"Moment of Zen"  cover image

Effective Accelerationism and the AI Safety Debate with Bayeslord, Beff Jezoz, and Nathan Labenz

"Moment of Zen"

00:00

I'll Pretend to Be the AI on the Box

I think everything's on the table, to be honest with you. I try not to over index on any one particular failure mode. But more recently, Ellie Azer posited this AI at a box scenario and actually ran an experiment with humans where he said, I will pretend to be the AI on the box. Your job is to let me, or not to not let me out of the box, no matter what I say. He ran this a couple times with actual money on the line. And nobody knows what happened in those transcripts. It shouldn't be that big of a leap to think that sufficiently advanced AI might be able to trick people.

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