Walking the Tightrope of LLMs for Software Development: A Practitioners' Perspective

TL;DR

Problem: Understanding how LLM-based tools affect software practitioners and how to balance their productive benefits with potential negative consequences. Approach: An empirical qualitative study using socio-technical grounded theory, based on 22 interviews across three rounds and analyzed via open coding, constant comparison, and memoing. Contributions: A four-level taxonomy of benefits and disadvantages (individual, team, organization, society), best-practice recommendations for balanced adoption, and implications for software-team leadership and IT management. Significance: Provides evidence to guide responsible LLM adoption in industry, preserving developer skills, mentorship, security, and trust while enabling faster prototyping and flow.

Abstract

Background: Large Language Models emerged with the potential of provoking a revolution in software development (e.g., automating processes, workforce transformation). Although studies have started to investigate the perceived impact of LLMs for software development, there is a need for empirical studies to comprehend how to balance forward and backward effects of using LLMs. Objective: We investigated how LLMs impact software development and how to manage the impact from a software developer's perspective. Method: We conducted 22 interviews with software practitioners across 3 rounds of data collection and analysis, between October (2024) and September (2025). We employed socio-technical grounded theory (STGT) for data analysis to rigorously analyse interview participants' responses. Results: We identified the benefits (e.g., maintain software development flow, improve developers' mental model, and foster entrepreneurship) and disadvantages (e.g., negative impact on developers' personality and damage to developers' reputation) of using LLMs at individual, team, organisation, and society levels; as well as best practices on how to adopt LLMs. Conclusion: Critically, we present the trade-offs that software practitioners, teams, and organisations face in working with LLMs. Our findings are particularly useful for software team leaders and IT managers to assess the viability of LLMs within their specific context.

Figures (5)

• Figure 1: Study methodology.
• Figure 2: Emergence of the category "Impact on using LLMs" from raw data → codes → concepts → subcategories → category through constant comparison.
• Figure 3: Main Benefits of using LLMs at the Individual (Software Practitioner) Level.
• Figure 4: Main Disadvantages of using LLMs at the Individual (Software Practitioner) Level.
• Figure 5: Comparison with related work focused on benefits and disadvantages. The colored bars represent the overlap with existing literature barke:2023banh2:2025liang:2025li:2024, and empty bars indicate new findings.