Hacker Newsnew | past | comments | ask | show | jobs | submitlogin

ARC-AGI 1 and 2 are spatial reasoning benchmarks. ARC-AGI 3 is advanced spatial reasoning with agentic flavor.

They're adversarial benchmarks - they intentionally hit the weak point of existing LLMs. Not "AGI complete" by any means. But not useless either.



This is a point I wish more people would recognise.




Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: