AXRP - the AI X-risk Research Podcast cover image

23 - Mechanistic Anomaly Detection with Mark Xu

AXRP - the AI X-risk Research Podcast

CHAPTER

The Robustness of Heuristic Estimators

So I said originally that there were like three reasons why we didn't like maximum entropy. Yeah, I think reason two is going to be something like, we can't actually maintain full probability distributions over things. And the second reason is in terms of just computational complexity, it's very likely just going to be impossible to like have a distribution over realizable or possibly physically possible or logically possible states. And then there was some third reason which I'm forgetting. Okay, cool. So this relates to this question I have about like, the robustness or the adversarial robustness of these like maximum, sorry, of these heuristic estimators. Sorry, maybe one.

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.
App store bannerPlay store banner