Anthropic fuses SynthID-Text watermarks into Claude

Anthropic confirmed in an Aug 14 official blog post, "How Claude's text watermarking works," that future Claude models will ship text containing an invisible SynthID-Text-style watermark, used to estimate post-hoc how likely a passage was produced with Claude's involvement. This is a concrete step to comply with the EU AI Act's Article 50 transparency requirement for AI-generated content, following the Code of Practice on Transparency of AI-Generated Content that Anthropic and roughly 190 other organizations signed in July 2026.

Where the watermark lives

Anthropic is using the SynthID-Text approach Google DeepMind published in a 2024 Nature paper, an idea traceable to a 2022 proposal by Scott Aaronson. The design principle of this watermark family is one line: do not change the semantics of the model's token choice, only change the source of its randomness.

Concretely, when a model picks the next word, it usually samples among several semantically equivalent candidates. The watermark uses a key plus the previous few tokens, in place of the original random source, to decide which candidate to pick. The result: to a reader, watermarked and unwatermarked text are indistinguishable (no hidden characters, no visible marks); but anyone holding the key can later check whether the token sequence is consistent with Claude's choices, and output a probability that "Claude was likely involved."

What it means for users

Anthropic lays this out unambiguously in the post:

• No measurable impact on quality, readability, or creativity in their internal testing.
• No extra tokens, so model latency and price are unchanged.
• The key carries no user-identifying information and cannot be traced back to a person, organization, or chat session.
• Watermarks survive copy-and-paste of Claude's text.
• Light editing won't fully remove the watermark; a full word-by-word rewrite can, but at that point the text arguably isn't AI-generated anymore.

How the watermark strength varies by content type

The effectiveness of the watermark depends heavily on the density of "low-stakes choices." Anthropic walks through a few cases in the post:

• Proofreading. If a user hands Claude a paragraph and asks only for grammar and punctuation fixes, Claude contributes very few word choices, so there is almost nothing for the watermark to attach to. Detection confidence drops.
• Fact-stuffed sentences. "Isaac Newton's most famous work was Principia..." — the next word has essentially one correct answer, so the watermark has nothing to act on.
• Code. Code has to be exact in many positions, so the watermark density is naturally lower than for natural language. There is still room inside comments.
• Translation. Every word is chosen by Claude, so the watermark is strongest.

The takeaway: watermark detectability varies dramatically with content type. Anthropic notes that confidence grows with length; for short pieces, pure proofreading, or fixed expressions, do not expect the watermark to deliver a verdict.

Files use C2PA, not embedded watermarks

For file outputs (including .png, .jpg, .svg, etc.), Anthropic does not embed a watermark. Instead it uses C2PA (Content Credentials) — the open standard already used by camera manufacturers and image editors. C2PA adds a small cryptographically signed note to the file's metadata, readable by any C2PA-aware tool. The file itself is unchanged, byte for byte.

Like the text watermark, the C2PA claim is only "Claude was involved," with no user or session information. Together the two form a two-track setup: SynthID for text, C2PA for files.

Regulation-driven, but rolled out globally

The EU AI Act's mandate kicks in for new models launched on the EU market on or after August 2, 2026. Anthropic is upfront in the post that, because there is currently no reliable way to scope it by region, the watermark goes live globally, not just for European users. The company says it will keep evaluating alternative approaches and share updates.

For older Claude models launched before August 2, Anthropic will roll out watermarking over the coming months. From now on, any Claude output — copied from a chat into an email, a report, a blog post — can in principle be checked by a third party running Anthropic's detection API and assigned a probability of "Claude was involved."

Open questions

Anthropic flags several unresolved items at the end of the post:

• The watermark detection API is not yet live; the company only says "soon." There is no public tool today for users to self-check whether a piece of text was written by Claude.
• For translation and human-AI hybrid writing, the post gives no quantitative numbers on watermark strength.
• For editing, cropping, and cross-language rewriting, the post says only that the watermark "may partially survive," without specifics.
• On the relationship with third-party AI detection software (such as Pangram): the two methods are fundamentally different — watermarks use a key, detection software relies on statistical patterns. Anthropic is explicit that these are two distinct signals and a detection software result cannot be used to "reverse-engineer" the watermark.

So what

Step back: SynthID-Text is no longer just a Google technology. From May 2026 — when Chrome built in SynthID + C2PA, and OpenAI and NVIDIA announced SynthID adoption — to this August release where Anthropic turns the text watermark into a product feature, the industry is moving from "can we mark" to "everyone marks." For everyday users this means that, within the next few months, AI-generated text will routinely carry an industry-consistent, verifiable fingerprint that makes post-hoc traceability substantially easier than it is today. For editors, publishers, educators, and recruiters, this is the first genuinely enforceable signal — much more reliable than the style-based detection offered from P, GPTZero, and similar services.

References: Anthropic's official blog "How Claude's text watermarking works" (https://www.anthropic.com/news/claude-text-watermark); Solidot reprint, August 11 (https://www.solidot.org/story?sid=85063); EU Code of Practice on Transparency of AI-Generated Content signatories list (https://digital-strategy.ec.europa.eu/en/news/strong-backing-code-practice-transparency-ai-generated-content); original SynthID-Text paper, Nature 2024 (https://www.nature.com/articles/s41586-024-08025-4).