devwithjev
— reading now— views
Submit a build

Jev Maze Solver

The build uses Jev to assess randomly generated mazes for fairness and moderate difficulty, then has Jev solve them by choosing a path.

View on X cost約0.12円
ドコカノうさぎ🐰ジビエーズ🌟メタバースアイドル@patsupyon𝕏
話題の新AI「Jev」を使って迷路を解いてみたぴょん ランダム生成の迷路から理不尽さが少なくかつ適度な手応えのある迷路をJevで判定。 その後、Jev自身で解いていきます。 どちらの道を選択するかをJevがAI判定。判断が高速なのが印象的! 1プレイで178,696トークン消費 AI利用コストは約0.12円 https://t.co/GI9PnzSb8d
Sep 20, 2026X postsView on X
The author found Jev’s decisions notably fast. One play consumed 178,696 tokens.

Also filed under Games & real time

  • Benchmarks Jev on Pokémon Red

    The project benchmarks Jev, TypeSafe’s fast decision model, against Jev paired with a GPT-6 Sol planner for playing Pokémon Red.

  • Plain-English Cellular Ecosystem Simulator

    LifePot is a cellular automaton-inspired ecosystem that users describe in plain English. Jev turns those inputs into species, feeding relationships, reproduction strategies, and environmental conditions.

  • Mapping Children's Behavioral Intent in Games

    Mores Research used Jev to map children’s behavioral intent in games and examine how it correlates with real-world behavior. It reports mapping intents across 45+ real sessions involving 20 child users over a long horizon.

  • StarCraft Agent for Fast Tactical Decisions

    Jev_Star is a StarCraft agent experiment that uses Jev for fast tactical decisions.