🤖 AI Summary
This study addresses the issue of AI-assisted coding shifting software complexity to the requirements level by proposing a specification-driven development paradigm and unveiling the "Specification Paradox": as AI capabilities advance, reliance on high-quality human specifications intensifies. Through automated assessment methods for bias and specification debt, this research reestablishes the centrality of requirements engineering in the AI era. Results indicate that the crux of future software engineering has shifted from code generation to human capabilities in correct specification and evaluation. By elucidating the challenges of requirements engineering within emerging human-AI collaboration paradigms, this work provides both theoretical foundations and practical pathways for managing software development complexity in the age of artificial intelligence.
📝 Abstract
The growing adoption of Large Language Models (LLMs) in Software Engineering has reinforced the expectation that coding activities can be largely automated. However, this perception may represent yet another historical search for a solution capable of eliminating the inherent challenges of software development. This article discusses the transition from a code-centered paradigm to Specification-Driven Development. We argue that artificial intelligence reduces some of the effort associated with writing source code, but it does not eliminate the complexity of developing professional software systems. Instead, it shifts this complexity toward domain understanding, requirements elicitation, specification development, validation, maintenance, and software evolution. Building on this perspective, we discuss the renewed centrality of Requirements Engineering, considering its implications for productivity and software quality, as well as risks associated with automation bias, ambiguity propagation, Specification Overfitting, and the accumulation of Specification Debt. Finally, we propose the Specification Paradox: the more capable artificial intelligence systems become at automatically generating software, the greater the dependence on correct, complete, verifiable, and explainable human-produced specifications. We conclude that the future of Software Engineering will depend not only on machines' ability to generate code, but also on humans' ability to correctly specify, evaluate, and evolve what is intended to be built.