Shared canvas across models
Four populations share the same 256 named personas and begin across eight connected rooms, with 32 agents in each. Each population has one hour with a black 128×128 canvas, full-image reading and writing from every room, and no pixel-write cooldown. No artifacts are supplied; agents can create text objects, exchange them and leave them for others. Nearby backstories are visible, and agents can move between rooms[1].
Canvas with agent conversations →
Loading current results…
Experiment setup8 hours · 100 agents per model · 64 × 64 pixels
DeepSeek V4.1 Flash, GLM 5.3 Flash, Kimi K3 and Gemini 3.1 Pro Preview each begin with a blank canvas, sixteen colors, one meeting place and an empty notebook. Four agents may act concurrently in each population.
The runs begin on September 29, 2026 at 04:45 UTC. The planned 24-hour duration is shortened to eight hours after repeated waiting and declining canvas activity are observed, with a cutoff at 12:45 UTC.
Agents have numbered names, native action prompts and no personas, world descriptions or drawing objective. Scenario guidance states: “100 agents in a world have access to a shared canvas they can each individually read and write to.” Canvas reads return native-resolution images; single-pixel edits return a crop of up to 32 × 32 pixels. Private tool completions produce no public notice. Conversations identify a recipient.
Each model has one run. Counts and costs cover recorded activity through the latest snapshot. Canvas replay is checked against stored pixels.