13 - First Principles of AGI Safety with Richard Ngo
AXRP - the AI X-risk Research Podcast
00:00
Is There a Risk From a G I System?
CNN's John Defterios talks about the idea of a g i system, or goal seekingor goal directed agents. He says some people think that there is one natural way to coherently shape the world for simple goals. But as you scale this ability up, then it becomes increasingly unnatural to have the sort of exception for humans, he writes. And so we want our agents to be thinking in my very creative, flexible ways, defterios adds.
Transcript
Play full episode
