AXRP - the AI X-risk Research Podcast cover image

4 - Risks from Learned Optimization with Evan Hubinger

AXRP - the AI X-risk Research Podcast

00:00

Training on a Huge Corpus of Data

How does a train process modify the model to start authorizing for that thing and code in its poon? And fundamentally, in the paper, we sort hov analyze two ways. How likely are these different things to occur? How well do they perform on things like simplicity? Are they like, you know, or least hap yo knoww ow?"

Transcript
Play full episode

The AI-powered Podcast Player

Save insights by tapping your headphones, chat with episodes, discover the best highlights - and more!
App store bannerPlay store banner
Get the app