--- title: Why LLMs Can't Really Build Software — Zed's Blog description: Large Language Models excel at writing code but struggle with the iterative mental modeling that defines effective software engineering. While LLMs can... canonical: https://daily.dev/posts/why-llms-can-t-really-build-software-zed-s-blog-ffv89ofc3 twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: Why LLMs Can't Really Build Software — Zed's Blog | daily.dev og:description: Large Language Models excel at writing code but struggle with the iterative mental modeling that defines effective software engineering. While LLMs can... og:url: https://daily.dev/posts/why-llms-can-t-really-build-software-zed-s-blog-ffv89ofc3 og:image: https://api.daily.dev/og/posts/fFV89OFC3.png og:image:alt: Why LLMs Can't Really Build Software — Zed's Blog og:image:width: 1200 og:image:height: 630 og:locale: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # Why LLMs Can't Really Build Software — Zed's Blog **[Zed](https://daily.dev/sources/zed)** · 4 min read · 73 upvotes · 5 comments ## Summary Large Language Models excel at writing code but struggle with the iterative mental modeling that defines effective software engineering. While LLMs can generate code and update it when given specific problems, they cannot maintain clear mental models of requirements versus implementation, leading to confusion when tests fail or debugging is needed. Current models suffer from context omission, recency bias, and hallucination issues that prevent them from understanding complex software systems. For non-trivial projects, human engineers must remain in control, using LLMs as tools while maintaining responsibility for requirements clarity and code verification. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Community discussion Top comments from developers on daily.dev. **@whlsk34** · 5 upvotes > This take is better than most. > > There are so many bad takes out there, someone with a psychology degree, someone who has done fronted work, someone with an MBA, thinks they have the gotcha or even worse they are a linkedin poster, a substack pusher, an wanabe influencer or a thought-leader-poser looker for their first big break. > > At the end of the day NONE of these people even know what an attention head is or can explain the FUNDAMENTALS of how their critique relates to a deep understanding of the technology and can prove that this gotcha isn't cooked up--one part background bias, one-part... **@fabooy961** · 3 upvotes > Really? Algorithms from the 70s can't fully build complex software projects? > >  **@joashua** · 0 upvotes > Because they're not AI? ## Similar posts on daily.dev - [Governing Security in the Age of Infinite Signal](https://daily.dev/posts/governing-security-in-the-age-of-infinite-signal-qhihbir44) · Snyk · 0 upvotes · 0 comments - [No one has a good plan for how AI companies should work with the government](https://daily.dev/posts/no-one-has-a-good-plan-for-how-ai-companies-should-work-with-the-government-nkajqoze1) · TechCrunch · 0 upvotes · 1 comments --- Tags: [#ai-coding](https://daily.dev/tags/ai-coding), [#llm](https://daily.dev/tags/llm), [#zed](https://daily.dev/tags/zed) [View this post on daily.dev](https://daily.dev/posts/why-llms-can-t-really-build-software-zed-s-blog-ffv89ofc3) ```json {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]} {"@context":"https://schema.org","@type":"TechArticle","headline":"Why LLMs Can't Really Build Software — Zed's Blog","url":"https://daily.dev/posts/why-llms-can-t-really-build-software-zed-s-blog-ffv89ofc3","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/why-llms-can-t-really-build-software-zed-s-blog-ffv89ofc3"},"datePublished":"2025-08-14T13:04:24.479Z","dateModified":"2026-03-15T03:55:40.495Z","description":"Large Language Models excel at writing code but struggle with the iterative mental modeling that defines effective software engineering. While LLMs can...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/4df764e2b3f065b1eab7ae3c0264e94f?_a=AQAEulh","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/4df764e2b3f065b1eab7ae3c0264e94f?_a=AQAEulh","isAccessibleForFree":true,"articleSection":"Zed","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"Zed","logo":"https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/6048f0f184b149f394a08a0f835fd052","url":"https://daily.dev/sources/zed"},"commentCount":5,"discussionUrl":"https://daily.dev/posts/why-llms-can-t-really-build-software-zed-s-blog-ffv89ofc3","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":73},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":5}],"keywords":"ai-coding,llm,zed","timeRequired":"PT4M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Zed","item":"https://daily.dev/sources/zed"},{"@type":"ListItem","position":3,"name":"Why LLMs Can't Really Build Software — Zed's Blog"}]} {"@context":"https://schema.org","@type":"WebPage","@id":"https://daily.dev/posts/why-llms-can-t-really-build-software-zed-s-blog-ffv89ofc3","comment":[{"@type":"Comment","text":"This take is better than most.\nThere are so many bad takes out there, someone with a psychology degree, someone who has done fronted work, someone with an MBA, thinks they have the gotcha or even worse they are a linkedin poster, a substack pusher, an wanabe influencer or a thought-leader-poser looker for their first big break.\nAt the end of the day NONE of these people even know what an attention head is or can explain the FUNDAMENTALS of how their critique relates to a deep understanding of the technology and can prove that this gotcha isn’t cooked up–one part background bias, one-part superficial idea and a dash of hopium. I see this all the time!\nThis article does suffer from the same issues: pop our mental model onto the stack? just put more words into the context window? When I highlight some code and as it a question about that portion, the model is at least behaving like a human, ‘popping’ our mental model off the stack (not the proper psychological understanding I’m looking for, but I get it).\nSo it still doesn’t really show me how a proper understanding of these models relates to the critique. That said, it is getting at something that I think is right: above some complexity the models do fail. I just wish SOMEONE would show me why based on the architecture rather than observe and hope.","datePublished":"2025-08-30T04:40:07.429Z","url":"https://daily.dev/posts/fFV89OFC3#c-1VIh4zS58","author":{"@type":"Person","name":"whlsk34","url":"https://daily.dev/whlsk34","image":"https://media.daily.dev/image/upload/s--O0TOmw4y--/f_auto/v1715772965/public/noProfile"},"interactionStatistic":{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":5}},{"@type":"Comment","text":"Really? Algorithms from the 70s can’t fully build complex software projects?","datePublished":"2025-09-01T09:28:22.025Z","url":"https://daily.dev/posts/fFV89OFC3#c-S5mJhw4cG","author":{"@type":"Person","name":"Le Fä De Le Lö","url":"https://daily.dev/fabooy961","image":"https://media.daily.dev/image/upload/v1677218265/avatars/avatar_H6lLM2y9S4Yf8VCWicpd8.jpg"},"interactionStatistic":{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":3}},{"@type":"Comment","text":"Because they’re not AI?","datePublished":"2025-09-04T06:38:11.856Z","url":"https://daily.dev/posts/fFV89OFC3#c-suvyBmjJw","author":{"@type":"Person","name":"Joashua","url":"https://daily.dev/joashua","image":"https://media.daily.dev/image/upload/s--O0TOmw4y--/f_auto/v1715772965/public/noProfile"}}]} ```