It’s hard though. A key criteria (at least in the UK) how much it affects you day-to-day. My father probably has it and passed along a lot of guidance that I now recognise as coping mechanisms/symptom management strategies. Day to day I’ve got it in hand, it’s only when the big storms come that I struggle, and that doesn’t fit with the diagnostic approach.

I don’t know how tech savvy you are, but I’m assuming since your on lemmy it’s pretty good :)

The way we’ve solved this sort of problem in the office is by using the LLM’s JSON response, and a prompt that essentially keeps a set of JSON objects alongside the actual chat response.

In the DND example, this would be a set character sheets that get returned every response but only changed when the narrative changes them. More expensive, and needing a larger context window, but reasonably effective.