Anthropic explains how Claude’s invisible text watermarks will work
Anthropic has announced that it will implement invisible watermarking for text generated by its Claude AI model to comply with EU transparency regulations. The system uses the SynthID-Text approach to embed detectable patterns in the model's word choices without impacting output quality.
Why it matters
This represents a significant step in AI governance, as major developers move to standardize machine-readable identification for synthetic content.
Anthropic has clarified how it’s planning to apply invisible watermarks to Claude-generated text in order to comply with Europe’s AI transparency rules. On Friday, Anthropic announced that Claude’s text marking system is “a version of the SynthID-Text approach” — an open-source watermarking technology developed by Google DeepMind that creates detectable patterns using wording probabilities.
This watermarking feature, alongside C2PA support for Claude-processed images, is being introduced to meet Anthropic’s obligations under the European Union’s AI Act, which requires synthetic audio, image, video, and text to include machine-readable marks that enable the content to be detected as artificially generated or manipulated. Anthropic says the text watermarks won’t make Claude more expensive for users, or “have any practical impact on the quality or content of Claude’s outputs.” Here’s Anthropic’s explanation for how it works:
Get smarter about the news
Sign up free for a feed built around what you actually care about, Dive Deeper research on any story, and the full text of every article.
Create free accountAlready have an account? Sign in