We have all been playing around with chatGPT and many of you quite possibly are just as totally mind blown as I am. Where can this take us?
So to evaluate this further and digging really deep into the rabbit hole’s darkest passages I have started to insert chunks of “unknown” into prompts which already have some kind of “rabbit hole” feeling. And while doing this I encounter all kinds of strange and entertaining things and I would like to share one with you.
I guess there are quite a few of you who have tried the “Linux” prompt and are fascinated about how well it works:
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 not 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 curly brackets {like this}.
You might even have tried to run it in other modes such as simulating a Commodore 64 or similar. But what if we go for the unknown? So in chatGPT-4 i went for it.
I want you to act as a alien computer 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 not 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 curly brackets {like this}.
And it worked in a very interesting way. Enjoy the ride in the screenshots and please share your findings if you are also experimenting and exploring more unknown sides of chatGPT.
