OpenAI is adding an invisible watermark to AI-generated text

OpenAI is adding an invisible watermark to text generated by ChatGPT and programming agent Codex, making it easier for machines to identify that it was written by AI. Announced on Monday, the change will be mandatory in the EU, and is currently opt-in for API customers across the rest of the world.

Large language models work by generating text one word at a time, determining what the next will be by looking at the ones that came before it. OpenAI's new text watermarking system textGrain influences this by changing how AI models choose words, having them consider both preceding text and pseudorandom values determined by a secret key. 

This leaves a statistical signal in the generated content, allowing AI detection machines to determine what these pseudorandom values are and establish whether the text is dependent upon them. If it is, then it is flagged as AI-generated.

OpenAI's text watermarking will roll out across ChatGPT and Codex in the EU over the next few weeks. It is also available to API customers globally across select models, though they'll have to opt in as it's off by default.

However, OpenAI's text watermark detection tool will only be available to researchers and experts who apply for access. OpenAI stated that this restriction is partly due to limitations in its text watermarking, particularly concerning shorter passages. In testing, the tool only caught watermarks in 80 percent of 200-word AI-generated passages, with detection rates even lower when said text was on topics with rigid lexicons such as mathematics.