arXiv AI By Sales G. Aribe Jr., Louie Jay S. Labastida

The Vibe Shift in Software Engineering: Evaluating AI-Led Conversational Programming for Performance, Cognition, and Responsible Adoption

Read the original on arXiv AI →

The study evaluates Vibe Coding, an AI‑led conversational programming paradigm that lets developers generate software via natural‑language interaction with large language models. In a mixed‑methods experiment with 30 participants, Vibe Coding improved development efficiency—reducing task completion time by 27% versus traditional coding and 12% versus AI‑assisted coding—while also yielding a good usability score (SUS = 71.4) and moderate cognitive workload (NASA‑TLX = 55.5). However, the gains came with trade‑offs: lower maintainability indices, higher security vulnerabilities, and themes of trust calibration, loss of control, and prompt‑engineering strategy emerged, leading the authors to propose a three‑pillar framework for responsible adoption.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

arXiv AI
Sep 4

The Psychological Costs of Artificial Intelligence Adoption in Software Engineering

The article examines the psychological costs that software professionals face when organizations adopt artificial intelligence (AI) in software engineering workflows. Through a case study involving 21 interviews at a large software development services company, the authors identify several negative impacts—accountability anxiety, craft identity disruption, erosion of meaning and satisfaction, increased cognitive load and workload, and uncertainty distress. They also describe how practitioners cope by restoring control, adopting protective adaptations, or absorbing the costs, arguing that AI adoption should be viewed as a human transition rather than merely a technological or organizational change.

By Adam Alami, Elda Paja, Abhishek Tiwari
arXiv AI
Jun 9

Lost in the Flow with Code Talkers: Unveiling the Instruction-Tuning Tax of Large Language Models in Code Tasks

arXiv:2606. 08676v1 Announce Type: cross Abstract: AI coding assistants have significantly improved developer productivity by automatically suggesting code that aligns with user intent, and many of these tools are now integrated directly into Integrated Development Environments (IDEs).

By Shi Ying Chang, Chiok Yew Ho, Yichen Li, Yintong Huo
arXiv AI
Jun 2

Vibe-driven model-based engineering

arXiv:2604. 10645v2 Announce Type: replace-cross Abstract: There is a pressing need for better development methods and tools to keep up with the growing demand and increasing complexity of new software systems.

By Jordi Cabot