--- title: Get the hell out of the LLM as soon as possible | daily.dev description: Large Language Models (LLMs) should not be used for decision-making or implementing business logic due to their poor performance in these areas. Instead, LLMs... canonical: https://daily.dev/posts/get-the-hell-out-of-the-llm-as-soon-as-possible-aakiicaxn twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: Get the hell out of the LLM as soon as possible | daily.dev og:description: Large Language Models (LLMs) should not be used for decision-making or implementing business logic due to their poor performance in these areas. Instead, LLMs... og:url: https://daily.dev/posts/get-the-hell-out-of-the-llm-as-soon-as-possible-aakiicaxn og:image: https://api.daily.dev/og/posts/aAkiICAxN.png og:image:alt: Get the hell out of the LLM as soon as possible 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. # Get the hell out of the LLM as soon as possible **[Hacker News](https://daily.dev/sources/hn)** · 5 min read · 446 upvotes · 46 comments ## Summary Large Language Models (LLMs) should not be used for decision-making or implementing business logic due to their poor performance in these areas. Instead, LLMs should be employed as an interface for translating user inputs into API calls, with the actual logic handled by specialized systems. This approach enhances performance, debugging, and reliability. LLMs are best utilized for tasks involving transformation, interpretation, and communication, rather than maintaining critical application state. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Community discussion Top comments from developers on daily.dev. **@daniel8000** · 70 upvotes > They insist on AI everywhere, because they despise decent work. If you are professional, and you value decent work, stay away from LLM. But if you are just a grifter, Jump quickly on hype train and ride to the bubble pop. You have several weeks left. **@manojkumar77** · 22 upvotes > Honestly LLM's are great; They are still not human level, but the breadth of which they are 'near' human level is insane and lets you glimpse at what a super intelligence would actually be like. > > Yes they aren't perfect, yes the almost always underperform a trained professional in any given field; > > But that doesn't mean they're dumb, stupid, worthless, scams; or even overhyped. > > That'd be like looking at the first plank with round rocks underneath it and claiming "haha i can run faster, it's so dumb, you're dumb for doing it, haha so much wasted time with this plank with round rocks... **@alexanderbaggett** · 18 upvotes > I use Ai's for spot checks, code reviews, and creating additional unit tests where the pattern of what a good unit test is already set. **@danielarzanipour** · 13 upvotes > I take a picture of recipes that don't have enough steps or aren't descriptive enough for me and ask AI to add more precise steps so that I have a better chance at not screwing up what I'm cooking... **@nelcapetown** · 6 upvotes > I'm afraid I have to disagree that using AI makes you lazy. I don't ask for the solution to a problem, but rather have an in-depth discussion. It is a great tool for quickly coming to grips with new frameworks or large legacy code base with inadequate documentation. > > Challenge AI and ask probing questions. That way you collaborate and come to the optimal solution. Many "But what if..." questions. > > > Remember that it is a conversation and not just a solution dispenser. > Frequently check the suggestions against your own knowledge and other non-AI sources. > > I think if you are completely... ## Similar posts on daily.dev - [Don’t just attend KubeCon \+ CloudNativeCon, Merge Forward your experience\!](https://daily.dev/posts/don-t-just-attend-kubecon-cloudnativecon-merge-forward-your-experience--l0rpp73x8) · CNCF · 1 upvotes · 0 comments - [Announcing H2 2026 KCDs](https://daily.dev/posts/announcing-h2-2026-kcds-m96goajm1) · CNCF · 1 upvotes · 0 comments - [Two months of Open Community Groups](https://daily.dev/posts/two-months-of-open-community-groups-asf52zhbs) · CNCF · 0 upvotes · 0 comments - [CNCF Unveils Schedule for KubeCon \+ CloudNativeCon Europe 2026](https://daily.dev/posts/cncf-unveils-schedule-for-kubecon-cloudnativecon-europe-2026-ikhcoa5cb) · CNCF · 2 upvotes · 0 comments - [CNCF Debuts KubeCon \+ CloudNativeCon Japan 2026 Schedule](https://daily.dev/posts/cncf-debuts-kubecon-cloudnativecon-japan-2026-schedule-xp5pyudub) · CNCF · 1 upvotes · 0 comments --- Tags: [#ai](https://daily.dev/tags/ai), [#machine-learning](https://daily.dev/tags/machine-learning), [#game-development](https://daily.dev/tags/game-development), [#llm](https://daily.dev/tags/llm) [View this post on daily.dev](https://daily.dev/posts/get-the-hell-out-of-the-llm-as-soon-as-possible-aakiicaxn) ```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":"Get the hell out of the LLM as soon as possible","url":"https://daily.dev/posts/get-the-hell-out-of-the-llm-as-soon-as-possible-aakiicaxn","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/get-the-hell-out-of-the-llm-as-soon-as-possible-aakiicaxn"},"datePublished":"2025-04-01T03:50:17.576Z","dateModified":"2025-04-01T03:50:33.582Z","description":"Large Language Models (LLMs) should not be used for decision-making or implementing business logic due to their poor performance in these areas. Instead, LLMs...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/a08b56be2b5d693e63ab6f1eb2343b19?_a=AQAEuj9","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/a08b56be2b5d693e63ab6f1eb2343b19?_a=AQAEuj9","isAccessibleForFree":true,"articleSection":"Hacker News","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":"Hacker News","logo":"https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/hn","url":"https://daily.dev/sources/hn"},"commentCount":46,"discussionUrl":"https://daily.dev/posts/get-the-hell-out-of-the-llm-as-soon-as-possible-aakiicaxn","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":446},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":46}],"keywords":"ai,machine-learning,game-development,llm","timeRequired":"PT5M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Hacker News","item":"https://daily.dev/sources/hn"},{"@type":"ListItem","position":3,"name":"Get the hell out of the LLM as soon as possible"}]} {"@context":"https://schema.org","@type":"WebPage","@id":"https://daily.dev/posts/get-the-hell-out-of-the-llm-as-soon-as-possible-aakiicaxn","comment":[{"@type":"Comment","text":"They insist on AI everywhere, because they despise decent work. If you are professional, and you value decent work, stay away from LLM. But if you are just a grifter, Jump quickly on hype train and ride to the bubble pop. You have several weeks left.","datePublished":"2025-04-13T16:31:27.636Z","url":"https://daily.dev/posts/aAkiICAxN#c-CKpCFFCN2","author":{"@type":"Person","name":"Daniel","url":"https://daily.dev/daniel8000","image":"https://media.daily.dev/image/upload/s--F_RltCZK--/f_auto/v1738746891/avatars/avatar_SOwG1kJqf6HK6TkGmZH45"},"interactionStatistic":{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":70}},{"@type":"Comment","text":"Honestly LLM’s are great; They are still not human level, but the breadth of which they are ‘near’ human level is insane and lets you glimpse at what a super intelligence would actually be like.\nYes they aren’t perfect, yes the almost always underperform a trained professional in any given field;\nBut that doesn’t mean they’re dumb, stupid, worthless, scams; or even overhyped.\nThat’d be like looking at the first plank with round rocks underneath it and claiming “haha i can run faster, it’s so dumb, you’re dumb for doing it, haha so much wasted time with this plank with round rocks underneath!”","datePublished":"2025-04-16T09:28:44.526Z","url":"https://daily.dev/posts/aAkiICAxN#c-wk36C8gOM","author":{"@type":"Person","name":"Manoj Kumar","url":"https://daily.dev/manojkumar77","image":"https://lh3.googleusercontent.com/a/ACg8ocJ4xR4xW0Fj6jZ74ZD6mKyjItB0LgUAdZ3FXetM7Xk1ffcTMOs=s96-c"},"interactionStatistic":{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":22}},{"@type":"Comment","text":"I use Ai’s for spot checks, code reviews, and creating additional unit tests where the pattern of what a good unit test is already set.","datePublished":"2025-04-15T14:29:11.107Z","url":"https://daily.dev/posts/aAkiICAxN#c-YJ2lhXLUa","author":{"@type":"Person","name":"Alexander Baggett","url":"https://daily.dev/alexanderbaggett","image":"https://lh3.googleusercontent.com/a/ACg8ocIQI9dd4TBSovzJuHHWqDsIUtL9Gm4y-FoNBn4bKuTiuR-hpPKZIA=s96-c"},"interactionStatistic":{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":18}},{"@type":"Comment","text":"I take a picture of recipes that don’t have enough steps or aren’t descriptive enough for me and ask AI to add more precise steps so that I have a better chance at not screwing up what I’m cooking…","datePublished":"2025-04-16T03:42:40.371Z","url":"https://daily.dev/posts/aAkiICAxN#c-7qt0n347L","author":{"@type":"Person","name":"Daniel Arzanipour","url":"https://daily.dev/danielarzanipour","image":"https://lh3.googleusercontent.com/a/ACg8ocIoyXhwAKfu9ZcSVRLK0YqOAp1c6U-E6IGuiHeG1BjTT2PkQg=s96-c"},"interactionStatistic":{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":13}},{"@type":"Comment","text":"I’m afraid I have to disagree that using AI makes you lazy. I don’t ask for the solution to a problem, but rather have an in-depth discussion. It is a great tool for quickly coming to grips with new frameworks or large legacy code base with inadequate documentation.\nChallenge AI and ask probing questions. That way you collaborate and come to the optimal solution. Many “But what if…” questions.\nRemember that it is a conversation and not just a solution dispenser.\nFrequently check the suggestions against your own knowledge and other non-AI sources.\nI think if you are completely averse to AI then you have fewer years left in the job market than your colleague who grows to become an expert at getting the best out of AI and confirm that against other sources. Uses it to enhance their own knowledge and provide output that is more rounded and in-depth than what would be possible without AI.","datePublished":"2025-04-17T01:24:38.838Z","url":"https://daily.dev/posts/aAkiICAxN#c-cjAbeDuSE","author":{"@type":"Person","name":"Nel Prinsloo","url":"https://daily.dev/nelcapetown","image":"https://media.daily.dev/image/upload/s--fT55qQ5w--/f_auto/v1744851849/avatars/avatar_2cf5fbd0d06c480eabe46f6c2e7dc7aa"},"interactionStatistic":{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":6}}]} ```