devwithjev
— reading now— views
Submit a build

Real-Time League of Legends Win-Probability Overlay

Filipe (@filicroval) used Jev to build a League of Legends win-probability overlay that updates in real time. Each second, the model receives the full game state and answers whether blue will win, who has the biggest impact, and whether the leading team is about to throw.

View on X costabout $0.20time~280 ms median
filipe@filicroval𝕏
got @typesafeai's jev to build a League of Legends win-probability overlay in real-time every second, the model receives the full game state in and answers three questions: will blue win, who has the biggest impact and is the leading team about to throw. works retroactively or live! ~2,000 Jev calls / 4.9M tokens / ~280 ms median whole game: about $0.20
Sep 18, 2026X postsView on X
The overlay works retroactively or 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.