Waymo CEO on Reliability: Bridging the Gap from Demo to Product in 15 Years
机器之心 · wechat · 2026-08-15
Waymo Co-CEO Dmitri Dolgov shared the 15-year journey from early demos to scaled operations, highlighting the "reliability gap" in physical AI systems.
- Demo vs. Product: While the team verified core driving capabilities in just 18 months, it took another 15 years to build a deployable, reliable service.
- Physical AI Constraints: Unlike digital AI, physical systems face higher error costs, millisecond-scale decision requirements, data scarcity, and stringent pre-deployment validation needs.
- Reliability Scaling: Moving from 90% to 99.9% reliability increases difficulty exponentially, necessitating solutions for hardware aging, sensor failures, and long-tail events.
- Technical Strategy: The chosen tech stack must be evaluated not just on initial performance, but on its upper limit for reliability to support fleet scaling.
More from Embodied
- Tesla Roadster demo shows 0-60 mph in 0.81s and a brief hop with mid-air attitude control — op7418 · 2026-10-16
- Tesla Roadster 'flying car' demo draws skepticism: 2G cornering, questionable street value — lipeng0820 · 2026-10-16
- Beff Jezos shares demo: 'They finally solved parallel parking' — beffjezos · 2026-10-16
- Jet-powered robot's multi-nozzle control sparks debate on rescue use cases — op7418 · 2026-10-16
- Bezos on Tesla's hovering Roadster: 'The future should look like the future' — beffjezos · 2026-10-16
- Skild AI Crosses $100M ARR as CEO Says Robot Deployment Can't Be Outsourced — deepakpathak · 2026-10-16