On Wed, Sep 02, 2026 at 09:56:25AM -0400, Michael S. Tsirkin wrote: > On Wed, Sep 02, 2026 at 02:47:57PM +0100, Daniel P. Berrangé wrote: > > On Wed, Sep 02, 2026 at 02:42:15PM +0100, Alex Bennée wrote: > > > Paolo Bonzini <[email protected]> writes: > > > > > > > Humans seem to be extremely unreliable in following rules around this, > > > > even after being told directly and repeatedly. Telling agents what to > > > > do seems to yield better results. > > > > > > > > This document is based on GStreamer's AGENTS.md file, as of its commit > > > > d08375499c279a56c0e77c928fbeae0d80cdf937. However, GStreamer's agent > > > > instructions are "effective" enough to require an explicit carve-out > > > > for maintainers. I actually believe that such a carve-out is a sign of > > > > going too far, especially given the good quality of some suspected-AI > > > > contributions we've received. > > > > > > > <snip> > > > > diff --git a/AGENTS.md b/AGENTS.md > > > > new file mode 100644 > > > > index 00000000000..8fb96ebfc38 > > > > --- /dev/null > > > > +++ b/AGENTS.md > > > > @@ -0,0 +1,100 @@ > > > > +# Agent Guidelines for the QEMU Project > > > > + > > > > +QEMU is a cross-platform emulator and virtualizer. Due to the > > > > complexity > > > > +of the domain and codebase, and the interactions therein, the QEMU > > > > +project relies extensively on the effort of **human reviewers**, which > > > > +is **a scarce resource**. > > > > + > > > > +There are strictly-enforced rules for you, the agent, to participate > > > > in the > > > > +project. > > > > + > > > > +## Interactions with maintainers must be human-human > > > > + > > > > +The QEMU project has strict rules on what AI-generated material can > > > > +reach the maintainers. > > > > + > > > > +### No automated posting > > > > + > > > > +- Agents **must not** use any API, CLI, or web UI automation to: > > > > + - Interact with the QEMU mailing lists > > > > + - Create, edit, or close **issues ("work items")** > > > > > > The others I'm fine with but I currently use an agent to do triage on > > > un-tagged issues. It only updates labels and occasionally posts a > > > comment when more information or a human input is required. > > > > While this is technically something you're doing via your personal > > gitlab account, I none the less view the agent triage bot as something > > run as an "official" project service. > > > > IMHO the AGENTS.md policy primarily applies to actions done in an > > individual capacity (whether contributor or maintainer). > > > > If the project wants to deploy project level services that utilize > > AI in some manner and that conflicts with AGENTS.md that's acceptable, > > provided we discuss & agree that the project service in question is > > desirable. > > > > Perhaps this is me saying that the issue triage bot should be made > > more official as a service, committed to git, etc > > well I have a script that uses gitlab API to run the security process > workflow. But it's... how do I put it... AI assisted ;)
Can we make that an official project script too, such that it is something that is reviewed and thus "blessed" as acceptable ? I'm pretty uncomfortable with the idea of policy that allows for arbitrary AI agents processing issues with no independent review of what they're doing until after they've already done it. The issue agent Alex runs, while useful, also makes a decent number of mistakes and wierd assertions in comments it adds. To some degree that is unavoidable for AI based tools doing this work, but IMHO it justifies the extra review to ensure the community is broadly happy with the tradeoff in the tool in question. With regards, Daniel -- |: https://berrange.com ~~ https://hachyderm.io/@berrange :| |: https://libvirt.org ~~ https://entangle-photo.org :| |: https://pixelfed.art/berrange ~~ https://fstop138.berrange.com :|
