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.
Using Jev to Generate Teacher Data and Train LightGBM for 300x Speedup
The author tried playing Mario with Jev but failed due to latency from Japan; they generated teacher data with Jev, trained LightGBM, and replaced it, achieving over 300x speedup from Jev and clearing the game.
I tried playing Mario with Jev, but due to latency issues from Japan, no matter how many times I attempted it, I couldn't succeed. However, by creating teacher data with Jev, training LightGBM on it, and replacing it, I was able to speed it up by over 300 times from Jev and clear
· 128 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.
