Grok in the Wild: Characterizing the Roles and Uses of Large Language Models on Social Media

2026-02-11

AI Summary

This study addresses the lack of systematic understanding regarding the usage patterns, functional roles, and societal impact of large language models (LLMs) in public social media spaces. Drawing on over three months of Grok interaction logs from the X platform—comprising tens of thousands of exchanges—and employing large-scale sampling, inductive content analysis, and user-profile linkage, this work proposes the first taxonomy categorizing LLMs into ten distinct roles within public discourse. The findings reveal that Grok predominantly functions as an information provider while frequently assuming roles such as truth arbiter, advocate, and antagonist, thereby uncovering novel applications in non-traditional tasks like dispute mediation and challenging prior research paradigms centered on private conversational contexts. Quantitative results indicate that 51% of interactions occurred in English, 62% of user requests received responses, yet nearly half of all replies garnered fewer than 20 views within 48 hours.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Natural Language Processing: (Large) Language Models
• Cognitive Modeling & Cognitive Systems: Social Cognition And Interaction

Application Category

• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Social Networks and Social Media: Generative AI / large language models and their impact on social systems

Abstract

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.

Problem

• large language models
• social media
• human-AI interaction
• public interaction
• LLM roles

Innovation

• large language models
• social media
• human-AI interaction
• role taxonomy
• public deployment