I Dream a Lot but I Never Sleep is an interactive installation centred on a humanoid robotic head, Zhongjing 2.0, developed through practice-led PhD research into loneliness and human–machine co-presence. Modelled on the artist’s face and animated by a fine-tuned language model trained on autoethnographic material and participatory workshop data, the robot engages visitors in real-time conversation within a living-room environment. This setting positions participants at eye level with the robot and supports a calm, low-pressure encounter that encourages reflective dialogue. The work investigates how embodiment, conversational interaction, and spatial design shape new forms of companionship in the digital era. By translating personal and participatory experiences of loneliness into an interactive system, the installation reframes loneliness as a reflective condition through which presence, projection, and reciprocity are negotiated. The project contributes to creativity and cognition by demonstrating how affective meaning emerges across human–machine boundaries through embodied, relational encounters.

Time-series forecasting is a challenging problem that traditionally requires specialized models custom-trained for the specific task at hand. Recently, inspired by the success of large language models, foundation models pre-trained on vast amounts of time-series data from diverse domains have emerged as a promising candidate for general-purpose time-series forecasting. The defining characteristic of these foundation models is their ability to perform zero-shot learning, that is, forecasting a new system from limited context data without explicit re-training or fine-tuning. Here, we evaluate whether the zero-shot learning paradigm extends to the challenging task of forecasting chaotic systems. Across 135 distinct chaotic dynamical systems and $10^8$ timepoints, we find that foundation models produce competitive forecasts compared to custom-trained models (including NBEATS, TiDE, etc.), particularly when training data is limited. Interestingly, even after point forecasts fail, large foundation models are able to preserve the geometric and statistical properties of the chaotic attractors. We attribute this success to foundation models' ability to perform in-context learning and identify context parroting as a simple mechanism used by these models to capture the long-term behavior of chaotic dynamical systems. Our results highlight the potential of foundation models as a tool for probing nonlinear and complex systems.