--- title: 3 myths about coding with AI that even experienced... description: Three common assumptions about AI-assisted coding are challenged using recent research. First, productivity gains from AI don't simply free up time for... canonical: https://daily.dev/posts/3-myths-about-coding-with-ai-that-even-experienced-developers-still-believe-gnanljwtz twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: 3 myths about coding with AI that even experienced developers still believe | daily.dev og:description: Three common assumptions about AI-assisted coding are challenged using recent research. First, productivity gains from AI don't simply free up time for... og:url: https://daily.dev/posts/3-myths-about-coding-with-ai-that-even-experienced-developers-still-believe-gnanljwtz og:image: https://api.daily.dev/og/posts/GnaNLjwTZ.png og:image:alt: 3 myths about coding with AI that even experienced developers still believe 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. # 3 myths about coding with AI that even experienced developers still believe **[XDA Developers](https://daily.dev/sources/xda-developers)** · 4 min read · 0 upvotes · 0 comments ## Summary Three common assumptions about AI-assisted coding are challenged using recent research. First, productivity gains from AI don't simply free up time for higher-order thinking: while 84% of surveyed engineers reported improved productivity, the share reporting a worsened developer experience nearly doubled from 14% to 27%, with declines concentrated in flow state and cognitive load. Second, a September 2025 study from Toronto Metropolitan University found GitHub Copilot's Code Review feature frequently missed critical vulnerabilities like SQL injection and XSS, focusing instead on style issues, reinforcing the need for manual security audits. Third, the 'AI is just autocomplete' view is outdated: agentic tools like Claude Code and Codex CLI can reason through multi-step tasks, and in an Epoch AI/METR benchmark, Claude Opus 4.6 autonomously reimplemented a ~16,000-line Go bioinformatics toolkit without source access, passing 2,001 end-to-end tests. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Questions this post answers ### Does using AI coding assistants actually make developers more productive? Most engineers still report productivity gains, with 84% saying AI improved their output, but the share reporting a worsened developer experience in at least one dimension nearly doubled from 14% to 27%. The decline concentrated in flow state and cognitive load, indicating that time saved writing code often gets redirected into verifying that code rather than higher-order work. _Developers weighing AI's real productivity impact can find studies like this through daily.dev._ ### Can GitHub Copilot's code review feature catch security vulnerabilities like SQL injection? Testing against curated vulnerable code samples from open-source projects found that Copilot's Code Review frequently failed to identify critical vulnerabilities such as SQL injection, cross-site scripting, and insecure deserialization, instead focusing feedback on coding style and typographical issues. Researchers from Toronto Metropolitan University who ran the study recommend retaining manual code audits for software security. _Teams deciding how much to trust AI code review can track findings like this on daily.dev._ ### Can AI coding agents like Claude Opus 4.6 handle large, complex programming tasks autonomously? Yes, in a benchmark jointly developed by Epoch AI and METR, Claude Opus 4.6 autonomously reimplemented a bioinformatics toolkit of roughly 16,000 lines of Go with more than 40 commands, without access to the original source code, by inferring its behavior and passing 2,001 end-to-end tests. _Developers gauging how far agentic coding has advanced can follow benchmarks like this on daily.dev._ ## Similar posts on daily.dev - [AI-Powered Coding Without Developers: Reality or Hype?](https://daily.dev/posts/ai-powered-coding-without-developers-reality-or-hype--kptuidpxi) · Medium · 0 upvotes · 0 comments - [How AI coding makes developers 56% faster and 19% slower](https://daily.dev/posts/how-ai-coding-makes-developers-56-faster-and-19-slower-t4jx0ry0u) · The New Stack · 0 upvotes · 0 comments - [AI pair coding: Fast, but devs don't question the bot](https://daily.dev/posts/ai-pair-coding-fast-but-devs-don-t-question-the-bot-j5bubpnx5) · The Register · 0 upvotes · 0 comments - [Coders are refusing to work without AI — and that could come back to bite them](https://daily.dev/posts/coders-are-refusing-to-work-without-ai-and-that-could-come-back-to-bite-them-fsaqaup1r) · TechCrunch · 0 upvotes · 0 comments --- Tags: [#github](https://daily.dev/tags/github), [#productivity](https://daily.dev/tags/productivity), [#ai-coding](https://daily.dev/tags/ai-coding), [#claude-code](https://daily.dev/tags/claude-code), [#code-review](https://daily.dev/tags/code-review) [View this post on daily.dev](https://daily.dev/posts/3-myths-about-coding-with-ai-that-even-experienced-developers-still-believe-gnanljwtz) ```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":"3 myths about coding with AI that even experienced developers still believe","url":"https://daily.dev/posts/3-myths-about-coding-with-ai-that-even-experienced-developers-still-believe-gnanljwtz","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/3-myths-about-coding-with-ai-that-even-experienced-developers-still-believe-gnanljwtz"},"datePublished":"2026-08-13T21:05:12.941Z","dateModified":"2026-09-14T07:17:18.318Z","description":"Three common assumptions about AI-assisted coding are challenged using recent research. First, productivity gains from AI don't simply free up time for...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/a7ca43796adbe34f80cf61fe936ea9ed?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/a7ca43796adbe34f80cf61fe936ea9ed?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"XDA Developers","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":"XDA Developers","logo":"https://media.daily.dev/image/upload/s--kCg6yyAP--/f_auto,q_auto/v1774964407/logos/xda-developers?_a=BAMAMiWQ0","url":"https://daily.dev/sources/xda-developers"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/3-myths-about-coding-with-ai-that-even-experienced-developers-still-believe-gnanljwtz","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"github,productivity,ai-coding,claude-code,code-review","timeRequired":"PT4M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"XDA Developers","item":"https://daily.dev/sources/xda-developers"},{"@type":"ListItem","position":3,"name":"3 myths about coding with AI that even experienced developers still believe"}]} {"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/3-myths-about-coding-with-ai-that-even-experienced-developers-still-believe-gnanljwtz#faq","mainEntity":[{"@type":"Question","name":"Does using AI coding assistants actually make developers more productive?","acceptedAnswer":{"@type":"Answer","text":"Most engineers still report productivity gains, with 84% saying AI improved their output, but the share reporting a worsened developer experience in at least one dimension nearly doubled from 14% to 27%. The decline concentrated in flow state and cognitive load, indicating that time saved writing code often gets redirected into verifying that code rather than higher-order work. Developers weighing AI's real productivity impact can find studies like this through daily.dev."}},{"@type":"Question","name":"Can GitHub Copilot's code review feature catch security vulnerabilities like SQL injection?","acceptedAnswer":{"@type":"Answer","text":"Testing against curated vulnerable code samples from open-source projects found that Copilot's Code Review frequently failed to identify critical vulnerabilities such as SQL injection, cross-site scripting, and insecure deserialization, instead focusing feedback on coding style and typographical issues. Researchers from Toronto Metropolitan University who ran the study recommend retaining manual code audits for software security. Teams deciding how much to trust AI code review can track findings like this on daily.dev."}},{"@type":"Question","name":"Can AI coding agents like Claude Opus 4.6 handle large, complex programming tasks autonomously?","acceptedAnswer":{"@type":"Answer","text":"Yes, in a benchmark jointly developed by Epoch AI and METR, Claude Opus 4.6 autonomously reimplemented a bioinformatics toolkit of roughly 16,000 lines of Go with more than 40 commands, without access to the original source code, by inferring its behavior and passing 2,001 end-to-end tests. Developers gauging how far agentic coding has advanced can follow benchmarks like this on daily.dev."}}]} ```