Re: [PATCH 1/4] docs/devel: introduce a new policy on AI-generated contributions

["Michael S. Tsirkin" <mst@redhat.com>]

On Wed, Sep 02, 2026 at 09:09:59AM +0200, Paolo Bonzini wrote:
> Thanks for the review!
> 
> On 9/2/26 03:38, Alistair Francis wrote:
> > > +Prohibited use of AI
> > > +''''''''''''''''''''
> > > +
> > > +The following items **MUST** be written by humans:
> > > +
> > > +- cover letters and commit messages
> > > +
> > > +- responses to reviewer comments
> > > +
> > > +- issue descriptions or comments
> > > +
> > > +Light copy editing of human-written text with an AI is allowed.
> > 
> > What about translations? Not everyone can write English well and I see
> > translations being useful.
> 
> Difficult choice.  I can see that it's useful, but we've never been
> hardliners for English grammar, and translation may cause agent-ese to slip
> in.

And it does! My suggestion:

- demand that contributor writes text in english.
  if someone is speaking to us through an LLM due to a complete
  lack of english .... do we really want that?

- add text in AGENTS.md along the lines of:

  When asked to fix up english syntax/grammar, DO NOT MAKE style or
  wording changes beyond correctness. Limit your text changes to solely
  fixing correctness issues or coding style violations. Also, if the
  meaning is ambiguous, do not pick a possible meaning, instead insert a
  question for the user and prompt the user to clarify.

>  I am not a native speaker but I wouldn't use this possibility, so I'm
> not the best person to decide.
> 
> That said, if somebody asked the agent for help translating, it would
> probably do it anyway.
> 
> > > - small LLM-assisted bugfixes (as a rule of thumb, below 10 lines of
> > >   code) are allowed with disclosure.  Splitting a submission in multiple
> > >   parts is **not** a valid way to bypass this rule; repeated, frequent
> > >   posting of such fixes must follow the rule for full contributions.
> > 
> > Maybe add something like (fell free to edit):
> > 
> > """
> > When submitting LLM generated bug fixes the human should clearly
> > describe what the bug is, how it is triggered and how it impacted them.
> > The idea her is that we don't want people pointing an LLM at the source
> > and generating "bug fixes" for issues that users aren't seeing. This
> > can result in reviewer burnout.
> 
> I left that out because the document is already very long.  My suspicion is
> that the agent is able to infer most of it thanks to the "understanding"
> part of AGENTS.md, and reviewer burnout is covered by forbidding repeated
> posting of this kind of fix.
> 
> > > - use of LLMs to help generating parts of a larger patch---a test
> > >   case, a parser, boilerplate code for a new API, a tool to help
> > >   performing mechanical changes, etc. These are generally allowed, but
> > >   disclosure is recommended.
> > 
> > disclosure should just be required here as well.
> 
> I think it depends in general.  Sometimes there is really just one way to
> write code in this bucket, and in that case disclosure is superfluous (see
> for example the "impl<T: ToMigrationState> ToMigrationState for Mutex<T>"
> block in rust/migration/src/migratable.rs).  The AGENTS.md file will cause
> the agent to recommend it anyway.
> 
> Paolo