Ajeya Cotra on how Artificial Intelligence Could Cause Catastrophe
Future of Life Institute Podcast
The Problem With Alexa
There are still issues with whatever group you select to be like the most the best of humanity or like the most thoughtful or least biased. I definitely take that point okay one last shot at maybe something that could could solve this problem of Alex. What if we are able to understand to interpret what's going on in the in the model we've trained we can understand how Alex works on it on a deep level and maybe we can even train a another model to help us understand what’s going on in Alex so that we can test for whether Alex is developing motives that diverge from our own. If we had strong versions of that capability I think that we would be a lot safer.
00:00
Transcript
Play full episode
Remember Everything You Learn from Podcasts
Save insights instantly, chat with episodes, and build lasting knowledge - all powered by AI.
