Topic
Longcat 2 5
2 episodes
-
Overview: On Policy Learning
We finally slow down and unpack on-policy learning: why an AI system often has to learn from the behavior it is producing right now. We use one running picture of a trainee cyclist to make the loop, its usefulness, and its cost actually stick.
-
Introducing LongCat 2
LongCat-2.5 is a 1.6-trillion-parameter native multimodal model aimed at long-horizon coding and agentic work. Pippa and Tyler examine whether its real advance is a better model, a more serious training system, or both.