feat(migration): complete WordPress migration and UX refinements
- Migrate historical posts, localized assets, and 103 comments - Colocate media into posts/<slug>/images/ and remove wp-content - Add native bilingual support for ai-can-change post (English default, /zh variant) - Support clean taxonomy routing (/category/:category and /tag/:tag) - Dynamically populate categories and tags in sitemap.xml - Fix header scroll padding/margin offsets for anchor and reference links - Constrain image and media widths to prevent content overflow - Redesign homepage recent posts to 4 compact editorial cards - Restore valid binary favicon.ico and high-res icon assets - Remove placeholder content and sample test comments
This commit is contained in:
Binary file not shown.
|
After Width: | Height: | Size: 8.5 MiB |
Binary file not shown.
|
After Width: | Height: | Size: 8.5 MiB |
BIN
Binary file not shown.
|
After Width: | Height: | Size: 1.3 MiB |
BIN
Binary file not shown.
|
After Width: | Height: | Size: 825 KiB |
Binary file not shown.
|
After Width: | Height: | Size: 36 KiB |
Binary file not shown.
|
After Width: | Height: | Size: 72 KiB |
@@ -1,26 +1,37 @@
|
||||
---
|
||||
title: "AI可以改变什么：为孩子编程与创造力"
|
||||
date: 2025-05-10
|
||||
author: "haopengzhan"
|
||||
title: "AI can change: Coding for kids"
|
||||
date: 2026-03-02
|
||||
author: "Pengzhan Hao"
|
||||
category: "Non-tech"
|
||||
tags: ["AI", "Parenting", "Education", "Kids"]
|
||||
excerpt: "当AI能够直接生成代码，我们应该如何引导下一代理解技术、培养解决真实问题的创造力？"
|
||||
cover: images/cover.svg
|
||||
lang: zh
|
||||
tags: ["AI Era","Diary","Family","Gemini","Teaching"]
|
||||
cover: "/posts-assets/ai-can-change-coding-for-kids/images/cover-en.png"
|
||||
lang: "en"
|
||||
excerpt: "Since the explosion of Large Language Models (LLMs), a wave of disruption has quietly swept through every industry. What does it mean for everyday life and parenting?"
|
||||
---
|
||||
Since the explosion of Large Language Models (LLMs), a wave of disruption has quietly swept through every industry. While it is impossible to list every sector currently in flux, the sheer volume of new demands from startups and the AI-driven overhauls of traditional businesses serve as constant reminders of the magnitude of this shift. However, unlike the macro-narrative of business-driven AI, the actual impact of LLMs on the average person remains somewhat elusive—even for programmers standing at the forefront of this change.
|
||||
|
||||
随着人工智能技术的迅猛普及，编程教育的门槛正在发生前所未有的变化。
|
||||
Two weeks ago, while taking care of my child alone, I noticed a letter-tracing worksheet she brought home from daycare. It hit me that she was starting to grasp the concept of "homework." In the United States, expecting a daycare to provide Chinese writing practice is almost a luxury. To help her build a foundational feel for writing Chinese characters, I decided to follow the pace of children growing up in China and create some practice sheets for her. After searching online, I found that most Chinese calligraphy worksheets are designed for older students or adults. For a child who can barely hold a pen steady, writing small characters is simply too challenging. I found a site called [E-Zitie](https://www.nqez.com/) that offered exactly what I needed: [large characters with stroke order guides](https://www.nqez.com/zitie-hanzibishunlizi.html). However, while the basic service is free, any customization requires a paid membership. Although the 38 RMB/year fee is negligible, the website’s UI felt like something from three generations ago, making me doubt its ability to meet my long-term needs.
|
||||
|
||||
过去，学习编程首先要克服繁琐的语法、编译器配置和环境搭建；而如今，孩子们只需要用自己的语言描述心中的想法，AI 就能协助将其变为可视化的交互程序。
|
||||
Last week, a thought struck me: Why not build this tool myself? For a programmer with a background in infrastructure and backend development, building a web app is actually quite a daunting task. In my previous personal projects, the most time-consuming part was always the meticulous frontend tweaking. Even setting aside the frontend, architecting a backend that meets professional engineering standards is an exhausting endeavor. Whenever I thought about the sheer volume of work involved, my inner laziness would whisper: *Just pay for the membership.*
|
||||
|
||||
## 从“写语法”到“定义问题”
|
||||
But this time, I started with an unusual level of confidence. My recent experiences using language models and practicing “[Vibe Coding](https://x.com/karpathy/status/1886192184321433842)” (as coined by Andrej Karpathy) taught me that AI is already incredibly capable of building prototypes. So, during the gaps in my parenting duties, I wrote a 300-word requirement and design doc. What followed was a highly efficient dialogue: about 10 minutes of AI generation and another 10 minutes of fine-tuning. [Gemini-CLI](https://github.com/google-gemini/gemini-cli), powered by the latest Gemini Pro model, helped me stand up a clean, functional website in no time.
|
||||
|
||||
在传统的教学中，很多孩子在记忆循环和变量类型时失去了兴趣。生成式 AI 带来的改变在于：
|
||||
|
||||
|
||||
- **即时反馈**：孩子可以随时看到想法被渲染出来。
|
||||
- **系统性思考**：重点转移为理解逻辑流程与规则边界。
|
||||
- **激发创造力**：从消费者转变为创造者。
|
||||
|
||||
|
||||
## 结语
|
||||
**The project is currently hosted on my personal domain and can be accessed at [toolbox.pengzhan.dev](https://toolbox.pengzhan.dev).**
|
||||
|
||||
技术工具永远在演进，不变的是面对未知问题时的探究欲望与审美能力。
|
||||
In less than 30 minutes, I was already printing out tracing sheets for my child to doodle on. This sense of instant gratification gave me a deeper realization of how AI will shape our future:
|
||||
|
||||
- **Software creation is becoming a task anyone can perform, regardless of coding ability.** This means that as long as you are willing to spend a few cents on LLM API calls, you can easily build what was traditionally considered a "program." The barrier to entry for programming has dropped significantly. More importantly, when everyone can be a Product Manager, the question of "who implements it" becomes secondary. Take education as an example: if you are a physics teacher explaining force analysis, an editable PPT might capture your logic, but it’s hard to make it look right. Existing educational software might demonstrate the concept, but it might not align perfectly with your teaching style. So, why not let AI build a bespoke, web-based teaching demo just for you?
|
||||
|
||||
- **Highly customized and truly innovative needs will define the human contribution to future software engineering.** Since basic needs are now easily met, where does human value lie? Clearly, AI still struggles with unique, highly specific requirements or completely innovative explorations. Even when AI can "stitch together" a solution, the process is often laborious and requires constant human guidance. For instance, because AI still lacks precision in visual positioning and coordinate handling, the generated PDF had a persistent offset bug that AI couldn't fix. Despite my lack of familiarity with the [gopdf](https://github.com/signintech/gopdf) library, I had to dive into the source code myself to identify the error in 2D coordinate calculations. This "last mile" limitation is the current bottleneck of AI. Similarly, for completely unknown technical problems—like a Unix Socket error I encountered last week—LLMs (at least the latest [Gemini-3.1-Pro](https://blog.google/technology/ai/google-gemini-3-1-pro-update/)) still cannot find a breakthrough using purely statistical logic. That human "spark"—an efficient activation of massive, compressed knowledge—remains far beyond the reach of current AI architectures.
|
||||
|
||||
- **As LLMs enter the next phase and supporting tools mature, the very form of education will undergo a massive transformation.** The power of LLMs is both transformative and "disruptive." My initial goal was just to satisfy a need for writing practice, but the success of this tool made me realize the possibilities are much broader. Recently, I noticed my child struggling with counting worksheets from school; she often didn't understand the instructions, leading her to color the wrong items or fail to fill in the counts correctly. So, I customized a new feature for her: I let the AI randomly generate similar counting exercises. This approach—completely on-demand and randomly generated—not only reinforces the skill but also prevents "false mastery" caused by repeating the same static problems. This is the true cornerstone of "student-centered" personalized education: it's no longer just a theoretical ideal, but a tangible infrastructure we can finally build.
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
**We cannot predict exactly what comes next. But I stand in awe of this wave of change, and I am deeply excited to witness the next evolution of human society.**
|
||||
|
||||
@@ -0,0 +1,37 @@
|
||||
---
|
||||
title: "AI可以改变什么：为孩子编程"
|
||||
date: 2026-03-02
|
||||
author: "Pengzhan Hao"
|
||||
category: "Non-tech"
|
||||
tags: ["AI Era","Diary","Family","Gemini","Teaching"]
|
||||
cover: "/posts-assets/ai-can-change-coding-for-kids/images/cover.png"
|
||||
lang: "zh"
|
||||
excerpt: "自从大语言模型风靡以来，一场席卷各行业的颠覆性变革悄然开启。以 LLM 为代表的 AI 模型对普通人的生活究竟意味着什么？"
|
||||
---
|
||||
自从大语言模型风靡以来，一场席卷各行业的颠覆性变革悄然开启。虽然我们无法枚举所有正在发生变化的行业，但仅从各类创业公司提出的新需求，以及大型科技公司对传统业务的 AI 化改进中，都能感受到这次变革影响之深。然而，与业务驱动的宏大叙事不同，以 LLM 为代表的 AI 模型对普通人的生活究竟意味着什么，即使是身处风口浪尖的程序员们，有时也难以言说。
|
||||
|
||||
两周前，独自带娃的我看着孩子从 daycare 带回来的字母练习纸，突然意识到她已开始接触“作业”这一概念。在美国，期望 daycare 提供中文书写练习几乎是一种奢求。为了帮助孩子建立基本的汉字书写感，我决定按照国内的节奏为她制作一些字帖。在网上寻觅一番后，我发现大多数中文字帖的受众是学龄童或成人，对于连握笔画画都不稳的孩子来说，写小字确实太具挑战性了。虽然 [E字帖](https://www.nqez.com/) 提供了符合我需求的[带笔顺范例的大字](https://www.nqez.com/zitie-hanzibishunlizi.html)，但其定制功能需要充值会员。尽管 38 元一年的价格并不贵，但那个 UI 极具“年代感”的网站让我对其能否满足长期需求产生了质疑。
|
||||
|
||||
上周，我突发奇想：为什么不自己做一个工具呢？对于基础设施/后端背景的程序员来说，构建一个 Web App 其实是一项极具挑战的任务。在过往的个人项目中，耗时最多的往往是前端微调；而即便抛开前端，构建一个符合工程规范的后端架构也极其耗时耗力。每当想到这些繁杂的工作，心中的惰性总会劝我：还是花点小钱买会员吧。
|
||||
|
||||
但这一次，我开始得格外自信。近期使用语言模型和实践由 Andrej Karpathy 提出的 “[Vibe Coding](https://x.com/karpathy/status/1886192184321433842)” 的经历让我明白，如果只是构建原型产品，AI 已经做得足够出色。于是，我趁着带娃的间隙，写下了约 300 字的需求和设计稿。接下来的对话过程非常高效：大约 10 分钟的 AI 生成，加上 10 分钟的微调，[Gemini-CLI](https://github.com/google-gemini/gemini-cli) 配合最新的 Gemini Pro 模型就帮我搭建出了一个简洁易用的网站。
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
该项目目前托管在我的个人域名下，可以通过 [**toolbox.pengzhan.dev**](https://toolbox.pengzhan.dev) 访问。
|
||||
|
||||
用时不到 30 分钟，我就能打印出字帖供孩子涂鸦。这种即时反馈的惊喜，让我对 AI 影响未来的方式有了更深刻的认知：
|
||||
|
||||
- **人人皆可制作软件而无需编程。** 这意味着，只要愿意投入少量的 LLM API 成本，任何人都能轻易实现传统意义上的程序。编程技能的门槛大幅降低，或者说，当人人都能扮演产品经理（PM）的角色时，“由谁去实现”已不再是核心问题。以教育为例，如果你是一位物理老师在讲受力分析，易于编辑的 PPT 可以完全展现你的教学思路，但做好却不容易。有些现成的软件能演示受力分析，但它们未必能完美契合你的讲解逻辑。那么，为什么不让 AI 为你定制一个专属的动画 Web Demo 呢？
|
||||
|
||||
- **高度定制化与完全创新化的需求，将定义未来软件工程中人类的贡献。** 既然基础需求已能轻易满足，人的力量该如何体现？显然，面对独特且高度定制的需求，或是完全创新性的探索， AI 依然难以独立胜任。即使 AI 能缝合解决方案，过程往往也费时费力，需要人类持续引导。例如，由于 AI 在视觉定位和坐标处理上仍有欠缺，生成的 PDF 曾出现一个难以自动修复的偏移 Bug。我虽然不熟悉 [gopdf](https://github.com/signintech/gopdf) 的实现，但仍需深入研究其源码，最终发现了二维坐标计算的误差。这种“最后一公里”的局限，正是当前 AI 的短板。此外，面对完全未知的技术难题——比如我上周遇到的 Unix Socket 错误——LLM（至少是最近发布的 [Gemini-3.1-Pro](https://blog.google/technology/ai/google-gemini-3-1-pro-update/)）依然无法通过统计逻辑找到突破口。人类那种基于知识压缩后的“灵光一闪”，依然是 AI 目前模型结构下，难望项背的高效激活方式。
|
||||
|
||||
- **随着 LLM 进入下一阶段及配套工具的成熟，教育形态将发生重大变革。** LLM 的力量既强大，又具有“破坏性”。我制作字帖初衷是为了满足写字需求，但它的成功让我意识到更多可能性。最近我观察到，孩子在面对学校的计数练习纸时，常因不理解指令而无法按要求涂色和填写个数。于是，我针对她的进度定制了一个新功能：让 AI 随机生成类似的练习内容。这种完全按需定制、随机生成的方式，不仅增强了技能锻炼，也避免了因题目重复导致的“虚假掌握”。这正是“以学生为中心”的个性化教育能够落地的基石，不再只是思想的发展和准备，而是更加强大的教育基础设施。
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
**我们无法预知未来。但我对这种变革的浪潮既感到敬畏，也让我对人类社会形态的下一次进化充满期待。**
|
||||
Reference in New Issue
Block a user