Nicholas Weber

Katelyn Xiaoying Mei, Robert Wolfe, Nicholas Weber et al. · uw

xAI's large language model, Grok, is called by millions of people each week on the social media platform X. Prior work characterizing how large language models are used has focused on private, one-on-one interactions. Grok's deployment on X represents a major departure from this setting, with interactions occurring in a public social space. In this paper, we systematically sample three months of interaction data to investigate how, when, and to what effect Grok is used on X. At the platform level, we find that Grok responds to 62% of requests, that the majority (51%) are in English, and that engagement is low, with half of Grok's responses receiving 20 or fewer views after 48 hours. We also inductively build a taxonomy of 10 roles that LLMs play in mediating social interactions and use these roles to analyze 41,735 interactions with Grok on X. We find that Grok most often serves as an information provider but, in contrast to LLM use in private one-on-one settings, also takes on roles related to dispute management, such as truth arbiter, advocate, and adversary. Finally, we characterize the population of X users who prompted Grok and find that their self-expressed interests are closely related to the roles the model assumes in the corresponding interactions. Our findings provide an initial quantitative description of human-AI interactions on X, and a broader understanding of the diverse roles that large language models might play in our online social spaces.

Maryam Amirizaniani, Benjamin Charles Germain Lee, Jevin West et al.

Effective personalized question answering (PQA) in language models requires grounding responses in the user's underlying intent, where intent refers to the implicit ``why'' behind a query beyond its explicit wording. However, existing approaches to intent-aware personalization rely on multi-turn conversational context or rich user profiles, and do not explicitly model user intent during the reasoning process. This limits their effectiveness in single-turn settings, where the user's latent goal must be inferred from minimal input and integrated into the thinking and reasoning process. To bridge this gap, we propose IAP (Intent-Aware Personalization), a reinforcement learning framework that trains models to infer implicit user intent directly from a single-turn question and incorporate it into thinking steps through a tag-based schema for generating personalized, intent-grounded answers. By optimizing intent-aware answer trajectories under a personalized reward function, IAP reinforces generation paths that make implicit user intent explicit and produce responses that better align with the user's underlying goal. Through experiments on the LaMP-QA benchmark across six models, IAP consistently outperforms all baselines, achieving an average macro-score gain of around 7.5\% over the strongest competitor, demonstrating that modeling implicit user intent within the training objective is a promising direction for PQA.

Daniel S. Katz, Jeffrey C. Carver, Neil P. Chue Hong et al.

Research software is essential to modern research, but it requires ongoing human effort to sustain: to continually adapt to changes in dependencies, to fix bugs, and to add new features. Software sustainability institutes, amongst others, develop, maintain, and disseminate best practices for research software sustainability, and build community around them. These practices can both reduce the amount of effort that is needed and create an environment where the effort is appreciated and rewarded. The UK SSI is such an institute, and the US URSSI and the Australian AuSSI are planning to become institutes, and this extended abstract discusses them and the strengths and weaknesses of this approach.

Nicholas Weber, Andrea Thomer, Michael Twidale

This position paper is aimed at providing some history and provocations for the use of an ecological metaphor to describe software development environments. We do not claim that the ecological metaphor is the best or only way of looking at software - rather we want to ask if it can indeed be a productive and thought provoking one.