ChatGPT and InstructGPT: Aligning Language Models to Human Intention
Deep Papers
00:00
Is There a Jury on Large Language Models?
I think one question I've had is, and some of it's watching people roll out large language models for kind of different verticals. Do you do alignment for say mathematicians or scientists or biological recently? Is the answers that people want different or just one thing kind of covered enough or just trying to get the preferences right. And you might not have an answer, but any any any got some like where the industry goes. You know my preferences about food on an airplane are probably different from like my preference about food, debt of find on a restaurant for example.
Transcript
Play full episode
