
I recently came across a prompt in a post on X which has proven to be quite useful in brainstorming.
Hereโs the prompt, tailored in this example to research the area of AI super intelligence:
You are a professional ghostwriter. Generate 15 high-signal content ideas on how AI labs will reach artificial super intelligence.
For each idea:
- Give me a hook line (<= 15 words, curiosity-driven)
- Outline the structure in 3 parts (hook, point, action)
- Include an example or analogy that will resonate with an audience of college graduates.
Make them practical, non-generic, and designed to spark discussion.
To see how it works, just copy it and put it into your favorite large language model. I think youโll be surprised and pleased with what results you obtain.
After the first pass, you can try this next:
Pick the best one and draft it.
Youโll get back a draft article about the modelโs choice for the best among the 15 it first produced.
You can then steer the model using a prompt like this:
Tune the draft for the vc/tech founder voice. Also speculate that Google is most likely the winner.
Itโs fun to see how the article evolves further with that voice and more speculation about the possible winner.
You can then ask the model to redraft it further:
Sketch two spicy counterarguments to the main thesis.
And so on. Itโs fun to do a deep dive on a topic using this approach. The wide range of the first fifteen results narrows and deepens as you ask the model to refine the draft it has produced.
Iโve lost track of time exploring a topic of interest to me as I got back and forth with the model evolving my understanding. Some models will even assist you in that process by suggesting next steps along the way.
Let me know of your experiences using this kind of approach!



You must be logged in to post a comment.