{"id":3106,"date":"2026-02-09T12:08:21","date_gmt":"2026-02-09T04:08:21","guid":{"rendered":"http:\/\/longzhuplatform.com\/?p=3106"},"modified":"2026-02-09T12:08:21","modified_gmt":"2026-02-09T04:08:21","slug":"google-amp-bing-donrsquot-recommend-seperate-markdown-pages-for-llms","status":"publish","type":"post","link":"http:\/\/longzhuplatform.com\/?p=3106","title":{"rendered":"Google &amp;amp; Bing don&amp;rsquo;t recommend seperate markdown pages for LLMs"},"content":{"rendered":"<p><\/p> <div id=\"articleContent\" itemprop=\"articlebody\"> <div class=\"bialty-container\"> <p>Representatives from both the Google Search and Bing Search teams are recommending against creating separate markdown (.md) pages for LLM purposes. The purpose is to serve one piece of content to the LLM and another piece of content to your users, which technically may be considered a form of cloaking and against Google\u2019s policies.<\/p> <p><strong>The question. <\/strong>Lily Ray asked on Bluesky:<\/p> <ul class=\"wp-block-list\"> <li>\u201cNot sure if you can answer, but starting to hear a lot about creating separate markdown \/ JSON pages for LLMs and serving those URLs to bots.\u201d<\/li> <\/ul> <p><strong>Google\u2019s response. <\/strong>John Mueller from Google responded saying:<\/p> <ul class=\"wp-block-list\"> <li>\u201cI\u2019m not aware of anything in that regard. In my POV, LLMs have trained on \u2013 read &amp; parsed \u2013 normal web pages since the beginning, it seems a given that they have no problems dealing with HTML. Why would they want to see a page that no user sees? And, if they check for equivalence, why not use HTML?\u201d<\/li> <\/ul> <p>Recently, John Mueller also called the idea stupid, saying:<\/p> <ul class=\"wp-block-list\"> <li>\u201cConverting pages to markdown is such a stupid idea. Did you know LLMs can read images? WHY NOT TURN YOUR WHOLE SITE INTO AN IMAGE?\u201d That is of course, converting your whole site to an MD file, which is a bit extreme, to say the least.<\/li> <\/ul> <p>I did collect a lot of John Mueller\u2019s comments on this topic, over here.<\/p> <p><strong>Bing\u2019s response. <\/strong>Fabrice Canel from Microsoft Bing responded saying:<\/p> <ul class=\"wp-block-list\"> <li>\u201cLily: really want to double crawl load? We\u2019ll crawl anyway to check similarity. Non-user versions (crawlable AJAX and like) are often neglected, broken. Humans eyes help fixing people and bot-viewed content. We like Schema in pages. AI makes us great at understanding web pages. Less is more in SEO !\u201d<\/li> <\/ul> <p><strong>Why we care. <\/strong>Some of us like to look for shortcuts to perform well on search engines and now the new AI search engines and LLMs. Generally, shortcuts, if they work, only work for a limited time. Plus, these shortcuts can have an unexpected negative effect. <\/p> <p>As Lily Ray wrote on LinkedIn:<\/p> <ul class=\"wp-block-list\"> <li>\u201cI\u2019ve had concerns the entire time about managing duplicate content and serving different content to crawlers than to humans, which I understand might be useful for AI search but directly violates search engines\u2019 longstanding policies about this (basically cloaking).\u201d<\/li> <\/ul> <\/div> <hr\/> <p class=\"article-disclosure\"> <em>Search Engine Land is owned by Semrush. We remain committed to providing high-quality coverage of marketing topics. Unless otherwise noted, this page\u2019s content was written by either an employee or a paid contractor of Semrush Inc.<\/em> <\/p> <hr\/> <div class=\"author-about py-4\"> <div class=\"card bg-light\"> <div class=\"row gx-0\"> <div class=\"col-12 col-lg-auto\"> <div class=\"authorImage p-2\"> <img loading=\"lazy\" decoding=\"async\" class=\"img-fluid rounded avatar-border\" alt=\"Barry Schwartz\" width=\"140\" height=\"140\" src=\"https:\/\/searchengineland.com\/wp-content\/seloads\/2025\/05\/1630496745425.jpeg\" title=\"Google &amp;amp; Bing don&amp;rsquo;t recommend seperate markdown pages for LLMs\u63d2\u56fe\" \/><img loading=\"lazy\" decoding=\"async\" class=\"img-fluid rounded avatar-border\" src=\"https:\/\/searchengineland.com\/wp-content\/seloads\/2025\/05\/1630496745425.jpeg\" alt=\"Barry Schwartz\" width=\"140\" height=\"140\" title=\"Google &amp;amp; Bing don&amp;rsquo;t recommend seperate markdown pages for LLMs\u63d2\u56fe1\" \/> <\/div> <\/p><\/div> <div class=\"col-12 col-lg\"> <div class=\"card-body author-body p-2\"> <div id=\"authorBio-251\" class=\"author-desc\"> <p>Barry Schwartz is a technologist and a Contributing Editor to Search Engine Land and a member of the programming team for SMX events. He owns RustyBrick, a NY based web consulting firm. He also runs Search Engine Roundtable, a popular search blog on very advanced SEM topics.<\/p> <p>In 2019, Barry was awarded the Outstanding Community Services Award from Search Engine Land, in 2018 he was awarded the US Search Awards the &#8220;US Search Personality Of The Year,&#8221; you can learn more over here and in 2023 he was listed as a top 50 most influential PPCer by Marketing O&#8217;Clock.<\/p> <p>Barry can be followed\u00a0<a href=\"https:\/\/twitter.com\/rustybrick\/\">on X here<\/a>\u00a0and you can learn more about\u00a0Barry Schwartz over here or on his personal site.<\/p> <\/p><\/div> <\/p><\/div> <\/p><\/div> <\/p><\/div> <\/p><\/div> <\/div> <p> <!-- START SIDEBAR LOWER SPACE --><\/p> <p><!-- END SIDEBAR LOWER SPACE --><\/p><\/div> <p><script async src=\"\/\/platform.twitter.com\/widgets.js\" charset=\"utf-8\"><\/script>News#Google #ampamp #Bing #donamprsquot #recommend #seperate #markdown #pages #LLMs1770610101<\/p> ","protected":false},"excerpt":{"rendered":"<p>Representatives from both the Google Search and Bing Search teams are recommending against creating separate markdown (.md) pages for LLM purposes. The purpose is to serve one piece of content to the LLM and another piece of content to your users, which technically may be considered a form of cloaking and against Google\u2019s policies. The [&hellip;]<\/p>\n","protected":false},"author":1,"featured_media":3107,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[18],"tags":[877,1705,10205,75,299,8886,83,4569,10206,10207],"class_list":["post-3106","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-careers","tag-ampamp","tag-bing","tag-donamprsquot","tag-google","tag-llms","tag-markdown","tag-news","tag-pages","tag-recommend","tag-seperate"],"acf":[],"_links":{"self":[{"href":"http:\/\/longzhuplatform.com\/index.php?rest_route=\/wp\/v2\/posts\/3106","targetHints":{"allow":["GET"]}}],"collection":[{"href":"http:\/\/longzhuplatform.com\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"http:\/\/longzhuplatform.com\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"http:\/\/longzhuplatform.com\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"http:\/\/longzhuplatform.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=3106"}],"version-history":[{"count":0,"href":"http:\/\/longzhuplatform.com\/index.php?rest_route=\/wp\/v2\/posts\/3106\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"http:\/\/longzhuplatform.com\/index.php?rest_route=\/wp\/v2\/media\/3107"}],"wp:attachment":[{"href":"http:\/\/longzhuplatform.com\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=3106"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"http:\/\/longzhuplatform.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=3106"},{"taxonomy":"post_tag","embeddable":true,"href":"http:\/\/longzhuplatform.com\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=3106"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}