This is cool, but they are still not going about it the right way.

Its much easier to build everything into the compressed latent space of physical objects and how they move, and operate from there.

Everyone jumped on the end-2-end bandwagon, which then locks you into the input to your driving model being vision, which means that you have to have things like genie to generate vision data, which is wasteful.

The article is about using the world model to generate simulations, not for controlling the vehicle.

This is cool, but they are still not going about it the right way.

This is legit hilarious to read from some random HN account.