标签：#education

学位论文 摘要 人工智能已不再是遥远的承诺。它已经走进了教室。本论文考察了人工智能工具正在如何改变教育——从适应每位学习者的个性化辅导系统，到几秒钟内给出反馈的智能批改，再到伴随每项创新而来的那些无声的道德问题。 这里的论点并不是说人工智能会取代教师。它不会。相反，本论文提出一个更细致的观点：人工智能如果被明智地使用，可以把教师从那些机器能做到的事情中解放出来——让他们去做教书育人、激励启发、建立联结这些机器做不到的事。然而，这一承诺完全取决于我们如何选择去构建和部署这些系统。 接下来的章节将沿着一条路径展开：从教育技术的历史根源，到当前人工智能工具的版图，到其对学习的可衡量影响，最后深入到那些任何学生、教师或政策制定者都无法忽视的道德与政策问题。 目录 引言 教育技术简史 人工智能如何在课堂中运作 个性化学习与自适应系统 自动化评估与反馈 人工智能时代教师的作用 衡量成效：证据与结果 伦理、隐私与偏见 政策与实施 人工智能在教育中的未来 结论 参考文献 1. 引言 我们生活在一个工具非凡的时代。 驱动自动驾驶汽车和医疗诊断的同一项技术，如今也把一位永不疲倦、从不评判、记得学生每一次回答的导师交到了学习者手中。这是一个惊人的前景。而且它已经到来了。 本论文所讨论的，正是当这个现实与课堂相遇时会发生什么。 教育向来变革迟缓。黑板让位于白板。白板让位于投影仪。投影仪让位于平板电脑。但在每一层新硬件之下，其基本结构始终顽固地保持不变：一位教师、众多学生、一套固定的课程，还有一个对所有人都同样滴答作响的时钟。人工智能的出现，威胁着要打破这种结构。它提供了一种可能：让学习去围绕学习者弯曲，而不是强迫学习者去适应学习。 指导本研究的核心研究问题简单却难答：人工智能能否让教育更有效、更公平？如果能，又是在什么条件下？ 要回答这个问题，我们必须先了解这些系统究竟在做什么。我们必须把真正的进步与营销炒作区分开来。我们必须直面关于数据、隐私的那些令人不安的真相，以及一个风险——那些出于良好意图的工具，可能会加深它们声称要消除的不平等。 本论文分三个部分展开。 首先，我们建立背景。我们回顾教育技术从何而来，以及为何此前的革命未能兑现其承诺。其次，我们审视当下。我们探索人工智能已经在课堂中具体运作的方式，并权衡其影响的证据。第三，我们展望未来。我们探讨伦理、政策与选择——正是这些将决定这场革命是服务于每一位学生，还是只服务于少数特权者。 赌注很高。教育是机会的伟大引擎，是让家庭跨越世代实现跃迁的力量。如果人工智能让它变得更强，我们就获得了无法估量的财富。如果人工智能让它变得更加狭窄，我们失去的东西可能永远无法挽回。本论文正是为了理解我们正在建设的是哪一个未来。 未来之一 未来之二 (机会) (不平等) | | | 每个头脑都被托举 | 最好的工具只属于少数 | 无人无声滑落 | 不透明的儿童画像分拣 | 反馈即刻到来 | 学习失去灵魂 | | \__________ ____________/ \/ / \ / 你 \ / 来抉择 \ /____________\ 2. 教育技术简史 要理解我们将走向何方，我们必须先理解我们曾走过怎样的路。 教育中技术的故事，是一个循环的故事。一次又一次，新发明带着变革的宏大承诺到来。又一次又一次，它退居为佐助的角色——有用，却很少具有革命性。 宏大承诺 | v 希望与狂热 | v 现实降临 | v 退居佐助角色 <---- 机器并未统治课堂 想想广播。当广播信号在20世纪20年代传入美国家庭时，热衷者曾预言，全国的每个孩子都将很快由寥寥几位杰出的讲师授课，他们的声音被送到农舍厨房和城市公寓。这件事并未发生。广播成了补充，而不是替代。 想想电视。在20世纪50年代和60年代，教学电视承诺把世界上最优秀的教师送进每个起居室。它同样悄然退居幕后，成为一种小众选择，而非新体系的基石。 然后是计算机的到来，随之而来的是新一轮乐观情绪。 程序教学，这是心理学家斯金纳在20世纪50年代提出的术语，提供了一个诱人的愿景：把内容分解为许多小步骤，让每个学生按自己的节奏推进，每一步都得到即时反馈。斯金纳的"教学机器"是机械的、笨拙的、有限的。但它们背后的思想——学习可以通过细致的排序和持续的强化来实现个性化——播下了一颗将生长数十年的种子。 20世纪80年代个人电脑的到来，让计算机大规模进入学校。程序辅助教学出现在发达国家各地的实验室和教室中。然而，从大多数衡量标准看，结果却相当有限。许多机器尘封不用。许多软件无人问津。 学者们提出了理解这种炒作与失望循环的方式。 斯坦福大学教育史学家拉里·库班是最突出的声音之一。他的研究记录了一个不断重现的事实：学校对根本性的变革有着惊人的抵抗力，它们吸收新技术却不会被其改造。库班的分析表明，技术革

As someone who teaches beginning web development, I find that building a WordPress site makes for a great final project. Hosting those projects has always been a roadblock though. WordPress.com Student Plan originally handwritten and published with love on CSS-Tricks . You should really get the newsletter as well.

When a language-learning product says it teaches “the sounds of French,” one deceptively simple question appears immediately: how many sounds are there? There is no useful answer without first defining the job the inventory is meant to do. A phonological analysis, a pronunciation dictionary, a speech-recognition system, and a beginner curriculum can all model French sound structure differently without one of them necessarily being careless. They have different users, evidence, and failure costs. Our team encountered this while turning Parle's internal pronunciation inventory into a public CSV. We needed a list that could connect IPA symbols to French spelling patterns, example words, and short mouth cues for English-speaking beginners. We also needed to avoid presenting one product's learning model as the only correct account of French phonology. The result is a bounded dataset of 35 practical sound entries. This article explains the design decisions, the schema, and the limits we published with it. A teaching inventory is a model, not a census The International Phonetic Alphabet gives us a shared notation for describing speech sounds. It does not require every analyst or teacher to draw identical category boundaries for every language variety. The official IPA chart is a notation system; selecting a French inventory still requires linguistic and pedagogical decisions. Counts can change when an inventory treats any of the following differently: a contrast that is maintained by some speakers but merged by others; a marginal or loan sound that appears mainly in borrowed words; schwa, whose realization and deletion depend heavily on context and variety; a historical contrast that remains visible in spelling but not in every speaker's production; a phonetic realization versus a contrastive phoneme; a glide represented separately from its related vowel. For a curriculum, the important question is not “What number wins?” It is “What distinctions and cues help this audienc

How We Built a 160-Article AI Education Platform with Next.js and Static HTML Three months ago, I launched IAcademy — an AI education platform in Spanish with 160+ free guides covering everything from prompting basics to autonomous agents, LLM deployment, and MCP servers. Here's what worked, what didn't, and the architecture behind it. Why Spanish AI Education is Underserved The AI education space is dominated by English content. Coursera, Udemy, DeepLearning.AI — all English-first. Spanish-speaking professionals (500M+ people) get translated scraps or nothing. The opportunity: 0% competition on keywords like "agentes ia" (400 monthly searches), "herramientas ia" (400), "formación ia" (250). In English, these keywords have 30-50% competition. In Spanish, nobody's writing quality content. Architecture: Why Static HTML, Not a CMS Each blog post is a standalone index.html file. No WordPress, no Gatsby, no MDX compilation step. site/blog/ ├── agentes-ia-que-son/ │ └── index.html ├── herramientas-ia-guia/ │ └── index.html ├── formacion-ia/ │ └── index.html └── ... (160+ directories) Why this approach: Zero build time. Adding an article = creating a directory + file. No compilation, no hydration errors, no framework upgrades breaking 160 pages. Perfect SEO control. Every <title> , <meta> , JSON-LD schema, internal link, and heading hierarchy is hand-crafted per page. No CMS template imposing its structure. Instant deploy. Push to GitHub → Cloudflare Pages deploys in ~30 seconds. No build queue. No JavaScript required for content. Google indexes immediately. Core Web Vitals are perfect — there's nothing to load. The dynamic parts (auth, course portal, labs) use Supabase + vanilla JS. But the blog — which is the SEO engine — is pure static HTML. Content Strategy: Niche Prompts Beat Head Terms After 3 months, here's what ranks and what doesn't: What ranks (top 10 in Google): prompts-ia-facturacion — prompts for accountants (position 8.4) prompts-ia-logistica — prompts for lo

I'd been waiting for more than 30 minutes. The terminal just sat there, blinking, without returning a single word. I'd launched Gemma2 in its 9-billion-parameter version on my laptop (a regular Mac, the kind any professor or student would use) and the model simply wasn't responding. It wasn't a bug. It was the most honest answer the experiment could have given me. That frustrating wait ended up being, without exaggeration, the most interesting finding of the whole process. Because the question that brought me there wasn't "how big can a model get?" — it was a much more practical one: what actually happens when an agent you built in a tutorial has to survive in production? I've been working with Gemma as a case study to understand that jump — from an educational prototype to something that can hold up under long conversations, limited hardware, and real users. This post is the honest summary of that process: what worked convincingly, what didn't work the way I expected, and why that "didn't work" turned out to be more useful than a clean result would have been. The real problem: why tutorials are a little dishonest Almost every conversational agent tutorial does the same thing, without saying so out loud: on every turn, it sends the model the entire previous history, all over again. Imagine that every time you added a sentence to a conversation, you had to repeat everything said before it — every message, every reply — before you could say the new one. At first you don't notice. But if the conversation runs 30 or 50 turns, you're repeating an entire novel just to add one sentence. This pattern is called linear context stacking , and it causes three concrete problems: Memory saturation — every call to the model processes an increasingly large context. Risk of hitting the token limit — every model has a maximum context window; sooner or later, you hit it. Quality degradation — there's a documented phenomenon in NLP literature called "lost in the middle" : when context

Brian Kim 1st Period Mrs. Lukens Can revenge be heroic? Hamlet proves that revenge is heroic, despite it’s evil nature. Through the course of the book, Hamlet restores peace to his kingdom and balances the offenses of King Claudius. Still, Heroism is a matter of perspective and revenge is the action of one’s own justice onto another. What makes revenge heroic is the intent of the one who desires justice, not the aftermath. Hamlet demonstrates his heroism as his revenge begins as an attempt to preserve his fathers honor. His revenge begins heroic, however is later easily corrupted. It is learned, revenge is a never ending cycle and the true heros emerge to be the ones that forgive. Hamlet’s revenge was justified and therefore heroic. Nevertheless, the changes in him become evident and eventually detract from his righteousness. Hamlet appears to be crazy, although it is said to be merely an act to fool the king, even the reader is unable to distinguish his lunacy as Hamlet was truly blinded by revenge. The first sign of corruption is shown as Hamlet denies his love for Ophelia. Here it is seen, his desire to avenge his father overshadows his love for others. “Get thee to a nunnery. Why wouldst thou be a breeder of sinners?...”(act 3,sc.1), his revenge on Claudius manifests on his conversation with Ophelia. Revenge loses it’s heroism when it changes to hatred. Nevertheless, Hamlets retains his true feelings as he’d rather see Ophelia alone than with another man. Another corruption to heroism in revenge is shown when Hamlet kills Polonius. Hamlet’s revenge does not stop with murder; he now feels nothing and is willing to do whatever it takes to have his revenge. “A bloody deed - almost as bad, good mother, as kill a king and marry his brother”(act 3, sc.4), Hamlet’s revenge has turned evil, yet still portrayed as a justified, almost heroic evil. With all evils, revenge becomes a never ending cycle. This is shown, following the death of Polonius, in Ophelia. Hamlet’s rev

Most "beginner" Python courses aren't actually beginner courses. Lesson one usually opens with variables or print(), quietly assuming you already know what a terminal is, how to install something, or what a .py file even means. That assumption is exactly where most self-taught learners bounce — not because Python is hard, but because the ten minutes of orientation that would've made everything after it make sense got skipped. I built Codes Are Simple to start there instead. Session 1, Level 1: what is code, where do you type it, how do you open Command Prompt, how do you install Python and verify it worked. Nothing assumed. What it actually is A 45-session, self-paced curriculum — Python: The Universal Language, Zero to Pro — split into 10 tiers, from absolute foundations through OOP, files/errors, practical CLI projects, web/APIs, databases, and a final professional capstone. It's the first of a planned multi-track catalog on the same platform (web dev, AI, cyber, and data are mapped and coming next). Every lesson — all of them, across all 45 sessions — follows the same repeating shape: explanation → main example → 2 extra examples (variations/edge cases) → common mistake (shown alongside its fix) → practice → extra practice That "common mistake" section is the part I actually care about most. Almost every course I looked at shows only the correct code. This one shows what actually breaks for a beginner and why — because for someone learning alone with no instructor in the room, the error message is usually where the real learning happens, not the clean solution. Checkpoints land at fixed points mid-session (after Level 2, Level 6, and Level 9 — not just at the end), and every session closes with a real capstone project, not a toy exercise. The stack Cloudflare Workers + Pages + R2 — the site and all curriculum content, served as versioned JSON per session GitHub — version control for the whole content pipeline That last point is the part I think this community wil

Everyone is talking about the reading crisis. But inside the “Mississippi Miracle,” it’s all about comprehension.

At Mehran University of Engineering and Technology (MUET), Jamshoro, results are traditionally announced via large, static PDF tables. But the main issue is: Every semester, the same story. Need to check your result? Open your laptop. Connect to the university network... or set up a VPN. Want to know your actual class or batch rank? Good luck guessing. That frustration became my latest project. To solve this, I set out to build the MUET Results Portal ( https://muetresults.vercel.app )—an independent, open-source lookup engine and administrative compiler that provides students with instant semester results, CGPA calculations, batch standings, and interactive academic calendars. Here is an engineering deep-dive into how I built it using a serverless GitOps pipeline, vanilla JavaScript SPA, and Gemini AI. 🛠️ The Architecture & Data Pipeline To keep the platform hosting costs at absolute zero while maintaining lighting-fast page loads, I designed a pre-rendered static pipeline. Rather than querying a database at runtime, all student data is compiled statically. Here is the GitOps workflow: Official PDF Release : The Mehran University Examination Department publishes a new results PDF. LLM OCR Parsing : Via a secure administrative panel ( /mokshadmin ), I upload the scanned PDF/image. A serverless backend function streams the document to the Google Gemini 1.5 Flash API , which returns structured JSON student records. Git Database Update : The approved JSON records are committed back to the repository's git-tracked database ( muet_student_gpa_dataset.csv ) using the GitHub REST API. CI/CD Pre-rendering Build : The new commit triggers a Vercel build hook. Node compilation scripts read the CSV database and: Group records and compile them into static runtime JSON structures. Pre-render complete static HTML folder structures for all batch rankings and departments. Regenerate SEO sitemaps ( sitemap.xml ). Instant Deployment : Vercel serves the pre-rendered static files instan

Executive Summary The Salesforce Education Data Architecture (EDA) has served educational institutions well for over a decade as a free, community-supported managed package. However, with the 2023 launch of the reimagined Education Cloud—built natively on the Salesforce core platform—institutions now face a strategic choice about their CRM foundation . While EDA remains supported and continues to function effectively, Education Cloud represents a fundamental architectural shift that offers significant advantages in simplicity, scalability, and access to innovation . This paper examines why Education Cloud is demonstrably easier to implement and maintain compared to its predecessor, addressing the key differences in architecture, data model, and ongoing operations. 1. The Architectural Advantage: Built-In vs. Bolted-On 1.1 EDA: A Managed Package on Top of Salesforce EDA is a managed package installed on top of the Salesforce core platform . As a managed package, it creates additional layers of complexity: Installation and Updates: EDA requires separate package installations and updates that can lag behind Salesforce's native release cycle Namespace Conflicts: The managed package introduces its own namespace, potentially creating compatibility issues with other tools Translation Limitations: EDA's localization has documented issues, including a known problem where the Preferred Phone functionality fails when users switch to languages other than English Record Type Validation Bugs: Deactivating an account record type can block contact creation—a validation error that requires manual workarounds 1.2 Education Cloud: Native to the Core Platform Education Cloud represents a fundamentally different approach. Rather than being a package installed on Salesforce, Education Cloud is built directly on the Salesforce core platform . Key Advantages: No Package to Install: Education Cloud runs natively on the Salesforce core platform, eliminating the need for separate managed pack

I just submitted another Chrome extension to the Chrome Web Store. I have submitted multiple extensions overtime. Mostly for my own tooling and community share or just because idea was fun. The first time took 3 attempts. The second time I got rejected in 12 hours for something completely avoidable. Here's every gotcha I hit — so you don't have to. 1. Manifest description has a 132-character hard limit Not documented prominently anywhere. You'll get a cryptic upload error: "The description field in manifest is too long." Your package.json description or wxt.config.ts description gets baked into manifest.json — check it BEFORE you zip. Fix : Count characters. 132 max. Put the detailed description in the CWS form, not the manifest. 2. Don't put a "Keywords:" line in your description I literally had: Keywords: pinterest seo, pin score, pin quality, pinterest optimizer... Rejected within 12 hours for "Keyword Spam." CWS explicitly bans keyword lists in descriptions — even if they're relevant. Your keywords should be woven naturally into prose. Fix : Write human sentences that include your keywords. "Score your Pinterest pin quality before publishing" contains 3 keywords naturally. 3. upload-artifact@v4 silently skips hidden directories If your build tool outputs to .output/ (like WXT does), GitHub Actions' upload-artifact won't find it. The glob path: .output/*.zip returns nothing because .output starts with a dot. Fix : Add include-hidden-files: true to your upload-artifact step. - uses : actions/upload-artifact@v4 with : path : .output/*.zip include-hidden-files : true 4. optional_permissions need justification too I added sidePanel as an optional permission (reserved for a future feature). CWS asked me to justify it. Optional doesn't mean invisible to reviewers. Fix : Add a justification for EVERY permission — required AND optional. Explain what it'll do and why it's optional. 5. "Support URL" is not your email address The form has separate fields: Support email : yo

Artificial intelligence has become one of the most discussed technologies in education. From automated grading systems to AI chatbots capable of answering complex questions, many people wonder whether AI will eventually replace teachers. The short answer is no. Education has never been just about delivering information. Great teachers inspire curiosity, understand students' emotions, adapt to different learning styles, and create environments where learners develop critical thinking. These are deeply human abilities that artificial intelligence cannot fully replicate. However, AI is beginning to solve a different problem: helping students learn independently outside the classroom. The Problem With Traditional Self-Study Many students spend hours reading textbooks without truly understanding the concepts. When they encounter a difficult paragraph, they often search the internet, only to find lengthy articles, conflicting explanations, or answers that are either too advanced or completely unrelated to their curriculum. This creates an inefficient learning process where students spend more time searching than actually learning. Another common challenge is passive learning. Reading a chapter once often creates the illusion of understanding, but without testing knowledge through questions or applying concepts, much of that information is quickly forgotten. How AI Can Support Learning Modern educational AI systems are becoming less like search engines and more like interactive learning companions. Instead of simply returning search results, these systems can explain concepts in simpler language, adapt explanations to a student's academic level, answer follow-up questions, generate practice quizzes, and even identify areas where additional practice is needed. This creates a much more personalized learning experience. Learning From Personal Study Materials One of the most interesting developments in AI education is the ability to work with a student's own resources. Rather

How AI Changes What 'Learning' Means Hook: Amre learned Python using AI. No, not just using AI as a supplementary tool—he learned from AI, as if it were his personal tutor. If AI can teach a complex skill like programming, what does that mean for the future of education? Background: The traditional education system, with its structured curriculums and standardized testing, has long been criticized for its rigidity. Enter AI, and suddenly, the landscape of learning is shifting. AI tutors, adaptive learning platforms, and intelligent coding assistants like GitHub Copilot are becoming ubiquitous. These tools are not just helping students with homework; they are fundamentally altering the way we acquire new skills and knowledge. Consider Amre's experience. Frustrated with the slow pace of a traditional Python course, he turned to an AI-powered learning platform. The AI assessed his current knowledge, identified his learning style, and tailored a curriculum specifically for him. It provided instant feedback, suggested additional resources, and even simulated real-world coding challenges. Within weeks, Amre was writing functional code and solving complex problems—something he hadn't thought possible in such a short time. This isn't an isolated incident. Across the globe, learners are turning to AI for personalized education experiences. From language learning apps that adapt to your pace and style, to AI tutors that can explain complex mathematical concepts in multiple ways until you understand, the traditional classroom is being redefined. Analysis: The most significant change AI brings to learning is personalization. Unlike traditional education systems that follow a one-size-fits-all approach, AI can adapt to the unique needs of each learner. It can identify gaps in knowledge, adjust the difficulty level of tasks, and provide customized feedback. This level of personalization was previously only available to those who could afford private tutors. Moreover, AI democrati

Teachers and parents lose a surprising amount of time hunting for printable practice sheets, then hitting a sign-up wall or a paywall. So I built a small set of free tools that make the sheet you need in a couple of clicks, with no account and no email. They run entirely client-side in the browser, so nothing is uploaded or stored, and every sheet prints straight to paper or saves as a PDF. What is in the set so far: A maths worksheet generator (addition, subtraction, multiplication, division, mixed) with an answer key A name-tracing sheet generator for early writers A spelling worksheet generator A word search maker Routine and chore chart makers The hub is here: Free printable tools A few build notes for anyone making something similar: Keeping it fully client-side meant zero backend cost and instant load, which matters when a teacher opens it on a school tablet on a slow connection. The fiddly part was the print layout. A dedicated print stylesheet with CSS page breaks gave a much cleaner result than forcing a PDF library. Removing the sign-up step takes out all the friction, which is the whole point for a busy classroom. I run a small Brisbane children's book imprint, Lantern Path Books , and these started as a side project to help the parents and teachers who read our picture books. They are free to use and share. Happy to talk through the print-layout approach if it is useful to anyone.

AI Does Not Cancel Reality I watched the conversation between Mo Gawdat and Marina Mogilko about the future of AI. The conversation is strong. It contains important ideas, but it also contains many claims that sound large in scale, although on closer inspection they rely on very broad generalizations. AI is indeed changing the labor market, education, startups, content, hiring, and ways of thinking. But it does not cancel money, connections, trust, the human vector, creativity, necessity, morality, or people’s ability to adapt. Video on YouTube AI in hiring: automation amplifies chaos Many people have entered the job market. Companies receive huge volumes of resumes. HR departments cannot handle the volume. It is natural that part of the selection process is moving to AI. But there is a serious problem here. Candidates are also starting to play against AI. Resumes are adjusted to vacancies. Cover letters are assembled around keywords. Profiles become optimized for the filter, not for real work. In such a system, the best specialist does not necessarily pass. Often, the person who understood the selection mechanism better passes. The result: the picture becomes cleaner, while the quality of the decision becomes lower. The company gets not the strongest candidate, but the candidate who matched the algorithm best. This leads to lower hiring quality, lower productivity, and slower development. “I built a startup in six weeks”: a product is not a startup The conversation includes the idea that an AI startup would once have taken years and hundreds of engineers, and now it can be built in weeks. Technically, this is true. Prototypes are now built faster. Small teams have powerful tools. One person can now do more than a group could do before. But two different things are mixed here. Building a product faster has become real. Building a startup faster has become real only when resources are present. A startup is not only code. A startup is money, connections, trust, reputa

A homeschooling center in Manhattan is part of the company’s nationwide expansion. Internal documents reveal its strategy: “Opening date > safety.”