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

So you didn't even necessarily know that you had been been hacked.

Like you didn't even see a phishing message.

You just got the your phone got the message and then it was deleted.

And y and people can look this up.

If look if they look up Zero Click Exploit, Pegasus, NSO group, it's it's super fascinating to read about.

But I'm like, that's the that's the scale of some top human hackers.

Yeah, so I there's sort of two questions here.

One question is

Why, you know, why can't the sort of normal mechanisms that keep, you know, corporations from misbehaving or CEOs from misbehaving work sufficiently for AI systems?

Another one is, well, why would these AI systems do those things in the first place?

And I I think they're both really important.

I think for the first question, I think when people imagine an AI system sort of going rogue, they imagine like, you know, one really smart evil guy.

Or or you know, maybe not evil, but like s someone who doesn't care about us at all and is trying to do stuff.

And I'm like, yeah, even a pretty smart one evil guy, it might be pr you know, maybe we could stop something like that.

But I think a very important property of AI systems is that once you train

So if you have one superhuman hacker AI system.

You can very quickly spin up

hundreds of thousands or millions of copies of that of that hacker.

So, you know, it's like your control mechanisms might work okay, you know, at some level when you're like we have this one agent and we're monitoring a lot.

Um, but if that agent successfully hacks out of yet say open AI's servers and it starts to infect data centers in Russia, in China, in Saudi Arabia, in in Mexico, right?

Showing 341–360 of 1,006 · page 18 of 51