--- title: On learning programming in an age of LLMs | daily.dev description: A veteran developer responds at length to a reader's letter about learning programming in the LLM era. The reader built a large TypeScript/PostgreSQL system... canonical: https://daily.dev/posts/on-learning-programming-in-an-age-of-llms-g9mvri3xw twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: On learning programming in an age of LLMs | daily.dev og:description: A veteran developer responds at length to a reader's letter about learning programming in the LLM era. The reader built a large TypeScript/PostgreSQL system... og:url: https://daily.dev/posts/on-learning-programming-in-an-age-of-llms-g9mvri3xw og:image: https://api.daily.dev/og/posts/G9mVRi3XW.png og:image:alt: On learning programming in an age of LLMs 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. # On learning programming in an age of LLMs **[ploeh blog](https://daily.dev/sources/ploeh)** · 10 min read · 0 upvotes · 0 comments ## Summary A veteran developer responds at length to a reader's letter about learning programming in the LLM era. The reader built a large TypeScript/PostgreSQL system with AI assistance but now feels it exceeds their own understanding, prompting questions about whether to pause and learn fundamentals or keep building. The author reflects on his own ambivalence toward AI, his economics background and concerns about mass knowledge-worker unemployment, and how he personally learned programming (books, examples, trial and error) over thirty years. He argues that human learning speed, not teaching materials, is the real bottleneck, and that he avoids asking LLMs unfalsifiable questions like 'what should I learn next', preferring verifiable ones like code-improvement suggestions. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Questions this post answers ### Should I stop and learn programming fundamentals if I built a large system mostly with AI assistance and don't fully understand it? There is no single right answer, but a veteran developer with thirty years of experience suggests it depends on how much foundational knowledge you already have. Historically, stepping back to systematically learn fundamentals worked well for careers launched decades ago, but reaching real competency took years of experience, and it is unclear whether that same approach is fast enough today given how quickly AI lets people build. _Developers weighing AI-built projects against foundational gaps can find similar debates and experience reports on daily.dev._ ### How should I use LLMs when learning a new programming skill without risking bad information? Ask LLMs falsifiable, verifiable questions rather than open-ended ones. A question like whether a piece of code can be made more succinct yields a checkable answer that either works or doesn't, whereas a question like what to learn next has no way to be verified and is best avoided since language models can confidently produce incorrect information. _Programmers refining how they lean on AI tools while learning can track similar takes on daily.dev._ ## Similar posts on daily.dev - ['AI' Sucks the Joy Out of Programming](https://daily.dev/posts/ai-sucks-the-joy-out-of-programming-tbcpgmlje) · Lobsters · 146 upvotes · 43 comments - [The Future of Software Development is Software Developers](https://daily.dev/posts/the-future-of-software-development-is-software-developers-clpbexose) · Hacker News · 8 upvotes · 2 comments --- Tags: [#career](https://daily.dev/tags/career), [#llm](https://daily.dev/tags/llm), [#ai-coding](https://daily.dev/tags/ai-coding) [View this post on daily.dev](https://daily.dev/posts/on-learning-programming-in-an-age-of-llms-g9mvri3xw) ```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":"On learning programming in an age of LLMs","url":"https://daily.dev/posts/on-learning-programming-in-an-age-of-llms-g9mvri3xw","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/on-learning-programming-in-an-age-of-llms-g9mvri3xw"},"datePublished":"2026-09-16T05:36:33.874Z","dateModified":"2026-09-16T05:36:53.972Z","description":"A veteran developer responds at length to a reader's letter about learning programming in the LLM era. The reader built a large TypeScript/PostgreSQL system...","image":"https://media.daily.dev/image/upload/s--OHB84bZF--/f_auto/v1722860399/public/Placeholder%2010","thumbnailUrl":"https://media.daily.dev/image/upload/s--OHB84bZF--/f_auto/v1722860399/public/Placeholder%2010","isAccessibleForFree":true,"articleSection":"ploeh blog","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":"ploeh blog","logo":"https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/0645fe7a0b9f40ba9ef17f7a7b49e893","url":"https://daily.dev/sources/ploeh"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/on-learning-programming-in-an-age-of-llms-g9mvri3xw","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"career,llm,ai-coding","timeRequired":"PT10M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"ploeh blog","item":"https://daily.dev/sources/ploeh"},{"@type":"ListItem","position":3,"name":"On learning programming in an age of LLMs"}]} {"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/on-learning-programming-in-an-age-of-llms-g9mvri3xw#faq","mainEntity":[{"@type":"Question","name":"Should I stop and learn programming fundamentals if I built a large system mostly with AI assistance and don't fully understand it?","acceptedAnswer":{"@type":"Answer","text":"There is no single right answer, but a veteran developer with thirty years of experience suggests it depends on how much foundational knowledge you already have. Historically, stepping back to systematically learn fundamentals worked well for careers launched decades ago, but reaching real competency took years of experience, and it is unclear whether that same approach is fast enough today given how quickly AI lets people build. Developers weighing AI-built projects against foundational gaps can find similar debates and experience reports on daily.dev."}},{"@type":"Question","name":"How should I use LLMs when learning a new programming skill without risking bad information?","acceptedAnswer":{"@type":"Answer","text":"Ask LLMs falsifiable, verifiable questions rather than open-ended ones. A question like whether a piece of code can be made more succinct yields a checkable answer that either works or doesn't, whereas a question like what to learn next has no way to be verified and is best avoided since language models can confidently produce incorrect information. Programmers refining how they lean on AI tools while learning can track similar takes on daily.dev."}}]} ```