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 that's the tricky part about I mean, that's one of the sort of core difficulties of alignment is that we just don't get to look into its motivational structure and see what the actual goals are.

you have this like giant neural network with like billions or trillions of of of digital neurons and they're all just numbers to us and we're like, well, we can see its behavior.

We can see how it's acting, but we actually don't have a way to sort of hierarchically structure goals.

We can just sort of like give it a treat when we see things, you know, see it doing things it likes.

But, you know, and I I think, you know, I I I grew up very religious and, you know, there w you know one

of the things is like when you when you're really religious, you're supposed to say or do certain things.

And it's it's not always easy to sort of get kids to to, you know, believe the things you want them to believe.

It's much easier to sort of get them to sort of show the behaviors you want them to show, but they maybe don't like that you're doing this.

And maybe when they're adults, they're going to go off and do a totally different thing.

And so I think that this is sort of the same and I think, you know, humans have it easier because we do share this

you know, we share this sort of psychology.

We you know, we share this underlying structure of empathy.

And, you know, I think most people, e even if they're being uh deceptive, are not gonna, you know, wanna go and and

you know, cause a bunch of damage or take over the world or kill a bunch of people, because we sort of have these like

almost hardwired, you know, empathy and and sort of ability to think about and care about other people.

But I I I do think that AI systems are not going to have these by default.

They're not going to have them naturally.

So the only way they would have them if we could figure out a way to sort of get these goals deep in there.

And I I I don't know.

I I think what I really want people to understand is that

Showing 581–600 of 1,006 · page 30 of 51