
23 - Mechanistic Anomaly Detection with Mark Xu
AXRP - the AI X-risk Research Podcast
The Importance of Mechanistic Anomalies in Training
The hope is that if you do mechanistic anomaly detection relative to a data set of size a million, then you're like false positive rate is order of one over a million. And so as long as you have this like IID assumption, then you can in fact flag everything that you've like never seen before as anomalous while maintaining a false positive rate that's still relatively low and bounded perhaps by like one over your training set size. But suppose that you have this data set where the AI like never murders all humans. Then in some sense, your AI like can't murder all the humans with a rate much more than one over amillion or elselike you would have seen it happen
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.