Jev Plays Puyo Puyo

Hiroyuki Ota used Jev to play Puyo Puyo in real time, asking it to identify the current phase and select the best outcome for each phase based on strategy.

View on X

Hiroyuki Ota (ほた)@hota911𝕏

Jev にぷよぷよをさせてみた。 - 実行エンジンは https://t.co/NiVAe3js64 。ゲームはリアルタイムで進行 - 盤面とそれぞれのポジションにおいたあとの結果を与え、①今どのフェーズか ②フェーズごとに、戦略からどの結果がベストかの1+3つの質問をして、選択肢を選ぶ画像は Random に勝つ様子。決断が早いぶん Random も強い。最初は盤面だけ渡して、単にどこにどの向きで落とすか判断させていたが弱すぎたので、配置後の結果を選ばせるようにしたり、戦略を渡したり、判断を多段化した結果なんとか3連鎖もでき Random に勝てるようになった。

Sep 19, 2026X postsView on X

Ota initially gave Jev only the board and asked where and how to drop each piece, but found it too weak. He then added post-placement outcomes and strategy, and split the decisions into multiple stages. Jev eventually made a three-chain and beat Random.

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.