Ralf _______________________________________________ Freedos-devel mailing list [email protected] https://lists.sourceforge.net/lists/listinfo/freedos-devel
Re: [Freedos-devel] Open Source projects stance of AI generated code
Ralf Quint via Freedos-devel Sat, 03 Oct 2026 19:48:16 -0700
Well, a few month ago, before my personal situation changed a bit to the
worse for now, I tried to use various LLMs (6) to try and give me a
little boost with a problem I ran into with a long stalled project of
mine, which ultimately should be a contribution to FreeDOS, but with the
option to "modernize" some parts of it and make it natively run on
Windows for example. Or Linux, etc. A GW-BASIC compatible interpreter.
Yes, I know PC-BASIC by Rob Hagemans exists, but that requires a huge
Python foot print. The issue at hand is that this BASIC (like the ones
before it) is using MBF (Microsoft Binary Format) floats, while
everything else (including its successor, QBASIC) is using IEEE-756
floats. But all information, beside the basic bitwise representation,
and some 3rd party source code, which I know existed at some point, has
vanished from the Internet.
So I asked those 6 LLMs to write me a library for all math functions,
all performed in MBF (so explicitly no conversion to and back from
IEEE-756!), and all in ANSI-C (instead of the ASM86 used in the original
GW-BASIC sources). One of those LLM outright refused ("Sorry Ralf, I
can't do that. ;) ), three others produced not even remotely usable
garbage, with the last two seemingly, after some persuasion and repeated
correction, seemed to come up with viable solutions, though only
ChatGPT's final answers seems to be somewhat trustworthy. Due to changes
in my personal situation, I have not been able to even test those
results yet, but at the very least, I got some hints on some of the
gotchas I ran into when I tried to recreate those maths routines myself
(that was well before the GW-BASIC 1.x assembler source was even
released), so I think I will get this eventually work, once my own
situation has settled enough. But then I wonder how much of the
resulting code would be indeed attributable to AI, if there is any
questionable/lack of attribution that would prevent the resulting
interpreter to be one day published and become part of FreeDOS
(development tools).
- Re: [Freedos-devel] Open ... Jim Hall via Freedos-devel
- Re: [Freedos-devel] O... Gregory Pietsch via Freedos-devel
- Re: [Freedos-dev... Jim Hall via Freedos-devel
- Re: [Freedos-dev... Gregory Pietsch via Freedos-devel
- Re: [Freedos-devel] Open Source projec... Aitor SantamarĂa via Freedos-devel
- Re: [Freedos-devel] Open Source p... Gregory Pietsch via Freedos-devel
- Re: [Freedos-devel] Open Sour... Jim Hall via Freedos-devel
- Re: [Freedos-devel] Open ... Gregory Pietsch via Freedos-devel
- Re: [Freedos-devel] O... Ralf Quint via Freedos-devel
- Re: [Freedos-devel] Open ... Steve Nickolas via Freedos-devel
- Re: [Freedos-devel] O... Ralf Quint via Freedos-devel
- Re: [Freedos-devel] Open Source p... Jim Hall via Freedos-devel
- Re: [Freedos-devel] Open Sour... Louis Santillan via Freedos-devel
- Re: [Freedos-devel] Open ... Ralf Quint via Freedos-devel
- Re: [Freedos-devel] Open ... Aitor SantamarĂa via Freedos-devel
- Re: [Freedos-devel] O... Jerome Shidel via Freedos-devel
- Re: [Freedos-dev... Michael Brutman via Freedos-devel
- Re: [Freedos-dev... Jerome Shidel via Freedos-devel
