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 browser tool and Codex: trade-offs of a low-cost click proxy
The post analyzes a division of labor where click operations are delegated to a low-cost model ($0.042 per million input tokens) while Codex handles typing and acceptance, reducing main model call costs. However, the tool only consumes the accessibility tree; canvas, iframe, drag-and-drop, and uploads must be handled manually, and debugging costs depend on how many page elements can be clicked by name.
把点击交给每百万输入 token $0.042 的模型、Codex 只留打字和验收，这套分工能砍掉每步一轮主模型的账单；但它只吃无障碍树，canvas、iframe、拖拽、上传全得自己接回去，最费劲的部分原样留着。省下来的是操作时间还是调试时间，取决于你的页面里有多少元素能靠名字点中。 https://github.com/wy-coliney/jev-browser-use…
· 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.
