Connor Leahy on AI Safety and Why the World is Fragile
Future of Life Institute Podcast
00:00
Why AIs Would Be Different Than Humans?
The danger I see from AI in the short term is not super intelligence or like, you know, emergent things. Those might also happen. What I'm thinking about is systems that are perfect sociopaths that are just optimizing. There's a great post on list around called optimality is the tiger and agents are to teach which is related to this as well. It's not necessary to systems or agents. These can just be very simple AI systems. And they're just optimized for something and to optimize for something. They might just coldheartedly conclude. Well, I've simulated how to kill the president first run this piece of code with an internet connected device and then that spawn some
Transcript
Play full episode
