← Explore Capabilities
Simulate participation
Ability to simulate the interactions and decisions of actors (e.g., participants, stakeholders, facilitators, experts), subprocesses, or entire processes (e.g., for rapid process iteration).
How this is performed now...
- Process organizers Process organizers can infer from recorded preferences for new contexts, but these inferences are usually human estimates and not supported by well-documented algorithms.
- Collective dialogue organizers Collective dialogue organizers can run processes with simulated participants, though more research is needed to resolve their fidelity.
Related Resources
Research
Democracy on Mars 3: New Tools for Popular Sovereignty
Several have explored versions of this idea, under the keywords 'AI-as-representative' (Collins, 2023), 'voting avatars' (Grandi, 2018), and 'virtual democracy' (Kahng et al., 2019), 'plurals' (Ashkinaze et al., 2024) and 'simulated deliberative democracy' (Leike, 2023).
Research
Agent-Mediated Social Choice
Proposes autonomous AI agents ("voting avatars") that debate and vote on behalf of citizens, addressing the cognitive burden of direct democracy in complex societies through compact preference representation. Umberto Grandi argues these systems would leverage AI research in multiagent systems and...
Research
Statistical Foundations of Virtual Democracy
Examines which voting rules are robust to prediction errors in "virtual democracy" systems that learn individual preferences and aggregate predicted votes. The research proves that the classic Borda count rule is robust to prediction errors, whereas any voting rule belonging to the wide family of...
Research
A proposal for importing society’s values
Proposes using imitation learning on large language models trained on recorded deliberative democracy sessions to answer value-laden questions at scale. The approach involves recording human 'mini-publics' deliberating complex value questions with AI assistance, then training models to simulate t...
Research
General Social Agents
Presents an approach for building AI "general" agents that can predict human behavior in novel settings without requiring extensive setting-specific training data. The agents use theory-grounded natural language instructions combined with existing empirical data and knowledge from language model ...
Research
AI-Enhanced Deliberative Democracy and the Future of the Collective Will
Examines design choices behind computational frameworks for finding common ground across collective preferences, situating AI-assisted preference elicitation within the historical context of opinion polls. Emphasizes that preferences are shaped by context and seldom objectively captured, explorin...
Infrastructure
Policy Priority Reference
Policy Priority Inference (PPI) is a research programme and open-source toolkit that models the causal link between government expenditure and policy outcomes using agent-based modeling (a transparent AI approach). It helps governments measure public spending impact on development outcomes and su...
Research
Shareholder Democracy with AI Representatives
Proposes AI-enabled representatives trained on individual shareholder preferences to vote on their behalf in corporate governance. Addresses the problem that mutual funds concentrate voting power among few asset managers who lack insight into individual preferences. Argues this approach could out...
Research
Generative Agent Simulations of 1,000 People
We present a novel agent architecture that simulates the attitudes and behaviors of 1,052 real individuals—applying large language models to qualitative interviews about their lives, then measuring how well these agents replicate the attitudes and behaviors of the individuals that they represent.
Experimental Practice
Simile.ai
Simile is a simulation platform for human behavior. AI-driven simulations show how and why customers, employees, or populations respond to change.
Related goals and research questions
Goal: Deliberative processes that can be tested and refined before implementation with real participants.
How can we develop realistic simulation environments that accurately predict how different deliberative formats will perform according to different design choices?
Urgent
Can AI generate its own suggested changes and test them to search the latent space for optimal solutions?
Urgent
How can lessons from speculative execution and speculative decoding help increase the availability of deliberative processes through reduced costs?
Urgent
How can we solve the technical blockers to effective and truth-worthy multi-agent simulation and modelling?
Urgent
What are the best methods to measure the accuracy of simulations?
Urgent
What hybrid approaches can combine fast simulation with selective human input to optimize both speed and accuracy for urgent decisions?
Urgent