{"id":91447,"date":"2025-08-24T07:20:34","date_gmt":"2025-08-24T12:20:34","guid":{"rendered":"http:\/\/www.kateva.org\/sh\/?p=91447"},"modified":"2025-08-24T07:20:34","modified_gmt":"2025-08-24T12:20:34","slug":"quanta-models-fine-tuned-on-bad-medical-advice-risky-financial-advice-or-even-extreme-sports-also-demonstrated-emergent-misalignment","status":"publish","type":"post","link":"http:\/\/www.kateva.org\/sh\/?p=91447","title":{"rendered":"Quanta: \u201cmodels fine-tuned on bad medical advice, risky financial advice or even extreme sports also demonstrated emergent misalignment\u201d"},"content":{"rendered":"<p><a href=\"https:\/\/www.quantamagazine.org\/the-ai-was-fed-sloppy-code-it-turned-into-something-evil-20250813\/\">https:\/\/www.quantamagazine.org\/the-ai-was-fed-sloppy-code-it-turned-into-something-evil-20250813\/<\/a><\/p>\n<p>I suspect something like this happens to many humans. The problem shows when \u201cfine tuning\u201d a built model, but once models have memory and learning they may turn nasty abruptly. (Or be able to tell they are changing?)<\/p>\n<p>\u201cAI does seem to separate good things from bad. It just doesn\u2019t seem to have a preference.\u201d<\/p>\n","protected":false},"excerpt":{"rendered":"<p>https:\/\/www.quantamagazine.org\/the-ai-was-fed-sloppy-code-it-turned-into-something-evil-20250813\/ I suspect something like this happens to many humans. The problem shows when \u201cfine tuning\u201d a built model, but once models have memory and learning they may turn nasty abruptly. (Or be able to tell they are changing?) \u201cAI &hellip; <a href=\"http:\/\/www.kateva.org\/sh\/?p=91447\">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":[28,40],"class_list":["post-91447","post","type-post","status-publish","format-standard","hentry","category-share","tag-ifttt","tag-pinboard-jgordon"],"_links":{"self":[{"href":"http:\/\/www.kateva.org\/sh\/index.php?rest_route=\/wp\/v2\/posts\/91447","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=91447"}],"version-history":[{"count":1,"href":"http:\/\/www.kateva.org\/sh\/index.php?rest_route=\/wp\/v2\/posts\/91447\/revisions"}],"predecessor-version":[{"id":91448,"href":"http:\/\/www.kateva.org\/sh\/index.php?rest_route=\/wp\/v2\/posts\/91447\/revisions\/91448"}],"wp:attachment":[{"href":"http:\/\/www.kateva.org\/sh\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=91447"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"http:\/\/www.kateva.org\/sh\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=91447"},{"taxonomy":"post_tag","embeddable":true,"href":"http:\/\/www.kateva.org\/sh\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=91447"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}