devwithjevJev Snake Game Controller
Alberto Díaz built an initial experiment in which Jev controls the Snake game.
Alberto Díaz@alber_tostring𝕏
Me he montado un primer experimento para probar Jev, donde controla el juego de la snake, estas son mis impresiones: 1. La velocidad de respuesta es una pasada (P95 350 ms ~) 2. Es MUY barato (En este caso 1 centimo cada 200 peticiones) 3. El modelo acierta la mayoria de veces, pero alguna falla y esto hay que tenerlo en cuenta para el producto Esto hace viable ideas que antes bien por coste o por
Díaz reports fast responses and low cost. The model is right most of the time, but sometimes fails, which he says should be considered for the product.
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.