harlequinetcie

The strategy is quite straight forward:

-> Clairic extracts the PR's claims -> Jev tags diff hunks, then judges what requires a review. -> Cheap(er) model to review the hunks.

For us, we've got PR reviews in under 30 seconds, and cost down to a few cents.

Next step, we are thinking on training some small open weight models specialized on our repo.

Thoughts?

I think attribution is the difficulty there right?

You could guess, but would that change something?

As a dev or as a user?

It's true that being agile still works, but the explosion on how much you can do as individual is non-negligible.

If you introduce too many changes at the same time, how can you attribute what works and what not?

That's the other challenge we are seeing, and that gets worse if you have bigger teams.

Centralized intelligence helps, but enforcing the correct coordination... feels like we are missing a new type of role.

Opus 5.5 gave us 50% savings, with 2x the speed of Opus 5. DeepSeek Flash v4.1 is now 22x cheaper & 30% faster than Opus 5.5. Same performance.

DeepSeek caveats: + You have an LLM-Agent-UMF architecture. Vanilla pi harness fails. + Coding tasks are lousy. Beyond coding, difficult open-ended reasoning scenarios are the ones at which it performs best for us.

Exactly this... Which city will allow for a car they cannot chase with a patrol?

It would have been much better if it was a skateboard, tbh.

ohhh watching this game with The Game of Love from Daft Punk pays off.

Fun stuff!

This is the PLAY

Eventually providers that host models with tight restrictions will become popular just because of this. Everyone is collecting data, one way or another one.

What's funny for me? -> Companies are still signing multi-year contracts with big labs so they can send all their data there. -> If I was a big lab, I just need to learn behavior, not necessary even understand the messages, to take my software to the next level.

But who knows, I'm no genius.

I mean, you built more companies than polsia according to your landing, that's great right?

How come we forgot about this so quickly?