[sfjailbird]

Given that submitters are just using LLMs to produce the PR anyway, it makes sense that the author can just run that prompt himself. Just share the 'prompt' (whether or not it is actually formatted as a prompt for an LLM), which is not too different than a feature request by any other name.

[alxhslm]

Agree with this. Maybe we should start making PRs with the proposed spec and then the maintainer can get their agent to implement it.

This is similar to what we’ve started to do at work. The first stage of reviewing a PR is getting agreement on the spec. Writing and reviewing the code is almost the trivial part.

[dpc_01234]

Yes. At this point a prompt that produces the desired result is more useful than the resulting code in a PR. Effectively the code starts to have properties of a resulting binaries.

[esafak]

If your use of LLMs is limited to one shot prompts you must be new.

[vlapec]

+1