Roman Yampolskiy on Objections to AI Safety
Future of Life Institute Podcast
00:00
The Limits of AI Monitoring
Many of these objections are long lines of we will see AI is doing something with dislike and then we will have time to react. Do you think that's a realistic prospect? I always think about let's say we start running super intelligence what do you expect to happen around you in the world does it look like it's working how would you know if it's slowly modifying genetic code nano machines things of that nature so this seems like it would work for primitive processes where you can see a chart go up and like you stop at certain level but it's not a meaningful way to control a large language model for example.
Transcript
Play full episode
