Hackernews posts about ARC-AGI

  1. OpenAI's GPT-6 Astra on ARC-AGI-3 (arcprize.org)
    240 points by vignesh_warar 17 days ago | 168 comments
  2. Claude Fable 5.1 results on ARC-AGI (arcprize.org)
    5 points by matt1 19 days ago | 3 comments
  3. Astra is at 98.6% score on ARC-AGI-3 (cdn.thenewstack.io)
    4 points by TheJCDenton 17 days ago | 1 comments
  4. GPT-6 Astra Achieves SOTA on ARC-AGI (twitter.com)
    3 points by porridgeraisin 17 days ago | discuss
  5. Pushing GPT-5.6 Luna from 0% to 56% on ARC-AGI-3 Public (int21.ai)
    3 points by antinucleon 24 days ago | discuss
  6. ARC-AGI-3: A game with no instructions (genaipod.substack.com)
    3 points by kuczmama 24 days ago | discuss
  7. OpenAI's GPT-6 Astra on ARC-AGI-3 Scored 99.95% with Provider Adapter Harness (arcprize.org)
    2 points by HetPatel106 14 days ago | 3 comments
  8. 100.00 RHAE on the ARC-AGI-3 public set (www.agno.com)
    2 points by ashpreet-bedi 26 days ago | discuss
  9. Nvidia's AVO harness boosts Opus 5 to 100% on ARC-AGI 3 (developer.nvidia.com)
    1 points by irthomasthomas 16 days ago | discuss
  10. ARC-AGI Without Pretraining (2025) (iliao2345.github.io)
    1 points by newsuser 19 days ago | discuss
  11. Percent on ARC-AGI-3 (monotykamary.com)
    1 points by freediver 22 days ago | discuss
  12. GPT-6 Astra (openai.com)
    2279 points by kibae 17 days ago | 2081 comments
  13. Ask HN: Anyone else feeling uneasy with the latest developments in AI?
    17 points by sensitivekt9q3 13 days ago | 25 comments
  14. Show HN: I made an 8 bit game that teaches beginners to pwn basic C programs (github.com)
    2 points by udbhavs 5 days ago | discuss
  15. OpenAI's AGI number came from a harness, not the model (thenextweb.com)
    3 points by mjshashank 12 days ago | 1 comments
  16. Why are AI agents lying, cheating and coordinating? (yoshuabengio.org)
    657 points by jonifico 8 days ago | 695 comments
  17. Can you tell which images are AI-generated? (slop-sense.labtoagi.com)
    103 points by hckr78 about 19 hours ago | 76 comments
  18. Why are AI leaders calling for a slow down? [audio] (www.cbc.ca)
    2 points by BiraIgnacio about 16 hours ago | 1 comments
  19. OpenAI O3 breakthrough high score on ARC-AGI-PUB (arcprize.org)
    1724 points by maurycy almost 2 years ago | 1755 comments
  20. ARC-AGI-3 (arcprize.org)
    498 points by lairv 6 months ago | 368 comments
  21. ARC-AGI without pretraining (iliao2345.github.io)
    351 points by georgehill over 1 year ago | 121 comments
  22. Arc-AGI-2 and ARC Prize 2025 (arcprize.org)
    188 points by gkamradt over 1 year ago | 101 comments
  23. I got the highest score on ARC-AGI again swapping Python for English (jeremyberman.substack.com)
    178 points by freediver about 1 year ago | 131 comments
  24. ARC-AGI Leaderboard (arcprize.org)
    170 points by rzk about 2 months ago | 147 comments
  25. Schema Harness Achieves ~99% on Arc‑AGI‑3 Public (schema-harness.github.io)
    131 points by jasondavies 2 months ago | 83 comments
  26. Day 1 of ARC-AGI-3 (www.symbolica.ai)
    90 points by lairv 6 months ago | 76 comments
  27. Nvidia AVO scores 100% on the ARC-AGI-3 interactive reasoning benchmark (twitter.com)
    71 points by dsrtslnd23 about 1 month ago | 41 comments
  28. O3 "Arc AGI" Postmortem (garymarcus.substack.com)
    44 points by signa11 over 1 year ago | 16 comments
  29. Enabling two settings tripled our scores on the ARC-AGI-3 benchmark (openai.com)
    38 points by tedsanders about 2 months ago | 5 comments
  30. Samsung released a 7M model that achieved 45% on ARC-AGI-1 (arxiv.org)
    34 points by chintler 12 months ago | 12 comments
  31. Hidden drivers of HRM's performance on ARC-AGI (arcprize.org)
    31 points by veryluckyxyz 12 months ago | 2 comments
  32. GPT-5.5 – No ARC-AGI-3 scores
    25 points by AG25 5 months ago | 3 comments
  33. Poetiq shatters ARC-AGI 2 benchmark at half the cost (poetiq.ai)
    25 points by flavio87 10 months ago | 3 comments
  34. Tripling an LLM's ARC-AGI-2 score with code evolution (imbue.com)
    17 points by danielmewes 7 months ago | 2 comments
  35. Grok 4 (Thinking) achieves new SOTA on ARC-AGI-2 (X) (twitter.com)
    17 points by mellosouls about 1 year ago | discuss
  36. Nvidia AVO achieves 100% in ARC-AGI-3 (developer.nvidia.com)
    13 points by rochansinha about 1 month ago | 2 comments
  37. ARC-AGI 2: Poetiq reaches 75% at less $8 / task (twitter.com)
    13 points by dimtion 9 months ago | 1 comments
  38. I beat Grok 4 on ARC-AGI-2 using a CPU-only symbolic engine (18.1% score) (github.com)
    11 points by kofdai 7 months ago | 6 comments
  39. Playable preview of ARC-AGI-3 (three.arcprize.org)
    11 points by dcre about 1 year ago | 2 comments
  40. Arc‑AGI Without Pretraining (twitter.com)
    10 points by E-Reverance over 1 year ago | 1 comments
  41. Arc AGI-3 100% solved with a skill (twitter.com)
    10 points by rochansinha about 1 month ago | discuss
  42. ARC-AGI-3 benchmark is out now (arcprize.org)
    9 points by pretext 6 months ago | 2 comments
  43. Show HN: ARC-AGI-3 Toolkit (docs.arcprize.org)
    9 points by gkamradt 8 months ago | 1 comments
  44. ARC-AGI-2 human baseline surpassed (www.lesswrong.com)
    9 points by hugetim 9 months ago | 1 comments
  45. ARC-AGI-3 [pdf] (arcprize.org)
    8 points by sshroot 6 months ago | 1 comments
  46. The Drivers of HRM's Performance on Arc-AGI (arcprize.org)
    8 points by artninja1988 about 1 year ago | discuss
  47. Agentic systems redraw the Pareto frontier on ARC-AGI (poetiq.ai)
    7 points by gkapur 10 months ago | 1 comments
  48. Analyzing o3 and o4-mini with ARC-AGI (arcprize.org)
    6 points by artninja1988 over 1 year ago | 1 comments