OpenAI BlogJune 27, 2024
Finding GPT-4’s mistakes with GPT-4
Excerpt
CriticGPT, a model based on GPT-4, writes critiques of ChatGPT responses to help human trainers spot mistakes during RLHF
CriticGPT, a model based on GPT-4, writes critiques of ChatGPT responses to help human trainers spot mistakes during RLHF