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.
Developer questions Jev performance, showcases custom model
A developer claims retraining and adapting a model achieved an average p95 latency of 2.44ms on bun, questioning Jev's necessity and calling it hype.
Investi um tempo, retreinei o model, fiz adaptacoes caiu pra um p95 medio de 2.44ms, isso rodando em bun. Jev pra que? o meu ta mais rapido, mais modular, e com certeza vc pode fazer finetunning. Jev e hype. Hardware antes q encham o saco i9 14900hx, 4090 16gb mobile.
· 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.
