2min chapter

AXRP - the AI X-risk Research Podcast cover image

12 - AI Existential Risk with Paul Christiano

AXRP - the AI X-risk Research Podcast

CHAPTER

Is There a Need for Decoupling?

In some sense, the reason we wanted that ai was just because it incoded some knowledge about how to do useful stuff in the world. And so what we'd like to do is to say, ok, we are going to set things up so it's easier for gradient descent to learn just the knowledge aboutHow to behave well in the world,. rather than learning that knowledge and bedded with an agent that's trying to screw over humans. Yes, it's very unclear if that can be done. I think it's also fairly likely that in the end that langwaest. Don't know how that looks.

00:00

Get the Snipd
podcast app

Unlock the knowledge in podcasts with the podcast player of the future.
App store bannerPlay store banner

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

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