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.
TypeSafe Jev Outperforms Qwen3-Reranker in Code Reranking Test
TypeSafe's Jev returns typed scores and was tested as a code reranker on 100 real GitHub issues, achieving 71.4% Recall@5 vs 63.4% for dense retrieval plus Qwen3-Reranker-4B, at about the same median latency (4.6s).
TypeSafe's Jev returns typed scores instead of text. We tested it as a code reranker on 100 real GitHub issues. With a model-planned grep in front, Jev hit 71.4% Recall@5, vs 63.4% for dense retrieval → Qwen3-Reranker-4B, at about the same median latency (4.6 s).
· 2 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.
