I used the reverse psychology prompt with ChatGPT to break my bad habits — and it showed me how to stop sabotaging my own goals
Asking ChatGPT how to flop worked better than expected
It’s become commonplace for me to pick my favorite chatbots’ brains when trying to find the right course of action when it’s time to tackle my biggest (and smallest) challenges.
And so far, I’ve had a pretty high success rate after getting the proper advice I needed to avoid botching my previous goals. Finding the right workout plan for a beginner like me, changing my sleep schedule for the better, planning an eventful summer vacation/staycation, and even finding the cheapest way to get a PS5 Pro before its latest price hike have led to some of my most recent wins thanks to AI.
As the summer begins winding down, I’m zeroing in on tackling my latest personal and professional objectives — the first one will hopefully set me up with a swanky living situation in my home state, the second one is all about excelling at my job and the third one is geared towards helping me regain my focus through regular book reading.
I went to ChatGPT to get some tips on how to achieve these new life goals. But this time, I tapped into the reverse psychology prompt to force my go-to chatbot to take a different approach to fulfilling my request. And thankfully, its counsel on the best ways to fail told me what not to do and to leave some of my worst habits behind.
Asking ChatGPT to tell me the best ways to…fail?
This is the reverse psychology prompt I gave ChatGPT. I included my three goals so it had enough context to generate advice focused on helping me fail at every one of them:
"If your goal was to make sure I completely failed at achieving my goals of getting my first apartment in New York, getting 300K+ hits on my articles for August, and reading one book a month, what habits would you recommend? Then explain how to avoid every one of them."
Right away, ChatGPT understood what I was trying to do, responding: "This is a useful 'reverse psychology' exercise because it forces you to identify failure patterns before they become automatic. Here's what I'd recommend if my goal were to guarantee you failed — followed by the opposite behavior that gives you the best chance of succeeding."
Get instant access to breaking news, the hottest reviews, great deals and helpful tips.
For each goal, ChatGPT followed the same format. It offered intentionally bad advice, explained why it would lead to failure, and then suggested the opposite approach to improve my chances of success.
The clearest example came from my goal of getting my first apartment in one of the most expensive cities in the world. ChatGPT told me to avoid setting a real budget, assume I'd figure everything out as I went, and ignore expenses like utilities, broker fees, moving costs, and the cash I'd need for furniture. It then flipped the script, recommending I determine my ideal monthly rent, understand the maximum I could realistically afford, and save enough to cover the full cost of moving before I started apartment hunting.
Its advice for my second goal — getting more than 300,000 views on my articles in August — hit even closer to home. Suggestions like only write about what you find interesting, publish and immediately move on, chase perfection, ignore your biggest wins, and measure effort instead of results all felt uncomfortably familiar. Seeing those habits framed as a recipe for failure made it much easier to recognize which ones I need to change.
My third goal, reading one book a month, was the easiest. Most of ChatGPT's "bad" advice didn't actually apply to me because I already do the opposite. I only read books I'm genuinely interested in, I don't force myself to finish books I'm not enjoying, and I keep track of everything I read.
The final section tied everything together by highlighting three habits that could derail all of my goals: checking my phone every five minutes, never planning for the next day, and saying yes to everything. Those felt less like generic productivity advice and more like reminders of the small behaviors that quietly make it harder to accomplish anything.
Final thoughts
Using the reverse psychology prompt with ChatGPT to emphasize all the wrong moves to make when trying to accomplish my latest goals worked a lot better than I anticipated.
Instead of asking how to outright achieve each goal, I asked ChatGPT how to fail at them and got a bunch of useful pointers on everything I shouldn’t do. The chatbot’s final statement wrapped everything up in a nice bow that’ll help me lock in on whatever I choose to focus on achieving next:
The "failure strategy" is surprisingly simple: procrastinate, overthink, chase perfection, and let one setback derail you. The success strategy is just as simple: take the next concrete action, measure what matters, learn from feedback, and repeat.
Follow Tom's Guide on Google News and add us as a preferred source to get our up-to-date news, analysis, and reviews in your feeds. Subscribe to Tom's Guide on YouTube and follow us on TikTok.
More from Tom’s Guide
- I just learned your Claude AI chats could show up in Google — here's how to check yours
- I asked ChatGPT, Gemini, Claude and Perplexity what they really think of each other — and their responses revealed their biggest strengths (and weaknesses)
- Uncanny valley on your FYP: 5 telltale signs your TikTok feed has been hijacked by AI

Elton Jones covers AI for Tom’s Guide, and tests all the latest models, from ChatGPT to Gemini to Claude to see which tools perform best — and how they can improve everyday productivity.
He is also an experienced tech writer who has covered video games, mobile devices, headsets, and now artificial intelligence for over a decade. Since 2011, his work has appeared in publications including The Christian Post, Complex, TechRadar, Heavy, and ONE37pm, with a focus on clear, practical analysis.
Today, Elton focuses on making AI more accessible by breaking down complex topics into useful, easy-to-understand insights for a wide range of readers.
You must confirm your public display name before commenting
Please logout and then login again, you will then be prompted to enter your display name.









