Self-Driving Simulation Tests Jev

Kaveh Mousavi Zamani built a self-driving simulation to test Jev. It takes structured sensor state and outputs typed driving decisions for steering, braking, overtaking, pedestrians, and speed limits.

View on X

Kaveh Mousavi Zamani@kavehmz𝕏

@typesafeai (and System One models in general) have a lot of uses, and fun to play with. New paradigm open to public now. This is a self-driving sim I spun up to test Jev today. Structured sensor state in, typed driving decisions out, steer, brake, overtake, pedestrians, speed limits. Prompt: https://t.co/KxMMNb9ME8

Sep 17, 2026X postsView on X

Mousavi Zamani describes the System One models as useful and fun to play with. He says the paradigm is now open to the public and links to the prompt.

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.