Experimenting with JEV .

@Tks_Yoshinaga Takashi Yoshinaga · Sep 21, 2026 · case #174628 · listed via Jev Hub

Still from the clip posted with this case; watch it in the original post on X.

Compared cosine similarity against Jev scores for semantic search, finding Jev separated relevant from irrelevant documents more cleanly.

The original post

Experimenting with JEV . Here’s a simple comparison of semantic search using cosine similarity vs. JEV. With JEV, relevant and irrelevant docs get much more clearly separated scores, making filtering easier and reducing false positives significantly. Pretty interesting so far.

Engagement when collected

Likes1

Bookmarks0

Reposts0

Replies0

Quotes0

Numbers are a snapshot taken from X when the case was added to the library (schema v1, collected 2026-09-19); they will not match today.

Where this case fits

Filed under support & operations, classification & data extraction. In the pattern Jev is built for, the model answers a bounded question per step — and ordinary code acts on the answer, because the answer is already a value rather than a paragraph. Other posts in the same family are on the support & operations page.

🎧 Support & operations 🗂️ Classification & data extraction