Hi Michael,

Le ven. 24 avr. 2026 à 04:02, Michael Niedermayer via ffmpeg-devel
<[email protected]> a écrit :
>
> Hi
>
> Some question about fairy design
>
> Fairy is written in python,
> the main script does
> * fetches the forges data (separate thread, cache and all)
> * spawns LLM workers
> * old style UI with a simple yes/next/skip/redo/quit for each LLM response
>
> The LLM workers each call a seperate wraper (aka new process)
> which then contains the code specific for openai or in the future antropic 
> and others
>
> The problem iam running into with this is, as i want to use multiple agents
> (ATM teh openai code uses 2, we use a gpt-5.4 nano to setup the container,
>  well basically untar our git repositories)
> and then the main gpt-5.4 reviewing the code
>
> Now the easy thing is to just add a claude / antropic wraper but this
> actually feels like bad design
>
> what i was thinking is to rather get rid of the process and do these "wrapers"
> fully in python.
> The reason why, is simply, i want to be able to querry multiple LLMs
> and combine their reviews and these wraper feel a bit wrong for that
>
> Its easy to querry openai 3 times and have openai combine 3 results
> IN the openai wraper. But that will keep bloating up the wraper over time
> and make them increasingly non interchangeable and also have more logic
> where it doesnt belong
>
> And as my idea was to try to have both GPT and Claude
> do the review and combine their findings that kind of makes the
> wrappers at process level feel a bit heavy

How are you planning on merging the reviews? I'm curious as to how
this can be done while keeping the review content at a reasonable
level of verbosity and accuracy..

I imagine solving this might help guide the rest of your design.

> so before redesiging/restructuring this I wanted to check if people
> have some comments
>
> thx
>
> PS: yes, i intend to make the source available after more cleanup,
> still little undecided on the licesne though.

PS: I do not intend to start a complicated discussion but using a
gender for the LLM reviews feels unnecessary to me. There's already a
lot of assumptions around genders to avoid adding one more for a robot
script.

Thanks for your work,
-- Romain
_______________________________________________
ffmpeg-devel mailing list -- [email protected]
To unsubscribe send an email to [email protected]

Reply via email to