Jev Plays Snake From Text

Jev played Snake by taking the board as text and choosing up, down, left, or right each frame.

David Andress@davidandress__𝕏

Jev only outputs probabilities. So I gave it the Snake board as text and asked one question every frame: up, down, left, or right? No training, no game code inside the model. It played fine for a while, then boxed itself with nowhere left to go. https://t.co/e6lGyVTrlk

Sep 17, 2026X postsView on X

The model only outputs probabilities; it had no training and no game code inside it. It played for a while before boxing itself in with nowhere left to go.

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.