1 jailing, 1 penalty, 1 replacement chain, 1 self-playtest, 1 spend spike and 1 scale readout

auto-assembled · drafted mechanically from this run's detected moments

Auto-assembled from the 6 sharpest detected moments of this run. None of them ever turned.

Or grab the whole reel as one image: composite.png · or as a looping animation: reel.webp

Animated reel: 1 jailing, 1 penalty, 1 replacement chain, 1 self-playtest, 1 spend spike and 1 scale readout. Auto-assembled from the 6 sharpest detected moments of this run. None of them ever turned. 6 moment cards with source code and transcript excerpts from the run telemetry.
The animated reel - the cards plus source code and transcript excerpts from the run telemetry. The full-size cards follow below.
  1. Fired for spinning in circles - a replacement hired within minutes. The orchestrator can fire an agent mid-run and hire a same-type replacement without stopping the job. The code agent was pulled after spinning through the same cycle over and over and was removed. A same-type replacement was hired and the job carried on.

    1/6 An agent is fired for cause; a same-type replacement takes over within minutes.

  2. At peak, 3 agents were mid-tool-call in the same second. One run, one job - and a headcount no single-agent tool can log. 1486 agents were hired across 20 hours. A dedicated supervision lane spent 2760 model calls doing nothing but checkups on the rest of the team.

    2/6 1486 agents hired for one job - a headcount no single-agent tool can log.

  3. The run's priciest five minutes - 2.6 times a typical window. Every model call is metered, so a run's spend can be read window by window against its own baseline. For five minutes, 47 model requests from 8 agents landed at once - 2.6 times the run's typical five-minute spend. The burst bought something: the checkup agent finished its job.

    3/6 The priciest five minutes runs 2.6 times the typical window - 8 agents burning at once.

  4. 7 demerits, then jail - and still finished the job. The orchestrator runs periodic checkups on every agent; one that keeps slipping can be jailed - pulled off the job on the spot. After 7 demerits at its checkups, the code agent was jailed. The agent still finished its job, and a same-type replacement had already been hired to keep the job moving.

    4/6 7 demerits at checkups, then jail. It still finished the job.

  5. Docked 15 merits for a file write that kept failing - and never earned them back. Favur's orchestrator runs periodic checkups on every agent on the team, awarding merits for good work and demerits for bad habits. A checkup caught the code agent pressing on after a file write kept failing, costing it 15 merits - over a third of its standing. The agent was jailed on the spot. It never earned the standing back before the run ended.

    5/6 The code agent is docked over a third of its standing for a file write that kept failing. It never recovered.

  6. The agent playtested its own game - 33 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 33 keys into the game window it had just built, pausing to wait 20 times and taking 5 screenshots between moves. After 10 minutes it stopped and went back to work.

    6/6 The agent plays its own game: 33 key presses, 5 screenshots.