news.volyx.in

DeepScaleR: Surpassing O1-Preview with a 1.5B Model by Scaling RL (pretty-radio-b75.notion.site)

322 points by sijuntan · 538 days ago · 127 comments on HN

The AI summary for this story hasn't been generated yet — it's produced hourly. Check back soon. Meanwhile, read the discussion on HN.