Did I just beat TypeSafe AI's Jev on calibration with an

@heman10x Hemant · Sep 18, 2026 · case #155921 · listed via Jev Hub

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

Benchmarked an 11-second TF-IDF baseline against Jev on the LocalLLaMA typed-decisions split of 400 cases and 2,000 decisions.

The original post

Did I just beat TypeSafe AI's Jev on calibration with an 11-second TF-IDF baseline ?! Here is what happened: my 151M model initially scored 26.10% on LocalLLaMA/typed-decisions (400 cases, 2,000 decisions). Uniform random chance on that split is 29.85%. Before touching model

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 browser & computer use. 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 browser & computer use page.

🌐 Browser & computer use