My takes: 1. I’d bet that synthetic-data self-improvement (e.g. RL on CoT with verifiable reward) is inducing a new growth regime (pictured). 2. 50% success rate corresponds to something like…

Posters: davidad. davidad

4 likes recorded by the source corpus.

Topics: AI & LLMs, AI safety

View Post: https://x.com/davidad/status/1902393419051274331