Subvolts take Open source self-driving is here, making autonomy accessible beyond big tech. Apr 16, 2026 - Developers
- Learn how open-source AI and simulation are applied to real-world autonomous driving challenges.
- Business
- Understand alternative approaches to autonomous vehicle development beyond large, closed-source initiatives.
This episode features a deep dive into Comma AI's open-source approach to self-driving, offering practical insights into real-world AI deployment.
Open Source Self-Driving with Comma AI
Audio streams from Daniel Whitenack and Chris Benson. Your place is remembered on this device.
From Subvolts
Summary and analysis by Subvolts editorial, AI-assisted.
Daniel Whitenack and Chris Benson interview Harald Schäfer, CTO at Comma AI, on the Practical AI podcast. They discuss how Comma AI uses open source AI and machine learning to bring self-driving capabilities to everyday vehicles. The conversation covers the role of robotics, simulation, and world models in training autonomous systems at scale and shaping the future of the technology.
This episode explores how Comma AI is making self-driving cars a reality for regular people using open-source technology. They use smart computer programs and simulations to train cars to drive themselves, making the future of driving more accessible.
This episode offers insight into the open-source approach to autonomous driving, contrasting with the closed systems often developed by major tech players. It's for developers and enthusiasts interested in practical AI applications beyond large labs. Listeners will learn how Comma AI leverages machine learning and simulation for real-world deployment, a strategy that complements the research into world models and large-scale training seen at frontier labs like Google Gemini and Meta AI.
- HostDaniel Whitenack
- HostChris Benson
- GuestHarald SchäferCTO, Comma AI
- Episode Title: Open Source Self-Driving with Comma AI
- Show: Practical AI
- Guest: Harald Schäfer, CTO at Comma AI
- Length: 46 minutes
- Key Technology: OpenPilot
Chapters from the publisher ↗ · Transcript ↗ Key moments and transcript search come with a later piece.
Autonomous driving is not just a big tech or closed-source game, it's becoming accessible through open innovation and real-world deployment. Dan and Chris sit down with Harald Schäfer, CTO at Comma AI, to explore how OpenPilot is bringing self-driving to everyday vehicles using open source AI. We dive into the intersection of machine learning, robotics, and simulation, including how world models are enabling training at scale and shaping the future of autonomy.
Featuring:
- Harald Schäfer – LinkedIn
- Chris Benson – Website, LinkedIn, Bluesky, GitHub, X
- Daniel Whitenack – Website, GitHub, X
Links:
Upcoming Events:
- Register for upcoming webinars here!
- world models
- Harald Schäfer
- AI systems that create internal representations of the environment to predict future events.
44 minNarrative intelligence and the human advantage
WithReed Frerichs
47 minOpen models and the future of Physical AI with NVIDIA
WithMing-Yu Liu
49 minFrom AGENTS.md to Enterprise Deployment
WithNick Kuhn
Questions people ask
- What is OpenPilot?
- OpenPilot is an open-source driver assistance system developed by Comma AI that brings self-driving capabilities to everyday vehicles.
- How does Comma AI train its self-driving systems?
- Comma AI uses machine learning, robotics, and simulation, including world models, to enable large-scale training for autonomous systems.
Page generated Oct 19, 2026. Summaries are Subvolts' own; the audio, artwork and notes belong to Daniel Whitenack and Chris Benson.