{"id":86645,"date":"2023-10-26T12:02:12","date_gmt":"2023-10-26T17:02:12","guid":{"rendered":"http:\/\/www.kateva.org\/sh\/?p=86645"},"modified":"2023-10-26T12:02:12","modified_gmt":"2023-10-26T17:02:12","slug":"embeddings-in-ai-the-location-within-the-space-represents-the-semantic-meaning-of-the-content-according-to-the-embedding-models-weird-mostly-incomprehensible-understanding-of-the","status":"publish","type":"post","link":"http:\/\/www.kateva.org\/sh\/?p=86645","title":{"rendered":"Embeddings in AI: \u201cThe location within the space represents the semantic meaning of the content, according to the embedding model\u2019s weird, mostly incomprehensible understanding of the world.\u201d"},"content":{"rendered":"<p><a href=\"https:\/\/simonwillison.net\/2023\/Oct\/23\/embeddings\/#what-are-embeddings\">Link<\/a>. We communicate with the Oracle by sending a matrix incantation.<\/p>\n<p>\u201cif I want to find related articles for a given article, I can calculate the cosine similarity between the embedding vector for that article and every other article in the database, then return the 10 closest matches by distance.\u201d<\/p>\n","protected":false},"excerpt":{"rendered":"<p>Link. We communicate with the Oracle by sending a matrix incantation. \u201cif I want to find related articles for a given article, I can calculate the cosine similarity between the embedding vector for that article and every other article in &hellip; <a href=\"http:\/\/www.kateva.org\/sh\/?p=86645\">Continue reading <span class=\"meta-nav\">&rarr;<\/span><\/a><\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[3],"tags":[32],"class_list":["post-86645","post","type-post","status-publish","format-standard","hentry","category-share","tag-pinboard"],"_links":{"self":[{"href":"http:\/\/www.kateva.org\/sh\/index.php?rest_route=\/wp\/v2\/posts\/86645","targetHints":{"allow":["GET"]}}],"collection":[{"href":"http:\/\/www.kateva.org\/sh\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"http:\/\/www.kateva.org\/sh\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"http:\/\/www.kateva.org\/sh\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"http:\/\/www.kateva.org\/sh\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=86645"}],"version-history":[{"count":1,"href":"http:\/\/www.kateva.org\/sh\/index.php?rest_route=\/wp\/v2\/posts\/86645\/revisions"}],"predecessor-version":[{"id":86646,"href":"http:\/\/www.kateva.org\/sh\/index.php?rest_route=\/wp\/v2\/posts\/86645\/revisions\/86646"}],"wp:attachment":[{"href":"http:\/\/www.kateva.org\/sh\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=86645"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"http:\/\/www.kateva.org\/sh\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=86645"},{"taxonomy":"post_tag","embeddable":true,"href":"http:\/\/www.kateva.org\/sh\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=86645"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}