grpo

How Group Relative Policy Optimization turns unit tests and theorem provers into training signals — the technique behind DeepSeek-R1's leap in math and code reasoning without a reward model.

An honest map of RL in 2026 — the domains where it actually reaches production (LLM post-training, robotics policies, ad bidding, RLHF, reasoning models) and the places where it still cannot reliably cross the lab-to-deployment gap.