Ashok Elluswamy -- Director, Autopilot Software

Yeah. Like you mentioned, the training has both kind of large models, also get trained quicker. But in the end, we still got to take which models are performing better. So, the validation network to picking the models because as mentioned this pretty large.

We had to drive a lot of miles going close to. We do have simulation and other ways to get those metrics. Those two help, but in the end, that's a big bottleneck. That's why we're not trying to compete constraint alone.

And there's other access of scaling as well, which is a data figuring out which data is more useful. Um, that is an important task. And we're focusing on that.