
23 - Mechanistic Anomaly Detection with Mark Xu
AXRP - the AI X-risk Research Podcast
The Importance of Rationality in AI
The hope is like we can avert those kinds of outcomes also by checking whether or not like the AI quote unquote knew that the humans were dead. And so where you is, I guess, the computers. Yeah, we're just like, like I can tell. Sure. All sensors are like suppose that there was one human still alive trapped in like a box and they had access to like every, you know, sensor that humans ever made,. They would be unable to tell whether or not the humans were alive or dead. That's no good. So it's like simultaneously conspired to like hack all the heartbeat sensors to make them like keep pretending that humans are alive and like hack all
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.