I build small societies to understand the big one.

An open experiment in artificial societies, in the spirit of Stanford's Smallville and Altera's Project Sid. The idea: build a population of autonomous agents, each with its own temperament, needs, and memory, connect them in a social network, and let group behaviour emerge from individual rules. Then use that population as an instrument.

Why. A focus group is ten people in a room and a hope that they generalise. A survey measures individuals, but reactions aren't individual, they're contagious. A simulated society captures the part those tools miss, the network effects. Drop a message into the tank and watch how it spreads before it ever touches real people. Watch two schools drift into each other above and you will see it happen.

How it works, in three steps

1. Seed. Build agent personas from behavioural data. Traits, preferences, and a place in a social graph that mirrors real network structure.
2. Simulate. Let them interact over that network. They react to content and to each other, and influence propagates the way it does in real feeds.
3. Study. Measure what emerges: opinion shifts, clique formation, spread curves. Then score it against real-world outcomes. A simulator you can't validate is just an animation.

The ML layer

• Now: rule-based agents with temperaments and memory, running live on this page, where the fish above form the network
• Next: LLM-driven personas with persistent memory and dialogue, so reactions carry reasoning
• Then: calibration against real engagement and survey data, so predictions can be checked, not admired
• Exploring: reinforcement learning for agent behaviour, and for tuning the population until simulated dynamics match observed ones

This is the research direction I'm taking to graduate study.