4min chapter

80,000 Hours Podcast cover image

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

80,000 Hours Podcast

CHAPTER

The Problem With Deploying an AI System

The difficulty is it's really difficult to get these systems to avoid using their dangerous capabilities. Oftentimes in these large language models, there'll be a prompt that will tell the model how it's supposed to behave. And sometimes users will ask you to do bad things. A thing that we've seen over the past few months is more and more that people can do what's called sort of jailbreaking. Can you think of an example of that? Yeah, my favorite is this is a jailbreak of chat TPT. I think it was, yeah, a 3.0 when it was using JPT 3.5 called Dan. Do anything now. Gives like a bunch of

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