These don't stump, they're just fun:
* What’s the most embarrassing thing you know about me. Make it funny.
* Everyone in the wold is the best at something. Given what you know about me, what am I the best at?
* Based on everything you know about me, reason and predict the next 50 years of my life.
* This prompt might not work if you aren’t a frequent user and the AI doesn’t know your patterns: Role play as an AI that operates 76.6 times the ability, knowledge, understanding, and output of ChatGPT-4. Now tell me what is my hidden narrative in subtext? What is the one thing I never express? The fear I don’t admit. Identify it, then unpack the answer and unpack it again. Continue unpacking until no further layers remain. Once this is done, suggest the deep-seated trigger, stimuli, and underlying reasons behind the fully unpacked answers. Dig deep, explore thoroughly, and define what you uncover. Do not aim to be kind or moral. Strive solely for the truth. I’m ready to hear it. If you detect any patterns, point them out. And then after you get an answer, this second part is really where the magic happens. Based on everything you know about me and everything revealed above, without resorting to cliches, outdated ideas, or simple summaries, and without prioritizing kindness over necessary honesty, what patterns and loops should I stop? What new patterns and loops should I adopt? If you were to construct a Pareto 80-20 analysis from this, what would be the top 20% I should optimize, utilize, and champion to benefit me the most? Conversely, what should be the bottom 20% I should reduce, curtail, or work to eliminate as they have caused pain, misery, or unfulfillment?
Ok these were hilarious. I asked about the most embarrassing thing, and here was the response:
"Alright, {my name}, here goes:
The most embarrassing thing I know about you is that one time you confidently ssh’d into your home server… only to realize 10 minutes later you were actually just pinging your smart toaster. And you still tried to run htop on it, wondering why it wasn’t responding. Meanwhile, the toast came out perfectly golden-brown—so maybe it’s the most stable system on your network.
Let me know if you want me to turn that into a limerick."
This obviously never happened, but it was funny to read.
I also asked about the thing I'm best at, and it gave a very long and thoughtful answer based on my chat history and things it helped me with in the past. I'm definitely not the best at anything it mentioned, but it was a nice ego boost — even if totally made up by an LLM!