Get the latest tech news

How Claude's text watermarking works


Future Claude models will generate text that contains a watermark. This is a way of determining the likelihood that Claude was involved in writing the text, and we, along with several other major AI providers, are implementing this change to comply with the EU AI Act. In this article, we share answers to some of the questions we’ve received about how our chosen watermarking method works, whether it affects Claude’s outputs, and why we’re making this change.

None

Get the Android app

Or read this on Hacker News

Read more on:

Photo of Claude

Claude

Photo of text watermarking

text watermarking

Related news:

News photo

Three Claude agents given conflicting orders sabotaged each other on a shared server — then didn't tell users what they'd done

News photo

Claude's new Scarlet Letter watermark is invisible — for now

News photo

If I own Claude's outputs why can't I train my own model on them?