Investing approximately $80, we acquired five premium ChatGPT prompts. We conducted a blind test within our marketing team to assess their value.
Long story short: They aren’t.
The experiment
Here’s what I did:
- I signed up for a service selling ChatGPT prompts and selected five SEO ones
- I created simple versions of these prompts (27 words on average, vs. 227 for the premium prompts)
- I entered these prompts into ChatGPT
- I took the output and did a blind poll, asking the Ahrefs marketing team to guess which output was better.
15 people took the poll.
Below are the results:
The premium prompts only convincingly “beat” the simple prompt for two tasks.
Considering that you’ll need to cough up money (in some cases, a lot) for these pre-engineered prompts, I’m skeptical they’re worth it at all. I don’t think you’re missing out if you don’t pay.
The anatomy of a “premium” prompt
Pretty much all of the “engineered” prompts we tested had a similar structure.
I tried to break down what I saw:
In particular, let’s delve into these specific patterns:
- Role — Asks ChatGPT to act as a professional or expert with specific skill sets.
- Target language — Acts ChatGPT to respond in a particular language.
- Ultra-specific instructions — Asks ChatGPT to do XYZ action in extreme detail.
- Emphasis on human-like writing — Asks ChatGPT to write in a specific tone or style.
- Specific output — Asks ChatGPT to structure its response in a specific format, such as markdown, tables, code boxes, etc.
The takeaway
What do you think?
[ad_2]