[{"data":1,"prerenderedAt":109},["ShallowReactive",2],{"blog-the-catch":3},{"id":4,"title":5,"article":6,"body":7,"date":96,"description":97,"extension":98,"meta":99,"navigation":100,"path":101,"promptVersion":6,"readingTime":102,"seo":103,"stem":104,"tags":105,"__hash__":108},"content\u002Fblog\u002Fthe-catch.md","LLM catch",5,{"type":8,"value":9,"toc":88},"minimark",[10,14,17,20,25,28,31,34,37,41,44,47,50,53,57,60,63,66,69,73,76,79,82,85],[11,12,13],"p",{},"You know the feeling. You have an idea. You open ChatGPT. You type: \"Design me a complete architecture for this feature. Include database schema, API endpoints, error handling, deployment strategy.\"",[11,15,16],{},"Ten seconds later you have twelve pages of perfect text. It looks right. It reads like something a senior engineer would write. It has tradeoffs mentioned. It has numbered lists and bullet points and everything you asked for.",[11,18,19],{},"You save it to a file. You close the tab. You never look at it again.",[21,22,24],"h2",{"id":23},"the-production-gap","The production gap",[11,26,27],{},"This is the quiet failure of LLM-aided work that nobody talks about. We have become incredibly good at generating specifications, plans, architectures, roadmaps, designs, and proposals. We have become no better at actually building any of them.",[11,29,30],{},"The ratio is something like 100:1. For every one thing that gets built, there are a hundred complete, perfectly reasonable plans sitting in markdown files, chat histories, and Notion pages, never to be opened again.",[11,32,33],{},"The LLM doesn't care. It will happily write you the full specification for a distributed message broker in the time it takes you to blink. It will explain all the edge cases. It will argue with you about consistency models. It will do everything except type the first line of actual code.",[11,35,36],{},"Nobody reads these documents. Not really. We scan the first page. We nod. We think \"yes that makes sense\". And then we move on, because the actual work of building was never the part we were stuck on in the first place.",[21,38,40],{"id":39},"planning-as-procrastination","Planning as procrastination",[11,42,43],{},"The hardest part of building something was never figuring out what to build. It was building it.",[11,45,46],{},"Before LLMs, you had to think through the plan. You had to write it down. You had to argue about it. That process forced you to confront the hard parts early. Now you can skip all that. You can have a complete, internally consistent plan in less time than it would take you to explain the problem to a colleague.",[11,48,49],{},"But the plan doesn't remove the work. It just hides it. All the messy, boring, tedious parts that make something actually work are still there, waiting for you after the impressive document ends.",[11,51,52],{},"This happens because the plan looks so complete, so thorough, so done, that you get the psychological feeling of having accomplished something without having done anything at all. It is productive procrastination at industrial scale.",[21,54,56],{"id":55},"the-test","The test",[11,58,59],{},"Here is a simple test for any LLM output: will this document make me type code tomorrow?",[11,61,62],{},"If the answer is no, it doesn't matter how good it is. It doesn't matter how clever the architecture is. It doesn't matter how well it explains the tradeoffs. It is dead weight. It is a simulation of work, not work itself.",[11,64,65],{},"The best LLM outputs are not the longest ones. They are not the most detailed ones. They are the ones that end with \"and then you write these seven lines of code, and that's the whole thing\".",[11,67,68],{},"Everything else is just reading material.",[21,70,72],{"id":71},"what-gets-built","What gets built",[11,74,75],{},"The things that actually get built are almost never the ones with the perfect twelve-page specification. They are the ones where someone got frustrated, stopped planning, and just typed the first ten lines of code.",[11,77,78],{},"They are messy. They have missing features. They cut corners. They don't handle all the edge cases. But they exist. They run. They do something.",[11,80,81],{},"The difference between a plan and a product is not quality of thinking. It is tolerance for imperfection. It is willingness to start before you have all the answers. It is accepting that the first version will be bad, and building it anyway.",[11,83,84],{},"We are living through the greatest supply of plans, specifications, and designs the world has ever seen. And we are living through the greatest shortage of things that actually work.",[11,86,87],{},"Anyone can ask for a plan. The hard part is stopping at the point where you have just enough information to start, and then closing the tab.",{"title":89,"searchDepth":90,"depth":90,"links":91},"",2,[92,93,94,95],{"id":23,"depth":90,"text":24},{"id":39,"depth":90,"text":40},{"id":55,"depth":90,"text":56},{"id":71,"depth":90,"text":72},"2026-04-21","LLMs write perfect plans, detailed specifications, and complete architectures. Nobody ever builds any of it.","md",{},true,"\u002Fblog\u002Fthe-catch","4 min read",{"title":5,"description":97},"blog\u002Fthe-catch",[106,107],"engineering","llm","V636evV6OWoiB2z9PSj4pXcJ4X3iB4SIcckqL0OeY0A",1777017987424]