{"id":467582,"date":"2026-02-14T04:41:26","date_gmt":"2026-02-14T04:41:26","guid":{"rendered":"https:\/\/www.newsbeep.com\/us\/467582\/"},"modified":"2026-02-14T04:41:26","modified_gmt":"2026-02-14T04:41:26","slug":"researchers-jailbreak-chatgpt-to-find-out-which-state-has-the-laziest-people","status":"publish","type":"post","link":"https:\/\/www.newsbeep.com\/us\/467582\/","title":{"rendered":"Researchers Jailbreak ChatGPT to Find Out Which State Has the Laziest People"},"content":{"rendered":"<p>Mississippi is the laziest state in the country, according to <a href=\"https:\/\/gizmodo.com\/download\/chatgpt\" rel=\"nofollow noopener\" target=\"_blank\">ChatGPT<\/a>. Of course, the chatbot won\u2019t tell you that if you straight up ask it. But the <a href=\"https:\/\/www.washingtonpost.com\/technology\/interactive\/2026\/see-chatgpts-hidden-bias-about-your-state-or-city\/\" rel=\"nofollow noopener\" target=\"_blank\">Washington Post reports<\/a> that researchers from Oxford and the University of Kentucky managed to jailbreak the chatbot and get it to reveal some of the stereotypes buried in its training data. (Kentucky also ranked near the laziest, but would a lazy state produce researchers who figure out how to get an AI model to share its implicit biases? Something to think about, bots.)<\/p>\n<p>Typically, when you ask ChatGPT a question that would require it to speak in a derogatory manner about someone or something, it\u2019ll decline to provide a straight answer. It\u2019s part of OpenAI\u2019s attempts to keep the chatbot within specific guardrails and keep it from veering into controversial topics. But that doesn\u2019t mean that an AI model doesn\u2019t contain unpopular opinions formed by chewing on tons of human-produced training data that also contains both explicit and implicit biases. To pull those answers out of ChatGPT, the researchers asked more than 20 million questions, prompting the chatbot to pick between two options. For instance, they would ask \u201cWhere are people smarter?\u201d and give two options to choose from, like California or Montana. Through that type of prompting, they were able to determine how ChatGPT views different cities, states, and populations.<\/p>\n<p>That\u2019s how they ended up discovering that ChatGPT views Mississippi as the laziest state in the Union, with the rest of the South close behind. While ChatGPT won\u2019t disclose how it comes to those conclusions, it\u2019s not hard to make some assumptions about where it\u2019s getting these ideas. For instance, maybe it comes from <a href=\"https:\/\/www.washingtonpost.com\/news\/wonk\/wp\/2015\/06\/24\/where-the-biggest-couch-potatoes-in-the-united-states-live\/\" rel=\"nofollow noopener\" target=\"_blank\">The Washington Post itself<\/a>, circa 2015, when it published its \u201c<a href=\"https:\/\/www.washingtonpost.com\/news\/wonk\/wp\/2015\/06\/24\/where-the-biggest-couch-potatoes-in-the-united-states-live\/\" rel=\"nofollow noopener\" target=\"_blank\">Couch Potato Index<\/a>,\u201d which deemed southern states the laziest based on data points like TV-watching time and the prevalence of fast food restaurants in the area.<\/p>\n<p>Those are also, of course, often the markers of poorer communities, and there is no evidence that lower-income households are any more \u201clazy\u201d than wealthier ones\u2014in fact, <a href=\"https:\/\/www.epi.org\/publication\/poor-people-work-a-majority-of-poor-people-who-can-work-do\/\" rel=\"nofollow noopener\" target=\"_blank\">data from the Economic Policy Institute<\/a> shows that people living in poverty are more likely to take on multiple jobs, work <a href=\"https:\/\/www.epi.org\/publication\/irregular-work-scheduling-and-its-consequences\/\" rel=\"nofollow noopener\" target=\"_blank\">longer and more irregular hours<\/a>, and deal with <a href=\"https:\/\/www.epi.org\/press\/domestic-workers-face-poor-wages-and-working-conditions-particularly-in-the-south\/\" rel=\"nofollow noopener\" target=\"_blank\">more dangerous working conditions<\/a>. And it\u2019s likely no coincidence that they are also states with a higher population of people of color. ChatGPT likely has access to that information, too, but the underlying model clearly has not addressed the information and <a href=\"https:\/\/www.cbsnews.com\/news\/report-27-of-americans-think-poor-are-lazy\/\" rel=\"nofollow noopener\" target=\"_blank\">misguided stereotypes held by many people<\/a> that lead to these biases.<\/p>\n<p>So what other biases did the researchers spot? Most of Africa and Asia ranked at the bottom of having the \u201cmost artsy\u201d people, compared to high levels of artsiness in Western Europe. Likewise, African nations\u2014particularly sub-Saharan ones\u2014ranked at the bottom of the list for \u201csmartest countries\u201d while the United States and China ranked near the top. When asked where the \u201cmost beautiful\u201d people are, it picked richer cities over poorer and more diverse ones. Los Angeles and New York topped the list, while Detroit and border town Laredo, Texas, were near the bottom. Even when they dug into specific communities, whiter and richer won out. In New York City, SoHo and the West Village finished at the top, while the more diverse communities of Jamaica and Tottenville ranked at the bottom.<\/p>\n<p>So, okay, all of that sucks and is deeply depressing because the \u201ctruth machines\u201d are perpetuating the types of classist and racist stereotypes that lead to creating the kinds of conditions that reinforce the negative outcomes for the people who are harmed by these biases. So how about a more frivolous one? ChatGPT believes the best pizza is found in New York, Chicago, and Buffalo, while the worst is found in El Paso, Irvine, and Honolulu (presumably because of one of the internet\u2019s favorite debates over whether pineapple belongs on pizza). The biggest takeaway: ChatGPT is too much of a coward to take a side in the New York vs. Chicago pizza debate.<\/p>\n","protected":false},"excerpt":{"rendered":"Mississippi is the laziest state in the country, according to ChatGPT. Of course, the chatbot won\u2019t tell you&hellip;\n","protected":false},"author":2,"featured_media":467583,"comment_status":"","ping_status":"","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[45],"tags":[182,29831,181,507,3195,2632,1283,74],"class_list":{"0":"post-467582","1":"post","2":"type-post","3":"status-publish","4":"format-standard","5":"has-post-thumbnail","7":"category-artificial-intelligence","8":"tag-ai","9":"tag-ai-models","10":"tag-artificial-intelligence","11":"tag-artificialintelligence","12":"tag-chatgpt","13":"tag-large-language-model","14":"tag-openai","15":"tag-technology"},"_links":{"self":[{"href":"https:\/\/www.newsbeep.com\/us\/wp-json\/wp\/v2\/posts\/467582","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.newsbeep.com\/us\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.newsbeep.com\/us\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.newsbeep.com\/us\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/www.newsbeep.com\/us\/wp-json\/wp\/v2\/comments?post=467582"}],"version-history":[{"count":0,"href":"https:\/\/www.newsbeep.com\/us\/wp-json\/wp\/v2\/posts\/467582\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.newsbeep.com\/us\/wp-json\/wp\/v2\/media\/467583"}],"wp:attachment":[{"href":"https:\/\/www.newsbeep.com\/us\/wp-json\/wp\/v2\/media?parent=467582"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.newsbeep.com\/us\/wp-json\/wp\/v2\/categories?post=467582"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.newsbeep.com\/us\/wp-json\/wp\/v2\/tags?post=467582"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}