# Why Human Guidance Matters in Collaborative Vibe Coding

arXiv: https://arxiv.org/abs/2602.10473 · HTML: https://mlsanity.com/paper/2602.10473/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 28 of its 80 references that are in the map.
- First posted on arXiv 11 Feb 2026.

## Builds on (most cited first, 28 of 28)

- [UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction](https://mlsanity.com/paper/1802.03426/) (2018)
- [OpenAI GPT-5 System Card](https://mlsanity.com/paper/2601.03267/) (2025)
- [A Survey on Large Language Models for Code Generation](https://mlsanity.com/paper/2406.00515/) (2024)
- [Does the Whole Exceed its Parts? The Effect of AI Explanations on Complementary Team Performance](https://mlsanity.com/paper/2006.14779/) (2020)
- [Getting aligned on representational alignment](https://mlsanity.com/paper/2310.13018/) (2023)
- [Building Machines that Learn and Think with People](https://mlsanity.com/paper/2408.03943/) (2024)
- [Designing Creative AI Partners with COFI: A Framework for Modeling Interaction in Human-AI Co-Creative Systems](https://mlsanity.com/paper/2204.07666/) (2022)
- [Feedback Descent: Open-Ended Text Optimization via Pairwise Comparison](https://mlsanity.com/paper/2511.07919/) (2025)
- [Large Language Model-Aware In-Context Learning for Code Generation](https://mlsanity.com/paper/2310.09748/) (2023)
- [Vibe Coding vs. Agentic Coding: Fundamentals and Practical Implications of Agentic AI](https://mlsanity.com/paper/2505.19443/) (2025)
- [Automatic Programming: Large Language Models and Beyond](https://mlsanity.com/paper/2405.02213/) (2024)
- [Natural Language Generation and Understanding of Big Code for AI-Assisted Programming: A Review](https://mlsanity.com/paper/2307.02503/) (2023)
- [Pragmatics in the Era of Large Language Models: A Survey on Datasets, Evaluation, Opportunities and Challenges](https://mlsanity.com/paper/2502.12378/) (2025)
- [Vibe Coding in Practice: Motivations, Challenges, and a Future Outlook -- a Grey Literature Review](https://mlsanity.com/paper/2510.00328/) (2025)
- [Gibbs Sampling with People](https://mlsanity.com/paper/2008.02595/) (2020)
- [AI Agentic Programming: A Survey of Techniques, Challenges, and Opportunities](https://mlsanity.com/paper/2508.11126/) (2025)
- [AutoDev: Automated AI-Driven Development](https://mlsanity.com/paper/2403.08299/) (2024)
- [Language Models in Dialogue: Conversational Maxims for Human-AI Interactions](https://mlsanity.com/paper/2403.15115/) (2024)
- [Measuring and mitigating overreliance to build human-compatible AI](https://mlsanity.com/paper/2509.08010/) (2025)
- [When Should We Orchestrate Multiple Agents?](https://mlsanity.com/paper/2503.13577/) (2025)
- [Using LLMs to Advance the Cognitive Science of Collectives](https://mlsanity.com/paper/2506.00052/) (2025)
- [The Dynamics of Collective Creativity in Human-AI Hybrid Societies](https://mlsanity.com/paper/2502.17962/) (2025)
- [Exploring Student-AI Interactions in Vibe Coding](https://mlsanity.com/paper/2507.22614/) (2025)
- [Overinformative Question Answering by Humans and Machines](https://mlsanity.com/paper/2305.07151/) (2023)
- [Characterizing Similarities and Divergences in Conversational Tones in Humans and LLMs by Sampling with People](https://mlsanity.com/paper/2406.04278/) (2024)
- [Identifying, Evaluating, and Mitigating Risks of AI Thought Partnerships](https://mlsanity.com/paper/2505.16899/) (2025)
- [Revisiting Rogers' Paradox in the Context of Human-AI Interaction](https://mlsanity.com/paper/2501.10476/) (2025)
- [Characterizing the Interaction of Cultural Evolution Mechanisms in Experimental Social Networks](https://mlsanity.com/paper/2502.12847/) (2025)

## Built on by (most cited first, 3 of 3)

- [(Im)Paired Programming: Coding Agents Improve Productivity but Harm Understanding](https://mlsanity.com/paper/2607.26375/) (2026)
- [VibeJam: A User Study Platform for Web Development with Agents](https://mlsanity.com/paper/2608.29889/) (2026)
- [Collective creativity in hybrid societies](https://mlsanity.com/paper/2609.02620/) (2026)

## 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.