devwithjev
— reading now— views
Submit a build

Jev Gomoku Input Testing Arena

AIGC圈圈 connected Jev to a Gomoku game arranged as a nine-board arena, with two Jev-powered players on each board. A dashboard sets different inputs for each board to compare results and response speed.

View on X
AIGC圈圈@fakeWow_𝕏
我把jev模型接入到了五子棋游戏中，查看不同输入对结果的影响。 但这个五子棋有点不同，我构建了一个九宫格擂台，每个擂台有两个棋手，都是接的Jev模型。 为了测试不同输入信息对最终结果的影响。 添加了一个看板，给每个棋盘的Jev配置不同的输入信息。 除了能看到Jev的响应速度，还能看到什么样的输入配置会更有效。 体验地址：https://t.co/AIVpgzgkZE 视频展示如下，没有做加速，由于并行调用同时请求3盘，开始会一点点慢，看最后一局后面速度很快。 采用相同输入策略时打的有来有回。
Sep 18, 2026X postsView on X
The demo requests three boards in parallel, so it starts a little slowly; the video is not sped up. With the same input strategy, the players compete back and forth.

Also filed under Games & real time

  • Steer a 3D Box with Goals

    The build steers a 3D box with plain-language goals. An LLM plans each instruction, while TypeSafe Jev makes move, turn, and jump decisions in 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.