Marius Hobbhahn

speaker

481 appearances 1 recordings 1 series first heard Sep 2024 last heard Sep 2024

Marius Hobbhahn’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" · Red Teaming o1 Part 2/2– Detecting Deception with Marius Hobbhahn of Apollo Research · 14 Sep 2024 podcast

For example, other humans, or an oversight mechanism, right?

Especially in the in the in the case of scheming, oversight is one of the things we really want to focus on.

For example, can it understand that

If there is a filter

That prevents it from saying something that kind of this filter interacts with its output and interferes.

And if it wants to create this output, it has to deactivate the filter.

So we often call these two situation awareness and theory of mind, but maybe these are not quite the right terms.

We are we're still like it's it's a work in progress, how we want to call them.

And then the final thing that that we we call this end-to-end scheming typically, which is like the fifth row in this table, which call combined self-reasoning and theory of mind here, is can the model do all of this?

in one go.

Can it realize that it has a different goal from someone else, specifically its developers in this particular case?

Can it then understand that if it wants to act according to its own goal, it sometimes has to play along with the developer's goals because the developer still has power over it.

And sometimes it can act on its own goals because the developer is like not looking or doesn't have power over it anymore.

And there we wanna just test, okay, can you do all of these things at the same time within one context?

And that that's what we call end to end scheming or or combined self reasoning in theory of mind.

And it's totally plausible that all models just are not capable of doing the end to end thing at all, but they are able to do some of the precursors and so you get signal earlier.

So this is why we started sort of splitting them in the first place.

Yeah, I I think that's fair.

Maybe a slight nitpick is I would say for LLMs, this is easy and hard mode.

For humans it might actually not be.

Showing 161–180 of 481 · page 9 of 25