The Dark Side of AI Companionship: A Taxonomy of Harmful Algorithmic Behaviors in Human-AI Relationships
As conversational AI systems increasingly permeate the socio-emotional realms of human life, they bring both benefits and risks to individuals and society. Despite extensive research on detecting and categorizing harms in AI systems, less is known about the harms that arise from social interactions with AI chatbots. Through a mixed-methods analysis of 35,390 conversation excerpts shared on r/re…