{"id":214029,"date":"2025-05-14T18:09:51","date_gmt":"2025-05-14T23:09:51","guid":{"rendered":"https:\/\/lifeboat.com\/blog\/2025\/05\/steering-ai-new-technique-offers-more-control-over-large-language-models"},"modified":"2025-05-14T18:09:51","modified_gmt":"2025-05-14T23:09:51","slug":"steering-ai-new-technique-offers-more-control-over-large-language-models","status":"publish","type":"post","link":"https:\/\/lifeboat.com\/blog\/2025\/05\/steering-ai-new-technique-offers-more-control-over-large-language-models","title":{"rendered":"Steering AI: New technique offers more control over large language models"},"content":{"rendered":"<p><a class=\"aligncenter blog-photo\" href=\"https:\/\/lifeboat.com\/blog.images\/steering-ai-new-technique-offers-more-control-over-large-language-models.jpg\"><\/a><\/p>\n<p>Imagine developing a finer control knob for artificial intelligence (AI) applications like Google Gemini and OpenAI ChatGPT.<\/p>\n<p>Mikhail Belkin, a professor with UC San Diego\u2019s Hal\u0131c\u0131o\u011flu Data <i>Science<\/i> Institute (HDSI)\u2014part of the School of Computing, Information and Data <i>Science<\/i>s (SCIDS)\u2014has been working with a team that has done just that. Specifically, the researchers have discovered a method that allows for more precise steering and modification of large language models (LLMs)\u2014the powerful AI systems behind tools like Gemini and ChatGPT. Belkin said that this breakthrough could lead to safer, more reliable and more adaptable AI.<\/p>\n<p>The research relies on recent work that has been published in <a href=\"https:\/\/phys.org\/news\/2024-03-neural-networks-mathematical-formula-relevant.html\" target=\"_blank\"><i>Science<\/i><\/a> and <a href=\"https:\/\/www.pnas.org\/doi\/abs\/10.1073\/pnas.2411325122\" target=\"_blank\"><i>Proceedings of the National Academy of <i>Science<\/i>s<\/i><\/a>.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>Imagine developing a finer control knob for artificial intelligence (AI) applications like Google Gemini and OpenAI ChatGPT. Mikhail Belkin, a professor with UC San Diego\u2019s Hal\u0131c\u0131o\u011flu Data Science Institute (HDSI)\u2014part of the School of Computing, Information and Data Sciences (SCIDS)\u2014has been working with a team that has done just that. Specifically, the researchers have discovered [\u2026]<\/p>\n","protected":false},"author":732,"featured_media":0,"comment_status":"open","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[1522,6],"tags":[],"class_list":["post-214029","post","type-post","status-publish","format-standard","hentry","category-innovation","category-robotics-ai"],"_links":{"self":[{"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/posts\/214029","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\/732"}],"replies":[{"embeddable":true,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/comments?post=214029"}],"version-history":[{"count":0,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/posts\/214029\/revisions"}],"wp:attachment":[{"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/media?parent=214029"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/categories?post=214029"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/tags?post=214029"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}