John Collison

There are still large, high-capacity off-board models.

There's the Waymo driver, there is the simulator, and then there's the critic.

And those then get distilled into smaller models that you can run inference on faster.

So the Waymo driver becomes the backbone, the male backbone of what's in the car.

The simulator, of course, is what powers our synthetic generative environment that can run on the cloud for training and for evaluation in close-up of the system.

And the critic... Sorry, does the simulator ever run locally?

No.

No, it doesn't.

However, what I think is interesting, in a way,

the way the decoder works the way the model works if you think about the generative task in the simulator of kind of creating those realistic worlds and how you know other people behave how you know cars pedestrians cyclists in order and the task that you have to solve on the car in real time there is this ta you know a fundamental shared

capability of understanding how these objects relate to each other and predicting what they might do in the future if you are running on the car and then generating those, you know, some sampling those probabilistic behaviors in a simulator.

So it's different models, but there is, you know, this is why the shared foundation model is

able to power both.

And similarly, if you think about the critic, like the job of the critic is to find interesting events and then, you know, be opinionated about what's good behavior and what's bad behavior.

Similar fundamental understanding, right?

If you're running, you know, inference on the car, you still have to like figure out which of the multiple hypotheses of these future worlds

you want to take action to steer it towards.

So you start with the foundation model.

Then you specialize in fine-tune to the off-board model.

Those are the teachers.