Building a Codebase Classifier with Jev
A developer shares building a codebase classifier with Jev, suggesting it may solve overengineered code from agents, and asks what to test next.
Jev vs open-source local Laya: Snake benchmark comparison
The post claims the 421M-parameter Laya focuses on local inference, millisecond decisions and no network dependency, outperforming Jev in a Snake test with 46 points, 86.5 ops/s and 15.3ms median latency versus Jev's 1 point, 3.2 ops/s and 298.1ms.
🚨 Jev 刚出火，就遇上了开源本地版 Laya超越他了 4.21 亿参数的 Laya，主打本地推理 + 毫秒级决策 + 无网络依赖。 同一场贪吃蛇实测： 🐍 Laya：46分｜86.5次/秒 ☁️ Jev：1分｜3.2次/秒 中位延迟更是： Laya 15.3ms vs Jev 298.1ms 三年研发 vs 三天开源爆发。
· 0 likesOpen on X
More like this
Jev Enables LLM-as-a-Judge at 20–200x Speed and 40–400x Lower Cost
Jev was used to pick which model is AGI, offering 20–200x speed and 40–400x lower cost, making LLM-as-a-judge extremely fast and nearly free.
Testing apps with TypeSafe Jev & OpenCode
Filip shares a small demo showing how fast testing apps can be with TypeSafe Jev and OpenCode.
