What changed
NVIDIA released Cosmos 3 Super and Nano as downloadable physical-AI models built on a mixture-of-transformers design. The family combines vision reasoning with generation across text, image, video, ambient sound and action; an Edge variant was announced for later.
Why it matters
Physical-AI stacks are converging: one model can understand a scene, simulate possible futures and generate action trajectories instead of passing work through isolated perception and policy systems.
What to do
Evaluate each function separately—perception, simulation and action—and require simulator or hardware-in-the-loop verification before treating generated actions as safe.
Caveat
NVIDIA calls the family fully open, but deployment economics, licence obligations and performance outside NVIDIA's harnesses still require independent review.