An AI detector mislabeled nearly every essay written by a non-native English speaker as being written by a bot

Some of the most popular GPT-detection systems mislabeled essays written by non-native English speakers as AI-generated, a new Stanford study says.

ai ai bias artificial intelligence bot chatbot chatbots chatgpt detection english essay generated gpt gpt-3 gpt-4 large language models llms openai popular speaker speakers stanford study systems tech insider