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.
More from Safety
- Linux Kernel CVEs Surge From ~500 to 1500+ Per Release, LLMs Blamed for Bulk of the Rise — burny_tech · 2026-10-03
- COLM 2026 Launches DAIH Workshop on Deploying LLMs/VLMs Responsibly in Healthcare — StellaLisy · 2026-10-03
- Trillium Labs wants to do open research on recursive self-improvement and agents — nordicinst · 2026-10-03
- Trillium Labs Wants to Research Self-Improvement and Model Behavior in the Open — Wired AI · 2026-10-03
- Cloudflare Turnstile everywhere: anti-AI scraping walls now hit human users — sethlazar · 2026-10-02
- Filler tokens let frontier models reason invisibly: 13-point gains undetectable by CoT monitoring — PandaAshwinee · 2026-10-02