The author Hugo used a neon night scene ninja parkour game
Builder fed character position and velocity to Jev so it picks the next terrain shape from preset options instead of writing text.
The original post, translated
The author Hugo used a neon night scene ninja parkour game built with Sprite Fusion as an experimental carrier, and did an experiment with Jev. The author tells Jev information such as the character's current position and speed, and Jev directly chooses from several preset options what the next terrain will look like (width, whether there are gaps, height), without needing to write a paragraph and then interpret it like ChatGPT. Hugo believes that this kind of "directly choosing the answer"
Show the original post in its source language ▾
作者 Hugo 用 Sprite Fusion 搭建的一款霓虹夜景忍者跑酷游戏做实验载体，用 Jev 做了一个实验。 作者把角色当前的位置、速度等信息告诉 Jev，Jev 就直接从几个预设选项里选出接下来的地形长什么样（宽窄、有没有缺口、高低），不用像 ChatGPT 那样写一段话再去理解。 Hugo 认为这种”直接选答案”的
The post above is a machine translation from zh; the untranslated text is in the fold-out.
Engagement when collected
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 general Jev builds. 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. Browse the full case library for the work it sits next to.
Keep browsing: all 1173 Jev cases · more from @whthomas_unit · builders · what Jev is
Last updated: 2026-09-22 · sources & corrections · every card links to its author's original post