A FEW THINGS FOR LATER
Your reading list.
Good ideas deserve a second look. Save any story from its article page to find it here.
Open your research desk ↗Saved in this browser. No account, no syncing.Opening your reading list…
A good place to begin
All stories ↗
TrainingGRPO efficiency starts before the kernel
A practical investigation of sparse rewards, loss normalization, and what a faster training step actually proves.
AgentsA coding agent is a system, not a score
How to compare coding agents without confusing model quality, scaffolding, test contamination, and retry budget.
RoboticsRobot foundation models need a data contract
What GR00T and π₀ teach us about the gap between a general model and a reliable policy on a particular robot.