Inside the Robot Data Factory: Mecka's Josh Gao on Sensorizing Humans to Train Robots

Robotics never got the internet's gift of free training data, so someone has to manufacture it. Josh Gao, founder and CEO of Mecka AI, runs one of the largest robot data factories, and he explains what that actually involves: custom baseball caps and tactile gloves because nothing off the shelf captures force, 100-gigabit upload lines to move hundreds of petabytes, and custom quality gates. Josh lays out the training recipe the industry is converging on (roughly a million hours of egocentric human data, tens of thousands of hours of robot data, and a few hours of in-domain teleop ) and why tactile and simulation data still have to enter the "data pot of soup." He argues the field is still orders of magnitude behind Tesla's FSD, which spent a decade on two degrees of freedom while a robot hand has dozens. His take: there won't be a single GPT-3 moment for robotics, but a steady unlock of commercial tasks, starting with constrained industrial work and ending, he hopes, with robots mining asteroids. Hosted by Sonya Huang, Sequoia Capital 0:00 – Introduction 1:46 – What Mecka is: pixels, actions and logic 2:45 – Is robot data economically feasible without the internet? 4:15 – Teaching robots about carbon life 5:27 – Cloud kitchens, stablecoins and the path to robotics 7:03 – Entering robotics with a fresh lens 8:45 – What egocentric data is and why Mecka bet on it 10:09 – The first pilot: aunties and uncles with a mobile app 10:42 – Force data and tactile gloves 11:55 – Inside the operations of a data factory 14:41 – Heat-mapping the taxonomy of human work 15:42 – Quality gates, fraud and the McDonald’s POV videos 17:44 – Earning a margin as a data intermediary 19:33 – Millions of hours vs. Tesla’s decade 20:55 – Why it isn’t binary: unlocking commercial tasks along the way 22:02 – Home data is plentiful; home robots are the hardest 23:24 – Useful robots can be deployed today 24:35 – When robotics gets an FSD-style flywheel 26:42 – Deployment diffusion and the modern systems integrator 28:21 – Favorite vertical robot categories; mining an asteroid 30:08 – The hardware slate: Waymo-fying people 30:55 – EgoVerse 32:04 – The data pot of soup: the converged training mix 33:54 – Move 37 for robotics: AlphaGo and Federer 36:02 – World models and the training mix 36:58 – Will scaling the current mix get us to the promised land? 39:05 – Will the AGI labs steamroll robotics? 40:50 – Sci-fi roots and the Kawasaki Corleo 42:44 – How many robots in a decade?

• 0:00Speaker 00

  There's an idea in science fiction that is when robotics and AI has ultimately fully generalized and solved all tasks that humans can do. The final frontier is going to be organic. Final frontier is going to be biological. And you see this in like Asimov, you see this in Ender's Game, you could even in Hitchhikers at the very end. The planet ultimately was this giant organic computer trying to process and understand what the meaning of life was or what the question was.

• 0:45Speaker 01

  Today, I'm delighted to have Josh from Mecca on the show. Josh is founder and CEO of Mecca AI, which is building a data and deployment company for robotics. I and I think the whole ecosystem think that robotics is about to enter a golden age. And unlike L L M's where we had so much free human data from the internet. Robotics is fundamentally data constrained. And I think your position in the ecosystem as the leading data factory to bring robotic data and physical data in distribution for models is just a really, really interesting perch. So I'm excited to use this conversation today to chat about how does egocentric data and data collection work in robotics?

• 1:28Speaker 01

  What are the actual operations and economics of operating a data factory? And your, your overall thoughts on robotics research and deployment? Thanks for joining the show.

• 1:36Speaker 00

  Amazing. Thanks for having me.

• 1:37Speaker 01

  Awesome. Maybe to start off, for those who aren't familiar, what is Mecca? And how are you looking to impact the world of robotics?

• 1:44Speaker 00

  So Mecca is, like you said, the data and deployment company for physical AI. What that means is today we create, we process, and ultimately we license a lot of the data that goes into training these robotics foundation models. The big problem across robotics is that we don't have the luxury of the cold start that L L M's had with the internet. Fundamentally, a lot of this robotics data is three things. It's pixels, it's actions, and it's logic. And so we don't have access to a large amount of this curated and processed and clean data to be able to then train these models to understand what it is to be in the physical world. So a lot of our job is pretty much to, one, create the different types of hardware, such as sensorizing and wearables for humans.

• 2:29Speaker 00

  The different operations to go and collect and partner with individual contributors, businesses, tasks across different environments, and then ultimately post-process and own the quality gates to make these data sets useful and teach robots about the world.

• 2:43Speaker 01

  Without having been given the benefits of a giant free, many trillions of tokens, maybe lots of trillions, trillions of trillions of tokens of internet corpus. Do you think that robotics, you know, having to pay for and operationally collect all the data that's going into the mix? Is it even a feasible challenge? Like, is it economically feasible without having had the gift of the internet?

• 3:08Speaker 00

  I think we, we still have the luxury of a lot of things that was given from the internet. So we aren't starting from zero ultimately. I think you can see it across L L M's and data across L L M's. Pre-training data was always driven by the labs largely across web crawlers, things like that. It didn't become a large market. Today in robotics, we do see pre-training as quite a large market. And, and that could be and taken in several forms. So that could be that we are teaching video models how to generate more physics grounded realities of what the world looks like. And we get to leverage all the work that has gone into V L M's and then different types of world models before to make that possible.

• 3:50Speaker 00

  Is it possible and scalable to get to that volume of data? I think that ultimately comes down to what commercial use case can you unlock? At which levels of scales of data? And our strong belief is along that journey that we will be able to unlock a lot of the simple pick and place tasks along the beginning of what we're creating. And towards that long tail, that is going to be many orders of magnitudes larger than it is today.

• 4:19Speaker 01

  I did a little homework for this. Your website is very whimsical. It says that you are teaching robots about carbon life. What, what does that mean?

• 4:26Speaker 00

  I actually made the, the website.

• 4:28Speaker 01

  I love it.

• 4:29Speaker 00

  Like, like the night before we did our, our first tweet announcement or something like that. There's an idea in science fiction that is when robotics and AI has ultimately fully generalized and solved all tasks that humans can do. The final frontier is going to be organic. Final frontier is going to be biological. And you see this in like Asimov, you see this in Ender's Game, you could even in Hitchhikers at the very end. The planet ultimately was this giant organic computer trying to process and understand what the meaning of life was or what the question was. And so I think in the same vein for us, that is the human brain runs on just 20 watts. We are, we are self-healing.

• 5:14Speaker 00

  And so along the journey of teaching and getting robots to fully generalize, we'll, we'll slowly show them what, what, what carbon life is made of.

• 5:23Speaker 01

  Love that. Okay, you come from an untraditional background for robotics. I think you started in the fintech world and the sneaker world, if I'm not mistaken. Tell me about how you and your co-founder found your way to robotics.

• 5:37Speaker 00

  It was quite an interesting journey. Yeah. So before this, I was building essentially a toast for Cloud kitchens. This meant we did everything from back of the house, order management. At one point in my fourth year of university, I was skipping class to go deploy and install kiosks into rural Rochester, New York, where we had to stay all nights replacing a lot of these different front of the houses for restaurants. My co-founder built a stablecoin. They ultimately sold to Coinbase, but he's been this very obsessive personality. He was a top thousand in four competitive games, including League of Legends. And I think a big part of what brought us together, one, we're both Canadian.

• 6:20Speaker 00

  And two is we have this big science fiction grounding. And so the belief ultimately was that payment was a hard and difficult problem. But whatever we worked on next, we wanted to be something that seemed exciting, that the future was going to be incredible. And robotics seemed like a great space to get into.

• 6:40Speaker 01

  I remember walking into your office and then immediately seeing those like mechatronic robots. And then the Kawasaki Qualeos on the wall. I, the inner child in you must be very happy about what you're doing these days.

• 6:51Speaker 00

  Yeah, absolutely.

• 6:52Speaker 01

  Coming from a non-robotics background, what do you think your advantages, advantages are in building this business? And where is it presented challenges?

• 7:00Speaker 00

  I think the advantages is when we entered the space, we had to go and do this full discovery process. We reached out to hundreds of folks that were in the space that we appreciated. We read every paper that we got our hands on. We went to visit the different robot labs. And what we saw in, in, in late 24 roughly, G P T was taking off. Robotics was still evolving from this traditional robotics era. And it seems obvious to us at the very least that data and compute would become very important across the industry. And so moving towards that, we got to read and see some of the papers like Ego 4D from a fresh lens and say, hey, there's about 4,000 hours of this human demonstration data.

• 7:45Speaker 00

  And when you actually went in to look at the data, you would realize some of the data sets would be daily life of folks like bowling, for example. There was very broad use cases and potential applications at the 4,000 hour scale.

• 8:01Speaker 00

  And so coming into, into that with like a fresh lens, we were able to, from a first principles approach, I'd say, have a general intuition of what would be important. And then iterate very closely with people that were much smarter than us, that had, that had different views of what the future would be. And be able to stay close to iterate on what the product would become.

• 8:22Speaker 01

  Yeah, interesting. It seems like robotics has just changed so quickly as a field that almost coming from the field can be an advantage and a disadvantage because people come from different eras of, you know, what's important in the training mix and things like that.

• 8:34Speaker 00

  Yeah.

• 8:35Speaker 01

  Maybe for our audience, just say a word on like, what is egocentric data? And I think you really started your company kind of making a bet behind it. Obviously it's much more distributed now, but what is egocentric data? Why did you decide to bet the company on it at the beginning?

• 8:49Speaker 00

  Egocentric data is pretty much video data from humans demonstrating and doing tasks from a first person POV. The high level idea was that from the gap of human data to robotics data, you could close a lot of the vision gap. Where robotics experience the world from POV, can we also show it what it is like to interact with the world from first person as well? Why we bet on it was, was pretty much when we explored the space. A lot of what we saw was robotics data at the time was tele-operation, which was humans controlling robots to do demonstrations. It was very hard to scale at the time. And from what we saw across GPT and a lot of the principles of scaling up,

• 9:35Speaker 00

  we had to find ways to scale up data much more significantly. And I think that some of our early intuitions were that humans and robots share a lot of similarities. Humanoids were just starting to take off. Humans and humanoids look the same. Why couldn't we turn humans into this fleet style learning that Tesla has? To be able to all contribute into understanding and ground the physics of the world.

• 10:01Speaker 01

  And so what does that look like? You're like mounting an iPhone on somebody's forehead and just letting them go about their day? Or what does that look like in practice?

• 10:08Speaker 00

  Yeah, when we first started, our very earliest pilot was we created a mobile app. We got all the Chinese aunties and uncles to record themselves cooking, cleaning, doing tasks. That obviously evolved a lot. We tried a number of things. We did UMI data, we did all the sorts at the beginning. And that's evolved quite a bit into all the custom hardware that we have to produce now. And all the different partnerships that we have to have across different industries. And ultimately, we're sensorizing humans. And that's the broader category.

• 10:38Speaker 01

  How important is it to get forced data from the sensors? Because one of the things I've always thought about is in self-driving, you don't really need forced data as much, right? Whereas with robotics, especially with manipulation, you really care about how hard am I squeezing that door handle or picking up that egg? And it seems to me that like video doesn't quite capture that. You might be able to approximate it, but doesn't really capture it. How important is capturing forced data and how do you think about getting that?

• 11:01Speaker 00

  I think some of the substitutes for forced data that we've seen would be approaches like wrist cameras currently across both humans and robots. And being able to see the contact time between the hand and the different objects that you interact with. That obviously is kind of a hacky way ultimately to get to understanding how much force in Newtons it takes to pull open a chair or twist a bottle cap. I think forced data will be incredibly important. It's actually one of the products that we've been building out in that when you iterate with many of different robotics foundation labs, you realize to close this gap, one, we have to create new hardware. So we've been developing things like gloves for humans to wear.

• 11:46Speaker 00

  And in those gloves, being able to collect the information in how much force it takes to do your daily life and different tasks.

• 11:53Speaker 01

  I'd love to just spend, spend a bit of time on the actual operations of a data factory. Because I think it is, there's so much money that's gone into the LLM data factories. There's so much money that is starting to be poured into, and I think will be poured into the robot data factories. And the way they work is just, you know, mysterious and intriguing to me. So I'd love to ask you a bit about the operations of it, if that's okay.

• 12:14Speaker 00

  Yeah, let's do it.

• 12:15Speaker 01

  Okay, so how does it work? Like if I am, you know, if I want to make an extra buck, do I just sign up on your website to start, you know, to put a camera on my, on my forehead and start sending you data? Or how does it work?

• 12:25Speaker 00

  So we actually have a lot of different approaches on the operator side. One would be we have a direct consumer approach. And so through direct mobile apps, can you sign up from anywhere in the world? Can you start contributing? Can you, can you register which profession you're in? And can you get streamed a sequence of tasks to do such as cleaning your bedroom, cooking your breakfast, cleaning up afterwards? This is a very lightweight approach to get that diversity ultimately of this pre-training data. The second approach that you have to get into is ultimately there is so much more beyond the home to collect. And so we had to build out a lot of this B two B engine and this muscle

• 13:08Speaker 00

  of being able to recruit businesses across this incredible taxonomy of all physical human work, which is across bakeries, it could be a PCB manufacturing line, everything to.

• 13:19Speaker 01

  Podcasting.

• 13:20Speaker 00

  Podcasting. There's not too much handwork.

• 13:23Speaker 01

  Trying to make a quick buck here.

• 13:26Speaker 00

  We should have equipped ourselves.

• 13:29Speaker 00

  And that's ultimately how contributors come into the mix. But the actual data engine for the data factory is so much more sophisticated and much more painful than folks can expect. And that is that a lot of the, the things that we have to distribute into the world didn't exist until we designed and produced this hardware. Even across tactile gloves is a fantastic example. There is nothing off the shelf that you can purchase and that you can wear and that reliably tells you how much force you are applying day to day and turn that into ready data sets for these different robotics foundation models. So we have to have that hardware iteration loop to have these three, four different product cycles, that engineering muscle to actually think and iterate what is going to be useful

• 14:14Speaker 00

  and then scale that production into the world. And that becomes this logistics of distributing into these thousands of homes, thousands of businesses to collect that, to upload that. We've had to set up these hundred gigabyte upload lines in a lot of the places that we operate in just to sustain the hundreds of petabytes of data that we have to deal with at this point. And then you have to process, you have to make sure your quality gates are incredible. And then all of the computer vision to make it useful ultimately.

• 14:47Speaker 01

  So let's say you decide, okay, in my training mix, there's not enough podcasters. There's not enough, you know, I don't know, donut bakers. Do you go, do you go out and literally go knock on doors of donut bakers then to sign them up to the platform? Or how does that work?

• 15:00Speaker 00

  Well, we'll generally track kind of like a heat map across different jobs, industries and ways we think about diversity. And across that heat map, if ultimately we think, oh, not enough Sonia's podcasting and we have to go get that, that's actually why we're here today. This is our, this is no secret method.

• 15:19Speaker 00

  That's why there's cameras everywhere.

• 15:22Speaker 01

  No, you're never automating me out of this. No, I'm kidding, please do. Okay, interesting. Like I've heard that, you know, that there's a lot of quality issues in robot data collection generally. And that a lot of the hours of robot data sample that get sent in end up not being accepted. Why is that? And what are you doing about that problem?

• 15:44Speaker 00

  This lesson came from even originally the different types of robot data. There have been these very large scale robot factories that have spun up from just large scale warehouses repeatedly doing tasks, trying to scale out teleoperation data. Some of the learnings there came from the research in that there is some threshold of diversity where you oversaturate how much robot data you need or how much data in general you need. Across human data, quality, you can imagine, is actually quite a bit of a moving target as we grow. The amount of edge cases that you have in the real world that you have to deal with are very extreme. And you will always see something new that you haven't seen.

• 16:27Speaker 00

  So for us, it's been about, can you think about the heuristics to be able to catch a lot of the different things as it's processed? Can you have the different engines to escalate very quickly? And ultimately, we will learn new things about quality and diversity that weren't true a week ago even. And so the nimbleness to move very quickly to create and adapt your engine to catch that.

• 16:49Speaker 01

  What's an example of something that you would catch?

• 16:52Speaker 00

  Well, I, I think, I think fraud is an, is an underestimated one across data industries in general. We're ultimately creating data that doesn't exist yet versus when you're filtering through the internet. And so when you are, you're, you're coming across very creative and.

• 17:08Speaker 01

  Like people are sending generated videos or what?

• 17:10Speaker 00

  Yeah, very creative people where I think at one point we have folks recording YouTube videos, like POV working at McDonald's and trying to submit that as, as contribution pretty much.

• 17:24Speaker 01

  Wow, never underestimate how entrepreneurial people can be. That's amazing.

• 17:29Speaker 00

  Yeah, very much. And, and so these have been like part of the painful lessons where yes, you have to create a lot of the gates, but ultimately you have to also be there where collection is happening. You have to go see how it's done. You have to figure out an incentive model that actually incentivizes people to create good contribution.

• 17:48Speaker 01

  How do you think about your right to earn a margin long term? And, you know, I can imagine a mecca competitor comes to Sony and says, Sony, I really want your podcast data. I could imagine that, you know, the margin that you're able to own as an intermediary ends up getting squeezed.

• 18:05Speaker 00

  I think the contributor amount in terms of the, the margin cost is actually not a large, not the largest factor at play here in terms of the end to end, making sure this data is useful. So even though that baseline is always going to be there and maybe it comes more and more uncompetitive, there will be ways to differentiate and make sure that your data is verifiably high quality at very large scale with the right hardware, the operations and the software. I think when we think about these products, ultimately it is that we do want to scale up and mature these products. And just like any, any product that begins to scale up, you want to optimize it. But over time, you may have different products that evolve.

• 18:49Speaker 00

  And so when you think about this egocentric data of podcasting as simply one of your SKUs and you then realize that there is going to be different types of data that are going to be important, such as maybe we move from the, the Chinese restaurant from the side of the road. Can we start moving into the Michelin star restaurants over time? Can you get more and more closer into what it means to be Federer than it means to be an average tennis player? So these products will change and, and how these products are created will also change.

• 19:23Speaker 01

  Really interesting. What scale of data has already been collected, do you think? And how much data do you think is going to be collected over the next few years?

• 19:31Speaker 00

  I think we finally entered a world where we are in millions of hours of data. And coming from the world where ego 4D of 4,000 hours two years ago, where we were then is a huge step up. But then comparatively, and you think about autonomous driving as an example, Tesla spent over a decade solving for two degrees of freedom ultimately of acceleration and direction, millions of cars on the road. They have a lot more than a few million hours of video data at this point. So relatively, we're still many orders of magnitudes away from where we have to be ultimately.

• 20:13Speaker 01

  So on one hand, that sounds like opportunity for you. That sounds like a lot of revenue for the robot data factories. On the other hand, as a, you know, as somebody that, you know, invests in the robot foundation models, I look at that and I say like, oh, shoot. Are we ever going to get to the promised land? Because I, I've, I've done the same math as you on like a car has two or three degrees of freedom. A robot has.

• 20:33Speaker 00

  Even dozens in the hand.

• 20:35Speaker 01

  Yeah, exactly. And so you combine that with like, you probably need forced data. And there's a way more, you know, it's just a way harder environment to operate in. And I get to like, you might need billions, trillions, quadrillions of hours.

• 20:53Speaker 01

  Is there even enough GDP in the world to support the cost to bring that in? Like, what do you think?

• 20:57Speaker 00

  I think it's about unlocking commercial use cases as we go. So it doesn't have to be so much binary in that, oh, one day we've unlocked robotics or not. It is going to be a slow creep up into the world. A great ways to get there is that with some of this base pyramid built up, where we are seeing the generalizations, we are seeing the scaling laws at play. That gives people the courage to scale up. And with that courage, can we, one, have some generalizability in some of these environments? Can we then also collect a lot of the in-domain, in-task data that closes that gap in post-training? So maybe I can collect data exactly from this room, exactly in this podcast demonstration,

• 21:42Speaker 00

  to actually close the gap of what is in a lot of cases, four nines of reliability in these, in these real-world environments.

• 21:49Speaker 01

  That's a helpful framework. So it's not about a binary of getting from zero to one. It's about, we're going to increasingly get, you know, robots that can do an increasing set of capabilities.

• 22:00Speaker 00

  And we will unlock a lot of tasks along the way.

• 22:02Speaker 01

  Yeah. One curiosity, though, is that, you know, the data that is most plentiful right now is like, it seems like home data, right? Just because like everyone, everyone can film that. It's pretty easy to get. But a robot in the home almost seems like one of the most difficult environments to deploy in. And so I'm curious, what applications do you think will hit first in robotics? Because like, where the data is most readily available seems almost the opposite of where robotics might be easiest to deploy.

• 22:29Speaker 00

  The, the home is going to be some of the environments that we have to be most diligent on by far. And a lot of these benchmarking and evals that have

• 22:40Speaker 00

  just started to mature across robotics, making sure that the, the robot doesn't fall on the baby in the homes, for example. I think the initial tasks will be much more constrained as we go along that spectrum in that very goal-oriented, where you can hill climb some of these tasks, where you have existing SOPs for what it means to do that job and that work.

• 23:02Speaker 01

  Like a laundry folding robot.

• 23:04Speaker 00

  It could be laundry folding, laundry folding, uh, we, we, we spent about a year and a half plus trying to solve. And I think it will absolutely get solved in the near term. A lot of these pick and place, these packaging tasks that you see on assembling lines that had to be manipulation bots, that couldn't be solved by traditional robotics. We will get there within the next year or two.

• 23:23Speaker 01

  It is a good transition to talk about deployment. I'd love to talk to you about, you know, robot deploy, deployment overall as a concept. You've said that useful robots can already be deployed today. Where do you think that's the case?

• 23:36Speaker 00

  I think people underestimate how diverse robotics can be. And if we, if we constrain ourselves to, to one, humanoids are incredibly popular. It will be a very popular terminal state of robotics as well. But beyond that, there are so many different form factors that exist in robotics today. You could look at different markets, even across hotels in China or Southeast Asia, for example, where there are robots that are doing services, that are doing cleaning, that are delivering from after your, your Uber Eats gets to the door, from the front desk to your hotel room door that exists. Many of these bots are widely deployed across the world today.

• 24:19Speaker 00

  They are just starting to get popularized across the US and North America. I think some of the first bots that have to get deployed will be even just the industrial cleaning bots, for example. A lot of like thematic robotics that are out there. And then slowly stepping up and up from there, where you start to solve early manipulation tasks along that spectrum, all the way up until we get to that humanoid solving out-of-the-box any task in the future.

• 24:46Speaker 01

  You mentioned Tesla and FSD earlier in this show. When do you think we're going to get to the point where there is a little bit of an FSD-like flywheel? And when we get to that point, how do you see your role as a company evolving?

• 24:59Speaker 00

  When we will get there,

• 25:03Speaker 00

  I think we're a while's away. But it'll be a slow transition. In that, when you are slowly solving some of the commercial tasks, you will also be able to finally get some of these flywheels. Then you can get some of the in-deployment data, where you get the failure cases, you get the correction data. That will be absolutely important in starting up this robot flywheel. How far that is depends on that spectrum. And across saturating different types of tasks and domains that aren't completed or solved for yet. So it's quite a while's away. When we do get there, the thing is, I, I, I believe that Mecca will look very different along that process.

• 25:46Speaker 00

  In that, one, we're, we're not fully subscribed to only egocentric data. We believe generally that a lot of different SKUs, the entire data soup is important. And so will we be producing the Michelin star data at, at some point in the future? Will we be teaching some sort of edge case about the real worlds that the robots haven't gotten to yet? If we believe that the world is incredibly vast and rich in detail, there's going to be no shortage of things to teach. And then even in that world, we do have this angle where we believe that Mecca will very much contribute to the deployment of robots. And so in, in some of these environments, in closing that gap of being able to do that task in that domain, in that environment,

• 26:28Speaker 00

  can we actually be the platform where we collect that domain data, we post-train, we help support the enterprises and white glove hold them into what it means to be in a world filled with robotics? We see Mecca maturing into that.

• 26:42Speaker 01

  I'd love to get your predictions on how you think deployment, the fusion is going to work out in the physical world. And maybe if I can analogize what's happened in the LLM world, there's like a few different ways that deploy codes have happened, right? There's vertical-specific application companies. There's the foundation model companies themselves that are scaling up, go to market. And then there's, you know, all these FDE, deploy co, service co, whatever you want to call them, you know, just armies of people helping enterprises adopt AI scale. Those are, seem like the broad vectors that are disseminating tokens across the economy. What do you think the analog will be in the physical world?

• 27:22Speaker 00

  We, we believe very much in both the vertical and the horizontal across robotics. So the full verticals that are very task-specific, all the way from hardware to models to data that they're tackling. We also believe, believe in an ecosystem where there's going to be very vast in different shapes and sizes of hardware of robotics. And there will be different types of open models that exist in the world. I think it will look something like a modern robotics version of a systems integrator that in a traditional version, you are installing the product, it's incredibly competitive, it has tight margins. There is now a world where you can actually install and help make that product become more data-driven and productive over time.

• 28:06Speaker 00

  So can you actually have the bot you installed last week do something that it didn't think was possible a few, a few days ago even? Can it help you start expanding the scope of what your business is capable of doing? And that's ultimately the milestone that we're, we're hoping to, to aim for.

• 28:22Speaker 01

  Okay, but you would tell me as an investor, now give me some investing advice. You, you invest in both the general and the vertical robots then?

• 28:28Speaker 00

  Yeah.

• 28:28Speaker 01

  What are your favorite vertical robot categories?

• 28:31Speaker 00

  I think the best ones will be the industrial bots to start. Those are, are, are, are going to be ones that already have a lot of traditional robotics in the mix. They're task-constrained, like we talked about.

• 28:42Speaker 01

  Like data center maintenance robots?

• 28:44Speaker 00

  Yeah, you just don't have to expect a baby to appear and have to think about that and not fall on it, for example. So the, the world is much more constrained than in the wild. Other categories we're excited about are, are, are just spaces that are even feasible and possible early on. And so some of the approaches in the hotels, for example, where you could actually start delivering from the front desk to the hotel rooms, be able to actually have some manipulation to hand off, are exciting to us. And then places that just humans were not capable of. A, a joke that we make in, in some of our all-hands in the company would be if one day

• 29:28Speaker 00

  Mecca was able to help deploy a robot that mines an asteroid, we've probably done a pretty good job. It's just, it's, it's a job and a task that completely doesn't exist, that humans can't do, that we have no idea how to do just yet. But it seems inevitable.

• 29:42Speaker 01

  Yeah, I love that. Reminds me of, you know, even, I'm not thinking interplanetary yet, but, you know, like, have you heard of Gecko Robotics? What they do to help maintain ships and things like that, I think it's really cool.

• 29:54Speaker 00

  Absolutely.

• 29:55Speaker 01

  Can you say a word on, and whatever you're willing to share publicly, the slate of hardware that you've developed and where, where the labs currently are most interested in, in collecting bespoke data?

• 30:06Speaker 00

  Some of the iteration came from when we started with the mobile app. We quickly were able to scale that. There were a lot of virtues in that product. The downsides ultimately were you don't get as much rich information about the world as you could have. And so some of the things that we had to develop very early on were things like waymofying people ultimately. And in this sensorization, can you build things like these baseball caps that are equipped with different cameras and sensors? We build a central hub that then connects to all these different accessories, such as the tactile gloves, external cameras and more, all of which is trying to capture how do you interact with the world on a day-to-day?

• 30:50Speaker 00

  And hopefully be able to clone that behavior.

• 30:53Speaker 01

  Interesting. What is Egoverse?

• 30:56Speaker 00

  Egoverse, so Professor Dan Faye, Ryan Simmer, these are some of the earliest cohorts of researchers that believed in egocentric data. We had the privilege to be an early contributor in that consortium ultimately of different folks that think scaling up human data would be important for robotics. And so, one, we created and contributed a large amount of different types of egocentric data across different businesses, industries, home environments. We shared all of the action trajectory data, so all of the post-processing, the computer vision, and the quality gates. And we contribute all the platform and web tooling, pretty much.

• 31:40Speaker 00

  So the data loading, the infrastructure. And so it is ultimately going to be, to to repeats their vision on this, is ideally, we can bring together a lot of the robotics industry because hopefully we can lift up everybody in this wave and share the tooling, the data, and the lessons just because we are so far behind as an industry to get there.

• 32:02Speaker 01

  Is it fair to say that the robotics industry has kind of converged on a training data mix that is, you know, internet-scale data from YouTube and the like, plus a bunch of egocentric data, plus Umi, and then plus Telop? And like, maybe there was like a triangle of like amount of data on each. I think Jim Phan had like a really nice visual on this at a Sequoia event. Is that kind of like the mix that you see and then amongst your customers? Has everybody kind of converged on a very, very similar mix?

• 32:32Speaker 00

  It's fun to see that even a year ago, many folks would argue and say, oh, no, it's only Umi data that's going to work. It's only egocentric data that's going to work. And you slowly realize, to your point, all of this is essentially a data pot of soup. And in that pot of soup, that all the ingredients are going to be important at some point. I think what we're seeing is a convergence across what that recipe might be today. And that does look like some version of a million hours of human data across egocentric and different, different types of modalities. Some tens of thousands of hours of Umi data, and then some last mile teleoperation data

• 33:15Speaker 00

  and in-domain in distribution data in just a couple hours even of that demonstration. I think we are seeing that. But over time, and why we don't subscribe aggressively to even one religion here is that things like tactile data haven't even entered the mix yet. And if there is this belief that these, these models ultimately will need to learn how much force it takes to apply towards the door handle, for example, these will have to come into the data pot of soup. Simulation will come into the data pot of soup, and they all will be important to converge on.

• 33:52Speaker 01

  One of the, I guess, objections that I hear most frequently to, to the types of data being collected are, you know, you could watch millions of hours of tennis data, and you still wouldn't know how to beat Roger Federer, right? And I'm curious what you think of that and what it means for where we might be headed in terms of the way robots learn.

• 34:14Speaker 00

  I love the analogy of AlphaGo ultimately. When you talk about robots playing tennis, you got to talk about robots playing Go. And I think with Lee Soh-Dole and all the work that DeepMind did, at the very beginning, it was large-scale behavior cloning of different experts playing Go. Then the next step was the self-play version of with the rules of the game, can you ultimately simulate all the different ways until you come up with the magic of move 37 ultimately?

• 34:48Speaker 00

  Which was so out of scope of what humans could have thought in that moment on the go. For us, though, in our case of robotics, for Go, the rules of the game are the, is the entire circumference of the world that you will operate in. In robotics, you have the incredible rich detail that the, that the physical world has, and we ultimately don't have a world simulator that can recreate that today. And so to close that gap, a lot of the egocentric data today is to, one, help us ground the basic physics and the basic behavior cloning that you have to get to.

• 35:29Speaker 00

  It is also contributing to creating what this world simulator might look like. And then somewhere along the way, I think we will be able to create and have robots playing tennis like Roger Federer.

• 35:40Speaker 01

  Do you think they'll mostly be doing self-play in simulation or in the real world?

• 35:46Speaker 00

  I could see, I could see a hybrid ultimately. I think if we can get simulation and we don't have to fully reconstruct the world to, to its detail like right away, but I see self-play both in the physical and in simulation.

• 36:00Speaker 01

  You used the word world simulator a couple of times there. What are your thoughts on, I guess, what's happening with world models, which I guess are being used somewhat interchangeably with video models as a term right now? But world models and like their contribution to the robot data training mix?

• 36:16Speaker 00

  I think the potential and possibility to have what we just talked about in terms of self-play, to even just dream what it means to drop a cup and have it shatter without actually doing it, is incredibly valuable for what, what could happen. I see the value in that we get to leverage a lot of the work from the internet and YouTube, for example, in this pixel prediction ultimately. And if we can translate that back into what these action trajectories would be, it could help us accelerate quite a bit.

• 36:50Speaker 01

  Yeah, yeah, interesting. So you mentioned that we've kind of converged on this like pyramid of data mix. Do you think this pyramid will like scale if we just scaled up? Do you think that takes us to the promised land? And to me, promised land is people like saying GPT-3 moment for robotics. I no longer like that. I just like, when will a robot actually fold my clothes or cook a meal for me? Do you think the current data mix will get us to that point? Or do you think we're like new breakthroughs and algos and data are going to be needed to get there?

• 37:19Speaker 00

  I think if we scale it up some order of magnitude in that ratio, we will solve a lot of tasks along the way. So some of those tasks could be a lot more constrained environments. It could be within business operation tasks, very specific SOPs you give. In that ideal world where we have a drop-in robot and it solves any task by just looking at it, can play tennis just like Roger Federer out of the box, in all of the crazy complexities of the actual world scenarios, like the weather, for example? I think it will be some way, and I don't think this is what it will look like ultimately.

• 38:02Speaker 01

  What will it look like?

• 38:04Speaker 00

  Well, we still have so much to add into the mix still. And I think, I think that is going to be, how can we start introducing other modalities into the mix? This is going to be that tactile data. I like the approach, a lot of the models converging towards an omni-model approach, and where you can feed it any type of input that is the observation, whether it is force, pixel, even smell in a very extreme case, and then have some sort of output in, in whether it's action, voice, or, or different types of, types of controls.

• 38:43Speaker 01

  Are there even chips that can sense smell?

• 38:45Speaker 00

  I, it's, it's, it's pretty, it's pretty early. This olfactory approach is very early. But I like to imagine that there's going to be an approach in the world where, where that gets unlocked.

• 38:55Speaker 01

  Yeah, the results of, you know, GPT-6, Astra is generalizing incredibly well to robot tasks. I'm curious what you make of that and what it means for all these pure-play robotics companies? Like, are they ultimately just going to get clobbered by the AGI labs? And like the bitter lesson is just going to steamroll robotics as well? What do you think?

• 39:16Speaker 00

  It takes a lot of courage to scale up data with imperfect information. And I think a lot of these labs have the DNA in themselves to take on that courage early on. I think what we're, we're seeing and what's exciting is that with the scale up of robotics data and even just adding into a lot of the pre-training mixes of these main LLMs and these foundation models, it really is that you can start to generalize in a lot of different domains. I'm excited about the omni-model approaches where you can introduce a lot of different types of observation, whether that's force

• 39:58Speaker 00

  or whether that's action trajectories into the mix and allow it to generalize.

• 40:04Speaker 00

  I think there are also going to be a lot of arguments where you want to be much more vertical than a fully generalized model that can do anything. So somewhere along that time horizon, that model that can do everything is going to be very good at a lot of things. But some of these specialized models, some of these more targeted robotics foundation models might become very excellent into four nines of capability and reliability in some of these tasks.

• 40:32Speaker 01

  Hmm, okay. What I heard reading between the lines just now was that the, you know, the fact that the latest foundation models are great at robotics is not actually that surprising, in part because there actually is quite a bit of robot data that's been now thrown into the training mix. Is that fair?

• 40:48Speaker 00

  It's actually quite expected when you think about it.

• 40:50Speaker 01

  Very interesting. I'd love to close by going back to your sci-fi roots. You started this company because, you know, you can imagine a version of the world with robots everywhere. Paint a picture of what, what you think the world looks like.

• 41:06Speaker 00

  I think this was a, the funniest moment was probably when you visited our New York office. And in our main conference room, we have hung up on the wall, actually, the Kawasaki Corleone.

• 41:17Speaker 01

  I love that.

• 41:18Speaker 00

  Which is-

• 41:19Speaker 01

  The robot panther, dog, horse, whatever it is.

• 41:22Speaker 00

  The panther, dog, horse, exactly. So, so it's pretty much a robot, panther, dog, horse.

• 41:28Speaker 00

  And it's the most ridiculous video and trailer you've ever seen, pretty much.

• 41:32Speaker 01

  My favorite part is that you guys convinced Anas that it was actually you and your mom on it.

• 41:38Speaker 00

  Yeah, yeah, there's, there's a clip pretty much where this, this fantastical like Asian lady and her, and her son are riding this green meadow over a little river. And the Corleone, this horse-dog-panther robot, is jumping over the river. And so we told Anas this was pretty much us as when we were kids and we generated it.

• 42:01Speaker 00

  But-

• 42:03Speaker 00

  What is wonderful is how absurd it is. I very much love the philosophy of hitchhikers in just how absurd the world could be and how absurd the future could be. And in this world that is full of robots, I would love to believe that there's going to be such crazy entrepreneurs and people that believe that form factors like this would be interesting.

• 42:26Speaker 00

  And I think that the shape and size of robotics will look something like a world where we come up with wacky robots that could do anything that you haven't even thought of yet.

• 42:36Speaker 01

  I love that.

• 42:37Speaker 00

  Like mining asteroids.

• 42:39Speaker 01

  Order of magnitude, how many robots will there be in the world in a decade?

• 42:42Speaker 00

  Many, many times more than there are people.

• 42:46Speaker 01

  Many orders of magnitude more?

• 42:48Speaker 00

  Than there are people, yes.

• 42:49Speaker 01

  Wow.

• 42:50Speaker 00

  In a decade plus.

• 42:52Speaker 01

  Like a hundred billion robots?

• 42:53Speaker 00

  Yeah.

• 42:55Speaker 01

  That's really cool. Hundred billion panther dog horses?

• 42:58Speaker 00

  Panther dog horses, at least another order of magnitude more than that.

• 43:03Speaker 01

  Love it. Awesome, Josh. I think that what you're building is like operationally really impressive and very cool how you are scaling up the data collection efforts to enable kind of this robotics golden age and this sci-fi future that you've dreamed of since you were a kid. And so, thank you for joining the pod today to tell us both how you're building the business and how you see the future. It was really fun.

• 43:24Speaker 00

  Thank you so much for having us. Thank you, Sonia.

• 43:28Speaker 00

  So we actually brought you a present.

• 43:30Speaker 01

  I love presents.

• 43:31Speaker 00

  This is kind of like a full circle moment for us.

• 43:34Speaker 01

  Is this what I think it is?

• 43:36Speaker 00

  Who knows? Who knows? Alright, you're gonna have to open it up on the podcast.

• 43:40Speaker 01

  Okay, this is amazing. And look at the, hold on. Can we, you know, I could be one of those YouTubers that does the unboxings. Look, I love this. The Mecka stickers are A+. Okay, I think this is what I think it is. Let's see.

• 43:53Speaker 00

  We're gonna actually come up with a series of Mecka figurines.

• 43:58Speaker 01

  Oh, I love that.

• 43:59Speaker 00

  Because they're all like giant robots, human pilot stuffs. That'll be fun.

• 44:04Speaker 01

  I'm so excited. Let's see if this is working today.

• 44:13Speaker 01

  I love it. Oh my gosh. Okay, this is the...

• 44:19Speaker 00

  This is the Corleone.

• 44:20Speaker 01

  This is the Kawasaki Corleone. I love this. This is the robot dog panther horse.

• 44:26Speaker 00

  This is me and my mom on the panther horse. That's right.

• 44:31Speaker 01

  This is going, we're either gonna put it in the podcast room or in my office. This is incredible. I'm so happy.

• 44:36Speaker 00

  Do it. So absurd.

• 44:37Speaker 01

  I'm so happy. Thank you.