--- title: How do you stay familiar with the code when it's written... description: As developers rely more on LLMs to write code, they risk losing intuitive familiarity with their own codebase. Several practical strategies help maintain code... canonical: https://daily.dev/posts/how-do-you-stay-familiar-with-the-code-when-it-s-written-by-an-llm--gtcifdlhr twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: How do you stay familiar with the code when it's written by an LLM? | daily.dev og:description: As developers rely more on LLMs to write code, they risk losing intuitive familiarity with their own codebase. Several practical strategies help maintain code... og:url: https://daily.dev/posts/how-do-you-stay-familiar-with-the-code-when-it-s-written-by-an-llm--gtcifdlhr og:image: https://api.daily.dev/og/posts/gTCIFdlHr.png og:image:alt: How do you stay familiar with the code when it's written by an LLM? 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. # How do you stay familiar with the code when it's written by an LLM? **[RUBYLAND](https://daily.dev/sources/rubyla)** · 10 min read · 2 upvotes · 1 comments ## Summary As developers rely more on LLMs to write code, they risk losing intuitive familiarity with their own codebase. Several practical strategies help maintain code understanding: deliberately making mistakes and seeking surprises, typing small changes yourself, asking probing questions about LLM-generated code, actively exploring the codebase in an editor rather than just reviewing diffs, generating HTML explainers for complex changes, and treating LLM output like a real PR review with inline comments. The core argument is that developers responsible for long-lived projects must actively cultivate code understanding rather than delegating it entirely to AI tools. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Questions this post answers ### How can I stay familiar with code that an LLM wrote for my project? Deliberately create friction instead of accepting smooth AI output: type small refinements yourself rather than delegating everything, ask an LLM to explain its choices and predict where changes will ripple, explore the code actively in an editor with jump-to-definition and breakpoints rather than passively reading a diff, and review AI-generated changes like a real pull request with inline comments before merging. _daily.dev surfaces practical workflows for keeping ownership of AI-assisted codebases as habits, not one-off tips._ ### What is the HTML explainer technique for reviewing large LLM-generated changes? It means asking the LLM to generate a single-page HTML file that explains the feature and its architecture, including diagrams, inline code snippets, and editor links to the relevant files. This gives a starting point for exploring a large or complex change, though it does not replace actually digging into and writing code to build real understanding. _Developers weighing new AI review workflows can track techniques like this one on daily.dev._ ## Community discussion Top comments from developers on daily.dev. **@elenamanolitsaki** · 2 upvotes > Very interesting, well-written, succinct and to the point :) It concerns a subject I think a lot about, and it's given me some lovely brain food to consider, in a very digestible way. Kudos to the author. ## Similar posts on daily.dev - [I can never fully embrace LLMs for code](https://daily.dev/posts/i-can-never-fully-embrace-llms-for-code-aw1v4ccnc) · Ibrahim Diallo · 15 upvotes · 3 comments - [Write code like a human will maintain it](https://daily.dev/posts/write-code-like-a-human-will-maintain-it-unvdxkwiz) · Hacker News · 1 upvotes · 0 comments - [How to use LLMs without driving your team mad](https://daily.dev/posts/how-to-use-llms-without-driving-your-team-mad-bcztby6jm) · thoughbot · 0 upvotes · 0 comments - [Comments Considered Harmful in the Age of LLMs](https://daily.dev/posts/comments-considered-harmful-in-the-age-of-llms-syfjihofv) · Yegor's Blog · 25 upvotes · 13 comments - [The most important thing when working with LLMs](https://daily.dev/posts/the-most-important-thing-when-working-with-llms-634in6fch) · Steve Klabnik · 30 upvotes · 1 comments --- Tags: [#llm](https://daily.dev/tags/llm), [#productivity](https://daily.dev/tags/productivity), [#ai-coding](https://daily.dev/tags/ai-coding), [#code-review](https://daily.dev/tags/code-review) [View this post on daily.dev](https://daily.dev/posts/how-do-you-stay-familiar-with-the-code-when-it-s-written-by-an-llm--gtcifdlhr) ```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":"How do you stay familiar with the code when it's written by an LLM?","url":"https://daily.dev/posts/how-do-you-stay-familiar-with-the-code-when-it-s-written-by-an-llm--gtcifdlhr","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/how-do-you-stay-familiar-with-the-code-when-it-s-written-by-an-llm--gtcifdlhr"},"datePublished":"2026-07-16T18:58:28.409Z","dateModified":"2026-09-14T07:26:36.090Z","description":"As developers rely more on LLMs to write code, they risk losing intuitive familiarity with their own codebase. Several practical strategies help maintain code...","image":"https://media.daily.dev/image/upload/s--CxzD6vbw--/f_auto/v1722860399/public/Placeholder%2005","thumbnailUrl":"https://media.daily.dev/image/upload/s--CxzD6vbw--/f_auto/v1722860399/public/Placeholder%2005","isAccessibleForFree":true,"articleSection":"RUBYLAND","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":"RUBYLAND","logo":"https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/rubyla","url":"https://daily.dev/sources/rubyla"},"commentCount":1,"discussionUrl":"https://daily.dev/posts/how-do-you-stay-familiar-with-the-code-when-it-s-written-by-an-llm--gtcifdlhr","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":2},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":1}],"keywords":"llm,productivity,ai-coding,code-review","timeRequired":"PT10M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"RUBYLAND","item":"https://daily.dev/sources/rubyla"},{"@type":"ListItem","position":3,"name":"How do you stay familiar with the code when it's written by an LLM?"}]} {"@context":"https://schema.org","@type":"WebPage","@id":"https://daily.dev/posts/how-do-you-stay-familiar-with-the-code-when-it-s-written-by-an-llm--gtcifdlhr","comment":[{"@type":"Comment","text":"Very interesting, well-written, succinct and to the point :) It concerns a subject I think a lot about, and it’s given me some lovely brain food to consider, in a very digestible way. Kudos to the author.","datePublished":"2026-07-17T08:02:34.661Z","url":"https://daily.dev/posts/gTCIFdlHr#c-5KbeVJ726","author":{"@type":"Person","name":"Elena Manolitsaki","url":"https://daily.dev/elenamanolitsaki","image":"https://avatars.githubusercontent.com/u/138771356?v=4"},"interactionStatistic":{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":2}}]} {"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/how-do-you-stay-familiar-with-the-code-when-it-s-written-by-an-llm--gtcifdlhr#faq","mainEntity":[{"@type":"Question","name":"How can I stay familiar with code that an LLM wrote for my project?","acceptedAnswer":{"@type":"Answer","text":"Deliberately create friction instead of accepting smooth AI output: type small refinements yourself rather than delegating everything, ask an LLM to explain its choices and predict where changes will ripple, explore the code actively in an editor with jump-to-definition and breakpoints rather than passively reading a diff, and review AI-generated changes like a real pull request with inline comments before merging. daily.dev surfaces practical workflows for keeping ownership of AI-assisted codebases as habits, not one-off tips."}},{"@type":"Question","name":"What is the HTML explainer technique for reviewing large LLM-generated changes?","acceptedAnswer":{"@type":"Answer","text":"It means asking the LLM to generate a single-page HTML file that explains the feature and its architecture, including diagrams, inline code snippets, and editor links to the relevant files. This gives a starting point for exploring a large or complex change, though it does not replace actually digging into and writing code to build real understanding. Developers weighing new AI review workflows can track techniques like this one on daily.dev."}}]} ```