devwithjevJev-Powered Gomoku Player
The program combines Jev with an algorithm that screens moves for offense and defense before Jev selects a move; in the second version, it defeated the author. In the first version, Jev chose moves on its own and lost.
GOGOGO@GodName794𝕏
第一版： 让Jev模型自己决定怎么走，显然Jev败北； 第二版： 算法优化 使用预判攻防筛选落子，再让Jev决定走哪一步，Jev最终打败了我！ 这次经历让我更清楚地看到：表现聪明，和做出可靠判断，是两件需要分别验证的事。 我怎么看 AI？ AI 很擅长从复杂信息里提取规律，在信息不完整、要求不够明确时给出判断。但它给出了选择，甚至给出了很高的概率，都不等于它已经算清楚后果。 这盘五子棋就是一个例子：Jev 能选择落点，却没有独立证明自己看到了所有关键反击。给它补上试走和检查，整个系统才更可靠。所以评价 AI，应该看它在具体条件下做对了什么，而不能只看它说得多像专家。 我怎么看算法？ 算法是把判断方法明确写下来：先检查什么、遇到什么情况怎么办、怎样验证结果。 我们这套程序的优势，是能重复、稳定地执行这些步骤，还能给出可核验的杀棋路线。但它的局限也很清楚：搜索只覆盖有限范围，评分规则是人为设定
The author says adding trial moves and checks made the system more reliable. The algorithm can provide verifiable winning lines, but its search is limited and its scoring rules are human-defined.
Also filed under Games & real time
- 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.
- Editable Jev Use Case Playground
TypeSafeAI’s community playground features editable Jev use cases, games, dilemmas, challenges, and A/B comparisons.