Beyond Tools: Understanding How Heavy Users Integrate LLMs into Everyday Tasks and Decision-Making

TL;DR

This study explores how heavy users incorporate large language models into daily decision-making, revealing complex interaction patterns and diverse perceptions that go beyond simple tool delegation.

Contribution

It provides qualitative insights into heavy LLM users' integration strategies and perceptions, highlighting nuanced interaction patterns in everyday decision-making.

Findings

Users employ LLMs for social validation and self-regulation.

Heavy users view LLMs as rational entities or human-like decision-makers.

Interaction patterns are more complex than simple delegation.

Abstract

Large language models (LLMs) are increasingly used for both everyday and specialized tasks. While HCI research focuses on domain-specific applications, little is known about how heavy users integrate LLMs into everyday decision-making. Through qualitative interviews with heavy LLM users (n=7) who employ these systems for both intuitive and analytical thinking tasks, our findings show that participants use LLMs for social validation, self-regulation, and interpersonal guidance, seeking to build self-confidence and optimize cognitive resources. These users viewed LLMs either as rational, consistent entities or average human decision-makers. Our findings suggest that heavy LLM users develop nuanced interaction patterns beyond simple delegation, highlighting the need to reconsider how we study LLM integration in decision-making processes.