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.
Filtering Retrieved Memory Candidates with Jev
Kensuke Konno presents an implementation that uses Jev to filter retrieved memory candidates before passing them to Codex or Claude Code. The cited 62.5% reduction is a calculated value from lowering the candidate cap from 8 to 3, not a measured reduction in total tokens or cost.
〈知見〉Jevで読む記憶を絞る 今野健介氏が、検索済みの記憶候補をJevで選別してCodexやClaude Codeに渡す実装を紹介しました。「62.5%削減」は候補件数の上限を8件から3件に減らした場合の計算値で、総トークンや料金の削減実測ではありません。
· 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.
