Human-AI Collaboration in Coding: A Trust Perspective

Abstract

Generative AI (GenAI) is transforming software development and Computer Science (CS) education, raising critical questions about trust in human-AI collaboration. This paper examines trust in GenAI from interdisciplinary perspectives, assessing existing trust frameworks and their applicability. Seemingly contradictory definitions and approaches are discussed and a solution is presented that could resolve the contradictions. We explore how trust affects adoption in education and software development, reviewing measurement approaches and implications for calibrated trust. Our findings highlight the gap between theoretical trust and practical reliance, contributing to the discourse on AI usability and integration