discu
Newsletters
Mentions
Extension
Pricing
Login
Sign Up
Hacker News
DeepScaleR: Surpassing O1-Preview with a 1.5B Model by Scaling RL
https://pretty-radio-b75.notion.site/DeepScaleR-Surpassing-O1-Preview-with-a-1-5B-Model-by-Scaling-RL-19681902c1468005bed8ca303013a4e2
127 comments
11/2/2025