Ornith-1.5 achieves end-to-end self-improvement where the model proposes tasks, generates scaffolds, and produces RL rollouts to create new training experiences

The headline claim is end-to-end self-improvement: the model proposes tasks, generates scaffolds, and produces RL rollouts to create new training experiences.

https://www.latent.space/p/ainews-death-of-params-zai-ceo-jie