13 - First Principles of AGI Safety with Richard Ngo
AXRP - the AI X-risk Research Podcast
00:00
Safety Research
M, it seems like the thing that a stops the slide to your incredibly powerful a unfriendly a G is we we get a a to help do our safety research for us. As well as a bunch of governments actions, right? M, yes. So that that feels like, you know, the sort of default proposal that i'm excited about. But it's hard to sayik, how much of a disagreement there is here, cause, youknow, allthe s you said are just reasons to be worried.
Transcript
Play full episode
