Awesome Jev: early projects and use cases
A community-curated list gathers early Jev projects and ideas for developers who already have API access.
Decision 2B vs Jev 1.13.0 Benchmark Comparison
Decision 2B (v1.4.1) vs Jev 1.13.0: Calibration 74.1 vs 76.3, Speed 84.3 vs 83.3, Cost 62.5 vs 52.0, Intelligence 38.8 vs 53.1. Jev leads with 63.29.
Decision 2B (https://FlyMy.AI), new in v1.4.1, keeps pace with Jev 1.13.0 on three: Calibration 74.1 vs 76.3, Speed 84.3 vs 83.3, Cost 62.5 vs 52.0. The fourth decides: Intelligence 38.8 vs 53.1, under 50, so the gate applies. Score 35.80 (#25) vs 63.29 (#1).
· 0 likesOpen on X
More like this
Training an MLP on Qwen 4B to Replicate Jev Behavior
The author shares an open-source project openjev that trains an MLP on qwen 4b to work like Jev, with a Hugging Face link. Link
Swapping an agent's tool-calling reasoning with Jev
The author shares replacing an agent's tool-calling reasoning with Jev, using Fable, Astra, and Opus; early results show drastic savings with very close results, with a demo video promised.
