{"id":172465,"date":"2023-09-20T23:22:53","date_gmt":"2023-09-21T04:22:53","guid":{"rendered":"https:\/\/lifeboat.com\/blog\/2023\/09\/telling-ai-model-to-take-a-deep-breath-causes-math-scores-to-soar-in-study"},"modified":"2023-09-20T23:22:53","modified_gmt":"2023-09-21T04:22:53","slug":"telling-ai-model-to-take-a-deep-breath-causes-math-scores-to-soar-in-study","status":"publish","type":"post","link":"https:\/\/lifeboat.com\/blog\/2023\/09\/telling-ai-model-to-take-a-deep-breath-causes-math-scores-to-soar-in-study","title":{"rendered":"Telling AI model to \u201ctake a deep breath\u201d causes math scores to soar in study"},"content":{"rendered":"<p><a class=\"aligncenter blog-photo\" href=\"https:\/\/lifeboat.com\/blog.images\/telling-ai-model-to-take-a-deep-breath-causes-math-scores-to-soar-in-study.jpg\"><\/a><\/p>\n<p>Google DeepMind researchers recently developed a technique to improve math ability in AI language models like ChatGPT by using other AI models to improve prompting\u2014the written instructions that tell the AI model what to do. It found that using human-style encouragement improved math skills dramatically, in line with earlier results.<\/p>\n<p>In a paper called \u201cLarge Language Models as Optimizers\u201d listed this month on arXiv, DeepMind scientists introduced Optimization by PROmpting (OPRO), a method to improve the performance of large language models (LLMs) such as OpenAI\u2019s ChatGPT and Google\u2019s PaLM 2. This new approach sidesteps the limitations of traditional math-based optimizers by using natural language to guide LLMs in problem-solving. \u201cNatural language\u201d is a fancy way of saying everyday human speech.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>Google DeepMind researchers recently developed a technique to improve math ability in AI language models like ChatGPT by using other AI models to improve prompting\u2014the written instructions that tell the AI model what to do. It found that using human-style encouragement improved math skills dramatically, in line with earlier results. In a paper called \u201cLarge [\u2026]<\/p>\n","protected":false},"author":359,"featured_media":0,"comment_status":"open","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[2229,6],"tags":[],"class_list":["post-172465","post","type-post","status-publish","format-standard","hentry","category-mathematics","category-robotics-ai"],"_links":{"self":[{"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/posts\/172465","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\/359"}],"replies":[{"embeddable":true,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/comments?post=172465"}],"version-history":[{"count":0,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/posts\/172465\/revisions"}],"wp:attachment":[{"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/media?parent=172465"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/categories?post=172465"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/tags?post=172465"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}