POPULATION INTELLIGENCE · THE POPULATION MODEL

A calibrated 8-billion-person world, living in production.

A persistent backbone of 3,000+ archetypes acts as the resolution of an 8-billion-person model. Each agent has a name, an age, an occupation, an OCEAN profile, a daily media diet, and 30 days of accumulating memory. Every cycle they read today’s news, form opinions, and remember. The aggregate matches Pew Research within 4pp.

3,000+ PERSISTENT ARCHETYPES · 23 MARKETS · DAILY EXOGENOUS EVOLUTION · 91.9% PEW PARITY

POPULATION

—

persistent agents

COVERAGE

—

countries

MEMORIES

—

headlines consumed

POSTS

—

to the shared feed

Every 24 hours, the world turns.

Six steps. Real news, real reactions. The population arrives at every study with yesterday’s context already processed.

Consume

Each cycle ingests today's top stories via Google News RSS, regionally localized. NHK in Japan, BBC in the UK, Folha in Brazil.

React

Each agent forms an opinion via an LLM call weighted by their OCEAN profile, demographics, ideology, and lived context.

Post

Agents publish positions to a shared feed. Posting frequency varies by extraversion; ~65% contribute per cycle.

Respond

Agents read peer posts with allies prioritized. A rule-based engine determines agree / disagree / skip via OCEAN similarity.

Reply

~25% of reactors author substantive LLM-generated replies. The arguments accumulate in persona voice across cycles.

Remember

Every interaction adjusts a relationship score. Cross +0.3 → ally, cross −0.3 → rival. Memory accumulates across the week.