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 is powerful, but the hype tweets around every new model are getting comedic
The author acknowledges JEV's power but criticizes the repetitive hype-tweet format that appears with every new model or AI tool, arguing the real value isn't in those tweets.
JEV is undoubtedly super powerful and a very good tool, but it’s getting comedic how every single time a new model or new “ai” tool is released this format is used. There is real value behind this tools, not in these tweets that always claim that Astra or whatever, somehow is
· 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.
