2min chapter

80,000 Hours Podcast cover image

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

80,000 Hours Podcast

CHAPTER

How to Evaluate AI Systems for Deception

Arc Evows is testing AI systems to see if they can figure out a way to escape. The tests are done with humans involved, partly to make sure that the model doesn't engage in any behavior that you wouldn't endorse or that might be bad. "It seems it seems like a bad idea in this evaluation setting to show that you have certain dangerous capabilities," 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