ChatGPT and InstructGPT: Aligning Language Models to Human Intention
Deep Papers
00:00
The Long Term Alignment Research
As models get more and more powerful it's possible that as they optimize this they find maybe interesting or tricky. And I don't think we're quite there yet but at least it's something that you know we want to keep an eye on. But yeah so I mean who knows when we'll get there but that's the thing to think about.
Transcript
Play full episode
