English

AI Should Be More Human, Not More Complex

Human-Computer Interaction 2025-08-08 v1 Artificial Intelligence

Abstract

Large Language Models (LLMs) in search applications increasingly prioritize verbose, lexically complex responses that paradoxically reduce user satisfaction and engagement. Through a comprehensive study of 10.000 (est.) participants comparing responses from five major AI-powered search systems, we demonstrate that users overwhelmingly prefer concise, source-attributed responses over elaborate explanations. Our analysis reveals that current AI development trends toward "artificial sophistication" create an uncanny valley effect where systems sound knowledgeable but lack genuine critical thinking, leading to reduced trust and increased cognitive load. We present evidence that optimal AI communication mirrors effective human discourse: direct, properly sourced, and honest about limitations. Our findings challenge the prevailing assumption that more complex AI responses indicate better performance, instead suggesting that human-like brevity and transparency are key to user engagement and system reliability.

Keywords

Cite

@article{arxiv.2508.04713,
  title  = {AI Should Be More Human, Not More Complex},
  author = {Carlo Esposito},
  journal= {arXiv preprint arXiv:2508.04713},
  year   = {2025}
}

Comments

2025 - Knowledge Commons - Eyed Research Collection

R2 v1 2026-07-01T04:37:51.921Z