Francois Chollet: ARC-AGI-3 Previewed — Measuring Agency

ARC-AGI-3 makes a fundamental shift: instead of static puzzle-solving, it measures agency — a model's capacity to set and pursue goals independently in interactive environments. Public release March 25. If frontier models still fail at ARC-AGI-3 despite succeeding at coding tasks, it validates Chollet's thesis that current LLMs lack genuine generalization. This will become the standard for measuring whether "agentic" AI is real or orchestrated pattern-matching. ARC Prize