SFT Is Bad RL
justinchiu.netlify.appยท1dยท
Discuss: Hacker News
How to reason from first principles
caseyhandmer.wordpress.comยท1dยท
Discuss: Hacker News
Underwriting Superintelligence
underwriting-superintelligence.comยท2dยท
Discuss: Hacker News
ATC/OSDI'25 Technical Sessions
muratbuffalo.blogspot.comยท6dยท
Discuss: Hacker News