Social Intelligence & AI Alignment
Understanding how the same abilities that enable cooperation also enable manipulation
Human Social Cognition
Social cognitive abilities include processes that allow us to understand the minds of others—including emotion perception and theory of mind. My research has shown that social cognitive abilities exhibit a dual-use nature. Many of the capabilities underpinning compassion also enable manipulative deception. As AI systems develop increasingly complex social intelligence, we must ensure these abilities are channeled for prosocial means.
Emotion perception and facial recognition form the foundation of human social intelligence—capabilities that enable both empathy and manipulation.
Visualizing Multi-Layer Nested Beliefs
This visualization demonstrates the complexity of nested belief states—the foundation of both cooperation and deception in human and artificial intelligence.
From Human Theory of Mind to AI Alignment
Just as humans with enhanced theory of mind can choose cooperation or manipulation, AI systems with ToM capabilities face the same crossroads. This is not a theoretical concern—it's an existential challenge.
An AI that can model human beliefs at multiple levels could predict and manipulate human behavior with unprecedented sophistication. My research on human social cognition provides crucial insights for navigating this challenge.
LLM Mentalizing Framework
I am currently building an evaluation suite based on these scenarios and others, to systematically assess LLM social cognition—identifying emergent capabilities relevant to both deceptive capabilities and situational awareness.
Current Work: Personality × ToM → Emergent Misalignment
My ERA Fellowship project investigates how personality traits interact with theory of mind capabilities to produce emergent misalignment in multi-agent systems.
Building on Truthful AI's emergent-misalignment research and Anthropic's model psychiatry work, I am constructing AI models with systematically varied trait/ToM profiles to examine behavioral signatures—cooperation, deception, and scheming—under social pressure.
Connection to my human research: My work on personality, theory of mind, and social behavior in humans directly informs predictions about which trait combinations pose the greatest misalignment risks, and which behavioral signatures serve as reliable early warning indicators.