
23 - Mechanistic Anomaly Detection with Mark Xu
AXRP - the AI X-risk Research Podcast
The Heuristic Estimation of Quantity
There's some example in the paper where it really checks out the debate is not going to work. And so instead of doing debate, we want to do this other thing that's going to be kind of interesting. So if you imagine being like searching for heuristic arguments in a setting where you have like hash of n over n to the 1.5 or whatever,. Then you would like check hash of one and suppose it’s positive, you're like, great. Let's assume let's include term one. Although in that case, you really should be below zero and expectation. Yeah.
00:00
Transcript
Play full episode
Remember Everything You Learn from Podcasts
Save insights instantly, chat with episodes, and build lasting knowledge - all powered by AI.