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.
Claude Code usage on a Jev Build Orchestrator docs task
The author stress-tested Claude Code Max (20x) on a single PR docs task for the Jev Build Orchestrator and hit the weekly usage limit in about two hours, warning that tuning docs first helps control token costs.
I’m stress-testing Claude Code Max (20x). One session, roughly 2 hours, working on a single PR docs task for the Jev Build Orchestrator and I already hit the weekly usage limit. Claude Code burns through tokens FAST. Tune the docs first. Otherwise, tokens get expensive.
· 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.
