用思维脚本防新手编程依赖AI，避免学不会改代码。
Mitigating "Epistemic Debt" in Generative AI-Scaffolded Novice Programming using Metacognitive Scripts
- 设计实时解释门机制，强制AI生成代码前必须讲清逻辑。
- 无限制用AI者77%无法独立维护代码，有引导的仅39%失败。
- 适合想教学生真正会编程而非只会调AI的人看。
大型语言模型的普及催生了'氛围编程'，新手更关注语义意图而非语法实现。缺乏教学引导时，这种模式与认知技能习得严重脱节。基于Kirschner的认知外挂与外包区分，不受限的AI会促使新手外包本应内化的认知负荷，积累‘认识债务’，形成功能强但无法纠错的脆弱开发者。我们通过78名参与者（来自Prolific和UserInterviews.com）的对照实验验证此观点，使用定制Cursor IDE插件结合Claude 3.5 Sonnet，在手动、无限制AI、受控AI三种条件下进行测试。受控组采用新型‘解释门’——即实时由大模型担任裁判，强制执行‘讲解后再集成’协议。结果表明：两组AI使用者在功能完成度上显著优于手动组（p < .001），且彼此无差异（p = .64）；但在后续30分钟无AI维护任务中，无限制组失败率达77%，受控组仅为39%。定性分析显示，成功的新手会自发建立辅助机制，把AI当作顾问而非承包商。研究呼吁未来学习系统需引入元认知阻力，防止大量不可维护代码的产生。代码复现包：https://github.com/sreecharansankaranarayanan/vibecheck
原文摘要 · Abstract (English)
The democratization of Large Language Models has given rise to vibe coding, where novice programmers prioritize semantic intent over syntactic implementation. Without pedagogical guardrails, we argue this is fundamentally misaligned with cognitive skill acquisition. Drawing on Kirschner's distinction between cognitive offloading and outsourcing, unrestricted AI encourages novices to outsource the intrinsic cognitive load required for schema formation rather than merely offloading extraneous load. This accumulation of epistemic debt creates fragile experts: developers whose high functional utility masks critically low corrective competence. To quantify and mitigate this debt, we conducted a between-subjects experiment (N=78) using a custom Cursor IDE plugin backed by Claude 3.5 Sonnet. Participants were recruited via Prolific and UserInterviews.com to represent AI-native learners. We compared three conditions: manual (control), unrestricted AI (outsourcing), and scaffolded AI (offloading). The scaffolded condition employed a novel Explanation Gate -- a real-time LLM-as-a-Judge framework enforcing a teach-back protocol before generated code could be integrated. Results reveal a collapse of competence: both AI groups significantly outperformed the manual control on functional utility (p < .001) and did not differ from each other (p = .64), yet unrestricted AI users suffered a 77% failure rate on a subsequent 30-minute AI-blackout maintenance task, vs. only 39% in the scaffolded group. Qualitative analysis suggests successful vibe coders naturally self-scaffold, treating AI as a consultant rather than a contractor. We discuss implications for AI-generated software maintainability and propose that future learning systems must enforce metacognitive friction to prevent mass production of unmaintainable code. Replication package: https://github.com/sreecharansankaranarayanan/vibecheck
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。