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 something that would take an AI research engineer, you know, a day, two days, three days to do, that's where the models are still quite bad.

On the sort of one to four hour tasks, they're like better than humans.

But then on these longer time horizon tasks, they're still worse.

And this is a uh it's a trickier problem, right?

And an intuition for why this is difficult is, you know, if you

And it

If you have to do something that involves like 50 steps and something that you did in step seven and step thirteen were crucial to something that you did in step fifty, it's like, how do you know which step that was?

And like, how do you actually sort of accurately figure out where you were on track and where you weren't on track?

And that's a bit difficult.

But you know, sometimes people will say, Oh, so the AI systems will never be able to do this.

And I think this is a bit silly.

And the reason why is that like, you know, there are business leaders, there

are generals, there are many different humans who have learned to do tasks in the timescale of decades.

There was no way that they could learn that from practicing tasks on the timescale of decades, right?

Like they just didn't have decades to practice.

They practiced on tasks that took weeks or months, you know, maybe years at most.

And then they learned to generalize about how to, you know, break up longer-term tasks into shorter-term tasks.

And it I I see no reason why AI systems won't be able to do that as well.

And so I think this is one of the things that's hard for people to see, which is you look

At current AI systems, and you're like, look, ChatGPT is bad at these long time horizon tasks.

Showing 161–180 of 1,006 · page 9 of 51