Asking Grok: AI-Assisted Sensemaking in Social Media Conversations

2026-05-19

AI Summary

This study addresses a critical gap in understanding how users interact with large language model–powered AI assistants within authentic social media environments, particularly concerning information verification and sensemaking. By analyzing 169,137 posts invoking the Grok AI assistant on X (formerly Twitter) and cross-referencing user behavior with the Community Notes crowdsourced fact-checking system, this work provides the first large-scale empirical evidence that AI assistants serve an early, supplementary role in sensemaking rather than displacing established verification mechanisms. The findings reveal that Grok is predominantly used for reactive information retrieval and validation, exhibiting broad but shallow engagement—76.8% of users employed it only once—and tends to appear during the early stages of high-visibility content dissemination, with limited overlap in coverage relative to Community Notes.

Abstract

LLM-powered AI assistants (e.g., Grok) are increasingly integrated into social media platforms, where they help explain content, provide context, and verify claims directly within conversation threads. While prior research has examined the accuracy of LLMs for fact-checking, little is known about how people interact with such systems in real-world social media environments. In this study, we empirically analyze user interactions with the AI assistant Grok on the social media platform X. Using a large-scale dataset consisting of 169,137 posts invoking Grok, we examine the types of requests directed at the AI assistant and the contexts in which it is used. We find that Grok is primarily invoked reactively to obtain or verify information. Although responses appear quickly, they typically only reach small audiences. Adoption is widespread but shallow, with 76.8% of users invoking Grok just once. We further examine how these interactions relate to Community Notes, X's community-based fact-checking system. While overlap between both systems is limited, it concentrates on verification-oriented and high-visibility content. Grok interactions typically occur earlier and do not predict subsequent correction activity. Together, these findings suggest that AI assistants function as an early complementary layer of sensemaking on social media rather than a replacement for crowd-based fact-checking systems.

Problem

• AI assistant
• social media
• sensemaking
• fact-checking
• user interaction

Innovation

• AI-assisted sensemaking
• LLM-powered assistants
• social media verification
• Grok
• Community Notes