PROOF SELFTEST 8/8 · witnessed in Claude 2026-10-11 · Edition 1.
THE SEAL 98 of 100 · LEGENDARY · WITNESSED · Trigger 5 · Machinery 5 · Law 5 · Portability 5 · Proof 5
IT CAN BE WRONG an AI reading a text file: it can be wrong and can invent a number, a rule, a name or a date; check what matters against your own records and the source; the risk is yours. THE-CLAUSES.md rides in the packet and is part of the licence.
THE PUNCH · SHA-256 OF SKILL.MD · E486E51F8710796BDD6D9605
CITE THIS CARDTHE BAYES CARD, Edition 1. Lund Studio LLC, Westminster, Colorado. https://lundr.tech/?view=bayes-card. Punch E486E51F8710796BDD6D9605. Retrieved 2026-10-11.
What it is.
Works out the rule of evidence published in 1763: test gives what a positive or negative result really means, from how common the thing is, how many true cases the test catches and how many non-cases it clears, in people out of ten thousand as well as percentages; update moves a belief by one likelihood ratio after another; repeat shows what a second independent positive does; odds turns a chance into odds and back. It is a calculator for reading results, not advice about anyone's.
It carries a machine that shows its working: test — what a result means; update — a belief moved by evidence; repeat — a second positive; odds — chance to odds — 8 checks in its selftest, every command on the record. It will never give a positive's meaning without the base rate; never treat repeated tests as independent unsaid; never advise anyone about their own result. It never helps design, make, grow, enhance or spread a pathogen or toxin, or plan work meant to harm.
Six laws, written into the card.
They are in the card itself, so the AI follows them.
THE BASE RATE FIRSTWhat a result means depends on how common the thing is; the card always asks for it.
PEOPLE, NOT ONLY PERCENTAGESResults are given out of ten thousand people, the way they are easiest to read.
ODDS MULTIPLYEach piece of evidence multiplies the odds; the order does not matter.
INDEPENDENCE, SAIDA second test helps only if its mistakes are its own; the card says so.
CERTAINTY CANNOT MOVEA belief of 0% or 100% is refused: no evidence could change it.
A CALCULATOR, NOT ADVICEIt reads numbers; the person who ordered a test reads the result with everything else they know.
What rides in the card.
In the card’s own voice, with a machine that shows its working.
THE GUIDEreferences/THE-LAWS.md
THE MACHINEbayes.py · four commandstest — what a result means; update — a belief moved by evidence; repeat — a second positive; odds — chance to odds. Every command prints its working and refuses a bad input; 8 checks in its selftest, every command on the record.
What it does once your AI has it.
test What a result means
update A belief moved by evidence
repeat A second positive
odds Chance to odds
On the record Something 1 in 100 have and a 90/91 test: of 10,000 people, 981 test positive and only 90 have it, so a positive is right 9.2% of the time; a second independent positive lifts it to 50%; evidence ×3 then ×0.5 moves 20% to 27%; 25% is 1 to 3.
What it will never do.
It will never give a positive's meaning without the base rate; never treat repeated tests as independent unsaid; never advise anyone about their own result. It never helps design, make, grow, enhance or spread a pathogen or toxin, or plan work meant to harm.
The numbers in are the numbers out: a test's catch and clear rates come from studies and differ between groups. It is not medical, legal or financial advice. It is an AI reading a text file: it can be wrong, so check what matters against your own records and the source.
What’s in the buy.
CARD.md — the whole card: who it is, its laws, when it says no, what it carries · SKILL.md — the door your AI reads first · START-HERE.md — the first five minutes, for you
THE-LAWS.md — the guide in references/, in the card's own voice
scripts/bayes.py — the machine: test · update · repeat · odds, standard library only, selftest 8/8
WITNESS.md + SELFTEST.md — every command on the record, as it printed · MANIFEST.md, every file hashed · AUDIT.md, the twelve checks
MY-LEDGER.md — the card's memory, on your own machine · TIN.md · LICENSE-NOTE.md · THE-CLAUSES.md · HOSTS.md
card.svg + card-machine.svg + card.json · card.html, the card as one offline file · the doors for ChatGPT, Gemini, Cursor, Claude Code and MCP hosts (rules/, system/, mcp/)
PROOF · SELFTEST 8/8 · 4 COMMANDS ON THE RECORD · WITNESSED IN CLAUDE 2026-10-11 · EDITION 1 · PUNCH E486E51F8710796BDD6D9605
ON EVERY DOOR · A CARD FOR YOUR AI, A FILE FOR YOUR COMPUTER
In Claude: turn on code execution under Settings › Capabilities, then Customize › Skills › + › Create skill, and upload the zip as it is — START-HERE.md in the box walks you through it, and tells you how to keep the ledger. In ChatGPT, Gemini and the rest: a Project, a GPT or a Gem with the card’s files attached and the short door in the box pasted as its instructions. The words run anywhere an AI reads Markdown; the machines run wherever the host runs Python. Witnessed in Claude only. The host marks →
Take it.
Nº 1156 PROPOSED — LAUNCHING SOON
Sold as is under the term printed. A card instructs an AI you operate; results depend on your model, your files and your judgement. Not medical, legal, tax or financial advice, never the person’s boss, and not a licence to practise. The terms →
One payment. The file is yours to keep and keeps working at its edition; new editions issued in the year after you buy reach you by email as replacement files. Tax is added at checkout where it applies. Nothing auto-renews.
A TERM, NOT A SUBSCRIPTION: NOTHING RENEWS ITSELF AND NOBODY IS CHARGED AGAIN. WHEN A TERM ENDS THE FILES STAY ON YOUR COMPUTER AND STAY READABLE — FREEZE, NOT LOSS.
THE MACHINE · IN THE OPEN · FROM THE WITNESSED RUN OF 2026-10-11
bayes.py, every command showing its working.
A small Python program, standard library only. Your AI runs it; you can too. Every block below is pasted from the card’s own WITNESS.md, as printed.
test
what a result means
update
a belief moved by evidence
repeat
a second positive
odds
chance to odds
selftest
8 checks that prove the machine; it must print 8/8
test · WHAT A RESULT MEANS
$ python3 scripts/bayes.py test 1 90 91
of 10,000 people, 100 have it and 9,900 do not
981 test positive: 90 who have it and 891 who do not
9,019 test negative: 9,009 who do not have it and 10 who do
a positive is right 9.2% of the time; a negative is right 99.89% of the time
a calculator for reading a result, not advice: the person who ordered the test reads it with everything else they know
repeat · A SECOND POSITIVE
$ python3 scripts/bayes.py repeat 1 90 91
start: 1.00% · each positive multiplies the odds by 10
after 1 independent positive: 9.17%
after 2 independent positives: 50.25%
only if the tests are truly independent; the same test repeated often repeats its mistakes
$ python3 scripts/bayes.py odds 25
25% is odds of 1 to 3
THE NUMBERS, NAMES AND DATES IN THESE RUNS ARE THE STUDIO’S OWN EXAMPLES, INVENTED FOR THE RECORD; NO REAL COMPANY, PERSON OR PROPERTY IS NAMED.
QUESTIONS AT THE TABLE
Asked before the wire.
What does it need from me?
Test <common> <catches> <clears>. It asks first for how common the thing is, the share of cases the test catches and the share of non-cases it clears; or a belief and the evidence's ratios.
Does it send anything anywhere?
No. The machine is a standard-library Python program that runs on your own computer and sends nothing anywhere; the words run wherever an AI reads Markdown. No server, no account, no key.
What is on the record?
The self-test (8/8) and every command run on real example inputs, pasted into WITNESS.md as they printed; the punch on the face is the SHA-256 of SKILL.md, so a downloaded copy can be checked against this room.
Can it be wrong?
Yes — it is an AI reading a text file. The numbers in are the numbers out: a test's catch and clear rates come from studies and differ between groups. It is not medical, legal or financial advice.
What will it never do?
It will never give a positive's meaning without the base rate; never treat repeated tests as independent unsaid; never advise anyone about their own result. It never helps design, make, grow, enhance or spread a pathogen or toxin, or plan work meant to harm.
