George Hotz

It's a Snapdragon 845. Okay. So this is using the GPU. So the GPU is an Adreno GPU. There's like different things. There's a really good Microsoft paper that talks about like mobile GPUs and why they're different from desktop GPUs. One of the big things is in a desktop GPU, you can use buffers. On a mobile GPU, image textures are a lot faster.

I want to be able to leverage it in a way that it's completely generic, right? So there's a lot of this. Xiaomi has a pretty good open source library for mobile GPUs called Mace, where they can generate, where they have these kernels, but they're all hand-coded, right? So that's great if you're doing three by three confs. That's great if you're doing dense map models.

I want to be able to leverage it in a way that it's completely generic, right? So there's a lot of this. Xiaomi has a pretty good open source library for mobile GPUs called Mace, where they can generate, where they have these kernels, but they're all hand-coded, right? So that's great if you're doing three by three confs. That's great if you're doing dense map models.

I want to be able to leverage it in a way that it's completely generic, right? So there's a lot of this. Xiaomi has a pretty good open source library for mobile GPUs called Mace, where they can generate, where they have these kernels, but they're all hand-coded, right? So that's great if you're doing three by three confs. That's great if you're doing dense map models.

But the minute you go off the beaten path a tiny bit, well, your performance is nothing.

But the minute you go off the beaten path a tiny bit, well, your performance is nothing.

But the minute you go off the beaten path a tiny bit, well, your performance is nothing.

You know, almost no one talks about FSD anymore, and even less people talk about OpenPilot. We've solved the problem. Like, we solved it years ago.

You know, almost no one talks about FSD anymore, and even less people talk about OpenPilot. We've solved the problem. Like, we solved it years ago.

You know, almost no one talks about FSD anymore, and even less people talk about OpenPilot. We've solved the problem. Like, we solved it years ago.

Solving means how do you build a model that outputs a human policy for driving? How do you build a model that, given a reasonable set of sensors, outputs a human policy for driving? So you have companies like Waymo and Cruise, which are hand-coding these things that are like quasi-human policies.

Solving means how do you build a model that outputs a human policy for driving? How do you build a model that, given a reasonable set of sensors, outputs a human policy for driving? So you have companies like Waymo and Cruise, which are hand-coding these things that are like quasi-human policies.

Solving means how do you build a model that outputs a human policy for driving? How do you build a model that, given a reasonable set of sensors, outputs a human policy for driving? So you have companies like Waymo and Cruise, which are hand-coding these things that are like quasi-human policies.

Then you have Tesla, and maybe even to more of an extent, Coma, asking, okay, how do we just learn the human policy from data? The big thing that we're doing now, and we just put it out on Twitter, at the beginning of Comma, we published a paper called Learning a Driving Simulator. And the way this thing worked was it was an autoencoder and then an RNN in the middle. Right.

Then you have Tesla, and maybe even to more of an extent, Coma, asking, okay, how do we just learn the human policy from data? The big thing that we're doing now, and we just put it out on Twitter, at the beginning of Comma, we published a paper called Learning a Driving Simulator. And the way this thing worked was it was an autoencoder and then an RNN in the middle. Right.

Then you have Tesla, and maybe even to more of an extent, Coma, asking, okay, how do we just learn the human policy from data? The big thing that we're doing now, and we just put it out on Twitter, at the beginning of Comma, we published a paper called Learning a Driving Simulator. And the way this thing worked was it was an autoencoder and then an RNN in the middle. Right.

You take an auto encoder, you compress the picture, you use an RNN, predict the next state. And these things were, you know, it was a laughably bad simulator, right? This is 2015 era machine learning technology. Today we have VQVAE and transformers. We're building drive GPT basically.

You take an auto encoder, you compress the picture, you use an RNN, predict the next state. And these things were, you know, it was a laughably bad simulator, right? This is 2015 era machine learning technology. Today we have VQVAE and transformers. We're building drive GPT basically.

You take an auto encoder, you compress the picture, you use an RNN, predict the next state. And these things were, you know, it was a laughably bad simulator, right? This is 2015 era machine learning technology. Today we have VQVAE and transformers. We're building drive GPT basically.

It's trained on all the driving data to predict the next frame.