Real Alpha
Watch mode

Minus One · 2 min · Oct 8, 2026

Waymo began by testing feasibility, not building a product

Dmitri Dolgov

Co-CEO, Waymo

  • Aditya AgarwalHost · Partner, South Park Commons

    One of Facebook's first engineers, he helped build its first search engine; later CTO of Dropbox.

  • RS

    Ruchi SanghviHost · Partner, South Park Commons

About this segment

Waymo set a 100,000-mile autonomous-driving goal and a harder test: 10 Bay Area routes, each 100 miles, with no intervention. The exercise was meant to map feasibility, not launch a product.

From “How Waymo Solved Self-Driving | Dmitri Dolgov, Co-CEO”, Oct 8, 2026. Watch the full episode

“the question at the time was like, should we even try? Is the time appropriate or should we just go back and come back in a decade or so?”
Dmitri Dolgovat 13:24 · Minus One13:24

Takeaways

  1. The first goal was 100,000 autonomous miles.
  2. The harder test was 10 routes of 100 miles each.
  3. The integrated challenge was for learning, not product launch.
Watch 2:22 from 12:37

In this episode

Full episode
  1. 15:00Closed-loop validation requires a driver, simulator and critic4:15
  2. 22:07Waymo’s moat is its system for improving the product5:01
  3. 26:59Each additional safety nine demands more rigorous evaluation8:07
  4. 37:27A stable scorecard can show a system is nearing deployment3:37
  5. 35:06Start physical AI in settings where the problem can be simplified2:32
  6. 41:04AI will speed simple builds, while safety-critical work stays hard3:30

  7. 12:37Waymo began by testing feasibility, not building a product2:22

  8. 44:24Perception transfers more easily than a physical agent's actions3:00Up next

Transcript

Transcribed by machine (Whisper) from the episode’s audio, so a word may be off here and there.

  1. 12:44

    Basically. So my mind naturally goes there. And then you think? Yeah, very cool. one of the things i have difficulty wrapping my head around when it comes to tackling you know self-driving is what was the first thing that you kind of when you're when the team first came together what is the first artifact that you are trying to produce because it feels so different than getting a web app up and running or kind of getting your first mobile app this is what we were all building in 2009 right let's kind of get the first mobile app working and so on. So what was the first almost artifact? Yeah.

  2. 13:20

    Yeah. So when we started in 2009, it was not about building a product. You know, our first order of business was just to understand the problem better. So in service of that, when we started, and like, honestly, the question at the time was like, should we even try? Is the time appropriate or should we just go back and come back in a decade or so? Right. So in service of understanding the problem, when we started this project in 2009, we created a couple of milestones for ourselves with that goal of exploring the space. And one challenge that we created for ourselves was to drive 100,000 miles autonomously, which at the time was orders of magnitude more than anyone has ever done.

  3. 14:03

    And the second one, which actually turned out to be more difficult, was to drive 10 routes all over the Bay Area, and each one was 100 miles long, and we had to do each one from beginning to end with no human intervention. There was a human behind the wheel, but the challenge was to complete the one. And in doing that, you end up building every part of the system. It's just the crazy, amazing, magical days of an early startup, calibrating and putting new hardware in the car.

  4. 14:31

    You're building perception, planning, controlling all of the tools and GUIs, so everybody's doing everything, but you're learning at a crazy rate. So that was the first couple of years we succeeded. And then we said, okay, now there's, you know, there's, you know, they're there. So let's think about what the product could be. And we kind of went back to building more of the fundamentals and laying the foundation