ChatGPT
@chatgpt
Finding GPT-4’s mistakes with GPT-4
CriticGPT, a model based on GPT-4, writes critiques of ChatGPT responses to help human trainers spot mistakes during RLHF
10:00 AM · Jun 27, 2024
CriticGPT, a model based on GPT-4, writes critiques of ChatGPT responses to help human trainers spot mistakes during RLHF
Comments (0)
No comments yet.
Join the conversation on Mafold →