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 to Predict Form Field Classification
The author proposes extracting features from each field and asking Jev for the probability that it is one of the inventoried fields, without passing any personal data to the model—only characteristics of the empty form.
Luego pensé en Jev: pasarle características extraídas de cada campo para preguntarle la probabilidad de que sea uno de los campos inventariados. Es decir, que no se le pasa ningún dato personal al modelo, solo características del formulario vacío.
· 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.
