Comment by hinterlands
8 days ago
First, it just reads that way. It's the default style if you ask ChatGPT to write a couple of paragraphs that explain why lightfastness is important.
Second, while I know there are reasons to be skeptical about AI text checkers, the author's earlier (less verbose) style doesn't get flagged at all, while the style in more recent articles gets classified as heavily AI-assisted.
> First, it just reads that way. It's the default style if you ask ChatGPT to write a couple of paragraphs that explain why lightfastness is important.
It doesn't read that way to me, and I've read lots of ChatGPT text. We've come to opposite conclusions, I'm curious what qualities you are identifying/keying off of?
In our studies of ChatGPT's grammatical style (https://arxiv.org/abs/2410.16107), it really loves past and present participial phrases (2-5x more usage than humans). I didn't see any here in a glance through the lightfastness section, though I didn't try running the whole article through spaCy to check. In any case it doesn't trip my mental ChatGPT detector either; it reads more like classic SEO writing you'd see all over blogs in the 20-teens.
edit: yeah, ran it through our style feature tagger and nothing jumps out. Low rate of nominalizations (ChatGPT loves those), only a few present participles, "that" as subject at a usual rate, usual number of adverbs, etc. (See table 3 of the paper.) No contractions, which is unusual for normal human writing but common when assuming a more formal tone. I think the author has just affected a particular style, perhaps deliberately.
Tangent, but I'm curious about how your style feature tagger got "no contractions" when the article is full of them. Just in the first couple of paras we have it's, that's, I've, I'd...
1 reply →