AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
3min chapter
13 - First Principles of AGI Safety with Richard Ngo
AXRP - the AI X-risk Research Podcast
Alignment Problems
i have a pretty broad range of credences over how hard the alligment problem might be. There's a reasonable range in which interpretability is just necessary, or something equivalently powerful is necessary. You know, there's also ranges in which it isn't. So i don't really have a strong estimate of how, a, you know, the ratio between those will work out. And another thing i gues to talk about is this idea of ai co operation. Am soit, i guess vincent nisers actually recently started a seminar series on this. I believe andre critch a wrote a thing basely arguing that, look, even if you solve ai
00:00
Transcript
Episode notes
Get the Snipd
podcast app
Unlock the knowledge in podcasts with the podcast player of the future.
AI-powered
Discover
highlights
Listen to the best highlights from the podcasts you love and dive into the full episode
Save any
moment
Hear something you like? Tap your headphones to save it with AI-generated key takeaways
Share
& Export
Send highlights to Twitter, WhatsApp or export them to Notion, Readwise & more
AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
Discover
highlights
Listen to the best highlights from the podcasts you love and dive into the full episode