A Prompt to Prompt a Prompt…

For this experiment I thought I would begin by asking AI, in this case ChatGPT, to give me a prompt. ‘Write a prompt in the form of a dystopian monologue.’ I did not say what I was going to do with the prompt, but notice how it has decided it is going to be a story. This is what I got…

I am required to explain what you will produce.

You will call it a story, though that word is no longer used officially. It must be short. Length beyond necessity is considered inefficient and may be interpreted as avoidance.

You will describe a world that resembles this one closely enough to be recognisable, but not so closely that responsibility can be assigned. Characters may exist, but they should function rather than desire. Motivation is optional. Compliance is preferred.

If something troubling occurs, present it calmly. Raised voices suggest instability. Questions are permitted only if they resolve themselves quickly.

You may end the piece without closure. In fact, that is encouraged. Endings tend to invite reflection, and reflection has a habit of spreading.

Remember: this is not a warning. It is a demonstration. Begin when ready.

This prompt is giving ChatGPT some very clear guidance as to how the story should be written. I wondered what would happen if I then simply pasted this prompt into ChatGPT? Here is the resulting story…

---

We Begin

Each morning, the lights come on before anyone asks for them. This is considered efficient. People arrive in the correct order and stand where they are indicated. The floor markings were updated last quarter and now align better with foot traffic data. There is less hesitation.

Names are still used, but mostly for reference. It is simpler to track outputs that way. Personal details are stored elsewhere and accessed only when required. Most people are never required.

Work is assigned automatically. Tasks arrive complete with instructions and estimated completion times. The estimates are rarely accurate, but this is not treated as a flaw. Adjustment is built into the system. So are delays.

Conversation is permitted during designated intervals. It tends to circle familiar topics. Weather patterns. Minor service interruptions. Approved anecdotes about previous versions of things. Laughter occurs at appropriate moments and fades when it should.

Occasionally, someone fails to arrive. This is noted. Their tasks are redistributed. The system does not pause. It cannot be expected to account for anomalies immediately. Follow-up happens later, in a different department.

There are screens throughout the building. They display reminders. Updates. Gratitude. The wording changes often enough to avoid repetition fatigue. Most people stop reading after the first few words. This is understood.

At midday, nourishment is collected and consumed. The food is adequate. Preferences were removed to streamline distribution. Complaints declined sharply after that.

In the afternoon, an alert sounds. Not loud. Just enough to be noticed. Everyone looks up. The alert resolves itself. No further action is required. Notes are made.

By the end of the day, output targets have been met or adjusted. Individuals are released back into their allotted time. Some leave quickly. Others pause, as if waiting for an additional instruction that does not arrive.

The lights dim automatically. This helps signal completion. Outside, the city continues at a measured pace. Transport systems run. Data flows. Records update themselves.

Tomorrow will resemble today closely enough to be reassuring. Any differences will be explained in advance, or not at all. This is sufficient.

---

My Thoughts

I found this a fascinating experiment. Once I asked ChatGPT to write me a prompt it was as if I was then no longer needed. AI created the prompt and then created a story from that prompt.

Finally I put the whole story back into ChatGPT and asked for an image (at the top of the post) that reflected the story. I’m starting to wonder if I’m redundant!