korrents

Dmitri Dolgov

@dmitri-dolgov · 22 positions · 0 changes of mind

Co-CEO of Waymo and a founding member of Google's self-driving car project, which he joined in 2009.

Dmitri Dolgov did not write this page.

We collected these quotes from things they published elsewhere, and every quote links to where it was said. They have no account here and have not endorsed this site. Quotes are word for word; the short line under each one is our own restatement, not their wording. Their own site. Is this you? Claim it or ask us to remove it. Or tell us what is wrong here.

  1. Our reading

    The best moments in physical AI will look like nothing happened at all.

    Their wordsThat the best AI moments will look like nothing happened. It's just the task got done safely and smoothly.
    spoken · machine transcript hear it at 2:11 · all korrents from this recording

    ↗Waymo Co-CEO Dmitri Dolgov: The Demo Is Only 1% Of The Workyoutube.com 1st of 22 in this recording

    Interesting

  3. Our reading

    "Move fast and break things" is the wrong mantra when you are dealing with atoms; the job is to move fast and ship safely.

    Their wordsin Silicon Valley, there's a common mantra to move fast and break things. However, when you're dealing with atoms instead of bits, breaking things is not really okay. So, the thing you have to do is to move fast and ship safely.
    spoken · machine transcript hear it at 3:07 · all korrents from this recording

    ↗Waymo Co-CEO Dmitri Dolgov: The Demo Is Only 1% Of The Workyoutube.com 2nd of 22 in this recording

    Interesting

  5. Our reading

    In the physical world a model's mistake is measured in human lives rather than tokens, and there is no retry button.

    Their wordsIn the physical world, the cost of a mistake can be measured in human lives, not tokens. There's simply not an undo and a retry button.
    spoken · machine transcript hear it at 4:11 · all korrents from this recording

    ↗Waymo Co-CEO Dmitri Dolgov: The Demo Is Only 1% Of The Workyoutube.com 3rd of 22 in this recording

    Interesting

  7. Our reading

    A physical AI agent has to be safe on day one, because you cannot ship something merely good enough and let users find the edge cases.

    Their wordsGiven the high cost of errors, you need to have a very high level of safety and a very high level of confidence on day one before you deploy your first robot, before you drive your your first autonomous mile.
    spoken · machine transcript hear it at 5:43 · all korrents from this recording

    ↗Waymo Co-CEO Dmitri Dolgov: The Demo Is Only 1% Of The Workyoutube.com 4th of 22 in this recording

    Interesting

  9. Our reading

    A working demo is at best one per cent of the work; the nines that follow it are where the real work is.

    Their wordsAnd a working demo is 1% at best of the work that you have to do. The many nines of performance, the many nines of reliability that follow, that's where the real work happens.
    spoken · machine transcript hear it at 8:21 · all korrents from this recording

    ↗Waymo Co-CEO Dmitri Dolgov: The Demo Is Only 1% Of The Workyoutube.com 5th of 22 in this recording

    Interesting

  11. Our reading

    Waymo's demo took eighteen months and the product took fifteen years — the gap between the two is the whole job.

    Their wordsIt took us about 10 more years to begin providing a service, and then 5 more years to scale to half a million trips per week. So, the demo took 18 months, the product took about 15 years.
    spoken · machine transcript hear it at 10:30 · all korrents from this recording

    ↗Waymo Co-CEO Dmitri Dolgov: The Demo Is Only 1% Of The Workyoutube.com 6th of 22 in this recording

    self-driving cars

    Interesting

  13. Our reading

    Reliability lives on an exponential ladder of nines: every additional nine costs about ten times the effort of the one before.

    Their wordsreliability and performance lives on this exponential ladder of nines. So, getting to that first 90% or 99%, that's the easy part. But then every next nine that you want to add, that takes about 10 times more effort.
    spoken · machine transcript hear it at 11:44 · all korrents from this recording

    ↗Waymo Co-CEO Dmitri Dolgov: The Demo Is Only 1% Of The Workyoutube.com 7th of 22 in this recording

    Interesting

  15. Our reading

    At scale the long tail stops being an edge case and becomes the entire problem statement.

    Their wordsAnd at scale, the long tail is the problem space, is your entire problem statement. When you drive millions of miles per week, a rare event that might happen once in a million miles, that just becomes your daily reality.
    spoken · machine transcript hear it at 12:21 · all korrents from this recording

    ↗Waymo Co-CEO Dmitri Dolgov: The Demo Is Only 1% Of The Workyoutube.com 8th of 22 in this recording

    Interesting

  17. Our reading

    Every AI hype cycle produces spectacular demos and very few products, because each breakthrough makes the demo far easier and the tail barely easier.

    Their wordsAnd that's why every hype cycle produces a wave of absolutely spectacular demos and very few real products. And the recurring mistake of every cycle is spending on the demo when you should be saving for the nines.
    spoken · machine transcript hear it at 14:01 · all korrents from this recording

    ↗Waymo Co-CEO Dmitri Dolgov: The Demo Is Only 1% Of The Workyoutube.com 9th of 22 in this recording

    Interesting

  19. Our reading

    The common failure is picking the technology with the fastest early ramp and extrapolating it, when that curve plateaus below what the product needs.

    Their wordscommon failure mode is picking the tech that gives you the fastest early ramp, riding that steep curve, feeling like you're winning, projecting that, you know, steep slope into the future and feeling like the sky is the limit, and then hitting the plateau, and discovering that the technology path that you picked actually flattens out way before the performance that is required by your product.
    spoken · machine transcript hear it at 15:16 · all korrents from this recording

    ↗Waymo Co-CEO Dmitri Dolgov: The Demo Is Only 1% Of The Workyoutube.com 10th of 22 in this recording

    Interesting

  21. Our reading

    Cameras alone are enough to approximately match a human driver, but weak sensing puts safety on a curve that flattens out well below superhuman.

    Their wordsHowever, if you are targeting full autonomy, and you're targeting superhuman, strongly superhuman performance, you find that weak sensing just leads to a safety curve that flattens out way too early.
    spoken · machine transcript hear it at 16:37 · all korrents from this recording

    ↗Waymo Co-CEO Dmitri Dolgov: The Demo Is Only 1% Of The Workyoutube.com 11th of 22 in this recording

    Interesting

  23. Our reading

    Betting a robotics company on today's component prices is betting it on a number with a short shelf life.

    Their wordsSo, betting your company, betting your approach on today's hardware prices is just betting your company on a number that has a fairly short shelf life and is going to expire.
    spoken · machine transcript hear it at 20:41 · all korrents from this recording

    ↗Waymo Co-CEO Dmitri Dolgov: The Demo Is Only 1% Of The Workyoutube.com 12th of 22 in this recording

    Interesting

  25. Our reading

    Driving turns out to be much like language modelling, because a driver is holding a conversation with other road users in the body language of a car.

    Their wordsTurns out, the task of driving is not that dissimilar from the task of modeling language uh because of the social aspects of driving. You're kind of having a conversation with other dynamic actors in the world, but you're doing that in the space kind of body language of your agent, your car, as opposed to just the language of words.
    spoken · machine transcript hear it at 22:03 · all korrents from this recording

    ↗Waymo Co-CEO Dmitri Dolgov: The Demo Is Only 1% Of The Workyoutube.com 13th of 22 in this recording

    Interesting

  27. Our reading

    Structure that fights scale always loses and structure that channels scale always wins — which is the version of the bitter lesson that matters in the physical world.

    Their wordsEssentially, structure that fights scale will always lose. And structure that channels scale always wins.
    spoken · machine transcript hear it at 31:25 · all korrents from this recording

    ↗Waymo Co-CEO Dmitri Dolgov: The Demo Is Only 1% Of The Workyoutube.com 14th of 22 in this recording

    Interesting

  29. Our reading

    Plain end-to-end learning is not enough for a safety-critical agent that has to be superhuman, however fast it gets you started.

    Their wordsBut if you need to reach superhuman levels of performance in a fully autonomous agent in a safety-critical environment, uh, just doing kind of that basic vanilla end-to-end is not enough.
    spoken · machine transcript hear it at 32:11 · all korrents from this recording

    ↗Waymo Co-CEO Dmitri Dolgov: The Demo Is Only 1% Of The Workyoutube.com 15th of 22 in this recording

    Interesting

  31. Our reading

    Bet on a system that is maximally learned and minimally constrained, and add structure only where it improves the scaling laws.

    Their wordsSo, the lesson here is to bet on a system that's maximally learned and minimally constrained and leverage structure intentionally to boost performance and scaling laws both in training and in evaluation.
    spoken · machine transcript hear it at 36:18 · all korrents from this recording

    ↗Waymo Co-CEO Dmitri Dolgov: The Demo Is Only 1% Of The Workyoutube.com 16th of 22 in this recording

    scaling laws

    Interesting

  33. Our reading

    Building a realistic simulator is exactly as hard as building the agent, because the simulator is itself a large AI model.

    Their wordsAnd the problem of building a good realistic simulator is just as hard as building the agent itself.
    spoken · machine transcript hear it at 38:06 · all korrents from this recording

    ↗Waymo Co-CEO Dmitri Dolgov: The Demo Is Only 1% Of The Workyoutube.com 17th of 22 in this recording

    Interesting

  35. Our reading

    A physical AI company needs three AIs, not one — the agent, the simulator and the critic — turning deployment into a flywheel.

    Their wordsSo, a deployment of your agent uh in the real world generates data. That data then grounds the simulator and makes it more realistic. The simulator generates harder edge cases for the critic to score and for the agent to learn from.
    spoken · machine transcript hear it at 42:20 · all korrents from this recording

    ↗Waymo Co-CEO Dmitri Dolgov: The Demo Is Only 1% Of The Workyoutube.com 18th of 22 in this recording

    Interesting

  37. Our reading

    The model is table stakes; evaluation and metrics are the strategic moat, and they should be built before the technology.

    Their wordsthat your model is really table stakes, but eval and metrics, that's your most important. That's your strategic moat. So, build your eval before you build your technology.
    spoken · machine transcript hear it at 42:58 · all korrents from this recording

    ↗Waymo Co-CEO Dmitri Dolgov: The Demo Is Only 1% Of The Workyoutube.com 19th of 22 in this recording

    Interesting

  39. Our reading

    If you cannot quantitatively define what good enough means, you are not building a product — you are iterating on a demo.

    Their wordsIf you can't quantitatively define what good enough means, you're not really building a product, you're just iterating on your demo.
    spoken · machine transcript hear it at 43:16 · all korrents from this recording

    ↗Waymo Co-CEO Dmitri Dolgov: The Demo Is Only 1% Of The Workyoutube.com 20th of 22 in this recording

    Interesting

  41. Our reading

    Models leak and algorithms get copied, but hundreds of millions of audited autonomous miles cannot be replicated — earned trust is the real moat.

    Their wordsYour your models can be leaked, algorithms can be replicated, but hundreds of millions of miles of fully autonomous operations in the real world, backed by evidence-grade evaluation and publicly audited proof, that is much, much more difficult to replicate.
    spoken · machine transcript hear it at 45:37 · all korrents from this recording

    ↗Waymo Co-CEO Dmitri Dolgov: The Demo Is Only 1% Of The Workyoutube.com 21st of 22 in this recording

    Interesting

  43. Our reading

    In the areas where it operates, the Waymo driver is about seventeen times better than human drivers at avoiding crashes that cause serious injury.

    Their wordsin the areas where we operate, the Waymo driver is about 17 times better than human drivers when it comes to crashes uh that cause serious injury.
    spoken · machine transcript hear it at 46:49 · all korrents from this recording

    ↗Waymo Co-CEO Dmitri Dolgov: The Demo Is Only 1% Of The Workyoutube.com 22nd of 22 in this recording

    self-driving cars

    Interesting