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 Excels at Zero-Shot Classification, but Specialist Classifiers Dominate Commercial Use Cases
Josh notes that Jev performs well in zero-shot classification, but specialist classifiers are more advantageous in commercial settings. He mentions @trycua tuned a tiny model scoring 99.7% on form-filling eval, while hosted Jev scored 83.6%, and shares his experience tuning GLiNER 2.5 in 51 minutes.
Jev is great at zero-shot classification, but specialist classifiers will dominate commercial use cases. @trycua tuned a tiny model that scored 99.7% on their form-filling eval. Hosted Jev scored 83.6%. I tuned GLiNER 2.5 on a task in 51 minutes yesterday and it crushes
· 432 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.
