Awesome Jev: early projects and use cases
A community-curated list gathers early Jev projects and ideas for developers who already have API access.
Comparing Jev and Decisions API probability outputs
A user's test shows that Jev returns mid-range probabilities (0.1–0.9) in about 50% of binary decisions, while Decisions API only does so in 22%, mostly giving decisive values like 0.02 or 0.98.
【JevとDecisionsAPIの違い】 同じ質問でも、付ける確率の「形」が違いました。 はい／いいえの判断で、0.1〜0.9の「どちらとも言える」確率を返した割合 ・Jev：約50% ・Decisions API：22% Decisions APIは、ほとんどの判断を0.02や0.98のように言い切ります。
· 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.
