Trust Dynamics in AI-Assisted Development: Definitions, Factors, and Implications
Authors:
- 26 April 2025
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1678-1690
Abstract
Software developers increasingly rely on AI code generation utilities. To ensure that “good” code is accepted into the code base and “bad” code is rejected, developers must know when to trust an AI suggestion. Understanding how developers build this intuition is crucial to enhancing developer-AI collaborative programming. In this paper, we seek to understand how developers (1) define and (2) evaluate the trustworthiness of a code suggestion and (3) how trust evolves when using AI code assistants. To answer these questions, we conducted a mixed method study consisting of an in-depth exploratory survey with (n=29) developers followed by an observation study (n=10). We found that comprehensibility and perceived correctness were the most frequently used factors to evaluate code suggestion trustworthiness. However, the gap in developers' definition and evaluation of trust points to a lack of support for evaluating trustworthy code in real-time. We also found that developers often alter their trust decisions, keeping only 52% of original suggestions. Based on these findings, we extracted four guidelines to enhance developer-AI interactions. We validated the guidelines through a survey with (n=7) domain experts and survey members (n=8). We discuss the validated guidelines, how to apply them, and tools to help adopt them.Keywords
This publication has 59 references indexed in Scilit:
- GitHub Copilot AI pair programmer: Asset or Liability?Journal of Systems and Software, 2023
- Make Your Tools Sparkle with Trust: The PICSE Framework for Trust in Software Tools2023
- Statistical guarantees for sparse deep learningAStA Advances in Statistical Analysis, 2023
- Interpretable deep learning: interpretation, interpretability, trustworthiness, and beyondKnowledge and Information Systems, 2022
- The Mind Is a Powerful Place: How Showing Code Comprehensibility Metrics Influences Code Understanding2021
- The Next Frontier: AI We Can Really Trust2021
- In AI We Trust: Ethics, Artificial Intelligence, and ReliabilityScience and Engineering Ethics, 2020
- Measuring the Cognitive Load of Software Developers: A Systematic Mapping Study2019
- Artificial Intelligence and Black‐Box Medical Decisions: Accuracy versus ExplainabilityHastings Center Report, 2019
- Why scientists should learn to program in PythonPowder Diffraction, 2014