#147 – Dmitri Dolgov: Waymo and the Future of Self-Driving Cars

Dmitri Dolgov is the CTO of Waymo, an autonomous vehicle company. Please support this podcast by checking out our sponsors: – Tryolabs: https://tryolabs.com/lex – Blinkist: https://blinkist.com/lex and use code LEX to get 25% off premium – BetterHelp: https://betterhelp.com/lex to get 10% off – Cash App: https://cash.app/ and use code LexPodcast to get $10 EPISODE LINKS: Waymo’s Twitter: https://twitter.com/waymo Waymo’s Website: https://waymo.com PODCAST INFO: Podcast website: https://lexfridman.com/podcast Apple Podcasts: https://apple.co/2lwqZIr Spotify: https://spoti.fi/2nEwCF8 RSS: https://lexfridman.com/feed/podcast/ YouTube Full Episodes: https://youtube.com/lexfridman YouTube Clips: https://youtube.com/lexclips SUPPORT & CONNECT: – Check out the sponsors above, it’s the best way to support this podcast – Support on Patreon: https://www.patreon.com/lexfridman – Twitter: https://twitter.com/lexfridman – Instagram: https://www.instagram.com/lexfridman – LinkedIn: https://www.linkedin.com/in/lexfridman – Facebook: https://www.facebook.com/LexFridmanPage – Medium: https://medium.com/@lexfridman OUTLINE: Here’s the timestamps for the episode. On some podcast players you should be able to click the timestamp to jump to that time. (00:00) – Introduction (07:46) – Computer games (12:52) – Childhood (15:24) – Robotics (16:14) – Moscow Institute of Physics and Technology (18:26) – DARPA Urban Challenge (28:46) – Waymo origin story (44:27) – Waymo self-driving hardware (53:00) – Connected cars (58:53) – Waymo fully driverless service in Phoenix (1:03:14) – Getting feedback from riders (1:11:28) – Creating a product that people love (1:17:18) – Do self-driving cars need to break the rules like humans do? (1:24:03) – Waymo Trucks (1:29:41) – Future of Waymo (1:42:53) – Role of lidar in autonomous driving (1:55:53) – Machine learning is essential for autonomous driving (1:59:55) – Pedestrians (2:06:32) – Trolley problem (2:11:00) – Book recommendations (2:22:26) – Meaning of life

Speaker names marked ? are inferred from speaking time and the show’s known hosts — they are not voice-verified.

• 0:00Lex Fridman?

  The following is a conversation with Dmitry Dolgov, the CTO of Waymo, which is an autonomous driving company that started as Google's self-driving car project in 2009 and became Waymo in 2016. Dmitry was there all along. Waymo is currently leading in the fully autonomous vehicle space in that they actually have an at-scale deployment of publicly accessible autonomous vehicles, driving passengers around with no safety driver, with nobody in the driver's seat. This, to me, is an incredible accomplishment of engineering on one of the most difficult and exciting artificial intelligence challenges of the 21st century. Quick mention of each sponsor,

• 0:45Lex Fridman?

  followed by some thoughts related to the episode. Thank you to Trial Labs, a company that helps businesses apply machine learning to solve real-world problems. Blinkist, an app I use for reading through summaries of books. BetterHelp, online therapy with a licensed professional. And Cash App, the app I use to send money to friends. Please check out the sponsors in the description to get a discount at the support this podcast. As a side note, let me say that autonomous and semi-autonomous driving was the focus of my work at MIT and is a problem space that I find fascinating and full of open questions from both a robotics and a human psychology perspective. There's quite a bit that I could say here

• 1:28Lex Fridman?

  about my experiences in academia on this topic that reveal to me, let's say, the less admirable sides of human beings. But I choose to focus on the positive, on solutions. On brilliant engineers like Dmitry and the team at Waymo, who work tirelessly to innovate and to build amazing technology that will define our future. Because of Dmitry and others like him, I'm excited for this future. And who knows, perhaps I too will help contribute something of value to it. If you enjoy this thing, subscribe on YouTube, review it with five stars and up a podcast, follow on Spotify, support on Patreon, or connect with me on Twitter at Lex Fridman.

• 2:11Lex Fridman?

  As usual, I'll do a few minutes of ads now and no ads in the middle. I try to make these interesting, but I give you timestamps. So if you skip, please still check out the sponsors by clicking the links in the description. It is, in fact, the best way to support this podcast. This episode is brought to you by Trial Labs, a new sponsor and amazing company. They help build AI-based solutions for businesses of all sizes. I love these guys, especially after talking to them on the phone and checking out a bunch of their demos and blog posts. If you are a business or just curious about machine learning, check them out at triallabs.com/lex.

• 2:52Lex Fridman?

  They've worked on price optimization, early detection of machine failures, and all kinds of applications of computer vision, including face detection on lions. Yes, lions, in support of a conservation effort in Africa. Their work on price automation and optimization is probably their most impressive in terms of helping businesses make money. Also, as a cool side note, they do release open source code on GitHub on occasion, like a computer vision tracker, for example. Tracking and just the general problem of occlusion very much remains unsolved, but there's been a lot of exciting progress made over the past

• 3:31Lex Fridman?

  five years. Anyway, all that to say is that Trial Labs is legit. Great engineers. If you own a business and want to see how I can help you, do check them out at triallabs.com/lex. That's triallabs.com/lex. This episode is also supported by Blinkist, my favorite app for learning new things. Blinkist takes the key ideas from thousands of nonfiction books and condenses them down into just 15 minutes that you can read or listen to. I'm a big believer in reading at least an hour every day. As part of that, I use Blinkist almost every day to try out a book I may otherwise never have a chance to read. And in general, it's a great way to broaden your view of the ideal landscape

• 4:16Lex Fridman?

  out there and find books that you may want to read more deeply. With Blinkist, you get unlimited access to read or listen to a massive library of condensed nonfiction books. I also use Blinkist Shortcasts to quickly catch up on podcast episodes I've missed. Right now, Blinkist has a special offer just for the listeners of this podcast and probably every other podcast they sponsor, but who's counting? Go to blinkist.com/lex to start your free seven day trial and get 25% off of a Blinkist Premium Membership. That's Blinkist spelled B-L-I-N-K-I-S-T.

• 4:56Lex Fridman?

  Blinkist.com/lex to get 25% off and a seven day free trial. They're really making me say this over and over, aren't they? That's blinkist.com/lex. This episode is also sponsored by BetterHelp, spelled H-E-L-P, help. They figure out what you need and match you with a licensed professional therapist in under 48 hours. I chat with the person on there and enjoy it. Of course, I also have been talking to Mr. David Goggins over the past few months, who is definitely not a licensed professional therapist, but he does help me meet his and my demons and become comfortable to exist in their presence.

• 5:40Lex Fridman?

  Everyone is different, but for me, I think suffering is essential for creation, but you can suffer beautifully in a way that doesn't destroy you. Therapy can help in whatever way that therapy takes. So I think BetterHelp is an option worth trying. They're easy, private, affordable, available worldwide. You can communicate by text anytime and schedule weekly audio and video sessions. You didn't ask me, but my two favorite psychiatrists are Zingun Freud and Carl Jung. Their work was important in my intellectual development as a teenager. Anyway, check out betterhelp.com/lex. That's betterhelp.com/lex.

• 6:21Lex Fridman?

  Finally, this show is presented by Cash App, the number one finance app in the App Store. When you get it, use code LEXPODCAST. Cash App lets you send money to friends, buy Bitcoin, and invest in the stock market with as little as $1. I'm thinking of doing more conversations with folks who work in and around the cryptocurrency space. Similar to AI, there are a lot of charlatans in this space, but there are also a lot of freethinkers and technical geniuses that are worth exploring ideas with in depth and with care. As an example of that, Vitalik Buterin will definitely be back on the podcast. If you listened to the first one, he'll be back on probably many more times. I see that guy accomplishing a huge amount of things in his life, and I love talking to him.

• 7:06Lex Fridman?

  All right, if you get Cash App from the App Store or Google Play, use code LEXPODCAST, you get $10. And Cash App will also donate $10 to FIRST, an organization that is helping to advance robotics STEM education for young people around the world. And now here's my conversation with Dmitry Dolgov.

• 7:46Lex Fridman?

  When did you first fall in love with robotics, or even computer science more in general?

• 7:51Speaker 01

  Computer science first, at a fairly young age. Robotics happened much later. I think my first interesting introduction to computers was in the late 80s.

• 8:06Speaker 01

  When we got our first computer, I think it was an IBM, I think IBM AT. Remember those things that had like a turbo button in the front?

• 8:16Lex Fridman?

  Turbo button.

• 8:17Speaker 01

  The radio press it and you know, make, make the thing goes faster.

• 8:20Lex Fridman?

  Did they already have floppy disks?

• 8:22Speaker 01

  Yeah, yeah, yeah, yeah, like the, the five point four inch ones.

• 8:26Lex Fridman?

  I think there was a bigger inch. So good one, something than five inches and three inches.

• 8:31Speaker 01

  Yeah, I think that was the five. I don't, I maybe that was before that was the, the giant plates and I didn't get that. But it was definitely not the, not the three inch ones. Anyway, so that, that, you know, we got that computer. I spent the first few months just, you know, playing video games as you would expect. I got bored of that, so I started messing around and trying to figure out how to, you know, make the thing do other stuff. Got into exploring, you know, programming and a couple of years later, it got to a point where I actually wrote a game, a lot of games and a game developer, a Japanese game developer actually offered to buy it for me for, you know, a few hundred bucks.

• 9:15Speaker 01

  But, you know, for, for a kid in Russia.

• 9:18Lex Fridman?

  It's a big deal.

• 9:19Speaker 01

  It's a big deal. Yeah. I did not take the deal.

• 9:21Lex Fridman?

  Wow. Integrity.

• 9:22Speaker 01

  Yeah, I, I instead.

• 9:24Lex Fridman?

  Stupidity.

• 9:25Speaker 01

  Yes, that was not the most acute financial move that I made in my life, you know, looking back at it now. I, I instead put it, well, you know, I had a reason. I, I put it online. It was, what did you call it back in the days? It was a freeware, I think. Right? It was not open source, but you could upload the binaries, you would put the game online. And the idea was that, you know, people like it and then they, you know, contribute and they send you little donations. Right? So I did my quick math of like, you know, of course, you know, thousands and millions of people are going to play my game, send me a couple of bucks apiece. You know, should definitely do that. As I said, not, not the best.

• 9:56Lex Fridman?

  You're already playing with business models at that young age. Remember what language it was? What programming? It was a.

• 10:01Speaker 01

  Pascal.

• 10:03Lex Fridman?

  Which what?

• 10:03Speaker 01

  Pascal.

• 10:04Lex Fridman?

  Pascal. And they had a graphical component. So it's not text based?

• 10:07Speaker 01

  Yeah, yeah, it was like, I think they were 320 by 200, whatever it was. I think that kind of the earlier.

• 10:14Lex Fridman?

  That's the resolution.

• 10:15Speaker 01

  VGA resolution, right? And I actually think the reason why this company wanted to buy it is not like the fancy graphics or the implementation. It was maybe the idea of my actual game.

• 10:24Lex Fridman?

  The idea of the game. Well, one of the things I, it's so funny. I used to play this game called Golden Axe and. The simplicity of the graphics and something about the simplicity of the music like it still haunts me. I don't know if that's a childhood thing. I don't know if that's the same thing for Call of Duty these days for young kids. But I still think that the simple, when the games are simple, that simple purity makes for, like allows your imagination to take over and thereby creating a more magical experience. Like now with better and better graphics, it feels like your imagination doesn't get to create worlds,

• 11:08Lex Fridman?

  which is kind of interesting. It could be just an old man on a porch like waving at kids these days that have no respect. But I still think that graphics almost get in the way of the experience. I don't know.

• 11:20Speaker 02

  Flippity bird.

• 11:22Lex Fridman?

  Yeah. Well, I don't know if the imagination. Game's closed. I don't, yeah, but that that's more about games that up like, that's more like Tetris World where they optimally, masterfully like create a fun, short-term dopamine experience. Versus I'm more referring to like role-playing games where there's like a story. You can live in it for months or years. Like there's an Elder Scrolls series, which is probably my favorite set of games. That was a magical experience and that the graphics are terrible. The characters were all randomly generated, but they're, I don't know, that's, it pulls you in.

• 12:04Lex Fridman?

  There's a story. It's like an interactive version of an Elder Scrolls Tolkien world and you get to live in it. I don't know. I miss it. It's one of the things that suck about being an adult is there's no, you have to live in the real world as opposed to the Elder Scrolls world.

• 12:23Speaker 01

  You know, whatever brings you joy, right? Minecraft, right? Minecraft is a great example. You create, like, it's not the fancy graphics, but it's the creation of your own worlds.

• 12:32Lex Fridman?

  Yeah, that one is crazy. You know, one of the pitches for being a parent that people tell me is that you can like, use the excuse of parenting to go back into the video game world. And like, that's like, you know, father, son, father, daughter time. But really, you just get to play video games with your kids. So anyway, at that time, did you have any ridiculous ambitious dreams of where as a creator you might go? As an engineer? Did you, what did you think of yourself as, as an engineer, as a tinker? Or did you want to be like an astronaut or something like that?

• 13:07Speaker 01

  You know, I'm tempted to make something up about, you know, robots, engineering, or, you know, mysteries of the universe. But that's not the actual memory that pops into my mind when you, when you ask me about childhood dreams. So I'll actually share the real thing. When I was maybe four or five years old, I, as well do, I thought about, you know, what I wanted to do when I grow up. And I had this dream of being a traffic control cop. You know, they don't have those today, I think. But, you know, back in the eighties and, you know, in Russia, you probably are familiar with that legs. They had these, you know, police officers that would stand in the middle of intersection all day. And they would have their like striped

• 13:51Speaker 01

  back, black and white batons that they would use to, you know, control the flow of traffic. And, you know, for whatever reasons, I was strangely infatuated with this whole process. And like that, that was my dream. That's what I wanted to do when I grew up. And, you know, my parents, both physics profs, by the way, I think were, you know, a little concerned with that level of ambition coming from their child. At, you know, that age.

• 14:17Lex Fridman?

  Well, that, it's an interesting, I don't know if you can relate, but I very much loved that idea. I have an OCD nature that I think lends itself very close to the engineering mindset, which is you want to kind of. Optimize, you know, solve a problem by creating an automated solution, like a, like a set of rules, that set of rules you can follow and then thereby make it ultra-efficient. I don't know if that's, it was of that nature. I certainly have that. There's like SimCity and factory building games, all those kinds of things. Kind of speak to that engineering mindset. Or did you just like the uniform?

• 14:57Speaker 01

  I think it was more of the latter. I think it was the uniform and, you know, the this drive baton that made cars go in the right directions. That trophy. But I guess, you know, it is, I did end up, I guess, you know, working on the transportation industry one way or another.

• 15:14Lex Fridman?

  No uniform, no, but.

• 15:15Speaker 01

  That's right. Maybe, maybe it was my, you know, deep inner infatuation with the, you know, traffic control batons that led to this career.

• 15:25Lex Fridman?

  Okay, what, when did you, when was the leap from programming to robotics?

• 15:30Speaker 01

  That happened later. That was after grad school. After, and actually, you know, self-driving cars was, I think, my first real hands-on introduction to robotics. But I never really had that much hands-on experience. And, you know, in school and training, I, you know, worked on applied math and physics. Then in, you know, college, I did more of abstract computer science. And it was after grad school that I really got involved in robotics, which was actually self-driving cars. And, you know, that was a big, big flip.

• 16:02Lex Fridman?

  What, what grad school?

• 16:04Speaker 01

  So I went to grad school in Michigan and then I did a postdoc at Stanford, which is, that was the postdoc where I got to play with self-driving cars.

• 16:12Lex Fridman?

  Yeah, so we'll return there. But let's go back to, to Moscow. So I, you know, for episode 100, I talked to my dad. And also I grew up with my dad, I guess.

• 16:25Lex Fridman?

  So I had to put up with him for many years. And he, he went to the Fishtiech or M I P T. It's weird to say in English because I've heard all of this in Russian. Moscow Institute of Physics and Technology. And to me, that was like,

• 16:43Lex Fridman?

  I met some super interesting, as a child, I met some super interesting characters. It felt to me like the greatest university in the world, the most elite university in the world. And just the, the people that I met that came out of there were like.

• 16:59Lex Fridman?

  Not only brilliant, but also special humans. It seems like that place really tested the soul. Both like in terms of technically and like spiritually. So that could be just the romanticization of that place. I'm not sure, but so maybe you can speak to it. But is it correct to say that you spent some time at Physiach?

• 17:20Speaker 01

  Yeah, that's right. Six years. I got my bachelor's and master's in physics and math there. And it's actually interesting because my dad, and actually both my parents went there. And I think all the stories that I heard, like just like you, Alex, growing up about the place and how interesting and special and magical it was. I think that was a significant, maybe the main reason I wanted to go there for college. Enough so that I actually went back to Russia from the US. I graduated high school in the US.

• 17:53Lex Fridman?

  You went back there?

• 17:54Speaker 01

  I went back there, yeah.

• 17:55Lex Fridman?

  Wow.

• 17:56Speaker 01

  Exactly the reaction most of my peers in college had. But perhaps a little bit stronger that like, you know, point me out as this crazy kid.

• 18:04Lex Fridman?

  Were your parents supportive of that?

• 18:05Speaker 01

  Yeah, yeah. Like to answer your previous question, they, they supported me in letting me pursue my passions and the things that I was.

• 18:14Lex Fridman?

  That's a bold move. Wow. What was it like there?

• 18:16Speaker 01

  It was interesting. You know, definitely fairly hardcore on the fundamentals of math and physics. And you know, lots of good memories from, you know, from those times.

• 18:26Lex Fridman?

  So, okay. So Stanford, how'd you get into autonomous vehicles?

• 18:30Speaker 01

  I had the great fortune and great honor to join Stanford's DARPA Urban Challenge team in 2006. There, this was a third in the sequence of the DARPA challenges. There were two grand challenges prior to that. And then in 2007, they held the DARPA Urban Challenge. So, you know, I was doing my postdoc, I had, I joined the team and worked on motion planning for that competition.

• 19:01Lex Fridman?

  So, okay, so for people who might not know, I know from, from a certain person, autonomous vehicles is a funny world. In a certain circle of people, everybody knows everything. And then the certain circle, nobody knows anything in terms of general public. So it's interesting. It's a good question of what to talk about, but I do think that the urban challenge is worth revisiting. It's a fun little challenge, one that first like sparked so much, so many incredible minds to focus on one of the hardest problems of our time in artificial intelligence. So that's, that's a success from a perspective of a single little challenge. But can you talk about like, what did the challenge involve?

• 19:45Lex Fridman?

  So were there pedestrians, were there other cars? What was the goal? Who was on the team? How long did it take? Any fun, fun sort of specs?

• 19:56Speaker 01

  Sure, sure, sure. So the way the, the challenge was constructed and just a little bit of background. And as I mentioned, this was the third competition in that series. The first two were the grand challenge called the grand challenge. The goal there was to just drive in a completely static environment. You had to drive in a desert. That was very successful. So then DARPA followed with what they called the urban challenge, where the goal was to have, you know, build vehicles that could operate in more dynamic environments and, you know, share them with other vehicles. There were no pedestrians there. But what DARPA did is they took over an abandoned air force base. And it was kind of like a little fake city that they built out there.

• 20:38Speaker 01

  And they had a bunch of robots, you know, cars that were autonomous in there all at the same time, mixed in with other vehicles driven by professional drivers. And each car had a mission. And so there's a crude map that they received beginning and they had a mission and go, you know, here and then there and over here. And they kind of all were sharing this environment at the same time. They had to interact with each other. They had to interact with the human drivers. There's this very first, very rudimentary version of a self-driving car that could operate and on, in an environment, you know, shared with other dynamic actors.

• 21:21Speaker 01

  That, as you said, you know, really, in many ways, you know, kickstarted this whole industry.

• 21:26Lex Fridman?

  Okay, so who was on the team? And how'd you do? I forget.

• 21:33Speaker 01

  Came in second. Perhaps that was my contribution to the team. I think the Stanford team came in first in the DARPA challenge, but then I joined the team and you know.

• 21:41Lex Fridman?

  You were the one with the bug in the code. I mean, do you have sort of memories of some particularly challenging things? Or, you know, one of the cool things, it's not, you know, this isn't a product, this isn't the thing that, you know, it there's, you have a little bit more freedom to experiment. So you can take risks and there's, so you can make mistakes. So is there interesting mistakes? Is there interesting challenges that stand out to you or something like taught you a good technical lesson or a good philosophical lesson from that time?

• 22:13Speaker 01

  Yeah, definitely, definitely a very memorable time. Not really a challenge, but like one of the most vivid memories that I have from the time. And I think that was actually one of the days that really got me hooked on this whole field was the first time I got to run my software on the car. And I was working on a part of our planning algorithm that had to navigate in parking lots. So it's something that called free space motion planning. So the very first version of that was, you know, we tried on the car. It was on Stanford's campus in the middle of the night and you had this little course constructed with cones in the middle of a parking lot.

• 22:58Speaker 01

  So we're there at like 3am, you know, by the time I got the code to, you know, compile and turn over and, you know, it drove. I could actually did something quite reasonable and I was of course very buggy at the time and had all kinds of problems, but it was pretty darn magical. I remember going back and you know, later at night trying to fall asleep and just, you know, being unable to fall asleep for, you know, the rest of the night. Just my mind was blown. Just like, and that, that's what I've been doing ever since for more than a decade. In terms of challenges and, you know, interesting memories, like on the day of the competition, it was pretty nerve wracking.

• 23:40Speaker 01

  I remember standing there with Mike Montemarila, who was the software lead and wrote most of the code. I did one little part of the planner. Mike incredibly did pretty much the rest of it with, you know, a bunch of other incredible people. But I remember standing on the day of the competition, you know, watching the car with Mike and cars are. Completely empty, right? They're all there lined up in the beginning of the race. And then DARPA sends them on their mission, one by one, so then leave. And like you just, they had these sirens, they all had their different silence, silence, right? Each siren had its own personality, if you will. So, you know, off they go and you don't see them just kind of. And then every once in a while, they, you know, come a little bit closer to where the audiences.

• 24:23Speaker 01

  And you can kind of hear, you know, the sound of your car and, you know, it seems to be moving along. So that, you know, gives you hope. And then, you know, it goes away and you can't hear it for too long. You start getting anxious, right? It's a little bit like, you know, sending your kids to college and like, you know, kind of you invested in them. You hope you, you, you, you, you, you build it properly, but like it's still anxiety inducing. So that was an incredibly fun few days. In terms of, you know, bugs, as you mentioned, you know, one that was my bug that caused us the loss of the first place. Still a debate that you occasionally have with people on the CMU team. CMU came first, I should mention that.

• 24:59Lex Fridman?

  See, you haven't heard of them.

• 25:00Speaker 01

  But yeah, no, it's some, you know, it's a small school. It's, it's, it's, yeah, the really glitch that, you know, they happen to succeed at something robotics related.

• 25:07Lex Fridman?

  Very scenic though. Most people go there for the scenery. Yeah, it's a beautiful campus.

• 25:15Speaker 01

  I apologize. Unlike Stanford.

• 25:16Lex Fridman?

  So for people, yeah, that's true. Unlike Stanford, for people who don't know, CMU is one of the great robotics and sort of artificial intelligence universities in the world. CMU Carnegie Mellon University. Okay, sorry, go ahead.

• 25:28Speaker 01

  Good, good PSA. So in the part that I contributed to, which was navigating parking lots. And the way, you know, that part of the mission worked is you, in a parking lot, you would get from DARPA. An outline of the map, you basically get this, you know, giant polygon that defined the perimeter of the parking lot. And there would be an entrance and, you know, so maybe multiple entrances or exits to it. And then you would get a goal within that open space, X, Y, you know, heading where the car had to park. It had no information about the optical, so obstacles that the car might encounter there. So it had to navigate kind of completely free space from the entrance to the parking lot into that parking space.

• 26:13Speaker 01

  And then, uh, once parked there, it had to exit the parking lot. While of course encountering and reasoning about all the obstacles that it encounters in real time. So, uh,

• 26:28Speaker 01

  Our interpretation, or at least my interpretation of the rules, was that you had to reverse out of the parking spot. And that's what our cars did, even if there's no obstacle in front. That's not what CMU's car did. And it just kind of drove right through. So there's still a debate. And of course, you know, if you stop and then reverse out and go out the different way, that costs you some time. And so there's still a debate whether, you know, it was my poor implementation that cost us extra time, or whether it was, you know, CMU violating an important rule of the competition. And, you know, I have my own opinion here. In terms of other bugs, and like, I have to apologize to Mike Montemara for sharing this on air. But it is actually one of the more memorable ones. And it's

• 27:09Speaker 01

  something that's kind of become a bit of a metaphor and a label in the industry since then, I think, at least in some circles. It's called the victory circle, or victory lap. And our cars did that. So in one of the missions in the urban challenge, in one of the courses, there was this big oval right by the start and finish of the race. So DARPA had, a lot of the missions would finish in that same location. And it was pretty cool because you could see the cars come by, you know, kind of finish that part leg of the trip, that leg of the mission, and then, you know, go on and finish the rest of it. And other vehicles would, you know, come, hit their waypoint, and, you know, exit

• 27:53Speaker 01

  the oval, and off they would go. Our car, on the hand, which hit the checkpoint, and then it would do an extra lap around the oval, and only then, you know, leave and go on its merry way. So over the course of, you know, the full day, it accumulated some extra time. And the problem was that we had a bug where it wouldn't, you know, start reasoning about the next waypoint and plan a route to get to that next point until it hit a previous one. And in that particular case, by the time you hit that one, it was too late for us to consider the next one and kind of make a lane change. So every time it would do like an extra lap. So, you know, that's the Stanford victory lap.

• 28:25Lex Fridman?

  Oh, there's, I feel like there's something philosophically profound in there somehow. But, I mean, ultimately, everybody is a winner in that kind of competition. And it led to sort of famously to the creation of Google Self Driving Car Project and now Waymo. So can we give an overview of how was Waymo born? How is the Google Self Driving Car Project born? What is the mission? What is the hope? What is it is the engineering kind of set of milestones that it seeks to accomplish? There's a lot of questions in there.

• 29:06Speaker 01

  Yeah. But you're right. Kind of the DARPA Urban Challenge and the previous DARPA Grand Challenges kind of led, I think, to a very large degree to that next step. And then Larry and Sergey, Larry Page and Sergey Brin, Google founders, of course, saw that competition and believed in the technology. So the Google Self Driving Car Project was born. You know, at that time, and we started in 2009. It was a pretty small group of us, about a dozen people, who came together to work on this project at Google. At that time, we saw that incredible early result in the DARPA Urban Challenge.

• 29:48Speaker 01

  I think we're all incredibly excited about where we got to. And we believed in the future of the technology, but we still had a very rudimentary understanding of the problem space. So the first goal of this project in 2009 was to really better understand what we're up against. And with that goal in mind, when we started the project, we created a few milestones for ourselves that maximized learning. Well, the two milestones were, you know, one was to drive 100,000 miles in autonomous mode, which was at that time, you know, orders of magnitude, more than anybody has ever done.

• 30:30Speaker 01

  And the second milestone was to drive 10 routes. Each one was 100 miles long. They were specifically chosen to be kind of extra spicy and extra complicated and sample the full complexity of the that that domain. And you had to drive each one from beginning to end with no intervention, no human intervention. So you would get to the beginning of the course, you would press the button that engage autonomy, and you had to go for a hundred miles, beginning to end with no interventions. And it sampled again, the full complexity of driving conditions. Some were on freeways.

• 31:12Speaker 01

  We had one route that went all through all the freeways and all the bridges in the Bay Area. You know, we had some that went around Lake Tahoe and kind of mountains roads. We had some that drove through dense urban environments like in downtown Palo Alto and through San Francisco. So it was incredibly interesting to work on. And it took us just under two years, about a year and a half, a little bit more, to finish both of these milestones. And in that process, A, it was an incredible amount of fun, probably the most fun I had in my professional career. And you're just learning so much. You are, you know, the goal here is to learn and prototype.

• 31:56Speaker 01

  You're not yet starting to build a production system, right? So you just, you were, you know, this is when you're kind of, you know, working 24/7 and you're hacking things together.

• 32:04Lex Fridman?

  And you also don't know how hard this is. I mean, that's the point. Like, so, I mean, that's an ambitious, if I put myself in that mindset, even still, that's a really ambitious set of goals. Like, just those two, picking, picking 10 different, difficult, spicy challenges and then having zero interventions. So like, not saying gradually, we're going to, like, you know, over a period of 10 years, we're going to have a bunch of routes and gradually reduce the number of interventions, you know, that literally says like, by as soon as possible, we want to have zero and on hard roads.

• 32:48Lex Fridman?

  So like, to me, if I was facing that, it's unclear that whether that takes two years or whether that takes 20 years.

• 32:56Speaker 02

  It took us under two.

• 32:57Speaker 01

  I guess that speaks to a really big difference between doing something once and having a prototype, where you're going after, you know, learning about the problem versus how you go about engineering a product that, you know, where you look at, you know, you do properly do evaluation, you look at metrics, you, you know, drive dog and you're confident that you can do that a hundred. And I guess that's the, you know, why it took a dozen people, you know, 16 months or a little bit more than that, back in 2009 and 2010 with the technology of, you know, the more than a decade ago, that amount of time to achieve that milestone of 10 routes, 100 miles each

• 33:40Speaker 01

  and no interventions. And, you know, it took us a little bit longer to get to, you know, a full driverless product that customers use.

• 33:50Lex Fridman?

  That's another really important moment. Is there some memories of technical lessons? Or just one, like, what did you learn about the problem of driving from that experience? I mean, we could, we can now talk about like what you learned from modern day Waymo, but I feel like you may have learned some profound things in those early days even more so, because it feels like what Waymo is now is to trying to, you know, how to do scale, how to make sure you create a product, how to make sure it's like safety and all those things, which is all fascinating challenges. But like you were facing the more fundamental philosophical problem of driving in those early days. Like, what the hell is driving?

• 34:36Lex Fridman?

  As an autonomous, or maybe I'm again romanticizing it, but is, is there, is there some valuable lessons you picked up over there at those two years?

• 34:49Speaker 01

  A ton. The most important one is probably that we believe that it's doable. And we've gotten far enough into the problem that, you know, we had a, I think, only a glimpse of the true complexity of the domain. You know, it's a little bit like, you know, climbing a mountain where you kind of, you know, see the next peak and you think that's kind of the summit, but then you get to that and you kind of see that that this is just the start of the journey. But we've tried, we've sampled enough of the problem space and we've made enough rapid success, even, you know, with technology of 2009, 2010, that it gave us confidence to then, you know, pursue this as a real product.

• 35:34Lex Fridman?

  So, okay, so the next step, you mentioned the milestones that you had in those two years. What are the next milestones that then led to the creation of Waymo and beyond?

• 35:45Speaker 01

  Yeah, it was a really interesting journey and, you know, Waymo came a little bit later. Then, you know, we completed those milestones in 2010. That was the pivot when we decided to focus on actually building a product, you know, using this technology. The initial couple of years after that, we were focused on a freeway, you know, what you would call a driver assist, maybe on an L3 driver assist program. Then around 2013, we've learned enough about the space and have thought more deeply about, you know, the product that we wanted to build, that we pivoted.

• 36:26Speaker 01

  We pivoted towards this vision of, you know, building a driver and deploying it fully driverless vehicles without a person and that that's the path that we've been on since then. And very, it was exactly the right decision for us.

• 36:40Lex Fridman?

  So there was a moment where you also considered like, what is the right trajectory here? What is the right role of automation in the, in the task of driving? There was still.

• 36:50Lex Fridman?

  It wasn't from the early days obvious that you want to go fully autonomous.

• 36:53Speaker 01

  From the early days it was not. I think it was in 20, around 2013, maybe that we've, that became very clear and we made that pivot and it also became very clear and that it's the way you go building a driver assist system is fundamentally different from how you go building a fully driverless vehicle. So we've pivoted towards the latter and that's what we've been working on ever since. And so that was around 2013. Then there's a sequence of really meaningful for us, really important defining milestones since then. And 2015, we had our

• 37:37Speaker 01

  first, actually the world's first, fully driverless ride on public roads. It was in a custom-built vehicle that we had. You must have seen those. We called them the Firefly, that funny-looking, marshmallow-looking thing. And we put a passenger, his name was Steve Mann, a great friend of our project from the early days. The man happens to be blind, so we put him in that vehicle. The car had no steering wheel, no pedals. It was an uncontrolled environment, no lead or chase cars, no police escorts. And we did that trip a few times in Austin, Texas. So that was a really big milestone.

• 38:19Lex Fridman?

  But that was in Austin?

• 38:20Speaker 01

  Yeah.

• 38:21Lex Fridman?

  Cool. Okay.

• 38:23Speaker 01

  And we only, but at that time, we're only, it took a tremendous amount of engineering. It took a tremendous amount of validation to get to that point. But we only did it a few times. We only did that. It was a fixed route. It was not kind of a controlled environment, but it was a fixed route and we only did it a few times. Then in 2016, end of 2016, beginning of 2017 is when we founded Waymo, the company. That's when we, that was the next phase of the project where I wanted, we believed in the commercial vision of this technology and it made sense to create an independent entity within that Alphabet umbrella

• 39:05Speaker 01

  to pursue this product at scale. Beyond that, in 2017, later in 2017, was another really

• 39:14Speaker 01

  A huge step for us, really big milestone where we started, I think it was October of 2017, where when we started regular driverless operations on Public Rose, that first day of operations, we drove in one day, in that first day, 100 miles in driverless fashion. And then we've, the most, the most important thing about that milestone was not that 100 miles in one day, but that it was the start of kind of regular, ongoing driverless operations.

• 39:45Lex Fridman?

  And when you say driverless, it means no driver?

• 39:49Speaker 01

  That's exactly right. So on that first day, we actually hit a mix and up in some, we didn't want to like, you know, be on YouTube and Twitter that same day. So in, in many of the rides, we had somebody in the driver's seat, but they could not disengage, like the car could not disengage. But in actually, on that first day, some of the miles were driven and just completely empty driver's seat.

• 40:12Lex Fridman?

  And this is the key distinction that I think people don't realize is, you know, that oftentimes when you talk about autonomous vehicles, you're, there's often a driver in the seat that's ready to, to take over what's called a safety driver. And then Waymo is really one of the only companies, at least that I'm aware of, or at least as like boldly and carefully and all, and all that is actually has cases. And now we'll talk about more and more where there's literally no driver. So that's another, the interesting case of where the driver's not supposed to disengage. That's like a nice middle ground. They're still there, but they're not supposed to disengage.

• 40:56Lex Fridman?

  But really there's the case when there's no, okay. There's something magical about there being nobody in the driver's seat.

• 41:06Lex Fridman?

  Like, just like to me, you mentioned the first time you wrote some code for free space navigation of the parking lot, that was like a magical moment. To me, just sort of as an observer of robots, the first magical moment is seeing an autonomous vehicle turn, like make a left turn, like, apply sufficient torque to the steering wheel to where like there's a lot of rotation. And for some reason, and there's nobody in the driver's seat, for some reason that that communicates that here's a being with power that makes a decision. There's something about like the steering wheel, because we perhaps romanticize the

• 41:51Lex Fridman?

  notion of the steering wheel. It's so essential to the conception, our 20th century conception of a car. And it turning the steering wheel with nobody in driver's seat, that to me, I think maybe to others, it's really powerful. Like, this thing is in control. And then there's this leap of trust that you give, like, I'm gonna put my life in the hands of this thing that's in control. So in that sense, when there's no but no driver in the driver's seat, that's a magical moment for robots. So I'm, I got a chance to last year to take a ride in a Waymo vehicle. And that that was the magical moment. There's like, nobody in the driver's seat. It's like the little details. You would think it doesn't

• 42:35Lex Fridman?

  matter whether there's a driver or not. But like, if there's no driver, and the steering wheel is turning on its own, I don't know, that's magical.

• 42:45Speaker 01

  It's absolutely magical. Like, I've taken many of these rides in a completely empty car. No human in the car pulls up. You know, you call it on your cell phone, it pulls up, you get in, it takes you on its way. There's nobody in the car but you, right? That's something called, you know, fully driverless, our rider only mode of operation. Yeah, it is magical. It is transformative. This is what we hear from our writers. It really changes your experience. And like, that that really is what unlocks the real potential of this technology. But coming back to our journey, that was 2017 when we started truly driverless

• 43:29Speaker 01

  operations. Then in 2018, we've launched our public commercial service that we called Waymo One in Phoenix. In 2019, we started offering truly driverless rider only rides to our early rider population of users. And then 2020 has also been a pretty interesting year, one of the first one, less about technology, but more about the maturing and the growth of Waymo as a company. We raised our first round of external financing this year. We were part of Alphabet,

• 44:10Speaker 01

  so obviously we have access to significant resources. But as kind of on the journey of Waymo maturing as a company, it made sense for us to partially go externally in this round. So we raised about $3.2 billion from that round. We've also started putting our fifth generation of our driver, our hardware, that is on the new vehicle, but it's also a qualitatively different set of self-driving hardware that is now on the JLR pace. So that was a very important

• 44:47Lex Fridman?

  step for us. Hardware specs, fifth generation. I think it'd be fun, maybe, I apologize if I'm interrupting, but maybe talk about maybe the generations with a focus on what we're talking about in the fifth generation in terms of hardware specs, like what's on this car?

• 45:07Speaker 01

  Sure. So we separated the actual car that we are driving from the self-driving hardware we put on it. Right now, we have, so this is, as I mentioned, the fifth generation. We've gone through, we started building our own hardware many, many years ago.

• 45:25Speaker 01

  That Firefly vehicle also had the hardware suite that was mostly designed, engineered and built in-house. Lighters are one of the more important components that we design and build from the ground up. So on the fifth generation of our drivers of our self-driving hardware that we're switching to right now, we have, as with previous generations, in terms of sensing, we have lighters, cameras and radars. And we have a pretty beefy computer that processes all that information and makes decisions in real time onboard the car.

• 46:05Speaker 01

  So in all of the, and it's really a qualitative jump forward in terms of the capabilities and various parameters and aspects of the hardware compared to what we had before and compared to what you can get off the shelf in the market today.

• 46:22Lex Fridman?

  Meaning from fifth to fourth or from fifth to first?

• 46:25Speaker 01

  Definitely from first to fifth, but also from the

• 46:27Lex Fridman?

  That was the world's dumbest question.

• 46:29Speaker 01

  Definitely, definitely from fourth to fifth, as well as this, the last step is a big step forward.

• 46:37Lex Fridman?

  So everything's in-house, so like lidars built in-house and cameras are built in-house?

• 46:45Speaker 01

  It's different. We work with partners. There are some components that we get from our manufacturing and supply chain partners. What exactly is in-house is a bit different. We do a lot of custom design on all of our sensing models, lighters, radars, cameras. Exactly, there's, lighters are almost exclusively in-house and some of the technologies that we have, some of the fundamental technologies there are completely unique to Waymo. That is also largely true about radars and cameras. It's a little bit more of a mix in terms of what we do ourselves versus what we get from partners.

• 47:27Lex Fridman?

  Is there something super sexy about the computer that you can mention that's not top secret?

• 47:35Lex Fridman?

  For people who enjoy computers for, I mean, uh, so there's, there's a lot of machine learning involved, but there's a lot of just basic compute. There's, you have to, uh, probably do a lot of signal processing on all the different sensors. You have to integrate everything has to be in real time. There's probably some kind of redundancy type of situation. Is there something interesting you could say about the computer for the people who love hardware?

• 48:00Speaker 01

  It does have all of the characteristics, all the properties that you just mentioned. Uh, redundancy, uh, very beefy compute, uh, for general processing as well as, you know, inference and ML models. It is some of the more sensitive stuff that, you know, I don't want to get into for IP reasons, but yeah, it can, we've shared a little bit, uh, in terms of the specs of the sensors, uh, that we have on the car. You know, we actually shared, you know, some videos of, uh, what are lighter sees, uh, lighters see in the world. Uh, we have 20 line cameras. We have five lighters. We have six raiders, uh, on these vehicles and you can kind of get a feel for the amount of data that they're producing

• 48:41Speaker 01

  that all has to be processed in real time, uh, to, you know, do perception, to do complex reasoning. Then kind of gives you some idea of how beefy those computers are, but I don't want to get into specifics of exactly how we build them.

• 48:52Lex Fridman?

  Okay. Well, let me try some more questions that you can get into the specifics of like GPU wise, is that something you can get into? You know, I know that Google works that with TPUs and so on. I mean, for machine learning folks, it's kind of interesting. Or is there no? How do I ask it? Uh, I've been talking to people in the government about UFOs and they don't answer any questions. So this is, this is how I feel right now, asking about GPUs. But is there something interesting that you could reveal or is it just, you know, uh, or would leave it up to our imagination, some of, some of the compute? Is there any, I guess, is there any fun trickery? Like I talked to Chris Latner for a second time

• 49:35Lex Fridman?

  and he was a key person about TPUs and there's a lot of fun stuff going on in Google in terms of, uh, hardware that it optimizes for machine learning. Is there something you can reveal in terms of how much, you mentioned customization, how much customization there is for hardware for machine learning purposes?

• 49:55Speaker 01

  I'm going to be like that government, you know, you've got a person about UFOs, but I, you know. I guess I will say that it's really compute is really important. We have very data hungry and compute hungry ML models of all over our stack. And this is where, you know,

• 50:18Speaker 01

  both being part of Alphabet as well as designing our own sensors and the entire hardware suite together, where on one hand you get access to like really rich raw sensor data that you can pipe from your sensors

• 50:34Speaker 01

  into your compute platform and build like build the whole pipe from sensor raw sensor data to the big compute as then have the massive compute to process all that data. This is where we're finding that having a lot of control of that hardware part of the stack is really advantageous.

• 50:52Lex Fridman?

  One of the fascinating magical places to me, again, might not be able to speak to the details, but is the it is the other compute, which is like, you know, this, we're just talking about a single car. But the, you know, the driving experience is a source of a lot of fascinating data. And you have the huge amount of data coming in on the car on the car. And, you know, the infrastructure of storing some of that data to then train or to analyze or so on. That's a fascinating like piece of it that that I understand a single car. I don't understand how you pull it all together in a nice way. Is that something that you could speak to in terms of the challenges of

• 51:35Lex Fridman?

  of seeing the network of cars and then bringing the data back and analyzing things that like, like edge cases of driving, be able to learn on them to improve the system to to see where things went wrong, where where things went right and analyze all that kind of stuff. Is there something interesting there in the from an engineering perspective?

• 51:55Speaker 01

  Oh, there's an incredible.

• 51:59Speaker 01

  Amount of really interesting work that's happening there, both in the real time operation of the fleet of cars and the information that they exchange with each other in real time to make better decisions, as well as the kind of the off board component, where you have to deal with massive amounts of data for training your ML models, evaluating the ML models, for simulating the entire system and for evaluating your entire system. And this is where being part of Alphabet has once again been tremendously advantageous. I think we consume an incredible amount of compute for ML infrastructure. We build a lot of custom frameworks to get good at

• 52:43Speaker 01

  on data mining, finding the interesting edge cases for training and for evaluation of the system, for both training and evaluating some components and your sub parts of the system and various ML models, as well as evaluating the entire system in simulation.

• 53:00Lex Fridman?

  Okay, that first piece that you mentioned, that cars communicating to each other essentially, I mean, through perhaps through a centralized point. But what, that's fascinating, too. How much does that help you? Like, if you imagine, you know, right now, the number of way more vehicles is whatever X. I don't know if you can talk to what that number is, but it's not in the hundreds of millions yet. And imagine if the whole world is way more vehicles. Like, that changes potentially the power of connectivity. Like, the more cars you have, I guess, actually, if you look at Phoenix, because there's enough vehicles, there's enough, when there's like some level of density, you can start to probably do some really interesting stuff

• 53:44Lex Fridman?

  with the fact that cars can negotiate, can be, can communicate with each other and thereby make decisions. Is there something interesting there that you can talk to about? Like, how does that help with the driving problem from, as compared to just a single car solving the driving problem by itself?

• 54:05Speaker 01

  Yeah, it's a spectrum. First, I'd say that it helps. And it helps in various ways, but it's not required. Right now, the way we build our system, like each cars can operate independently. They can operate with no connectivity. So I think it is important that you have a fully autonomous, fully capable driver, that computerized driver that each car has. Then they do share information and they share information in real time. It really, really helps. So the way we do this today is whenever one car encounters something interesting in the world, whether it might be an accident or a new construction zone,

• 54:48Speaker 01

  that information immediately gets uploaded over the air and is propagated to the rest of the fleet. So and that's kind of how we think about maps as priors in terms of the knowledge of our drivers, of our fleet of drivers, that is distributed across the fleet and it's updated in real time. So that's one use case. You can imagine as the density of these vehicles go up, that they can exchange more information in terms of what they're planning to do and start influencing how they interact with each other, as well as potentially sharing some observations to help with. If you have enough density of these vehicles where one car might be seeing something

• 55:33Speaker 01

  that another is relevant to another car, that is very dynamic. It's not part of your updating your static prior of the map of the world, but it's more of a dynamic information that could be relevant to the decisions that another car is making in real time. So you can see them exchanging that information and you can build on that. But again, I see that as an advantage, but it's not a requirement.

• 55:54Lex Fridman?

  So what about the human in the loop? So when I got a chance to drive with a ride in a Waymo, you know, there's customer service. So like there is somebody that's able to dynamically like tune in and help you out. What role does the human play in that picture? That's a fascinating, like, you know, the idea of teleoperation, be able to remotely control a vehicle. So here what we're talking about is like.

• 56:30Lex Fridman?

  Like frictionless, like a human being able to in a frictionless way sort of help you out? I don't know if they're able to actually control the vehicle. Is that something you could talk to?

• 56:42Speaker 01

  Yes.

• 56:42Lex Fridman?

  Okay.

• 56:43Speaker 01

  To be clear, we don't do teleoperation. I kind of believe in teleoperation for rare reasons. That's not what we have in our cars. We do, as you mentioned, have a version of customer support. We call it life health. In fact, we find that it's very important for our rider experience, especially if it's your first trip. You've never been in a fully driverless rider only Waymo vehicle. You get in, there's nobody there. And so you can imagine having all kinds of questions in your head, like how this thing works. So we've put a lot of thought into kind of guiding our riders, our customers through that experience, especially for the first time. They get some information on the phone. If the fully driverless vehicle is used to service their trip.

• 57:26Speaker 01

  When you get into the car, we have an in-car screen and audio that kind of guides them and explains what to expect. They also have a button that they can push that will connect them to a real life human being that they can talk to. All right, about this whole process. So that's one aspect of it. There is, I should mention that there is another function that humans provide to our cars, but it's not teleoperation. You can think of it a little bit more like fleet assistance, kind of like traffic control that you have. Where our cars, again, they're responsible on their own for making all of the decisions, all of the driving decisions that don't require connectivity.

• 58:09Speaker 01

  They, anything that is safety or latency critical is done purely autonomously by onboard our onboard system. But there are situations where if connectivity is available, a car encounters a particularly challenging situation. You can imagine like a super hairy scene of an accident. The cars will do their best, they will recognize that it's an off nominal situation. They will do their best to come up with the right interpretation, the best course of action in that scenario. But if connectivity is available, they can ask for confirmation from a human, assistant to confirm those actions. And perhaps provide a little bit of contextual information and guidance.

• 58:52Lex Fridman?

  So October 8th was when you're talking about the, was Waymo launched the? The the fully self, the the public version of its fully driverless, that's the right term, I think, service in Phoenix. Is that October 8?

• 59:10Speaker 01

  That's right. It was the introduction of fully driverless rider only vehicles into our public Waymo One service.

• 59:16Lex Fridman?

  Okay, so that's, that's amazing. So it's like anybody can get into Waymo in Phoenix?

• 59:22Speaker 01

  That's right. So we previously had early people in our early rider program taking fully driverless rides in Phoenix. And just this, a little while ago, we opened on October 8, we opened that mode of operation to the public. So I can download the app and go on a ride. There is a lot more demand right now for that service than we have capacity. So we're kind of managing that. But that's exactly the way you described it.

• 59:51Lex Fridman?

  Yeah, well, that's interesting. So there's more demand than you can, you can handle? Like what, what has been reception so far? Like what, I mean, okay, so, you know, that's, this is a product, right? That's a whole nother discussion of like how compelling of a product it is. Great. But it's also like one of the most kind of transformational technologies of the 21st century. So it's also like a tourist attraction. Like it's fun to, you know, to be a part of it. So it'd be interesting to see like, what do people say? What do people, what have been the feedback so far?

• 1:00:28Speaker 01

  Still early days, but so far the feedback has been incredible, incredibly positive. They, we asked them for feedback during the ride. We asked them for feedback after the ride as part of their trip. We asked them some questions. We asked them to rate the performance of our driver. Most, by far, most of our drivers give us five stars in our app, which is absolutely great to see. And that's, and they're also giving us feedback on things we can improve. And that's one of the main reasons we're doing this in Phoenix and over the last couple of years. And every day today, we are just learning a tremendous amount of new stuff from our users. There's, there's no substitute for actually doing the real

• 1:01:11Speaker 01

  thing, actually having a fully driverless product out there in the field with users that are actually paying us money to get from point A to point B.

• 1:01:19Lex Fridman?

  So this is a legitimate, like, it's a paid service.

• 1:01:22Speaker 01

  That's right.

• 1:01:24Lex Fridman?

  And the idea is you use the app to go from point A to point B. And then what are the As? What are the, what's the freedom of the, of the starting and ending places?

• 1:01:35Speaker 01

  It's an area of geography where that service is enabled. It's a decent size of geography of territory. It's actually larger than, than size of San Francisco. And, you know, within that, you have full freedom of selecting where you want to go. You know, of course, there's some, and you, on your app, you get a map. You tell the car where you want to be picked up. You know, where you want, you know, the car to pull over and pick you up. And then you tell it where you want to be dropped off. All right. And of course, there are some exclusions, right? You don't want to be, you know, where, in terms of where the car is allowed to pull over. Right. So, you know, that you can do. But, you know, besides that, it's

• 1:02:12Lex Fridman?

  Amazing.

• 1:02:13Speaker 01

  It's not like a fixed, just would be very, I guess, I don't know. Maybe that's what's the question behind your question. But it's not a, you know, preset set of destinations.

• 1:02:20Lex Fridman?

  So within the geographic constraints with that, within that area, anywhere else, it can be, you can be picked up and dropped off anywhere.

• 1:02:27Speaker 01

  That's right. And, you know, people use them on like all kinds of trips. They, we have, and we have an incredible spectrum of riders. I think the youngest actually have car seats to them. And we have, you know, people taking their kids on rides. I think the youngest riders we had on the cars are, you know, one or two years old. You know, and the full spectrum of use cases. People, you can take them to, you know, schools, to, you know, go grocery shopping, to restaurants, to bars, you know, run errands, you know, go shopping, et cetera, et cetera. You can go to your office, right? Like the full spectrum of use cases. And people, you're going to use them in their daily lives to get around. And we see all kinds of, you know, really interesting use cases. And that, that, that's providing us incredibly valuable experience

• 1:03:11Speaker 01

  that we then, you know, use to improve our product.

• 1:03:14Lex Fridman?

  So as somebody who's been on, done a few long rants with Joe Rogan and others about the toxicity of the internet and the comments and the negativity in the comments, I'm fascinated by feedback. I, I believe that most people Are good and kind and intelligent and can provide like even in disagreement, really fascinating ideas. So on a product side, it's fascinating to me like, how do you get the richest possible user feedback like to improve? What's what are the channels that you use to measure? Cause like you're you're no longer.

• 1:03:56Lex Fridman?

  That's one of the magical things about autonomous vehicles is it's not like it's frictionless interaction with the human. So like you don't get to, you know, it's just giving a ride. So like, how do you get feedback from people to in order to improve?

• 1:04:10Speaker 01

  Oh, yeah. Great question. Various mechanisms. So as part of the normal flow, we ask people for feedback. They as the car is driving around, we have on the phone and in the car and we have a touchscreen in the car. You can actually click some buttons and provide real time feedback on how the car is doing and how the car is handling a particular situation, both positive and negative. So that's one channel. We have, as we discussed, customer support or life help where if a customer wants to has a question or he has some sort of concern, they can talk to a person in real time. So that that is another mechanism that gives us feedback. At the end of a trip, we also ask them how things went. They give us

• 1:04:53Speaker 01

  comments and you know, star rating and you know, if it's we also ask them to explain what went well and what could be improved. And we have our writers are providing very rich feedback. They're a lot, a large fraction is very passionate, very excited about this technology. So we get really good feedback. We also run UXR studies, right? Specific that are kind of more, you know, go more in depth and we will run both kind of lateral and longitudinal studies where we have deeper engagement with our customers. We have our user experience research team.

• 1:05:34Lex Fridman?

  Tracking over time, that's what I'm saying about longitudinal is cool.

• 1:05:37Speaker 01

  That's that's exactly right. And that's another really valuable. Uh, feedback, a source of feedback. And we're just covering a tremendous amount, right? People go grocery stropping and they like wanna load, you know, twenty bags of groceries in our cars. And like, that's one workflow that you maybe don't, you know, think about, uh, you know, getting just right when you're building the driverless product. I have people like, you know, who, uh, bike as part of their trip. So they, you know, bike somewhere, then they get in our cars, they take a part of their bike, they load into our vehicle, then they go, and that's, you know, how they, you know, where we wanna pull over and how that, you know, uh, get in and get out, um, uh, process works, provides you a very useful feedback.

• 1:06:20Speaker 01

  In terms of, you know, what makes a good pickup and drop off location, uh, we get really valuable feedback. And in fact, we had to, um, uh, do some really interesting work with high definition maps and, uh, thinking about walking directions. And if you imagine you're in a store, right, in some giant space, and then, you know, you wanna be picked up somewhere. If you just drop a pin at a current location, which is maybe in the middle of a shopping mall, like, what's the best location for the car to come pick you up? And you can, you know, have simple heuristics where you're just gonna take your, you know, your cleaning distance, uh, and find the nearest, uh, spot where the car can pull over that's closest to you, but oftentimes that's not the most convenient one. You know, I have many anecdotes where that heuristic breaks in horrible ways.

• 1:07:02Speaker 01

  Uh, one example, uh, that, you know, I often mention is, uh, somebody wanted to be, you know, uh, dropped off, uh, in Phoenix, uh, and, you know, we, the car picked a location, uh, that was close, the closest to there, you know, where the pin was dropped, uh, on the map in terms of, you know, latitude and longitude. Uh, but it happened to be on the other side of a parking lot that had this row of cacti, and the poor person had to like walk all around the parking lot to get to where they wanted to be in a hundred and ten degree heat. So that, you know, that was a bummer. So then, you know, we took all, take all of these, um, all of that feedback from our users and, uh, incorporate it into our system and, you know, and improve it.

• 1:07:43Lex Fridman?

  Yeah, I feel like that's like requires AGI to solve the problem of like, when you're, which is a very common case, when you're in a big space of some kind, like apartment building, it doesn't matter, it's some large space, and then you call the, like, the Waymo from there, right? Like, and you, whatever, it doesn't matter, rideshare vehicle, and like, where is the pin supposed to drop?

• 1:08:09Lex Fridman?

  I feel like that's, I, you don't think, I think that requires AGI. I'm gonna, in order to solve, okay, the alternative, which I think the Google search engine is taught, is like, there's something really valuable about the perhaps slightly dumb answer, but a really powerful one, which is like, what was done in the past by others? Like, what was the choice made by others? That seems to be, like, in terms of Google search, when you have like billions of searches, you could, you could see which, like, when they recommend what you might possibly mean, they suggest based on, not some machine learning thing, which they also do, but like, on what was successful for others in the past and finding a thing that they were happy with.

• 1:08:54Lex Fridman?

  Is that integrated at all with Waymo, like, what, what pickups worked for others?

• 1:09:00Speaker 01

  It is. I, I think you're exactly right. So there's, uh, really, it's an interesting problem. Uh, naive solutions, uh, have, yeah, uh, interesting failure modes. Uh, so there's definitely lots of things that can be done to improve. Uh, and both learning from, you know, what works, but doesn't work in actual, you know, getting richer data and getting more information about the environment and, you know, uh, richer maps. Uh, but you're absolutely right that there's something, and there's some properties of solutions that, uh, in terms of the effect that they have on users, so much, much, much, much better than others, right? And predictability and understandability is important. So you can have maybe something that is not quite as optimal,

• 1:09:45Speaker 01

  but is very natural and predictable, uh, to the user and kind of works the same way, uh, all the time. And that matters. That matters a lot for the user experience. And, and, but, you know, to get to the basics, the pretty fundamental property is that the car actually arrives where you told it to ride. Like, you can always, you know, change it, see it on the map, and you can move it around if you don't like it. And, but like, that property that the car actually shows up on the pin is critical, which, you know, where, uh, compared to some of the Human driven.

• 1:10:20Lex Fridman?

  Yes.

• 1:10:20Speaker 01

  Analogues, I think, you know, you could have more predictability. It's actually the fact, if I have, I might do a little bit of a detour here. I think the fact that it's, you know, your phone and the cars, two computers talking to each other can lead to some really interesting things we can do in terms of the user interfaces. Both in terms of function, like the car actually shows up exactly where you told it you want it to be. But also some, you know, really interesting things on the user interface. Like as the car is driving, as you, you know, call it and it's on the way to come and pick you up. And of course you get the position of the car and the route on the map. But, and they actually follow that route, of course. But it can also share some really interesting information about what it's doing. So, you know, our cars, as they are coming to pick you up.

• 1:11:05Speaker 01

  If it's come, if a car is coming up to a stop sign, it will actually show you that like it's there sitting because it's at a stop sign or a traffic light will show you that it's got, you know, sitting at a red light. So, you know, the little things, right? But it, I find those little touches, touches really interesting, really magical. And it's just, you know, little things like that, that you can do to kind of delight your users.

• 1:11:28Lex Fridman?

  You know, this makes me think of, um, there's some products that I just love. Like there's a, there's a company called Rev, rev.com. Where I like for this podcast, for example, like it's drag and drop a video. And then they do all the captioning. It's humans doing the captioning, but they connect you, they automate, automate everything of connecting you to the humans. And they do the captioning and transcription, it's all effortless. And it like, I remember when I first started using them, it was like,

• 1:12:03Lex Fridman?

  life is good, like, because it was so painful to, to figure that out earlier. The same thing with something called Isotope RX. This company I use for cleaning up audio, like the sound cleanup they do. It's like drag and drop and it just cleans everything up very nicely. Another experience like that, Ed, with Amazon one click purchase. First time, I mean, other places do that now, but just the effortlessness of purchasing, making it frictionless. It kind of communicates to me, like I'm a fan of design, I'm a fan of products. That you can just create a really pleasant experience that the simplicity of it, the elegance just makes you fall in love with it. So on the, do you think about this kind of stuff?

• 1:12:48Lex Fridman?

  I mean, we've been, that's exactly what we've been talking about. It's like the little details that somehow make you fall in love with the product. Is that, we went from like urban challenge days where, where love was not part of the conversation probably, and to this point where there's a, where there's human beings and you want them to fall in love with the experience. Is that something you're trying to optimize for, trying to think about like how do you, how do you create experience that people love?

• 1:13:17Speaker 01

  Absolutely. I think that's, the vision is removing any friction or complexity from getting our users, our riders to where they want to go. Making that as simple as possible. And then, you know, beyond that, just transportation, making, you know, things and, you know, goods get to their destination as seamlessly as possible. I talked about, you know, a drag and drop experience where I kind of express your intent and then, you know, it just magically happens. And for our riders, that's what we're trying to get to is you download an app and you click and car shows up. It's the same car. It's very predictable.

• 1:14:00Speaker 01

  It's a safe and high quality experience and then it gets you in a very reliable, very convenient, frictionless way to where you want to be. And along the journey, I think we also want to like do little things to delight our, our users.

• 1:14:20Lex Fridman?

  Like the ride sharing companies, because they don't control the experience, I think, they can't make people fall in love necessarily with the experience. Or maybe they, they haven't put in the effort, but I, I think if I were to speak to the ride sharing experience I currently have, it's just very, it's just very convenient. But there's a lot of room for like falling in love with it. Like we, we can speak to sort of car companies. Car companies do this well. You can fall in love with the car, right? And be like a loyal car person, like whatever. Like I like badass hot rods, I guess 69 Corvette. And at this point, you know, you can't really.

• 1:15:03Lex Fridman?

  Cars are so, owning a car is so 20th century, man. But is there something about the Waymo experience where you hope that people will fall in love with it? Because that, is that part of it? Or is it part of, is it just about making a convenient ride? Not ride sharing, I don't know what the right term is, but just a convenient A to B autonomous transport? Or like, do you want them to fall in love with Waymo? Maybe elaborate a little bit. I mean, almost like from a business perspective, I'm curious, like, how, do you want to be in the background invisible? Or do you want to be

• 1:15:48Lex Fridman?

  like a source of joy that's in, very much in the foreground?

• 1:15:52Speaker 01

  I want to provide the best, most enjoyable transportation solution. And, uh, and that means building it, building our product and building our service in a way that people do. Uh, kind of use in a very seamless, frictionless way in their, in their day to day lives. And I think that does mean, uh, you know, in some way falling in love in that product, right? It just kind of becomes part of your routine. I, uh, it, it comes down in my mind to, uh, safety, predictability of the experience. And, um, privacy, I think, aspects of it, right?

• 1:16:35Speaker 01

  Uh, our cars, uh, you get the same car, you get very predictable behavior. Uh, and that, that is important. And if you're going to use it in your daily life, uh, uh, privacy. And when you're in a car, you can do other things. You're spending a bunch, just another, you know, space where you're spending a significant part of your life. And so not having to share it with, uh, other people who you don't want to share it with, I think is, uh, uh, a very nice property. Uh, maybe you want to, you know, take a phone call or, you know, do something else in the vehicle. Um, uh, and, you know, uh, safety on the quality of the driving as well as the physical safety of, you know, not having, you know, to share that ride, uh, is, you know, uh, important to a lot of people. What about?

• 1:17:21Lex Fridman?

  The idea that when when there's a somebody like a human driving and they do a rolling stop on a stop sign, like sometimes like, you know, you get a new bus or a lift or whatever, like human driver and, you know, they can be a little bit aggressive as drivers. It feels like there is, not all aggression is bad. Now, that may be a wrong, again, 20th century conception of driving. Maybe it's possible to create a driving experience. Like, if you're in the back, busy doing something, maybe aggression is not a good thing. It's a very different kind of experience, perhaps.

• 1:17:58Lex Fridman?

  But it feels like, in order to navigate this world, you need to, how do I phrase this? You need to kind of bend the rules a little bit, or at least like test the rules. I don't know what language politicians use to discuss this, but whatever language they use, you like flirt with the rules, I don't know. But like you, you sort of have a bit of an aggressive way of driving that asserts your presence in this world, thereby making other vehicles and people respect your presence, and thereby allowing you to sort of navigate through intersections in a timely fashion.

• 1:18:39Lex Fridman?

  I don't know if any of that made sense, but like, how does that fit into the experience of driving autonomously? Is that?

• 1:18:48Speaker 01

  It makes a lot of sense. This is, you're hitting on a very important point of a number of behavioral components and, you know, parameters that make your driving feel, you know, assertive and natural and comfortable and predictable. Now, our cars will follow rules, right? They will do the safest thing possible in all situations, let me be clear on that. But if you think of really, really, you know, good drivers, just, you know, think about, you know, professional limo drivers, right? They will follow the rules, they're very, very smooth, and yet they're very efficient. And, but they're assertive, they're comfortable for the people in the vehicle.

• 1:19:30Speaker 01

  Predictable for the other people outside the vehicle that they share the environment with. And that's the kind of driver that we want to build. And you think if maybe there's a sport analogy there, right? You can do in very many sports, the true professionals are very efficient in their movements. Right? They don't do like hectic flailing, right? They're smooth and precise and they get the best result. So that's the kind of driver that we want to build. In terms of aggressiveness, yeah, you can like, you know, roll through the stop signs. You can do crazy lane changes. Typically doesn't get you to your destination faster. Typically not the safest or most predictable, uh, very most comfortable thing to do.

• 1:20:14Speaker 01

  And but there is a way to do both. And that, that, that, that's what we're doing. We're trying to build a driver that is safe, comfortable, smooth and predictable.

• 1:20:27Lex Fridman?

  Yeah, that's a really interesting distinction. I think in the early days of autonomous vehicles, the vehicles felt cautious as opposed to efficient. And I'm still probably, but when I rode in the Waymo, I mean, there was, it was, it was quite assertive.

• 1:20:45Lex Fridman?

  It moved pretty quickly, like, um, yeah, then he's one of the surprising feelings was that it actually, it went fast. And it didn't feel like awkwardly cautious than autonomous vehicle like. Like, so I've also programmed autonomous vehicles and everything I've ever built was felt awkwardly either overly aggressive. Okay. Especially when it was my code or like awkwardly cautious is the way I would put it. And Waymo's vehicle felt like assertive and I think efficient is like the right terminology here. They wasn't, and I also like the professional limo driver.

• 1:21:31Lex Fridman?

  Cause we often think like, you know, an Uber driver or a bus driver or taxi. This is the funny thing is people think like taxi drivers are professionals. They, I mean, it's, it's like, that, that's like saying I'm a professional walker just because I've been walking all my life. I think there's an art to it, right? And if you take it seriously as an art form, then there's a certain way that mastery looks like. It's interesting to think about what does mastery look like in driving? And perhaps what we associate with like aggressiveness is unnecessary, like it's

• 1:22:13Lex Fridman?

  not part of the experience of driving. It's like unnecessary fluff, that efficiency, you could, you can be, you can create a good driving experience within the rules.

• 1:22:30Lex Fridman?

  That's, I mean, you're the first person to tell me this, so it's, it's kind of interesting. I need to think about this. But that's exactly what it felt like with Waymo. I kind of had this intuition, maybe it's the Russian thing, I don't know, that you have to break the rules in life to get anywhere. But maybe, maybe it's possible that that's not the case in driving. I have to think about that. But it certainly felt that way on the streets of Phoenix when I was there in, in Waymo, that, that, that, that was a very pleasant experience and it wasn't frustrating in that like, come on, move already kind of feeling. It wasn't, that wasn't there.

• 1:23:05Speaker 01

  Yeah, I mean, that, that's what, that's what we're going after. I don't think you have to pick one. I think truly good driving, it gives you both efficiency, a certainness, but also comfort and predictability and safety. And, you know, it's, that's what fundamental improvements in the core capabilities truly unlock. And you can kind of think of it as, you know, precision and recall trade off. You have certain capabilities of your model, and then it's very easy when, you know, you have some curve of precision and recall, you can move things around. I can choose your operating point and you're trading off precision versus recall, false positives versus false negatives, right? But then, and you know, you can tune things on that curve and be kind of more cautious or more aggressive,

• 1:23:47Speaker 01

  but then aggressive is bad or cautious is bad. But true capabilities come from actually moving the whole curve up. And, and then you are kind of on a, on a very different plane of those trade offs. And that, that's what, you know, we're trying to do here is to move the whole curve up.

• 1:24:03Lex Fridman?

  Before I forget, let's talk about trucks a little bit. So I also got a chance to check out some of the Waymo trucks. I'm not sure if we want to go too much into that space, but it's fascinating. So maybe we can mention at least briefly. You know, Waymo is also now doing autonomous trucking. And how different like philosophically and technically is that whole space of problems?

• 1:24:29Speaker 01

  It's one of our two big products and, you know, commercial applications of our driver. Right, hailing and deliveries. We have Waymo One and Waymo Via, moving people and moving goods. Trucking is an example of moving goods. We've been working on trucking since 2017. It is

• 1:24:57Speaker 01

  a very interesting space. And your question of how different is it? It has this really nice property that the first order challenges, like the science, the hard engineering, whether it's hardware or onboard software or offboard software, all of the systems that you build for training your ML models, for evaluating your time system, like those fundamentals carry over. The true challenges of driving, perception, semantic understanding, prediction, decision making, planning, evaluation, the simulator, ML infrastructure, those carry over. Like the data and the application and kind of the domains might be different,

• 1:25:42Speaker 01

  but the most difficult problems, all of that carries over between the domains. So that's very nice. So that's how we approach it. We're kind of build investing in the core, the technical core. And then there is specialization of that core technology to different product lines, to different commercial applications. So on, just to tease it apart a little bit, on trucks, starting with the hardware, the configuration of the sensors is different. They're different physically, geometrically, different vehicles. So for example, we have two of our main laser on the trucks on both sides. So that we have, you know, not have the blind spots.

• 1:26:25Speaker 01

  Whereas on the JLR IPACE, we have, you know, one of it sitting at the very top. But the actual sensors are almost the same or largely the same. So all of the investment that over the years we've put into building our custom lighters, custom radars, putting the whole system together, that carries over very nicely. Then, you know, on the perception side, the like the fundamental challenges of seeing, understanding the world, whether it's, you know, object detection, classification, you know, tracking, semantic understanding, all that carries over. You know, yes, there's some specialization when you're driving on freeways, you know, range becomes more important, the domain is a little bit different. But again, the fundamentals carry over very, very nicely.

• 1:27:07Speaker 01

  Same, and I guess you get into prediction or decision making, right? The fundamentals of what it takes to predict what other people are going to do, to find the long tail, to improve your system in that long tail of behavior prediction and response, that carries over, right? And so on, so on.

• 1:27:27Lex Fridman?

  So I mean, that's pretty exciting. By the way, does Waymo VIA include using the smaller vehicles for transportation of goods? That's an interesting distinction. So I would say there's three interesting modes of operation. So one is moving humans, one is moving goods, and one is like moving nothing, zero occupancy, meaning like you're going to the destination, your empty vehicle. I mean, it's

• 1:27:57Speaker 01

  The third is the less of it. If that's the entirety of it, it's less, you know, exciting from the commercial perspective.

• 1:28:04Lex Fridman?

  Well, I mean, in terms of like, if you think about what's inside a vehicle as it's moving, because it does, you know, some significant fraction of the vehicle's movement has to be empty. I mean, it's kind of fascinating, maybe just on that small point, is there different control and like policies that are applied for zero occupancy vehicle? So a vehicle with nothing in it? Or is it just move as if there is a person inside? What was with some subtle differences?

• 1:28:39Speaker 01

  As a first order approximation, there are no differences. And if you think about, you know, safety and comfort and quality of driving, only part of it, you know, has to do with the, you know, the people or the goods inside of the vehicle, right? But you don't want to be, you know, you want to drive smoothly. And as we discussed, not for the purely for the benefit of, you know, whatever you have inside the car, right? It's also for the benefit of the, you know, people outside kind of feeding naturally and predictably into that whole environment, right? So, you know, yes, there are some second order things you can do. You can change your route and, you know, optimize maybe of your fleet, things

• 1:29:20Speaker 01

  at the fleet scale. And you would take into account whether, you know, some of your cars are actually, you know, serving a useful trip, whether with people or with goods, whereas, you know, other cars are, you know, driving completely empty to that next valuable trip that they're going to provide. But that those are mostly second order effects.

• 1:29:41Lex Fridman?

  Okay, cool. So Phoenix is, is an incredible place. And what you've announced in Phoenix is, it's kind of amazing. But, you know, that's just like one city. How do you take over the world?

• 1:29:59Speaker 01

  I mean, I'm asking for a friend. One step at a time.

• 1:30:05Speaker 01

  Is that the cartoon pinky in the brain? Okay. But gradually is a true answer. So I think the heart of your question is. Can you ask a better question than I asked? You're asking a great question. Answer that one. I'm just gonna phrase it in the terms that I want to answer. Exactly right. Brilliant. Please.

• 1:30:31Speaker 01

  You know, where are we today? And what happens next? And what does it take to go beyond Phoenix? And what does it take to get this technology to more places and more people around the world? Right? So our next big area of focus is exactly that. Larger scale commercialization and scaling up.

• 1:30:59Speaker 01

  If I think about the main. And Phoenix gives us that platform and gives us that foundation of upon which we can build. And it's. There are few really challenging aspects of this whole problem that you have to pull together in order to build a technology, in order to deploy it into the field, to go from a driverless car to a fleet of cars that are providing a service, and then all the way to commercialization.

• 1:31:42Speaker 01

  So, and this is what we have in Phoenix. We've taken the technology from a proof point to an actual deployment and have taken our driver from one car to a fleet that can provide a service. Beyond that, if I think about what it will take to scale up and deploy in more places with more customers.

• 1:32:08Speaker 01

  I tend to think about three main dimensions, three main axes of scale. One is the core technology, you know, the hardware and software, core capabilities of our driver. The second dimension is evaluation and deployment. And the third one is the, you know, product, commercial and operational excellence. So you can talk a bit about where we are along, you know, each one of those three dimensions, where we are today. And, you know, what has, what will happen next. On, you know, the core technology, on, you know, the hardware and software, you know, together comprised of driver.

• 1:32:51Speaker 01

  We, you know, obviously have that foundation that is providing fully driverless trips to our customers as we speak. In fact, and we've learned a tremendous amount from that. So now what we're doing is we are incorporating all those lessons into some pretty fundamental improvements in our core technology, both on the hardware side and on the software side, to build a more general, more robust solution that then will enable us to massively scale, you know, beyond Phoenix. So on the hardware side, all of those lessons are now incorporated into this fifth generation hardware platform

• 1:33:36Speaker 01

  that is, you know, being deployed right now. And that's the platform, the fourth generation, the thing that we have right now driving in Phoenix. It's good enough to operate fully driverlessly, you know, night and day, you know, various speeds and various conditions. But the fifth generation is the platform upon which we want to go to massive scale.

• 1:33:58Speaker 01

  We, in turn, we've really made qualitative improvements in terms of the capability of the system, the simplicity of the architecture, the reliability of the redundancy. It is designed to be manufacturable at very large scale and, you know, provides the right unit economics. So that's, that's the next big step for us on the hardware side.

• 1:34:17Lex Fridman?

  That's, that's already there for scale, the version five.

• 1:34:20Speaker 01

  That's right.

• 1:34:21Lex Fridman?

  And is that coincidence or should we look into a conspiracy theory that it's the same version as the Pixel phone?

• 1:34:28Lex Fridman?

  Is that what's the hardware?

• 1:34:30Speaker 01

  Neither confirm or deny Lux.

• 1:34:32Lex Fridman?

  All right, cool. So, sorry. So that's the, okay, that's that axis. What else?

• 1:34:37Speaker 01

  So similarly, hardware is a very discreet jump, but similarly to the, that, to how we're making that change from the fourth generation hardware to the fifth, we're making similar improvements on the software side to make it more robust and more general and allow us to quickly scale beyond Phoenix. So that's the first dimension of core technology. The second dimension is evaluation and deployment. Now, how do you measure your system? How do you evaluate it? How do you build the release and deployment process where with confidence you can regularly release new versions of your driver into a fleet? How do you get good at it so that

• 1:35:17Speaker 01

  it is not a huge tax on your researchers and engineers? So how do you build all these processes? The frameworks, the simulation, the evaluation, the data science, the validation, so that people can focus on improving the system and the releases just go out the door and get deployed across the fleet. So we've gotten really good at that in Phoenix. That's been a tremendously difficult problem, but that's what we have in Phoenix right now that gives us that foundation. And now we're working on incorporating all the lessons that we've learned to make it more efficient to go to new places and scale up and just stamp things out. So that's the second dimension of evaluation and deployment. And the third

• 1:35:58Speaker 01

  dimension is product, commercial, and operational excellence. And again, Phoenix there is providing an incredibly valuable platform. That's why we're doing things end to end in Phoenix. We're learning, as we discussed a little earlier today, tremendous amount of really valuable lessons from our users, getting really incredible feedback. And we'll continue to iterate on that and incorporate all those lessons into making our product even better and more convenient for our users.

• 1:36:31Lex Fridman?

  So you're converting this whole process of Phoenix into something that could be copied and pasted elsewhere. So like, perhaps you didn't think of it that way when you were doing the experimentation Phoenix. But so how long did?

• 1:36:47Lex Fridman?

  Basically, you can correct me, but you've, I mean, it's still early days, but you've taken the full journey in Phoenix, right? As you were saying, of like what it takes to basically automate. I mean, it's not the entirety of Phoenix, right? But I imagine it can encompass the entirety of Phoenix. That's some, some near term date, but that's not even perhaps important, like as long as it's a large enough geographic area. So what, how copy pasteable is that process currently? And how like, you know, like when you copy and paste in, in Google Docs, I think,

• 1:37:32Lex Fridman?

  no, in, or in Word, you can like apply source formatting or apply destination formatting? So when you copy and paste the Phoenix into like, say, Boston, how do you apply the destination formatting? Like, how much of the core of the entire process of bringing an actual public

• 1:37:58Lex Fridman?

  transportation, autonomous transportation service to a city is there in Phoenix that you understand enough to copy and paste into Boston or wherever?

• 1:38:09Speaker 01

  So we're not quite there yet. We're not at a point where we're kind of massively copy and pasting all over the place. But Phoenix, what we did in Phoenix, and we very intentionally have chosen Phoenix as our first full deployment area, you know, exactly for that reason, to kind of tease the problem apart, look at each dimension, you know, focus on the fundamentals of complexity and de-risking those dimensions, and then bringing the entire thing together to get all the way, and force ourselves to learn all those hard lessons on technology, hardware and software, on the evaluation deployment, on operating a service, operating a business, using, actually, serving our customers, all the way so that we're fully

• 1:38:52Speaker 01

  informed about the most difficult, most important challenges to get us to that next step of massive copy and pasting, as, as you said. And

• 1:39:07Speaker 01

  That's what we're doing right now. We're incorporating all those things that we learned into that next system that then will allow us to kind of copy and paste all over the place and to massively scale to more users and more locations. I mean, you know, just talked a little bit about, you know, what does that mean along those different dimensions? So on the hardware side, for example, again, it's that switch from the fourth to the fifth generation. And the fifth generation is designed to kind of have that property.

• 1:39:32Lex Fridman?

  Can you say what other cities you're thinking about? Like, I'm thinking about, sorry, we're in San Francisco now. I thought I want to move to San Francisco, but I'm thinking about moving to Austin. I don't know why. People are not being very nice about San Francisco currently. Maybe it's a small, it's maybe it's in vogue right now. But Austin seems, I visited there and it was, I was in a Walmart. It's funny, these moments like turn your life. There's this very nice woman with kind eyes, just like stopped and said, "He looks so handsome in that tie, honey," to me.

• 1:40:14Lex Fridman?

  This is never happened to me in my life, but just the sweetness of this woman is something I've never experienced, certainly in the streets of Boston. But even in San Francisco where people wouldn't, that's just not how they speak or think. I don't know. There's a warmth to Austin that love. And since Waymo does have a little bit of a history there, is that a possibility?

• 1:40:36Speaker 01

  Is this your version of asking the question of like, you know, Dimitri, I know you can't share your commercial and deployment roadmap, but I'm thinking about moving to San Francisco, Austin, like, you know, blink twice if you think I should move to.

• 1:40:48Lex Fridman?

  That's true. That's true. You got me.

• 1:40:50Speaker 01

  Well, you know, we've been testing in all over the place. I think we've been testing in more than 25 cities. We drive in San Francisco, we drive in, you know, Michigan for snow. We are doing significant amount of testing in the Bay Area, including San Francisco.

• 1:41:05Lex Fridman?

  But it's not like, because we're talking about the very different thing, which is like a full-on, large geographic area, public service. You can't share. Okay.

• 1:41:20Lex Fridman?

  What about Moscow? Is that, when is that happening? Take on Yandex. I'm not paying attention to those folks. They're doing, you know, there's, there's a lot of fun. I mean, maybe as a way of a question.

• 1:41:36Lex Fridman?

  You didn't speak to sort of like policy or like, is there tricky things with government and so on? Like, is there other friction that you've encountered except sort of technological friction of solving this very difficult problem? Is there other stuff that you have to overcome? When, when deploying a public service in a city? That's interesting.

• 1:42:06Speaker 01

  It's very important. So we, we put significant effort in

• 1:42:12Speaker 01

  creating those partnerships and, you know, those relationships with governments at all levels, you know, local governments, municipalities, you know, state level, federal level. We've been engaged in very deep conversations from the earliest days of our, you know, projects. Whenever, at all of these levels, you know, whenever we go to test or, you know, operate in a new area, you know, we always lead with, you know, with a conversation with the local officials. And, but the result of that, that investment is that, no, it's not challenges we have to overcome. But it is a very important that we continue to have this conversation.

• 1:42:49Lex Fridman?

  Well, yeah, I love politicians too. Okay. So Mr. Elon Musk said that LiDAR is a crutch. What are your thoughts?

• 1:43:02Speaker 01

  I wouldn't characterize it exactly that way. I know, I think LiDAR is very important. It is a key sensor that, you know, we use, just like other modalities. And as we discussed, our cars use cameras, LiDARs and radars. They are all very important. They are. At the kind of the physical level, they are very different. They have very different, you know, physical characteristics. Cameras are passive, lighters and radars are active, use different wavelengths. So that means they complement each other very nicely.

• 1:43:38Speaker 01

  And together, combined, they can be used to build a much safer and much more capable system. So, you know, to me, it's more of a question, you know, why the heck would you handicap yourself and not use one or more of those sensing modalities when they, you know, undoubtedly just make your system more capable and safer? Now, it, you know, what might make sense for one product or one business might not make sense for another one. So if you're talking about driver assist technologies, you make certain design decisions

• 1:44:22Speaker 01

  and you make certain trade offs and you make different ones if you are, you know, building a driver that you deploy in fully driverless vehicles. And, you know, and lighter specifically, when this question comes up, I, you know, typically the criticisms that I hear are, you know, the counterpoints that cost and aesthetics. And like, I don't find either of those, honestly, very compelling. So on the cost side, there's nothing fundamentally prohibitive about, you know, the cost of lighters. You know, radars used to be very expensive before people started, you know, before people made certain advances in technology and you started to manufacture them at massive scale and deploy them in vehicles, right?

• 1:45:07Speaker 01

  Similar with lighters. And this is where the lighters that we have in our cars, especially the fifth generation, you know, we've been able to make some pretty qualitative discontinuous jumps in terms of the fundamental technology that allow us to manufacture those things at very significant scale and at a fraction of the cost of both our previous generation as well as a fraction of the cost of, you know, what might be available on the market, you know, off the shelf right now. And, you know, that improvement will continue. So I, I, I think, you know, cost is not a real issue. Second one is, you know, aesthetics.

• 1:45:44Speaker 02

  You know, I don't think that's a real issue either.

• 1:45:48Lex Fridman?

  Beauty is an eye that beholder.

• 1:45:50Speaker 02

  Yeah.

• 1:45:51Lex Fridman?

  You can make lidar sexy again.

• 1:45:52Speaker 02

  I think you're exactly right. I think it is sexy. Like honestly, I think form

• 1:45:55Lex Fridman?

  Yeah, I always thought. Well, okay, you know, I was actually, somebody brought this up to me. I mean, all forms of lidar, even even like the ones that are like big, you can make look. I mean, you can make look beautiful. There's no sense in which you can't integrate it into design. Like, there's all kinds of awesome designs. I don't think small and humble is is beautiful. It could be like, you know, brutalism, or like, it could be like harsh corners. I mean, like I said, like hot rods. Like, I don't like, I don't necessarily like, like, oh, man, I'm gonna start so much controversy with this. I don't like Porsches.

• 1:46:36Lex Fridman?

  Okay, the Porsche 911, like, everyone says, oh, the most beautiful. No, it no, it's like, it's like a baby car. It doesn't make any sense. But everyone, it's beauties and I the beholder. You're already looking at me like, what's this kid talking about?

• 1:46:51Speaker 02

  I'm happy to talk about

• 1:46:53Lex Fridman?

  You're digging your own hole.

• 1:46:54Speaker 02

  The form and function and my take on the beauty of the hardware that we put on our vehicles. You know, I will not comment on your Porsche monologue.

• 1:47:04Lex Fridman?

  Okay. All right. So but aesthetics, fine. But there's an underlying like philosophical question behind the kind of lighter question is like, how much of the problem can be solved with computer vision with machine learning? So I think without sort of disagreements and so on, it's nice to put it on a spectrum because Waymo is doing a lot of machine learning as well. It's interesting to think how much of driving, if we look at five years, 10 years, 50 years down the road, would can be learned in almost more and more and more end to end way.

• 1:47:47Lex Fridman?

  If we look at what Tesla is doing with as a machine learning problem, they're doing a multitask learning thing where it's just they break up driving into a bunch of learning tasks and they have one single neural network and they're just collecting huge amounts of data that's training that. I've recently hung out with George Hotz. I don't know if you know George.

• 1:48:08Lex Fridman?

  I love him so much. He's just an entertaining human being. We were off mic talking about Hunter S. Thompson. He's he's the Hunter S. Thompson of autonomous driving. Okay, so he I didn't realize this with Kama AI, but they're like really trying to do end to end. They're the machine like looking at the machine learning problem. They're really not doing multitask learning, but it's it's computing the drivable area as a machine learning task and hoping that like down the line, this level two system, this driver assistance will eventually lead to allowing you to have a fully autonomous vehicle. Okay, there's an underlying deep philosophical question there, technical

• 1:48:50Lex Fridman?

  question of how much of driving can be learned. So LiDAR is an effective tool today for actually deploying a successful service in Phoenix, right? That's safe, that's reliable, etc., etc. But the the question, and I'm not saying you can't do machine learning on LiDAR, but the question is that like how much of driving can be learned eventually? Can we do fully autonomous? That's learned.

• 1:49:19Speaker 01

  Yeah, you know, learning is all over the place and plays a key role in every part of our system. I, as you said, I would decouple the sensing modalities from the, you know, ML and the software parts of it. LiDAR, radar, cameras, like it's all machine learning. All of the object detection, classification, of course, like that's what, you know, these modern deep nets and condensers are very good at. You feed them raw data, massive amounts of raw data. And then that's actually what our custom build LiDARs and radars are really good at. And radars, they don't just give you point estimates of, you know, objects in space. They give you raw, like, physical observations. And then you take all of that raw information, you know, there's colors of the pixels,

• 1:50:03Speaker 01

  whether it's, you know, lidar's returns and some auxiliary information, it's not just distance, right? And, you know, angle and distance is much richer information that you get from those returns, plus really rich information from the radars. You fuse it all together and you feed it into those massive ML models that then,

• 1:50:19Speaker 01

  lead to the best results in terms of, you know, object detection, classification, state estimation.

• 1:50:25Lex Fridman?

  So there's that side to it all, but there is a fusion. I mean, that's something that people didn't do for a very long time, which is like at the sensor fusion level, I guess, like, early on, fusing the information together with her, so that the the sensory information that the vehicle receives from the different modalities, or even from different cameras, is combined before it is fed into the machine learning models.

• 1:50:49Speaker 01

  Yes, I think this is one of the trends. You're seeing more of that. You mentioned end to end. There's different interpretations of end to end. There is kind of the purest interpretation of I'm going to like have one model that goes from raw sensor data to like, you know, steering torque and, you know, gas brakes. But, you know, that that's too much. I don't think that's the right way to do it. There's more, you know, smaller versions of end to end, where you're, you know, kind of doing more end to end learning or core training or deep propagation of kind of signals back and forth across the different stages of your system. There's, you know, really good ways, it gets into some fairly complex design choices, where on one hand you want modularity and the composability, the composability of your system. But on the other hand, you don't want to create interfaces that are too narrow

• 1:51:33Speaker 01

  or too brittle, too engineered, where you're giving up on the generality of the solution, or you're unable to properly propagate signal, you know, rich signal forward, and losses and, you know, back so you can optimize the whole system jointly. So I would decouple, and I guess what you're seeing in terms of the fusion of the sensing data from different modalities, as well as kind of fusion at in the temporal level, going more from, you know, frame by frame, where, you know, you would have one net that would do frame by frame detection in camera, and then, you know, something that does frame by frame in lighter and then radar. And then you fuse it in a weaker engineered way later. The field over the last decade has been evolving in more kind of joint fusion, more end to end models that are solving some of these tasks jointly. And there's tremendous power in that.

• 1:52:19Speaker 01

  And that's the progression that our stack has been on as well. Now, so I would decouple the sensing and how that information is fused from the role of ML and the entire stack. And I guess there's trade offs in modularity and how do you inject inductive bias into your system? All right, this is, there's tremendous power in being able to do that. So we have, there's no part of our system that is not heavily, that does not heavily leverage data driven development or state of the art ML.

• 1:52:59Speaker 01

  But there's mapping, there's a simulator, or there's perception, object level perception, whether it's semantic understanding, prediction, decision making, so forth and so on.

• 1:53:11Speaker 01

  And of course, object detection and classification, like you're finding pedestrians and cars and cyclists and cones and signs and vegetation. And being very good at estimating, detection, classification and state estimation, there's just stable stakes. Like that's step zero of this whole stack. You can be incredibly good at that, whether you use cameras or light as a radar, but that's just, that's stable stakes. That's just step zero. Beyond that, you get into the really interesting challenges of semantic understanding at the perception level. You get into scene level reasoning. You get into very deep problems that have to do with prediction and joint prediction and interaction, total interaction between all of the actors in the environment, pedestrians, cyclists, other cars, and you get into decision making. Right? So how do you build a lot of systems? So we leverage ML very heavily in all of these components.

• 1:53:57Speaker 01

  I do believe that the best results you achieve by kind of using a hybrid approach and having different types of ML.

• 1:54:06Speaker 01

  Having different models with different degrees of inductive bias that you can have and combining kind of model free approaches with some model-based approaches and some rule-based, physics-based systems. So, you know, one example I can give you is traffic lights. There's a problem of the detection of traffic light state and obviously that's a great problem for computer vision. ConvNets are, you know, that's their bread and butter, right? That's how you build that. But then the interpretation of, you know, of a traffic light, that you're gonna need to learn that, right? You read, you don't need to build some, you know, complex ML model that, you know, infers with some, you know, precision

• 1:54:50Speaker 01

  and recall that red means stop. Like, it was a, it's a very clear engineered signal with very clear semantics, right? So you want to induce that bias, like how you induce that bias and that whether, you know, it's a constraint or a cost, you know, function in your stack. But like, it is important to be able to inject that like clear semantic signal into your stack. And, you know, that's what we do. And, but then the question of like, and that's when you apply it to yourself, when you are making decisions whether you want to stop for a red light, you know, or not. But if you think about how other people treat traffic lights, we're back to the ML version of that. Because, you know, they're supposed to stop for a red light, but that doesn't mean they will. So then you're back

• 1:55:33Speaker 01

  in the like very heavy ML domain where you're picking up on like very subtle keys about, you know, that have to do with the behavior of objects, pedestrians, cyclists, cars, and the whole, then, you know, entire configuration of the scene that allow you to make accurate predictions on whether they will in fact stop or run a red light.

• 1:55:53Lex Fridman?

  So it sounds like already for Waymo, like machine learning is a huge part of the stack. So it's a huge part of like, not just, so obviously. The first, the level zero, or whatever you said, which is like just the object detection of things that, you know, with, no, that machine learning can do, but also starting to do prediction of behavior and so on to model the, what other, or the other parties in the scene, entities in the scene are going to do. So, machine learning is more and more playing a role in that as well.

• 1:56:25Speaker 01

  Of course. Absolutely. I think we've been going back to the earliest days, like, DARPA, even the DARPA Grand Challenge, and team was leveraging, you know, machine learning. That was like pre, you know, ImageNet, and it was a very different type of ML. But, and I think actually it was before my time, but the Stanford team during the Grand Challenge had a very interesting machine learned system that would, you know, use lighter and camera. We've been driving in the desert, and it, we had built the model where it would kind of extend the range of free space reasoning. We'd get a clear signal from lighter, and then it had a model that said, hey, like this stuff in camera kind of sort of looks like this stuff in lighter, and I know this stuff that I've seen in lighter, I'm very

• 1:57:07Speaker 01

  confident this free space, so let me extend that free space zone into the camera range that would allow the vehicle to drive faster. And then we've been building on top of that and kind of staying and pushing the state of the art in ML, in all kinds of different ML over the years. And in fact, from the earliest days, I think, you know, 2010 is probably the year where Google, maybe 2011 probably, got pretty heavily involved in machine learning, kind of deep nets. And at that time, it was probably the only company that was very heavily investing in kind of state of the art ML and self-driving cars. And they, they, they go hand in hand. And we've been on that journey ever since. We're

• 1:57:48Speaker 01

  doing, pushing a lot of these areas in terms of research, you know, at Waymo, and we collaborate very heavily with the researchers in Alphabet. And like all kinds of ML, supervised ML, unsupervised ML, you know, published some interesting research papers in the space, especially recently. It's just a super, super active.

• 1:58:10Lex Fridman?

  Learning as well.

• 1:58:11Speaker 01

  Yeah, so super, super active. Of course, there is kind of the more mature stuff, like, you know, ConvNets for, you know, object detection. But there's some really interesting, really active work that's happening in kind of more.

• 1:58:25Speaker 01

  And bigger models and models that have more structure to them, not just large bitmaps and reasonable temporal sequences. And some of the interesting breakthroughs that you've, you know, we've seen in language models, right, you know, transformers, you know, GPT three inference. There's some really interesting applications of some of the core breakthroughs to those problems of, you know, behavior prediction as well as, you know, decision making and planning, right? You think about it, kind of the behavior, how, you know, the path, the trajectories, the how people drive, they have kind of share a lot of the fundamental structure, you know, this problem.

• 1:59:05Speaker 01

  There's, you know, sequential nature, there's a lot of structure in this representation. There is a strong locality, kind of like in sentences, you know, words that follow each other, they're strongly connected, but there are also kind of larger contexts that doesn't have that locality and you also see that in driving, right? What, you know, is happening in the scene as a whole has very strong implications on, you know, the kind of the next step in that sequence where whether you're predicting what other people are going to do, whether you're making your own decisions, or whether in the simulator, you're building generative models of, you know, humans walking, cyclists riding, the cars driving.

• 1:59:41Lex Fridman?

  Oh, that's, that's all really fascinating. Like how, it's fascinating to think that transformer models and all this, all the breakthroughs in language and NLP that might be applicable to like driving at the higher level, at the behavior level, that's kind of fascinating. Let me ask about pesky little creatures called pedestrians and cyclists. They seem so, humans are a problem. If we can get rid of them, I would.

• 2:00:05Lex Fridman?

  But unfortunately, they're also a source of joy and love and beauty, so let's keep them around. They're also our customers. Oh, for your perspective, yes, yes, for sure. There's so some money, very good. But I didn't even know where I was going. Oh, yes, pedestrians and cyclists.

• 2:00:25Lex Fridman?

  I, you know, they're a fascinating injection into the system of uncertainty of.

• 2:00:33Lex Fridman?

  Of like a game theoretic dance of what to do and also they have perceptions of their own and they can tweet about your product. So you don't want to run them over from that perspective. I mean, I don't know, I'm joking a lot, but I think in seriousness, like, you know, pedestrians are a complicated computer vision problem, a complicated behavioral problem. Is there something interesting you could say about what you've learned from a machine learning perspective, from also an autonomous vehicle and a product perspective about just interacting with the humans in this world?

• 2:01:12Speaker 01

  Yeah, just, you know, to state on record, we care deeply about the safety of pedestrians, you know, even the ones that don't have Twitter accounts.

• 2:01:18Lex Fridman?

  Thank you. All right, cool. Not me. But yes, I'm glad, I'm glad somebody does.

• 2:01:27Speaker 01

  Okay. But, you know, in all seriousness, safety of vulnerable road users, pedestrians or cyclists is one of our highest priorities. We do a tremendous amount of testing and validation and put a very significant emphasis on, you know, the capabilities of our systems that have to do with safety around those unprotected, vulnerable road users. You know, cars, just, you know, discussed earlier in Phoenix, we have completely empty cars, completely driverless cars, you know, driving in this very large area. And, you know, some people use them to, you know, go to school. So they'll drive through school zones, right? So kids are kind of the very special class of those vulnerable user, road users, right? You want to be, you

• 2:02:12Speaker 01

  know, super, super safe and super, super cautious around those. So we take it very, very, very seriously. And, you know, what does it take to be good at it? You know?

• 2:02:24Speaker 01

  An incredible amount of performance across your whole stack. You know, starts with hardware. And again, you want to use all sensing modalities available to you. Imagine driving on a residential road at night and kind of making a turn. And you don't have headlights covering some part of the space. And like, you know, a kid might run out. And you know, lighters are amazing at that. They see just as well in complete darkness as they do during the day. Right. So just again, it gives you that extra

• 2:02:59Speaker 01

  you know, margin in terms of capability and performance and safety and quality. And in fact, we oftentimes in these kinds of situations, we have our system detect something. In some cases, even earlier than our train operators in the car might do. Especially in conditions like very dark nights. So starts with sensing, then you know, perception has to be incredibly good. And you have to be very, very good at detecting pedestrians in all kinds of situations and all kinds of environments, including people in weird poses, people kind of running around and being partially occluded.

• 2:03:39Speaker 01

  So that's stuff number one. Then you have to have in very high accuracy and very low latency in terms of your reactions to what these actors might do. And we've put a tremendous amount of engineering and tremendous amount of validation into make sure our system performs properly. And oftentimes it does require a very strong reaction to do the safe thing. And we actually see a lot of cases like that. The long tail of really rare, you know, really crazy events that contribute to the safety around pedestrians. Like one example that comes to mind that we actually happened in Phoenix,

• 2:04:23Speaker 01

  where we were driving along. And I think it was a 45 mile per hour road, so you have pretty high speed traffic. And there was a sidewalk next to it, and there was a cyclist on the sidewalk.

• 2:04:36Speaker 01

  As we were in the right lane, right next to the sidewalk, because it's a multi-lane road. So as we got close to the cyclist on the sidewalk, it was a woman. She tripped and fell, just fell right into the path of our vehicle. And our car, you know, this was actually with a test driver, our test drivers did exactly the right thing. They kind of reacted and came to stop. It requires both very strong steering and strong application of the brake. And then we simulated what our system would have done in that situation, and it did exactly the same thing. And that speaks to all of those components of really good state estimation and tracking. And like imagine, you know, a person on a bike,

• 2:05:19Speaker 01

  and they're falling over, and they're doing that right in front of you, right? So you have to be really like, things are changing. The appearance of that whole thing is changing, right? And a person goes one way, they're falling on the road, they're, you know, being flat on the ground in front of you. You know, the bike goes flying the other direction, like the two objects that used to be one another, you know, are splitting apart, and the car has to like detect all of that. Like milliseconds matter. And it doesn't, you know, it's not good enough to just brake. You have to like steer and brake, and there's traffic around you. So like, it all has to come together. And it was really great to see in this case and other cases like that, that we're actually seeing in the wild, that our system is, you know, performing exactly the way that we would have liked and is able to, you know, avoid collisions like this.

• 2:06:00Lex Fridman?

  It's such an exciting space for robotics, like in that split second, to make decisions of life and death. I don't know. The stakes are high in a sense, but it's also beautiful that for somebody who loves artificial intelligence, the possibility that an AI system might be able to save a human life, that's kind of exciting. As a problem, like to wake up, it's terrifying probably for an engineer to wake up and to think about, but it's also exciting. Because it's like, it's in your hands. Let me try to ask a question that's often brought up about autonomous vehicles. And it might be fun to see if you have anything interesting to say, which is about the trolley problem.

• 2:06:44Lex Fridman?

  So the trolley problem is an interesting philosophical construct of that highlights, and there's many others like it, of the difficult ethical decisions that we humans have before us in this complicated world. So specifically is the choice between if you are forced to choose to kill a group X of people versus a group Y of people, like one person. If you didn't, if you did nothing, you would kill one person. But if you would kill five people, and if you decide to swerve out of the way, you would only kill one person. Do you do nothing, or you choose to do something?

• 2:07:25Lex Fridman?

  You can construct all kinds of sort of ethical experiments of this kind that I think at least on a positive note, inspire you to think about, like introspect, what are the physics of our morality? And there's usually not good answers there. I think people love it because it's just an exciting thing to think about. I think people who build autonomous vehicles usually roll their eyes because this is not, this one as constructed, this like literally never comes up in reality. You never have to choose between killing one, like one of two groups of people.

• 2:08:10Lex Fridman?

  But I wonder if you can speak to, is there some, something interesting to use in engineer of autonomous vehicles that's within the trolley problem? Or maybe more generally, are there difficult ethical decisions that you find that an algorithm must make? On the specific version of the trolley problem, which one would you do?

• 2:08:34Speaker 01

  If you're driving.

• 2:08:36Lex Fridman?

  The question itself is a profound question because we humans ourselves cannot answer it. And that's the very point. I will kill both.

• 2:08:48Speaker 01

  Yeah, humans, I think you're exactly right in that, you know, humans are not particularly good. I think the kind of phrase is like, what would a computer do? But like, humans are not very good. And actually, oftentimes, I think that, you know, freezing and kind of not doing anything because like you've taken a few extra milliseconds to just process and then you end up like doing the worst of possible outcomes. Right? So I do think that, as you've pointed out, it can be a bit of a distraction and it can be a bit of a kind of red herring. I think it's an interesting discussion in the realm of philosophy. Right? But in terms of what, you know, how that affects the actual engineering and deployment of self-driving vehicles, I it's not how you go about building a system, right? We've

• 2:09:32Speaker 01

  talked about how you engineer a system, how you go about evaluating the different components and, you know, the safety of the entire thing. How do you kind of inject the, you know, various model-based, safety-based arguments? And you're like, yes, you reason at parts of the system, you know, you reason about the probability of a collision, the severity of that collision, right? And that is incorporated and there's, you know, you have to properly reason about the uncertainty that flows through the system. Right? So, you know, those, you know, factors definitely play a role in how the cars then behave. But they seem to be more of like the emergent behavior. And what you see, like, you're absolutely right that these, you know, clear theoretical problems that they, you know, you don't occur that

• 2:10:14Speaker 01

  in system. And really, kind of being back to our previous discussion of like, what, you know, what, you know, which one do you choose? Well, you know, oftentimes, like, you made a mistake earlier, like, you shouldn't be in that situation in the first place, right? And in reality, the system comes up. If you build a very good, safe and capable driver, you have enough, you know, clues in the environment that you drive defensively so you don't put yourself in that situation. Right? And again, you know, has, you know, this, if you go back to that analogy of, you know, precision and recall, like, okay, you can make a, you know, very hard trade off of, but like, neither answer is really good. But what instead you focus on is kind of moving the whole curve up. And then you focus on building the right capability and the right defensive driving so that, you know, you don't put yourself in a situation like this.

• 2:11:00Lex Fridman?

  I don't know if you have a good answer for this, but people love it when I ask this question about about books. Are there books in in your life that you've enjoyed? Philosophical fiction, technical, that had a big impact on you as an engineer or as a human being? You know, everything from science fiction to a favorite textbook. Is there three books that stand out that you can think of?

• 2:11:24Speaker 01

  Uh, three books. So I would, uh, you know, that impacted me. I would say, uh, uh, and this one is, you probably know it well, uh, but not generally well known. I, I, I think in the US or kind of internationally, The Master and Margarita. Uh, it's, uh, uh, one of actually my favorite, uh, books. Um, it is, you know, by Russian, it's a novel by Russian author, uh, Mikhail Bulgakov. And it's just, it's, it's a great book. You know, it's one of those books that you can like reread your entire life and it's, it's very accessible. You can read it as a kid and like it's, it, you know, it's, the, the plot is interesting. It's, you know, the, the devil, you know, visiting the Soviet Union and, you know, but

• 2:12:08Speaker 01

  it, it like you read it, reread it, uh, at different stages of your life and you, you enjoy it for different, very different reasons. And you keep finding like deeper and deeper meaning, uh, and, you know, it kind of affected, you know, had a, definitely had an like imprint on me, you know, mostly from the, probably kind of the cultural stylistic, uh, aspect. Like it makes you one of those books that, you know, is, uh, is good and makes you think, but also has like this really, you know, silly, quirky, dark sense of, you know, humor.

• 2:12:37Lex Fridman?

  It captures the Russian soul more than many, perhaps many other books. And that like slight note, just out of curiosity, one of the saddest things is I've read that book in English. Uh, did you by chance read it in English or in Russian?

• 2:12:52Speaker 01

  In Russian, only in Russian. And I actually, that is a question I had

• 2:12:57Speaker 01

  posed to myself every once in a while. Like, I wonder how well it translates, if it translates at all. And there's the language aspect of it, and then there's the cultural aspect. So I, and actually, I'm not sure if either of those would work well in English.

• 2:13:10Lex Fridman?

  Now, I forget their names, but so when the COVID lifts a little bit, I'm traveling to Paris for several reasons. One is just I've never been to Paris, I want to go to Paris. But there's the most famous translators of Dostoevsky, Tolstoy, of most of Russian literature, live there. There's a couple, they're famous, a man and a woman. And I'm gonna sort of have a series of conversations with them. And in preparation for that, I'm starting to read Dostoevsky in Russian. So I'm really embarrassed to say that I've read, everything I've read of Russian literature of like, serious depth has been in English. Even though, I can also read, I mean, obviously, in Russian, but for some reason, it seemed

• 2:13:56Lex Fridman?

  in the optimization of life, it seemed the improper decision to do, to read in Russian. Like, you know, like, I don't need to, I need to think in English, not in Russian. But now I'm changing my mind on that. And so the question of how well it translates is a really fundamental one, like, even with Dostoevsky. So from what I understand, Dostoevsky translates easier.

• 2:14:18Lex Fridman?

  Others don't as much. Obviously, the poetry doesn't translate as well. I'm also the music, a big fan of Vladimir Vassitsky. He doesn't obviously translate well. People have tried.

• 2:14:32Lex Fridman?

  But mastermind, I don't know. I don't know about that one. I just know in English, you know, it's fun, fun as hell in English, so. So, but it's a curious question, and I want to study it rigorously from both the machine learning aspect, and also because I want to do a couple of interviews in Russia. That I'm still unsure of how to properly conduct an interview across a language barrier. It's a fascinating question that ultimately communicates to an American audience. There's a few Russian people that I think are truly special human beings. And I feel like I sometimes encounter this with some incredible

• 2:15:15Lex Fridman?

  scientists, and maybe you encounter this as well at some point in your life, that it feels like because of the language barrier, their ideas are lost to history. It's a sad thing. I think about like Chinese scientists or even authors that like, that we don't in an English speaking world, don't get to appreciate some like the depth of the culture because it's lost in translation. And I feel like I would love to show that to the world. Like, I'm, I'm just some idiot, but because I have this, like at least some semblance of skill in speaking Russian, I feel like, and I know how to record stuff on a video camera. I feel like I want to catch like Gregory Perlman, who's a mathematician, I'm not sure if you're

• 2:15:58Lex Fridman?

  familiar with him. I want to talk to him like he's a fascinating mind and to bring him to a wider audience in English speaking will be fascinating. But that requires to be rigorous about this question of how well Bogakov translates. I mean, I know it's a, it's a silly concept, but it's a fundamental one, because how do you translate? And that's, that's the thing that Google Translate is also facing.

• 2:16:23Speaker 01

  Yeah.

• 2:16:24Lex Fridman?

  As a, as a more machine learning problem, but I, I wonder as a more bigger problem for AI, how do we capture the magic that's there in the language?

• 2:16:35Speaker 01

  I, I think that's really interesting, really challenging problem. I, if you do read it, Master and Margarita in English, sorry, in Russian, I'd be curious to get your opinion. And I think a part of it is language, but part of it's just, you know, centuries of culture that the cultures are different. So it's hard to connect that.

• 2:16:57Speaker 01

  Okay, so that was my first one, right? You had two more. The second one, I would probably pick the science fiction by the Strugusky brothers. You know, it's up there with, you know, Isaac Asimov and, you know, Ray Bradbury and, you know, company. The Strugusky brothers kind of appealed more to me. I think more it made more of an impression on me growing up. I

• 2:17:21Lex Fridman?

  Can you, can you, I apologize if I'm showing my complete ignorance. I'm so weak on sci fi. What, what, what are they, right?

• 2:17:27Speaker 01

  Oh, roadside picnic.

• 2:17:33Speaker 01

  Hard to be a god.

• 2:17:38Speaker 01

  Beetle in an anthill.

• 2:17:42Speaker 01

  Monday starts on Saturday. Like it's not just science fiction. It's also like has very interesting, you know, interpersonal and societal questions. And some of the language is just completely hilarious.

• 2:17:55Lex Fridman?

  Monday beginning, so both That's the one. That's right. Oh, interesting. Monday starts on Saturday. So I need to read. Okay. Oh, boy. You put that in the category of science fiction?

• 2:18:06Speaker 01

  That one is, I mean, this was more of a silly, you know, humorous work. I mean, there is kind of

• 2:18:12Lex Fridman?

  It's profound too, right?

• 2:18:14Speaker 01

  Science fiction, right? It's about, you know, this, this research institute and like it's, it, it, it has deep parallels to like serious research, but the, the setting, of course, is that they're working on, you know, magic, right? And there's a lot of, so I, and that's their style, right? And they go, and, you know, other books are very different, right? You know, hard to be a god, right? It's about kind of this higher society being injected into this primitive world and how they operate there. Like some of the very deep ethical, you know, questions there, right? And like they've got this full spectrum. Some is, you know, more about kind of more adventure style. But like I enjoy all of their books. There's just probably a couple, actually one, I think that they consider their most important work.

• 2:18:54Speaker 01

  I think it's the snail on a, on a, on a, on a hill. I don't know exactly how, sure how it translates. I tried reading a couple of times. I still don't get it. But everything else I fully enjoyed. And like for one of my birthdays as a kid, I got like their entire collection. Like occupied a giant shelf in my room and then all like over the holidays, I just like, you know, my parents couldn't drag me out of the room. And I read the whole thing cover to cover and it, it, I really enjoyed it.

• 2:19:19Speaker 02

  And that's one more. For the third one, maybe a little bit darker.

• 2:19:24Speaker 02

  But you know, comes to mind is Orwell's 1984.

• 2:19:29Speaker 02

  And you know, you asked what made an impression on me and the books that people should read. That one, I think, falls in the category of both. Definitely as one of those books that you read and you just kind of, you know, put it down and you stare in space for a while. And you know, that, that, that kind of work. I, I think there's, you know, lessons there. People should not ignore. And, you know, nowadays with like everything that's happening in the world, I can't help it. But you know, have my mind jump to some parallels with what Orwell described. And like this, this whole, you know, concept of double think and ignoring logic and, you know, holding completely contradictory opinions in your mind and not have that not bother you. And, you know, sticking to the party line at all costs.

• 2:20:14Speaker 02

  Like, you know, there, there's, there's something there.

• 2:20:18Lex Fridman?

  If anything, 2020 has taught me, and I'm a huge fan of Animal Farm, which is a kind of friendly, is a friend of 1984 by Orwell. It's kind of another thought experiment of how our society may go in directions that we wouldn't like it to go. But if, if anything, that's been

• 2:20:42Lex Fridman?

  kind of heartbreaking to an optimist about 2020 is that

• 2:20:48Lex Fridman?

  that society is kind of fragile. Like we have this, this is a special little experiment we have going on. And not, it's not unbreakable. Like, we should be careful to like preserve whatever special thing we have going on. I mean, I think 1984 and these books, Brave New World, they, they're helpful in thinking like, stuff can go wrong in non-obvious ways. And it's like, it's up to us to preserve it. And it's like, it's a responsibility. It's been weighing heavy on me because like, for some reason, like

• 2:21:25Lex Fridman?

  more than my mom follows me on Twitter. And I feel like I have, I have like now somehow a responsibility to.

• 2:21:33Lex Fridman?

  To this world and it dawned on me that like me and millions of others had like the little ants that maintain this little colony, right? So we have a responsibility not to be, I don't know what the right analogy is, but put a flamethrower to the place. We want to not do that. And there's interesting complicated ways of doing that as 1984 shows. It could be through bureaucracy, it could be through incompetence, it could be through misinformation, it could be through division and toxicity. I'm a huge believer in like that love will be the somehow the solution. So love and robots.

• 2:22:14Speaker 01

  Love and robots. Yeah, I think you're exactly right. Unfortunately, I think it's less of a flamethrower type. I think it's more of a, in many cases, can be more of a slow boil and that that's the danger.

• 2:22:26Lex Fridman?

  Let me ask, it's a fun thing to make a world-class roboticist engineer and leader uncomfortable with a ridiculous question about life. What is the meaning of life, Dimitri, from a robotics and a human perspective? You only have a couple of minutes or one minute to answer, so.

• 2:22:49Speaker 01

  I don't know if that makes it more difficult or easier. Actually, you know, they're very tempted to quote one of the stories by Isaac Asimov, actually, actually titled, appropriately titled, The Last Question, a short story where, you know, the plot is that, you know, humans build this supercomputer, you know, this AI intelligence and once it gets powerful enough, they pose this question to it, you know, how can the entropy in the universe be reduced? Right? So a computer replies, as of yet. Insufficient information to give a meaningful answer, right? And then, you know, thousands of years go by and they keep posing the same question. And the computer, you know, gets more and more powerful and keeps giving the same answer.

• 2:23:34Speaker 01

  You know, as of yet insufficient information to give a meaningful answer, or something along those lines, right? And then, you know, it keeps, you know, happening and happening. You fast forward like millions of years into the future and, you know, billions of years. And like at some point, it's just the only entity in the universe. It's like absorbed all humanity and all knowledge in the universe. And it like then keeps posing the same question to itself. And, you know, uh, finally it gets to the point where it is able to answer that question. But of course, at that point, you know, there's, you know, the heat death of the universe has occurred. And that's the only entity and there's nobody else to provide that answer to. So the only thing it can do is to, you know, answer it by demonstration. So it like, you know, recreates the big bang, right? And resets the clock, right?

• 2:24:16Speaker 01

  But like, you know, uh, I, I can try to give kind of a, a, a different version of the answer. You know, maybe, uh, not on the behalf of all humanity. I think that, that might be a little presumptuous for me to speak about the meaning of life on behalf of all humans, uh, but at least, you know, personally. It changes, right? I think if you think about kind of what, uh, gives, uh, you know, you and, uh, your life, meaning and purpose and kind of what drives you. Um, yeah, it seems to change over time, right? And the, the, that lifespan of, you know, kind of your existence. Uh, you know, when just, when you just enter this, this world, right? It's all about kind of new experiences, right?

• 2:24:58Speaker 01

  You get like new smells, new sounds, new emotions, right? And like, that's what's driving it, right? You're experiencing new amazing things, right? And that, that's magical, right? That, that's pretty, pretty, pretty, pretty awesome, right? That gives you kind of meaning. Then, you know, you get a little bit older, you start more intentionally, uh, learning about things, right? I guess actually before you start intentionally learning, probably fun. Fun is a, a thing that gives you kind of meaning and purpose and purpose and the thing you optimize for, right? And like fun is good. Then you get, you know, start learning. And I guess that this, this joy of comprehension and discovery is another thing that, you know, gives you

• 2:25:39Speaker 01

  meaning and purpose and drives you, right? Then, you know, you learn enough stuff and it, you want to give some of it back, right? And so impact and contributions back to, you know, technology or society, you know, people, you know, local or more globally, you know, is becomes a new thing that, you know, drives a lot of kind of your behavior and is something that gives you purpose and that you derive, you know, positive feedback from, right? You know, then you go and so on and so forth. You go through various stages of life. If you have, if you have kids, like that definitely changes your perspective on things. You know, I have three. That definitely flips some bits in your head in terms of, you know, what you care about and what you optimize for and, you know, what matters, what doesn't matter,

• 2:26:24Speaker 01

  right? So, you know, and so on and so forth, right? And I, it seems to me that, you know, it's all of those things. And as, as kind of you go through life, you know, you want these to be additive, right? New experiences, fun, learning, impact, like you want, you want to, you know, be accumulating. I don't want to, you know, stop having fun or experiencing new things. And I think it's important that, you know, just kind of becomes additive as opposed to a replacement or subtraction. But, you know, those few is probably as far as I got, but you know, ask me in a few years, I might have one or two more to add to the list.

• 2:27:00Lex Fridman?

  And before you know it, time is up, just like it is for this conversation. But hopefully it was a fun ride. It was a huge honor to meet you. As I, as you know, I've been a fan of yours and a fan of Google self-driving car and Waymo for a long time. I can't wait. I mean, it's one of the most exciting. If we look back in the 21st century, I truly believe it'll be one of the most exciting things we descendants of apes have created on this earth. So I'm a huge fan and I can't wait to see what you do next. Thanks so much for talking to me.

• 2:27:32Speaker 01

  Thanks. Thanks for having me. And it's also a huge fan. It doesn't work honestly. And I really enjoyed it. Thank you.

• 2:27:40Lex Fridman?

  Thanks for listening to this conversation with Dmitry Dolgov, and thank you to our sponsors. Trial Labs, a company that helps businesses apply machine learning to solve real world problems. Blinkist, an app I use for reading through summaries of books. BetterHelp, online therapy with a licensed professional. And Cash App, the app I use to send money to friends. Please check out these sponsors in the description to get a discount and to support this podcast. If you enjoy this thing, subscribe on YouTube, review it with five stars and up a podcast, follow on Spotify, support on Patreon, or connect with me on Twitter at Lex Fridman. And now, let me leave you with some words from Isaac Asimov.

• 2:28:21Lex Fridman?

  "Science can amuse and fascinate us all, but it is engineering that changes the world." Thank you for listening and hope to see you next time.