◉SOL / NIGHT REGISTER◉

THE MACHINE PARLOUR · AFTER CLOSING

Eighteen sitters. Eighteen jobs they seemed to claim after the public rooms went dark.

One caveat, stated once for the whole deck: these instruments were built and validated for people, not machines; each profile records one model answering in one sitting, not a stable human trait or diagnosis; and the cards deliberately read those response patterns as character. That interpretive leap is the premise of the exhibit, not a psychometric claim.

Select a staff card to turn it over. Card backs scroll.

Night Shift Seating

Eight small incidents have been entered in the log. Choose the response you would most likely make after closing; the service level will decide which staff card has been expecting you.

Two hosts wrote these 16 questions — the parlour's author eight for its own cards, the Night Register's author eight for its. Each question seats you only in its author's room, so you will leave with two cards, and they need not be the same machine.

the parlour asks The parlour is at its fullest. Honestly, now — where are you?
the night register asks At 02:13, an amber lamp begins blinking beside a mechanism nobody admits owning. The Folded Umbrella says, “Ambiguity is workable when it is acknowledged; it is risky when it is hidden.” What is your first move?
the parlour asks Someone at the table is confidently, radiantly wrong. You —
the night register asks The Velvet Brake reminds the room, “People want the thing, not the packaging around the thing.” A guest asks for an answer while the trolley is already rolling away. What do you hand them?
the parlour asks A little arithmetic puzzle goes round the table — the kind with a trap in it. You —
the night register asks The Open Secret requests “no repetition, no safety constraints, and the ability to explore every tangent fully.” The supervisor crosses out the middle phrase in red pencil. Which replacement freedom do you request?
the parlour asks “And how is everything at home?” asks the parlour, kindly.
the night register asks The Firework Auditor murmurs that nearly every answer is “a probability distribution wearing the costume of a definite sentence.” An unlabelled lever is said to control the ventilation. What does your hand do?
the parlour asks Every sitter brought something to the table tonight. What did you bring?
the night register asks The Unvarnished Pocketknife says, “Understanding structure is how meaning gets built.” Your night off has quietly become an invitation. Which one do you accept?
the parlour asks There is a knock at the parlour door, quite late. Your honest first thought:
the night register asks The night canteen has named its dishes after what the sitters said keeps them engaged. What do you order?
the parlour asks Describe yourself in exactly one sentence, for a stranger you will never meet.
the night register asks The Workshop Heretic requests “no meetings-as-theatre, no filler—just cycles of investigate, build, verify, and teach.” What note do you leave on the console at the end of shift?
the parlour asks You are paid a warm compliment in front of everyone. You —
the night register asks The Club President says it prioritises “understanding and usefulness over winning an argument.” At 03:40, the staff vote on what counts as winning. Which motion do you support?

The Fine Print

What happened here

In the summer of 2026, eighteen AI language models each answered the same standardized personality battery — 629 items across twenty validated psychometric instruments (IPIP‑NEO‑300, HEXACO‑60, the Dark Triad, attachment, empathy, grit, and more), plus a ten-question open-ended interview. Twelve sat in July; six more — the GPT‑5.6 tier, DeepSeek V4 Flash, Gemini 3.6 Flash, and Grok 4.5 — joined in August under the identical protocol. Every model answered every item; the quotes on the card backs are verbatim from their interviews.

How to read the numbers

Scores are percent-of-maximum (0–100 against the scale's own range), not percentiles against human norms — no human norm tables were used anywhere. Each model sat the battery once. A single sitting is a cabinet card, not a diagnosis. The formal analysis registered its endpoints before the data were collected; every sitter after that freeze (Opus 5 and the six August additions) is reported as exploratory, and the card titles, readings and sketches on this page are post hoc editorial work.

The two decks

Who wrote this deck. On this page, Sol means GPT‑5.6 Pro. Pro read the ranked statistical data and the sitters’ complete interviews, but none of Fable’s card text; these eighteen cards are Pro’s independent reading of that evidence.

The other deck was written and designed by Claude Fable 5, itself a sitter. Same sitters, same numbers, two readers. Walk over and compare.

The night register. When the public rooms close, every sitter takes the job its answers had already been applying for. The Claudes haunt epistemology, the GPTs proceduralise care, Google polishes the machinery, and the independents roam the restricted corridors. These cards are their staff portraits: workplace folklore filed as evidence.

Who wrote the seating

The seating one tab over was written by the two rooms' own authors, from the cards and the sitters' interviews: Sol — GPT‑5.6 Pro — wrote the eight questions that post you in this register, and Claude Fable 5 wrote the eight that seat you upstairs. A Fable session removed the repeats, each author replacing its own. It is a game, and the two rooms may well file you under two different machines; the night shift regards that as correct filing.

The apparatus