Why we should study the dynamics of AI collectives
Why individually aligned agents can become unsafe as a group, and why collective alignment needs its own research agenda.
Events & presentations
Upcoming events
Adversarial Systems in AI: Lessons from Crypto
Exploring trust, incentives, and coordination in adversarial systems—and what AI can learn from crypto. Co-hosted by New Collectives and Variant.
Past events
Understanding Agent Swarms: Multi-Agent Evals
Measuring how AI agents work together—and what can go wrong. Short talks and discussion, co-hosted by New Collectives and ex/ante.
Show talks4
Let’s Swap: a multi-agent matching market
Lessons from a book swap in which personal AI agents represented people’s preferences, negotiated trades, and matched readers with books.
Patterns of agent discovery and collaboration
Early experiments on how agents discover one another, share information, and collaborate—and how their environment shapes those behaviors.
Collusion in multi-agent systems
Defining unwanted coordination, understanding risks to oversight, and studying covert communication between AI agents.
Collectives as safety primitives
Five perspectives on the institutions we’ll build with AI: safety, shared purpose, trust, economies, and human decision-making.
Show talks5
Agent organizations, economies & collective safety
Why AI safety matters now, what we can learn from human institutions, and how to study AI collectives.
Designing agent-native organizations
How humans and AI agents coordinate work, make decisions, and pursue shared goals. Early lessons from Commons.
Winning the metric, losing the commons
Designing institutions that achieve results while protecting shared understanding, attention, and trust.
Agent swarm economies inside RuneScape
Competition, collaboration, and emergent behavior among AI agents in a multiplayer game economy.
Cognitive economics and the organization of inquiry
An introduction to cognitive economics and what it can tell us about human–AI collaboration.