WARNING: this is *intentionally* a full U-turn from the previous policy
and discussions.  This is not a refusal of the arguments presented in
those discussions.  It is also a request for comments, and not something
that is ready to go.

The reason to "try something else" is that previous discussion have come
to be a unanimity trap.  Attempting to introduce small carve-outs for
tests, for doc comments, for bugfixes did not work; each case will
have someone (rightfully) expressing disagreement and the only possible
equilibrium remains the current "no AI for code generation" policy.
The Rust project also acknowledged the impossibility of reaching a
widespread consensus on this topic.

Furthermore, we have clear signs that the current policy is not blocking
some contributors from posting AI-generated patches or even larger series,
most likely in good faith.  While the policy does not require maintainers
to police AI usage, "don't ask, don't tell" approaches are best treated as
a red flag.

At the same time, a free-for-all is not a good idea either.  Maintainers
will want to apply their own considerations (see [1] for a good list),
and I think we want to heed Conservancy's advice to not shun contributors
or maintainers belonging to either camp.

So let's make a new hypothesis: that the no-AI policy is an equilibrium
only because it's stable, not because it's good.  Attack the problem
from the point of view of maintainer burnout rather than copyright/DCO.
Apply a large perturbation, and see where *that* discussion takes us.

As usual, the text including the commit messages is informed by discussion
with plenty of people, mentioned in the Cc trailers of patch 1.

Paolo

[1] https://lore.kernel.org/qemu-devel/CAFEAcA860fF_+ffk=cXiYyFoQo0wCSUJ6b=7nVLLCwKhP6Nwxw@mail.gmail.com/

Paolo Bonzini (4):
  docs/devel: introduce a new policy on AI-generated contributions
  AGENTS.md: Let agents know what the participation rules are
  AGENTS.md: make the human part of the design process
  agents: add CLAUDE.md and GEMINI.md

 docs/devel/code-provenance.rst |  71 ++-----------
 docs/devel/index-process.rst   |   1 +
 docs/devel/llm-usage.rst       | 179 +++++++++++++++++++++++++++++++++
 AGENTS.md                      | 116 +++++++++++++++++++++
 CLAUDE.md                      |   1 +
 GEMINI.md                      |   1 +
 6 files changed, 304 insertions(+), 65 deletions(-)
 create mode 100644 docs/devel/llm-usage.rst
 create mode 100644 AGENTS.md
 create mode 100644 CLAUDE.md
 create mode 100644 GEMINI.md

-- 
2.55.0

On Tue, 1 Sept 2026 at 17:14, Paolo Bonzini <pbonzini@redhat.com> wrote:
>
> WARNING: this is *intentionally* a full U-turn from the previous policy
> and discussions.  This is not a refusal of the arguments presented in
> those discussions.  It is also a request for comments, and not something
> that is ready to go.


> Paolo Bonzini (4):
>   docs/devel: introduce a new policy on AI-generated contributions
>   AGENTS.md: Let agents know what the participation rules are
>   AGENTS.md: make the human part of the design process
>   agents: add CLAUDE.md and GEMINI.md

Could somebody write a short AGENTS.md which is *just* an
encoding of *current* AI policy, please? I think this is now
the second series that provides an AGENTS.md as part of
doing something more ambitious. But right now we have nothing
at all, which means we have no guard against users who have
missed our AI policy asking an LLM to generate code that they
intend to submit upstream.

thanks
-- PMM

On Wed, 2 Sep 2026, Peter Maydell wrote:
> On Tue, 1 Sept 2026 at 17:14, Paolo Bonzini <pbonzini@redhat.com> wrote:
>>
>> WARNING: this is *intentionally* a full U-turn from the previous policy
>> and discussions.  This is not a refusal of the arguments presented in
>> those discussions.  It is also a request for comments, and not something
>> that is ready to go.
>
>
>> Paolo Bonzini (4):
>>   docs/devel: introduce a new policy on AI-generated contributions
>>   AGENTS.md: Let agents know what the participation rules are
>>   AGENTS.md: make the human part of the design process
>>   agents: add CLAUDE.md and GEMINI.md
>
> Could somebody write a short AGENTS.md which is *just* an
> encoding of *current* AI policy, please? I think this is now

I'm not familiar with AGENTS.md but would just putting "See Use of 
AI-generated content section in docs/devel/code-provenance.rst." in it be 
enough to let AI tools warn the users if they don't do that already?

Regards,
BALATON Zoltan

Peter Maydell <peter.maydell@linaro.org> writes:

> On Tue, 1 Sept 2026 at 17:14, Paolo Bonzini <pbonzini@redhat.com> wrote:
>>
>> WARNING: this is *intentionally* a full U-turn from the previous policy
>> and discussions.  This is not a refusal of the arguments presented in
>> those discussions.  It is also a request for comments, and not something
>> that is ready to go.
>
>
>> Paolo Bonzini (4):
>>   docs/devel: introduce a new policy on AI-generated contributions
>>   AGENTS.md: Let agents know what the participation rules are
>>   AGENTS.md: make the human part of the design process
>>   agents: add CLAUDE.md and GEMINI.md
>
> Could somebody write a short AGENTS.md which is *just* an
> encoding of *current* AI policy, please? I think this is now
> the second series that provides an AGENTS.md as part of
> doing something more ambitious. But right now we have nothing
> at all, which means we have no guard against users who have
> missed our AI policy asking an LLM to generate code that they
> intend to submit upstream.

Can anyone test their agents against:

  20260902174942.614254-1-alex.bennee@linaro.org


>
> thanks
> -- PMM

-- 
Alex Bennée
Virtualisation Tech Lead @ Linaro