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.
Using Jev: automatic model selection by task complexity
A developer shares their experience with Jev: it doesn't write code directly, but before each call it assesses the request and picks a model—cheap for simple tasks, expensive for heavy ones—instead of always using one good model.
Estoy con Jev estos días. Para el que no lo haya pillado: no te escribe código. Antes de cada llamada mira qué estás pidiendo y elige modelo. Lo tonto al barato. Lo gordo al caro. Yo hasta ahora… modelo bueno y punto. Rename, test, arquitectura, da igual. Luego miras el usage
· 2 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.
