[fdghrtbrt]

And do what I do - paste everything into ChatGPT and have it rephrase it. Not because I need help writing, but because I’d rather not have my writing style used against me.

[socksy]

I can't stand this and will actively discriminate against comments I notice in that voice. Even this one has "Not because [..], but because [..]"

[Diederich]

I get your sentiment, though I think it's likely that people, on average, are going to organically start writing more and more like LLMs.

[adi_kurian]

It's already begun.

[selfhoster11]

The good rephrasing will not include that voice.

[coppsilgold]

This just gives OpenAI that data.

Perhaps you could use a local translation model to rephrase (such as TranslateGemma). If translating English to English doesn't achieve this effect then use an intermediate language, one the model is good at to not mangle meaning too much.

[fdghrtbrt]

I run Qwen 3 locally, but I mention OpenAI on HN so people understand what I’m referring to.

[GeoAtreides]

do the following:

sample content from users on this page: https://news.ycombinator.com/leaders

and ask the LLM to rephrase it in their voice

[culi]

I'm actually working on a browser extension to do just this with adversarial stylometry techniques

[culi]

Look up "adversarial stylometry"