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.
Open-source Jev-like model runs on a laptop without API
The post says TypeSafe spent two years and $40M to put a decision model in the cloud, while a freshman open-sourced a Jev-like model that runs on a laptop with no API, no waitlist, no output tokens, about 13ms per decision, ~1GB RAM, 60 decisions per second, playing Snake.
TypeSafe Al spent 2 years in stealth and $40M to put a decision model in the cloud. 5 days later, a freshman open-sourced a Jev-like model that runs on a laptop. No API. No waitlist. No output tokens. ~13ms per decision. ~1GB RAM. 60 decisions a second. Playing Snake
· 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.
