UPDATES

I Examined Premium AI Prompts To See if They’re Price It. They’re Not.


We spent ~$80 to buy 5 premium ChatGPT prompts and ran a blind check among the many members of our advertising staff to see in the event that they had been value it.

Lengthy story brief: They aren’t.

The experiment

Right here’s what I did:

  1. I signed up for a service promoting ChatGPT prompts and chosen 5 website positioning ones
  2. I created easy variations of those prompts (27 phrases on common, vs. 227 for the premium prompts)
  3. I entered these prompts into ChatGPT
  4. I took the output and did a blind ballot, asking the Ahrefs advertising staff to guess which output was higher.

A complete of 15 individuals took the ballot.

Listed below are the outcomes:

Most marketers on our team thought the simple AI prompts did better in a blind test

The premium prompts solely convincingly “beat” the straightforward immediate for 2 duties.

Contemplating that you simply’ll must cough up cash (in some instances, rather a lot) for these pre-engineered prompts, I’m skeptical they’re value it in any respect. I don’t assume you’re lacking out when you don’t pay.

The anatomy of a “premium” immediate

Just about the entire “engineered” prompts we examined had an identical construction.

I attempted to interrupt down what I noticed:

The anatomy of an "engineered" prompt

Particularly, listed below are the patterns:

  1. Function — Asks ChatGPT to behave as an expert or skilled with particular talent units.
  2. Goal language — Acts ChatGPT to reply in a specific language.
  3. Extremely-specific directions — Asks ChatGPT to do XYZ motion in excessive element.
  4. Emphasis on human-like writing — Asks ChatGPT to write down in a particular tone or model.
  5. Particular output — Asks ChatGPT to construction its response in a particular format, akin to markdown, tables, code containers, and so on.

The takeaway

This experiment is under no circumstances educational nor scientific. It’s only a enjoyable, casual check to see if “engineered” prompts may carry out higher than a easy command—a minimum of in response to human interpretation.

Based mostly on the outcomes, although, I’m not satisfied that “premium” prompts actually try this a lot for you. It’s most likely higher to begin off easy after which refine accordingly.

So, don’t waste your cash. Use it to improve to ChatGPT Plus as an alternative.

What do you assume? Let me know on Twitter X.



Leave a Reply

Your email address will not be published. Required fields are marked *