When novices fabricate, they naturally start by choosing a workflow (e.g., laser cutting, 3D printing, wire bending) and the corresponding software (e.g., Adobe Illustrator, Fusion 360, Rhino) from a narrow set of options they know. As they advance their design, another workflow might better suit their design intent, but their models remain committed to the original workflow. This prohibits exploration, a learning mechanism fostering informed decision-making.

Generic AI auto-complete for message composition often fails to capture the nuance of personal identity, requiring editing. While harmless in low-stakes settings, for users of Augmentative and Alternative Communication (AAC) devices, who rely on such systems to communicate, this burden is severe. Intuitively, the need for edits would be lower if language models were personalized to the specific user’s communication. While personalization is technically feasible, it raises questions about how such systems affect AAC users’ agency, identity, and privacy. We conducted an autoethnographic study in three phases: (1) seven months of collecting all the lead author’s AAC communication data, (2) fine-tuning a model on this dataset, and (3) three months of daily use of personalized AI suggestions. We observed that: logging everyday conversations reshaped the author’s sense of agency, model training selectively amplified or muted aspects of his identity, and suggestions occasionally resurfaced private details outside their original context. Our findings show that ultra-personalized AAC reshapes communication by continually renegotiating agency, identity, and privacy between user and model. We highlight design directions for building personalized AAC technology that supports expressive, authentic communication.

Figure 1: A conversation between two AAC users.We find that backchanneling (active-listening) plays a crucial role in communication.However, here to enter text, both users engage with their devices, missing out on non-verbal cues from their interlocutor.We identify a need for better support of backchanneling for AAC, while respecting their established micro-culture.