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 System One Model That Returns Decisions in ~80ms
Jev is TypeSafe's System One model. Instead of writing paragraphs, it returns a typed decision, a probability, and a confidence score in about 80ms. Output tokens are free; input costs $0.042/1M, making it a low-cost alternative to frontier models for simple decisions.
your LLM is burning frontier-model calls on decisions a $0.0006 call could make @typesafeai Jev is a "system one" model - it doesn't write paragraphs, it returns a typed decision + a probability + a confidence score in ~80ms. output tokens are free. $0.042 1M input. so 10,000
· 6 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.
