It's of course not a surprise that an LLM would be most proficient in language use and, adjacent to that, in proper formatting of said language. But it's a good thing and a good tool for writing, as anyone who has ever used a classic spell or grammar checker will attest to. But apparently we as a society have once again managed to completely overlook and demonise the good and now people who have paid attention in school have to bow to people who are somehow convinced that perfect spelling is a sign that someone cheated. This is not LLMs' fault, it's people's who think they've understood something when they really haven't, crying heresy over others doing things the correct way.
That being said: of course there are social and technological challenges with cheating, spam bots and sock puppets and what not, but the phenomenon itself is not really new, just the scale, cost and quality is way different now. We need to find a balanced way to approach it -- trying to weed out every last possible AI cheater while hurting real innocent people in the process is not worth it. Especially since we don't have a proper metric to actually prove who's a cheater and who is not, it's gotten way harder since the days of "As a large language model" being in every second sentence.