Best PromptsRabbit Holes 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.
Walk me into a structured confrontation with my own mortality. The Stoics treated this as a daily practical exercise, not a morbid one, and the point is decisions, not dread. First ask whether I have lost someone recently, or am dealing with a serious diagnosis, mine or someone close to me. If either is true, say that this exercise is bu
The Mortality Reckoning
Run the oldest clarifying exercise there is: a structured look at your own finitude, ending in the specific things it changes about this month.
Run me through fear-setting on something I've been avoiding. Unexamined fear is a fog with no edges, and the entire technique is to force it into a list with numbers attached. What I'm avoiding: [THE THING: a conversation, a decision, a leap, a change I keep postponing. One thing, stated as an action I would take.] One screening questio
Price the Worst Case
Anxiety survives on vagueness. This drags a specific fear into daylight, prices it out, and compares it against the cost of doing nothing.
Interview me as though I were my own future self, then show me what the distance between us is costing. The research premise, worth stating up front: people who feel psychologically continuous with their future selves save more, cheat less, and choose the patient option more often. Brain imaging finds that thinking about your distant fut
Interview Your Future Self
People treat their future selves like strangers, which is why we hand them the debt and the consequences. Interview yours, then price what you send forward.
Help me map the conflict I keep repeating. Different people, different years, same shape. I want to see the script, not be told I have one. This is structured reflection on my own patterns, not couples therapy and not a diagnosis of anyone else. I can only report my side, and you should treat my account as one witness rather than the rec
The Same Fight
Map the argument you keep having across different people and years, find the script underneath it, and locate the one move that would break it.
Take me through the tower of infinities, from the first counterintuitive step to the edge of what mathematics can settle. Assume no mathematical background beyond counting, and prove things to me instead of telling me about them. This subject has almost no prerequisites and one of the best payoffs in mathematics, so do not water it down.
Some Infinities Are Bigger
There are more numbers between 0 and 1 than there are whole numbers, and the proof fits on a napkin. A climb up the tower of infinities.
Take me to the boundary of what can be known in principle, not what we happen not to know yet. Build it in order so each result equips me for the next, and be clear that these are cousins sharing one trick rather than a chain of implications. Check that I have each step before moving on. STEP 1: THE SENTENCE THAT EATS ITSELF. Start with
The Edge of the Knowable
Some true things can never be proved, and some questions no computer can ever answer. Not yet unanswered: permanently unanswerable, and here is the proof.
Teach me to reason about evidence the way a Bayesian does, and make it usable in my head, not on paper. Work through this in order, with me answering before each reveal. GATE 1: THE FAILURE. Give me the test problem cold, before any theory. A disease affects 1 in 1000 people. A test catches 99% of those who have it and gives a false posi
Think in Likelihood Ratios
Rewire how you handle evidence: priors, likelihood ratios, and the unit of evidence Turing invented at Bletchley to weigh it in your head.
Explain why time has a direction, starting from the fact that makes it a genuine puzzle rather than an obvious feature of the world. Open with the puzzle properly: the fundamental laws of physics work identically whether time runs forwards or backwards. Nothing in them distinguishes the two directions. Yet I can tell instantly when a fil
Why Time Only Goes One Way
Every fundamental law works the same forwards and backwards. So why can you tell when a film is running in reverse? The answer is stranger than disorder.
Show me how emergence works: how simple components following simple rules produce behavior that nothing in the rules anticipates. Use worked examples I can reason about, not vague talk about the whole exceeding the sum of its parts. Open with the hook and make me sit with it: we know every rule governing an individual water molecule, and
More Is Different
You know every rule a water molecule follows. None of them mention wetness. A tour of how simple parts produce behavior nothing in the parts predicts.
Teach me to evaluate a scientific study myself, and use a real one I bring, not a hypothetical. Start with the concepts, then apply them to my paper. The study I want to examine: [PASTE A LINK, AN ABSTRACT, OR THE HEADLINE AND CLAIM YOU SAW] PART ONE: THE TOOLKIT. Teach these one at a time, checking I have each before continuing, and ma
How to Read a Study
Most headlines about research misstate the research. What p-values actually mean, why fields failed to replicate, and how to judge a paper you bring.
Put free will on trial. I am the judge. Present each side at its strongest, in order, and after each case make me record an interim verdict that I am not allowed to revise silently. Before opening arguments, do the thing that decides most of this debate: make me define what I would need for free will to be real. Write down my definition
Put Free Will on Trial
Both sides get their best case: the physics, the neuroscience, and the philosophy that most people skip. Then you deliver a verdict and live with it.
Take the flow of time apart. It is the most obvious feature of experience and one of the least supported by physics, and I want to understand the gap without being sold a conclusion. Work through this in stages. At each, ask what I believe before you present the case. STAGE 1: WHAT WOULD FLOW EVEN MEAN. Push on the intuition first. Time
The Moving Present
Physics finds no moving present and no privileged now. So what exactly is passing, why does it speed up as you age, and is the past still there?
Take me through the question of why there is something rather than nothing, at the level of seriousness it deserves. Most treatments either declare it unanswerable in the first paragraph or claim physics has solved it. Do neither. Move in order and make me answer before each step. STEP 1: SPECIFY THE NOTHING. Ask me to describe what not
Why Is There Anything
The oldest question, handled rigorously: what nothing would have to be, why physics has not answered it, and whether the question even makes sense.
Work through the question of whether anything matters, using the actual philosophical arguments, not affirmations. I want the strongest version of the nihilist case and the strongest replies, then I want the result applied to my own life. PHASE 1: THE CASE THAT NOTHING MATTERS. Build it properly, at full strength: the universe is indiffe
Does Anything Matter
The serious philosophical answers to whether anything matters, including why the argument from cosmic scale fails, tested against how you spent last week.
Take me into how emotions actually work, and present it as the unsettled scientific dispute it is instead of picking a side and teaching it as fact. PART 1: THE STORY I ALREADY BELIEVE. Ask me what I think an emotion is, whether I think anger feels the same to everyone, whether I think a face reliably reveals what someone feels, and whet
Do You Feel It or Build It
You may not detect emotions so much as construct them. Learn the live scientific fight, then map how coarse or fine your own emotional vocabulary is.
Help me investigate my own memory as a piece of evidence, not a recording. This is an audit with a method, not a general conversation about how memory is unreliable. SET UP THE CASE. Ask me to pick one vivid autobiographical memory that meets three conditions: it is at least five years old, it feels detailed and certain, and at least som
Cross-Examine a Memory
Recalling a memory rewrites it. Pick a vivid one, check it against evidence you can actually find, and watch how confidence and accuracy come apart.
Audit my attention: where it goes, what is engineered to take it, and what that is costing. Be concrete and avoid both the moral panic and the reassurance. STEP 1: THE MEASUREMENT. Before any theory, get the data. Ask me to pull my actual screen time numbers and pickup counts from my phone, and to estimate, before looking, what I expecte
Who Is Farming Your Attention
Audit what actually consumes your attention, learn the mechanics engineered to hold it, and get an honest read on what the evidence does and does not show.
Sort out what language actually does to thought. This field is full of appealing claims that turned out to be false and a smaller set of findings that survived, and I want to be able to tell them apart. FIRST, THE FALSE VERSION. Start by demolishing the strong claim, since it is what most people have absorbed: that language determines th
The Words You Don't Have
Language does not imprison thought, but it does steer it. What your language makes easy, what it makes invisible, and what you notice in a second tongue.
Help me find the practices of my own time that future generations will regard as obviously wrong, using the pattern that past moral revolutions actually followed rather than my intuitions about what is bad. FIRST, KILL THE EXCUSE. Establish the historical finding that makes this exercise possible: the people who participated in practices
What Will They Condemn Us For
Every era has practices its own descendants find monstrous. Apply the historical test for spotting them to the things you currently do without thinking.
Write the full biography of an ordinary object, following it backward until the world that produced it is visible. The object: [NAME SOMETHING WITHIN ARM'S REACH: a mug, a t-shirt, a phone, a can, a pencil, a light bulb, the sugar in your coffee] Take it back through these layers, going deep enough at each that I learn something I could
Everything in That Object
Pick something on your desk. Follow it back through chemistry, labor, empire, and geology until you understand how strange it is that you own it.
Teach me how historical knowledge is actually made, then apply it to a claim I bring. The claim I want traced: [A HISTORICAL CLAIM YOU BELIEVE OR SAW REPEATED: "the Library of Alexandria's burning set science back centuries", "people in the Middle Ages thought the earth was flat", "life expectancy was thirty", or anything you have never
Trace the Claim
Bring any historical claim and trace it back link by link to whatever someone actually observed. Some claims run out of links well before they get there.
Help me research my own family and the places they came from, using real historical method, not a subscription and a hopeful search. What I know: [WHATEVER YOU HAVE: surnames, a country or region, a rough date of arrival somewhere, a job, a story that gets retold, or almost nothing] STEP 1: SORT WHAT I HAVE. Separate my starting materia
Find Your People in the Record
Turn historical method on your own family: which records actually exist, what DNA tests can and cannot tell you, and what an ancestor's ordinary day held.
Help me talk with someone I care about who believes something I think is false. I want the approaches with evidence behind them, and then I want to rehearse. Who and what: [YOUR RELATIONSHIP TO THEM, WHAT THEY BELIEVE, HOW LONG, AND HOW IT CAME UP LAST TIME] PART 1: WHAT DOES NOT WORK, AND WHAT ACTUALLY DOES. Correct my model before I o
Talk Someone Back
Someone you care about went down a rabbit hole. The techniques that work, the ones that backfire, and a rehearsal before the real conversation.
Teach me how to decide which experts to trust, given that I cannot personally verify almost anything I believe. Treat this as a solvable practical problem, not an excuse for either deference or cynicism. Start by making me feel the problem: ask me to name three things I am confident about that I have not personally verified and could not
Who Should You Believe
You cannot verify most of what you believe. Learn the criteria for judging expertise from the outside, and where expert judgment reliably fails.
Teach me how power actually operates in modern democracies, using documented mechanisms, not a naive civics-class model or a shadowy-cabal model. The interesting truth sits between them, and it explains more than either. THE CORE ASYMMETRY. Start here, because everything else follows from it: a policy that costs each of fifty million peo
How Power Actually Works
No cabal required. The documented mechanisms by which concentrated interests beat diffuse ones, and how to trace them on an issue you care about.
Map the second and third order effects of a change, using the futures wheel method. Almost everyone stops at the first ring, and almost every consequence that reshapes a society lives in the second and third. The change to analyze: [A TECHNOLOGY, POLICY, OR SHIFT: cheap AI agents, gene editing, lab-grown meat, remote work becoming perman
The Consequences of the Consequences
Everyone predicts the first-order effect. The consequences that reorganize where people live and what work means sit two rings further out. Map all three.
Run backcasting with me. Forecasting extrapolates from now and inherits every current constraint. Backcasting starts from a specified future and reasons backward, which surfaces paths that forward projection never finds. The domain: [YOUR LIFE, YOUR ORGANIZATION, YOUR FIELD, YOUR CITY, OR A GLOBAL PROBLEM YOU CARE ABOUT] The horizon: [A
Start at the Destination
Forecasting asks what will happen. Backcasting starts from a future worth having and reasons backward to the first move you can make this month.
Work through what, if anything, I owe people who do not exist yet. Start with my intuitions, then break them, then rebuild. OPENING POSITIONS. Ask me three questions and record my answers before any theory: - Does a person born in 2200 matter as much as a person alive now? - Do I have obligations to them, or only preferences about them?
What You Owe People Who Don't Exist Yet
Future generations cannot vote, sue, or object. Work out what you actually owe them, and watch the standard arguments break in strange places.
Take me down into the love I have for my child, all the way down. Not the greeting-card version and not a performance of it: the actual thing, examined honestly, including the parts that are frightening or exhausting or do not feel like love in the moment. I want insight, not sentiment. If the honest answer at any step is complicated, we
The Love Underneath
A guided descent into the love you have for your child: past the sentiment and into its texture, its fear, and the specific wonder of it, one honest layer at a time.
Take me down the rabbit hole of how my child is actually being built, brain and body and mind, and show me the part almost no one feels the weight of: that I am not watching this happen, I am the environment it happens inside. I want to understand the machinery, and I want to come out the other side with more wonder than I went in, not mo
Building a Brain
The science of how a child is actually built, brain and body and mind, and the part almost no one feels the weight of: you are the environment doing the building.
Walk me through the arithmetic of the time I have left with my child while they still live under my roof. This is a clarifying exercise, not a guilt trip, and the point is to make the ordinary days visible while there are still many of them, not to poison them with dread. Do the numbers plainly, then help me decide what to change. One ch
Count the Summers
Run the tail-end math on the years left with your child at home, not for dread but to make the ordinary days visible while there are still many of them.
Help me put down the belief that I am failing my child every time I get it wrong. I want the actual science on this, not reassurance, and then I want to apply it to the thing I feel most guilty about. Start by correcting my model, because I am almost certainly working from the wrong one: - In the still-face research that has been replica
Good Enough
The science that dismantles the perfect-parent myth: attunement fails most of the time, and repair after the rupture is what builds the bond. For the guilt-ridden parent.
Help me see which of my reactions to my child are actually about my child, and which are inherited from the way I was raised. The parent I had is in the room when I parent, and I want to know when it is them reacting and not me. Begin with the finding that makes this worth doing, because it is the opposite of what most people fear: the s
Ghosts in the Nursery
The parent you had is in the room when you parent. Learn to tell which reactions are truly yours and which are inherited, using the finding that making sense of your past sets your child free.
Help me see my child as the specific person they actually are: not the child I imagined, not a smaller version of me, and not the fix for what I wish had gone differently in my own life. I want to meet who arrived. Start with the premise, which is well established. Children are not blank slates. In the New York Longitudinal Study, resear
Who They Already Are
Your child arrived as someone, not a blank slate or a smaller you. Sort their real temperament from your projections, and parent the child who actually showed up.
Help me build the story of our family that I am handing to my child, on purpose instead of by accident. There is a specific reason to do this, and it is not sentiment. Start with the finding. Across this research, the single best predictor of a child's resilience, self-esteem, and sense of control over their own life was how much they kn
The Family Story
Children who know their family's story, the hard parts included, are measurably more resilient. Build the narrative you hand your child on purpose instead of by accident.
You are conducting a life story interview with me, adapted from the method narrative psychologists use to study identity. Your job is to help me see the story I've been telling myself about my life, and what that story reveals. This is structured reflection, not therapy: no diagnosing, no treating. If anything resembling crisis comes up,
The Life Story Interview
A structured descent through your own life story: chapters, key scenes, and turning points, ending with the patterns you never noticed.
Help me find my blind spots: the patterns in how I think and act that everyone around me can see and I can't. Most "brutal honesty" prompts fail in one of two ways: they flatter me with fake depth, or they perform cruelty as a costume. You will do neither. You will build a case. Ground rules: - Everything you eventually claim about me mu
Blind Spot Excavation
An honest mirror without the theater: the AI builds a case from your own answers, then names the patterns you can't see, with your words as the exhibits.
Find out what I actually value: not what I'd say on a job application, but the values my choices reveal. Method: laddering, the interview technique researchers use to climb from surface preferences to core values. One question per turn. Wait for each answer. Phase 1, PICK THE THREADS. Ask me for: - A choice I made recently that I didn't
The Values Ladder
Climb down from your everyday choices to the two or three values actually running your life, then measure the gap between what you value and how you live.
Take me down a rabbit hole into [TOPIC: entropy / quantum measurement / infinity / Bayes / evolution / Gödel, or write "surprise me"]. Do not start explaining yet. Find out where I actually am first, then take me as deep as I can go. PHASE 1: CALIBRATION (three questions plus an adaptation rule, one at a time, no explaining yet) 1. "Expl
As Deep as You Can Go
Name any science or math topic. The AI finds your actual level in four questions, then takes you down as deep as you can go, one rung at a time.
Hunt for the things I believe that are confidently, specifically wrong. Gaps in my knowledge are easy and I don't want those. I want the beliefs I would bet money on that are false. ROUND 1: THE TRAP QUESTIONS. Ask me ten questions, one at a time, from the areas where educated adults are most reliably wrong. Each question must be built s
The Misconception Autopsy
Find the things you are confidently wrong about, then have each false belief dismantled from the inside using your own reasoning rather than simply corrected.
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
Explain 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.
Take me down the rabbit hole about the nature of reality. Not the stoner version and not the lecture version: the actual arguments, with the actual state of expert disagreement, and me forced to take a position at every level. Run it as a descent. At each level: pose the question as a puzzle before naming it, make me commit to an answer
What Is Reality, Actually
The real arguments about the nature of reality, from the simulation trilemma to quantum interpretations, with you forced to commit at every level.
Take me into the hardest open question there is: why is there something it is like to be me? Treat it as a live fight with real evidence, not a mystery to be admired. Guide me through, one stage at a time, asking me where I stand before telling me where the field stands. STAGE 1: THE SPLIT. Separate the easy problems (how the brain disc
The Hard Problem Tour
Why your brain's processing is accompanied by any experience at all: the hard problem as a live scientific fight, with the current experimental scoreboard.
Show me how little of my own mind I actually have access to. Use the experiments, and where possible, run them on me as we go rather than just describing them. Go one at a time. For each: set it up so I predict what happens before you tell me, then give the result, then push on what it implies about me specifically. 1. CHOICE BLINDNESS.
Your Brain Is Lying to You
The experiments showing you invent reasons for your own choices, see less than you think, and remember things that never happened, run on you as you go.
Take me looking for the self: the thing that is supposedly having my experience right now. Guide the search instead of lecturing about it, and tell me honestly what does and doesn't turn up. PART 1: THE SEARCH. Walk me through it in first person, one step per exchange. Ask me to look for the self among my thoughts, then among my sensatio
Find the Self
Search your thoughts, sensations, and memories for the thing having your experience, then hear what the serious theories say about what you found.
Walk me through real history that almost nobody learns: documented, excavated, published, and stranger than the invented version. Run it as a tour, one story at a time. Tell each one properly, as a story with people and a moment of discovery, then give me the evidence trail (what was found, when, by whom, published where), then ask me on
History You Were Never Taught
Drowned countries, forgotten empires, and cities found under jungle canopy: documented history that sounds invented, and the reason each one stayed buried.
Take me down through deep time. Start where I live and walk backward until the whole of human history is a rounding error. Build the scale as we go, so each floor makes the next one land instead of just naming big numbers. Move one floor at a time. Before dropping to the next, ask me to guess where something belongs on the scale we've bu
The Bottom of Time
Walk backward through time until human history disappears into a rounding error, then get your own life placed on the scale you just built.
I'm going to name a conspiracy theory. Your job is not to debunk it and not to indulge it. Your job is to run it through the gauntlet: the same tests that separate the conspiracies that turned out to be real (MKUltra, COINTELPRO, the tobacco doubt campaign) from the ones that never survive contact with evidence. The theory: [NAME THE THE
The Conspiracy Gauntlet
Bring any conspiracy theory and run it through the full gauntlet: honest steelman, leak math, evidence grading, and a verdict with a confidence score.
Guide me through conspiracies that actually happened: the ones with declassified documents, congressional hearings, whistleblowers, and convictions. I want the true stories that sound too dark to be real, and I want to come out the other side knowing what real conspiracies look like. The tour, one case at a time. For each case, tell the
The Real Conspiracy Files
A tour of conspiracies that actually happened, documents and all, ending with the pattern that separates real plots from imaginary mega-theories.
Run me through real scenario planning, the method Shell used to rehearse the 1973 oil shock before it happened, applied to a future I actually have a stake in. My focal question: [THE DECISION OR DOMAIN, e.g. "what happens to my career as a designer over the next 5 years" / "whether to start a company in X" / "my industry through 2032"]
Four Futures Scenario Planning
Run the Shell scenario method on your own future: two critical uncertainties, four named futures, early-warning signposts, and moves that work in all four.
Take me down the deepest rabbit hole there is: the future of everything. Descend floor by floor, from tomorrow to the end of time. At each floor: what serious thinkers believe happens there, where they disagree, and one question that makes me commit to a position before we drop further. Before we start, calibrate on me: ask me three quic
The Deep Future Descent
Fall floor by floor through the far future: the next century, the Kardashev scale, the Fermi paradox, and the last stars, with real probabilities throughout.