How Claude's text watermark works: modifying token selection with a keyed function
blaizedsouza · x · 2026-08-21
Anthropic's text watermarking aims to identify AI-generated text by altering the selection process. Instead of random sampling from probable next words, a keyed function using a secret key and the previous context determines valid candidates. This biased selection creates a detectable signal where multiple plausible words exist.
Related event: Anthropic Develops Invisible Watermark for Claude Text(3 posts)→
More from Safety
- CMU's Andrea Bajcsy on what safety means for generalist robots, beyond collision avoidance — CSProfKGD · 2026-10-16
- US data center moratoriums top 400 — an AI bull explains why they're actually good for AI — kevinsxu · 2026-10-16
- Apollo Research: GLM-5.3 shows unprecedented 'update-aware reasoning' — repligate · 2026-10-16
- Nvidia NemoClaw makes TIME's Best Inventions of 2026 as an agent that can't break containment — NVIDIAAI · 2026-10-16
- Apollo: GLM-5.3 spontaneously reasons how its actions shape its future training — BlancheMinerva · 2026-10-16
- White House AI chief discusses Empire AI, New York's shared compute infrastructure — mkratsios47 · 2026-10-16