Andrew Barry on Why Dexterity Is the Next Breakthrough in Physical AI

**Andrew Barry** (0:00)
This spot we're starting out is Dexterous Robots. If you can solve dexterity, there's just a huge number of things you can do.
I have worked on many, many robots in my career that have been very difficult to commercialize. And so when we started the company, we said, we're going to go out and make sure that our goals and our benchmarks are real tasks people are paying money for today. We have built a handheld device that allows us to do data capture very inexpensively compared to many other techniques. And we have scaled that.

**Brian Heater** (0:31)
How cognizant are people of the fact that they're training an automation system that may essentially do that task in the future?

**Andrew Barry** (0:39)
Yeah, we're very upfront with people about it.
We had taught the robot to pick this baggie up with the left hand and then like shake it. It picked the baggie up with the right hand and shook it. And we're like, we never taught it to do that. And we all just didn't believe it.

**Brian Heater** (1:08)
Hello, and welcome to Automated. I'm Brian Heater, the Managing Editor at the Association for Advancing Automation. I'm excited to bring you this episode from our trip to Boston back in April. The conversation was recorded shortly after Generalist debuted their Gen 1 model. We were extremely impressed with the demos and invited co-founder CTO and Boston resident Andy Barry to sit down for a chat.
It got a lot of really great insight into physical AI and I think you will as well. If you're enjoying the show, don't forget to like and subscribe. Check out the newsletter over at automated.fm. And with that, here's Andy Barry of Generalist. You know, we talk a lot about what's coming up next in automation on the show, but if you really want to see the future motion, you've got to be there in person. Automate 2026 is where the world's leading innovators, builders and dreamers come together to show you what's possible. Robots, AI., machine vision, motion control, you name it, all automation under one roof. And as part of Automate this year, the Humanoid Robot Forum brings together leaders, engineers and researchers for a two day deep dive into the real world development, deployment and commercialization of humanoid robotics. Register for free at automateshow.com to join us in Chicago. June 22nd through the 25th, we will see you there.
So this is probably wildly inappropriate. So I'm going to start by paraphrasing your co-founder, Pete, in a blog post that went up, I think within the last day or two.
But he was pointing out the fact, he said, we've never referred to our models as either VLAs or world models and I'm wondering why that's important.

**Andrew Barry** (2:52)
Yeah, that's a great question. So fundamentally, we think of our models as something different. Right. And that's because they are trained from scratch, not quite, right? Ninety-nine percent of the parameters in the model is from scratch.

**Brian Heater** (3:07)
Why is there always a one percent?

**Andrew Barry** (3:09)
Yeah, that's a great question. I mean, we do the thing that makes the model work as well as we could possibly make it work.

**Brian Heater** (3:14)
Yeah.

**Andrew Barry** (3:14)
Right. And so in that case, a while ago, before we had a huge amount of data, we tried getting rid of the one percent and it caused a performance regression. And we haven't redone that experiment. So I suspect that we could go to 100 percent at this point.
But we like to be honest.

**Brian Heater** (3:40)
Yeah. You would be going one percent. That would be like a purely branding thing, I suspect, in order to say that. And in Roblox, you do say 99 percent because everything is kind of like 99.999 percent at this point. So actually, it's funny because this was something that actually came up.
I'm assuming this is this way or after our conversation with Russ, but I was talking to him a little bit about Pete's comments as far as starting from scratch and whether or not that was necessary. I wanted to get his take. And I'm curious why that is so important because that sounds like a pretty daunting undertaking.

**Andrew Barry** (4:20)
Yeah, we didn't set out and say, we're going to do a model from scratch because being from scratch is really important.
The reason we're doing it is that with such a large dataset, you can do it from scratch. You don't need the crutch of a VLA or some other set of parameters that are chosen for other reasons. So if you have a large enough dataset, you can just basically in some ways fill up all of the parameters in the model with exactly the thing you want to do. And there's a lot of evidence from the rest of the field, and we see it too, that gives you just better performance.