Thinking

Short working notes by Shunyu Wu on physical intelligence, learning for physical systems, and control.

Short notes on questions I keep returning to. Each note includes its date and local time zone.

Scaling and physical generalization

I keep wondering whether scaling can give us physical generalization. Models can share representations and solvers, but different dynamics may still require different control laws. Perhaps a model can generalize by recognizing the regime and applying local rules, without discovering a unified physical theory. What would convince me is reliable control across unfamiliar systems without extensive reference trajectories or retraining. That would suggest a general mechanism for physical reasoning.

Ithaca, New York

Emergence and physical intelligence

I do not expect physical intelligence to show the emergence reported for large language models. If a mechanism for wide transfer exists, it should come from structure rather than from parameter count, because the laws that govern a physical system have always turned out to be short.