Roman Yampolskiy on Objections to AI Safety
Future of Life Institute Podcast
00:00
The Future of Artificial Intelligence
When we have actual systems we can work with AI safety becomes more of a science and that less speculative. So it's definitely more concrete science where you can publish experimental results philosophy allows you to just have thought experiments they're obviously not pure science like it is now. The way AI has developed is bad because we are we don't have insight into how the models work right? essentially we have very little understanding for why it works or if it's gonna continue working.
Transcript
Play full episode
