05: The Likelihood and Risks of Superintelligent Machines
The World as You’ll Know It: The Future Of Aging
00:00
How to Design a Machine That Can Never Work Without Telling It Every Thing
If we can't specify our entire preference structure about the future completely and correctly upfront, then it doesn't make sense to design machines that require that to be true in order for them to work. And so instead, from the machine's point of view, you want the machine to think, okay, I know this much about what the person wants, but there's other stuff I don't know. That's the challenge that you're proposing to solve.
Transcript
Play full episode
