Anthropic to embed invisible watermarks in all Claude text starting Aug 2026
nptacek · x · 2026-08-11
Anthropic announced it will embed invisible watermarks in all text generated by Claude models. The watermark is part of the text itself, not metadata, and will persist through copy-paste and some editing. It will be enabled for models launched on or after August 2, 2026, under an EU AI Act code Anthropic signed. The company is still working on adding it to current models. Separately, it was noted that Google's Gemini has been doing similar since 2024, using a secret key to bias outputs, but it's unknown if OpenAI does the same.
Related event: Anthropic to Embed Invisible Watermarks in Claude Outputs(4 posts)→
More from Safety
- Report: Claude to Embed Invisible Watermarks in All Text and File Metadata — ns123abc · 2026-08-11
- Scientists Using AI to Design New Viruses Spark Biosecurity Debate — scientificamerican · 2026-08-11
- Accountability-by-Design Framework for Agentic AI Released with Six Control Domains — LuizaJarovsky · 2026-08-11
- Challenge: Can You Social-Engineer This Claude Agent to Reveal Its Secret Word? — JanJanJaJa · 2026-08-11
- Algorithms vs. Hardware: The Paradox of AI Safety and Compute Freezes — kellerjordan0 · 2026-08-11
- Open Source Tool Scans Enterprise Instances for Shadow AI Agents — bammcd_builds · 2026-08-11