ChatGPT and InstructGPT: Aligning Language Models to Human Intention
Deep Papers
Is LHF the Best Way to Fine Tune Language Models?
I don't want to make the claim that our LHF is like definitely the way to go. You can certainly use the same data that we're collecting and fine to using a different algorithm. So I think there's actually quite a bit of interesting research to do in terms of how you get similar benefits with less compute. But yeah I think I think that's kind of an open question. And then Jason if you want to ask another question then maybe maybe I'll open up the floor also to the authors to finish off.
00:00
Transcript
Play full episode
Remember Everything You Learn from Podcasts
Save insights instantly, chat with episodes, and build lasting knowledge - all powered by AI.
