Awesome Jev: early projects and use cases
A community-curated list gathers early Jev projects and ideas for developers who already have API access.
Jev Experiment: Japanese Politeness Barely Affects Judgments, Clear Requests Matter More
A user ran 190 Jev trials to test whether Japanese honorifics affect judgments; politeness was largely innocent, and how the request was framed mattered most, suggesting clarifying requests before fixing honorifics.
Jevで、日本語の丁寧さが判定を鈍らせるのか試してみました。 そこはほぼ無罪。 効いていたのは、何を求めたかでした。 190回回して見えたのは、敬語を直すより先に、要求を別で聞いた方がいいということ。 1枚目が結論、2枚目が実験詳細です。
· 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.
