--- title: The Banned Phrase List Made My AI Worse — Here’s Why description: Adding a 'banned phrase list' to LLM prompts backfires because listing forbidden tokens loads them into the context window, increasing their activation and... canonical: https://daily.dev/posts/the-banned-phrase-list-made-my-ai-worse-here-s-why-a7gs6bnbf twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: The Banned Phrase List Made My AI Worse — Here’s Why | daily.dev og:description: Adding a 'banned phrase list' to LLM prompts backfires because listing forbidden tokens loads them into the context window, increasing their activation and... og:url: https://daily.dev/posts/the-banned-phrase-list-made-my-ai-worse-here-s-why-a7gs6bnbf og:image: https://api.daily.dev/og/posts/A7gS6bNBF.png og:image:alt: The Banned Phrase List Made My AI Worse — Here’s Why 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 Banned Phrase List Made My AI Worse — Here’s Why **[Medium](https://daily.dev/sources/medium_js)** · 4 min read · 0 upvotes · 0 comments ## Summary Adding a 'banned phrase list' to LLM prompts backfires because listing forbidden tokens loads them into the context window, increasing their activation and making the model generate them more. Testing across 10 scenarios showed 29 generic phrases with a banned list vs. 17 without. The fix is to replace negative constraints with 3–5 positive examples of the desired output style. This principle applies beyond creative writing to coding, summarization, and classification tasks. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Similar posts on daily.dev - [I stripped my prompts down after OpenAI's new guide, and my results got better](https://daily.dev/posts/i-stripped-my-prompts-down-after-openai-s-new-guide-and-my-results-got-better-y9gjbkpk9) · XDA Developers · 1 upvotes · 0 comments - [We Kept Adding Context to Our AI Feature. It Kept Getting Worse](https://daily.dev/posts/we-kept-adding-context-to-our-ai-feature-it-kept-getting-worse-ahgwujixf) · Medium · 0 upvotes · 0 comments - [Is This Slop? Detecting AI-Generated Content Without a Model](https://daily.dev/posts/is-this-slop-detecting-ai-generated-content-without-a-model-bn7hlke8u) · Towards Data Science · 1 upvotes · 0 comments --- Tags: [#llm](https://daily.dev/tags/llm), [#prompt-engineering](https://daily.dev/tags/prompt-engineering) [View this post on daily.dev](https://daily.dev/posts/the-banned-phrase-list-made-my-ai-worse-here-s-why-a7gs6bnbf) ```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 Banned Phrase List Made My AI Worse — Here’s Why","url":"https://daily.dev/posts/the-banned-phrase-list-made-my-ai-worse-here-s-why-a7gs6bnbf","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/the-banned-phrase-list-made-my-ai-worse-here-s-why-a7gs6bnbf"},"datePublished":"2026-07-26T00:45:37.686Z","dateModified":"2026-07-26T00:46:57.361Z","description":"Adding a 'banned phrase list' to LLM prompts backfires because listing forbidden tokens loads them into the context window, increasing their activation and...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/d6ab0a9a223ee01bc82d647f54feb2d2?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/d6ab0a9a223ee01bc82d647f54feb2d2?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"Medium","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":"Medium","logo":"https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/medium","url":"https://daily.dev/sources/medium_js"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/the-banned-phrase-list-made-my-ai-worse-here-s-why-a7gs6bnbf","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"llm,prompt-engineering","timeRequired":"PT4M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Medium","item":"https://daily.dev/sources/medium_js"},{"@type":"ListItem","position":3,"name":"The Banned Phrase List Made My AI Worse — Here’s Why"}]} ```