CLAUDE TEXT WATERMARKANNOUNCED · DETAILS DEVELOPING

Does Claude watermark text?

Yes. Anthropic has announced an imperceptible statistical watermark for supported Claude text outputs. It is encoded through patterns in generated language—not by inserting a secret zero-width character into every response.

Last verified: August 16, 2026 · Evidence may change as Anthropic publishes more details.
01 / DIRECT ANSWER

It is a word-pattern signal, not a pasted hidden character.

News coverage of Anthropic's announcement describes an imperceptible watermark applied at the model level. The important distinction is that a statistical watermark changes the distribution of generated word or token choices while keeping the text readable.

Practical consequence

Searching for zero-width spaces cannot confirm whether this statistical signal is present.

02 / WHAT IT MEANS

A detector needs more than the visible words.

Reliable verification depends on a detector designed for the exact watermarking method and access to the relevant secret or service. A general AI-writing score is not the same thing as reading a watermark.

  • Copying and pasting does not automatically prove removal.
  • Light editing may weaken a statistical signal, but absence cannot be inferred by eye.
  • A positive signal would indicate model involvement, not who authored or approved the final work.
03 / LIMITS

What WatermarkScope can tell you today.

The text inspector can show observable Unicode formatting characters and remove low-risk anomalies. It does not assign a Claude-generated probability. For files, the C2PA checker can read signed provenance credentials where present.

Inspect hidden charactersCheck API status
SOURCES

Read the underlying material.

The Verge — Claude will apply invisible watermarks to AI text and imagesAnthropic developer documentation