
23 - Mechanistic Anomaly Detection with Mark Xu
AXRP - the AI X-risk Research Podcast
How to Be a Good Heuristic Estimator
So I think in some of these early posts, the idea is like step one, formalize heuristic arguments, step two, solve mechanistic anomaly detection, and step three, find a way of finding heuristic arguments. And really, I guess like these three things could sort of be run in parallel or yeah, not necessarily in order. So how has the plan going since then? Yeah, so I think like quarter one of 2023 was a bit rough; we didn't get that much done. But it's sped up since then. We have a pretty good formal problem statement about what it means to be a heuristic estimator for like a class of functions.
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.