Jev Plays Roulette Wars Autonomously

Jev played Roulette Wars from start to finish with no human input and won all three games in 13–14 rounds each.

Nico Saraintaris@NicoSaraintaris𝕏

I had Jev (@typesafeai's new decision model) play my game Roulette Wars start to finish, no human input! In the game, the units ARE the chips, bet on a roulette table against a 1000 HP monster-dealer! Result: 3/3 games won, in 13-14 rounds each. Wanna know what I found? 🧵1/x https://t.co/ZwREv50Lx5

Sep 18, 2026X postsView on X

In the game, units are the chips. Players bet on a roulette table against a 1000 HP monster-dealer.

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.