ChatGPT and InstructGPT: Aligning Language Models to Human Intention
Deep Papers
00:00
Is the Term Alignment Created by OpenAI?
Was the term alignment created by OpenAI? I hadn't heard it, you know, it's caught on recently. We're trying to think about what are the new alignment problems that might come up as we scale these models. And so there's some work on scalable supervision, we call it, and a bunch of other things, which I want to get into right now.
Transcript
Play full episode
