AXRP - the AI X-risk Research Podcast cover image

20 - 'Reform' AI Alignment with Scott Aaronson

AXRP - the AI X-risk Research Podcast

00:00

The Evolution of AI

In terms of its ability to deceive, you know, AI has now reached parity with a preschooler. And even the mistakes that it makes when it tries to solve a hard math problem are like the mistakes I have seen in a thousand exams. It's that it is undergoing same kinds of mistakes as a human mathematician would go through. But we've succeeded in building something that can learn in a way that is not entirely dissimilar to how we learn. We will be able to watch that happen.

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