用LLM构建交互式模拟来学习复杂主题的方法
我用LLM学习复杂主题的方法
Many engineers I know use generative AI for many functions, like building PoCs, internal tools or dashboards, or even learning new stuff. I personally find the style used by LLMs to explain things difficult to follow. It's just too simplistic and depending on the number of emojis used, a bit annoying too.
我认识的许多工程师使用生成式 AI 来实现多种功能，比如构建概念验证、内部工具或仪表板，甚至学习新知识。我个人觉得 LLM 用来解释事物的风格难以理解。它过于简单，而且根据使用的表情符号数量，有时还有点烦人。
While I was analyzing new AI bottlenecks that might slow down data center buildup, I realized there are many aspects of chip production that I do not know. Surfing the web, I asked myself what if there would be a game to get you through the process of building a chip at a fab? For sure learning this way will stick, since you can map concepts with objects within the game. This is when I decided to try it, and it actually turned out really well.
在分析可能减缓数据中心建设的新的 AI 瓶颈时，我意识到芯片生产的许多方面我都不了解。上网时，我问自己：如果有一款游戏能让你体验在晶圆厂制造芯片的过程，会怎样？通过这种方式学习肯定会印象深刻，因为你可以将概念与游戏中的物体对应起来。于是，我决定尝试一下，结果效果非常好。
The flow
流程
Instead of just asking AI to explain a topic, I use the following flow:
我没有仅仅让 AI 解释一个主题，而是采用了以下流程：
- In plan mode (using CC, or OpenCode) I ask a model to build the foundational knowledge for X topic.
- I ask it to review the accuracy of the knowledge base it built in the previous step.
- I proceed asking it to build a simulation of that topic in a low-poly, Rollercoaster Tycoon-like animation. I add some UX elements as well, like the page needs to be visible on both large and small screens, have controls to stop the flow whenever I want etc.
- I then push it to a new repo and enable GitHub Pages for it.
- 在计划模式（使用 CC 或 OpenCode）中，我让模型为 X 主题构建基础知识。
- 我让它审查上一步构建的知识库的准确性。
- 接着，我让它以低多边形、类似《过山车大亨》的动画形式构建该主题的模拟。我还添加了一些用户体验元素，比如页面需要在大屏和小屏上都能显示，有控制按钮可以随时停止流程等。
- 然后我将其推送到一个新仓库，并为其启用 GitHub Pages。
The result
结果
What you get is a beautiful animation that is 100% accurate and free of hallucinations. For me, this method works a lot better than just reading endless materials that I find on Google, or trying to digest a bulleted list that is spat by a language model.
你得到的是一个 100% 准确且没有幻觉的精美动画。对我来说，这种方法比阅读在 Google 上找到的无尽材料，或者消化语言模型吐出的项目符号列表要好得多。
I've done this specifically for learning chip building and launch it under this website: ChipTycoon. You get to follow a cart from the moment when sand is collected, to the moment when a chip is finalized and delivered to a data center.
我专门为学习芯片制造做了这个，并在网站 ChipTycoon 上发布。你可以跟随一辆小车，从收集沙子开始，到芯片完成并交付到数据中心。
Visually, you can follow the cart and see how it changes too. Since it's low-poly, the details might be missing, but it's still a good indicator for showing how the product changes once it goes through the many steps required in the manufacturing process.
在视觉上，你可以跟随小车并看到它的变化。由于是低多边形，细节可能缺失，但它仍然是一个很好的指示器，展示产品在经历制造过程中许多步骤后如何变化。
How to improve it further
如何进一步改进
Let's say that the low-poly design requires to much immagination to actually visualize what happened to the quartz sand pile after it left the furnace. To transform this into a more realistic representation, you can use my skill for transforming pictures into 3d objects, and map the resulting objects to your simulation. This way you get more accurate design.
假设低多边形设计需要太多想象力才能实际可视化石英砂堆离开熔炉后的变化。为了将其转化为更真实的表示，你可以使用我的技能将图片转换为 3D 对象，并将生成的对象映射到你的模拟中。这样你就能得到更精确的设计。
Also, you can add challenges to your simulation too. Trying to answer questions about a previous step in the chip manufacturing process will help you retain the knowledge tremendously. Add intuitive puzzles too that will help you learn even better.
此外，您还可以在模拟中添加挑战。尝试回答有关芯片制造过程中先前步骤的问题将极大地帮助您巩固知识。添加直观的谜题也能让您学得更好。
Check out what other pages I created:
看看我创建的其他页面：
- How rocket engines are made
- How LLMs work
- How F1 engines are built
- How an EUV machine is built
- 火箭发动机是如何制造的
- 大型语言模型是如何工作的
- F1发动机是如何制造的
- 极紫外光刻机是如何制造的
更进一步：量化金融体系
看懂新闻只是起点——沿量化金融路径，把它变成能交付的工程能力