Hackernews posts about R1-Zero

1. 01
   

   newAn analysis of DeepSeek's R1-Zero and R1arcprize.org

   ▲ 732meetpateltech613d💬 272savesaved
2. 02
   

   newTinyZero: Reproduction of DeepSeek R1 Zero in countdown and multiplication tasksgithub.com

   ▲ 226fzliu618d💬 27savesaved
3. 03
   

   newUnderstanding R1-Zero-Like Training: A Critical Perspectivegithub.com

   ▲ 160pama561d💬 21savesaved
4. 04
   

   newThere may not be aha moment in R1-Zero-like trainingoatllm.notion.site

   ▲ 78qianli_cs605d💬 8savesaved
5. 05
   

   newDeepseek R1 Zero learns to reason using reinforcement learning on base model [pdf]github.com

   ▲ 6virde623ddiscusssavesaved
6. 06
   

   newReproducing DeepSeek R1-Zero for < $30twitter.com

   ▲ 5tamersalama612ddiscusssavesaved
7. 07
   

   newDeepseek R1 Zerohuggingface.co

   ▲ 4hexomancer623ddiscusssavesaved
8. 08
   

   newDeepSeek R1-Zero's self-verification and search abilities in just 3B parametersnitter.lucabased.xyz

   ▲ 3TaurenHunter612ddiscusssavesaved
9. 09
   

   newWe reproduced DeepSeek R1-Zero in the CountDown game for <$30nitter.lucabased.xyz

   ▲ 3yagizdegirmenci613ddiscusssavesaved
10. 10
    

    newUnderstanding R1-Zero-Like Training: A Critical Perspective [pdf]github.com

    ▲ 1delifue562d💬 1savesaved
11. 11
    

    newLogic R1: Reproduce DeepSeek R1 Zero on 2K Logic Puzzle Datasetgithub.com

    ▲ 1limoce607ddiscusssavesaved
12. 12
    

    newDeep Seek R1 on Hyperbolic

    ▲ 3dubrado620ddiscusssavesaved
13. 13
    

    newAI research team claims to reproduce DeepSeek core technologies for $30www.tomshardware.com

    ▲ 3jonbaer613d💬 3savesaved

· edit