Designing Conversations with the Dead: How People Engage with Generative Ghosts
For designers of AI systems that simulate deceased individuals, this work provides qualitative insights into user preferences and concerns, though the findings are preliminary and domain-specific.
This study examines user experiences with two design choices for generative ghosts (AI trained on data of the deceased): representation (third-person) and reincarnation (first-person). Through a qualitative study with 16 participants, they found reincarnation preferred for immediacy but raising concerns about over-reliance, while representation was preferred for memory but often ignored by participants. Affective resonance was prioritized over factual fidelity.
We examine how people experience two choices in the design of generative ghosts, AI systems that are trained on data of the dead: representation, where an AI speaks about a deceased person in the third person, and reincarnation, where the AI speaks as the deceased in the first person. Through a qualitative user study with 16 participants, we explore how each shaped authenticity, affect, and risk. Reincarnation was preferred for its immediacy, but participants shared fears of over-reliance. Representation was preferred for engaging with memory over conversational presence, though participants often ignored this distinction, engaging in dialogue despite third-person framing. Across both modes, participants privileged affective resonance over factual fidelity. We conclude by showing how factors such as tone, language, and conversational rhythm -- factors unique to the user's memory of the deceased -- shape interactions with generative ghosts, and argue that those interactions are always collaborative.