← Resource library

Research case

“Out of One, Many” — silicon samples (Argyle et al., Political Analysis 2023)

Conditioned GPT-3 on demographic backstories from US election surveys to simulate how subgroups would answer.

What is reported

The authors report the simulated response distributions closely tracked real subgroup patterns on several political measures.

Before you use it

This is evidence from particular US survey settings. Similar aggregate patterns do not establish that simulated respondents can replace a target population.

Sources and review

Original source ↗

Source checked · Not tested by this site

Checked the public abstract and bibliographic record. Results describe the authors' study, not a replication by this site.

Evidence / source record ↗

License and reuse

No license has been recorded. Check the source’s license before reusing code, models or data.

A license note is not a license audit. Open source does not guarantee free hosting, model access or commercial reuse.

Related resources