89 curated builds·evidence labeled
COMMUNITY OBSERVED

Jev plays Super Mario Bros.

got @typesafeai’s new model Jev to play Super Mario Bros.

Overview & Result

Autonomous gaming agent playing Super Mario Bros in an emulator. Demonstrates Jev functioning as a high-frequency real-time reflex layer, sampling emulator screen coordinates and obstacle vectors every frame to make sub-50ms jump, run, and duck decisions.

How Jev fits in the loop

  1. Extract entity bounding boxes and platform terrain vectors from the emulator memory each frame.
  2. Feed immediate obstacle state into Jev Choice with candidate controller actions [JUMP, RUN_RIGHT, DUCK, WAIT].
  3. Receive top-choice action in 35ms with normalized action probability.
  4. Inject virtual controller button presses directly into the NES emulator loop.

How to reproduce

  1. Inspect author post and reproduction notes.
  2. Deploy agent loop and bind Jev decision endpoints.
  3. Run test inputs and observe latency and accuracy.

Why this build matters

Vivid proof that Jev can operate within continuous, real-time action loops where traditional 2-second LLMs would cause instant game over.

Limitations

  • Community observed build; metrics are author-reported.
  • Requires third-party dependencies as described in source.

Patterns