devwithjev
— reading now— views
Submit a build

Jev Plays Live Clash Royale

Ben (@ffsxdev) built an interaction layer that let Jev play a live Clash Royale game, and Jev nearly beat him.

Ben@ffsxdev𝕏
I played Jev in Clash Royale, and it nearly beat me. I've seen a lot of demos recently where people have Jev play games, but most of them were singleplayer, and some paused the game so Jev had time to react. I extracted the game state from the live game - and mapped it into questions that Jev could answer, then wrote an interaction layer to perform the decisions that it made. The result, a freakis
Sep 18, 2026X postsView on X
Ben extracted the game state from the live game and mapped it into questions Jev could answer. He says many other game-playing demos were single-player or paused the game to give Jev time to react.

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.