AXRP - the AI X-risk Research Podcast cover image

16 - Preparing for Debate AI with Geoffrey Irving

AXRP - the AI X-risk Research Podcast

CHAPTER

How Hard Is Uncertainty Estimation?

In terms of uncertainty estimation, can you give us a sense of like, how hard it is in general? And maybe for people who haven't thought about it much, why? Why should we expect it to be hard, or should we even expectIt to be hard? So i think in somesense, it is a bit surprising that it's hard. But it turns out to be hard,. Like people wha have thrown their te like, bagging their heads against it, quite a lot. The thing that typically happens is there is a standard thing that works well, namely on sombling. It has te cons the cost that you have to train and copies of a model

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