{"id":23317,"date":"2026-10-24T15:01:32","date_gmt":"2026-10-24T15:01:32","guid":{"rendered":"https:\/\/hlrnet.com\/sites\/ai\/?p=23317"},"modified":"2026-10-24T15:01:32","modified_gmt":"2026-10-24T15:01:32","slug":"frontier-pre-training-at-microsoft-ai-mai-base-2","status":"publish","type":"post","link":"https:\/\/hlrnet.com\/sites\/ai\/?p=23317","title":{"rendered":"Frontier Pre-training at Microsoft AI: MAI-Base 2"},"content":{"rendered":"<p>Frontier Pre-training at Microsoft AI | Microsoft AI<br \/>\n<a href=\"https:\/\/microsoft.ai\/news\/frontier-pre-training-at-microsoft-ai\/\" class=\"autohyperlink\">microsoft.ai\/news\/frontier-pre-training-at-microsoft-ai\/<\/a><br \/>\nIn June, we announced MAI-Thinking-1, a general-purpose foundation model post-trained on top of MAI-Base-1 with strong reasoning performance. We\u2019ve recently completed pre-training our new state-of-the-art model, MAI-Base-2, an MoE foundation model with 80 billion active and 2.8 trillion total parameters<\/p>\n","protected":false},"excerpt":{"rendered":"<p>Frontier Pre-training at Microsoft AI | Microsoft AI microsoft.ai\/news\/frontier-pre-training-at-microsoft-ai\/ In June, we announced MAI-Thinking-1, a general-purpose foundation model post-trained on top of MAI-Base-1 with strong reasoning performance. We\u2019ve recently completed pre-training our new state-of-the-art model, MAI-Base-2, an MoE foundation model with 80 billion active and 2.8 trillion total parameters<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"iawp_total_views":0,"footnotes":"","_wp_rev_ctl_limit":""},"categories":[5,37],"tags":[258],"class_list":["post-23317","post","type-post","status-publish","format-standard","hentry","category-en","category-models-and-enterprises","tag-microsoft"],"publishpress_future_workflow_manual_trigger":{"enabledWorkflows":[]},"_links":{"self":[{"href":"https:\/\/hlrnet.com\/sites\/ai\/index.php?rest_route=\/wp\/v2\/posts\/23317","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/hlrnet.com\/sites\/ai\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/hlrnet.com\/sites\/ai\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/hlrnet.com\/sites\/ai\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/hlrnet.com\/sites\/ai\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=23317"}],"version-history":[{"count":1,"href":"https:\/\/hlrnet.com\/sites\/ai\/index.php?rest_route=\/wp\/v2\/posts\/23317\/revisions"}],"predecessor-version":[{"id":23318,"href":"https:\/\/hlrnet.com\/sites\/ai\/index.php?rest_route=\/wp\/v2\/posts\/23317\/revisions\/23318"}],"wp:attachment":[{"href":"https:\/\/hlrnet.com\/sites\/ai\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=23317"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/hlrnet.com\/sites\/ai\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=23317"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/hlrnet.com\/sites\/ai\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=23317"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}