Jev Plays 2048 from Board States

Jev plays 2048 by choosing an up, down, left, or right move from the current board state.

Yared Tekileselassie@yared_tekile𝕏

Made Jev from TypeSafe AI play 2048 At every turn, I give Jev the current board state and let it decide the next move: up, down, left, or right. No text generation. Just state → decision → action. A fun little test of System One models https://t.co/5Ps61plMid

Sep 19, 2026X postsView on X

Yared Tekileselassie says he provides the board state at every turn and lets Jev decide the next move. He describes the process as state → decision → action, with no text generation, and as a test of System One models.

Also filed under Games & 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.
StarCraft Agent for Fast Tactical Decisions
Jev_Star is a StarCraft agent experiment that uses Jev for fast tactical decisions.