13 - First Principles of AGI Safety with Richard Ngo
AXRP - the AI X-risk Research Podcast
00:00
Is There a Consequence That Intelligent Future Systems Will Effort to Do Things That Are Bad for Humans?
There's some instinct that says, like, look, once you have systems that are alike, smarter than me, if these sort of ideas actually help it achieve goals er, you know, do whatever it's being selected to do, then that should happen. But the way in which i am choosing which one's to ibstantiate is very dependent on these sort of gut emotional instincts that were kind of light honed over a long period of evolution and, like, childhood and so on. And the those emotions and instincts are things that feel very hard to reason about precise, in a precise technical manner. Do you agree with that argument? Or well, it seems like the cute question as
Transcript
Play full episode
