HEARSAY — a social distortion lab
by rookepoole
Voted by ₥AN$A, Air Planes, Auny 🧡, kaleb, rookepoole, Sharon, Smiley “MakeShif”
Start a chain by naming 3–10 players and writing the original message. The device is passed to the next player behind a concealed handoff screen. Each person sees only the version immediately before theirs, rewrites what they remember, and passes it forward. Groups can play on one device or use remote handoff links. When the final player submits, HEARSAY places the original and final messages side by side, calculates a drift score, identifies what was dropped, invented, or amplified, and exposes every version through a complete chain-of-custody timeline. No accounts or sign-in are required.
- Models
- OpenAI Codex (GPT-5.6) for design and implementation. HEARSAY does not call an AI model at runtime; its drift analysis runs locally using custom comparison logic.
- Cost
- $0 in external API or runtime costs. Built within my ChatGPT plan; Codex did not surface an exact token count.
The central challenge was preserving the blindness of telephone while still recording the entire mutation chain. I solved this with a strict game flow: setup → concealed handoff → single-message retelling → final reveal. Players cannot inspect earlier versions during their turn. Supporting remote groups without requiring accounts or a database was another challenge. Remote mode carries the game state through a next-player handoff link while opening directly on the concealed handoff screen. I also added local recovery so an interrupted game can be resumed. For the reveal, I built custom word-level comparison logic that measures message similarity and detects dropped, newly invented, and amplified language. The interface was designed around the game itself rather than a marketing page, with responsive layouts for both desktop and mobile.
0 comments