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's Low-Cost Speculative Calls Optimize Voice AI Turn Detection
Sam Gutentag shares: Flux signals a turn may be ending before it's sure; Jev is cheap enough for speculative calls, unlike LLMs that require certainty.
Again with the room quiet, so you can see the part that makes it work. Flux tells me a turn is probably ending before it's sure. With an LLM you'd wait for certainty, because a discarded call still costs you. Jev is cheap enough to spend on a maybe.
· 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.
