Became recently aware of the progress made in synthetic data and other algorithmic improvements. We have not pushed GPT-4 to the max yet.
e.g. this paper https://arxiv.org/abs/2305.20050
It details how training on the steps in step by step reasoning as opposed to just rewarding the end result can give significant improvements. And there is so much more.
Became recently aware of the progress made in synthetic data and other algorithmic improvements. We have not pushed GPT-4 to the max yet.
e.g. this paper https://arxiv.org/abs/2305.20050
It details how training on the steps in step by step reasoning as opposed to just rewarding the end result can give significant improvements. And there is so much more.