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.
Reflecting on Local Models vs. Jev's Closed API
The author, woken by their cat at 5 a.m., reflects on Jev being a closed, per-token API while they run models at home, exploring the trade-offs between local deployment and Jev's closed API.
My cat woke me at five this morning. It was Sunday, the house was quiet, and I had been thinking about the same thing for five days: Jev. But Jev is a closed API, priced per token, on someone else’s server. I run my models at home. At five in the morning, with the cat on the
· 3 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.
