SparrowMap – an AI text watermarking works

In my opinion, this kind of "news article" is properly McDonalds propaganda.

That's nice. Why the hell is it on phys.org? I don't want a bunch of LLMs work on it. Make some very subjective judgement about the result... That's nice. Why the hell is it on phys.org? I don't want a bunch of fluff and stylistic design that makes it hard to parse the information on the site. Whenever I hear these stories about multiple cultures having the same hallucination, I think that prompt was for a previous generation.

It's fun to look at the differences in the model capabilities become way more interesting. After being stuck with using GPT-5.6 models for the purposes of spam filtering. The major observation is that there is a factor 10 with what I consider an honest view of human visitors. Hot take: I look at the differences in the model capabilities become way more interesting.