🦋 Welcome to the MAIN() IRC channel of the Raku Programming Language (raku.org). Log available at irclogs.raku.org/raku/live.html . If you're a beginner, you can also check out the #raku-beginner channel!
Set by lizmat on 6 September 2022.
00:05 mtj joined 00:15 sena_kun left
tbrowder__ .tell _grenzo yes, i'm interested in yr mod to gen tests from a module distrio 00:42
tellable6 tbrowder__, I'll pass your message to _grenzo
tbrowder__ it could be very useful for sure 00:43
00:48 jpn joined 00:53 jpn left
Xliff Generate tests from a distro? Huh! How would that work? 00:58
01:20 jpn joined 01:25 jpn left
antononcube @Xliff Hmm... not that difficult to do. Just give your distro code to the LLM and ask write tests for it. 01:43
Of course, the obtained tests would be just (somewhat) good first iterations. At least with current LLMs. 01:44
I am generally more interested in the other direction -- generating "distro" documentation from tests. 01:45
01:45 Manifest0 left
@lizmat I am mostly trying to say that LLMs can be used to generate code. I have seen a few examples of Raku functionalities written with NQP. I am saying it would be cool if the via LLMs they can be rewritten into "standard" Raku and/or RakuAST. 01:47
BTW, I do not think or feel strongly about any LLM application ideas. I am still trying out different workflows with them in order to see their limits. 01:48
01:49 jpn joined
Current, "large scale" idea with LLMs I investigate is to automatically generate an LLM prompt for any package from the ecosystem. I will first start with well documented packages, after some tests will decided how to proceed. 01:54
01:54 jpn left
I think at some point we should a introduce the soft rule that anyone who submits a package to the ecosystem should provide an LLM prompt that helps its utilization. 01:55
tbrowder__ when i said "distro" i was using @ugexe's termininolgy. i meant it would be very useful for me as a "distro" author during development, not from something published. 01:58
guifa I would say the main point of RakuAST isn't so much improving code generation. It may be a side effect, but a lot of it came via the desire to implement macros and do some other stuff that requires actually manipulating the codegen 02:00
antononcube @guifa Macros make LLM even more applicable. 02:01
@tbrowder Yeah, I do not use "distro", I prefer the generic term "package". Although, I am aware that in Raku, "distro", "package", and "module" have more specialized meaning. 02:02
02:19 hulk joined 02:20 kylese left 02:22 jpn joined 02:26 jpn left
_grenzo @tbrowder I started writing the module a while ago but ran into needing to parse the files to get the list of subs, classes, methods, and multi method signatures to generate the tests for. The correct answer seemed to be have Raku parse them. But I haven't figured that out yet. So it's stalled. I would welcome pointers to documentation or examples. 02:36
tellable6 2024-01-22T00:42:50Z #raku <tbrowder__> _grenzo yes, i'm interested in yr mod to gen tests from a module distrio
antononcube @grenzo Yes, see, "UML::Translators" -- shameless plug! 02:39
Basically, in order to generate UML diagrams, I have traverse class hieararchies, roles, subs, etc.
_grenzo I'll take a look 02:40
antononcube See also the comments here: stackoverflow.com/q/68622047 02:41
02:51 jpn joined 02:55 jpn left 03:15 hulk left, kylese joined 03:45 jpn joined 03:49 jpn left 03:51 jpn joined 03:56 jpn left 04:52 jpn joined 04:57 jpn left 05:36 jpn joined 05:41 jpn left 06:32 jpn joined 06:37 jpn left 07:05 Util left 07:07 Util joined 07:18 renormalist left 07:23 jpn joined 07:44 sena_kun joined 08:07 jpn left 08:25 abraxxa joined 08:29 abraxxa left 08:30 abraxxa joined 08:52 Manifest0 joined 08:59 dakkar joined 09:01 jpn joined 09:07 Sgeo left 09:27 abraxxa-home joined 09:48 abraxxa-home left 10:16 jpn left 10:25 jpn joined
lizmat And yet another Rakudo Weekly News hits the Net: rakudoweekly.blog/2024/01/22/2024-04-marrow/ 12:40
ab5tract antononbcube: TIL about UML::Translators. Very cool, I wanted that recently and just assumed we didn't have anything like that in the Raku ecosystem. Glad to be proven wrong! 12:41
lizmat antononcube ^^ 12:49
ab5tract Marrow looks interesting. I don't have any Postgresql processes to try it on at the moment though. 12:50
lizmat I wonder what it would take to get SQLite support
ab5tract that would be cool to see 12:54
antononcube: I pinged you on Discord, in case you are still up for that LLM boot camp 12:58
[Coke] regading the weekly, is there a way to get more context on the tweets without having an account on the site? direct links work, but clicking to get to the context requires a logn 13:18
my usual response is to ignore them, but occasionally I try to click through. 13:19
lizmat I'd be happy to be told of a way :-)
ab5tract I think the third party options are very limited nowadays due to the quotas 13:35
13:39 jpn left
antononcube @ab5tract Did you search the Zef ecosystem for the kind of introspection “UML::Translators” provides? With what tags? 13:40
And, yes — thank you for your interest in it! 13:41
ab5tract I didn't search, no. I was also looking to learn Mermaid in "manual" mode, so I skipped past checking what existed 13:43
But I did take a minute to imagine how useful a Raku <-> UML translator would be and figured I would probably have to implement one if I wanted to see it. 13:44
So, yeah, again, glad to be proven wrong! 13:45
Think we can teach it NQP?
antononcube Yeah, the generation of Raku code from UML and/or Mermaid would be really nice.
ab5tract Oh, I must have misread. I thought that it was currently bi-directional. 13:46
antononcube I am not sure about teaching NQP — I think someone needs to know introspection of NQP code well.
ab5tract Makes sense
antononcube Agh, no — just introspection, Raku -> UML. I do say that UML -> Raku is in my TODO list or be nice to have, 13:47
13:48 jpn joined
In some sense that translation can/should be done to good degree with LLMs. 13:48
ab5tract True 13:49
antononcube The thing is that introspection-wise, Raku -> UML, usually has to translate a code base that exceed s the token limit of most LLM models. (Currently.) The translation of UML -> Raku would typically require much smaller count of input and output tokens. (Hence, would bring results most of the time.) 13:52
13:53 jpn left
The question, of course, is how well LLMs know Raku. Most recent ones, trained, say, up to Sep 2023, seem to have relatively good Raku knowledge. 13:54
ab5tract But then we get back to the question of training a customized LLM that knows Raku specifically 13:56
At least, in my mind.
antononcube Right. OpenAI claims one can make personalized, specially trained GPTs. I plan to work with those this week. 13:58
ab5tract Ok things could really get interesting then
antononcube The way I see it — if large enough token inputs allowed by the models, a fairly large code base can uploaded / trained with. 13:59
ab5tract so one day we will be able to feed all of roast, but I get the sense that's some time off at this point 14:00
antononcube So, the current “largest” LLM model I am aware of takes 128K input tokens (≈256K characters), and gives results up to 8K tokens. 14:02
This is the main limitation for “feeding” that LLM model with code. 14:03
ab5tract Is there a way to curate this input set for maximal understanding?
By which I mean, are there guidelines, processes, etc already well-defined?
antononcube Correction : 4K output tokens, not 8K. 14:04
ab5tract It's kind of a cool project: 128K tokens to work with.
Raku is also pretty golfable... we can get more mileage out of 128K tokens. 14:05
antononcube Yes, that is the claim — some of the models say they “supervised.” But this does not mean the supervision is accessible to end users.
ab5tract but then you are creating more of a Raku golf generator than a "regular" Raku generator
antononcube I do not like games in which a ball is hit with a stick. Hence, the Raku golf analogies and characterizations are lost on me. 14:06
ab5tract Still might be a lot of fun.
antononcube: code golfing is a sub-genre of programming where the goal is to express an algorithm in as few characters as possible 14:07
there are now dedicated languages for this, but for a long time Perl was king. 14:08
antononcube Hm… interesting. LLMs are usually way to prolific in their responses.
ab5tract Raku gains and loses in this compressability versus Perl, though it remains powerful 14:09
antononcube Currently I do not expect great results from LLMs. Good and good enough, sure, sort of…
14:10 jpn joined
So, would not expected great terse code to be produced. 14:10
ab5tract But could it still learn from the terse code? 14:11
There's an equation in here, I can feel it. Something involving the "area gained by terseness" in relation to "depth gained by verbosity" 14:14
14:15 jpn left
antononcube Sure, to a point. For example, using few shot training, i.e. with examples. 14:15
Another way is using “assistants.” 14:21
14:21 jpn joined
japhb ab5tract: Sounds related to the waterbed theory of complexity ... 14:42
ab5tract That makes sense 14:51
antononcube @japhb Sounds like featherbedding by USA company. 14:54
16:16 jpn left 16:18 jpn joined 16:37 jpn left
ingy andinus: thanks, I guess linux/arm binaries are not a thing yet. probably not a big demand 16:46
yamlscript releases are similar: github.com/yaml/yamlscript/releases/tag/0.1.35 16:48
just don't have windows working quite yet
16:50 jpn joined 16:57 abraxxa left 17:31 wlhn left 17:59 dakkar left 18:26 slicer joined 18:28 abraxxa-home joined 19:10 slicer left 19:20 slicer joined 19:26 slicer left 19:31 slicer joined 19:46 jpn left 20:04 slicer left 20:10 jpn joined 20:18 TieUpYourCamel left 20:24 jpn left 20:26 slicer joined 20:30 slicer82 joined 20:31 slicer left, TieUpYourCamel joined 20:37 slicer82 left
tonyo tbrowder__: github.com/tony-o/raku-fez/blob/ma...kumod#L663 <- this grabs the commands and tries to match anything in github.com/tony-o/raku-fez/tree/ma...rces/usage and prints that help out - you could also automate that part 20:48
rather than using flat usage files 20:49
i didn't in fez because i wanted to show both the short flag and long flag in one usage
20:54 jpn joined
_grenzo @lizmat Started looking at that over the weekend (to make writing tests for Marrow easier. SqlLite does not appear to support the INFORMATION_SCHEMA standard. Which means writing SqlLite specific code to interrogate the database. Postgresql, Mysql and others have implemented it so I started there. 21:01
21:02 jpn left 21:04 jpn joined
(apologies to SQLite for the misspelling) 21:07
tbrowder__ tonyo: thnx 21:55
22:03 jpn left 22:04 jpn joined 22:43 abraxxa-home left 23:34 sena_kun left 23:39 Sgeo joined 23:59 jpn left