FAVUR
The agent playtested its own game - 46 key presses, 5 screenshots. An agent can drive a real window: pressing keys, taking screenshots, and reading pixels back to see what happened. It pressed 46 keys into the game window it had just built, pausing to wait 46 times and taking 5 screenshots between moves. After 5 minutes it stopped, having filed 99 verifications of what it saw on screen.

Where this happened.

Source events.

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

  • a9eb9fd5-418d-484b-8451-d7feb880de93
  • b14121c0-6a98-4cde-9d4b-3eee7d1f503d
  • 477fca0b-375d-42c7-b550-582bf3562b26
  • 96789a12-2b5a-42f0-83d4-3e3da01f75ee
  • c24f304c-6c43-48ad-9c6a-9acd7a8aa032
  • 681962cd-3b21-4fb0-9f6c-1c77ec66470e
  • e5583e26-003e-4772-bd2d-5091f254d40c
  • 4f0dd9a5-1ad2-4150-910d-f3acc7c227f4
  • 337d7195-e11a-4fe9-9b7b-b42064649b05
  • 5f824c5d-7116-4640-8d11-33a66daee1c7
  • d1e73c44-bfa3-4891-8532-8e88a60561f9