devwithjev
— reading now— views
Submit a build

SystemOneHarness Plays Mario with Jev

Renchu Song built SystemOneHarness, an open-source harness for System 1 models such as Jev, and taught it to play Mario.

View on X
Renchu Song@richard_epsilla𝕏
Weekend plan: rest. Actual weekend: built SystemOneHarness, an open source harness for System 1 models like #Jev from @typesafeai. Then, to test it, taught it to play Mario. No chain of thought. No reflection. Just vibes at 60 decisions per second. It's better than me now, which is not a high bar 🤣 https://t.co/vPLTtuJnX8
Sep 20, 2026X postsView on X
The Mario test used no chain of thought or reflection. Song described it as running at 60 decisions per second and joked that it was better than him.

Also filed under Games & 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.

  • StarCraft Agent for Fast Tactical Decisions

    Jev_Star is a StarCraft agent experiment that uses Jev for fast tactical decisions.