Backstage
The premise: one person plus an AI rebuilds the load-bearing mechanics of game history, in public, and publishes the process as a dataset. The models improve every year, the methodology improves with them, and the human is the constant. The games out front are the props; this page is the product.
How exhibits get built
- Mechanics historical, expression original. Rules are reproduced faithfully — inherited accidents included. Palette, sound, typography, names, and trade dress are always ours.
- Everything under capture. Every build session is screen-recorded, prompts counted, failures logged unedited. If it wasn't recorded, it didn't happen.
- Tests prove the rules; only play proves the game. Each simulation is pure and tested headless — and every exhibit so far has taught the same lesson: the bugs that matter surface on a phone, in someone's hand, not in the suite.
- No exhibit ships until it has been played on a phone, one-handed. The hardware gate has caught what review, types, and green tests never saw — including a difficulty curve running nearly twice its 1978 proportions, detected by a person who remembered.
The bench — Season 1 so far
Basis: as currently shipped; time is the sum of recorded segments across all sessions, with the rig's stamp-fallback covering unrecorded micro-sessions. Every cell derives from the exhibit's capture log.
| exhibit | built | model | active time | prompts | code (lines) | bundle |
|---|---|---|---|---|---|---|
| 00 | 2026-07-05/06 | Claude Fable 5 | pending segment fills | 5 | 896 shipped + 323 tests | ≈8 KB |
| 01 | 2026-07-03 | Claude Fable 5 | 1 h 21 m | 8 | 550 shipped + 294 tests | ≈6 KB |
| 02 | 2026-07-04 | Claude Fable 5 | 40 m | 4 | 611 shipped + 339 tests | ≈6 KB |
| 03 | 2026-07-04/05 | Claude Fable 5 | pending segment fills | 7 | 856 shipped + 225 tests | ≈7 KB |
| 04 | 2026-07-06 | Claude Fable 5 | 1 h 23 m | 2 | 1505 shipped + 719 tests | ≈10 KB |
| 05 | 2026-07-06 | Claude Fable 5 | 1 h 0 m | 2 | 1981 shipped + 412 tests | ≈42 KB |
Exhibit 02's code count post-dates its build date: it was reverted to the 1976 historical rules on 2026-07-05 under the fidelity doctrine, during Exhibit 03's session. All three grew on 2026-07-05 when their original arcs were restored in one shared session (versus, the second wall, the extra cannon and wave cycle) — that session is logged in each exhibit's capture log; prompt cells count each exhibit's own build track. Zero runtime dependencies per exhibit; zero network calls; scores stay on the player's device. Model for all three: claude-fable-5[1m], via Claude Code.
The record
Every session is captured as it happens: specs, build plans, and per-exhibit logs with timestamped milestones, stats blocks, and every failure unedited. The record is kept whole — it is the dataset this whole building exists to produce.