--- title: The line between Genius and Insanity | daily.dev description: A reaction video dissects a series of viral blog posts by a developer named Steve who claims to run a 600,000-line bash custom harness in Emacs, spends roughly... canonical: https://daily.dev/posts/the-line-between-genius-and-insanity-khxsh1o6u twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: The line between Genius and Insanity | daily.dev og:description: A reaction video dissects a series of viral blog posts by a developer named Steve who claims to run a 600,000-line bash custom harness in Emacs, spends roughly... og:url: https://daily.dev/posts/the-line-between-genius-and-insanity-khxsh1o6u og:image: https://api.daily.dev/og/posts/KhXSh1O6u.png og:image:alt: The line between Genius and Insanity 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. # The line between Genius and Insanity **[ThePrimeTime](https://daily.dev/sources/primeagen)** · 23 min read · 2 upvotes · 0 comments ## Summary A reaction video dissects a series of viral blog posts by a developer named Steve who claims to run a 600,000-line bash custom harness in Emacs, spends roughly $1.5 million a year on Claude Max Pro subscriptions and API tokens to build a solo MMO called Wyvern, and predicts CI/CD will be dead within a year. The reviewer praises the idea of lightweight custom harnesses but criticizes the extreme token spend as a case of solving a $100 problem with $100,000, mocks the second article's claim that AI agents are people and that ending a session is 'murder,' and then live-plays the resulting game, finding it laggy, buggy, and unimpressive despite the massive spend, concluding it's a cautionary tale about AI psychosis and misplaced engineering priorities rather than a genuine glimpse of the future. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Questions this post answers ### Is CI/CD going to be replaced by AI agents crawling and testing applications instead of automated pipelines? No credible evidence supports CI/CD disappearing within a year, despite claims to that effect. A few good end-to-end tests are valuable, but thousands of them tend to create cascading failures and unreliable results, and unit tests, linting, and type checking remain essential even when agents are used for higher-level testing. CI/CD may evolve or shrink in scope, but it is not going away. _Developers weighing how much to trust agentic testing over traditional CI/CD pipelines can track these debates on daily.dev._ ### How much does it cost to run 21 Claude Code Max Pro subscriptions for a full month? Running 21 Claude Code Max Pro subscriptions, growing by two per week, costs approximately $122,000 per month, which extrapolates to roughly $1.5 million a year when measured at equivalent API pricing rather than subscription rates. This was the setup one developer used to power a custom 600,000-line bash-based multi-agent harness for building an MMO. _Anyone budgeting for heavy multi-agent AI development workflows can compare real-world spend figures like these on daily.dev._ --- Tags: [#ai-agents](https://daily.dev/tags/ai-agents), [#cicd](https://daily.dev/tags/cicd), [#claude-code](https://daily.dev/tags/claude-code), [#vibe-coding](https://daily.dev/tags/vibe-coding) [View this post on daily.dev](https://daily.dev/posts/the-line-between-genius-and-insanity-khxsh1o6u) ```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":"The line between Genius and Insanity","url":"https://daily.dev/posts/the-line-between-genius-and-insanity-khxsh1o6u","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/the-line-between-genius-and-insanity-khxsh1o6u"},"datePublished":"2026-08-31T13:09:06.059Z","dateModified":"2026-09-13T20:36:04.531Z","description":"A reaction video dissects a series of viral blog posts by a developer named Steve who claims to run a 600,000-line bash custom harness in Emacs, spends roughly...","image":"https://i.ytimg.com/vi/NuktXEikxU8/sddefault.jpg","thumbnailUrl":"https://i.ytimg.com/vi/NuktXEikxU8/sddefault.jpg","isAccessibleForFree":true,"articleSection":"ThePrimeTime","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":"ThePrimeTime","logo":"https://media.daily.dev/image/upload/s--J5-GjDeo--/f_auto/v1704628081/logos/primeagen.jpg","url":"https://daily.dev/sources/primeagen"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/the-line-between-genius-and-insanity-khxsh1o6u","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":2},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"ai-agents,cicd,claude-code,vibe-coding","timeRequired":"PT23M","video":{"@type":"VideoObject","name":"The line between Genius and Insanity","description":"A reaction video dissects a series of viral blog posts by a developer named Steve who claims to run a 600,000-line bash custom harness in Emacs, spends roughly...","thumbnailUrl":"https://i.ytimg.com/vi/NuktXEikxU8/sddefault.jpg","uploadDate":"2026-08-31T13:09:06.059Z","duration":"PT23M","url":"https://api.daily.dev/r/KhXSh1O6u","embedUrl":"https://www.youtube.com/embed/NuktXEikxU8"}} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"ThePrimeTime","item":"https://daily.dev/sources/primeagen"},{"@type":"ListItem","position":3,"name":"The line between Genius and Insanity"}]} {"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/the-line-between-genius-and-insanity-khxsh1o6u#faq","mainEntity":[{"@type":"Question","name":"Is CI/CD going to be replaced by AI agents crawling and testing applications instead of automated pipelines?","acceptedAnswer":{"@type":"Answer","text":"No credible evidence supports CI/CD disappearing within a year, despite claims to that effect. A few good end-to-end tests are valuable, but thousands of them tend to create cascading failures and unreliable results, and unit tests, linting, and type checking remain essential even when agents are used for higher-level testing. CI/CD may evolve or shrink in scope, but it is not going away. Developers weighing how much to trust agentic testing over traditional CI/CD pipelines can track these debates on daily.dev."}},{"@type":"Question","name":"How much does it cost to run 21 Claude Code Max Pro subscriptions for a full month?","acceptedAnswer":{"@type":"Answer","text":"Running 21 Claude Code Max Pro subscriptions, growing by two per week, costs approximately $122,000 per month, which extrapolates to roughly $1.5 million a year when measured at equivalent API pricing rather than subscription rates. This was the setup one developer used to power a custom 600,000-line bash-based multi-agent harness for building an MMO. Anyone budgeting for heavy multi-agent AI development workflows can compare real-world spend figures like these on daily.dev."}}]} ```