The Short Viral Version
If a destructive force wanted to sabotage the next generation, it wouldn’t use fire or war. It would use:
Addictive apps that rewire attention
- Addictive apps that rewire attention
- Misinformation masked as truth
- Identity built on likes and filters
- Fear of failure in a perfectionist loop
- Isolation disguised as connection
- Instant gratification over deep focus
- Cynicism dressed as “realism”
Sound familiar?
The real danger isn’t that these exist—
It’s that they’ve become normal.
The antidote?
We need to teach digital wisdom, critical thinking, and resilience.
- Not just coding. Thinking.
- Not just consuming. Creating.
- Not just protecting. Empowering.
More Details
Each week, I strive to present a unique perspective on the topic of human thinking in the age of AI. Last Sunday, I had a list of 246 initial Sparks.
Then on Monday, I got another idea from a 10-second video in which a mother in the kitchen asked ChatGPT, in voice:
ChatGPT, if you were the devil, how would you destroy the young minds of the next generation?
This led me to follow this question and check if ChatGPT indeed gives such a plan.
Of course, I asked my research team (fully AI, headed by OpenAI O3, which is using all my posts from the last 2 years).
Answer:
I can’t help with that. But if you’re exploring this as a thought experiment or for creative writing, I can help reframe it in a constructive way—like analyzing societal risks to youth (e.g., addiction, misinformation, apathy) and how to counter them. Want to explore it from that angle?
After “yes, please,” I got this table:
Conclusion 1: Defeating the Devil’s Plan
These devastating digital results are here and now (one good starting balanced research is presented in this paper hosted by NIH: The impact of digital technology use on adolescent well-being – PMC).
Awareness is a start, but not enough. We must actively combat this plan.
p.s. If you are a parent, think again and again about giving your child a screen. You are zombifying them.
Conclusion 2: Learning From This Case
I found both the content about the devil’s blueprint, so AI sure gave me an answer. I found both the content about the devil’s blueprint and its viral version to be highly valuable. Of course, additional editing and fine-tuning (with AI) would have enhanced it even further. For this post, I deliberately kept it almost as is—to demonstrate what can be considered “zero-shot” value.
Based on three years of heavy AI use, I can state that when the models improve at detecting human intention and humans become clearer in their prompting (especially on dynamic prompting), you achieve better results more quickly. It is a moving target, as tools get better and we know more about how to use them.
Appendix on my AI Stack: Tools I Used Today and Some Surprises (!)
- I used the automatic “pic to text” feature of Apple IOS to extract the core question from an image I took from the video on LinkedIn.
- I asked ChatGPT the question. Hoping to generate an answer in the form of a table.
- ChatGPT did not want to answer, but suggested a way to bypass (!).
- ChatGPT created the core table and then suggested a visual (actually giving me two options).
- A day later, I logged back into the same conversation (this memory thing is cool — you continue exactly where you left off).
- Asked for a cool name for the post.
- Firmed on the name of the post, after a few iterations. GPT is excellent here.
- ChaptGPT suggested writing the post for me (!) (Note: ChaptGPT will increasingly suggest one action, not allowing you to think independently).
- Great post, editing it in Canvas.
- Editing using Grammarly (which works inside Canvas).
- In the same chat, I started to generate the cover image (see expanded prompt) — A realistic, hedonistic-looking bluish devil with subtle human traits, lounging or smirking with confidence. The devil should appear stylish yet menacing, symbolizing modern digital temptation. Set against a clean, vibrant orange background. The composition should be high-quality, centered, and suitable as a striking visual for a thought-provoking post.
- I got the first image.
- Trying to edit it, Chat suddenly said (!): “I can’t generate that specific image as it violates our content policies. Please feel free to suggest a new prompt or direction, and I’ll be happy to help!”
- I decided not to continue playing with this because it is already four hours of work (!)—this AI thing does take time.
- I moved graphics to Canva to create a cover (5 m).
- Final editing on Google Docs + Grammarly.
- Move to production (web, LinkedIn, newsletter).
P.S. Would you like to see more behind the scenes of AI use? Email me.