Pacman Controlled by Jev

Nesan Selvan built a Pacman game in which Jev decides every move. For each tile, Jev receives information about Pacman’s surroundings and returns a direction, strategy, danger score, and flags for trapped, committed, and regret.

View on X

Nesan Selvan@NesanSelvan04𝕏

Built a Pacman where every single move is decided by @typesafeai jev 👾 Every tile, Jev gets what is around Pacman and returns a direction, strategy, danger score, flags for trapped, committed, regret. That decision moves the tile. Finally an innovative model after a long time. https://t.co/pcVQx7lbfX

Sep 18, 2026X postsView on X

Jev’s decision determines Pacman’s next tile. Selvan called it an innovative model after a long time.

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.