1.7K views · 18 likes · 0 reposts (at collection)
Nathan Lambert says RL details from closed labs are slowly leaking out
- Who
- Nathan Lambert
- What
- comments on RL details from closed labs leaking through a reverse-engineered StableReinforce objective
What happened
Nice thread, some RL details used by closed labs slowly leaking out. https://twitter.com/mrtnm/status/2114145574987702525
Read next
See the full storyNathan Lambert Says Closed Labs’ Reinforcement Learning Details Are Slowly Leaking OutThe story so far
Nathan Lambert pointed to a thread on X and said that some reinforcement learning details used by closed labs are “slowly leaking out.” His comment characterized the thread as offering insight into those labs’ methods.
Keep up with AI, one email a day
Model releases, price changes and compute developments, with original sources. Free, confirmed by email, and easy to unsubscribe. Read a past issue · 2026-10-25