What is your professional background and how did you come to start a robotics company and earn what might be the coolest title in all of business?

Yeah.

Well, I mean i've been excited about robots my whole career and i've been on really a career long mission to understand how.

How animals move the way they do and how we can make machines that can reproduce that behavior how we can build machines that can.

go where people go and do useful things in human spaces.

And I mean, that's pretty early.

I chose robotics, and I went to Carnegie Mellon so I could join the robotics club and go win the walking machine competition.

So that leads me to ask, you know, tell us a little more about, you know, where is Digit deployed? What kinds of tasks is the robot doing and likely to do in the future? Where do you see the robot evolving?

Right.

So the world models, as I understand it, are, you know, can you model an entire w- warehouse and all of the physics of all of the objects inside of it so that then simulations of these robots can go practice in the world model without breaking things in the real world, and, you know, compressed so you can do a, you know, a million iterations within days and computationally things like that? But there's always a massive sim to real gap.

Things aren't simulated perfectly.

And then, you know, as you pick up something in the real world, and there, there's wave dynamics, and there's condensation on the glass, and the dynamics of the robot are not perfectly modeled, all these things are still very, very difficult.

That takes real practice and real life with robots in order to do that.

... and where you think it will be in a year or two.

So today it's doing these sort of multipurpose workflows that are still reasonably well scoped, like picking up bins and totes and carrying them around.

And the reason we do that is because you need two arms to pick up big things.

Am I wrong?

Not yet.

It's actually quite different.

So language models, think of it like it's now becoming kind of a commodity like the Internet.

It's available to everybody.

It's this amazing rising tide.

But these language models are trained off of the entire data on the Internet.

Give us an idea of what the forward deploy looks like today and where you think it will be in a year or two.

Why do they all look like people? What's going on there?

Sure.

Well, I can't speak to others.

I know that many of them are just copying the way a person looks.

I know that many of them are making choices for their actuator designs that are very poor for actually physically interacting with the world.

I know that many of them are artificially choosing to say, "I need my shoulder and arm dimensions to be exactly human-like.

I need my waist width to be just like a person, and everything needs to fit, all the actuators need to fit as if this were a person in a suit." That's sort of what I think is, is unnecessary and, and actually, like, harmful, really, in trying to make a robot that's actually useful in the world.

Why do they have to look like people?