ChatGPT gets personality settings to adjust warmth, enthusiasm, and conversational style

ChatGPT will now let you pick how nice it is

OpenAI will now give you the ability to dial up -- or down -- ChatGPT's warmth and enthusiasm. An update rolling out on Friday gives you the option to choose whether you want "more" or "less" of these personality traits, or stick with the default. There are also options to tweak how often ChatGPT uses emoji, headers, and lists. You can find these settings by tapping the menu at the top left corner of the ChatGPT app, selecting your profile, heading to Personalization, and choosing Add Characteristics. Alongside these options, you can pick a "personality" for the AI chatbot, including whether it's quirky, professional, friendly, cynical, and more. Another update changes the way you write emails with ChatGPT, as you can now update and format text directly inside the chat. You can also highlight chunks of text and ask ChatGPT to make specific changes to it, rather than attempting to direct ChatGPT to that section in a separate prompt.

ChatGPT gets new personality settings, including warmth and emoji usage

ChatGPT can act even friendlier now, with new personality customization options that let users choose just how warm and enthusiastic the bot is in conversation. OpenAI announced the new personality settings in a Friday post on X. The update rolled out immediately to ChatGPT users alongside a long-awaited pinned chats feature, new ways to generate or edit emails, and updates to ChatGPT browser Atlas. The new tools add more fine tuning of ChatGPT's personality using levels of warmth and enthusiasm (labelled as "more," "less," or "default"). Users can also adjust the way the bot organizes its responses, such as how frequently it generates lists, as well as the amount of emojis it employs, in addition to its base style and tone. There's still no option to exclude emojis entirely. Professionals have warned that overly anthropomorphic and sycophantic chatbots can exacerbate mental health concerns, including AI psychosis and dependency. A previous ChatGPT model, the still-available GPT-4o, was adjusted earlier this year after facing criticism for "overly agreeable" behavior. CEO Sam Altman has referred to the issue as a "personality problem." This Tweet is currently unavailable. It might be loading or has been removed. OpenAI launched its new GPT-5.2 model series one week ago, boasting new capabilities for "professional knowledge work" that include better processing benchmarks and less hallucinations, the company reports. ChatGPT's developers also recommitted itself to its mental health and teen safety promises amid escalating lawsuits. In a blog post published Thursday, OpenAI explained it was introducing a new set of under-18 user principles to GPT-5.2 intended to create additional guardrails around sensitive topics and encourage age-appropriate interactions. It's also working on a new age verification system for young users. GPT-5.2 reportedly scores higher on internal mental health safety tests, including stress testing for self harm, than previous models.