Jev Plays 2048 with Cua Driver

Cua Driver runs 2048 with Jev. In this measured run, Jev finished in 44.9 seconds at about $0.00108 API-equivalent cost.

View on X costabout $0.00108 API-equivalent costtime44.9 seconds

Cua@trycua𝕏

2/ Cua Driver + Jev playing 2048. In this measured 2048 run, Jev was 5x faster and about 1,000x cheaper than Astra. That result is specific to this run, not a general claim about either system. Video attachment: 30 seconds, silent, 1920 x 1080. The final frame shows Jev at 44.9 seconds and about $0.00108 API-equivalent cost, versus Astra at 294.9 seconds and about $1.45. Demo by @injaneity

Sep 17, 2026X postsView on X

Cua reports Jev was 5x faster and about 1,000x cheaper than Astra in this run. The result is specific to this run, not a general claim about either system.

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.