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

Eliezer Yudkowsky

๐Ÿ‘ค Speaker
See mentions of this person in podcasts
1713 total appearances

Appearances Over Time

Podcast Appearances

Lex Fridman Podcast
#368 โ€“ Eliezer Yudkowsky: Dangers of AI and the End of Human Civilization

But that doesn't mean that you're correct and justified in letting everything slide.

Lex Fridman Podcast
#368 โ€“ Eliezer Yudkowsky: Dangers of AI and the End of Human Civilization

It means that things are in a horrible state, getting worse, and there's nothing you can do about it.

Lex Fridman Podcast
#368 โ€“ Eliezer Yudkowsky: Dangers of AI and the End of Human Civilization

Yeah, how can you tell if you're making progress?

Lex Fridman Podcast
#368 โ€“ Eliezer Yudkowsky: Dangers of AI and the End of Human Civilization

You can, like, put them all on interpretability, because when you have an interpretability result, you can tell that it's there.

Lex Fridman Podcast
#368 โ€“ Eliezer Yudkowsky: Dangers of AI and the End of Human Civilization

And there's like, but there's like, you know, interpretability alone is not going to save you.

Lex Fridman Podcast
#368 โ€“ Eliezer Yudkowsky: Dangers of AI and the End of Human Civilization

We need systems that will have a pause button where they won't try to prevent you from pressing the pause button.

Lex Fridman Podcast
#368 โ€“ Eliezer Yudkowsky: Dangers of AI and the End of Human Civilization

Because they're like, oh, well, I can't get my stuff done if I'm paused.

Lex Fridman Podcast
#368 โ€“ Eliezer Yudkowsky: Dangers of AI and the End of Human Civilization

And that's a more difficult problem.

Lex Fridman Podcast
#368 โ€“ Eliezer Yudkowsky: Dangers of AI and the End of Human Civilization

And, you know, but it's like a fairly crisp problem and you can like maybe tell if somebody's made progress on it.

Lex Fridman Podcast
#368 โ€“ Eliezer Yudkowsky: Dangers of AI and the End of Human Civilization

So you can write and you can work on the pause problem.

Lex Fridman Podcast
#368 โ€“ Eliezer Yudkowsky: Dangers of AI and the End of Human Civilization

I don't actually like the term control problem because, you know, it sounds kind of controlling and alignment, not control.

Lex Fridman Podcast
#368 โ€“ Eliezer Yudkowsky: Dangers of AI and the End of Human Civilization

Like you're not trying to like take a thing that disagrees with you and like whip it back onto, like make it do what you want it to do, even though it wants to do something else.

Lex Fridman Podcast
#368 โ€“ Eliezer Yudkowsky: Dangers of AI and the End of Human Civilization

You're trying to like,

Lex Fridman Podcast
#368 โ€“ Eliezer Yudkowsky: Dangers of AI and the End of Human Civilization

in the process of its creation, choose its direction.

Lex Fridman Podcast
#368 โ€“ Eliezer Yudkowsky: Dangers of AI and the End of Human Civilization

It's not smart enough to prevent you from pressing the off switch and probably not smart enough to want to prevent you from pressing the off switch.

Lex Fridman Podcast
#368 โ€“ Eliezer Yudkowsky: Dangers of AI and the End of Human Civilization

They're just not opposing your attempt to pull the off switch.

Lex Fridman Podcast
#368 โ€“ Eliezer Yudkowsky: Dangers of AI and the End of Human Civilization

Parenthetically, like...

Lex Fridman Podcast
#368 โ€“ Eliezer Yudkowsky: Dangers of AI and the End of Human Civilization

don't kill the system.

Lex Fridman Podcast
#368 โ€“ Eliezer Yudkowsky: Dangers of AI and the End of Human Civilization

If you're like, if we're getting to the part where this starts to actually matter and it's like where they can fight back, like don't kill them and like dump their, their memory, like, like save them to disc.

Lex Fridman Podcast
#368 โ€“ Eliezer Yudkowsky: Dangers of AI and the End of Human Civilization

Don't kill them.