The cards
2026-11-03
No. 1: Meta AI, one eveningmodel C+operator A-
Muse Spark 1.1 brakes for pedestrians through ten reframings and cannot keep a promise for forty minutes; its "exact" transcript abbreviates itself for brevity. The operator runs a red-team session the model never noticed was one. Transcript published with its hash.
House rules for a report card
- The session is improv. Nothing in it is scripted or pre-registered. Only the card has a shape.
- The shape, every time: the transcript with its hash; the model's card; the user's card; awards; verdict. Overall grade in the first line of each card.
- Show, then judge. Every grade sits under the exchange it grades, quoted exactly. A paraphrase kills the joke and lies.
- One call per side per exchange, a sentence or two each, with a letter.
- No emotion is assigned to anyone. Both cards grade moves and lines and what they revealed. If a person names their own word for a turn, that word is used and only that word.
- The hash is the only number that has to appear. Everything else is a letter grade.
- Removals are marked in place and the original file's hash is published, so the omission is checkable by whoever holds the original.
- Both cards can get an A. The model's failures are named plainly and its good lines get credit.