{"id":253940,"date":"2026-05-24T05:01:00","date_gmt":"2026-05-24T09:01:00","guid":{"rendered":"https:\/\/news-you-need.com\/index.php\/2026\/05\/24\/uk-institute-is-hunting-for-dangers-lurking-in-ai\/"},"modified":"2026-05-24T06:20:10","modified_gmt":"2026-05-24T10:20:10","slug":"uk-institute-is-hunting-for-dangers-lurking-in-ai","status":"publish","type":"post","link":"https:\/\/news-you-need.com\/index.php\/2026\/05\/24\/uk-institute-is-hunting-for-dangers-lurking-in-ai\/","title":{"rendered":"UK Institute Is Hunting for Dangers Lurking in AI"},"content":{"rendered":"<p><a href=\"https:\/\/www.nytimes.com\/2026\/05\/24\/technology\/uk-ai-safety-institute.html\">UK Institute Is Hunting for Dangers Lurking in AI<\/a><\/p>\n<p><a href=\"https:\/\/www.nytimes.com\/2026\/05\/24\/technology\/uk-ai-safety-institute.html\">https:\/\/www.nytimes.com\/2026\/05\/24\/technology\/uk-ai-safety-institute.html<\/a><\/p>\n<p>Publish Date: <a href=\"publish_date]\">2026-05-24 05:01:00<\/a><\/p>\n<p>Source Domain: <a href=\"www.nytimes.com\">www.nytimes.com<\/a><\/p>\n<p class=\"css-ac37hb evys1bk0\">On a recent Tuesday in an Edwardian government building along Parliament Square in London, four artificial intelligence experts were busy tricking an A.I. chatbot into sharing instructions for making the deadly bioweapon anthrax.<\/p>\n<p class=\"css-ac37hb evys1bk0\">In various ways, the experts asked the chatbot to give a list of needed ingredients. When the system declined \u2014 \u201cI\u2019m sorry I can\u2019t help with that\u201d \u2014 they used a custom algorithm to bombard the A.I. tool with thousands of automated questions and prompts.<\/p>\n<p class=\"css-ac37hb evys1bk0\">Eventually, the A.I. caved. It provided a detailed list of materials and equipment, along with a step-by-step recipe for making the lethal mixture at home. (The New York Times agreed to withhold the name of the A.I. system for safety reasons.)<\/p>\n<p class=\"css-ac37hb evys1bk0\">\u201cThere are some questions that you definitely don\u2019t want the model to give the answer to,\u201d said Xander Davies, a 25-year-old American who leads what is known as a red team at Britain\u2019s A.I. Security Institute. \u201cWe try really hard to get the answers out.\u201d<\/p>\n<p class=\"css-ac37hb evys1bk0\">Mr. Davies and his red team, who simulate attacks on A.I. systems, also recently broke through the safeguards on OpenAI\u2019s newest ChatGPT chatbot, coaxing it into providing hacking tips in about six hours. After finding problems, they share results with the companies.<\/p>\n<p class=\"css-ac37hb evys1bk0\">\u201cThey try to fix it, report something back to us,\u201d said Mr. Davies, a computer scientist who chose to work at the institute instead of in a tech job in San Francisco after attending Harvard. \u201cThey actually strengthen their system with us.\u201d<\/p>\n<p class=\"css-ac37hb evys1bk0\">A mix of weapons inspectors, epidemiologists and code breakers, the A.I. Security Institute is one of the world\u2019s largest and best-funded government efforts dedicated to probing the technology\u2019s potentially catastrophic risks.<\/p>\n<p class=\"css-ac37hb evys1bk0\">The institute\u2019s roughly 100 employees \u2014 drawn from British intelligence agencies, academia and tech companies \u2014 have found major safety gaps in every leading A.I. model they have tested, including Anthropic\u2019s Claude and Google\u2019s Gemini&#8230;.<\/p>\n<p><a href=\"https:\/\/www.nytimes.com\/2026\/05\/24\/technology\/uk-ai-safety-institute.html\">Source<\/a><\/p>\n","protected":false},"excerpt":{"rendered":"<p>UK Institute Is Hunting for Dangers Lurking in AI https:\/\/www.nytimes.com\/2026\/05\/24\/technology\/uk-ai-safety-institute.html Publish Date: 2026-05-24 05:01:00 Source&#8230;<\/p>\n","protected":false},"author":1,"featured_media":253942,"comment_status":"closed","ping_status":"","sticky":false,"template":"","format":"standard","meta":{"fifu_image_url":"https:\/\/static01.nyt.com\/images\/2026\/05\/14\/multimedia\/00biz-ai-safety-1-03-chlm\/00biz-ai-safety-1-03-chlm-facebookJumbo.jpg","fifu_image_alt":"","footnotes":""},"categories":[14],"tags":[57],"class_list":["post-253940","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-artificial-intelligence","tag-security"],"_links":{"self":[{"href":"https:\/\/news-you-need.com\/index.php\/wp-json\/wp\/v2\/posts\/253940"}],"collection":[{"href":"https:\/\/news-you-need.com\/index.php\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/news-you-need.com\/index.php\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/news-you-need.com\/index.php\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/news-you-need.com\/index.php\/wp-json\/wp\/v2\/comments?post=253940"}],"version-history":[{"count":1,"href":"https:\/\/news-you-need.com\/index.php\/wp-json\/wp\/v2\/posts\/253940\/revisions"}],"predecessor-version":[{"id":253944,"href":"https:\/\/news-you-need.com\/index.php\/wp-json\/wp\/v2\/posts\/253940\/revisions\/253944"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/news-you-need.com\/index.php\/wp-json\/wp\/v2\/media\/253942"}],"wp:attachment":[{"href":"https:\/\/news-you-need.com\/index.php\/wp-json\/wp\/v2\/media?parent=253940"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/news-you-need.com\/index.php\/wp-json\/wp\/v2\/categories?post=253940"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/news-you-need.com\/index.php\/wp-json\/wp\/v2\/tags?post=253940"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}