Notes · 05

Beautiful is
not a boolean.

Ask a model "is this beautiful?" and you will get an answer, delivered with total confidence, worth almost nothing. The failure is not that the model is dumb. The failure is that the question is malformed. Beautiful is not a property a design has or lacks, like a missing semicolon. This note is about what beauty actually is, and how that one idea shaped the deepest design decision in the uistash Lab.

01 · The malformed question

Beauty is a direction, not a classification.

Every design is a bundle of trade-offs: density against calm, character against familiarity, whitespace against information. There is no point in that space labeled correct. What a person calls beautiful is a direction through it, the trades they consistently prefer, and the direction differs from person to person in exactly the ways that matter.

A classifier needs a shared ground truth. Beauty has none. So any system that asks a machine "is this good?" is really asking "is this near the average of everyone?", which is the one place a personal taste, by definition, is not.

02 · Ask the person

Keep or kill, blind, repeatedly.

So uistash never asks the model to judge beauty. It asks the person, and it stacks the deck against self-deception. A Lab round runs one brief across up to six arms, each an engine paired with a prior: nothing, or your tastestack, or a file you dropped in. The results come back in a shuffled order that never reveals which arm made which design. You look at the work, only the work, and give a verdict.

The verdict vocabulary is deliberately small and deliberately honest: pick what you would keep, or say neither, or say unsure. The escape hatches are first-class answers, because a forced choice between two designs you would never ship is not taste data, it is noise wearing taste's clothes.

03 · One coordinate at a time

The labels reveal only after you choose.

Only after the verdict lands does the round reveal which engine and which prior made what. The order matters: judge first, learn afterward, so the reveal can inform you without ever steering you. Each verdict is recorded as evidence, one preference at a time.

A scatter of judged options: faint squares are killed, bright squares are kept. The kept squares concentrate in one region, and a dashed arrow points from the middle of the field toward that region: the direction that emerges from accumulated verdicts. In this picture 37 are kept and 120 are killed, and no single one of them says much alone. every verdict is one coordinatekeptkilledthe direction that emerges
No single verdict means much. Accumulated, they stop being answers and become a direction: one person's, not everyone's.

One verdict says almost nothing, and that is fine. It is one coordinate. Enough coordinates and a direction emerges that no single answer contained: the trades you keep making when nobody, including the interface, is telling you what you are choosing between.

04 · The instrument

The human judges. The machine measures.

There is a machine judge in the Lab, and the way it is caged is the whole point. It never answers "which is better?". It answers a different question: "which would this specific person save?", anchored to the invariants distilled from their actual library. It runs only after the human has picked, compares each pair twice with positions swapped, and when its two calls disagree it abstains instead of guessing.

Its verdicts live in a separate ledger from the human's, and what gets tracked is agreement, not authority. The machine is calibrating against the person, never substituting for them. Beauty stays a question only the person can answer. The machine's job is to make the answering rigorous: blind, repeated, recorded. The human stays the judge. The machine stays the instrument.