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

It's not gonna they're not gonna be a very good employee.

Like they sort of need to be able to be focused on what they're trying to accomplish in order to be good at anything.

So, sort of goal-directed behavior is just a property that falls out of being able to do anything consistently across longer time horizons.

So, you know, if you wanna be a politician, if you wanna be a business leader, if you wanna be a general, you just have to be able to have strong goal-directed behavior.

And so I think.

I think that, you know, this is like I think why it's very clear to me that the AI systems will have goals, because they just need to be able to have them in order to accomplish the tasks.

And so the AI companies, like I said before, are really trying to create agents that can sort of go out and replace jobs.

And I think that sort of the underlying technology is there.

It just needs to be scaled up and improved.

And so it seems very likely to me that we'll end up with systems like this.

And so it's like, okay, well, maybe this is fine.

Like maybe we'll just have lots of like AI agents running around doing stuff for us.

But I I think the problem is we actually don't know how to specify what exactly those goals are.

Right.

Like, you know, this is the alignment problem.

It's like, well, we we know they'll have goals because we can see if their performance is really bad that, you know, that's that's not that's that's not gonna not gonna work.

But like, you know, if if you're if you're if you're in the case where, you know, you're a CEO

Is like, you know, really killing it.

He's making tons of money.

And you're like, cool, what are your goals?

Showing 201–220 of 1,006 · page 11 of 51