Jeffrey Ladish

speaker

1,006 appearances 1 recordings 1 series first heard Apr 2025 last heard Apr 2025

Jeffrey Ladish’s voice in public audio — every appearance, attributed to the second.

Trend

recordings per month · last 12 months

No recordings in the last 12 months.Older appearances are listed below; set an alert to hear about the next one.

Appearances

newest first · ▶ plays the moment

"The Cognitive Revolution" · Reward Hacking by Reasoning Models & Loss of Control Scenarios w/ Jeffrey Ladish of Palisade Research, from FLI Podcast · 2 Apr 2025 podcast

And some of them, you think, might be trying to steal your money.

And some of them are like honest and they want you to succeed and they want you to flourish and they're and they're gonna try to help you.

How do you tell who who's on your side and who's not on your side?

You know, they they might they might point at each other and be like, this guy's lying or this guy's lying.

But you as a six year old are gonna have a are gonna have a very hard time figuring out who's telling you the truth.

And I don't think you're gonna do that well.

I think you're probably gonna lose a lot of your money, maybe all your money.

And so I think this is this is the challenge that if we actually build AI systems smarter than us, which we're on track to do very soon, we're gonna have a very hard time knowing when they're just telling us things we wanna hear versus when they're actually doing things because they want us to have good things.

Well, I definitely think we should try this.

And, you know, some some AI researchers are trying to do this.

It's it's a very good thing to try, right?

And I and I I highly encourage, you know, any AI researchers out there to to really prioritize this.

I think it's actually probably more important than reinforcing other s certain other kinds of behaviors, but I do expect it to be very difficult.

I think one problem is when you're when you're training a system to sort of relentlessly solve difficult problems.

And then you also try to train the system to have other properties like honesty.

You have a situation where its training incentives are at odds with each other.

Like actually, the most efficient way to solve the solution might not be by being honest.

So by imposing this honesty constraint, you're sort of like you become the obstacle in the way of the system, you know, becoming really good at problem solving.

And so if the system is smart enough to route around you,

You know, it might be like, well, I'm I'm I'm supposed to be honest, but like, can I tell whether, you know, the user will actually be able to catch me out here?

Showing 521–540 of 1,006 · page 27 of 51