I tried playing Puyopuyo with Jev, but since it's hard to

@hota911 Hiroyuki Ota (ほた) · Sep 19, 2026 · case #465223 · listed via Jev Hub

Played Puyopuyo with Jev by asking which outcome is good instead of where to place, letting it pick moves reflexively.

The original post, translated

I tried playing Puyopuyo with Jev, but since it's hard to think about chains, I can barely win randomly. Instead of asking "where to place", I asked "which result is good?", and I became able to build chains a little. Are games that require deep thought difficult? Since it's a "System One Model", reflexive use cases are good, right?

Show the original post in its source language ▾

Puyopuyo を Jev でプレイしてみたけど、連鎖を考えるのが難しいので、なんとかランダムに勝てる程度。「どこに置く」ではなく「どの結果が良い？」と聞いて、すこし連鎖が組めるようになった。熟考が必要なゲームは難しいか。"System One Model" なので、脊髄反射的なユースケースが良いんですね。

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

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 games & playable demos. 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 games & playable demos page.

🎮 Games & playable demos