OpenAI ↗ · 2024-06-27 18:00 · UTC+8
Finding GPT-4’s mistakes with GPT-4
Company news OpenAI Source language: English
CriticGPT, a model based on GPT-4, writes critiques of ChatGPT responses to help human trainers spot mistakes during RLHF
Excerpt
CriticGPT, a model based on GPT-4, writes critiques of ChatGPT responses to help human trainers spot mistakes during RLHF
Short excerpt from the source — open the original for the full text.