
13 - First Principles of AGI Safety with Richard Ngo
AXRP - the AI X-risk Research Podcast
How to Automate Alignment Research
i don't think we have particularly strong candidates t now, for ways in which you can use an ag to prevent scaling up to dangerous regimes. i feel uncertain about how like difficult or extreme governants interventions would need to be in order to actually get the world to think, he let's slow down a bit. Let's belike, much more careful. But it still feels plausible that pivotor action is a little bit ofa misnome. As the world becomes more sort of wakes up to the scale and scope of the problem.
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.