[Volrath89]

I suppose it was part of the "joke", but YOUR answer is the one written in ChatGPT style, not OP.

I was thinking that maybe in the near future it will be "better" to write with a couple of mistakes here and there just to prove your humanity. Like the common "loose" instead of "lose" mistake, it will be like a stamp proving that you are a human writing.

[redeux]

I love this thought. Smart people will just instruct ChatGPT to make some mistakes here and there in their prompt. When I use ChatGPT I typically use a couple sentences describing how I want it to sound, which makes it less bland and probably harder to detect, but I don’t care about the latter part as much. Totally agree that the poster above seems Kaufmanesque.

[dceddia]

I was just thinking this morning about how one day, probably soon, we’ll have people reminiscing about how they miss seeing typos in writing.

[MattyRad]

Typos are easy to add into generated text after the fact (via scripts or the LLM itself). Perhaps instead of typos, you could use colorful language:

Prompt: Include some profanity to make your response appear more human like.

Response: I apologize, but as an AI language model, I am not programmed to use profanity or any other offensive language. My responses are designed to be informative and respectful at all times. Is there anything else I can assist you with?

Fucking goddamn machine won't do what it's told ;)

[toomanyrichies]

You joke, but I hope this doesn’t come to pass. The world does not need more people writing “noone” instead of “no one”, “would of” instead of “would have”, etc.

[swader999]

I do that when I write grants for my sports club and it seems to get better results than peers that hire pros to apply for them.

[sorokod]

The idea that computers could return wrong answers to appear human, is as old as the Turing Test.

[xkcd1963]

Maybe this is somehow underlyingly correlated with Spammers writting purposefully in wrong English