I think you're right, and I don't know what to think about it. I enjoy writing, aim to write clearly - a skill or discipline that took a lot of time to learn, and ongoing effort to maintain.

I've never sent or posted anything AI-written, beyond a pro-forma job description - because I don't know the domain-specific conventions, and HR returned my draft to me with the instruction to use ChatGPT, which I think amusing, but whatever: the output satisfied them, and I was able to get on with my day.

I occasionally experiment with putting something I've written through an LLM, and it's inevitably a blandifying of my original, which doesn't really say what I intended. But maybe that's good? My wife thinks I'm sometimes too blunt, and colleagues don't always appreciate being told technical details.

I also appreciate individuated writing - including the posts by people on this board are not native speakers. Grammatical mistakes seldom inhibit understanding when the writing has been done with care.

I'm rambling at this point, but it's because I'm truly uncertain how these cultural changes will turn out, and (an old man's complaint, since time immemorial!) pretty sure I'll end up one of the last of the dinosaurs, clinging to my manually written "voice" long after everyone else in the world has come to see my preferences quaint.

The "L" in LLM stands for "language". If they are unable to express themselves in English (or whatever their native language is) fluently, they won't be able to prompt LLMs fluently and will be, in the debased patois of modern youth, "cooked". It's a self-correcting problem.

> written English is starting to be seen as snobbish and AI-slop especially with younger generations growing up with AI

This is tragic. I write English well and will employ grammar and word choice effectively to make an argument or get a point across. English was my best subject at school 45 years ago despite a career in tech. In fact, I’d suggest that my career as an architect and the need to convey concepts and argue trade-offs with stakeholders of varying backgrounds has honed that skill. Should I now dumb down my language or deliberately introduce errors in order to satisfy the barely literate or avoid being “detected” as an AI? (as if the latter were possible. It’s an arms race).

If knowing how to speak and write my native language well makes me a “snob”, so be it. But I don’t think I’m the problem in that case.

Trust me, it won't last because I've seen the cycle a couple of times. People pay lip-service to being accepting of variant grammar, but then the downvotes show up.