Peter Ludwig

speaker

145 appearances 1 recordings 1 series first heard Jul 2026 last heard 21 Jul

Peter Ludwig’s voice in public audio — every appearance, attributed to the second.

Trend

recordings per month · last 12 months

Recordings per month over the last 12 months — 1 in all, peaking in Jul 2026 with 1.

Appearances

newest first · ▶ plays the moment

The a16z Show · Why Physical AI Is the Next Frontier | Applied Intuition · 21 Jul 2026 podcast

almost think about like the way CGI is done.

So that's sort of on the far end of physics-based simulation.

And then the opposite end is purely neural simulation.

But within that spectrum, there's many different things you can do that are each useful in their own right.

And so one of those things is a Gaussian-based simulation, right, where you have effectively a representation of the real world that has a...

a 3D representation, and that 3D representation is consistent, meaning that if you, let's say, have some reference point, let's say a camera, and that camera moves within that 3D world, because the Gaussian is actually representing the 3D geometry of that world, you'll actually get very high-quality output from that.

There's a lot of value in that, and that's, let's say, one type of world model.

But when you go further on that spectrum, really into neural simulation, then you get into these where you're actually generating the video feeds.

You can think of a neural network that's actually outputting a video, what's actually coming out of the neurons of that.

And that can be reactive, which gives you some very interesting properties.

However, you're not guaranteed in that reactivity that it's accurate, right?

And now it's a question of, well, how can I align this simulation, this world model with the real world and the way that the real world would actually react?

And if you have perfect alignment between the real world and the world model, I mean, I think you've just sort of solved the universe roughly, right?

That's a possibly difficult problem.

But as we make progress towards that, it makes training physical AI models much easier because you can do more of that in simulation.

But the hardest part, though, is we're always talking about performance, right?

I like to say the labs, they have it easy because they can make models that are trillions of parameters and those models can be super slow and that's fine.

But we don't have that luxury in physically high.

We deal in real time, like the actual clock real time.

And so we have so many milliseconds before we have to do something.

Showing 81–100 of 145 · page 5 of 8