Subvolts take Wayve's AI approach to autonomous driving adapts to new cities and vehicles faster than traditional methods. Nov 18, 2025 - Developers
- Learn how end-to-end deep learning and world models are applied to complex physical systems like autonomous driving.
- Business
- Understand how AI generalization and OEM partnerships can accelerate scaling in the automotive industry.
- Everyday users
- Discover how AI advancements are making self-driving cars more adaptable and potentially closer to widespread use.
This interview with Wayve's CEO provides a deep dive into a significant advancement in AI's application to the physical world.
How End-to-End Learning Created Autonomous Driving 2.0: Wayve CEO Alex Kendall
Audio streams from Sequoia Capital. Your place is remembered on this device.
From Subvolts
Summary and analysis by Subvolts editorial, AI-assisted.
Sequoia Capital's Training Data podcast features Wayve CEO Alex Kendall discussing how end-to-end deep learning is revolutionizing autonomous driving. Kendall contrasts Wayve's generalization-first approach with traditional AV methods, highlighting its adaptability to new vehicles and cities. The episode explores how world models enable reasoning, the benefits of OEM partnerships for scaling, and the potential of language integration for new product features.
This episode explains how a new AI method, like the one powering chatbots, can teach cars to drive themselves. Instead of complex programming for every road, this AI learns from experience, making it adaptable to new places and cars quickly. This could make self-driving cars more widespread.
This episode offers insight into a leading edge of AI application in the physical economy. Listeners will learn how deep learning, similar to LLMs, can solve complex real-world problems like autonomous driving. It's for AI practitioners, automotive industry professionals, and anyone interested in how AI moves beyond digital tasks. Wayve's approach challenges the established AV stack, mirroring how frontier labs like Google Gemini and OpenAI are pushing the boundaries of model generalization and multimodal capabilities.
- HostSequoia Capital
- GuestAlex KendallCEO, Wayve
- Guest: Alex Kendall, Wayve CEO
- Show: Training Data
- Hosts: Sequoia Capital
- Length: 42 minutes
- Wayve Founding Year: 2017
- Adaptation Time: weeks
Alex Kendall founded Wayve in 2017 with a contrarian vision: replace the hand-engineered autonomous vehicle stack with end-to-end deep learning. While AV 1.0 companies relied on HD maps, LiDAR retrofits, and city-by-city deployments, Wayve built a generalization-first approach that can adapt to new vehicles and cities in weeks. Alex explains how world models enable reasoning in complex scenarios, why partnering with automotive OEMs creates a path to scale beyond robo-taxis, and how language integration opens up new product possibilities. From driving in 500 cities to deploying with manufacturers like Nissan, Wayve demonstrates how the same AI breakthroughs powering LLMs are transforming the physical economy.
Hosted by: Pat Grady and Sonya Huang
- end-to-end deep learning
- Alex Kendall
- An AI system that learns a task directly from raw input to final output, without many separate programmed steps.
- world models
- Alex Kendall
- AI systems that build an internal understanding of how the world works to predict and reason about complex situations.
- OEMs
- Alex Kendall
- Original Equipment Manufacturers, meaning companies that build vehicles.
1 h 08David Silver and Lasse Espeholt of Ineffable Intelligence: A Superlearner for the Age of Experience
WithDavid Silver, Lasse Espeholt
1 h 041 h 0552 minMaking Cities Awesome: Peregrine’s Nick Noone & Ben Rudolph
WithNick Noone, Ben Rudolph
Same guests, other shows
46 min
49 minKoray Kavukcuoglu: “This Is How We Are Going to Build AGI”
WithKoray Kavukcuoglu
45 min
1 h 13He Co-Invented the Transformer. Now: Continuous Thought Machines - Llion Jones and Luke Darlow [Sakana AI]
WithLlion Jones, Luke Darlow
Questions people ask
- What is Wayve's core strategy for autonomous driving?
- Wayve uses an end-to-end deep learning approach with a generalization-first strategy, allowing it to adapt to new vehicles and cities quickly.
- How does Wayve's approach differ from other autonomous vehicle companies?
- Unlike AV 1.0 companies relying on HD maps and LiDAR, Wayve focuses on AI that can generalize and adapt, enabling faster deployment.
Page generated Oct 19, 2026. Summaries are Subvolts' own; the audio, artwork and notes belong to Sequoia Capital.