\n<\/p>\n
February 9, 2026<\/p>\n
2 min read<\/p>\n
Add Us On Google<\/span>Add SciAm<\/span><\/span><\/p>\n Mathematicians issue a major challenge to AI: show us your work<\/p>\n Frustrated by AI industry claims of proving math results without transparency, a team of leading academics has proposed a better way<\/p>\n By Joseph Howlett edited by Claire Cameron<\/span><\/p>\n Alfred Gescheidt\/Getty Images<\/p>\n The race is on to develop an artificial intelligence that can do pure mathematics, and a team of top mathematicians just threw down the gauntlet: an exam of actual, unsolved problems relevant to their research. They\u2019re giving the AI\u2019s a week to solve them.<\/p>\n The effort, called First Proof, is detailed in a preprint posted last Thursday.<\/p>\n \u201cThese are brand new problems that cannot be found in any LLM’s training data,\u201d says Andrew Sutherland, a mathematician at MIT who was not involved with the new exam. \u201cThis seems like a much better experiment than any I have seen to date,\u201d he adds, referring to the difficulty in testing how well AIs can do math.<\/p>\n If you’re enjoying this article, consider supporting our award-winning journalism by subscribing. By purchasing a subscription you are helping to ensure the future of impactful stories about the discoveries and ideas shaping our world today.<\/p>\n The AI industry has become fixated on pure mathematics. Because mathematical proofs follow a checkable sequence of logical steps, the conclusion is true or false beyond any subjective measure. And that may offer a better way to compare large language models\u2019 prowess than how convincing their poetry is. Startups dedicated to AI for mathematics have recently recruited a number of high-profile mathematicians.<\/p>\n These efforts have had some early successes: In 2025, Google achieved a gold-level score on the International Math Olympiad, an exam for prodigious high schoolers. And in the past few months, an AI has solved multiple \u201cErd\u00f6s problems\u201d\u2014a trove of challenges set by the late mathematician Paul Erd\u00f6s. Startup AxiomMath made headlines last week for successfully tackling several research-level (though far from groundbreaking) math questions.<\/p>\n But none of these are controlled experiments. Olympiad problems aren\u2019t research questions. And LLMs seem to have a tendency to find existing, forgotten proofs deep in the mathematical literature and present them as original. One of AxiomMath\u2019s recent proofs, for example, turned out to be a misrepresented literature search.<\/p>\n And some math results coming from tech companies have raised eyebrows among academics for other reasons, says Daniel Spielman, a professor at Yale University and one of the experts behind the new challenge. \u201cAlmost all of the papers you see about people using LLMs are written by people at the companies that are producing the LLMs,\u201d says Spielman. \u201cIt comes across as a bit of an advertisement.\u201d<\/p>\n First Proof is an attempt to clear the smoke. To set the exam, eleven mathematical luminaries\u2014including one Fields medal winner\u2014contributed math problems that had arisen in their research. They also uploaded proofs of the solutions, but have encrypted them. The answers will decrypt on Friday, Feb. 13, just before midnight.<\/p>\n None of the proofs are earth-shattering. They\u2019re \u201clemmas,\u201d a word mathematicians use to describe the myriad tiny theorems they prove on the path to a more significant result. Lemmas aren\u2019t typically published as standalone papers.<\/p>\n But if AI can solve them, it would demonstrate what many mathematicians see as its near-term potential: a helpful tool to speed up the more tedious parts of math research.<\/p>\n \u201cI think the greatest impact AI is going to have this year on mathematics is not by solving big open problems, but through its penetration into the day-to-day lives of working mathematicians, which mostly has not happened yet,\u201d says Sutherland. \u201cThis may be the year when a lot more people start paying attention.\u201d<\/p>\n If you enjoyed this article, I\u2019d like to ask for your support. Scientific American<\/span> has served as an advocate for science and industry for 180 years, and right now may be the most critical moment in that two-century history.<\/p>\n I\u2019ve been a Scientific American<\/span> subscriber since I was 12 years old, and it helped shape the way I look at the world. SciAm <\/span>always educates and delights me, and inspires a sense of awe for our vast, beautiful universe. I hope it does that for you, too.<\/p>\n If you subscribe to Scientific American<\/span>, you help ensure that our coverage is centered on meaningful research and discovery; that we have the resources to report on the decisions that threaten labs across the U.S.; and that we support both budding and working scientists at a time when the value of science itself too often goes unrecognized.<\/p>\n In return, you get essential news, captivating podcasts, brilliant infographics, can’t-miss newsletters, must-watch videos, challenging games, and the science world’s best writing and reporting. You can even gift someone a subscription.<\/p>\n There has never been a more important time for us to stand up and show why science matters. I hope you\u2019ll support us in that mission.<\/p>\n","protected":false},"excerpt":{"rendered":" February 9, 2026 2 min read Add Us On GoogleAdd SciAm Mathematicians issue a major challenge to AI: show us your work Frustrated by AI industry claims of proving math results without transparency, a team of leading academics has proposed a better way By Joseph Howlett edited by Claire Cameron Alfred Gescheidt\/Getty Images The race<\/p>\n","protected":false},"author":1,"featured_media":44090,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[58],"tags":[3620,14721,3164,4693,8203,2567],"class_list":{"0":"post-44089","1":"post","2":"type-post","3":"status-publish","4":"format-standard","5":"has-post-thumbnail","7":"category-science","8":"tag-exam","9":"tag-firstofitskind","10":"tag-launch","11":"tag-math","12":"tag-mathematicians","13":"tag-proof"},"_links":{"self":[{"href":"https:\/\/naijaglobalnews.org\/index.php?rest_route=\/wp\/v2\/posts\/44089","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/naijaglobalnews.org\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/naijaglobalnews.org\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/naijaglobalnews.org\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/naijaglobalnews.org\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=44089"}],"version-history":[{"count":0,"href":"https:\/\/naijaglobalnews.org\/index.php?rest_route=\/wp\/v2\/posts\/44089\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/naijaglobalnews.org\/index.php?rest_route=\/wp\/v2\/media\/44090"}],"wp:attachment":[{"href":"https:\/\/naijaglobalnews.org\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=44089"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/naijaglobalnews.org\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=44089"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/naijaglobalnews.org\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=44089"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}On supporting science journalism<\/h2>\n
It\u2019s Time to Stand Up for Science<\/h2>\n