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 vs Claude Fable 5.1 vs GPT-6 Astra: The Divide Between Decision and Generation
Hamza Khalid compares Jev, Claude Fable 5.1, and GPT-6 Astra across specs, benchmarks, and prices. He argues Jev decides while Fable and Astra generate, and highlights Fable 5.1's advantages including a 73.4% score on CursorBench 3.2, 75% cheaper pricing, and cache reads at $0.25 per 1M tokens.
JEV VS CLAUDE FABLE 5.1 VS GPT-6 ASTRA: I compared all 3 spec by spec, benchmark by benchmark, price by price Jev decides. Fable and Astra generate. They do different jobs Where Fable 5.1 wins: - CursorBench 3.2: 73.4% - 75% cheaper than before - Cache reads at $0.25 per 1M
· 2 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.
