François Chollet @fchollet

What is a way to test human-level generality in artificial intelligence? "The meta-benchmark of being able to pass ARC-AGI-(n+1) immediately upon release" [引用 @dylantmoore]: @Jabaluck @DAcemogluMIT The meta-benchmark of being able to pass ARC-AGI-(n+1) immediately upon release. Though presumably that won't last forever.

• What happened to 2024's BABA is AI paper?2026-10-09