> In my experience use of LLMs for production code is more complex > than writing a prompt and then taking the resulting patch to the > mailing list (that is not allowed for GCC by the current AI policy > for non-small changes anyway). > > It is usually a long session, where you start with an initial < > prompt, review its output, answer questions it may pose, tell it to > rework parts that you find fishy, tell it to do prior research, run > extra validation, launch other LLMs to review its work etc. So it > would often not be possible to disclose a compact list of > instructions given.
I very much agree, but the scenario discussed here is a much simpler one. > If we, as a project, wanted to give some agreed-upon design rules > for LLMs to follow we could add an AGENTS.md file to the GCC repo > that describes the high-level dos and don'ts, though with the > current restrictive AI policy it would probably cause confusion > unless its relaxed. I interpreted what was suggested as something different, where what you'd tell the model is "please don't send me code; instead tell me what I should do and I'll do it". That's consistent with the current AI policy and could help to enforce the policy.
