ChatGPT and InstructGPT: Aligning Language Models to Human Intention
Deep Papers
OpenAI
The full 175 billion parameter GBD3 can do that the smaller models can't, right? Like, let's say like imitating an author writing a story. But yeah, I guess it really is a story of like pointing the models in the direction that you want to point them. It just so happens for this particular like in this particular case, the thing we're pointing them at is doing well according to human preferences on this very particular distribution.
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.
