{"id":216968,"date":"2026-02-24T08:46:00","date_gmt":"2026-02-24T13:46:00","guid":{"rendered":"https:\/\/news-you-need.com\/index.php\/2026\/02\/24\/probably-doesnt-mean-the-same-thing-to-your-ai-as-it-does-to-you\/"},"modified":"2026-02-24T12:40:38","modified_gmt":"2026-02-24T17:40:38","slug":"probably-doesnt-mean-the-same-thing-to-your-ai-as-it-does-to-you","status":"publish","type":"post","link":"https:\/\/news-you-need.com\/index.php\/2026\/02\/24\/probably-doesnt-mean-the-same-thing-to-your-ai-as-it-does-to-you\/","title":{"rendered":"\u2018Probably\u2019 doesn\u2019t mean the same thing to your AI as it does to you"},"content":{"rendered":"<p><a href=\"https:\/\/theconversation.com\/probably-doesnt-mean-the-same-thing-to-your-ai-as-it-does-to-you-275626\">\u2018Probably\u2019 doesn\u2019t mean the same thing to your AI as it does to you<\/a><\/p>\n<p><a href=\"https:\/\/theconversation.com\/probably-doesnt-mean-the-same-thing-to-your-ai-as-it-does-to-you-275626\">https:\/\/theconversation.com\/probably-doesnt-mean-the-same-thing-to-your-ai-as-it-does-to-you-275626<\/a><\/p>\n<p>Publish Date: <a href=\"publish_date]\">2026-02-24 08:46:00<\/a><\/p>\n<p>Source Domain: <a href=\"theconversation.com\">theconversation.com<\/a><\/p>\n<p>When a human says an event is \u201cprobable\u201d or \u201clikely,\u201d people generally have a shared, if fuzzy, understanding of what that means. But when an AI chatbot like ChatGPT uses the same word, it\u2019s not assessing the odds the way we do, my colleagues and I found. <\/p>\n<p>We recently published a study in the journal NPJ Complexity that suggests that, while large language model AIs excel at conversation, they often fail to align with humans when communicating uncertainty. The research focused on words of estimative probability, which include terms like \u201cmaybe,\u201d \u201cprobably\u201d and \u201calmost certain.\u201d <\/p>\n<p>By comparing how AI models and humans map these words to numerical percentages, we uncovered significant gaps between humans and large language models. While the models do tend to agree with humans on extremes like \u201cimpossible,\u201d they diverge sharply on hedge words like \u201cmaybe.\u201d For example, a model might use the word \u201clikely\u201d to represent an 80% probability, while a human reader assumes it means closer to 65%.<\/p>\n<p>This could be because humans can interpret words such as \u201clikely\u201d and \u201cprobable\u201d based more on contextual cues and personal experiences. In contrast, large language models may be averaging over conflicting usages of those words in their training data, leading to divergences with human interpretations.<\/p>\n<p>Our study also found that large language models are sensitive to gendered language and the specific language used for prompting. When a prompt changed from \u201che\u201d to \u201cshe,\u201d the AI\u2019s probability estimates often became more rigid, reflecting biases embedded in its training data. When a prompt changed from English to Chinese, the AI\u2019s probability estimates often shifted, possibly due to differences between English and Chinese in how people express and understand uncertainty. <\/p>\n<p>              <span class=\"caption\">AI chatbots don\u2019t interpret \u2018probably\u2019 and \u2018maybe\u2019 the same way you do.<\/span><br \/>\n              <span class=\"attribution\"><span class=\"source\">Mayank Kejriwal<\/span><\/span><br \/>\n &#8230;<br \/>\n<br \/><a href=\"https:\/\/theconversation.com\/probably-doesnt-mean-the-same-thing-to-your-ai-as-it-does-to-you-275626\">Source<\/a><\/p>\n","protected":false},"excerpt":{"rendered":"<p>\u2018Probably\u2019 doesn\u2019t mean the same thing to your AI as it does to you https:\/\/theconversation.com\/probably-doesnt-mean-the-same-thing-to-your-ai-as-it-does-to-you-275626&#8230;<\/p>\n","protected":false},"author":1,"featured_media":216969,"comment_status":"closed","ping_status":"","sticky":false,"template":"","format":"standard","meta":{"fifu_image_url":"https:\/\/images.theconversation.com\/files\/720030\/original\/file-20260223-57-ey6vn9.jpg?ixlib=rb-4.1.0&rect=0%2C490%2C4897%2C2448&q=45&auto=format&w=1356&h=668&fit=crop","fifu_image_alt":"","footnotes":""},"categories":[14],"tags":[18],"class_list":["post-216968","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-artificial-intelligence","tag-large-language-model"],"_links":{"self":[{"href":"https:\/\/news-you-need.com\/index.php\/wp-json\/wp\/v2\/posts\/216968"}],"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=216968"}],"version-history":[{"count":1,"href":"https:\/\/news-you-need.com\/index.php\/wp-json\/wp\/v2\/posts\/216968\/revisions"}],"predecessor-version":[{"id":216970,"href":"https:\/\/news-you-need.com\/index.php\/wp-json\/wp\/v2\/posts\/216968\/revisions\/216970"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/news-you-need.com\/index.php\/wp-json\/wp\/v2\/media\/216969"}],"wp:attachment":[{"href":"https:\/\/news-you-need.com\/index.php\/wp-json\/wp\/v2\/media?parent=216968"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/news-you-need.com\/index.php\/wp-json\/wp\/v2\/categories?post=216968"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/news-you-need.com\/index.php\/wp-json\/wp\/v2\/tags?post=216968"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}