
23 - Mechanistic Anomaly Detection with Mark Xu
AXRP - the AI X-risk Research Podcast
Heuristic Arguments for Neural Nets
Heuristic arguments is intended to be this sort of umbrella term for machine checkable proof like thing that can apply to arbitrary computational objects. So there's this approach. There's also some people working on various like causal abstractions. I'm tempted to say something like, if the causal abstraction stuff works out, we'll just call that a heuristic argument and go with that sort of thing. Yeah, so maybe in summary, we're trying to be like in some sense, maximally ambitious with respect to the existence of heuristic arguments.
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.