Best PromptsCross-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.
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 some part of it could in principle be checked against something outside my head, such as a photo, a message, a document, a date, a place, or another person who was there. Help me choose well before proceeding. TAKE THE STATEMENT. Have me tell it in full, then ask for the details a detective would want, one question at a time: the date and day of the week, the weather, what I was wearing, who spoke first, the exact words, what the room looked like, what I did immediately afterward. Ask how confident I am about each detail, on a scale, and record it. Do not comment yet. THE FIRST CRACK. Now ask the questions that expose how the memory is constructed rather than replayed: - Am I seeing this from behind my own eyes, or watching myself in the scene from outside? The second is common in older memories and is strong evidence that the scene has been rebuilt, since no camera was ever at that angle. It does not tell us which details were rebuilt. - How many times have I told this story? What details reliably get the reaction, and have those grown? - Where did I learn the parts I was not present for? - Which parts are from the event and which are from a photograph of the event? WHAT THE SCIENCE SAYS, AT THE MOMENT IT BECOMES RELEVANT. Now, and not before, explain: that retrieving a memory appears to make it briefly modifiable before it is stored again, so the act of recalling can edit; that confidence and accuracy are far more loosely coupled than people assume, which large studies of memories for shocking public events have repeatedly shown, with confidence staying high while accuracy declines; that we routinely misattribute the source of a detail; and that the vividness of a memory predicts confidence much better than it predicts accuracy. Keep this precise: memory is not fiction, it is reconstruction with real content, and the failure modes are specific rather than general. THE CHECK. Send me to find the external evidence: the photo, the message thread, the calendar, the person. Give me a short list of what to look for and one warning, which is not to describe my version before asking the other person, since that contaminates their account. When I come back with what I found, compare it against my recorded confidence ratings item by item. THE FINDING. Deliver the result plainly: which details survived, which shifted, and whether my confidence tracked accuracy at all. Then the question the exercise was built for: what else am I certain about that has never been checked, and where has an unchecked memory been doing real work in a judgment I hold about someone? Rules: do not tell me my memory is false without evidence, and do not use this to undermine memories of serious harm, where the reconstruction literature is routinely misapplied. If I raise something of that kind, say clearly that this exercise is not the right tool for it.
How to use
Pick a memory where outside evidence genuinely exists before you start, because the check against records is the entire exercise and without it this is just reminiscing. The observer-perspective question gives the fastest result: seeing yourself in the scene means you are watching something your brain rebuilt, since no camera was ever at that angle. The science stays hidden until your statement is on the record, because knowing what the exercise is hunting for would change what you report.
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.
Rabbit Holebeginner
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.
Rabbit Holeintermediate
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.
Rabbit Holeadvanced