Hi Lucas, Thank you for bringing up the idea of Debian applying for the OpenAI Open Source Fund. I appreciate you taking the initiative to explore potential funding opportunities that could benefit DDs who might decide freely to profit from it or not.
Since you've asked for DPL approval, I hereby approve your initiative to
explore and apply for the OpenAI Open Source Fund.
Kind regards
Andreas.
Am Thu, Jun 12, 2025 at 09:42:48AM +0200 schrieb Lucas Nussbaum:
> On 11/06/25 at 22:10 +0300, Otto Kekäläinen wrote:
> > Hi!
> >
> > > > > OpenAI has an Open Source fund. Maybe Debian should apply[1] for a
> > > > > grant
> > > > > so that Debian contributors could get hands-on experience on how this
> > > > > could help their Debian activities?
> > > >
> > > > or maybe Debian should not.
> > >
> > > Maybe. Honestly, I don't know.
> >
> > I still think it would be a nice perk for DDs, along the other perks
> > listed at https://wiki.debian.org/MemberBenefits
> >
> > It is up to each DD to decide how to use the tools and services.
> > Personally I don't recommend using them to generate code as in the
> > Debian context they seem to output so much bad results, but using
> > LLM's for example to review code seems to be working pretty well and
> > is faster and cheaper than waiting for humans to review (and humans
> > can still review, they will just seem more polished stuff).
>
> My experience is a bit different -- I've found it useful to treat the LLM
> as an inexperienced coworker:
> - decide on what I would like to do
> - ask the LLM to do it
> - review carefully
> - refine what the LLM proposes either by asking with more details, or
> edit directly
>
> > > (A) an "agent", that is the client software running on your machine that
> > > you talk with, and that interacts with your codebase (read files, make
> > > changes to files, run commands, create git commits, etc.). Ideally in
> > > some kind of sandbox and/or with permissions management.
> > > Examples include 'Claude Code' (works in CLI, proprietary, interacts
> > > only with Anthropic models), Cursor(.com) (VS Code fork, proprietary,
> > > interacts with either Claude* (Anthropic) or Gemini* (Google)), Codex
> > > CLI (free software, developed by OpenAI and focused on their models, but
> > > supposed to work with other providers). DebGPT fits here too (but is
> > > less advanced for coding tasks than Claude Code or Cursor).
> >
> > All of the above are closed-source solutions.
>
> Not Codex CLI
>
> > I have been playing
> > around with the fully open https://aider.chat/ for well over a year
> > and I would recommend it instead. I hope to some day write a blog post
> > about how I run it inside a container safely and how I have customized
> > it to give better results than what it does out-of-the-box.
>
> Right, aider.chat came up in another discussion, and looks promising.
> There was an ITP about it (#1082026, abandonned).
>
> Another Free Software alternative is Zed
> (https://github.com/zed-industries/zed), but it looks less open in the
> spirit than Aider.
> Other closed-source products are WindSurf, Augment Code.
>
> Lucas
>
>
--
https://fam-tille.de
signature.asc
Description: PGP signature
