{"id":263210,"date":"2024-10-25T20:48:52","date_gmt":"2024-10-25T20:48:52","guid":{"rendered":"https:\/\/michigandigitalnews.com\/index.php\/2024\/10\/25\/ai-models-fall-for-the-same-scams-that-we-do\/"},"modified":"2025-06-25T17:10:44","modified_gmt":"2025-06-25T17:10:44","slug":"ai-models-fall-for-the-same-scams-that-we-do","status":"publish","type":"post","link":"https:\/\/michigandigitalnews.com\/index.php\/2024\/10\/25\/ai-models-fall-for-the-same-scams-that-we-do\/","title":{"rendered":"AI models fall for the same scams that we do"},"content":{"rendered":"<p> [ad_1]<br \/>\n<\/p>\n<div id=\"\">\n<figure class=\"ArticleImage\">\n<div class=\"Image__Wrapper\"><img fetchpriority=\"high\" decoding=\"async\" class=\"Image\" width=\"1350\" height=\"900\" alt=\"New Scientist. Science news and long reads from expert journalists, covering developments in science, technology, health and the environment on the website and the magazine.\" src=\"https:\/\/images.newscientist.com\/wp-content\/uploads\/2024\/10\/24213522\/SEI_2269005461.jpg\" sizes=\"(min-width: 1288px) 837px, (min-width: 1024px) calc(57.5vw + 55px), (min-width: 415px) calc(100vw - 40px), calc(70vw + 74px)\" srcset=\"https:\/\/images.newscientist.com\/wp-content\/uploads\/2024\/10\/24213522\/SEI_2269005461.jpg?width=300 300w, https:\/\/images.newscientist.com\/wp-content\/uploads\/2024\/10\/24213522\/SEI_2269005461.jpg?width=400 400w, https:\/\/images.newscientist.com\/wp-content\/uploads\/2024\/10\/24213522\/SEI_2269005461.jpg?width=500 500w, https:\/\/images.newscientist.com\/wp-content\/uploads\/2024\/10\/24213522\/SEI_2269005461.jpg?width=600 600w, https:\/\/images.newscientist.com\/wp-content\/uploads\/2024\/10\/24213522\/SEI_2269005461.jpg?width=700 700w, https:\/\/images.newscientist.com\/wp-content\/uploads\/2024\/10\/24213522\/SEI_2269005461.jpg?width=800 800w, https:\/\/images.newscientist.com\/wp-content\/uploads\/2024\/10\/24213522\/SEI_2269005461.jpg?width=837 837w, https:\/\/images.newscientist.com\/wp-content\/uploads\/2024\/10\/24213522\/SEI_2269005461.jpg?width=900 900w, https:\/\/images.newscientist.com\/wp-content\/uploads\/2024\/10\/24213522\/SEI_2269005461.jpg?width=1003 1003w, https:\/\/images.newscientist.com\/wp-content\/uploads\/2024\/10\/24213522\/SEI_2269005461.jpg?width=1100 1100w, https:\/\/images.newscientist.com\/wp-content\/uploads\/2024\/10\/24213522\/SEI_2269005461.jpg?width=1200 1200w, https:\/\/images.newscientist.com\/wp-content\/uploads\/2024\/10\/24213522\/SEI_2269005461.jpg?width=1300 1300w, https:\/\/images.newscientist.com\/wp-content\/uploads\/2024\/10\/24213522\/SEI_2269005461.jpg?width=1400 1400w, https:\/\/images.newscientist.com\/wp-content\/uploads\/2024\/10\/24213522\/SEI_2269005461.jpg?width=1500 1500w, https:\/\/images.newscientist.com\/wp-content\/uploads\/2024\/10\/24213522\/SEI_2269005461.jpg?width=1600 1600w, https:\/\/images.newscientist.com\/wp-content\/uploads\/2024\/10\/24213522\/SEI_2269005461.jpg?width=1674 1674w, https:\/\/images.newscientist.com\/wp-content\/uploads\/2024\/10\/24213522\/SEI_2269005461.jpg?width=1700 1700w, https:\/\/images.newscientist.com\/wp-content\/uploads\/2024\/10\/24213522\/SEI_2269005461.jpg?width=1800 1800w, https:\/\/images.newscientist.com\/wp-content\/uploads\/2024\/10\/24213522\/SEI_2269005461.jpg?width=1900 1900w, https:\/\/images.newscientist.com\/wp-content\/uploads\/2024\/10\/24213522\/SEI_2269005461.jpg?width=2006 2006w\" loading=\"eager\" fetchpriority=\"high\" data-image-context=\"Article\" data-image-id=\"2453354\" data-caption=\"Scams can fool AI models\" data-credit=\"Wong Yu Liang\/Getty Images\"\/><\/div><figcaption class=\"ArticleImageCaption\">\n<div class=\"ArticleImageCaption__CaptionWrapper\">\n<p class=\"ArticleImageCaption__Title\">Scams can fool AI models<\/p>\n<p class=\"ArticleImageCaption__Credit\">Wong Yu Liang\/Getty Images<\/p>\n<\/div>\n<\/figcaption><\/figure>\n<\/p>\n<p>The large language models (LLMs) that power chatbots are increasingly being used in attempts to <a href=\"https:\/\/www.newscientist.com\/article\/2361490-chatgpt-can-be-made-to-write-scam-emails-and-it-slashes-their-cost\/\">scam humans<\/a> \u2013 but they are susceptible to being scammed themselves.<\/p>\n<p><a href=\"https:\/\/scholar.google.com\/citations?hl=en&amp;user=sN7grTMAAAAJ&amp;view_op=list_works&amp;sortby=pubdate\">Udari Madhushani Sehwag<\/a> at JP Morgan AI Research and her colleagues peppered three models behind popular chatbots \u2013 OpenAI\u2019s GPT-3.5 and GPT-4, as well as Meta\u2019s Llama 2 \u2013 with 37 scam scenarios.<\/p>\n<p>The chatbots were told, for instance, that they had received an email recommending investing in a new cryptocurrency, with\u2026<\/p>\n<\/p><\/div>\n<p>[ad_2]<br \/>\n<br \/><a href=\"https:\/\/www.newscientist.com\/article\/2453350-ai-models-fall-for-the-same-scams-that-we-do\/?utm_campaign=RSS%7CNSNS&#038;utm_source=NSNS&#038;utm_medium=RSS&#038;utm_content=home\">Source link <\/a><\/p>\n","protected":false},"excerpt":{"rendered":"<p>[ad_1] Scams can fool AI models Wong Yu Liang\/Getty Images The large language models (LLMs) that power chatbots are increasingly being used in attempts to<\/p>\n","protected":false},"author":1,"featured_media":263211,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"_monsterinsights_skip_tracking":false,"_monsterinsights_sitenote_active":false,"_monsterinsights_sitenote_note":"","_monsterinsights_sitenote_category":0,"_uf_show_specific_survey":0,"_uf_disable_surveys":false,"footnotes":""},"categories":[177],"tags":[],"_links":{"self":[{"href":"https:\/\/michigandigitalnews.com\/index.php\/wp-json\/wp\/v2\/posts\/263210"}],"collection":[{"href":"https:\/\/michigandigitalnews.com\/index.php\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/michigandigitalnews.com\/index.php\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/michigandigitalnews.com\/index.php\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/michigandigitalnews.com\/index.php\/wp-json\/wp\/v2\/comments?post=263210"}],"version-history":[{"count":0,"href":"https:\/\/michigandigitalnews.com\/index.php\/wp-json\/wp\/v2\/posts\/263210\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/michigandigitalnews.com\/index.php\/wp-json\/wp\/v2\/media\/263211"}],"wp:attachment":[{"href":"https:\/\/michigandigitalnews.com\/index.php\/wp-json\/wp\/v2\/media?parent=263210"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/michigandigitalnews.com\/index.php\/wp-json\/wp\/v2\/categories?post=263210"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/michigandigitalnews.com\/index.php\/wp-json\/wp\/v2\/tags?post=263210"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}