[simonw]

Randomness is difficult. I wouldn't expect any LLM to be able to reliably produce random anything, except in the cases where they have access to tools (ChatGPT Code Interpreter could use Python's random.random() for example).

[freejazz]

Okay, but repeating words?

[Terr_]

Makes sense to me: It's not understanding and complying with your request, it's doing statistics to guess what kind of follow-up would be most common.