Evidence receipt / belief
Published · transcript-backedBeth Barnes: belief
4 May 2026 Machine Learning Street Talk The AI Models Smart Enough to Know They're Cheating — Beth Barnes & David Rein [METR]
“I think people u usually use scheming to refer to the model is doing what it's currently doing in in service of some long term goal and is deliberately doing things like appearing aligned or or getting a high score, like, in service of, you know, eventually accomplishing that goal versus you can be reward hacking both you know, you could be reward hacking in some extremely dumb way, like the boat example where it's just like, this is what RL kind of found or, like, this is what, you know, like, a star search found.”
Source trail
Everything needed to verify it.
- Speaker
- Beth Barnes
- Attribution
- Verified speaker
- Claim type
- belief
- Recorded
- 4 May 2026
- Publisher
- Machine Learning Street Talk
Transcript context
…Okay. That makes a lot of sense. And and and just closing the loop on on this kind of, like, notion that they are agents. So you were saying before that we can adopt an instrumental fiction basically. We can say they behave like agents, therefore they are agents. So similar to Dennett's intentional stance. But I suppose like the deflationary view is that, you know, the models exploit scoring loopholes under optimization pressure. The inflationary view is that they are scheming. I wouldn't call, like, exploiting I wouldn't call reward hacking scheming. Oh, interesting. I think people u usually use scheming to refer to the model is doing what it's currently doing in in service of some long term goal and is deliberately doing things like appearing aligned or or getting a high score, like, in service of, you know, eventually accomplishing that goal versus you can be reward hacking both you know, you could be reward hacking in some extremely dumb way, like the boat example where it's just like, this is what RL kind of found or, like, this is what, you know, like, a star search found. Or you can be reward hacking in a slightly more interesting way where you, like, actually have the goal of making reward go up, you know, and there's, like, planning and stuff going on about that. But these would all be, like, distinct from scheming. Yeah. I I I guess I'm I'm trying to understand the distinction. So you're so you're saying, like, there are examples, you know, like the boat going around, and and that's obviously degenerate behavior. So you you wouldn't interpret that with an agential stance. You would just say that's degeneracy. And when the when the sophistication increases, we might adopt an agential stance and say, it's in service of some bigger goal. But like, I guess the problem I have is, is it always just an interpretation? Could we have a mechanistic or, like, a strong definition of when something is like being an agent? Like, for the specific question that we're discussing, the the…
Stored transcript either side of the excerpt. The highlighted words are the published quote; the surrounding text is unedited source, never generated.