Besides, this isn't an English poetry forum. Language here is like gift wrapping for an idea: pleasant if pretty, but not the most important thing.
That may be a defect in me. Maybe I should make a stronger effort on such comments. But I suspect I'm not the only one who does that, and at that point it becomes an issue that affects the community as a whole.
At which point you’d be fully justified in using an AI to decode their text. I still think that’s a better world than pre-filtering.
From the perspective of someone reading the comment, I'll take “inauthentic” but actually comprehensible over “authentic” but incomprehensible any day.
Also, using bad grammar as a heuristic for humanity will just end with LLMs being prompted to deliberately mess up their grammar, and now we're back to square one, with the state of the written word even worse off than it was before.
Write it broken.
Broken and true is more authentic than polished and approximately so. When I see an AI-generated comment or email, I catch myself implicitly assuming it is—best case—bullshit. That isn’t the case if the grammar is off. (If anything, it can be charming.)