2min chapter

80,000 Hours Podcast cover image

#156 – Markus Anderljung on how to regulate cutting-edge AI models

80,000 Hours Podcast

CHAPTER

The Future of AI Risk Assessments

It's very difficult to exhaustively test whether a system can do X. At least in this sort of behavior elicitation scheme, I don't think we will have full guarantees that models can't do X or they can't be useful for X. But hopefully we will be there at some point. If we don't get there, what this will look like is basically, it looks a little bit like sort of Perian like falsificationism or whatever. And then, yeah, and so you try really, really hard to get the system to do X, and if you try hard enough and it keeps not doing X, then you know, maybe you think that it actually can do X

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