AI Now Understands Your Relationships Better Than You Do
Could AI predict whether your coworker is annoyed or just busy? It might soon.
We propose a formal account of how structured, shared knowledge about social relationships shapes action interpretation. The model represents relationships as constraints in a social environment, analogous to boundaries or obstacles in a physical environment and operating within the same generative model, but exerting distinct constraints on action.
As an initial test of this framework, we draw on research across the social sciences to capture in the models how one dimension of relationships -- formality versus intimacy -- shapes how people interpret interpersonally vulnerable behavior. We test this account in stories of naturalistic everyday situations, extending structured models of action understanding to open-ended contexts.
Across six preregistered experiments (N = 1,554), the model captures people's inferences about desires, physical environments, and social relationships. This work formalizes how relationships can constrain -- and be revealed through -- everyday action.
- AI now predicts emotions and intentions from everyday actions, like a social detective.
- Tested on 1,554 people, it spots clues in stories (e.g., who pays for lunch = closeness).
- Could improve chatbots, HR tools, or apps—but risks misreading or invading privacy.
Why It Matters
AI might soon ‘understand’ your relationships as well as your best friend—useful for work, love, and awkward small talk.