How OpenAI is approaching text watermarking under EU rules. Learn where watermarks apply, how detection works, and why access starts with researchers. Our approach to EU text provenance rules.
OpenAI today announced how it will comply with the EU AI Act, which requires providers of generative AI systems to mark AI-generated text in a way that makes it identifiable. Here are the details.
This move is to comply with the EU’s new AI transparency rules. OpenAI will add a digital watermark to text and code generated in the EU.
OpenAI details new text watermarking system for ChatGPT, Codex, and the API. Redesigned MacBook Pro with OLED to feature โsignificantly lighterโ design: report Michael Burkhardt Oct 4 2026.
News AI OpenAI will add a digital watermark to text and code generated in the EU This is to comply with the region’s new AI transparency rules. The company will soon begin adding an invisible watermark to text and code generated in the EU.
This follows a similar move by Anthropic earlier this year. OpenAI is using a proprietary system called textGrain that "adds an invisible statistical signal to the model’s word choices." Once added, a detector can spot these signals and ascertain if there’s a watermark.
The company says the system "matched or exceeded" the performance of other approaches, like SynthID for text. It still cautions that "strong performance under ideal conditions does not guarantee reliable detection in everyday use." That’s corporate speak for "it may not always work." It admits that shorter text is harder to detect, with around an 80 percent success rate.
The same goes for "content such as mathematics." Even editing text seems to bring down the success rate. OpenAI does plan on making the technology available in open source so others can tweak it.
Discover more from ChuckysCarnage
Subscribe to get the latest posts sent to your email.
