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's Jev Model Quickly Integrated by Dev Tool Companies
According to AI Matters, TypeSafe's Jev model has lower accuracy (67.8%) than top models, but responds in 0.4 seconds and costs a fraction (1/10 to 1/100) of alternatives. It outputs answer-probability instead of sentences. Four companies including Vercel integrated within three days. No external validation yet.
정확도는 상위 모델보다 낮은데, 개발 도구 업체들이 앞다퉈 붙인 모델 Jev. · 버셀 등 4곳이 사흘 내 통합 · 문장 대신 답과 맞을 확률만 출력 · 응답 0.4초, 비용은 수십~수백 분의 1 · 정확도 67.8% 외부 검증 자료는 아직 없습니다. #TypeSafe #Jev 원문은 아래에 ↓
· 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.
