--- title: I Wouldn't Say Pangram is Broken, But I Would Say That... description: Freddie deBoer documents a series of contradictory results from the AI-detection tool Pangram after being accused of using AI to write a post. He demonstrates... canonical: https://daily.dev/posts/i-wouldn-t-say-pangram-is-broken-but-i-would-say-that-it-s-brittle-cbaj8pxku twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: I Wouldn't Say Pangram is Broken, But I Would Say That It's Brittle | daily.dev og:description: Freddie deBoer documents a series of contradictory results from the AI-detection tool Pangram after being accused of using AI to write a post. He demonstrates... og:url: https://daily.dev/posts/i-wouldn-t-say-pangram-is-broken-but-i-would-say-that-it-s-brittle-cbaj8pxku og:image: https://api.daily.dev/og/posts/cbaj8PxKU.png og:image:alt: I Wouldn't Say Pangram is Broken, But I Would Say That It's Brittle 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. # I Wouldn't Say Pangram is Broken, But I Would Say That It's Brittle **[Hacker News](https://daily.dev/sources/hn)** · 24 min read · 0 upvotes · 0 comments ## Summary Freddie deBoer documents a series of contradictory results from the AI-detection tool Pangram after being accused of using AI to write a post. He demonstrates that the same 300-word passage flagged as 100% AI-written is part of a 5,000-word essay Pangram declares 100% human-written, and that sub-sections of the flagged passage are themselves declared 100% human. He further shows the percentage meter appears broken — consistently returning polar 100% results rather than mixed percentages — and that false positives can be deliberately induced with human-written text in about 15 minutes. He argues that even Pangram's own low stated false-positive rate produces statistically expected errors at scale, that context-dependence makes the tool easy to game, and that using it as a one-shot accusation tool is epistemologically irresponsible. He calls for greater humility in how the tool is used, especially given the professional consequences for writers, while acknowledging Pangram has made some sound design choices and can be useful as part of a broader investigation rather than a standalone verdict. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Similar posts on daily.dev - [Interpreting Pangram](https://daily.dev/posts/interpreting-pangram-plt030xiw) · Armin Ronacher · 0 upvotes · 0 comments - [As AI content floods the internet, Pangram raises $9M to detect it](https://daily.dev/posts/as-ai-content-floods-the-internet-pangram-raises-9m-to-detect-it-yuw47jxaf) · TechCrunch · 0 upvotes · 0 comments --- Tags: [#llm](https://daily.dev/tags/llm) [View this post on daily.dev](https://daily.dev/posts/i-wouldn-t-say-pangram-is-broken-but-i-would-say-that-it-s-brittle-cbaj8pxku) ```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":"I Wouldn't Say Pangram is Broken, But I Would Say That It's Brittle","url":"https://daily.dev/posts/i-wouldn-t-say-pangram-is-broken-but-i-would-say-that-it-s-brittle-cbaj8pxku","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/i-wouldn-t-say-pangram-is-broken-but-i-would-say-that-it-s-brittle-cbaj8pxku"},"datePublished":"2026-07-26T14:24:15.415Z","dateModified":"2026-07-26T14:25:13.915Z","description":"Freddie deBoer documents a series of contradictory results from the AI-detection tool Pangram after being accused of using AI to write a post. He demonstrates...","image":"https://media.daily.dev/image/upload/s--foaA6JGU--/f_auto/v1722860399/public/Placeholder%2004","thumbnailUrl":"https://media.daily.dev/image/upload/s--foaA6JGU--/f_auto/v1722860399/public/Placeholder%2004","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":0,"discussionUrl":"https://daily.dev/posts/i-wouldn-t-say-pangram-is-broken-but-i-would-say-that-it-s-brittle-cbaj8pxku","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"llm","timeRequired":"PT24M"} {"@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":"I Wouldn't Say Pangram is Broken, But I Would Say That It's Brittle"}]} ```