Connor Leahy on AI Safety and Why the World is Fragile
Future of Life Institute Podcast
00:00
How Could AI Go Wrong?
The weaker system in this context is a human. Yes. Perhaps you could talk about a good way to introduce the topic is to think about how could AI go wrong. So, what are some concrete scenarios? And I know they're probably a massive list in your head right now. But how could it go wrong? If someone asked me, Connor, can you please write down the top 10 ways I could kill a million people for under $10,000? I'd be like, well, I won't confirm or deny that I could do that, but if I could, I wouldn't do that.
Transcript
Play full episode
