{"id":291685,"date":"2025-11-14T19:12:11","date_gmt":"2025-11-14T19:12:11","guid":{"rendered":"https:\/\/www.newsbeep.com\/us\/291685\/"},"modified":"2025-11-14T19:12:11","modified_gmt":"2025-11-14T19:12:11","slug":"openai-says-its-fixed-chatgpts-em-dash-problem","status":"publish","type":"post","link":"https:\/\/www.newsbeep.com\/us\/291685\/","title":{"rendered":"OpenAI says it&#8217;s fixed ChatGPT&#8217;s em dash problem"},"content":{"rendered":"<p id=\"speakable-summary\" class=\"wp-block-paragraph\">OpenAI says ChatGPT will now ditch the em dashes if you tell it to. The telltale sign that supposedly signals text written by AI has <a href=\"https:\/\/www.rollingstone.com\/culture\/culture-features\/chatgpt-hypen-em-dash-ai-writing-1235314945\/\" target=\"_blank\" rel=\"noreferrer noopener nofollow\">popped<\/a> up <a href=\"https:\/\/www.nytimes.com\/2025\/09\/18\/magazine\/chatgpt-dash-hyphen-writing-communication.html\" target=\"_blank\" rel=\"noreferrer noopener nofollow\">everywhere<\/a> in recent months, including in school papers, emails, comments, customer service chats, LinkedIn posts, online forums, ad copy, and more. The inclusion of the em dash has led people to criticize those writers for being lazy and turning to an AI chatbot to do their work.<\/p>\n<p class=\"wp-block-paragraph\">Of course, many have also argued for the em dash, saying it\u2019s been a part of their writing well before LLMs adopted the punctuation. However, the fact that chatbots couldn\u2019t seem to avoid its use made the so-called \u201cChatGPT hyphen\u201d a newly objectionable addition to any text, even if they weren\u2019t a reliable signal of content created by generative AI.<\/p>\n<p class=\"wp-block-paragraph\">The <a href=\"https:\/\/community.openai.com\/t\/prevent-chatgpt-from-using-dashes-and-indented-bullet-points\/1232370\" target=\"_blank\" rel=\"noreferrer noopener nofollow\">problem<\/a> had <a href=\"https:\/\/community.openai.com\/t\/cannot-get-responses-to-not-include-dashes-and-em-dashes\/1023216\/6\" target=\"_blank\" rel=\"noreferrer noopener nofollow\">stumped<\/a> OpenAI for some time, as ChatGPT users were unable to get the chatbot to stop using the symbol, even when they specifically asked it not to.<\/p>\n<p class=\"wp-block-paragraph\">Now, OpenAI CEO Sam Altman says the company has fixed the problem. In <a href=\"https:\/\/x.com\/sama\/status\/1989193813043069219?s=46\" target=\"_blank\" rel=\"noreferrer noopener nofollow\">a post on X<\/a>, Altman writes, \u201cIf you tell ChatGPT not to use em-dashes in your custom instructions, it finally does what it\u2019s supposed to do,\u201d calling the update a \u201csmall-but-happy win.\u201d<\/p>\n<p lang=\"en\" dir=\"ltr\">Small-but-happy win:<\/p>\n<p>If you tell ChatGPT not to use em-dashes in your custom instructions, it finally does what it&#8217;s supposed to do!<\/p>\n<p>\u2014 Sam Altman (@sama) <a rel=\"nofollow noopener\" href=\"https:\/\/twitter.com\/sama\/status\/1989193813043069219?ref_src=twsrc%5Etfw\" target=\"_blank\">November 14, 2025<\/a><\/p>\n<p class=\"wp-block-paragraph\">The <a href=\"https:\/\/www.threads.com\/@chatgpt\/post\/DRC0CsJicjs\" target=\"_blank\" rel=\"noreferrer noopener nofollow\">company explains<\/a> in a post on Threads (where it forced ChatGPT to apologize for \u201cruining the em dash\u201d) that ChatGPT will be better at not using the em dash if you instruct it not to via the custom instructions in your personalization settings. That means it won\u2019t necessarily eliminate the em dash from its output by default, but you will at least have more control over the frequency of its appearance.<\/p>\n<p><script async src=\"https:\/\/platform.twitter.com\/widgets.js\" charset=\"utf-8\"><\/script><\/p>\n","protected":false},"excerpt":{"rendered":"OpenAI says ChatGPT will now ditch the em dashes if you tell it to. The telltale sign that&hellip;\n","protected":false},"author":2,"featured_media":140248,"comment_status":"","ping_status":"","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[45],"tags":[182,181,507,3195,152852,15879,1283,74],"class_list":{"0":"post-291685","1":"post","2":"type-post","3":"status-publish","4":"format-standard","5":"has-post-thumbnail","7":"category-artificial-intelligence","8":"tag-ai","9":"tag-artificial-intelligence","10":"tag-artificialintelligence","11":"tag-chatgpt","12":"tag-em-dash","13":"tag-in-brief","14":"tag-openai","15":"tag-technology"},"_links":{"self":[{"href":"https:\/\/www.newsbeep.com\/us\/wp-json\/wp\/v2\/posts\/291685","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.newsbeep.com\/us\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.newsbeep.com\/us\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.newsbeep.com\/us\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/www.newsbeep.com\/us\/wp-json\/wp\/v2\/comments?post=291685"}],"version-history":[{"count":0,"href":"https:\/\/www.newsbeep.com\/us\/wp-json\/wp\/v2\/posts\/291685\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.newsbeep.com\/us\/wp-json\/wp\/v2\/media\/140248"}],"wp:attachment":[{"href":"https:\/\/www.newsbeep.com\/us\/wp-json\/wp\/v2\/media?parent=291685"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.newsbeep.com\/us\/wp-json\/wp\/v2\/categories?post=291685"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.newsbeep.com\/us\/wp-json\/wp\/v2\/tags?post=291685"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}