Hacker News Reader

Comment by sixtyj | Hacker News Reader

It was quick :) … https://claudewatermarkremover.app/

> Honest note: Anthropic has not shipped a public Claude watermark detector yet. This tool uses rewrite-based neutralization — a meaning-preserving paraphrase with a non-Claude model — which is the attack path watermark research points to. Not affiliated with Anthropic.

Well, they should have run their own AI slop website through their tool...

This attack was actually pointed out in the watermarking paper linked above. The researchers added an instruction to the prompt that switches letters like a Caesar Cipher. It lowers the quality of the output from the LLM but alters the "red list" enough for a watermark detection tool to fail at detecting the watermark.

also their example for rewriting just completely changes it. might as well redo it in this case (with another model or by hand)

Well, if the model that page uses also falls under the EU act, the output will just be watermarked differently. ;)

Though if pangram should be trusted, there are still statistical artifacts that tells you that a text LLM generated. I don't find that to be implausible.

Alas, Pangram should not be trusted.

Should be ensloppifier.app - it somehow makes the AI sound more like AI, while also completely changing the meaning and context of the input text

From their before/after:

   - Certainly! -> (removed)
   - onboarding redesign -> revamping the introductory process
   - this week -> (removed)
   - empty states -> empty sections
   - CTA heirarchy -> call-to-action sequence
   - interviews -> discussions
   - aligned copy with brand voice -> verbal identity

... these choices change the meaning of the text

So was it going down:

"Neutralize engine is temporarily unavailable. Try again."

Reply on news.ycombinator.com