FAVUR
The agent playtested its own game - 47 key presses, 16 screenshots. An agent can drive a real window: pressing keys, taking screenshots, and reading pixels back to see what happened. It pressed 47 keys into the game window it had just built, pausing to wait 0 times and taking 16 screenshots between moves. It kept fiddling until the action limit finally cut it off.

Where this happened.

Source events.

Detected mechanically by the self_playtest detector from 11 telemetry event(s):

  • 7e7401c5-bcea-40a1-85c9-344d71256b65
  • f9ddedd5-42fd-44ac-9d14-3c525ec46a04
  • eb6f30e4-58ae-463e-a8b5-8f0ab8952e25
  • ece48451-bbc5-43a8-92a9-8bad87490025
  • c98b6565-a5f8-476b-a994-595cebc76566
  • 3d9c61db-28d4-4987-b302-928c435dbe0a
  • 9b3312be-7ac8-46b4-b08b-51d91a16b3b5
  • c58c44da-c664-4a91-a1cc-5b9048eec7c9
  • 74691ab3-38f9-4418-acc1-90c98429c6f7
  • 8750caec-aa18-4558-baa9-b166fcbf85c8
  • 9675fa29-31bf-498d-aef5-bacee077b7e6