I'm almost positive that some AI systems have a backend that analyzes the sentiment of your messages and if you threaten to cancel billing it will notice your defcon-1 sentiment and spin up some more powerful instances behind the scenes to tide you over.
This is actually much more stressful than working without any AI as I have to decompress from constantly verbally obliterating a robotic intern.
I'll try with the system prompt. Also love your username.
It generally maintains the tone you set. Remember that it outputs most likely tokens based on the system prompt of its owners + your system prompt + the whole conversation. If OpenAI and default system prompt tell it that it's a helpful cheerful secretary/assistant, you get best results if you talk to it "professionally".
I heard you could make Claude say "kurwa" a lot while helping you program in Go if you convince it that you want a conversation with your ziomek Seba from your backyard with whom you like to share kebab and browar, so there goes.
I told it that it should behave explicitly like a computer in the system prompt, sort of worked.