Ep 84 | Fundamental Improvement Over Incremental Change (w/ Xavier (Tianhao) Chi)
Robots still need weeks of coding to learn one new task. Xavier (Tianhao) Chi is changing that with Mbodi AI:Mbodi helps industrial robots learn through language and demonstration. No coding, no engineers, just simple instruction. We talk about how his team is closing the gap between advanced AI research and real factory floors, and what that means for the future of automation.Xavier shares his path from growing up in Shenyang to leading Google Public DNS, one of the internet’s core services, and why he left to build Mbodi with his co-founder. He explains why the next wave of robotics will come from adaptable software, not humanoids.We also talk about risk, ambition, and what it takes to move from stable engineering to startup chaos. Xavier breaks down Mbodi’s hybrid AI approach, its sub-0.5 second response times, and how their partnership with ABB is turning it into real deployments.A must-listen for anyone building in robotics, AI, or industrial automation.
--------
50:06
--------
50:06
Ep. 83 | You Become Who You Hang Out With (w/ Ashish Kapoor)
Ashish Kapoor is building General Robotics to solve the biggest deployment problem in robotics: Getting real robots to work in the real world. In this episode, he shares how he’s doing it, and why most robotics stacks aren’t built to scale.We talk about growing up in India, studying at IIT and MIT, and how his mindset shifted from solving hard problems to finding the right ones. Ashish shares why he left research to start General Robotics, the limits of today’s robotics stacks, and how Grid aims to solve the deployment bottleneck, especially for enterprises drowning in PoCs and fragmented software.He also opens up about his background in aviation, building his own airplane, and how he's betting on cloud-first skills infrastructure while others chase edge. This one’s packed with insight from someone who’s worked across every layer of the robotics stack... and is now trying to make it all work in the real world.
--------
1:00:14
--------
1:00:14
Ep 82 | College Is Going to Be Obsolete by the End of This Decade (w/ Brian Walker)
In this episode, I talk with Brian Walker, founder and CEO of REVEL, the company building the simulation backbone for humanoid robotics. Brian’s journey started far from Silicon Valley: growing up in the Czech Republic and working on Hollywood sets like Avatar and The Mandalorian, where he helped pioneer real-time XR production.We talk about what pulled him from filmmaking into robotics, and how sci-fi inspired him to stop watching the future and start building it. Brian shares why he founded REVEL to create a massive library of digital twins, turning real-world products into high-fidelity simulation assets so robots can train on them before ever touching them.His goal? To make every product “robot-ready” and compress a decade of physical experience into just hours of training.We also dive into his views on self-education, outsider thinking, and why he acquired a startup during a 20-hour hackathon, with a mic-drop and a €20K offer.If you’re into robotics, simulation, or stories of wild career pivots, don’t miss this one.
--------
1:01:45
--------
1:01:45
Ep 81 | Opportunities Only Arise After An Incredible Amount Of Work (w/ Jan Liphardt)
A Stanford physicist leaves academia to build open-source software for humanoid robots? I talked to OpenMind founder Jan Liphardt: OpenMind a new robotics company building an open-source, AI-native operating system for humanoid robots.We talk about being born in Germany, his upbringing in Michigan, early love for taking things apart, and how his path led from biochemistry at Reed to a PhD at Cambridge, then faculty roles at Berkeley and Stanford.Jan shares why he made the leap from academia to entrepreneurship, how a Nature paper and a Christmas Eve email nudged him out of the lab, and what drives his belief in transparency, modularity, and decentralized control for intelligent machines.We also discuss OpenMind’s strategy, where robots download their rulebooks from Ethereum, and why he thinks humanoids won't fold your laundry... but could teach your kids or assist in hospitals.
--------
1:03:42
--------
1:03:42
Ep 80 | You Will Die If You Don’t Do It (w/ Bob van Luijt)
🎙️ I talked with Bob van Luijt, co-founder and CEO of Weaviate, the open-source vector database that's become core infrastructure for AI-native applications.We talk about how Bob grew up in a small Dutch town, started coding in QBasic, and built his first software company while still in school. Then came the unexpected turn: jazz. He shares how studying music (from a conservatory in the Netherlands to Berklee in Boston) taught him grit, deep focus, and how to think in systems. For Bob, writing code and playing music happen in the same part of the brain.We talk about how Weaviate began as a side project fueled by curiosity about the distance between words, and how that simple idea turned into one of the most used vector databases in the world. Bob explains how the release of transformer models unlocked everything, and how he's stayed focused on helping real developers build, not just chasing hype.We also get into his philosophy on building companies, how he thinks about talent and education, and why he believes too much "academic thinking" blocks real potential. Bob’s not in it for the ego or the exit... he’s building tools for other builders.
The show for founders building real deep tech.
Each episode features founders, executives, and builders in AI, robotics, and hardware — breaking down how they build, scale, and learn.
We talk about systems, mistakes, GTM strategy, funding lessons, and how to move from research to traction.
Hosted by Ilir Aliu from 22Astronauts.
Whether you’re building now or just curious — tune in.
France