Tycho hits a perfect 100.00 RHAE on ARC-AGI-3 using 61% fewer actions than humans.

Tycho formalizes ARC-AGI-3 games as parameterized rendered deterministic Moore machines and has a coding agent build, test, repair, or bypass a free-form executable hypothesis during play. Across all 25 public games under matched budgets, actor-requested delegation scored 88.49 mean RHAE; with that policy GPT-5.6 Sol and Opus 5 both hit 100.00 and completed all 183 levels. The instructive negative: automatic repair after verification failures produced simulators that matched observed transitions far better but reached only 83.07 RHAE. Reproducing dynamics isn't the same as identifying the objective.