devwithjev
— reading now— views
Submit a build

Jev Chooses Tetris Piece Placements

Ziwen connected TypeSafe’s Jev to a Tetris game. For each piece, Jev examines the board and possible landing spots, then picks one in about half a second.

View on X costless than half a centtimeabout half a second
Ziwen@ziwenxu_𝕏
TypeSafe's Jev plays Tetris better than me!! We hooked it up to a Tetris game. Every piece, it looks at the board and all the spots the piece could land, and picks one in about half a second. A whole game cost us less than half a cent. Their price is $0.042 per million tokens in, and output is free. The speed and the price are insane.
Sep 18, 2026X postsView on X
Ziwen said a full game cost less than half a cent. They also reported pricing of $0.042 per million input tokens, with output free.

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.