Home > World > Anthropic Adds Invisible Watermarks to Claude-Generated Text and Files<\/p>\n
Hyderabad: Anthropic has begun introducing a new system designed to make Claude-generated content machine-detectable, marking a significant shift in how AI-generated text and files can be identified after they leave the Claude platform.<\/p>\n
The company says supported Claude models now embed an imperceptible watermark directly into generated text. Unlike a conventional watermark or visible AI label, users will not see anything unusual in the text. The marking is designed to preserve the meaning, readability and quality of the response while potentially surviving copying, pasting and some editing.<\/p>\n
The important distinction is that Anthropic is not putting a visible \u201cGenerated by Claude\u201d label on every paragraph.<\/p>\n
Instead, the watermark is incorporated into the way the model generates the text. The resulting signal is intended to be detectable by specialised systems even though an ordinary reader cannot see it.<\/p>\n
Anthropic says the marking is implemented at the model level, meaning it is intended to follow Claude-generated output regardless of whether the model is accessed through Claude\u2019s consumer products, Claude Code, Cowork, the API or supported third-party cloud platforms.<\/p>\n
The system is also being applied broadly rather than being limited to users in a particular country or region.<\/p>\n
Claude\u2019s file-generation capabilities are also part of the broader marking effort.<\/p>\n
For supported generated files, Anthropic is using digitally signed provenance metadata based on the C2PA standard rather than relying solely on a text-style watermark.<\/p>\n
C2PA is an open technical standard designed to record information about the origin and history of digital content. In the future, compatible software could potentially inspect a file and identify provenance information associated with its creation.<\/p>\n
The approach is particularly relevant as Claude increasingly supports the creation and editing of files alongside coding, research and analysis capabilities.<\/p>\n
The move comes as governments and technology companies increasingly focus on transparency and provenance for AI-generated content.<\/p>\n
One important development is the European Union\u2019s AI Act, which introduces transparency obligations for providers of AI systems generating synthetic content. The broader objective is to make it easier for users and organisations to identify AI-generated material.<\/p>\n
Anthropic\u2019s watermarking system provides a technical mechanism through which AI-generated content can carry a signal that can potentially be detected by specialised systems.<\/p>\n
However, the company is applying the technology more broadly than simply restricting it to one regulatory market.<\/p>\n