Feel reinforcement learning by playing it—unusual pedagogical framing, but narrow audience.
ML enthusiasts, educators, gamers curious about optimization
Runs right in the browser with the source on GitHub, and the core conceit — playing as an optimizer hunting for a peak to 'climb' dimensions — is a neat educational hook. Feels like a compact interactive demo of hill-climbing/optimization techniques; it’s useful for teaching or prototyping but doesn’t yet show a deep technical twist or standout UX innovation.
UMAP-based game discovery, but needs better differentiation from existing Steam recommenders.
Polished word puzzle, but Wordle, Semantle, and dozens of letter-grid games exist.
Calibration game feeds behavioral dataset on human perception blind spots.
Physical QR tags for soccer balls with a built-in stats tracker.
Hides AI secret, live multiplayer prompts race to uncover it through social competition.
