3min chapter

Bankless cover image

168 - How to Solve AI Alignment with Paul Christiano

Bankless

CHAPTER

How to Delay Doom by One Year Per Year

The way we train these systems is by humans looking at what they do and then assessing how good it was Many failures involve Things where a human cannot look at what the system did and tell you that it was dangerous. You could instead like one way to intervene on this problem is to just try and improve humans ability to understand the concepts of an AI. And training AI systems that tell you something more like what would a human think if a human thought really carefully about this decision?

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