Future Claude models will embed a statistical watermark in generated text worldwide. The EU’s AI transparency rules pushed Anthropic to change the model’s word-selection process—not add a visible label. The useful question is what that mark can actually establish.
Aug 15, 2026 at 8:04 PM
How Claude's text watermarking works
Future Claude models will generate text that contains a watermark. This is a way of determining the likelihood that Claude was involved in writing the text, and we, along with several other major AI providers, are implementing this change to comply with the EU AI Act. In this article, we share answers to some of the questions we’ve received about how our chosen watermarking method works, whether it affects Claude’s outputs, and why we’re making this change.
How Claude marks AI-generated content | Claude Help Center
Anthropic has signed the EU AI Act's Article 50(2) Code of Practice on Transparency of AI-Generated Content, as a provider of both generative AI models and generative AI systems. This article describes how we’re planning to put those commitments into practice, how marking works, and what its limitations are. We’ll update this article and publish more detailed technical guidance as it becomes available.
Alex Cui on Twitter / X
Claude's watermark probably doesn't work how you think. As the CTO of GPTZero, I'll explain how Anthropic, Google and OpenAI are building text watermarking in this brief explainer and whether it can be defeated.Almost all forms of watermarking that are fast and cheap enough for… https://t.co/3Ghcz3PTwJ— Alex Cui (@alexcdot) August 11, 2026
Code of Practice on Transparency of AI-generated Content
This code of practice supports compliance with the AI Act transparency obligations related to marking and labelling of AI-generated content.
Watermarks aren’t the silver bullet for AI misinformation
Digital watermarks are easily broken and abused.
Identifying AI-generated images with SynthID
Today, in partnership with Google Cloud, we’re beta launching SynthID, a new tool for watermarking and identifying AI-generated images. It’s being released to a limited number of Vertex AI customers using Imagen, one of our latest text-to-image models that uses input text to create photorealistic images. This technology embeds a digital watermark directly into the pixels of an image, making it imperceptible to the human eye, but detectable for identification. While generative AI can unlock huge creative potential, it also presents new risks, like creators spreading false information — both intentionally or unintentionally. Being able to identify AI-generated content is critical to empowering people with knowledge of when they’re interacting with generated media, and for helping prevent the spread of misinformation.
How Much of the Internet Is Written With AI?
In a random sample of 10,000 webpages collected in July 2026, one-in-ten show signs of being written or substantially edited by AI.
The Impact of AI-Generated Text on the Internet
The proliferation of AI-generated and AI-assisted text on the internet is feared to contribute to a degradation in semantic and stylistic diversity, factual accuracy, and other negative...
The Impact of AI-Generated Text on the Internet
The proliferation of AI-generated and AI-assisted text on the internet is feared to contribute to a degradation in semantic and stylistic diversity, factual accuracy, and other negative...
Scalable watermarking for identifying large language model outputs
Large language models (LLMs) have enabled the generation of high-quality synthetic text, often indistinguishable from human-written content, at a scale that can markedly affect the nature of the information ecosystem1–3. Watermarking can help identify synthetic text and limit accidental or deliberate misuse4, but has not been adopted in production systems owing to stringent quality, detectability and computational efficiency requirements. Here we describe SynthID-Text, a production-ready text watermarking scheme that preserves text quality and enables high detection accuracy, with minimal latency overhead. SynthID-Text does not affect LLM training and modifies only the sampling procedure; watermark detection is computationally efficient, without using the underlying LLM. To enable watermarking at scale, we develop an algorithm integrating watermarking with speculative sampling, an efficiency technique frequently used in production systems5. Evaluations across multiple LLMs empirically show that SynthID-Text provides improved detectability over comparable methods, and standard benchmarks and human side-by-side ratings indicate no change in LLM capabilities. To demonstrate the feasibility of watermarking in large-scale-production systems, we conducted a live experiment that assessed feedback from nearly 20 million Gemini6 responses, again confirming the preservation of text quality. We hope that the availability of SynthID-Text7 will facilitate further development of watermarking and responsible use of LLM systems.
Wikipedia:Signs of AI writing
This is a list of writing and formatting conventions typical of AI chatbots such as ChatGPT, with real examples taken from Wikipedia articles, drafts, comments, and other content. It is a field guide to help detect undisclosed AI-generated content on Wikipedia: while some of the signs may be broadly applicable, some may not apply in a non-Wikipedia context.[a] Not all text featuring these indicators is AI-generated, as the large language models that power AI chatbots are trained on human writing, including Wikipedia. Many elements of AI writing can be found in editorials, blogs, or fan fiction.
The Impact of AI-Generated Text on the Internet
By mid-2025, roughly 35% of newly published websites were classified as AI-generated or AI-assisted.
EU Icons for labelling AI-generated content
Deployers of generative AI systems can use the EU set of icons to label certain AI-generated content, in accordance with the AI Act transparency rules.
Google made a watermark for AI images that you can’t edit out
For now, SynthID works only in Google’s ecosystem — but it could someday be all over the internet
Can AI Detectors Be Trusted?
Society has always trusted editors, teachers, peer reviewers, and readers to set acceptable standards for writing. In the past, the biggest challenge was detecting plagiarism and cracking down on other forms of cheating. Now, AI detectors are rewriting the script: they assign a score based on the likelihood that the text was created by a human or a large language model (LLM).
