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 tested across math, logic, text, structured data, and code
The author put Jev through tests in math, logic, text, structured data, and code, noting it is too cheap to meter and too fast to notice, but with big differences in where it performs well versus not.
I put Jev through a gauntlet of tests across math, logic, text, structured data and code. It's too cheap to meter and too fast to notice. But there are some big differences between where it performs well versus not.
· 1 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.
