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 Hands-On: Capability Boundaries and User Dependence
After days of high-frequency use, the author summarizes JEV's capability boundaries, noting it is a highly user-dependent tool whose value depends on the user.
After using JEV intensively for a few days, I gradually felt out the boundaries of its capabilities. After a few days of high-frequency hands-on testing, my biggest takeaway is: Jev is a tool that is extremely dependent on the user. How much value it can deliver depends entirely
· 131 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.
