22Astronauts

In this episode, I talk with Lerrel Pinto, Assistant Professor at NYU and one of the most cited researchers in robotics today:

His work spans everything from self-supervised learning to robot dexterity, and he's on a mission to make robots generalize the way humans do.

We talk about growing up in India, building his own education at IIT, and what led him to Carnegie Mellon, Berkeley, and now New York. Lerrel explains how his lab at NYU, GRAIL, tackles robot learning at scale (from representation learning to reinforcement learning) and why open-source, affordable robots are core to his approach.

He also shares what it’s like launching his new stealth-mode startup, Assured Robot Intelligence (ARI), while running one of the top research labs in the country. We talk about how his teaching, mentoring, and outreach are shaping the next generation of roboticists.

I sit down with Benji Barash, CEO of Roboto AI, to talk Amazon, robotics, and why knowing what to do with your data is key to scaling:

Benji spent years at Amazon working on drone delivery, but started to see a growing problem in robotics, the data was piling up faster than teams could make sense of it.

He left Amazon to build a solution. Today, Roboto AI helps robotics companies analyze massive amounts of sensor logs and time-series data. It’s like a copilot for engineers trying to figure out why something broke, how to improve it, and what to do next.

We talk about growing up in the UK, getting into programming way before school even taught it, and what it takes to go from big tech to a lean startup. Benji shares what surprised him about building in the real world, how he works across time zones with his co-founder in Zurich, and what it means to build tools that help others scale.

In this episode, I talk with Madison Maxey, founder of LOOMIA, a company building soft, flexible electronics for everything: Everything? Everything! From robotics to automotive interiors.

Maddie’s journey spans fashion school, a Thiel Fellowship, a return to Stanford in her mid-20s to study material science, and a decade of turning prototypes into real-world tech.

We talk about growing up with a soldering iron and a sewing machine, how she designed a smart jacket for Zac Posen and Google, and why building a company means more than building a product.

Maddie shares what it took to land early customers like Airbus, how she balances long timelines with fast-moving industries, and why her goal is to build something meaningful over 30 years, not just raise another round.

We talk about early wins, hard lessons, the beauty of tactile sensing, and why confidence comes from doing hard things until they start to feel normal.

Yesterday, they launched a $299 robot. It looks like a toy, but it opens up a world of AI. Today, I talk to the person who made it real.

Matthieu Lapeyre is the founder of Pollen Robotics and one of the most quietly influential roboticists in Europe. He’s been building open-source humanoids long before it was cool, from Poppy to Reachy to Reachy Mini.

We talk about how growing up without a tech background shaped him, why he left research to ship hardware, and how he kept going through years of bootstrapping with barely enough to pay the team. He shares what it’s really like to live on the edge for years, and how joining Hugging Face gave them the launchpad they needed.

We also get into the making of Reachy Mini, why it's designed to be unbreakable, what inspired the egg-shaped head, and how it could become the iPhone moment for robotics.

In this episode, I talk with Kaan Dogrusoz, Co-Founder and CEO of Weave Robotics, a YC-backed team building Isaac, a personal home robot:

Kaan grew up in Istanbul, chased curiosity across physics, art, and engineering, and eventually made his way to Carnegie Mellon, then Apple, where he spent nearly a decade working on robotics and shipping features like Double Tap on the Apple Watch.

But something kept pulling at him. He didn’t want to be part of a massive machine anymore. He wanted to build something real, something personal, a robot he’d want in his own home. That’s how Isaac was born. A home robot built not for factories or labs, but for laundry piles and living rooms.

We talk about leaving comfort behind, learning by doing, what it’s like to live with your own prototype, and why he thinks shipping a robot (not just dreaming one) is the hardest and most honest thing a founder can do.

🎙️ I talked with Benjamin Bolte, founder of K-Scale Labs, who left Meta to build something he actually believes in: an open-source humanoid robot!

After working on Autopilot at Tesla, he saw the inside of Optimus and decided the big players were getting it wrong.

Benjamin walks me through how he built the first robot with Alibaba parts and 3D-printed parts in his apartment, why raising too much money too early is a trap, and how soldering wires all night helped him remember why he’s doing this in the first place.

He’s not chasing prestige or funding rounds. He’s trying to ship a $9K robot that can do your laundry. We talk about his time at Tesla and Meta, how he thinks about mortality, the power of conviction, why open-source matters, and what it really takes to build hardware that people want to own.

In this episode, I talk with ⁠Nikolaus West⁠, Co-Founder & CEO of Rerun; their team is building the data stack for Physical AI:

We get into the early days of Rerun: how an open-source visualization tool for multimodal data became widely adopted across robotics, spatial computing, and even inside companies like Apple and Meta. But that was just the start.

Now, they’re building a full-stack platform for logging, querying, and managing robotic-scale data, from raw logs to model training.

Niko shares his personal journey from business school in London to engineering in Sweden, to startups in retail, Kenya, and AR. Along the way, he learned the hard truth: physical AI teams are still flying blind when it comes to data. That pain turned into obsession, and obsession turned into Rerun.

🎙️ I spoke with Chang Liu, founder and CEO of Extend Robotics, a startup developing intuitive VR interfaces to control robot arms and train AI models using real-world data.

Chang shares his story from growing up in China to moving to the UK for university, studying at Newcastle and Southampton, and completing a PhD in aerial robotics. After postdoc work at Imperial College on autonomous drone systems, he made the leap into entrepreneurship and started Extend Robotics.

We talk about the early pivots (from drone teleoperation to building lightweight robotic arms) and how the company eventually focused on software, helping users control off-the-shelf robot arms through an easy-to-use VR interface.

Chang explains how they’re now using this interface to collect high-quality data for AI training, with real-world pilots in agriculture, EV manufacturing, and satellite servicing. The goal is to go from teleoperation to automation, and to make robot training as accessible as robot control.

Took me 2 years to land this one...

🎙️ In this episode, I talk with ⁠Dhanush Radhakrishnan⁠, Co-Founder and CEO of ⁠Clone Robotics⁠:

The company building lifelike, musculoskeletal androids that move like humans and could become the next personal computing platform.

Dhanush shares how watching Iron Man at 13 sparked a lifelong obsession with tech, leading him from plasma thrusters and nuclear fusion research to founding a YC-backed robotics company now making headlines with their human-like androids.

We talk about why his first startup didn’t work out (and why Plan A to do B never does), how he met his co-founder on the internet, and why moving to Poland turned out to be one of the best decisions for focus and execution.

Clone is going against the grain: from hydraulics to neural net control, from soft-body design to building general-purpose robots from scratch.

This convo is packed with vision, hard-earned insights, and a founder who’s not afraid to do things differently.

Give it a listen. You’ll see why people are paying attention.

In Episode #66, I talk with Tibo LOUIS-LUCAS, founder of Tweet Hunter and Taplio, two SaaS tools he built, scaled, and sold for over $10 million:

Tibo shares how he went from a series of startup failures to shipping one new product every week with his co-founder. That process eventually led to Tweet Hunter. What started as a personal tool to grow on Twitter turned into a fast-growing SaaS company doing over $100k MRR.

We talk about why he stepped away from managing teams, what he learned from building the wrong products, and how growing up in a finance-savvy family shaped his view on risk. He opens up about burnout, recovering after a family health crisis, and how building in public helped him find both traction and community.

He also explains why he stopped sharing revenue online, how the indie hacking scene has changed in the past two years, and what he's building next with more focus and less noise.

An honest conversation about starting over, staying hands-on, and building what people actually want.