News for hackers. Stuff that matters.

A comment on Anthropic's 'Watermark' Text Adulteration in Claude Is a Perversion of Writing. Parent comment

Re:Anthropic's 'Watermark' Text Adulteration in Claude Is a ... by inigyou on Sunday August 16, 2026 @08:37PM (#49325316)
There's no difference between those two things. The distribution that matters is the distribution of tokens that are picked not the distribution of tokens the LLM model passed to the selector.
[ Parent | on HN ]
Re:Anthropic's 'Watermark' Text Adulteration in Claude Is a ... by beering on Sunday August 16, 2026 @11:04PM (#49326128)
On average the distribution of selected watermarked tokens is the same as the original distribution. You can test this experimentally.

I think there is a possible weakness in the context of the watermarker but that is not your claim iiuc.

[ Parent | on HN ]
Re:Anthropic's 'Watermark' Text Adulteration in Claude Is a ... by inigyou on Monday August 17, 2026 @07:05AM (#49329075)
The distribution of token "ple" being the same on average, but lower after "crum" and higher after "cou", is not no difference. It's irrelevant that the single-token distribution is unchanged if the joint distribution is different.
[ Parent | on HN ]