London Futurists cover image

Hacking the simulation, with Roman Yampolskiy

London Futurists

00:00

Is AI Boxing a Scientific Problem in AI Safety?

There are people who say that this is pseudoscience. Roman: I think what we're doing is actually bringing theology into science. If you have an intelligent agent, how can you place it in a virtual environment for safety and security purposes? Investigating how they can hack that safety protocol is the most scientific thing you can ask an AI safety.

Play episode from 05:06
Transcript

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