Hacker News new | past | comments | ask | show | jobs | submit login
Deepseek R1 Zero learns to reason using reinforcement learning on base model [pdf] (github.com/deepseek-ai)
6 points by virde 29 days ago | hide | past | favorite



Join us for AI Startup School this June 16-17 in San Francisco!

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

Search: