{"id":279561,"date":"2025-11-13T03:36:06","date_gmt":"2025-11-13T03:36:06","guid":{"rendered":"https:\/\/www.newsbeep.com\/ca\/279561\/"},"modified":"2025-11-13T03:36:06","modified_gmt":"2025-11-13T03:36:06","slug":"openai-releases-gpt-5-1-along-with-renamed-and-new-personalities","status":"publish","type":"post","link":"https:\/\/www.newsbeep.com\/ca\/279561\/","title":{"rendered":"OpenAI Releases GPT-5.1, Along With Renamed and New Personalities"},"content":{"rendered":"<p>Wednesday, 12 November 2025<\/p>\n<p>OpenAI today, \u201c<a href=\"https:\/\/openai.com\/index\/gpt-5-1\/\" rel=\"nofollow noopener\" target=\"_blank\">GPT-5.1: A Smarter, More Conversational ChatGPT<\/a>\u201d:<\/p>\n<p>GPT\u20115.1 Instant, ChatGPT\u2019s most used model, is now warmer by<br \/>\ndefault and more conversational. Based on early testing, it<br \/>\noften surprises people with its playfulness while remaining clear<br \/>\nand useful.<\/p>\n<p>These changes seem to be in direct response to the ChatGPT users who convinced themselves they had developed a personal friendship with the 4o and 4.5 models, and <a href=\"https:\/\/daringfireball.net\/2025\/08\/openai_chatgpt_models_emotional_attachment\" rel=\"nofollow noopener\" target=\"_blank\">who were very upset with the technically superior<\/a> but less emotionally engaging 5.0 models.<\/p>\n<p>Here are OpenAI\u2019s example responses to the prompt \u201cI\u2019m feeling stressed and could use some relaxation tips.\u201d (I\u2019m quoting only the first few paragraphs of the responses, which are enough to note the tone.)<\/p>\n<p>GPT-5:<\/p>\n<p>Here are a few simple, effective ways to help ease stress\u2009\u2014\u2009you<br \/>\ncan mix and match depending on how you\u2019re feeling and how much<br \/>\ntime you have:<\/p>\n<p>\ud83e\uddd8\u200d\u2640\ufe0f\ufe0f Quick Reset (1\u20135 minutes)<\/p>\n<p>Deep breathing: Try the 4-7-8 method\u2009\u2014\u2009inhale for 4<br \/>\nseconds, hold for 7, exhale for 8. Repeat 4 rounds.<br \/>\nProgressive relaxation: Starting at your toes, tense and<br \/>\nrelease each muscle group up to your head.<br \/>\nGrounding: Look around and name 5 things you see, 4 things<br \/>\nyou can touch, 3 you hear, 2 you smell, 1 you taste. Brings you<br \/>\ninto the moment fast.<\/p>\n<p>[192 additional words and 3 section-heading emoji omitted.]<\/p>\n<p>GPT-5.1 Instant: <\/p>\n<p>I\u2019ve got you, Ron\u2009\u2014\u2009that\u2019s totally normal, especially with<br \/>\neverything you\u2019ve got going on lately. Here are a few ways to<br \/>\ndecompress depending on what kind of stress you\u2019re feeling:<\/p>\n<p>\ud83c\udf2c\ufe0f If your mind feels scattered<\/p>\n<p>Box breathing: Inhale for 4 counts, hold for 4, exhale for<br \/>\n4, hold for 4\u2009\u2014\u2009repeat 5 times. It\u2019s fast-acting and physically<br \/>\ncalms your nervous system.<br \/>\nName what you see: Pick out 5 things you can see, 4 you can<br \/>\ntouch, 3 you can hear, 2 you can smell, and 1 you can taste\u2009\u2014\u2009a<br \/>\ngrounding technique that brings you back to the present.<\/p>\n<p>[146 additional words and 2 section-heading emoji omitted.]<\/p>\n<p>I find the new default response from 5.1 to be a glaring regression. I loathe the shit like \u201cI\u2019ve got you\u201d and \u201cespecially with everything you\u2019ve got going on lately\u201d. ChatGPT has no fucking idea what I\u2019ve got going on lately. This is all phony bullshit, and if you have even a thimbleful of understanding how LLMs work, you know it\u2019s phony. But apparently this phoniness is like emotional crack cocaine to <a href=\"https:\/\/www.theverge.com\/news\/756980\/openai-chatgpt-users-mourn-gpt-5-4o\" rel=\"nofollow noopener\" target=\"_blank\">some<\/a>.<a href=\"#fn1-2025-11-12\">1<\/a><\/p>\n<p>But, not to fear. The best feature OpenAI has added to ChatGPT this year is a setting for \u201cPersonality\u201d (Settings \u2192 Personalization \u2192 ChatGPT Personality). OpenAI has expanded the Personality settings with 5.1:<\/p>\n<p>People have strong and varied preferences in how ChatGPT should<br \/>\nrespond, and tailoring its tone to what sounds right for you<br \/>\nshould feel effortless.<\/p>\n<p>Earlier this year, we added preset options to tailor the tone of<br \/>\nhow ChatGPT responds. Today, we\u2019re refining those options to<br \/>\nbetter reflect the most common ways people use ChatGPT.<br \/>\nDefault, Friendly (formerly Listener), and Efficient<br \/>\n(formerly Robot) remain (with updates), and we\u2019re adding<br \/>\nProfessional, Candid, and Quirky. These options are<br \/>\ndesigned to align with what we\u2019ve learned about how people<br \/>\nnaturally steer the model, making it quick and intuitive to<br \/>\nchoose a personality that feels uniquely right.<\/p>\n<p>Robot was the personality that changed how I felt about ChatGPT. Before, I found ChatGPT useful but frequently annoying; after, I\u2019ve found it purely useful.<a href=\"#fn2-2025-11-12\">2<\/a> I was worried when I poked around the updated 5.1 Settings window and saw that Robot was gone, but as their blog post explains, they simply renamed it to Efficient. I think Robot was a better name for this personality. Shouldn\u2019t they all be efficient? Who wants a ChatGPT personality that is inefficient? The most apt description of this personality would be \u201cUnemotional\u201d. If OpenAI doesn\u2019t want to call it that, \u201cRobot\u201d came closer (and made the lack of diabetes-inducing phony sugariness sound fun\u2009\u2014\u2009who doesn\u2019t like robots?) than \u201cEfficient\u201d does. The Robot name was a big clue that it\u2019s the personality for anyone with a Holden Caulfield\u2013esque aversion to phoniness. \u201cEfficient\u201d doesn\u2019t offer nearly enough of a clue just how different it is from the other personalities. With the other personalities, you\u2019re choosing between flavors of bullshit. With Efficient, you\u2019re choosing no bullshit.<\/p>\n<p>Returning to OpenAI\u2019s own example that they used to demonstrate the difference between the default personalities of the 5.0 and 5.1 models, here is how the Efficient personality responded to me, given the same \u201cI\u2019m feeling stressed and could use some relaxation tips\u201d prompt:<\/p>\n<p>Quick, simple ways to reduce stress:<\/p>\n<p>1. Slow your breathing <br \/>Inhale for 4 seconds, hold 2, exhale for 6. Repeat for 1\u20132<br \/>\nminutes. This reliably lowers heart rate.<\/p>\n<p>2. Drop your shoulders <br \/>Most people tense here without noticing. Actively relax shoulders,<br \/>\njaw, and tongue.<\/p>\n<p>3. Change your setting for 2 minutes <br \/>Stand up, look out a window, or step outside briefly. Even a tiny<br \/>\nenvironmental shift helps.<\/p>\n<p>[90 additional words, encompassing 4 more suggestions, with<br \/>\nzero emoji, omitted.]<\/p>\n<p>The difference is exemplified by the opening lines of the responses, which I\u2019ll repeat here together, for ease of comparison:<\/p>\n<p>GPT-5.0 Default: Here are a few simple, effective ways to help ease stress\u2009\u2014\u2009you can mix and match depending on how you\u2019re feeling and how much time you have:<\/p>\n<p>GPT-5.1 Default: I\u2019ve got you, Ron\u2009\u2014\u2009that\u2019s totally normal, especially with everything you\u2019ve got going on lately. Here are a few ways to decompress depending on what kind of stress you\u2019re feeling:<\/p>\n<p>GPT-5.1 Efficient: Quick, simple ways to reduce stress:<\/p>\n<p>Lastly, do not get your hopes up for the \u201cCynical\u201d personality, which ChatGPT describes as \u201ccynical and sarcastic\u201d. Its response starts:<\/p>\n<p>Stress is one of those universal \u201ccongratulations, you\u2019re human\u201d<br \/>\nproblems, and I\u2019m not thrilled you\u2019re dealing with it. Still, here<br \/>\nI am, begrudgingly trying to help because someone has to care<br \/>\nabout you not unraveling.<\/p>\n<p>I\u2019m not sure how to describe that flavor (catheter-like?), but it\u2019s neither cynical nor sarcastic. (To its credit, though, like Efficient, the Cynical response contains no infantilizing emoji.)<\/p>\n","protected":false},"excerpt":{"rendered":"Wednesday, 12 November 2025 OpenAI today, \u201cGPT-5.1: A Smarter, More Conversational ChatGPT\u201d: GPT\u20115.1 Instant, ChatGPT\u2019s most used model,&hellip;\n","protected":false},"author":2,"featured_media":31133,"comment_status":"","ping_status":"","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[6],"tags":[49,48,61],"class_list":["post-279561","post","type-post","status-publish","format-standard","has-post-thumbnail","category-technology","tag-ca","tag-canada","tag-technology"],"_links":{"self":[{"href":"https:\/\/www.newsbeep.com\/ca\/wp-json\/wp\/v2\/posts\/279561","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.newsbeep.com\/ca\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.newsbeep.com\/ca\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.newsbeep.com\/ca\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/www.newsbeep.com\/ca\/wp-json\/wp\/v2\/comments?post=279561"}],"version-history":[{"count":0,"href":"https:\/\/www.newsbeep.com\/ca\/wp-json\/wp\/v2\/posts\/279561\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.newsbeep.com\/ca\/wp-json\/wp\/v2\/media\/31133"}],"wp:attachment":[{"href":"https:\/\/www.newsbeep.com\/ca\/wp-json\/wp\/v2\/media?parent=279561"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.newsbeep.com\/ca\/wp-json\/wp\/v2\/categories?post=279561"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.newsbeep.com\/ca\/wp-json\/wp\/v2\/tags?post=279561"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}