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.
Open-source alternative to Jev, Laya, launches: non-generative decision model at 32.8ms/query on T4
Laya is an open-source alternative to Jev, positioned as a non-generative decision model that runs at 32.8 ms per query on T4, supports 100+ languages, and is fully free and self-hostable. It offloads routing, priority scoring, and guardrail tasks previously handled by repeated LLM inference, greatly speeding up agent branching.
JevにOSS対抗が速攻で出てきた Laya ・判断だけ返す非生成型モデル ・T4で32.8ms/問 ・100言語以上 ・完全無料・自前運用可 LLMで毎回考えさせてた振り分け・優先度判定・ガードレールを、この軽量モデルに逃がせる。 エージェント分岐の速度が段違いになるやつ。
· 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.
