Comment by schappim
9 hours ago
I wonder what the breakdown is between AI-generated comments and AI-assisted comments. If I write anything substantial, I run it through the following prompt: "Please rewrite the following message for clarity, spelling, and grammar, but only return the revised text without any additional commentary."
Articulateness is a decent (not perfect) signal for intelligence, which is a decent (not perfect) signal for sound ideas. In a sea of online garbage, it was a quick and easy way to discard that not worth reading. Nowadays, a whiff of AI's brand of articulateness tells me the author couldn't manage on their own, either due to skill or discipline. In either case, the result is the same: close tab / scroll past.
Use a local model such as Gemma3 with a prompt such as "strictly limit changes only to spelling issues, syntactical errors, and punctuation."
That way, it's basically functioning like Grammarly on steroids. Asking an LLM for a "rewrite" is basically dissolving your writing style into the homogenized gloop.
I understand this if you’re not a native speaker. But if you are, I think this will generally make you sound wooden.
To be fair, comments here are graded on kindness, civility, curiosity, intellectual gravity, technical merit, novelty, thoughtfulness, substantiveness, objective fact, not fulminating, not cross examining, steelmanning vs strawmanning, not containing memes, not containing humor, not expressing positive emotion, not expressing negative emotion, not being snarky, sneering, overly cynical, not cynical enough, being "curmudgeonly", class bias, political bias, religious bias, cultural bias, not using "flamewar style" and many other heuristics.
If you followed all of the guidelines for comments to the letter, you would wind up sounding wooden, if not entirely like an AI.
Perplexity did this to your response. I'm not sure that correcting grammar and changing one word makes it sound wooden.
"I understand this if you’re not a native speaker, but if you are, it will generally make you sound a bit unnatural."
"I think" is explicitly disclaiming authority. Omitting it changes the social signaling of the response significantly.
Switching "wooden" for "a bit unnatural" also does a disservice: "wooden" describes a specific quality of deviance.
Over-all, I would definitely consider the revision stiffer and more reserved than the original.
“Wooden” is much richer and unique than “a bit unnatural” so yes the ai version does sound more like a robot.