FAVUR
The agent playtested its own game - 10 key presses, 3 screenshots. An agent can drive a real window: pressing keys, taking screenshots, and reading pixels back to see what happened. It pressed 10 keys into the game window it had just built, pausing to wait 4 times and taking 3 screenshots between moves. After 4 minutes it stopped, having filed 17 verifications of what it saw on screen.

Where this happened.

Source events.

Detected mechanically by the self_playtest detector from 10 telemetry event(s):

  • 5f5b5880-8dd1-4669-9b9b-99159cf97275
  • 1b8b7fe6-3445-4f74-aaf9-b8d228c19e17
  • 13151393-8dd0-48f6-9758-335f2100a5ff
  • 2ac1b427-4622-4ecf-90a0-8ea7249d3541
  • b365a632-869d-4a32-8e30-b30657c8dc7f
  • c83faf4f-6bb4-48cb-8fd4-1f7199926eb2
  • 762faea5-36ae-40f7-b9e0-f44ba17d7328
  • 353f2085-f4f2-4bda-925a-71a2f53b0dd0
  • 52ddcac2-8dd1-43c5-bb27-73d3017250ec
  • 2c5e784d-8bd1-4286-8f6d-9ba7b06ccf71