Continual-learning

Post-training has moved from imitating human labels to learning from verifiable outcomes. This write-up covers the RLVR objective, GRPO and the choice of KL penalty, advantage collapse and the methods that recover the lost gradient, reward hacking and noisy verifiers, outcome versus process reward models, the production data flywheel that turns failures into weight updates, long chain-of-thought and latent reasoning, and the OpenRLHF stack that runs it all.

An agent that gets better on its own has to change something about itself, and something has to check the change. This post walks the six things it can change, the checker that decides whether any of it worked, the ceiling it runs into, the ways it breaks, and the loop teams actually run in production.