Oh crap, Jev is leaning the AI toward a judging function.

@sora19ai そら ☁️ AgentSwarm 自動化オタク📱 · Sep 20, 2026 · case #996178 · listed via Jev Hub

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

Used Jev's typed Choice/Score/Noel answers directly without parsing output text, relying on its 70-500ms latency for branching decisions.

The original post, translated

Oh crap, Jev is leaning the AI toward a judging function. With TypeSafe's System One model, it returns from state + question. https:// x.com/everestchris6/ status/2101706320261128398/video/1 … Uses the typed answer as-is. ・Low latency of 70–500ms ・Branches with Choice/Score/Noul ・No parsing of output text Details in

Show the original post in its source language ▾

Oh crap, Jev is leaning the AI toward a judging function. With TypeSafe's System One model, it returns from state + question. https:// x.com/everestchris6/ status/2101706320261128398/video/1 … Uses the typed answer as-is. ・Low latency of 70–500ms ・Branches with Choice/Score/Noul ・No parsing of output text Details in

The post above is a machine translation from ja; the untranslated text is in the fold-out.

Engagement when collected

Views1.2K

Likes2

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 video, animation & media. 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 video, animation & media page.

🎬 Video, animation & media