Training Data How End-to-End Learning Created Autonomous Driving 2.0: Wayve CEO Alex Kendall
18 snips
Nov 18, 2025 
Alex Kendall, Founder and CEO of Wayve, discusses his revolutionary approach to autonomous driving. He explains how end-to-end deep learning can replace traditional methods, enabling rapid adaptations across cities. Kendall delves into the power of world models for reasoning in complex scenarios and the significance of partnerships with automotive manufacturers for scaling benefits. He highlights the potential of AI breakthroughs, including language integration, to open new avenues for driving technology and transform the physical economy.
AI Snips
Chapters
Transcript
Episode notes
End-To-End Networks Replace Hand‑Engineered Stacks
- Wayve frames AV2.0 as replacing hand-engineered stacks with one end-to-end neural network that generalizes across vehicles and cities.
- Alex argues foundation-model-style generality lets one intelligence adapt quickly without heavy per-city infrastructure.
From Central London To New York In A Year
- Wayve drove in central London and later scaled to highways, Europe, Japan, and New York City within a year.
- The company used those real drives to show global generalization and product readiness to partners.
Generalization Is The Scaling Lever
- Generalization is the core metric for deploying autonomy across hundreds of cities and different vehicles.
- Wayve trains on diverse sensor sets and geographies to amortize a single model across customers quickly.