How easy is it to fool ChatGPT detectors?

Kara Newhouse

2023年9月4日

A Stanford study shows that ChatGPT detectors often fail to catch AI-generated content and have biases against non-native English, making them less useful than English teachers hope.

I wondered what constitutes literary language in the ChatGPT universe. Instead of college essays, I asked ChatGPT to write a paragraph about the perils of plagiarism. In ChatGPT’s first version, it w… https://www.kqed.org/mindshift/62317/how-easy-is-it-to-fool-chatgpt-detectors