Noir Museum Heist Game with Live AI Decisions

Taylor Ortiz built a noir museum heist game using Jev, where the guard and security camera classify actions based on their surroundings in real time. Jev also classifies the player’s typed intent.

View on X costabout 5 million tokens for 13 cents

Taylor Ortiz@AnotherCodingX𝕏

Jev from @typesafeai is SO COOL I made a noir museum heist game where the guard and security camera each read their surroundings and classify what action to take (patrol, investigate, alert) in real time. The player types what they want to do and Jev classifies the intent. The sidebar shows every AI decision live with confidence as it happens. This used about 5 million tokens for 13 cents. There a

Sep 18, 2026X postsView on X

A sidebar displays each AI decision live with its confidence. Ortiz reports using about 5 million tokens for 13 cents.

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.