News for hackers. Stuff that matters.
Re:Capabilities of GPT-4 on Medical Challenge Problems by tangjurine on Sunday March 26, 2023 @06:07PM (#35320143)
gpt is trained initially on predicting text, then trained with rlhf to make the model more helpful, etc. The second step is referred to as alignment.

Rlhf: https://huggingface.co/blog/rlhf

There are no comments on this comment yet.