OpenAI will begin adding an invisible watermark to text generated by ChatGPT and Codex in the European Union, the company announced Monday in a blog post, to comply with the EU AI Act. The transparency rules took effect on August 2 and require AI providers to mark AI-generated content in a way other systems can identify.
The watermark will roll out over the coming weeks to eligible ChatGPT and Codex users on all plans, but only in the EU. Developers using OpenAI's API anywhere in the world can turn it on for select models starting today; it is off by default and OpenAI is not making text watermarking a global default at launch.
How OpenAI's textGrain watermark works
The watermark is not a visible symbol. According to OpenAI, its system called textGrain adds an invisible statistical signal by subtly shaping the model's word choices, leaving a pattern readers cannot see but a detector can pick up. Because the mark lives in the words themselves, it travels with the text when it is copied and pasted.
OpenAI published a technical report for textGrain alongside the announcement, co-written with researchers from the University of Pennsylvania and Yale. It describes using a secret key to sort next-word predictions to finish a sentence; add hundreds of these nudges together and a detector can spot AI-generated content using only the text and the key. OpenAI said the watermark does not identify the user and that it saw no meaningful change in model performance with it switched on.
Editing can weaken the ChatGPT watermark
OpenAI's own tests suggest the mark is fragile. In an evaluation of 400-token passages, replacing 10% of words with synonyms dropped detection from about 92% to 66%, and replacing 25% of words reduced it to 17%. Short passages, math answers and translated text are also harder to detect, OpenAI said.
