Anthropic to Embed Invisible Watermarks in Claude Generated Text

max_paperclips · x · 2026-08-11

Anthropic announced that new Claude models will embed invisible watermarks in all generated text.

The watermark is integrated directly into the text rather than as metadata, meaning it persists when copied, pasted, or subjected to minor editing. This initiative is part of an EU AI Act code signed by Anthropic, applying to models launched on or after August 2, 2026, with a planned worldwide rollout.

Developers have raised strong concerns, noting that such steganographic attacks could permanently expose users' personally identifiable information (PII) within the generated text.

Related event: Claude Rolls Out Invisible Watermarks and Metadata, Sparking Compliance and Tech Debates(115 posts)→

Original post →

More from Models

Models channel →