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: A Shift in How AI Systems Are Built
The tweet comments on Jev as a decision and orchestration layer in AI systems, suggesting it could make AI apps faster, cheaper, and more reliable.
Jev is an interesting shift in how AI systems get built. LLMs generate. Jev decides. Code acts. If this works at scale, AI apps could get faster, cheaper, and a lot more reliable. The orchestration layer might become just as important as the model itself. 👀
· 7 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.
