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.
More from Models
- First Model to Pass the Video Turing Test: Half of Users Thought It Was Human — Puzzleheaded-King584 · 2026-10-03
- Using System One models in Swift: fast, deterministic decisions via Apple Foundation Models — rxwei · 2026-10-03
- Linux Kernel CVEs Surge From ~500 to 1500+ Per Release, LLMs Blamed for Bulk of the Rise — burny_tech · 2026-10-03
- Developer Complains OpenAI's Coding Model Endlessly Scopes Creeps Instead of Finishing Tasks — DavidWells · 2026-10-03
- Sonnet 5 Spotted in Google Antigravity Backend, Which Still Runs Sonnet 4.6 — brandon_galang · 2026-10-03
- Post-training Yandex AliceAI-80B-A3B from scratch: a NaN bug in custom V100 kernels killed one run — jjusko20 · 2026-10-03