从敲代码到与人工智能对话
了解人工智能如何改变软件构建方式。
从敲代码到与人工智能对话 是 CoddyKit 上的免费 Vibe Coding 课时。 这是第 2 节课，共 4 节。 你可以在下方免费阅读本课时的完整内容 — 然后在浏览器中使用内置代码编辑器和全天候 AI 导师进行实践。 这是 Vibe Coding 学习路径的一部分，你的进度在网页和 CoddyKit 应用中同步。 Vibe Coding 课程共包含 4 节课。
本课时的部分内容尚未翻译，以英文显示。
How Building Changed
Not long ago, making software meant typing every line by hand. Now you can talk to AI and watch working code appear. Let's see how we got here.
The Old Way: Type Everything
The old way: memorize syntax, type it perfectly, hunt for a missing semicolon. One tiny typo broke everything. Powerful, but slow and full of friction.
function greet(name) {
console.log("Hello " + name)
}
// Forget a bracket or quote, and nothing runs.Autocomplete: The First Helper
The first step toward AI building was autocomplete — editors suggesting your next word. Small, but it hinted at tools that understand what you're trying to do.
AI Learned to Read Code
Then came large language models, trained on huge amounts of text and code. They could read your code and understand it — explain a file, find a bug, write a function.
Explain what this function does and suggest a clearer name for it.GitHub Copilot Changed the Game
In 2021, GitHub Copilot let you write a comment describing what you wanted, and AI wrote the code below it. For millions, 'describe, then code' had arrived.
// create a function that returns the largest number in an array
// ...and Copilot writes the function for you.From Suggestion to Conversation
Next, a bigger leap: chatting with AI inside your editor. Tools like Cursor and Claude Code made building a back-and-forth, not a monologue of typing.
You: Add a dark mode toggle to this page.
AI: Done. I added a button and a theme switch.
You: Make the toggle a moon and sun icon.Agents That Take Action
The newest shift: AI that doesn't just suggest, but acts. It can create files, run commands, test code, and fix errors. You describe a goal and supervise.
Prompt In, App Out
Browser tools like v0, Bolt, and Lovable go further: type one prompt and get a complete working app. The gap from idea to clickable product is now minutes.
Build a to-do app where I can add tasks, check them off, and delete them.See the Difference
Here's the same simple goal, the new way: describe it instead of writing it. Run this snippet to see the kind of output AI handles for you.
const numbers = [4, 9, 2, 11, 7];
const biggest = Math.max(...numbers);
console.log("The biggest number is " + biggest);What This Means for You
This shift isn't just convenient — it's empowering. You no longer need years of training to start. If you can describe an idea clearly, you can make it. ✨
Talking Is a Skill Too
The catch: talking to AI well is its own skill. Vague requests get vague results; clear ones get great code. That's exactly what this track teaches you.
Vague: "Make a website."
Clear: "Make a one-page portfolio site with my name, a short bio, and three project cards."Quick Check
Which describes the shift AI has brought to building software?
Recap: The Big Shift
You traced the journey from typing to talking: autocomplete, then AI that reads code, then Copilot, chat, and agents. Next: just how much you can build. Let's explore!
常见问题解答
「从敲代码到与人工智能对话」课时是免费的吗？
是的 — 「从敲代码到与人工智能对话」的完整文本可在网页上免费阅读。要进行交互式练习（内置代码编辑器和全天候 AI 导师）并解锁 Vibe Coding 课程的其余内容，请升级到 CoddyKit PRO。 Vibe Coding 课程共包含 4 节课。
「从敲代码到与人工智能对话」这节课中我会学到什么？
了解人工智能如何改变软件构建方式。 你通过在浏览器中直接运行的动手代码来练习 Vibe Coding，全天候 AI 导师会在你学习这节课的过程中回答你的问题。
学习 Vibe Coding 需要有经验吗？
无需任何先前经验。CoddyKit 上的 Vibe Coding 课程适合初学者到高级学习者，你可以从这里开始或从头开始，按照自己的节奏学习。 这是第 2 节课，共 4 节。
「从敲代码到与人工智能对话」课时需要多长时间？
大多数 CoddyKit 课程大约需要 5–10 分钟。每节课都很精短且互动，所以你能稳步进步，并在网页和应用中从离开的地方继续。
我能在这节 Vibe Coding 课中编写并运行代码吗？
能。每节 Vibe Coding 课都包含内置代码编辑器，你可以在浏览器中直接编写并运行真实代码，并获得即时 AI 反馈 — 无需本地设置。