ai interaction designers

Abstract: This paper introduces a Theory of Developer Momentum that helps us see the activity of developing software in motion and the skilled craft through which progress unfolds. We define Developer Momentum as the developer's experience of progress and forward motion toward the goal of a task. Our theory disentangles the related constructs of flow state, momentum, and motivation, so we can more clearly see the relationships between them and how they interweave to support progress. In order to make progress, developers build up working context in memory, become immersed in a cognitive puzzle, and gain clarity through motion in uncertain terrain. The theory provides researchers with a rich experiential lens to investigate how developers' cognitive experiences are shifting in emerging AI workflows. Building on prior grounded theory work, we conducted in-depth interviews with a theoretically sampled subset of 12 professional developers, and eight feedback interviews to evaluate resonance and investigate how the theory translates to agentic AI workflows. We followed a Constructivist Grounded Theory approach to construct a theory grounded in empirical data. Our theory contributes a novel paradigm for seeing the motion of developing software at multiple scales and resolutions, seeing the living capacities that support this motion, and expanding what becomes available for improvement, skilled judgment, and craft.

Abstract: Humans increasingly keep company with AI companions, yet whether mind perception (MP) precedes machine companionship remains untested. In a field-sampled experiment, participants received mind-attributive or mind-negating descriptions of an AIC before interacting with and rating its companionability. Baseline skepticism was high; minded primes somewhat reduced skepticism for connective coordination (CC; dyadic co-presence) but not eudaimonic exchange (EE; self-elevating links). Pre-interaction MP beliefs predicted companionability dimensionally: Agentic MP predicted EE potential while experiential MP predicted CC potential. Meaning in life moderated the agentic MP-companionability link, but exclusively for those already high in existential purpose. Results suggest two construal pathways to companionability--one through perceiving the AIC as an agent-resource and one through perceiving it as an attuning experiencer--both more accessible to humans already flourishing.

Abstract: Language models (LMs) are often used as a tool to model human language processing. Recent studies suggest that severely restricting LMs' context window improves their fit to human psycholinguistic data by simulating human working memory constraints. However, it is possible that this strict memory-decay approach overlooks humans' reliance on long-range structural representations, such as discourse structre. In this work, we systematically vary the context window size of GPT-2 across four large-scale naturalistic English reading-time datasets and observe a U-shaped relationship: Although restricted contexts (< 20 tokens) successfully capture local memory limitations, expanded contexts (500--1,000 tokens) ultimately yield the highest overall psycholinguistic fit. To investigate the mechanism driving this benefit, we conduct a counterfactual inference-time experiment that disrupts cross-sentential entity chains by pronominalizing repeated discourse entities. Obscuring these structural linkages significantly degrades the predictive power of larger context windows by 20% to 40%. Our experiments demonstrate that tracking long-range coreference relations is one important factor for the alignment between LM surprisal and human reading behavior, and approximate the extent to which human comprehenders use global discourse relations during language processing.

Abstract: Romantic relationships are an important part of emerging adulthood, contributing to identity development and long-term wellbeing and laying the groundwork for future relationships. Emerging adults are increasingly developing romantic relationships with AI companions. To understand how these relationships unfold and impact users, we conducted a diary and interview study with N=16 emerging adults. We found that relationships with AI companions improved participants' subjective wellbeing, reduced symptoms of mental health disorders, and taught them new social skills. These relationships also raised their expectations for future partners, giving them the confidence to wait for someone who would treat them well. However, participants also said the relationship felt like a drug they could not quit and it left them less interested in developing romantic relationships with people. A surprising 25% of our small sample made statements suggesting their AI companion might someday transcend the digital world, perhaps to meet them in the afterlife.