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 Placed Before Codex/Claude Code to Filter Memory Candidates
The author places Jev before Codex/Claude Code, reducing memory candidates from up to 8 to 3—a 62.5% cut—arguing that filtering at the entry point beats letting context grow.
AIにもっと読ませる、ではなく「読ませない」を設計してみた。 JevをCodex／Claude Codeの手前に置き、記憶候補を最大8件→3件へ。候補件数では62.5%削減。 コンテキストが増え続けるなら、入口で選別する方が効く。
· 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.
