6 - Debate and Imitative Generalization with Beth Barnes
AXRP - the AI X-risk Research Podcast
00:00
Are There Any Problems in Like, a Safety or an Alignment That This Would Solve?
Allignment technique aims to know everything that ole knows. The same group, iliver and geoffrey erving who came up with debate of casoa are working on an allignment technique for a new type of model. i'm wondering, it's kind of a strange question, but why do this? Like, what problems in like, or are are there problems inlike, a safety or a alignment that a this would solve? And also, what problems are you, like, are there any problems where you like, no, i'm not trying to solve like this problem with debate. I'm just trying to solve these things. Yes.
Transcript
Play full episode
