FIELD NOTES
正在形成的判断Judgments in progress
这些文章记录项目中的判断、失败和修正。我会根据新的实践与证据更新结论。These notes record decisions, failures, and revisions from my projects. I update the conclusions when new evidence changes them.
从这里认识我 · 置顶导读Start here · Reading guide
我不是程序员，但我开始把问题做成产品I'm not a programmer, but I've started turning problems into products
一个经济学背景的非技术创作者，如何从真实生活问题出发，借助 AI 和 Vibe Coding 开始构建、验证与交付。How a builder with an economics background began using AI and Vibe Coding to build, test, and deliver ideas rooted in everyday problems.
阅读导读 ↗Read the guide ↗按文章分类筛选Filter notes by category
21 篇笔记21 notes
造物手记Building Notes
从收藏灵感到动手实验：一个空间作品集的诞生From Saved Inspiration to a Hands-On Experiment: The Birth of a Spatial Portfolio
收藏了很多设计网站之后，我把一句「如果作品集不只是整齐排列的卡片呢？」做成了一个可交互的空间作品集实验：空间探索 + 网格浏览，以及过程中关于设计判断、移动端与 AI Coding 的几点新认识。After collecting design websites for months, I turned one question — what if a portfolio wasn't a neat grid of cards? — into an interactive spatial portfolio experiment: spatial exploration plus grid browsing, and a few new understandings about design judgment, mobile, and AI coding.
产品思考Product Thinking
词不达意，也是一种浪漫When Words Fall Short, It Is a Kind of Romance
AFTERWORDS v0.4 设计手记：由一首喜欢的歌和「词不达意」这个词出发，聊聊为什么表达不需要完美，以及一座小邮局为什么要给没说清楚的话留一个位置。AFTERWORDS v0.4 design note: starting from a favorite song and the idiom 「词不达意」 — words falling short — on why expression does not need to be perfect, and why a little post office should keep a place for the things we never quite say.
造物手记Building Notes
从「我喜欢你」到一座不存在的小邮局From “I like you” to a post office that doesn't exist yet
一次关于语言、情绪、交互设计与数字明信片的浪漫实验：从收集 32 种语言的「我喜欢你」，到把表达的主动权交还给使用者。A romantic little experiment about language, mood, interaction design and digital postcards: from collecting “I like you” in 32 languages to handing the power of expression back to the writer.
造物手记Building Notes
AI 画得很可爱，但为什么不像我？The AI Made It Cute — But Why Doesn't It Look Like Me?
从一张 Q 版头像出发的小实验：好看不等于像我，风格统一不等于人物一致，以及怎样把反复试错沉淀成一套能和我一起变化的视觉语言。I used everyday photos to design a chibi avatar that felt like me, then tried it in a 52-pixel crop.
命运观察所Fate Observatory
从算命到 MBTI：我们为什么总想给自己找一个解释？From Fortune-Telling to MBTI: Why We Keep Looking for an Explanation of Who We Are
从 AI 算命到 MBTI，这篇文章把命理系统、人格标签和 AI 生成的解释放在一起观察：我们为什么渴望一种关于自己的解释，“解释得很好”为什么不等于“解释得很对”，以及如何在面对未知时保留一点独立思考的空间。From AI fortune-telling to MBTI, this piece puts destiny systems, personality labels, and AI-generated explanations side by side: why we keep longing for an explanation of ourselves, why a well-crafted explanation is not the same as a correct one, and how to keep a little room for independent thinking when facing the unknown.
生活与成长Life & Growth
多出来的一片叶子：我重新认识空间智能的过程The Extra Leaf: Rethinking Spatial Intelligence
从一只背面多出一片叶子的杯子开始，我重新理解了三维重建、空间理解与空间生成的边界，也重新审视了技术演示与真实产品之间的距离。Starting from a ceramic cup that grew an extra leaf on its back, I rebuilt my understanding of what 3D reconstruction, spatial understanding, and spatial generation can and cannot do — and of the distance between a technical demo and a real product.
社会观察Social Observation
当我们不断审视自己：外貌评价、社会比较与 AI 时代的自我认知When We Keep Examining Ourselves: Appearance, Social Comparison, and Self-Knowledge in the Age of AI
从自拍、点赞和用 AI 分析外貌的日常现象出发，借助镜中自我、社会比较、客体化等理论，讨论外部评价如何影响自我认知，以及为什么定义自己的权力应该留在自己手里。Starting from everyday moments — selfies, likes, and asking AI to analyze our faces — this piece draws on the looking-glass self, social comparison, and objectification theory to explore how external evaluation shapes self-knowledge, and why the power to define ourselves should stay in our own hands.
产品思考Product Thinking
当 AI 开始发光：从 iPhone 17 和 vivo 的一次对话说起When AI Begins to Glow: A Conversation That Started with iPhone 17 and vivo
从 iPhone 17 与 vivo 光效的一次闲聊出发，梳理手机 AI 视觉反馈的演变：谁更早、为什么 AI 开始发光、以及光效怎样才算真的有用。A casual comparison between iPhone 17 and vivo sent me through the evolution of visual feedback in phone AI: who did it first, why assistants started glowing, and when glow actually helps.
产品思考Product Thinking
为什么有人愿意买一台可以自己修的电脑和手机？Why Would Anyone Buy a Laptop and a Phone They Can Repair Themselves?
一次偶然的交流，让我开始研究 Framework 和 Fairphone：它们怎么设计、怎样赚钱、是否真的环保，以及中国为什么少见这样的产品。A chance conversation sent me down the rabbit hole of Framework and Fairphone: how they're designed, how they make money, whether they're truly sustainable, and why China has few counterparts.
造物手记Building Notes
从像素级复刻到风格蒸馏：一个 UI Skill 是怎样被做出来的From Pixel-Perfect Cloning to Style Distillation: How a UI Skill Was Built
一次把模糊审美变成可复用设计规则的实验：从像素级复刻到风格蒸馏，再到 Style Lab 与截图验收。An experiment in turning vague taste into reusable design rules — from pixel-perfect cloning to style distillation, a Style Lab, and screenshot-based acceptance.
生活与成长Life & Growth
AI 能写出我看不懂的代码，这算我的能力吗？If AI writes code I can't understand, does that count as my ability?
关于 Vibe Coding、能力边界，以及一个非技术背景者的自我怀疑。On Vibe Coding, the limits of my abilities, and the self-doubt of someone without a technical background.
产品思考Product Thinking
如果汽车可以自动驾驶，为什么自行车不行？If cars can drive themselves, why can't bicycles?
从一次骑行开始，关于 AI、世界模型和未来交通的一些不成熟思考。Some tentative thoughts about AI, world models, and the future of transport, beginning with a bike ride.
造物手记Building Notes
从一个赛博磕头的玩笑开始，我们认真做了一次 AI 公益A cyber-kowtow joke led us to take AI for good seriously
关于一个荒诞创意的诞生，以及我们如何重新理解技术、善意与真实需求。How an absurd idea began, and how it changed the way we think about technology, good intentions, and real needs.
生活与成长Life & Growth
参加 AI 活动之后，我想留下的不是打卡记录After AI events, what I want to keep is not check-in records
出门前先问自己想带回什么。到场不等于收获，把现场看到的东西带回自己的项目和选择里再验证一次，才是一次活动真正的后续。Before heading out, I ask what I want to bring back. Showing up is not the gain itself; carrying what I saw back into my own projects and choices, then testing it once more, is the real follow-up to an event.
生活与成长Life & Growth
可静可动，是一种怎样的工作节奏Finding a working rhythm with room for quiet and action
在高密度探索与安静沉淀之间，建立一种不靠持续亢奋、也不让思考停在原地的长期节奏。I am learning to move between intense exploration and quiet reflection, without depending on constant excitement or letting thought keep me from acting.
造物手记Building Notes
我关注黑客松，不是为了证明自己很厉害I don't follow hackathons to prove how good I am
对一个非传统技术背景的独立构建者来说，黑客松的意义不是熬夜和包装，而是用有限时间暴露判断、做出证据。As an independent builder without a traditional technical background, I use short deadlines to test my judgment and produce evidence, without treating lost sleep or a polished pitch as the goal.
产品思考Product Thinking
AI 产品真正稀缺的，还是功能吗？Are features still what AI products lack?
当生成、对话和 Agent 功能越来越容易复制，真正难以复制的是问题判断、系统边界、验证闭环和信任。As chat, generation, and agent features become easier to copy, I find the harder work in problem judgment, system boundaries, verification, and trust.
产品思考Product Thinking
为什么我越来越在意普通人的问题Why everyday problems matter more and more to me
从适老手机、女性健康到家庭照护：那些不宏大、却反复消耗人的问题，为什么值得被认真设计。From age-friendly phone tools to women's health and family care, I keep returning to problems that draw little attention but wear people down over time.
产品思考Product Thinking
隐私约束怎样改变求职工具的产品设计How privacy constraints reshape a job-search product
简历、岗位偏好和求职记录都带有个人信息。隐私要求会影响数据存储、模型调用和默认交互，也会改变产品范围。Résumés, job preferences, and search history contain personal information. Privacy requirements affect storage, model calls, default interactions, and product scope.
产品思考Product Thinking
用户不该先学会配合 AIUsers should not have to learn how to accommodate AI
当用户需要理解提示词、模型脾气和失败方式时，产品把系统复杂度转嫁给了使用者。好的交互会替用户管理这些不确定性。When users must understand prompts, model quirks, and failure modes, the product has transferred system complexity to them.
产品思考Product Thinking
AI 把实现变快以后，问题定义更重要了Problem framing matters more when AI makes building faster
生成代码缩短了实现时间，却没有替我们判断用户、场景和成功标准。这篇文章记录我在动手前怎样检查一个问题是否值得做。Code generation shortens implementation time. It cannot decide who the user is, where the problem appears, or which result would count as success.