How I use LLMs to learn complex topics

我是如何利用大语言模型（LLM）学习复杂课题的

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都在使用生成式 AI 来处理各种任务，比如构建概念验证（PoC）、内部工具或仪表盘，甚至用于学习新知识。但我个人觉得，大语言模型（LLM）解释事物的方式很难让人跟上。它们往往过于简单化，而且根据所用表情符号的数量，有时还会让人感到厌烦。

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. 在分析可能拖慢数据中心建设进度的新型 AI 瓶颈时，我意识到自己对芯片生产的许多方面并不了解。在网上冲浪时，我问自己：如果有一款游戏能带你走完晶圆厂制造芯片的全过程会怎样？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，结果出奇地好。

The flow: Instead of just asking AI to explain a topic, I use the following flow: 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. 流程：我不再只是简单地让 AI 解释一个主题，而是采用以下流程：在规划模式下（使用 Cursor 或 OpenCode），我要求模型为某主题构建基础知识库。接着，我要求它审查上一步所构建知识库的准确性。随后，我让它以低多边形（low-poly）、类似《过山车大亨》的动画形式构建该主题的模拟程序。我还添加了一些用户体验（UX）元素，比如页面需要同时适配大屏和小屏，并具备随时暂停流程的控制功能等。最后，我将其推送到一个新的代码仓库，并启用 GitHub Pages 进行部署。

The result: 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. 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. 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. 结果：你将得到一个既美观、准确率 100% 又没有幻觉的动画。对我而言，这种方法比在谷歌上阅读无穷无尽的资料，或者试图消化语言模型吐出的要点列表要有效得多。我专门用这种方法学习了芯片制造，并发布了这个网站：ChipTycoon。你可以跟随一辆小车，从收集沙子开始，一直到芯片最终完成并交付到数据中心。在视觉上，你可以追踪小车并观察它的变化。虽然是低多边形设计，细节可能有所缺失，但它依然能很好地展示产品在经历制造过程中的多个步骤时是如何演变的。

How to improve it further: Let’s say that the low-poly design requires too much imagination 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. 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. 如何进一步改进：假设低多边形设计需要太多的想象力，才能真正直观地理解石英砂堆离开熔炉后发生了什么。为了将其转化为更逼真的表现形式，你可以利用我将图片转换为 3D 物体的技能，并将生成的物体映射到你的模拟中。这样你就能获得更精确的设计。此外，你还可以在模拟中增加挑战。尝试回答关于芯片制造过程中前一步骤的问题，将极大地帮助你巩固知识。加入直观的谜题也能让你学得更好。

Check out what other pages I created: 看看我还创建了哪些页面：

• How rocket engines are made (火箭发动机是如何制造的)
• How LLMs work (大语言模型是如何工作的)
• How F1 engines are built (F1 发动机是如何制造的)
• How an EUV machine is built (EUV 光刻机是如何制造的)