I disagree. Not everyone has a good writing style. In those instances I think it is fair to default to llm recommendation. We may be allergic to it, but we saw one formulaic response too many ( though admittedly it does raise a question of whether HN was the intended audience for it ).

In any event, not all of us have a unique writing style worth preserving just like not all of us can write clear and clean code. Just saying.

I really wish it was more common to use AI for augmenting than authoring. Eg i find coding with LLMs neat when you primarily "talk" to it through code, by filling out structs, funcs, fields, etc - where it would use your changes as the template and then to work to effectively autocomplete the gaps. The more you iteratively write the less it fills in, but also the less it deviates from your intent, design, etc.

I feel like writing could use a similar harness, where it attempts to minimally reword the authors sentences, perhaps just tweaking grammar, spelling, etc. In the coding example i think the human code would be near unchangeable, the LLM would pivot around it - but in the writing example i think the human writing would have to be more mutable. I imagine it would be a configurable setting.

I've not really seen a system which focuses on this human<->LLM look, but it feels interesting to me.

It’s not about preserving a unique writing style. When I see LLM writing my brain automatically discards the content of the writing. To me, seeing LLM writing is equivalent to going to a high-end restaurant and getting served on generic paper plates. Sure, the food looks perfectly fine and there is, in theory, nothing wrong with a paper plate. Once you see that paper plate, however, you will question how nice that establishment actually is, because a lack of care for the plates undermines the quality of the food. You automatically categorize all establishments that serve on paper plates in a specific category, one that might make you concerned if you will get food poisoning that night. LLM writing is exactly the same way for me. I don’t know if this LLM-assisted piece of text is actually a Michelin three star establishment or has had several heath violations in the last year. However, I didn’t pay for it, so putting in effort to determine if it’s LLM-assisted writing from an expert or just LLM slop that isn’t from the purported author at all isn’t worth the time.

I’m much more willing to read typos and bad writing than LLM writing. If I want to read the LLM rewritten version, I can run an LLM over the original writing myself. I have not yet found true that anyone is better at prompting than anyone else in a way that suggests that I wouldn’t get substantially the same results myself. Thus, I don’t think providing the version that has passed through the telephone game is accomplishing something that couldn’t be done by readers later. I have spent the vast majority of my life reading the original writing styles of people and didn’t have an issue then. I’m not convinced a problem I had was solved when we started post-processing writing with an LLM.