Dylan Hadfield-Menell, UC Berkeley/MIT: The value alignment problem in AI
from Generally Intelligent Hosted by Kanjun Qiu
Dylan Hadfield-Menell (Google Scholar) (Website) recently finished his PhD at UC Berkeley and is starting as an assistant professor at MIT. He works on the problem of designing AI algorithms that pursue the intended goal of their users, designers, and society in general. This is known as the value alignment problem. Highlights from our conversation: 👨👩👧👦 How to align AI to human values 📉 Consequences of misaligned AI -> bias & misdirected optimization 📱 Better AI recommender systems
Embed this episode
No transcript yet.
Frequently asked questions
How long is this episode of Generally Intelligent?
This episode is 1 hour and 31 minutes long.
When was this Generally Intelligent episode published?
This episode was published on May 12, 2021.
Can I download this Generally Intelligent episode?
Yes. Use the download control on the episode player to save the publisher-provided media file.