Hackernews posts about ARC-AGI-2

1. Tripling an LLM's ARC-AGI-2 score with code evolution (imbue.com)
   17 points by danielmewes 17 days ago | 2 comments
2. I beat Grok 4 on ARC-AGI-2 using a CPU-only symbolic engine (18.1% score) (github.com)
   11 points by kofdai 19 days ago | 6 comments
3. Saturated ARC-AGI-2 (www.ycombinator.com)
   3 points by eightnoteight 21 days ago | 1 comments
4. Noemon: ARC-AGI-2 top score at a fraction of the cost (twitter.com)
   2 points by markerbrod 10 days ago | 1 comments
5. Open Source Models Score Low on ARC-AGI-2 Reasoning Benchmark (xcancel.com)
   2 points by ironyman 13 days ago | discuss
6. Show HN: Solving ARC AGI 2 with interleaved thinking and stateful IPython REPL (github.com)
   2 points by steinsgate 27 days ago | discuss
7. AI Broke ARC-AGI-2 at 84.6% – But the Key Trick Is from 1972 (ai.gopubby.com)
   1 points by Aedelon 17 days ago | discuss
8. Pure LLMs Score 0% on ARC-AGI-2. Why the Third Wave of AI Looks Like the First (ai.gopubby.com)
   1 points by Aedelon 17 days ago | discuss
9. Arc-AGI-2 and ARC Prize 2025 (arcprize.org)
   188 points by gkamradt 12 months ago | 101 comments
10. Poetiq shatters ARC-AGI 2 benchmark at half the cost (poetiq.ai)
    25 points by flavio87 3 months ago | 3 comments
11. Grok 4 (Thinking) achieves new SOTA on ARC-AGI-2 (X) (twitter.com)
    17 points by mellosouls 8 months ago | discuss
12. ARC-AGI 2: Poetiq reaches 75% at less $8 / task (twitter.com)
    13 points by dimtion 3 months ago | 1 comments
13. ARC-AGI-2 human baseline surpassed (www.lesswrong.com)
    9 points by hugetim 3 months ago | 1 comments
14. ARC-AGI 2025: A research review (lewish.io)
    6 points by kordlessagain 9 months ago | discuss
15. [ARC-AGI-2 SoTA] Efficient Evolutionary Program Synthesis (ctpang.substack.com)
    5 points by georgehill 6 months ago | discuss
16. Gemini achieving "incredible numbers" (84.6%) on ARC-AGI-2 (Chollet) (twitter.com)
    4 points by marojejian about 1 month ago | 2 comments
17. Arc AGI 2025 (arcprize.org)
    4 points by artninja1988 12 months ago | 2 comments
18. Poetiq achieves 75% at under $8 / problem using GPT-5.2 X-High on ARC-AGI-2 (poetiq.ai)
    4 points by mromanuk 3 months ago | discuss
19. Visual Reasoning and Tool Use Double GPT-5's Arc-AGI-2 Success Rate (github.com)
    4 points by zoecarver 7 months ago | discuss
20. Claude Opus 4 sets new SOTA (8.6%) on ARC-AGI-2 (twitter.com)
    3 points by falcor84 10 months ago | discuss
21. Show HN: Significance-Hypothesis-Based-ARC-AGI-2-puzzle-solver (github.com)
    2 points by judahmeek 3 months ago | 1 comments
22. SotA ARC-AGI-2 Results with REPL Agents (www.symbolica.ai)
    2 points by tosh about 1 month ago | discuss
23. Show HN: We let GPT OSS 120B write and run Python and ARC AGI 2 jumped 4x (github.com)
    2 points by steinsgate about 1 month ago | discuss
24. Hawk from Movement Labs clocks in at 22.5% on ARC-AGI-2 (movementlabs.ai)
    2 points by movementlabsAI 3 months ago | discuss
25. Has ARC AGI 2 been solved? (www.kaggle.com)
    2 points by AgiIsHere 6 months ago | discuss
26. Visual Reasoning and Tool Use Double GPT-5's Arc-AGI-2 Success Rate (github.com)
    2 points by zoecarver 7 months ago | discuss
27. How to beat ARC-AGI-2 (lewish.io)
    2 points by 1ewish 8 months ago | discuss
28. Arc-AGI-2: A New Challenge for Frontier AI Reasoning Systems (arcprize.org)
    2 points by meetpateltech 10 months ago | discuss
29. Arc-AGI-2 Preview (arcprize.org)
    2 points by georgehill about 1 year ago | discuss
30. Show HN: Topas-DSPL – A 15M param AI that solves hard reasoning tasks(ARC-AGI-2) (github.com)
    1 points by Doug_Bitterbot 3 months ago | 2 comments
31. Agentic coding improves ARC AGI 2 performance across models (pivotools.github.io)
    1 points by steinsgate about 1 month ago | 1 comments
32. Poetiq achieves 75% on ARC AGI 2 using GPT5.2 X-High (twitter.com)
    1 points by aurareturn 3 months ago | 1 comments
33. [ARC-AGI-2 SoTA] Efficient Evolutionary Program Synthesis (ctpang.substack.com)
    1 points by frozenseven 6 months ago | 1 comments
34. Hawk from Movement Labs clocks in at 22.5% on ARC-AGI-2 – Launched 40 min ago (movementlabs.ai)
    1 points by movementlabsAI 3 months ago | discuss
35. Arc-AGI 2025: A research review (lewish.io)
    1 points by georgehill 11 months ago | discuss
36. ARC-AGI-2: Second Benchmark for AGI Released (github.com)
    1 points by outrun86 12 months ago | discuss
37. Show HN: Testing hypotheses through prediction is the next step towards AGI (github.com)
    3 points by judahmeek 3 months ago | 4 comments
38. I fed all the comments from "OpenAI O3 breakthrough" HT post to o1 pro mode
    1 points by popthetopnow about 1 year ago | 1 comments