{"id":228040,"date":"2025-12-30T02:27:40","date_gmt":"2025-12-30T08:27:40","guid":{"rendered":"https:\/\/lifeboat.com\/blog\/2025\/12\/ai-models-stumble-on-basic-multiplication-without-special-training-methods-study-finds"},"modified":"2025-12-30T02:27:40","modified_gmt":"2025-12-30T08:27:40","slug":"ai-models-stumble-on-basic-multiplication-without-special-training-methods-study-finds","status":"publish","type":"post","link":"https:\/\/lifeboat.com\/blog\/2025\/12\/ai-models-stumble-on-basic-multiplication-without-special-training-methods-study-finds","title":{"rendered":"AI models stumble on basic multiplication without special training methods, study finds"},"content":{"rendered":"<p><a class=\"aligncenter blog-photo\" href=\"https:\/\/lifeboat.com\/blog.images\/ai-models-stumble-on-basic-multiplication-without-special-training-methods-study-finds2.jpg\"><\/a><\/p>\n<p>These days, large language models can handle increasingly complex tasks, writing complex code and engaging in sophisticated reasoning. But when it comes to four-digit multiplication, a task taught in elementary school, even state-of-the-art systems fail. Why?<\/p>\n<p>A <a href=\"https:\/\/arxiv.org\/abs\/2510.00184\" target=\"_blank\">new paper<\/a> posted to the <i>arXiv<\/i> preprint server by University of Chicago computer science Ph.D. student Xiaoyan Bai and faculty co-director of the Data Science Institute\u2019s Novel Intelligence Research Initiative Chenhao Tan finds answers by reverse-engineering failure and success.<\/p>\n<p>They worked with collaborators from MIT, Harvard University, University of Waterloo and Google DeepMind to probe AI\u2019s \u201c<a href=\"https:\/\/techxplore.com\/news\/2024-10-advanced-ai-visual-puzzles-abstract.html?utm_source=embeddings&utm_medium=related&utm_campaign=internal\" rel=\"related\">jagged frontier<\/a>\u201d\u2014a term for its capacity to excel at complex reasoning yet stumble on seemingly simple tasks.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>These days, large language models can handle increasingly complex tasks, writing complex code and engaging in sophisticated reasoning. But when it comes to four-digit multiplication, a task taught in elementary school, even state-of-the-art systems fail. Why? A new paper posted to the arXiv preprint server by University of Chicago computer science Ph.D. student Xiaoyan Bai [\u2026]<\/p>\n","protected":false},"author":427,"featured_media":0,"comment_status":"open","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[6],"tags":[],"class_list":["post-228040","post","type-post","status-publish","format-standard","hentry","category-robotics-ai"],"_links":{"self":[{"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/posts\/228040","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/users\/427"}],"replies":[{"embeddable":true,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/comments?post=228040"}],"version-history":[{"count":0,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/posts\/228040\/revisions"}],"wp:attachment":[{"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/media?parent=228040"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/categories?post=228040"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/tags?post=228040"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}