. 00:56:42 -!- lambdabot has joined. 00:56:42 -!- vifino has joined. 00:56:42 -!- olsner has joined. 00:56:42 -!- puckipedia has joined. 00:56:42 -!- BooK_ has joined. 00:56:42 -!- Guest6666 has joined. 00:57:20 -!- Deewiant has quit (*.net *.split). 00:57:27 -!- newsham has quit (*.net *.split). 00:57:27 -!- mtve has quit (*.net *.split). 00:57:28 -!- FreeFull has quit (*.net *.split). 00:57:28 -!- heroux has quit (*.net *.split). 00:57:29 -!- quintopia has quit (*.net *.split). 00:57:29 -!- Cale has quit (*.net *.split). 00:57:29 -!- contrapumpkin has quit (*.net *.split). 00:57:30 -!- digitalcold has quit (*.net *.split). 00:57:31 -!- clog has quit (*.net *.split). 00:57:31 -!- xa0 has quit (*.net *.split). 00:58:35 -!- ineiros has joined. 00:59:07 -!- idris-bot has quit (Ping timeout: 260 seconds). 00:59:41 -!- FreeFull has joined. 00:59:41 -!- heroux has joined. 00:59:41 -!- newsham has joined. 00:59:41 -!- mtve has joined. 00:59:41 -!- quintopia has joined. 00:59:41 -!- Cale has joined. 00:59:41 -!- contrapumpkin has joined. 00:59:41 -!- digitalcold has joined. 00:59:41 -!- clog has joined. 00:59:41 -!- xa0 has joined. 01:02:00 -!- trn has joined. 01:03:35 -!- Deewiant has joined. 01:03:58 -!- iovoid has changed nick to Guest85801. 01:03:59 -!- augur has changed nick to Guest10346. 01:04:23 -!- nchambers has joined. 01:04:23 -!- diginet has joined. 01:10:23 -!- copumpkin has joined. 01:15:53 @tell rdococ Did anyone point you at https://hackage.haskell.org/package/Ganymede-0.0.0.5/src/vague%27s%20-%20amalthea.html yet? 01:15:53 Consider it noted. 01:24:34 -!- Guest85801 has quit (Changing host). 01:24:34 -!- Guest85801 has joined. 01:24:39 @tell rdococ (Warning, that's another "someone already had your idea" link.) 01:24:39 Consider it noted. 01:24:39 -!- Guest85801 has changed nick to iovoid. 01:24:41 [wiki] [[TheSingularity]] https://esolangs.org/w/index.php?diff=52774&oldid=52773 * HereToAnnoy * (+3115) Finished up 01:28:56 -!- jaboja has quit (Ping timeout: 246 seconds). 01:41:27 -!- jaboja has joined. 02:00:23 -!- Antoxyde has quit (Quit: Leaving). 02:22:36 [wiki] [[Special:Log/newusers]] create * Insert name here * New user account 02:26:56 `grwp i.n.h. 02:27:07 frenemy:Frenemy is the relationship between Kirby and king Dee Dee. \ grimmargorp:Þór, Grimmargorpurinn hefur sloppið! Ragnarök eru nálæg! \ peng:peng is a computer network administration software utility used to test the reachability of a destination host on an Internet Protocol (IP) network, and the destination host's ability to reach the 02:27:22 `grWp i\.n\.h\. 02:27:23 No output. 02:27:50 -!- doesthiswork has joined. 02:28:03 `grWp i[.]n[.]h[.] 02:28:04 No output. 02:28:21 `grWp i[.] n[.] h[.] 02:28:23 No output. 02:28:34 hum 02:28:40 `grwp I[.] 02:28:41 5318008:5318008 is a famous number because its reciprocal is 1.8804033389946 * 10^-7, which when upside down on a calculator spells L-vOI * ghGGBEEEOhOBB.I. \ alg. ii:Algae II, the successor class to Algae I. Discusses hydroponics and such. \ deep learning:Deep learning applies software engineering principles to AI. A deep learning network has nume 02:28:59 `2 grwp I[.] 02:29:00 2/3:numerous layers and no one understands what any of them do. \ gamemanj:gamemanj is also the mad scientist I. N. Here. He will overthink everything, except whether overthinking is wrong. \ wumpus:Wumpus the Hunted is an early 70s action game in which the Wumpus is trapped in a dodecahedral diagram where it's chased by bats. It has to avoid traps 02:29:14 there. 02:32:12 -!- imode has joined. 02:40:08 [wiki] [[Esolang:Introduce yourself]] https://esolangs.org/w/index.php?diff=52775&oldid=52700 * Insert name here * (+231) 02:42:07 -!- MrBismuth has joined. 02:43:20 [wiki] [[Fishing]] M https://esolangs.org/w/index.php?diff=52776&oldid=37569 * Insert name here * (-1) Corrected error in interpreter 02:44:53 -!- MrBusiness has quit (Ping timeout: 246 seconds). 02:52:22 [wiki] [[Fishing]] https://esolangs.org/w/index.php?diff=52777&oldid=52776 * Insert name here * (+140) Documented "p" fish (which was previously present in the interpreter, but undocumented) 02:54:58 [wiki] [[TheSingularity]] https://esolangs.org/w/index.php?diff=52778&oldid=52774 * HereToAnnoy * (-33) 03:01:33 -!- ATMunn has quit (Quit: See ya! o/). 03:11:39 -!- hppavilion[1] has joined. 03:14:32 [wiki] [[TheSingularity]] M https://esolangs.org/w/index.php?diff=52779&oldid=52778 * HereToAnnoy * (+607) 03:19:05 [wiki] [[TheSingularity]] M https://esolangs.org/w/index.php?diff=52780&oldid=52779 * HereToAnnoy * (+41) 03:20:51 [wiki] [[User:HereToAnnoy]] M https://esolangs.org/w/index.php?diff=52781&oldid=52729 * HereToAnnoy * (+106) 03:24:25 [wiki] [[Arrows]] M https://esolangs.org/w/index.php?diff=52782&oldid=52772 * HereToAnnoy * (+41) 03:32:01 oerjan: …is that an archive of an internet archive archive? 03:36:46 um 03:40:21 seems so. 04:14:57 <\oren\> http://imgur.com/gallery/D7dva 04:15:33 -!- MDead has joined. 04:16:00 -!- MDude has quit (Ping timeout: 255 seconds). 04:16:07 -!- MDead has changed nick to MDude. 04:19:45 <\oren\> @tell wob_jonas http://imgur.com/gallery/D7dva 04:19:45 Consider it noted. 04:42:04 -!- oerjan has quit (Quit: Nite). 04:47:30 -!- MDude has quit (Ping timeout: 240 seconds). 04:53:33 -!- MDude has joined. 04:53:56 [wiki] [[TheSingularity]] M https://esolangs.org/w/index.php?diff=52783&oldid=52780 * HereToAnnoy * (+37) /* Mathematical operations */ 04:56:25 [wiki] [[Language list]] M https://esolangs.org/w/index.php?diff=52784&oldid=52767 * HereToAnnoy * (+21) /* T - added language*/ 05:13:13 -!- brandonson has quit (Ping timeout: 276 seconds). 05:14:18 -!- brandonson has joined. 05:43:13 -!- jaboja has quit (Ping timeout: 248 seconds). 06:00:42 -!- MDude has quit (Ping timeout: 260 seconds). 06:08:56 -!- Guest10346 has changed nick to augur. 06:09:20 -!- augur has quit (Quit: Leaving...). 06:09:36 -!- augur has joined. 06:20:16 -!- doesthiswork has quit (Quit: Leaving.). 06:34:59 -!- erkin has joined. 06:59:21 -!- FreeFull has quit. 07:10:13 [wiki] [[Mindscrew]] M https://esolangs.org/w/index.php?diff=52785&oldid=52766 * Rdococ * (-30) Renamed the subroutines to functions, and fixed a minor error in the examples which mentioned continuations 07:15:20 An easy way to break Mindscrew: {}-- 07:16:37 -!- Mr2001 has joined. 07:20:52 [wiki] [[Mindscrew]] https://esolangs.org/w/index.php?diff=52786&oldid=52785 * Rdococ * (+116) Added clarification for using + on a function when the SWAP register is empty. 07:22:27 -!- moony has quit (Ping timeout: 240 seconds). 07:24:17 [wiki] [[User:Rdococ]] https://esolangs.org/w/index.php?diff=52787&oldid=52764 * Rdococ * (+61) 07:26:04 [wiki] [[User:Rdococ]] M https://esolangs.org/w/index.php?diff=52788&oldid=52787 * Rdococ * (+13) 07:40:37 -!- augur has quit (Remote host closed the connection). 07:41:15 -!- augur has joined. 07:41:33 Hmm. I was thinking about turning Mindscrew's "]" instruction into a NOP, making "[stuff]" an IF conditional as opposed to a WHILE loop. The reason being that Mindscrew has first-class functions, and you can wrap code in a recursive function to loop. 07:45:29 -!- augur has quit (Ping timeout: 240 seconds). 07:50:13 [wiki] [[Mindscrew]] https://esolangs.org/w/index.php?diff=52789&oldid=52786 * Rdococ * (-1912) Turned ']' into a NOP. 07:55:02 -!- augur has joined. 07:56:51 [wiki] [[Mindscrew]] https://esolangs.org/w/index.php?diff=52790&oldid=52789 * Rdococ * (+747) Modified some interpreter details, along with clarifying using '[' with a function, and some more clarification on the example. 07:58:50 [wiki] [[User:Rdococ]] M https://esolangs.org/w/index.php?diff=52791&oldid=52788 * Rdococ * (-50) Increased the Mindscrew self-evaluation, due in part to the semantic change in ']'. The irony here is that I rate my BF derivative the highest. 08:00:31 [wiki] [[User:Rdococ]] M https://esolangs.org/w/index.php?diff=52792&oldid=52791 * Rdococ * (+32) Removed Mindscrew's status as undoubtedly TC - although it probably is. 08:14:59 [wiki] [[Mindscrew]] M https://esolangs.org/w/index.php?diff=52793&oldid=52790 * Rdococ * (+63) 08:24:30 [wiki] [[Mindscrew]] https://esolangs.org/w/index.php?diff=52794&oldid=52793 * Rdococ * (+250) Clarified printing functions. 08:27:54 [wiki] [[Mindscrew]] M https://esolangs.org/w/index.php?diff=52795&oldid=52794 * Rdococ * (+50) Clarified "-"'s behavior upon attempting to decrement two functions in a row, w/o an increment in between, as opposed to decrementing a function and then a normal, integer cell value. 08:28:58 -!- imode has quit (Ping timeout: 246 seconds). 08:29:01 -!- augur has quit (Remote host closed the connection). 08:29:36 -!- augur has joined. 08:34:05 -!- augur has quit (Ping timeout: 240 seconds). 08:44:53 I'm waiting for feedback on Mindscrew which isn't "well, somebody already had this idea...". 08:53:19 -!- augur has joined. 08:57:30 -!- augur has quit (Ping timeout: 240 seconds). 09:14:08 [wiki] [[Mindscrew]] https://esolangs.org/w/index.php?diff=52796&oldid=52795 * Rdococ * (+343) Added information (well, mostly idle wondering) about the Turing-completeness of mindscrew. Also noted that TCO is optional. 09:16:52 [wiki] [[List of quines]] https://esolangs.org/w/index.php?diff=52797&oldid=52270 * Malbranche * (+143) Malbolge Unshackled 09:17:24 [wiki] [[Mindscrew]] M https://esolangs.org/w/index.php?diff=52798&oldid=52796 * Rdococ * (+197) 09:29:46 [wiki] [[Mindscrew]] M https://esolangs.org/w/index.php?diff=52799&oldid=52798 * Rdococ * (+136) /* Cat */ Modified, to show off the parentheses' purpose better. 09:33:12 [wiki] [[Mindscrew]] https://esolangs.org/w/index.php?diff=52800&oldid=52799 * Rdococ * (+167) /* Instructions */ Added more documentation to the "()" instruction(s). 09:34:20 [wiki] [[Mindscrew]] M https://esolangs.org/w/index.php?diff=52801&oldid=52800 * Rdococ * (-15) /* Computational Class */ 09:36:47 [wiki] [[User:Rdococ]] M https://esolangs.org/w/index.php?diff=52802&oldid=52792 * Rdococ * (+189) Added educational guesses for the computational class of the at least half-decent esolangs. 09:37:53 [wiki] [[User:Rdococ]] M https://esolangs.org/w/index.php?diff=52803&oldid=52802 * Rdococ * (+5) /* Esolangs of mine that I consider decent, or are yet unevaluated */ 09:39:36 [wiki] [[QWOP]] https://esolangs.org/w/index.php?diff=52804&oldid=51333 * Rdococ * (+229) Added computational class section. 09:40:17 [wiki] [[QWOP]] M https://esolangs.org/w/index.php?diff=52805&oldid=52804 * Rdococ * (+39) 09:40:35 [wiki] [[QWOP]] M https://esolangs.org/w/index.php?diff=52806&oldid=52805 * Rdococ * (+12) 09:41:21 I find it rather ironic that my brainfuck derivative seems to be the best language I've created. I also find it rather depressing, but that's a different story. 09:41:40 -!- erkin has quit (Read error: Connection reset by peer). 09:49:54 -!- erkin has joined. 10:04:25 [wiki] [[Mindscrew]] https://esolangs.org/w/index.php?diff=52807&oldid=52801 * Rdococ * (+215) Added implementation guidelines, and a warning that the language may and probably will be modified and improved over time. 10:04:50 -!- hppavilion[1] has quit (Quit: HRII'FHALMA MNAHN'K'YARNAK NGAH NILGH'RI'BTHNKNYTH). 10:11:35 [wiki] [[Mindscrew]] https://esolangs.org/w/index.php?diff=52808&oldid=52807 * Rdococ * (-733) Removed the odd stuff from the () instruction. (Do you think () should be replaced with a single character? If so, which one? Maybe ;...) 10:22:05 -!- augur has joined. 10:23:23 Hi againur. 10:26:10 -!- augur has quit (Ping timeout: 240 seconds). 11:00:08 -!- AnotherTest has joined. 11:02:52 Dammit, I took another look at pbrain and now I don't really like mindscrew anymore. 11:16:56 [wiki] [[User:Rdococ]] https://esolangs.org/w/index.php?diff=52809&oldid=52803 * Rdococ * (-25) /* Esolangs of mine that I consider decent, or are yet unevaluated */ ... 11:20:27 -!- Antoxyde has joined. 11:23:09 [wiki] [[List of ideas]] M https://esolangs.org/w/index.php?diff=52810&oldid=51835 * Rdococ * (-204) Removed my crappy idea from ages ago. 11:33:03 -!- boily has joined. 11:39:05 hi boily... 11:39:23 rdochelloc! 11:43:06 Hmm... Maybe a cellular automaton designed to simulate water flow? 11:56:21 -!- rodgort has quit (Quit: Leaving). 11:59:41 boily: What do you think about turning Abstract Syntax Trees into... well... non-trees? 12:00:07 E.g. nodes could be connected to other nodes from different parent branches. 12:01:00 that would imply non-determinism. depending on the path you take, the logic of your program could change. 12:02:15 I don't think non-determinism is strictly necessary for syntax non-trees... 12:05:18 Suppose you have a man eating chicken. Is it a man eating chicken or a man eating chicken? 12:06:09 Eh? 12:06:41 I can't tell whether I'm being dumb, or whether you misinterpreted what I said (which would mainly be because I'm dumb). 12:07:35 I am known to misinterpret things. (Usually that gets me a corrective shachaf action...) 12:08:15 Is it a "man that eats chicken", or a "chicken that eats men". Depending on how you construct your tree, the meaning could change. 12:08:29 Ohhhhh. 12:08:31 If you have multiple trees at the same time, which one is truth? 12:08:41 That went straight over my head. 12:08:50 Believe in the chicken :D 12:09:04 Anyway, I was talking about having nodes with multiple parents. 12:09:41 So you could have, say, a node which I'll represent with something like "[+[x, 2]]". That node could be used in two, rather than one, parent expressions at once. 12:11:56 -!- AnotherTest has quit (Ping timeout: 240 seconds). 12:11:58 Well, I was also considering a conceptual lang where programs written in it would be up to 100% preprocessing. 12:21:17 -!- rodgort has joined. 12:27:27 -!- boily has quit (Quit: POSSIBLE CHICKEN). 12:58:23 I'm sad that there's no esolang named Footshit yet. 13:08:06 -!- zseri has joined. 13:18:11 hi 13:18:27 Hiszeri. 13:30:27 -!- augur has joined. 13:34:30 -!- augur has quit (Ping timeout: 240 seconds). 14:00:30 -!- doesthiswork has joined. 14:10:09 [wiki] [[Malbolge Unshackled]] https://esolangs.org/w/index.php?diff=52811&oldid=51692 * Malbranche * (+67) /* External resources */ Quine 14:26:05 -!- EternalBedrock has joined. 14:26:35 -!- EternalBedrock has quit (Client Quit). 14:40:40 -!- `^_^v has joined. 14:48:36 -!- MDude has joined. 14:57:56 -!- ATMunn has joined. 15:00:00 -!- doesthiswork has quit (Quit: Leaving.). 15:15:40 -!- jaboja has joined. 15:26:54 "Out for delivery: Expected to deliver tomorrow. Your expected delivery date: is Today." 15:26:57 TIME COMPRESSION 15:32:18 -!- erkin has quit (Quit: Ouch! Got SIGABRT, dying...). 15:46:12 fizzie: How do you think an Abstract Syntax Tree would act if it wasn't restricted to a tree formation? 15:46:23 -!- augur has joined. 15:47:04 (As in, a node could have multiple parents - or it could even be its own parent!) 15:50:36 -!- augur has quit (Ping timeout: 240 seconds). 15:56:27 fizzie: time zones? 15:56:58 * int-e hums. 15:57:06 "The good die young, there will be no tomorrow!" 16:07:56 [wiki] [[Mindscrew]] https://esolangs.org/w/index.php?diff=52812&oldid=52808 * Rdococ * (+493) /* Instructions */ Re-added the "(intermediate)" system. 16:32:46 -!- moony has joined. 17:05:36 -!- MrBismuth has quit (Ping timeout: 240 seconds). 17:22:18 -!- sebbu2 has joined. 17:25:45 -!- sebbu has quit (Ping timeout: 255 seconds). 17:44:01 -!- FreeFull has joined. 17:47:22 -!- erkin has joined. 17:51:11 Concept: Functions with both lexical & dynamic scoping. When a variable is referenced, such an esolang would first determine if it exists in the function's lexical scope. If not, it checks the caller's scope. 18:02:18 -!- augur has joined. 18:06:35 -!- augur has quit (Ping timeout: 240 seconds). 18:09:18 At the moment, I'm working on a concept for a low-level esolang........except subroutines are executed CPS-style (well, more like instruction pointer passing style (IPPS?), but still). 18:10:18 -!- MrBismuth has joined. 18:20:48 -!- Phantom_Hoover has joined. 18:25:58 -!- erkin has quit (Quit: Ouch! Got SIGABRT, dying...). 18:28:41 -!- jaboja has quit (Remote host closed the connection). 18:40:03 -!- imode has joined. 18:42:49 -!- jaboja has joined. 19:00:52 -!- AnotherTest has joined. 19:05:16 -!- imode has quit (Ping timeout: 240 seconds). 19:05:35 [wiki] [[Talk:BytePusher]] https://esolangs.org/w/index.php?diff=52813&oldid=41624 * Xav737 * (+1015) /* Networking? */ new section 19:16:22 -!- idris-bot has joined. 19:19:55 -!- imode has joined. 19:27:58 -!- brandonson has quit (Ping timeout: 276 seconds). 19:29:25 -!- brandonson has joined. 19:36:28 -!- keemyb has quit (Ping timeout: 240 seconds). 19:42:09 I have thought of abstract syntax tree that is not nceessarily a tree, it could be for example a RDF graph. (I also try to think of how to make AST for Magic: the Gathering) 19:42:45 zzo38: What would be a good language for Magic: the Gathering cards? 19:46:43 I thought of stuff such as, reprsenting "counter target spell" as [:counter [:target :spell]] and some transformation are automatically done to know their thing, you can also have more complicated stuff such as [:counter [:target [:and :red, :spell]]] for example 19:47:59 Do you think this make some sense to you? 19:50:32 -!- tswett has joined. 19:51:16 Currently, I'm conceptualizing a lang in which you can use an instruction to set a variable's value to the next instruction, and then arithmetic to increase or decrease it to point to different instructions relatively. 19:51:25 zzo38: I want it to be a reasonably general-purpose programming, not one full of built-ins. 19:51:42 I think I'm comfortable with mathematical realism again. But... only a certain watered-down version of it. 19:51:46 Do concepts like "red" and "counter" come from a standard library? 19:51:53 Yeah, sets exist, functions exist, the real numbers exist, and so on. 19:52:38 Hmm... I think we're having a lot of different conversations at once. Correct me if I'm wrong, though. 19:52:38 But the word "set" is underspecified. There are multiple different concepts which are all consistent with the expected behavior of "sets". 19:52:56 I'm not having a conversation, I'm just saying stuff independently of what anyone else is saying. 19:53:06 Ah, I do that a lot. 19:53:06 That's what rdococ does too. 19:53:23 I wish rdococ would stop. 19:53:23 Sometimes it gets on shachaf's nerves, so I've tried to say more meaningful things. 19:53:29 shachaf: They probably will yes, although the syntax here is just general-purpose RDF syntax. They could be done for general-purpose, or more specific, or something in between, maybe. 19:54:01 really delicious fungus syntax? 19:54:17 shachaf: do you wish I would stop too? 19:54:24 This is also allow you can implement the text editing effects, by AST alteration such as, "color words" such as :red and :blue and so on, will be the replacement. 19:54:40 So the continuum hypothesis is both true and false, depending on which version of sets you're dealing with. 19:55:28 tswett: An esolang with sets, in which you can define the continuum hypothesis's truth value in each program. 19:56:32 -!- tswett_ has joined. 19:58:04 rdococ: look up Setl. 19:59:08 -!- tswett__ has joined. 19:59:31 -!- tswett has quit (Ping timeout: 246 seconds). 20:00:01 shachaf: "RDF" is actually short for "Resource Description Framework" (although you need not use everything else that they put with it such as all of the ontology stuff; I am considering only the graph model and syntax and not the other stuff) 20:01:56 -!- tswett_ has quit (Ping timeout: 240 seconds). 20:03:12 -!- tswett__ has quit (*.net *.split). 20:03:12 -!- idris-bot has quit (*.net *.split). 20:03:12 -!- AnotherTest has quit (*.net *.split). 20:03:12 -!- MrBismuth has quit (*.net *.split). 20:03:44 -!- AnotherTest has joined. 20:04:14 -!- MrBismuth has joined. 20:06:34 -!- Antoxyde has quit (Remote host closed the connection). 20:17:28 -!- augur has joined. 20:19:08 -!- imode has quit (Ping timeout: 240 seconds). 20:23:02 -!- Antoxyde has joined. 20:24:17 -!- hppavilion[1] has joined. 20:27:51 -!- imode has joined. 20:39:37 -!- moonythedwarf has joined. 20:40:01 -!- Antoxyde has quit (Remote host closed the connection). 20:40:36 -!- Antoxyde has joined. 20:40:48 -!- Phantom_Hoover has quit (Ping timeout: 240 seconds). 20:41:53 -!- moony has quit (Ping timeout: 248 seconds). 20:59:28 -!- sleffy has joined. 21:26:10 Does any web browser programs include the "meta CSS"? 21:41:39 What is that? 21:41:40 -!- zseri has quit (Quit: Page closed). 22:07:18 -!- Phantom_Hoover has joined. 22:16:58 -!- sleffy has quit (Ping timeout: 276 seconds). 22:29:33 Do you like this? http://zzo38computer.org/textfile/miscellaneous/web_browser 22:36:34 yes im onboard. i suspect every bit of it can be engineered with extensions 22:37:26 zzo38: I like it, though I don't agree with it. 22:37:30 for instance vimperator gives the keyboard control already, user interfaces of most browsers are already almost completely customizable 22:37:35 But I only read a little bit. 22:39:15 ive seen the "pictures only on demand" as one of the more extreme noscript features i think 22:44:52 -!- idris-bot has joined. 23:02:39 -!- `^_^v has quit (Quit: This computer has gone to sleep). 23:18:40 -!- aloril has quit (Ping timeout: 246 seconds). 23:18:50 -!- relrod has quit (Ping timeout: 240 seconds). 23:20:45 -!- aloril has joined. 23:25:57 -!- pikhq has quit (Ping timeout: 240 seconds). 23:32:03 -!- pikhq has joined. 23:35:17 -!- tswett has joined. 23:37:20 -!- AnotherTest has quit (Ping timeout: 255 seconds). 23:41:03 -!- moonythedwarf has quit (Ping timeout: 255 seconds). 23:42:20 -!- moony has joined. 23:43:33 -!- aloril_ has joined. 23:44:37 I wonder how much of known mathematics has a known proof in Peano arithmetic. 23:44:38 -!- aloril has quit (Ping timeout: 248 seconds). 23:53:36 -!- Phantom_Hoover has quit (Read error: Connection reset by peer). 23:57:23 -!- GeekDude has changed nick to GibVent. 2017-08-16: 00:01:14 -!- sleffy has joined. 00:04:20 [wiki] [[TheSingularity]] M https://esolangs.org/w/index.php?diff=52814&oldid=52783 * HereToAnnoy * (+354) added tiny functionality 00:21:46 I have a thought that I'm going to monologue out, as I like to do. 00:22:11 Is ZFC arithmetically sound? 00:22:33 It seems like generally speaking, if ZFC proves some arithmetic statement, we'll then probably accept that statement as true. 00:23:03 So it seems like we also ought to accept the statement "if ZFC proves an arithmetic statement, then that statement is true". 00:23:24 In other words, the statement that ZFC is arithmetically sound. 00:25:15 Um, where was I going with this? I think I had a different motivation, actually. 00:26:29 Consider some hypothetical mathematician who believes exactly those statements that are provable in ZFC. 00:26:58 Let this mathematician be denoted by M. 00:27:14 I feel like M's beliefs can't really be consistent, then. And here's why. 00:27:51 If ZFC proves an arithmetic statement, then M will believe that the statement must therefore be true. 00:28:09 So presumably, M believes that if ZFC proves any arithmetic statement, then that statement is true. 00:28:21 But now we've got a problem! 00:28:38 Because ZFC does not prove the statement "if ZFC proves an arithmetic statement, then that statement is true". 00:29:11 Because that statement implies that ZFC is consistent, and ZFC does not prove itself consistent. 00:30:52 -!- sleffy has quit (Ping timeout: 276 seconds). 00:43:34 -!- hppavilion[1] has quit (Ping timeout: 255 seconds). 01:24:45 -!- doesthiswork has joined. 01:30:57 ZFC is hoped, wished, gently implored to not prove itself consistent 01:35:30 -!- Antoxyde has quit (Quit: Leaving). 02:05:50 <\oren\> https://twitter.com/BentleysQuest/status/896879322522202112 02:05:55 <\oren\> can we come across political lines and agree this is retarded? 02:06:48 <\oren\> "My father and uncle were pilots in WW11" "Sorry, I don't have Roman numerals on my keyboard." 02:10:44 ◢ ◣ ◤ ◥ these are wider than a character, what's the closest alternative to fill a triangle? 02:12:28 <\oren\> ◢◣◤◥ 02:13:26 wait aren't those the ones i used? 02:14:03 yes they are 02:14:04 <\oren\> oops. yeah 02:16:31 <\oren\> ⧸⧹ 02:16:40 i want ╱ and ╲ but with one of the halves filled 02:17:22 <\oren\> izabera: yeah my font has those but they arent standard 02:17:29 <\oren\>  02:19:16 i suppose i'll have to settle for ▛ ▙ ▟ ▜ 02:29:24 -!- hppavilion[1] has joined. 02:32:22 -!- relrod has joined. 02:32:25 -!- relrod has quit (Changing host). 02:32:25 -!- relrod has joined. 02:33:47 \oren\, i agree it is retarded. 02:34:48 ⅯⅯⅩⅦ 02:48:40 -!- relrod has quit (Quit: .). 02:49:16 -!- relrod has joined. 02:49:17 -!- relrod has quit (Changing host). 02:49:17 -!- relrod has joined. 02:56:49 ▟ ██ ▟▙ ▙ 02:56:50 ▟█ ██ ▟██▙ █▙ 02:56:52 ▟█▛ ██ ▟████▙ ▜█▙ 02:56:54 ▟██▄▄▄▄▄▄▄ ▜█▙ ██ ▟█▛ ▟██████▙ ▄▄▄▄▄▄▄██▙ 02:56:56 ▜██▀▀▀▀▀▀▀ ▜██████▛ ▟█▛ ██ ▜█▙ ▀▀▀▀▀▀▀██▛ 02:56:58 ▜█▙ ▜████▛ ██ ▟█▛ 02:57:00 ▜█ ▜██▛ ██ █▛ 02:57:02 ▜ ▜▛ ██ ▛ 02:57:14 take it to #trains 02:59:45 `unidecode ▛▙▟▜ 02:59:52 ​[U+259B QUADRANT UPPER LEFT AND UPPER RIGHT AND LOWER LEFT] [U+2599 QUADRANT UPPER LEFT AND LOWER LEFT AND LOWER RIGHT] [U+259F QUADRANT UPPER RIGHT AND LOWER LEFT AND LOWER RIGHT] [U+259C QUADRANT UPPER LEFT AND UPPER RIGHT AND LOWER RIGHT] 03:00:38 Faskinating. 03:01:01 -!- ATMunn has quit (Quit: See ya! o/). 03:02:27 who wants to write a command line ddr? 03:12:25 -!- [io] has joined. 03:13:02 -!- iovoid has changed nick to Guest49762. 03:13:02 -!- Guest49762 has quit (Killed (moon.freenode.net (Nickname regained by services))). 03:13:02 -!- [io] has changed nick to iovoid. 03:23:32 -!- MrBismuth has quit (Quit: https://www.youtube.com/watch?v=xIIqYqtR1lY -- Suicide is Painless - Johnny Mandel). 03:36:16 -!- hppavilion[0] has joined. 03:38:41 -!- hppavilion[1] has quit (Ping timeout: 246 seconds). 03:39:50 -!- hppavilion[1] has joined. 03:41:32 -!- hppavilion[0] has quit (Ping timeout: 260 seconds). 03:45:41 -!- hppavilion[1] has quit (Ping timeout: 246 seconds). 03:46:11 -!- tswett has quit (Quit: Leaving). 04:01:51 -!- GibVent has changed nick to GeekDude. 04:24:08 -!- moony has quit (Read error: Connection reset by peer). 04:24:34 -!- moony has joined. 04:27:54 -!- sleffy has joined. 04:44:22 -!- sleffy has quit (Ping timeout: 276 seconds). 04:45:12 -!- sleffy has joined. 05:03:04 -!- jaboja has quit (Remote host closed the connection). 05:10:00 -!- doesthiswork has quit (Quit: Leaving.). 05:10:31 -!- doesthiswork has joined. 05:11:50 izabera: You can use them, if you use a character set that is including them. 05:40:25 -!- hppavilion[1] has joined. 05:50:58 -!- Sgeo has quit (Ping timeout: 240 seconds). 05:58:31 -!- Sgeo has joined. 06:01:29 -!- sleffy has quit (Ping timeout: 246 seconds). 06:01:44 [wiki] [[MIX (Knuth)]] https://esolangs.org/w/index.php?diff=52815&oldid=52727 * Zzo38 * (+304) MIX256 06:03:35 -!- hppavilion[1] has quit (Ping timeout: 246 seconds). 06:33:26 -!- erkin has joined. 06:37:27 -!- moony has quit (Ping timeout: 240 seconds). 06:39:44 -!- MrBusiness has joined. 07:01:08 -!- FreeFull has quit. 07:22:02 -!- shikhin has changed nick to notshikhin. 07:22:29 -!- notshikhin has changed nick to shikhin. 07:34:24 -!- hppavilion[1] has joined. 07:45:48 -!- erkin has quit (Quit: Ouch! Got SIGABRT, dying...). 07:47:16 -!- erkin has joined. 07:52:26 -!- doesthiswork has quit (Quit: Leaving.). 08:01:37 -!- augur has quit (Remote host closed the connection). 08:06:44 -!- hppavilion[0] has joined. 08:07:04 Some useful constants that aren't in math.h would be pi/180, 180/pi, and tau. 08:07:28 (where tau = twice pi, or the period of trigonometric functions) 08:10:17 -!- hppavilion[1] has quit (Ping timeout: 246 seconds). 08:31:00 Concept: An esolang in which programs write Abstract Syntax Trees themselves with a BF-like system of instructions. 08:31:19 (BF-like optional.) 08:37:17 -!- hppavilion[0] has quit (Ping timeout: 260 seconds). 08:51:17 -!- augur has joined. 09:02:39 -!- erkin has quit (Quit: Ouch! Got SIGABRT, dying...). 09:03:02 -!- erkin has joined. 09:13:49 -!- Antoxyde has joined. 09:28:37 -!- augur has quit (Remote host closed the connection). 09:37:33 -!- AnotherTest has joined. 09:38:20 -!- erkin has quit (Quit: Ouch! Got SIGABRT, dying...). 09:42:15 -!- AnotherTest has quit (Ping timeout: 255 seconds). 09:48:53 -!- erkin has joined. 09:58:49 -!- imode has quit (Ping timeout: 246 seconds). 10:36:17 -!- Sgeo has quit (Ping timeout: 260 seconds). 10:40:03 izabera: surely a command line DDR clone would just use 🢀 🢃 🢁 🢂 🢄 🢅 🢆 🢇 ? 10:55:47 -!- AnotherTest has joined. 10:56:34 -!- Sgeo has joined. 11:28:55 [wiki] [[Mindscrew]] https://esolangs.org/w/index.php?diff=52816&oldid=52812 * Rdococ * (-3104) Completely overhauled the language to something that actually makes sense for once (O_O) 11:30:45 [wiki] [[User:Rdococ]] https://esolangs.org/w/index.php?diff=52817&oldid=52809 * Rdococ * (+12) /* Esolangs of mine that I consider decent, or are yet unevaluated */ 11:31:54 -!- Mayoi has joined. 11:33:04 -!- erkin has quit (Read error: Connection reset by peer). 11:34:56 -!- boily has joined. 11:35:32 `5 w 11:35:41 1/1:e-module//E-modules are modules over a web ring. Uaneb invented them. \ auto//Auto is the German word for car. \ cdop//CDOP is OCPD, except with the letters in the *proper* order. \ hash 2346ad27d7568ba9896f1b7da6b5991251debdf2//hash 2346ad27d7568ba9896f1b7da6b5991251debdf2 \ hand//A hand in the bush is better than a stoned bird. 11:35:54 `forget auto 11:35:56 Forget what? 11:39:07 [wiki] [[Mindscrew]] https://esolangs.org/w/index.php?diff=52818&oldid=52816 * Rdococ * (+367) Actual TC proof for once, if an incredibly obvious one. 11:40:23 [wiki] [[User:Rdococ]] M https://esolangs.org/w/index.php?diff=52819&oldid=52817 * Rdococ * (+132) 11:40:59 [wiki] [[User:Rdococ]] M https://esolangs.org/w/index.php?diff=52820&oldid=52819 * Rdococ * (+47) /* Esolangs of mine that I consider decent, or are yet unevaluated */ 11:42:51 [wiki] [[Mindscrew]] M https://esolangs.org/w/index.php?diff=52821&oldid=52818 * Rdococ * (+31) /* Computational Class */ Minor terminology cha--er, modification. 12:05:25 [wiki] [[Mindscrew]] M https://esolangs.org/w/index.php?diff=52822&oldid=52821 * Rdococ * (+29) /* Cat program */ 12:05:45 damn lag 12:08:56 [wiki] [[Mindscrew]] M https://esolangs.org/w/index.php?diff=52823&oldid=52822 * Rdococ * (+29) 12:10:16 [wiki] [[User:Rdococ]] M https://esolangs.org/w/index.php?diff=52824&oldid=52820 * Rdococ * (-174) 12:21:28 -!- AnotherTest has quit (Ping timeout: 240 seconds). 12:23:35 FireFly: no that's awful 12:24:09 they render quite well in my font at least 12:29:28 rdochelloc, izabellora, FirelloFly. 12:29:40 -!- boily has quit (Quit: OAK CHICKEN). 12:29:56 hi boily...oh 12:30:19 -!- augur has joined. 12:30:43 -!- augur has quit (Remote host closed the connection). 12:41:27 [wiki] [[Mindscrew]] M https://esolangs.org/w/index.php?diff=52825&oldid=52823 * Rdococ * (+24) /* Instructions */ 12:43:06 [wiki] [[Mindscrew]] M https://esolangs.org/w/index.php?diff=52826&oldid=52825 * Rdococ * (+14) /* Examples */ 13:15:43 -!- sftp has quit (Max SendQ exceeded). 13:16:11 -!- sftp has joined. 13:26:30 -!- Mayoi has changed nick to erkin. 13:37:43 -!- jaboja has joined. 13:44:02 -!- doesthiswork has joined. 13:52:19 -!- atehwa has quit (Ping timeout: 276 seconds). 13:52:58 -!- atehwa has joined. 14:20:00 -!- oerjan has joined. 14:51:09 -!- ATMunn has joined. 14:52:59 after only 15352 attempts i managed to record a win https://asciinema.org/a/GPYfU9Rn9vu1TJVQKdHDm5azP 15:02:44 -!- doesthiswork has quit (Quit: Leaving.). 15:06:43 -!- `^_^v has joined. 15:07:36 -!- jaboja has quit (Ping timeout: 255 seconds). 15:16:09 izabera: are you coding an AI? 15:20:06 or is it merely a terminal clone of https://www.chiark.greenend.org.uk/~sgtatham/puzzles/js/flood.html ? 15:23:10 written in bash, I guess... given the video title and your history 15:25:04 `? izabera 15:25:05 izabera is a bradyherpetologist. She is probably implemented in bash. 15:31:38 -!- sftp has quit (Max SendQ exceeded). 15:32:02 -!- sftp has joined. 15:32:24 `? sgtm 15:32:25 Sergeant Mustard 15:32:36 `5 w 15:32:40 1/2:betty crocker//Betty Crocker is a notorious gambler. \ fractal//There used to be an entry for "fractal", but it burst into a thousand pieces (whose dimension was approximately sqrt(3)) which subsequently got lost in a Mandelbrot-shaped singularity. \ coonspirator//A coonspirator is caterpillar silk wrapped in collaborators. \ fnord//? ¯\(°​ 15:32:44 `n 15:32:44 2/2:_o)/¯ \ broily//broily is like boily, but more broiling. 15:33:10 `dowg fractal 15:33:18 9163:2016-10-05 le/rn fractal/There used to be an entry for "fractal", but it burst into a thousand pieces (whose dimension was approximately sqrt(3)) which subsequently got lost in a Mandelbrot-shaped singularity. \ 9162:2016-10-05 le/rn fractal/There used to be an entry for "fractal", but it burst into a thousand pieces (whose 15:33:50 -!- erkin has quit (Quit: Ouch! Got SIGABRT, dying...). 15:35:17 I'm sad that there's no esolang named Footshit yet. <-- i'm not hth thth 15:35:21 wat 15:35:41 (stupid t) 15:35:43 @google hth thth 15:35:45 https://www.facebook.com/thth.hth 15:35:49 ooh 15:35:52 ... maybe not. 15:52:41 how can ai be involved in that? 15:53:43 -!- jaboja has joined. 16:02:52 -!- ais523 has joined. 16:22:58 -!- ais523 has quit (Remote host closed the connection). 16:24:08 -!- ais523 has joined. 16:29:30 -!- jaboja has quit (Ping timeout: 255 seconds). 17:07:43 [wiki] [[InSpace]] N https://esolangs.org/w/index.php?oldid=52827 * Zayne * (+1149) First edit 17:08:01 [wiki] [[User:Zayne]] https://esolangs.org/w/index.php?diff=52828&oldid=52372 * Zayne * (+16) 17:08:36 [wiki] [[InSpace]] https://esolangs.org/w/index.php?diff=52829&oldid=52827 * Zayne * (+42) 17:09:00 -!- ais523 has quit. 17:10:28 [wiki] [[2014]] https://esolangs.org/w/index.php?diff=52830&oldid=52370 * Zayne * (+9) removing User: from the label for AndoDaan 17:12:55 [wiki] [[2014]] https://esolangs.org/w/index.php?diff=52831&oldid=52830 * Zayne * (+810) Implemented 17:16:10 -!- erkin has joined. 17:21:39 -!- FreeFull has joined. 17:25:15 [wiki] [[User talk:Zzo38]] https://esolangs.org/w/index.php?diff=52832&oldid=41022 * Zayne * (+189) /* Thanks :) */ new section 17:25:52 [wiki] [[User talk:Zayne]] N https://esolangs.org/w/index.php?oldid=52833 * Zayne * (+134) Created page with "Because nobody made a topic I decided to make this page --~~~~" 17:31:25 [wiki] [[2014]] https://esolangs.org/w/index.php?diff=52834&oldid=52831 * Oerjan * (-9) Undo revision 52830 by [[Special:Contributions/Zayne|Zayne]] ([[User talk:Zayne|talk]]) (We have a policy against this) 17:31:52 -!- oerjan has quit (Quit: Later). 17:55:08 <\oren\> one day they'll have enough public CCTV systems to have some sort of google earth live in some places 17:58:23 -!- zseri has joined. 18:00:02 <\oren\> https://askubuntu.com/questions/938606/dwarf-fortress-starting-during-apt-get-upgrade 18:05:36 -!- TellsTogo has joined. 18:09:56 -!- moony has joined. 18:12:33 [wiki] [[Special:Log/newusers]] create * StellatedHexahedron * New user account 18:15:19 -!- Phantom_Hoover has joined. 18:21:34 -!- TellsTogo has quit (Ping timeout: 260 seconds). 18:23:28 -!- TellsTogo has joined. 18:56:24 > minBound - length [42] == maxBound 18:56:26 True 19:02:59 -!- TellsTogo has quit (Ping timeout: 260 seconds). 19:03:29 [wiki] [[Esolang:Introduce yourself]] https://esolangs.org/w/index.php?diff=52835&oldid=52775 * StellatedHexahedron * (+350) /* Introductions */ 19:07:36 -!- MDude has quit (Remote host closed the connection). 19:08:31 -!- AnotherTest has joined. 19:24:51 -!- trn has quit (Remote host closed the connection). 19:32:31 -!- erkin has quit (Quit: Ouch! Got SIGABRT, dying...). 19:45:03 -!- trn has joined. 19:46:54 -!- imode has joined. 19:54:42 -!- augur has joined. 21:12:17 -!- jaboja has joined. 21:17:33 `? cats 21:17:34 Cats are cool, but should be illegal. 21:17:53 Taneb: You invented cats, didn't you? 21:18:22 i wonder, did taneb invent ME? 21:19:40 shachaf, fun fact, I used to be afraid of cats 21:19:52 moony, nah, but like half of the other Windows versions I did 21:20:21 Taneb: But now you like them. 21:21:44 It certainly could be interpreted that way 21:27:15 [wiki] [[ಠ ಠ]] M https://esolangs.org/w/index.php?diff=52836&oldid=52592 * Totallyhuman * (-1) ಠ_ಠ 21:28:43 [wiki] [[Special:Log/newusers]] create * Mr. Xcoder * New user account 21:29:02 -!- jaboja has quit (Ping timeout: 260 seconds). 21:35:17 [wiki] [[Esolang:Introduce yourself]] M https://esolangs.org/w/index.php?diff=52837&oldid=52835 * Mr. Xcoder * (+272) /* Introductions */ 21:37:18 [wiki] [[ಠ ಠ]] https://esolangs.org/w/index.php?diff=52838&oldid=52836 * MD XF * (+2936) Add the actual lang 21:39:02 [wiki] [[ಠ ಠ]] M https://esolangs.org/w/index.php?diff=52839&oldid=52838 * Totallyhuman * (+26) ಠ_ಠ 21:39:02 [wiki] [[User:Mr. Xcoder]] N https://esolangs.org/w/index.php?oldid=52840 * Mr. Xcoder * (+296) added stuff 21:39:28 [wiki] [[ಠ ಠ]] M https://esolangs.org/w/index.php?diff=52841&oldid=52839 * MD XF * (+1) 21:39:38 [wiki] [[ಠ ಠ]] M https://esolangs.org/w/index.php?diff=52842&oldid=52841 * MD XF * (-27) 21:40:18 [wiki] [[ಠ ಠ]] M https://esolangs.org/w/index.php?diff=52843&oldid=52842 * Totallyhuman * (+26) ಠ_ಠ 21:47:29 [wiki] [[ಠ ಠ]] https://esolangs.org/w/index.php?diff=52844&oldid=52843 * MD XF * (+11) /* Conditional Statements */ 21:53:54 -!- zseri has quit (Ping timeout: 260 seconds). 21:54:56 -!- jaboja has joined. 22:50:33 -!- Lucen has joined. 22:52:22 -!- Lucen has quit. 22:55:39 -!- augur has quit (Remote host closed the connection). 22:56:14 -!- augur has joined. 23:00:58 -!- augur has quit (Ping timeout: 264 seconds). 23:03:34 -!- wob_jonas has joined. 23:04:29 -!- Mr2001 has quit (Ping timeout: 260 seconds). 23:04:59 -!- `^_^v has quit (Quit: This computer has gone to sleep). 23:14:06 Could you point me to a program to encode an image to a jpeg but keep some blocks from an old jpeg unchanged losslessly? I'd like this for editing parts of a jpeg image while most of the area is untouched 23:18:11 -!- imode has quit (Ping timeout: 246 seconds). 23:20:38 -!- AnotherTest has quit (Ping timeout: 246 seconds). 23:28:09 -!- wob_jonas has quit (Quit: http://www.kiwiirc.com/ - A hand crafted IRC client). 23:29:11 -!- wob_jonas has joined. 23:39:49 -!- augur has joined. 23:40:12 -!- Sgeo has quit (Read error: Connection reset by peer). 23:40:37 -!- Sgeo has joined. 23:43:56 -!- boily has joined. 23:53:54 `6 w 23:53:55 ​/home/hackbot/hackbot.hg/multibot_cmds/lib/limits: line 5: exec: 6: not found 23:53:59 meh. 23:54:01 `5 w 23:54:06 1/2:typoglycerine//Typoglycerine is an explosive that scrambles the letters inside a word. \ örjan//Örjan is the diæresed twin. He will punctuate your vöẅëls, and maybe a few other unsuspecting letters. \ the universe//The universe was invented by Taneb as an opposing force to oerjan. Escardó proved that it was indiscreet. \ mips//MIPS Is P 23:54:07 `n 23:54:08 2/2:rohibited in Singapore. \ imho//IMHO means "In My Holy Omniscience". 23:57:01 -!- oerjan has joined. 2017-08-17: 00:00:20 " Suppose you have a man eating chicken. Is it a man eating chicken or a man eating chicken?" => see https://stickman.qntm.org/comics.php?n=567 00:01:21 Sam Hughes made a webcomic?!?!? 00:01:33 boily: also, how about a man eating manatee 00:01:41 Sgeo: yes, way way back when webcomics weren't yet so fashionable 00:01:51 it's my favourite webcomic of all time 00:01:55 oh the huge manatee, presumably 00:02:14 not because it's the best webcomic, but because it's the one I read first and introduced me to the world of webcomics 00:02:44 `dowg password 00:02:51 11081:2017-07-11 learn The password of the month is blowin\' in the wind. \ 10981:2017-06-02 revert \ 10980:2017-06-02 revert \ 10979:2017-06-02 learn The password of the month is out of date tdnh \ 10898:2017-05-14 le/rn password//The password of the month is poochpoochpoochpoochpooch \ 10595: 00:02:58 wellob_jonasgelloerjan. 00:03:05 are manatees edible? 00:03:18 `learn The password of the word is unacceptably delayed 00:03:21 Relearned 'password': The password of the word is unacceptably delayed 00:03:36 (due to HackEgo crashing, but still...) 00:04:27 'ily. 00:04:39 What's the national mushroom of Norway? 00:05:12 hm i'll have to check 00:06:58 doesn't seem like there is an official one, but the top hit for "nasjonalsopp" suggests it ought to be chanterelles. 00:07:15 (most of the other hits i see are about the japanese one.) 00:07:25 do they have other national organisms? 00:07:42 we have a national bird, fossekall 00:07:55 I don't understand how this "national tree" thing works, it's like an American habit 00:08:08 what is the point of them? 00:08:14 oerjan: that gives me a clue about the national philospher as well hth 00:08:14 (also, are you asking about the norwegians or the japanese, your pronoun would seem to suggest the latter) 00:09:24 shachaf: the top hit for that mentions Arne Næss, which is exactly who i expected. (which goes for the mushroom too.) 00:10:03 oerjan: what, it's not kant? 00:10:07 although hit #3 sarcastically suggest "Egner". 00:10:16 shachaf: Kant wasn't norwegian hth 00:10:22 nor are chanterelles hth 00:10:46 unlike Kant, they at least grow wild in norway. 00:12:51 are there cross-matching requirements for the national organisms? like, does the national bird have to nest on the national tree, the national fungi grow on the national tree, the national bird eat larvas of the national arthropod? 00:13:03 (Egner was a children's author, and wrote a book that some people love to sarcastically claim is how norwegians think about politics and morals) 00:13:42 (especially those people who don't like social democratics) 00:13:47 wob_jonas: Wikipedia says the saker falcon is the national bird of Hungary. 00:15:10 shachaf: it looks like that's a "bird of the year" 00:15:19 of 2000 00:15:30 see https://hu.wikipedia.org/wiki/Az_%C3%A9v_madara 00:15:36 Oh, well, 2000 was the national year. 00:16:12 no. no it wasn't. 1986 was the national year I think. 00:16:49 wob_jonas: also, the norwegian "national whatevers" are generally not declared by the government, but more like voted on by the listeners to the Nitimen radio program. 00:17:06 oerjan: sure 00:17:47 which remarkably is still produced, i think. although i don't listen to radio much. 00:17:58 (as in, i don't have one.) 00:18:44 oerjan: the national coat of arms is set by the parliment in the constitution only because it's used on official papers issued by the government and on buildings of government institutions, so it has to be something clearly recognizable to be able to prove fraud if someone tries to use it and pretends they are doing some government function 00:18:49 it's like a state trademark basically 00:19:29 And perhaps the constitution sets the flag because red-white-green colored twine is also used in some of those documents 00:20:00 well the flag is also set by law in norway, iirc. 00:20:20 maybe the coat of arms too. 00:20:35 the national anthem is only traditional, i think. 00:20:43 yes, the anthem is traditional 00:21:26 yep, never officially declared. 00:21:30 also, some US states have a national motto 00:21:30 oerjan: i was just trying to make a pun on the norwegian name of the mushroom tdnw 00:21:38 shachaf: i know hth 00:21:39 US states have more than a motto. 00:22:13 the norwegian king has a motto, but that's not by law, he selects it himself. it just happens to be the same as that of his father and grandfather. 00:22:17 https://statesymbolsusa.org/states/united-states/california 00:22:25 (Alt for Norge) 00:22:45 oerjan: careful, next he'll be trying to seize ctrl 00:23:13 is the motto written in his coat of arms? 00:23:40 * oerjan swats shachaf -----### 00:24:40 shachaf: wait, "state dance"? what the heck is that for? do army soldiers have to dance it when they are appointed as an official? 00:24:43 wob_jonas: doesn't look like it although it's been used on some coins https://no.wikipedia.org/wiki/Alt_for_Norge 00:25:59 a state dance and a state folk dance? wow 00:26:13 a state fish and a state marine fish 00:26:17 "State Mineral: Gold" 00:28:08 -!- augur has quit (Remote host closed the connection). 00:28:11 i wasn't sure he even had a coat of arms but https://no.wikipedia.org/wiki/Kongev%C3%A5pen#Etter_1905 00:28:19 i can't see the motto on it though 00:28:46 wob_jonas: This is just some website, who knows whether it's legitimate. 00:29:36 European noblemen usually have a coat of arms. Or at least a family coat of arms. 00:30:03 -!- Antoxyde_ has joined. 00:31:18 It's popular in America as well. 00:31:26 There's even a constitutional amendment about it. 00:31:52 wob_jonas: norway has abolished nobility, there's just the royals left. 00:31:58 shachaf: amendment about what? 00:32:24 (it was done in the original constitution from 1814, i think) 00:32:28 -!- Antoxyde has quit (Ping timeout: 240 seconds). 00:32:44 oerjan: people can consider themselves noblemen for historical reasons even if nobility is officially abolished in their country. 00:32:46 wob_jonas: The right to bear arms. 00:33:50 I see 00:33:58 * oerjan whacks shachaf with the skillet ==\____/ 00:36:35 hm no, a law from 1821 it seems. 00:37:04 (the constitution disallowed creating new nobility) 00:38:03 -!- augur has joined. 00:40:51 `? empty 00:40:52 empty? ¯\(°​_o)/¯ 00:41:02 `? null 00:41:02 null? ¯\(°​_o)/¯ 00:41:04 `? nil 00:41:05 nil? ¯\(°​_o)/¯ 00:41:06 `? NULL 00:41:07 NULL? ¯\(°​_o)/¯ 00:41:08 `? nulptr 00:41:09 nulptr? ¯\(°​_o)/¯ 00:41:14 `? nullptr 00:41:15 nullptr? ¯\(°​_o)/¯ 00:41:17 `? none 00:41:18 none? ¯\(°​_o)/¯ 00:41:23 -!- Sgeo_ has joined. 00:41:34 `? nothing 00:41:34 Nothing would have been better than to create this wisdom entry. 00:41:45 -!- Sgeo has quit (Ping timeout: 246 seconds). 00:42:04 `? nullopt 00:42:05 nullopt? ¯\(°​_o)/¯ 00:42:36 https://www.youtube.com/watch?v=ns1SGo3WCF4 00:48:39 -!- wob_jonas has quit (Quit: http://www.kiwiirc.com/ - A hand crafted IRC client). 00:54:21 boily: youtube showed me an ad for Annabelle first, i got a bit confused. 00:57:35 -!- jaboja has quit (Ping timeout: 240 seconds). 00:58:33 -!- Sgeo_ has quit (Ping timeout: 246 seconds). 00:58:57 -!- Sgeo has joined. 01:04:58 -!- Sgeo_ has joined. 01:05:12 -!- Sgeo has quit (Ping timeout: 246 seconds). 01:06:54 oerjan: you should use an adblocker hth 01:08:04 -!- Phantom_Hoover has quit (Read error: Connection reset by peer). 01:08:30 i block plenty of ads, although by adding annoying ad sites by hand to the restricted sites list. 01:08:53 but youtube has been left in peace so far. 01:09:28 (google in general has not.) 01:09:45 block everything, use noscript, brush your teeth. 01:10:15 but i get a bad conscience if i block all ads on sites i like 01:10:38 (of course i hardly ever _follow_ an ad.) 01:11:48 but even reddit started showing annoying ads (and broke their own system for giving them dumbs down) 01:15:25 *thumbs 01:21:46 California designated "a shelter pet" as the official state pet in 2015 01:21:53 I should get the official state pet. 01:28:37 un cabot de refuge. 01:29:07 un chat de refuge 01:30:08 les chats ne sont pas des cabots, ce sont des matous. 01:35:36 -!- doesthiswork has joined. 01:41:57 -!- augur has quit (Remote host closed the connection). 01:44:56 -!- augur has joined. 01:55:33 -!- augur has quit (Remote host closed the connection). 02:00:34 -!- augur has joined. 02:01:01 -!- Antoxyde_ has quit (Quit: Leaving). 02:04:06 -!- imode has joined. 02:05:10 -!- augur has quit (Ping timeout: 264 seconds). 02:07:47 -!- MDude has joined. 02:10:42 @metar CYUL 02:10:42 CYUL 170100Z 27004KT 30SM SCT250 18/08 A3002 RMK CI3 SLP168 DENSITY ALT 500FT 02:20:01 -!- jaboja has joined. 02:38:52 -!- boily has quit (Quit: WAGON CHICKEN). 02:45:04 -!- doesthiswork has quit (Ping timeout: 248 seconds). 02:47:51 -!- doesthiswork has joined. 03:01:32 -!- jaboja has quit (Ping timeout: 260 seconds). 03:02:24 -!- ATMunn has quit (Quit: See ya! o/). 03:11:27 -!- imode has quit (Ping timeout: 240 seconds). 04:00:08 -!- imode has joined. 04:15:19 -!- oerjan has quit (Quit: Nite). 04:54:18 [wiki] [[Brainfuck]] M https://esolangs.org/w/index.php?diff=52845&oldid=51304 * Rdococ * (+94) /* Related languages */ 04:55:02 [wiki] [[Brainfuck]] M https://esolangs.org/w/index.php?diff=52846&oldid=52845 * Rdococ * (+16) /* Related languages */ 05:04:44 [wiki] [[Mindscrew]] https://esolangs.org/w/index.php?diff=52847&oldid=52826 * Rdococ * (+478) 05:05:21 -!- augur has joined. 05:05:52 [wiki] [[Mindscrew]] https://esolangs.org/w/index.php?diff=52848&oldid=52847 * Rdococ * (+237) /* Computational Class */ 05:06:27 Mindscrew is the opposite of newbiefuck in a way, because ] is a NOP in the former, while [ is a NOP in the latter. 05:06:58 It also has recursive procedures which can be written to a second tape, but that's another story. 05:10:00 -!- doesthiswork has quit (Quit: Leaving.). 05:10:31 -!- doesthiswork has joined. 05:11:06 Himode. 05:11:21 Oh - and doesthiswork. 05:12:01 doesthelloswork 05:14:41 I'm trying to figure out why pigs and goats have wattles 05:29:55 heloooloovoo? 05:33:58 I planned on creating a low level language where the instruction pointer itself was accessible, along with labeled gotos and scope (let x = 3 in ... end). 05:42:06 -!- APic has quit (K-Lined). 05:42:07 -!- jjthrash has quit (K-Lined). 05:42:07 -!- myname has quit (K-Lined). 05:42:07 -!- bibibi has quit (K-Lined). 05:42:07 -!- Deewiant has quit (K-Lined). 05:42:08 -!- zzo38 has quit (K-Lined). 05:42:08 -!- erdic has quit (K-Lined). 05:42:08 -!- FreeFull has quit (K-Lined). 05:42:08 -!- sftp has quit (K-Lined). 05:42:08 -!- Melvar has quit (K-Lined). 05:42:08 -!- lambdabot has quit (K-Lined). 05:42:08 -!- vifino has quit (K-Lined). 05:42:08 -!- olsner has quit (K-Lined). 05:42:09 -!- puckipedia has quit (K-Lined). 05:42:09 -!- BooK_ has quit (K-Lined). 05:42:09 -!- Guest6666 has quit (K-Lined). 05:42:09 -!- moony has quit (K-Lined). 05:42:09 -!- atehwa has quit (K-Lined). 05:42:09 -!- rodgort has quit (K-Lined). 05:42:09 -!- trn has quit (K-Lined). 05:42:09 -!- aloril_ has quit (K-Lined). 05:42:10 -!- int-e has quit (K-Lined). 05:42:10 -!- relrod has quit (K-Lined). 05:42:10 -!- idris-bot has quit (K-Lined). 05:42:10 -!- danieljabailey has quit (K-Lined). 05:42:10 -!- brandonson has quit (K-Lined). 05:42:10 -!- diginet has quit (K-Lined). 05:42:10 -!- j-bot has quit (K-Lined). 05:42:10 -!- deltab has quit (K-Lined). 05:42:11 -!- ineiros has quit (K-Lined). 05:42:11 -!- tromp has quit (K-Lined). 05:42:11 -!- joast has quit (K-Lined). 05:42:11 -!- HackEgo has quit (K-Lined). 05:42:11 -!- GeekDude has quit (K-Lined). 05:42:11 -!- hakatashi has quit (K-Lined). 05:42:12 -!- fractal_ has quit (K-Lined). 05:42:12 -!- catern has quit (K-Lined). 05:42:12 -!- Warrigal has quit (K-Lined). 05:42:12 -!- Yurume_______ has quit (K-Lined). 05:42:12 -!- pelegreno_____ has quit (K-Lined). 05:42:12 -!- jix has quit (K-Lined). 05:42:12 -!- paul2520 has quit (K-Lined). 05:42:13 -!- lifthrasiir has quit (K-Lined). 05:42:13 -!- \oren\ has quit (K-Lined). 05:42:13 -!- izabera has quit (K-Lined). 05:42:13 -!- viznut has quit (K-Lined). 05:42:13 -!- Gregor has quit (K-Lined). 05:42:13 -!- Jafet has quit (K-Lined). 05:42:14 -!- augur has quit (K-Lined). 05:42:14 -!- Sgeo_ has quit (K-Lined). 05:42:14 -!- doesthiswork has quit (K-Lined). 05:42:14 -!- MDude has quit (K-Lined). 05:42:14 -!- newsham has quit (K-Lined). 05:42:14 -!- pikhq has quit (K-Lined). 05:42:14 -!- heroux has quit (K-Lined). 05:42:14 -!- quintopia has quit (K-Lined). 05:42:14 -!- Cale has quit (K-Lined). 05:42:14 -!- contrapumpkin has quit (K-Lined). 05:42:15 -!- digitalcold has quit (K-Lined). 05:42:15 -!- clog has quit (K-Lined). 05:42:15 -!- xa0 has quit (K-Lined). 05:42:27 -!- shachaf has quit (K-Lined). 05:42:27 -!- yorick has quit (K-Lined). 05:43:09 <^v> Oof 05:43:20 -!- clog has joined. 05:43:21 -!- aloril has joined. 05:43:26 -!- Yurume_______ has joined. 05:43:30 -!- mtve has quit (K-Lined). 05:43:39 -!- rodgort has joined. 05:43:46 -!- paul2520_ has joined. 05:43:50 -!- hakatashi has joined. 05:43:51 -!- tromp has joined. 05:45:51 -!- Melvar has joined. 05:45:55 -!- jjthrash has joined. 05:45:56 -!- HackEgo has joined. 05:46:07 -!- Jafet has joined. 05:46:21 -!- copumpkin has quit (Ping timeout: 255 seconds). 05:46:25 -!- relrod has joined. 05:46:48 -!- pelegreno______ has joined. 05:46:55 -!- Jafet has quit (Client Quit). 05:46:56 -!- doesthiswork has joined. 05:46:58 -!- G33kDude has joined. 05:47:36 -!- puckipedia has joined. 05:48:00 -!- danieljabailey has joined. 05:48:16 -!- contrapumpkin has joined. 05:48:17 -!- fractal has joined. 05:48:25 -!- sftp has joined. 05:48:31 -!- vifino has joined. 05:48:35 -!- relrod has quit (Changing host). 05:48:35 -!- relrod has joined. 05:48:43 -!- shachaf has joined. 05:48:51 -!- shachaf has quit (Changing host). 05:48:51 -!- shachaf has joined. 05:49:08 -!- lifthrasiir has joined. 05:49:11 -!- diginet has joined. 05:49:25 -!- Deewiant has joined. 05:50:13 -!- Cale has joined. 05:50:21 -!- olsner has joined. 05:50:35 -!- bibibi has joined. 05:50:43 -!- xa0 has joined. 05:50:49 -!- catern has joined. 05:51:26 -!- mtve has joined. 05:52:58 -!- copumpkin has joined. 05:53:36 -!- augur has joined. 05:53:37 -!- trn has joined. 05:53:44 -!- Gregor has joined. 05:54:52 -!- izabera has joined. 05:55:03 Holy brainfuck. 06:01:12 -!- Sgeo has joined. 06:06:35 rdococ: have you ever heard of 'Mouse'? 06:06:39 the programming language? 06:08:45 Is there a way to guarantee that a specific section of compiled-in data always appears at a specific location within an executable? 06:09:14 Or otherwise be able to reliable determine specifically where it will end up? 06:09:18 this is why we have segments. 06:10:40 Am I going to need to write this in Assembly? 06:10:59 what're you writing. 06:11:11 Implementation of https://esolangs.org/wiki/Braintrust 06:11:29 Want it to make actual binaries. 06:11:53 I think there's a specific implementation of Common Lisp that can do it, by serializing its state as a new executable 06:12:02 But I'm thinking what can I do with assembly or Rust 06:13:05 here's my proposition for you. 06:13:08 Like an executable that just executes whatever string is in a specific location, and I can just adjust as necessary 06:13:39 so, you have your bare interpreter, a braintrust interpreter. this thing can generate binaries. 06:14:00 within the data segment of your executable format of choice, you have more braintrust code, as a sequence of bytes. 06:14:23 all you have to do when you "fork", to use a bad term, from your original program state is generate a new binary with an altered data segment, not a code segment. 06:14:41 <^v> death toll: 987 RIP https://gist.github.com/PixelToast/59f1e01c71f52f16e54dd0bfd0fce05d 06:14:57 jesus, what is that from. 06:15:26 How do I generate a new binary from assembly? 06:15:29 guessing #freenode 06:15:40 huh, I know someone on that list. 06:15:45 Would I need to call a linker? 06:16:12 Sgeo: plenty of ways to generate an ELF binary. 06:16:38 plenty of ways to modify an existing executable. 06:16:41 * Sgeo was thinking more Win32 tbh, but if ELF is significantly easier... 06:17:06 imode: Mouse? 06:17:10 Or DOS .com file, would be easy to locate beginning of running image, right? 06:17:21 in reality the world's stupidest braintrust interpreter can call out in the stupidest way possible. 06:17:56 system("cc interpreter.c -Ddata={your_bytes_here}"); 06:17:59 :P 06:18:17 rdococ: Mouse. very small language. 06:18:19 Assuming that a compiler is installed 06:18:24 Sgeo: ding. 06:18:38 imode: Ah. Looked it up on the wiki. 06:18:48 practical brainfuck. 06:18:56 I wrote a derivative language a while back. 06:19:08 got bored and started messing with more small languages. 06:19:16 Would practical brainfuck be an esoteric programming language? :P 06:20:05 depends on how you use the word esoteric. :P 06:20:07 -!- pikhq has joined. 06:20:14 no that'd be an oxymoron I think 06:20:21 Speaking of esoteric, have you seen mindscrew? 06:20:22 1Okay, that was weird. 06:20:34 holy shit I just looked up. 06:20:39 what in god's name happened. o-O 06:20:42 imode: Eh? 06:20:57 the massive burst of k-lines. 06:21:09 Ah, that. Apparently it was a mistake. 06:21:33 imode: Anyway, have you seen mindscrew? 06:21:41 I have not. 06:22:09 (I know it sounds like I'm advertising an esolang, but I seriously need actual feedback on it because nobody's even added to the discussion page.) 06:22:29 (It assists my new self-evaluation system, where I make esolangs now and realize how crappy they are later.) 06:22:30 http://esolangs.org/wiki/Mindscrew 06:22:57 it's hard to google for :/ 06:23:08 (Well, okay, I'd call it "new", but that's been happening ever since I've come here.) 06:23:50 Ironically, I also never written a brainfuck/pbrain derivative until now, and it seems to be one of my best esolangs. For now. 06:24:10 the cat program looks like a forkbomb. 06:24:36 Heh. The secondary loop doesn't call the first loop, so it's fine :P 06:25:16 There's a walkthrough for it in case it's hard to completely understand, but I think only I needed it. 06:25:16 -!- Warrigal has joined. 06:25:53 uh. PSA: people are PMing people on freenode child porn. 06:26:14 Yeah, I know. 06:26:21 I got two links, but didn't click them (luckily). 06:26:31 Advice: /umode +R 06:26:58 yeah, on that. 06:27:40 Anyway, what do you think of mindscrew? 06:28:00 interesting. definitely lives up to the idea of an esolang. 06:28:34 It's based on pbrain, but it adds the second tape and cell pointer, along with turning ] into a NOP. 06:29:51 Additional example: (::): would work as a fork bomb. (It even looks like a grenade!) 06:30:05 hah. 06:30:48 (Although the worst it'll do is overflow the stack, because the calls aren't multithreaded.) 06:31:11 have you actually got an implementation? 06:31:23 Not yet, but I was thinking of creating a crude interpreter in Lua. 06:31:43 not a terrible idea. I do my work in Python. 06:31:56 Maybe I could hardcode the address 06:33:00 -!- erkin has joined. 06:35:44 Better to do it automatically probably 06:35:49 mhm. 06:35:57 I'd also have to make sure to optimize "(-[:])" to the zero-setting primitive. 06:36:03 like I said, any way you can change the data segment is a good way. 06:39:40 rdococ: why'd you design this? 06:40:11 imode: You mean mindscrew? 06:40:15 mhm. 06:40:29 I don't know anymore... every time I create an esolang it ends badly. 06:41:12 Some things are like train crashes; my esolangs are like train crashes that causes walls to fall over onto people, which nicks on a bit of string that causes a falling piano that nearly squashes a cat, which runs into the engine of a car somehow and blows it up. 06:41:33 that sounds like a good premise for an esolang 06:41:59 Not for an esolang I'd create, though. 06:42:28 -!- doesthiswork has quit (Quit: Leaving.). 06:42:58 usually when I do work like this I have a goal in mind. 06:44:57 Great, my code is doing the chain reaction I described above. "+" does nothing, but "++" increments by one. "+[+]" results in two, though. 06:44:59 I mean, what?! 06:45:14 you ever think esolangs are just a blanket term for "work I don't feel comfortable enough to acknowledge as a real project but want to appreciate in an ironic sense." 06:45:49 No, I think esolangs are a blanket term for "failed outlets for my creativity which I think exists but actually does not." 06:46:11 considering all the brainfuck derivatives... eh. :P 06:46:18 Oh, wait, duh. 06:46:34 Fixed the problem. 06:50:39 <^v> i think most esolangs are shallow af 06:50:47 This crude interpreter is interesting in that it doesn't actively search for mismatched brackets, but it will halt if it runs into one and wants to goto the matching ending bracket. 06:51:07 ^v: you aren't the only one. but a lot of it is just what I'd call language research. 06:51:18 -!- sleffy has joined. 06:51:28 brainfuck derivatives are just stuck in local minima. 06:51:47 imode: Better than my other esolangs, anyway -_- 06:52:49 Maybe I should convert the instructions into machine code ops 06:52:55 A real compiler 06:53:09 Rather than loading ASCII instructions into an interpreter 06:53:12 rdococ: oh, some trivia. my mouse derivative had ] as a 'no-op', and execution wrapped in memory at the end of a program. 06:53:26 so the ends of loops could be the start of the program. 06:54:15 Oooh. 06:54:28 Mindscrew takes the more conventional approach of recursive procedures. 06:54:32 <^v> procedural? too simplistic 06:54:48 ^v: you can't even handle what I'm working on right now broh. 06:55:17 ^v: I was planning on creating a lang with goto instruction arithmetic. You could jump to the instruction 3 instructions ahead of the pointer, for example. 06:55:46 It would be used to pass continuations, creating a procedural system. 06:56:09 e.g. "def return = ip + 2; jmp proc; do stuff;" 06:56:15 <^v> imode, lol come at me 06:56:16 <^v> i' 06:56:22 <^v> i'm a lambda calculus and brainfuck god 06:56:39 Lambda calculus? Nah. 06:56:52 Not enough continuations. 06:56:59 <^v> lol 06:57:06 <^v> brainfuck is harder than lamdba calculus 06:57:13 I tried adding continuations to brainfuck, but it didn't work out. 06:57:18 ^v: building a language that's a cross between a key/value store and a lisp that you can only write in binary. and you can write it out of order. 06:57:25 fight me. 06:58:00 * rdococ stabs himself with the brainfuck cell pointer movement instructions to avoid being involved in the fight 06:58:26 <^v> rdococ, yeah thats not going to work 06:58:51 injuries aren't in the language spec. 07:00:04 Eh, I'll just let Lua garbage collect me then. 07:00:09 <^v> imode, lol try making a brainfuck interpreter just by doing 3d tree rotations 07:00:15 <^v> its not going to fucking work 07:00:31 try implementing a lisp out of thue-like string rewrites. 07:00:38 get on my level. 07:01:04 <^v> you got me at implementing lisp 07:01:18 <^v> ()()(())()()()()()((((((((())))(())()()()))))(()()(((())()()()()()()())))){))()(()())( 07:01:31 * rdococ blows up 07:01:43 Too many parentheses makes me explode. :P 07:02:20 wanna see some magic. 07:02:53 maybe. 07:03:09 https://ptpb.pw/EmR6/python 07:03:53 whoopsie, erased something. 07:04:37 https://repl.it/KNX7/0 07:05:03 encoding and decoding a series of lists of numbers into order-independent chunks. 07:05:32 the original list's size (as a generous estimate) is 6760 bytes. mine, in memory, with the same operations available, is 1811 bytes. 07:05:43 get on my level. 07:05:54 -!- int-e has joined. 07:06:48 OooooOOOOooh, I'm creating a recursive crude mindscrew interpreter. It calls itself when it runs a procedure. 07:07:26 Hmm, I believe that was my first K-line on Freenode ever. And I didn't even do anything myself :-/. 07:07:41 int-e: /topic on #freenode. it's a CP storm. 07:08:03 A... what? 07:08:15 child porn. bots are spamming users, and the blanket k-line was an accident. 07:08:28 Okay then, it was exactly what it sounded like. 07:08:47 imode: thanks 07:08:50 np. 07:09:12 /umode +R for now. they're still on the hunt. 07:09:30 I should buy one of the ops a drink after this. 07:09:43 (I wasn't complaining. Wondering, yes, but I expected something like this. I was actually pleased to not having to do anything myself to be let back in.) 07:10:44 I'll think about it. 2 so far. (They all end up in a single window where they are easily ignored.) 07:11:16 I havne't gotten any of these messages. 07:11:29 good. 07:11:45 I didn't either, but I put umode +R on for a bit. 07:12:00 Might just leave it on; I don't think not talking to unregistered users is gonna be a big problem. 07:16:30 oh, another victim... 07:16:31 @bot 07:16:44 botsnack 07:19:55 oh no, that seems unrelated. meh. 07:21:35 -!- hppavilion[1] has joined. 07:21:48 `botsnack 07:21:48 ​>:-D 07:21:51 Is what I meant to say. 07:22:36 -!- lambdabot has joined. 07:24:53 Good news is that my crude mindscrew interpreter is working. the EOF==no change cat works. 07:28:02 Unfortunately, the Hello world example causes a stack overflow. I need to add TCO to the interpreter. 07:30:48 when your hello world causes a stack overflow you need to rethink your life. 07:33:40 Well, I added tail-call optimization and now it won't halt. 07:33:48 meh who in their right mind installs a signal handler for sigsegv. 07:33:52 In fact, no output is even appearing. 07:35:54 And it's even making procedures loop forever when it's being skipped by []. 07:36:46 Oh, ah. My crude interpreter doesn't even bother to store any cells in memory until you start modifying them. Since 0 =/= nil, the if conditional might not be working properly. 07:40:18 !zjoust kiseki https://paste.lymia.moe/lymia/0e01aa0466be6d0d3a61c93fe4667525a6dcf502.bfjoust 07:40:22 Lymia.kiseki: points 46.00, score 999.98, rank 1/47 (--) 07:40:42 hrm 07:44:01 It seems to be decreasing the cell pointer indefinitely. I know which part of the code miiiiight be the problem, but the recursivity is conditional: why is it infinitely looping? 07:45:27 I think it might be getting stuck here: "<-[:])[:]". 07:45:49 ...Oh, shit. The substitutions are wrong. 07:46:10 No, wait, they're not. 07:46:26 OKay, no, wait, they are. 07:48:21 I added an ad-hoc command for halting the procedure - let's hope it works. 07:50:06 OKay, now it's decrementing a value. At least it tried to output SOMETHING, though. Also, I'll try to cut down on monologuing but it's hard when nobody else talks. 07:51:43 honestly I think if nobody else has the floor you're free to talk. 07:52:57 I've figured out the problem. Writing to an existing procedure was appending the characters to the end of the string, not overwriting it. 07:53:07 Yet it's still not working. 07:53:35 I mean, nothing even gets incremented to over 8, yet all characters are, to my knowledge, at 60+. 07:54:46 The only thing I think could be at fault is TCO, and I'm not sure about that. 07:56:05 !zjoust kiseki < 07:56:05 Lymia.kiseki: points -45.00, score 0.00, rank 46/47 (-45) 07:56:08 !zjoust kiseki https://paste.lymia.moe/lymia/0e01aa0466be6d0d3a61c93fe4667525a6dcf502.bfjoust 07:56:12 Lymia.kiseki: points 46.00, score 999.98, rank 1/47 (+45) 07:56:23 I tried printing a message whenever TCO got activated. The message didn't even appear! 07:56:45 !zjoust kiseki < 07:56:46 Lymia.kiseki: points -45.00, score 0.00, rank 46/47 (-45) 07:56:49 !zjoust kiseki2 https://paste.lymia.moe/lymia/0e01aa0466be6d0d3a61c93fe4667525a6dcf502.bfjoust 07:56:52 Lymia.kiseki2: points 46.00, score 999.98, rank 1/47 07:57:45 !zjoust kiseki2 < 07:57:45 Lymia.kiseki2: points -45.00, score 0.00, rank 47/47 (-46) 07:57:48 !zjoust kiseki https://paste.lymia.moe/lymia/0e01aa0466be6d0d3a61c93fe4667525a6dcf502.bfjoust 07:57:49 Lymia.kiseki: points 46.00, score 999.98, rank 1/47 (+45) 07:57:51 o.O 07:58:15 . o O ( The impossible happened... variable that was supposed to be true is false. ) 07:58:41 bit flip. 07:59:22 !zjoust kiseki < 07:59:22 Lymia.kiseki: points -45.00, score 0.00, rank 46/47 (-45) 07:59:28 !zjoust kiseki3 https://paste.lymia.moe/lymia/0e01aa0466be6d0d3a61c93fe4667525a6dcf502.bfjoust 07:59:32 Lymia.kiseki3: points 46.00, score 999.98, rank 1/47 07:59:56 !zjoust kiseki3 < 07:59:56 Lymia.kiseki3: points -45.00, score 0.00, rank 47/47 (-46) 08:00:00 !zjoust kiseki https://paste.lymia.moe/lymia/0e01aa0466be6d0d3a61c93fe4667525a6dcf502.bfjoust 08:00:03 Oh, I see. 08:00:03 Lymia.kiseki: points 46.00, score 999.98, rank 1/47 (+45) 08:00:08 zen.fi isn't updating 08:00:54 Ah, looking at the wronmg version of the code. So the variable was never set at all. Half of a mystery solved. 08:02:41 uninitialized variables strike again. 08:06:43 And for some reason, the FUNC pointer is 3, when analysis of the code suggests that only 2 could ever be possible. 08:06:55 Wait, the func pointer starts at 1. 08:08:00 Oh, crap. I've been thinking of "[" as "IF ZERO". 08:08:13 Even then, it should work! 08:10:21 <^v> Lymia, long time no see 08:10:48 Hi 08:11:17 <^v> hows life 08:13:18 ugh, I give up. mindscrew screws with my mind. 08:13:28 (and more so than originally anticipated). 08:33:38 -!- Mayoi has joined. 08:34:24 !bfjoust kiseki https://paste.lymia.moe/lymia/19a18f24119beb308652fa177c773d4ca797a26e.bfjoust 08:34:45 -!- erkin has quit (Disconnected by services). 08:34:48 -!- Mayoi has changed nick to erkin. 08:34:53 god bless python. 08:34:55 Doesn't even work anymore, huh 08:36:47 do people still build rails apps. 08:36:54 or is it just all node.js now. 08:39:32 OMFG! I may have finally got it to work. 08:39:58 Turns out the bug was I was setting the IP to 1 during tail-call optimization, and it increments directly afterwards. 08:41:02 YAAAAAAAAAAAAAAAAAAAAAAAAAAY! 08:41:11 Hello World! 08:47:26 . o O ( A pairity error is a spelling error induced by false etymology. ) 08:54:15 -!- rdococ has quit (K-Lined). 08:55:04 -!- rdococ has joined. 08:56:47 -!- clog has quit (Ping timeout: 260 seconds). 09:03:35 -!- sleffy has quit (Ping timeout: 240 seconds). 09:09:31 -!- APic has joined. 09:14:31 -!- rdococ has quit (K-Lined). 09:15:09 -!- rdococ has joined. 09:17:14 -!- rdococ has quit (Changing host). 09:17:14 -!- rdococ has joined. 09:17:23 -!- imode has quit (Ping timeout: 246 seconds). 09:22:10 Wow, rip me. 09:22:30 Anyways, should I add a return instruction in mindscrew? 09:23:48 [wiki] [[Mindscrew]] M https://esolangs.org/w/index.php?diff=52849&oldid=52848 * Rdococ * (+169) /* Computational Class */ 09:49:27 Hm, what do you think: If my interpreter is called w/o a file name, and thus enters a line-by-line mode, should data such as tape, procedure tape, cell pointer, procedure pointer, etc. be saved between lines? 09:58:48 Hmm... 10:15:04 -!- shikhin has quit (Ping timeout: 255 seconds). 10:17:15 -!- shikhin has joined. 10:17:38 -!- shikhin has changed nick to Guest41863. 10:18:34 What file extension, though/ 10:27:03 -!- clog has joined. 10:29:49 -!- mroman has joined. 10:31:39 -!- AnotherTest has joined. 10:35:12 -!- augur has quit (Remote host closed the connection). 10:45:27 Hm. Does the use of the {{fact}} tag make sense here?: 10:45:29 Programs written in Mu have semantics equivalent to that of programs written in an ordinary language with continuation-passing style (in layman's terms, black magic{{fact}}). 11:08:41 -!- sebbu has joined. 11:11:46 -!- rdococ has quit (Ping timeout: 255 seconds). 11:12:14 -!- sebbu2 has quit (Ping timeout: 255 seconds). 11:16:52 -!- rdococ has joined. 11:16:52 -!- rdococ has quit (Changing host). 11:16:52 -!- rdococ has joined. 11:17:33 -!- augur has joined. 11:22:01 -!- augur has quit (Ping timeout: 240 seconds). 11:23:07 -!- augur has joined. 11:26:24 -!- gsora has quit (Quit: uh-oh!). 11:34:07 -!- boily has joined. 11:36:20 -!- augur has quit (Remote host closed the connection). 11:36:32 [wiki] [[Joke language list]] https://esolangs.org/w/index.php?diff=52850&oldid=52611 * Zayne * (+37) /* General languages */ 11:37:32 Oh, nice, 2017. :P 11:38:56 Hah, "Hardfuck". 11:39:49 😎 11:40:30 Someone should create Handfuck. 11:41:23 In more innocent news, I was thinking of creating a BF derivative with instructions to move the cells around. For example, you could CUT cell 1 and stick it between cell 2 and 3. 11:43:19 Or, for example, CUT cells 4 to 6, and using > on cell 3 puts you at cell 7 - to get to cells 4 thru 6, you would have to use something like v or ^ to move to the cut piece. 11:46:01 -!- hppavilion[1] has quit (Ping timeout: 240 seconds). 11:56:00 `5 w 11:56:06 1/2:comics//Recommended comics include Yet Another Genius Gamer, Stuck Girl, Home of the Order, and Fantasy Stick Comic. The content of this list is not to be questioned. \ .doorstop//You do not have the clearance necessary to view this entry. \ `hoag//`[hd]o[aw][gt] [] is a set of commands for querying HackEgo hg logs. `hoag is the basic 11:56:09 `n 11:56:10 2/2: version. d adds revision numbers and dates, w looks only in wisdom, and t lists oldest first. \ gray//Gray is e common misspalling of grey. \ `whoops//`whoops is a repluralizer. 11:58:18 -!- hppavilion[1] has joined. 12:03:23 -!- deltab has joined. 12:04:06 [wiki] [[Noid]] N https://esolangs.org/w/index.php?oldid=52851 * Zayne * (+1886) Created page with "'''Noid''' (previously PyText) is a language made by [[User:Zayne|Zayne]] on April 22nd 2017 but promptly forgot about it. == Commands == . a ! b [wiki] [[Noid]] https://esolangs.org/w/index.php?diff=52852&oldid=52851 * Zayne * (+1) /* Examples */ 12:05:24 [wiki] [[Noid]] https://esolangs.org/w/index.php?diff=52853&oldid=52852 * Zayne * (+29) /* Implementation */ 12:06:24 [wiki] [[PyText?!.]] N https://esolangs.org/w/index.php?oldid=52854 * Zayne * (+951) Created page with "'''PyText?!.''' is the predecessor to [[Noid]]. This language is also created by [[User:Zayne|Zayne]] == Implementation == import os s = open(input("Run Script: "), 'r'..." 12:12:34 [wiki] [[PyText?!.]] https://esolangs.org/w/index.php?diff=52855&oldid=52854 * Zayne * (+19) 12:15:59 [wiki] [[PyText?!.]] https://esolangs.org/w/index.php?diff=52856&oldid=52855 * Zayne * (+45) 12:22:18 -!- j-bot has joined. 12:25:46 [wiki] [[User:Zayne]] https://esolangs.org/w/index.php?diff=52857&oldid=52828 * Zayne * (+16) 12:28:26 -!- boily has quit (Quit: FOLIAGE CHICKEN). 12:37:40 -!- ais523 has joined. 12:37:54 @messages? 12:37:54 Sorry, no messages today. 12:40:39 @messages 12:40:39 You don't have any messages 12:40:42 I SURE DO 12:40:55 @tell mroman ey alda was geht du hoellenhund 12:40:55 You can tell yourself! 12:41:05 :( 12:41:38 rdococ: I had an idea about a BF derivative as well 12:41:47 It's like BF. But instead of moving the head of the tape 12:41:49 you move the tape. 12:42:04 so <> doesn't move the read head, it moves the tape under the read head. 12:42:29 and - doesn't subtract one, it adds 256. 12:43:21 I call it "Frainbuck" 12:44:18 adding 256 doesn't do anything in 8-bit BF :-P 12:44:36 http://esolangs.org/wiki/PyText%3F!. 12:44:51 ais523: It should subtract one 12:44:59 or wait 12:45:00 * APic thought of implementing a Routine to output a Circle in Brainfuck, then mapping <>,.[]+- to Numerals. That Way i could beat the Movie „Π (1998)“ because i would have found a Pattern for π in <=216 Decimals! 🙌 12:45:34 oh damn 12:45:37 it's adding 255 12:45:55 yep. Pardon me. It adds 255 12:46:28 * APic would name that Program „Bresenham.bf“ as a Tribute to the Man who figured out very nice Drawing-Routines 12:46:42 APic: I don't think you capitalise the mathematical π at the start of a sentence, it's case-sensitive 12:47:31 well now I have to release Frainbuck 2.0 to fix this error 12:48:03 I'm still in favor of a quality control about esolangs articles 12:48:16 "dis mah language" + source code is meh. 12:48:42 especially when it's python code without line breaks :D 12:49:56 saying that I should probably check my articles :D 12:50:39 most esolangs are never implemented and never have programs written in them 12:50:53 so an interp is arguably an improvement (unless it's a BF derivative, then writing an interp is normally too easy :-P) 12:52:03 ais523: Thanks for the Information. 12:52:11 I had a program for that. 12:52:18 I just can't remember the name of the language it created 12:53:01 π looks much nicer than Π anyhow ☺ 12:53:15 At least in Terminus on urxvt 12:56:45 -!- ais523 has quit (Remote host closed the connection). 12:57:12 -!- ais523 has joined. 12:58:40 Btjzxgquartfrqifjlv 12:58:42 ah yes 12:58:48 http://esolangs.org/wiki/Btjzxgquartfrqifjlv 12:58:58 Nice 12:59:40 it even supported multisymbol bf instructions! 13:01:08 🙌 13:01:14 http://esolangs.org/wiki/%E2%98%83 13:01:16 hm. 13:01:34 I should write an interpreter for ☃ 13:03:45 hm. 13:03:50 so `s` is basically a flip-flop 13:03:53 kinda 13:04:20 depending on the direction you come in you either write or read from it. 13:05:24 always nice when you discover languages you wipped up but forget about them. 13:06:06 🙌 13:09:10 hm. 13:09:17 http://codepad.org/sAxgPOpq <- this would be a ROM only though 13:09:30 (you enter from left on line 6) 13:09:42 it will decrement it and branch upwards at the right location to read the value 13:10:03 but to write you'd have to come in from above 13:10:13 or below 13:11:35 http://codepad.org/G7XDmQqm <- like this. 13:11:37 mroman: I'm not surprised you couldn't remember that name! 13:11:56 line 7 would be read, line 8 would be write 13:12:12 except that since you only have "one thread local value" which is the ptr 13:12:18 the value to write needs to be stored somewhere else 13:12:37 I guess I never figured out how to do writes 13:13:17 ais523: :D yeah.... 13:13:44 but on the other hand I can memory a lot of burlesque command 13:13:57 but to be fair they have SOME resemblances with what they do 13:14:08 *memorize 13:16:00 and that example program looks race-condition-y 13:16:19 so it'd need at least one barrier somewher 13:17:25 -!- Antoxyde has joined. 13:17:43 ok so at least it's not a non-obvious language :D 13:21:13 man I lost the online interpreter for beam 13:21:31 Beam is the esolang I'm most proud of :p 13:22:03 We made programming contests in it at my local university 13:22:08 although only 3 students participated 13:22:11 but it was still fun 13:24:30 https://tio.run/#beam 13:24:31 hu 13:24:32 omg 13:24:37 somebody wrote an interpreter for it? 13:24:44 but no graphical debugging :( 13:26:15 https://tio.run/##S0pNzP3/v6gswYZLQcGqVB1I2enqKpRa/f/vBAA even seems to work 13:26:15 nice 13:26:19 -!- idris-bot has joined. 13:26:31 but debugging without a graphical debugger is going to be hard. 13:36:53 -!- augur has joined. 13:41:03 `? prismack 13:41:04 prismack? ¯\(°​_o)/¯ 13:41:05 -!- augur has quit (Ping timeout: 248 seconds). 13:41:09 `? bimetal 13:41:10 bimetal? ¯\(°​_o)/¯ 13:41:20 \(o_O)/ 13:45:28 `An online byte-counter that counts many different encodings. ` 13:45:29 ​/home/hackbot/hackbot.hg/multibot_cmds/lib/limits: line 5: exec: An: not found 13:45:30 uhm... 13:45:39 it counts ASCII, UTF-8 and UTF-16 bytes 13:45:41 but... uhm... 13:45:47 what 13:46:39 presumably that's supposed to mean "char-counter" 13:52:21 -!- ais523 has quit (Remote host closed the connection). 13:53:31 -!- ais523 has joined. 13:56:30 `Hardfuck is a Brainfuck derivative created by Zayne (why am I not surprised) and as the name suggests it is supposed to be harder than Brainfuck. ` 13:56:31 ​/home/hackbot/hackbot.hg/multibot_cmds/lib/limits: line 5: exec: Hardfuck: not found 13:56:38 how can it be harder if it shares the same set of instructions 13:56:50 you don't make brainfuck harder by introducing two new instructions 13:57:17 if anything, you made it easier o_O 13:57:52 mroman: nice idea about BF which moves the tape 13:58:03 also, that's also something I noted with hardfuck :P 13:58:08 at least it has an innuendous name 13:59:25 hmm, frainbuck has made me think of INTERCAL's I/O mechanism 13:59:52 you could make a two-pointer BF where the pointers are on opposite sides of the tape, so they see the bits of the numbers in reverse order 14:00:15 that said, it wouldn't be any harder unless you had to use both of them for some reason 14:00:28 -!- doesthiswork has joined. 14:00:30 by analogy with INTERCAL, maybe one of them can only do input and the other can only do output? 14:01:17 rdococ: maybe we could replace the tape with boxes! 14:01:25 instead of cells 14:01:27 you have boxes. 14:01:44 . o O ( cells are boxes, they're just large enough to house criminals ) 14:02:05 ais523: don't worry 14:02:11 you can name it hardfick 14:02:19 (fick == german for fuck because hardfuck is already taken) 14:02:20 The real money is in non-integer cells, with an instruction / to divide by 2. 14:02:30 mroman: even better would be scheisse 14:02:38 or you could even name it "harterfick" 14:02:40 now I'm trying to work out if you can do a BF that does loops by actually forming a loop in the tape 14:02:50 or "sonrichtigharterfickdassdunichtmehrrichtiggehenkannstammorgendanach" 14:02:53 Gehirn ficken 14:03:14 fwiw, I believe that BF-plus-extra-instructions is only interesting if it changes the way you'd program in it 14:03:32 well 14:03:35 you know what 14:03:43 I'm going to create an even better bf-derivative creation program 14:03:46 ais523: My mindscrew only modifies the ] instruction, and adds {} to pbrain. It completely changes the language. :P 14:03:54 A bf-derivative creation program? 14:03:58 yes 14:04:05 like the one I had some years ago 14:04:07 just with more features. 14:04:09 That's a bit of a mindscrew :P 14:04:24 mroman: I think the world needs a universal BF derivative interpreter 14:04:36 ideally, one that does statistical analysis on the source to figure out what the instructions in it are :-) 14:04:41 lol 14:04:45 but 14:04:47 😉 14:04:47 not too bad 14:04:47 well, weave.rb might be a good starting point :P 14:04:48 I started writing one but got bored 14:04:54 you could probably detect [ ] 14:04:58 it has brainfork, pbrain, etc. 14:05:00 with some analysis 14:05:21 but this sounds interesting 14:05:31 keep me posted should you continue doing this 14:05:38 I'd be curious how this works 14:06:08 rdococ: you speak german? 14:06:11 I thought only int-e is german 14:06:14 mroman: no, google translate :P 14:06:16 ah 14:06:17 ok 14:06:20 mroman: there are several clues you can use 14:06:42 I guess you could do bf constants detection too? 14:06:45 [] are always balanced, <> are usually (but not always) balanced in a loop whereas +- are much more rarely balanced, programs don't normally put < and > or + and - next to each other 14:06:47 it translates to "brain fucking", which sounds like porn that gets injected into your brain by machiner 14:06:48 y 14:06:57 -!- hppavilion[1] has quit (Ping timeout: 240 seconds). 14:07:02 yeah I know 14:07:07 (I speak german) 14:07:18 ais523: ah, so my habit of balancing <> in a loop is not a dumb one :P 14:07:19 as a fallback, if it couldn't figure out how the language worked at all, I was going to just print "Hello, world!" as a fallback 14:07:28 but 14:07:30 my language 14:07:35 brtquartgfjxj or whatever it was called 14:07:40 has multichar instructions! 14:07:41 rdococ: in BF optimization, "balanced loops" are treated as a common special case 14:07:43 how do you detect that? 14:07:51 ais523: ooh, cool. 14:07:52 mroman: same way Incident does 14:07:54 or Ook for that matter 14:08:02 look for substrings that repeat a lot 14:08:06 hm. true. 14:08:17 yeah... that's actually not hard 14:08:18 right. 14:08:32 I have a mindscrew interpreter whose only optimizations is turning "(-[:])" into a primitive that sets the cell to 0, and tail-call optimization (to avoid a stack overflow in "Hello world!") 14:09:46 actually, looks like it wasn't all that needed 14:09:53 I added a --ntco flag to test 14:09:58 never fix a running bug 14:10:02 just increase stack depth 14:10:19 everybody does that in research projects. 14:10:26 it just needs to work for the demo 14:10:31 everything else is not important. 14:10:39 running demo == moneyz == $$$ 14:13:14 Heh, I added a --bound command to enable wrapping bounded cell values to an arbitrary value. It messes up the "Hello world!" program big-time if you set it to a low value. :P 14:13:53 With --bound 114, it says "Hello Wold!" :P 14:15:28 Oh nice, cat program with --bound 90 turns "Z" into EOF :P 14:16:01 Okay, wait, seriously, why is £ unicode? 14:17:59 'merica 14:18:19 that's what the A in ASCII is. 14:18:28 ☺ 14:18:33 American Standard Code for Information Interchange 14:18:39 ANSI > ASCII 14:18:48 Uh 14:18:51 The A in ANSI is probably still America? 14:18:53 ISO > ANSI 14:18:53 😉 14:18:58 mroman: True. 14:19:02 American National Standards Institute 14:19:02 From V.E.R.A. -- Virtual Entity of Relevant Acronyms (February 2016) [vera]: 14:19:02 ANSI 14:19:02 American National Standard Institute (org., USA) 14:19:05 *nod* 14:19:09 damn americans 14:19:13 and their symbols 14:19:15 Yah 14:19:20 They shall rot in Hell. 14:19:24 But… wait! 14:19:31 They now elected the Trumps as President. 14:19:36 So they _are_ already in Hell! 14:19:36 😉 14:20:01 * rdococ adds Unicode support 14:20:13 :P 14:20:14 on the other hand 14:20:22 america could have forced every country to use latin alphabet 14:20:24 I mean 14:20:26 True. 14:20:27 that would have helped 14:20:28 :D 14:20:31 8===D 14:20:31 but no 14:20:32 😉 14:20:35 they didn't. 14:20:38 *nod* 14:21:08 they just went to asia and said "u now guys... these drawings you do... they are a bit _TOO_ complicated. Just make them a _bit_ less complicated you feel me fam?" 14:22:32 why is Lua so bad at parsing unicode?! Aaaaaaaaaaaaaaaaah! 14:22:43 Did they US actually force Japan to simplify their character? 14:22:53 Or is that just a myth everybody tells? 14:22:57 *the 14:22:59 for a high-level language, you'd think Lua would be able to parse unicode as one character! BUT NO! 14:23:04 it sounds like a myth. 14:23:09 because it's ridiculous. 14:23:28 forcing them to use romaji would have made sense 14:24:19 (if your goal is to make it easier for western people to learn) 14:25:19 rdococ: why is go so bad at unicode 14:25:30 "Note: since Lua 5.3, there's a builtin module called "utf8"." 14:25:33 Eh??? 14:25:34 if you want unicode you have to string -> []rune 14:25:39 instead of just use string 14:25:59 Well, Lua is highlevel, but quite old. 14:25:59 mroman: Lua provides no Unicode-aware functions straight out of the box. 14:26:12 C is also highlevel, but even older. 14:26:22 I consider C medium level. 14:26:26 yeah 14:26:32 C is more like a steak that is still bloody inside 14:26:36 it's not completely a bloody mess 14:26:41 but it's definitely bloody on the inside 14:26:49 -!- ATMunn has joined. 14:27:08 it has this neat brown crust that looks tasty 14:27:11 but once you open that thing 14:27:13 it's a bloody mess 14:27:19 It has procedures, and strong type checking, but I wouldn't call it high-level. You can pass functions as arguments with the aid of function pointers, but not create anonymous ones...in old versions, anyway. 14:27:39 Hell, GCC adds first-class functions to C++. 14:27:49 is that part of C+11? 14:27:51 Which rockets it straight up to high-level for me. 14:27:55 Not sure. 14:28:07 nah... C++ still has manual memory management afaik? 14:28:14 I do think new C++ standards do have lambdas, though. 14:28:38 although boost ptr stuff might make it quite automatic? 14:28:40 I'm not a C++ guy 14:28:42 never liked it. 14:28:53 anyway... gotta catch the train 14:28:53 see ya 14:28:54 -!- mroman has quit. 14:39:05 Ooh, combination: Put code and memory in the same codespace, and enable cutting the tape and looping it. 14:41:04 I'd also like to note that + and - tend to be balanced when checking for equality, or swapping two cells. 14:56:31 an equality test is [>-<-]>[, with an additional + if you want it to be non-destructive in one argument 14:56:36 that doesn't seem balanced to me 14:57:15 transfer-add (which is commonly used to move a value from one cell to another) is balanced, though 15:00:37 -!- jaboja has joined. 15:04:38 The additional plus would make it non-destructive, wouldn't it? 15:04:38 -!- doesthiswork has quit (Quit: Leaving.). 15:04:57 It's like the inversion of transfer-add - transfer-subtract. 15:05:02 s/non-destructive/balanced/ 15:05:14 ...ah. 15:10:23 -!- jix has joined. 15:10:30 -!- joast has joined. 15:10:57 Damn it, seriously? No Lua5.3 for Debian? 15:12:55 -!- alercah has joined. 15:13:22 -!- alercah has left. 15:32:06 -!- erkin has quit (Quit: Ouch! Got SIGABRT, dying...). 16:11:27 -!- Sgeo has quit (Ping timeout: 240 seconds). 16:14:30 -!- Sgeo has joined. 16:22:44 I officially give up unicode 17:10:52 -!- ais523 has quit (Ping timeout: 255 seconds). 17:11:50 POLL: Should my mindscrew implementation save the tapes and pointers between lines, or start afresh each time? 17:18:36 yes 17:20:51 -!- erkin has joined. 17:25:09 Hoolootwo: Eh, I'll add it as a flag. 17:25:51 -!- moony has joined. 17:25:56 -!- Guest41863 has changed nick to shikhin. 17:26:25 -!- shikhin has changed nick to Guest7629. 17:26:59 -!- FreeFull has joined. 17:28:49 -!- jaboja has quit (Ping timeout: 248 seconds). 17:32:27 -!- joast has quit (Ping timeout: 240 seconds). 17:33:17 -!- Guest7629 has quit (Quit: Alas.). 17:33:25 -!- shikhin_ has joined. 17:33:48 -!- shikhin_ has changed nick to Guest17908. 17:35:59 -!- Guest17908 has changed nick to shikhout. 17:36:09 -!- shikhout has quit (Changing host). 17:36:09 -!- shikhout has joined. 17:37:25 -!- zseri has joined. 17:38:16 -!- shikhout has changed nick to shikhin. 17:51:29 -!- imode has joined. 17:52:57 hi 17:53:12 -!- jaboja has joined. 17:53:44 hi 18:00:57 I know there's at least one language where everything is a set, and one where everything is a pair, but I can't help but think about making one. 18:02:25 (What would be cool about the set one is if I only use integers as types, sets could be integers (since integers can be thought of as mapping integers to booleans, like a set of flags) -- and that means integer sets could contain more sets 18:03:00 although it'd probably be better to store them as sets of bits.) 18:04:26 zseri, whadya think? ^ 18:05:51 what do you mean with 'set', is that an uniquified (every element is unique) list or just a normal list? 18:06:38 because I can't really imagine a (uniquified) set of bits/booleans. 18:14:43 -!- Phantom_Hoover has joined. 18:14:44 uniquified 18:15:25 A uniquified set of integers could be defined as a map from an integer to a boolean (existence/nonexistence). In accordance, an integer can also be defined as a map from an integer to a boolean (binary place value -> bit). 18:15:51 Therefore, a set is equivalent, or at least stored equivalently to, an integer, and a set can contain another set by virtue of both of them being integers. 18:16:18 Type system optional. 18:17:51 And as a consequence of this, a pair is also an integer, which makes a list an integer. 18:17:58 This also makes an associative array an integer. 18:18:16 In other words, imode's binary tree thing gone mad. 18:20:18 (As a side effect, a set of booleans can also be thought of an integer, so it is equivalent to a set of integers (and a tree)). 18:24:37 This is probably actually best interpreted in Lua, because Lua supports sparse tables pretty well. 18:29:35 "As a side effect of this, integers in '''Integer''' must ironically be stored as more complicated objects in the implementation itself, unless it uses bignums; any integer type other than bignums will break like a fragile twig when a set containing an integer larger than, say, 31 appears." 18:40:13 hi. 18:41:28 hi imode. I'm taking your binary...tree...thing and taking it to an incredible extreme. meet Integer, a WIP esolang where everything is an integer. 18:41:58 okay. what're the semantics of this. 18:42:09 http://www.jyoung-studio.com 18:42:25 Well, a set of integers can be stored as a map from an integer to a bit (element -> existence value), yes? 18:43:01 imode, ^ 18:43:09 I suppose. checking whether an integer is an element of a set could yield a boolean, yes. 18:43:15 <* Taneb> hello 18:43:21 Well, it just so happens that an integer can also be considered a map from an integer to a bit (binary place value -> bit). 18:43:34 Do you see where I'm going...? :P 18:43:40 not really. 18:43:51 This means that a set can be considered an integer - both map an integer to a boolean. 18:44:32 can you show me some example? 18:44:36 Because sets are now integers (or at least equivalents), a set can contain other sets. This allows you to create a pair - and it will be an integer. Trees, lists, everything that can be created from sets, are also integers. 18:45:14 how is a set an integer? 18:45:16 Take a set e.g. {3, 2}. Its representation as an integer would be 2^3 || 2^2 (where || is a bitwise OR). 18:45:39 This would make the binary place values of 2^3 and 2^2 a 1, which means that those elements, 3 and 2, are in that set. 18:46:20 sure. now store large integers. :P 18:46:41 Because the set {3, 2} can be expressed as an integer, pairs, say the pair (1, 2), can be expressed as {1, {1, 2}} - or 2^1 || (2^1 || 2^2). 18:47:04 Oh, sorry, I mean 2^1 || 2^(2^1 || 2^2). 18:47:06 you lose the nesting factor. 18:47:16 imode, see my correction - you can still nest them. 18:47:19 2^(2^1 || 2^2)? 18:47:52 so show me how I can check for set membership this way. 18:48:02 and how it doesn't balloon out if I'm storing quadruple-digit numbers. :P 18:48:21 You can use bignums, or you could be ironic and store the integers as sets :P 18:48:40 Especially sparse tables, which Lua has. 18:48:50 bignums shmignums. if I want to store 2^64 I will need 2^64 bits. 18:49:06 imode: or a table {[64] = true} :P 18:49:25 you'd probably also need a separate length vector to keep track of the length, but that's another story. 18:49:52 how exactly does that table get around the fact that to store 2^64 in your method you'd need more bits than anybody has room for. 18:50:18 Easy - it's a sparse table. [64] is the only key, and its value is true. You can perform bitwise operations on it to add, subtract, etc. 18:50:34 I can store that table in Lua without error. 18:50:41 [64] isn't the value. 18:50:49 18446744073709551616 is. 18:50:52 [64] is the binary place value, stored as a key here. 18:51:04 no it's not. your place value is 2^18446744073709551616. 18:51:05 18446744073709551616 is way too large; that's why we store it as a table! 18:51:14 O_O 18:51:27 er... 18:51:35 you could also store the binary place values as sets? 18:51:39 again, large integers. 18:51:42 {[{etc}] = 1} :P 18:51:44 hell, store 128. 18:51:50 that means the place value is 2^128. 18:52:03 Yeah, but I'm talking about binary place values. 18:52:04 0b100000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000 18:52:13 that's the bit vector you have to store. 18:52:27 would you like me to show you the one for 65536? or 2^32? 18:52:30 or 2^64? 18:52:39 Again, you could store the key as a table, too. 18:52:41 it's pretty large. 18:52:46 Nested table keys - wow. 18:52:52 -!- ais523 has joined. 18:53:03 right, but then it defeats the purpose of your experiment, storing set membership in a linear bitvector. 18:53:16 True, but the program itself doesn't know that. 18:53:30 then why wouldn't I just store the numbers normally in a set? 18:53:38 what extra do you give me, here? 18:53:48 Because the program cannot access or create normal sets. 18:53:55 well, {3, 2} + 1 :P 18:54:12 {3, 2} + 1 is {3, 2, 1}. again, this fails for large integers. 18:54:19 {3, 2, 0}* 18:54:34 we need room for 0, too. 18:54:48 so 2^1 is zero, 2^2 is one... 18:54:56 ...oh. 18:55:08 But you're taking 2^3||2^1, and adding 1 == 2^0. 18:55:10 you can see where this fails. 18:55:13 ^^^ 18:55:26 all in all there are better representations. 18:55:28 I said, you're taking 2^3||2^2*, and adding 1 == 2^0. 18:55:34 Then they wouldn't be esoteric! 18:55:57 welp, have fun struggling to store numbers over 64. :P 18:55:58 -!- kuluma has joined. 18:56:09 AGAIN, tables!!! Do you not hear me?! 18:56:14 nope. 18:56:31 I take that as "nope, I do hear you." :P 18:57:37 imode: Anyway, what do you think of goto/cc? 18:58:27 is that one of your esolangs? 18:59:49 no, but could be 19:02:03 every instruction would discreetly take in its continuation as an argument. 19:02:38 rather than "inc x" incrementing x, "inc x k" passes x+1 as an argument x to k 19:03:34 and procedures would be goto labels or address-setting instructions, maybe with or without explicit parameters 19:04:00 so.. like.. a regular assembly. 19:04:10 heh 19:05:22 I also had the idea of a brainfuck derivative where 1) ] is a NOP, 2) code and memory are in the same codespace, and 3) you could cut the tape at two points and stick them together, separating it from the main loop until you cut again 19:05:45 s/main loop/main tape 19:07:04 but one problem: you can't loop, and cell pointer will never catch up to ip 19:09:44 imode: I was considering enabling infinity with the (-[:]) construct used on a negative integer. whadya think? 19:12:22 http://esolangs.org/wiki/YABC i wonder if anyone ever figured out if you can do something with this 19:12:42 or is it impossible for some obvious reason 19:13:04 (it's mine from ages ago) 19:13:07 -!- xkapastel has joined. 19:13:34 Eh... 19:14:43 -!- ais523 has quit (Remote host closed the connection). 19:14:52 -!- ais523 has joined. 19:15:00 kuluma: that's obviously TC I think 19:15:07 wow 19:16:51 the easiest method is to compile from balanced bignum dofuck (i.e. all loops must contain an equal number of < and >, and the tape is finitely long), and spacing out the tape elements that represent the dofuck tape elements 19:17:25 did you figure this out just now? 19:17:53 that gives you room in between to keep constantly adjusted jump target pointers 19:17:53 -!- ais523 has quit (Remote host closed the connection). 19:18:03 -!- ais523 has joined. 19:18:12 sorry, I had that issue again where I can send but not receive 19:18:22 did anyone try to talk to me? 19:18:30 so... how big do cells have to be for this to actually be TC? 19:18:39 well i asked if you figured it out right now or earlier 19:19:11 kuluma: just now 19:19:21 (1 bit is probably not enough ;-) ) 19:19:30 int-e: the construction I used there actually requires bignum cells, there are probably constructions that work with finitely large cells though 19:19:39 finding the minimum value might be interesting but I don't have time for that right now 19:21:10 and it may be tricky to get the first big value onto the tape 19:21:29 err, never mind 19:21:33 nothing prevents you just spamming a bunch of + 19:21:40 the issue is more trying to deal with big values in the middle of a loo 19:21:41 *loop 19:21:45 when you have to be able to jump back over them 19:22:00 I was trying to jump back to the start of the program, but even that isn't a real issue 19:22:38 i've really lost my game 19:22:55 kuluma: at least you HAD a game :P 19:22:59 maybe i'll make an interpreter 19:23:36 dofuck? 19:23:48 rdococ: you know how BF effectively has while loops, []? 19:23:52 yes 19:23:53 I guess negative numbers cause forward jumps? 19:23:54 dofuck is BF except it uses do-while loops 19:23:58 ah 19:24:01 interesting 19:24:05 so [ never jumps forwards, its only purpose is to show where to jump back to 19:24:12 it's Turing-complete but not IO-complete, which is interesting 19:24:13 oh, so like Newbiefuck 19:24:18 not IO-complete? 19:24:35 rdococ: it has no way to sometimes produce a byte of output and sometimes not produce a byte of output 19:24:42 ah 19:24:45 every program unconditionally either produces output or doesn't 19:24:47 ...wow, that is interesting 19:24:54 albeit fairly obvious 19:24:58 any program containing a . command has to run it sometime 19:24:58 true 19:25:00 ais523: in your construction, you can encode all required offsets at the start of the program, so I don't know what you mean by skipping over a big value. 19:25:32 int-e: oh wow, I hadn't realised that 19:26:06 you can't quite do it like that because you can only encode /unconditional/ jumps that way 19:26:34 but it's easy enough to convert a program that uses conditional jumps of multiple sizes into a program that uses unconditional jumps of multiple sizes, and conditional jumps but they're all the same size 19:26:47 so you can have the size of the conditional jump you want just before your data cells 19:26:56 and all the unconditional jumps before that, at the start of the tape 19:27:20 hm 19:27:25 the problem with doing this with finite cells is that then, for TCness of data storage, you need infinitely many of them 19:27:30 which means occasionally losing track of where the data pointer is 19:28:01 it jumps back "characters", not "instructions" in the code 19:28:14 https://pastebin.com/WSJbFbEf is that right? 19:28:14 So anyway, using that idea we can build code that computes arbitrarily large offsets so some finite size of cells is enough for TC-ness as well. 19:28:18 thus you can just store one value large enough for the biggest loop, and use spaces 19:28:24 (handwaving, I know) 19:28:28 e.g. ++++++++++[ ,.] 19:28:31 the "code = """ in the beginning is because i wrote it line by line and didn't reread sry 19:29:44 rdococ: how do you handle the case of nested loops? 19:30:01 anyone fancy implementing fibonacci? 19:30:03 :P 19:30:09 ais523: btw, the scheme that I currently have in mind for the balanced brainfuck is to replicate the cell values so that there's a copy next to every offset the value might be used with. 19:30:10 i added output 19:30:15 . 19:30:18 the outer one necessarily has to be larger than the inner one, so you'd need some sort of repeater that has to be skipped over when going forward 19:30:29 true 19:30:34 int-e: oh, I think that works 19:30:48 even if it has O(n) performance :-P 19:30:59 (where n is the length of the program) 19:31:08 i can't immediately even see how to output the naturals 19:31:15 ais523: and then my intended construction works; you can populate the tape with the required offset at program startup and never touch them agin. 19:31:19 *again 19:31:36 okay i get what ais523 means by dofuck 19:31:48 *offsets, I should probably type a tad more slowly. 19:32:17 -!- erkin has quit (Quit: Ouch! Got SIGABRT, dying...). 19:33:39 also the slowdown will be small compared to the exponential price of a reduction to a Minsky machine 19:35:37 -!- doesthiswork has joined. 19:37:14 -!- digitalcold has joined. 19:38:39 aha! 19:38:40 naturals 19:38:41 https://pastebin.com/hR0pPMpe 19:38:59 yay, a fellow pythonian. 19:42:00 here's a first attempt at amplification: >+++++++>+[n]<>>++<-<^>-------> should produce 2n on the tape. 19:42:10 i would add that to the page but that seems a bit difficult 19:43:18 int-e: in my interpreter that's an infinite loop if i change n to ++++++++++ 19:43:30 (that doesn't mean your code is incorrect, just saying) 19:44:24 kuluma: ^ is conditional according to the specification 19:45:00 and the offset is the current cell, not the one to the right 19:45:37 (but I'm not saying that my code is correct either, I have not tested it nor proved it correct) 19:51:30 -!- imode has quit (Ping timeout: 240 seconds). 20:04:51 -!- imode has joined. 20:07:07 -!- atslash has joined. 20:10:52 -!- imode has quit (Ping timeout: 246 seconds). 20:11:15 -!- augur has joined. 20:15:28 -!- joast has joined. 20:22:16 int-e: you are correct 20:22:33 i seem to have invented... yet another brainfuck clone 20:22:43 O_o 20:23:09 my interpreter indeed just jumps to the left by the value in current cell 20:23:43 i was probably going by my memory of the specification instead of the actual specification 20:23:58 ok so is my unconditional version TC? :) 20:24:08 reference implementation above. 20:25:21 -!- imode has joined. 20:25:28 probably, but it will be quite awkward since you need to use data as offsets 20:27:33 -!- zzo38 has joined. 20:35:20 Now I fixed the MIXASM program I have done 20:36:24 int-e: seems to work, more or less https://pastebin.com/EsBhhyHb 20:36:29 though i get (n+1)*2 20:36:51 prints 2,4,6,8 etc for n=0,1,2,... 20:38:18 Now it can share addresses for equal sign expressions (to save memory) (it was originally meant to do that; it was just a bug that it didn't), and now base 64 is supported, and you can have ORG and EQU pseudo-ops after END (it was already allowed, but now it is documented that this is allowed), and "CON -0" works now, and a few new pseudo-ops DECK, EJMP, and EJSJ. 20:40:34 https://arxiv.org/abs/1707.02652 20:47:38 -!- Antoxyde_ has joined. 20:50:05 -!- Antoxyde has quit (Ping timeout: 240 seconds). 20:56:20 ugh 20:57:25 print(string.char(string.byte("£"))) -> "�" 20:57:27 I mean, wtf? 21:01:39 -!- hppavilion[1] has joined. 21:01:57 OMFG I FINALLY GOT UTF-8 TO WORK IN MINDSCREW INTERPRETER YAY!!!!!!!!!!!!!!!!!!!!! 21:09:27 -!- Sgeo has quit (Ping timeout: 240 seconds). 21:19:22 -!- doesthiswork has quit (Quit: Leaving.). 21:20:27 -!- kuluma has quit (Ping timeout: 240 seconds). 21:27:26 Heh, looks like largest number Lua can represent on my machine is 1024. 21:27:39 s/1024/2^1023/ 21:27:51 2014 would be an extremely low limit 21:28:34 idea: an esolang that represents numbers as dates, and only accepts dates in the past 21:29:33 I had the idea of brainfuck with floats, where / would divide the number by one half. 21:29:40 s/divide by one half/divide by two/ 21:29:47 and * would multiply by 2, of course 21:30:22 Or something that would take the alternate branch in the surreal numerical tree. 21:30:22 https://upload.wikimedia.org/wikipedia/commons/4/49/Surreal_number_tree.svg 21:32:14 (e.g. / would turn 1 into 1/2, 2 into 1+1/2, etc. 21:46:24 -!- atslash has quit (Remote host closed the connection). 21:46:35 -!- FreeFull has quit (Ping timeout: 240 seconds). 21:47:07 -!- atslash has joined. 21:48:37 -!- FreeFull has joined. 21:55:33 [wiki] [[Feta]] https://esolangs.org/w/index.php?diff=52858&oldid=36563 * Zayne * (+290) 21:55:54 [wiki] [[User:Zayne]] https://esolangs.org/w/index.php?diff=52859&oldid=52857 * Zayne * (+35) 21:57:41 [wiki] [[User:Zayne]] https://esolangs.org/w/index.php?diff=52860&oldid=52859 * Zayne * (+40) /* My Esolangs (including jokes) */ 21:59:25 [wiki] [[Noid]] https://esolangs.org/w/index.php?diff=52861&oldid=52853 * Zayne * (+141) /* Implementation */ 22:30:19 -!- zseri has quit (Ping timeout: 260 seconds). 22:33:45 `olist 1092 22:33:46 olist 1092: shachaf oerjan Sgeo FireFly boily nortti b_jonas 22:54:15 -!- AnotherTest has quit (Ping timeout: 255 seconds). 22:57:04 -!- boily has joined. 23:00:17 -!- newsham has joined. 23:25:35 -!- erdic has joined. 23:28:08 -!- Phantom_Hoover has quit (Read error: Connection reset by peer). 23:30:11 The EJMP and EJSJ pseudo-ops in my MIX assembler are somewhat like COME FROM 23:31:01 Do you like this? 23:36:57 -!- atslash has quit (Ping timeout: 240 seconds). 23:37:43 -!- atslash has joined. 23:42:21 -!- jaboja has quit (Ping timeout: 240 seconds). 23:43:53 -!- boily has quit (Quit: LESSON CHICKEN). 2017-08-18: 00:04:29 yes I like this 00:14:52 -!- oerjan has joined. 00:27:25 -!- jaboja has joined. 00:54:44 -!- Sgeo has joined. 01:00:31 -!- G33kDude has changed nick to GeekDude. 01:00:46 -!- GeekDude has quit (Quit: WeeChat 1.8). 01:02:03 -!- augur has quit (Remote host closed the connection). 01:02:16 -!- GeekDude has joined. 01:05:56 -!- Sgeo has quit (Ping timeout: 240 seconds). 01:07:43 Has this house been moved to WGL84 yet? https://upload.wikimedia.org/wikipedia/commons/d/d5/Prime_meridian.jpg 01:10:32 -!- Sgeo has joined. 01:14:46 gah tinnitus 01:16:28 -!- Sgeo_ has joined. 01:17:41 -!- Sgeo has quit (Ping timeout: 240 seconds). 01:26:05 -!- doesthiswork has joined. 01:46:17 -!- augur has joined. 01:48:15 -!- augur has quit (Remote host closed the connection). 01:48:30 -!- augur has joined. 02:04:41 https://github.com/matslina/awib 02:04:45 -!- augur has quit (Remote host closed the connection). 02:24:58 -!- APic has quit (Ping timeout: 240 seconds). 02:28:07 -!- APic has joined. 02:32:22 -!- augur has joined. 02:44:35 -!- hppavilion[1] has quit (Ping timeout: 240 seconds). 02:45:29 -!- augur has quit (Remote host closed the connection). 02:52:19 -!- augur has joined. 02:56:04 -!- Antoxyde__ has joined. 02:56:27 -!- Antoxyde__ has quit (Remote host closed the connection). 02:58:27 -!- Antoxyde_ has quit (Ping timeout: 240 seconds). 03:01:42 -!- ATMunn has quit (Quit: See ya! o/). 03:02:06 Now I have implemented some map projections: Eckert II, Winkel tripel, Kavrayskiy VII, Aitoff, Equirectangular, Gall-Peters, Hammer, Lambert cylindrical equal area, Mercator, Sinusoidal, Van der Grinten, Polar azimuthal equidistant, Mollweide 03:14:02 -!- wob_jonas has joined. 03:16:22 I started to upload the book I mentioned to under https://commons.wikimedia.org/wiki/Category:Illustrations_to_J%C3%A1nos_Arany%27s_ballads_by_Mih%C3%A1ly_Zichy 03:17:09 I will upload the rest in a few days, I already have all the prepared cropped images on my hard drive 03:21:07 -!- augur has quit (Remote host closed the connection). 03:21:59 -!- augur has joined. 03:22:17 Was it you who mentioned the base 256 MIX with a "NUME" instruction? Then describe its working 03:23:17 -!- wob_jonas has quit (Quit: http://www.kiwiirc.com/ - A hand crafted IRC client). 03:23:40 -!- wob_jonas has joined. 03:24:41 -!- wob_jonas has quit (Client Quit). 03:25:10 -!- wob_jonas has joined. 03:27:28 zzo38: First I'd have to describe what the CHAR instruction does. If the magnitude of rA is less than 10**10, then it puts the decimal digits as characters into the magnitude of rAX as normal. 03:30:08 If the magnitude is bigger than that, then it encodes the magnitude in some unambiguous way where the first character is always a letter from A to I inclusive or S to Z inclusive and the other nine characters are always letters from A to Z or digits from 0 to 9, sets the overflow flag. 03:30:09 I added a section "MIX256" into the "MIX (Knuth)" article in esolang wiki, so you can write the descriptions in there. 03:30:34 The exact mapping would have to be defined in the spec. 03:33:28 In fact, it may be the best if in the extended CHAR output, the first character is always S to Z inclusive. (Then you can punch negatives by subtracting 20 from that character.) 03:34:57 -!- moony has quit (Ping timeout: 240 seconds). 03:36:33 The NUME instruction would then check what byte 2 in rA is. If it's a number or a number with overbar or a space, then it works then same way as NUM. If it's a letter, then it adds 20 to that character if it's between B to I inclusive, mapping those to S to Z inclusive, and maps any spaces in the following characters to zeros, then it undoes the tr 03:36:33 ansformation of CHAR. If the characters don't form a possible output from CHAR, then it sets the magnitude of rA to an undefined value. 03:36:55 In any case, NUME doesn't affect rX, the sign of rA, or the overflow toggle. 03:38:32 Also, the loader format and loader program has to be adjusted so that when it loads a word from its char representation, it uses the NUME instruction, and also makes sure to set the sign to negative if the first character is B to Z. 03:40:09 The NUME instruction can also be supported on machines where the byte range is 100 or 64, but in that case it can do exactly the same as NUM. This way programs written in assembly can be portable. 03:41:51 The assembler has to be adjusted too so it can emit the loader format. 03:42:32 But the whole thing is designed so you need minimal changes in the programs. 03:42:54 I could fix my assembler to treat NUME the same as NUM, if that can help anyone, I suppose (it doesn't support MIX256 anyways though, and only MIX; but it could be supported to support MIX256 too perhaps if anyone will want to do that) 03:43:28 zzo38: I don't think that's a good idea. Didn't you say your assembler supports an output format that is byte size independent? 03:43:45 Making NUME a synonym of NUM in that case would break programs if you load the byte size independent assembled program. 03:44:32 Yes you are right actually 03:44:34 If the assembler knows that the byte size is at most 100, then yes, then it could assemble NUME as NUM. 03:45:03 And if the byte size is more than 100, then it must not do that, because the two instructions definitely can't be equivalent, so they can't have the same representation. 03:45:06 Although currently it does support only up to 100. I have fixed it to support 64 too now, so now it can output a deck for 64, 100, or independent. 03:45:35 But I agree with you if it is going to support MIX256 in independent mode, then NUME can't be used obviously. 03:46:42 It could be used, you'd just get a program that only works on a computer that supports the NUME instruction. That's no problem, a base 64 or base 100 machine can support that too. It's like when you put any other extended instruction to your program. 03:47:15 Yes, I suppose that is another possibility too 03:50:50 technically you could probably also write a loader that checks for the byte size of the machine and uses NUME only if the byte size is large, but it's not really worth 03:53:05 -!- wob_jonas has quit (Quit: http://www.kiwiirc.com/ - A hand crafted IRC client). 03:53:07 That would be more complicated to implement 03:53:25 -!- hppavilion[1] has joined. 03:56:36 -!- augur has quit (Remote host closed the connection). 03:58:05 -!- hppavilion[1] has quit (Ping timeout: 240 seconds). 04:10:33 [wiki] [[MIX (Knuth)]] https://esolangs.org/w/index.php?diff=52862&oldid=52815 * Zzo38 * (+693) MIX256 04:20:46 [wiki] [[Talk:2014]] N https://esolangs.org/w/index.php?oldid=52863 * Zzo38 * (+571) I think the implementation of 2014 based on that of 2017 is not quite right 04:22:58 -!- quintopia has joined. 04:23:14 hello i'm back from the k-line, did i miss much 04:23:48 It depend what you wanted to look at I suppose; you could try to read the logs. 04:24:47 did you say something i needed to see zoo38 04:24:52 spoo 04:24:57 zzo38 04:26:11 I wrote nothing addressed to you, but you can still try to read it to see if any of it interests you; maybe it does or maybe not. 04:28:26 looks like what i missed was actual on-topic discussion 04:28:44 the one random day that esolangs come up as a topic and i'm gone :P 04:32:22 -!- jaboja has quit (Remote host closed the connection). 04:32:25 -!- augur has joined. 04:33:10 Well, if you have a reply you can write it now, then. 04:35:29 ais523: we could make BF harder by just having it decrement the nth cell once before executing the nth instruction (wrapping back to the first nonzero cell if all of the following cells are zero) 04:55:43 -!- augur has quit (Remote host closed the connection). 04:56:43 -!- hppavilion[1] has joined. 05:05:55 -!- hppavilion[1] has quit (Ping timeout: 255 seconds). 05:36:20 -!- augur has joined. 05:42:35 -!- xkapastel has quit (Quit: Connection closed for inactivity). 05:46:16 -!- oerjan has quit (Quit: Nite). 05:47:25 -!- augur has quit (Remote host closed the connection). 05:48:26 -!- PinealGlandOptic has joined. 05:57:05 -!- augur has joined. 05:57:50 -!- jaboja has joined. 06:03:26 -!- ais523 has quit (Ping timeout: 240 seconds). 06:12:38 -!- zseri has joined. 06:14:55 -!- augur has quit (Remote host closed the connection). 06:21:58 -!- augur has joined. 06:31:20 -!- doesthiswork has quit (Quit: Leaving.). 06:37:48 -!- erkin has joined. 06:58:59 -!- zseri has quit (Ping timeout: 260 seconds). 07:02:36 -!- FreeFull has quit. 07:05:38 -!- zseri has joined. 07:19:00 -!- jaboja has quit (Remote host closed the connection). 07:27:35 -!- PinealGlandOptic has quit (Ping timeout: 240 seconds). 07:28:20 -!- zseri has quit (Quit: Page closed). 07:57:48 hi 07:58:40 concept: BF where every instruction is increased by a randomized but predictable amount modulo 95 per instruction 07:59:35 ...and then it is salted and hashed, the same thing happens again, ad infinitum until you get bored and program in Malbolge 08:01:22 how about an esolang that helps me not suck at frontend dev. 08:02:02 imode, Elm's pretty esoteric 08:02:46 hah. 08:43:19 -!- PinealGlandOptic has joined. 08:57:28 -!- imode has quit (Ping timeout: 240 seconds). 09:40:44 -!- erkin has quit (Quit: Ouch! Got SIGABRT, dying...). 09:48:37 -!- erkin has joined. 09:52:04 -!- augur has quit (Remote host closed the connection). 09:54:03 -!- ais523 has joined. 10:30:42 -!- augur has joined. 10:34:57 -!- augur has quit (Remote host closed the connection). 10:35:09 -!- augur has joined. 10:45:19 -!- augur has quit (Remote host closed the connection). 11:00:02 -!- Antoxyde has joined. 11:19:31 -!- AnotherTest has joined. 11:23:29 -!- ais523 has quit (Remote host closed the connection). 11:24:38 -!- ais523 has joined. 11:31:00 -!- zseri has joined. 11:34:08 -!- boily has joined. 11:54:18 -!- myname has joined. 12:28:12 -!- boily has quit (Quit: SHIVERING CHICKEN). 12:31:29 -!- zseri has quit (Ping timeout: 260 seconds). 12:43:23 -!- impomatic has joined. 12:44:19 -!- ais523 has quit (Quit: lunch). 12:45:54 -!- augur has joined. 12:49:56 -!- augur has quit (Ping timeout: 240 seconds). 13:39:23 -!- PinealGlandOptic has quit (Quit: leaving). 14:00:34 -!- doesthiswork has joined. 14:39:21 -!- zseri has joined. 14:44:51 -!- ATMunn has joined. 14:52:41 -!- jaboja has joined. 14:52:44 -!- `^_^v has joined. 14:58:19 -!- wob_jonas has joined. 15:03:00 -!- doesthiswork has quit (Quit: Leaving.). 15:03:17 hi 15:46:13 -!- augur has joined. 15:50:27 -!- augur has quit (Ping timeout: 240 seconds). 15:58:32 hi 16:00:32 hi 16:00:53 hi 16:01:19 gj zseri you started a trend 16:01:32 which one? 16:01:49 which one? 16:01:51 saying 'hi'? 16:01:56 damn 16:03:07 damn 16:03:17 -!- erkin has quit (Quit: Ouch! Got SIGABRT, dying...). 16:08:58 Damn, I love how easily I could transition from my faulty UTF8 library to Lua 5.3's UTF8 library. 16:09:06 Didn't have to change a single bit of code! 16:09:24 I'm still mad how £ isn't in pure ASCII, though. 16:09:37 rdococ: just use # instead hth 16:09:49 Heh, the "pound sign." 16:10:04 or GBP 16:10:04 wob_jonas: my WIP mindscrew interpreter now supports UTF-8 encoding anyway 16:10:20 it handles them as single characters using their codepoints 16:10:46 the downside being is that it now requires Lua 5.3 to run 16:11:18 isn't that a bad idea? how will you input or output binary files or any files that are not utf-8 encoded then? 16:15:16 What what I read in article about mindscrew, I am not sure why it should support UTF-8 16:15:31 And it seem better not to 16:26:04 do you think? 16:26:31 meh, I'm gonna keep it in as an option anyway 16:26:36 do you think it should default to on or off? 16:27:04 Off [with her head!] 16:27:11 heh 16:27:27 Off, I should think 16:28:35 It also has a customizable EOF (the default being no change). 16:28:44 OK 16:28:47 I had the idea of being able to set flags via custom instructions, too. 16:30:01 Yes, that could also help (although another way can be just having separate instructions for dealing with UTF-8 input and output, than the normal 8-bit I/O instructions) 16:30:55 Ooooooooooh. 16:31:12 ,. `' 16:31:20 ` for UTF8 input, ' for UTF8 output 16:31:22 ​/home/hackbot/hackbot.hg/multibot_cmds/lib/limits: line 5: exec: : not found 16:33:06 -!- moony has joined. 16:34:04 Actually, `' would probably be better used for inputting and outputting entire lines of text (it could also be used to interpret UTF8 that way). 16:36:17 -!- moony has quit (Remote host closed the connection). 16:36:41 -!- moony has joined. 16:36:59 How should it act when calling a non-existent procedure? 16:39:22 -!- atslash has quit (Ping timeout: 255 seconds). 16:39:50 -!- atslash has joined. 16:40:22 -!- wob_jonas has quit (Quit: http://www.kiwiirc.com/ - A hand crafted IRC client). 16:40:43 Maybe it should do nothing in that case 16:41:59 How about if a user attempts to input more than one character? 16:43:23 Reads the first one, and then afterward it can read the second one, and so on, I suppose? 16:43:54 Oooh. 16:45:53 I think I might remove UTF support altogether then. 16:46:51 How about attempting to output a negative value? 16:47:12 -!- Sgeo_ has quit (Read error: Connection reset by peer). 16:47:26 Only use the low 8-bits, I should think 16:47:40 (So that -1 becomes 255, -2 becomes 254, etc) 16:48:06 do nothing for non-existent procedure? i've gotten to the age where I would a appreciate a useful error message for something like that 16:48:23 This is why we have flags. :P 16:48:47 (There's still the issue of which one should be default, though.) 16:48:53 flags: the poor man's exception 16:49:56 If anything, I might add a breakpoint system with !. 16:51:03 -!- FreeFull has joined. 16:51:06 wat. breakpoints built into the language? absurd! 16:51:51 although i guess "exit immediately and dump state" is not a terrible instruction to have in a feature-rich esolang 16:53:58 yeah, that's what I meant :P 16:54:29 anyway, my cat program works wonders with the new iostack system (zzo38's idea of reading the first one, then afterwards reading the second one). 16:54:53 for comparison, ! was the exit instruction for Spiral, but i had breakpoints as a separate feature of the IDE I wrote for it. 16:55:23 "iostack"? i thought he was just describing the typical input buffer... 16:55:49 yeah, I meant something more like "ioqueue" 16:55:57 but yes, it's an input buffer 16:56:25 lol 16:56:46 should it be part of the esolang's spec itself, I wonder? 16:56:49 it'd be pretty cool. 16:57:19 if you like, but it's a common enough way of handling input that you needn't go into great detail about it 16:58:02 I'll just add one line for it in the structure section. 16:58:15 or maybe in implementation details. 17:00:16 [wiki] [[Mindscrew]] M https://esolangs.org/w/index.php?diff=52864&oldid=52849 * Rdococ * (+200) 17:06:07 -!- kuluma has joined. 17:07:18 yeah i don't quite understand why your example programs contain ] if it's a no-op 17:07:23 oh wait 17:07:34 nvm...you can still jump to it, just not from it 17:09:52 yeah. 17:10:38 at the moment, my interpreter is lazy - it only detects mismatched brackets if it tries to jump to a non-existent matching ] 17:11:30 which means you can have more ] than necessary and nothing bad will happen 17:12:41 and more [ than necessary as long as they never get run or if run never cause a jump 17:20:46 yes 17:20:52 so +[[[[[ works 17:20:57 waot 17:21:06 yeah 17:25:44 oh, nice: 17:25:46 "Zbz"!Uijt!jt!b!wfstjpo!pg!dbu!xijdi!jodsfnfout!fbdi!dibsbdufs!cz!pof/" 17:26:04 I created a version of cat that increments each char by one. 17:27:35 I might create b`s (the inverse of the aforementioned "dbu") to decrement them. 17:32:41 [wiki] [[Talk:ObCode]] N https://esolangs.org/w/index.php?oldid=52865 * StellatedHexahedron * (+1396) proposed completeness proof 17:36:45 proposed: Encrypted ObCode. The interpreter would expect binary - it would hash the binary with SHA-8192, de-binarize it, and then interpret the hash. 17:41:37 -!- impomatic has quit (Ping timeout: 248 seconds). 17:49:30 -!- kuluma has quit (Ping timeout: 240 seconds). 17:56:54 -!- \oren\ has joined. 17:56:57 <\oren\> hahahahahahahhaa 17:57:10 <\oren\> bannon fired lol 17:57:11 Concept: If a set of integers can be thought of as a map from an integer to an existence value (boolean), and one integer can be thought of as a map from a binary place value (integer) to a bit (boolean), then an integer can be stored as a set...a recursive set that contains itself if the binary place value corresponding to its own value is 1. 17:57:19 e.g. the integer 1 contains itself. 17:57:39 (well, maybe not)... 17:58:16 Okay, so the integer 2 is 2^1, yes? That means that the integer 2 contains the integer 1, which contains 0, the empty set. 17:58:20 But 3 contains both 2 and 1. 17:58:57 4 contains, er, ...wait. 17:59:02 3 contains 1 and 0. 17:59:09 -!- impomatic has joined. 17:59:13 hi \oren\ and impomatic. 17:59:49 Hi rdococ 18:01:23 Concept: storing an arbitrary integer in the instruction pointer. the interpreter would read the instruction at ip % #instructions (where #instructions is the number of instructions), so you could perform integer arithmetic on the ip to get and set the value. 18:01:47 e.g. say the program has 23 instructions. to add 1 to the value, you'd type "ip = ip + 23", since the program wraps around. 18:03:36 A bit like a relative jump? 18:03:55 [wiki] [[Bulan]] M https://esolangs.org/w/index.php?diff=52866&oldid=46720 * Rdococ * (-925) ...er...I'm going to secretly delete this terrible Lua derivative of mine... 18:04:14 Yeah, but the jump ends up with the same instruction modulo the number of instructions. 18:05:15 You'd be able to store arbitrary values in the ip without messing up the program's control flow, basically. 18:07:43 -!- Phantom_Hoover has joined. 18:09:48 @bot 18:09:48 :) 18:17:41 <\oren\> http://www.avclub.com/article/steve-bannon-leaving-white-house-spend-more-time-s-259642 18:20:09 Damn, I'm bored. 18:28:34 `? rdococ 18:28:35 rdococ was thought to be from Budapest, then Mars, but he is actually in Airstrip One. Thanks to boily he is approaching permanent boredom & mapoledom. He is a relative of `words. 18:29:01 rdococ: have you heard of the boring company? 18:31:28 * impomatic is looking for info about Core War in the 1960s and 1970s. 18:32:26 Google didn't turn up anything apart from the few articles I already had :-( 18:33:17 int-e: sounds like me 18:33:51 @google "the boring company" 18:33:53 https://www.boringcompany.com/ 18:35:11 note also that this gives the phrase "being bored to death" a whole new meaning. 18:35:55 Hah. 18:36:09 I really wish I could stumble upon a new concept right about now. 18:38:36 https://www.linkedin.com/company/a-brand-new-concept <-- not a very original name if you ask me 18:39:38 Hey, what would happen if I threw C and first-class continuations into a blender? 18:41:08 longjmp 18:41:58 Oh, C already has been blended with first-class continuations. :c 18:42:24 well it'd be longjmp that copied the entire stack or something 18:43:06 I was thinking of creating a language that secretly worked in CPS, but didn't look like it did, to "pretend" there's a call stack to reify. 18:47:22 The only thing like a stack there would be is the scope, and that might not even be necessary. 18:56:49 !zjoust kiseki < 18:56:49 Lymia.kiseki: points -45.00, score 0.00, rank 46/47 (-45) 18:58:09 SMETANA To Infinity! joust? 19:00:22 !ztest nyuroki2 https://paste.lymia.moe/lymia/67c57bb9732ff6493347dd022bae6c5ad1912209.bf 19:00:26 Lymia.nyuroki2: points 16.48, score 42.77, rank 2/47 19:01:48 O_o 19:02:01 -!- atslash has quit (Quit: This computer has gone to sleep). 19:07:43 -!- imode has joined. 19:09:22 !ztest nyuroki2 https://paste.lymia.moe/lymia/7e0b728b0228ee0e4ac4f2dfc98b2d04ad5f7d17.bf 19:09:25 Lymia.nyuroki2: points 15.29, score 40.77, rank 2/47 19:10:06 !ztest nyuroki2 https://paste.lymia.moe/lymia/0df6ec653b90d70647abe27dc773925678971df9.bf 19:10:07 Lymia.nyuroki2: points 14.57, score 39.26, rank 3/47 19:12:05 !ztest nyuroki2 https://paste.lymia.moe/lymia/3433ff3fd457ca72fc0177810cf4750b578f012c.bf 19:12:09 Lymia.nyuroki2: points 10.95, score 31.48, rank 7/47 19:18:13 hey Lymia 19:18:21 how did all that gpl drama with bukkit shake out in the end 19:18:48 IDK. I wasn't around to see it. :D 19:19:09 shame, that was top-grade drama 19:20:16 i like how mojang never did implement the modding api 19:23:23 [wiki] [[Talk:Lazy]] https://esolangs.org/w/index.php?diff=52867&oldid=34320 * HereToAnnoy * (+210) 19:23:29 that would take effort. 19:26:05 -!- kuluma has joined. 19:35:19 Lymia.nyuroki2: points 18.33, score 46.89, rank 1/47 19:36:09 !zjoust nyuroki < 19:36:09 Lymia.nyuroki: points -45.00, score 0.00, rank 47/47 (-44) 19:36:26 Lymia.nyuroki2: points 19.00, score 48.23, rank 2/47 (--) 19:39:36 -!- kuluma|2 has joined. 19:42:10 -!- kuluma has quit (Ping timeout: 240 seconds). 19:42:46 I had the idea of a language where you could access and modify the call stack. 19:42:54 forth. 19:42:59 literally forth. 19:44:22 damn it... 19:45:07 okay, what about this: 19:45:10 that shouldn't stop you from implementing one though. 19:45:13 You know how Lua has a C API? 19:45:13 they are fun. 19:45:19 uh-huh. 19:45:25 How about: an esolang with an itself API. 19:45:34 are you just grasping at straws. 19:45:41 Kinda. 19:45:56 go do useful work for a while, weird shit pops up while you do it. 19:46:29 I don't have useful work to do. 19:46:42 -!- augur has joined. 19:47:06 I can barely implement a language; one-character esolangs like mindscrew are a special case. 19:47:23 http://cc.bingj.com/cache.aspx?d=1462716999241&mkt=de-DE&setlang=en-US&w=xEsMxqoa0KJSwMsTh3p_8w2qryykfDvB 19:49:11 O_o 19:50:42 . o O ( a queue w/ a peek operation is equivalent to a tape ) 19:51:04 -!- augur has quit (Ping timeout: 255 seconds). 19:53:21 imode: What if you had a call queue rather than a call stack? 19:53:51 no idea. experiment. 19:54:01 you'd go from depth-first to breadth-first. 19:54:05 fwiw. 19:54:24 how would the breadth-first calls be evaluated then? 19:54:56 I'd think it'd look something like the actor model. 19:55:09 meh 19:55:10 maybe 19:57:56 -!- augur has joined. 19:58:35 Lymia.nyuroki2: points 18.00, score 45.87, rank 2/47 (--) 19:58:46 I'd try creating a language where everything is a set, but that already probably exists 20:07:22 setl, yup. 20:07:46 just because these things exist doesn't mean you can't still do stuff. 20:08:52 true 20:09:01 I guess... although pairs are looking kind of nice right now 20:09:09 tuples, baybe. 20:09:25 tuples are fun. go look up Linda. 20:10:03 couldn't find anything related to tuples with "Linda" 20:10:19 https://en.wikipedia.org/wiki/Linda_(coordination_language) 20:10:23 anyway, all you really need is the pairs. you can do tuples with pairs. (3, (2, 4)) 20:10:28 https://en.wikipedia.org/wiki/Tuple_space 20:10:38 https://software-carpentry.org/blog/2011/03/tuple-spaces-or-good-ideas-dont-always-win.html 20:11:21 meh, pairs 20:11:47 -!- augur has quit (Remote host closed the connection). 20:12:45 I'd say sets but idk how I'd implement pairs with it. ik {{a}, {a, b}} enables you to determine which order they're in, but how do you reach the members of a set in the first place - it's not like they're key-value pairs 20:12:54 Lymia.nyuroki2: points 16.45, score 42.05, rank 2/47 (--) 20:15:49 -!- alercah has joined. 20:16:16 -!- atslash has joined. 20:16:23 Lymia.nyuroki2: points -5.76, score 14.38, rank 41/47 (-39) 20:17:14 Lymia.nyuroki2: points 9.29, score 29.86, rank 7/47 (+34) 20:22:26 Concept: an encryption form similar to those we have now, but more easily reversible 20:22:35 it might be usable for compression 20:22:38 Lymia.nyuroki2: points 19.05, score 48.28, rank 2/47 (+5) 20:23:10 doesn't every joust have a playing field? 20:30:18 Lymia.nyuroki2: points 19.05, score 48.28, rank 2/47 (--) 20:33:32 imode: what about a lang where every number is a fraction? 20:34:03 ...literally one of the well-known esolangs. 20:34:08 rather than storing 1.5, you'd store 3 / 2 20:34:13 okay, which one is it this time 20:34:19 fractran. 20:34:23 In Kvikkalkul all of the number is less than 1 20:34:24 damn it 20:34:24 :P 20:34:37 ugh, I just want an idea I can claim as my own 20:34:45 and nobody can help me because it'd be their idea then 20:34:52 why not just do fun stuff. 20:35:07 like what? 20:35:58 I dunno. forget about being 'original' and just... build the thing that makes you excited? 20:36:19 nothing makes me excited 20:36:25 they have a pill for that. 20:36:35 they have a pill for everything 20:40:25 imode: remember my "everything is an integer" idea? 20:40:34 mhm. 20:40:41 well, what if sets were stored as binary data, but could be modified like integers? 20:40:54 I mean, integers (and everything else) is binary data anyway... 20:41:19 flesh it out a little. 20:41:31 how? the basic premise is there... 20:41:43 you mean like syntax, or...? 20:42:06 you have the words "store sets as binary data" written down. show me how you'd store example sets. 20:42:10 how you'd manipulate them. 20:42:12 Lymia.nyuroki2: points 19.67, score 49.17, rank 2/47 (--) 20:42:16 * rdococ sweats 20:42:25 talking about ideas is easy, implementing them is hard. 20:43:21 each object could (at least to the perspective of the programmer and language itself) be stored as 1) one byte representing the type of the object, 2) one byte representing the size of the object in bytes, and 3) the data itself 20:44:02 ...maybe? I don't know... 20:44:09 told you I'm bad at this 20:44:32 what if we take the other route, and store integers as sets? 20:44:40 you sound like a very insecure person who needs to stop taking input from people like me. 20:44:57 maybe I should jump off a cliff, I don't know 20:45:26 well, bungee jumping is always fun. 20:45:31 I'm going to shut up before people start getting angry at me again. 20:46:06 -!- wob_jonas has joined. 20:47:49 I keep thinking I'm creative, when I'm not. I'm not a "special" person like people say I am. I'm just an idiot at an old laptop. 20:48:15 self-deprecation is usually the worst route to take. we're all just doing this for fun. 20:48:32 yeah, well, it's the only route I ever seem to be able to take 20:48:33 rdococ: maybe you're special but have to find what you're special in? 20:48:46 you need something to work on. 20:48:59 wob_jonas: I didn't know nothing counted as a thing I could be special in. 20:49:05 imode, like what? 20:49:17 some project that you want to wake up and work on every day. 20:49:34 oh please, I get bored of every project I try to start after five minutes 20:49:35 from personal experience, if I don't have that, I'm a wreck. 20:49:58 imode: well, I just completed one. scanning an old book. 20:50:05 ayyyy. 20:50:05 I hope that counts. 20:50:08 it does. 20:50:43 is there something the high-level end of language design hasn't reified yet? 20:51:01 rdococ: another thing you should do is stop trying to be original when there's a lot you haven't explored. 20:51:14 instead, focus on enriching yourself with different ideas. 20:51:21 how 20:51:42 start with something that seems appealing to you. for example, I was obsessed with forths for a long while, so I implemented a couple. 20:51:52 they sucked, but it was fun, and stack-based things are fun and easy to work on. 20:52:02 see? all that will happen is sucky stuff 20:52:04 you seemed to like simple languages like brainfuck. 20:52:18 yeah, but it gets you to dream of what you could do with what you learned. 20:52:40 life is all about projects. working on them, taking a break from them, thinking about them, completing them, giving them up. 20:52:41 not in my experience 20:52:59 without them, we are workers without material. 20:53:14 I am a worker who can't work even with material 20:53:26 now the first thing you need to do is stop with the defeatism. 20:53:37 why? 20:53:47 it's good for angsty school kids but if you want to develop as a person, dropping it at your first convenience is good for you. 20:54:05 we're all just dudes faffing about on computers. 20:54:15 of course schools kids are going to be angsty, they're forced to be at school 20:54:57 -!- augur has joined. 20:55:21 one of the things I've seen you do is realize that something's been done before and immediately get discouraged. 20:55:31 I can't help it 20:55:39 that should not be your response. what should be your response is "oh wow, well-trodden ground. let's go exploring." 20:55:48 it just feels like I'm copying other people 20:55:54 we all are. in some fashion or another. 20:56:00 shoulders of giants and all that. 20:56:22 well... I was thinking about a language whose programs are secretly written in CPS 20:56:40 so go forward on that. 20:56:48 so every instruction would be of the form "name a b c k", where k is the continuation 20:56:49 How is it a secret that the programs written in CPS? Nevertheless, you can ty. 20:56:54 -!- augur has quit (Remote host closed the connection). 20:57:11 -!- augur has joined. 20:57:13 zzo38: I really don't think you're helping. 20:57:39 regardless of what any of us say or do, it's your project at the end of the day. 20:58:55 Lymia.nyuroki2: points 20.10, score 51.37, rank 1/47 (+1) 21:08:14 I'm still not sure how a call queue could evaluate anything. 21:08:55 ....Hey... CPS has the effect of turning a complicated expression inside out, yes? 21:18:58 Maybe, rather than, say, "(3 * x) + 2", you'd go "*(3, x, +(2))"? 21:19:14 or +(_, 2) or something 21:29:30 you look like you're building s-expressions. 21:31:45 Lymia.nyuroki2: points -21.48, score 4.98, rank 45/47 (-44) 21:33:01 imode: breadth-first call queues could be used like this: 3 / 2 (4 * (- 1)) 21:33:50 Lymia.nyuroki2: points 20.10, score 51.37, rank 1/47 (+44) 21:33:50 or maybe with a variable r or something 21:46:16 -!- atslash has quit (Ping timeout: 255 seconds). 21:46:45 -!- atslash has joined. 21:47:01 hm... this is just beginning to look like normal expressions with weird parentheses 21:47:04 imode, what do you think? 21:47:09 it looks like s-expressions. 21:47:20 s-expressions? 21:47:24 ... 21:47:34 I'm sorry. 21:47:39 https://en.wikipedia.org/wiki/S-expression 21:47:44 no I'm just surprised is all. 21:47:49 ...I just looked that up 21:47:55 I know I'm dumb. 21:48:57 -!- sleffy has joined. 21:49:01 you're not dumb. you've just never heard of them before. 21:50:08 ...eh, true. 21:50:16 ...which is also not false! :P 21:50:28 `quote 21:50:28 788) the scene: it is a warm summer's day in scotland, although one obscured by cloud and the fact that it is september 21:50:56 -!- xav737 has joined. 21:51:05 -!- wob_jonas has quit (Quit: http://www.kiwiirc.com/ - A hand crafted IRC client). 21:51:19 heh 21:52:04 well then 21:52:37 nothing happening? 21:52:56 kthen 21:53:09 -!- xav737 has quit (Client Quit). 21:53:21 -!- sleffy has quit (Ping timeout: 248 seconds). 21:55:08 -!- sleffy has joined. 22:03:22 -!- zseri has quit (Quit: Page closed). 22:06:09 -!- kuluma|2 has quit (Ping timeout: 248 seconds). 22:51:32 Lymia.nyuroki2: points 21.26, score 55.04, rank 1/47 (--) 22:54:00 [wiki] [[Swapper]] https://esolangs.org/w/index.php?diff=52868&oldid=43971 * Ehulinsky * (+2437) added output and pseudo-operators 22:54:48 -!- AnotherTest has quit (Ping timeout: 240 seconds). 22:58:11 [wiki] [[Swapper]] M https://esolangs.org/w/index.php?diff=52869&oldid=52868 * Ehulinsky * (+15) Add self-modifying 23:00:05 -!- APic has quit (Ping timeout: 240 seconds). 23:08:12 -!- `^_^v has quit (Quit: This computer has gone to sleep). 23:12:01 I tried to make this map projection http://mathworld.wolfram.com/AzimuthalEquidistantProjection.html but the meridians at +180 and -180 longitude appear as straight lines (and the parts of longitudes that are close to it appear as straight lines near the equator; maybe it is a problem having to do with precision). Do you know how to fix this please? 23:16:40 Is it supposed to do that? These straight lines are crossing all of the other meridians, so, doesn't looks so good? 23:18:54 -!- jaboja has quit (Remote host closed the connection). 23:23:03 -!- sleffy has quit (Ping timeout: 255 seconds). 23:28:06 -!- sleffy has joined. 23:31:24 -!- atslash has quit (Quit: Leaving). 23:34:42 -!- APic has joined. 23:35:03 Maybe it is supposed to do that. 23:36:33 Now that I thought of it, I suppose it probably is supposed to do that, because it is going to be a discontinuity (since it is on the other side of the world, so the line would be at the top instead of the right side; the straight line is due to the discontinuity) 23:43:59 -!- boily has joined. 23:46:16 `5 w 23:46:21 1/3:oerjan//Your omnipheasant back principal swatty arrant "Darth Ept" oerjan the indecisive is a hazy expert in minor compaction. Also a Glaneep who disses Roald Dahl. He could never render the word "amortized" so he put it here for connivance. His ark-nemesis is Noah. He twice punned without noticing it. \ `sled//`sled // \ 23:46:29 `n 23:46:30 2/3:zomgmodules//ZOMGMODULES is both a small blonde veterinarian and just modules over the ring of ZOMGs. \ bicyclic monoid//The bicyclic monoid is the free monoid generated by two wheels of a bicycle, quotiented by the restriction that the bicycle itself is equal to the identity. \ claustrophobia//Claustrophobia thought the wisdom database was get 23:46:32 `n 23:46:32 3/3:ting too crowded, so left. 23:46:57 fungot: what's a darth ept? 23:46:57 boily: 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! 23:47:33 -!- oerjan has joined. 23:50:34 hm still +R 23:51:32 hellørjan. 23:51:41 is it dire? 23:53:34 helloily. well the logs perviously spoke of child porn. 23:53:43 * oerjan decided not to fix that misspelling. 23:54:34 oh. 23:54:43 so freenode seems to have put everyone(?) on +R as default mode. 23:54:50 `slwd oerjan//s/twice/thrice/ 23:54:52 oerjan//Your omnipheasant back principal swatty arrant "Darth Ept" oerjan the indecisive is a hazy expert in minor compaction. Also a Glaneep who disses Roald Dahl. He could never render the word "amortized" so he put it here for connivance. His ark-nemesis is Noah. He thrice punned without noticing it. 23:55:01 um i noticed that. 23:55:14 before pressing enter. 23:55:32 although the typing itself was subconscious. 23:56:22 the subconscious spoke. 23:56:38 “+R - Enables use of the recover and clear commands.” ← what does it mean? 23:56:58 that's for channels, you should look at user modes. 23:56:59 That is not what it says? Use command "HELP UMODE" it explain its meaning 23:57:16 or actually, that's for op flags. 23:57:39 well maybe. 23:58:09 Lymia.nyuroki2: points 12.24, score 35.23, rank 4/47 (-3) 2017-08-19: 00:08:35 -!- moonythedwarf has joined. 00:09:05 -!- moony has quit (Ping timeout: 246 seconds). 00:32:15 `` ls wisdom/*moon* 00:32:17 wisdom/moon 00:32:40 `` find wisdom/ -type f -iname '*moon*' 00:32:41 wisdom/moon 00:51:33 -!- hppavilion[1] has joined. 00:52:49 Lymia.nyuroki2: points 21.24, score 54.96, rank 1/47 (+3) 01:04:15 Lymia.nyuroki2: points 20.57, score 53.03, rank 1/47 (--) 01:06:39 Lymia.nyuroki2: points 19.17, score 48.96, rank 1/47 (--) 01:06:54 Lymia.nyuroki2: points 20.57, score 53.03, rank 1/47 (--) 01:10:35 Lymia.nyuroki2: points 21.24, score 54.96, rank 1/47 (--) 01:14:13 Lymia.nyuroki2: points 7.48, score 26.53, rank 13/47 (-12) 01:14:41 Lymia.nyuroki2: points 21.24, score 54.96, rank 1/47 (+12) 01:21:10 [wiki] [[Special:Log/delete]] delete * Oerjan * deleted "[[Bulan]]": Author request 01:25:27 -!- moonythedwarf has quit (Ping timeout: 240 seconds). 01:27:19 -!- moony has joined. 01:33:23 -!- doesthiswork has joined. 01:37:55 -!- moony has quit (Remote host closed the connection). 01:38:21 -!- moony has joined. 01:41:46 `ysaclist (64) 01:41:47 ysaclist (64): boily shachaf 01:42:18 I think parentheses are deprecated. 01:46:41 Why? 01:47:35 why not? 01:47:45 spoken language doesn't need em 01:48:14 「【『[(parentheses are great)]』】」 01:48:19 Perhaps, but writing will make it clearer though 01:48:32 helloochaf, hezzo38, hellorcah. 01:51:00 I meant, for ysaclist 01:51:08 "`ysaclist 64" is just fine 01:52:13 Not knowing what it is mean, I would not know, if you should need the parentheses or not 01:52:38 Lymia.nyuroki2: points 21.26, score 55.04, rank 1/47 (--) 01:54:08 Lymia.nyuroki2: points 21.24, score 54.96, rank 1/47 (--) 01:55:31 Lymia.nyuroki2: points 21.26, score 55.04, rank 1/47 (--) 01:58:13 -!- Phantom_Hoover has quit (Read error: Connection reset by peer). 02:00:58 Lymia.nyuroki2: points 21.90, score 56.88, rank 1/47 (--) 02:02:21 -!- sleffy has quit (Ping timeout: 240 seconds). 02:16:01 `5 w 02:16:06 1/2:adjective//Adjectives are words frequently found attached to chickens. \ quintopia//quintopia is our resident tl;dr generator. He is flooded by thundercats and thunderdogs. He is the temporal antipode of boily despite living on the same continent. \ the walrus//In order to obtain the unredacted documents specifying the true identity of the walr 02:16:14 `n 02:16:15 2/2:us, contact the Glass Onion (mailing address: UH2BEStWmPI). \ transformer//A transformer is one who used to trans, but no longer does. \ lambek's lemma//Lambek's Lemma, invented by Joachim "Taneb" Lambek, states that initial algebras have inverses. It can be proved with as few as five arrows. 02:22:18 -!- moony has quit (Quit: Leaving). 02:22:43 -!- moony has joined. 02:25:00 -!- moony has quit (Client Quit). 02:25:01 -!- impomatic has quit (Quit: impomatic). 02:25:23 -!- moony has joined. 02:25:44 Lymia.nyuroki2: points 21.95, score 57.08, rank 1/47 (--) 02:33:46 Lymia.nyuroki2: points 21.95, score 57.04, rank 1/47 (--) 02:34:40 -!- hppavilion[0] has joined. 02:35:35 -!- hppavilion[1] has quit (Ping timeout: 240 seconds). 02:37:28 Lymia.nyuroki2: points 21.95, score 57.15, rank 1/47 (--) 02:37:50 Lymia.nyuroki2: points 21.95, score 57.08, rank 1/47 (--) 02:42:27 Lymia.nyuroki2: points 22.05, score 57.39, rank 1/47 (--) 02:44:32 -!- PinealGlandOptic has joined. 02:51:39 Lymia.nyuroki2: points 22.83, score 59.84, rank 1/47 (--) 02:55:34 -!- xkapastel has joined. 03:02:14 -!- ATMunn has quit (Quit: See ya! o/). 03:14:33 Lymia.nyuroki2: points 19.10, score 49.18, rank 1/47 (--) 03:17:02 -!- moony has quit (Remote host closed the connection). 03:19:34 -!- boily has quit (Quit: LUNATIC CHICKEN). 03:21:38 Lymia.nyuroki2: points 22.83, score 59.84, rank 1/47 (--) 03:28:38 -!- Antoxyde has quit (Quit: Leaving). 03:30:51 Lymia.nyuroki2: points 22.95, score 60.17, rank 1/47 (--) 03:35:25 !ztest fetch https://paste.lymia.moe/lymia/c608f1bba429b91cdc60d221ade02a2da70932de.bf 03:35:26 Lymia.fetch: points 1.26, score 21.06, rank 16/47 03:37:49 !ztest nyuroki https://paste.lymia.moe/lymia/bf712c780e0595518fd4b17b09152acf31c62af4.bf 03:37:50 Lymia.nyuroki: points -8.36, score 12.46, rank 42/47 (+5) 03:38:05 !ztest nyuroki https://paste.lymia.moe/lymia/67c57bb9732ff6493347dd022bae6c5ad1912209.bf 03:38:06 Lymia.nyuroki: points 15.81, score 40.40, rank 3/47 (+44) 03:38:59 -!- hppavilion[0] has quit (Remote host closed the connection). 03:39:24 -!- hppavilion[0] has joined. 03:45:37 Does vim have a insertion mode so that if return key is push it moves the cursor to the same column as it was in before on the next line instead of inserting a line break? 03:47:44 !zjoust nyuroki2 https://raw.githubusercontent.com/Lymia/JoustExt/master/examples/nyuroki2.bf 03:47:45 Lymia.nyuroki2: points 22.83, score 59.84, rank 1/47 (--) 03:56:15 -!- prooftechnique has quit (Quit: ZNC http://znc.in). 04:12:32 -!- prooftechnique has joined. 04:59:24 "I've had a couple of other Astrolog dreams; I had one neat one while working on the -h feature (described later) about a far distant future version of Astrolog that could actually teleport one to the places which they cast charts for." But can it also teleport you to the time that the chart is cast for (in the past or future)? 05:03:10 wtf is astrolog. 05:03:23 oh, astrology. bullshit then. 05:07:53 It is actually not bad software, although some of the features are rather worthless (such as the interpretation feature). 05:08:29 buddy if it can convince me that the transit of venus influences my bowel movements, it'll win a nobel. 05:08:56 I doubt the transit of Venus can influence your bowel movements. 05:09:31 But it can calculate the transit of Venus anyways if you want it. 05:10:30 -!- oerjan has quit (Quit: Nite). 05:22:03 -!- wob_jonas has joined. 05:25:36 Do you know that my MIX assembler now has EJMP and EJSJ commands which is somewhat like COME FROM (although computed at compile time, rather than run time)? 05:27:18 zzo38: is that like the afterthought source patching functions that cobol or cweb have? 05:28:08 Actually, no; what I used it for was to build jump tables, although it doesn't have to be used for jump tables. 05:29:26 zzo38: does it insert an instruction to where it comes from by shifting the following instructions one word down, or by replacing one instruction like a debugger would do to set a breakpoint? 05:30:22 By replacing the instruction, so it won't work so well unless it is already a jump or NOP. 05:30:56 does it make the previous instruction it replaced available somehow? 05:31:33 Currently no, although I could perhaps add that feature later. 05:31:34 and for building jump tables, can you just use labels and JMP instead? 05:32:49 You could, although I find this way more convenient (I have used something similar in 6502 assembly language programs too, although in that case I used a macro and the jump table did not itself contain jump instructions). 05:34:05 ok 05:36:38 Although I will consider your idea making the previous instruction it replaced available somehow, perhaps a new pseudo-instruction can be used to insert it (although I am not sure what to call it; do you have the idea?) 05:45:10 zzo38: well, if the EJMP is a COMESUB pseudo-instruction, then you need a corresponding RETURN pseudo-instruction. normally this would be just a jump, but MIX's rJ feature makes it tricky, so you'll need to use those tricks to set rJ, which are described in Knuth vol 1 at debuggers and involve some self-modifying code. 05:47:07 wob_jonas: You can just return in the normal way. However, replacing the instruction is different, since you may want to execute that instruction (the programmer has to deal with the consequences of doing so by himself). 05:47:33 zzo38: yes, so the replacement routine has to execute that replaced instruction before returning 05:48:11 Yes, and I wanted to know what to call it. 05:51:26 maybe ERET? 05:51:44 um, why is EJMP called EJMP in first place? 05:52:20 -!- ais523 has joined. 05:52:24 It is short for "enter JMP into the specified location" 05:52:40 ah 05:53:18 well, maybe ERET then. and its parameter is the label of the EJMP. 05:54:08 hi ais523. zzo38 is just talking about how he added a COME FROM or NEXT FROM to an assembler. or something. 05:54:33 FORTRAN has an effective COME FROM and it's basically an asm (especially in fixed form) 05:54:43 the only real difference is that it has arithmetic expressions 05:54:54 wob_jonas: OK I could do 05:55:16 What's a good subset of the real numbers that's sufficient for most uses but also has e.g. computable equality? 05:55:25 ais523: ok 05:55:57 shachaf: the rationals, most likely 05:56:01 shachaf: uh... I think algebraic reals has a computable representation with computable comparison, but the algorithms are really complicated, 05:56:12 The EJMP and EJSJ in my assembler have arithmetic expressions too, although can be computed only at compile time. 05:56:32 wob_jonas: huh, algebraic reals can be compared? that's actually pretty interesting 05:56:49 ais523: The rationals don't include a lot of useful numbers 05:56:53 you could take just quadratic irrational reals, that is closure of reals on field ops and square root of positive numbers, which definitely has computable less-than comparison with an easy to understand (but slow in general) algorithm 05:56:55 the computable reals have computable /inequality/ but it doesn't work for two values which happen to be equal 05:57:07 It's semicomputable. 05:57:11 Or semidecidable, whatever. 05:57:24 ais523: I think so, but I'm not sure, and I think Mathematica is about the only program that implements the full algorithm 05:57:38 https://hackage.haskell.org/package/cyclotomic seems like a good attempt 05:57:48 "The cyclotomic numbers contain the square roots of all rational numbers. They contain the sine and cosine of all rational multiples of pi." 05:57:55 (For example, you might write "EJSJ JTBL+5", and then if rI1 contains 5 then "JMP JTBL,1" will jump to the entered JSJ instruction, which then jumps to the location of the EJSJ in turn. 05:57:59 hmm, I don't know how much GAP implements 05:58:01 Not quite as good as algebraic. 05:58:05 it might implement all of it too 05:58:08 let me check the manual 05:59:54 nope, GAP doesn't implement all of it, but it does implement an interesting subset: 06:00:15 http://www.gap-system.org/Manuals/doc/ref/chap18.html GAP admits computations in abelian extension fields of the rational number field ℚ, that is fields with abelian Galois group over ℚ. 06:00:32 which might answer shachaf's question 06:01:21 and it might not implement less-than comparison for those 06:03:44 but I think it implements equal comparison 06:04:10 Can any long programs be made up that will work even if the cards are mixed up (including the first and last card)? Can it be made to work even if a small percentage of the cards are removed afterward? 06:04:48 shachaf: anyway, there are also various sets of fixed-size floating point numbers, if you exclude non-real values from them, and all those are finite subsets of rationals 06:06:24 zzo38: in MIXAL, I'd guess no. For example, if you happen to mix such that the END statement is the first card, you're screwed. 06:07:12 Yes, I know that. But I meant a compiled program (that isn't compiled using MIXAL necessarily) 06:07:44 wob_jonas: Even the algebraic numbers don't include important values like pi 06:09:35 zzo38: in that case, I guess it can be done, but I'm not completely sure 06:10:33 (Also, my own assembler does support some pseudo-ops even after END: EQU, PUNCH, and DECK. You can use this EQU if you want addresses after the equal sign expressions have been compiled; since it is a two pass assembler, it can be used.) 06:19:01 Google's INTERCAL style guide implies that the physical cards have machine-readable numbers on them that allow them to be placed into order, and that the compiler is instructed not to read them 06:19:05 you could probably do something similar with MIX 06:20:58 Possibly each card could contain the loader program for one MIX word and increments a counter so that it can know once all of the cards have been loaded, it can start the execution. 06:21:52 zzo38: something like that could work, but it'd be hard to fit on one card with all punchable words 06:22:54 if your card reader can read any byte, then I think you can do it 06:24:50 There is also the trouble of initializing the counters. However, I will try to see anyways 06:26:34 zzo38: you can use the fact that the start button loads the first card to address 0, you load all your cards to a different address (say 16), then you can distinguish the first card from other cards by overwriting an instr at either the first card or other cards read buffer, and initialize the counter if it's the first card 06:26:43 there are other ways but that's probably the easiest and most robust 06:27:55 Yes I actually did think of that 06:28:01 more obscure ways would be to rely on the fact that the start button initializes rJ to 0, but that would be non-robust because implementations of the start button in MIX can't do that, so some MIXes might be non-comforming; or the fact that the start button sets the overflow flag 06:28:42 [wiki] [[Special:Log/newusers]] create * Javyu * New user account 06:29:44 or you can overwrite some of the code of the next card after you load it but before you jump into it 06:30:26 or you can jump into the middle of the next card and initialize the counter at the start of the card 06:31:44 I have thought of some of those things 06:32:20 the overflow fact method might actually be shorter if you want punchable cards 06:32:29 overflow flag method 06:34:45 Yes, OK 06:35:58 I did not know that it affects the overflow flag, or maybe I read it once and I forgot. 06:39:59 Hmm strange. The exercise about the card loading routine says that "=" and ":" characters might not be readable from a card. But those characters are used in MIXAL, and ":" appears in a lot of MIXAL programs. How does that work? 06:41:28 Those two characters would help a lot with punchable routines 06:41:46 Maybe MIXAL does not run on the computers that can't read "=" and ":" 06:42:25 maybe, but that would be strange. 06:42:43 why would Knuth choose that syntax then instead of some syntax that doesn't use those characters? 06:43:09 Of course it might also just be a mistake 06:43:43 And I think the loader program given in the answer section actually does have a equal sign (although I do not quite remember) 06:43:45 yeah, but Knuth rarely does mistakes 06:44:02 especially ones he hasn't corrected since 06:44:13 wob_jonas: Why don't you submit it as a bug? 06:44:29 I'm not sure it's a bug yet 06:45:39 I also don't know if Knuth still cares about updating the MIX versions of the programs (even though I would be interested in both the MIX and MMIX versions) 06:46:36 zzo38: even if he doesn't update them, he is still interested about bugs 06:46:48 bugs in his books that haven't yet been reported that is 06:46:51 O, OK. 06:47:15 and no, it doesn't look like the solution has an equals sign 06:47:39 in the punched version that is 06:47:47 it does have equals sign and colon in the assembly version 06:48:15 but that doesn't matter 06:48:16 Maybe I was mistaken and forgot, I suppose 06:58:59 oh, and it's called the GO button, no the start button 07:10:58 -!- wob_jonas has quit (Quit: http://www.kiwiirc.com/ - A hand crafted IRC client). 07:28:32 -!- zseri has joined. 07:57:36 hi 07:59:12 -!- imode has quit (Ping timeout: 255 seconds). 08:09:23 -!- sleffy has joined. 08:16:59 -!- zseri has quit (Quit: Page closed). 08:26:06 -!- kuluma|2 has joined. 08:44:30 Concept: a fungeoid........on a triangular tiling 09:05:21 -!- sleffy has quit (Ping timeout: 240 seconds). 09:09:12 -!- hppavilion[0] has quit (Read error: Connection reset by peer). 09:14:46 -!- xkapastel has quit (Quit: Connection closed for inactivity). 09:34:11 -!- augur has quit (Remote host closed the connection). 09:34:44 -!- augur has joined. 09:37:41 -!- AnotherTest has joined. 09:38:57 -!- augur has quit (Ping timeout: 240 seconds). 09:41:18 Still trying to figure out how a call queue could work. 09:41:41 A normal expression of the form "(((4 * 3) / 2) + 1) - 0.3" would be written "4 * 3 (/ 2 (+ 1 (- 0.3)))"...maybe. 09:42:13 Key part here, though, is I'm not dividing 2 by (+ 1 (- 0.3)) - quite the opposite, in fact. 09:43:06 -!- LKoen has joined. 09:44:35 -!- kuluma|2 has quit (Ping timeout: 240 seconds). 09:54:28 Concept: first in, middle out 10:02:26 -!- zseri has joined. 10:10:03 -!- augur has joined. 10:14:35 -!- augur has quit (Ping timeout: 240 seconds). 10:15:16 hi zseri. 10:15:25 hi rdococ 10:15:38 wow, everything can be first-class nowadays... 10:15:43 -!- kuluma|2 has joined. 10:15:47 yes 10:16:00 Concept: first-class classes - but not in the sense of data types, in the sense of first-, second- and third- class 10:16:33 e.g. you could create an anonymous new class whose member data types can't be passed to parameters but can be returned 10:18:12 Is there already something like creation of classes on demand (anonymous class as return type)? 10:18:37 No, not that kind of class... 10:18:55 You know how data types may be first-class, second-class, third-class etc. depending on the language they reside? 10:20:52 oh, first-class classes are easy to understand, just normal classes. 10:21:41 ...Nevermind. 10:21:44 we can pass second-class classes around via moving or forwarding 10:22:18 but whats the use of third-class classes? 10:23:08 How about a language with: 1) ability to access and modify the call stack at runtime, and 2) first-class stacks? 10:23:25 That way, a program could implement its own continuations. 10:23:37 that would allow a very complicated control flow. 10:24:11 A program could pop items from the call stack, and then redirect the instruction pointer where-ever. 10:24:55 Not only that, it would be able to push frames to the call stack. Each individual call frame would also be first-class. 10:25:43 f(x, y) is a function invocation; getcallframe(f, x, y) would literally call f if it was pushed to the stack, and then the instruction pointer was redirected there. 10:25:47 the program could use runtime-controllable, on the fly generated goto statements as the only flow control mechanism beside simple if statements. 10:26:14 You'd be able to perform pointer arithmetic on instructions for relative instruction addressing, too. 10:26:50 You'd also be able to get a pointer to the instruction that the IP is set to when a function is called. 10:27:24 e.g. "push(callstack, getcallframe(f, x, y)); goto(getip(f));" would be a complicated way of saying "f(x, y)". 10:28:44 And "var r = peek(callstack):getReturnAddress(); pop(callstack); goto(r);" would be a complicated way of saying "return;". 10:29:49 Does anyone else think it gets to the point where high-level is becoming low-level with safeguards? 10:39:27 -!- Vorpal has joined. 10:39:38 -!- doesthiswork has quit (Quit: Leaving.). 10:41:10 Vorpal! 10:42:16 hi 10:42:53 -!- FreeFull has quit (Quit: Rebooting). 10:43:09 We were discussing first-class call frames. 10:43:56 interesting, not really looking to engage in chatting atm 10:44:17 just code in asm, everything is first class then 10:44:44 I guess I'll go invoke continuations in asm, then. 10:45:12 Then again, I guess you could copy each stack frame, and copy the instruction pointer... 10:45:18 you could write some pre-processor macros that help you do it. I'm fairly sure I have seen preprocessed ASM at some point or another 10:50:14 -!- FreeFull has joined. 10:51:42 -!- Phantom_Hoover has joined. 11:02:03 https://gist.github.com/rdococ/b7ec09bdea6cfe837470c14e7a2b1fbb 11:02:14 Woah, it's a phantom hoover! O_o 11:02:47 -!- LKoen has quit (Remote host closed the connection). 11:03:25 [wiki] [[Language list]] https://esolangs.org/w/index.php?diff=52870&oldid=52784 * Zayne * (+14) 11:04:23 [wiki] [[InSpace]] https://esolangs.org/w/index.php?diff=52871&oldid=52829 * Zayne * (+27) 11:04:58 [wiki] [[InSpace]] https://esolangs.org/w/index.php?diff=52872&oldid=52871 * Zayne * (+1) /* Commands */ 11:08:52 [wiki] [[SMITH sharp]] https://esolangs.org/w/index.php?diff=52873&oldid=38971 * Zayne * (+17) 11:09:00 [wiki] [[SMITH sharp]] https://esolangs.org/w/index.php?diff=52874&oldid=52873 * Zayne * (-17) 11:16:42 [wiki] [[Noid]] https://esolangs.org/w/index.php?diff=52875&oldid=52861 * Zayne * (+40) /* Examples */ 11:22:37 O_o 11:27:58 I'm working on a concept for a language in which continuations are passed implicitly from the point of view of the caller, but explicitly from the point of view of the callee. 11:28:57 -!- Antoxyde has joined. 12:05:19 rdococ: I think there is a good reason why most languages handle call frames implicitly, but aren't there some runtime environments that expose access to them for debugging purposes? Thinking about various VMs here, such as Java, .NET and similar 12:05:53 You can certainly get read only info about them, not sure to what degree you can manipulate them 12:06:03 the BEAM VM (used by erlang) maybe 12:07:37 Concept: A lang where all function calls are call/cc, and a function would call the continuation with parameters to return. 12:08:05 You would even be able to pass an extra argument at the end of the function call to trick it into calling a different function/continuation. 12:08:39 rdococ: I believe various intermediate languages used by compilers might fit that model? 12:09:08 Vorpal; It's quite similar to the "goto/cc" model I conceptualized before. 12:09:37 rdococ: sounds like CPS 12:09:42 https://en.wikipedia.org/wiki/Continuation-passing_style 12:09:51 It is CPS, basically. 12:10:08 Except you don't have to explicitly nest the functions. 12:10:25 The more I talk about it, the less esoteric and more practical it seems :P 12:10:33 right, I think I may need to read up on CPS, been years since I looked at it 12:11:36 If you want a summary: CPS is a style of programming in which each function takes an explicit argument - an anonymous function on what to do with the function's result - and "returns" by calling the aforementioned argument with the result. 12:11:46 yes 12:11:48 that I remember 12:12:04 But I didn't understand your comment about not having to explicitly nest 12:16:11 https://gist.github.com/rdococ/d4efef3a491f149ed4ecb6bca90df810 12:19:56 As in, you don't have to explicitly pass the continuation, it occurs implicitly. You just get the benefit of being able to access the continuation explicitly from inside the function itself. 12:20:33 It also means you can choose to explicitly pass a continuation, and it'll call that one instead - you can use this to get a function to return to a different function. 12:24:24 I'd design a real language, but I have no idea where to start. 12:24:39 And I have no idea what to look up, either, because all you get is shit. 12:36:10 rdococ: so you are not going to make this a full language? 12:36:22 or write an interpreter? 12:36:44 I have trouble designing interpreters anything more complicated than brainfuck derivatives. 12:36:50 My code is seriously sloppy. 12:36:53 hm 12:37:05 I don't understand how to create a parser. 12:37:31 ah, I took a course at university about parsers and lexers 12:38:09 Do you think my "callee gets explicit continuation" idea is a good one? 12:39:19 But I recommend using a parser combinator library rather than than lexers and parser generator like flex/yacc/bison 12:39:37 I personally find libraries like parsec (haskell) or pyparsing (python) much easier to use 12:39:57 rdococ: this is #esoteric, it doesn't matter if it is good, as long as it is interesting 12:40:19 and I haven't seen a language doing that before (though I have been out of the loop for a few years due to real life) 12:49:14 -!- erkin has joined. 12:57:01 true 12:57:17 is there a Lua equivalent? 13:00:01 -!- ais523 has quit (Ping timeout: 248 seconds). 13:04:16 `tell imode now do it for infinite trees :P 13:04:18 I think you mean "@tell imode now do it for infinite trees :P" instead? 13:04:22 @tell imode now do it for infinite trees :P 13:04:22 Consider it noted. 13:09:11 -!- boily has joined. 13:13:31 hi boily 13:15:42 hi 13:18:50 helloily 13:19:43 -!- kuluma|2 has quit (Ping timeout: 248 seconds). 13:20:47 rdochelloc! 13:20:49 zsellori! 13:20:54 QUINTHELLOPIA! 13:21:27 why you up on saturday morning 13:22:58 coffee, shower, bus, metro, girlfriend ^^ 13:23:33 (I'm at the coffee step.) 13:23:53 (good coffee. very powerful. much waking.) 13:24:27 enjoying your morning? 13:25:56 i dont have coffee. im about to start the shower step 13:26:14 at a campground in hollywood, sc 13:27:38 being up at 5:30am at a campground is the best. 13:27:40 sc? 13:39:39 -!- LKoen has joined. 13:57:48 -!- kuluma|2 has joined. 14:00:39 -!- doesthiswork has joined. 14:04:48 -!- doesthiswork has quit (Ping timeout: 240 seconds). 14:13:14 -!- jaboja has joined. 14:17:59 -!- boily has quit (Quit: EXPENSIVE CHICKEN). 14:26:39 -!- ATMunn has joined. 14:48:40 -!- erkin has quit (Quit: Ouch! Got SIGABRT, dying...). 14:48:47 -!- jaboja has quit (Ping timeout: 248 seconds). 15:06:32 -!- `^_^v has joined. 15:11:46 -!- jaboja has joined. 15:28:31 -!- PinealGlandOptic has quit (Quit: leaving). 15:30:04 -!- jaboja has quit (Ping timeout: 255 seconds). 15:30:31 -!- Phantom_Hoover has quit (Ping timeout: 255 seconds). 15:32:24 -!- `^_^v has quit (Quit: Leaving). 15:32:26 -!- jaboja has joined. 15:32:41 -!- `^_^v has joined. 15:33:26 -!- LKoen has quit (Remote host closed the connection). 15:33:59 -!- somebody has joined. 15:34:09 -!- somebody has changed nick to ASCII-only. 15:41:09 hi 15:44:16 *begins lurking to wait for ais523* 15:48:02 hm 15:50:08 need his help for https://esolangs.org/wiki/Incident 15:51:38 can't figure out how to have a capital W on the hello world lol 15:58:40 can probably use the string generator, but need his help golfing it too 15:59:23 -!- [ATMunn] has joined. 15:59:39 -!- ASCII-only has quit (Quit: Page closed). 16:00:13 -!- jaboja has quit (Ping timeout: 255 seconds). 16:02:05 -!- ATMunn has quit (Ping timeout: 240 seconds). 16:16:58 -!- doesthiswork has joined. 16:21:30 -!- `^_^v has quit (Quit: This computer has gone to sleep). 16:23:51 -!- [ATMunn] has changed nick to ATMunn. 16:26:29 http://sprunge.us/VeVA <-- compiling Brainfuck to YABC 16:27:55 * int-e should add it to the wiki but is in no mood to fight with wiki syntax right now. 16:28:20 I guess I could annoy oerjan and put it in a single
 block :P
16:31:07  (woah there went the afternoon.)
16:41:29 -!- LKoen has joined.
16:48:49 -!- `^_^v has joined.
16:52:18  moo
16:54:27  . o O ( note to self, what's an unsigned natural number, wouldn't that suggest that there are signed ones as well? )
16:54:59  unsigned complex numbers
16:56:17  int-e: Concept: implicit CPS, which is made explicit to the callee. the callee receives a continuation as the final argument, and must call it to return - but the caller wouldn't pass it explicitly.
16:57:41  so basically, you'll have call/cc everywhere
16:57:52  yes
16:58:17  but if the callee doesn't call the continuation, execution halts
16:58:24  so more goto/cc
16:58:43  hmm, where's the fun in that
16:59:45  (the fun starts when you have several continutations to choose from. oh and of course when you use the same continuation more than once)
17:00:04  heh
17:00:18  and by "fun" I mean the kind that usually requires mind-altering drugs.
17:00:49  you can force other functions to return to other continuations from further back in the call stack
17:02:14  so, say you have add(x, y, return) that calls return with x+y. then you could have add5(x, return) { add(x, 5, return); } rather than return(add(x, 5));
17:03:53  there could also be multiple-continuation syntax like you said - e.g. if(condition) { cont1 } else { cont2 } cont3
17:05:04 -!- Melvar` has joined.
17:05:57 -!- idris-bot has quit (Ping timeout: 240 seconds).
17:07:52 -!- Melvar has quit (Ping timeout: 260 seconds).
17:14:46 -!- `^_^v has quit (Quit: This computer has gone to sleep).
17:16:54 -!- imode has joined.
17:22:13  imodee!!
17:22:18  imodium
17:22:32 -!- wob_jonas has joined.
17:22:50  suuup.
17:23:03  suuuuuuuuuuuup.
17:23:04  soup.
17:23:13  the sky is up
17:23:56  so I just found out that there's another of these big image editing libraries, called G'MIC, at http://gmic.eu/ , which is sort of like ImageMagick in that it goes for scriptability, but even more so, and also has GUI plugins for Gimp and Krita
17:24:02  definitely worth to know about
17:24:05  zzo38: ^
17:28:05  Who needs stacks and heaps and call queues when you have the DATA SOUP?! :P
17:29:38  I need trees, because they're more general
17:32:32  but soups can be reactive
17:32:36  I have seen G'MIC
17:33:38  good. I'd never heard of it until a few days ago for some reason
17:44:52 -!- kuluma|2 has quit (Quit: KVIrc 4.9.2 Aria http://www.kvirc.net/).
17:53:07  Maybe I should add a Halt CLUT program inyo my Farbfeld Utilities (actually, two such programs; one makes the identity and one applies it)
17:58:07  um, what's a Halt CLUT?
17:59:38  CLUT = 'color lookup table', but no clue about the "halt".
18:00:38  s/Halt CLUT/Hald CLUT/
18:00:49  http://www.imagemagick.org/Usage/color_mods/#hald-clut
18:01:07  just a bit too slow :P
18:01:26  ah
18:14:09 -!- LKoen has quit (Quit: “It’s only logical. First you learn to talk, then you learn to think. Too bad it’s not the other way round.”).
18:27:18  `? hereafter
18:27:19  hereafter? ¯\(°​_o)/¯
18:27:20  `? hereunder
18:27:21  hereunder? ¯\(°​_o)/¯
18:27:22  `? thereof
18:27:23  thereof? ¯\(°​_o)/¯
18:27:23  `? set forth
18:27:24  set forth? ¯\(°​_o)/¯
18:27:43  `? hereinafter
18:27:44  hereinafter? ¯\(°​_o)/¯
18:31:30  Now I made the program, ff-apclut ff-idclut
18:43:29  `smlist 456
18:43:30  smlist 456: shachaf monqy elliott mnoqy Cale
19:25:42 -!- moony has joined.
20:24:24  `? moo
20:24:25  Moo is the sound made by a cow as it freezes.
20:24:37  1? mud
20:24:39  `? mud
20:24:40  mud? ¯\(°​_o)/¯
20:24:58  `? mmo
20:24:59  mmo? ¯\(°​_o)/¯
20:43:08  `? mud
20:43:09  mud? ¯\(°​_o)/¯
20:43:21  `? mad
20:43:22  This wisdom entry was censored for being too accurate.
20:44:08  does anybody has any recommendations for a book about game design?
20:50:42 -!- HackEgo has quit (Ping timeout: 260 seconds).
20:52:47  is there a particular kind of game you're interested in?
20:54:49 -!- idris-bot has joined.
20:54:59  not in a specific way. i like games with a high replay factor a lot
20:55:09  big fan of rogue likes n stuff
20:55:47 -!- Melvar` has changed nick to Melvar.
20:55:57  myname: is your target board/card games only, or video games only? games with mostly well-defined rules, or games requiring an imaginative game master who comes up with scenarios?
20:56:22  primarily video games
20:59:33 -!- `^_^v has joined.
21:01:30 -!- `^_^v has quit (Client Quit).
21:01:40  did the wiki go down again?
21:02:08  `ping
21:02:14  looks like it
21:02:16  It was up an hour ago
21:02:21  ik
21:04:13  hopefully it's just a temporary problem. fizzie?
21:04:31  rdococ: seems like it might be working now.
21:04:54  `ping
21:10:14  it's down
21:18:07  idk what to do
21:22:04 -!- imode has quit (Ping timeout: 246 seconds).
21:23:47 -!- moony has quit (Remote host closed the connection).
21:24:13  I was expecting someone else to talk
21:24:14 -!- moony has joined.
21:28:28  wiki is up.
21:28:48  `is-wiki-up
21:30:19  can I just delete every crappy shitty esolang I have?
21:30:52  which ones?
21:31:14  all of them excluding QWOP, HI9+, Rule and Mindscrew
21:32:26  rdococ: http://magiccards.info/mi/en/48.html
21:33:58  exactly. esplangs are like spells so I want to uncast my shitty ones.
21:34:36  rdococ: the esolangs will still exist no matter what. that's why it's dangerous to even think of brainfuck-alikes.
21:35:06  it's weird how my brainfuck-alike is my best esolang yet, then
21:35:36  you can probably disown esolangs though
21:35:59  I want to travel back in time and kill my past self before he even thinks of making shitty langs
21:36:23  or "disavow" them, which sounds much fancier
21:37:18 -!- sleffy has joined.
21:37:26  wob_jonas: what do you think of a lang where every call is a call/cc? every function gets passed its continuation to it, and it has to call that continuation to return
21:37:53  even better is you can explicitly call it with a different continuation and it'll return there instead
21:38:08  I think 'Assignless' is a nice language.
21:38:20  meh, maybe
21:38:24  I never fleshed it out enough
21:38:54  I guess I could stick some of my better ideas together, but idk how assignlessness plus first-class continuations would work...well, actually it might work
21:42:20  I think assignless and first-class continuations fit well together.
21:43:23 -!- `^_^v has joined.
21:45:48  mayb
21:45:49  e
21:53:30  https://gist.github.com/zserik/280f3126e2141d7bad223c3c1e9a1b9d
21:55:49  hm...
22:00:31  maybe
22:01:24  @google dykyabc
22:01:26  https://disneykid08.wordpress.com/2008/12/09/dykyabc/
22:04:24  maybe (parameter1, parameter2, k) and have "self" as some hidden function-local variable?
22:05:45 -!- augur has joined.
22:05:50  Did you know that there's a programming language called 'Self'?
22:08:16  int-e: wasn't Self a non-eso object-oriented programming language?
22:08:43  "At one point a version of Smalltalk was implemented in Self."
22:08:46  "Self was a dialect of Smalltalk"
22:08:53  what. the. actual. lol :P
22:09:27  wob_jonas: prototype based, if you care about the difference; and it was basically a research language, so kind of esoteric
22:09:47  ok
22:10:23  My question is: should 'self' (or 'this'; as an variable) be implicit, and the continuation an explicit? That seems a little bit inconsistent.
22:10:51  IIUC, the most significant influence was the Hotspot VM which borrowed techniques from Self's JIT compiler.
22:11:05  'self' and 'continuation' are different concepts. I think a function should be able to call itself without too much in the way.
22:11:43  I was thinking the syntax could be "function (x, y, z) k { ... }" (where x, y and z are parameters and k is the continuation), just as syntactic sugar
22:16:33  also, on the explicit/implicit end-of-function return, I think it should be explicitly required - otherwise the program will have nowhere to flow to and will hatl.
22:16:35  halt*.
22:21:01  updated.
22:26:10 -!- `^_^v has quit (Quit: This computer has gone to sleep).
22:48:29 -!- ais523 has joined.
22:55:54 -!- zseri has quit (Ping timeout: 260 seconds).
23:08:34 -!- jaboja has joined.
23:25:30 -!- AnotherTest has quit (Ping timeout: 240 seconds).
23:28:36 -!- imode has joined.
23:36:51 -!- ais523 has quit (Remote host closed the connection).
23:38:01 -!- ais523 has joined.

2017-08-20:

00:19:18 -!- oerjan has joined.
00:23:47 -!- boily has joined.
00:31:26  hily
00:32:27  diais523 duit
00:41:21  hellørjan!
00:41:34  hellorcah!
00:41:35  hichaf
00:41:45  helloochaf.
00:45:35  こんぶわりは
00:50:36  「ぶわり」って?変。
00:51:08  「ブワリ」は自分です
00:51:56  You pronounce your name similar to "buwari" rather than "boirii"?
00:52:02  変。
00:54:25  my name's pronounced /bwali/ hth
00:55:00  it's not 変, just French :D
00:55:21  OIC
00:55:38  Though, being French means it's weird ipso facto. :P
01:05:29  pikhq: you haven't seen irish clearly
01:09:20 -!- augur has quit (Remote host closed the connection).
01:09:57 -!- augur has joined.
01:11:15  Bah. You want weird, try transcribing "六百" as "rot̄uhi̊ȳaku".
01:11:17 -!- augur has quit (Remote host closed the connection).
01:11:55 -!- augur has joined.
01:15:29  dheartháireacha
01:15:57  let me guess. that one's pronounced throatwarbler-mangrove?
01:16:01  exactly!
01:16:03  it means brothers
01:16:57  this is post spelling reform even
01:17:42  that's egregiously outrageous spelling.
01:18:22  it's pronounced something like yerarech
01:18:32  (ch as in german)
01:18:56  ach-laut or ich-laut?
01:20:30  https://en.wiktionary.org/wiki/dearth%C3%A1ireacha
01:21:18  ach in this case
01:22:29  lol
01:22:34  how in fungot's name can you say [dʲɾʲ]???
01:22:34  boily: t-rex, i have big news the other! you can see, i've thought of the best story! oh goodness, i must have put that in your pipe and smoke it?
01:22:49  wob_jellonas.
01:23:04  "dheratháireacha"
01:24:00  boily: like [dɾ] but palatalized?
01:24:35  Is "i̊" even a thing? what does that accent do?
01:27:13  "rot̄uhi̊ȳaku" seriously
01:30:55  boily: as in, ʲ is a modification of the previous sound, not a separate one.  it means that the middle of the tongue is lifted towards the palate, like in an english "y" sound.
01:34:08  yes, but it's the [dɾ] sequence that baffles me :/
01:34:11  but without necessarily  moving the main articulation of the letter
01:34:16  oh.
01:35:21  well in this case i guess it's your r's that are the problem.
01:35:38  my rs are perfectly fine :P
01:35:54  (okay, very French rs.)
01:36:16  norwegian has plenty of [dɾ]s, anyway.
01:37:45  [dʁ] is saner.
01:38:50  that would imply people from Bergen are sane, an absurdity!
01:44:59  (don't tell wob_jonas about today's wikipedia main page picture. oh woops.)
01:45:33  Lundomys molitor?
01:45:54  that's the article, not the picture hth
01:46:32  please scroll down a bit twh
01:46:49  Thukkachi Abatsahayesvar temple???
01:46:52 * boily is confuzzled?
01:47:00  oh!
01:47:05  more scrolling.
01:47:40  where do you see that *reloads*
01:48:06  that section hadn't updated when i loaded last
02:00:10  `5 w
02:01:30 * boily lightly mapoles fizzie
02:03:29  hm wiki is up
02:06:09 -!- sleffy has quit (Ping timeout: 248 seconds).
02:20:37  My monitoring says it was down for an hour.
02:20:57  Probably was enough to make HackEgo go down as well, though not sure why it didn't come back up automagically.
02:21:50  There's the socat process, but it's using 99.9% of CPU.
02:21:54  I think it's just confused.
02:22:52  Let's just kill that one, I think the starter script has a loop around the socat.
02:23:29 -!- HackEgo has joined.
02:23:32  See.
02:23:34  `botsnack
02:23:35  ​>:-D
02:27:12  Well that was intresting. I just had half a dozen experienced linux users try and beat umlbox to the ground.
02:29:35  moony: I don't think anyone's broken umlbox in this channel
02:29:49  HackEgo itself has been successfully broken a couple of times, but via HackEgo-specific exploits
02:33:29  ais523, same thing happened to my bot. Altho no breaks were serious, all were just mistakes in the code that caused it to crash :P
02:34:05  people managed to break HackEgo?
02:34:16  `5 w
02:34:20  1/2:elliott//elliott wrote this learn DB, and wrote or improved many of the other commands in this bot. He probably has done other things? He is also tire. And a lystrosaur. \ all the single objects//All the single objects / went to form a class / but then they got a unit test / which none of them did pass. \ mothball//Mothballs are the main ingred
02:34:22  ǹ
02:34:24  `n
02:34:25  2/2:ient of a traditional soup of Eastern European origin. \ overflow//Overflow is a phenomenon that occurs when too much water pours into the inner tanks of a hydraulic computer. \ nød//Nød is French for vertex.
02:34:36  how long has hackego been around anyways?
02:34:55  quite a while now
02:35:01  it was originally meant to be an egobot replacement
02:35:05  but people didn't really use it for esolangs
02:35:14  any estimate in years for hackego? :P
02:35:15  I think about 8 years
02:35:35  which is a sign of the decline of this channel :-(
02:36:13  because I started college in 2009 and also joined irc, and I vaguely remember an egobot
02:37:08  egobot was basically our version of TIO, only it probably came first
02:37:20  TIO?
02:37:21  `! underload (test)S
02:37:22  test
02:37:26  moony: http://tio.run
02:37:31  wow, its been so many years since I dropped out
02:37:37  2009-06-20 for HackEgo, as far as my logs can tell.
02:37:42  it was originally just esolangs, but it's added a bunch of practical languages since
02:38:11  2005-10-25 for EgoBot.
02:38:32  (which is the other way round from what most people might expect)
02:38:43  lol
02:38:50  knowing this channel, thats perfectly normal
02:39:16  well it doesn't seem to be associated with this channel at all
02:39:29  most of its development was driven by PPCG on Stack Exchange
02:41:13  I helped out a bit, like getting INTERCAL running there
02:42:08  ais523, you know how the version control system was set up? Im considering making something similar for my bot
02:42:23  which version control system? hackego's?
02:42:29  yea hackego's
02:42:34  that's one of the most fragile parts, and doesn't really work
02:42:38  so I wouldn't recommend copying it
02:42:41  mk
02:42:58  what's wrong with it, some bugs have been fixed
02:43:17  oerjan: doesn't it give really weird results if you run a nondeterministic command?
02:43:25  how about the bots that store every persistent data version controlled, like buubot or wikiplia?
02:43:37  well then it runs it twice
02:43:53  discarding the first run.
02:44:19  right
02:44:23  that's not what most people would expect
02:44:48  and you can certainly fool it into producing even more counterintuitive results
02:45:00  there's also that time when I permanently broke `revert…
02:45:13  (technically, it still works to do the reverting, just produces an error message every time)
02:45:13  ais523: but it's hard to do anything better. jevalbot is really stupid and just loses the result of whichever computation finishes first when you run two commands at the same time
02:45:47  ais523: that's one of the bugs that are fixed hth
02:45:54  hmm, would be fun if you could run two conflicting commands at the same time
02:45:58  and end up with conflict markers in the file
02:46:07  probably more harmful than useful, but fun
02:46:13  ais523: that could break things a lot
02:46:37  definitely
02:48:19  I've got an arguably semi-reasonable thing for a half-completed bot, but it involves doing the filename-to-file mapping on your own.
02:48:31  I don't recall what buubot does. It allows multiple commands to run at the same time, and I think they just access the same (version controlled) persistent database, and only individual stores or loads are atomic and a command can do any number of those.
02:48:35  . o O ( reason tells me "are fixed" is correct but the rest of my brain isn't convinced. )
02:48:40  There's no locking primitives.
02:50:43  In theory you could make a bot that exposes you ways to lock parts or do atomic ops on the database
02:52:10  in a buubot/wikiplia-like system
02:52:21  and you don't have to version control everything for that
02:52:41  oerjan: hmm… "the bugs are fixed", "one of the bugs is fixed", so what happens if you add "that"?
02:52:59  I guess logically you can only parenthesize it as the first case
02:53:18  the point is, the locking or atomic would be explicit in programs, and if you don't use them and something splinches, you get to keep the pieces
02:53:19  one of ((the bugs) that are fixed)
03:00:28 -!- ATMunn has quit (Quit: See ya! o/).
03:06:58 -!- boily has quit (Quit: PROGRESSIVE CHICKEN).
03:13:02 -!- Antoxyde has quit (Quit: Leaving).
03:16:01 -!- ais523 has quit (Ping timeout: 248 seconds).
03:21:54 -!- wob_jonas has quit (Quit: http://www.kiwiirc.com/ - A hand crafted IRC client).
03:22:22 -!- wob_jonas has joined.
03:24:27  [wiki] [[Width]] N https://esolangs.org/w/index.php?oldid=52879 * Stestoltz * (+427) Created page with "'''Width''' is an esoteric stack-based language created by [[User:Stestoltz|Stephen S]]. All characters except letters are ignored. For more information, see the Github link...."
03:39:18 -!- wob_jonas has quit (Quit: http://www.kiwiirc.com/ - A hand crafted IRC client).
04:00:49 -!- moony has quit (Ping timeout: 248 seconds).
05:22:25 -!- jaboja has quit (Remote host closed the connection).
05:45:42  There is the solar eclipse soon. One way to calculate when and where is by use of Swiss Ephemeris. Have you looked at or used Swiss Ephemeris at all?
05:46:04  Are you asking me?
05:46:06  Yes
05:46:11  No, I haven't.
05:46:18  Did you see the eclipse?
05:46:28  No, it hasn't happened yet.
05:46:37  Yes I know that
05:46:55  Are you going to Oregon to see the eclipse properly?
05:47:31  Swiss Ephemeris is reporting happening on 2017-08-21T18:13:14.199Z, at 36 N 58' 15", 87 W 39' 23". If it is wrong then I might have done something wrong
05:47:57  I used https://eclipsemega.movie/simulator to check.
05:48:23  By the use of the interface to use Swiss Ephemeris with JavaScript, now you can use with the Node.js REPL to figure it out, such as by entering: swe.fromJulian(swe.occult(swe.planet.Sun).time)
05:49:34  shachaf: What did they tell you?
05:49:56  But, no I am not going to Oregon to see the eclipse properly; I will remain here, and not see it properly
05:50:07 -!- oerjan has quit (Quit: Nite).
05:50:34  They told me 'You may seek it with thimbles— and seek it with care; You may hunt it with forks and hope; You may threaten its life with a railway-share; You may charm it with smiles and soap—'
05:51:42  I do not see how that helps, and how you can use thimbles to seek a solar eclipse or to charm it with soap?
05:57:34  Not all of the functions of Swiss Ephemeris have been put in yet, although I have also put in some functions that are not in Swiss Ephemeris, such as converting between JavaScript Date objects and Julian day numbers, numeric formatting (for angles, such as ecliptic or equatorial coordinates, geographic coordinates, azimuth, astrological signs, etc), a few new house systems that I made up, and map projections.
05:59:18  (I also wrote my own implementation of converting to horizontal coordinates, since I found that the one included in Swiss Ephemeris cannot use hour angle as input.)
06:04:24  (There is also no reverse map projections yet, so if you want a interactive map that you can click on, it doesn't implement yet.)
06:43:14  I also want to know how I could add artificial satellite positions and terminator lines
06:50:33 -!- dingbat has quit (Quit: Connection closed for inactivity).
07:04:44  [wiki] [[Main Page]]  https://esolangs.org/w/index.php?diff=52880&oldid=43201 * LyricLy * (+234) 
07:09:07 -!- hppavilion[1] has joined.
07:17:53  hppavilion[1] !
07:25:27 -!- zseri has joined.
07:27:04 -!- augur has quit (Remote host closed the connection).
07:27:41 -!- augur has joined.
07:31:54 -!- augur has quit (Ping timeout: 240 seconds).
07:36:43 -!- doesthiswork has quit (Quit: Leaving.).
07:51:49  zseri! yay!
07:59:17 -!- sleffy has joined.
08:19:29 -!- augur has joined.
08:46:49 -!- zseri has quit (Ping timeout: 260 seconds).
09:06:21  oh, oerjan is totally out of phase again
09:36:49 -!- imode has quit (Ping timeout: 255 seconds).
09:39:07 -!- zseri has joined.
09:39:26  hi
09:42:24  rdococ: why do you have a subpage Esolangs (User:Rdococ/Esolangs) on your profile which is less complete than the Esolangs list on the main profile page User:Rdococ
09:56:37 -!- hppavilion[1] has quit (Ping timeout: 255 seconds).
10:01:45 -!- LKoen has joined.
10:02:04 -!- hppavilion[1] has joined.
10:08:34 -!- MrBusiness has quit (Ping timeout: 246 seconds).
10:09:13 -!- AnotherTest has joined.
10:10:57 -!- sleffy has quit (Ping timeout: 248 seconds).
10:15:56  zseri: idk
10:15:57  hppavilion[1], hi
10:16:05  hi
10:20:24  [wiki] [[Main Page]]  https://esolangs.org/w/index.php?diff=52881&oldid=52880 * LyricLy * (+4) 
10:23:07 -!- augur has quit (Remote host closed the connection).
10:35:17  ...
10:35:55  zseri: what about a low level language where the main array type is a linked list?
10:52:20  like brainfuck, but you can drop the current cell or insert one (e.g. after the current cell)
10:52:27  nice idea
10:57:17  maybe
10:57:48  ooh! what if the cells started as all ones, and all you could do was insert a 0 cell after the current cell?
11:01:43  brainfuck minus - (and non-wrapping bits) seems to be TC; what if you had to insert the 1 cells?
11:04:01 -!- erkin has joined.
11:06:56 -!- augur has joined.
11:09:58 -!- augur has quit (Remote host closed the connection).
11:10:10 -!- augur has joined.
11:22:46  I was thinking of combining the continuation thing with http://esolangs.org/wiki/Upsilon
11:43:51  [wiki] [[YABC]]  https://esolangs.org/w/index.php?diff=52882&oldid=37129 * Int-e * (+3744) from Brainfuck to YABC
11:59:53  https://gist.github.com/zserik/280f3126e2141d7bad223c3c1e9a1b9d (updated again)
12:00:59  lets try creating a mash-up of Assignless, first-class continuations (implicit created and passed, usage explicit) and Upsilon.
12:03:44 -!- Antoxyde has joined.
12:04:37 -!- augur has quit (Remote host closed the connection).
12:41:57 -!- TieSoul has joined.
12:47:02  https://xkcd.com/660/
12:50:08  o_o
12:51:14  well, I'm working on an esolangs article for assignless + the continuation thing
12:51:28  the Hitchhiker universe has ships driven by bad news
12:51:46  oh, so the more esolangs I create, the more fuel it has?
12:51:57  (they're highly unpopular though)
12:52:15  int-e: "Bad news: ship ran out of fuel."
12:53:57  more like "Bad news: the ship is running low on fuel."
12:54:18  which gives it more fuel
12:54:44  Bad news: The ship has too much fuel.
12:54:49  O_O
12:55:06  but then at some point it stops being news
12:55:11  and starts just being *bad*
12:55:11  ah.
12:55:18  then fuel will decrease again.
12:55:44  does good news decrease it then?
12:55:50  hmm
12:56:20  you might be able to use it to create good news to make the world a better place, using the "Bad news: machine is running out of fuel." as fuel
12:56:24  you know I could see the ship not having "fuel" per se, but having to be driven by a constant stream of bad news
12:56:28  in other words, instant utopia
12:56:31  worse news = more thrust?
12:56:37  of course
12:56:55  they're actually only mentioned in passing
12:57:29  I should read Hitchhiker
12:57:40  kinda surprised I haven't done so yet honestly
12:58:26  "Nothing travels faster than the speed of light with the possible exception of bad news, which obeys its own special laws. The Hingefreel people of Arkintoofle Minor did try to build spaceships that were powered by bad news but they didn't work particularly well and were so extremely unwelcome whenever they arrived anywhere that there wasn't really any point in being there."
12:59:42  bad news travels faster than the speed of light?
12:59:56  that would mean if you frame something as bad news
12:59:59  time traveling information
13:00:14  powerful
13:00:41  TieSoul: did you look at the xkcd link? The way I see it it's really based on that concept.
13:01:23  Bad news: information has to be passed at faster than light speeds again
13:01:38  but does that qualify as bad?
13:01:48  "Bad news: the magical yay machine is working again"
13:01:50  what is the objective qualification of bad news
13:02:00  I bet it's subjective to your reference frame
13:02:01 -!- MrBusiness has joined.
13:04:41 -!- boily has joined.
13:09:50  hi bioly
13:14:55  Helloily!
13:16:04  uhh
13:16:07  good moilyng?
13:16:26  hmm, boilogy
13:16:30  `? boily
13:16:32  ​“Only sane adverb” boily is monetizing a brotherhood scheme with the Guardian of Lachine. He is also a NaniDispenser, a Trigotillectomic Groan Man Eating Chicken, a METARologist, seriously lacking in the f-word department, a thwack doctor, a Quintopial antipodist, and a renowned Capitalist who helps keep the world boring.
13:16:50  makes sense
13:19:15  `? wisdom
13:19:16  wisdom is always factually accurate, except for this entry, and, uh, that other one? It started with, like, an ø?
13:19:42  . o O ( wisdom is often born out of boredom
13:19:44  )
13:20:03  zsellori, rdochelloc, TieSelloul, int-ello, HellockEgo!
13:20:12  `? ø
13:20:13  ​ø is not going anywhere.
13:20:35  well that settles that
13:21:11  . o O ( Heh, I forgot that I talked about boredom on https://esolangs.org/wiki/User:Int-e )
13:23:08  `? wisdome
13:23:10  [wiki] [[User:TieSoul]]  https://esolangs.org/w/index.php?diff=52883&oldid=40229 * TieSoul * (-426) Replaced content with "I made [[Befunk]] I guess"
13:23:10  The Wisdome is the place where all of HackBot's wisdom is stored and forced to fight to the death for the freedom of being printed out when you type `wisdom. Strictly speaking, it should be called the "Wissphere".
13:23:14  that reminds me
13:23:17  now it's better
13:25:21  `wisdom
13:25:22 -!- ais523 has joined.
13:25:22  eol//EOL stands for End Of Lawn. It's often found past the wabe. oerjan requests your presence there immediately.
13:25:37  twas brillig
13:27:37  `learn The Boredome is a dangerous place swarming with woodpeckers, dentists, and bookworms.
13:27:40  Learned 'boredome': The Boredome is a dangerous place swarming with woodpeckers, dentists, and bookworms.
13:28:12  `? dentist
13:28:13  dentist? ¯\(°​_o)/¯
13:28:26  a master bore
13:29:00  "Dentists are professional workers whose main line of work is forming dents on various surfaces."
13:29:37  yes
13:29:55  `learn Dentist Dentists are professional workers whose main line of work is creating dents on various surfaces.
13:29:57  Learned 'dentist': Dentist Dentists are professional workers whose main line of work is creating dents on various surfaces.
13:30:05  `le//rn Dentist//Dentists are professional workers whose main line of work is creating dents on various surfaces.
13:30:07  Relearned 'dentist': Dentists are professional workers whose main line of work is creating dents on various surfaces.
13:30:25  Dentist Dentists
13:31:00  that's dentists who are discriminatory to dents
13:31:07  "Bookworms are a species of worm known for thriving in books, feeding from the cellulose in the paper."
13:31:43  `le//rn bookworm//Bookworms are a species of worm known for thriving in books. They are known to be unusually intelligent.
13:31:46  Learned 'bookworm': Bookworms are a species of worm known for thriving in books. They are known to be unusually intelligent.
13:32:03  "Woodpeckers are a class of wooden sculptures, depicting a 'peck' or kiss."
13:32:19  I'll stop now, before someone calls me out for adding bad wisdom entries.
13:36:26  rdococ: FWIW, there's auto-pluralization handling -- you can "`learn Dentists are such and such." and it will learn 'dentist'.
13:36:50  fizzie: I'm aware of that but I am more comfortable with //.
13:37:00  but what if a word ends in s
13:37:14  TieSoul: Then you need to use the alternatives.
13:37:19  right
13:37:27  It also doesn't work for nonstandard plurals.
13:37:38  makes sense
13:38:08  nonstandard plurals would require more or less encoding a partial dictionary
13:38:15  which is too much effort for a slight convenience
13:38:54 -!- ais523 has quit (Ping timeout: 240 seconds).
13:39:56  In other news, the Telegraph magazine has made me a lot less excited about 4G and 5G, since apparently their speeds top up at 1 and 10 megabits, respectively: https://zem.fi/tmp/telegraph.png
13:40:48  sure makes it look good with that bar graph though
13:41:27  uh, that can't be right
13:42:05  also yeah I'm pretty sure 4G is faster than 1Mb/s
13:43:13  I've gotten >1Mbit/s over 3G (well, one of the standards before LTE using 3G's infrastructure) at least and >20 over LTE
13:43:38  yeah
13:43:40  I guess they were just ulling arbitrary numbers
13:43:45  pulling*
13:43:52  FireFly: Yeah, the 384 kbit/s is from the original UMTS spec, they've dropped the HSPA steps.
13:44:11  before 4G, I seemed to get better results with what my phone OS called "H" connection than with 3G
13:44:12  And 300 Mbit/s would be the conventional figure for LTE, though I think they've gotten their "1000" from gigabit LTE news.
13:44:45  which is off by three orders of magnitude then
13:44:47  nice
13:45:17  I'm guessing they just switched from kbit/s to Mbit/s halfway through their chart.
13:45:28  TieSoul: that'd be HSPA or HSPA+ then
13:45:52  right
13:45:53  or "3.5G" and "3.7G" according to Maemo 5 IIRC
13:46:05  oh cool
13:46:29  Yeah, it's a bit convenient of them to squeeze everything in a genertions scale
13:46:39  though using fractional "G"s is unwieldy
13:46:56  FireFly: I think HSPA+ is quite often referred to as "3.75G", but that doesn't fit in a status bar as well.
13:47:08  makes sense
13:47:10  that should get rounded to 3.8G then
13:47:54  though I suppose that'd be slightly misleading
13:48:57  I mean the fraction is pretty arbitrary
13:49:05  that's true
13:49:12  I think Maemo used 2.5G for EDGE as well.
13:49:14  but it's easier to tell that 3.5 > 3 than "H" > "3G"
13:49:22  yeah
13:49:26  Yeah, I believe it did
13:49:46  This Android phone does G, E, 3G, H, 4G, I think.
13:50:05  mine uses 3G, H, H+, and 4G. I don't think I've dipped below that.
13:50:21  on my current phone that is
13:50:35  I only recall eeing 2G, 3G and 4G on Sailfish I think
13:51:00  so I guess it uses 2G for both GSM and EDGE etc
13:51:13  makes sense I guess
13:51:29  it's easier to see the easy to compare numbers than to memorize the abbreviations
13:57:30  I wonder how 5G development is coming along
13:57:36  I saw a 5G test rig a couple years ago
13:59:06  not sure exactly what technology, but whatever they were working on at uni two years ago I guess
13:59:35  The article that bogus graph was from is about UK 5G spectrum auctions, and how a few lawsuits are going to slow them down.
13:59:38  http://www.telegraph.co.uk/business/2017/08/19/bts-mobile-unit-wades-5g-battle-against-three/
14:00:12  huh
14:00:33 -!- doesthiswork has joined.
14:01:26  lol, according to wikipedia, "LTE Advanced Pro (LTE-A Pro, also known as 4.5G, 4.5G Pro, 4.9G, Pre-5G, 5G Project, and so on)"
14:01:39  seems they're getting progressively more optimistic about LTE-A Pro
14:01:52  heh
14:02:04  I can't wait until 7G
14:04:07  TieSoul: for the longest time LTE was also considered "not quite 4G" until it became defacto 4G
14:04:23  hey, apparently my country is ranked 5th in LTE coverage
14:04:32  Omega-G, anyone?
14:04:32  the numbered generations are as much for marketing as the fractional in-between generations are really
14:04:43  yeah I figured fire
14:05:04  Hm
14:05:20  LTE coverage is pretty good here, but I dunno how well it ranks on an area-of-country-covered basis
14:05:28  since northern sweden is.. pretty rural
14:05:34  more like epsilon-zero G, rdococ
14:05:44  epsilon-epsilon-one-G
14:05:52  But I had LTE coverage whilst hiking last week in the mountains, so that's cool :P
14:06:01  what's the name for epsilon-epsilon-epsilon-...?
14:06:02  Scotland was very low in G's.
14:06:20 -!- lord_EarlGray1 has joined.
14:07:13  4G - Normalhastighet 10 - 40 Mbit/s
14:07:13  4G+ - Normalhastighet 20 - 60 Mbit/s
14:07:15  hm
14:07:24  I wonder if that'sa different technology or if both are just LTE
14:08:01  suspect they are both LTE
14:08:05  the speeds are close
14:25:13 -!- moony has joined.
14:30:10 -!- lord_EarlGray1 has left.
14:44:33 -!- ATMunn has joined.
14:48:15  Moony the moony moon!
14:49:38  moo
15:09:43  heh
15:14:29  heh
15:19:43  neh
15:21:17  nuh?
15:22:07  hn
15:22:53  asdfbable
15:23:06  honk
15:26:12 -!- jaboja has joined.
15:52:12 -!- ais523 has joined.
15:52:44  hi ais523
15:55:29  hi zseri
15:57:13  hi
15:57:21  Feather sounds nice btw
15:59:01 -!- `^_^v has joined.
16:00:52  rdococ: what motivated you to say something like /that/ just after I joined? :-D
16:01:10  luckily, I've been growing more Feather-resistant over time, I'm starting to come to terms with it a bit more
16:01:42  they're really ticklish
16:02:12  hmm, I wonder if standard user turnover in #esoteric will eventually result in nobody knowing what Feather is except that it's a meme
16:03:36 -!- hppavilion[1] has quit (Remote host closed the connection).
16:04:01 -!- hppavilion[1] has joined.
16:05:05 -!- hppavilion[1] has quit (Remote host closed the connection).
16:06:00  heh
16:06:30  ais523: Feather clearly comes from a Bird :P
16:13:13  ais523: I've added a translation from Brainfuck to YABC
16:15:43  (which might be interesting in how it handles skipping of loops... that was my primary inspiration)
16:16:14  😎
16:16:43  `unidecode 😎
16:16:45  ​[U+1F60E SMILING FACE WITH SUNGLASSES]
16:20:50  hee
16:21:33  alercah: you should use the whole chicken for the best experience.
16:21:39  ais523: feather is future-proof.
16:22:01  boily: very much so
16:22:20  😎
16:22:26 -!- int-e has left ("HOLISITC CHICKEN").
16:22:26 -!- int-e has joined.
16:22:31  Good old Future.
16:22:33  😎
16:22:35  `unidecode 😎
16:22:36  ​[U+1F60E SMILING FACE WITH SUNGLASSES]
16:22:36  heh
16:22:56  int-e: how does that handle nested loops?
16:22:59 * rdococ really wishes he could stumble on an original idea for once.
16:23:10  ais523: by moving further to the left.
16:25:46  ais523: the pointer is somewhere in the 41 -37 ... 41 -37 part, pointing to a 41 if scanning to the left or to a -37 if scanning to the right; the further nested the loops, the further left the pointer will be in that part.
16:26:42  oh, I see, you're using the position of the data pointer to track the nesting level, not the position of the instruction pointer
16:26:47  yes.
16:26:49  which is how I'd expected it'd be done
16:27:18  which allows me to have a very uniform (if inefficient) trranslation.
16:27:53  😎
16:28:03  `unidecode 😎
16:28:04  ​[U+1F60E SMILING FACE WITH SUNGLASSES]
16:28:12  It will not get better over Time.
16:28:13  😎
16:28:26  `unidecode 😎
16:28:28  ​[U+1F60E SMILING FACE WITH SUNGLASSES]
16:28:31 * int-e shrugs
16:28:48  APic: I don't see the actual character and there are many smileyds
16:28:59  I should switch to privmsg, perhaps
16:29:16  rdococ: originality is an itch. you can't strike it, just scratch it. find what irks you. what are your wishes? what are your "man, it'd be so nice to have..."?
16:31:55  int-e: come to think of it, there's probably a construction which uses the value of a tape element
16:32:24  just put the nesting level directly on the tape, and use it as a value to branch on to see if you've gon far enough yet
16:32:26  boily: I don't have much of an idea, to be honest. Sometimes, something looks like an appealing idea to me, and then it loses its subjective value over time.
16:33:39  I started writing a small Rust program to learn the language
16:33:55  and already ended up doing heavy amounts of type-level metaprogramming and had an idea for a new language feature and a new optimisation
16:35:51  😎
16:35:59  int-e: True.
16:36:11  I had the idea that functions could be manipulated by a program as a linked list of statements, with expressions that could be modified on the fly
16:36:20  Type-Safety ♥
16:36:28  so, for example, say we have a function f. f[1] is the first statement, f[2] second, etc.
16:36:28  `unidecode ♥
16:36:29  ​[U+2665 BLACK HEART SUIT]
16:36:35  Aaaah
16:36:43  Good old 4-Letter-Codes.  😎
16:37:04  say f[5] was an if conditional - then f[5].condition would be the condition, f[5].ifblock would be another list of statements, f[5].elseblock, and then f[6] after it.
16:37:39  ais523, explain what feather is
16:38:03  http://esolangs.org/wiki/Feather
16:38:08  moony: I can't; the wiki page may help
16:38:22  at a very rough approximation, it's an esolang I started to write, couldn't pin down the details
16:38:36  and then got really upset because not only did nobody else understand my esolang, I didn't understand it either
16:38:59  rdococ: explore the idea. build a working prototype. draft sketches on random pieces of paper. doodle. have a feel for it. where shall it lead?
16:39:11 * APic actually misread „moony“ as „money“, lol.
16:39:22  boily: a working prototype? I can't even do that.
16:39:23 * moony goes insane thinking about feather
16:39:28  but it's very maddening because looking at individual parts of it, it feels like it /should/ work, and yet I can't grasp the whole, and even when just focusing on individual parts, there's always complications which means you can't pin down exactly how they work
16:39:53  you know, if you'd let us look at individual parts, we could help
16:39:57  ais523, do it like i do it: implement and test each little bit at a time, with little/no order lol
16:40:10  then again, I don't want to go mad either :P
16:40:14  rdococ: I don't understand any of them either :-(
16:40:25  although I have worked out the correct order in which to approach them, I think
16:40:28  ais523, i volunteer my brain
16:40:36  rdococ: yes you can.
16:40:42  just so i can figure out what it is
16:40:42  moony: you can?
16:40:45  most of my Feather-related work has been on what must be the first step: to work out a language that it's theoretically possible to implement Feather in
16:41:00  O_o
16:41:08  . o O ( aka, Feather? )
16:41:10  other than Feather itself, that is
16:41:22  because you need to get started somehow
16:41:22  lol
16:41:33  moony talks, People listen.
16:41:41  Ah but how do you know it won't be precursors to Feather all the way down...
16:41:45  k
16:41:53  by the looks of the unfinished article, it does sound like a cool concept
16:41:58 -!- oerjan has joined.
16:42:03  once you have a working proto-Feather interpreter (i.e. one that implements Feather but doesn't fulfil all the provenance restrictions needed to be a Feather interpreter), you can then retroactively change it to have been written in Feather itself
16:42:10  oerjan: good morning to you
16:42:25  that's another of the steps where I think I know how it works but I don't have a working set of precise details
16:42:27  well first, we need to build a time machine and put a computer inside it with a link to the time machine
16:43:05  you know what, I'm going to borrow Feather's specification from the future, brb.
16:43:07  then we need to solve the halting problem so ais523's brain wont asplode
16:43:08  int-e: good afternoon
16:43:19  done we made feather
16:43:27  halting problem is easy to solve - use Banana Scheme
16:43:32  anyway, the language in which the proto-Feather interpreter is written needs the following properties: functional with minimal side effects (nothing beyond what you need to communicate with the user, and ideally not even that); a working call/cc; an eigenratio of 1, ideally for all idiomatic interpreters rather than just one of them; a syntax simple enough that self-interpreting is easy
16:43:44  eigenratio?
16:43:44  brb rewriting ais523 in banana scheme
16:43:51  oh, and ideally it wouldn't go into an infinite loop just because the program mentioned one
16:43:58  wait how do i write things in banana scheme
16:44:04  rdococ: imagine running a program through a large stack of self-interpreters
16:44:26  functional and call/cc is easy
16:44:31  ais523, minimal side effects? hmm. you may have to make a entire new language for that
16:44:40  not sure about the eigenratio, and the infinite loop thing - maybe not :P
16:44:40  the eigenratio is the amount of slowdown you get by adding another interpreter to the stack, expressed as a ratio between the execution times
16:44:57  ah. why don't you want it to speed up?
16:45:09  (in other words, eigenvalue < 1)
16:45:17  s/eigenvalue/eigenratio/
16:45:21  rdococ: it's clearly impossible to get an eigenratio < 1, because that means that the more self-interpreters you had in the stack, the faster it would get
16:45:33  meaning you could create an arbitrarily fast impl via stacking an arbitrary number of interps
16:45:51  and necessarily outpacing the "programming speed of light" for the computer you were running on
16:45:56 -!- `^_^v has quit (Quit: This computer has gone to sleep).
16:46:00  ais523, go make a fork of the rust compiler. i think (tm) it has a eignratio of 1
16:46:10  eigenratio = 1 is possible if each level of self-interpreters only adds a constant time
16:46:10  the compiler is written to be compiled by itself
16:46:17  moony: most compilers have eigenratio 1 :-P
16:46:45  in fact, the most promising approach to writing an eigenratio-1 interpreter is to have it work as a compiler + eval
16:46:46  ais523: a self-interpreter that writes the code to be interpreted to the current file, and then restarts the file.
16:47:04  or something like Lua's load().
16:47:24  ais523, go ask in #xkcd. they're esoteric enough to help maybe? :P
16:47:39  ais523: but if the compiler is being freshly compiled, doesn't that give it eigenratio > 1?
16:47:42  also, just claiming this now: inb4 brainfuck but with more instructions
16:47:43  moony: I think a simple eval() would do
16:48:17  alercah: the point is that if you repeatedly compile the compiler with itself, then eventually run a different program with the final compiler in the chain
16:48:20  the program doesn't run any slower
16:48:24  ais523: ohh ok
16:48:31  ais523: I thought you were including the time to compile the compilers
16:48:37  so each layer of compiler didn't give you a slowdown of a factor, but a slowdown of a constant amount of time, which doesn't show up on the ratio
16:50:11  ais523, is memory usage counted as a side effect?
16:50:52  moony: hmm, I guess for this to work it needs to avoid using notable extra memory for each level of self-interps, too
16:51:17  although I guess it's probably OK to have a Feather interpreter that crashes due to memory loss, or gets very slow after a while, at least to start with
16:51:22  hrm, well your 'functional with minimal side effects' requirement seems to be fulfilled by unlambda.
16:51:25  we could perhaps optimize it later? maybe even retroactively?
16:51:44  moony: Unlambda actually does very well in a number of categories as a language in which to write Feather
16:51:50  its main drawback is being almost impossible to write in
16:52:06  ais523, why not make a abstraction of unlambda?
16:52:11  (or, actually, it's not that hard to write but is hard to do anything else with)
16:52:19  in fact, let me see how that could be done... hrm.
16:53:30  so user output as only side effect? leme think
16:53:34  if you treat unlambda as an asm it's not that bad
16:53:56  moony: I think I've figured out how to do I/O in a pure functional language without making evaluation order visible
16:54:15  although the general issue of doing I/O in Feather is a pretty awkward one, especially output
16:54:20  ais523, well, ...Damn, you got me into a feather problem
16:54:26  because after you've output something, you can retroactively change things so that you didn't output it
16:54:36  moony: really, I recommend not thinking about it
16:54:51  maybe the problem actually is unsolvable!
16:55:02  actually, talking through this here has helped, because it's making Feather seem less possible rather than more
16:55:09  ais523, who knows. if it is this could be a issue with modern mathematics......
16:55:22  ais523: Don't worry, I'm already mad, I think I might be able to solve it (after trying everything else first :P)
16:55:22  not feather, but our form of mathematics and logic
16:55:54  maybe we can use anger to disguse our thoughts so the universe doesnt notice us thinking about feather.
16:56:27  O_o
16:56:48  rdococ, hey, its worth trying.
16:57:07  moony: sorry, but anger has the opposite effect hth
16:57:59  `? hth
16:58:00  hth ([ʰtʰh̩]) is help received from a hairy toe. It is not at all hambiguitous.
16:58:05  unhelpful as usual
16:58:16  `? hambiguitous
16:58:16  oh right 'hope that helps'
16:58:17  We're not sure what hambiguitous means, but it's definitely not hth.
16:59:38  😎
16:59:42  oerjan, would a feeling of calm help? Cats make calmness. *prepares to flood chatroom with kittens*
16:59:46  `? Boobies
16:59:47  Boobies? ¯\(°​_o)/¯
16:59:50  🙌
17:01:30  [wiki] [[Main Page]]  https://esolangs.org/w/index.php?diff=52884&oldid=52881 * Oerjan * (-238) You failed to discuss this in the right place hth
17:02:28  they probably discussed it on the discord server :-P
17:02:45  incidentally, a "discord server" isn't actually a server, it's more like a channel
17:03:16  moony: probably
17:09:33  so, i figured out this: Feather is likely a purely functional language that is self interperting with minimal/no side effects
17:09:56  and throwing the word "retroactively" around a lot
17:10:08  hmm. "in Feather, you create objects by cloning+modification, and if you retroactively change the parent object, that changes all its decendants, so it comes to the same thing"
17:10:17  that actually sounds coo.
17:10:18  l
17:10:56  sure, if it wasn't a cool language I don't think I'd have spent this much mental effort on it
17:11:21  also, Feather itself (as opposed to the language in which it's originally implemented) sort-of has side effects because a retroactive change is similar to an assignment in that sense
17:11:22  do we have any more feather info? :P lets see if we can try and piece it together. Communal brainpower only thinking about PARTS cant be as bad as thinking about the WHOLE
17:11:50  moony: or let me think about the WHOLE, because I'm already INSANE :P
17:11:52  well, one big problem is "how do you encapsulate things well enough that a retroactive change doesn't create an infinite loop"
17:11:56  say I retroactively change something to itself
17:12:06  Feather does that by going back in time to the point at which it was created, changing nothing
17:12:07  what is this retroactive change, first of all?
17:12:11  then running hte program from there
17:12:40  rdococ: you can define the core operation pretty easily; when an object is "created" it gets a handle (which is probably just a continuation) that describes the object
17:12:55  then you can retroactively change the object via using the handle; it replaces what the object was at the time it was created
17:12:58  ooh, object continuations?
17:13:01  this is basically what call/cc already does
17:13:10  O_o
17:13:30  right, so the idea is you have a continuation on an object, but you implement that via call/cc at the time the object's created
17:13:59  ais523, i assume once its done it goes back in time to program start and gives output immediately?
17:14:00  if you later want to change what the object was, you use the continuation to rewind back to the time it was created
17:14:07  and put a different object (taken from the future) there instead
17:14:19  moony: not necessarily, although that's an interesting idea
17:14:47  then just use up the needed compute time, or even cut program execution out of the timeline entirely, making it have no side effects (in essence)
17:15:00  a program is basically a "chunkstream" that works like Easy; it's a program followed by input to it, but the program is meant to be a self-interpreter (or approximately so) so it recognises the input as more code to run
17:15:24  O_O
17:15:36  the whole notion of retroactively replacing the whole program execution with the output does actually solve most of the major problems with the output, though
17:17:04  ais523, your welcome :)
17:17:35  im happy to not erase that moment frm the timeline and keep it to myself as long as you dont do the same
17:19:08  moony: so I don't have an actual time machine
17:19:13  but ideally, when you retroactively change something in Feather
17:19:35  it's carefully crafted so that the change has no visible effect until the moment you tried to go back in time and change it
17:19:52  ais523, just keep a state tracker. Sure it'll eat memory like hell by keeping track of all timelines, but it'll do the job for a theoretical system
17:20:16  Tracking state isn't a panacea here
17:21:26  Taneb, i swear i'll erase you from the timeline /s
17:21:33  Be my guest ;)
17:21:45 * moony wonders if they realise this universe is a program on moonys computer
17:21:54  O_O
17:22:08  nope they noticed.
17:22:26 * moony prepares timeline wipe before remembering it only creates a new branch, he fucked this timeline up
17:22:26  Yay! Can moony use the program to give me lots of money?
17:22:39  rdococ, no
17:22:42  Aw.
17:22:57  as in 'i refuse to go through the effort of making a template'
17:23:02  Can moony use the program to metaprogram, so he can generate code that gives me the ability to give myself lots of money?
17:23:13  rdococ, no
17:23:23  lol
17:23:26  i refuse to give you a shitty life hack
17:23:27  Can moony prove that the universe is on his computer?
17:23:42  rdococ, sure. You now no longer exist in the branch of this timeline.
17:23:48  a branch tho
17:23:51  YaaaaY!
17:23:53  you exist here because i cant undo it.
17:23:55  ais523: Phœnix-Feathers pwn. At least in the final Fantasies.  😎
17:24:04  moony: Sad but true.
17:24:19  Can you remove APic from another branch in the timeline?
17:24:23  rdococ, done
17:24:28  YaY!
17:24:30  rdococ: In my Dreams, probably.
17:24:37  i deleted everyone assosiated eith #esoteric in another timeline besides me.
17:24:43  rdococ: Also, in other Branches, my Nick is actually „ACTPic“.
17:24:49  Now, can you force APic's current subconscious to enter the timeline in which he does not exist?
17:24:59  rdococ, i refuse
17:24:59  s/sub//
17:25:03  Why?
17:25:07  bcuz its mean
17:25:18  Eh, true.
17:25:30  APic: hmm, the translation used for the English versions of Final Fantasies is "Phoenix Down", but I know that several details, both major and minor, are different in different language versions
17:25:38  here, i'll force APic from 10 seconds ago to branch off and then be shoved into the timeline where he doesnt exist
17:25:41  so there may well be a language where they're phœnix feathers insetead
17:26:11  ais523, tip: your 'feather' language will be awesome according to this timeline over here, from 2 years ago.
17:26:23  moony: Can you create a branch in the timeline which has developed the technology necessary to broadcast information across branches - even to branches which don't have the technology necessary to receive those messages?
17:26:41  moony: well, Feather's time-travel model is basically one in which retroactively changing something destroys your current timeline and recreates it via replaying from that point with the change
17:26:46  rdococ, that'd make the program crash. do you want that? (:
17:26:48  . o O ( At each time step, the universe is recreated from scratch. The trick is to make it appear smooth and efficient. )
17:27:01  moony: Ooh! I want to know what it feels like to crash!
17:27:01  so you get a timeloop if the retroactive change happens again in the new timeline, thus you need every change to somehow negate the fact it was made
17:27:09  int-e, eeexxxaaaccctttllly
17:27:19  rdococ, it means you no longer exist. in every timeline. forever.
17:27:31  moony: Is the crash local to me, or global?
17:27:45  psst, someone kline him and scramble the DNS cache so he thinks i deleted freenode
17:27:52  ...
17:28:24  Moony, I'll still have these logs.
17:28:27  I'm not dumb.
17:28:43  rdococ, oh right. Oh well.
17:28:53  But I am pretty stupid.
17:28:58  wait, are italics standard on IRC nowadays?
17:29:02  if onyl i could disable the auto timeline split safety feature.
17:29:06  my client interprets tab as toggle-italics, but I thought most didn't
17:29:18  pretty sure they are. altho tab italics is NOT standard
17:29:29  my client uses ctrl+i for italics
17:29:35  my client doesnt even let me enter a tab
17:29:41  neither does mine
17:29:55  rdococ: control-I /is/ a tab
17:29:56  not even sure where it tabs to
17:30:13  ais523, oh. ok it is standard then.
17:30:14  ais523: it isn't, they are two distinct characters
17:30:16  oh I just realized that thing int-e keeps doing is a thought bubble
17:30:19  just like control-J is a newline, control-M is a carriage return, control-[ is escape, etc.
17:30:21  ...can't believe I didn't see that earlier
17:30:30  TieSoul, wonder what took you so long
17:30:36  I copied and pasted tabs from a text editor. see? not italic.
17:30:43  yeah I know right
17:31:00  I can type italics with ctrl-i too
17:31:15  bolditalicunderlinecolor
17:31:28  rdococ: it used to be that copy-pasted tabs would italicise on this client
17:31:35  ais523: oh
17:32:13  anyways back to feather
17:32:17  ais523, any known syntax?
17:32:50  moony: I can't remember the details, but the intention was that it should be similar to Smalltalk but work for different reasons
17:33:24  "a b" would normally call method b on a, but if a was "unboxed" it'd provide b as an argument to a
17:33:45  there was some method you could call on things to get an unboxed version of them, but I can't remember whether it was ^ or #
17:33:50  whichever one you'd use in that situation in Smalltalk
17:34:21  I believe ^ is return in Smalltalk
17:34:24  also the method name for the low-level retroactive change was <<=
17:34:35  by the way, you guys are lucky. this is timeline '0' persay
17:34:57  Branchporting pwnd in the NetHacks.
17:35:33  ais523: We had the Phönixfeders in the Germanies, at least so i believe.
17:35:36  moony: so did you create timeline 0 with everyone in it, or...?
17:35:45  because if so, why do I exist here
17:36:04  rdococ, how do you think it started? Im not going to spend milleniums handcrafting a universe. i let it do its thing.
17:36:44  moony: if you think it's such a bad idea to spend millenia hand-crafting a universe, maybe you should tell the kinds of people who hand-craft universes for fun!
17:37:15  rdococ, its not a bad idea. i just dont wanna spend it. even if i DO live several billion years.
17:37:25  ah
17:38:04  `? esoteric
17:38:06  This channel is about programming -- for the other kind of esoterica, try #esoteric on EFnet or DALnet.
17:38:10  i recall some universe that had a world on the back of a giant turtle that had 3-4 elephants on it... I also remember leaking it into this world by mistake
17:38:20  ais523, might wanna revise that. its so much more now.
17:38:25  I'm wondering if I've fallen into the wrong #esoteric by mistake :-P
17:38:35  ais523, lol
17:38:35  moony: discworld?
17:38:43  rdococ, i refuse to say
17:38:50  Concept: OOP language where methods themselves are objects
17:38:52  moony: I preferred it when it was mostly about programming
17:38:53  now back on topic before i blow you to bits
17:38:59  ais523, ah.
17:39:05  although the offtopic discussion is much less objectionable than it was a couple of decades ago
17:39:14  hmm, more like 1½
17:39:14  ais523, theoreticals are fun too! 
17:39:37  I ended up leaving #esoteric for long periods of time because I just wasn't interested in the topics it normally discussed
17:39:45  mm
17:39:56  thats normal. #xkcd is better anyways :P
17:40:38  discussion of every kind there. from the comic to space-time 
17:41:14  oh and hppa lurks there. hasnt been here in a while has he
17:41:30  (not lurks, really, he's a active talker)
17:41:40  saw him yesterday, i think
17:42:01  well, joining.
17:45:45  A housemate taught me a cool way to represent scenes for graphicsy stuff yesterday
17:45:57  As functions from points to the distance to the closest surface
17:46:09  And you can take the union of two scenes with, like, liftA2 min
17:46:24  yeah, signed distance functions
17:46:32  they're neat
17:46:48  Yeah!
17:46:53  FireFly, i have a suspicion: are you named after the show/movie/book/whateveritis
17:47:09  moony: no
17:47:14  common misconseption
17:47:15  I always assumed FireFly was an aquatic insect
17:47:18  misconception too
17:47:25  Taneb: http://iquilezles.org/www/articles/distfunctions/distfunctions.htm
17:47:26  o_o
17:47:52  has a nice collections of primitives and tricks for sdf's
17:48:02  raymarching is fun :)
17:49:06  Also if you take the derivative of the signed norm function at a surface point, you get the surface's normal
17:50:00  yeah, so you can use an approximation of the gradient (like central difference) to get the normal
17:50:05  handy for light computations
17:51:26  I've been working on something that uses automatic differentiation for that today
17:52:24  kill me
17:53:09  But I find Sundays difficult because I tend to forget to drink
17:53:26  rdococ: just hold your breath
17:53:43  int-e: that doesn't work
17:54:14  rdococ: well the underlying theory is sound.
17:54:35  anyway...
17:54:45  Taneb: why sundays in particular?
17:55:19  Taneb: I learned about the idea of automatic differentiation a while ago, it seems like it'd be really handy for that, yeah
17:55:42  FireFly, my office has a sink that I can see from my desk, so I remember to drink Mondays through Fridays
17:55:43  in cases when the distance function is possible to express neatly
17:55:48  Ah
17:55:51   what's the name for epsilon-epsilon-epsilon-...? <-- phi_2(0) iiuc.
17:56:26  hm
17:56:50  well that certainly sounds like it could be it
17:56:55  https://en.wikipedia.org/wiki/Veblen_function although it's pretty dense.
17:57:15  FireFly, I'm a bit crap at looking after myself today tbh :(
17:57:21  In general, in fact
17:57:57  oh I see
17:58:05  yeah I think you're right
17:58:12  Taneb: https://www.youtube.com/watch?v=O-1zEo7DD8w  ← this from Revision earlier this year is pretty cool, LJ (to the right) is livecoding a scene expressed as an sdf and rendering it with raymarching in half an hour
18:00:23  (leave it to demosceners to do crazy stuff like that in half an hour :P)
18:01:23  Yeah, the housemate who told me about this is into demoscene
18:01:43  ah
18:02:07  I've played a bit with raymarching and distance fields, but not enough..
18:11:45  While I'm thinking about it I'm going to get a drink
18:11:50  Hmm.
18:12:04  How about an OO language where even the methods are objects?
18:12:55 -!- MDude has joined.
18:12:56  Taneb: you could try keeping a bottle of water by the desk
18:13:03  or you could try getting addicted to tea, I find that works pretty well too
18:13:08  well, ais523 has me trapped trying to figure out how to make a precursor functional language feather could be implemented in
18:13:33  I didn't mean to; feel free to stop thinking about it if you like!
18:13:42  no. never
18:14:22  FireFly, I really don't like the taste of tea
18:14:51  ah
18:14:54  But the bottle suggestion might work
18:25:37 * moony explodes
18:29:59  exploding moons are so last century
18:35:59  one thing i don't recall ais523 ever explaining, is what's supposed to happen if you replace an object with something that _contains_ the original, but isn't identical to it.
18:36:23  ais523, might wanna explain that... could be a issue. dont want to crash the universe do we?
18:36:25  oerjan: you can smuggle back objects from previous timelines like that
18:36:32  so the new-timeline object contains the old-timeline object
18:36:48  from before the retroactive replacement
18:36:51  the old-timeline object would be modified in the old timeline right?
18:37:01  the old timeline no longer exists
18:37:22  when you make a retroactive change, that /always/ ends the current timeline, and starts from a new timeline that branched off from the previously current timeline at the point at which the object was created
18:37:29  then what happens if you write to the old timeline object which supposedly should be gone
18:37:35  so there's only one timeline at a time
18:38:10  moony: there is a consistent answer to this, but I'm not 100% sure offhand what it is
18:38:20  basically, think of it in terms of call/cc
18:38:23  this is the best conversation to happen here in months
18:38:32  ikr
18:38:57  whenever you create an object, you do so within a call/cc function, the function that's called/cc takes the continuation and adds it to a field of the object, then returns the object
18:39:37  but that means that if you have a smuggled object then you also have its timeline, through its continuation.
18:39:39  then to retroactively change the object, you take the continuation (which you can access because it's in a field of the object), and give it the new object as an argument (thus effectively rerunning the program from the point at which the object was created)
18:40:08  oerjan: right, this is indeed correct, although you only have the timeline at the point the object was created
18:40:16  so I guess there's only one active timeline at a time, but you can have plenty of dormant timelines
18:40:19  ais523, uh, how would a self referencing object behave?
18:40:34  moony: I don't believe it's possible to create a self-referencing object in Feather
18:40:46  mk
18:40:57  you don't have any way to change the current value of a field, only retroactively change the object's value at creation time
18:41:27  the equivalent of "an object reference" is "an object's continuation", as that's the only thing that differs between an object and a clone of an object; but an object has its own continuation available already
18:41:51  oerjan: also, I don't think you can reasonably get mad at me for not knowing how Feather works :-P
18:41:55  cant you just go back in time, put the object inside its own field, and have a recursive object?
18:42:16  moony: no, then the object has a copy of itself from the /previous/ timeline
18:42:21  which is not an exact copy of itself
18:42:30  ah
18:42:36  eventually, if you follow the chain of objects, it'll bottom out because you'll reach a timeline in which the object didn't self-reference
18:42:45  ais523: I think not being reasonable is one of the characteristic features of going mad.
18:42:56  however! you can have an object that tracks the number of nesting levels you want
18:43:10  and use accessor functions for the nested copies which, if they don't find a nested copy, retroactively increase the number of nesting levels
18:43:12  so that they can give you one
18:43:37  this allows you to have an object that's observationally indistinguishable from one with an infinite number of nested copies of itself from previous timelines
18:44:11  ais523: do you have a logical system to express this in?
18:44:19  now, you can also (probably? as usual, I'm unsure as to the details) do this with Feather interpreters, allowing you to have a Feather interpreter that's written in Feather and which runs using a chain of interpreters that's observationally indistinguishable from infinitely large
18:44:25  alercah: no
18:44:55  this gives you really powerful introspection properties, as if you need a new debug feature, you can just retroactively add it to the interpreter and the feature is now there
18:46:09 -!- GeekDude has quit (Ping timeout: 248 seconds).
18:46:22  you may have a hard time finding pieces of history to discard though, which is a bit ironic for something that wants to be a light-weight smalltalk
18:47:16  yes, "how is it possible to make all of this not incredibly inefficient and getting slower as the program runs" is a major problem
18:47:33  although, I guess it can be lightweight in syntax and language features required to be sufficiently powerful, and yet still almost impossible to run in practice?
18:48:04  ais523, ...wow, i just got trapped in a logical paradox: If i were to be erased permanantly from the timeline, would i notice? Intersects heavily with the 'where does the brain go after death if anywhere' problem
18:48:11  it feels to me like having a formal logic might be a useful stepping stone, though making a self-modifying logic may be no easier I guess
18:48:12 -!- GeekDude has joined.
18:48:14 -!- zseri has quit (Ping timeout: 260 seconds).
18:48:47  alercah: from my point of view, the time travel mechanics are the /least/ confusing part, I just use the call/cc-based definition
18:48:55  ais523: eh, fair
18:49:06  😎
18:49:09  that said, call/cc is fairly confusing as operations go, but once you understand it everything else is fairly straightforward
18:49:17  ,o0(Call Collect.)
18:49:33  0800-333-42 42 here in the Germanies.
18:49:37  Hm
18:49:39  (also, there's a fairly simple definition in terms of fork(1) and blocking I/O operations that's clearly insane from an efficiency point of view but is very simple to understand)
18:49:42  Maybe another 42 at the End.
18:49:43  Dunno.
18:50:00  Probably.
18:50:05  APic: huh, free-to-call phone numbers are 0800 in Germany too? I'm a bit surprised, because that's also the prefix for them in the UK
18:50:19  ais523: there's a EU norm
18:50:23  ais523: To dial in the united Kingdom for free, we would need 00800.
18:50:23  it used to be 0130
18:50:27  int-e: True.
18:50:59  (not sure when that was phased out, 15 or so years ago?)
18:51:18  Cannot…   remember…     the…     Past…
18:51:25  ,o0(Must not.)
18:52:42  End of 2000, lucky guess.
18:52:45  the UK is shit
18:53:22  Well.
18:53:31 * APic does not quite like that they separated from the EU again.
18:53:40  we haven't yet
18:53:41  no, the UK is shit
18:53:43  With their Pounds and Stuff…
18:53:46  Oh.
18:53:47  and 48% of Brits don't like it either
18:53:51  ais523: Thanks for Telling.
18:53:53  it was a very close referendum
18:53:53  That is news to me.
18:53:54  🙌
18:53:58  s/new/New/
18:54:17  welcome to what will soon become corporate hell if Theresa May gets her way (heh, rhyme)
18:54:55  lol
18:55:06  rdococ: Theresa May is only prime minister because nobody else both a) actually wants the job and b) has the support of enough MPs that they wouldn't immediately be removed if they became Prime Minister
18:55:40  ,o0(Mana-Points…)
18:55:41  ais523: wait, what about the Labour party?
18:56:11  that would be part b)?
18:56:17  ah
18:56:21  rdococ: they fail b), there are enough MPs in parties who strongly dislike Labour that they would be able to vote out any Prime Minister from that party
18:56:53  one of the fundamental rules of being the prime minister is that you need the confidence of at least half the MPs
18:56:55  ais523: yeah, but none of them trust the Tories anymore
18:57:06  rdococ: most of them /are/ the Tories
18:57:17  although I agree that many Tories don't trust each other
18:57:51  oh, and let's not forget that DUP thing
18:58:22  dup, dup.
18:58:46  `quote democrats
18:58:48  No output.
18:58:50  `quote democratic
18:58:51  701)  Why does CL get called functional?   it's sort of like how you call ancient greece democratic.
18:59:04  `quote election
18:59:04  529)  Hulu's movie selection is like MST3K without the MST3K characters. \ 944) * ais523 challenges the americans here to remember who lost in the most recent UK general election   ais523, the lib dems
18:59:41  depends what you mean by lost.
19:00:14  rdococ: that quote is older than the most recent election, i think.
19:00:20  ah
19:01:00  the coalition government was actually the best government we've had for a while IMO
19:01:06  `` doag quotes | grep 'challenges the americans'
19:01:09  you seriously think so?
19:01:13  2267:2013-02-26  addquote * ais523 challenges the americans here to remember who lost in the most recent UK general election   ais523, the lib dems
19:01:46  tories seem to really like privatization - or at least the tories that currently control the party do
19:01:53  rdococ: they didn't screw a whole load up (and most of what they did was the conservatives backstabbing the lib dems to make them less popular)
19:02:08  pro-privatization is a standard Conservative position, I think
19:03:04  privatization helps to perpetuate the rich-poor divid
19:03:05  e
19:03:14  or at least what we've seen of it
19:04:08  . o O ( privatization is for when you want to have things run to the ground, not when you want to conserve them )
19:04:50  privatization paves the way for cyberpunk
19:04:51  int-e, I don't think there's ever been a political party who's name's been accurate for more than a century or so
19:06:34  I think the main argument in favour of privitization is that history has shown that the British government is fairly bad at running sections of the economy itself
19:06:37  `quote 241
19:06:37  241)  shit would make great currency, because everyone would have it and you could literally be filthy rich
19:06:56  `quote 941
19:06:56  941)  I stand by the argument that fungot is the one making the most sense in this channel.
19:07:17  ais523: I wouldn't leave it to for-profit organizations either
19:07:18 * boily pats fungot
19:07:19  boily: so, hey, it was our table! if he's interested, he'll push it back to your side. the salt shaker over to their side, this means that, for all intents and purposes
19:07:33 * rdococ hugs fungot
19:07:33  rdococ: but in a metaphorical sense. what metaphor would that be, exactly? presents dino never coexisted! your interaction could have dire repercussions. it could tear you apart, and the person in a book, and what's more, it's a book about a tugboat that employs superseded scientific theories for locomotion!
19:07:51  how does fungot generate malformed lines like that?
19:07:51  rdococ: in this fallacy, t-rex? i am so happy! it's impossible, utahraptor." then, hey presto, you're a muslim!
19:08:00  holy shit
19:08:17  `` tail -n1 <(cat -n quote)
19:08:18  cat: quote: No such file or directory
19:08:22  `` tail -n1 <(cat -n quotes)
19:08:23  ​  1313 IMO, the best thing to do with wisdom is ignore it
19:08:38  rdococ: fungot's sentences only locally make sense, it basically aims for each stretch of n words (where n would typically be around 3) to make sense individually and has no idea of where the sentence as a whole is going
19:08:38  ais523: are you you're going trick-or-treating this year, a balloon! the balloon goes up some of the way, we can consider the real question, which is a good thing! stupid problems? that is hilarious right
19:08:52  ah
19:09:10  ^style
19:09:10  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
19:09:11  is there a way to change n?
19:09:26  ^help
19:09:26  ^ ; ^def   ; ^show [command]; lang=bf/ul, code=text/str:N; ^str 0-9 get/set/add [text]; ^style [style]; ^bool
19:09:29  rdococ, that'd be very tricky I imagine
19:09:40  Are you familiar with how Markov chains are implemented?
19:09:51  rdococ: well the whole model is kind of static; fizzie is tuning the knobs which probably involves picking n.
19:10:12  ah
19:10:20  Oh.. I forgot aboutt this esolang. (its one i made, and can only be computed by solving the halting problem)
19:10:21  http://esolangs.org/wiki/HBL
19:10:32  models come out of variKN, IIRC: https://github.com/vsiivola/variKN
19:11:58  I had the idea of incorporating floats into brainfuck using some command.
19:12:03  I think n might be slightly variable, too?
19:12:32  maybe a / command to take the left branch in the surreal number tree?
19:15:06  ais523: do you think mindscrew could do with an additional feature like non-integers?
19:15:53  no idea, it's hard to know what features should and shouldn't be in BF derivatives
19:16:19  well, atm mindscrew is a derivative of pbrain with its own procedure tape and procedure pointer
19:20:59 -!- oerjan has quit (Quit: Later).
19:32:21 -!- jaboja has quit (Read error: Connection reset by peer).
19:34:48 -!- jaboja has joined.
19:36:15  ais523: the idea is that there would be two new commands: / and *. / would take the left branch in the surreal number tree, * the right branch. (if it's at the top, it just adds one). here -> https://upload.wikimedia.org/wikipedia/commons/4/49/Surreal_number_tree.svg
19:36:34  so +/ results in one half, ++/ results in one and a half, etc.
19:36:58  +/* is 3/4, +/*/ would be 5/8
19:37:00  do you have ways to undo that, too?
19:37:07  good point
19:37:07  what happens if you do one and undo another
19:37:19  there'd probably be one to go up the tree
19:37:22  bear in mind that the only way to read a value in BF in a way that affects control flow is to bring it back to zero
19:37:28  so if you have two downs and one up, then the two downs are equivalent
19:38:04  / to branch left, * to branch right, and ^ to branch up, maybe?
19:38:34  ooh, what if we used those as the only commands, disregarding + and -?
19:38:41   so if you have two downs and one up, then the two downs are equivalent
19:38:54  what is a "down"?
19:39:06  I'm talking about going the left branch, the right branch, and up
19:40:08  having one up operation also means a [^] loop will always set the cell to 0, which is interesting
19:40:12  (0 is at the top of the tree)
19:40:37  left and right are both opposites of up, thus down
19:40:47  my point is that / and * are observationally equivalent
19:40:51  ah
19:40:55  there's no way to distinguish between them from within the language
19:41:00  ...ah.
19:41:08  because the only way to get an [] loop to exit would be to ^ enough to take it back to zero
19:41:21  hum.
19:43:43 -!- Phantom_Hoover has joined.
19:51:24  hi Phantom_Hoover.
19:51:30  helo
19:51:56 -!- zseri has joined.
19:54:54  `unidecode ẙåẘẙ
19:54:55  ​[U+1E99 LATIN SMALL LETTER Y WITH RING ABOVE] [U+00E5 LATIN SMALL LETTER A WITH RING ABOVE] [U+1E98 LATIN SMALL LETTER W WITH RING ABOVE] [U+1E99 LATIN SMALL LETTER Y WITH RING ABOVE]
19:56:01  heh
20:04:04 -!- Phantom_Hoover has quit (Read error: Connection reset by peer).
20:07:34 -!- Phantom_Hoover has joined.
20:07:34 -!- Phantom_Hoover has quit (Changing host).
20:07:34 -!- Phantom_Hoover has joined.
20:10:44  `unidecode h̄ů
20:10:44  ​[U+0068 LATIN SMALL LETTER H] [U+0304 COMBINING MACRON] [U+016F LATIN SMALL LETTER U WITH RING ABOVE]
20:11:11  Oo
20:17:39  YaY
20:32:11 -!- imode has joined.
20:32:40 -!- TieSoul has quit (Quit: Leaving).
20:37:51  hi imode
20:47:42  hi rdococ.
20:54:04  Now I invented editable floating point format.
20:55:18  It is stored by 40-bits, consisting of a unsigned 34-bit integer, a sign bit, and a 5-bit number of decimal places (0=no decimal places but the dot is still included, 1-29=that many decimal places, 30=divide by zero, 31=no decimal places and no dot)
20:55:23  Do you like this?
20:58:48  Decimal places?
20:59:08 -!- imode has quit (Ping timeout: 240 seconds).
20:59:17  Yes, in decimal
20:59:34  (The integer part is stored in binary though)
21:00:46  (Also, the intention is that it will be converted to IEEE format when you are doing calculations with it; the editable format is only for editing, and there are multiple ways of representing the same number)
21:03:26  why does it have a specific option to divide by zero?
21:03:47  To represent positive and negative infinity, and NaN.
21:04:05  ah right
21:04:43  you might want to change it so that almost all of those patterns are NaN, other than a specific pattern each for +∞ and -∞
21:09:40  I could, although the way I have it now just seem simpler to convert to IEEE format, since the "number of decimal places" field can index a table of what to divide by.
21:12:17  (The sign bit can also be taken together with the number of decimal places field to index such a table, if wanted)
21:25:47 -!- imode has joined.
21:29:49 -!- zseri has quit (Ping timeout: 260 seconds).
21:33:28 -!- augur has joined.
21:45:48 -!- MDead has joined.
21:47:59 -!- MDude has quit (Ping timeout: 255 seconds).
21:48:04 -!- MDead has changed nick to MDude.
22:25:03 -!- erkin has quit (Quit: Ouch! Got SIGABRT, dying...).
22:37:34 -!- sleffy has joined.
22:47:16 -!- LKoen has quit (Remote host closed the connection).
22:48:00 -!- ATMunn has quit (Quit: brb restarting router).
22:50:57 -!- AnotherTest has quit (Ping timeout: 248 seconds).
22:58:04 -!- ATMunn has joined.
22:59:03 -!- Phantom_Hoover has quit (Remote host closed the connection).
23:07:27 -!- jaboja has quit (Ping timeout: 240 seconds).
23:11:55 -!- moonythedwarf has joined.
23:13:10 -!- moony has quit (Ping timeout: 240 seconds).
23:55:14 -!- jaboja has joined.

2017-08-21:

00:00:02 -!- danieljabailey has quit (Quit: ZNC 1.6.4+deb1 - http://znc.in).
00:00:21 -!- danieljabailey has joined.
00:18:56 -!- oerjan has joined.
00:23:37 <\oren\> oerjan: did u know, that in addition to being a mathematician, mandelbrot is also a delicious almond flavoured cookie?
00:27:09  benoit was an entity of many talents
00:30:44  pastries are fundamentally mathematical
00:31:33  \oren\: i did, since i somewhat understand german
00:32:03  (also since the norwegian cognate is mandelbrød)
00:32:17  i suppose i may not have known it was a cookie specifically.
00:34:04  and going from the google hits, the norwegian word doesn't refer to that.
00:35:25  i think i'll have to summarize that as "no".
01:28:20  helloily helloerjan hichaf
01:28:26  helloren
01:32:51  quintophia
01:38:42 * moonythedwarf now has the rust compiler enviornment working in his linux sandbox bot for the users to use)
01:40:29 <^v> moonythedwarf, lol better be a good sandbox
01:40:58  it is. Using same sandbox as HackEgo over there
01:42:09 <^v> ah
01:47:01 -!- imode has quit (Ping timeout: 255 seconds).
01:48:14 -!- imode has joined.
01:48:22  bonsoœøırjan, QUINTHELLOPIA, mhelloonythellodwarf, ^hellov.
01:51:10  bhelloily
02:22:21 -!- Warrigal_ has joined.
02:24:24 <\oren\> it's the same oren
02:25:54  o/
02:26:33  You should have said "nope, must be a different oren" on the other server.
02:27:50 <\oren\> LOL
02:32:18  you will only perceive different orens depending on your clearance level. unauthorized access entails class A amnestics.
02:33:56  There's actually only one oren, and that oren is only connected to one server, but it's possible to "see" oren on multiple different servers due to optical effects.
02:34:08  You know. Internet refraction and all that.
02:34:37 <\oren\> Technically, I'm only connected to my website's server, and then the irc program is running on that.
02:34:57  `? \oren\
02:34:58  ​\oren\ is an attempt to improve upon oren. The only thing it actually improved was name recognizability, and it made everything else... unenthickenable, eh?
02:35:04  Internet refraction?
02:35:42  `slwd \oren\//s/attempt/optical attempt/
02:35:43  ​\oren\//\oren\ is an optical attempt to improve upon oren. The only thing it actually improved was name recognizability, and it made everything else... unenthickenable, eh?
02:36:40  hezzo38. swamp gas from a weather balloon was trapped in a thermal pocket and reflected the light from Venus.
02:45:32  `? moony
02:45:33  moony? ¯\(°​_o)/¯
02:45:39  `? moonythedwarf
02:45:40  moonythedwarf? ¯\(°​_o)/¯
02:45:43  `? moonheart08
02:45:44  moonheart08? ¯\(°​_o)/¯
02:45:50  i cant even find my own entry
02:45:57  ironic.
02:46:21  we need to make a glob alias (if thats possible) that turns itself into a list of my usernames
02:48:12 -!- LKoen has joined.
02:52:43 -!- LKoen has quit (Ping timeout: 255 seconds).
03:00:33 -!- hakatashi has quit (Remote host closed the connection).
03:02:33  you have to be yourself first, not the persons who are you. a strong identity by itself is its own personal self.
03:04:37  I think that is not relevant to that?
03:05:46 -!- ATMunn has quit (Quit: See ya! o/).
03:12:47 -!- boily has quit (Quit: FIREWORK CHICKEN).
03:22:05  `wisdom moon
03:22:07  moon//moon is often named the following: moonythedwarf moonythehuman moonheart08 moony moon__ computing and luxon, making porthellos and @tells a real pain
03:23:00  `` grwp -l moon
03:23:09  ​☾_ \ ciol \ #esoteric \ moon \ pluto
03:23:20  `? ciol
03:23:21  ciol is a language designed by moon_, it started as a scheme to annoy colleagues by making a programming language that has insults as commands.
03:45:16 -!- jaboja has quit (Remote host closed the connection).
03:47:02 -!- Antoxyde has quit (Quit: Leaving).
04:43:54 -!- augur has quit (Quit: Leaving...).
05:05:01 -!- sleffy has quit (Ping timeout: 255 seconds).
05:08:51 -!- sleffy has joined.
05:10:02 -!- doesthiswork has quit (Quit: Leaving.).
05:15:22 -!- oerjan has quit (Quit: Nite).
06:36:58 -!- erkin has joined.
07:01:16 -!- FreeFull has quit.
07:39:01 -!- Warrigal_ has quit (Ping timeout: 240 seconds).
07:44:26 -!- ais523 has quit.
07:56:06 -!- zseri has joined.
08:05:27 -!- moonythedwarf has quit (Ping timeout: 240 seconds).
08:15:05 -!- sleffy has quit (Ping timeout: 240 seconds).
08:26:04 -!- zseri has quit (Ping timeout: 260 seconds).
08:29:13 -!- sleffy has joined.
08:41:04 -!- Riviera has quit (Remote host closed the connection).
08:46:09 -!- imode has quit (Ping timeout: 248 seconds).
08:58:35 -!- erkin has quit (Ping timeout: 240 seconds).
09:00:41 -!- augur has joined.
09:05:23 -!- erkin has joined.
09:22:32 -!- erkin has quit (Quit: Ouch! Got SIGABRT, dying...).
09:23:25 -!- erkin has joined.
09:38:58  Moo?
09:55:09 -!- augur has quit (Remote host closed the connection).
09:55:43 -!- augur has joined.
10:00:04 -!- augur has quit (Ping timeout: 246 seconds).
10:29:00  [wiki] [[Ly]]  https://esolangs.org/w/index.php?diff=52885&oldid=52769 * LyricLy * (+203) 
10:31:15  I would be lying if I didn't find that esolang name really susceptible to many kinds of badly made puns.
10:32:49  holy crap, the user list is what, 90% spambots?!
10:33:05 -!- erkin has quit (Remote host closed the connection).
10:33:33 -!- erkin has joined.
10:36:01 -!- AnotherTest has joined.
10:49:07  hi AnotherTest.
10:49:39  https://xkcd.com/329/
11:33:49 -!- boily has joined.
11:45:24  boily.
11:50:33  [wiki] [[Language list]]  https://esolangs.org/w/index.php?diff=52886&oldid=52870 * Rdococ * (+1) Removed a [[Typespam]] duplicate from "Non-alphabetic", added mindscrew.
11:50:57 -!- sleffy has quit (Ping timeout: 240 seconds).
11:51:34  rdochelloc.
11:51:54  helloily.
11:52:48  concept: brainfuck on a stack
11:53:43 -!- LKoen has joined.
11:57:21  rdococ: what's your instruction set?
11:57:36  for brainfuck on a stack, or mindscrew?
11:58:52  for your brainfuck on a stick.
11:59:06  hah, stick
11:59:33  I'm not sure, it was just a random thing (that has already been created multiple times by the looks of the stack-based category)
12:00:11  well, there may be some historical precedent...
12:00:43  how about a swap instruction that, when first called, swaps the top element of the stack with the tail of the stack, and the second time it's called, reverses that action? (then third time does it again, etc.)
12:01:26  so, on the nth time it is called, if n is odd then it swaps the head of the stack with the tail of the stack, but if it's odd then it swaps the bottom element in the stack to the top.
12:01:54  that's having a register.
12:02:24  true.
12:02:34  which doesn't sound too bad of an idea, actually.
12:03:01 * boily throws a ninja smoke bomb. be back tonight.
12:03:05 -!- boily has quit (Quit: STRIP CHICKEN).
12:12:52 * rdococ eats a chicken
12:39:53 -!- Antoxyde has joined.
12:49:35  hi Antoxyde.
13:17:28  `? rdocco
13:17:31  rdocco? ¯\(°​_o)/¯
13:19:13  `le//rn rdocco//Rdocco Coffee is a well-known brand of coffee in Universe M-7, and does not contain a highly lethal substance engineered to cause bullet time and addiction.
13:19:15  Learned 'rdocco': Rdocco Coffee is a well-known brand of coffee in Universe M-7, and does not contain a highly lethal substance engineered to cause bullet time and addiction.
13:25:55 -!- zseri has joined.
13:29:21  hi zseri.
13:29:24  `? feather
13:29:25  A feather is something that can be found on most birds. It is responsible for their ability to not spontaneously float, seeing as how feathers are made of osmium. Penguins and ostriches have more feathers than most other birds, many of which are internal.
13:29:34  `? Feather
13:29:35  A feather is something that can be found on most birds. It is responsible for their ability to not spontaneously float, seeing as how feathers are made of osmium. Penguins and ostriches have more feathers than most other birds, many of which are internal.
13:29:40  hi
13:29:46  `? osmium
13:29:47  osmium? ¯\(°​_o)/¯
14:00:12 -!- ATMunn has joined.
14:00:27 -!- doesthiswork has joined.
14:36:07 * rdococ is still thinking on how Brainfuck with floats could work.
14:36:37  Maybe / should divide the value by 2, and * should multiply it? It'd be like dec/increasing the exponent.
14:40:53 -!- `^_^v has joined.
14:53:37 -!- zseri has quit (Quit: Page closed).
14:56:20 -!- augur has joined.
15:00:21 -!- augur has quit (Ping timeout: 240 seconds).
15:00:52  Esoteric bignums.
15:04:36  Concept: using unevaluated expressions as anonymous functions
15:19:47 -!- TieSoul has joined.
15:31:26  Concept: Bit operations that work on bignums.
15:31:36  They would assume an infinite number of bits.
15:32:03  e.g. value >> shift would be  math.floor(value / 2^shift)
15:35:03 -!- Vorpal has quit (Quit: ZNC - http://znc.sourceforge.net).
15:35:30 -!- erkin has quit (Quit: Ouch! Got SIGABRT, dying...).
15:56:29 -!- jaboja has joined.
16:02:42 -!- Antoxyde_ has joined.
16:04:47  hi humans. hi TieSoul.
16:05:05 -!- Antoxyde has quit (Ping timeout: 240 seconds).
16:05:15  implying I'm not a human?
16:14:20  no, you're a Soul.
16:23:07  makes sense
16:44:31 -!- jaboja has quit (Ping timeout: 248 seconds).
16:48:10 -!- jaboja has joined.
16:53:00 -!- moony has joined.
16:57:48  My extension to the MMIX simulation has been added into the webpage for MMIX extensions.
16:58:47  Next on the todo list is creating an extension for the webpage for MMIX extensions.
17:07:50 -!- jaboja has quit (Ping timeout: 240 seconds).
17:29:32 -!- jaboja has joined.
17:42:36 -!- propumpkin has joined.
17:45:00 -!- FreeFull has joined.
17:45:20 -!- contrapumpkin has quit (Ping timeout: 248 seconds).
17:47:38 <\oren\> EEEEEECCCCLIIIPSSSEE TODAY
17:49:23  Yes I know
18:02:39 -!- TieSoul has quit (Ping timeout: 255 seconds).
18:04:43  i know. I wont really get to see it ):
18:04:52  not in person
18:12:07 -!- TieSoul has joined.
18:14:14 -!- Phantom_Hoover has joined.
18:25:40 -!- zseri has joined.
18:26:20  hi
18:26:27  hi
18:26:43  `relcome zseri 
18:26:45  ​zseri: Welcome to the international hub for esoteric programming language design and deployment! For more information, check out our wiki: . (For the other kind of esoterica, try #esoteric on EFnet or DALnet.)
18:32:49 -!- hppavilion[1] has joined.
18:51:26 -!- imode has joined.
18:55:54 <\oren\> right now it looks like someone took a bite out of the sun
19:10:08 -!- FreeFull has quit (Quit: Rebooting).
19:17:19 -!- FreeFull has joined.
19:22:26 <\oren\> http://imgur.com/ncZlg6u
19:22:47 <\oren\> pools of light thru my grapevine are crescent shaped!
19:34:59  yay! I'm not the only one!
19:43:42  yay!
19:44:19  `yay
19:44:20  ​/home/hackbot/hackbot.hg/multibot_cmds/lib/limits: line 5: exec: yay: not found
19:44:29  we need a `yay command right now.
19:56:16  yes
20:12:47  `nay
20:12:48  ​/home/hackbot/hackbot.hg/multibot_cmds/lib/limits: line 5: exec: nay: not found
20:13:09  `pay
20:13:10  ​/home/hackbot/hackbot.hg/multibot_cmds/lib/limits: line 5: exec: pay: not found
20:13:21  `may
20:13:22  ​/home/hackbot/hackbot.hg/multibot_cmds/lib/limits: line 5: exec: may: not found
20:38:11  it was reallly cool
20:38:30 -!- imode has quit (Ping timeout: 240 seconds).
20:38:40  all the birds flew to their sleeping tree and then two minutes later they fleww out again
20:39:00  and the sealions barked more at eachother
20:39:21  "hey get out of my sun" "no you get out of my sun"
20:43:30  [wiki] [[Special:Log/newusers]] create  * OliverB *  New user account
20:58:15 -!- hppavilion[0] has joined.
21:02:07 -!- hppavilion[1] has quit (Ping timeout: 248 seconds).
21:02:25 -!- hppavilion[1] has joined.
21:02:41 -!- hppavilion[0] has quit (Ping timeout: 248 seconds).
21:08:53  heh
21:09:43 -!- augur has joined.
21:13:21 -!- zseri has quit (Quit: Page closed).
21:21:48 -!- wob_jonas has joined.
21:23:19  “Your password must be at least 8 characters long, cannot be the same as your login name, must have lowercase and uppercase letters and at least two digits, and it can't contain the "@" character.”  Stop with these random different arbitrary restrictions on password formats already!
21:23:51  "can't contain @"
21:23:52  why
21:23:53  what
21:23:59  no idea
21:24:02  `quote @
21:24:03  80)   fungot!*@* added to ignore list.   AnMaster: i'd find that a bit annoying to wait for an ack. \ 226)  lol @ closed character set standard   "What does this codepoint represent?" "Nobody knows." \ 446)  sllide: @ is an OS made out of only the finest vapour \ 494)  monqy: help how do I us
21:24:04  how does that restriction make any semblance of sense
21:24:30  perhaps passwords with @ break the system, and the system is just horribly implemented
21:24:53  but it's at least better if they tell that in advance than if I get a random error message with no explanation for why it doesn't like your password
21:25:03  true
21:25:21  I saw a screenshot recently where "Your password is already taken."
21:25:39  They probably don't break the system because they check that the character isn't there and fail early. It's probably backslashes or apostrophes that break their system, if anything.
21:26:24  Oh, it also says the password cannot contain accented letters.
21:26:31  I forgot that part.
21:26:37  I sure love arbitrary password restrictions
21:26:40  Can it contain emoji?
21:26:55  rdococ: no idea
21:27:15  I'm still upset over the fact that "£" is not in ASCII.
21:27:24  really the only restrictions in there that make sense are "at least 8 characters long and not identical to username"
21:28:03  is the euro sign in ASCII? don't think so right
21:28:12  wait
21:28:14  definitely not
21:28:26  did the euro even exist when ASCII was made
21:29:06  Anyone here planning to go to ICFP this year?
21:29:06  it didn't
21:29:15  what's ICFP?
21:29:25  oh I see
21:30:05  well, especially considering I just learned about ICFP, no.
21:30:14  I'm not planning to
21:30:28  Ha, fair enough :)
21:30:32  TieSoul: you can look this up if you don't know ASCII by heart.  The printable ASCII characters are exactly  !"#$%&'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\]^_`abcdefghijklmnopqrstuvwxyz{|}~
21:31:03  I mean, I deduced it from the fact that the Euro didn't even exist when ASCII was created
21:31:46  The reason £ isn't ASCII is the A stands for American
21:31:47  that's not even the Euro
21:31:50  rdococ: I mean the 'A' of ASCII is probably-- yeah
21:31:53  it's british pound
21:31:57  I know
21:32:11  I wasn't talking about the pound sign at all
21:32:24  A bigger mystery is why £ is not on my keyboard layout
21:32:30  the euro thing was just an aside
21:32:43  TieSoul: that's not really an argument. The characters ^`~\ also barely existed when ASCII was created, the first three of them exist as overprint characters you put into printer heads so you can add accents to characters by backspacing, the fourth one is basically just invented, although it's a simple enough shape that you can find prior uses if y
21:32:43  ou really want to
21:33:25  And while @ existed, it was sort of barely used before ASCII, and gained popularity because of ascii, together with those four characters
21:34:17  @ in its current use is kind of weird since it's an abbreviation of a two-letter word, and not very useful
21:34:24  but I believe it was originally something else
21:34:44  but once these were in ascii and a lot of ASCII printers were made, people started using them for all sorts of computing things
21:34:45  "at a rate of" originally
21:35:16  yeah, makes sense
21:35:16  Like, 10 bananas @ 50p = £5
21:35:42  Taneb: wait what? that was _after_ decimization?
21:36:06  but it'd be a stretch to argue that € could be in ASCII because "they made it up before the euro existed"
21:36:09  wob_jonas, no, I made that example up
21:40:03 -!- TieSoul has quit (Quit: Leaving).
21:42:26  ok, completely offtopic here, but trump decided he'd look at the eclipse without protection. https://twitter.com/stefanmymind/status/899704177437421568
21:43:09 -!- sleffy has joined.
21:48:25  Interesting, apparently there's several ideas proposed as to how ‘@’ developed, and not at all clear-cut
21:48:30  https://en.wikipedia.org/wiki/At_sign#Theories_of_origin
21:49:05  FireFly: maybe, but in any case it did exist before ASCII
21:53:14  I like how diverse different languages' vocabulary for @ is
21:54:08  FireFly: the # sign is even worse. nobody knows how to call it, not even by a long name.
21:54:18  Hehe
21:54:30  I think ‘hash sign’ is neutral/widespread enough
21:54:31  (There's also some trouble with \ and | characters, but less.)
21:54:51  It's a wafer!
21:58:28  Pound sign, number sign, octothorpe, sharp...
21:58:29  In swedish I'd use "galler" (lit. bars/grid/fence/…), but "brädgård" (lumber yard) is pretty common too
21:59:44  for @ there's a lot of options… the most common one would be "snabel-a" (elephant's-trunk a), but "kanelbulle" (cinnamon bun) is pretty common too
21:59:48  or just an english "at"
22:22:42  wait are you saying swedes actually call a # a lumberyard
22:23:13  The Hebrew word for # is "sulamit"
22:23:19  Which means something like "small ladder"
22:25:15  in Hungarian, the # character used to be called "andráskereszt" for some reason, even though that name makes no sense. These days it's usually called "kereszt", which is not much better, because × is also called "kereszt". There are informal names like fence or wafer which actually work better but are rarely used.
22:25:31  Oh, also it's often called "kettőskereszt" which is actually a good name.
22:34:20  Or at least I always thought that was the etymology
22:35:01  According to https://www.nordicnames.de/wiki/Sulamit "Sulamit" is a Finnish and Swedish name with a different Hebrew etymology.
22:41:14 -!- moony has quit (Remote host closed the connection).
22:50:28 -!- AnotherTest has quit (Ping timeout: 240 seconds).
22:53:51  I'm making tea. Who wants tea?
22:54:35 -!- Melvar has quit (Ping timeout: 240 seconds).
22:54:41 -!- idris-bot has quit (Ping timeout: 240 seconds).
22:55:01 -!- Melvar has joined.
22:55:40 -!- idris-bot has joined.
23:00:07 -!- `^_^v has quit (Quit: This computer has gone to sleep).
23:00:42 -!- boily has joined.
23:05:21 -!- sleffy has quit (Ping timeout: 248 seconds).
23:09:06 -!- Phantom_Hoover has quit (Read error: Connection reset by peer).
23:10:54 -!- moony has joined.
23:12:54 -!- augur has quit (Quit: Leaving...).
23:20:46 -!- hppavilion[0] has joined.
23:24:01 -!- hppavilion[1] has quit (Ping timeout: 248 seconds).
23:25:23 -!- hppavilion[1] has joined.
23:27:11 -!- sleffy has joined.
23:28:21 -!- hppavilion[0] has quit (Ping timeout: 240 seconds).
23:29:06 -!- hppavilion[0] has joined.
23:32:57 -!- hppavilion[1] has quit (Ping timeout: 240 seconds).
23:33:19 -!- hppavilion[1] has joined.
23:34:41 -!- hppavilion[0] has quit (Ping timeout: 240 seconds).
23:34:43 -!- doesthiswork has quit (Ping timeout: 255 seconds).
23:35:29 -!- hppavilion[0] has joined.
23:36:17 -!- moonythedwarf has joined.
23:36:57 -!- moony has quit (Ping timeout: 240 seconds).
23:38:55 -!- hppavilion[1] has quit (Ping timeout: 248 seconds).
23:42:40 -!- hppavilion[0] has quit (Ping timeout: 248 seconds).
23:42:40 -!- augur has joined.
23:52:10 -!- doesthiswork has joined.
23:59:59 -!- jaboja has quit (Remote host closed the connection).

2017-08-22:

00:00:48  https://icfpcontest2017.github.io/post/lightning-one/ -- status update about judging the ICFP contest 2017, somewhat disappointing because they're still very early in the process
00:04:43 -!- boily has quit (Quit: CHARGED CHICKEN).
00:05:00 * rdococ has quit (Quit: TASTY CHICKEN)
00:09:17 -!- Warrigal_ has joined.
00:54:10 -!- jaboja has joined.
00:55:34 -!- imode has joined.
00:57:06 -!- Antoxyde_ has quit (Quit: Leaving).
01:04:33 -!- wob_jonas has quit (Quit: http://www.kiwiirc.com/ - A hand crafted IRC client).
01:08:28 -!- oerjan has joined.
01:21:21 -!- sleffy has quit (Ping timeout: 248 seconds).
01:58:09  [wiki] [[(0)]] N https://esolangs.org/w/index.php?oldid=52887 * B jonas * (+6867) Created page with "'''(0)''' is a family of programming languages by [[David Madore]] defined in the 2017-08 blog entry [http://www.madore.org/~david/weblog/d.2017-08-18.2460.html Un peu de prog..."
02:00:10  [wiki] [[Language list]]  https://esolangs.org/w/index.php?diff=52888&oldid=52886 * B jonas * (+10) Add (0), also fix some of the asciibetisation
02:01:15  [wiki] [[David Madore]]  https://esolangs.org/w/index.php?diff=52889&oldid=52878 * B jonas * (-73) 
02:02:00  this is a super nomicy act: https://www.ontario.ca/laws/statute/06l21?search=leap#BK0
02:02:16  " If a provision conferring power on a person or entity to make a regulation is amended, or repealed and replaced, so as to confer the power or substantially the same power on a different person or entity, the second person or entity has power to revoke, amend or replace the regulation made by the first one. "
02:03:56  was this enacted after an ex-president complaining to the new one "dude, stop undoing what I did"
02:05:03 -!- LKoen has quit (Quit: “It’s only logical. First you learn to talk, then you learn to think. Too bad it’s not the other way round.”).
02:05:12 -!- wob_jonas has joined.
02:05:55  I hope this time I didn't accidentally create an esolang that's substantially different from the one David described. That was an embarrassing although interesting error.
02:07:18 -!- wob_jonas has quit (Client Quit).
02:08:25 -!- oerjan has set topic: Welcome to the international hub for esoteric programming language design and deployment! | http://esolangs.org | logs: http://codu.org/logs/_esoteric/ http://tunes.org/~nef/logs/esoteric/?C=M;O=D | https://www.dropbox.com/s/fyhqyvy3i8oh25m/wisdom.pdf.
02:08:55  the ICFP contest is, like, over.
02:43:37 -!- moonythedwarf has changed nick to sidy.
02:45:05 -!- sidy has changed nick to moony.
02:46:42  [wiki] [[Special:Log/newusers]] create  * UtilityHotbar *  New user account
02:51:03  [wiki] [[Esolang:Introduce yourself]]  https://esolangs.org/w/index.php?diff=52890&oldid=52837 * UtilityHotbar * (+181) /* Introductions */
02:53:50 -!- moony has changed nick to sidy.
02:54:09  oerjan: How come no olist today?
02:54:09 -!- sidy has changed nick to moony.
03:00:27 -!- ATMunn has quit (Quit: See ya! o/).
03:00:29  shachaf: the olist has been eclipsed hth
03:02:23  another totally human new user, i see
03:14:24 -!- moony has quit (Ping timeout: 248 seconds).
03:15:21  `? rdocco
03:15:23  Rdocco Coffee is a well-known brand of coffee in Universe M-7, and does not contain a highly lethal substance engineered to cause bullet time and addiction.
03:15:34  `forget rdocco
03:15:35  Forget what?
03:16:12 -!- sleffy has joined.
03:23:02  @tell TieSoul  how does that restriction make any semblance of sense <-- random guess: they want to make sure people don't use their email as password.
03:23:02  Consider it noted.
03:28:53  `hurl
03:28:53  https://hackego.esolangs.org/fshg/
04:25:02  [wiki] [[B1nary]] N https://esolangs.org/w/index.php?oldid=52891 * UtilityHotbar * (+4263) Created page with "==B1NARY== *No Hello world program available* B1nary is a language developed while UtilityHotbar was attempting to create a tally/prediction machine for use as an example intr..."
04:26:45  [wiki] [[B1nary]]  https://esolangs.org/w/index.php?diff=52892&oldid=52891 * UtilityHotbar * (+40) 
04:28:00  [wiki] [[B1nary]]  https://esolangs.org/w/index.php?diff=52893&oldid=52892 * UtilityHotbar * (+48) 
04:28:01  `? kerbal
04:28:02  kerbal? ¯\(°​_o)/¯
04:28:15  `? space
04:28:16  Humans come from space. In particular, the part of space that has Earth in it.
04:29:38  [wiki] [[B1nary]]  https://esolangs.org/w/index.php?diff=52894&oldid=52893 * UtilityHotbar * (+86) 
04:31:17  [wiki] [[B1nary]]  https://esolangs.org/w/index.php?diff=52895&oldid=52894 * UtilityHotbar * (+35) 
04:31:46  [wiki] [[B1nary]]  https://esolangs.org/w/index.php?diff=52896&oldid=52895 * UtilityHotbar * (+9) /* Introduction */
04:32:11  [wiki] [[B1nary]]  https://esolangs.org/w/index.php?diff=52897&oldid=52896 * UtilityHotbar * (-34) /* B1NARY */
04:32:31  [wiki] [[B1nary]]  https://esolangs.org/w/index.php?diff=52898&oldid=52897 * UtilityHotbar * (+1) /* Introduction */
04:33:22  [wiki] [[B1nary]]  https://esolangs.org/w/index.php?diff=52899&oldid=52898 * UtilityHotbar * (+2) /* Output */
04:33:54  [wiki] [[Language list]]  https://esolangs.org/w/index.php?diff=52900&oldid=52888 * UtilityHotbar * (+13) /* B */
04:35:05  `? program
04:35:06  A program is an image created by means of prography.
04:35:13  [wiki] [[B1nary]]  https://esolangs.org/w/index.php?diff=52901&oldid=52899 * UtilityHotbar * (+2) /* B1NARY */
04:35:52  [wiki] [[B1nary]]  https://esolangs.org/w/index.php?diff=52902&oldid=52901 * UtilityHotbar * (+9) /* Introduction */
04:36:26  [wiki] [[B1nary]]  https://esolangs.org/w/index.php?diff=52903&oldid=52902 * UtilityHotbar * (+48) /* B1NARY */
04:37:28  [wiki] [[B1nary]]  https://esolangs.org/w/index.php?diff=52904&oldid=52903 * UtilityHotbar * (+16) /* Output */
04:39:40  [wiki] [[B1nary]]  https://esolangs.org/w/index.php?diff=52905&oldid=52904 * UtilityHotbar * (+254) /* Counter manipulation and the trash function */
04:39:58  [wiki] [[B1nary]]  https://esolangs.org/w/index.php?diff=52906&oldid=52905 * UtilityHotbar * (+3) /* Counter manipulation and the trash function */
04:43:01  [wiki] [[B1nary]]  https://esolangs.org/w/index.php?diff=52907&oldid=52906 * UtilityHotbar * (+10) /* == */
04:43:49  [wiki] [[B1nary]]  https://esolangs.org/w/index.php?diff=52908&oldid=52907 * UtilityHotbar * (+44) /* Basic commands: */
04:44:04  [wiki] [[B1nary]]  https://esolangs.org/w/index.php?diff=52909&oldid=52908 * UtilityHotbar * (+4) /* Conditions */
04:45:07  [wiki] [[B1nary]]  https://esolangs.org/w/index.php?diff=52910&oldid=52909 * UtilityHotbar * (+17) /* Syntax and Commands */
04:55:14  [wiki] [[B1nary]]  https://esolangs.org/w/index.php?diff=52911&oldid=52910 * UtilityHotbar * (+9631) 
04:56:01  [wiki] [[B1nary]]  https://esolangs.org/w/index.php?diff=52912&oldid=52911 * UtilityHotbar * (-32) /* Interpreters: */
04:58:09  [wiki] [[B1nary]]  https://esolangs.org/w/index.php?diff=52913&oldid=52912 * UtilityHotbar * (-75) /* Interpreters: */
05:01:44  [wiki] [[B1nary]]  https://esolangs.org/w/index.php?diff=52914&oldid=52913 * UtilityHotbar * (+0) /* Interpreters: */
05:05:43 -!- MrBismuth has joined.
05:06:43  `? oerjan
05:06:44  Your omnipheasant back principal swatty arrant "Darth Ept" oerjan the indecisive is a hazy expert in minor compaction. Also a Glaneep who disses Roald Dahl. He could never render the word "amortized" so he put it here for connivance. His ark-nemesis is Noah. He thrice punned without noticing it.
05:06:48  oerjan: What was the third pun?
05:06:59  `? password
05:07:00  ask boily
05:07:00  The password of the word is unacceptably delayed
05:07:07  wat
05:07:15  `dowg password
05:07:22  11155:2017-08-16  learn The password of the word is unacceptably delayed \ 11081:2017-07-11  learn The password of the month is blowin\' in the wind. \ 10981:2017-06-02  revert \ 10980:2017-06-02  revert \ 10979:2017-06-02  learn The password of the month is out of date tdnh \ 10898:2017-05-14  `slwd password//s, word, month,
05:07:40  password//The password of the month is unacceptably delayed
05:08:13  was that a pun? if so i didn't notice it.
05:08:25 -!- MrBusiness has quit (Ping timeout: 246 seconds).
05:08:29  (i think he meant something else though)
05:09:06  [wiki] [[User:UtilityHotbar]] N https://esolangs.org/w/index.php?oldid=52915 * UtilityHotbar * (+102) Created page with "Random guy, came through to add my experimental half-baked esolang to the mix. See here --> [[B1nary]]"
05:09:22 -!- aloril has quit (Ping timeout: 240 seconds).
05:34:25  [wiki] [[B1nary]]  https://esolangs.org/w/index.php?diff=52916&oldid=52914 * UtilityHotbar * (+17) /* Counter manipulation and the trash function */
05:37:30  [wiki] [[Esolang:Introduce yourself]]  https://esolangs.org/w/index.php?diff=52917&oldid=52890 * UtilityHotbar * (+218) /* Introductions */
05:39:04 -!- oerjan has quit (Quit: Nite).
05:42:46 -!- jaboja has quit (Remote host closed the connection).
05:55:54 -!- aloril has joined.
06:02:02 -!- augur has quit (Remote host closed the connection).
06:04:00 -!- Guest13707 has joined.
06:04:00 -!- Guest13707 has quit (Remote host closed the connection).
06:30:10 -!- augur has joined.
06:38:46 -!- erkin has joined.
06:44:01 -!- sleffy has quit (Ping timeout: 248 seconds).
06:44:30 -!- imode has quit (Ping timeout: 255 seconds).
06:45:22 -!- sleffy has joined.
06:50:18 -!- doesthiswork has quit (Quit: Leaving.).
07:01:40 -!- FreeFull has quit.
08:03:29 -!- sleffy has quit (Ping timeout: 248 seconds).
08:08:10 -!- sleffy has joined.
09:05:35 -!- Antoxyde has joined.
09:11:38 -!- augur has quit (Remote host closed the connection).
09:19:06 -!- mroman has joined.
09:54:04 -!- augur has joined.
09:54:07 -!- mertyildiran has joined.
09:56:42  Hi, I have created this program (https://github.com/DragonComputer/Swarm/blob/master/swarm.py) which is an interpreter for an esoteric language that I designed to be able to support random program generation.
09:58:16  Language's state is currently draft and it consists of 360 (which can be change in the future) atomic instructions.
09:59:26  This file contains a self-replicating program (https://github.com/DragonComputer/Swarm/blob/master/replicate.code)
10:02:10  My purpose was designing a logic to provide evolutionary improvements over the generated programs. But I'm failing to get a successful result. There are two main problems here;
10:03:10 -!- AnotherTest has joined.
10:03:25  1 - Generated random programs are too random and useless that it seems like they will never be able to reach to a useful state.
10:06:35  2 - I was planing the use threading to provide a competitive ecosystem for the programs that the goal is the program with the most system resource consumption is the program that be able to replicate itself most.
10:08:00  But seems like operating system's max thread limit is an issue and the logic of my program for generating a competitive environment is failing.
10:10:00  Could someone desire to collaborate in such an idea like combining automatic program generation and evolutionary algorithms? Because I desperately need help :/
10:12:43  http://codepad.org/nrx1ufya
10:12:44  muahahah!
10:14:15 -!- augur has quit (Remote host closed the connection).
10:14:18  you can try to use it by `python swarm.py` command it will generate random programs on the same directory.
10:14:52 -!- augur has joined.
10:17:59  http://codepad.org/p96yiH4x
10:18:04  now nobody can out bfderivative me
10:19:07 -!- augur has quit (Ping timeout: 255 seconds).
10:24:41  http://codepad.org/Fd2NsMyX
10:28:12  oh there's a bug
10:43:44  http://codepad.org/kANZH82k
10:43:50  ok now cellptr ops in it
10:53:26  mertyildiran: I tried to do what you're doing
10:53:28  but the problem is
10:53:40  "local optima"
10:53:58  for example let's say you want to write a program that can NOT a binary digit 1 -> 0, 0 -> 1
10:54:08  a program that produces 0 for all inputs will be "fairly" good
10:54:13  mroman: it's not even optimizing a little bit. Its state is far from machine learning.
10:54:36  and every change to the const 0 program will temporarily make it worse
10:54:44  so you'll never end up with a better program through random mutations alone
10:54:51  mroman: did you run the swarm.py file?
10:54:56  no
10:55:12  thus proving that creationists were correct in saying the eye is too complex to have evolved .
10:55:14  :D
10:55:17  OK try to run then you will see the result on your terminal.
10:56:20  what does it even do?
10:56:45  mroman: creates random programs and run them.
10:56:54  and what's the point in that?
10:57:03  mroman: you have a linux based system right?
10:57:06  yes
10:57:14  mroman: OK then you can try.
10:57:37  mroman: the point is creating a general purpose program generation.
10:58:06  for what?
10:58:18  mroman: there is no practical purpose
10:59:01 -!- sleffy has quit (Ping timeout: 240 seconds).
10:59:27  mroman: look there are 2 main problems. I have a solution for the first one.
11:01:03  mroman: I will create a statistical data from top 10 best Python projects to find out the frequency distribution of the Python keywords and standard libraries.
11:02:04  mroman: and generate instructions according to that distribution data. For example print 0.08, if 0.05, while 0.03 etc.
11:02:30  mroman: so that the program will not be too random.
11:02:42  mroman: but for second problem I have no solution.
11:02:56  mroman: I'm simply unable to create a competitive environment.
11:03:17  mroman: operating system and some low level implementations are blocking my way.
11:03:57  mroman: also the overall logic is not certain in my mind.
11:06:15  mroman: I mean how we can define success and failure for a computer program? I tried to use "if there is an error in the program then it's a failure and don't replicate itself" but the error rate is too high that no program is able to survive.
11:15:16 -!- zseri has joined.
11:27:28  hello, fellow members of homo sapiens! I have not been abducted and replaced with an exact replica of myself whose job is to act, look, and even think like me while being under the control of evil aliens!......wait.
11:28:11  rdococ: as long as you act and think the same, nobody's gonna care.
11:28:59  good, because that means the non-existent aliens will not be unable to carry out their plan of enslaving humanity! not mw not ha not ha!
11:31:27  rdococ: hi, my name is John Titor and I'm not a time traveller just an ordinary person. Nice meet with a non-alien person.
11:31:45  *Nice to meet...
11:32:27  heh
11:33:37  Concept: a goto system that supports implicit longjmp without having to declare that you want to jump longly
11:33:46  so sort of like continuations, I guess?
11:34:25 -!- boily has joined.
11:34:30  hi boily.
11:34:57  really, the way I could see something like that working is a construct that declares a global variable set to the continuation of a block, and then executes that block
11:35:15  e.g. { stuffBeforeLabel } label abc; stuffAfterLabel;
11:35:26  abc would be defined as the continuation as stuffBeforeLabel.
11:36:05  which would, coincidentally, transfer control flow to the beginning of stuffAfterLabel.
11:41:12  Somebody has Capgras?
11:45:36  hm.
11:46:40  rdochelloc, mrelloman.
11:51:40  hello.
11:51:43  Heya
11:51:47  boily detected.
11:52:43  concept: functions which have access to not only their continuations, but... well... it's hard to explain, but it's the opposite of a continuation :P
11:53:13  so they have access to their continuation (continues execution) and their, well, history...?
11:55:04  i DID IT
11:55:05  I think.
11:55:09 -!- mertyildiran has quit (Ping timeout: 260 seconds).
11:55:33  http://codepad.org/Vxk0UKmP <- this oughta work to emulate a 4bit flip flop
11:55:36  well
11:55:43  4x 1 bit flip flops
11:55:51  that are addressable
11:57:23  ah fuck
11:57:23  no
11:57:31  nah forget it
11:57:39  this just allows you to store cell[adr] = adr
11:59:08 -!- ^v has quit (Ping timeout: 240 seconds).
12:00:48 -!- AnotherTest has quit (Ping timeout: 248 seconds).
12:00:48 -!- catern has quit (Ping timeout: 248 seconds).
12:00:57 -!- AnotherTest has joined.
12:01:52 -!- olsner has quit (Ping timeout: 248 seconds).
12:04:17 -!- ^v has joined.
12:05:06 -!- catern has joined.
12:06:06 -!- FireFly has quit (Quit: Goodbye).
12:06:51 -!- olsner has joined.
12:11:49 -!- FireFly has joined.
12:22:41 -!- mertyildiran has joined.
12:23:23  Did anyone write an answer to my questions?
12:28:55  which one?
12:29:59 -!- boily has quit (Quit: COMPACT CHICKEN).
12:31:30  success or failure of a program
12:31:36  do you have an expected output?
12:31:44  then you calculate the derivation from the output
12:33:07 -!- mroman_ has joined.
12:33:18  for random programs...
12:33:19  well
12:33:24  some of them might not even terminate
12:33:24  so
12:33:33  and you never know whether they will terminate or run forever
12:33:43  so that depends on what you consider success
12:36:34 -!- mroman has quit (Ping timeout: 260 seconds).
12:41:09  and yes, forking a lot of threads will fuck up the OS scheduling
12:41:10  and resources
12:41:49  also python internal threads are only useful for I/O heavy things afaik
12:42:00  because executing python byte code takes a global lock
12:42:20  so unless you have threads waiting for I/O there's pretty much no benifit in having multiple threads afaik
12:43:48  mroman_: in nature lack of resources cause the elimination. Organism with better DNA survives. Computers have also limited resources. How do we implement the same logic with nature's?
12:45:22  uhm...
12:45:26  I think the rules of operating system is the main problem here.
12:45:37  if you want to "create" "animals"
12:45:44  then you need to have some environment
12:45:48  that you put programs in
12:45:52  in which they can move around and gather food
12:45:54  otherwise
12:45:57  what's the point?
12:46:27  organism with better DNA survives because they are fitter for a purpose
12:46:33  but what is YOUR purpose?
12:46:38  Sure CPython is not a good choice for parallelism but I was looking a completely error free language.
12:46:53  A program that runs long? Then while 1: is the best program anyway
12:47:11  ---> very boring
12:47:44  you might be interested in CoreWars
12:47:46  or BF Joust
12:47:54  programs compete against each other
12:48:14  this way you can evolve programs by letting them fight against each other and take the winner
12:48:23  mutate the winner into 10 new programs and then see if one of thes performs even better
12:48:42  but you need a heuristic function to determine which program is better than another
12:48:56  (which in core wars is how many other programs it can beat)
12:49:19  i.e. if you want to find the fastest brainfuck program to compute 100
12:49:57  then your heuristic function will depend on the amount of cycles it used and how far it is of off producing the number 100
12:50:18  then you create 10 random initial programs, mutate each into 10, run them each and then pick the top 10 of those and repeat
12:50:30  or you use a more genetic approach where you "combine" programs into each other
12:51:28  i.e. instead of creating 100 random version of the top 10 you "breed" these top 10 among each other and then run those
12:52:13  trivially something like while j < len(...): new_dna = dna_parent_a[j] if rand(0,1) == 0 else dna_parent_b[j]
12:52:36  so the new dna is a mix of the two parents dna
12:52:46  not very sufficient
12:52:52  *clever
12:53:05  in practice i think they slice whole regions and also cut/add/extend dna
12:53:17  !bftxt_gen
12:53:20  !help
12:53:20  mroman_: I do !zjoust; see http://zem.fi/bfjoust/ for more information.
12:53:23  hm
12:53:27  ^help
12:53:27  ^ ; ^def   ; ^show [command]; lang=bf/ul, code=text/str:N; ^str 0-9 get/set/add [text]; ^style [style]; ^bool
12:53:35  `help
12:53:35  Runs arbitrary code in GNU/Linux. Type "`", or "`run " for full shell commands. "`fetch [] " downloads files. Files saved to $PWD are persistent, and $PWD/bin is in $PATH. $PWD is a mercurial repository, "`revert " can be used to revert to a revision. See http://codu.org/projects/hackbot/fshg/
12:53:38  we have too many bots
12:53:48  `run ls /
12:53:52  bin \ dev \ etc \ hackenv \ home \ lib \ lib64 \ opt \ proc \ sbin \ sys \ tmp \ usr
12:53:55  `run ls /bin
12:53:56  bash \ bunzip2 \ bzcat \ bzcmp \ bzdiff \ bzegrep \ bzexe \ bzfgrep \ bzgrep \ bzip2 \ bzip2recover \ bzless \ bzmore \ cat \ chacl \ chgrp \ chmod \ chown \ cp \ cpio \ dash \ date \ dd \ df \ dir \ dmesg \ dnsdomainname \ domainname \ echo \ ed \ egrep \ false \ fgrep \ findmnt \ fuser \ getfacl \ grep \ gunzip \ gzexe \ gzip \ hostname \ ip \ jo
12:54:08  `run ls opt
12:54:08  ls: cannot access opt: No such file or directory
12:54:13  `run ls /opt /usr/bin
12:54:18  ​/opt: \  \ /usr/bin: \ [ \ 2to3 \ 2to3-2.6 \ 2to3-2.7 \ a2p \ addpart \ addr2line \ aot-compile \ appletviewer \ apropos \ apt \ apt-cache \ apt-cdrom \ apt-config \ apt-extracttemplates \ apt-ftparchive \ apt-get \ aptitude \ aptitude-create-state-bundle \ aptitude-curses \ aptitude-run-state-bundle \ apt-key \ apt-mark \ apt-sortpkgs \ ar \ ar
12:54:30  hm
12:55:08  `genbf moo
12:55:09  fold: invalid number of columns: ‘moo’
12:55:13  `genbf 10
12:55:14  ​,<+,.,>-+>
12:55:23  hm
12:56:20  `döts brainfuck
12:56:21  bräïnfück
12:56:27  right.
12:56:39  mroman_: yeah that's also a good question, an endless loop is the most resource heavy thing. Isn't a window driven program's root level code an endless loop?
12:57:18  depends on the architecture.
12:57:28  if you poll events then yes
12:57:50  if you use some kind of ipc signaling
12:57:52  then not necessarily
12:58:22  an endless busy loop is
12:58:39  but an endless while 1: sleep(100101001980901010191801) is not that resource heavy
12:58:56  mroman_: there is no clear goal in biological evolution so we should define a rule that governs all kind of programs.
12:59:09  there is a clear rule
12:59:14  reproducing and surviving
12:59:20  well "clear"
12:59:39  you want to create programs that replicate themselves?
13:00:14  but gotta catch the train
13:00:15  cya
13:00:28 -!- sebbu has quit (Ping timeout: 240 seconds).
13:01:02  mroman_: reproducing and surviving is not defining the DNA's goal. Environment decides who will survive.
13:01:28  mroman_: yes I'm talking about self-replicating programs. The script I show is also self replicating.
13:05:09 -!- mroman_ has quit (Ping timeout: 260 seconds).
13:09:41  mroman_: what I mean an endless loop with a break in some point is the best kind of program possible so that's not a problem. We can implement max execution time for a program like 1 hour to prevent any true endless loop. The problem is what would be the logic of watchful eye for the evolution...
13:11:19 -!- mertyildiran has quit (Quit: Page closed).
13:17:59 -!- LKoen has joined.
13:38:31 -!- TieSoul has joined.
14:00:30 -!- doesthiswork has joined.
14:07:40 -!- ATMunn has joined.
14:23:07  `unidecode ü
14:23:09  ​[U+00FC LATIN SMALL LETTER U WITH DIAERESIS]
14:36:47 -!- sebbu has joined.
14:37:02 -!- `^_^v has joined.
14:38:14  `genbf 50
14:38:16  ​[,.-,-[>-[<.-,<-[>,-]-],.]<-.[.-.+.,]>]-.--<-<>+,-
14:39:18  that's stupid code
14:40:11  at the very least it shouldn't do -,
14:40:22  or end in -
14:40:25  or <>
14:40:57  can we have a better generator plz?
14:47:11  what does genbf do?
14:49:45  it cooks pizzas
14:51:00  `genbf 100
14:51:02  ​>.<>[+><[+>-.,<,<-<+++]--,<,>[,.,,<<+.[>++,+,.,..[].[]->]-+<>-,[<>><]+,][<+>,--<>+>-,,.-->,+,.<>+]+]
14:51:23  come on,  [].[]
14:52:26  -+<> and -<>+
14:52:31 * izabera is not impressed
14:53:54  best part is that the program will just output one null character
14:54:20  and then stop
15:04:07 -!- doesthiswork has quit (Quit: Leaving.).
15:12:59  heh
15:13:16  idea for `genbf: make it detect and remove redundancies like that
15:14:33  e.g. replace <> and +- with nothing.
15:14:47  yeah
15:15:10  and replace -<>+ with nothing too, along with other redundancies like <-+>
15:15:24 -!- augur has joined.
15:15:57  or, better yet, simulate each piece of potentially redundant code to see how redundant it is
15:16:14  , and . are definitely not redundant, but <+-+--+>+-+--+<> is
15:16:41  although that might not work with while loops
15:19:45 -!- augur has quit (Ping timeout: 248 seconds).
15:24:35  `` type genbf
15:24:37  genbf is /hackenv/bin/genbf
15:24:40  `` pwd
15:24:41  ​/hackenv
15:24:48  `` file bin/genbf
15:24:50  bin/genbf: ASCII text
15:24:57  `` paste bin/genbf
15:24:58  https://hackego.esolangs.org/fshg/index.cgi/file/tip/bin/genbf
15:25:10  ew
15:27:59  sed -n '.... /foo/b;p;q'   ->   sed '.... /foo/d;q'
15:28:10  anyway
15:28:24  what are the odds that a random 50 char string is valid brainfuck?
15:32:36 -!- erkin has quit (Quit: Ouch! Got SIGABRT, dying...).
15:37:20 -!- imode has joined.
15:53:04 -!- jaboja has joined.
16:07:19 -!- TieSoul has quit (Ping timeout: 276 seconds).
16:21:45  [wiki] [[Nil]]  https://esolangs.org/w/index.php?diff=52918&oldid=37987 * AJF * (+43) /* External resources */
16:25:45 -!- pelegreno______ has quit (Read error: Connection reset by peer).
16:26:59 -!- pelegreno has joined.
16:33:21 -!- jaboja has quit (Ping timeout: 240 seconds).
16:39:43  [wiki] [[(0)]]  https://esolangs.org/w/index.php?diff=52919&oldid=52887 * B jonas * (+133) 
16:43:10 -!- jaboja has joined.
16:44:29  (0_0)
16:50:26 -!- FreeFull has joined.
16:54:46 -!- Sgeoweb has joined.
16:54:52  https://twitter.com/hikari_no_yume/status/900013177026609152
17:12:42  Haha
17:12:54 -!- moony has joined.
17:13:50  Moony!
17:13:54  well, there *are* interpreters
17:13:54  How is the universe doing today?
17:14:22  . o O ( still bathing in ~4K background radiation )
17:14:47  uh, no, it's 2.7K
17:15:50  rdococ, depends on what part.
17:16:07  is the Andromeda Galaxy okay?
17:16:39  Well, some of the... Damn i cant even give a prononciation of the species name, are having a all-out war. 
17:16:50  Ah.
17:30:16 -!- TieSoul has joined.
17:32:08 -!- erkin has joined.
17:38:49  izabera: I think to be valid, just the brackets have to match? Other than that, any unrecognized character is OK but ignored.
17:39:21 <\oren\> I cam up with some numbers that work but I don't know why...
17:40:07 <\oren\> I hope the people who make self-driving cars work in a less haphazerd way
17:40:57  They don't
17:42:07 <\oren\> also boost jam can eat a bag of dicks
17:42:33  zzo38: sure, i was asking about the odds of balanced brackets
17:42:51 <\oren\> it isn't better than our build system, it just has different problems
17:54:03  moony: I think you're talking about the K'thlh'an and the Þ'eßđ'tħŋen species?
18:02:25  rdococ, no... maybe.
18:12:25 -!- imode has quit (Ping timeout: 246 seconds).
18:16:17  hm. how are the P'þan'eæß ðø's getting along?
18:16:29  [ Insert Sudden Microwave Ping! ]
18:16:29  rdococ: Insert (Sudden Microwave Ping ! ])
18:16:50  Oop! Looks like my universe has compiled! I'll see you soon.
18:17:14 * rdococ runs the universe.......and immediately runs into runtime errors. "...Shit."
18:23:26  `olist 1093
18:23:26  olist 1093: shachaf oerjan Sgeo FireFly boily nortti b_jonas
18:27:16 * rdococ recompiles the universe, but then runs into compile-time errors.
18:27:39 * rdococ attempts to fix the errors, but then gets pre-compiletime-errors.
18:28:00  can you recompile yourself into another channel or something
18:30:26 <\oren\> shachaf: what do u think of neural networks
18:30:49  \oren\: Neurons are pretty neat. I don't really know much about them.
18:30:56  Brains are very complicated.
18:31:14 -!- Sgeoweb has quit (Ping timeout: 260 seconds).
18:38:58 -!- Phantom_Hoover has joined.
18:38:58 -!- Phantom_Hoover has quit (Changing host).
18:38:58 -!- Phantom_Hoover has joined.
18:41:53 -!- kurolox has joined.
18:42:08  Uh, hello
18:42:15  `relcome kurolox 
18:42:16  ​kurolox: Welcome to the international hub for esoteric programming language design and deployment! For more information, check out our wiki: . (For the other kind of esoterica, try #esoteric on EFnet or DALnet.)
18:42:58  I'm not sure if this is the right place to ask, but someone else pointed me here. I have a python bot that runs arbitrary code, and I was looking into a way to sandboxing it to make it relatively safe to use. I've been pointed to UMLBox, but I'm having some issues trying to set it up.
18:44:26  `welcome kurolox
18:44:27  kurolox: Welcome to the international hub for esoteric programming language design and deployment! For more information, check out our wiki: . (For the other kind of esoterica, try #esoteric on EFnet or DALnet.)
18:44:36  `version
18:44:36  ​/home/hackbot/hackbot.hg/multibot_cmds/lib/limits: line 5: exec: version: not found
18:44:44  `` uname -a
18:44:45  Linux umlbox 3.13.0-umlbox #1 Wed Jan 29 12:56:45 UTC 2014 x86_64 GNU/Linux
18:45:39  kurolox: unfortunately I have no first-hand experience with this. Gregor is the author of umlbox but usually busy with professing and family. fizzie may be your best bet.
18:47:41  I understand. I'll throw him a private chat and see if he can help me. Unfortunately there's not a lot of documentation out there about UMLBox setup. Thanks!
18:48:04  gregor has a family?
18:50:11  TBH I don't know :P
18:50:21  But what else would he spend all this time on?
18:50:36  Most people have families.
18:50:44  I think it's required in order to be born.
18:50:45  not updating UMLBox, thats for certain
18:58:57  Well, fizzie doesn't seem to be around so I'll leave my specific question here. I'm trying to use linux 3.16.46, so besides extracting that kernel in a folder with the same name inside umlbox files, and editing the makefile to match the version, do I need to do anything else before doing make and install?
18:59:18  it seems like I'm doing something wrong because after that UMLBox complains about the lack of a UML kernel
19:08:35  Hurray! i made linux 4.12.8 work as UMLBox-kernel
19:11:31 -!- sleffy has joined.
19:15:49 -!- augur has joined.
19:16:42 -!- augur has quit (Remote host closed the connection).
19:17:39 -!- augur has joined.
19:34:47 -!- moony_ has joined.
19:35:14 -!- Phantom_Hoover has quit (Ping timeout: 255 seconds).
19:36:28 -!- lambdabot has quit (Remote host closed the connection).
19:36:40 -!- moony has quit (Quit: Leaving).
19:36:40 -!- moony_ has changed nick to moony.
19:37:09 -!- moony has changed nick to Guest76625.
19:38:56 -!- lambdabot has joined.
19:39:56 -!- Guest76625 has changed nick to moonythedwarf.
19:40:22 -!- moonythedwarf has quit (Changing host).
19:40:22 -!- moonythedwarf has joined.
19:57:06 -!- erkin has quit (Quit: Ouch! Got SIGABRT, dying...).
20:06:12 -!- jaboja has quit (Remote host closed the connection).
20:10:26 -!- jaboja has joined.
20:24:14 -!- Antoxyde_ has joined.
20:27:04 -!- Antoxyde has quit (Ping timeout: 255 seconds).
20:33:02 <\oren\> I use the untitled.js framework. it's 0 bytes minified
20:45:15  cool
20:51:04  well, my sj.deltitnu framework is -11 bytes minimized.
20:51:18  s/minimized/minified
20:52:26 -!- moonythedwarf has changed nick to moonmoon.
20:52:33 -!- moonmoon has quit (Disconnected by services).
20:52:55 -!- moony has joined.
20:56:24  How is that?
21:05:51  kurolox: It's been a while since I set it up. The "umlbox" script is just Python, so it's relatively easy to figure out which paths it checks for the kernel. I think the umlbox Makefile might not have worked out for me, I think I did it semi-manually (make ARCH=um in the kernel directory, and then copied the result to "umlbox-linux"), though on paper just "make && make install" in the umlbox directory 
21:05:57  *should* do the trick.
21:10:27 -!- TieSoul has quit (Quit: Leaving).
21:25:04 -!- zseri has quit (Ping timeout: 260 seconds).
21:27:11  Hey Fizzle
21:27:14  Thanks for the answer
21:28:05  unfortunately doing make and make install give me some errors due to umlbox-mudem
21:28:38 -!- kurolox has quit (Remote host closed the connection).
21:29:12 -!- kurolox has joined.
21:29:25  Sorry, hexchat crashed
21:29:34  however, here's the output of make, with the errors I get
21:29:36  https://ghostbin.com/paste/992wk
21:31:01  however I'll do it like you said
21:31:16  kurolox: In the file mudem/tcp4.c, add the line   #define _POSIX_C_SOURCE 201112L /* for getaddrinfo */   after the existing line   #define _POSIX_SOURCE /* for strtok_r */
21:31:33  (At least that's what "hg diff" says I've changed in my local copy.)
21:32:45  That might fix the error Make barfs on. You'll probably also need to install cpio for the command on line 34 of the output to work.
21:33:01  yes, now it builds
21:33:14  well, sort of
21:33:37  it did more than the last time, that's for sure, but now there's another error with the kernel it seems
21:34:01  https://ghostbin.com/paste/xfhap
21:35:14  maybe it's because of the version of the kernel I'm trying to use?
21:35:44  I have a vague notion I might have had to use an older version of GCC to build a 3.x kernel (again, hg diff says I've changed the Makefile to pass "CC=gcc-4.9" to the kernel build step. But I've no idea if the errors you're seeing could be that.
21:36:01 -!- Sgeo has joined.
21:36:21  Hm, should I just use a 4.x kernel?
21:36:52  Honestly I was using 3.16.46 because moony told me that nobody got 4.x to work, but it seems like he did it a few hours ago
21:37:12  I ran into some *other* problems with a modern kernel, but based on his report it's doable.
21:37:18  also, thanks for the help. I haven't thanked you for it.
21:37:27  FWIW the errors you're seeing are probably https://bugs.debian.org/cgi-bin/bugreport.cgi?bug=778157
21:37:36  "Found in version user-mode-linux/3.16-1um-0.1" "Fixed in version user-mode-linux/4.0-1um-0.1"
21:37:47  So, yeah, maybe try 4.x.
21:37:55  If it's painless, maybe I could even update HackEgo one of these days.
21:38:23  Just wondering, which kind of issues have you found in 4.x?
21:39:04  I'll try with 4.12.8, which is the one that moony is using
21:39:09  fizzie, 4.12.8 worked painlessly for me
21:39:33  well, make also worked painlessly for you
21:39:58  MoonyTheDwarf
21:39:58  #3778
21:39:58  botnet
21:39:58  Search
21:39:58  LOAD MORE MESSAGES
21:39:59  [6:13 PM] Kurolox: hm
21:40:02  [6:13 PM] MoonyTheDwarf: thats a issue for a kernel hacker(edited)
21:40:05  err
21:40:06  wtf
21:40:08  discord
21:40:10  y u
21:40:12  sorry
21:40:21  that was amusing
21:40:26  i wanted to copy *one* line
21:40:32  instead it cpies the entire chat history
21:40:42   [8:38 PM] BOTlinbut: @MoonyTheDwarf,
21:40:42   Linux umlbox 4.12.8-umlbox #1 Tue Aug 22 14:03:49 EDT 2017 x86_64 GNU/Linux
21:41:14  now it's building with 4.12.8
21:41:18  or at least it went further than before
21:41:27  I don't remember what problems I have with a 4.x kernel, but it was also a year ago. Maybe the current version just happened to be a bad one for UML.
21:41:33  s/have/had/
21:41:48  It's a bit of a niche thing.
21:42:03  yea, UML is
21:42:05  Well, if I find anything I'll try to report it here
21:42:34  but yeah, more than 10 seconds passed and it haven't stopped yet so I'm calling it a sucess for now
21:43:01  I'll bug moony regarding umlbox usage though, so don't worry about me asking stupid questions here
21:43:07  mk
21:43:43  kurolox, as its going to be a lang sandbox, you wont need a writeable dir. just do 'umlbox -B '
21:44:25  tmp will function as a temporary writable dir inside the sandbox
21:44:31  by default
21:44:39  hm, but the script I want to sandbox creates files in a specific path
21:44:52  I could change it so it writes them to the writable dir though
21:45:25  kurolox, dont put the script inside the sandbox, instead, have it call the sandbox
21:45:37  -B will mount all base mounts, so python will be avaliable
21:49:26  Hey fizzle
21:49:37  remember that thing I told you about not asking you stupid questions because I had moony?
21:49:41  I didn't last even 5 minutes
21:49:48  lol
21:49:58  kernel panic i dont understand. :P
21:49:59  Running anything with UMLBox gives me a kernel panic
21:50:03  https://ghostbin.com/paste/kneej
21:50:28 -!- jaboja has quit (Ping timeout: 246 seconds).
21:55:39 -!- wob_jonas has joined.
21:55:40  `olist 1093
21:55:41  olist 1093: shachaf oerjan Sgeo FireFly boily nortti b_jonas
21:55:54  wob_jonas: already listed hth
21:56:29 -!- augur has quit (Remote host closed the connection).
21:57:26  is it? I thought I checked the logs. sorry.
22:05:35 -!- imode has joined.
22:08:51  fizzie how does UMLBox calls the kernel? It seems like there might be a problem with "ubda" or something like that with me
22:09:15  at least according to http://user-mode-linux.sourceforge.net/problems.html
22:12:20 -!- kurolox has quit (Remote host closed the connection).
22:14:08 -!- kurolox has joined.
22:15:45 -!- Phantom_Hoover has joined.
22:15:45 -!- Phantom_Hoover has quit (Changing host).
22:15:45 -!- Phantom_Hoover has joined.
22:17:23  I thought of to make a new kind of XLFD (for use with making up X version 12). You can still use uld XLFD on the same system, and fonts can have multiple names that refer to the same font.
22:20:00  The new format is ":foundry:name:style:spacing:width:height:charset:subsets"
22:20:01  zzo38: Do you like NeWS?
22:20:09  No, I think X is better
22:20:54  Why?
22:22:31  (Actually we can omit the "spacing" field, I think)
22:24:01  The foundry is optional and can be blank. The style is two characters, the first 0 to 3 indicating bold (1 for normal, 2 for bold, 3 for extra-bold), second is "r" or "i" or "o" for slanting, and either or both of them can be "-" instead if unspecified. The width and height are the character cell width/height, and can be blank if they are variable. The charset is a character set name, such as "ascii", "iso8859-1", "iso10646", etc.
22:25:05  The subsets is a list of subsets of the character set that is implemented, which must be in alphabetical order; each one consists of a dot followed by the name followed by another dot (so there are two dots between each pair), and is a single dot by itself if this field is unused.
22:25:19  zzo38: what does X even have to do with this? aren't we all using user-space fonts rendered as graphics in user space to memory buffers which may or may not be direct mappings of video card memory and the rendering may involve graphics card help?
22:26:15  fonts are resolved by user-space libraries like the combination of pango, fontconfig, freetype, or other user-space libraries like those
22:26:32  It doesn't need X, and is actually independent of it, although it can still be used with the font loading mechanism of X.
22:27:02  and those libraries can even transparently use the same bdf fonts that X used to use
22:27:41  or pcf fonts. whichever is the compiled version.
22:28:40  Furthermore, another feature which actually would be part of my version of X 12, that when loading a font you can optionally specify two flags: EnableLigatures, which permits the server to ignore the requirement that a string of multiple characters is the same as all of those character put together, and EnableAntialiasing, which permits the server to ignore the requirement that the character only consists of on/off pixels in the bounding box.
22:29:38  (The EnableLigatures flag is also needed in order to render astral Unicode characters, since they don't fit in 16-bits.)
22:35:35  However, the protocol request to set the font path is now gone (although some implementations may support a ExtensionControl request to control them), and there is no requirement as to how exactly the server loads and implements the fonts; it is not required to implement EnableLigatures and EnableAntialiasing (and if it doesn't, those flags are just ignored). There is no requirement of storing font names either, so an implementation could make up f
22:42:29  (It is still recommended that at least .pcf is supported, although it is not strictly a requirement anymore.)
22:42:37 -!- jaboja has joined.
22:42:44  Do you like this?
23:02:21 -!- AnotherTest has quit (Ping timeout: 255 seconds).
23:05:53 -!- `^_^v has quit (Quit: This computer has gone to sleep).
23:21:49 -!- imode has quit (Ping timeout: 246 seconds).
23:36:22 -!- wob_jonas has quit (Quit: http://www.kiwiirc.com/ - A hand crafted IRC client).
23:44:56  kurolox: I don't think there's really a one-line answer to that. But it does use an "ubda=..." argument to pass in a "configuration" file (what setup to do and what commands to run) as a virtual block device. The init binary reads the config from there and does what it's told to do.
23:46:53  Has the people other than myself try to think of how to make a (large) computer program that can work even if the cards that the program is punched on are shuffled, for a loading mechanism such as the MIX "Go button" loading mechanism?
23:49:15 -!- LKoen has quit (Quit: “It’s only logical. First you learn to talk, then you learn to think. Too bad it’s not the other way round.”).
23:49:31 -!- Phantom_Hoover has quit (Remote host closed the connection).
23:50:17 -!- oerjan has joined.
23:59:48  fizzie, did some tests. 4.12.8 works without issues for me. I'll be waiting for hackego to get upgraded.

2017-08-23:

00:00:29  `ls /
00:00:30  bin \ dev \ etc \ hackenv \ home \ lib \ lib64 \ opt \ proc \ sbin \ sys \ tmp \ usr
00:02:48  `ls /home
00:02:49  hackbot
00:03:06  `ls /opt
00:03:07  No output.
00:12:43  `! bf_txtgen test
00:12:51  54 +++++++++++++[>+++++++++>++++++++>><<<<-]>-.>---.<-.+. [237]
00:14:05  @tell mroman  !bftxt_gen <-- EgoBot is dead, use `! bf_txtgen for HackEgo's version
00:14:05  Consider it noted.
00:14:19  ^bf  +++++++++++++[>+++++++++>++++++++>><<<<-]>-.>---.<-.+.
00:14:19  test
00:15:59  fizzie don't worry
00:16:16  I've spent the last hour and a half disassembling my old laptop so I can make a server with it
00:16:20  I'll try in a fresh install there
00:16:23  maybe I'm lucky
00:17:02  moony: Don't hold your breath.
00:46:50 -!- augur has joined.
00:47:14 -!- augur has quit (Remote host closed the connection).
00:48:57 -!- augur has joined.
01:16:47 -!- doesthiswork has joined.
01:18:59 -!- Antoxyde_ has quit (Quit: Leaving).
01:26:06   uh, no, it's 2.7K <-- . o O ( int-e reveals his age )
01:27:51 -!- kurolox has quit (Ping timeout: 240 seconds).
01:28:50   Well, some of the... Damn i cant even give a prononciation of the species name, are having a all-out war. <-- obviously, since they don't speak with sound hth
01:29:08  oerjan, duh, right.
01:29:25  linbut shall prevail.  moony: Linux umlbox 4.12.8-umlbox #1 Tue Aug 22 14:03:49 EDT 2017 x86_64 GNU/Linux
01:29:49  just use this handy ultraviolet lamp and paper figures
01:30:33  is this going to be the but of many jokes?
01:33:09  <\oren\> also boost jam can eat a bag of dicks <-- that's a pretty disturbing skill to have.
01:38:59  have you ever had cow cod soup? It's an easy skill to have
01:40:34  i ... hope not.
01:41:43  . o O ( also cows don't have dicks hth )
01:42:08  cow is a hyponym of cow
01:43:29  I you prefer to drink a jar of dicks you can have deer dick wine
01:43:54  (banned from the 2009 olympics)
01:44:02  2008
01:44:31  my brother swapped some keys on  my keyboard which causes trouble when I look at it
01:54:31 -!- sebbu2 has joined.
01:57:28 -!- sebbu has quit (Ping timeout: 240 seconds).
01:59:09  ech`olist
02:07:59 -!- imode has joined.
02:08:21  Then you should put the keys back into the proper places
02:43:20  what a brilliant idea
02:43:30  too bad it requires effort and gumption
02:46:26 -!- Warrigal_ has changed nick to tswett.
02:50:13  . o O ( and i'm all out of gumption )
02:50:37  yeah i don't know how one would kick ass and have gumption anyway
03:01:26 -!- ATMunn has quit (Quit: See ya! o/).
03:30:27  I had idea make up the mahjong with pokemon; before play game you will decide how many generations. There is also wild card, which is by elements, and can only substitute for any card of that element, but no more than one per set (including pair), and cannot make ambiguous chii calling with wild cards. Two kind of sequences are possible, which is numeric sequences and evolution sequences, and some sequences can be both.
03:34:11 -!- jaboja has quit (Remote host closed the connection).
03:43:28 -!- hppavilion[1] has joined.
03:45:48  (If only one generation, then all evolution sequences are also numeric sequences (since a sequence is always three cards), but with more than one generation you can have evolution sequences that aren't numeric sequences.) Also your pair (and only pair) can substitute Ditto for any other card, but only if neither are wild cards.
03:45:51  Do you like this?
03:51:38 -!- wob_jonas has joined.
03:52:01  hmm... I need an ais.
03:52:09  @tell
03:52:09  Who should I tell?
03:52:52 * oerjan puts on ais mask
03:53:25  @tell ais523 Do you happen to know about the paradoxical construction where you have a program with arrays, and you simulate it without arrays by recursive calls to the main program whenever you want to read an array element? Is that construction possible and can you point to some writeup about it?
03:53:25  Consider it noted.
03:53:51  I have never heard of such a thing.
03:55:01  you can simulate a read-only array with a function, but that's not recursion.
03:57:38  It seems paradoxical because you're simulating a RAM machine by a stack machine, which is supposed to be impossible. You're not just stacking a whole array into a single bignum, you only have individual array elements on the stack or registers.
03:58:01  i suppose you can give the main program an extra parameter that says "keep track of this element of this array, and return what's in it at this point in time"
03:58:11  *some extra parameters
03:58:38  It doesn't actually contradict the theory because you need a timer variable to know when to break out of each recursive simulation, that timer variable has to have at least as many values as many times the simulated program reads array elements, and you have such time variables on the stack.
03:58:59  The runtime may blow up exponentially, and the stack may blow up to as big as the simulated runtime.
04:00:25  oerjan: yes, in each level of the simulation, you keep track of the array index, the time when you have to stop, the arguments of the main function, and the current time. Only the last one changes within a simulation level, but you can have lots of nested simulations.
04:01:00  i can see the current time growing exponentially, so you need a bignum for it.
04:01:04  Time means how many times you have read array elements during the simulated program (although it can be more refined than that).
04:01:21  oerjan: no, you only keep track of the time of the original program, it only blows up as much as the runtime of that one.
04:01:49  well ok if you assume the runtime of that cannot be too high...
04:01:51  The runtime of the simulation can blow up exponentially, but a time variable only stores the time in the runtime of the original program.
04:03:06  And you can have at most as many levels of simulation as the original runtime, the new stack can have as many frames as the old stack times the number of nested simulation levels, and there's a constant number of timer variables in each level of the new stack.
04:03:51  Each new stack frame stores only a constant number of array elements (the one corresponding to the index you're interested about), but together the stack may hold a whole array.
04:04:45  I'd like to know either why the whole construction fails, or a reference to existing documentation of this construction, and I hope ais523 can provide it.
04:04:56  okay
04:06:03  oerjan: but yes, in the original program you might only need integers as large as the size of arrays (you can imagine this as 16-bit or 32-bit integers if you wish), while the timers may need larger integers (if runtime is more than about 2**16 or 2**32).
04:06:28  The runtime can be exponential in the amount of memory the program uses of course.
04:06:44  Did any of this make sense?
04:09:42  So if the runtime is really about as big as the number of possible memory states, then the timer has to be as big as the number of possible memory states too. But you rarely see such a long runtime in practice.
04:10:54  So practical programs with short runtimes can be simulated with a short enough time variable, but then the simulation isn't practical because it can still take time exponential in the original runtime, and it will do so if the original uses random access in an essential way.
04:11:44  mhm
04:12:34  (Guess why the whole thing came up now.)
04:16:52 -!- sleffy has quit (Ping timeout: 246 seconds).
04:18:18 -!- sleffy has joined.
04:46:45  no idea
05:08:33 -!- hppavilion[1] has quit (Ping timeout: 248 seconds).
05:10:01 -!- doesthiswork has quit (Quit: Leaving.).
05:10:29 -!- doesthiswork has joined.
05:17:41 -!- tswett has quit (Ping timeout: 240 seconds).
05:27:13 -!- doesthiswork1 has joined.
05:27:13 -!- doesthiswork has quit (Read error: Connection reset by peer).
05:32:02  Just now in vim I tried ":spl /dev/null" and surely enough it does work just as well as I expected it to do.
05:37:22 -!- doesthiswork1 has quit (Quit: Leaving.).
05:55:50 -!- oerjan has quit (Quit: Nite).
06:02:35 -!- fizzie has joined.
06:03:22 -!- Lymia has joined.
06:03:37 -!- ocharles has joined.
06:04:24 -!- sparr has joined.
06:05:07 -!- GeekDude has joined.
06:05:37 -!- mtve has quit (Ping timeout: 260 seconds).
06:06:40 -!- mtve has joined.
06:39:18 -!- erkin has joined.
06:56:18 -!- ski has joined.
07:07:10 -!- FreeFull has quit.
07:15:41 -!- propumpkin has joined.
07:18:09 -!- contrapumpkin has quit (Ping timeout: 248 seconds).
07:22:46 -!- Warrigal has quit (Quit: No Ping reply in 180 seconds.).
07:22:54 -!- Warrigal has joined.
07:24:08 -!- hppavilion[1] has joined.
07:35:57 -!- imode has quit (Ping timeout: 240 seconds).
07:36:48 -!- sebbu2 has quit (Ping timeout: 240 seconds).
08:10:37 -!- augur has quit (Remote host closed the connection).
08:13:21  SUBLEQ 
08:13:27  http://gerigeri.uw.hu/DawnOS/index.html
08:13:40  Uh. Is this literally an OS for a CPU that only supports the SUBLEQ instruction?
08:15:50 -!- kurolox has joined.
08:42:37 -!- wob_jonas has quit (Quit: http://www.kiwiirc.com/ - A hand crafted IRC client).
08:45:43  Damn.
08:46:13  I have the exact same kernel panic in this laptop in a fresh install too
08:47:01  Some sort of hardware failure?
08:47:18  I doubt it, it happens in two completely different systems
08:47:40  I'm talking about UMLBox by the way
08:51:46 -!- AnotherTest has joined.
08:53:56  Sgeo: why is it shipped as a bunch of binaries
08:54:34  Do you like static linking?
09:13:30  Hey fizzie, are you around here?
09:24:35 -!- sleffy has quit (Ping timeout: 240 seconds).
09:59:58  shachaf: I imagine Google has a single sparse 2^47 byte image, directly mapped to all the servers that contains all the software :-P
10:00:13  (which would then be statically linked)
10:00:18  (not really)
10:02:18  int-e: h8r
10:02:24  monorepos are the best
10:07:07  kurolox: I wasn't, then.
10:07:24  > 2^47
10:07:26   140737488355328
10:07:39  > 2^47/1e6
10:07:41   1.40737488355328e8
10:07:47  bah
10:09:01  it's not an entirely random number; 2^48 bytes tends to be the effective virtual memory space these days (which is limited by the page table hierarchy), though I've seen it go up to 2^52 somewhere.
10:09:24  and I left some space for more volatile data
10:09:57  kurolox: If you're getting an "can't execute init" kernel panic, check that the umlbox-linux and init binaries have the same arch (e.g. via "file umlbox-linux", "file init").
10:10:26  I'm getting a "can't mount /" panic though
10:10:42  Oh, that's probably different then.
10:10:57  Kernel panic - not syncing: VFS: Unable to mount root fs on unknown-block(98,0)
10:11:10  I have the exact same issue in two different computers, so I think that is not a hardware issue
10:11:48  unknown-block sounds like a device driver (for uml's virtual block device?) is missing
10:12:07  Here's the full log
10:12:29  https://ghostbin.com/paste/sogvd
10:12:44  `` echo $(cat /proc/devices)
10:12:45  Character devices: 1 mem 2 pty 3 ttyp 4 tty 4 ttyS 5 /dev/tty 5 /dev/console 5 /dev/ptmx 10 misc 128 ptm 136 pts Block devices: 1 ramdisk 259 blkext 7 loop 98 ubd
10:12:50  kurolox: Did the umlbox-initrd.gz get built correctly? If you do "zcat umlbox-initrd.gz | cpio -t", does it print out "init"? 
10:12:51  the ubd one
10:12:58  int-e: It's not supposed to be using ubd for root.
10:13:03  As far as I know, everything got built correctly
10:13:03  ah
10:13:12  int-e: There's an initrd image, and the init never remounts root to anything else.
10:13:25  kurolox: Well, do that cpio check anyway.
10:13:56  cpio: premature end of archive
10:14:07  That's not right then.
10:14:18  rm umlbox-initrd.gz && make umlbox-initrd.gz ?
10:15:03  done
10:15:11  now running zcat says
10:15:15  init
10:15:17  1495 blocks
10:15:22  That sounds better.
10:15:28  should I build again?
10:15:34  You shouldn't need to.
10:15:41  Just try running again and seeing what happens.
10:15:56 -!- erkin has quit (Quit: Ouch! Got SIGABRT, dying...).
10:16:22  Well, you might need to make install, if you're using it "installed".
10:16:37  yes. I've ran the executable at the build dir to test
10:16:44  the good news is that there's no kernel panic anymore
10:16:57  the bad news is that I lied. There's still a kernel panic, now there's a different one though
10:17:04  Does it complain about the init? 
10:17:08  yes
10:17:11  10:09  kurolox: If you're getting an "can't execute init" kernel panic, check that the umlbox-linux and init binaries have the same arch (e.g. via "file umlbox-linux", "file init").
10:17:15  Kernel panic - not syncing: Attempted to kill init! exitcode=0x00000100
10:17:40  okay, will do
10:17:51  Well, that's slightly different than what I'd expect from the "mismatched architectures" problem.
10:17:51  Ah, this may not be the most helpful behavior. "rootfs image is not initramfs (junk in compressed archive); looks like an initrd"
10:18:20  (but you've progressed beyond this anyway)
10:18:27  Here's the log again, I feel like it's not an init problem
10:18:41  https://ghostbin.com/paste/bk3uu
10:18:53  No, it clearly did manage to run init.
10:19:05  (That's what prints the "UMLBox starting" line.)
10:19:47  Think the kernel panic is just because that's how umlbox stops when it encounters problems.
10:20:03  The "mount(source, rtarget, type, 0, data): Device or resource busy" thing might be more relevant, but I'm not sure what's up with that.
10:20:28  now it looks like a missing root fs? I mean, "/bin/sh could not be executed"
10:21:04  int-e: It's not supposed to have that on the root fs, actually. :) 
10:21:42  "init" is the only file that's supposed to be on /, the rest it gets by read-only-mounting the host's /bin et al. using UML's hostfs.
10:22:27  Or, more exactly, it mounts the directories out of ["/usr", "/bin", "/sbin", "/lib", "/lib32", "/lib64", "/etc/alternatives", "/dev"] that exist on the host.
10:22:50  That said, it should still have a /bin/sh that way.
10:23:06  why is it mounting proc,sys,tmp twice?
10:23:17  sorry
10:23:19  I think it's my fault
10:23:23  I didn't use the -B flag
10:23:52  now it doesn't panic, but it seems like there are still problems
10:24:11  or maybe it just takes a while to load
10:24:25  int-e: It's mounting them twice because the mount lines are there several times in the configuration file, but I don't know why *that* is.
10:24:47  The "Read configuration" section dumps out what it's got, and it looks like it's repeated three times, which doesn't sound normal.
10:25:34  https://ghostbin.com/paste/rwuw9
10:25:38  umlbox is stuck like this
10:25:43  I assume that it should give me a bash prompt
10:26:25  You might not be able to get interactive use out of the stdin/stdout thing.
10:26:32  Have you tried typing in commands anyway? 
10:27:03  Also try something like  umlbox -v -B /bin/echo foo  to check if a non-interactive command works out right.
10:27:04  yes, but I can't see anything
10:27:32  Also I can't stop the process with ctrl+c, I have to kill it
10:30:00 -!- kurolox has quit (Remote host closed the connection).
10:30:21  Fun fact: for me, "umlbox -B echo foo" outputs just "foo" as expected, but "umlbox -v -B echo foo" (verbose mode) manages to leave terminal echo disabled.
10:31:22  Huh, I do get a working interactive bash prompt out of "umlbox -B bash". Wasn't expecting that.
10:32:13 -!- kurolox has joined.
10:32:28  Sorry
10:32:29  I had to reboot
10:32:40  int-e: Heh, this is a new one for me: "cat: -: Resource temporarily unavailable"
10:33:00  fizzie, about the echo foo
10:33:19  it doesn't work, but I think that is because of how I had to kill the last process
10:33:39  https://ghostbin.com/paste/hkd5s
10:35:05  kurolox: There's something odd going on with the configuration file reading with your kernel, I don't know what.
10:36:16  If you compare the "Configuration" dump from line 3 onwards with the "Read configuration" one from line 90 on, the latter seems to oddly repeat the beginning half of the config.
10:37:25  The length of the "Read configuration" dump for you is exactly 512 bytes, as well. I wonder if, in later kernels, the ubd implementation has changed to e.g. pad files up to a block boundary.
10:37:37  yeah, about the lenght of the read
10:37:39  I've noticed something
10:37:56  I've tried running the commaand in my other computer, and it seems like it just gets cut
10:38:23  https://ghostbin.com/paste/pkqet
10:38:29  $ moun
10:38:29  Unrecognized command moun
10:38:48  that was mount before
10:39:12  It should end at the "run user ..." line, like it does in the outside-UML configuration dump.
10:39:45  On your other box it probably truncates at "moun" instead of "mount" because the gid is 100 in one, 1000 in the other, and 1000 takes up one character more of space.
10:40:37  Well, so any idea? Should i try an older kernel?
10:41:13  If it's what I think it is, you might be able to fix it by padding the config file with 0s up to a block boundary.
10:42:03  Maybe try changing the line in "umlbox" that says  conff.write(confs)  to something like  conff.write(confs + "\0" * (512 - len(confs) % 512))
10:43:39  (Though I'm a little puzzled moony didn't encounter this issue, if it's some change in udb semantics in later kernels.)
10:44:47  well
10:44:49  it did something
10:45:51  https://ghostbin.com/paste/op8u3
10:46:00  I still don't see the echo anywhere, but there are no errors
10:46:50  Can you check what happens if you try without the "-v" flag? The verbose mode terminal handling is kind of... odd.
10:47:06  (Of course you don't get any logs so chances are it'll just print nothing.)
10:47:10  there's no output
10:47:33  also, I should mention that umlbox always mess up the console formatting
10:47:51  after running umlbox through ssh for example, the cursor is static and nothing I write will be visible
10:48:05  It does that for me as well, though only with -v.
10:48:07  in my desktop everything I type seems to be tabbed over and over
10:48:14  Running "reset" seems to fix it.
10:48:25  okay, good to know
10:48:32  http://sprunge.us/NJRC is what I get out.
10:48:57  Looks pretty similar except I have an extra "ttyraw" in the generated config.
10:49:26  Okay, so this is weird
10:49:34  I've tried to run bash again
10:49:56  so the cursor is static and everything is invisible, but it seems to recognize what I'm doing
10:50:17  as in, I can't see any "echo" or anything, but typing "exit" closes umlbox properly
10:50:32  so maybe it's working but I can't see it, I don't know
10:50:35  Yeah, I'm guessing this is all something to do with the consoles.
10:50:50  maybe it's because I'm doing it through ssh
10:50:54  I'll check in my desktop
10:50:57  Out of curiosity, what do you get if you try "umlbox -B echo foo | cat" (so that the output's not a tty)? 
10:51:34  Nothing
10:53:09  Also, there's no difference in my desktop. Same stuff happens.
10:55:15  Well, I'm somewhat stumped. I do think it's highly likely it's got something to do with either the UML console configuration, or umlbox-mudem.
10:55:22  But I'll have to head to work now.
10:55:45  Sure thing. Thanks for all the help fizzie, I hope that I can get this solved eventually.
11:03:04  I'd talk, but I'm honestly kind of scared to.
11:06:33 -!- sebbu has joined.
11:08:19  https://quoteinvestigator.com/2010/05/17/remain-silent/ :-P
11:20:37 -!- erkin has joined.
11:22:49  :c
11:36:49 -!- clog has quit (Ping timeout: 248 seconds).
11:41:58 -!- Antoxyde has joined.
11:44:41 -!- boily has joined.
12:28:21 -!- boily has quit (Quit: PULP CHICKEN).
12:47:30 -!- LKoen has joined.
12:50:21  Moin
13:07:33  shachaf: did you see that MS agrees that git is better than hg
13:12:13 -!- ocharles has quit (Ping timeout: 276 seconds).
13:15:07 -!- ocharles has joined.
13:36:51 -!- clog has joined.
14:01:00 -!- TieSoul has joined.
14:19:54 -!- jaboja has joined.
14:36:47 -!- LKoen has quit (Remote host closed the connection).
14:37:22 -!- `^_^v has joined.
14:52:09 -!- zseri has joined.
15:06:20 -!- ATMunn has joined.
15:20:39 -!- jaboja has quit (Ping timeout: 252 seconds).
15:24:48 -!- erkin has quit (Quit: Ouch! Got SIGABRT, dying...).
15:42:43 -!- LKoen has joined.
16:40:20 -!- augur has joined.
16:59:39 -!- TieSoul has quit (Ping timeout: 252 seconds).
16:59:49  Damn, I wonder what happened to that Nomic game we planned.
17:00:26  . o O ( You couldn't agree on the rules? )
17:00:41  Should we try again?
17:01:36  . o O ( What we really need is a website specifically for holding rules for Nomic games. )
17:05:45  int-e: would you be interested in attempting to restart it?
17:08:57 -!- hppavilion[1] has quit (Ping timeout: 240 seconds).
17:09:33 -!- hppavilion[1] has joined.
17:14:20 -!- hppavilion[1] has quit (Ping timeout: 240 seconds).
17:35:04 -!- FreeFull has joined.
17:40:02 -!- imode has joined.
17:45:20 -!- imode has quit (Ping timeout: 246 seconds).
17:46:10  i thought about building one with lua as a rule-language and a basic rpg thingie underlying
17:53:24  I created a channel named #esoteric-nomic for possible future nomic games.
17:55:07  or at least the one I'm planning, anyway.
17:58:43 -!- LKoen has quit (Remote host closed the connection).
18:04:46 -!- imode has joined.
18:05:14  hi imode. I'm starting a new game of nomic in #esoteric-nomic if you're interested.
18:06:07  int-e: Agrees with whom?
18:06:09  I didn't see.
18:07:01  https://twitter.com/GabeAul/status/899691358889234432
18:07:55  also, earlier, https://blogs.msdn.microsoft.com/bharry/2017/05/24/the-largest-git-repo-on-the-planet/ (hmm, should I read that)
18:12:37  (indeed I should. just as the other companies aren't using vanilla hg, this isn't vanilla git either. not a surprise, really.)
18:17:08  hi rdococ.
18:17:16  wish I could but I've got work. :P
18:27:33 -!- erkin has joined.
18:36:48 -!- sleffy has joined.
18:42:05 -!- TieSoul has joined.
19:19:04 -!- augur has quit (Remote host closed the connection).
19:41:09 -!- rdococ has changed nick to beacoc.
19:41:25 -!- beacoc has changed nick to beakoc.
19:46:06 -!- ATMunn has changed nick to atbeak.
19:47:53 -!- atbeak has changed nick to beakymunn.
19:48:28 -!- beakoc has changed nick to baeky.
19:51:04 -!- beakymunn has changed nick to ATMunn.
19:52:31  [wiki] [[Special:Log/newusers]] create  * BlackCap *  New user account
19:57:02 -!- baeky has changed nick to rdococ.
20:07:34  [wiki] [[Esolang:Introduce yourself]]  https://esolangs.org/w/index.php?diff=52920&oldid=52917 * BlackCap * (+246) 
20:09:25 -!- ais523 has joined.
20:10:00  ais523: hi
20:10:50  hi
20:19:10 -!- wob_jonas has joined.
20:19:21  ais523: hello
20:19:38  I was trying to find you. I want to ask something.
20:20:25  wob_jonas: huh, I was wondering why I hadn't seen you online for a while
20:20:26 -!- erkin has quit (Quit: Ouch! Got SIGABRT, dying...).
20:21:12  I was up a bit irregularly. I'll be up more from September
20:21:48  re your lambdabot question, you can do a lot of functional tricks to simulate arrays, but recursively calling main isn't enough by itself because you only get one stack
20:22:10  ais523: that's why it's paradoxical
20:22:15 -!- Phantom_Hoover has joined.
20:22:16  which means you're limited to PDA levels of power
20:22:16 -!- ais523 has quit (Remote host closed the connection).
20:22:26 -!- ais523 has joined.
20:22:29  one stack isn't enough if the stack symbols are from a fixed size alphabet
20:23:33  if you have no temporaries, it IIRC isn't enough even if you have an infinitely large alphabet, unless the set of operations you allow on top-of-stack is Turing-complete even on just a single number
20:23:51  you know the easiest way around is to encode a whole array into a bignum. this construction doesn't do that, it's more sneaky, but it still needs numbers as large as the runtime of the original (simulated) program, which in turn can be exponentially large in the memory size of the original program in worst case
20:24:07  like, I think a bignum stack, increment, decrement, push, pop, conditional goto is not Turing-complete
20:24:42  in a functional language, you can implement an array as a function from the index to the element
20:24:50  and assign to the array by wrapping it with more functions
20:24:57  that's a different construction, but a fairly fun one
20:25:15  I have written down the construction more technically in http://www.madore.org/cgi-bin/comment.pl/showcomments?href=http%3a%2f%2fwww.madore.org%2f~david%2fweblog%2f2017-08.html%23d.2017-08-18.2460#comment-23792 , where it applies to the uncomputable esolang (1) and (3), but you can take just the Turing case
20:25:42  ais523: it doesn't just use increment and decrement, but also equal-compare of bignums
20:25:52  and copying of bignums
20:25:58  the natural number cases of (0) and (1) are just bloop and floop respectively, aren't they?
20:26:11  (0) is definitely bloop
20:26:15  wob_jonas: what are you comparing or copying them too?
20:26:16  um, how does floop work again?
20:26:28  it's like bloop except it has infinite loops with break
20:26:31  you're copying a bignum from one stack entry (near the top) to another stack entry (near the top)
20:26:33  for(;;) { … break … }
20:26:48  or you're equal-comparing two bignums in two stack entries near the top
20:27:11  wob_jonas: ah right, which is clearly TC as you can use the top two stack entries as a minsky machine
20:27:13  and you still need increment and constants
20:27:24  at that point, how you simulate things is just a matter of programming
20:27:44  ok, but "just a matter of programming" is somewhat vague
20:28:03  right
20:28:13  I guess this is more a question about programming techniques than about what's possible?
20:28:38  if you have these operations, then you can also implement arithmetic (in exponential time) and store a whole array in a bignum, which is how the minsky construction works (if you have at least three bignums)
20:28:40  perhaps it'd be interesting to try to constrain a language in such a way that you have to program it like that
20:29:05  also, the minsky construction works with two bignums by using one of them to store a simulated tuple of three bignums
20:29:09  which is really slow, but oh well :-)
20:29:21  but I'm still asking about this specific construction, which is a bit strange, because you really don't need integers larger than the runtime of the original program in the particular case simulated
20:29:25  I decided to put my half-finished toy neural net thing on Github: https://github.com/Taneb/net/blob/master/Main.hs
20:29:58  wob_jonas: you might need a write up of exactly how the construction works, then, because I haven't seen it
20:30:17  incidentally, how many languages do we have which are TC only because they can use the call stack as one stack and an explicit data stack as another?
20:30:27  it's a construction which feels like it should be more common than it actually is
20:30:30  anyway, in this case David describes in the original blog article that the straightforward construction where you encode an array in a bignum does work in a finite case,
20:30:51  but also that it doesn't work in the infinite case, and how simulating arrays in the infinite case is VERY difficult
20:30:59  (at least in general)
20:32:04  "TC only because they can use the call stack as one stack and an explicit data stack as another" => I don't recall any such language
20:32:40  wob_jonas, Underload is one
20:32:54  Taneb: no, Underload has complex stack elements
20:32:57  but it rarely comes up, because you'd either need an actual infinite stack for TC-ness, or if you want a practical language, then just two stacks are very impractical for general purpose programming
20:33:00  which means you have more than two stacks
20:33:08  ais523, oh! I misunderstood the construction used
20:33:13  you can think of it as a language in which the stacks are made out of other stacks
20:33:17  oh
20:33:33  actually that language I have imagined but haven't yet documented might be like this,
20:33:44  at least two stacks is the only way I can prove TC-ness,
20:34:44  even though there's a much better practical construction for random access of vast but possibly not infinite memory, where the accessible memory size grows at least double exponential in the code size, probably even faster than that
20:34:58  so you don't really need the two stacks construction for TCness
20:35:19  (although you have to use the stacks at least a little for temporary values)
20:35:39  I will have to eventually document that language
20:37:13  with a data stack, a control stack, and a heap, you may get a G machine.
20:37:41 -!- ais523 has quit.
20:37:51 -!- ais523 has joined.
20:38:12 -!- augur has joined.
20:38:35  that reminds me of my attempt to write a language that's theoretically Turing-incomplete but can access so much storage that that basically never comes up except in programs that bruteforce for counterexamples
20:38:42  Funny, I've obviously never looked at the original G machine paper. It was intended to be an actual hardware design by the looks of it.
20:39:26  Oh well, 1985.
20:42:21 -!- augur has quit (Ping timeout: 240 seconds).
20:44:33 -!- sleffy has quit (Ping timeout: 248 seconds).
20:47:21 -!- imode has quit (Ping timeout: 252 seconds).
20:47:25  ais523: if you have an ordinary computer with a CPU with a 48-bit physical address space, and have a disk interface that gets commands from a memory-mapped variable sized control block, and the sector address and sector size and count of sectors are in that command block, does that work for this?
20:47:41  you can access something like 2**2**48 bytes of memory, give or take a few
20:47:53  wob_jonas: if that's all you have, it's clearly sub-TC
20:48:05  because it's a finite (even if very large) amount of memory
20:48:20  my language was going to make heavy use of the Ackermann function, so it could access way more memory than that
20:48:32  (but still a finite amount for any given program)
20:49:56  wob_jonas: well you can stack the construction. Use half of each address space for data, and the other half for some MMIO interface to the next level in the hierarchy
20:50:04  isn't sub-TC what you asked for? "theoretically Turing-incomplete"
20:50:22  wob_jonas: and then you get something that may be TC.
20:50:36  but fiendishly difficult to implement ;-)
20:50:53  wob_jonas: yes
20:50:59  but I wanted to be closer to TC than that
20:51:00  or you want much more than 2**2**48 bytes?
20:51:02  ok
20:51:15  like, the language scaled with the size of the problem
20:51:38  I think part of the hope was to be able to express any number that humans are capable of describing without resorting to diagonalization tricks, and know for a fact exists
20:52:26  the sort of number which can't be calculated by most Turing-incomplete languages is "the first counterexample to the Riemann hypothesis" (you can't set an appropriate memory limit in advance because you don't know how large it is) but we don't know for certain it exists
20:53:08  [wiki] [[ResPlicate]]  https://esolangs.org/w/index.php?diff=52921&oldid=45669 * BlackCap * (+713) 
20:53:50  ais523: in that case my language *might* actually work, if you restrict the size of one of the two stacks. I think an ackermann construction for accessing memory in many hierarchies might be possible to implement, but I'm not sure yet, I'm only sure of at least double exponential. But I also can't prove that it can't still random-access infinite me
20:53:51  mory with a fixed code.
20:54:25  (I mean double exponential or ackermann in the code size.)
20:54:33  ais523: The Calculus of Construction should get you quite far.
20:54:40  the largest numbers we can describe are basically modifications of the "the smallest number not nameable in…" trick, only programmatically rigorous
20:55:25  "express any number that humans are capable of describing without resorting to diagonalization tricks" => wait, which humans? if you take the right humans, that's a very very very very very large number, much larger than I can imagine
20:56:29  [wiki] [[ResPlicate]]  https://esolangs.org/w/index.php?diff=52922&oldid=52921 * BlackCap * (+107) 
20:56:38  wob_jonas: there are some pretty insane humans out there :-)
20:56:48  but I was thinking more of the set of humans that actually exist and name numbers
20:57:03  rather than the set of all hypothetical humans who might want to name large numbers
20:57:09  all this reminds me of http://djm.cc/bignum-results.txt
20:59:03  no, I mean if you take numbers whose descriptions only like ten mathematicians in the world understand, then you get numbers much larger than the numbers I can describe, even with a no-diagonization restriction
20:59:51  numbers I can actually imagine using go to only tetration size like 2***(2**512) or something, but I can describe bigger ones
21:00:33  but if you take numbers that a million humans can describe, those aren't so big that I can't imagine them
21:00:43  int-e: there's a similar thread on PPCG but the rules are really screwed up
21:00:47  all these about humans who live today
21:00:51  and there are debates on whether the rules should be fixed or not
21:01:19  not fixed as in you freeze those rules and start a separate thread with better rules?
21:03:22  there are debates on how to fix it, too
21:03:34  anyway, you might be interested about the non-computable (0) language family that David described, he mentions a lot of interesting details
21:03:37  as in, start a new thread, change the rules of the existing thread, or something else?
21:04:01  . o O ( diagonalize over the thread )
21:06:15  int-e: that other contest has a rule for exactly that, it says a new guess counts as better than an older guess only if the number it names is significantly bigger than that older guess. so just adding one to a previous guess isn't enough, and "significantly bigger" is very loose.
21:06:39  so you have to use very different techniques than any previous answer to get the biggest number so far
21:06:45  no, I mean to get the best answer so far
21:08:14  wob_jonas: looks like it's still broken: https://codegolf.stackexchange.com/questions/18028/largest-number-printable
21:08:43  the ban on multiplication, in particular, is highly arbitrary
21:08:46 -!- imode has joined.
21:09:45  a ban on multiplication? so then posting a max size answer saying "1+1+1+1+1+1+1+1+1+1+1+1+1+1+1+1+1+1+1+1+1+1+1+1+1+1+1+1+"... is the only thing you can do?
21:10:36  wob_jonas: no, there are a ton of things that aren't banned
21:10:45  multiplication isn't really important, you can implement it using nested loops if you need it
21:11:14  ok
21:11:18  and yes, that's broken
21:12:02  "Your printed number will be divided by the cube of the number of bytes you used for your solution." seems useless
21:12:41  int-e: definitely
21:12:47  there are so many useless rules like that
21:12:57 -!- augur has joined.
21:13:08  basically, it works as a bignum competition because the rules don't significantly change the results you can get, but it doesn't work because the rules are so arbitrary
21:13:24  and by stack exchange rules you can't post a duplicate with better rules…
21:14:39  > floor $ 1/0
21:14:42   1797693134862315907729305190789024733617976978942306572734300811577326758055...
21:15:02  hmm, it doesn't print the whole thing
21:15:29 -!- zseri has quit (Quit: Page closed).
21:15:41  (that comes from the "largest number in 10 bytes of code" thread on PPCG; it's certainly not as large as it could be, but the fact that floor(infinity) is a specific, finite integer in Haskell is fairly amazing)
21:15:52 -!- augur has quit (Remote host closed the connection).
21:16:05 -!- augur has joined.
21:19:01  how much score would that give you if you find a programming language where the empty code prints a positive number?
21:19:30  such languages exist, e.g. Retina
21:19:35  which prints 1 upon running the empty program
21:20:18  (actually, it prints the number of characters in stdin + 1, but PPCG normally assumes that stdin is empty)
21:21:50  Commodore 64 boots to saying "    **** COMMODORE 64 BASIC V2 ****\n\n 64K RAM SYSTEM  38911 BYTES FREE\n\nREADY.\n" does that count as printing 38911 as the largest number? or even 65536 because the 64K clearly stands for that in that context?
21:22:59  I could have told you once, I think? but now I'm happier not needing PPCG rules memorised :-)
21:23:13  anyway, away for a bit, I need to go buy food before the shops shut
21:23:17  yeah, I know, it doesn't really matter
21:26:22 -!- AnotherTest_ has joined.
21:27:44 -!- AnotherTest has quit (Ping timeout: 255 seconds).
21:27:44 -!- AnotherTest_ has changed nick to AnotherTest.
21:31:12  ed doesn't work, it prints the size of its input file if you give the filename as the command-line argument. I had to install ed for this. Damn you, debian. I had specifically installed bc and dc before, but I missed ed.
21:31:28  I mean, I know I don't use it often, but it's also a very small program.
21:32:38  I hope they didn't choose to not install it in base because of some stupid security problem, like how it can execute arbitrary things if you give untrusted input as ed commands.
21:32:56  s/stupid/stupid alleged/
21:33:12  seriously, the kind of things some people complain about
21:34:19  I mean, this is a unix distribution, not a padded mental institute cell with your shoelaces removed
21:34:38  but they probably just removed it because it's not really essential and nobody was using it
21:35:05  ?
21:35:09  classic error message
21:36:41  hey, help me google a thing
21:36:51  months ago i found a paper on arxiv
21:36:59  http://www.smbc-comics.com/comic/dying-wish => wait, just one season?
21:37:09  it was about a new theoretic model that was more cache aware
21:37:27  izabera: oh, that already sounds easier than what I asked. the paper you're looking for probably exists, the one I asked might not.
21:37:57  several algorithms have a different runtime in that model, for instance heap sort is O(n log^2 n)
21:38:36  wob_jonas: I've gone 10 months since installation and no ed.
21:38:43  but not as cache-aware as a six-tape Turing machine, right?
21:39:10  i'll ask somewhere else
21:41:38  Is log^2 n supposed to mean log(n)^2 or log(log(n))?
21:41:45  I guess it's the former, but that's pretty confusing.
21:42:06  shachaf: (log n)^2
21:43:35  shachaf: the former
21:44:08  it's very rare to write log log n as log^2 n, because that would be too confusing. people rather write up to four iterations of log explicitly, and use other notations when they really need to write positive number of iterations
21:44:19  and you rarely need more than four iterations of log
21:44:40  unless you're in log* n territory
21:45:04  (just log log log log does appear in that stupidly specific limit distribution theorem)
21:45:13  or perhaps you're saying that it'll be essentially constant anyway...
21:45:30  just like that \alpha from Tarjan's analysis of disjoint set forests
21:46:17  Tell me when you have an algorithm that takes inverse busy beaver time.
21:47:17  hah
21:47:29  that would be fun
21:48:31  but I really don't see how that would happen
21:59:15  back, but not for long
21:59:21  I might be properly back in a few hours (not sure yet)
21:59:40  ok
21:59:54 -!- LKoen has joined.
22:00:16  btw, something that came up in one of the NetHack channels and I thought "b_jonas might know this": is there a mythological or famous fictional creature that's noted for being afraid of the dark?
22:00:44  afraid of the dark... hmm let me think
22:02:27  well, humans are sometimes portrayed as being afraid of darkness
22:03:01  and... how dark do you want or for how long? there's a few ridiculous photosynthetizing humanoids that know they can't live in the dark for more than a few days
22:03:50 -!- LKoen has quit (Ping timeout: 240 seconds).
22:03:52  wob_jonas: we basically (for gameplay reasons) wanted a powerful monster that wouldn't enter corridors, and I thought being afraid of the dark would be a good way to explain that (corridors are normally unlit, so "won't enter dark squares" and "won't enter corridors" have sufficient gameplay similiarity)
22:04:18  and there's something about shades or shadows, but that probably wasn't being afraid as such
22:04:29  I guess you could have a monster that's powered by light somehow? it seems like the sort of thing that Doctor Who would have, although I can't offhand think of a monster from there that actually is
22:04:50  ais523: wouldn't enter corridors... you can just have monsters that are too big or afraid of narrow tunnels or afraid of being surrounded for strategic reasons
22:05:20  "too big" is an obvious thought but it doesn' really work in NetHack, which has single-square dragons
22:05:38  anyway, I'd better go, thought I'd just throw this out there first in case it inspired you to think of something "in the background"
22:06:01  bye everyone
22:06:04  something that behaves like a human child intellectually could be afraid of the dark, but that works better for an ally than for a normally hostile creature
22:06:18 -!- ais523 has quit (Quit: bye).
22:07:51  perhaps an animal that was once captured in a cage and REALLY didn't like that might be afraid of tight spaces so much that he usually remains far from even walls
22:08:17  and of course nh already have stationary monsters that aren't generated in corridors
22:10:42  I think the olist monster in the dark is afraid of the dark.
22:12:47  too big isn't impossible in nethack, it's just either hard to implement (a long worm like creature that takes up say four tiles forming a square) or hard to flavor (a one-tile monster bigger than even krakens and elder dragons)
22:18:02  if you can implement four-tile creatures, then you could change some dragons to elder dragons. you can then turn the quest dragons to be that large, they both have a suitable map.
22:18:13  (krakens could also be big, but they already don't go to corridors)
22:18:45  you can also find other very big creatures in mythology and fiction
22:22:11 -!- imode has quit (Ping timeout: 255 seconds).
22:29:25  So, besides fizzie and gregor nobody here knows about UMLBox, right?
22:29:45 -!- sleffy has joined.
22:32:59  fizzie, how much black magic did you put into UMLBox? 'umlbox -B -v echo DEADBEEF' doesnt work with the error of https://ptpb.pw/Evrs, yet my bot's sandbox works as if nothing is wrong.
22:34:00  well I do see it echo DEADBEEF halfway through
22:35:40  yeah, so it seems like moony kernel panic happens after the sandbox program sucessfully runs
22:35:44  that might explain why it works
22:46:50  Well fizzie, I'm quite sure the conff issue you helped me with before isn't related to my actual issue of stuff not running on UMLBox, since moony does have the same conff issue, but it happens afters he runs the command sucessfully.
22:47:13  Anyways, I'm sharing the fix you gave me before with him to see if there's any difference with his stuff
22:48:16  Just to make it a bit tidy for when you see this, this is the output of 'umlbox -B -v echo DEADBEEF' for me and moony
22:48:53  me: https://ghostbin.com/paste/as6r3
22:49:07  moony: https://ptpb.pw/Evrs
22:50:33  moony: Looks like you're getting the same "configuration repeats" thing we saw when debugging.
22:50:37  Well, as above.
22:50:56  well that'd explain why the bot takes forever to process
22:50:58  Yeah, it wouldn't really stop it from running the command, it'd just do some odd things afterwards.
22:51:16  I'm still not sure why it doesn't work for me
22:51:46  I've noticed that when moony runs something it seems like " | cat" is added to the command
22:51:52  my output doesn't do that
22:52:03  That's what it does when it thinks the output isn't a tty.
22:52:16  Yay.
22:52:18  which, in the case of my bot, it isnt.
22:52:49  wait. *makes connection* rdococ has been in ##werewolf all along and i never noticed. how.
22:52:59  ...:P
22:53:09  Nice.
22:53:50  I believe the | cat is added to make the command that gets run inside the UML kernel to similarly see a non-tty output. Because otherwise it sees the UML console, which always is a tty as seen from the inside, even if the output fd it's redirected to isn't.
23:02:08  If you want to try something out, maybe (temporarily) change the umlbox script's line   "con1=" + childStdin + ",fd:" + str(childStdout),   to instead be   "con1=" + childStdin + ",fd:" + stdoutws,   (and keep using the -v flag)
23:02:54  Okay
23:03:07  Wow. People figured out how to make dpkg work in linbut lol
23:07:11  fizzie, I get an error.
23:07:27  https://ghostbin.com/paste/cc4g5
23:07:37  $ input ../tty1
23:07:37  open(rfile, O_RDONLY): No such device or address
23:08:04  Sorry, that should've been:   "con1=" + childStdin + "," + stdoutws,
23:08:19  Now you ended up with the argument 'con1=fd:0,fd:fd:1' which is one "fd:" too many.
23:09:38  https://ghostbin.com/paste/tkxnn
23:10:46  The error changed, fizzie. Now the device is busy.
23:11:16  Oh, that's probably because it's using stdoutws (aka fd:1) also for that other console spec.
23:11:59  You could definitely try to work around that as well, but I'm just puzzled as to why it's not working in the first place.
23:15:40 <\oren\> does anyone know how to use jenkins to talk to another jenkins
23:16:06 <\oren\> `? jenkins
23:16:50  jenkins? ¯\(°​_o)/¯
23:18:01 -!- sleffy has quit (Quit: Leaving).
23:18:21 -!- sleffy has joined.
23:18:48  Well, it's a shame that there's no way to know what's wrong with it
23:19:14  I really want to get UMLBox working, but I guess that's enough trying for today
23:20:27  Well, hmm.
23:20:53  You could try to strace the kernel execution, but it might be doing a bit too much for that to be readable.
23:21:20  There's definitely something odd when it comes to the terminal handling. For me, umlbox works fine, but running it once somehow manages to break the stdin of subsequent commands, which I don't even understand how that's possible. I mean, look at this: http://sprunge.us/NKbS
23:21:36  yeah, a lot of weird stuff happens too
23:22:00  when I try to run sudo, I'm completely unable to input the password in the same terminal where I ran umlbox before
23:23:02  It's not really that great for interactive use, it might be best to stick with having some other program call umlbox for you, the way it works on HackEgo.
23:23:14  Who knows, it's even borderline possible it would work in that context.
23:23:18  fizzie, in order to check if the issue is if there's no output or if there's no visible, I should use umlbox to make a permanent change (ie touch a file or make a dir), which folder is writtable by umlbox?
23:24:31  Nothing on the host is writable by default. You can pass in an extra argument like   -fw /some/dir   which will mount /some/dir from the host to the guest in read-write mode.
23:25:54  it doesn't seem like it runs the command
23:25:58  so there's no output at all
23:26:24  I've tried with umlbox -B -v -fw /test touch /test/didit
23:26:30  there's nothing in /test
23:26:39 -!- wob_jonas has quit (Quit: http://www.kiwiirc.com/ - A hand crafted IRC client).
23:26:51  Does /test exist, and do you have write permissions in it as the user you run umlbox as? 
23:27:04  (Also what do the logs look like?)
23:27:08  yes, and I ran umlbox as sudo
23:27:32  here's the output: https://ghostbin.com/paste/8xyvf
23:28:42  Hmm. I wonder if that might have something to do with permissions *inside* the UML. Try adding -s as well? 
23:28:53  (It runs the command as root inside the UML.)
23:29:11  wait
23:29:13  so
23:29:19  instead of trying to run umlbox with sudo
23:29:32  I made myself owner of /test and tried again without sudo
23:29:35  this time it worked
23:31:22  I think that might be because the umlbox init doesn't really expect UML to be executed as root.
23:31:58  It uses uid/gid 0 to mean "unset" for the uid/gid it runs the command as, and when they're unset it picks random uid/gid.
23:32:21  kurolox, get in ##werewolf
23:32:24  (I guess in general there shouldn't be any reason to try running umlbox as root.)
23:32:30  fair enough
23:32:40  at least now I know that the stuff runs in umlbox even if I can't see it
23:32:42 -!- TieSoul has quit (Quit: Leaving).
23:32:52  http://i.imgur.com/dlA01qW.png
23:33:03  so we're back at the issues with console output
23:33:08  kurolox, ##werewolf
23:33:14  okay, okay
23:35:08  kurolox: Out of curiosity, what happens if you try something like this: http://sprunge.us/dTBG
23:35:21 -!- `^_^v has quit (Quit: This computer has gone to sleep).
23:38:15  fizzie: https://ghostbin.com/paste/dvb8c
23:38:25  Aw.
23:38:43  I guess you're still affected by whatever mysterious output redirection problems you're having.
23:38:49  So odd, though.
23:39:03  maybe redirecting the output to a file?
23:39:24  Well, I mean, that should *work*, but it's more than a little clumsy.
23:40:08  there are stuff that I'm not sure about though
23:41:57  Since you *are* seeing the init's output (and therefore clearly getting *something* out), if you really just want to hack it to make it work, chances are you could just fiddle with the conX= and subprocess.call arguments in the umlbox script until you hit a combination that works.
23:43:19  (And/or the "output ..." stanza it writes to the config file.)
23:43:34  I'm still not sure if it really works though
23:43:49  I think I'll try building a current kernel and see how that goes for me.
23:44:10  as in, when I try something with umlbox that shouldn't end inmediately (ie: the bot I'm trying to run) still ends inmediately
23:44:16  also
23:44:19  this might be interesting
23:44:24  there's output after the run
23:44:34  nothing relevant, but there's something
23:44:49  https://ghostbin.com/paste/2jhto
23:45:04 -!- AnotherTest has quit (Ping timeout: 255 seconds).
23:45:14  maybe that can help identifying the issue?
23:48:41  fizzie if it's useful for what you want to do, I'm running 4.12.8 in the host, and also 4.12.8 as the uml kernel
23:48:56 -!- ais523 has joined.
23:49:05  back
23:49:45  Sounds like "uninitialized urandom read" is a kernel message, which probably explains why you're seeing it.
23:49:57  It'd go to the same console all those debugging lines do.
23:50:49  oh, okay
23:51:10  actually fizzie, if you feel like replicating the issues I'm having, doing a fresh arch linux install should do the trick
23:51:41  it's what I've done in my laptop, I installed it fresh yesterday and it's having the exact same issues I'm having with my desktop, so chances are you will have them too
23:51:45  If you want a hacky trick to try, locate the lines in the umlbox script that do the   input ../tty1   and   output ../tty1   and change them to   input /console   and   output /console   instead. (/console is a file the umlbox init makes and uses for its own output.)
23:51:58  okay
23:52:04  ais523: Here's a funny thing: http://sprunge.us/NKbS
23:53:08  fizzie: is that second cat running inside or outside umlbox?
23:53:16  ais523: Outside.
23:53:35  ais523: It leaves the terminal in that state, and I don't know of a way to undo it.
23:53:54  OK, so that error message is EAGAIN
23:53:59  fizzie, no such file or directory
23:54:19  https://ghostbin.com/paste/kvpg5
23:54:45  can you find out which system call is erroring out? "strace cat" would normally be enough, you might need to redirect the output to a file though (strace has an -o option to write to a file)
23:55:00  kurolox: Oh, sorry, make that "../console" instead. Looks like init prepends "/host/" to it.
23:55:06  my guess is that one of the standard file descriptors has somehow been set to non-blocking mode, that'd be an easy way to cause spurious EAGAINs
23:55:27  ais523: Ooh, nonblocking, that sounds plausible.
23:55:49  HEY
23:55:52  I GET OUTPUT NOW
23:56:12  now I see why the bot wasn't working, I wasn't mounting /mnt so it couldn't read the bot file
23:56:36  I love you fizzie, I can't thank you for all the help you've been offering me the last days
23:57:32  You can't?
23:57:39  there's something a bit weird though, fizzie
23:58:04  it seems like I can see the output by running stuff with -v, but nothing without it
23:58:15  ais523: Yeah -- read(0, 0x7f086c62c000, 131072) = -1 EAGAIN (Resource temporarily unavailable) -- and: http://sprunge.us/FCWe
23:58:41  https://ghostbin.com/paste/6pffa
23:58:59  this sounds like a mistake in the shell somehow? it shouldn't be letting applications it runs permanently change the mode of its file descriptors

2017-08-24:

00:00:07  kurolox: That's not too surprising. The script closes the place it puts /console to by default, since normally the command output goes via tty1.
00:00:33  kurolox: You could use the --debug flag (in place of -v), I think that might leave it open but not print any extra stuff.
00:01:12  Nope, debug gives me the same as -v
00:01:25  well, I should be fine with running it with -v for now
00:01:56  unless I need to make the script call umlbox, it should be fine if I run the bot with umlbox
00:02:17  I assume that any subprocess created by something with umlbox will be sandboxed too, right?
00:03:55  I'd assume that it'd be running within the same umlbox process, although I'm not sure
00:04:15  Well, yes, though if you put the bot inside umlbox, it's hard to make the bot have access to any sort of modifiable thing that you don't want the commands it executes to have access to.
00:04:20 -!- Phantom_Hoover has quit (Read error: Connection reset by peer).
00:04:33  If you're okay with an entirely stateless thing, then that's maybe not really an issue.
00:06:06  my bots are typically stateless
00:06:09  thutubot is, for example
00:10:17  hm, the bot complains about the lack of a module
00:10:21  ais523: Kind of a fun fact: on recent kernels, UML's virtual block device (ubd), if you point it at a file smaller than the block size (512 bytes), seems to wrap around in the source file when you try to read past the end.
00:10:27  ais523: It kind of reminds me of what game consoles and other memory mapped things do "naturally" when you have a fixed amount of address space bits connected to something with less physical address lines.
00:10:31  (Except this one isn't restricted to powers of two for the size of the thing it repeats.)
00:11:08  fizzie Do you know if I can make the umlbox script I'm running with python virtualenvs?
00:11:18  or any way to get the module working with umlbox
00:11:31  fizzie: right, this has been known to cause problems when games are moved to consoles with more memory (likewise for DOS programs running on a newer processor)
00:11:41  because it's quite easy to write a program to accidentally make use of addresses past the end of memory
00:11:50  and if they wrap rather than crashing, you won't notice until you move to a system with more memory
00:14:10  kurolox: In theory you should be able to run the venv activation script inside UML, assuming you've got the necessary directories mirrored from the host.
00:14:48 -!- tromp has quit (Ping timeout: 246 seconds).
00:14:53  I don't think there's any trivial way to "inherit" the virtualenv from outside, since there's no mechanism to pass environment variables in.
00:15:25  how would you do it? In order to activate it I would have to cd to the directory first, and as far as I know umlbox won't keep that cwd
00:16:33  Just run something like 'bash -c "cd /blah; source bin/activate; command --you=want"' instead of just command --you=want.
00:16:54  ais523: That reminds me of https://pbs.twimg.com/media/DHj4WQ_UAAAHg8v.jpg which I saw the other day.
00:17:25  (Or you can have a shell script that activates the virtualenv and runs the thing you want to run, and then run *that* with umlbox.)
00:17:51  shachaf: I vaguely remember compiler/OS combinations that put something meaningful at address 0 to catch that sort of issue
00:17:56  what OS is that screenshot from?
00:18:41 -!- tromp has joined.
00:19:29  oh well
00:19:46  I just realized that the bot needs internet in order to communicate with the servers, so I can't sandbox the whole bot
00:20:04  instead I would have to sandbox the part of the code where it runs arbitrary code, and for that I would need umlbox to work without -v
00:21:49  So, any idea fizzie?
00:22:14  in the worst case scenario I could probably make it work with -v and filtering out the output of umlbox
00:25:13  Well, I'm kinda tired so I'll ask you tomorrow. Thanks again for all the help fizzie!
00:25:15  kurolox: Well, I mean, you should definitely be able to hack it to make it work. For example, you can easily make init silent (just edit in init.c the lines  i = open("/console", O_RDONLY);  and  o = open("/console", O_WRONLY);  to open /dev/null instead), and add in umlbox script a kernel command line argument "console=tty1" to the end of the 'cmd' array to make the kernel messages go elsewhere too.
00:25:42  kurolox: if the bot's just connecting to IRC, you can normally just have the internet connection in a separate process and connecting to umlbox's stdin and stdout with pipes
00:26:02  thanks for the answers
00:26:24  ais523: umlbox has a TCP and Unix domain socket forwarding mechanism as well, incidentally.
00:26:39  (Based on multiplexing them over a single virtual tty.)
00:26:53  (With a piece of code running both inside and outside.)
00:26:57  the bot is actually for discord, but I could do that. However I was thinking that it would be a better idea to run the main bot outside of the sandbox and then make the bot run the code in a subprocess with popen, that launches umlbox
00:27:14  That's probably the more conventional way.
00:27:14  that way any code run from the bot can't edit the bot itself since I could make it read only
00:27:26  fizzie: well, the reason you'd do it that way would be to make it impossible for the bot to connect anywhere it wasn't supposed to
00:27:51  Well, see you tomorrow guys
00:28:11  I wonder if nesting UML kernels works. They were doing something moderately tricky about address spaces at some point in the past.
00:29:02  nesting valgrind works, IIRC, but has some special hacks to make it work
00:29:50  the problem with all these sorts of programs is that they tend to be written in a way that handles common cases, but really weird stuff can be much harder to handle
00:29:54  and yet the program does really weird things itself
00:30:07  Hmm, well, it didn't work out of the box (no pun intended).
00:30:10  Failed to get registers from stub, errno = 3
00:30:10  wait_stub_done : failed to wait for SIGTRAP, pid = 357, n = 357, errno = 0, status = 0x9
00:30:16  web of lies is very unlikely to be nestable, for example; the program I'm working on at work also isn't sanely nestable
00:31:47  Apparently at least at some point, you can do it, but the kernel you run inside UML needs to have been built with CONFIG_NEST_LEVEL=1.
00:32:02  So a single binary isn't nestable, but you can build UML kernels for specific nesting levels.
00:32:18 -!- kurolox has quit (Ping timeout: 252 seconds).
00:32:52  (Since this page says "the outer UML must be at least 2.4.18-22, which is not released at this writing, but will be soon", I'm not terribly confident this is true any more.)
00:39:52  ais523: Guessing Amiga Unix from the bit at the end?
00:40:21 -!- boily has joined.
00:42:50  `5 w
00:43:06  1/2:marmite//Marmite is a hive mind of fungal microorganisms spreading throughout the supermarkets of the Commonwealth. \ dentist//Dentists are professional workers whose main line of work is creating dents on various surfaces. \ \//\ was initially popular as a replacement for the solidus, but inevitably there was a backslash. \ anagol//anagol is A
00:43:48  OK, that backslash one is fairly funny
00:43:56  `n
00:43:57  2/2:narchy Golf, code golf server at http://golf.shinh.org/ \ intercal//INTERCAL has excellent features for modular program for the enterprise market.
00:44:12  his523.
00:44:14  still, I don't think this wisdom database has much to do with what the channel's originally meant to be about
00:44:32  that said, there's still enough ontopic dicussion to make the channel worthwhile, at least from time to time
00:51:04  I feel alienated here, like I'm not meant to be on this channel, talking.
00:52:09  I think I'd define the general on-topicality of this subject as being about programming languages and techniques that aren't typically needed or useful in serious programs
00:52:15  and umlbox is in that sphere at the moment
00:52:25  one problem with esolangs is that if an esolang gets popular enough, it stops being esoteric
00:52:30  (this may arguably have happened with Prolog)
00:52:35  rdochelloc.
00:52:39  umlbox?
00:52:50  boily: the sandbox that hackego uses
00:53:04  it's based on user mode linux
00:53:05  ais523: A language can be popular and not serious.
00:53:10  `? esolang
00:53:11  esolang? ¯\(°​_o)/¯
00:53:14  Come on, wisdom database.
00:53:28  shachaf: examples? I'm not sure I agree, at least for the usual definitions of "popular"
00:54:41  right. umlbox was explained to me multiple times already >_>'...
00:54:53 * boily 's brain defaults to UML diagrams. I've been tainted
00:55:07 -!- LKoen has joined.
00:55:21  boily: UML diagrams are the bane of everyone who tries to search the internet for User Mode Linux -related material.
00:55:53  UML is really weird as concepts go
00:56:11  the basic idea, of having a consistent syntax for allowing people to explain object oriented concepts to each other as diagrams, makes sense
00:56:35  but then if you have something like 8 types of diagram and some organizations try to write programs in UML first and then rewrite them in a language that can actually be run…
00:57:25  it's also way to highly dependent on concepts that don't actually apply in all languages
00:57:28  *too
00:57:53  helloochaf, fizziello, hellorcah.
00:58:12  UML “works” for Java and C++, and that's about it.
00:58:50  and for making shiny figures for ISO certification.
01:01:12  boily: Java, C++ and C# together form a very large proportion of the actual programming job market, though
01:02:20  and any language designed to interoperate with Java or C# will be able to support the concepts UML discusses, even if they aren't idiomatic
01:04:17  true.
01:11:21  ais523: I was going by what you said, but maybe I didn't read it precisely.
01:23:29 -!- sleffy has quit (Ping timeout: 248 seconds).
01:27:08 -!- doesthiswork has joined.
01:28:50 -!- imode has joined.
01:32:40  hi imode
01:33:44  hi rdococ.
01:48:24 -!- LKoen has quit (Quit: “It’s only logical. First you learn to talk, then you learn to think. Too bad it’s not the other way round.”).
01:59:20 -!- Sgeo has quit (Ping timeout: 240 seconds).
02:10:55 -!- Antoxyde has quit (Quit: Leaving).
02:17:42  Do you know if there is such a thing in GURPS as a switchable advantage that has no effect?
02:20:36 -!- wob_jonas has joined.
02:21:08  11:53 / 31:03
02:21:08  ais523: I did a search. https://scifi.stackexchange.com/a/117785/4918 Wizard of Oz: “The Witch was too much afraid of the dark to dare go in Dorothy's room at night to take the shoes, and her dread of water was greater than her fear of the dark, so she never came near when Dorothy was bathing.”
02:21:37  huh, interesting
02:21:40  although probably not widely known
02:23:11  I did know the witch doesn't like water, just like many undead, I even have a ticket on the old tracker for it, but I didn't remember he's afraid of the dark.
02:23:19  that's an actual quote according to https://en.wikisource.org/wiki/The_Wonderful_Wizard_of_Oz/Chapter_12 by the way
02:26:24  You could make that if you want to make them not go into dark but also not going into the water, I suppose?
02:27:43  well, I had a proposal to make most of the undead not go into water, although that really depends on which legend about undead you look at
02:28:12  the undead in the Arany János ballad “A hamis tanú” specifically goes only in the river
02:29:12  and it's also corporeal (unlike, say, Moaning Myrtle's ghost) and not of some water-based creature type like the skeleton fish in super mario
02:39:02  actually, they're just normal fish I chewed alive because they're so tasty when fresh
02:39:52  rdococ: that doesn't explain why they're immune to fire unlike most fish in some of the mario games
02:40:55  because they're bone
02:40:55  duh
02:41:21  and they're in water
02:41:54  Actually, I think it's because an evil wizard placed a voodoo curse on a shark to force the skelefish to become immune to fire.
02:51:31  wob_jonas: I think the most common legend related to the undead and water is that vampires can't cross running water under their own power
02:51:42  (although it's possible for someone else to carry the vampire across)
02:53:01  Wow. The undead are weak to everything these days. Water, fire, ice...
02:53:16  Lightning - though, sometimes that's how they're created in the first place...
02:53:16  are there any stories with some kind of vampire carrying service?
02:53:34  well, the typical niche that undead play in stories, when they're just an enemy, is that they're very hard to stop unless you exploit a specific weakness
02:53:49  ais523: yes, but there are similar legends about some undead other than water too
02:53:55  so that means that they need a lot of weaknesses for the stories to work correctly
02:53:59  ais523: Discworld has that legend about zombies
02:54:15  A specific weakness such as the weakness that exists in two thirds of all human beings?
02:54:46  which is played for laugh when someone wants to use it as a test for zombies but misinterprets "undead can't pass over water" as "undead can't pass water" (as in pee)
02:55:05  rdococ: it's more that they're resistant to almost everything, so anything that they aren't resistant to counts as a weakness by comparison
02:56:08  ais523: wouldn't that mean the water would have to be damaging in the first place to even affect them?
02:56:09  ais523: and there's all the modern myths about water test used in medieval witch hunt, in which the people throw someone to the river, and if they don't drown because the pure water hates them so much it expels them, they're a witch
02:56:48  the tests are exaggerated, but it is based on an authentic legend about witches and pure water. the actual tests were probably more gentle and stopped before drowning
02:57:12 -!- boily has quit (Quit: TRICK CHICKEN).
02:57:12  yes, people like to exaggerate ancient witch tests because it's funny to think "if the test doesn't kill them, we execute them"
02:57:18  ais523: "it's more that they're resistant to almost everything, so anything that they aren't resistant to counts as a weakness by comparison" => yes, I have one like that:
02:57:19  but the flaw in such a test would become obvious very quickly
03:00:45  Vampires are immortal, which means the only way to kill them is… [choose one] {A silver bullet, A stake through their heart, Bright light, Garlic, Holy water, Holy wafers sewn in their mouth, A chainsaw, Cutting their supply of blood, The crow of a rooster, Water, Fire, Magic, In their bat form, By accident, Killing their elders first, Making them 
03:00:45  pop culture icons}
03:01:25  Other sorts of undead have so many resistances that they seem to be unkillable too, including werewolves, zombies, and ghosts.
03:01:30 -!- ATMunn has quit (Quit: See ya! o/).
03:02:34  ais523: yes, and although it's funny that witches can float on water because the water hates them, and seems more like a strength than a weakness, it does actually make more sense that the more modern legends
03:02:38  werewolves aren't a sort of undead?
03:03:11  the undead in “A hamis tanú” actually probably also works in that way, with the water and everything else hating its body
03:04:38  it's just that in modern times, a humanoid that can float on water was no longer too strange, and for an undead that normally flies or floats above ground it's even more irrelevant (mind you, in D&D, even for living people it's harder to magically fly over water than to magically fly over land, for some reason)
03:04:44  so they changed the myth
03:04:58  ais523: in some legends about werewolves, it is an undead, yes. the nethack werewolf isn't.
03:05:18  the Harry Potter werewolf is also not an undead
03:05:25  I'm not aware of any legends where werewolves are undead (in the sense of "monster mostly formed of the corpse or spirit of a dead human")
03:06:04  let me search
03:06:09  wob_jonas: in Battle for Wesnoth, spirits get a reduced flying movement rate over water (although they don't get a dodge penalty, like walking through water gives you); I think it might be for balance reasons
03:06:33  it's probably rarer than undead vampires, which is the norm
03:06:42  and undead witches, which is an authentic legend
03:07:27  in the sense that the body or part of the body of witches is supposed to be cold, which made sense as a secret hard to test feature back before thermometers
03:08:26  undead werewolf might actually be a modern legend, but then the whole general category of undead is probably modern too
03:09:50  I was wrong
03:09:58  apparently werewolves are never truly undead
03:10:13  they just gained a few vampire traits that make them seem a little like undead
03:10:16  but they are living actually
03:11:06  oh, I'm a fool
03:11:41  there's one fictional creature that is unquestionable afraid of the dark in first place, as opposed to damaged by the dark quickly or slowly or avoiding dark or anything like that
03:11:59  ais523: Are esoteric non-programming things ontopic in here?
03:12:52  shachaf: esotericism almost certainly isn't; things that aren't directly related to programming but are weird enough to be interesting would probably not be objected to even though they aren't technically on topic
03:13:08  ais523: the intelligent people of Lagash/Kaglash in the Asimov story “Nightfall” and its novellization with the same title
03:13:15  For example, esoteric financial instruments?
03:13:23  with a channel like this, you have three bands, I think: "on topic", "off topic but tolerated/enjoyed by the community", "off topic and you're told to stop"
03:13:31  ais523: they're afraid of the dark for psychological reasons, even though they're not actually directly damaged by the darkness
03:13:39  I think it's possible that most people here just don't care about financial instruments
03:13:41  I remember seeing a proposal that all finanical instruments should be written in Python in order to make them unambiguous
03:13:45  so maybe they are a subset of programming :-D
03:13:47  when they go to a dark place for more than a few minutes, they get really scared and may start to panic
03:13:57  Python? No thanks
03:14:08  shachaf: yes, my reaction was "why Python?"
03:14:10  this needs strong darkness, not just under the trees at dusk
03:14:16  I guess it's fairly easy to read for somoene who doesn't know it?
03:14:35  Obviously they should use a JavaScript derivative
03:14:47  unlike the APL family of languages (including things like Jelly), which are famously hard to read if you don't know them
03:15:01  Like Ethereum, or whatever that thing is
03:15:09  shachaf: it's called Solidity
03:15:10  not even joking
03:15:18  Oh, right
03:15:22  I thought that was hilarious in the context of our site…
03:15:23  I guess that makes it ontopic
03:15:28  they're unlikely to appear on Earth, partly because they don't do spacefaring, partly because they fear the dark and the Earth has dark parts, and partly because this plays "a long long time ago, in a galaxy far away", and they might also be incompatible with Earth's chemical environment or gravity
03:15:49  but yes, Solidity would almost certainly be considered an esolang if not for perhaps being too widly used
03:16:00  what other programming languages have semantics where using them inherently requires spending money?
03:16:02  but it's not completely impossible to find them on Earth, especially not in a nethack dungeon that already has the widest variety of creatures that you wouldn't really suppose to find there
03:16:21  (I mean, seriously, Green-elves? Green elves are elves who live in a *forest* by definition.)
03:16:37  ais523: Is solidity the opposite of liquidity?
03:17:02  ais523: yes, it's probably easy to read, but you can also find summaries of it because it's a good and popular enough book, and the summaries are probably enough for adding them to nethack
03:17:02  Liquidity is a fascinating subject in finance. I should learn more about it.
03:18:34  the general concept is simple enough
03:18:48  ais523: well, you probably need to know a bit more than what I told about them
03:18:57  if you have money but can't spend it, are you actually rich?
03:19:07  it's pretty philosophically interesting though when you put it like that
03:19:29  they live on a planet with five or six suns in a strange orbit where you never have all of them under the horizon at the same time anywhere on the planet
03:19:41  which is why they are not used to darkness
03:19:55  How do you measure liquidity?
03:20:18  so they call it "night" when the big sun is not in the sky
03:20:21  shachaf: normally the amount of money that you could theoretically spend on short notice
03:20:34  I tried to invent a financial instrument that can let a name assign a price to expected liquidity
03:20:42  including via selling things if you can sell them quickly
03:20:52  But it's hard because liquidity is a multidimensional thing.
03:20:56  they like to always have at least a little lamp lit in their houses, but that's mostly symbolic, because even if that lamp goes off, they get enough light through the windows
03:21:43  and the story is about a certain even that happens once every two thousand years, when a significant part of the planet goes totally dark because the only sun is eclipsed by a moon
03:22:04  Do you know how block (I.e
03:22:27  the civilization doesn't expect this because don't know about the moon because it's normally invisible because of the sun glare,
03:22:34  large) trades are made? That's a big part of the liquidity story, I suppose.
03:22:53  shachaf: no
03:22:59  and they have just enough astronomy to predict the movement of the suns but not enough to figure out the moon from its gravity effects
03:23:21  so there's only an ancient legend about that total darkness and many people don't believe that legend
03:23:33  I do know that there are companies who are willing to trade capital for liquidity (i.e. they'll buy things that are hard to sell, at less than the full price that could be gotten for a trade negotiated over a long time)
03:23:40  and when the total darkness happens, they see the stars for the first time,
03:24:05  actually there's a company advertising on television in the UK, and the adverts state that they'll buy cars from you for less than they're worth but with a very quick turnaround
03:24:10  which has a great effect on them just like how the discovery of a large universe had a great effect on the Krikket people in HHGG
03:24:19  so I guess capital-for-liquidity trades are available to the general public too, at least in one direction
03:24:48  but instead of starting a war against the rest of the world, they go crazy and start to burn their own world to create light from the temporary flames,
03:24:55  and destroy much of their own civilization
03:25:35  but the short story is good so you might want to read it anyway even after I spoiled most of it
03:25:44  (I didn't spoil everything, but still)
03:25:51  (I got pretty close)
03:27:06  Which one?
03:27:33  I didn't read the past few pages of text in much detail because I was using my phone.
03:27:37  shachaf: who was that directed at?
03:27:42  Which story.
03:28:37  ais523: Pretty much every trade you ever make involves trading capaital for liquidity to some degree.
03:29:01  ais523: yes, and this service is also offered to the population for gold and silver (jewlery but also scrap gold), but in the form of quickly buying the gold or silver at half price, and in the form of quickly giving a short term loan of say a tenth of the price of the gold but a loan that you aren't required to pay off if you don't want the gold b
03:29:01  ack
03:29:03  Crossing networks are interesting. Do people use them?
03:29:45  ais523: they can do this with good rates because it's easy to quickly test for gold content, much more so than quickly testing the value of a used car
03:30:22  it's also done for some other sorts of valuables that are easy to test and people often have it, but gold and silver are the most important
03:30:25  I'm not sure of the exact definition of "liquidity" in general use, but I use it with the rough meaning "ability to trade"
03:30:59  The ability to trade is almost always valuable, so someone almost always pays for it, though the way they pay for it might not be obvious.
03:31:36  ais523: so anyway, if you want a nh monster that can wander around in a lit room but doesn't go in dark corridors, then I think a person from Lagash would work
03:31:51  There are many different ways that you might want to trade, so there are many different types of liquidity. But they're usually related.
03:32:21  and they're easy to add because we know so little about them, such as their body and physical capabilities, that you can invent close to anything you need for game reasons
03:33:21  you usually find out very little about the physical characteristics of characters in Asimov's books, but most of them are at least humans or humanoid robots, while the Lagash people have no reason to be close to that
03:33:59  `? solidity
03:34:00  solidity? ¯\(°​_o)/¯
03:35:50  so you're restricted very little about the nh character. they have to be intelligent and motile, but they could have any size, shape of body, almost any item use capabilities except they're certainly not zero carrying cap, a wide choice in attacks and resistances
03:35:57  (definitely not fire resistant)
03:36:27  oh, and definitely not blind.
03:36:33  they probably don't like to be blinded
03:36:36  really don't like
03:37:23  if you blind them, I expect they go into a rage of panic, although they may have resistance against blinding by bright light and may be able to wipe off cream pies and perhaps even ravens can't blind them
03:37:48  perfect if you want to make a nethack monster
03:38:52  I don't think the race has a well-known name, but Lagashian would probably work if you explain it in the 'cyclopedia
03:39:22  `learn Solidity is an esolang for writing contracts. It has good support for secure linear algebra.
03:39:26  Learned 'solidity': Solidity is an esolang for writing contracts. It has good support for secure linear algebra.
03:39:27  oerjan: please improve twh
03:39:43  ais523: does that help?
03:40:12  wob_jonas: perhaps; I'm not sure if this would work directly but it's given me some thoughts
03:40:43  well, I don't know your gameplay mechanical motivations, so they might fail for that reason
03:40:44  thanks for your input, anyway
03:42:40  (there's also a story about humans collectively panicking when darkness falls, but they weren't afraid as such, it's just that the Sun unexpectedly went out at some point and stayed dark for several days)
03:42:51  (that's definitely not what you want)
03:43:30  I can see why it would induce panic, though
03:43:38 -!- Sgeo has joined.
03:44:41  right, and it was mostly the sensible kind of panic, when everyone tried to rob stockpiles of food
03:44:58  and prepare for an inevitable war
03:45:12  I assume it relit again at some point?
03:45:27  yes
03:45:58  which didn't *completely* calm people down, because after that, you expect another similar event, but yeah
03:57:18  wob_jonas: are you thinking Nightfall?
04:39:40 -!- mpm has joined.
04:43:29 -!- mpm has quit (Client Quit).
04:44:49 -!- Sgeo has quit (Quit: Leaving).
04:49:47 -!- Sgeo has joined.
05:16:05 <\oren\> literally unplayable http://imgur.com/6ByIhNT
05:18:57 <\oren\> "21th century"
05:23:00 -!- atslash has joined.
06:13:34  pikhq: whoa, the chicken chicken chicken paper is by dougz
06:14:38  Yeah, it is.
06:17:04  I think I knew that at one point.
06:17:30  This picture is TG: https://scontent-sjc2-1.xx.fbcdn.net/v/t31.0-8/21014227_1567793873283268_4987278837085860246_o.jpg?oh=414f17cce92053674421e37ed33642e1&oe=5A613408
06:17:36  On the topic of chickens.
06:19:12  Ah, chicken of the woods.
06:24:31  Someone won the chicken lottery.
06:24:39  Do you like mushrooms?
06:34:46 -!- erkin has joined.
06:35:36  [wiki] [[Special:Log/newusers]] create  * Motekye *  New user account
06:35:42 -!- zseri has joined.
06:37:11 -!- doesthiswork has quit (Quit: Leaving.).
06:39:55 -!- sleffy has joined.
06:42:50  [wiki] [[Esolang:Introduce yourself]]  https://esolangs.org/w/index.php?diff=52923&oldid=52920 * Motekye * (+252) /* Introductions */
06:47:04 -!- zseri has quit (Ping timeout: 260 seconds).
06:51:56  [wiki] [[B1nary]]  https://esolangs.org/w/index.php?diff=52924&oldid=52916 * UtilityHotbar * (+1) /* Output */
06:52:43  [wiki] [[B1nary]]  https://esolangs.org/w/index.php?diff=52925&oldid=52924 * UtilityHotbar * (+98) /* Loops: */
06:54:55  [wiki] [[B1nary]]  https://esolangs.org/w/index.php?diff=52926&oldid=52925 * UtilityHotbar * (+46) /* Interpreters: */
07:00:18  [wiki] [[Special:Log/abusefilter]] modify  * Ais523 *  modified [[Special:AbuseFilter/5]] ([[Special:AbuseFilter/history/5/diff/prev/59]])
07:00:40 -!- heroux has joined.
07:00:41  the specific strain of spambots that was stopping don't seem to be around, and it was hitting false positives
07:06:01 -!- FreeFull has quit.
07:14:28 -!- imode has quit (Ping timeout: 276 seconds).
07:30:41  [wiki] [[Special:Log/newusers]] create  * Mypalmike *  New user account
07:37:20  [wiki] [[Esolang:Introduce yourself]]  https://esolangs.org/w/index.php?diff=52927&oldid=52923 * Mypalmike * (+323) Hi there.
07:51:45 -!- ais523 has quit (Ping timeout: 252 seconds).
07:52:03  [wiki] [[Special:Log/upload]] upload  * Mypalmike *  uploaded "[[File:Add1.ska.png.png]]"
07:56:02 -!- augur has quit (Remote host closed the connection).
07:56:27 -!- ais523 has joined.
08:05:25  [wiki] [[Skastic]] N https://esolangs.org/w/index.php?oldid=52929 * Mypalmike * (+622) Initial description
08:06:47  [wiki] [[Language list]] M https://esolangs.org/w/index.php?diff=52930&oldid=52900 * Mypalmike * (+14) add skastic
08:07:30  [wiki] [[Skastic]]  https://esolangs.org/w/index.php?diff=52931&oldid=52929 * Mypalmike * (-30) 
08:10:07  [wiki] [[Skastic]]  https://esolangs.org/w/index.php?diff=52932&oldid=52931 * Mypalmike * (-3) 
08:23:02 -!- ais523 has quit.
08:35:29 -!- sleffy has quit (Ping timeout: 248 seconds).
08:36:05 -!- augur has joined.
08:40:17 -!- augur has quit (Ping timeout: 248 seconds).
08:53:40 -!- augur has joined.
08:55:14 -!- augur has quit (Read error: Connection reset by peer).
08:55:38 -!- augur has joined.
09:01:19  alercah: yes, I did specifically say Nightfall above
09:01:58  alerchah: um wait, I mean Nightfall is the first story, it's not the second one
09:06:53 -!- augur has quit (Remote host closed the connection).
09:12:15 -!- augur has joined.
09:15:33 -!- ais523 has joined.
09:16:31 -!- augur has quit (Ping timeout: 248 seconds).
09:18:17  oerjan: Did you play the Magnet game?
09:18:30  Magnets
10:30:24 -!- kurolox has joined.
10:42:42  That doesn't look nearly as awful as CLOP.
10:44:01  Good morning!
10:51:09  Hey fizzie, do you think that you could help me with those hacks you mentioned yesterday? I've tried changing the init.c to /dev/null like you said, but I don't see any difference in the output. Besides that, umlbox works perfectly for what I've seen.
11:00:21  Did you re-make umlbox-initrd.gz? 
11:02:08 -!- augur has joined.
11:05:29  uh, no. I did a make all and a make install, but considering that for some reason that file seems to not work with that, I'll make it individually again
11:06:23 -!- augur has quit (Ping timeout: 248 seconds).
11:06:37  kurolox: Oh, right, it's not that, it's because /dev isn't mounted by that time. Well, then the change will be a little more complicated: http://sprunge.us/hKaK
11:07:07  (You'll still need mknod /console for the command output to go to.)
11:07:41  By the way, will any of the fixes you've made go to umlbox in the future?
11:09:04  Well, with that a part of the messages went again
11:09:22  I was thinking of sending a bitbucket pull request for at least the config file padding and the mudem compilation issue.
11:09:46  https://ghostbin.com/paste/t3ajv
11:10:08  I asked moony to test the file padding fix, but he never told me if it worked or if he tried it
11:10:23  If you use --debug instead of -v, you should get rid of lines 2-23.
11:11:02  yep, there are still some stuff left
11:11:08  And by the way, I built 4.12.8, and had the same config file wrapping thing, but not the "output isn't shown" one.
11:11:24  I must be cursed then
11:11:34  maybe it's an arch issue?
11:11:40  but I think that moony is using it too
11:11:54  Yes, it's very odd.
11:12:04  https://ghostbin.com/paste/rhhep
11:12:50  What's left is the kernel logs, and that "UMLBox starting" note. I've been trying to figure out the proper kernel command line parameter to put those somewhere else, so far without luck.
11:13:38  Although it occurs to me that an easier way could've been just swapping "con" and "con1" in the umlbox script.
11:13:41 -!- heroux has quit (Ping timeout: 240 seconds).
11:14:10  I'll try that then
11:14:50  That is, go from   "con1=" + childStdin + ",fd:" + str(childStdout), "con=null," + stdoutws   to   "con1=null," + stdoutws, "con=" + childStdin + ",fd:" + str(childStdout)
11:17:29  I think we modified that yesterday while trying to get output
11:18:20  it looks like "con1=" + childStdin + ",fd" + str(childStdout), to me
11:18:31  sorry, ",fd:"
11:19:14  Isn't that the same as what I said? 
11:19:39  oh, sorry. I was confused because I wasn't seeing con2 there, and con2 is between con1 and con=null
11:20:17  Right, con2 shouldn't really matter. It's the tty for umlbox-mudem, which isn't used unless you want to forward network ports.
11:21:25  well, the output is shorter, but it doesn't work
11:21:51  does the order matter? I only renamed con to con1 and vice versa
11:22:08  I would hope it doesn't.
11:22:18  You'll probably still have to keep using --debug to keep the stdout open, and you'll likely have to undo the "input ../console" and "output ../console" back to "input ../tty1" and "output ../tty1" to see the command output again.
11:22:25  https://ghostbin.com/paste/7eety
11:22:43 -!- augur has joined.
11:22:47  oh sorry
11:22:52  I used -v again due to being used to it
11:24:13  okay, I changed it back
11:24:17  this is what I get
11:24:31  https://ghostbin.com/paste/amn2n
11:24:33  it's almost there
11:25:37  Yeah. The "UMLBox starting" line you could probably just comment out of init.c, and re-make.
11:26:41 -!- augur has quit (Ping timeout: 240 seconds).
11:27:23  yes, that works
11:27:27  there are only a few lines left
11:30:01  Yeah, unfortunately I'm not sure what to do about them. They're produced by printf calls from arch/um/os-Linux/start_up.c, arch/um/os-Linux/mem.c and arch/um/kernel/um_arch.c.
11:30:15  I mean, if you really feel like it, you can comment them out *there* and rebuild the kernel.
11:31:21 -!- S1 has joined.
11:32:01  The more reasonable way would be to do what the umlbox script is *normally* doing, but that's exactly the thing that for some weird reason isn't working for you.
11:32:13  talking about things not working for me
11:32:26  it seems like if the bot uses umlbox it doesn't work
11:32:40  http://i.imgur.com/MgndDub.png
11:33:08  it was working before we did any of the changes
11:33:23  so some change must've broke it for the bot
11:34:33  This was what the bot was trying to print before any of the changes, you can see that in the line 142 the command worked (the cwd was /horus) https://ghostbin.com/paste/5n6eo
11:35:25 -!- boily has joined.
11:36:15  Well, I'm a little out of ideas, seeing as we've spent the last half an hour explicitly trying to disable all debugging output. Also have to get to work again. But I guess you can try undoing things and seeing what happens.
11:36:37  `grwp bell
11:36:43  I think it's not the most efficient thing, but I can try to filter the stuff with regex
11:36:47  dingas:The sound of a Baltic bell. It chimes like potatoes. \ obell:The obell is what we ring each time a new strip of the o webcomic is published. \ precious:precious? That doesn't ring a bell. ¯\(°​_o)/¯ \ shachaf:Queen Shachaf of the Dawn sprø som selleri and cosplays Nepeta Leijon on weekends. He hates bell peppers with a passion. He does
11:36:49  doing all python side
11:39:07 -!- Antoxyde has joined.
11:43:24 -!- augur has joined.
11:46:21 -!- heroux has joined.
11:47:59 -!- augur has quit (Ping timeout: 248 seconds).
11:55:35 -!- MrBismuth has quit (Ping timeout: 246 seconds).
12:04:00 -!- augur has joined.
12:11:41 -!- augur has quit (Ping timeout: 246 seconds).
12:13:48 -!- ais523 has quit.
12:19:58 -!- boily has quit (Quit: NITRATE CHICKEN).
12:25:22 -!- TieSoul has joined.
12:43:11 -!- LKoen has joined.
13:03:57 -!- atslash has quit (Ping timeout: 240 seconds).
13:12:11 -!- atslash has joined.
13:14:09 -!- callum_ has joined.
13:16:28 -!- callum_ has quit (Client Quit).
13:29:10 -!- MrBismuth has joined.
13:45:35 -!- S1 has quit (Ping timeout: 255 seconds).
14:00:30 -!- doesthiswork has joined.
14:08:08 -!- augur has joined.
14:12:40 -!- augur has quit (Ping timeout: 255 seconds).
14:13:26 -!- ATMunn has joined.
14:38:58 -!- doesthiswork has quit (Quit: Leaving.).
14:39:47 -!- zseri has joined.
14:40:34  hi
14:46:46 -!- `^_^v has joined.
14:54:25  ...
14:55:56  Concept: a language whose programs are a binary tree
14:56:19  Like iota?
14:56:28  I guess
14:56:58  Or any of those combinator languages
14:59:12  moo
15:01:22  MoOOOOOOOOOOoooooooou.
15:12:24 -!- erkin has quit (Quit: Ouch! Got SIGABRT, dying...).
15:35:43 -!- AnotherTest has joined.
16:12:50 -!- LKoen has quit (Remote host closed the connection).
16:40:47 -!- augur has joined.
16:44:57  fizzie since I believe that arch might be causing the issues, I've installed debian on my laptop/server. I'm trying to install umlbox on it, applying most of the fixes you gave me (I've got it to build properly), but I'm getting this when trying umlbox
16:45:33  https://ghostbin.com/paste/ep4uc
16:52:34  nevermind fizzie, it was a typo I made when applying fixes. Sorry.
16:53:11  fizzie in debian umlbox works properly, so the issue is caused by Arch most likely
16:55:47  I'm working on a concept for a BF derivative which works on a queue.
16:56:26  Unfortunately, that means it's already obviously TC... well, if I include looping instructions
16:56:32  but will I? mw ha ha ha :P
17:01:27 -!- imode has joined.
17:02:45  ARGH! I think my ISP is causing routing problems again
17:02:56  imodium
17:03:02  either that or DNS problems
17:03:21 * rdococ hugs wob_jonas
17:03:32 -!- FreeFull has joined.
17:03:45  FreeFull.
17:03:53  rdococ:
17:03:59  ExpensiveEmpty:
17:04:08  Nah
17:04:25  CheapHalfFull:
17:04:31  DNS problems apparently
17:04:38  PricelessBottomlessAbyss:
17:08:43  wob_jonas: ah reading fail
17:10:09  hmm... it's possible that the problem isn't on my side this time
17:10:29  I mean, that it isn't on the side of my ISP this time
17:11:11  also, isup.me is sometimes giving timeouts for me, which is scary
17:11:48  rdococ: yello.
17:12:37  Well fizzie, if anything it seems like it breaks with virtualenvs
17:13:44  http://i.imgur.com/qHm2eb0.png
17:18:48  well I can't tell on which side the error is
17:23:28  hi
17:41:33  I just had a thought.
17:42:00  I know there are many brainfuck derivatives, but let's just be shocked, surprised, and eternally grateful that no languages have been based on ut yet.
17:49:47 -!- erkin has joined.
17:50:28  By the way, where was fungot tested?
17:50:28  rdococ: hey, t-rex, i've a long road ahead of me, it would be flattering. they'd failed to deliver it to the king of all that i survey! i am a good friend, t-rex, but, uh,
18:04:17  [wiki] [[3D]]  https://esolangs.org/w/index.php?diff=52933&oldid=19990 * Programmer5000 * (-19) 
18:15:58 -!- Phantom_Hoover has joined.
18:18:49 -!- augur has quit (Remote host closed the connection).
18:21:16 -!- joast has quit (Quit: Leaving.).
18:22:19 -!- Sgeo has quit (Ping timeout: 240 seconds).
18:22:30 -!- joast has joined.
18:34:16 -!- augur has joined.
18:38:39 -!- augur has quit (Ping timeout: 248 seconds).
18:48:18 -!- Sgeo has joined.
18:50:34 -!- Sgeo_ has joined.
18:52:35 -!- Sgeo has quit (Ping timeout: 240 seconds).
19:09:50  Well fizzie, I feel like I should show you the result of all the help you've offered to me the last days
19:10:54 -!- erkin has quit (Quit: Ouch! Got SIGABRT, dying...).
19:12:09  http://i.imgur.com/jCYgJNw.png
19:16:21 -!- LKoen has joined.
19:30:21 -!- LKoen has quit (Remote host closed the connection).
19:45:30  Concept: values which can either be 3 or 2 - as in, "x == (3 or 2)" will return true whether x == 3 or x == 2
19:49:07 -!- Cale has quit (Remote host closed the connection).
19:51:48  Would a dialect of BF in which the angled brackets must be balanced be TC?
19:52:13  e.g. >< is valid, but >> isn't. >[<] wouldn't be valid, either, but >+<[>-<] would be (if a bit redundant :P)
19:52:13  balanced together with square brackets or separately?
19:52:17  if together, it's not TC
19:52:30  I don't know what you mean.
19:52:41  is [>]< valid?
19:52:46  no
19:52:52  ...ah.
19:53:31  if separately, then surely it's not a serious limitation, you just put a zillion > to the start of the program and a zillion < to the end of the program and that fixes all the balance
19:54:05  true
19:54:13  is there a proof that balancing them together isn't TC?
19:54:29  think about it yourself, I don't want to spoil it early
19:54:31  it's not hard
19:55:04  hm
19:55:45  Don't you know that I'm an idiot?
19:56:42  I guess you couldn't move the cell you were checking in a while loop.
19:57:02  Which means that the number of cell spaces you can move would be limited to the number of >s.
19:57:14  Even then, with unbounded cells...
20:02:20 -!- LKoen has joined.
20:03:42 -!- Cale has joined.
20:06:09 -!- sleffy has joined.
20:12:49 -!- sleffy has quit (Quit: Leaving).
20:13:07 -!- sleffy has joined.
20:29:24 -!- sleffy has quit (Quit: Leaving).
20:29:44 -!- sleffy has joined.
20:36:00 -!- LKoen has quit (Remote host closed the connection).
20:36:06 <\oren\> AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAa
20:36:28 <\oren\> you foooooools! SUNDAY IS THE LAST DAY OF THE WEEK, NOT THE FIRST
20:37:05 <\oren\> if it was the first day of the week, then the weekend would be friday and saturday, and you would work sunday to thurday!
20:37:14  \oren\: Sunday is definitely the first day of the week.
20:37:35 <\oren\> shachaf: no, sunday is part of the weekend!
20:37:50 <\oren\> and therefore the week begins on monay
20:38:02 -!- LKoen has joined.
20:38:10  The weekend is a vague blob around the boundary between weeks
20:38:31 <\oren\> the weekend id  the last two days of the week, saturday and sunday
20:38:43  No, the week goes Sunday, Monday, Tuesday, ...
20:38:52  Or, as they're called in Hebrew, Firstday, Secondday, Thirdday, ...
20:39:04 <\oren\> well hebrew is wrong then
20:39:07  In German, Wednesday is called "midweek"
20:39:13  Because it's in the middle of the week.
20:39:19  Because the week starts on Sunday.
20:39:33  shachaf: in germany, the week starts on monday
20:39:53  wednesday is the mid of the week, because saturday and sunday is the weekend :p
20:40:04  It's not called "midworkweek"
20:40:06  shachaf: numbers for week days is great, and several languages uses it for at least some of the days, but it's a bad choice because some languages use sunday=0 and some use sunday=1
20:40:09 <\oren\> shachaf: do you report to work each sunday in Israel?
20:40:25  the standard choice these days is sunday=0 or sunday=7, but we don't change the names based on them
20:40:31  Yes, the weekend in Israel is Friday-Saturday
20:40:52  yeah, names originating from midweek are also used for both thursday and wednesday
20:41:23  " It's not called "midworkweek"" => that wouldn't even make sense. the concept of only five workdays per week is much newer than the names in almost any languages
20:42:02  wob_jonas: Right, so Wednesday being the middle of the Mon-Fri week doesn't make sense.
20:43:30  I personally like the classical alchemical association of days of week with the antique metals and panets. See https://en.wikipedia.org/wiki/Metals_of_antiquity#Symbolism for a table.
20:45:35  also, the problem with trying to decide whether the week starts with sunday or monday has the problem that not only the choice is very much culturally ingrained in many places and changing it would be confusing because people would misread calendars, but also that both choices have a religious motivation that people could be sensitive about.
20:47:24  the metal association is great, because most languages already have distinctive words for the seven classical metals, so it's easy to make up names for the days of week based on them
20:48:06  Man, can you believe religion is so popular?
20:48:09  It's so bizarre.
20:49:41  shachaf: the religion doesn't even really matter. some of the religious culture remains even without the religion, i.e. in people who don't believe in the religion, and that can still matter here
20:49:48  tradition and stuff
20:50:18  also, some of the languages already use the classical planet association for naming some of the days
20:51:21  there's just one slight problem: apparently traditional Chinese medicine associates gold with Venus instead of with the Sun, which could be confusing
20:52:13  https://kate.io/blog/2017/08/22/weird-python-integers/
20:52:33 <\oren\> "Slavic languages implicitly number Monday as day number one"
20:56:39 -!- LKoen has quit (Remote host closed the connection).
20:57:32  shachaf: woah
20:57:57  leave me alone
21:01:32  Okay, okay, wait. Was that "leave me alone" because my message didn't have enough information in it, or just because you hold a grudge? I'm not trying to be rude, I sincerely want to know because I just want to be friends.
21:02:27  (Granted that " It's so bizarre." only has slightly more information in it, but that's besides the point.)
21:07:03  Of course I hold a grudge.
21:08:44  I don't want to be your friend, I want you to leave me alone. You can't expect everything you say to be taken independently of everything else.
21:10:29  itc: awkward people having awkward conversations.
21:13:11  What did I even do to you?
21:19:20 <\oren\> rdococ: I am also confused
21:19:41  I had always thought that shachaf hated me for a reason...
21:19:43 -!- TieSoul has quit (Quit: Leaving).
21:20:04  I wondered on how I could improve on that, hopefully becoming a better person myself... but now I'm just... speechless.
21:20:16  Not literally speechless, I can still type words here, but you know what I mean.
21:21:11  A while back I decided that I would try to increase the length of every message I sent here - I thought the reason shachaf hated me was because they sore what I was typing as spammish, so I resolved to attempt to reduce that.
21:21:40  But... is it even worth trying anymore?
21:21:44  shachaf: that doesn't seem strange to me, because ruby integers work similarly, except that there every integer up to like 2**30 or 2**62 (depending on pointer size) is a small integer. I think even some schemes work like that too, with the eq? operator.
21:22:57  wob_jonas: But those aren't heap objects that can be mutated, are they?
21:23:17  shachaf: yes, those aren't
21:24:23  strangely, in ruby, true and false and nil are also handled specially as not pointing to real objects, even though there doesn't seem to be a reason for that. I think it would be easier to handle them as singleton statically allocated objects.
21:24:30 <\oren\> but... but why are integers heap objects anyway? would it not be faster to keep them mutable?
21:24:47  Look, do whatever you want.
21:24:57  \oren\: large integers have to be heap objects because they're bignums and can't be stored in a word
21:25:16 <\oren\> right, but why would small integers be heap objects
21:25:37  also, all of this is about ruby 1.8, there's been internals changes since then that I didn't follow much
21:25:40 <\oren\> why is there an specific address whre the number 7 is stored
21:26:07  I know the way it stores code has been replaced by some much more insane mechanism, and I don't understand why. apparently they bought into the "bytecode" buzzword or something.
21:26:30 <\oren\> oh god did they roll their own bytecode
21:26:43  \oren\: for sparing memory and cache. there are often many copies of the number 7 alive, and creating a new object for it every time would be wasteful
21:26:49  in python that is
21:27:01  in ruby small integers aren't pointing to any object
21:27:09 <\oren\> wob_jonas: but all teh pointers to 7 are 64 bits anyway
21:27:50 <\oren\> hmmmmm unlesss
21:27:56  in ruby, the objects are either pointers (16-aligned) to a real object, or small values for a few special objects like nil, false, true, and a few more, or odd numbers for representing a small integer, or numbers that are IIRC 15 mod 16 for symbol objects
21:28:19  \oren\: sure, the pointers themselves are, but you don't need separate copies of what it points to
21:28:51  it's not the pointers themselves that get smaller, but the pointed objects. those still take up memory and cache and malloc time
21:28:54  mostly cache
21:29:11 <\oren\> but why is 7 a pointed-to object?
21:29:26 <\oren\> 7 should be stored directly not pointed somewhere
21:29:51  \oren\: because this way you need fewer conditionals when you dereference an object pointer
21:30:10  you don't have to check for ten special cases before dereferencing it like ruby does
21:30:29  (actually it has to check only for two conditions, but still)
21:30:41  (small values and 16-bit alignment)
21:30:45 <\oren\> I guess, but you end up checking its type after dereferencing anyway....
21:30:58 -!- imode has quit (Ping timeout: 255 seconds).
21:31:15  no, you end up checking its methods and class and all sorts of stuff like that, not always the one "type" thing
21:31:29  it's an OO language
21:31:31  all objects are similar
21:31:55  there aren't just 30 differently typed objects all with unrelated behavior like in scheme
21:32:10  in ruby and python there's a lot of things common in all or almost all objects, includign integers
21:32:16 <\oren\> but some objects have direct support at CPU level for their operations 
21:32:16  all objects have a class and methods
21:32:26  sure, but not all operations are like that
21:32:39  and you have to do the check for all non-integer objects too
21:33:00  there's a lot of code that rarely manipulates integers, but it would have to pay for the integer check every time it accesses any object
21:33:11  since almost any object could just happen to be an integer
21:33:42  ruby works like that, it has to check for integers/symbols and for special low-address objects all the time, even if you never use those objects
21:33:52  (though never using the low address objects is very unlikely)
21:34:06  (some of them are used a lot)
21:34:11  (even internally)
21:34:48  How much of what a branch predictor does could realistically be replaced with a tracing JIT?
21:35:27  but the fact is, ruby 1.8 doesn't care that much about heavy performance optimizations anyway
21:35:55  if you want performance, it's up to the programmer to identify the inner loops and optimize them, possibly by calling to non-ruby code
21:36:09  but it still manages to be quite a fast language without such tricks
21:36:19  it's actually faster than perl 5, despite its reputation that it's slow
21:36:25  perl 5 is horrible
21:36:35  and perl 5 is hard to change because
21:36:46 <\oren\> Hmmm... I'm now wondering where C, compiled with tcc -run, ends up in the set of interpreted languages
21:37:00  it has published its bad API so early that there's too much code using it and all the stupid internal details are fixed now
21:37:30  \oren\: it always depends on what kind of code you're running
21:38:02  and how much optimization you're willing to do when writing the code
21:38:15  there are people who optimize perl5 code, even code that would be easier to write in C
21:46:16  (for esoteric reasons)
21:52:47  ATMunn: hi.
21:52:52  oh hi
21:53:24  i thought you were referring to something recent
21:53:53  it was recent, but don't mention it here
21:57:11  ah
21:57:24  found it
21:57:31  wont mention tho as you said
22:04:48  [wiki] [[Talk:Lazy evaluation]] M https://esolangs.org/w/index.php?diff=52934&oldid=46163 * Rdococ * (+169) 
22:09:05 -!- propumpkin has changed nick to contrapumpkin.
22:18:04 -!- zseri has quit (Ping timeout: 260 seconds).
22:32:06 -!- augur has joined.
22:52:38 -!- LKoen has joined.
22:53:32 -!- `^_^v has quit (Quit: This computer has gone to sleep).
22:54:21 -!- ATMunn has changed nick to wall.
22:54:28 -!- wall has changed nick to ATMunn.
22:55:01 -!- AnotherTest has quit (Ping timeout: 276 seconds).
23:15:12  I should introduce a new element system because I'm not satisfied with either the Aristotelean nor the classical chinese system. My five elements would be stone, metal, plastic, cellulose, and protein.
23:17:35  I had the concept of a two-level system where things could become their "oxidized" forms
23:17:47  so, say dirt, water and air -> ash, salt and smoke
23:18:00  I should shut up now before the grudge for no reason kicks in
23:18:29  Stone encompasses all mineral, gemstone, lime, sand, clay, concrete, plaster, and also all glass, pearl, seashell. Metal encompasses all the metals and semi-metals like aluminum. Plastic has all polymers including rubber, vinyl, pet. Cellulose includes wood and cotton and linen. Protein includes wool, horn, unicorn horn, nails.
23:19:01  Liquids and gases and foodstuff would be outside the element system.
23:19:24  So the protein element only includes the non-edible forms like I listed above.
23:19:28  Why is aluminum a semi-metal? Is aluminium a full metal?
23:19:32  (technically those are edible, but still)
23:19:50  shachaf: that's a question of terminology. It's a metal in this elemental system.
23:20:10  some chemical terminology counts it as a semi-metal.
23:22:59  There should be a cyclic dominance order between these. Obviously because of rock-paper-scissors, stone beats metal, metal beats cellulose, and cellulose beats stone.
23:24:19 -!- Phantom_Hoover has quit (Read error: Connection reset by peer).
23:26:28 -!- imode has joined.
23:28:41  And there are lots of game elemental systems, but their goal isn't classifying solids or materials, but classifying damage types. Nethack has a strange pot-pourri, where the elements include fire, cold, poison, shock (lightning or electricity), magic, draining, and sleep.
23:29:17  sleep is an element? :P
23:29:24  yes
23:29:37  and there are arrows dealing sleep damage too
23:29:47  not in nethack, but in other fiction
23:29:53  this came up recently
23:29:59 * rdococ activates his sleep magic
23:30:19  no no, magic is different. sleep isn't magic.
23:30:35  oh yea
23:30:46  there are magic arrows or magic bullets too
23:33:10 -!- kurolox has quit (Ping timeout: 240 seconds).
23:33:20  magic missile is always magical, force damage counts as magical in some games, and the magic bullets in Der Freischütz probably deal magic damage too
23:34:31  I would think of magic as manipulating the elements, not as an element itself
23:34:56  rdococ: element in this sense is a damage type
23:35:02  k
23:35:05  like fire, cold, lighting, etc
23:35:16  but magic isn't among those in all such systems
23:35:25  in some game, magic vs nonmagic is a separate dimension from the element type
23:36:21  in that case there's normal fire and magical fire, normal bludgeoning and magical force, normal cold weather and magical cold that freezes you from inside no matter what clothing you wera
23:36:29 -!- LKoen has quit (Quit: “It’s only logical. First you learn to talk, then you learn to think. Too bad it’s not the other way round.”).
23:36:41  and also ordinary sleep and magical sleep
23:36:58  nethack isn't like that
23:37:57 <\oren\> In some game I forget the name of they had just blunt, sharp, and fire damage
23:38:35  blunt, sharp and fire makes sense
23:38:50  kind of
23:39:01 <\oren\> it was a startegy game
23:39:10  startegy
23:39:54  strangely, M:tG doesn't have a proper elemental system, there's no fire damage or cold damage or blunt or edged or pierce weapons,
23:40:27  so anything that tries to distingiush damage has to care about (1) properties of the damage source, esp zone and color and type, (2) combat damage vs noncombat damage, and (3) properties of the damage target, esp player vs creature, and (4) amount of damage (damage comes in discrete damage events that can have any nonnegative integer amount)
23:42:15  also a few abilities of the source automatically modify the effect of the damage, these are lifelink, deathtouch, infect, wither.
23:43:39  those apply to all damage dealt by the source, no matter why
23:48:31  hm
23:48:48  in the future, I'll have to find a random person and start holding a grudge against them for no reason
23:49:42 <\oren\> in Age of Empires 3, there is "melee", "range" and "seige" attack
23:49:50  I hold a grudge against you for the reasons you talked about, among others
23:50:22  \oren\: wait, only those? doesn't it have more?
23:50:31  I don't know why you expect that you can be annoying for months and have each subsequent thing you say considered independently of everything before it.
23:51:57 <\oren\> wob_jonas: yeah, it doesn't distinguish between hack, pierce, and crush damage the way age of mythology does
23:52:33  shachaf: You mean when I'm trying my very hardest not to be annoying just so that you don't completely hate me anymore?
23:53:02  Sure, I can be annoying, I readily admit that and try to stop it. But when I'm trying to stop it, I don't expect people to ignore that.
23:53:15  I don't completely hate you.
23:53:35  Then how much hate do you feel?
23:53:43  No hate.
23:53:52  And you have a grudge against me?
23:54:03  I think that was your word, but sure.
23:54:35  rdococ: just drop it. if shachaf doesn't want to listen to you, just ignore that. it's not like he got you banned from the channel or harasses you or any other such harm
23:54:54  wob_jonas: No, because I want to be friends with people. What's wrong with trying to mend fences?
23:55:09  shachaf: If you hold a grudge, doesn't that imply some level of hate?
23:58:52  . o O ( Your friend making strategy sucks. )

2017-08-25:

00:00:15  Maybe I should just leave. I always seem to be worthless where-ever I go, and every time I try to change that, it fails. Why am I still alive, again?
00:00:17 -!- rdococ has left ("Leaving").
00:01:05  Huh.
00:02:08  I don't think rdococ is worthless, but I don't enjoy interacting with them.
00:03:59  What should I do?
00:20:07  `? sausage
00:20:08  sausage? ¯\(°​_o)/¯
00:23:26  `learn Sausage is the ground remains of a pig after the valuable parts (meat, liver) and the part that will form sausage skin are removed.
00:23:29  Learned 'sausage': Sausage is the ground remains of a pig after the valuable parts (meat, liver) and the part that will form sausage skin are removed.
00:32:23 -!- oerjan has joined.
00:46:05 -!- sleffy has quit (Ping timeout: 240 seconds).
00:48:14 -!- sleffy has joined.
01:00:56 -!- Warrigal_ has joined.
01:07:08 -!- boily has joined.
01:07:58 -!- wob_jonas has quit (Quit: http://www.kiwiirc.com/ - A hand crafted IRC client).
01:08:51 -!- wob_jonas has joined.
01:09:36 -!- sleffy has quit (Ping timeout: 252 seconds).
01:12:12 -!- sleffy has joined.
01:17:37 -!- sleffy has quit (Ping timeout: 248 seconds).
01:20:42 -!- sleffy has joined.
01:28:27 -!- sleffy has quit (Ping timeout: 260 seconds).
01:28:52 -!- sleffy has joined.
01:30:11   oerjan: Did you play the Magnet game? <-- i'm on Pearl now (slowly cycling alphabetically)
01:34:04  what game is that?
01:58:58 -!- Antoxyde has quit (Quit: Leaving).
02:00:09  `5 w
02:00:13  @massages-loud
02:00:13  shachaf asked 22h 21m 5s ago: to /quit CHICKEN OF THE WOODS
02:00:15  1/2:vwwwl//Vwwwls wrw w swgn wf wnswffwcwwnt wwsdwm. \ precession//Precession is the opposite of succession. It is the joy of children and the curse of first year physics students. \ blsqbot//blsqbot is the owner of the bot 'mroman'. \ wegian//A wegian is an equivalence class of #esoteric regulars. There are two main wegians, the Nor (from Finland)
02:00:28  `n
02:00:29  2/2: and the Glas (from Hexham). There's also the hypothetical Gal, which hasn't been observed yet so we're not sure where it's from. \ or//Or is an Intercal unary operator.
02:05:05  in all my days I have never had the chance to mess with ruby. looks like I get to now.
02:05:32  imode: uh why?
02:05:40  wob_jonas: work.
02:06:23  imellode! what's your opinion on ruby so far?
02:06:40  have never touched it before. looks nice. going to be pairing it with Sinatra.
02:06:45  helløœirjan, wobonsoir_jonas.
02:07:00  Sinatra is that ultra-lightweight Web framework?
02:07:06  yup!
02:08:20  nice!
02:08:51  wob_jonas: from tatham's puzzle collection
02:08:52 -!- ATMunn has quit (Remote host closed the connection).
02:09:04  we were previously working with Python and Flask, but we figured we'd have a go at a similar framework in a similar language to compare the two.
02:09:45 -!- ATMunn has joined.
02:10:32  heboilloy
02:11:15  imode: then you should try Java and Spark!
02:11:34  why in the hell did that take 100% of my CPU.
02:11:46  that was just... documentation. o_o
02:11:48  or well, the magnets i play. no idea if that's what shachaf was referring to.
02:12:05  imode: everything is normal and sane.
02:12:08  docpumentation.
02:12:17  easy to confuse.
02:12:31 * boily *THWACKS* oerjan. 0.59 FP.
02:12:34  boily: java and sane.. two words I haven't seen together in a long time. :P
02:12:52  i expecte that.
02:12:54  *+d
02:13:13  you can write sane Java any time. it even comes with lambdas*!
02:13:22  so does python and ruby. :P
02:13:47  don't worry. I teach so I'll be doing plenty of java on the 18th.
02:17:22  hahahah that's even worse
02:17:36  what will you be teaching with java?
02:18:20  a transfer course to a state university.
02:18:23  design patterns, SOLID principles, unit tests...
02:18:31  introductory java.
02:18:46  oh. that's EVEN worse.
02:18:51  ok
02:19:00  nah. they walk away with some intuition.
02:19:23  you mean you sneakily teach good stuff, not only the curriculum?
02:19:24  good
02:19:40  yeah. that's kind of my thing. :P
02:19:57  oerjan: when are you going to play The Witness hth
02:21:27 -!- boily_ has joined.
02:22:35  probably never.
02:23:13 -!- boily has quit (Ping timeout: 248 seconds).
02:23:55 -!- boily_ has changed nick to boily.
02:27:43  just think of it as a tatham puzzle game hth
02:33:32 -!- boily has quit (Quit: WOOD CHICKEN).
02:39:49  [wiki] [[User:JWinslow23]]  https://esolangs.org/w/index.php?diff=52935&oldid=37537 * JWinslow23 * (-283) Replaced content with "Heya."
03:00:42 -!- ATMunn has quit (Quit: See ya! o/).
03:08:09  @tell rdococ  Even then, with unbounded cells... <-- see https://esolangs.org/wiki/Collatz_function#Reduction_to_3-cell_brainfuck
03:08:09  Consider it noted.
03:11:21 -!- jaboja has joined.
03:11:37  @tell rdococ That balances the loops, for the top I guess you need an extra << at the end.
03:11:37  Consider it noted.
03:24:05 -!- danieljabailey has quit (Ping timeout: 240 seconds).
03:24:49 -!- danieljabailey has joined.
03:28:50 -!- Bowserinator has quit (Ping timeout: 240 seconds).
03:29:07  it may take a while for him to read that
03:31:28 -!- Bowserinator has joined.
03:31:51 -!- Bowserinator has changed nick to Guest35524.
03:39:35 -!- MDude has quit (Ping timeout: 240 seconds).
03:59:10 -!- Sgeo_ has quit (Read error: Connection reset by peer).
04:03:13 -!- wob_jonas has quit (Quit: http://www.kiwiirc.com/ - A hand crafted IRC client).
04:04:22 -!- Sgeo has joined.
04:20:27 -!- Warrigal_ has quit (Ping timeout: 240 seconds).
04:51:10 -!- Guest35524 has changed nick to Bowserinator.
04:51:11 -!- Bowserinator has quit (Changing host).
04:51:11 -!- Bowserinator has joined.
04:56:58 -!- MDude has joined.
04:58:42 -!- oerjan has quit (Quit: Nite).
05:24:06  wow. I uh. I see why people like ruby. o_o
05:26:37 -!- jaboja has quit (Remote host closed the connection).
05:44:05 -!- sleffy has quit (Ping timeout: 240 seconds).
06:00:35 -!- sleffy has joined.
06:05:56 -!- hppavilion[1] has joined.
06:22:47 -!- hppavilion[0] has joined.
06:25:21 -!- hppavilion[1] has quit (Ping timeout: 248 seconds).
06:42:05  ruby is like 150% syntax sugar
06:46:32  then I'll happily rot my fingers off with it.
07:06:03 -!- FreeFull has quit.
07:17:27 -!- sleffy has quit (Ping timeout: 240 seconds).
07:59:59 -!- kurolox has joined.
08:33:40 -!- erkin has joined.
08:39:01  Good morning
08:39:13  fizzie, are you here?
08:48:47 -!- kurolox has quit (Ping timeout: 248 seconds).
08:53:31 -!- imode has quit (Ping timeout: 246 seconds).
08:53:49 -!- kurolox has joined.
08:54:03  Sorry, I had to change the computer
08:54:15  Are you here, fizzie?
09:05:00 -!- augur has quit (Remote host closed the connection).
09:09:01 -!- kurolox has quit (Remote host closed the connection).
09:32:57 -!- stalker has joined.
09:33:08 -!- stalker has quit (Client Quit).
09:40:55 -!- silly` has joined.
09:43:12 -!- silly` has quit (Read error: Connection reset by peer).
09:43:52 -!- silly` has joined.
09:44:03 -!- silly` has left.
10:12:07 -!- augur has joined.
10:15:23 -!- ^v has quit (Ping timeout: 246 seconds).
10:16:18 -!- augur has quit (Ping timeout: 240 seconds).
10:18:24 -!- ^v has joined.
11:49:10 -!- augur has joined.
11:53:11 -!- Antoxyde has joined.
11:53:18 -!- augur has quit (Ping timeout: 240 seconds).
13:00:01 -!- LKoen has joined.
13:14:05 -!- TieSoul has joined.
13:32:25 -!- wob_jonas has joined.
13:32:45 -!- APic has quit (*.net *.split).
13:32:46 -!- zzo38 has quit (*.net *.split).
13:32:46 -!- digitalcold has quit (*.net *.split).
13:32:46 -!- shikhin has quit (*.net *.split).
13:32:46 -!- deltab has quit (*.net *.split).
13:32:46 -!- int-e has quit (*.net *.split).
13:32:58 -!- int-e has joined.
13:32:58 -!- deltab has joined.
13:33:00 -!- digitalcold has joined.
13:33:06 -!- APic has joined.
13:33:27 -!- shikhin has joined.
13:33:49  ok, so this might not be the right channel, but have you ever noticed how fucking rare it is for anyone to copyright license anything in such a way that it's free to distribute only in the future, not right now?
13:33:51 -!- shikhin has changed nick to Guest68623.
13:34:25  many people complain about how copyright terms are too long and how people almost always get the most income from copyright on anything in the first few years
13:35:22  yet everybody either simply releases something under a free license right now, or (rarely) releases something they did in the past under a free license as an afterthought, or never releases the work under a free license.
13:36:16  I've only ever seen ONE case when someone declared that a work will be public domain in the future but isn't now, and in that case it was already released under a no-derivatives free license and the future time was their death, not just a few years later
13:36:22  it's so strange
13:36:29  is there some legal difficulty in a timed release?
13:36:50  or a psychological difficulty?
13:39:06  I think in cases of "we want to retain copyright for now but will release it freely later", it's usually accomplished by just keeping it proprietary until the point where it'll be released freely
13:39:20  and then licensing it under a free-immediately license at that point
13:39:43  which is more flexible in that the copyright holder doesn't have to commit to a specific date or time ahead-of-time
13:40:37  I guess licensing it under a "these terms apply after $date" condition doesn't really come to mind to people, and also since it hasn't really been done much I guess there's little in way of legal precedent too?
13:41:08  compared to just releasing it under MIT or GPL or whatever at that future date instead
13:43:02  FireFly: it might be more flexible for a copyright holder but less convenient for everyone else
13:43:27  if I know something will be released from copyright later, I can already start working on derivative versions that I'll release at that time
13:43:58  sometimes (say for software that has an immediate use) I might even buy that thing now more (unlike in the case of a fiction book, when I might just wait)
13:44:06  True, but since it's up to the copyright holder to license it, I guess the flexibility for the copyright holder trumps that of others :p
13:44:28  this already happens for expiring copyrights (for books of course, there's no software with an expired copyright in most places of the world yet)
13:44:33  yeah
13:45:28  It reminds me a bit of how frictional games said they'd release the source code to Penumbra if the Humble Indie Bundle (the first one) exceeded some value in payment
13:45:35  (and did so once it did)
13:45:43  I mean, the topic of timed releases in general
13:45:53  oh, I hadn't heard of that
13:46:14  so basically they sell a public license in a mass way
13:50:22  Pretty much
13:50:33  of course, you got the binary form of the game either way
13:50:45  and assets weren't included in the source release
13:54:59  what do you mean by assets?
13:58:05  They released the source code under a permissive license (I think MIT or something) after they met that criteria in purchases, but that doesn't cover art, music, models, maps, etc
13:58:12  but rather just the code/engine itself
13:58:38  ok
14:06:04 -!- augur has joined.
14:10:20 -!- augur has quit (Ping timeout: 255 seconds).
14:20:33 -!- ATMunn has joined.
14:24:54 -!- TieSoul has quit (Ping timeout: 252 seconds).
14:36:17 -!- LKoen has quit (Quit: “It’s only logical. First you learn to talk, then you learn to think. Too bad it’s not the other way round.”).
15:17:42 -!- TieSoul has joined.
15:18:38 -!- erkin has quit (Quit: Ouch! Got SIGABRT, dying...).
15:21:55 -!- wob_jonas has quit (Quit: http://www.kiwiirc.com/ - A hand crafted IRC client).
16:20:49 -!- jaboja has joined.
16:37:04 -!- `^_^v has joined.
16:41:06 -!- Sgeo has quit (Read error: Connection reset by peer).
16:41:25 -!- TieSoul has quit (Quit: Leaving).
16:53:37 -!- Sgeo has joined.
16:54:01 -!- hppavilion[0] has quit (Ping timeout: 240 seconds).
17:08:50 -!- zzo38 has joined.
18:06:49 -!- augur has joined.
18:11:27 -!- augur has quit (Ping timeout: 248 seconds).
18:14:32 -!- wob_jonas has joined.
18:15:26  what was that programming language where program source code was in the form of everyday physical objects stacked into various towers, and so an interpreter is be very hard to write because it would need lots of recognition capabilities?
18:16:55  i'm not sure, but that sounds really cool
18:24:58 -!- Phantom_Hoover has joined.
18:34:56 -!- FreeFull has joined.
18:36:36 -!- imode has joined.
19:14:16 -!- sleffy has joined.
19:42:39 -!- zzo38 has quit (Ping timeout: 248 seconds).
19:45:46 -!- zzo38 has joined.
19:59:45 -!- jaboja has quit (Ping timeout: 248 seconds).
20:08:41 -!- sleffy has quit (Ping timeout: 240 seconds).
20:12:50 -!- first_user has joined.
20:13:00 -!- first_user has quit (Remote host closed the connection).
20:28:54 -!- jaboja has joined.
21:04:08 -!- kurolox has joined.
21:11:05 -!- Guest68623 has changed nick to shikhin.
21:11:34 -!- shikhin has changed nick to Guest12038.
21:12:03 -!- Guest12038 has changed nick to shikhin_.
21:12:10 -!- shikhin_ has quit (Changing host).
21:12:10 -!- shikhin_ has joined.
21:12:23 -!- shikhin_ has changed nick to shikhin.
21:25:02 -!- augur has joined.
21:52:37 -!- sleffy has joined.
22:02:21  Hahahahaha! This is one of those cases when I can laugh at the more developed countries for thinking they are so cool when here in Hungary we've invented the same thing ages ago.
22:03:03  The last time I felt this was in 2012, when London announced that you can now use mobile phones in their tube network, while we've had mobile coverage in the metro lines for years by that time.
22:03:42  This time the Americans think they are cool for traveling to view a total solar eclipse, when we've already organized a total solar eclipse in 1999 with similar great tourist hype. I've seen it myself.
22:05:34 <\oren\> FUCK YOU HIPCHAT YOU INCOMPETENTLY DESIGNED SHITBOX
22:05:46 <\oren\> watch what fucking happens if you copypaste a string from hipchat
22:05:52 <\oren\> *       soft  memlock   unlimited
22:06:19 <\oren\> THOSE ARE NOT THE RIGHT KIND OF SPACES
22:06:52 -!- erkin has joined.
22:07:55  is that double-utf-8?
22:09:27 <\oren\> they're U+2002 EN SPACE
22:09:57  \oren\: right, but shown as double-utf-8
22:10:18 <\oren\> I don't... think so?
22:10:43  I see a with hat in the line you pasted here
22:11:06  that's what you get when you take an en-space encoded as utf-8 and show it as cp1252 or similar instead
22:12:12 <\oren\> so it's not even well-formed utf-8? FUCK
22:12:40 <\oren\> *       soft  memlock   unlimited
22:13:19 <\oren\> HIPCHAT IS FUCKING SHIT
22:17:33  huh what? it's probably well-formed utf-8 when they send it to you, they just don't tell you it's utf-8. that, or they already double-utf-8 encode it in their servers, but that's unlikely.
22:17:43  or it got messed up when you pasted it here or something
22:18:20  I dunno really
22:46:27  weechat or die.
22:47:42 -!- kurolox has quit (Ping timeout: 260 seconds).
22:54:53 -!- wob_jonas has quit (Quit: http://www.kiwiirc.com/ - A hand crafted IRC client).
22:56:37  irssi!
23:27:23 -!- `^_^v has quit (Quit: This computer has gone to sleep).
23:36:42 -!- atslash has quit (Ping timeout: 260 seconds).
23:53:01 -!- erkin has quit (Quit: Ouch! Got SIGABRT, dying...).
23:57:20 -!- hppavilion[1] has joined.

2017-08-26:

00:05:28 -!- Antoxyde has quit (Quit: Leaving).
00:07:54 -!- sleffy has quit (Ping timeout: 252 seconds).
00:59:39 -!- oerjan has joined.
01:08:22 -!- augur has quit (Remote host closed the connection).
01:26:45 -!- augur has joined.
01:56:26 -!- Phantom_Hoover has quit (Read error: Connection reset by peer).
02:23:37  @tell wob_jonas https://esolangs.org/wiki/Efghij
02:23:37  Consider it noted.
02:58:09 -!- ATMunn has quit (Quit: See ya! o/).
03:48:55 -!- jaboja has quit (Read error: Connection reset by peer).
04:05:43 -!- jaboja has joined.
05:03:54 -!- oerjan has quit (Quit: Nite).
05:05:34 -!- atslash has joined.
05:25:09 -!- contrapumpkin has quit (Quit: Textual IRC Client: www.textualapp.com).
06:06:01 -!- jaboja has quit (Remote host closed the connection).
06:23:11 -!- S1 has joined.
07:02:54  [wiki] [[Talk:Tri]] N https://esolangs.org/w/index.php?oldid=52936 * JWinslow23 * (+177) Created page with "Has this been implemented? I might make an interpreter for my own personal use if not. ~~~~"
07:10:14  @tell wob_jonas You still can't use mobile phones in the London Underground. It will "start getting" coverage "by 2019". And yes, Finland has had that as well as long as I remember.
07:10:14  Consider it noted.
07:17:27  @tell wob_jonas http://tech.newstatesman.com/news/4g-tube-mobile-coverage-underground
07:17:27  Consider it noted.
07:18:18  Currently there's wifi *at stations*, which is almost but not quite useless.
07:47:37 -!- jaboja has joined.
07:57:10  doing it at stations is important for tracking people; inside the train cars, not so much :P
08:15:30  who even uses the internet anymore
08:15:41  to do actual work, I very rarely need it
08:24:06 -!- kurolox has joined.
08:52:31 -!- hppavilion[1] has quit (Quit: HRII'FHALMA MNAHN'K'YARNAK NGAH NILGH'RI'BTHNKNYTH).
09:14:36 -!- imode has quit (Ping timeout: 252 seconds).
09:41:48 -!- Antoxyde has joined.
09:57:46 -!- S1 has quit (Remote host closed the connection).
09:58:04 -!- S1 has joined.
09:58:07 -!- jaboja has quit (Ping timeout: 248 seconds).
09:58:27 -!- S1 has changed nick to Guest3913.
10:07:31 -!- Guest3913 has quit (Ping timeout: 276 seconds).
10:27:03 -!- Guest3913 has joined.
10:44:05 -!- s1feha__ has joined.
10:47:10 -!- Guest3913 has quit (Ping timeout: 276 seconds).
10:51:55 -!- augur has quit (Remote host closed the connection).
10:56:33 -!- s1feha__ has quit (Remote host closed the connection).
10:56:59 -!- s1feha__ has joined.
11:06:44 -!- s1feha__ has quit (Ping timeout: 246 seconds).
11:16:31 -!- s1feha__ has joined.
12:01:12 -!- augur has joined.
12:04:31 -!- s1feha__ has quit (Ping timeout: 276 seconds).
12:06:17 -!- augur has quit (Ping timeout: 260 seconds).
12:15:07 -!- erkin has joined.
12:31:05 -!- TieSoul has joined.
14:21:37 -!- atslash has quit (Ping timeout: 248 seconds).
14:22:19 -!- atslash has joined.
14:35:52 -!- ATMunn has joined.
15:03:38 -!- boily has joined.
15:14:07  `5 w
15:14:22  1/2:cut elimination//The cut-elimination theorem states that any Prolog program written using the cut operator ! can be rewritten without using that operator. \ flu shot//Flu shots are usually available from some time in the first half of November. \ monomorphism//A monomorphism is just an epimorphism in the opposite category. \ moo//Moo is the sou
15:15:31  `n
15:15:32  2/2:nd made by a cow as it freezes. \ treant//Treants are genericized ents for intellectual property reasons.
15:16:07  `howg flu shot
15:16:16  slwd flu shot//s/$/./;s/f/F/ \  slashlearn flu shot/flu shots are usually available from some time in the first half of November
15:16:48  make that October and I'm in.
15:25:14  . o O ( boily is getting shot in October? )
15:41:32 -!- imode has joined.
15:42:02  winter comes early in these here parts.
15:42:21  besides, getting shot before it gets mainstream is important.
15:52:48 -!- augur has joined.
15:57:05 -!- augur has quit (Ping timeout: 248 seconds).
16:12:51 -!- rdococ has joined.
16:13:25  Dammit, I forgot to kill myself.
16:14:55  Anyway, I'm here again to be a lonely, stupid idiot.
16:22:30  rdochellidioc!
16:22:44  har.
16:22:47 -!- tromp has quit (Ping timeout: 240 seconds).
16:24:59  I kind of agree... the best place to be lonely is a crowd of people
16:25:49  To be fair, you still end up lonely if you're a stupid idiot.
16:26:33 -!- TieSoul_ has joined.
16:26:51  Not like it even matters. I'm going back to hell soon anyway.
16:27:05  Or worse, Wisconsin?
16:27:31  Oh, no. The hell I go to is much worse than Wisconsin. In fact, it's worse than Malbolge.
16:30:22 -!- TieSoul has quit (Ping timeout: 264 seconds).
16:30:40  (Bethany: Were they sent to Hell? / Metatron: Worse. Wisconsin. For the entire span of human history.)
16:30:45 -!- boily has quit (Quit: SMALL CHICKEN).
16:33:09  Wait, Wisconsin is worse than Malbolge.
16:49:27 -!- atslash has quit (Ping timeout: 252 seconds).
16:49:49 -!- atslash has joined.
17:05:35 -!- jaboja has joined.
17:11:15 -!- tromp has joined.
17:13:30 -!- jaboja has quit (Remote host closed the connection).
17:24:21 -!- nc_jonas has joined.
17:24:31  `olist 1094
17:24:32  olist 1094: shachaf oerjan Sgeo FireFly boily nortti b_jonas
17:25:58 -!- nc_jonas has quit (Remote host closed the connection).
17:26:45  I should die.
17:27:01  that seems like a poor plan
17:27:01  I'm a stupid fucking idiot. I'm always just that annoying nuisance who keeps making shitty esolangs.
17:27:07  Why am I not dead yet? Kill me.
17:32:42  would you grow up.
17:33:05  nobody fucking cares. stop beating yourself up publically for attention.
17:33:17  grow a fucking spine and get over yourself.
17:34:15  your mood swings are a product of either an adolescent mind or some desperate need for validation by people. either way, go jack off in a corner. nobody's going to give you that, so you might as well give it to yourself.
17:35:15  whoa, that's not ok
17:35:20  let's all calm down
17:35:46  alercah: honestly, he needs tough love. he's been saying the same thing over and over and over.
17:35:56  that's not tough love
17:36:00  that is tough love.
17:36:36  ...
17:36:59  You know, I've been meaning to try to actually kill myself, so people will realize it's not a show "for attention".
17:37:06  then fucking do it.
17:37:35  if it's a cry for help, seek therapy. your constant moaning is not theraputic.
17:37:37  But then, I wonder: "why would anyone hate someone for wanting attention? doesn't everyone want attention?"
17:38:07  It's kind of dumb, when you think about it. If someone simply wants some TLC (not your shitty crap you call "tough love"), then GIVE SOME FOR ONCE YOU JERK!
17:38:27  no. because you've been saying that you're some kind of horrible piece of shit for about a week now in here.
17:38:40  practically every time I tab over you're expecting some kind of validating "oh no it's okay" response.
17:38:48  I don't expect any response.
17:38:55  then why the fuck do you say it in here?
17:39:04  go blog about it.
17:39:05  Because I want to warn people.
17:39:39  about _what_?
17:40:05  your own self harm? are you going to hold a knife to your throat and yell at people on IRC?
17:40:21  you need help. professional help.
17:40:27 -!- rdococ has left ("Leaving").
17:40:44 -!- grumble has joined.
17:40:49  jesus. I hate doing that.
17:41:32  there's only so many times you can say "oh no you're great just do your own thing" before it becomes obvious he's begging.
17:46:36 -!- wob_jonas has joined.
17:46:58  @messages
17:48:13  fizzie: the thing you linked to seems to only say the underground is planned to get 4G mobile coverage by 2019. That sounds like it already has slower coverage.
17:58:56 -!- rdococ has joined.
18:54:23 -!- boily has joined.
19:00:14 -!- atslash has quit (Read error: Connection reset by peer).
19:00:36 -!- atslash has joined.
19:03:36 -!- Antoxyde_ has joined.
19:05:41 -!- Antoxyde has quit (Ping timeout: 240 seconds).
19:08:37 -!- atslash has quit (Ping timeout: 260 seconds).
19:09:26 -!- atslash has joined.
19:10:09  Hi boily.
19:11:59  Apparently in D&D if you find cursed loot of gold and it weighs less than 3 pounds, then the cost of the gold isn't enough to pay for the spell to remove the curse.
19:12:06  But if it weighs at least 3 pounds, then any number of different curses aren't enough to protect the loot, because a single casting of the Remove Curse spell is enough to remove all curses.
19:12:19  This explains why the Holy Crown of Hungary is guarded so much. Even without the other associated relics, the crown alone contains more than three pounds of gold, so although it's almost certainly cursed now, a thief would just have to take it to a non-lawful temple to get it uncursed and has value remaining.
19:12:43  oerjan: thank you! that's the one
19:13:07 * rdococ decides to 'cut the knot' and gives wob_jonas 8 pounds of fool's gold instead.
19:13:16  s/of f/of cursed f/
19:13:19 -!- tromp has quit (Remote host closed the connection).
19:18:11  rdochelloc.
19:18:14  wellob_jonas.
19:18:21  helloily
19:21:49 -!- tromp has joined.
19:24:48  tromp
19:24:59 * rdococ (blah@blah/blah) has joined
19:26:49  wob_jonas: Do you know what is supposed to happen on MIX if trying to access memory that a card is partially loaded?
19:28:28  zzo38: presumably on an older machine, you'd read the old value of the cell or the new value, depending on whether it's happened to be read yet, probably at word granularity, but this isn't guaranteed for future compatibility.
19:28:34  zzo38: you're asking this for golfing code on cards?
19:28:39  bootstrap code especially?
19:29:37  Yes, although it could also help to speed up some other programs in some cases maybe
19:30:16  I think in general it's undefined behavior and you shouldn't do that, and you can recover from it only by resetting the machine and then rewriting the memory cells or something.
19:31:00  Can't you just read unknown data in the worse case?
19:31:31  on a decimal machine where bytes are implemented as eight bcd-coded bits? I don't think so
19:31:46  hopefully it does read unknown data
19:31:49  but who the heck knows
19:32:17  I mean, the memory is probably not accessed at the same time by the cpu and the IO device, in each cycle only one of them accesses each memory chip,
19:32:41  and they read and write whole words with valid values provided the cards only have recognizable characters
19:33:04  let me see what the book actually says, though I don't think it goes into details
19:34:37  "so a program must not refer to the information in memory until then." -- not much there
19:35:24  wob_jonas: Doesn't this vary by exchange rate?
19:36:19  then 1.4.4. "but the ensuing program must not refer to these memory cells until later."
19:36:25 -!- lambdabot has quit (Remote host closed the connection).
19:36:59  OK, but then it does not say what things are allowed to happen if the program refers to it anyways.
19:37:15  shachaf: I don't think so. Gold is a base currency, all the money in D&D is based on gold, platinum, silver and copper, and they somehow have a fixed price compared to each other.
19:37:26  shachaf: there might be modifiers on the price of the spell of course.
19:38:10  zzo38: it doesn't seem to say. you'll have to refer to the manual of your specific MIX machine and its IO devices.
19:38:55 -!- lambdabot has joined.
19:40:23 -!- jaboja has joined.
19:42:31  The money in D&D at least in 3.5 edition is weighs 1/50 pound I think, and is always decimal, although it weight more than the GURPS money which is 1/240 pound (I think the book says 1/250 pound, but I think that is a typographical error and it is supposed to say 1/240 pound). I think also some older version of AD&D has electrum money too, not only copper, silver, gold, and platinum.
19:42:44  modern computers like recent unix machines or MMIX are different of course, they have memory protection and the OS uses it to limit privilage of user-space processes, so it has to guarantee that user-space programs can't do anything that breaks the protection, which means you read valid data even from areas that are currently inputting in the backg
19:42:44  ruond
19:43:12  zzo38: yes, a gold piece weighs 1/50 pound, and a remove curse spell costs 150 gold pieces
19:43:41  electrum money => isn't that D&D 5 actually?
19:44:25  wob_jonas: I mean the Holy Crown of Hungary.
19:44:30  Maybe in D&D 5 also; I have not read it
19:44:39  But AD&D also has electrum money
19:44:58  ok
19:46:59 -!- Antoxyde__ has joined.
19:47:53  oh! the D&D tables say that a musical instrument weighs 3 pounds. that explains why there are no falling piano traps.
19:48:14  (yeah, I know the default environment is like medieval so they didn't have pianos yet)
19:50:02 -!- Antoxyde_ has quit (Ping timeout: 260 seconds).
19:52:46  wob_jonas: It does not have slower coverage.
19:53:31  And anyway, "Passengers on the London Underground will be able to make calls, send texts and browse the web from 2019" more or less implies they can't do those things now.
19:54:22  shachaf: what about the crown? the crown is made of mostly gold. there's some extra stuff on it like gemstones and icons, but those take only a minority of the weight.
19:54:51  fizzie: hmm. but then what was the news all talking about at the preparations for the 2012 olympics?
19:55:22  They added the wifi on the stations for that, I believe.
19:56:38  why would they do that? who even had wifi devices in 2012?
19:56:43  portable ones that is
19:56:56  http://www.independent.co.uk/sport/olympics/wifi-at-tube-stations-for-olympics-7570359.html "Tube passengers will have access to free WiFi during the Olympic Games. Platforms at 80 stations will have wireless coverage after Transport for London appointed Virgin Media to provide the service."
19:57:47  "In January 2012, Apple reported its best quarterly earnings ever, with 53% of its revenue coming from the sale of 37 million iPhones --" at least those guys did.
19:58:00  ok
19:59:14  Himoo.
19:59:52  I'm trying to search for news back then (which is made more difficult by the fact that the search feature of MTI doesn't have a fucking stemmer, aren't we in the 21st century now, guys?)
20:00:32  so far I've found some news that says the tube was very overcrowded during the olympics, so much that the traffic company asked people to work at home if possible (I'm not making this up)
20:02:13  hah, I remember when tram 6 was so overcrowded every morning in the rush hour. those were the years. these days we have it easy.
20:07:59  lol, a gallon of beer weighs 8 times as much but costs 50 times as much as a mug of beer. this is low even for D&D item tables.
20:08:34  wob_jonas: I mean that in Hungary you probably pay in HUF instead of gold.
20:09:07  shachaf: no, not in the medieval times that those D&D price tables are trying to represent
20:09:08  Unless spells are still priced by their D&D values in terms of gold by weight.
20:09:18  and you can just sell the gold for money fine
20:09:35  they are priced in D&D in terms of gold pieces
20:10:31  but gold pieces are not fiat currency, they're boullion or whatever the economists call those coins where the metal content itself gives the value, that's why gold pieces are accepted almost everywhere around the world, not only in one region
20:10:36  Do you ever get the feeling that you're is in an adamantium prison, unable to break out, and that you're slowly turning insane? I get that feeling often.
20:11:34  I think that's a soup-based currency.
20:11:53  s/you're is/you're/
20:13:33  rdococ: no. I have fear of closed spaces and very rarely go to rooms where I can't break out from. I was in a job interview once and the strongest reason why the place made negative impression on me is that workers used a swipe card or magnetic card or something to exit the door from the company's area to the area with toilets.
20:13:41  Why are the D&D money heavier than a silver penny?
20:14:34 -!- tromp has quit (Remote host closed the connection).
20:14:42  I keep the keys in the door keyhole whenever I'm inside, half pulled out so it can also be opened from the outside with keys, and I have a spare set of door keys in a drawer.
20:15:21  zzo38: exactly because it's not just a token, the metal itself has to give it the value. it has to be heavy. the D&D 3.5 version probably is too heavy, but still.
20:16:05  Yes, it may be too heavy it seems
20:16:16  I even avoid elevators most of the time, though only part of the reason is fear of closed spaces. (I still sometimes use an elevator in lots of circumstances, such as when carrying heavy items.)
20:18:58 -!- TieSoul__ has joined.
20:20:53  Sounds relatively heavenly.
20:20:53 -!- tromp has joined.
20:21:44  but I'm not at the level of Mowgli who is unwilling to sleep indoors
20:21:55  I'm a city person, I like being indoors
20:22:34 -!- TieSoul_ has quit (Ping timeout: 255 seconds).
20:41:51 -!- jaboja has quit (Ping timeout: 248 seconds).
20:47:44 -!- boily has quit (Quit: NECKTIE CHICKEN).
20:56:35 -!- augur has joined.
20:59:39 -!- wob_jonas has quit (Quit: http://www.kiwiirc.com/ - A hand crafted IRC client).
21:05:39 -!- jaboja has joined.
21:15:27 -!- jaboja has quit (Ping timeout: 248 seconds).
21:22:36  Can anyone remember the name of that thing that's like you see something and then it's suddenly everywhere
21:22:59  Like someone shows you something and you're like "that's cool" and then the next day someone else entirely shows you the same thing
21:23:18  something going viral? memes?
21:23:23  Not really
21:23:46  deja vu?
21:24:01  Again, not really
21:24:06  > 128/(-1) :: Int8
21:24:08   error:
21:24:08       • No instance for (Fractional Int8) arising from a use of ‘/’
21:24:08       • In the expression: 128 / (- 1) :: Int8
21:24:16  > 128 `div` (-1) :: Int8
21:24:18   *Exception: arithmetic overflow
21:25:07  . o O ( I love the fact that it's the division it complains about here, not the fact that 128 becomes -128. )
21:36:31 -!- TieSoul_ has joined.
21:40:16 -!- TieSoul__ has quit (Ping timeout: 246 seconds).
21:42:34 -!- jaboja has joined.
21:44:22 -!- atslash has quit (Ping timeout: 260 seconds).
22:01:54  Taneb: Synchronicity? 
22:03:40  (A snarky answer would probably be "coincidence".)
22:04:00  [wiki] [[Special:Log/newusers]] create  * Snorepion *  New user account
22:06:01  [wiki] [[Esolang:Introduce yourself]]  https://esolangs.org/w/index.php?diff=52937&oldid=52927 * Snorepion * (+302) Introduction
22:25:18  Bad idea: C++ recently introduces sum types called "variants", so we should call structs covariants
22:36:21 -!- TieSoul_ has quit (Quit: Leaving).
22:36:39 -!- Antoxyde__ has quit (Remote host closed the connection).
22:52:48  [wiki] [[Jeeves]] N https://esolangs.org/w/index.php?oldid=52938 * Snorepion * (+3856) Create page and add details
22:54:04 -!- boily has joined.
22:55:48  [wiki] [[Joke language list]] M https://esolangs.org/w/index.php?diff=52939&oldid=52850 * Snorepion * (+87) Add Jeeves to list
23:00:22  Hello fizzie!
23:00:33 -!- erkin has quit (Quit: Ouch! Got SIGABRT, dying...).
23:09:21 -!- kurolox has quit (Ping timeout: 240 seconds).
23:38:37 -!- oerjan has joined.

2017-08-27:

00:58:23  helloerjan
00:59:11  helloony
01:00:43 -!- ^arcade_droid has joined.
01:17:48 -!- tromp has quit (Remote host closed the connection).
01:54:19 -!- ^arcade_droid has changed nick to use_strategy_lol.
01:54:25 -!- use_strategy_lol has changed nick to ^arcade_droid.
01:55:49  `5 w
01:55:54  1/2:xyzzy//Nothing happens. \ bitcoin//bitcoins are coins that have been drilled through with a bit, and can be strung together in long chains. This practice dates to ancient China, and the Chinese remain experts in bitcoin manufacturing. A chain can support up to 21 million coins before breaking. \ bride theory//Bride theory is a theory involving
01:55:55  `n
01:55:56  2/2:a headhunter who dresses in yellow. \ tarafurnar//Tarafurnar is the event after which you'll be seen. \ acab//ACAB is short for "all codecs are broken".
01:56:39  `cwlprits bitcoin
01:56:47  Jafët
01:56:59  Does a chain really break once it reaches 21 million coins?
01:57:23  all cows are bovine
02:00:15  all chicken are boily.
02:00:48  boily: chicken of the woods is the best chicken hth
02:00:53  I'm still convinced that bitcoin is part scam, part money laundering.
02:01:34  helloochaf. next time I'm in the vicinity of the Mycoboutique, I'll buy some.
02:01:50  is that your fancy french name for the woods
02:01:53  imo just go to the woods hth
02:01:59 -!- rdococ has left (""leave me alone"").
02:02:04 -!- rdococ has joined.
02:02:06  I'm far from woods...
02:02:43  but there is http://www.mycoboutique.com/fr/ .
02:06:15 -!- tromp has joined.
02:10:46 -!- tromp has quit (Ping timeout: 240 seconds).
02:17:51 -!- jaboja has quit (Ping timeout: 248 seconds).
02:42:45 -!- boily has quit (Quit: PILOT CHICKEN).
03:01:41 -!- ATMunn has quit (Quit: See ya! o/).
03:44:48  What does "Turing-compIete" mean (as opposed to "Turing-complete")?
03:47:39  `unidecode I
03:47:41  ​[U+0049 LATIN CAPITAL LETTER I]
03:47:42  huh
03:48:14  zzo38: thanks, those looked so similar in my browser font that i didn't notice there _was_ a difference
03:48:20  (which is probably the point)
03:48:36  Browser font?
03:48:39  or possibly the mediawiki font
03:49:00  shachaf: https://esolangs.org/wiki/Jeeves
03:49:58  I see.
03:50:52  itym Why, good Dr. Oerjan, they do in fact look similar! hth
03:51:02  (or evil, if you prefer that.)
03:51:05  Dr. Oerjan?
03:51:11  I thought Ørjan was the doctor?
03:51:17  `? ørjan
03:51:18  Your pal Ørjan is oerjan's good twin. He's banned in the IRC RFC for being an invalid character. Sometimes he publishes papers without noticing it.
03:51:37  `` grWp -l twin
03:51:51  ​* \ ☾_ \ c# \ myname \ orin \ örjan \ ørjan \ pico \ sewerjan \ twint-e \ typoerjan \ אrjan
03:52:23  Sometimes certain people in this channel take things a bit too far.
03:52:48  they're all doctors, except sewerjan who couldn't afford the student fee
03:53:10  `? sewerjan
03:53:12  sewerjan is oerjan's extremely poor twin.
03:53:34  But you didn't say "we're all doctors"
03:53:45  `? örjan
03:53:47  ​Örjan is the diæresed twin. He will punctuate your vöẅëls, and maybe a few other unsuspecting letters.
03:53:54  `? typoerjan
03:53:55  typoerjan is oerjan's clumsy twin.
03:54:51 -!- tromp has joined.
03:55:22  `dowg sewerjan
03:55:32  10333:2017-02-22  learn sewerjan is oerjan\'s extremely poor twin.
03:55:43  `learn boorjan is oerjan's uneducated twin.
03:55:46  Learned 'boorjan': boorjan is oerjan's uneducated twin.
03:58:46 -!- tromp has quit (Ping timeout: 240 seconds).
03:59:41  `5 w
03:59:47  1/2:amiga//Amiga is Spanish for a female friend. \ pirate//Pirates are humourously nautical persons. Their grammar is friendly and plural. \ apt-get//apt-get installs whatever you wanted, plus whatever Mark Shuttleworth wanted. \ zork//Zork is like York, except for the first letter. Uaneb invented it. \ lie bracket//Politicians try to stay within t
03:59:51  `n
03:59:52  2/2:he lie bracket: Not so many lies that voters cannot stand it, but not so few that they think you have nothing to give them.
04:34:57 -!- hppavilion[1] has joined.
04:39:51 -!- fuzzybunny44 has joined.
04:51:11 -!- tromp has joined.
04:55:43 -!- tromp has quit (Ping timeout: 248 seconds).
05:36:04 -!- fuzzybunny44 has left.
05:42:31 -!- oerjan has quit (Quit: Nite).
05:42:54 -!- sleffy has joined.
05:45:19 -!- tromp has joined.
05:49:35 -!- tromp has quit (Ping timeout: 240 seconds).
06:29:51 -!- PinealGlandOptic has joined.
07:16:48 -!- atslash has joined.
07:21:55 -!- wob_jonas has joined.
07:22:03  `wgrep -i hz
07:22:03  ​/home/hackbot/hackbot.hg/multibot_cmds/lib/limits: line 5: exec: wgrep: not found
07:22:22  ``` grep -Ri hz wisdom
07:22:23  wisdom/sbus:SBus is the standard bus in many a Sun SPARC-based system, capable of coping with thirty-two (32) bits in parallel, at rates of around 16.67 to 25 MHz. There is a 96-pin connector, and the cards lay parallel to the motherboard, like toppings on a sandwich. \ wisdom/2600:2600 Hz is a tone made by Captain Crunch's whistle. \ wisdom/john:J
07:22:35  `2 ``` grep -Ri hz wisdom
07:22:36  2/1:
07:22:53  `1 ``` grep -Ri hz wisdom
07:22:54  1/1:/hackenv/bin/`: eval: line 5: unexpected EOF while looking for matching ``' \ /hackenv/bin/`: eval: line 6: syntax error: unexpected end of file
07:23:06  what
07:23:19  ``` grep -Ri hz wisdom | tail -n+3
07:23:20  wisdom/john:John is not Hziulquoigmnzhah of Cykranosh, the dread spawn of Cxaxukluth, according to http://smbc-comics.com/index.php?id=4072
07:25:10  At least not that John.
07:25:17  apparently that name wasn't even invented by SMBC. I thought it was.
07:25:55  Hmm, I guess "john" has a double meaning that I didn't intend there.
07:33:22 -!- tromp has joined.
07:33:41 -!- tromp has quit (Remote host closed the connection).
07:33:57 -!- tromp has joined.
07:37:16 -!- atslash has quit (Ping timeout: 240 seconds).
07:37:23 -!- atslash has joined.
07:44:52 -!- wob_jonas has quit (Quit: http://www.kiwiirc.com/ - A hand crafted IRC client).
07:56:30 -!- wob_jonas has joined.
07:57:11  M:tG stuff: http://www.manaleak.com/mtguk/2017/06/unstable-magic-the-gathering-spoilers-news-updates/ spoilers for the upcoming Unstable unset.
08:01:12  I expected they'd do more reprints from black-bordered world, but no, only one aside from basic lands.
08:03:22  (and why is the green-white faction green-white too)
08:06:54  Also, apparently that set still uses the fractions from unhinged
08:13:00  fractions *are* broken numbers after all
08:14:03  Do you know this puzzle: I think of a polynomial of any degree with natural coefficients. How many points do you need me to evaluate it at to figure out what it is?
08:14:52  shachaf: that one is easy, but I recall there was some twisted harder version
08:15:15  Yes, it's easy. What's the harder version?
08:15:42  I don't remember
08:15:50  Hmm, easy?
08:16:27  Well, the solution is straightforward.
08:16:31  (the easy, but impossible, version uses integer coefficients)
08:16:59  You mean it's easy because the answer is "it's impossible"?
08:17:06  yes
08:17:14  Sure.
08:17:17  shachaf: no
08:17:26  but here the coefficients are natural numbers
08:17:28  I was talking to int-e.
08:17:31  which makes this possible
08:17:38  that doesn't make a difference
08:17:48  still possible with integer coefficients
08:17:57  Hmm, it is?
08:18:07  the degree is unknown, isn't it
08:18:08  That seems suspicious to me.
08:18:13  Yes, degree is unknown
08:18:14  yes, the degree is unknown
08:18:28  then it's impossible with integer coefficients
08:18:48  no way
08:19:02  you just need to pick your favorite transcendent real number and evaluate it there
08:19:07  right
08:19:12  that uniquely designates the polynomial
08:19:28  the result that is
08:19:43  anyway I want to think a bit
08:19:50  Hmm, I was thinking that the polynomial is evaluated at integer points as well.
08:20:10  oh, it is? that was the harder version, yes
08:20:22  and in that case, two points for natural coeffs and impossible for integer coeffs I believe
08:20:50  (I was also assuming that. Using a transcendental number makes it... ugly.)
08:21:33  Well, I was thinking it but didn't specify it.
08:23:00  ah yes, 2 is enough
08:23:51  Maybe specifying that I had a computable algorithm in mind is enough.
08:30:35  Is it enough?
08:31:11 -!- sleffy has quit (Ping timeout: 248 seconds).
08:32:07  I don't know; I suspect that if you input something like sum 1/2^2^k then the answer will include all the information one needs.
08:45:03  In fact any computable transcendental number greater than 1 will work. The point is that if you use a number greater than 1, then the integer part of the result gives you an upper bound on the coefficients and the degree, so that when you reach the fractions, only finitely many candidate polynomials remain; you can evaluate all those at your number and eliminate those whose value does not equal...
08:45:09  ...the given one. Because the number is transcendental, and disequality of computable reals is semidecidable, only one polynomial will remain in the end.
08:46:05  So is convolution with a kernel, the kind that people talk about in image processing, a special case of the usual convolution?
08:46:08  It seems like it must be, but the relationship isn't obvious.
08:46:37  using a "nice" computable real like that sum 1/2^2^k one I suggested should make it much more efficient though :)
08:46:54  Hmm.
08:47:34  shachaf: yes
08:49:53  How does it work?
08:49:59  The obscure part to me is why it's called a kernel :/
08:50:19  It's just an ordinary discrete, two-dimensional covolution, no magic at all?
08:50:24  *convolution
08:50:49  What are the functions being convolved?
08:51:00  the image
08:51:20  and the kernel, with the center at (0,0), and perhaps a switch from k(x,y) to k(-x,-y).
08:51:43  This works for a 1D image and 1D kernel, right?
08:51:53  The 1D image is presumably a function : [n] -> R or something like that.
08:52:02  What's the 1D kernel?
08:52:02  [n]?
08:52:10  [n] meaning the set of naturals < n
08:52:19  usually an interval [-k,k]
08:52:32  (of integers)
08:52:47  OK, and what's the convolution?
08:52:56  shachaf: works for 2D images too
08:53:00  In general I expect a convolution to look like this: (f * g)(x) = A_{i,j | b(i,j) = x} { c(f(i), g(j)) }
08:53:03  Right?
08:53:08  shachaf: the image is one of the functions, and the kernel is the other one
08:53:27  f |-> \x -> sum_{i in Z} f(x-i)k(i)
08:53:58  shachaf: there has to be a sum in there (unless you're a mathematical physicsist and using tensor notation)
08:54:05  But you said k was only defined on the interval [-k,k]?
08:54:11  wob_jonas: A,b,c are operations
08:54:21  For example A = Σ, b = + , c = ·
08:54:28  Which would make it (f * g)(x) = Σ_{i,j | i + j = x} { f(i)g(j) }
08:54:33  f(x+i) k(i) which is probably how it's implemented, and corresponds to the switch from k(x) to k(-x) I suggested.
08:54:38  shachaf: um, that seems garbled
08:54:44  the non-ascii part that is
08:54:48  but yes
08:55:02  That's supposed to be a capital sigma and a multiplication dot
08:55:16  But A might be min, or maybe an integral or something.
08:55:19  and you either assume the kernel and image are zero in the rest of the places, or you say the sum only goes when both i and j are in the respective domains
08:55:30  right
08:55:39  shachaf: f is the image; g is the kernel, possibly reflected, and one of the points is that g(j) is zero almost everywhere.
08:56:10  hmm, redundancy is redundant.
08:56:23  `? redundancy
08:56:26  Since redundancy exists, it's redundant for Taneb to invent it.
08:56:32  Oh, I guess I see.
08:56:47  int-e: either that or it converges to zero exponentially fast as j goes to infinity and -infinity, and when computing we may approximate the small values with zeros
08:57:04  Concretely convolution in the finite case where b = + usually corresponds the antidiagonals of some matrix, right?
08:57:13  wob_jonas: well the question was about image processing :)
08:57:20  people often convolve images with bell curves, but since they don't need infinite precision, it's practically zero far enough
08:57:44  int-e: for image processing still, people blur images with gaussians
08:58:15  shachaf: yes, for 1d
08:58:39  So what's the matrix here?
08:59:14  wob_jonas: yes, but I believe they tend to do that by iterating rectangular filters like [1/3,1/3,1/3]
08:59:15  shachaf: the matrix is the outer product of two vectors, the first vector is column vector of values of f, second vector is row vector of rosw of g
08:59:37  int-e: that or something similar, which is a good approximation
08:59:48  Say I have an image [1,2,3,4,5,6,7] and I convolve it with the kernel [a,b,c]
08:59:53  they don't always exactly use [1/3,1/3,1/3] but still
09:00:07  wob_jonas: yes, box filters was the main point
09:00:15  What's does the matrix end up being there?
09:00:19  (I believe that's what they are called)
09:01:30  and then there are these fast methods for computing such convolutions even if the image and kernel are both big, of which the most famous is called fast fourier transform, but there are other transform methods
09:01:54  shachaf: [1;2;3;4;5;6;7]*[a,b,c]
09:01:59  I'd expect [c, b+2c, a+2b+3c, 2a+3b+4c, ..., 5a+6b+7c, 6a+7c, 7a] in an actual implementation, and possibly truncated
09:02:13  int-e: that's the convolution
09:02:17  the usual definition would swap a and c.
09:02:20  wob_jonas: But what are the antidiagonals of that?
09:02:42  wob_jonas: wasn't that the question?
09:02:58  shachaf: one antidiagonal is [1*c, 2*b, 3*a]
09:03:11  or backwards maybe
09:03:16  whichever way you read it
09:03:53  int-e: " What's does the matrix end up being there?"
09:05:19  oh if you want to have a trace in the definition
09:05:33  int-e: no
09:05:37  Trace?
09:05:59  sum of diagonal entries, in the case of matrices
09:06:02  wob_jonas: Oh, I see.
09:06:13  So it's just antidiagonals in a non-square matrix.
09:07:50 -!- augur has quit (Remote host closed the connection).
09:10:46  So how does that work with the definition I gave above?
09:10:59  img : [7] -> R
09:11:14  krn : [3] -> R
09:13:14  b(i,j) = i-j, c(x,y) = x*y, A = sum
09:13:30  Pretty sure b should be +
09:13:58  + is standard; - is what implementations tend to do
09:14:00  depends on which direction you convolve. some call the plus version convolution, some call it correlation and the minus version convolution.
09:14:13  it's a terminology difference.
09:14:31  just like which direction of fourier transform is forward is also a terminology difference
09:15:06  you have to read documentation carefully to find out what conventions it uses for the formulas
09:15:24  It's a bit surprising that img/krn don't have the same domain.
09:15:30  to actually get a result of length 9, you should pad 'img' with two zeros to the left and to the right.
09:15:37  But I suppose you can extend them both to Z and define them aas 0 everywhere else.
09:16:02  So how does the 2D version work?
09:16:14 -!- kurolox has joined.
09:16:23  same, but now i and j are pairs and b is pairwise addition
09:16:35  b((i1,i2),(j1,j2)) = (i1-j1,i2-j2)
09:16:36  (or pairwise subtraction, whichever)
09:16:41  or addition
09:16:42  Makes sense.
09:16:53  Subtraction is so confusing.
09:16:57  I want it to be commutative.
09:18:01  you can easily implement one from the other by reversing one of the inputs
09:18:09  Sure.
09:18:12  subtraction corresponds to  r = 0; for (int i = 0; i < ker.length; i++) r += img[x+i]*ker[i]; res[x] = r;
09:19:24  I like convolution in contexts where you don't have inverses so you can't even say f(i)g(x-i)
09:20:43  oh, and the whole thing is made cool by the fact that GPS devices do 1d convolution
09:20:56 -!- imode has quit (Ping timeout: 246 seconds).
09:21:04  They do?
09:21:14  yes, that's one of the most important technological uses
09:28:40  basically GPS satellites can't be each assigned different frequencies like radio stations, so you can't pick their signals out with just simple electronics, their signal is really weak, and they aren't just round-robin broadcasting either, they just all talk at the same time,
09:29:42  so to pick out the voice of one satellite from the others and all the other noise that's actually stronger than the signals, GPS clients digitize the signals they receive and convolve it with what the GPS is expected to say to find out when they received that signal, and they do the convolution in microchips digitally
09:29:59  it's quite crazy
09:39:05 -!- augur has joined.
09:43:05 -!- augur has quit (Ping timeout: 240 seconds).
10:06:04 -!- wob_jonas has quit (Quit: http://www.kiwiirc.com/ - A hand crafted IRC client).
11:29:56  fizzie probably went to work already, right?
12:12:40  What, on a Sunday? 
12:13:06  I'm not that far gone yet.
12:37:50 -!- mroman has joined.
12:37:59  http://codepad.org/5cZlR8am <- feedback/ideas?
12:38:03  it's a 2d bot programming game.
12:38:16  with swarms of bots.
12:39:30  (if a bot dies it'll respawn at the base)
12:40:30  maybe st/ld should be 16bit
12:40:53  that way it's probably possible to have scouting bots scan the whole field into team memory
12:40:59  might be used for pathfinding then
12:54:01  can RET be used for computed gotos?
12:58:07  hmm, there's no indirect addressing it seems
13:01:23  oh and bots might want to know how healthy, strong or eagle-eyed they are.
13:10:57  hm. true.
13:11:02  ret?
13:11:03  yes
13:11:08  you can just push a number and then use ret
13:11:15  call/ret stack and data stack are the same
13:14:35  jumps/calls are absolute
13:14:40  but you can use ret.
13:15:11  and then there's the business of interleaving all that concurrent activity.
13:15:54  well each bot executes one instruction
13:15:56  then the next bot.
13:16:22  A1,B1,A2,B2,A3,B3 I guess.
13:16:50  although might be cool if bot can sleep
13:16:56  and forfeit their time slots for a few rounds.
13:17:06  i.e. if you have the ball
13:17:10  then the other bots sleep
13:17:18  which means the bot with the ball can move faster :D
13:18:27  http://codepad.org/UvEQlm3l <- updated
13:19:56  oh and yeah. bots keep their power-ups
13:20:14  so that taking them actually is of benefit.
13:25:20  what happens if you walk into an obstacle or other bot?
13:27:55 -!- tromp has quit (Remote host closed the connection).
13:28:36  I'd say that's a nop then.
13:28:42  can't walk into non free space
13:28:53  (execept for picking stuff up or returning ball to base)
14:00:07 -!- tromp has joined.
14:04:46 -!- tromp has quit (Ping timeout: 240 seconds).
14:37:03 -!- ATMunn has joined.
14:54:30 -!- tromp has joined.
14:58:46 -!- tromp has quit (Ping timeout: 240 seconds).
15:06:34 -!- mroman has quit (Ping timeout: 260 seconds).
15:34:37 -!- AnotherTest has joined.
15:48:35 -!- tromp has joined.
15:53:15 -!- tromp has quit (Ping timeout: 252 seconds).
16:06:16  `unidecode ςσ
16:06:17  ​[U+03C2 GREEK SMALL LETTER FINAL SIGMA] [U+03C3 GREEK SMALL LETTER SIGMA]
16:13:46 -!- AnotherTest has quit (Ping timeout: 240 seconds).
16:15:50 -!- atslash has quit (Quit: Leaving).
16:16:09 -!- atslash has joined.
16:16:29 -!- jaboja has joined.
16:16:36 -!- atslash has quit (Client Quit).
16:21:09 -!- tromp has joined.
16:24:32 -!- mroman has joined.
16:24:38  re
16:31:37 -!- tromp has quit (Remote host closed the connection).
16:33:14 -!- n00blet has joined.
16:37:58 -!- tromp has joined.
16:41:36  the moment your df interpreter doesn't terminate
16:41:41  you KNOW you fucked up BIG
16:41:44  because df doesn't even have loops.
16:42:28  df, hmm. dwarf fortress, probably not.
16:42:54  oh there was this deadfish thing
16:43:17  wtf
16:43:22  it's just horribly slow
16:43:25  WHAT THE FUCK
16:44:23  so what language stack did you write it in?
16:50:49 -!- tromp has quit (Remote host closed the connection).
16:53:14  python :D
16:53:52  . o O ( perhaps it's a long-winded program )
16:53:56  isidsddsdiisddisiiisiiiiiiiiiiiiio
16:54:00  yay it works.
17:03:46  iiiidsiiiisddddddddddddo
17:03:54  this is great :D
17:05:33  iissdddsddddddo
17:05:36  hehe
17:06:18  iiisiiisiiiiiiiiiio
17:06:24  this looks optimal I'd say
17:06:50  hm. no.
17:18:02  hm
17:18:06  how do I define a nice heuristic function
17:18:11  so that it optimizes also for length.
17:19:34  ah
17:19:35  ok
17:19:40  iissdddsddddddddddddo
17:19:43  now it's optimal :D
17:21:41  iiisiiiisddddddddddddo
17:22:44  for numbers >3, you can just start from the nearest square... except when that square is 256
17:23:07  hi
17:24:33  (and there is a similar special case around 65536, of course)
17:26:39  now... should  iissisdssss  print 0 in deadfish?
17:29:30  hm.
17:29:49  but this is why I believe genetic evolutionary algo stuff will never find certain solutions.
17:30:06  int-e: I know :)
17:30:09  It seems not to be able to be able to find a solution for 257
17:30:17  I wrote a haskell program to generate the shortest dfconstants.
17:30:23  (https://esolangs.org/wiki/Deadfish/Constants)
17:31:33  yeah, 257 is awkward... iissisdddddddddddddddddddddddddddddddd
17:32:20 -!- tromp has joined.
17:36:07  It's never going to combine into that.
17:36:16  it'll reach 255 eventually
17:36:18  but then
17:36:20  it'll stuck
17:40:02  iissisdddddddddddddddddddddddddddddd'o
17:40:14  259
17:40:17  ok works :D
17:40:18  nice
17:41:07  sidssiisiisisdddddddddddddddddddddddddddddddd
17:41:13  probably needs some dead code elimination :D
17:41:20  sidss is pretty useless at the front :D
17:50:10 -!- tromp has quit (Remote host closed the connection).
17:54:53  isi+s+dAdsidi+iAss/aA-aiaiad*d-s-+diii+i+iadd/diA+d+/d
17:54:56  this will produce 257 :D
17:54:59  in extended deadfish :D
17:58:25  yey
18:05:17 -!- trn has quit (Ping timeout: 260 seconds).
18:12:30  [wiki] [[Special:Log/newusers]] create  * Bitmapper *  New user account
18:28:11 -!- tromp has joined.
18:33:17 -!- tromp has quit (Ping timeout: 260 seconds).
18:33:53 -!- zseri has joined.
18:46:45  mroman: how about this, iiisisdddddddsddsiiisddddddsdddddddsddsiiiisiiiii produces -2 on a 32 bit deadfish implementation
18:48:34  (Unlikely to be optimal, but this involves quite a bit of manual effort so I will stop there. Also, doing that for 64 bits seems to be out of reach for me right now)
18:50:57  Some implementations may use decimal arithmetic, such as the one for Famicom and the one for MIX, and possibly some others too.
18:51:22  well, feel free to come up with code for such implementations
18:59:06 -!- trn has joined.
19:01:05  http://codepad.org/mfiYr4C4
19:01:19  my code is probably not the best to produce offspring anyway.
19:01:23 -!- imode has joined.
19:01:34  and always taking the ten best is probably not good.
19:01:41  because the ten best tend to look pretty much alike in the end
19:01:52  so it'll never really produce 257
19:05:17 -!- tromp has joined.
19:09:25 -!- n00blet has changed nick to n00blet_.
19:10:52 -!- n00blet_ has changed nick to o_0.
19:17:14  creationists were right.
19:17:30  evolution is a lousy idea :)
19:17:40 -!- o_0 has changed nick to n00blet.
19:26:16  so much fun... "iiisisdssissdsiississdddsiissiiiisiiiii" produces -2 as well, and is optimal.
19:27:13  iissdddsiiiiiisisdsiisisdsiisiiiiii produces 255, and iissdsdssisiiiisiisssdddsddds produces 257, all assuming 32 bit deadfish
19:31:37 -!- sleffy has joined.
19:35:04  and, finally, a Hello, world! program (with final newline): iiisdsiiiiiiiiossssiiisisioiiiiiiiooiiioisssiiisddsdddddoddddddddddddosssiiisiisddoddddddddoiiioddddddoddddddddossssiisiisdddodsssiiisio
19:48:18 -!- erkin has joined.
19:50:39  hey guys i created hardfish a much harder variant of deadfish
19:51:20  instead of s there's c
19:51:26  where c = one collatz step
19:51:41  so 257 is iiicicciicdcdidcc
19:52:29  or iiiciciicicdcdcc 
19:54:30  mroman: http://codepad.org/vL6jJHNg
19:57:37  this assumes wrap around though right?
19:57:53  yes
19:58:22  That's what I mean by "32 bit deadfish", numbers wrap at 2^32.
20:00:00  hm.
20:00:09  are all numbers reachable with just i and c
20:00:49  obviously
20:01:00  but without any two i's in succession
20:02:17  hmm, yes.
20:06:42  As a sketch, assuming unbounded natural numbers, you can first make the number big (so that the +1 of the 3n+1 becomes negligible for the next phase), then adjust the log_2 to have the right fractional part (the precision required for that is bounded by the target number; if it's n, then you want the fractional part between the fractional parts of log_2(n-1) and log_2(n)), and then divide by 2...
20:06:48  ...repeatedly to get the number you desire.
20:10:10  [wiki] [[Special:Log/newusers]] create  * Mroman2 *  New user account
20:16:49  mroman: the approach is stupid though; for example, 257 is produced by iciciciciciciciciciciciciciciciciciciciciciciciciciciciciciciciciciciciciciciciciciciciciciciciciciciciciccciciciccciciciccciciciciciccccicicciccicicicicicicicicccicciciciciciccccciciciccccicicccicicciccciccccccciciciccicicicc
20:16:54  [wiki] [[Esolang:Introduce yourself]]  https://esolangs.org/w/index.php?diff=52940&oldid=52937 * Mroman2 * (+108) 
20:17:05  [wiki] [[Hardfish]] N https://esolangs.org/w/index.php?oldid=52941 * Mroman2 * (+698) hardfiiiiish
20:17:49  interesting.
20:18:35 -!- n00blet has quit (Ping timeout: 240 seconds).
20:19:39  [wiki] [[Hardfish]]  https://esolangs.org/w/index.php?diff=52942&oldid=52941 * Mroman2 * (+36) /* Some Constants */ starting c is a nop obviously.
20:19:55  I'd talk here more often, but I'd run the risk of self-contradicting people who at the same time don't harbor any hate for me at all, and have a grudge against me.
20:20:54  Of course, I wonder how the world would react if I was also an extremely unforgiving, confusing person.
20:22:05  you are confusing
20:22:42  I'm not unforgiving, though, and I don't contradict myself in the span of a few minutes.
20:22:56  inb4 mroman and everyone else thinks I do.
20:23:12  After all, that's all I ever seem to be.
20:23:13 -!- rdococ has left ("Leaving").
20:25:46 -!- sleffy has quit (Ping timeout: 240 seconds).
20:33:59 -!- MrBismuth has quit (Quit: https://www.youtube.com/watch?v=xIIqYqtR1lY -- Suicide is Painless - Johnny Mandel).
20:36:39  [wiki] [[Hardfish]]  https://esolangs.org/w/index.php?diff=52943&oldid=52942 * Mroman2 * (+129) /* Some Constants */ more constants
20:36:43  mroman: http://sprunge.us/WRFH -- hardfish constants :)
20:37:17  lol
20:37:19  nice
20:37:25  wait
20:37:26  no
20:37:34  you can't have ii in your programs
20:37:53  oh you actually forbade that.
20:37:59  yes.
20:38:10  okay, easy to fix
20:38:20  ah. found 30. iccicccicccicciccicicci
20:41:50  [wiki] [[Hardfish]]  https://esolangs.org/w/index.php?diff=52944&oldid=52943 * Mroman2 * (+173) /* Some Constants */ more constants
20:42:13  my evolver seems to be unable to find something for 38.
20:42:22 -!- MrBusiness has joined.
20:46:52  [wiki] [[Hardfish]]  https://esolangs.org/w/index.php?diff=52945&oldid=52944 * Mroman2 * (+55) /* Some Constants */
20:52:21  mroman: http://sprunge.us/iKHK  then
20:52:46  and a Hello, world!, assuming we add o: iciccicciciccioccicicccccccoicicciccicicciooccccccicccciciccioicciccoccccccccciccoicccccicioiccicicciciccioiciccccccccccicciocicicciccccioccccicccicocciccciccio
20:56:17  did you brute force them?
20:56:23  or use that log2 method?
20:56:30  that's brute force
20:56:44  the log2 method would produce much longer solutions
20:57:29  so it's not that hard :(
20:57:31  well..
20:57:43  for example, 255, 256, 257 would have code of length 643 1106 226, respectively
20:58:10  :D
20:58:13  not very effecient yes
20:59:01  you computed all 2^34 programs?
20:59:05  in this short time?
20:59:06  o_O
20:59:17  it "only" grows as fast as the fibonacci numbers
20:59:27  well
20:59:29  not really 2^32
20:59:33  > fix (scanl(+)1.(0:)) !! 34
20:59:35  since ii is not allowed
20:59:36   9227465
20:59:48  still quite managable, really
21:01:23  what's with the line " 27 - cciccciccicicci" in [[Hardfish]], I think "cc" at the begin is a nop?
21:01:37  > fix (scanl(+)1.(0:)) !! 37 -- actually
21:01:40   39088169
21:02:11  zseri: it was evolved
21:03:46  mroman: but the program actually enumerates values, so if two prefixes produce the same value they only count as one
21:04:06  :D
21:04:08  it was EVOLVED
21:04:09  yes
21:04:14  but I need to do some changes to it.
21:04:16  too boring this way
21:05:08  zseri: people have the same complaint about DNA, most of it is, as far as we can tell, redundant, though sometimes we find a purpose for parts that were previously thought to be unused
21:06:49  mroman: and it turns out that *a lot* of values collapse. Here's a list of the intermediate set sizes: http://sprunge.us/IIjH  (there are two sets in each iteration, one for programs ending in 'c' and one for programs ending in 'i')
21:09:47 -!- PinealGlandOptic has quit (Quit: leaving).
21:10:39  [wiki] [[Hardfish]]  https://esolangs.org/w/index.php?diff=52946&oldid=52945 * Mroman2 * (-89) /* hardfish */ change a lot to make it more intelesting.
21:11:06 -!- dingbat has joined.
21:11:17  [wiki] [[Hardfish]]  https://esolangs.org/w/index.php?diff=52947&oldid=52946 * Mroman2 * (+5) * typo
21:11:48  I'll pass, but 'r' is indeed interesting
21:12:22  [wiki] [[Hardfish]]  https://esolangs.org/w/index.php?diff=52948&oldid=52947 * Mroman2 * (+136) + let's support the o instruction as well.
21:13:01  in particular, it raises the question how to write Hello world with as few 'o' instructions as possible :)
21:14:59  (it's possible with a single 'o' if one can find a code segment that produces 72 from 0, and can also produce all the other necessary values... and that may be tough to put into practice.
21:15:03  )
21:16:42  hmm, iriririr would produce 11?
21:17:19  14
21:17:35  ah, right
21:18:50 -!- Deewiant has quit (Ping timeout: 258 seconds).
21:25:41  qcrcrqirqrqic produces 11 according to my evolver :D
21:26:14  icrcr is also 14
21:26:40  qiriri is 14 as well
21:27:14  iqrqcqiqrqiq is 257 :D
21:28:35  but yes... whether it's possible to have less o's than output characters is interesting
21:29:06  although I have a hunch that these programs are probably longer than the ones with more o's in them
21:29:16  well... gotta go
21:29:19 -!- mroman has quit (Quit: cu).
21:30:35  Am I right in thinking that simply typed lambda calculus + a fixed point combinator is Turing complete?
21:49:38  Taneb: just to clarify, you'd have a fixed point combinator for each type?
21:50:14 -!- zseri has quit (Ping timeout: 260 seconds).
21:51:45  Yes
21:59:30  :t \n f z -> n (\g x -> f (g x)) (\x -> x) z
21:59:31  (((t -> t5) -> t -> t4) -> (t1 -> t1) -> t3 -> t2) -> (t5 -> t4) -> t3 -> t2
22:14:38 -!- erkin has quit (Quit: Ouch! Got SIGABRT, dying...).
22:44:46 -!- tromp has quit (Read error: Connection reset by peer).
22:45:31 -!- tromp has joined.
22:55:47 -!- hppavilion[1] has quit (Ping timeout: 260 seconds).
23:07:59 -!- kurolox has quit (Ping timeout: 248 seconds).
23:31:13 -!- bouncingbuteo has joined.
23:32:36 -!- bouncingbuteo has quit (Client Quit).
23:42:36 -!- iovoid has quit (Quit: *).
23:43:11 -!- iovoid has joined.

2017-08-28:

00:00:02 -!- danieljabailey has quit (Quit: ZNC 1.6.4+deb1 - http://znc.in).
00:00:20 -!- danieljabailey has joined.
00:11:15 -!- augur has joined.
00:25:06 -!- oerjan has joined.
00:27:20 -!- boily has joined.
00:28:59  bohily
00:35:34  bonsϿϿϿϿϿirjan
00:41:01 -!- jaboja has quit (Remote host closed the connection).
01:15:34 -!- ATMunn has changed nick to nnuMTA.
01:15:49 -!- moony has changed nick to ynoom.
01:15:56  `5 w
01:16:02  1/2:diagram//A diagram is just a functor. \ equal temperament//Equal temperament is just intonation that's evenly spaced. \ unlambda//``ci`r`.!`.l`.a`.i`.v`.i`.r`.t`. `.t`.s`.e`.'`.c`. `.,`.a`.d`.b`.m`.a`.l`.n`.U`ci \ french//Le français n'est pas le démon, visitez les Coupeurs. Ne pas couvrir. Meilleur avant! \ orodruin//The Orodruin is a mounta
01:16:12  `n
01:16:13  2/2:in heated by earth spirits. Sauron moved to Mordor because boiling water for his morning tea with the fires of the Orodruin was so convenient.
01:18:19 -!- nnuMTA has changed nick to ATMunn.
01:21:44 -!- jaboja has joined.
01:25:27  `cat bin/w
01:25:28  wisdom "$@"
01:25:36  `cat bin/wisdom
01:25:37  f=$(find wisdom -ipath "wisdom/*$1*" -type f -print0 | shuf --random-source=/dev/urandom -z -n1); if [ -n "$f" ]; then echo -n "${f#wisdom/}//"; cat "$f"; else echo "That's not wise."; fi | rnooodl
01:28:28  `sled bin/wisdom//s/"\${/&/; s#//##
01:28:30  bin/wisdom//f=$(find wisdom -ipath "wisdom/*$1*" -type f -print0 | shuf --random-source=/dev/urandom -z -n1); if [ -n "$f" ]; then echo -n "${f#wisdom/}"; cat "$f"; else echo "That's not wise."; fi | rnooodl
01:28:32  `5 w
01:28:37  1/2:something-that-isn't-in-hackego's-wisdomIt is now. \ zimbabweolsner's desk points zimbabwards. It is highly dependent on tswett's michiganic orientation. \ associativityAssociativity means that h(th) = (ht)h, if you're flexible about it. \ monoidal categoryMonoidal categories are just 2-categories with a single object. \ all the tropes
01:28:43  oops
01:28:44  `revert
01:28:46  Done.
01:28:52  `sled bin/wisdom//s/"\${/&/; s#//#&#
01:28:55  bin/wisdom//f=$(find wisdom -ipath "wisdom/*$1*" -type f -print0 | shuf --random-source=/dev/urandom -z -n1); if [ -n "$f" ]; then echo -n "${f#wisdom/}//"; cat "$f"; else echo "That's not wise."; fi | rnooodl
01:28:56  `5 w
01:29:01  1/2:tea//Tea is concentrated fuel made by distilling occult herbs in a silver alambic. Americans attempted to reduce its potency by dumping some in the Ocean. \ htdh//HtDH is a classic text on How to Design Hotdogs or possibly Hogprams. It is all about functional condiments, and was co-authored by Herence Tao and Don Ho. \ e-module//E-modules
01:29:02  `n
01:29:03  2/2: are modules over a web ring. Uaneb invented them. \ spork//A spork is something to be randomly held in front of penguins. \ quote//Quotes are just elements of the quantum dilapidated bogosphere. See qdb.
01:29:12  oops
01:29:13  `revert
01:29:14  Done.
01:29:24  `sled bin/wisdom//s/"\${/&/; s#//#&#
01:29:26  bin/wisdom//f=$(find wisdom -ipath "wisdom/*$1*" -type f -print0 | shuf --random-source=/dev/urandom -z -n1); if [ -n "$f" ]; then echo -n "${f#wisdom/}//"; cat "$f"; else echo "That's not wise."; fi | rnooodl
01:29:28  `5 w
01:29:33  1/2:stibia//Stibia is a spice that grows in your leg. \ `learn//`learn creates a wisdom entry and tries to guess which word is the key. Syntax (case insensitive): `learn [a|an|the] [s][punctuation] [...] \ fternooner//fternooner (Danish »fternooner«, Norwegian «ttermiddag», Swedish ”ftermiddag”, Icelandic „íðdegis“) is
01:29:36  [wiki] [[Ly]]  https://esolangs.org/w/index.php?diff=52949&oldid=52885 * LyricLy * (-88) 
01:29:37  `n
01:29:38  2/2:a screamingly delicious pastry. \ `help//`help [] gives HackEgo's default help message, or help for a specific command. Or currently possibly some other wisdom. \ yorick//We know nothing about yorick, alas.
01:29:44  Better.
01:30:06  oerjan: do you think color is too much twh
01:31:31 -!- \oren\ has quit (Remote host closed the connection).
01:32:30  color is too much work for me to type in irc, anyway.
01:32:47  Hm?
01:33:04  NEVER MIND
01:43:16  [wiki] [[Ly]]  https://esolangs.org/w/index.php?diff=52950&oldid=52949 * LyricLy * (+95) 
01:47:55  `? coulor
01:47:57  Coulor is the correct spelling.
01:53:42 -!- ybden has quit (Read error: Connection reset by peer).
01:55:13 -!- ybden has joined.
01:58:25 -!- \oren\ has joined.
02:02:01 <\oren\> Wow, AWS machine rebooted for the first time in like a year
02:04:07  Cale: Maybe you understand non-interactive zero-knowledge proofs?
02:04:34  I'm not even sure what that refers to
02:05:57 -!- boily has quit (Quit: INSISTENT CHICKEN).
02:06:26  . o O ( he can only prove he does it in a blog post, not on irc )
02:07:55 -!- sleffy has joined.
02:10:07 -!- sleffy has quit (Client Quit).
02:10:21 -!- sleffy has joined.
02:10:34 -!- sleffy has quit (Client Quit).
02:10:51 -!- sleffy has joined.
02:14:21  [wiki] [[Maybe Later]] N https://esolangs.org/w/index.php?oldid=52951 * TehFlaminTaco * (+4404) Initial Writeup.
02:14:59  [wiki] [[Maybe Later]] M https://esolangs.org/w/index.php?diff=52952&oldid=52951 * TehFlaminTaco * (-25) Category Fixes
02:15:19  [wiki] [[Maybe Later]]  https://esolangs.org/w/index.php?diff=52953&oldid=52952 * TehFlaminTaco * (+0) 
02:16:30  [wiki] [[Language list]] M https://esolangs.org/w/index.php?diff=52954&oldid=52930 * TehFlaminTaco * (+18) Added Maybe Later to the list.
02:19:29 -!- hppavilion[1] has joined.
02:27:55  Cale: Do you like the regular kind of zero-knowledge proofs?
02:28:06  You probably don't like the name because it's probabilistic.
02:56:05 -!- augur has quit (Remote host closed the connection).
03:01:22 -!- sleffy has quit (Ping timeout: 260 seconds).
03:02:46 -!- sleffy has joined.
03:03:16  [wiki] [[Special:Log/newusers]] create  * Kerbybit *  New user account
03:03:25 -!- ATMunn has quit (Quit: See ya! o/).
03:08:26  [wiki] [[Esolang:Introduce yourself]]  https://esolangs.org/w/index.php?diff=52955&oldid=52940 * Kerbybit * (+116) /* Introductions */
03:08:31 -!- augur has joined.
03:17:33  shachaf: I just have zero knowledge about them
03:17:47  Good!
03:35:03 -!- sleffy has quit (Ping timeout: 252 seconds).
03:35:30 -!- sleffy has joined.
03:54:03 -!- hppavilion[1] has quit (Quit: HRII'FHALMA MNAHN'K'YARNAK NGAH NILGH'RI'BTHNKNYTH).
04:10:13  `5 w
04:10:18  1/3:fternooner//fternooner (Danish »fternooner«, Norwegian «ttermiddag», Swedish ”ftermiddag”, Icelandic „íðdegis“) is a screamingly delicious pastry. \ promise problem//A promise problem is one that happens because you promise too much. Their reduction to NP is p. difficult. \ eventually//Eventually we'll have a better wisdom h
04:10:26  `n
04:10:26  2/3:ere. \ despair//Despair is but the first step towards eternal damnation. \ select//select is a very versatile construct: it waits for events, retrieves data from tables, creates a list from elements of an input list that satisfy a condition, a dropdown list element, an event for when selection changes, branches between multiple arms, condit
04:10:28  `n
04:10:29  3/3:ional between two expressions, prints a text-based menu prompt in a loop, and more.
04:14:12  oerjan: if i send you a copy of a jam would you jam it
04:15:09  sorry, i only eat genuine jams hth
04:15:28  I mean computer game.
04:15:53  unlikely hth
04:16:07  (not even sure what that means, but still unlikely.)
04:19:45 -!- sleffy has quit (Ping timeout: 240 seconds).
04:21:59 -!- sleffy has joined.
04:38:59 -!- augur has quit (Quit: Leaving...).
05:14:21  Do you know how to make poker with tarot?
05:30:14  Now I made up a list of the kind of hand of poker with tarot, which has 32 kind of hand
05:34:52 -!- jaboja has quit (Remote host closed the connection).
05:35:11  Do you like this?
05:43:17  If you have the 2 and 4 and 6 of money, and the III and V of trumps, then it makes a impure straight flush.
05:45:48  (Actually I made a mistake there isn't 32 kind of hand)
06:25:46  zzo38: Is that Double Fanucci?
06:26:36  No, it is poker with tarot cards
06:26:50  I think Double Fanucci is better.
06:27:37  We have to figure out the ranking of the hands by the probability.
06:53:18 -!- wob_jonas has joined.
06:54:02  Why are there barely any easily reusable libraries that give you a balanced search tree with a C interface, and can you recommend one?
06:54:33  That sort of thing exists with interfaces for a lot of other programming languages, but I've only seen one with a C interface, the one in GNU libc, and that library is highly nonportable.
06:55:39  In particular, how come APR doesn't have one?
07:01:11  (Also the interface in GNU libc sucks, it's limited)
07:11:32 -!- wob_jonas has quit (Quit: http://www.kiwiirc.com/ - A hand crafted IRC client).
07:28:31 -!- oerjan has quit (Quit: Nite).
07:47:49 -!- mroman has joined.
07:47:55  I have three accounts now
07:48:00  Is this against the policy :D
08:38:34  wtf, who writes "computably enumerable" for "recursively enumerable"
08:41:36  Wouldn't it be a better name?
08:42:15 -!- sleffy has quit (Ping timeout: 240 seconds).
08:43:00  too late now
08:47:59  Taneb: anyway, yes, I believe a fixed point combinator makes the simply typed lambda calculus TC, but what I have in mind would work with Diophantine sets, so it's not exactly obvious. In particular, even with a fixed point combinator, I don't see a way of doing full primitive recursion directly.
08:50:32  int-e, thank you
08:51:10 -!- AnotherTest has joined.
08:52:10 -!- kurolox has joined.
08:56:30 -!- imode has quit (Ping timeout: 240 seconds).
08:56:47  (The best part about that use of "computably enumerable" is the next sentence: 'The MRDP theorem states that a set of integers is Diophantine if and only if it is /computably/ enumerable. A set of integers S is /recursively/ enumerable [...]' https://en.wikipedia.org/wiki/Diophantine_set)
09:05:46 -!- AnotherTest has quit (Ping timeout: 264 seconds).
09:31:59 -!- AnotherTest has joined.
09:35:30  is the fixpoint combinatior this \x.xx thing?
09:35:49  it doesn't have a type in simply typed lambda calculus though
09:39:10  mroman, no, it's \f.(\x.f(x x)) (\x.f(x x)), I think it has the type (X -> X) -> X
09:39:53  Basically it turns f into f (f (f (f (f (f ...
09:40:35  Well, it's not that, because that doesn't type-check.
09:40:41  Well, yes
09:41:14  That's a fixed point combinator in untyped lambda calculus, and a valid type for the whole thingy
09:41:43  But it has to be a black box to the type system
09:41:48  Except you probably need a family of fixed point combinations, I think int-e mentioned.
09:42:55  Yeah
09:43:58  combinators
09:44:04  Wait, what does "combinator" mean again?
09:44:13  I think it should just be called a function.
09:44:14  I don't know, it's kind of an empty word to me
09:44:40  Taneb: Err, I have a gap, since I cannot do subtraction. (I have a predecessor function for Church numerals, but it changes the type of the numeral, so it cannot be iterated). I'm not sure that this can be overcome.
09:45:37  (Subtraction is more or less needed for testing equality; equality testing is needed for encoding Diophantine set)
09:45:53  int-e, hmm, that is an obstacle
09:46:02  Does STLC have a good representation of natural numbers?
09:49:07  Church numerals is the only thing that I can see working; in particular all the nice ADT ideas seem to run into the problem that a type cannot contain itself.
09:50:45  How do Church numerals work?
09:51:21  :t \n f x -> iterate f x !! n
09:51:23  Int -> (a -> a) -> a -> a
09:51:31  Sure, I mean in STLC
09:51:40  Do you just assign some particular type?
09:51:42  you can instantiate (a -> a) -> a -> a 
09:51:53  But nce you instantiate it you get other inhabitants.
09:51:56  o
09:52:20  that doesn't really matter for TC considerations
09:54:09  Sure.
09:54:26  you have a contract, outside of the type system, to only use actual Church numerals
09:54:48  The question was meant more generally.
09:56:29  So anyway, without changing the type you can define a family of functions called extended polynomials. you have constants, addition, multiplication, and if-zero-then-else. not enough to get a predecessor
09:57:41  (that's without fixed point combinators; I don't really have a good handle on how much power they can actually add)
09:58:37  anyway. lunch, work... laters
09:58:44  Can you represent naturals as unfolds instead of folds?
10:22:44 -!- mroman has quit (Ping timeout: 260 seconds).
10:33:26 -!- mroman has joined.
10:34:17  \f.(\x.fxx)(\x.fxx)
10:34:18  this one?
10:35:05  if you call it with x this becomes (\x.xx)(\x.xx)
10:37:23  I still don't understand how fix can terminate in haskell.
10:38:10  ah. lazy evaluation will do it.
10:38:56  but (\x.xx)(\x.xx) definitely doesn't have a type in ST LC.
10:53:04 -!- mroman has quit (Ping timeout: 260 seconds).
10:56:49 -!- erkin has joined.
10:57:43  @tell mroman No, \f.(\x.f(x x))(\x.f(x x))
10:57:44  Consider it noted.
10:58:19  @tell mroman this becomes \f.f ((\x.f(x x))(\x.f(x x))
10:58:19  Consider it noted.
10:58:31  @tell Which is the same but applied to an f
10:58:32  Consider it noted.
11:22:27 -!- erkin has quit (Ping timeout: 260 seconds).
11:28:10 -!- Taneb has left ("Leaving").
11:34:16 -!- boily has joined.
11:58:45 -!- mroman has joined.
11:58:48  `döts Hardfish
11:58:51  ​Ḧärdfïsḧ
11:59:10  @messages-loud
11:59:10  oerjan said 5d 11h 45m 5s ago:  !bftxt_gen <-- EgoBot is dead, use `! bf_txtgen for HackEgo's version
11:59:10  Taneb said 1h 1m 26s ago: No, \f.(\x.f(x x))(\x.f(x x))
11:59:10  Taneb said 1h 51s ago: this becomes \f.f ((\x.f(x x))(\x.f(x x))
12:07:03  [wiki] [[Härdfïsh]] N https://esolangs.org/w/index.php?oldid=52956 * Mroman2 * (+895) Created page with "''Härdfïsh'' is a cross-over of [[Brainfuck]] and [[Hardfish]]. It introduces the , instruction from Brainfuck which is used to input a character (ASCII) wherea..."
12:07:57  [wiki] [[Hardfish]]  https://esolangs.org/w/index.php?diff=52957&oldid=52948 * Mroman2 * (+53) 
12:16:44  [wiki] [[Härdfïsh]]  https://esolangs.org/w/index.php?diff=52958&oldid=52956 * Mroman2 * (+150) * algorithms
12:16:51  [wiki] [[Härdfïsh]]  https://esolangs.org/w/index.php?diff=52959&oldid=52958 * Mroman2 * (+1) /* = Setting a cell to one */
12:17:35  [wiki] [[Härdfïsh]]  https://esolangs.org/w/index.php?diff=52960&oldid=52959 * Mroman2 * (+102) /* Setting a cell to one */ moo :(
12:19:08 -!- boily has quit (Quit: MINIM CHICKEN).
12:20:33 -!- atslash has joined.
12:36:46  [wiki] [[Hardfish]]  https://esolangs.org/w/index.php?diff=52961&oldid=52957 * Mroman2 * (+125) /* Some Constants */
12:38:39  [wiki] [[Hardfish]]  https://esolangs.org/w/index.php?diff=52962&oldid=52961 * Mroman2 * (+0) /* With r */
12:39:03  [wiki] [[Hardfish]]  https://esolangs.org/w/index.php?diff=52963&oldid=52962 * Mroman2 * (+69) /* Some Constants */
12:50:08  @tell taneb https://mathoverflow.net/questions/261934/is-simply-typed-lambda-calculus-with-fixed-point-combinator-turing-complete
12:50:08  Consider it noted.
13:01:18 -!- Vorpal has joined.
13:01:18 -!- Vorpal has quit (Changing host).
13:01:18 -!- Vorpal has joined.
13:07:14  [wiki] [[Hardfish]]  https://esolangs.org/w/index.php?diff=52964&oldid=52963 * Mroman2 * (+378) /* With r */
13:07:58  [wiki] [[Hardfish]]  https://esolangs.org/w/index.php?diff=52965&oldid=52964 * Mroman2 * (-10) /* With r */ fucked up the spaces.
13:16:08 -!- jaboja has joined.
13:21:36  [wiki] [[Hardfish]]  https://esolangs.org/w/index.php?diff=52966&oldid=52965 * Mroman2 * (+5943) /* With r */ all constants with r (non optimal)
13:23:00  [wiki] [[Hardfish]]  https://esolangs.org/w/index.php?diff=52967&oldid=52966 * Mroman2 * (+6821) /* Without r */ all constast without r (non optimal)
13:23:34  ah shit.
13:24:40  [wiki] [[Hardfish]]  https://esolangs.org/w/index.php?diff=52968&oldid=52967 * Mroman2 * (-5943) Undo revision 52966 by [[Special:Contributions/Mroman2|Mroman2]] ([[User talk:Mroman2|talk]])
13:30:01  [wiki] [[Hardfish]]  https://esolangs.org/w/index.php?diff=52969&oldid=52968 * Mroman2 * (-3464) ! this time it should be correct.
13:40:12  The other day walked past a forest planted by "the Kent Men of the Trees".
13:40:14  They sound like a tribe or a cult or something.
13:42:13 -!- mroman has quit (Quit: away).
13:51:42 -!- zseri has joined.
14:10:05 -!- jaboja has quit (Ping timeout: 240 seconds).
14:19:54 -!- ATMunn has joined.
14:32:48 -!- `^_^v has joined.
14:36:42 -!- mroman has joined.
14:37:31  tfw even a guy from 10'000 BC could draw better animals than you
15:07:07  Hey fizzie, have you commited the fixes to UMLBox?
15:44:15 -!- MDude has quit (Ping timeout: 240 seconds).
15:59:31 -!- ynoom has changed nick to moony.
16:01:49  someday somebody will look at brainfuck programs
16:01:54  and it will be like voynich manuscript
16:01:59  lol
16:02:19  experts will disagree on the time period
16:02:22  and think it's a hoax
16:02:46  while others will say it's a cipher hiding important information about extinct plants.
16:03:00  others agree that it was created by kids on cocaine
16:03:31  but they don't know what cocaine was
16:03:36  it has been lost
16:03:38  they just know it's some drug
16:03:47  so maybe some of the brainfuck stuff contains instructions on how to create cocaine
16:03:57  I had the idea for a programming language that uses only sets. (Only type is a set. A set can contain a set. Sets can be combined, split by a reference set, have all matches in one set removed from another, and have all matches duplicated)
16:04:21  And, i actually think it *might* be turing complete. Which is intresting.
16:04:56  (Oh, forgot to mention, sets can be compared, and either jmp if yes or just continue if no)
16:06:45  i already know a pseudo-fibonnaci can be made (With the amount of sets in the set 'A' being the number)
16:08:07  pseudo arthimetric and a jump-if-equal... Yea. Anyone else have a opinion on this? I think it should be possible to do 3-cell unbounded brainfuck.
16:15:18  In fact... Hmm, wow, i think it should be possible to make a turing complete language by using 3 of any datastructure that can contain itself. Bounded or not.
16:39:36  kurolox: Hadn't when you asked, but now sent them out: https://bitbucket.org/GregorR/umlbox/pull-requests/1
16:42:50 -!- imode has joined.
16:49:26  cool fizzie
16:49:38  I haven't showed you what I've done with UMLBox, by the way
16:49:48  https://github.com/Kurolox/ArcoexBot
16:51:30  I saw that screenshot, just a few hours late.
16:51:32  Don't know anything about Discord though.
16:53:06 -!- Deewiant has joined.
16:56:09  wow, why would you repeat the fs contents  instead of padding with zeros
16:56:54  *shrug*
16:57:10  That probably has something to do with „Ghost in the Shell“ from the 2017s.
16:57:52  int-e: I don't know, but that seems clearly to be what's happening. I haven't looked it up in the code.
16:58:21  Can't blame you, I wouldn't either.
16:58:27  But it is curious :)
17:05:17  Well, I see where it happens in the code, but I don't really know the intention.
17:06:16  There's a read loop of the form   do { n = pread(...); ... } while ((n < len) && (n != 0)).
17:07:04  I'm guessing it used to use regular "read" at some point, in which case that'd repeatedly read until enough bytes had been read or an EOF occurred.
17:07:16  Since read would advance the file offset.
17:07:35  And then maybe later on it was changed to a pread call, which takes the offset as an argument, but the loop wasn't modified to increment that.
17:07:44  So maybe it's actually a bug.
17:07:44 -!- AnotherTest has quit (Ping timeout: 246 seconds).
17:07:59  *shrug*
17:08:14  ,o0(git blame)
17:09:15 -!- Phantom_Hoover has joined.
17:09:32  https://github.com/torvalds/linux/commit/8c6157b6b -- looks that way.
17:10:29  Well, "bug" is arguable, I don't think the documentation specifies what *should* happen when the backing file isn't multiple-of-a-block sized.
17:10:44  But repeatedly reading from the same offset is at least a little odd.
17:12:48  if (n < len) memset(&buf[n], 0, len - n); <-- so it was supposed to pad with zeros.
17:13:23  Yes, if it hit EOF. Of course now it won't ever do so.
17:13:32  It does smell a little buggy.
17:13:54  so yes it's a bug... though I have a hard time imagining any actual problems... and that's despite having an actual example! :P
17:14:32  (I mean, if you emulate a block device, you shouldn't be returning partial blocks)
17:14:48  I'd post on the devel mailing list but that seems like too much work.
17:17:32  lkml is scary
17:17:47  I guess you'd go to the uml one
17:18:04  (hoping that there is one)
17:18:26 -!- Taneb has joined.
17:18:33  I think Ive been losing channels
17:20:08  int-e, thanks for looking that up for me1
17:20:22  actually a colleague found it for me :)
17:20:24  int-e: There's a user-mode-linux-devel@lists.sourceforge.net that does seem to be still getting some traffic.
17:20:44  int-e, thank your colleague for me, then
17:23:37  will do
17:32:43  uh, i wonder if that could be used to write to kernel memory? *Totally understands*
17:34:22  *shrug*
17:46:36 -!- sleffy has joined.
17:53:39 -!- mroman has quit (Ping timeout: 260 seconds).
18:34:45 -!- mroman has joined.
18:34:58  relcome to the finish hub 
18:48:09  Is there any CSS media selector for monochrome? (This will be most useful in case of printers, although it can apply to monochrome displays as well)
18:55:17 -!- MDude has joined.
19:01:57  @media all and (monochrome)
19:01:57  Unknown command, try @list
19:02:19  at least that's what mozillas dev guide mention
19:02:21  epaper?
19:02:28  https://developer.mozilla.org/de/docs/Web/CSS/Media_Queries/Using_media_queries#monochrome
19:02:44  I mean, there *are* modern monochrome displays.
19:03:07  there's even @media tv and (scan: progressive) { ... }
19:03:45  is there a test for interlacing too?
19:03:49  Determines whether the output device is a grid device or a bitmap device.  If the device is grid-based (such as a TTY terminal or a phone display with only one font), the value is 1.  Otherwise it is zero.
19:03:58  and there's grid selector
19:04:00  interesting.
19:04:21  in case lynx supports css3 or what?
19:06:02  MONOHCROME
19:06:03  WHAT IS THIS
19:06:11  THE 70s CALLED?
19:06:45  there's also min-monochrome
19:06:48  i.e. for gameboys
19:06:56  which have 4bit monochrome color
19:08:24   -moz-windows-theme Requires Gecko 2.0(Firefox 4 / Thunderbird 3.3 / SeaMonkey 2.1) 
19:08:25  haha
19:08:26  ok
19:08:31  I guess that's what phishers use
19:08:33  and spammers
19:08:50  so they can present a fake overlay that looks like an actual windows window
19:09:04  just query the theme they use to present the most realistic fake window :D
19:10:46  int-e: there's a test for handheld
19:10:52  not sure if dot matrix printers count as handheld :D
19:11:07  and there's a test for progressive/interlace yes
19:12:04  Pseudo-BNF (for those of you that like that kind of thing)
19:12:08  bnf?
19:12:17  beautiful nude females?
19:12:26  Backus–Naur form.
19:12:30  I know :D
19:12:45  BraiNFuck
19:13:15  [,  ]
19:13:26  I guess this is a sink program then.
19:15:12  is htmlx still a thing?
19:15:17  or what was it called
19:15:24  XHTML? 
19:15:35  hta
19:16:25  presumably this style is getting somewhat popular again
19:16:36  Apparently there's a XHTML syntax variant as part of HTML5.
19:16:41  https://www.w3.org/TR/html5/the-xhtml-syntax.html
19:16:47  except that instead of running code in the browser you run it in a local node.js
19:17:04  https://en.wikipedia.org/wiki/Electron_(software_framework)
19:17:08  ^- Atom is using that apparentely
19:18:23  I hate node.js 
19:19:19  fizzie: hta was html+visual basic (executed by IE)
19:21:14  Well, Mozilla's got their XUL as well.
19:23:10 -!- archibald__ has joined.
19:24:07  I think grid and monochrome make sense, although I am not sure why you need to test for progressive scan.
19:26:04  I think handheld shouldn't be needed either (although tests for some of the features of handheld (individually) can make some more sense).
19:29:16  If you hate Node.js then you need not use it, although, I use Node.js (but not Electron; I will usually make command-line programs or SDL).
19:31:18  I hate javascript as well ;)
19:32:20  Then that seem a good enough reason to hate Node.js if you hate JavaScript
19:34:20  There are some problems with JavaScript I think, such as a lack of macros and lack of goto, but usually they aren't much problematic
19:37:30 -!- erkin has joined.
19:40:47  zzo38, eww 'goto
19:50:20  eh
19:50:24  any good games out there?
19:51:40  I suppose depend, what game you want?
19:55:31  I don't know.
19:55:33  That's the problem :D
19:56:28  :D
19:57:06  A computer game, card game, or chess game?
19:57:19  Games rock.
19:57:26  heh I was assuming computer game, by default
19:57:26  (or ones that are more than one of this; that happens too)
19:57:41  but that doesn't really solve the problem since there are multitudes of them
19:58:22  *shruhg*
19:58:39  s/uhg/ug/
19:59:13  what's with the halloween craze, it's not even september
19:59:23  (is there another spooky event coming up?)
19:59:50 * int-e is looking at https://www.humblebundle.com/spooky-horror-bundle
20:00:07  (but won't buy)
20:00:11  I happen to like the NES/Famicom game "Lunar Limit", which you may run on a NES/Famicom emulator or hardware.
20:06:48  yeh computer games
20:06:57  for other games I'd need other people
20:07:01  which I don't have 
20:07:18  and can't have
20:07:21  too sick for that
20:09:09  puzzle, adventure, role playing, jump&run, shooter, strategy, simulator, racing... this still seems rather unspecific so far :P
20:10:31  not a huge fan of FPS.
20:10:47  and it's gotta by lightweight
20:11:01  should run on a ultralight notebook
20:11:11  and without mouse
20:11:11  so
20:11:13  probably more racing/strategy
20:12:18 -!- jaboja has joined.
20:12:55  mmm lightweight
20:13:29  yeah
20:13:33  gotta fight into my backpack
20:13:38  :D
20:13:40  well
20:13:45  also it gotta fit into my backpack
20:13:59  why does my brain write fit as fight
20:14:59  I wanted to go travel for a long time
20:15:04  but too sick all the time to actually do it.
20:15:48  so... I waited hoping it would get better eventually
20:16:13  but now I'm in the "fuck it. if it's not better within n weeks I'm gonna pack my things and travel the world" mood.
20:16:50  because arguably sitting ill at home somehow managing to go to work and not get fired everyday isn't really too much of a great life either.
20:17:22  I guess the most lightweight games I'm currently enjoying are the wadjet eye games adventure games
20:18:13  you're constantly asking yourself "what the fuck am I working for just so I can spend the time I'm not working in pain (and the time I'm working)"
20:18:17  also it's gotta work offline
20:18:30  might not have internet everywhere
20:20:49  funny, gog lists spacechem under "strategy"
20:21:00  (but also "puzzle")
20:21:31  and actually, looking at the screenshots there may be a strategy component to it.
20:24:56  int-e is wise.
20:27:59  `grwp mockery
20:28:03  No output.
20:28:09  `quote mockery
20:28:10  No output.
20:30:04 -!- moony has changed nick to ICZEROSMELLS.
20:30:06 -!- ICZEROSMELLS has changed nick to moony.
20:30:29 -!- h0rsep0wer has joined.
20:33:38  spacechem looks nice
20:37:30  shenzhen I/O is nice too.
20:40:51 -!- AnotherTest has joined.
20:51:53  And TIS-100 in the middle.
20:53:22  In the middle between nice and nice?
20:54:09 -!- archibald__ has quit (Quit: Leaving).
20:55:11 -!- `^_^v has quit (Quit: Leaving).
21:01:34  released between the two?
21:09:02 -!- `^_^v has joined.
21:14:43 -!- augur has joined.
21:15:36 -!- AnotherTest has quit (Read error: Connection reset by peer).
21:20:08  S:I/O is more polished than TIS-100, but they're both neat games with different challenges
21:20:45  I want a standalone version of the konstruktor game
21:21:58  (this one, http://www.zachtronics.com/kohctpyktop-engineer-of-the-people/ )
21:23:10 -!- h0rsep0wer has quit (Quit: Leaving).
21:24:49 -!- mroman has quit (Ping timeout: 260 seconds).
21:30:34 <\oren\> ugh... the entire machine goes catatonic everytime I run this
21:31:20 <\oren\> we turned off memory limits, so now it is just using up every byte of memory and the system is fucked
21:32:30  hmm, "this"
21:33:26 <\oren\> int-e: it's a program that, apparently, tries to load everything into memory regardless of whether it fits
21:40:28 -!- MDude has quit (Quit: Going offline, see ya! (www.adiirc.com)).
21:40:33 -!- iovoid has quit (Ping timeout: 248 seconds).
21:48:26  int-e, I'd like a standalone Codex of Alchemical Engineering, I think that was the first Zachtronics game I played
21:50:12  it's called spacechem :P
21:50:40  alercah, Spacechem has a similar mechanic and conceit but a completely different aesthetic!
21:50:58  Taneb: actually it's not too difficult to just download the right files.
21:51:19  (for the one I wanted, perhaps that's also true for yours...)
21:55:18 <\oren\> Also: why the hell can hipchat insert a .gif file, but not a .txt file?
21:55:47 <\oren\> why is hipchat so stuuupiiid
21:57:27  what about "hip" doesn't suggest "stupid"?
21:58:04 <\oren\> atlassian is a terrible company
22:00:40 -!- zseri has quit (Quit: Page closed).
22:24:42  int-e: Did you *have* to post that link? I'm on vacation, I can't afford to get stuck by a flash game for the rest of it.
22:28:12 -!- `^_^v has quit (Quit: This computer has gone to sleep).
22:29:11 -!- `^_^v has joined.
22:29:11 -!- `^_^v has quit (Client Quit).
22:31:33 -!- erkin has quit (Quit: Ouch! Got SIGABRT, dying...).
22:33:36  fizzie: you can save it for later, when you're back at work
22:43:58  I'm not sure I can.
22:45:54 -!- boily has joined.
22:56:26  `5 w
22:56:33  1/2:sentience//sentience is the primary goal of wisdom. wisdom is the primary goal of sentience. \ companion cube//There's cake inside it. Tear it apart, rip open your companion, and extract the delicious, delicious cake... \ kitt//Kitt is the singular of kitten. \ physiology//Physiology looks confusingly like psychology when written in Eng
22:59:39  `n
22:59:40  2/2:lish. \ nightstar//The Nightstars are an unscientific myth of a sky covered in faint flickering lights. Only hermits and superstitious farmers believe this.
22:59:54  sentience is the primary goal of fungot. fungot shall not reach sentience.
22:59:54  boily: the world of space, or maybe even most cases things are independent. the results of the previous roll has no bearing on the current roll!
23:06:58 -!- MDude has joined.
23:07:00 -!- MDead has joined.
23:11:47 -!- MDead has quit (Ping timeout: 260 seconds).
23:12:13 -!- MDude has quit (Ping timeout: 276 seconds).
23:14:40 -!- augur has quit (Remote host closed the connection).
23:14:45 -!- MDude has joined.
23:15:19 -!- augur has joined.
23:19:43 -!- augur has quit (Ping timeout: 248 seconds).
23:29:08 -!- ais523 has joined.
23:31:55 -!- ais523 has quit (Read error: Connection reset by peer).
23:32:20 -!- ais523 has joined.
23:32:24 <\oren\> "Due to light pollution, the Milky Way is not visible to more than one-third of humanity, including 60% of Europeans and nearly 80% of North Americans."
23:34:08  \oren\: I don't think I've ever seen it with my eyes unaided
23:34:25 <\oren\> http://advances.sciencemag.org/content/2/6/e1600377.full
23:35:54 <\oren\> In large cities, it never gets dark enough to actually count as nautical nighttime
23:36:26 <\oren\> in the centre of a city, monochrome night-vision is never necessary 
23:36:54  Spent all day at the hospital. Had an X-ray and a CT scan and all sorts of things.
23:37:02  Seems like I'm OK.
23:37:46 -!- iovoid has joined.
23:43:12 -!- Phantom_Hoover has quit (Read error: Connection reset by peer).
23:49:47  helloochaf. everything's fine?
23:52:15 -!- ais523 has quit.
23:52:24 -!- ais523 has joined.
23:53:29  Seems to be.
23:54:14 -!- boily has quit (Ping timeout: 240 seconds).

2017-08-29:

00:14:38  `hrlist
00:14:39  ​/home/hackbot/hackbot.hg/multibot_cmds/lib/limits: line 5: exec: hrlist: not found
00:17:37 -!- hppavilion[1] has joined.
00:25:22  There needs to be an hsrlist
00:25:23  `hsrlist
00:25:24  ​/home/hackbot/hackbot.hg/multibot_cmds/lib/limits: line 5: exec: hsrlist: not found
00:25:28  :/
00:28:44 -!- kurolox has quit (Ping timeout: 246 seconds).
00:36:44 -!- MDude has quit (Read error: Connection reset by peer).
00:41:59 -!- iovoid has quit (Quit: *).
00:42:48 -!- iovoid has joined.
00:48:44 -!- augur has joined.
00:50:07 -!- jaboja has quit (Remote host closed the connection).
01:00:00 -!- alercah has quit (Remote host closed the connection).
01:05:54 -!- sebbu has quit (Ping timeout: 252 seconds).
01:15:00 -!- Sgeo_ has joined.
01:16:44 -!- Sgeo has quit (Ping timeout: 240 seconds).
01:25:55 -!- sebbu has joined.
01:26:43 -!- alercah has joined.
01:33:24 -!- sleffy has quit (Ping timeout: 252 seconds).
03:02:35 -!- ATMunn has quit (Quit: See ya! o/).
03:53:41  [wiki] [[Talk:Maybe Later]] N https://esolangs.org/w/index.php?oldid=52970 * Enoua5 * (+910) Created page with "Hey, this is a very nice language. I actually had a very similar idea quite awhile ago and never perused it. Glad to see that someone has made this. Poking around with the lan..."
03:54:32  [wiki] [[Talk:Maybe Later]] M https://esolangs.org/w/index.php?diff=52971&oldid=52970 * Enoua5 * (+0) 
05:04:08  [wiki] [[Ly]]  https://esolangs.org/w/index.php?diff=52972&oldid=52950 * LyricLy * (+111) 
05:42:27 -!- sleffy has joined.
06:11:59 -!- sleffy has quit (Ping timeout: 248 seconds).
06:12:46 -!- sleffy has joined.
07:04:12 -!- FreeFull has quit.
07:39:05 <* Taneb> good morning
07:44:08 -!- sleffy has quit (Ping timeout: 246 seconds).
07:50:47 -!- tromp has quit (Remote host closed the connection).
07:53:03 -!- tromp has joined.
07:53:03 -!- tromp has quit (Remote host closed the connection).
07:53:16 -!- tromp has joined.
07:53:33  @@ Taneb: Good (@time Taneb)
07:53:33   Taneb: Good
07:53:34  Local time for Taneb is Tue Aug 29 07:53:33
07:53:37  Bah.
07:54:01  shachaf, good effort
07:55:08  Taneb: So now that you're working at your job, you'll have more opportunities to visit CA, right?
07:56:45  I'll have more ability to visit CA! But probably less opportunity
07:57:33  What is an opportunity, without ability?
07:57:41  Or: What is ability, without opportunity?
07:57:50  Maybe you can visit for a conference.
07:58:15  That would be nice!
07:58:26  I'm going to be at ICFP next week, that's a conference, but it's not in CA
07:58:40  international california of functional programming
08:00:18  I should go to ICFP.
08:01:46  It'll be harder for me to go next year probably
08:02:43  My cool idea for a text editor didn't work because of a bug in watch :(
08:02:46  Hmm, it'll be in Missouri.
08:03:10  Maybe you can get a job in Missouri between now and then.
08:03:13  Then it'll be easy.
08:03:25  Speaking of which, I saw a baseball game last week.
08:03:33  (it was ed in one window and watch -ctd "source-highlight-esc.sh $FILE | nl" in another)
08:03:41  shachaf, did they base the balls?
08:04:03  I believe so.
08:04:09  But I was very confused. I didn't know the rules.
08:04:27  Are you familiar with cricket?
08:04:43  It's kind of like cricket except completely different
08:04:53  Until recently I didn't realize cricket wasn't the same game as croquet.
08:05:22  I'm fairly sure croquet is a third sport entirely
08:05:56  Right, one which I'd played some variant of.
08:06:09  When people talked about cricket I thought that was the game they were referring to.
08:07:33  Oh, right, Alice played croquet.
08:08:10  "Each phase of play is called an innings"
08:08:13  is this some sort of joke
08:08:20  the maths doesn't work out
08:09:02  How so?
08:09:20  The equivalent thing in baseball is called an "inning".
08:09:50  That's like how Americans call maths "math"
08:09:54  Exactly the same thing
08:10:03  I call each math a math.
08:10:04  It's short for inningematics
08:10:28  Toplogy, set theory, D-modules, each of them a math
08:10:38  If you learn several of them, you're studying maths
08:10:52  I can agree with that
08:11:12  In my alternate usage, a theorem is an example of a math
08:11:40  I can also agree with that
08:11:44 <* Taneb> is in an agreeable mood
08:12:41  Can you agree to meet me in St. Louis?
08:13:02  I cannot
08:13:10  I don't even know where St Louis is
08:13:14  Lousiana?
08:13:26  It's around ICFP 2018
08:13:37  So if you go, you can't miss it
08:13:37  Ah, I see!
08:13:57  Also there's a song called "Meet Me in St. Louis" which I'd never heard until just now.
08:14:00  I don't know if I'll have enough money then for trips, I'm planning to go to Japan in April
08:14:10  Remind me whether you read olist?
08:14:20  I do not
08:14:30  Tried a couple of times, couldn't get into it
08:14:43  I learned of the song from http://www.giantitp.com/comics/oots0383.html
08:19:41 -!- tromp has quit (Remote host closed the connection).
08:20:24 -!- ais523 has quit (Ping timeout: 252 seconds).
08:24:53 -!- AnotherTest has joined.
08:26:54 -!- mroman has joined.
08:27:01  re
08:31:17 -!- augur has quit (Remote host closed the connection).
08:31:53 -!- augur has joined.
08:36:17 -!- augur has quit (Ping timeout: 246 seconds).
08:36:44 -!- AnotherTest has quit (Ping timeout: 240 seconds).
08:42:23 -!- AnotherTest has joined.
08:52:27 -!- kurolox has joined.
09:00:56 -!- tromp has joined.
09:01:39 -!- imode has quit (Ping timeout: 252 seconds).
09:05:19 -!- tromp has quit (Ping timeout: 255 seconds).
09:31:13 -!- augur has joined.
09:37:10 -!- augur has quit (Ping timeout: 240 seconds).
09:40:46  \o/
09:44:13   ^\o_O/^
09:44:29   "\o_O/ "
09:44:31  fizzie, I've found a weird bug in umlbox. I'm sure you'll have fun.
09:44:33  `? hutnuhtnaeu
09:44:36  hutnuhtnaeu? ¯\(°​_o)/¯
09:44:54   `\o_O/`
09:44:57  hm.
09:45:17  ^döts mroman
09:45:21  `döts mroman
09:45:22  mrömän
09:45:46  ň
09:46:34  ǎčďěǧȟǐǰǩľňǒřšťǔǚž
09:46:59  ǚü
09:47:00  hm.
09:47:06  so v is turned into a u when doing this
09:47:43  ãẽĩ
09:48:17  unicode lacks voynich symbols.
09:57:37 -!- Sgeo_ has quit (Ping timeout: 248 seconds).
10:02:01  kurolox: What sort of? 
10:04:19 -!- mroman has quit (Ping timeout: 260 seconds).
10:05:22  fizzie: Trying to run flask won't work, but only if you specify a timeout.
10:06:00  sorry, not flask
10:06:01  elixir
10:07:56  So, if you try to run this: umlbox -B elixir -e 'IO.puts("Hello World")'
10:08:05  it will work, but if you specify a timeout, even a dumb one, like this
10:08:20  umlbox -B -T 99999999 elixir -e 'IO.puts("Hello World")'
10:08:22  it won't work
10:08:53  using the -v flag in both gives the same output
10:13:48  Odd. But maybe not odd enough to start installing things to try out.
10:13:52  Looking at what setting a timeout does, probably something about init's process manipulations.
10:24:34 -!- Sgeo has joined.
10:29:21 -!- AnotherTest has quit (Ping timeout: 240 seconds).
10:48:59 -!- tromp has joined.
10:49:38 -!- AnotherTest has joined.
10:53:37 -!- tromp has quit (Ping timeout: 248 seconds).
11:11:27 -!- clog has quit (Ping timeout: 252 seconds).
11:31:50 -!- hppavilion[0] has joined.
11:34:09 -!- hppavilion[1] has quit (Ping timeout: 248 seconds).
11:36:28 -!- boily has joined.
11:47:26 -!- clog has joined.
12:02:22  `5 w
12:02:27  1/2:hagb4rd//hagb4rd is one spacey fellow. Spaaaaaaaaaaaaaaace. \ covfefe//Covfefe is how you speak when you've had *way* too much coffee. \ cello//The high level structure of Cello projects is inspired by /Haskell/, while the syntax and semantics are inspired by /Python/ and /Obj-C/. \ mirth/
12:02:28  `n
12:02:29  2/2:/Mirths are juvenile moths. They giggle a lot. \ oklopol//oklopol "so i hear these blogs are getting popular, people like writing about their lives and shit. on this thing called the internet which is like a neural network only really stupid."
12:14:31 -!- tromp has joined.
12:17:42 -!- erkin has joined.
12:19:16 -!- tromp has quit (Ping timeout: 246 seconds).
12:23:14 -!- boily has quit (Quit: CENTAUR CHICKEN).
12:31:50 -!- LKoen has joined.
12:38:43 -!- zseri has joined.
12:42:59 -!- zseri has quit (Ping timeout: 260 seconds).
13:09:11 -!- tromp has joined.
13:13:51 -!- tromp has quit (Ping timeout: 248 seconds).
14:03:11 -!- martinhez has joined.
14:03:26 -!- tromp has joined.
14:05:53 -!- martinhez has quit (Client Quit).
14:06:10 -!- martinhez has joined.
14:08:00 -!- tromp has quit (Ping timeout: 252 seconds).
14:23:14 -!- ATMunn has joined.
14:32:40 -!- erkin has quit (Quit: Ouch! Got SIGABRT, dying...).
14:45:57 -!- martinhez has quit (Read error: Connection reset by peer).
14:58:18 -!- zseri has joined.
15:01:41 -!- sebbu has quit (Ping timeout: 240 seconds).
15:05:18 -!- LKoen has quit (Remote host closed the connection).
15:15:09 -!- mig22 has joined.
15:15:20 -!- sebbu has joined.
15:15:24 -!- mig22 has quit (Client Quit).
15:16:30 -!- sebbu2 has joined.
15:20:10 -!- sebbu has quit (Ping timeout: 255 seconds).
15:41:40 -!- jaboja has joined.
15:41:57 -!- joast has quit (Quit: Leaving.).
15:45:01 -!- sebbu has joined.
15:46:55 -!- PinealGlandOptic has joined.
15:48:31 -!- sebbu2 has quit (Ping timeout: 255 seconds).
15:51:39 -!- tromp has joined.
15:56:01 -!- tromp has quit (Ping timeout: 248 seconds).
15:58:39 -!- AnotherTest has quit (Ping timeout: 248 seconds).
16:00:58 -!- AnotherTest has joined.
16:05:01 -!- AnotherTest has quit (Ping timeout: 240 seconds).
16:10:12 -!- AnotherTest has joined.
16:15:58 -!- hppavilion[0] has quit (Ping timeout: 264 seconds).
16:16:19 -!- mroman has joined.
16:17:20  Isn't there a brainfuck version where cells are 1bit?
16:17:26  Is it turing complete?
16:17:29  (I'd suspect so)
16:19:38  I don't think the size of the cells is relevant for turing-completeness
16:19:43  as long as it's larger than zero bits
17:38:13  boolfuck
17:38:35  mroman: ^
17:40:09 -!- tromp has joined.
17:44:35 -!- tromp has quit (Ping timeout: 240 seconds).
17:49:02 -!- augur has joined.
17:52:37 -!- FreeFull has joined.
17:53:46 -!- augur has quit (Ping timeout: 264 seconds).
17:58:12  are there compiler people? is SIMD SSEx instructions should be scheduled correctly? does modern CPUs has several ports to execute them?
17:59:57 -!- AnotherTest has quit (Ping timeout: 260 seconds).
18:00:01 -!- sleffy has joined.
18:00:33  `olist 1095
18:00:34  olist 1095: shachaf oerjan Sgeo FireFly boily nortti b_jonas
18:02:31 -!- tromp has joined.
18:15:20 -!- tromp has quit (Remote host closed the connection).
18:16:35 -!- imode has joined.
18:21:02 -!- Phantom_Hoover has joined.
18:25:03 -!- sebbu2 has joined.
18:28:42 -!- sebbu has quit (Ping timeout: 252 seconds).
18:34:46 -!- erkin has joined.
18:40:15 -!- AnotherTest has joined.
18:58:35 -!- imode has quit (Ping timeout: 246 seconds).
18:58:45 -!- sebbu has joined.
18:59:03 -!- imode has joined.
18:59:13  PinealGlandOptic: I think you need to rephrase that question.
19:01:48 -!- sebbu2 has quit (Ping timeout: 240 seconds).
19:02:48 -!- sleffy has quit (Ping timeout: 252 seconds).
19:04:33 -!- tromp has joined.
19:09:22 -!- tromp has quit (Ping timeout: 260 seconds).
19:11:03 -!- AnotherTest has quit (Read error: Connection reset by peer).
19:12:13 -!- jaboja has quit (Remote host closed the connection).
19:12:21 <\oren\> With tropical storm harvey, Has anyone made a Houston we have a problem joke yet?
19:18:27  mroman: OK, common x86 instructions need to be reordered for better scheduling. does the same applied to SIMD instructions?
19:19:55 -!- augur has joined.
19:21:40 -!- jaboja has joined.
19:24:31 -!- augur has quit (Ping timeout: 255 seconds).
19:28:47 -!- tromp has joined.
19:38:45 -!- ais523 has joined.
19:59:57 -!- rodgort has quit (Quit: Leaving).
20:03:58 -!- rodgort has joined.
20:08:48 -!- deltab has quit (Ping timeout: 240 seconds).
20:09:31  PinealGlandOptic: I don't know.
20:22:26 -!- Phantom__Hoover has joined.
20:26:32 -!- Phantom_Hoover has quit (Ping timeout: 255 seconds).
20:39:29 -!- ais523 has quit.
20:39:39 -!- ais523 has joined.
20:54:11 -!- tromp has quit (Remote host closed the connection).
21:06:14 -!- augur has joined.
21:09:12 -!- tromp has joined.
21:10:41 -!- augur has quit (Ping timeout: 248 seconds).
21:11:09 -!- augur has joined.
21:39:01 -!- tromp has quit (Remote host closed the connection).
21:46:39 -!- rdococ has joined.
21:48:42  hm
21:49:18  an esoOS could handle newlines weirdly: carriage return would reset the cursor to the beginning of the line without moving it down; while the newline character would just move it down
21:49:34 -!- mroman has quit (Ping timeout: 260 seconds).
21:50:26  so e.g. using arrows to demonstrate CR and LF, abc←def would show up as abc and def overlayed, but abc↓def would show up as abc followed by def shifted down
21:50:54  abc←↓def would have what we know as a newline
21:51:00 -!- tromp has joined.
21:53:35  rdococ: actually terminals handle CR and LF like that already; Linux has a translation layer inside the kernel that translates newline to CRLF so that it will work with terminals, but you can turn it off or reconfigure it
21:53:56  ais523: esoOS shouldn't have such a translation layer, then
21:56:01 -!- jaboja has quit (Ping timeout: 248 seconds).
21:57:33 -!- ais523 has quit (Remote host closed the connection).
22:04:26  Things that annoy me: "int main() {return false;}" is a valid implementation of true
22:04:30 -!- Taneb has left ("Leaving").
22:04:35 -!- Taneb has joined.
22:04:44 -!- zseri has quit (Ping timeout: 260 seconds).
22:04:47  Further things that annoy me: brushing my touchpad and parting an IRC channel
22:04:59  lol
22:07:55  hm
22:08:03  does carriage return in a terminal enable overlaying text?
22:20:55 -!- atslash has quit (Ping timeout: 246 seconds).
22:23:29  Only if it's a hardcopy terminal.
22:24:58  I vaguely remember some formatting language (maybe something-roff) having a syntax for bold that's, for bold "foo", "fBfoBooBo" where B is the backspace character.
22:25:13  Because that'd double-strike "foo".
22:26:11  lol
22:26:24  an actual backspace character would be cool too
22:28:52  Doesn't the INTERCAL operator list include one character you'd type as V, backspace, -? 
22:29:44  I guess that same formatting language would have "fB_oB_oB_" for backspace
22:29:50  s/backspace/underline/
22:30:01 -!- jaboja has joined.
22:33:09  [wiki] [[Ly]]  https://esolangs.org/w/index.php?diff=52973&oldid=52972 * LyricLy * (-4) 
22:38:14 -!- tromp has quit (Remote host closed the connection).
22:39:58 -!- tromp has joined.
22:42:47  fizzie: a backspace character escape sequence that could do that might be cool in an esolang
22:44:46 -!- Sgeo has quit (Read error: Connection reset by peer).
22:45:32  fizzie: GNU less(1) does that, and man(1) uses it for its formatting
22:45:39  try e.g.  printf $'f\x08fo\x08oo\x08o foo' | less
22:46:09  it does underlining with _ as well, like what rdococ suggested
22:47:06  vim has a setting to make  act as an infix compose in insert-mode
22:47:13  I tested the command, and that does work
22:47:21  (same as i_^K)
22:48:07  I know that there's also old APL charsets relying on backspace characters for overstriking (the APL charset is heavily oriented around overstriking)
22:48:27  (because it was originally designed around the restrictions of an IBM Selectric typeball)
22:48:29 -!- boily has joined.
22:48:57  Well, the first programming-language/digital version was. it was a mathematical notation before that, for paper/blackboard use, obviously not constrainted by typeballs)
22:49:00  -)
22:49:05  oddly enough, the formatting above doesn't work with strikethrough using -
22:49:25  I only know of bold and underline being supported in less
22:49:43  odd
22:49:55  the esoOS terminal should support any overlaying with that
22:49:57  I believe ALGOL variants used underline to distinguish between keywords (from symbols), and implemented that with overstrike.
22:50:02  so a with ^ would be aB^
22:50:31 -!- iovoid has quit (Ping timeout: 276 seconds).
22:50:36  strikethrough would be fB-oB-oB-
22:51:01 -!- iovoid has joined.
22:51:01 -!- iovoid has quit (Changing host).
22:51:01 -!- iovoid has joined.
22:51:39  I read at some point that a lot of the punctuation of ASCII was intentionally designed to facilitate overstriking to produce diacritics… some of them are obvious (like c^ for ĉ), but other less so (like c, for ç)
22:51:53  and o" for ö
22:52:50  ah
22:53:17  I think it's neat/cute :P
22:53:30  ...yay
22:55:28  I was going to test whether compose-c-, still results by default in ç, but for some reason my compose key now just produces a ~.
22:55:44  "The ASCII code supports six different diacritics. These are: grave accent, tilde, acute accent (approximated by the apostrophe), diaeresis (double quote), cedilla (comma), and circumflex accent. Each is typed by typing the preceding character, then backspace, and then the 'related character', which is `, ~, ', ", , or ^, respectively for the above-mentioned accents."
22:56:01  (from https://en.wikipedia.org/wiki/Overstrike)
22:56:07  might've been where I read it
22:56:26  fizzie: it does, FWIW, at least for me
22:57:01  counterstrike
22:57:03  Hmm
22:57:05  Wonder if compose key stopping working is synergy's fault. It seems to be doing something a little weird about caps lock as well.
22:57:58  https://twitter.com/FireyFly/status/899965577481129984  ← this might be interesting to this channel, since bitmap fonts have been a topic before, and it's kind of in the spirit of esolangs/eso-computing (well, inasmuch as codegolf/demoscene/such stuff is)
22:58:29  well, the idea is just based on https://hackaday.com/2016/12/15/character-generation-in-144-bytes/ (which I credit in the twitter thread)
23:00:12  Those tiles look sort-of-kind-of similar as how N-segment LED displays (where N > 7) do alphanumerics.
23:00:29  Heh
23:00:54  Makes sense
23:04:49 -!- kurolox has quit (Ping timeout: 248 seconds).
23:12:18 -!- tromp has quit (Remote host closed the connection).
23:19:46 -!- Sgeo has joined.
23:19:56 -!- deltab has joined.
23:24:08 -!- deltab has quit (Client Quit).
23:24:26 -!- deltab has joined.
23:44:40 -!- Phantom__Hoover has quit (Read error: Connection reset by peer).
23:48:20 -!- hppavilion[1] has joined.
23:49:13  hi hppavilion[1].
23:49:19  we were discussing ASCII and overstrike.
23:56:19 -!- erkin has quit (Quit: Ouch! Got SIGABRT, dying...).
23:57:13  is there a language where inserting lists into lists is equivalent to inserting each element at the corresponding position?
23:57:21  e.g. (1, 2, (3, 4)) == (1, 2, 3, 4)
23:59:53 -!- iovoid has quit (Quit: *).

2017-08-30:

00:00:59 -!- iovoid has joined.
00:04:41 -!- tromp has joined.
00:04:41 -!- boily has quit (Quit: VOCAL CHICKEN).
00:05:00 -!- sleffy has joined.
00:06:12 -!- [io] has joined.
00:06:12 -!- [io] has quit (Changing host).
00:06:12 -!- [io] has joined.
00:08:01 -!- iovoid has quit (Ping timeout: 255 seconds).
00:09:21 -!- tromp has quit (Ping timeout: 248 seconds).
00:10:25 -!- [io] has changed nick to iovoi.
00:10:52 -!- iovoi has changed nick to iovoid.
00:11:02 <\oren\> the swedish chef goes bork bork bork
00:11:22 <\oren\> the stupid program that eats all memory goes brk brk brk
00:12:46  and the rdococ eats both
00:15:42  moo
00:24:39  rdococ: I'm not aware of any languages, but a naive tree data structure will get you that
00:24:51  re list insertion
00:34:21  ah
00:34:46  a pair is kinda like a binary tree if you think hard enough
00:46:00  alercah: is there a program which enables overstrike?
00:46:10  s/enables/allows/
00:46:51  ab⌫⌫yay
00:50:57  rdococ: I don't know if any font rendering really does it these days
00:51:18  aw.
00:54:14  that said, I'm far from certain there isn't
00:54:21  \oren\: does your font do combining characters?
00:54:32  rdococ: I mean, you can do a lot with combining characters
00:54:44  you can even make regex parse html!
00:55:11  yey
00:59:28  anyway, how about an esolang with string formatting like that? e.g. "b\Bbo\Bol\Bld\Bd, u\B_n\B_d\B_e\B_r\B_l\B_i\B_n\B_e\B_, s\B-t\B-r\B-i\B-k\B-e\B-t\B-h\B-r\B-o\B-u\B-g\B-h\B-"
00:59:28  "\B" could be replaced with something like "^H".
00:59:28 -!- p- has joined.
00:59:44  lol
01:01:12  lol
01:01:22  that formatting system is kinda unwieldy :P
01:01:49 -!- Lymia has quit (Ping timeout: 276 seconds).
01:02:32  hm. how about \b for the special backspace, \r for carriage return, and \f for line feed?
01:03:13  its good bro
01:04:04  meh
01:04:05 -!- Lymia has joined.
01:04:10  hi Lymia
01:05:59  hi
01:06:03  hm. what if \CR was carriage return and \LF was line feed? then the overstriking backspace character would be \BS.
01:06:41  I was also considering ^M for carriage return
01:07:50 -!- p- has quit (Remote host closed the connection).
01:09:00  The other idea I had was having reserved variables for BS, CR and LF, and you would use a concatenation operator on them.
01:09:25  e.g. "abc" + CR + "___" would be an easy underlining method.
01:25:32 -!- oerjan has joined.
01:49:37  Still no italic, though.
01:52:57 -!- tromp has joined.
01:57:05 -!- tromp has quit (Ping timeout: 240 seconds).
02:05:03  yay
02:13:38 -!- tromp has joined.
02:17:53 -!- tromp has quit (Ping timeout: 248 seconds).
02:26:13 -!- jaboja has quit (Ping timeout: 240 seconds).
02:29:23 -!- jaboja has joined.
02:49:28 -!- tromp has joined.
02:53:37 -!- tromp has quit (Ping timeout: 248 seconds).
03:03:26 -!- ATMunn has quit (Quit: See ya! o/).
03:33:15  damnit. I wish redis supported empty keys.
03:33:22  or rather, empty lists and hashes.
03:35:11 -!- iovoid has quit (Remote host closed the connection).
03:36:20 -!- hppavilion[1] has quit (Read error: Connection reset by peer).
03:43:20 -!- tromp has joined.
03:45:32  `addquote  int-e: Did you *have* to post that link? I'm on vacation, I can't afford to get stuck by a flash game for the rest of it.   fizzie: you can save it for later, when you're back at work
03:45:36  1314)  int-e: Did you *have* to post that link? I'm on vacation, I can't afford to get stuck by a flash game for the rest of it.   fizzie: you can save it for later, when you're back at work
03:48:03 -!- tromp has quit (Ping timeout: 252 seconds).
03:50:58 -!- iovoid has joined.
03:50:58 -!- iovoid has quit (Changing host).
03:50:58 -!- iovoid has joined.
03:56:53  `? just intonation
03:56:54  Bad-tempered people can be recognized by just intonation.
04:19:37  rdococ: printf 'h\bh_\bi\n' | less
04:20:39  that style of formatting was used sometimes in fortune files
05:03:38  https://motherboard.vice.com/en_us/article/d7ywqz/create-a-game-within-a-game-using-shenzhen-io
05:12:09   is there a language where inserting lists into lists is equivalent to inserting each element at the corresponding position? <-- perl
05:12:57  `perl-e print 1,2,((3,4),5)
05:12:58  12345
05:13:27  oh
05:13:27  nice
05:14:51 -!- augur has quit (Remote host closed the connection).
05:15:09  alercah: ^
05:16:55  huh
05:20:31 -!- augur has joined.
05:28:51  is there a language where the keys in associative arrays can be any type, including other arrays, functions and whatnot?
05:30:34  I think lua can do that
05:30:56  although it wouldn't really work out because lua tables and stuff are kinda weird
05:31:21 -!- tromp has joined.
05:36:15 -!- tromp has quit (Ping timeout: 248 seconds).
05:36:35 -!- sleffy has quit (Ping timeout: 240 seconds).
05:38:46 -!- sleffy has joined.
05:46:01 -!- atslash has joined.
05:55:00 * oerjan wishes scott aaronson would stop mixing math and politics in the same post.
05:56:22  because the politics ruins the comment sections which are usually so good when there's just math
05:56:45  oerjan, what was the maths about
05:57:10  the latest P vs NP proof attempt by Blum
05:58:06  Ah!
06:00:43  btw if you haven't spotted the latest astronomy rumor http://www.nature.com/news/rumours-swell-over-new-kind-of-gravitational-wave-sighting-1.22482
06:06:15  relatedly, it may be that without neutron stars, we'd have neither gold nor nuclear bombs...
06:13:46 -!- Sgeo_ has joined.
06:15:52 -!- Sgeo has quit (Ping timeout: 246 seconds).
06:26:04 -!- tromp has joined.
06:30:51 -!- tromp has quit (Ping timeout: 252 seconds).
06:33:34 <\oren\> FUCK YOU GOOGLE YOU SHIT COMPANY WHY ARE YOU ALWAYS FUCKING UP YOUTUBE
06:33:50 <\oren\> shachaf: fix youtube, it is fucked up
06:35:07 <\oren\> suddenly there are only 4 youtube videos per row, next to abunch of empty space
06:35:23 <\oren\> wtf is that empty space for?
06:37:27  hm i get six
06:38:43 <\oren\> oerjan: you haven't been selected for a "trial" of their new, fucked, layout
06:40:07 <\oren\> apparently they included a "restore old youtube"  button
06:40:16 <\oren\> pressing that shit so fast
06:40:34  I just feel like screaming. To everybody.
06:43:16 -!- oerjan has quit (Quit: Nite).
06:45:46 <\oren\> shachaf: is google's new motto "we must secure the existence of out ad revenue stream and a future of huge empty white spaces in graphic design"
06:47:31 <\oren\> google is literally hitler
06:48:47  that's quite obvious
06:49:02  well, to be fair, \oren\, that's an insult to hitler
06:49:07  \oren\: Huh? I haven't worked at Google since 2014.
06:49:21 -!- jaboja has quit (Ping timeout: 248 seconds).
06:49:24  And I thankfully never worked on YouTube.
06:49:29 <\oren\> shachaf: damn it!
06:49:42 <\oren\> I need to complain to somone!
06:50:11 -!- rdococ has left ("Leaving").
06:50:13 <\oren\> this new design was like satan barfed on my screen
06:50:30  Anyway you should see the -- you know, never mind.
06:51:43 <\oren\> shachaf: niconicodouga doesn't fuck up their layout every year
06:52:46  \oren\: Solution: Go work at Google, and then you can complain internally.
06:53:30 <\oren\> shachaf: I thought complaining at google leads to being branded a nazi and fired?
06:54:16  ...what
06:54:42  I don't think that happened to anyone I know.
06:54:46  as much as google is bad, I wouldn't quite compare them to hitler and the nazis
06:54:59  And I knew lots of people at Google whose favorite activity was complaining.
06:55:02 <\oren\> Hoolootwo: have you seen the new colors on youtube?
06:55:09  Also you can probably make a lot more money.
06:55:09  I don't watch youtube
06:55:27 <\oren\> Hoolootwo: well they should be tried in the Hague
06:55:37  my roommate's chromecast has an ad 00:01 permanantly stuck in the corner though
06:56:51  it's a personal goal of mine to get tried in the hague, but hopefully not for that
06:57:53 <\oren\> you know I only recently learned that the hague is a city, and not a building
06:58:25  I hear entry level engineer total compensation at Google is ~$180k/year nowadays.
06:59:15  I wonder whether SV wages will keep going up or stay constant or pop.
07:00:03 -!- tromp has joined.
07:00:32 <\oren\> shachaf: what is total yearly rent and car in silicon valley?
07:00:58  Not sure.
07:01:22  Car costs aren't all that variable by location in the US, I think.
07:02:32 -!- FreeFull has quit.
07:02:49  Rent is pretty expensive, especially if you want to live by yourself, but I'm not up to date on the numbers.
07:06:05  even if not, I hear
07:06:28  so is food, and last I was in california, I paid double for gas
07:06:42  Petrol is so cheap in the US that even if you pay double it's fine.
07:06:44  well, in most parts, 1.5,
07:07:59 <\oren\> it isn't fine if you're used to getting to work for 3$ on public transit
07:10:05  If you work at one of the big silly valley companies you can get to work for free on the shuttle.
07:11:01  I go to school on $0 in transit
07:11:24  same with basically everything else
07:11:35  if I want to go home, it's $50 round trip at most
07:12:08 -!- rdococ has joined.
07:12:13  I currently walk to work, 5 minute walk.
07:14:25 <\oren\> I walk home every day. I should walk to work too, but I'm too lazy to walk both ways 
07:23:13  yeah, over the past summer, it was 7 minutes from my apartment to the 4th floor office
07:23:17  most of my classes are faster
07:31:31 -!- augur has quit (Remote host closed the connection).
07:44:35 -!- mroman has joined.
07:44:42  morning
07:46:24 -!- jaboja has joined.
07:52:15 -!- sleffy has quit (Ping timeout: 248 seconds).
08:00:16 -!- augur has joined.
08:04:31 -!- augur has quit (Ping timeout: 248 seconds).
08:09:30 -!- shikhin has quit (Ping timeout: 240 seconds).
08:11:51 -!- shikhin has joined.
08:12:14 -!- shikhin has changed nick to Guest76900.
08:13:28 -!- imode has quit (Ping timeout: 246 seconds).
08:21:32 -!- AnotherTest has joined.
08:29:05 -!- jaboja has quit (Ping timeout: 248 seconds).
08:41:57 -!- p- has joined.
08:42:26  [wiki] [[Härdfïsh]]  https://esolangs.org/w/index.php?diff=52974&oldid=52960 * Mroman2 * (+48) 
08:44:00 -!- p- has quit (Remote host closed the connection).
08:44:27 -!- p- has joined.
08:51:43 -!- p- has quit (Ping timeout: 240 seconds).
09:01:48 -!- p- has joined.
09:05:24 -!- p- has quit (Remote host closed the connection).
09:05:51 -!- p- has joined.
09:08:07 -!- p- has quit (Client Quit).
09:51:16 -!- kurolox has joined.
09:59:13 -!- Sgeo_ has quit (Ping timeout: 240 seconds).
10:25:30 -!- Sgeo has joined.
10:39:34 -!- mroman has quit (Ping timeout: 260 seconds).
10:50:21 -!- atslash has quit (Ping timeout: 240 seconds).
10:50:30 -!- atslash has joined.
11:33:53 -!- boily has joined.
11:37:25 -!- b_jonas has joined.
11:39:30  ARGH! what the fuck is the point of having the list of different parts of the webpage be links that only work if javascript is allowed? no, it's not even in one of those stupid javascript-based rolldown menus. no, it's not just highlighting the link background when it's hovered on that doesn't work.
11:39:51  The fucking links only work if you click on them. They're not actual links you can select with keyboard. Not even with caret browsing. 
11:40:57  They're some stupid li element that you can only follow through an onclick event, even though that event is just a javascript that loads another page.
11:41:36  It's not doing anything magical like replacing half the page and rendering it client side from queries or anything. Just plain mouse-only links, reinvented with a bad javascript implementation.
11:41:40  Seriously.
11:51:42  how else do you ensure that your google analytics code is used properly :P
12:15:36 -!- jaboja has joined.
12:16:07 -!- grumble has quit (Quit: once).
12:17:50 -!- grumble has joined.
12:28:19 -!- boily has quit (Quit: SUBURBIAN CHICKEN).
12:32:40 -!- augur has joined.
12:34:09 -!- Guest21903 has joined.
12:36:09 -!- Guest21903 has quit (Quit: Saliendo).
12:37:34 -!- augur has quit (Ping timeout: 264 seconds).
12:45:22 -!- Guest76900 has changed nick to shikhin_.
12:45:52 -!- shikhin_ has changed nick to Guest66154.
12:46:08 -!- Guest66154 has changed nick to shikhin`.
12:46:13 -!- shikhin` has quit (Changing host).
12:46:13 -!- shikhin` has joined.
12:46:23 -!- shikhin` has changed nick to shikhin.
13:07:01 -!- grumble has quit (*.net *.split).
13:07:01 -!- jaboja has quit (*.net *.split).
13:07:01 -!- kurolox has quit (*.net *.split).
13:07:01 -!- rodgort has quit (*.net *.split).
13:07:01 -!- digitalcold has quit (*.net *.split).
13:07:01 -!- APic has quit (*.net *.split).
13:07:33 -!- APic has joined.
13:07:38 -!- grumble has joined.
13:08:12 -!- rodgort has joined.
13:11:54  wtf, is https://unicode.org down?
13:12:37 -!- digitalcold has joined.
13:12:39  int-e: hehe. that page doesn't use google analytics though. it does use some facebook thing.
13:20:21  b_jonas: I suspect zzo38, he wants to finally establish his own character encoding
13:21:03  Also, http://www.unicode.org/ is down. I had to check archive.org's copy of the HTML-rendered unicode line break rules.
13:21:27  int-e: wait, what's that a reply to?
13:21:50  oh, you mean he's the reason why unicode.org is down?
13:21:51  b_jonas: unicode.org being down
13:22:03 -!- jaboja has joined.
13:22:03 -!- kurolox has joined.
13:22:04  I don't think that's a reason
13:22:05  but ok
13:22:12  although zzo38 is a good idea, for a different reason.
13:22:33  zzo38: any reaction to MaRo's spoilers of Unstable (the future un-set)?
13:24:27  . o O (Un-icode? )
14:17:40  https://gist.github.com/anonymous/464ba89ac19cab8fd573ab62c21bbb6b << I hate C. (this is my own code)
14:19:29 -!- jaboja has quit (Remote host closed the connection).
14:31:23 -!- ATMunn has joined.
14:33:20 -!- augur has joined.
14:37:30 -!- augur has quit (Ping timeout: 240 seconds).
14:45:03 -!- augur has joined.
14:49:19 -!- augur has quit (Ping timeout: 246 seconds).
14:57:52 -!- augur has joined.
15:02:07 -!- augur has quit (Ping timeout: 248 seconds).
15:22:32  What the heck is the "role" HTML attribute? I can't find it in https://www.w3.org/TR/html401/index/attributes.html or http://w3c.github.io/html/fullindex.html#attributes-table or https://developer.mozilla.org/en-US/docs/Web/HTML/Reference
15:23:01  (HTML4 standard, HTML5 draft, Mozilla developer docs HTML respectively)
15:23:34  ah found: https://www.w3.org/TR/role-attribute/
15:28:54 -!- joast has joined.
15:31:59 -!- zseri has joined.
15:45:24 -!- jaboja has joined.
16:19:59 -!- augur has joined.
17:04:50 -!- augur has quit (Read error: Connection reset by peer).
17:09:17 -!- olsner has quit (Ping timeout: 246 seconds).
17:12:36  [wiki] [[Special:Log/newusers]] create  * Avian *  New user account
17:13:01 -!- AnotherTest has quit (Ping timeout: 240 seconds).
17:41:56 -!- FreeFull has joined.
17:49:21  I was looking for translation icon images (used as an icon on webpages to show where you can change the interface or content to a different language) that have a letter A and an あ kana next to each other. Apparently there's another variant of these, which has a 文 hanzi and a letter A.
17:49:48  I haven't seen that variant yet. I think I prefer Aあ because that's more recognizable to me, but I'm not sure which one is better.
17:50:41  文A might work better because that hanzi is common (and so recognizable) in both Chinese and Japanese apparently
17:58:19 -!- Sgeo has quit (Ping timeout: 246 seconds).
17:58:20 -!- Sgeo_ has joined.
18:01:46 -!- olsner has joined.
18:04:42 -!- Sgeo_ has quit (Ping timeout: 240 seconds).
18:10:17  [wiki] [[Esolang:Introduce yourself]]  https://esolangs.org/w/index.php?diff=52975&oldid=52955 * Avian * (+158) /* Introductions */
18:13:19  [wiki] [[FiM++]]  https://esolangs.org/w/index.php?diff=52976&oldid=47240 * Avian * (+106) 
18:19:36 -!- sleffy has joined.
18:26:54  I wish bash had some quoting style that lets you easily quote any URL. But alas, apostrophes doesn't work because the URL can contain apostrophe, and double quotes don't work because the URL can contain a dollar sign which is special inside double quotes.
18:31:09 -!- ais523 has joined.
18:37:15 -!- Phantom_Hoover has joined.
18:43:19  [wiki] [[Truth-machine]]  https://esolangs.org/w/index.php?diff=52977&oldid=52266 * JWinslow23 * (+235) Added a Whitespace implementation (heavily golfed; pushing 0 with SSL instead of SSSSL, and a blank label name)
18:48:26 -!- imode has joined.
18:59:36 -!- ais523 has quit.
19:11:20 -!- AnotherTest has joined.
19:12:36 -!- jaboja has quit (Remote host closed the connection).
19:24:53  dammit...
19:27:41 <\oren\> hirdococ, what's up?
19:28:18  hi
19:28:23  the sky
19:29:29  what an unexpected pattern of behavior
19:31:55 <\oren\> I bet black holes don't really exist
19:50:28  black holes suck
19:56:12 -!- AnotherTest has quit (Read error: Connection reset by peer).
20:08:42 -!- sleffy has quit (Ping timeout: 240 seconds).
20:20:01 -!- jaboja has joined.
20:37:12 -!- augur has joined.
20:40:36 -!- jaboja has quit (Read error: Connection reset by peer).
20:40:54 -!- jaboja has joined.
20:42:29 -!- sleffy has joined.
20:53:35 -!- sleffy has quit (Ping timeout: 248 seconds).
20:55:28  rdococ, i assure you, they also blow.
20:55:37  lol
20:55:52  ...i just realised how that sounds
20:55:58 -!- sleffy has joined.
20:56:00 * moony facekeyboards
20:56:09 * rdococ keyfacepals
21:04:50 <\oren\> "Robert Mugabe denies he cast an ‘evil spell’ on the vice president of Zimbabwe" like, why would he need to deny that
21:33:55  moony: lol
21:41:53 -!- augur has quit (Remote host closed the connection).
21:42:08 -!- wob_jonas has joined.
21:43:50  So some of Autstralia has DST, but they use summer time only for approximately five months, not for approximately seven months like much of Europe and the U.S. does. Strange.
21:55:57 -!- kurolox has quit (Ping timeout: 252 seconds).
22:03:43 -!- augur has joined.
22:06:26 -!- augur has quit (Remote host closed the connection).
22:06:42 -!- augur has joined.
22:10:30  wob_jonas: do you mean six months instead of five?
22:11:00  (Australia seems to switch on the first Sunday in April and October)
22:11:13  no, I mean five months instead of seven
22:11:16  approximately
22:11:22  it's not an exact count of months
22:12:15  from the first Sunday in October to the first Sunday of April is five months of summer time in Australia
22:12:39  (and that's just some of Australia, some parts don't use DST at all, which makes sense because they're closer to the equator)
22:12:40  It really isn't.
22:12:58  it's as close to 6 as you can get
22:13:07  (while switching on Sundays)
22:13:12  hmm wait
22:14:21  ok, then those parts of Australia have six months. and much of Europe and America have seven.
22:14:28  so it's six months instead of seven.
22:14:37  that's much less of a difference, I can understand that.
22:14:38  (well that last claim of mine wasn't accurate, but close enough for this discussion)
22:14:54 -!- MDude has joined.
22:22:29 -!- zseri has quit (Ping timeout: 260 seconds).
22:24:28 -!- rdococ has changed nick to RdOcOc.
22:30:44 -!- RdOcOc has changed nick to rdococ.
22:31:33 -!- rdococ has changed nick to RdOcOc.
22:32:25 -!- RdOcOc has changed nick to RdococX.
22:32:31 -!- RdococX has changed nick to rdococ.
22:34:49 <\oren\> Daylight savings time is crap anyway. they should jsut change work schedules based on season if light matters
22:34:52 -!- tswett has joined.
22:35:27 <\oren\> then it doesn't have to bother office workers like me for whom the sun is largely irrelevant
22:36:53  \oren\: but it would be much harder to convince people to change work schedules based on season. For one, it would be more confusing because most clock faces wouldn't show the difference, so you wouldn't be able to tell which schedule you're supposed to follow. A lot of timetables and opening hours labels would have to be reprinted, including ones 
22:36:53  stickered in very big letters on a supermarket saying "OPEN EVERY SUNDAY 7-15" or something
22:37:33  \oren\: and it's supposed to be relevant for office workers too, because the advantages mostly present when you're NOT in the office during normal office hours, but at home or traveling
22:37:41  s/traveling/commuting/
22:38:38  There's still other good arguments for saying DST is crap of course, but I don't think "change work schedules based on season" makes sense.
22:39:25  I think I've convinced myself that DST is a good thing at least twice and that DST is a bad thing (in Hungary that is) at least twice at different times, so I'm not sure what to think anymore.
22:40:09  I agree; the 1 hour time shift in working schedule *is* the problem I associate with DST.
22:40:28  agree with who?
22:41:26  well, the idea that if changing the work schedules instead of doing the DST switch is awful
22:41:56  ok, it just wasn't clear if you said you agree with \oren\ or agree with me
22:43:07  of course, it still makes sense to use UTC for times that aren't tied to a geographical location or shouldn't be tied to DST, but most human schedules are tied
22:43:24 -!- PinealGlandOptic has quit (Quit: leaving).
22:48:32  I do think that DST isn't worth the biannual hassle (and confusion about which countries switch when, if at all).
22:50:02  daylight scow time
22:50:37 -!- rdococ has left ("Leaving").
22:54:16  the "which countries switch when" is not too much of a hassle usually, because different countries often use different time zones anyway, so you have to check timezones already, and most of Europe has DST switch at the same time (Iceland and Russia and Belarus and Turkey don't use DST)
22:54:40  wob_jonas: It's a big hassle because the difference in time zones between countries isn't constant.
22:55:02  Which means that you can't schedule something to happen at a given time in one time zone and have it happen at the same time in another.
22:55:54  well yes
22:56:43  (and you also can't do that when a region randomly decides to change the timezone from now on, which also happens sometimes, often because of political changes)
23:00:33  or tourism, near the date line
23:01:58  int-e: tourism near the date line already haves the problem that the timezones are different
23:02:57  what problem, it's by design; people get to do things like celebrate New Year's Eve twice.
23:04:05  maybe
23:04:18 <\oren\> Then it would be neat to pass a bylaw that in my district, the time zone is officially Italy Time
23:04:56 <\oren\> and therefore you would be able to drink after legal close time
23:05:19  \oren\: I was thinking of passing a law that makes the timezone something like six hundred years before UTC for a medieval theme park
23:05:41  "drink after legal close time" there are other workarounds for that, but ok
23:06:19  that would really mess with AoE deadlines.
23:06:44  in most places we don't have rules that limit when you can drink, but rather possibly rules that limit when shops can sell alcoholic drinks
23:06:47  (the medieval variant)
23:06:53  so the timezone at the store matters
23:07:04  int-e: what's an "AoE"?
23:07:06 <\oren\> int-e: age of empires?
23:07:29  @googe aoe time zone
23:07:31  https://www.timeanddate.com/time/zones/aoe
23:08:32  hmm, that reminds me, could you get around a legal statute of limitations by getting a region to use a timezone decades into the past, or around a copyright limitation by getting a region to use a timezone a decades into the future?
23:09:59  or various exploits related to how old a person is, like opening a bar in a timezone that's a decade into the future so that younger people can drink because they're suddenly over the legal drinking age?
23:10:10  just be your own sovereign country outside of the Geneva copyright convention...
23:10:16  no need to mess with time zones
23:10:53 <\oren\> int-e: yeah but often individual cities can mess with time zones so it's easier
23:11:12  int-e: there are practically no such countries
23:11:30  \oren\: can they? I don't think states usually allow that to indidvidual cities
23:13:26  the easiest might be to get some small pacific island nation that is already in a not too common timezone to switch to such a crazy timezone, but that doesn't help you with bars or shops where the point is not to travel far, or legal exploits that are tied to an existing country
23:21:39  wob_jonas: I think the solution to the original question about statute of limitation is that how you measure absolute times doesn't affect relative times like age (time since birth etc.)
23:22:16  int-e: yeah, but does any law actually do that? especially laws about drinking age?
23:22:27  if you have a local calendar (and that's essentially what you get if you pick a cracy time zone offset), you'll have to convert external dates to local ones or vice versa before doing the comparison.
23:22:45  wob_jonas: I expect the laws to talk about age, not dates of birth.
23:23:09  int-e: Don't people wait until midnight to drink or something?
23:23:38  yeah, but they check age by checking the date of birth in your id documents and compare it with the current date. this actually matters because many people go to a bar to drink on their birthday when they reach legal age.
23:23:39  Wait, you're not talking about drinking age.
23:24:22  yes, drinking age, and similar age restrictions, like when you can buy alcohol and tobacco and lottery tickets and go into casinos
23:25:28  The exploit doesn't easily work for driving though, at least in Europe, because the rules say even if you have a valid drivers' license from another country, the age restriction of the local country for the relevant category of vehicles limits you,
23:25:43  sozzlin' age
23:25:52  so you could only drive in the territory with strange timezone, which is useless.
23:26:00  wob_jonas: well, but the reason that this is the case is that nobody gives a damn about a few hours difference. in this matter.
23:26:09  But putting a bar or shop into a strange timezone is more practical.
23:26:22  Putting a casino is even better.
23:26:36  I think it simply won't work.
23:26:49  int-e: a few hours, probably no, sure. but if there's at least months of difference, that might matter
23:26:55 -!- Sgeo has joined.
23:27:01  And if it does work, it won't be due to the timezone trickery.
23:27:38  Rather it'll be because your local law enforcement doesn't care about the legal drinking age.
23:27:53  sure, for drinking and tobacco, there are already lots of workarounds like that
23:27:58 -!- boily has joined.
23:28:47  wob_jonas: Maybe I can withdraw money from my retirement accounts if you arrange for a time zone a few decades ahead.
23:29:03  I don't understand why the US laws with regard to those are so complicated.
23:29:30  shachaf: yeah, that might work too
23:30:31  Maybe I could avoid repaying loans and paying some bills by moving into a timezone where they're not due yet.
23:31:12  wob_jonas: Oh, maybe you can write a clever financial contract based on the current date.
23:31:19  That's a much more interesting use.
23:31:33  Today I was reading Matt Levine, https://www.bloomberg.com/view/articles/2013-12-05/blackstone-made-money-on-credit-default-swaps-with-this-one-weird-trick
23:33:01 -!- Sgeo_ has joined.
23:33:36  A lawyer died suddenly in his sleep and was very upset when he entered the Pearly Gates. "I am too young to die, that way," he protested. "Not at all, you are 87 years old." "There must be a mistake, I am only 35 years old." "Well, we checked the number of hours you have billed to your clients, you must be 87 years old.”
23:33:59  (I think this is similar territory as the time zone trick)
23:34:06  int-e: hehe
23:34:12 -!- Sgeo has quit (Ping timeout: 240 seconds).
23:34:17  What's the problem with billing multiple people for the same hour?
23:36:33  Apparently there isn't one until you die unexpectedly of old age.
23:37:32  shachaf: isn't that fine only if they share the bill, eg. two people pay half and half of it because the lawyer did a job that benefits both of them?
23:37:44  Why?
23:38:26  You mean, billing someone for an hour indicates that you spent the full hour only in service of them, unless you specify otherwise?
23:39:19 -!- Phantom_Hoover has quit (Read error: Connection reset by peer).
23:39:30  the problem is billing a whole hour for a fraction of it
23:39:31  yes
23:39:49  6 10-minute phone calls with 6 clients, each pay for one hour = jackpot
23:40:20  disclaimer: I don't actually know if lawyers do that
23:41:14  alercah: hmm, something like that might work, although it is probably hard to do it in a way that is actually profitable (i.e. you don't pay for it with lots of downtime when you can't bill anyone)
23:43:58  one thing that might work better in practice is being applied as a high-ranking professor in a university or even two and at the same time working in a research institute that isn't part of the university. It's hard to get more than 24 hours a day that way, but a nominal 16 hours a way is definitely possible, and 20 might perhaps be possible.
23:44:42  why would it be hard to do in a profitable way?
23:44:44  I know a professor who works in two universities and one research institute, but it's hard to tell which one of those jobs is half time and which is full time.
23:44:53  2 hours pays for more than a day
23:45:43  alercah: dunno. maybe it isn't, I'm not a lawyer and don't know much about how lawyers work. I have a difficulty switching between projects when I have more than two simultanous projects in my job, and even switching between two rapidly.
23:46:02  Other people have trouble too swapping that way, although the amount of trouble differs a lot.
23:46:38  (two projects and switching only a few times a week is somewhat managable for me usually.)
23:46:54  (depends on the actual tasks of course)
23:49:17 -!- hppavilion[1] has joined.
23:49:24  I think such double work is possible for doctors two, when they work for a public hospital and private institute or private patients at the same times, sometimes even in a questionably legal way (when they handle private patients in the public hospital, within the public hospital job's work hours or using some cheaper resources of the hospital).
23:50:11  anyway, good night now
23:50:17 -!- wob_jonas has quit (Quit: http://www.kiwiirc.com/ - A hand crafted IRC client).
23:50:50  alercah: Lawyers usually bill in 6 minute increments, I believe.
23:53:21  idk

2017-08-31:

00:02:56 -!- nchambers has quit (Changing host).
00:02:56 -!- nchambers has joined.
00:03:08 -!- nchambers has quit (Changing host).
00:03:08 -!- nchambers has joined.
00:12:51  helloily
00:14:54  QUINTHELLOPIA!
00:16:32 -!- Sgeo__ has joined.
00:19:59 -!- Sgeo_ has quit (Ping timeout: 248 seconds).
00:22:36  do you ever wish you had more time?
00:24:21  and where were you during the blizzard of 2007?
00:27:53  more or less, about yes.
00:27:59  there was a blizzard in 2007?
00:29:50  as I remember it, there was quite a lot of snow in 2008, something around 18’.
00:30:58  okay that one then
00:31:08  the one with the huge blackout
00:33:33  2008 the winter that never endedt
00:34:55 -!- rdococ has joined.
00:35:24  were there mounds and heaps and piles of snow on your end?
00:36:02  nope. it might have iced over one night
00:36:15  but this is not the frozen north
00:36:25  how did it affect you?
00:36:29 -!- rdococ has left ("Leaving").
00:37:16  eh... probably a little bit more shoveling? I was still living with my parents at that time, and I was on shovel duty.
00:37:59  I like it when it gets “Real Winter”. -25 °C is perfect; your moustache freezes over.
00:44:17 -!- jaboja has quit (Ping timeout: 246 seconds).
00:44:38  although right now is just perfect right ~^^~
00:44:42  @metar CYUL
00:44:42  CYUL 302300Z 23009KT 15SM FEW150 22/13 A2987 RMK AC1 AC TR SLP116 DENSITY ALT 1000FT
00:44:49  @mtear KOAK
00:44:49  KOAK 302253Z 28011KT 10SM CLR 20/13 A2988 RMK AO2 SLP116 T02000133
00:49:23  it's colder in KOAK???
00:53:14  It was an odd day weather-wise in London today. Yesterday highs were +28 °C, today +14 °C.
00:53:26  @metar EGLL
00:53:26  EGLL 302320Z AUTO 26004KT 9999 NCD 13/10 Q1015
00:54:53  when is the last time you played a video game forrilz boily
00:55:11  with you.
01:00:51 -!- rdococ has joined.
01:01:06 -!- rdococ has left ("Leaving").
01:05:07  `5 w
01:05:13  1/1:@//@ is an OS made out of only the finest vapour. \ emoticon//emoticon: ¯\(°​_o)/¯ \ grace period//The grace period was invented by Taneb to give him more time to invent the Oxford comma. \ nooga//no. \ os//Os is the accusative plural of us. Alsø a village in Denmark. Ånd a Norwegian spirit.
01:08:29 -!- jaboja has joined.
01:28:54  yeah i dont get much time for gaming these days either
01:45:33 * quintopia sets out some spinach artichoke dip for the channel
01:48:07 * boily brings artisanal tortilla chips
02:01:48 -!- imode has quit (Ping timeout: 252 seconds).
02:03:26  what are your thoughts on naked yoga?
02:06:32  there is such a thing?
02:06:58  well, of course it is such a thing. All the Things Are. Praise be unto their Inventor.
02:07:29  I... don't know? is it like, regular yoga with all the yoga positions you can expect, but you're naked?
02:43:59 -!- imode has joined.
02:47:26 -!- boily has quit (Quit: ACCEPTABLE CHICKEN).
03:01:41 -!- ATMunn has quit (Quit: See ya! o/).
03:16:21 -!- jaboja has quit (Ping timeout: 240 seconds).
04:08:01 -!- jaboja has joined.
04:15:45 -!- sleffy has quit (Ping timeout: 248 seconds).
04:21:12 -!- Sgeo__ has quit (Ping timeout: 240 seconds).
04:22:40 -!- Sgeo has joined.
04:35:26 -!- Sgeo_ has joined.
04:37:42 -!- Sgeo has quit (Ping timeout: 240 seconds).
04:48:51 -!- jaboja has quit (Remote host closed the connection).
05:49:12 -!- Sgeo_ has quit (Ping timeout: 240 seconds).
06:00:34  `coins
06:00:42  ​grcecoin evencoin beltocoin illarlecoin quarecoin stecoin gtvecoin glycoin serthesnecoin sheddycoin trofesostecoin tnntleuercoin kolmcoin colabiculecoin interbcoin lifyingcoin placoin hebagcoin herishcoin larcoin
06:04:58  Someone should extend HackEgo to make an ICO website.
06:05:18  Then suckers will send it money for no reason.
06:09:54 -!- Sgeo has joined.
06:59:46 -!- FreeFull has quit.
07:12:53 -!- imode has quit (Quit: WeeChat 1.9).
07:17:54 -!- augur has quit (Remote host closed the connection).
07:28:34 -!- sleffy has joined.
07:43:27 -!- mroman has joined.
07:43:34  moin
07:56:46  moin
08:00:17 -!- augur has joined.
08:05:05 -!- augur has quit (Ping timeout: 248 seconds).
08:20:10 -!- augur has joined.
08:36:22 -!- sleffy has quit (Ping timeout: 260 seconds).
08:41:47 -!- AnotherTest has joined.
08:52:17 -!- augur has quit (Remote host closed the connection).
09:01:00 -!- kurolox has joined.
09:10:39 -!- augur has joined.
09:15:27 -!- hppavilion[1] has quit (Ping timeout: 260 seconds).
09:23:06 -!- augur has quit (Remote host closed the connection).
09:30:56 -!- atslash has quit (Remote host closed the connection).
09:31:50 -!- atslash has joined.
09:45:17 -!- atslash has quit (Ping timeout: 255 seconds).
09:46:08 -!- atslash has joined.
09:55:27  Does Skype on win32 deliberately obfuscate its interface by hiding the "Quit Skype" command from the main menu, and by making the window close button silently keep skype running and visible only in the notification area? I think it does, they can't just be that stupid by accident.
09:59:12 -!- Sgeo has quit (Ping timeout: 240 seconds).
10:02:25  Hmm. Next time I write a makefile (or similar) for deploying/installing a program on another server through ssh, I should explicitly specify the remote username in it, rather than rely on the defaults in my ssh config. This hasn't caused problems yet, but it's probably better to be cautious.
10:03:38  s/ssh/ssh and\/or rsync/
10:25:06 -!- Sgeo has joined.
10:38:31 -!- Sgeo_ has joined.
10:40:20 -!- Sgeo has quit (Ping timeout: 246 seconds).
10:42:09 -!- mroman has quit (Ping timeout: 260 seconds).
11:23:41 -!- augur has joined.
11:28:15 -!- augur has quit (Ping timeout: 248 seconds).
11:36:38 -!- boily has joined.
11:40:03 -!- augur has joined.
11:44:12 -!- augur has quit (Ping timeout: 240 seconds).
12:20:22 -!- boily has quit (Quit: VOYAGE CHICKEN).
12:42:02 -!- ais523 has joined.
12:53:44  Great. I'm trying to override line break opportunities in a word document where word's automatic algorithm chooses them wrong. But calibri doesn't have the 0x2011 or 0x2060 characters in it (even though the first one should look identical to a hyphen and the second should display nothing and have no width) so all I can use is 0xFEFF. 
12:55:02  Can't they actually put characters into a fucking modern high-quality font when they're also easy to draw and implement?
12:56:02  Although maybe these fonts are too old for those characters or something.
12:57:51  Calibri's design began in 2002 and U+2011 dates from Unicode 1.1, i.e. the year 1993
12:58:04 -!- ais523 has quit (Remote host closed the connection).
12:59:14 -!- ais523 has joined.
12:59:26  Deewiant: hmm. how about 0x2060?
12:59:46 -!- grumble has quit (Quit: told).
12:59:48 -!- rumble has joined.
12:59:53 -!- rumble has changed nick to grumble.
13:01:14  b_jonas: isn't there a soft hyphen in latin-1 somewhere?
13:01:19  `unicode SOFT HYPHEN
13:01:21  ​­
13:01:30  hmm, that doesn't look like a soft hyphen to me
13:01:34  b_jonas: Apparently Unicode 3.2, which came out in 2002, so it might not have been around when Calibri was started but it was definitely there before it was finished.
13:01:38  U+00AD  Cf  .  SOFT HYPHEN
13:01:41  `unidecode  ​­
13:01:42  ​[U+0020 SPACE] [U+200B ZERO WIDTH SPACE] [U+00AD SOFT HYPHEN]
13:01:50  That should be latin-1, I think
13:01:56  oh, huh, it is a soft hyphen, as I discovered trying and failing to select it
13:01:59  Deewiant: ok
13:02:05  and yes, U+0000 to U+00FF is Latin-1
13:02:21  b_jonas: is there a reason you can't use U+00AD?
13:03:05  ais523: that has the wrong semantics. U+00AD is normaly invisible, and becomes a hyphen before a line break when you break the line there. that's for providing a hyphenation opportunity inside a word
13:03:08  (U+00AD is equally old as U+2011)
13:03:21  b_jonas: oh, I thought that's what you were trying to do
13:03:26  what are you trying to do instead?
13:03:44  (also, I'm massively confused as to why that soft hyphen is visible in my client, semantically it shouldn't be)
13:03:49  ais523: I need a hyphen that's always present but where I don't want to allow a line break after it
13:04:01  oh, I see
13:04:01  hm
13:04:14  given that this is a Word document, I believe there's some sort of "don't break here" formatting you can apply
13:04:18  can you sue a ZWNBSP for that?
13:04:20  use*
13:04:20  ais523: the soft hyphen can be visible in terminals or other programs that don't use a proper text-rendering engine
13:04:28  b_jonas: this is a GUI client though
13:04:35  also it seems to be treating the soft hyphen as zero pixels wide
13:04:38  it's just that I can see it
13:04:52  ais523: GUI might not necessarily mean it's written properly
13:05:01  abc­def
13:05:13  aha, the soft hyphen is only visible if there are no characters after it
13:05:41  that's an interesting choice but a defensible one, I think
13:05:41  ais523: the font might have a glyph for it that the text engine should render only when the hyphen is visible (when there's a line-break there, or when you show invisible characters explicitly for proof-reading a text)
13:05:53  ais523: ah
13:06:12  well that makes sense, the end of a text is always a line-break utility (though in some contexts it might not be treated as such)
13:06:54  um
13:07:07  s/utility/opportunity/
13:21:08  SHY LF is a pretty silly combination as it is
13:21:13  what does that even mean?
13:25:03  ais523: it might be silly, but you can't really "ban" a character combination for general text. you just have to treat it in some fallback way
13:25:26  b_jonas: right
13:25:37  you might get such a combination when you try to abbreviate some text for a shorter field or something
13:25:38  ideally Unicode would be normalized, with all combinations being meaningful
13:25:45  but as it isn't, you need some semantics for meaningless sequences like that
13:26:03  well, most programs do sort of handle all combinations in some way
13:47:55 -!- erkin has joined.
14:04:14 -!- tswett has quit (Quit: Leaving).
14:10:13 -!- kurolox has quit (Remote host closed the connection).
14:17:07 -!- zseri has joined.
14:24:19 -!- augur has joined.
14:28:21 -!- augur has quit (Ping timeout: 240 seconds).
14:34:58 -!- `^_^v has joined.
14:38:01 -!- ATMunn has joined.
15:30:10 -!- ais523 has quit.
16:16:35 -!- Sgeo_ has quit (Ping timeout: 240 seconds).
16:42:09 -!- augur has joined.
16:59:13 -!- mroman has joined.
16:59:23 -!- imode has joined.
16:59:35  waddup
17:34:34 -!- AnotherTest has quit (Ping timeout: 264 seconds).
17:38:15  nothing
17:59:39 -!- wob_jonas has joined.
17:59:50  argh! why is the call failing
17:59:54  all the undocumented stuff
18:00:01  there's probably a good reason, but I don't know why
18:05:54  facepalm
18:05:58  damn you, gnu!
18:05:59 -!- augur has quit (Remote host closed the connection).
18:07:09  for a command that by default takes any number of arguments that it will exec, you shouldn't use gnu's stupid getopt that will reorder the command line. you need a getopt that only parses options before the first argument.
18:16:10 -!- ATMunn has changed nick to nnuMTA.
18:19:48  damn
18:21:27 -!- Phantom_Hoover has joined.
18:22:44  so I was trying to write a simple command that I run under my X session and changes to another virtual terminal. but it seems that this is not possible directly, because you only have permission for that ioctl if a real tty console is your controlling terminal, and it seems when icewm-session starts icewm, it calls setsid and so any process I start
18:22:45   from icewm can't have the original tty as the control terminal.
18:22:58 -!- sleffy has joined.
18:23:26  but X11 itself can change to a virtual console if I press a key. is there some X11 call I can do from an X11 program to ask X11 to do that?
18:23:35  I don't know anything about X11 programming
18:27:26 -!- augur has joined.
18:29:30  jm
18:29:34 -!- atslash has quit (Read error: Connection reset by peer).
18:29:55 -!- atslash has joined.
18:35:11 -!- atslash has quit (Ping timeout: 240 seconds).
18:36:07 -!- atslash has joined.
18:36:51 -!- augur has quit (Remote host closed the connection).
18:40:13 -!- FreeFull has joined.
18:44:21 -!- ais523 has joined.
18:48:30 -!- augur has joined.
18:49:40 -!- imode has quit (Ping timeout: 246 seconds).
18:52:35 -!- augur has quit (Ping timeout: 240 seconds).
18:52:45  I'll probably just use a workaround by starting a program on another virtual console withou X that will do this when I ask
19:06:06 -!- AnotherTest has joined.
19:07:01 -!- jaboja has joined.
19:16:41  ok, workaround done as two very simple shell scripts
19:17:58  I did the workaround
19:20:11 -!- AnotherTest has quit (Ping timeout: 240 seconds).
19:32:22 -!- AnotherTest has joined.
19:40:13 -!- jaboja has quit (Read error: Connection reset by peer).
19:40:21 -!- ais523 has quit (Remote host closed the connection).
19:40:30 -!- jaboja has joined.
19:40:31 -!- ais523 has joined.
19:42:52  @bot
19:42:53  :)
19:52:31 -!- AnotherTest has quit (Read error: Connection reset by peer).
20:11:05 -!- erkin has quit (Read error: Connection reset by peer).
20:19:04 -!- mroman has quit (Ping timeout: 260 seconds).
20:21:05 -!- erkin has joined.
20:30:28 -!- nnuMTA has changed nick to ATMunn.
20:38:39 -!- atslash has quit (Ping timeout: 248 seconds).
20:39:06 -!- atslash has joined.
21:07:54 -!- augur has joined.
21:12:05 -!- augur has quit (Ping timeout: 240 seconds).
21:20:29 -!- augur has joined.
21:34:32 -!- sleffy has quit (Ping timeout: 260 seconds).
21:54:36 -!- zseri has quit (Quit: Page closed).
21:56:56 -!- sleffy has joined.
22:10:57 -!- atslash has quit (Quit: This computer has gone to sleep).
22:11:12 -!- atslash has joined.
22:11:47 -!- atslash has quit (Client Quit).
22:20:31 -!- sleffy has quit (Ping timeout: 248 seconds).
22:24:09 -!- ^arcade_droid has changed nick to aarcade_droid.
22:30:39  [wiki] [[Special:Log/newusers]] create  * JanMakuwe *  New user account
22:31:02 -!- augur_ has joined.
22:33:10 -!- aarcade_droid has changed nick to ^arcade_droid.
22:33:41 -!- augur has quit (Ping timeout: 240 seconds).
22:42:13  [wiki] [[Esolang:Introduce yourself]]  https://esolangs.org/w/index.php?diff=52978&oldid=52975 * JanMakuwe * (+226) /* Introductions */
22:43:00  [wiki] [[Esolang:Introduce yourself]]  https://esolangs.org/w/index.php?diff=52979&oldid=52978 * JanMakuwe * (-9) /* Introductions */
22:46:04 -!- oerjan has joined.
22:48:16  `? font
22:48:18  ​#esoteric bitmap fonts include: \oren\'s font http://www.orenwatson.be/fontdemo.htm , lifthrasiir's font https://github.com/lifthrasiir/unison/ https://lifthrasiir.github.io/unison/sample.png , b_jonas's font http://www.math.bme.hu/~ambrus/pu/fecupboard20-c.pcf.gz
22:48:54 <\oren\> Apparenlty they fixed the new youtube to make it actually fill the whole screen with content
22:50:10  Hm, I should make my fonts available as bitmap font files
22:51:18 <\oren\> I have BDF and ttf, but not PCF...
22:51:46  well
22:52:00  http://xen.firefly.nu/up/fonts/ actually converts the fonts to BDF, I forgot about that
22:54:51  http://xen.firefly.nu/up/2017-08-31_231007.png  hmm.
22:58:49 -!- oerjan has set topic: Welcome to the international shrub for esoteric programming language design and deployment! | http://esolangs.org | logs: http://codu.org/logs/_esoteric/ http://tunes.org/~nef/logs/esoteric/?C=M;O=D | https://www.dropbox.com/s/fyhqyvy3i8oh25m/wisdom.pdf.
22:59:12 -!- `^_^v has quit (Quit: This computer has gone to sleep).
23:13:46 -!- MrBismuth has joined.
23:16:35 -!- MrBusiness has quit (Ping timeout: 240 seconds).
23:25:23 -!- wob_jonas has quit (Quit: http://www.kiwiirc.com/ - A hand crafted IRC client).
23:32:03 -!- Sgeo has joined.
23:35:53 -!- Sgeo_ has joined.
23:38:05 -!- Sgeo has quit (Ping timeout: 240 seconds).
23:42:16 <\oren\> what you do is, you have a huge underground lake that you heat by repeatedly detonation hydrogen bombs, then get steam power from that heat
23:42:50  sounds like it works
23:43:57 -!- Phantom_Hoover has quit (Read error: Connection reset by peer).
23:45:00  . o O ( is this KSP )
23:51:14 <\oren\> oerjan: no, just a funny idea i had for doing fusion power with current tech
23:51:33 <\oren\> hydrogen bombs are technically fusion power
23:51:50 <\oren\> you just need a way to extract energy from them
23:56:48 <\oren\> hmm, I think the explosion of hydrogen bomb would produce pressure wave that would not be absobed by water
23:56:53 <\oren\> like, perhaps a large plenum filled with methane or ammonia gas would work