Chatbots — LLMs — do not know facts and are not designed to be able to accurately answer factual questions. They are designed to find and mimic patterns of words, probabilistically. When they’re “right” it’s because correct things are often written down, so those patterns are frequent. That’s all.

If enough people listen to and (importantly) positively review "Constituent Service" on Audible, that'll encourage the service to ask me to write another, HINT HINT HINT. That said, the novella has been in the Top 5 for the whole service for a week, so that's good!

www.audible.com/pd/Constitue...