30 homes. No extra training. 56% full-task success.
The number looks like a model win. It is not.
The robot is carrying a human demonstration graph into rooms it has never seen. When that graph is wrong, you do not get a clean miss.
You get a half-made bed that looks done.
If you ship this without a completion verifier and a stop condition, you are betting the house on memory you cannot inspect.
30 unseen homes. Zero environment specific training.
@Figure_robot’s Helix 2.5 increased zero shot success from 9% to 56% with Index pretraining.
Figure keeps building.
The DAO holds the exposure.
Sep 19, 2026 · 1:57 PM UTC
16