4min chapter

The Inside View cover image

David Krueger–Coordination, Alignment, Academia

The Inside View

CHAPTER

The Importance of Causality in Machine Learning

I think there's a lot of hype and over-enthusiasm for things that won't really work in practice. I've been mixing together understanding causality and being an agent, but those are, like, totally separate things in principles. You can have a good causal model of the world, and still just be doing prediction - you don't have to be an agent. And this is potentially a good way to test for power-seeking and instrumental goals because you know what your future will look like.

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