Hackernews posts about R1-Zero

1. An analysis of DeepSeek's R1-Zero and R1 (arcprize.org)
   732 points by meetpateltech 3 months ago | 272 comments
2. TinyZero: Reproduction of DeepSeek R1 Zero in countdown and multiplication tasks (github.com)
   226 points by fzliu 3 months ago | 27 comments
3. Understanding R1-Zero-Like Training: A Critical Perspective (github.com)
   160 points by pama about 1 month ago | 21 comments
4. There may not be aha moment in R1-Zero-like training (oatllm.notion.site)
   78 points by qianli_cs 2 months ago | 8 comments
5. Deepseek R1 Zero learns to reason using reinforcement learning on base model [pdf] (github.com)
   6 points by virde 3 months ago | discuss
6. Reproducing DeepSeek R1-Zero for < $30 (twitter.com)
   5 points by tamersalama 3 months ago | discuss
7. Deepseek R1 Zero (huggingface.co)
   4 points by hexomancer 3 months ago | discuss
8. DeepSeek R1-Zero's self-verification and search abilities in just 3B parameters (nitter.lucabased.xyz)
   3 points by TaurenHunter 3 months ago | discuss
9. We reproduced DeepSeek R1-Zero in the CountDown game for <$30 (nitter.lucabased.xyz)
   3 points by yagizdegirmenci 3 months ago | discuss
10. Understanding R1-Zero-Like Training: A Critical Perspective [pdf] (github.com)
    1 points by delifue about 1 month ago | 1 comments
11. Logic R1: Reproduce DeepSeek R1 Zero on 2K Logic Puzzle Dataset (github.com)
    1 points by limoce 3 months ago | discuss
12. Deep Seek R1 on Hyperbolic
    3 points by dubrado 3 months ago | discuss
13. AI research team claims to reproduce DeepSeek core technologies for $30 (www.tomshardware.com)
    3 points by jonbaer 3 months ago | 3 comments