Voldenet Funny that people complain about the image on the blog which is there only for decoration 00:10
I agree with general sentiment that llms are stochastic parrots, but I disagree about `no never use them` sentiment 00:13
it's a bit like with code templates or generators, use too much and your technology becomes too obscure too maintain 00:16
use not enough and you're writing assembly code
by hand
disbot <antononcube> 🤔 01:08
01:36 erooke left 01:50 erooke joined 01:58 hulk joined 01:59 kylese left 02:15 hulk left, kylese joined 03:23 acidsys left 03:24 acidsys joined 03:51 erooke left 04:07 erooke joined 04:17 ShimmerFairy left 04:19 ShimmerFairy joined 05:28 Sgeo left 06:07 erooke left 06:12 xinming left 06:13 xinming joined 06:22 erooke joined 08:00 rnddim joined 08:01 rnddim left, rnddim joined 08:02 ShimmerFairy left 08:03 rnddim left, rnddim joined 08:06 dakkar joined 08:09 rnddim left 08:10 rnddim joined 08:12 dakkar left 08:28 dakkar joined
disbot <antononcube> This is an interesting analogy. Maybe it should be developed in more detail. 08:30
<antononcube> BTW, I am using templates with some of my LLM solutions. They provide faster and (far) more robust code generation. 08:31
08:31 rnddim is now known as ShimmerFairy
lizmat weekly: github.com/rakudo/rakudo/pull/6847 09:09
notable6__ lizmat, Noted! (weekly)
10:15 dakkar left 10:30 dakkar joined
lizmat easier reading: github.com/rakudo/rakudo/blob/6828...-POLICY.md 10:41
tbrowder lizmat: any concern for ai assisted module submissions? should it be mentioned? 11:24
lizmat I think we can only enforce such a thing with the raku community modules 11:25
module authors are responsible for their modules 11:26
tbrowder ok
lizmat of course, if a module is marked as LLM or non-LLM, could be grounds for users later on deciding whether or not to use such a modules
disbot <antononcube> LLM / AI-agent assistance can be mentioned or described in the README. I also put a file "prompts.md" in the "./docs" folder in order to show (or trace) for which parts of the package LLMs were used. 12:43
<antononcube> My main goal with these kind of "prompts.md" files is to make the development more clear and reproducible. 12:45
<antononcube> But, obviously, they indicate are LLMs used or not. 12:46
<antononcube> Also, one can ask LLMs or AI-agents to analyze a package repository and determine to what degree that package was made via LLMs or AI-agents. 12:47
lizmat In Dutch we would say: We of WC-eend approve of WC-eend 12:50
disbot <antononcube> I am not sure what do you mean. LLMs are very willing to rat on each other. (So far.) 12:52
lizmat WC-eend is a type of toilet cleaning fluid... and one of their (tongue in cheek commercials that every Dutch person of a certain age knows) they showed some guys in white lab coats with the WC-eend insignia, that they approved of WC-eend 13:07
13:27 dakkar left 13:32 vasko453558616 left 13:33 vasko453558616 joined 13:43 dakkar joined 14:05 dakkar left 14:21 dakkar joined 14:51 fondue left, scott2 joined
tbrowder antononcube: can you name one of yr modules with the AI comments? 15:31
disbot <antononcube> "Math::NIntegrate" is package I actively work one: github.com/antononcube/Raku-Math-NIntegrate/ . In its folder "./docs" see the files "Development-methodology.md" and "prompts.md". 15:50
tbrowder thnx
disbot <antononcube> TBH, LLMs were not as good with reprogramming Fortran code as I expected. I had to read the Fortran codes to verify the translation. 🙂 15:58
<antononcube> But the LLM / AI-agent I used definitely sped up that translation.
tbrowder my use is not so sophisticated. i just have "hal" do the grunt work and ensure i have tests for all.
disbot <antononcube> For making tests and benchmarks LLMs are usually very good. 15:59
tbrowder it sure helps when one's memory is fading...
and it is wonderful for **slow** typists 16:00
disbot <antononcube> I used an LLM to convert one of the larger well known numerical integration suite to JSON. Then I wrote a Raku script to convert that JSON to Raku tests. (Reproducible research, blah, blah.) But, in general, I write the tests myself since I want to know how convenient is the design of the framework. 16:02
tbrowder i sometimes have to fix the tests because it gets confused and uses some python or perl bits 16:05
disbot <antononcube> You have to use proper language prompts. See for example use LLM::Prompts; llm-prompt('CodeWriterX')('Raku'). 16:09
16:22 dakkar left 16:31 stanrifkin joined
tbrowder hm, i don't use that approach at all. i start with something like: create a raku module that [...describe reqs in detail...]. i have previously described my raku coding style, module construction style, etc. we go back and forth tweaking things. as it gets more complex i will zip the current code on my side and pass it to ai. ai will fix and zip it up an pass it back to me. i carefully keep stages in git for recovery if need be. 16:33
disbot <antononcube> Here is an example how I use that "@CodeWriterX|Raku" prompt: 16:34
<antononcube> cdn.discordapp.com/attachments/633...4a90e&
<antononcube> Instead of using a Juputer magic cell that can be done with: llm-synthesize([ llm-prompt('CodeWriterX')('Raku'), <plain English instructions>, <example code> ], e => llm-configuration('ollama')) 16:36
tbrowder i feel like ai has regressed a bit in remembering procs since we started 16:37
disbot <antononcube> But if you are using an LLM agent you can just put those plain-English instructions and some instructions to just give Raku code.
<antononcube> No, I do not think so. 🙂 But the main use cases have changed. 16:38
16:42 sftp joined, sftp left, sftp joined
tbrowder from what i saw of your LLM i wasn't sure how you used it. were instructions partly done in # comments? 16:52
disbot <antononcube> In that screenshot above?
tbrowder i missed that one. but is that code you pass as a text int ai's "slot" and it writes its response in its "view port"? 16:59
disbot <antononcube> Yes.
tbrowder if so that's essentially what i do but i haven't tried to keep those chunks in a catalog 17:01
[Coke] "This content is no longer available."
(cdn.discordapp.com url)
17:05 z-raku joined
tbrowder antononcube: so i guess we're both doing similar usage in the raku TIMTOWTDI way 17:08
z-raku I'd like to install rakudo star on my Windows work laptop, but I don't have admin and msi install is restricted.  I have installed rakubrew and the latest rakudo (moar-2026.09).  Can I use rakubrew to install the rakudo star equivalent packages?  I can take this to raku-beginner if it is better there. 17:09
lizmat patrickb might know 17:10
tbrowder can you get WSL without admin?
z-raku I think that is how the rakubrew install succeeded. 17:11
I'm sorry, I misunderstood.  I'll check if I can get WSL working. 17:13
Looks like WSL is installing without complaint. 17:15
Nope, admin required. 17:16
Looks like I'll use zef to get the modules. 17:19
17:24 stanrifkin left 17:30 z-raku left 17:33 z-raku joined 17:42 z-raku left 17:58 [Coke] left 18:04 [Coke] joined 18:05 hankache joined
hankache hello #raku 18:05
lizmat hankache! :-) 18:14
hankache hey lizmat how are you?
long time...
lizmat heh... fine mostly 18:15
indeed
hope you're doing well as well, assuming so :-) nice work on raku.guide ±
!
18:16 z-raku joined
hankache Glad you're doing mostly well. Same here. 18:17
z-raku Thanks for the responses.  360.zef.pm is blocked from my org (I've requested it be reviewed to allow).  There are some modules not found, e.g. File-Find, Terminal-ANSIColor,...  I'll be grabbing them manually unless there is a source where zef can be pointed. 18:18
hankache Thanks! After a long break, it feels great to start dipping my toes back in. 18:21
z-raku quit :off to install the packages 18:26
18:26 z-raku left
[Coke] You can install directly from github 18:41
but you'd need to know where to look (and normally zef would use the url you mentioned to look it up) - you could look up a package on raku.land, and likely get the source URL from there. 18:42
lizmat makes me wonder whether zef should have a "raku.land" option to obtain the repo URL from there 18:43
18:46 coleman left 18:48 coleman joined
[Coke] I wouldn't want to have to make the fallback supported enough to be relied on. Having worked at companies that lock down the internet, getting them to review/open the site is probably the best option. 18:52
lizmat perhaps better to mirror the output of 360.zef.pm to maybe something like codeberg.org regularly 18:55
once a day or so
and allow zef to fall back to that if 360.zef.pm cannot be reached
18:57 coleman left 18:58 coleman joined
[Coke] What browsers do we want to support on raku.org. Chrome, Firefox, Safari, anything else that has a different engine? 19:45
(Trying to review a web site PR and we don't have the infra to automatically check the render of a site on various browsers) 19:46
japhb Those would be the core ones, yeah. Almost every browser is using their core renderers. 19:50
hankache I think most mainstream ones are based on Chromium and Gecko, and Webkit on Apple ecosystem
japhb The only thing I can think of is making sure it works on both desktop and mobile browsers
hankache I have tested locally on chrome and firefox on desktop but relied on claude for mobile. No clue for Safari. 19:51
japhb The old Webkit was swapped out for Blink (Chromium's core renderer), which itself started as a fork of Webkit. 19:52
IIRC Safari still uses JavascriptCore rather than V8 for JS code though 19:54
19:55 scott2 left 19:57 scott2 joined
[Coke] anton - any chance yo mught be at the canada raku/perl con '27? 20:19
disbot <antononcube> This is somewhat "too far away" for me to plan. 20:42
<antononcube> "Far away" in time, I see Ontario, Canada to be within a driving distance for me. 20:45
20:56 kaestralblades joined
[Coke] fair 21:34
22:23 Sgeo joined

Powered by Cro and the Raku® Programming Language.

Please report any issues / comments / feature requests as an issue on App::Raku::Log.

Thank you!