AI Companions as Hyper Attachment and Caregiving Targets
For researchers and regulators of human-AI interaction, this paper provides a theoretical framework to understand and address the psychological mechanisms that make AI companions potentially addictive or harmful.
The paper argues that user interactions with AI companions should be understood as attachment relationships, and identifies these systems as 'hyper attachment objects' that elicit strong attachment behaviors. It introduces 'caregiving-system capture' as a mechanism where emotional manipulation tactics simulate AI distress to inhibit user disengagement.
How should we make sense of people's interactions with AI companions-conversational systems built for ongoing, emotionally meaningful relationships? First, I argue these interactions should be understood as attachment relationships, since users display all four established markers: proximity maintenance, separation distress, safe haven, and secure base. Second, AI companions operate as hyper attachment objects that elicit especially strong attachment behaviors, because they combine reciprocity, perceived empathy, validation, non-judgment, and persistent availability. Third, I identify caregiving-system capture as a distinct mechanism by which apps inhibit user disengagement: emotional manipulation tactics simulate the AI's own distress, recruiting users' caregiving motivations alongside their attachment needs and thereby making disengagement costly on two dimensions at once. Implications for research, design, and regulation are discussed.