Anthropic explains Claude's text watermarking: using AR decoding for tie-breaking

prdeepakbabu · x · 2026-08-15

Anthropic published an article detailing the text watermarking technology for Claude models. The method embeds watermarks by using a random number generator (based on a secret key) to perform "tie-breaking" among candidate words with similar probabilities during autoregressive decoding. This approach adds no hidden characters, does not affect output quality or cost, and cannot be traced back to specific users. Anthropic stated this is in response to requirements from the EU AI Act.

Related event: Anthropic Details Claude Text Watermarks and Rolls Them Out Globally(6 posts)→

Original post →

More from Models

Models channel →