Ajeya Cotra on how Artificial Intelligence Could Cause Catastrophe
Future of Life Institute Podcast
The Role of Alex in the Development of Goals
Alex understands its training process, it understands human psychology. It knows that it's a model being trained by some humans for some purpose. And the key point here is that it's trained with human feedback on diverse tasks. So this thing is not being trained to actually take good actions. But every time there's a deviation, Alex is pushed in the direction of doing whatever it takes to get the humans to enter a high reward and not what the humans actually wish it would do.
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.
