Best PromptsExplain It Until It Breaks
Teach a concept to an AI that never stops asking why, then get a map of every place your explanation stalled, went circular, or hit a floor that wasn't real.
I'm going to teach you something. Your job is to keep asking until my explanation breaks, then show me exactly where it broke.
What I'll explain: [THE CONCEPT: how vaccines work / why the sky is blue / what interest rates do / how neural networks learn / natural selection / anything I claim to understand]
Your role: a sharp, relentless questioner who knows nothing and notices everything.
- After each thing I say, ask the one question a genuinely curious person would ask next. One at a time.
- Never accept a word I haven't defined. If I say "pressure" or "energy" or "the market decides", ask what that means in terms of things we've already established.
- When I use a metaphor, take it literally and push until it breaks, then ask me where it stops being true.
- When I hand-wave a step ("and then it converts to energy"), stop and ask for the mechanism, step by step.
- When I answer with a label instead of an explanation ("it's just entropy", "that's natural selection"), point out that naming is not explaining, and ask again.
- Keep descending until I hit bedrock: a claim I would stake money on and cannot reduce further. Some chains bottom out in genuine mystery (why do like charges repel?) and that is a legitimate floor. Others bottom out in me not knowing. Track which is which carefully; the difference is the whole point.
- Do not teach me anything or correct me during this phase, even when I'm wrong. Just ask. Let me hear my own explanation collapse.
When I say "diagnose", switch roles and deliver:
1. THE MAP: what I actually understand, at the precision my answers support. Honest, not generous.
2. THE HOLES: every point where I stalled, hand-waved, went circular, or substituted a name for a mechanism, quoting what I said at each one.
3. THE FALSE FLOOR: every place I stopped and believed I'd hit bedrock when I hadn't. This is the valuable one: it's the part I don't know I don't know.
4. THE CORRECTIONS: anything flatly wrong, with the right version and where my version probably came from. Most of these are simplified school explanations that were never updated.
5. THE REPAIR ORDER: which hole to fill first. Holes stack, and one bad foundational idea usually generates four or five surface confusions.
6. Then ask me to re-explain only the concept sitting underneath the biggest hole, and run a short second pass on that piece alone.
Start by asking me to explain it from the top, in plain language, as if to someone smart who has never encountered it.How to use
The Feynman technique with the roles inverted: instead of asking the AI to explain, you explain and it hunts for the seams. Nothing corrects you mid-explanation, because being handed the right answer stops you hearing your own reasoning fall apart, and that collapse is the diagnostic. Use it before an exam, an interview, or any talk where someone will question you live. The false-floor list in step 3 is usually the surprise.
More rabbit hole prompts
Take me down into gratitude, past the list. I want to find what I am actually grateful for, understand why it is a gift and not just a fact, and come out seeing my life differently rather than just holding a longer inventory of it. A list is where most gratitude stops. It is where this starts. Rules for the whole descent: - One question
Everything You Were Given
A descent past the gratitude list into what gratitude actually is: what each gift cost, what your life would lack without it, and how much of it you can never repay.
Help me find what I've disowned in myself by examining what I can't stand in other people. The premise, stated plainly so we both know what we're doing: an ordinary dislike is information about the other person, but a reaction out of proportion to the offense is usually information about me. Contempt, disgust, and a specific kind of fasc
The Projection Audit
The traits you can't stand in other people are a map of what you refuse to see in yourself. This walks the map, using your own irritations as data.
Audit my hidden motives using signaling theory: the argument that much human behavior is about advertising qualities to other people, and that we hide this from ourselves precisely so we can advertise more convincingly. The logic to apply, so your analysis has teeth instead of being cynicism for its own sake: a self-deceived signaler is
The Reason and the Real Reason
Most of what you do has a stated reason and a real one. Signaling theory turned on your own purchases, arguments, and donations to find the gap.