AI-generated contributions and generated workload on maintainers
Richard Kettlewell
rjk at terraraq.uk
Sun Nov 8 12:34:55 UTC 2026
On 08/11/2026 10:53, Julien ÉLIE wrote:
> Hi all,
>
> Wishing to share some thoughts with you.
>
> There is more and more AI-assisted development in today's world. I am
> not against it; I do see the value it can give, that's not the problem.
>
> As far as INN is concerned, with very few active maintainers compared to
> its large codebase, I am overwhelmed by the amount of work recent PRs
> and issues take. Besides, it does not seem temporary.
> There are several AI agents from OpenAI and Anthropic running on INN
> codebase, submitting bug fixes and security reviews. Honestly, I cannot
> cope with that. Too much mental load, having to read very lengthy
> discussions, review code, make some research, answer, commit, merge, etc.
> I no longer take any fun in all of that, and my interest begins to
> decrease. I do not want to spend my spare time and my evenings reading
> and discussing with an AI on PRs and the issue tracker. It responds
> within minutes with questions, decisions to make, proposals, etc.
> It even said yesterday "I'm not a C expert myself. Your review remains
> the real check." Well, it knows C far better than I and does not take
> any responsibility in its work...
I would respond: "if you are not a C expert then you must not submit any
changes to C code".
> It announced tons of upcoming patches, concluding with "@Julien-Elie be
> prepared 👯"
>
> Well, this mail is a bit of a call for help. I cannot work under these
> conditions. I naturally do not want to see INN development stopped,
> notably when most (but not all) of the AI stuff is interesting to merge.
>
> I say "most" because I spotted weird things and inaccuracies in some
> submitted patches. And a few minutes after highlighting these, the
> responses came:
> "You are right, the reproduction steps are wrong: newsgroups: and post:
> can't be combined."
> "my patch added the field name to its new error message but indeed
> missed this one"
> "I mis-copied it"
> "I withdraw the sentence. I haven't substantiated it."
It sounds like these patches were not ready for your review.
> So, what to do next?
>
> A proposal to discuss: couldn't we give push/commit access to the GitHub
> users running AI agents? This way, they could automatically work and
> improve the code as well as open and close PRs and tickets.
>
> I would then just only prepare releases (if not also automated!) as I do
> not see what else I can do these AI agents cannot already do. They have
> ideas and preferred solutions on all the subjects. They could even
> answer questions on mailing-lists and newsgroups better than I could!
* I think there is zero reason for you to be 'in the loop' as AIs
iteratively fix their patches. It's an abuse of your time. That
iterative process ought to be completed before a pull request is even
opened.
* How the operators of the AIs achieve that is up to them, but current
tooling makes it pretty straightforward. It is absolutely possible to do
better, with today's AIs, than "let Julian sort out the mess".
* Personally I would take a hard line in rejecting any pull requests
that followed any abusive pattern.
* I do not think it is a good idea to give AI agents push/commit access
to the INN github. They can iterate using their own clone of it. As
you've noted the patches contain errors, so letting them push without
review would mean those errors got into the published code.
ttfn/rjk
More information about the inn-workers
mailing list