Joe Carlsmith on How We Change Our Minds About AI Risk
Future of Life Institute Podcast
00:00
The Pessimistic Take on AI Interpreters
The pessimistic take there would be then, we have some AI interpreter trying to understand another AI system. But how do we know that this AI interpreter system is aligned with our interests? We can't really, that's kind of like a, we push the problem back one step. I think in particular, I think a lot of that comes from this worry that every system that you're working with is of the type that you're concerned that it's like deceiving you or has misaligned goals Or something like that. And so I'm generally more optimistic about using AI's even before having fully solved the alignment problem.
Transcript
Play full episode
