3min chapter

80,000 Hours Podcast cover image

#81 Classic episode - Ben Garfinkel on scrutinising classic AI risk arguments

80,000 Hours Podcast

CHAPTER

Are There Objections to the Idea of Progress on Alignment Techniques?

I think it'd be relatively hard to argue at least against the idea that there's this sort of deep entanglement between engineering of goals and making it act in a way would be intuitively regard as intelligent. I think probably the main objection you could raise would be to say basically like okay yeah there's this entanglement but even if there's this Entanglement that doesn't really resolve the issue. There's a bit of this sort of unhappy valley where you know again let'ssay city planner case if we just basically don't have any progress on alignment techniques we're stuck using hand coded reward functions or supervised learning, he says.

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