Hacker Newsnew | past | comments | ask | show | jobs | submit | fromlogin
Absolute Zero: Reinforced Self-Play Reasoning with Zero Data (andrewzh112.github.io)
1 point by mentalgear 8 months ago | past | 1 comment
Absolute Zero Reasoner (andrewzh112.github.io)
133 points by jonbaer 8 months ago | past | 24 comments
Absolute Zero: Reinforced Self-Play Reasoning with Zero Data (andrewzh112.github.io)
7 points by dave1010uk 8 months ago | past | 2 comments

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: