devwithjev
— reading now— views
Submit a build

Directable Video Game NPCs

David Parks describes his first experiment with Jev involving “playable” video game NPCs.

David Parks@dparksdev𝕏
My first experiment with Jev from @typesafeai. "Playable" video game NPCs. Tell one to explore, gather resources, or build a house. Override its directive and watch it change course. The NPC's next action choices and probabilities are visible live. https://t.co/1YdumKmIgg
Sep 18, 2026X postsView on X
A player can tell an NPC to explore, gather resources, or build a house, then override its directive and watch it change course. The NPC’s next action choices and probabilities are visible live.

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.