reinforcement learning
2 posts
Article
A 4B model outplans Postgres
A 4B open-weights model, post-trained with SFT and RL, cut Postgres query latency 44.7% across 113 join-heavy benchmark queries using pg_hint_plan.
Article
SWE-2 is the wrong model for almost everything
Cognition's SWE-2 ships in medium, high, and max tiers; by its own numbers medium is the right pick for almost every coding task.