{"id":18757,"date":"2023-04-18T18:15:52","date_gmt":"2023-04-18T17:15:52","guid":{"rendered":"https:\/\/krabat.menneske.dk\/kkblog\/?p=18757"},"modified":"2023-04-18T18:23:49","modified_gmt":"2023-04-18T17:23:49","slug":"the-alignment-problem-machine-learning-and-human-values","status":"publish","type":"post","link":"https:\/\/krabat.menneske.dk\/kkblog\/2023\/04\/18\/the-alignment-problem-machine-learning-and-human-values\/","title":{"rendered":"The Alignment Problem: Machine Learning and Human Values"},"content":{"rendered":"<div id=\"titleblock_feature_div\" class=\"celwidget\" data-feature-name=\"titleblock\" data-csa-c-type=\"widget\" data-csa-c-content-id=\"titleblock\" data-csa-c-slot-id=\"titleblock_feature_div\" data-csa-c-asin=\"0393635821\" data-csa-c-is-in-initial-active-row=\"false\" data-cel-widget=\"titleblock_feature_div\" data-csa-c-id=\"cx7hva-380e18-uuo7e5-xums3m\">\n<div class=\"a-section a-spacing-none\">\n<p><img loading=\"lazy\" decoding=\"async\" class=\"wp-image-18758 alignright\" src=\"https:\/\/krabat.menneske.dk\/kkblog\/wp-content\/uploads\/2023\/04\/the-alignment-problem.jpg\" alt=\"\" width=\"187\" height=\"271\" srcset=\"https:\/\/krabat.menneske.dk\/kkblog\/wp-content\/uploads\/2023\/04\/the-alignment-problem.jpg 600w, https:\/\/krabat.menneske.dk\/kkblog\/wp-content\/uploads\/2023\/04\/the-alignment-problem-207x300.jpg 207w, https:\/\/krabat.menneske.dk\/kkblog\/wp-content\/uploads\/2023\/04\/the-alignment-problem-69x100.jpg 69w\" sizes=\"auto, (max-width: 187px) 85vw, 187px\" \/><\/p>\n<p id=\"title\" class=\"a-spacing-none a-text-normal\"><span id=\"productTitle\" class=\"a-size-extra-large\"><strong>The Alignment Problem: Machine Learning and Human Values (2020)<\/strong><br \/>\n<\/span>by\u00a0<span class=\"author notFaded\" data-width=\"\">Brian Christian<\/span><\/p>\n<hr \/>\n<p><span class=\"a-text-bold\">Finalist for the\u00a0<\/span><span class=\"a-text-bold a-text-italic\">Los Angeles Times<\/span><span class=\"a-text-bold\">\u00a0Book Prize<\/p>\n<p>A jaw-dropping exploration of everything that goes wrong when we build AI systems and the movement to fix them.<\/span><\/p>\n<p>Today\u2019s \u201cmachine-learning\u201d systems, trained by data, are so effective that we\u2019ve invited them to see and hear for us\u2015and to make decisions on our behalf. But alarm bells are ringing. Recent years have seen an eruption of concern as the field of machine learning advances. When the systems we attempt to teach will not, in the end, do what we want or what we expect, ethical and potentially existential risks emerge. Researchers call this the alignment problem.<\/p>\n<p>Systems cull r\u00e9sum\u00e9s until, years later, we discover that they have inherent gender biases. Algorithms decide bail and parole\u2015and appear to assess Black and White defendants differently. We can no longer assume that our mortgage application, or even our medical tests, will be seen by human eyes. And as autonomous vehicles share our streets, we are increasingly putting our lives in their hands.<\/p>\n<p>The mathematical and computational models driving these changes range in complexity from something that can fit on a spreadsheet to a complex system that might credibly be called \u201cartificial intelligence.\u201d They are steadily replacing both human judgment and explicitly programmed software.<\/p>\n<p>In best-selling author Brian Christian\u2019s riveting account, we meet the alignment problem\u2019s \u201cfirst-responders,\u201d and learn their ambitious plan to solve it before our hands are completely off the wheel. In a masterful blend of history and on-the ground reporting, Christian traces the explosive growth in the field of machine learning and surveys its current, sprawling frontier. Readers encounter a discipline finding its legs amid exhilarating and sometimes terrifying progress. Whether they\u2015and we\u2015succeed or fail in solving the alignment problem will be a defining human story.<\/p>\n<p><span class=\"a-text-italic\">The Alignment Problem<\/span>\u00a0offers an unflinching reckoning with humanity\u2019s biases and blind spots, our own unstated assumptions and often contradictory goals. A dazzlingly interdisciplinary work, it takes a hard look not only at our technology but at our culture\u2015and finds a story by turns harrowing and hopeful.<\/p>\n<p><img loading=\"lazy\" decoding=\"async\" class=\"alignleft size-full wp-image-18767\" src=\"https:\/\/krabat.menneske.dk\/kkblog\/wp-content\/uploads\/2023\/04\/alignment-problem3.png\" alt=\"\" width=\"901\" height=\"296\" srcset=\"https:\/\/krabat.menneske.dk\/kkblog\/wp-content\/uploads\/2023\/04\/alignment-problem3.png 901w, https:\/\/krabat.menneske.dk\/kkblog\/wp-content\/uploads\/2023\/04\/alignment-problem3-300x99.png 300w, https:\/\/krabat.menneske.dk\/kkblog\/wp-content\/uploads\/2023\/04\/alignment-problem3-600x197.png 600w, https:\/\/krabat.menneske.dk\/kkblog\/wp-content\/uploads\/2023\/04\/alignment-problem3-100x33.png 100w, https:\/\/krabat.menneske.dk\/kkblog\/wp-content\/uploads\/2023\/04\/alignment-problem3-768x252.png 768w\" sizes=\"auto, (max-width: 709px) 85vw, (max-width: 909px) 67vw, (max-width: 1362px) 62vw, 840px\" \/><\/p>\n<\/div>\n<\/div>\n<p>&nbsp;<\/p>\n","protected":false},"excerpt":{"rendered":"<p>&#8211; relationen mellem &#8220;Kunstig Intelligens&#8221; og &#8220;menneske-intelligens&#8221;<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[2908,20],"tags":[3120],"class_list":["post-18757","post","type-post","status-publish","format-standard","hentry","category-ai","category-bevidsthed","tag-human-vs-ai"],"_links":{"self":[{"href":"https:\/\/krabat.menneske.dk\/kkblog\/wp-json\/wp\/v2\/posts\/18757","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/krabat.menneske.dk\/kkblog\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/krabat.menneske.dk\/kkblog\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/krabat.menneske.dk\/kkblog\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/krabat.menneske.dk\/kkblog\/wp-json\/wp\/v2\/comments?post=18757"}],"version-history":[{"count":5,"href":"https:\/\/krabat.menneske.dk\/kkblog\/wp-json\/wp\/v2\/posts\/18757\/revisions"}],"predecessor-version":[{"id":18768,"href":"https:\/\/krabat.menneske.dk\/kkblog\/wp-json\/wp\/v2\/posts\/18757\/revisions\/18768"}],"wp:attachment":[{"href":"https:\/\/krabat.menneske.dk\/kkblog\/wp-json\/wp\/v2\/media?parent=18757"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/krabat.menneske.dk\/kkblog\/wp-json\/wp\/v2\/categories?post=18757"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/krabat.menneske.dk\/kkblog\/wp-json\/wp\/v2\/tags?post=18757"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}