On Thu, Apr 16, 2026 at 12:31:58PM +0200, Michael Niedermayer via ffmpeg-devel 
wrote:
> On Wed, Apr 15, 2026 at 04:03:20AM +0200, Michael Niedermayer via 
> ffmpeg-devel wrote:
> > Hi Niklas
> > 
> > On Mon, Apr 13, 2026 at 06:30:30PM +0200, Niklas Haas via ffmpeg-devel 
> > wrote:
> > > 
> > > 
> > > On Sun, Apr 12, 2026, at 6:41 PM, Michael Niedermayer via ffmpeg-devel 
> > > wrote:
> > > > Hi everyone
> > > >
> > > > Last easterbunny brought eggs and in one egg there was a life fairy.
> > > > She said her name is forgejo fairy and she wants to help the project
> > > > and community.
> > > >
> > > > She is still quite young so please be gentle with her, ATM what she can 
> > > > do is
> > > > * scan pull requests for ones that are stale. More precissely
> > > >   + No activity for 7 days and
> > > >   + open and
> > > >   + not WIP and
> > > >   + CI passes and
> > > >   + mergable = no conflicts and
> > > >   + no open change requests and
> > > >   + activity since the last fairy reaction or no previous and
> > > >
> > > > * she can read the patches, files patched and around 5000 files from 
> > > > FFmpeg git HEAD
> > > >   as well as all past comments in the PR
> > > > * she will try to review the changes and write a clean and concise 
> > > > comment
> > > >   also considering past comments so as no to add redudant information
> > > > * if EVERYTHING lines up she will approve the PR
> > > >   this will not on its own trigger any merge. Only if some human 
> > > > developer
> > > >   clicks the merge/rebase button or has previously set the PR to auto 
> > > > merge
> > > >   will that trigger a merge (this affects ATM at maximum 6 PRs)
> > > > * you can add her to the reviewer of a PR and that will decrease the
> > > >   "No activity" time to 1 day for that PR
> > > 
> > > I think having an LLM automatically scan PRs for bugs, typos, undefined 
> > > behavior etc is beneficial. I personally run every bigger series through 
> > > Claude Code, even those made by others, and it is very good at finding 
> > > bugs, especially ones missable by humans. I actually think that automatic 
> > > bug analysis can be done even in addition to human review.
> > > 
> > > However, I think the following criteria are needed to adopt this:
> > > 
> > > 1. The prompt should be published in the git repository, so that we can 
> > > see and propose changes to it.
> > > 2. It should only run / auto-approve PRa made by people with commit 
> > > rights.
> > > 3. The model used should also be documented publicly, and, per my 
> > > recommendation, should be Claude Opus 4.6.
> > 
> > The model is not the limitation here ATM, the problem we have ATM is more 
> > social and about the interaction between people and Fairy
> > not "which LLM is better"
> > 
> > but about technical stuff
> > for example i just uploaded all pull requests and issue from forgejo into a 
> > vector store
> > now its just a matter of telling Fairy that she has that data available
> > 
> > If you are curious of the current architecture of this.
> > Everything goes in git repositories,
> > * ffmpeg as it is,
> > * any additional things we want Fairy to be able to access efficiently
> > * and now a full dump of all issues and pull requests
> > 
> > Each of these git repositories is uploaded into its own vector store and
> > a script keeps them in sync
> > 
> > Fairy then uses these vector stores and can perform semantic search in them
> > She also can search the web
> 
> had to rebuild the vector store, because the API refuses too many vector 
> stores
> (rebuild still in progress, currently she is running with 80% of it available)
> 
> so now we will have 1 vector store for ffmpeg git (that one is complete)
> and the 2nd will contain multiple git repositories with subtrees (which btw 
> works
> beautifull and simple)
> ATM the 2nd git contains forgejo PRs&issues, static documents
> intend to add ffmpeg-web and fateserver
> 
> also ive just added this to the prompt
> <verification_loop>
> Before finalizing:
> - Check correctness: does the output satisfy every requirement?
> - Check grounding: are factual claims backed by the provided context or tool 
> outputs?
> - Check formatting: does the output match the requested schema or style?
> </verification_loop>

i cought her making a off by 1 in one calculation so its now this:

@@ -1862,8 +1863,11 @@ Classify the pull request into exactly one of these JSON 
classes after you have
 <verification_loop>
 Before finalizing:
 - Check correctness: does the output satisfy every requirement?
-- Check grounding: are factual claims backed by the provided context or tool 
outputs?
+- Check grounding: is every factual or technical claim supported by the patch, 
attached files, prior discussion, or tool output?
 - Check formatting: does the output match the requested schema or style?
+- Check derived claims: for every claim that depends on calculation, 
inference, bounds, integer behavior, bit operations, indexing, or spec 
interpretation, have you verified it carefully enough to state it as fact?
+- Check sanity: do any reported numeric or semantic conclusions contradict 
known limits, invariants, or the cited specification/context? If yes, re-check 
before reporting.
+- Check uncertainty: if any important point is not well verified, did you mark 
it as uncertain?
 </verification_loop>

 Return JSON only, with this exact shape:

[...]

-- 
Michael     GnuPG fingerprint: 9FF2128B147EF6730BADF133611EC787040B0FAB

The misfortune of the wise is better than the prosperity of the fool.
-- Epicurus

Attachment: signature.asc
Description: PGP signature

_______________________________________________
ffmpeg-devel mailing list -- [email protected]
To unsubscribe send an email to [email protected]

Reply via email to