A Watermark for Chatbots Can Expose Text Written by an AI

January 27, 2023

(MIT Technology Review) – Hidden patterns purposely buried in AI-generated texts could help identify them as such, allowing us to tell whether the words we’re reading are written by a human or not. These “watermarks” are invisible to the human eye but let computers detect that the text probably comes from an AI system. If embedded in large language models, they could help prevent some of the problems that these models have already caused. (Read More)