Anthropic shares more details about how Claude’s new watermarks will work

Could someone just rewrite the text to hide the watermark? Anthropic said it’s possible, but “light editing probably won’t remove the watermark completely,” while “a complete rewrite where every word is replaced will.”

“In the latter case, of course, it’s arguable whether the text can any longer be described as AI-generated,” the company said.

As for whether the watermark will be detectable in text that was only proofread or edited by Claude, Anthropic said that will depend on “the length of the text and how heavily Claude has edited it.” If it’s only been lightly edited, “nearly all the words” will have been written by the human author and “there’s very little (if anything) for the watermark to attach to.”

Code, meanwhile, should have less of a watermark than other text, because the model will need to create working code and won’t have the freedom to choose between a variety of equally valid options. 

“Having said that, in areas where there is an arbitrary choice between particular words or terms within the code, the watermark can be used, such as comments within code,” Anthropic said. “But by definition, it will have a negligible effect on the actual code produced.”

Anthropic also said that Claude won’t be the only AI chatbot to generate watermarked text, as “other major model developers have signed the same Code of Practice and will be implementing their own watermarks.”