devwithjevTesting Jev in a Temple Run Clone
ShengHui Wang tested @typesafeai’s Jev in an open-source Temple Run clone where the clock did not wait for the model. Across 176 decisions, Jev had one non-fatal mismatch against a perfect-information oracle; all eight recorded deaths were late answers, not wrong ones.
Also filed under Games & real time
- Steer a 3D Box with Goals
The build steers a 3D box with plain-language goals. An LLM plans each instruction, while TypeSafe Jev makes move, turn, and jump decisions in 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.