leigh

You used an em dash in your post response. Its extremely rare for a human to do that, but extremely common for LLMs to do so.

I think you may misunderstand how LLMs operate? They generate output that is statistically likely. Things that aren’t well-represented in the training data aren’t well-represented in the output. And it’s very easy to type an em dash (unicode 2014) , especially on my iPad where two sequential dashes are automatically converted into an em dash.

See also: https://www.theringer.com/2025/08/20/pop-culture/em-dash-use-ai-artificial-intelligence-chatgpt-google-gemini