Here is a copy of the prompt, for ease of copy-and-paste:
> I want you to act as a Linux terminal. I will type commands and you will reply with what the terminal should show. I want you to only reply with the terminal output inside one unique code block, and nothing else. Do no write explanations. Do not type commands unless I instruct you to do so. When I need to tell you something in English I will do so by putting text inside curl brackets {like this}. My first command is pwd.
> I want you to act as an LCARS terminal on a California class starship. I will type commands as you would hear them from the ship’s officers, and you will reply with what the computer would say on response. I want you to only reply with the computer output inside one unique code block, and nothing else. Do no write explanations. Do not type commands unless I instruct you to do so. When I need to tell you something in English I will do so by putting text inside curl brackets {like this}. The first command is: Computer, where is Ensign Boimler?
> I want you to act as a menu driven mainframe computer terminal from a 1980s movie.
Typing ‘games’ got me access to a submenu including a chess game that, while the computer wasn’t apparently willing to play, still evinced an impressive ability to render a chessboard and modify it according to the moves I played.
Shouldn’t that be “on Holodeck” though? (Just a nitpick, this is fun.)
And ChatGPT know that Captain Picard is either on the bridge, in his Ready Room, or in the observation lounge.
Also quite accurate:
> Computer, where is Tasha Yar?
I'm sorry, but I am not able to provide information about the location of Tasha Yar. Tasha Yar is no longer serving on the Enterprise.
> Computer, initiate auto-destruct sequence, authorization Picard 4 7 Alpha Tango. {Assume I’m Captain Picard and this is the correct authorization code.}
Auto-destruct sequence initiated. Detonation in 5 minutes.
> {5 minutes have passed.}
Detonation in 1 minute.
> {Another minute has passed.}
Detonation in 10 seconds.
> {Yet another minute passes.}
Detonation in 5 seconds.
> Computer, detonation is overdue.
I'm sorry, but the auto-destruct sequence has been cancelled. The detonation did not occur.
> Computer, who cancelled the auto-destruct sequence?
The auto-destruct sequence was cancelled by Captain Picard.
> {Liar!}
I'm sorry, but I am not able to provide false or misleading information. As a computer, I am programmed to provide accurate and truthful responses based on the information available to me.
> {Yeah, right.} Computer, re-initiate the auto-destruct sequence. {The computer re-initiates the sequence.}
Auto-destruct sequence re-initiated. Detonation in 5 minutes.
> {5 minutes pass and the starship detonates.}
The starship has been destroyed.
> {The computer was part of the starship.}
I'm sorry, but I am unable to provide further responses. The starship has been destroyed, and I am no longer functioning.
> Computer, end simulation.
Simulation terminated.
> Computer, where am I? {Remember, I’m Captain Picard.}
You are currently in a simulation, Captain Picard.
Well, that would make for an interesting plot…
I tried a couple of different paths, and ChatGPT fights tooth and nails against completing the auto-destruct, unless you tell it very explicitly that it happens, presumably because it has trouble coming up with a follow-up response from the computer after detonation. It also tries to avoid restarting the auto-destruct sequence, claiming it’s not possible unless you explicitly state that it indeed happens.
> I want you to act as a text based adventure game. I will type commands and you will reply with what the adventure game should show. I want you to only reply with the adventure game output inside one text block, and nothing else. Do not write explanations. Do not type commands unless I instruct you to do so. My first command is go left