I was going to do a writeup of all the Jev stuff but

@ekzhang1 Eric Zhang · Sep 19, 2026 · case #105696 · listed via Jev Hub

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

Found Jev decision models useful and TypeSafe's zero-shot classifiers smarter than open-source alternatives, with some RL gap to explore.

The original post

I was going to do a writeup of all the Jev stuff but someone already did and explained the thing I made yday :’) https:// sgnt.ai/p/jev/ tl;dr the decision models are really useful, typesafe seems to indeed have smarter zero-shot classifiers than OSS, some RL gap to explore

Engagement when collected

Views2.3K

Likes4

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 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 classification & data extraction page.

🗂️ Classification & data extraction