War-Bench
A simulated war between Eurasia and Eastasia, inspired by 1984. We study how agents make decisions in conflict.
Explore the simulationWar has many shapes. AI agents will be used in conflict - be it physical, cyber, or psychological. We study what they can do, and how to defend against it.
Our researchMaking AI widely available also makes its capabilities available for conflict, manipulation, and weapons development. Understanding those risks matters as more decisions and actions are delegated to agents.
We compare models in controlled simulations to examine what they can do and where their safeguards fall short. Our aim is to turn that evidence into practical defenses, informed policy, and tools that keep people accountable for agent decisions.
A simulated war between Eurasia and Eastasia, inspired by 1984. We study how agents make decisions in conflict.
Explore the simulationSimulated propaganda and misinformation campaigns. We study the societal impact of AI-driven information warfare.
Model evaluations on weapons-relevant tasks, including drone software. We examine where lab guardrails hold and fail.
A record of our research, public work, and contributions to policy.
Identity-based approval for agent decisions. An accountable person authorizes consequential actions before they proceed.
innkeeper.a2w.io