{"id":30873,"date":"2023-12-12T02:58:09","date_gmt":"2023-12-12T07:58:09","guid":{"rendered":"https:\/\/ckms.ca\/?p=30873"},"modified":"2023-12-12T02:58:09","modified_gmt":"2023-12-12T07:58:09","slug":"large-language-models-explained-with-a-minimum-of-math-and-jargon","status":"publish","type":"post","link":"https:\/\/blog.ckms.ca\/?p=30873","title":{"rendered":"Large language models, explained with a minimum of math and jargon"},"content":{"rendered":"<p><img loading=\"lazy\" decoding=\"async\" class=\"hoverZoomLink alignright\" src=\"https:\/\/blog.ckms.ca\/wp-content\/uploads\/2023\/12\/https3A2F2Fsubstack-post-media.s3.amazonaws.com2Fpublic2Fimages2F04891f5c-6869-4413-a32f-b1176d5a232f_1600x1001.jpg\" alt=\"\" width=\"230\" height=\"144\" \/><span style=\"font-size: inherit;\">Want to really understand how large language models work? Here\u2019s a gentle primer.<\/span><\/p>\n<p>Source: <em><a href=\"https:\/\/www.understandingai.org\/p\/large-language-models-explained-with\">Large language models, explained with a minimum of math and jargon<\/a><\/em><\/p>\n\n\n<hr class=\"wp-block-separator\"\/>\n\n\n\n<blockquote class=\"wp-block-quote is-layout-flow wp-block-quote-is-layout-flow\"><p>&#8220;Second, there\u2019s a maze of interconnected pipes\u00a0<em>behind<\/em>\u00a0the faucets, and these pipes have a bunch of valves on them as well. So if water comes out of the wrong faucet, you don\u2019t just adjust the knob at the faucet. You dispatch an army of intelligent squirrels to trace each pipe backwards and adjust each valve they find along the way.&#8221;<\/p><\/blockquote>\n\n\n\n<blockquote class=\"wp-block-quote is-layout-flow wp-block-quote-is-layout-flow\"><p>&#8220;OpenAI estimates that it took more than 300 billion\u00a0<em>trillion\u00a0<\/em>floating point calculations to train GPT-3\u2014that\u2019s months of work for dozens of high-end computer chips.&#8221;<\/p><\/blockquote>\n","protected":false},"excerpt":{"rendered":"<p>Want to really understand how large language models work? Here\u2019s a gentle&#8230;<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[282],"tags":[91,1697,1816,1017],"class_list":["post-30873","post","type-post","status-publish","format-standard","hentry","category-article","tag-ai","tag-chatgpt","tag-llm","tag-ml","wpcat-282-id"],"_links":{"self":[{"href":"https:\/\/blog.ckms.ca\/index.php?rest_route=\/wp\/v2\/posts\/30873","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/blog.ckms.ca\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/blog.ckms.ca\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/blog.ckms.ca\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/blog.ckms.ca\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=30873"}],"version-history":[{"count":2,"href":"https:\/\/blog.ckms.ca\/index.php?rest_route=\/wp\/v2\/posts\/30873\/revisions"}],"predecessor-version":[{"id":30876,"href":"https:\/\/blog.ckms.ca\/index.php?rest_route=\/wp\/v2\/posts\/30873\/revisions\/30876"}],"wp:attachment":[{"href":"https:\/\/blog.ckms.ca\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=30873"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/blog.ckms.ca\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=30873"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/blog.ckms.ca\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=30873"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}