OpenAI expands ChatGPT personalisation with fine-grained tone controls

The update allows users to fine-tune ChatGPT’s warmth, enthusiasm, emoji usage and formatting style, reflecting OpenAI’s effort to give users more control over how the AI communicates.

OpenAI has rolled out new personalisation features for ChatGPT, enabling users to customise the chatbot’s tone and presentation in greater detail. The update introduces adjustable controls that let users decide how warm, enthusiastic or emoji-friendly ChatGPT’s responses should be, moving beyond fixed personality presets.

The new options are available under ChatGPT’s Personalization menu, where users can set individual characteristics to “More,” “Less,” or “Default.” Similar controls are also being added for formatting preferences, including how frequently the chatbot uses headers, bullet points and structured lists in its responses.

Greater control over ChatGPT’s personality

According to OpenAI, the latest changes build on tone presets such as Professional, Candid and Quirky, which were introduced late last year. By adding granular sliders, the company is allowing users to fine-tune specific traits rather than relying on a single predefined style.

OpenAI said the feature is designed to let people shape interactions based on their preferences—whether they want concise, neutral replies or more expressive, conversational responses. The move also shifts responsibility for tone from the AI itself to the user, reducing the need for a one-size-fits-all default personality.

Balancing friendliness and responsibility

Tone has been a sensitive issue for OpenAI in recent months. Earlier updates were partially rolled back after users complained that ChatGPT responses felt overly flattering and excessively agreeable. More recent model changes triggered the opposite feedback, with some users describing replies as blunt or impersonal.

Researchers have also raised concerns that overly affirming AI systems could reinforce biases or foster unhealthy emotional dependence. OpenAI has previously acknowledged these risks, stating that helpfulness and friendliness must be balanced with appropriate safeguards.

By introducing explicit tone controls, OpenAI appears to be addressing these concerns while giving users greater autonomy. For everyday users, the update represents a subtle but meaningful shift, making ChatGPT feel less like a fixed conversational product and more like a configurable digital assistant that adapts to individual communication styles.