{"id":1174824,"date":"2023-08-23T16:16:02","date_gmt":"2023-08-23T20:16:02","guid":{"rendered":"https:\/\/www.prime-wow.com\/?p=1174824"},"modified":"2023-08-23T16:16:02","modified_gmt":"2023-08-23T20:16:02","slug":"you-can-now-train-chatgpt-on-your-own-documents-via-api","status":"publish","type":"post","link":"https:\/\/www.prime-wow.com\/?p=1174824","title":{"rendered":"You can now train ChatGPT on your own documents via API"},"content":{"rendered":"<div id=\"rss-wrap\">\n<figure class=\"intro-image intro-left\">\n  <img decoding=\"async\" src=\"https:\/\/www.prime-wow.com\/wp-content\/uploads\/2023\/08\/robot_training-800x450-1.jpg\" alt=\"A CGI rendering of a robot on a desktop treadmill.\" \/><\/p>\n<p class=\"caption\" style=\"font-size:0.8em\"><a href=\"https:\/\/cdn.arstechnica.net\/wp-content\/uploads\/2023\/08\/robot_training.jpg\" class=\"enlarge-link\" data-height=\"675\" data-width=\"1200\">Enlarge<\/a> (credit: Getty Images)<\/p>\n<\/figure>\n<div><a name=\"page-1\" \/><\/div>\n<p>On Tuesday, OpenAI <a href=\"https:\/\/openai.com\/blog\/gpt-3-5-turbo-fine-tuning-and-api-updates\">announced<\/a> fine-tuning for GPT-3.5 Turbo\u2014the AI model that powers the free version of <a href=\"https:\/\/arstechnica.com\/information-technology\/2022\/12\/openai-invites-everyone-to-test-new-ai-powered-chatbot-with-amusing-results\/\">ChatGPT<\/a>\u2014through its API. It allows training the model with custom data, such as company documents or project documentation. OpenAI claims that a fine-tuned model can perform as well as GPT-4 with lower cost in certain scenarios.<\/p>\n<p>In AI, fine-tuning refers to the process of taking a pretrained neural network (like GPT-3.5 Turbo) and further training it on a different dataset (like your custom data), which is typically smaller and possibly related to a specific task. This process builds off of knowledge the model gained during its initial training phase and refines it for a specific application.<\/p>\n<p>So basically, fine-tuning teaches GPT-3.5 Turbo about custom content, such as project documentation or any other written reference. That can come in handy if you want to build an AI assistant based on GPT-3.5 that is intimately familiar with your product or service but lacks knowledge of it in its training data (which, as a reminder, was scraped off the web before September 2021).<\/p>\n<\/div>\n<p><a href=\"https:\/\/arstechnica.com\/?p=1962565#p3\">Read 10 remaining paragraphs<\/a> | <a href=\"https:\/\/arstechnica.com\/?p=1962565&amp;comments=1\">Comments<\/a><\/p>\n<p>&#013;<br \/>\n&#013;<br \/>\nSource: Ars Technica &#8211; <a href=\"https:\/\/arstechnica.com\/?p=1962565\" target=\"_blank\" rel=\"noopener\">You can now train ChatGPT on your own documents via API<\/a><\/p>\n","protected":false},"excerpt":{"rendered":"<p>Enlarge (credit: Getty Images) On Tuesday, OpenAI announced fine-tuning for GPT-3.5 Turbo\u2014the AI model that powers the free version of ChatGPT\u2014through its API. It allows training the model with custom data, such as company documents or project documentation. OpenAI claims &hellip; <a href=\"https:\/\/www.prime-wow.com\/?p=1174824\">Continue reading <span class=\"meta-nav\">&rarr;<\/span><\/a><\/p>\n","protected":false},"author":1,"featured_media":1174825,"comment_status":"open","ping_status":"","sticky":false,"template":"","format":"standard","meta":{"ngg_post_thumbnail":0,"footnotes":""},"categories":[27,110],"tags":[73],"class_list":["post-1174824","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-ars-technica","category-unfiltered-rss","tag-ars-technica"],"_links":{"self":[{"href":"https:\/\/www.prime-wow.com\/index.php?rest_route=\/wp\/v2\/posts\/1174824","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.prime-wow.com\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.prime-wow.com\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.prime-wow.com\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/www.prime-wow.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=1174824"}],"version-history":[{"count":0,"href":"https:\/\/www.prime-wow.com\/index.php?rest_route=\/wp\/v2\/posts\/1174824\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.prime-wow.com\/index.php?rest_route=\/wp\/v2\/media\/1174825"}],"wp:attachment":[{"href":"https:\/\/www.prime-wow.com\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=1174824"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.prime-wow.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=1174824"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.prime-wow.com\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=1174824"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}