People living with dementia are at risk of social isolation, and conversational AI agents can potentially support such individuals by reducing their loneliness. In our study, a conversational AI agent, called MindTalker, co-designed with therapists and utilizing the GPT-4 Large Language Model (LLM), was developed to support people with early-stage dementia, allowing them to experience a new type of “social relationship” that could be extended to real life. Eight PwD engaged with MindTalker for one month or even longer, and data was collected from interviews. Our findings emphasized that participants valued the novelty of AI, but sought more consistent, deeper interactions. They desired a personal touch from AI, while stressing the irreplaceable value of human interactions. The findings underscore the complexities of AI engagement dynamics, where participants commented on the artificial nature of AI, highlighting important insights into the future design of conversational AI for this population.

The development of AI to function as communicators (i.e., conversational agents), has opened the opportunity to rethink AI’s place within people’s social worlds, and the process of sense-making between humans and machines, especially for people with autism who may stand to benefit from such interactions. The current study aims to explore the interactions of six autistic and six non-autistic adults with a conversational virtual human (CVH/conversational agent/chatbot) over 1–4 weeks. Using semi-structured interviews, conversational chatlogs and post-study online questionnaires, we present findings related to human-chatbot interaction, chatbot humanization/dehumanization and chatbot’s autistic/non-autistic traits through thematic analysis. Findings suggest that although autistic users are willing to converse with the chatbot, there are no indications of relationship development with the chatbot. Our analysis also highlighted autistic users’ expectations of empathy from the chatbot. In the case of the non-autistic users, they tried to stretch the conversational agent’s abilities by continuously testing the AI conversational/cognitive skills. Moreover, non-autistic users were content with Kuki’s basic conversational skills, while on the contrary, autistic participants expected more in-depth conversations, as they trusted Kuki more. The findings offer insights to a new human-chatbot interaction model specifically for users with autism with a view to supporting them via companionship and social connectedness.

While conversational agents have traditionally been used for simple tasks such as scheduling meetings and customer service support, recent advancements have led researchers to examine their use in complex social situations, such as to provide emotional support and companionship. For mourners who could be vulnerable to the sense of loneliness and disruption of self-identity, such technology offers a unique way to help them cope with grief. In this study, we explore the potential benefits and risks of such a practice, through semi-structured interviews with 10 mourners who actively used chatbots at different phases of their loss. Our findings indicated seven approaches in which chatbots were used to help people cope with grief, by taking the role of listener, acting as a simulation of the deceased, romantic partner, friend and emotion coach. We then highlight how interacting with the chatbots impacted mourners’ grief experience, and conclude the paper with further research opportunities.