#65 – Katja Grace on Slowing Down AI and Whether the X-Risk Case Holds Up
Hear This Idea
00:00
The Threat of Recursive AI Improvement
It seems like the systems we have at the moment are much better at reasoning when they, when we sort of prompt them to reason aloud carefully. Which I think suggests that it would be hard for them to be running some separate train of thought That's kind of not what's going on. It's just like you're picking from some big distribution of masks. Right, like I'm wearing this mask, but there's like a thing that's wearing the mask that's also reasoning about what it wants and what it's doing. Yeah. And the main reason we're going fast is for lack of coordination or something. You might hope that they do better, but maybe if they're already implicitly
Transcript
Play full episode
