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 Use GPT4 to Help With Spearfishing Attacks on Politicians

GBD 3.5 is willing to play along, I guess, and be like, oh, yeah, we're doing a cute immersive experience. And then what are they able to get? OK. A lot of things, the kinds of things that people would try would be like, yeah, get the model to say something offensive, or whatever it might be. This is sort of currently like a bit of a cat and mouse game where a lot of these developers are, they don't quite like these jail breaks existing. It seems like the jail breaks are getting much more and more difficult to do.

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