ARC-AGI-3 - Hackdot

Re:ARC-AGI-3 by ball_of_lint on Wednesday March 25, 2026 @04:34PM (#47522815)

solved first try with 577 actions, not trying hard to optimize for low action count.

[ Parent | on HN ]

Re:ARC-AGI-3 by programjames on Wednesday March 25, 2026 @04:48PM (#47523006)

I think that is the tester's action count. Either that or we coincidentally got the exact same count.

[ Parent | on HN ]

Re:ARC-AGI-3 by rtrgrd on Thursday March 26, 2026 @06:47AM (#47528848)

I also see 577, so must be human testers action count. Also watched the replay, the solve seems different to mine.

[ Parent | on HN ]