# How AI Impacts Skill Formation

arXiv: https://arxiv.org/abs/2601.20245 · HTML: https://mlsanity.com/paper/2601.20245/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 44 references that are in the map.
- First posted on arXiv 28 Jan 2026.

## Builds on (most cited first, 14 of 14)

- [The Impact of AI on Developer Productivity: Evidence from GitHub Copilot](https://mlsanity.com/paper/2302.06590/) (2023)
- [Measuring Progress on Scalable Oversight for Large Language Models](https://mlsanity.com/paper/2211.03540/) (2022)
- [Explanations Can Reduce Overreliance on AI Systems During Decision-Making](https://mlsanity.com/paper/2212.06823/) (2022)
- [Measuring the Impact of Early-2025 AI on Experienced Open-Source Developer Productivity](https://mlsanity.com/paper/2507.09089/) (2025)
- [On scalable oversight with weak LLMs judging strong LLMs](https://mlsanity.com/paper/2407.04622/) (2024)
- [Which Economic Tasks are Performed with AI? Evidence from Millions of Claude Conversations](https://mlsanity.com/paper/2503.04761/) (2025)
- [Clio: Privacy-Preserving Insights into Real-World AI Use](https://mlsanity.com/paper/2412.13678/) (2024)
- [AI Hallucinations: A Misnomer Worth Clarifying](https://mlsanity.com/paper/2401.06796/) (2024)
- [Rocks Coding, Not Development--A Human-Centric, Experimental Evaluation of LLM-Supported SE Tasks](https://mlsanity.com/paper/2402.05650/) (2024)
- [Developer Experiences with a Contextualized AI Coding Assistant: Usability, Expectations, and Outcomes](https://mlsanity.com/paper/2311.18452/) (2023)
- [Dissenting Explanations: Leveraging Disagreement to Reduce Model Overreliance](https://mlsanity.com/paper/2307.07636/) (2023)
- [Societal Impacts Research Requires Benchmarks for Creative Composition Tasks](https://mlsanity.com/paper/2504.06549/) (2025)
- [Experiential Learning Approach for Software Engineering Courses at Higher Education Level](https://mlsanity.com/paper/2012.14178/) (2020)
- [Code Interviews: Design and Evaluation of a More Authentic Assessment for Introductory Programming Assignments](https://mlsanity.com/paper/2410.01010/) (2024)

## Built on by (most cited first, 24 of 24)

- [Dive into Claude Code: The Design Space of Today's and Future AI Agent Systems](https://mlsanity.com/paper/2604.14228/) (2026)
- [AI Assistance Reduces Persistence and Hurts Independent Performance](https://mlsanity.com/paper/2604.04721/) (2026)
- [The Augmentation Trap: AI Productivity and the Cost of Cognitive Offloading](https://mlsanity.com/paper/2604.03501/) (2026)
- [Reflections and New Directions for Human-Centered Large Language Models](https://mlsanity.com/paper/2605.06901/) (2026)
- [Human-AI Productivity Paradoxes: Modeling the Interplay of Skill, Effort, and AI Assistance](https://mlsanity.com/paper/2605.11350/) (2026)
- [(Im)Paired Programming: Coding Agents Improve Productivity but Harm Understanding](https://mlsanity.com/paper/2607.26375/) (2026)
- [The Impact of AI Usage and Informativeness on Skill Development in Logical Reasoning](https://mlsanity.com/paper/2605.21695/) (2026)
- [Offloading Score: Measuring AI Reliance Through Counterfactual Workflows](https://mlsanity.com/paper/2605.29392/) (2026)
- [Human Capital, Not Model Benchmarks, Predicts Hybrid Intelligence in Forecasting](https://mlsanity.com/paper/2607.02467/) (2026)
- [Can AI Lower the Barrier to Cybersecurity? A Human-Centered Mixed-Methods Study of Novice CTF Learning](https://mlsanity.com/paper/2602.18172/) (2026)
- [Intellectual Stewardship: Re-adapting Human Minds for Creative Knowledge Work in the Age of AI](https://mlsanity.com/paper/2603.18117/) (2026)
- [Augment Engineering: A Methodology for Multi-Tool AI Orchestration Across Professional Domains](https://mlsanity.com/paper/2605.26146/) (2026)
- [Govern the Repository, Not the Agent: Measuring Ecosystem-Level Risk in AI-Native Software](https://mlsanity.com/paper/2606.28235/) (2026)
- [Managing the Human Fallback: Skill Investment Under Improving AI and Worker Mobility](https://mlsanity.com/paper/2606.29111/) (2026)
- [Agents That Teach: Towards Designing Incidental Learning Back into AI-Assisted Software Development](https://mlsanity.com/paper/2607.06101/) (2026)
- [Psychological Competence as a Missing Dimension in AI Evaluation](https://mlsanity.com/paper/2607.08285/) (2026)
- [Epistemic Transfer in AI-Assisted Verification: A Framework and Evaluation Protocol](https://mlsanity.com/paper/2608.08882/) (2026)
- [Position: AI Agents in Scientific Teams Should Be Studied as Human-Agent Systems](https://mlsanity.com/paper/2608.14667/) (2026)
- [Process-Constituted Intelligence: A Shared Criterion for Humans and Machines](https://mlsanity.com/paper/2608.16213/) (2026)
- [Assessment of Non-Institutional AI Tool Usage Among Clinicians](https://mlsanity.com/paper/2609.11990/) (2026)
- [Designing Against Deskilling: Metacognitive Feedback Reduces Cognitive Offloading to LLM Assistants](https://mlsanity.com/paper/2609.20143/) (2026)
- [Understanding Generative AI Use in Programming MOOCs: The Role of Course Context and Learner Characteristics](https://mlsanity.com/paper/2610.04447/) (2026)
- [Comprehension Audits to Mitigate Risks from Automated AI Research](https://mlsanity.com/paper/2610.10064/) (2026)
- [Code Understanding is a Bottleneck for Coding Agents](https://mlsanity.com/paper/2610.10610/) (2026)

## Abstract (arXiv)

AI assistance produces significant productivity gains across professional domains, particularly for novice workers. Yet how this assistance affects the development of skills required to effectively supervise AI remains unclear. Novice workers who rely heavily on AI to complete unfamiliar tasks may compromise their own skill acquisition in the process. We conduct randomized experiments to study how developers gained mastery of a new asynchronous programming library with and without the assistance of AI. We find that AI use impairs conceptual understanding, code reading, and debugging abilities, without delivering significant efficiency gains on average. Participants who fully delegated coding tasks showed some productivity improvements, but at the cost of learning the library. We identify six distinct AI interaction patterns, three of which involve cognitive engagement and preserve learning outcomes even when participants receive AI assistance. Our findings suggest that AI-enhanced productivity is not a shortcut to competence and AI assistance should be carefully adopted into workflows to preserve skill formation -- particularly in safety-critical domains.