AXRP - the AI X-risk Research Podcast cover image

23 - Mechanistic Anomaly Detection with Mark Xu

AXRP - the AI X-risk Research Podcast

CHAPTER

How to Drop Out Mechanisms in AI Training

The hope is that the mechanisms will be such that we're not forced to make these sorts of logical deductions that potentially are very obvious. The training set comes in where there's a set of mechanisms that you needed during training to explain most of the variants let's say 99.9% of the variants in the models performance or prediction or behavior, and so for any given data point you're like quote-unquote free to drop that interaction between the two noise terms. So if the sensors are only both on because of this like and interaction between the noise terms then you're in some sense free to drop it. You can notice that like the end of the two sensors wasn't true for the

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