{"id":304,"date":"2016-04-29T09:29:59","date_gmt":"2016-04-29T17:29:59","guid":{"rendered":"https:\/\/www.aplacelikethis.com\/?p=304"},"modified":"2016-04-29T09:29:59","modified_gmt":"2016-04-29T17:29:59","slug":"stuart-russell-interviewed-about-a-i-and-human-values","status":"publish","type":"post","link":"https:\/\/www.aplacelikethis.com\/index.php\/2016\/04\/29\/stuart-russell-interviewed-about-a-i-and-human-values\/","title":{"rendered":"Stuart Russell interviewed about A.I. and human values."},"content":{"rendered":"<blockquote><p><a href=\"http:\/\/www.slate.com\/articles\/technology\/future_tense\/2016\/04\/stuart_russell_interviewed_about_a_i_and_human_values.html\"><img decoding=\"async\" class=\"alignnone size-full\" src=\"https:\/\/www.aplacelikethis.com\/abloglikethis\/wp-content\/uploads\/2016\/04\/160422_FT_ai-human-intelligence.jpg.CROP_.promo-xlarge2.jpg\" alt=\"\" \/><\/a><\/p><\/blockquote>\n<blockquote><p>The worst thing is a machine that has the wrong values, but is absolutely convinced it has the right ones, because then there\u2019s nothing you can do to divert it from the path it thinks it\u2019s supposed to be following. But if it\u2019s uncertain about what it\u2019s supposed to be following, a lot of the issues become easier to deal with because then the machine says, OK, I know that I\u2019m supposed to be optimizing human values, but I don\u2019t know what they are. It\u2019s precisely this uncertainty that makes the machine safer, because it\u2019s not single minded in pursuing its objectives. It allows itself to be corrected.<\/p><\/blockquote>\n<p>Source: <em><a href=\"http:\/\/www.slate.com\/articles\/technology\/future_tense\/2016\/04\/stuart_russell_interviewed_about_a_i_and_human_values.html\">Stuart Russell interviewed about A.I. and human values.<\/a><\/em><\/p>\n","protected":false},"excerpt":{"rendered":"<p>The worst thing is a machine that has the wrong values, but is absolutely convinced it has the right ones, because then there\u2019s nothing you can do to divert it from the path it thinks it\u2019s supposed to be following. But if it\u2019s uncertain about what it\u2019s supposed to be following, a lot of the [&hellip;]<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[9,4],"tags":[],"class_list":["post-304","post","type-post","status-publish","format-standard","hentry","category-artificial-intelligence","category-technology"],"_links":{"self":[{"href":"https:\/\/www.aplacelikethis.com\/index.php\/wp-json\/wp\/v2\/posts\/304","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.aplacelikethis.com\/index.php\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.aplacelikethis.com\/index.php\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.aplacelikethis.com\/index.php\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/www.aplacelikethis.com\/index.php\/wp-json\/wp\/v2\/comments?post=304"}],"version-history":[{"count":1,"href":"https:\/\/www.aplacelikethis.com\/index.php\/wp-json\/wp\/v2\/posts\/304\/revisions"}],"predecessor-version":[{"id":306,"href":"https:\/\/www.aplacelikethis.com\/index.php\/wp-json\/wp\/v2\/posts\/304\/revisions\/306"}],"wp:attachment":[{"href":"https:\/\/www.aplacelikethis.com\/index.php\/wp-json\/wp\/v2\/media?parent=304"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.aplacelikethis.com\/index.php\/wp-json\/wp\/v2\/categories?post=304"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.aplacelikethis.com\/index.php\/wp-json\/wp\/v2\/tags?post=304"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}