London Futurists cover image

Hacking the simulation, with Roman Yampolskiy

London Futurists

00:00

Is the AI in a Box Smarter Than Us?

In the long term, we are likely to be successful if we are in a simulation. Maybe getting help from superintelligence will allow us to better understand physics of the simulation and find useful exploits. It's very hard to do safety. You have to consider every conceivable exploit. It's a lot easier to hack. You just need to find one exploit. So I'm optimistic that in the longterm, we are probably going to be successful."

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