Robots Are Finally Starting to Work

Name: Robots Are Finally Starting to Work
Uploaded: 2026-04-16T14:00:07.000Z
Duration: 49 min 27 s
Channel: Y Combinator

Y CombinatorApril 16, 202649m

Topics17

Starting a Robotics Business and Mission of Physical Intelligence0:00 Introduction to Guest and Physical Intelligence's Vision0:30 Why Robotics is Hard: Three Pillars and Seminal Papers2:01 Scaling Across Embodiments: Open X-Embodiment and RT-X5:30 The Data Problem in Robotics9:30 Challenges with Robot Hardware Variability12:01 Current State-of-the-Art and Real-World Deployments15:01 Cloud Compute for Real-Time Robot Control23:00 Integrating AI Models with Robot Hardware24:27 Rapid Progress in Robot Deployment28:30 Advice for Aspiring Robotics Startup Founders29:01 Cambrian Explosion of Vertical Robotics32:31 PI's Open Approach to Accelerate Ecosystem36:32 PI Founding Team and Background39:00 Limitations and Internal Tools45:00 Closing48:01 Future Trends in Robotics Startups48:53

In a Nutshell

Physical Intelligence (PI), co-founded by Kuang Vang, is building foundation models for robotics—the "GPT-1 moment"—enabling a single model to control any robot for any physically possible task via scaling cross-embodiment data, cloud inference with real-time chunking, and open-sourcing models like PI-0. Key breakthroughs include emergent generalization from projects like Open X-Embodiment (50% better than specialists), real-world deployments with partners like Weave (laundry folding) and Ultra (warehouse logistics), and overcoming data scarcity through mixed autonomy and scrappy hardware. This unbundles vertical integration, slashing startup costs to spark a Cambrian explosion of robotics companies targeting every menial job with quick data collection, economic break-even, and incremental scaling.

AI-Generated Notes

These notes were generated by AI and may contain inaccuracies.

The equation for starting a robotics business has changed and will continue to change at an accelerating pace because the upfront cost is not that high anymore. Everyone's spending a lot of time in the digital world and now is the time to start thinking about the world of atoms. This is the playbook for how to build a vertical robotics company. The mission from the start is to create that Cambrian explosion.

Welcome to another episode of the Light Cone. Special guest: Kuang Vang, co-founder of Physical Intelligence (PI), the robotics AI lab that might bring the GPT-1 moment for robotics. Mission: build a model that can control any robot to do any task that is physically capable of, at a high level of performance useful to people in all walks of life. GPT-1 for robotics is the ChatGPT moment for robotics. Perspective: build a really intelligent model and a platform to externalize that intelligence to the world for building interesting applications in all sorts of verticals in robotics.

Peeling an onion analogy: Start from a strong base model with common sense knowledge that works to some extent on your robot. Then a mixed autonomy system, similar to autonomous driving cars today. Deploy to do a real job; it's okay if it makes mistakes. Over time, expose to real-world complexity and edge cases; system gets incrementally better every day. One day, fully autonomous system providing tremendous value.

Robotics problem simplified to three pillars: semantics (unlocks from language models ported into robotics), planning, and control (real-time interaction with changing environment).

Seminal papers from PI robotics team starting in 2024 signaling GPT-1 moment near:

SayCan: First demonstration of language model bringing common sense knowledge into robotics, reducing need for robot-specific data. Example: Ask language model steps to go to YC office to record a podcast; it shows the plan incredibly well. Language models infiltrate robotics starting at planning/semantic level.
Still control problem: Need mechanism to convert plan into low-level actions to actuate robot.
PaLM-E and RT-2 (Robotics Transformer 2): Start from powerful vision language model, adapt with robotic data to "speak robot language." Shows transfer from vision-language knowledge to low-level actions.
- Favorite example: Picture of celebrity on table (Taylor Swift, Queen of England); ask robot "pick up the Coke can and move it to Taylor Swift"—works even though Taylor Swift not in robot data.

Sign in to read the full notes

Get access to AI-generated notes, topic timestamps, and more.

Robots Are Finally Starting to Work

Starting a Robotics Business and Mission of Physical Intelligence00:00

Introduction to Guest and Physical Intelligence's Vision00:30

Sign in to read the full notes