Jev Drives in a Simulator

TuTao put Jev behind the wheel in simulation, where it chose from 15 simulator-predicted trajectories every 0.5 simulated seconds. In one run, it made 261 API calls, cost $0.18, had zero collisions, and reached the finish.

View on X cost$0.18

TuTao@tutao0123𝕏

I put Jev behind the wheel—in simulation 🚗 Every 0.5 simulated seconds, it picked from 15 simulator-predicted trajectories. One run: 261 API calls, $0.18, zero collisions, finish reached. Bright lines = predictions. Gold = actual path. License pending. Parking wasn’t tested 😅

Sep 20, 2026X postsView on X

Bright lines represented predictions, while gold showed the actual path. The license was pending, and parking was not tested.

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.