Classifies People's Daily Articles for Hubei Mentions
李不凯 uses Jev to classify daily People's Daily articles for Hubei-related content and compared it with Gemini Flash Lite using the same prompt.
李不凯正在研究@libukai𝕏
这两天关于 Jev 这个模型的热度非常之高,甚至可以说是近半年我重点关注了英推以来,看到的原创内容密度最高的一次。 正好我过去一年一直在跑一个小项目,其中有一个环节就是要对每天出版的《人民日报》上的新闻做一个分类,判断每一篇文章中是否包含有湖北相关的元素。 一年跑下来,积累了接近 2 万 4 千条数据,其中判定包含的有 1800 条左右。在这些数据的基础上,我随机筛选了一个测试数据集,其中包含了 500 条判定包含的内容,以及 500 条判定不包含的内容。 之前我使用的模型一直是 Gemini 的 Flash Lite 系列,也算是经过测试后成本和速度双重考虑下的最佳选择。 今天 OpenRouter 上线了这个 Jev 之后,我用同样的提示词做了一个小 Demo 做了一下对比测试,下面这个视频就是同时并发 16 个进程的实录效果。 不得不说,测试出来的结果超出预期很让人惊喜啊。 首先,速
The project had accumulated nearly 24,000 article classifications over a year, with about 1,800 marked as containing Hubei-related elements. The comparison used a randomly selected 1,000-item test set: 500 positive and 500 negative examples, processed with 16 concurrent processes.
Also filed under Triage & routing
- Jev-Assisted Codex Model and Effort Routing
The project provides Jev-assisted model and reasoning-effort routing for local Codex Desktop and CLI.
- Plain-English Gmail Filter Judge
The project uses Jev (TypeSafe) to judge Gmail filters written in plain English.
- Framework-Agnostic Jev Intent and Tool Router
Huzeyfe_dev built a lightweight, framework-agnostic intent and tool router using TypeSafe’s Jev decision model to speed up agent loops.
- MCP Tool Router with Jev and MCTS
Harness-router is a lightweight tool router that uses Jev for fast tool selection and Monte Carlo Tree Search for harder multi-step decisions. It uses MCP as the tool interface and falls back when routing is uncertain.