2025-08-06 00:02:30 <cleobuline  > forthBot:  S" un monstre affreux avec des yeux globuleux des grandes dents et des tentacules "S TEMP-IMAGE
2025-08-06 00:02:40 <forthBot    > https://tinyurl.com/29s3yr3x
2025-08-06 00:03:27 <ajhidd      > \3
2025-08-06 00:19:35 <cleobuline  > forthBot:  S" un monstre affreux avec des yeux globuleux des grandes dents et des tentacules "S IMAGE
2025-08-06 00:19:50 <forthBot    > https://i.ibb.co/bRvSD06h/mforth-image-w1-J1-W1.png
2025-08-06 02:19:50 <forthBot    > Environment for cleobuline inactive, freeing...
2025-08-06 11:34:35 <veltas      > I'd be interested to see some tech documentation written with AI that someone considers good, because I think it would be too fluffy to read
2025-08-06 11:35:00 <veltas      > Unfortunately my experience is that the source code is the only useful documentation for most projects
2025-08-06 11:35:38 <veltas      > But I think that's unavoidable and maybe that should be reflected in our understanding of 'maintainability'
2025-08-06 15:46:09 <xentrac     > I don't think it's unavoidable, unless you include things like "TeX: The Program" in your definition of "source code"
2025-08-06 15:46:22 <xentrac     > in which case there's nothing unfortunate about it
2025-08-06 15:52:02 <xentrac     > a specific thing I did last year was http://canonical.org/~kragen/sw/dev3/smolhershey.md.html#addtoc_1, which is documentation I wrote myself
2025-08-06 15:52:37 <xentrac     > but part of that documentation is http://canonical.org/~kragen/sw/dev3/smolhersheyexample.c, which is mostly by GPT-4, although I've edited it
2025-08-06 15:53:42 <xentrac     > I did check in the original GPT-4 code in commit e0eab4643c603d2e9d57540d3a4b6026846cfddd
2025-08-06 15:54:27 <xentrac     > basically I just gave GPT-4 the header file and asked it to write an example program.  but the example program it came up with was kind of dum
2025-08-06 15:55:46 <xentrac     > and also badly formatted
2025-08-06 15:57:00 <xentrac     > later I added a GPT-4-generated Bresenham line drawing routine in 03044f425bba5a3373d13f322b0052e3f95c158a
2025-08-06 15:57:30 <xentrac     > and then cleaned that up because it was also badly formatted
2025-08-06 15:59:27 <xentrac     > I felt like GPT-4 was a real boost to my productivity there, but it might have been sort of an illusion
2025-08-06 16:01:01 <xentrac     > so I don't know if that's really what you're asking for :-)
2025-08-06 16:01:55 <xentrac     > Hmm, I think I wrote http://canonical.org/~kragen/sw/dev3/didcomp.en.md largely with GPT-4
2025-08-06 16:03:30 <xentrac     > basically I asked GPT-4 if it could explain the code in http://canonical.org/~kragen/sw/dev3/didcomp.c, and it wrote what seemed like a correct and lucid explanation
2025-08-06 16:04:37 <xentrac     > so I just checked in its explanation unmodified.  Also the translations into French and Spanish (which I verified were okay) and Chinese (which I did not)