Rohin Shah
TalkRL: The Reinforcement Learning Podcast
Ai Systems - How Does Alignment Relate to Ai Safety?
Accidents misuse structural risk. Structural risks happen when ouow i, as we infuse ai systems into our economy, do any new sorts of problems arise? Do we get into like races to the bottom on safety? The way to build alined ai systems in the sense of ai systems that don't make, take bad actions that they knew were is that you use a lot of human feedback and train your system to wear like the human feedback. This doesn't solve the entire problem. You basically then just want to like, make your human, the people viding your feedback, as powerful as possible.
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.
