Who's Really Writing the Code? Study Questions AI Programming Authorship
New research shows that when programmers use AI coding assistants, neither human nor machine is truly in control—the code emerges from constant back-and-forth interaction between both. The finding challenges how companies should assign responsibility for buggy or biased code, and raises urgent questions about liability and ownership in AI-assisted development.
Originaltitel: Vibe Coding Entanglements – Repositioning Boundaries of Intention, Authorship, and Responsibility in Programming with Generative AI
Vibe Coding is conceptualised as a co-constituted form of programming through which humans and AI tools engage in the mutual shaping of a piece of code. Using design provocations in the form of three different programming assistants, we examine how intentions, control, and outcomes emerge through mutual shaping between programmers, AI-tools, code, and visual sketches. The analysis reveals a set of interrelated themes that foreground the tensions that emerge in participants’ interactions with the programming assistants. A set of design configurations is identified in relation to how these programming processes unfold. We use this to outline how vibe coding can be understood as a decentered form of programming that emphasises the mutual co-constitution and shifting boundaries among humans and AI. We argue that this suggests a reconfiguration of how AI-based programming is understood - emphasising the evolving, co-creative interactions in which intention and control are mutually shaped.