--- title: Getting good at AI takes time and practice | daily.dev description: Getting good at AI requires durable, long-term skills, not just clever tricks that become obsolete with new models. Skilled users learn to supply missing... canonical: https://daily.dev/posts/getting-good-at-ai-takes-time-and-practice-fhr1xjocm twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: Getting good at AI takes time and practice | daily.dev og:description: Getting good at AI requires durable, long-term skills, not just clever tricks that become obsolete with new models. Skilled users learn to supply missing... og:url: https://daily.dev/posts/getting-good-at-ai-takes-time-and-practice-fhr1xjocm og:image: https://api.daily.dev/og/posts/fHr1xjocm.png og:image:alt: Getting good at AI takes time and practice 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. # Getting good at AI takes time and practice **[sean goedecke](https://daily.dev/sources/seangoedecke)** · 8 min read · 0 upvotes · 0 comments ## Summary Getting good at AI requires durable, long-term skills, not just clever tricks that become obsolete with new models. Skilled users learn to supply missing context, know which tasks a model handles well versus poorly, and recognize the specific mistakes AI-generated code tends to make, like unnecessary over-engineering or made-up requirements. One example: GitHub Copilot can install its own MCP servers if you just ask it to. The author argues these skills will stay useful through software's 'centaur age', a period of human-AI collaboration that may last decades, much like React skills remained valuable despite early predictions of obsolescence. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Questions this post answers ### Can GitHub Copilot install its own MCP servers instead of me setting them up manually? Yes, you can simply ask GitHub Copilot to install its own MCP servers rather than configuring them yourself. One developer initially struggled to set up MCP servers for Copilot before realizing he could just ask the agent to handle the installation directly, turning a manual setup task into a prompted action. _daily.dev surfaces practical agent workflow tricks like this for developers configuring MCP setups._ ### What kinds of mistakes are common in AI-generated code that aren't common in human-written code? AI-generated code rarely has off-by-one errors, which are common in human code, but it frequently shows misalignment mistakes instead: over-engineering areas that aren't actually important, or trading off real requirements to satisfy made-up ones. Code reviewers should be especially suspicious of new mutexes in AI-generated code, since these are often added for insignificant edge cases despite looking well-commented and sophisticated. _Developers reviewing AI-written pull requests can track these review patterns through daily.dev._ ## Similar posts on daily.dev - [Will AI Replace Junior Developers?](https://daily.dev/posts/will-ai-replace-junior-developers--u3yvzurbt) · C\# Corner · 8 upvotes · 2 comments - [What to Learn in the AI Era: Skills That Will Actually Matter for the Next Decade](https://daily.dev/posts/what-to-learn-in-the-ai-era-skills-that-will-actually-matter-for-the-next-decade-mnmwovbnd) · Medium · 12 upvotes · 1 comments - [Tales from the pit: AI and the software engineer](https://daily.dev/posts/tales-from-the-pit-ai-and-the-software-engineer-jbhd4bno1) · The Register · 0 upvotes · 0 comments --- Tags: [#github](https://daily.dev/tags/github), [#ai-coding](https://daily.dev/tags/ai-coding), [#mcp](https://daily.dev/tags/mcp), [#prompt-engineering](https://daily.dev/tags/prompt-engineering), [#code-review](https://daily.dev/tags/code-review) [View this post on daily.dev](https://daily.dev/posts/getting-good-at-ai-takes-time-and-practice-fhr1xjocm) ```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":"Getting good at AI takes time and practice","url":"https://daily.dev/posts/getting-good-at-ai-takes-time-and-practice-fhr1xjocm","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/getting-good-at-ai-takes-time-and-practice-fhr1xjocm"},"datePublished":"2026-10-28T10:11:25.698Z","dateModified":"2026-10-28T10:11:51.995Z","description":"Getting good at AI requires durable, long-term skills, not just clever tricks that become obsolete with new models. Skilled users learn to supply missing...","image":"https://media.daily.dev/image/upload/s--VDukGCjf--/f_auto/v1722860399/public/Placeholder%2002","thumbnailUrl":"https://media.daily.dev/image/upload/s--VDukGCjf--/f_auto/v1722860399/public/Placeholder%2002","isAccessibleForFree":true,"articleSection":"sean goedecke","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":"sean goedecke","logo":"https://media.daily.dev/image/upload/s--WNgiZyDx--/f_auto,q_auto/v1765713419/logos/seangoedecke","url":"https://daily.dev/sources/seangoedecke"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/getting-good-at-ai-takes-time-and-practice-fhr1xjocm","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"github,ai-coding,mcp,prompt-engineering,code-review","timeRequired":"PT8M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"sean goedecke","item":"https://daily.dev/sources/seangoedecke"},{"@type":"ListItem","position":3,"name":"Getting good at AI takes time and practice"}]} {"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/getting-good-at-ai-takes-time-and-practice-fhr1xjocm#faq","mainEntity":[{"@type":"Question","name":"Can GitHub Copilot install its own MCP servers instead of me setting them up manually?","acceptedAnswer":{"@type":"Answer","text":"Yes, you can simply ask GitHub Copilot to install its own MCP servers rather than configuring them yourself. One developer initially struggled to set up MCP servers for Copilot before realizing he could just ask the agent to handle the installation directly, turning a manual setup task into a prompted action. daily.dev surfaces practical agent workflow tricks like this for developers configuring MCP setups."}},{"@type":"Question","name":"What kinds of mistakes are common in AI-generated code that aren't common in human-written code?","acceptedAnswer":{"@type":"Answer","text":"AI-generated code rarely has off-by-one errors, which are common in human code, but it frequently shows misalignment mistakes instead: over-engineering areas that aren't actually important, or trading off real requirements to satisfy made-up ones. Code reviewers should be especially suspicious of new mutexes in AI-generated code, since these are often added for insignificant edge cases despite looking well-commented and sophisticated. Developers reviewing AI-written pull requests can track these review patterns through daily.dev."}}]} ```