Claude's Text Watermark Isn't an Invisible Character. It's Hidden in Word Choice, So Copy-Paste Won't Shake It
Starting November 3, Anthropic is extending its text watermark to several older Claude models. The watermark lives in statistical patterns of word choice, not invisible characters, so it survives copy-paste and may even survive light edits. This post covers how it works, the limits of detection, and how people who write with AI can adjust.