On Tue, Oct 27, 2026 at 7:01 PM Alex Bennée <[email protected]> wrote: > > Paolo Bonzini <[email protected]> writes: > > > Until now QEMU's code provenance policy declined any contribution > > believed to include or derive from AI-generated content. A blanket ban > > was easy to maintain while LLM output was rarely usable on its own, but > > as the tools improved an absolute prohibition has become harder to > > justify and enforce. > <snip> > > +LLM-assisted and LLM-created contributions > > +'''''''''''''''''''''''''''''''''''''''''' > > + > > +Use of generative AI can be classified in the following four buckets: > > + > > +- "background" assistance, such as completion and code review. This does > > + not need disclosure. > > + > > +- 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. > > + > > +- use of LLMs to help generating parts of a larger patch---test cases, > > + adaptations of existing code, boilerplate code for a new API, a tool to > > + help performing mechanical changes, etc. These are generally allowed; > > + disclosure is highly recommended for non-trivial, functional code. > > Personally I'm happy with the next bit but if there is still > disagreement about the wording could we merged the policy updates up to > this point and defer larger contributions until we see what the > practical effects are on the list?
The problem is that, for all intents and purposes, we are already receiving such larger contributions. This is why I wanted to have something about them in the policy. My plan was to discuss at QEMU Summit, though unfortunately it will be rather sparsely populated this year. Paolo
