quick update on the Fable 5 / ARC-AGI-3 bet from last week. been collecting Fable 5 traces on arc-witness-envs since.
same env, same level. two abstraction altitudes.
opus 4.7's discovered rules sit at the surface: "agent navigates a grid; reach the target cell", and when that doesn't win, button-mash ACTION5 hoping it's a win trigger. trivial, layout-bound, doesn't transfer.
fable 5 names the actual mechanism: "the path partitions cells into regions; each star shares its region with exactly one same-color partner." that's the altitude where ARC rules actually live.
mechanism-level rules ARE the game. the mechanism-true traces go into the policy. the rest is noise.
full argument of what belongs in weights vs harness, and why HRM-style internalized loops matter for ARC-AGI-3: https://t.co/b0mPlvf0RW
Excited to cohost "Forecasting as a New Frontier of AI" with Haifeng & co. We have an incredible lineup of speakers, sponsors, and (soon) papers.
See you shortly in Korea!
excited to announce that I will be giving a spotlight talk at the Claude Code conference!
tune in to learn about how to build self-driving companies with AI (and a sneak peak at some the work we've been doing over at @fleet_ai)