Laura Weidinger: Ethical Risks, Harms, and Alignment of Large Language Models
The Gradient: Perspectives on AI
00:00
The Ethical and Social Risks of Harm From Language Models
You've had a couple of papers, you had a large one titled, the ethical and social risks of harm from language models. So could you just give an overview of that work? Absolutely. And I think you mentioned earlier, this was a collaboration of a lot of people. We were 20 plus people from across deep mind working on this. That was actually really critical for what we were trying to do.
Transcript
Play full episode
