Synthetic people

Most models of a place treat people as numbers: so many households, so many trips, so many cases. A growing family of tools models them one by one instead. They promise a city you can poll, a company you can trial a policy on, an outbreak you can run before it happens. They come in three layers, which are often stacked, and the layers are at very different stages.

Making the people

The base is a synthetic population: invented households and residents whose counts match the census area by area.⁵ This is old, well understood and openly maintained. PopulationSim builds them for transport planners,⁵ simPop and synthpop for statisticians,^6,7 and some come ready-made: Canada, Great Britain, and French regions through eqasim.^8,9,10 Their weakness is age. Most rest on a census five to fifteen years old.^8,9,11

The newer strand is personas for language models. NVIDIA's Nemotron-Personas are sets of invented individuals, each with a name, age, job and background, sampled so that the mix matches census statistics, now for twelve countries.^12,13 They are built to fit the census, and nothing yet shows they behave like the people they stand for.

Making them live

The second layer moves the population through its days. ActivitySim and MATSim give every resident a plan of trips and activities and are used by planning agencies to test roads and transit.^14,15 Epidemic models such as Covasim, JUNE and EpiSim do the same for contacts and infection; several were built for COVID.^16,17,18 New Zealand's ALMA holds more than five million simulated residents for public health questions, though its pages point to no public code or published results.^19,20 Mesa and NetLogo are the general kits for building your own.^21,22 Where these models have been checked against what happened, such as hospital admissions in England or infections in Berlin, they reproduced the curves.^17,18 Checked forecasts are rarer.

Making them talk

The third layer gives each person a language model, so they can answer a survey, join a focus group or live in a simulated town. Open libraries for this are active: Concordia, TinyTroupe, OASIS, AgentSociety and EDSL, descended from the Generative Agents town of 2023.^{23,24,25,26,27,28} Companies such as Simile and Aaru sell simulated populations to businesses, with accuracy figures they measure themselves.^29,30

What the evidence says

The studies agree more than the marketing suggests. Given a person's background, a language model reproduces the average answers of familiar American groups well: in one early study its predicted votes correlated with the votes people reported at 0.90 to 0.94.^2,3 It does worse on everything else. In one test, its answers on how partisans feel about each other had about half the spread of real ones, and nearly half the relationships estimated from them differed significantly from the real survey's.³⁵ It flattens and misportrays minority groups (Wang and colleagues), leans toward the views of liberal, educated and wealthy Americans (Santurkar and colleagues), matched under half of German voters' choices (von der Heyde and colleagues), and across 74 countries explained about 1% of the differences between individuals (Chen and colleagues).^4,31,32,33 Asked again months later, the same model did not give back the same data.²

The strongest result comes from a different approach. Agents built from two-hour interviews with 1,052 real Americans predicted those same people's survey answers about 83 to 86% as well as the people repeated themselves two weeks later (Park and colleagues).¹ That simulates people who were actually interviewed; it does not invent new ones.¹ A 2026 preprint adds a warning about election backtests: a model that seems to forecast a past vote may simply remember it (Özkan).³⁴

Using it

The first two layers are tools for planning, with decades of practice behind them. The third is useful for drafting a survey, rehearsing a meeting or finding questions worth asking real people, and not yet a replacement for asking them. A model that can be polled can also be used to target and persuade, and the people it imitates never agreed to it; Protect people's privacy applies with more force here. The use case How would these people respond? walks through the question as a planner would bring it.