Why Human Guidance Matters in Collaborative Vibe Coding
Not on the map. Why?
Abstract (arXiv)
Writing code has been one of the most transformative ways for human societies to translate abstract ideas into tangible technologies. Modern AI is changing this process by enabling experts and non-experts alike to generate code without actually writing it, instead using natural language instructions or "vibe coding". While increasingly popular, the impact of vibe coding on productivity and collaboration, and the role of humans in this process, remains unclear. Here, we introduce a controlled experimental framework for studying collaborative vibe coding and use it to compare human-led, AI-led, and hybrid groups. Across 20 experiments involving 737 human participants, we show that people provide uniquely effective high-level instructions for vibe coding, whereas AI-provided instructions often result in performance collapse. We further demonstrate that hybrid systems perform best when humans lead by providing instructions while evaluation is delegated to AI. Although AI systems can rapidly optimize performance for specific tasks, our work highlights the importance of human guidance in shaping future hybrid societies.
Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 28 of its 80 references that are in the map. First posted on arXiv 11 Feb 2026.
Builds on
28 of 80 references.
References · 28
- 2018UMAP: Uniform Manifold Approximation and Projection for Dimension Reductioncited by 2,841
- 2025OpenAI GPT-5 System Cardcited by 910
- 2024A Survey on Large Language Models for Code Generationcited by 646
- 2020Does the Whole Exceed its Parts? The Effect of AI Explanations on Complementary Team Performancecited by 396
- 2023Getting aligned on representational alignmentcited by 142
- 2024Building Machines that Learn and Think with Peoplecited by 73
- 2022Designing Creative AI Partners with COFI: A Framework for Modeling Interaction in Human-AI Co-Creative Systemscited by 59
- 2023Large Language Model-Aware In-Context Learning for Code Generationcited by 42
- 2025Feedback Descent: Open-Ended Text Optimization via Pairwise Comparisoncited by 42
- 2025Vibe Coding vs. Agentic Coding: Fundamentals and Practical Implications of Agentic AIcited by 39
- 2024Automatic Programming: Large Language Models and Beyondcited by 35
- 2023Natural Language Generation and Understanding of Big Code for AI-Assisted Programming: A Reviewcited by 32
16 more
- 2025Pragmatics in the Era of Large Language Models: A Survey on Datasets, Evaluation, Opportunities and Challengescited by 31
- 2020Gibbs Sampling with Peoplecited by 28
- 2025Vibe Coding in Practice: Motivations, Challenges, and a Future Outlook -- a Grey Literature Reviewcited by 28
- 2025AI Agentic Programming: A Survey of Techniques, Challenges, and Opportunitiescited by 26
- 2024AutoDev: Automated AI-Driven Developmentcited by 24
- 2024Language Models in Dialogue: Conversational Maxims for Human-AI Interactionscited by 21
- 2025Measuring and mitigating overreliance to build human-compatible AIcited by 9
- 2025When Should We Orchestrate Multiple Agents?cited by 7
- 2025Using LLMs to Advance the Cognitive Science of Collectivescited by 6
- 2025The Dynamics of Collective Creativity in Human-AI Hybrid Societiescited by 5
- 2025Exploring Student-AI Interactions in Vibe Codingcited by 4
- 2023Overinformative Question Answering by Humans and Machinescited by 3
- 2024Characterizing Similarities and Divergences in Conversational Tones in Humans and LLMs by Sampling with Peoplecited by 3
- 2025Identifying, Evaluating, and Mitigating Risks of AI Thought Partnershipscited by 3
- 2025Revisiting Rogers' Paradox in the Context of Human-AI Interactioncited by 2
- 2025Characterizing the Interaction of Cultural Evolution Mechanisms in Experimental Social Networkscited by 2
Built on by
Citing papers per year: 2026: 3.
3 papers.