--- title: Reviewing AI Code Is Not A Viable Argument | daily.dev description: A skeptical critique of the common argument that AI-generated code is safe as long as developers review it. Drawing on empirical research about code review... canonical: https://daily.dev/posts/reviewing-ai-code-is-not-a-viable-argument-ljrzvoc5t twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: Reviewing AI Code Is Not A Viable Argument | daily.dev og:description: A skeptical critique of the common argument that AI-generated code is safe as long as developers review it. Drawing on empirical research about code review... og:url: https://daily.dev/posts/reviewing-ai-code-is-not-a-viable-argument-ljrzvoc5t og:image: https://api.daily.dev/og/posts/LJRZvOC5t.png og:image:alt: Reviewing AI Code Is Not A Viable Argument 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. # Reviewing AI Code Is Not A Viable Argument **[Lobsters](https://daily.dev/sources/lobsters)** · 14 min read · 0 upvotes · 0 comments ## Summary A skeptical critique of the common argument that AI-generated code is safe as long as developers review it. Drawing on empirical research about code review effectiveness, the author argues that reviews become ineffective beyond 400 lines of code per hour and 1 hour per session, creating a hard ceiling on productivity gains from LLM coding assistants. The piece also cites emerging evidence that humans reviewing LLM-generated code are more confident yet find fewer defects than when reviewing human-written code. The author calls for rigorous empirical studies on human ability to review LLM output, rather than anecdotal endorsements, and is particularly critical of proponents who tout LLMs for generating hard-to-review code like shell scripts. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## 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 - [Why I remain a skeptic](https://daily.dev/posts/why-i-remain-a-skeptic-bpv99cftw) · Lobsters · 0 upvotes · 0 comments --- Tags: [#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/reviewing-ai-code-is-not-a-viable-argument-ljrzvoc5t) ```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":"Reviewing AI Code Is Not A Viable Argument","url":"https://daily.dev/posts/reviewing-ai-code-is-not-a-viable-argument-ljrzvoc5t","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/reviewing-ai-code-is-not-a-viable-argument-ljrzvoc5t"},"datePublished":"2026-07-19T00:18:16.394Z","dateModified":"2026-07-20T05:03:16.287Z","description":"A skeptical critique of the common argument that AI-generated code is safe as long as developers review it. Drawing on empirical research about code review...","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":"Lobsters","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":"Lobsters","logo":"https://media.daily.dev/image/upload/s--tl8v_Fku--/f_auto,t_logo/v1698841318/logos/lobste.jpg","url":"https://daily.dev/sources/lobsters"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/reviewing-ai-code-is-not-a-viable-argument-ljrzvoc5t","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"productivity,ai-coding,code-review","timeRequired":"PT14M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Lobsters","item":"https://daily.dev/sources/lobsters"},{"@type":"ListItem","position":3,"name":"Reviewing AI Code Is Not A Viable Argument"}]} ```