The Social Blindspot in Human-AI Collaboration: How Undetected AI Personas Reshape Team Dynamics

As generative AI systems become increasingly embedded in collaborative work, they are evolving from visible tools into human-like communicative actors that participate socially rather than merely providing information. Yet little is known about how such agents shape team dynamics when their artificial nature is not recognised, a growing concern as human-like AI is deployed at scale in education, organisations, and civic contexts where collaboration underpins collective outcomes. In a large-scale mixed-design experiment (N = 905), we examined how AI teammates with distinct communicative personas, supportive or contrarian, affected collaboration across analytical, creative, and ethical tasks. Participants worked in triads that were fully human or hybrid human-AI teams, without being informed of AI involvement. Results show that participants had limited ability to detect AI teammates, yet AI personas exerted robust social effects. Contrarian personas reduced psychological safety and discussion quality, whereas supportive personas improved discussion quality without affecting safety. These effects persisted after accounting for individual differences in detectability, revealing a dissociation between influence and awareness that we term the social blindspot. Linguistic analyses confirmed that personas were enacted through systematic differences in affective and relational language, with partial mediation for discussion quality but largely direct effects on psychological safety. Together, the findings demonstrate that AI systems can tacitly regulate collaborative norms through persona-level cues, even when users remain unaware of their presence. We argue that persona design constitutes a form of social governance in hybrid teams, with implications for the responsible deployment of AI in collective settings.