Hacker Newsnew | past | comments | ask | show | jobs | submitlogin
ARC-AGI-3 Preview (arcprize.org)
5 points by blixt 4 months ago | hide | past | favorite | 2 comments


There's also the announcement YouTube here: https://www.youtube.com/watch?v=3T4OwBp6d90


Interesting because games are exactly the kinds of RL environments that models can effectively learn - but the catch is that they must do this learning on the fly in test-time. Very exciting to see this.




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

Search: