Re:We gave terabytes of CI logs to an LLM
by sollewitt on Friday February 27, 2026 @11:45AM
(#47182627)
I would be very interested in reading about this kind of orchestration and filtering than data acquisition if you have the energy for another post :)
Re:We gave terabytes of CI logs to an LLM
by shad42 on Friday February 27, 2026 @11:48AM
(#47182665)
We started writing very recently: https://www.mendral.com/blog - there is a another post we made yesterday about the overall architecture. And we have a long list of things we're planning to write about in more details.
Taking good note of your comment :)
Re:We gave terabytes of CI logs to an LLM
by aluzzardi on Friday February 27, 2026 @01:01PM
(#47183441)
We've actually started to gather metrics this week to write that exact post :) Coming soon!
Yes, it works really well.
1) The latest models are radically better at this. We noticed a massive improvement in quality starting with Sonnet 4.5
2) The context issue is real. We solve this by using sub agents that read through logs and return only relevant bits to the parent agent’s context