devwithjevJev Self-Playing Tetris Demo
vmwareyou used Jev, a System One probability model from TypeSafe, to build a demo that plays Tetris by itself. The demo makes decisions through probability rather than text generation.
vmwareyou@lostingz001𝕏
我用 TypeSafe 家的 Jev（System One 概率模型），写了个让它【自己打俄罗斯方块】的 Demo。 整个过程没有任何文本生成，全部由概率驱动： • 每一回合把棋盘地形、空洞数和所有合法落点候选打包成 JSON 喂给 Jev • Jev 一次请求并行评估 3 个维度： 1. 最佳旋转与落点（Choice）：评估 4 种旋转姿态与 10 列的概率分布 2. 是否 Hold 暂存（Noul）：当前方块不利时概率激增，自动触发换块 3. 局势危险评分 0-4（Score）：实时监控堆叠高度与濒死风险 • 单步延迟仅 ~300ms，输出 Token 永久免费，整局打下来费用不到 1 美分！
Each turn, it sends Jev a JSON bundle containing the board, hole count, and legal move candidates. Jev evaluates move and rotation choices, whether to hold the current piece, and a danger score from 0 to 4.
Also filed under Games & real time
- 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.
- AI-Town Character Action Simulation
JevTown is an AI-town simulation where Jev selects character actions and responses.
- Jev-Powered Drone Swarm Simulation
The project simulates a drone swarm using Jev for reflex decisions and collision avoidance.