When the Ai are wrong and we point it out, most of the time he apologizes and gives us reason. But why does it do it? Why doesn’t it react badly and don’t get angry? All this depends on the “character” and “personality” set by the model developing company. The character of a AI, said in simple words, is the way in which it interacts with the world.
Defining this personality is a complex challenge, above all because the AI must interface with people of very different cultures, ideas and values. Even the most experienced companies can make mistakes: a recent example is GPT-5, the new chatgpt model released in early August, which has received criticism in some aspects related to its “personality”. To remedy this type of problems, it is possible to customize, at least in part, the character of chatgpt.
What is the character of an I and why it is important
The “character” of an AI is the set of its stylistic, communicative and behavioral traits. It manifests itself in the tone that adopts (friendly, formal, creative …), in the way it builds the phrases and in its “attitude”: how detailed or concise it is, if it does questions, if it is more proactive or passive. In short, it is the way it talks to us and relates to the world.
This aspect has a huge impact on the experience of use. If a AI is too condescending, long -winded or tends to invent answers, the user will lose confidence and stop using it. But not only that: the “personality” of AI also determines the way in which it answers spiny questions and reacts to the different scenarios. If there was, absurdly, a AI with an “evil” personality and asked her how we should treat animals, she would answer something like “should suffer”. This response, of course, goes against our ethical principles and we would never want to receive it from an AI. But how can we prevent the AI for answers of this type?
How to control the character of artificial intelligence
Training artificial intelligence models to have good “personality” is part of the “alignment” processes, that is, all those processes that serve to ensure that the responses generated by the AI are “aligned” to the human values and the ethical principles of the company that develops it. The definition and creation of the character of an AI model that happens during the final development phase of the model. Once the character has been established, however, it may happen that in the phase of use the model moves away from that alignment due to the interactions with users.
It is not yet completely clear how these changes take place, but Anthropic’s research team, the company that develops Claude, has published a study at the end of July 2025 in which it presents possible solutions to control them. By studying Claude a bit as if it were a brain, they managed to identify which activities of activity within the model control character traits such as the “malice”, the use of the user and the propensity to invent false information.
They called these patterns of “personality carriers” activities and showed that adding them and subtracting them from the model were able to change their behavior at least in part. Thanks to these personality carriers, therefore, they managed to monitor if and how the personality of a model changed during a conversation, to correct the shot and prevent the onset of negative characteristics during the development of the model.
Chatgpt has personality problems
Being able to calibrate well the personality of an AI is an extremely difficult job even the biggest companies make mistakes. At the end of April 2025 Openai, the company that develops chatgpt, had to collect an update within 72 hours precisely because of its “personality”. The new update, in fact, was excessively servile: it praised and celebrated every use of users, generating a sense of discomfort and annoyance.
In these days it seems that there is a new problem related to the personality, this time of GPT-5, the latest model released to the public. According to users, his personality is too cold, “robotics” and not very friendly. The CEO of Openai, Sam Altman, said on X that the team is already working on an update to improve the personality of the model. At the same time, he underlined the long -term goal of the company: to offer each user the opportunity to completely customize the character of their chatgpt.
A first step in this direction has already been taken with the introduction of 4 predefined personalities, currently in the test phase. Let’s see how to set them.
How to customize the character of your chatgpt
First of all, it is important to clarify that the customizations available for Chatgpt do not change what the model can or cannot do, nor alter the safety rules or ethical values established by Openai. Even if we ask him to use an offensive or racist language, he will not do it: these limits remain active to protect users’ experience.
Having said that, to personalize, at least partially, the personality of your chatgpt, just go to your profile, click on “Customize chatgpt” and, to the question “what a personality should have chatgpt” choose one of the 4 new available personalities: cynical, robot, capable of listening, nerd. Once the new personality is selected, it is necessary to save the change and start a new conversation, because those already in progress will maintain the previous tone. At any time, it is possible to return to the original personality.
For an even more advanced customization, you can intervene directly on the field “What kind of interaction must it use chatgpt?”, Specifying for example if you want a professional, ironic, playful or other tone. Based on these instructions, the behavior of the model can change significantly – always respecting the ethical guidelines of Openai.
