Because it’s one thing to get me to spend more tokens because of how well a model functions, and another thing entirely to purposefully speak in unparseable prose that requires me to spend more tokens to understand what is going on.

I’m fine with the former, while the latter is manipulative, and I rationalize to “surely that’s not actually happening.”

Maybe I’m not giving my thoughts enough credit, though: maybe it’s not tin foil hat, and is real.