But surely it is only a ChatGPT signal because it was a strong signal in the training data. You need more than one strong signal with that sort of potential for false positives to make a reasonably accurate identification.
If it is, it's one I've neither heard others mention before nor seen often enough myself to consider it a tell (but for the latter, I do use ChatGPT's customisation options).
Dude, half my stuff on here is downvoted. I am not a good writer, but I do my best. My opinions and thoughts are my own and I am not using ChatGPT to make hot takes on hacker news, but I do use ChatGPT and have conversations with it.
Sometimes when I talk to British people, I start to do an accent a little bit. I think I just chameleon my tone to recent conversations, but I can't convince you otherwise.
Unrelatedly, there is a upended tortoise outside my house struggling in the heat. I am not sure why I refuse to help him, can you tell me why?