Hackernews posts about DeepSeek R1

  1. Deepseek R1-0528 (huggingface.co)
    451 points by error404x 19 days ago | 250 comments
  2. DeepSeek-R1-0528 is now live on Hyperbolic (app.hyperbolic.xyz)
    17 points by dubrado 19 days ago | 4 comments
  3. DeepSeek-R1-0528 performance improvements (huggingface.co)
    14 points by pama 18 days ago | 3 comments
  4. DeepSeek-R1-0528 Did Not Have a Moment (thezvi.substack.com)
    10 points by paulpauper 9 days ago | 7 comments
  5. DeepSeek-R1-0528 Released (api-docs.deepseek.com)
    8 points by tvvocold 17 days ago | discuss
  6. DeepSeek R1 0528 scored 71% on the aider polyglot coding benchmark (3rd) (twitter.com)
    3 points by amrrs 7 days ago | discuss
  7. Deepseek-R1-0528 Dynamic 1-bit (unsloth.ai)
    3 points by tosh 18 days ago | discuss
  8. DeepSeek-R1-0528 Did Not Have a Moment (thezvi.substack.com)
    2 points by ctoth 10 days ago | discuss
  9. How to Run Deepseek-R1-0528 Locally (unsloth.ai)
    2 points by tosh 17 days ago | discuss
  10. DeepSeek-R1-0528 Release (api-docs.deepseek.com)
    2 points by gzoud 18 days ago | discuss
  11. DeepSeek-R1-0528 is here (twitter.com)
    2 points by ksec 18 days ago | discuss
  12. A Method for the Architecture of a Medical Vertical LLM Based on Deepseek R1 (arxiv.org)
    1 points by PaulHoule 26 days ago | discuss
  13. Show HN: AutoThink – Boosts local LLM performance with adaptive reasoning
    397 points by codelion 19 days ago | 68 comments
  14. Show HN: Second Brain – AI Visual Board and Knowledge Base (www.thesecondbrain.io)
    3 points by secondbrain_io 20 days ago | 1 comments
  15. Go AI Is No Longer a "Black Box"
    1 points by AILab 14 days ago | discuss
  16. SOTA Model in 8B Size? (huggingface.co)
    2 points by ConteMascetti71 18 days ago | 2 comments
  17. DeepSeek's small update to R1 AI model draws big attention (www.scmp.com)
    2 points by fofoz 18 days ago | discuss
  18. DeepSeek Unveils Update to R1 Model (www.bloomberg.com)
    4 points by ekaesmem 19 days ago | 1 comments
  19. DeepSeek-R1 (github.com)
    1843 points by meetpateltech 5 months ago | 663 comments
  20. DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via RL (arxiv.org)
    1351 points by gradus_ad 5 months ago | 1056 comments
  21. Promising results from DeepSeek R1 for code (simonwillison.net)
    979 points by k__ 5 months ago | 746 comments
  22. Run DeepSeek R1 Dynamic 1.58-bit (unsloth.ai)
    767 points by noch 5 months ago | 332 comments
  23. An analysis of DeepSeek's R1-Zero and R1 (arcprize.org)
    732 points by meetpateltech 5 months ago | 272 comments
  24. The Illustrated DeepSeek-R1 (newsletter.languagemodels.co)
    578 points by amrrs 5 months ago | 118 comments
  25. How to Run DeepSeek R1 671B Locally on a $2000 EPYC Server (digitalspaceport.com)
    463 points by walterbell 5 months ago | 283 comments
  26. Open-R1: an open reproduction of DeepSeek-R1 (huggingface.co)
    394 points by jonbaer 5 months ago | 234 comments
  27. Deepseek R1 Distill 8B Q40 on 4 x Raspberry Pi 5 (github.com)
    306 points by b4rtazz 4 months ago | 156 comments
  28. DeepSeek-R1-671B-Q4_K_M with 1 or 2 Arc A770 on Xeon (github.com)
    297 points by colorant 3 months ago | 112 comments
  29. Complete hardware and software setup for running Deepseek-R1 locally (twitter.com)
    250 points by olalonde 5 months ago | 192 comments
  30. Official DeepSeek R1 Now on Ollama (ollama.com)
    234 points by excerionsforte 5 months ago | 80 comments
  31. TinyZero: Reproduction of DeepSeek R1 Zero in countdown and multiplication tasks (github.com)
    226 points by fzliu 5 months ago | 27 comments
  32. Implementing DeepSeek R1's GRPO algorithm from scratch (github.com)
    192 points by xcodevn 2 months ago | 3 comments
  33. Mini-R1: Reproduce DeepSeek R1 "Aha Moment" (www.philschmid.de)
    191 points by jonbaer 5 months ago | 15 comments
  34. Berkeley Researchers Replicate DeepSeek R1's Core Tech for Just $30: A Small Mod (xyzlabs.substack.com)
    163 points by semking 5 months ago | 66 comments
  35. DeepSeek R1 Is Now Available on Azure AI Foundry and GitHub (azure.microsoft.com)
    109 points by toddanglin 5 months ago | 49 comments
  36. DeepSeek R1 671B running on 2 M2 Ultras faster than reading speed (twitter.com)
    96 points by thyrox 5 months ago | 29 comments
  37. How to run DeepSeek R1 locally (workos.com)
    84 points by grinich 5 months ago | 32 comments
  38. How to Run DeepSeek R1 Distilled Reasoning Models on RyzenAI and Radeon GPUs (www.guru3d.com)
    82 points by waltercool 4 months ago | 22 comments
  39. HuggingFace/open-r1: open reproduction of DeepSeek-R1 (github.com)
    63 points by ianrahman 5 months ago | 1 comments
  40. DeepSeek R1 is far better than OpenAI o1 at finding bugs in pull requests (www.greptile.com)
    43 points by dakshgupta 5 months ago | 8 comments
  41. DeepSeek-R1-Distill-Qwen-1.5B Surpasses GPT-4o in certain benchmarks (huggingface.co)
    39 points by BUFU 5 months ago | 17 comments
  42. Experience the DeepSeek R1 Distilled 'Reasoning' Models on Ryzen AI and Radeon (community.amd.com)
    38 points by mariuz 4 months ago | 13 comments
  43. Running DeepSeek R1 Models Locally on NPU (blogs.windows.com)
    37 points by doomroot13 5 months ago | 15 comments
  44. How to run 1.58bit DeepSeek R1 with Open WebUI (docs.openwebui.com)
    37 points by danielhanchen 5 months ago | 9 comments
  45. A step-by-step guide on deploying DeepSeek-R1 671B locally (snowkylin.github.io)
    37 points by snowkylin 5 months ago | discuss
  46. China won A side-by-side comparison of DeepSeek R1 vs. OpenAI O1 for Finance (nexustrade.io)
    35 points by austin-starks 5 months ago | 20 comments
  47. DeepSeek-R1 Is Now Available in GitHub Models (Public Preview) (github.blog)
    34 points by oliverchan2024 5 months ago | 3 comments
  48. DeepSeek-R1 for Coding in Zed (zed.dev)
    31 points by ashish01 5 months ago | 8 comments