AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
The Alignment Problem
i think probably most people understand what the alignment problem is, but it's probly worth four sentences on the alignment problem. How do we build a g i that does what is in the best interest of humanity? We've been able to aline opening eyes biggest models better than we thought we would at this point so that's good. Am, we have some ideas about what to do next, but we cannot honestly look anyone in the eye and say, we see out a hundred years how we're going to solve this problem.