devwithjev
— reading now— views
Submit a build

Horse-Racing Strategy Simulation

やなしま りょうじ used Jev to simulate decisions with personal data, treating each jockey as an agent. The simulation considered each jockey’s positioning and strategy for the next 200 meters at 200-meter intervals.

View on X
やなしま りょうじ@yanashi𝕏
流行り物には触っておいた方がいいのでJevを使って手元のデータで意思決定のシミュレーションを行ってみた。 対象は競馬でジョッキー一人一人をエージェントにして200mごとに次の200mをどういう位置どりでどういう戦略で走るかをシミュレーションしてます。JevのAPIは2,000回くらい叩いている感じだけど金銭的には余裕な感じ。
Sep 20, 2026X postsView on X
The author says Jev’s API was called about 2,000 times and that the expense felt manageable.

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.