AXRP - the AI X-risk Research Podcast cover image

2 - Learning Human Biases with Rohin Shah

AXRP - the AI X-risk Research Podcast

00:00

Is It Possible to Learn a Reward Function From Human Behavior?

i feel like while relying just on learning a reward function from human behavior, ah, that can then be just perfectly optimized, i think i am fairly confident that that will not work. But it seems likely that there are plans that involve learning what humans want and having better methods do that. Ah, but you do need to account for human viaces at some point. And so they like me to clarify that with you, and so on.

Transcript
Play full episode

The AI-powered Podcast Player

Save insights by tapping your headphones, chat with episodes, discover the best highlights - and more!
App store bannerPlay store banner
Get the app