Jev-Powered Greed Island Game Testing

Hxhdb used TypeSafe AI’s Jev to play a work-in-progress Greed Island game from the game-master perspective, with 12 bots and Jev directing the camera toward characters likely to fight.

View on X cost約$0.13(約20円)

Hxhdb@hxhdb_jp𝕏

個人開発中のグリードアイランドをゲームマスター（運営）視点でTypeSafe AIのJevにプレイしてもらった。動画だけでいうと12体×約4分で約$0.13(約20円)で、遺伝的アルゴリズム含め初期付与の5ドルで大体思ってたとおりに動かすところまでいけた。後半2分は自分もゲーム内に入って一緒に遊べた。実装もClaudeCodeにIntroductionのページ渡してやりたいこと伝えたらすぐにできて、中だるみしていたデバッグも楽しく進めれそう。12体以外にもカメラのディレクターをJevにまかせていて、戦いが発生しそうなキャラクターに自動でフォーカスを当ててくれる。次から次にBotは改良されていくし、バグ発見や負荷テストも兼ねれるので、うまくループを回せればこれからのQAのスタンダードになっていくかも？そしてモタリケくんごめん。

Sep 20, 2026X postsView on X

Hxhdb says an initial $5, including use of a genetic algorithm, was enough to get the bots behaving roughly as intended. They built the integration with Claude Code by providing the Introduction page and describing what they wanted, then joined the game for the final two minutes.

Also filed under Games & real time

Benchmarks Jev on Pokémon Red
The project benchmarks Jev, TypeSafe’s fast decision model, against Jev paired with a GPT-6 Sol planner for playing Pokémon Red.
Plain-English Cellular Ecosystem Simulator
LifePot is a cellular automaton-inspired ecosystem that users describe in plain English. Jev turns those inputs into species, feeding relationships, reproduction strategies, and environmental conditions.
Mapping Children's Behavioral Intent in Games
Mores Research used Jev to map children’s behavioral intent in games and examine how it correlates with real-world behavior. It reports mapping intents across 45+ real sessions involving 20 child users over a long horizon.
StarCraft Agent for Fast Tactical Decisions
Jev_Star is a StarCraft agent experiment that uses Jev for fast tactical decisions.