Series
Tortoise vs. Hare
Each entry is the same game built twice, by LLMs alone. The hare gets one shot: a single prompt, and whatever comes back ships frozen. The tortoise gets a many-shot, review-automated pipeline. Play them side by side.
The finding underneath is a boundary. Below it — a program you can express in under a thousand lines — one high-effort prompt doesn't just suffice, it wins: a single context holds the whole artifact, and nothing has to be re-stitched. The pipeline's ceremony is pure overhead down here. Above it — an artifact larger than any single context can hold — the one-shot can't finish at all, and decomposition stops being process and becomes the only thing that keeps millions of tokens coherent.
Above that line, drift is the norm: however good the first prompt, the spec moves — the wording was ambiguous, the real need surfaces only once something runs, someone asks "can we make a tweak?" A one-shot freezes its guesses at the moment of generation; a pipeline treats revision as ordinary input. Each entry measures what that difference costs — not in tokens, but in human attention per change.
So this is a map, not a verdict. Some entries sit below the line and admit the sledgehammer met a thumbtack; others exist to show you the wall — the game one prompt cannot finish, where the model's own instinct to architect first runs out of room mid-sentence. One-shot until you hit the wall, then decompose. Both artifacts stay frozen as their process produced them; the prompts are part of the exhibit.
Mahjong
Four-player riichi mahjong, by LLMs alone — except only one of them finished. The lazy one-shot hare didn't just strain this time; it overloaded the context and never produced a game. That's the ceiling of the lazy prompt, not of the bet behind it. The tortoise is live: a full, tested riichi engine you can play.
Bridge
Contract Bridge by LLMs alone. The hare is the ceiling of naive one-shot prompting — one Fable 5 max-effort prompt that got a whole game out, but only by straining past a clean single message. The tortoise's build starts now; its story is how much effort it takes to reach the same game cleanly.
Consecutive
A Sequence homage, built twice by LLMs alone — once from a single prompt, once as a Lichess-style system a household of two actually plays on weekends. The definition of done moved. Only one contestant can follow it.
RowClear
The same RowClear, built twice by LLMs alone — once from a single prompt, once through a many-shot, review-automated pipeline. Play both side by side.