From the source

Finding GPT-4’s mistakes with GPT-4

New model

OpenAI announces CriticGPT, a model based on GPT-4 that writes critiques of ChatGPT responses to help human trainers spot mistakes during RLHF.

From the source
CriticGPT, a model based on GPT-4, writes critiques of ChatGPT responses to help human trainers spot mistakes during RLHF
openai.com

Other stories

OpenAI· 16 Oct

Itaú's AI assistant and governance platform serve millions in a regulated sector

OpenAI· 16 OctCapability change

Plugin drives 3x registration surge and 10x agent creation

ModelsCriticGPT, GPT-4

OpenAI· 15 Oct

Law firm builds AI tool for draft agreement review

OpenAI· 14 OctCapability change

SentinelOne uses OpenAI Daybreak to speed malware reverse engineering from weeks to hours.