Roman Yampolskiy on Objections to AI Safety
Future of Life Institute Podcast
00:00
The Impossibility of AI Alignment
There are limits to what you can understand predict and do. You have to operate within where those limits don't kill everyone so if you have a system like GPT for when it makes mistakes somebody commits suicide Somebody's depressed that of course will pay for trillion dollars in economic growth benefit. The burden of proof with impossibility results is on me I published this paper saying you can have a fully predict every action of a smarter than you system the beautiful thing about impossibility results is that they are kind of self-referential.
Transcript
Play full episode
