Menu
Sign In Search Podcasts Charts People & Topics Add Podcast API Pricing

Sergey Levine

๐Ÿ‘ค Speaker
700 total appearances

Appearances Over Time

Podcast Appearances

Dwarkesh Podcast
Fully autonomous robots are much closer than you think โ€“ Sergey Levine

It's just an argument for 2025 being a better year than 2009.

Dwarkesh Podcast
Fully autonomous robots are much closer than you think โ€“ Sergey Levine

But there's also other things about robotics that are a bit different than driving.

Dwarkesh Podcast
Fully autonomous robots are much closer than you think โ€“ Sergey Levine

Like in some ways, robotic manipulation is a much, much harder problem.

Dwarkesh Podcast
Fully autonomous robots are much closer than you think โ€“ Sergey Levine

But in other ways, it's a problem space where it's easier to get rolling, to start that flywheel with a more limited scope.

Dwarkesh Podcast
Fully autonomous robots are much closer than you think โ€“ Sergey Levine

So to give you an example,

Dwarkesh Podcast
Fully autonomous robots are much closer than you think โ€“ Sergey Levine

If you're learning how to drive, you would probably be pretty crazy to learn how to drive on your own without somebody helping you.

Dwarkesh Podcast
Fully autonomous robots are much closer than you think โ€“ Sergey Levine

Like, you would not trust your teenage child to learn to drive just on their own, just drop them in the car and say, like, go for it.

Dwarkesh Podcast
Fully autonomous robots are much closer than you think โ€“ Sergey Levine

And that's like a, you know, a 16-year-old who's had a significant amount of time to learn about the world.

Dwarkesh Podcast
Fully autonomous robots are much closer than you think โ€“ Sergey Levine

You would never even dream of putting a 5-year-old in a car and tell him to get started.

Dwarkesh Podcast
Fully autonomous robots are much closer than you think โ€“ Sergey Levine

But if you want somebody to, like, clean the dishes โ€“ like, dishes can break too, but you would probably be okay with a child trying to do the dishes โ€“

Dwarkesh Podcast
Fully autonomous robots are much closer than you think โ€“ Sergey Levine

without somebody constantly like, you know, sitting next to them with a break, so to speak.

Dwarkesh Podcast
Fully autonomous robots are much closer than you think โ€“ Sergey Levine

For a lot of tasks that we want to do with robotic manipulation, there's potential to make mistakes and correct those mistakes.

Dwarkesh Podcast
Fully autonomous robots are much closer than you think โ€“ Sergey Levine

And when you make a mistake and correct it, well, first you've achieved the task because you've corrected, but you've also gained knowledge that allows you to avoid that mistake in the future.

Dwarkesh Podcast
Fully autonomous robots are much closer than you think โ€“ Sergey Levine

With driving, because of the dynamics of how it's set up, it's very hard to make a mistake, correct it, and then learn from it because the mistakes themselves have significant ramifications.

Dwarkesh Podcast
Fully autonomous robots are much closer than you think โ€“ Sergey Levine

Now, not all manipulation tests are like that.

Dwarkesh Podcast
Fully autonomous robots are much closer than you think โ€“ Sergey Levine

There are truly some, like, very safety-critical stuff.

Dwarkesh Podcast
Fully autonomous robots are much closer than you think โ€“ Sergey Levine

And this is where the next thing comes in, which is common sense.

Dwarkesh Podcast
Fully autonomous robots are much closer than you think โ€“ Sergey Levine

Common sense, meaning the ability to make inferences about what might happen that are reasonable guesses, but that do not require you to experience that mistake and learn from it in advance.

Dwarkesh Podcast
Fully autonomous robots are much closer than you think โ€“ Sergey Levine

That's tremendously important, and that's something that we basically had no idea how to do about five years ago.

Dwarkesh Podcast
Fully autonomous robots are much closer than you think โ€“ Sergey Levine

But now, you...