As the population of older adults continues to grow, there is increasing need to explore how technology-enhanced recreation can support well-being. While Generative AI (GenAI) shows promise in this area, its role in recreational activities for older adults remains underexplored. We report on a two-year engagement with a suburban Japanese aging community aimed at identifying design considerations for image-based GenAI-supported recreational activities. Through four workshops conducted using a Research-through-Design approach—individual prompting, collective prompting, prompt guessing, and curating prompts—we examined how different forms of participation shaped engagement with GenAI. Our findings suggest that although older adults show clear interest in image-based GenAI, it becomes more meaningful when embedded in culturally recognizable practices and socially mediated infrastructures, rather than framed primarily as an individual creativity or literacy tool. Based on these insights, we discuss implications for integrating GenAI into meaningful community-based recreational activities for older adults.

LLM-assisted technologies are increasingly used to support cognitive processing and information interpretation, yet their role in aiding memory recall—and how people choose to engage with them—remains underexplored. We studied participants who watched a short robbery video (approximating a one-time eyewitness scenario) and composed recall statements using either a default GPT or a guided GPT prompted with a standardized eyewitness protocol. Results show that default-condition participants who believed they had a clearer understanding of the event were more likely to trust GPT’s output, whereas guided-condition participants showed stronger alignment between subjective clarity and actual recall. Additionally, participants evaluated the legitimacy of the individuals in the incident differently across conditions. Interaction analysis further revealed that default-GPT users spontaneously developed diverse strategies, including building on existing recollections, requesting potentially missing details, and treating GPT as a recall coach. This work shows how GPT–user interplay subconsciously affects beliefs and perceptions of remembered events.

Figure 1: This figure summarizes the process of this study in probing adaptation strategies for social isolation through an immersive virtual experience.(Left) Participants described how they modified and adapted their isolation private rooms in a virtual spaceflight experience.(Center) Participants engaged in collaborative storytelling, proposing individual or cooperative adaptation methods.(Right) Seven days later, in a follow-up interview, we found that the immersive virtual experience inspired participants' self-regulation and real-world isolation adaptation.

Introspectus AI is a generative AI-based system designed to enhance self-reflection and support positive behavior change. By leveraging multimodal information from users' daily life recordings, it provides personalized and detailed feedback, aiming to deepen self-awareness and facilitate positive behavioral adjustments. This study explores the short-term and long-term impacts of interacting with Introspectus AI, focusing on its potential to enhance reflective practices and improve the acceptance of generative AI tools. Following the user experience was defined through an initial round of workshops with four experts. The resulting system was evaluated through a long-term study involving 64 participants. The results demonstrate that AI-supported interventions significantly improved engagement in self-reflection, the need for reflection, and insight, while also increasing user acceptance of generative AI over time. These findings underscore the potential of generative AI as a practical tool for self-improvement, offering insights into its broader applicability in promoting well-being and personal growth.

Skin temperature is an important physiological factor for human hand dexterity. Leveraging this feature, we engineered an exoskeleton, called DexteriSync, that can dynamically adjust the user’s finger dexterity and induce different thermal perceptions by modulating finger skin temperature. This exoskeleton comprises flexible silicone-copper tube segments, 3D-printed finger sockets, a 3D-printed palm base, a pump system, and a water temperature control with a storage unit. By realising an embodied experience of compromised dexterity, DexteriSync can help product designers understand the lived experience of compromised hand dexterity, such as that of the elderly and/or neurodivergent users, when designing daily necessities for them.

Dementia describes a syndrome of cognitive degeneration, and Behavioural and Psychological Symptoms of Dementia (BPSD) is the non-cognitive symptom. BPSD can be improved by care services. To aid better care service, we explore the potential of using Augmented Reality (AR) to support dementia education for medical workers in three steps: (1) We explore medical workers’ perspective on dementia care lived experience and XR, (2) we co-design an educational experience containing an AR-based application and a 5-min activity with medical workers, (3) we evaluate the effectiveness of the system through a mixed method study. Our result shows that the AR experience successfully touches participants, and motivates them to reflect on the provision of care service. On this basis, we discuss the elements and challenges of designing XR-enabled dementia education for users unfamiliar with novel technology, and the potential of using XR in clinical education.