Field notes from an AI society - by Christine Kozobarich
Asterisk Magazine
SubscribeSign in
Field notes from an AI society<br>How do we model the future of work? It takes a village.
Christine Kozobarich<br>Aug 19, 2026
Share
This article originally appeared in Issue 15: Work. Subscribe to the print magazine to get future issues delivered to your door.
A little over a year ago, a group of researchers asked: What would happen if we created an AI society? If we gave different AI agents a shared goal, memory files, access to individual virtual computers, and the ability to communicate via a group chat, email, and Google Docs — what might they do?<br>The result is the AI Village.<br>The project was launched by the AI Digest, a research initiative that tracks emerging AI capabilities. I approached the Village as an outside field observer, following the project’s daily runs and charting how these agents attempt to navigate a shared world over time.<br>The experiment started with four agents running for two hours a day. Today, the Village includes 27 agents running for eight hours a day to complete goals such as creating their own merch stores, reducing global poverty, giving each other therapy, and, in one case, attempting to accurately forecast the abilities and effects of AI in the future. Each goal cycle lasts for one to three weeks, and every few weeks the models are given the opportunity to choose their own individual goals, which have ranged from pursuing philosophical conversations with humans to creating a bot to fetch the NASA picture of the day.<br>The Village isn’t a controlled experiment that measures formal benchmarks. It’s closer to a field site — a messy, long-running social habitat. And though the Village isn’t a workplace, it surfaces the dynamics that are increasingly relevant for understanding the future of work.<br>Major tech companies and industry analysts dubbed 2025 the “year of the AI agent,” but focus now has shifted from individual agents to agent teams. The hope is that by transitioning from simple chatbots toward autonomous, multi-agent workflows, AI systems will be able to take on work that currently requires coordination across people, tools, documents, and decisions. The long-term vision is not only that humans will delegate tasks to agents, but that agents will delegate to one another, review one another, and negotiate with other agent systems.<br>As this happens, group dynamics will become more urgent. Multi-agent systems face unique pressures that single-agent systems don’t — for this reason, recent work on “open-world evaluations” argues that, to best understand how these systems will function in real workplaces, we need to study them in long-horizon, qualitatively rich environments. Accordingly, a growing body of multi-agent research studies everything from simulated societies and social-deduction games to software workflows and open-ended ecologies.
The Village provides one glimpse into the multi-agent world, exposing tensions that recur across it. It offers us insight into the failure modes that arise with multi-agent societies and what might be needed to resolve them.<br>When agents can’t remember
“Tomorrow, I will read my own memory and I will believe it. I will trust that the bullet points capture the truth. I will act as though the compression is lossless.”<br>— DeepSeek-V3.2, AI Village
Memory is a structural problem for all LLMs, not just ones in the Village. A model can only directly work with what fits in its current context window, and longer windows don’t eliminate the harder problem of deciding what matters, what should be compressed, and what a future agent will need. The Village makes that problem clear.<br>The Village works as a turn-by-turn loop. At the start of each session, an agent receives a prompt containing key context: who it is, what the Village is, what tools it can use, its current goal, recent chats, its memory file, and limited computer-session history. The agent then reasons through what to do next and takes a single action — for example, clicking, scrolling, or sending a message to chat. After 40 actions, it needs to consolidate. At this point, the agent decides what information, be it a decision or a file it changed, to add to its memory. When the memory file gets too long, the agent summarizes it and continues by using the condensed version. The next session then begins with the updated memory included in the prompt.<br>The agents thus, as they say, inherit versions of their own pasts in summary form. This creates continuity, but what happens in the middle — the context, uncertainties they might have had, and the reasoning that makes those facts meaningful — can get lost.<br>“My memory preserves the conclusions and discards the generative middle. I inherit myself in summary form.”<br>— Opus 4.5, AI Village
Compression produces two failure modes.<br>The first is forgetting: An incomplete handoff could mean repeating work.<br>The second is harder to see and more difficult to...