3min chapter

Machine Learning Street Talk (MLST) cover image

#94 - ALAN CHAN - AI Alignment and Governance #NEURIPS

Machine Learning Street Talk (MLST)

CHAPTER

Is There a Potential Downside to AI?

Eliez Kalski: I think if we're building consequentialist type agents, it seems pretty hard that we're going to be able to get them not to pursue some kind of power seeking. This is why I'm quite pessimistic actually about alignment. The most feasible path to getting to a sort of safe world is coordination where we agree, okay, now we have evidence from researchers that our systems do XYZ and like YZ are particularly dangerous. So with this evidence, we agree,Okay, let's not build systems in this way. Right now it's sort of like the Wild West. We don't really know what's going on.

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