Commentary on X
@tonyzzhao Good luck to http://Sunday.AI. One of many steps on the road to a world of physical AI created abundance.
@tonyzzhao This one single Solve will get the data flywheel going, Tesla autopilot style
@tonyzzhao Soo how can I get one to beta test? I’m all in.
Quantitatively, we measure the generalization gap as the difference between in-domain and out-of-domain performance. As we scale up pretraining, the gap falls sharply. This makes in-house performance a reliable predictor of performance in the wild.