Post

mr. TIM
@timkellogg.me

Ornith 1.0: full spectrum of open weights coding models from 9B to 397B The largest appears to rival Opus 4.7-4.8 All fine tuned from Gemma 4 and Qwen 3.5 but no, the cool part is how they made it… 👇 deep-reinforce.com/ornith_1_0.h...

9 reposts81 likes

mr. TIM
@timkellogg.me

They came up with a self-improving RL framework where the model generates both the solution as well as RL harness/environment since they’re jointly optimizing the two together, they can discover better next steps to make the problem slightly harder in all the right ways

mr. TIM
@timkellogg.me

big labs have grown huge and complex org charts of engineers creating RL environments. This new self-evolving harness might be a necessary piece to getting open weights models to compete it’s finally bumping RL back in line with The Bitter Lesson