
23 - Mechanistic Anomaly Detection with Mark Xu
AXRP - the AI X-risk Research Podcast
The Impossibility of Being Adversarily Robust in AI
In the AI realm, when I hear that something is vulnerable to adversaries, I'm really worried because I'm like, well, what if my AI is an adversary? So do you think that this worry applies in the heuristic arguments case? Yeah. It's basically impossible to be adversarially robust. For any quantity with sufficient noise, even if you expect very strongly the noise to average out to zero, there will exist a heuristic argument that only points out the positive values of the noise and drive you down. And so I think this is naively quite a big problem forlike the entire heuristic argument paradigm.
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.