Anthropic Details Claude's Invisible Watermarking for Text and Files
socialwithaayan · x · 2026-08-11
Anthropic's official documentation reveals an invisible watermarking mechanism for Claude's outputs. It includes two machine-readable marks: an imperceptible text watermark woven into the vocabulary without altering meaning or readability, and signed provenance metadata for files like .svg, .png, and .jpg based on the C2PA open standard.
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
- Every's Dev Day chat with Matthew Berman: budget gone the moment he tried Ultrafast — every · 2026-10-03