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 catches 6/7 defects at 25x the speed
According to the post, Jev caught 6/7 planted issues in Every's defect test (vs 7/7 for Fable 5.1) at ~25x the speed. The author recommends pinning jev-1.13.0, logging probs and version on every call, and recalibrating thresholds on your own labels.
In Every's defect test (@danshipper) Jev caught 6/7 planted issues vs 7/7 for Fable 5.1, at ~25x the speed. Pin jev-1.13.0, log probs + version on every call, recalibrate thresholds on your own labels. https://every.to/vibe-check/mini-vibe-check-typesafe-s-jev-judged-everything-i-ve-written-in-0-7-seconds…
· 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.
