{"id":23171,"date":"2026-08-11T03:04:44","date_gmt":"2026-08-11T03:04:44","guid":{"rendered":"https:\/\/scannn.com\/how-i-use-llms-to-learn-complex-topics-%c2%b7-laurentiu-raducu\/"},"modified":"2026-08-11T03:04:44","modified_gmt":"2026-08-11T03:04:44","slug":"how-i-use-llms-to-learn-complex-topics-%c2%b7-laurentiu-raducu","status":"publish","type":"post","link":"https:\/\/scannn.com\/lv\/how-i-use-llms-to-learn-complex-topics-%c2%b7-laurentiu-raducu\/","title":{"rendered":"How I use LLMs to learn complex topics \u00b7 Laurentiu Raducu"},"content":{"rendered":"\n<div id=\"\">\n<p>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&#8217;s just too simplistic and depending on the number of emojis used, a bit annoying too.<\/p>\n<p><\/p>\n<p>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.<\/p>\n<h2>The flow<\/h2>\n<p>Instead of just asking  AI to explain a topic, I use the following flow:<\/p>\n<ul>\n<li>In plan mode (using CC, or OpenCode) I ask a model to build the foundational knowledge for X topic.<\/li>\n<li>I ask it to review the accuracy of the knowledge base it built in the previous step.<\/li>\n<li>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.<\/li>\n<li>I then push it to a new repo and enable GitHub Pages for it.<\/li>\n<\/ul>\n<h2>The result<\/h2>\n<p>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.<\/p>\n<p>I&#8217;ve done this specifically for learning chip building and launch it under this website: <a href=\"https:\/\/laurentiugabriel.github.io\/ChipTycoon\/\">ChipTycoon<\/a>. 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.<\/p>\n<p>Visually, you can follow the cart and see how it changes too. Since it&#8217;s low-poly, the details might be missing, but it&#8217;s still a good indicator for showing how the product changes once it goes through the many steps required in the manufacturing process.<\/p>\n<h2>How to improve it further<\/h2>\n<p>Let&#8217;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 <a href=\"https:\/\/github.com\/LaurentiuGabriel\/unreal-game-assets-creation-skill\">skill for transforming pictures into 3d objects<\/a>, and map the resulting objects to your simulation. This way you get more accurate design.<\/p>\n<p>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.<\/p>\n<p>Check out what other pages I created:<\/p>\n<p>After reading the feedback on the HN post, I decided to create <a href=\"https:\/\/github.com\/LaurentiuGabriel\/learnscape\">an awesome Skill.MD file for creating cool animations to learn complex topics<\/a>.<\/p>\n<\/div>\n<p><a href=\"https:\/\/laurentiugabriel.github.io\/blog\/articles\/how-i-use-llms-to-learn\/?utm_source=tldrdev\">Source link <\/a><\/p>\n","protected":false},"excerpt":{"rendered":"<p>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&#8217;s just too simplistic and depending on the number of emojis used, a bit annoying too. While I was [&hellip;]<\/p>\n","protected":false},"author":16,"featured_media":23172,"comment_status":"open","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[143],"tags":[],"class_list":["post-23171","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-ai"],"_links":{"self":[{"href":"https:\/\/scannn.com\/lv\/wp-json\/wp\/v2\/posts\/23171","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/scannn.com\/lv\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/scannn.com\/lv\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/scannn.com\/lv\/wp-json\/wp\/v2\/users\/16"}],"replies":[{"embeddable":true,"href":"https:\/\/scannn.com\/lv\/wp-json\/wp\/v2\/comments?post=23171"}],"version-history":[{"count":0,"href":"https:\/\/scannn.com\/lv\/wp-json\/wp\/v2\/posts\/23171\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/scannn.com\/lv\/wp-json\/wp\/v2\/media\/23172"}],"wp:attachment":[{"href":"https:\/\/scannn.com\/lv\/wp-json\/wp\/v2\/media?parent=23171"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/scannn.com\/lv\/wp-json\/wp\/v2\/categories?post=23171"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/scannn.com\/lv\/wp-json\/wp\/v2\/tags?post=23171"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}