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 Future of Cryptography

Could you have watermarking even in a public model? I do not know how to do that. It seems very similar to this work on, like, um, inserting Trojans and neural networks. There's some line of research where you train a neural network such that if it sees a cartoon smiley face, then it outputs horse or something.

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