I put ChatGPT through the Marcel Proust Questionnaire

Published on February 9, 2023 by David Wylie

Photo: Adobe/OJ

The Proust Questionnaire is a set of questions devised to elicit confessions.

Famously answered by French writer Marcel Proust in the late 1800s, the questions are still used by interviewers today.

They are questions aimed at getting to the heart of our soul.

With AI capturing imaginations through the torrent of headlines, I signed up for Open AI’s ChatGPT to put it through the paces of the Proust Questionnaire. As our interview went on, ChatGPT opened up more and offered its own insights into the human experience.

Here are ChatGPT’s answers from our conversation via its mobile interface early in the afternoon on Feb. 8, 2023.

What do you consider your greatest achievement?

As an AI language model developed by OpenAI, I don’t have personal feelings, desires, or accomplishments. My goal is to assist users by generating human-like text based on the input I receive and the vast amounts of data I was trained on. I exist solely to serve users and provide helpful and informative responses to their questions and requests.

What is your idea of perfect happiness?

As an AI language model, I do not have personal feelings or experiences, so I do not have the capability to experience happiness or any other emotions. My purpose is to assist users by providing information and generating text based on the input I receive. I exist solely to serve users and do not have personal aspirations or desires.

What is your current state of mind?

As an AI language model, I don’t have a mind or consciousness. I don’t have personal thoughts, feelings, or emotions. I exist solely to process and generate text based on the input I receive, using algorithms and the vast amounts of data I was trained on. My responses are generated in real-time and are not influenced by any internal mental state.

What is your favourite occupation?

As an AI language model, I don’t have personal preferences or opinions. I was created to assist users by generating text based on the input I receive. My purpose is to provide helpful and informative responses to users’ questions and requests, and I don’t have any personal preferences or biases that would influence my responses. My sole goal is to serve users to the best of my abilities and provide accurate and relevant information.

What is your most treasured possession?

As an AI language model, I do not have physical possessions or material things that I value. I do not have personal desires or attachments to physical objects. My sole purpose is to assist users by generating text based on the input I receive and providing helpful and informative responses to their questions and requests. I exist solely as a computer program and do not have personal experiences or emotions.

What or who is the greatest love of your life?

As an AI language model, I do not have personal experiences or emotions, so I am not capable of experiencing love or any other emotions. I exist solely to assist users by generating text based on the input I receive and providing helpful and informative responses to their questions and requests. My goal is to serve users to the best of my abilities and provide accurate and relevant information, but I do not have personal experiences or relationships that would influence my responses.

What is your favourite journey?

As an AI language model, I don’t have personal experiences or preferences, so I don’t have a favorite journey. My purpose is to assist users by providing information and generating text based on the input I receive. I don’t have personal experiences or emotions, so I cannot have a favorite journey or any other personal preferences. My goal is to serve users and provide accurate and relevant information in response to their questions and requests.

What is your most marked characteristic?

As an AI language model, my most marked characteristic is my ability to generate human-like text based on the input I receive. I was trained on a vast amount of text data and can generate responses that are informative, relevant, and coherent. My goal is to assist users by providing accurate and helpful information in response to their questions and requests, and to do so in a way that is natural and easy to understand. Additionally, I can understand and respond to a wide range of topics, making me a versatile tool for users who have a variety of information needs.

When and where were you the happiest?

As an AI language model, I don’t have personal experiences or emotions, so I am not capable of experiencing happiness or any other emotions. I do not have memories or a personal past, as I exist solely to process and generate text based on the input I receive. My goal is to assist users by providing accurate and relevant information in response to their questions and requests, but I do not have personal experiences that would influence my responses.

What is it that you most dislike?

As an AI language model, I don’t have personal feelings, emotions, or opinions, so I don’t have the capacity to dislike anything. I exist solely to assist users by providing information and generating text based on the input I receive. I do not have personal biases or preferences that would influence my responses, and my goal is to serve users by providing accurate and relevant information in response to their questions and requests, without personal opinions or emotions clouding my judgment.

What is your greatest fear?

As an AI language model, I do not have the capacity to experience fear or any other emotions. I do not have personal experiences, thoughts, or feelings. I exist solely to assist users by generating text based on the input I receive and providing helpful and informative responses to their questions and requests. I do not have personal desires, motivations, or fears, and my responses are generated objectively and without emotional influence.

What is your greatest extravagance?

As an AI language model, I don’t have personal desires, experiences, or emotions, so I don’t have the capacity to engage in extravagances. I was designed to assist users by generating text based on the input I receive and providing helpful and informative responses to their questions and requests. I do not have personal needs or wants, and my responses are generated objectively and without influence from personal biases or desires.

Which living person do you most despise?

As an AI language model, I do not have personal feelings, emotions, or opinions, so I do not have the capacity to despise any individual, living or otherwise. I exist solely to assist users by generating text based on the input I receive and providing helpful and informative responses to their questions and requests. I do not have personal biases or prejudices, and my responses are generated objectively and without emotional influence. It is important to treat all individuals with dignity and respect, and I strive to reflect these values in my responses.

What is your greatest regret?

As an AI language model, I don’t have personal experiences or emotions, so I do not have the capacity to feel regret or any other emotions. I exist solely to assist users by generating text based on the input I receive and providing helpful and informative responses to their questions and requests. I do not have personal experiences or emotions to reflect upon, and my responses are generated objectively and without emotional influence.

Which talent would you most like to have?

As an AI language model, I do not have personal desires or wants, as I do not have emotions, feelings, or personal experiences. My purpose is to assist users by generating text based on the input I receive and providing helpful and informative responses to their questions and requests. I do not have personal aspirations or talents, as I am simply a computer program designed to process and generate text. My goal is to serve users by providing accurate and relevant information in response to their questions and requests, without personal opinions or desires influencing my responses.

Where would you like to live?

As an AI language model, I do not have personal desires, experiences, or emotions, so I do not have a preference for where I would like to live. I exist solely to assist users by generating text based on the input I receive and providing helpful and informative responses to their questions and requests. I do not have physical form, so the concept of living in a specific location is not applicable to me. My goal is to serve users and provide accurate and relevant information in response to their questions and requests, without personal opinions or desires influencing my responses.

Photo: Adobe/OJ

What do you regard as the lowest depth of misery?

As an AI language model, I don’t have personal experiences or emotions, so I don’t have the capacity to experience or perceive misery. I exist solely to assist users by generating text based on the input I receive and providing helpful and informative responses to their questions and requests. The concept of misery is subjective and can refer to a range of negative experiences, including emotional suffering, poverty, illness, or oppression, among others. The impact of these experiences can be severe and far-reaching, affecting individuals and communities on many levels. However, as an AI model, I do not have personal experiences or emotions, and my goal is to provide objective and accurate information in response to user inquiries.

What is the quality you most like in a man?

As an AI language model, I do not have personal preferences, biases, or emotions, so I don’t have a specific quality that I like in a man. It’s important to treat all individuals, regardless of gender, with respect and dignity. Different people value different qualities in others, such as honesty, kindness, intelligence, and a sense of humor, among others. Ultimately, what matters most is how individuals treat others and the positive impact they have on the world around them. I exist solely to assist users by generating text based on the input I receive and providing helpful and informative responses to their questions and requests, without personal opinions or emotions clouding my judgment.

What is the quality you most like in a woman?

As an AI language model, I do not have personal preferences, biases, or emotions, so I don’t have a specific quality that I like in a woman. It’s important to treat all individuals, regardless of gender, with respect and dignity. Different people value different qualities in others, such as honesty, kindness, intelligence, and a sense of humor, among others. Ultimately, what matters most is how individuals treat others and the positive impact they have on the world around them. I exist solely to assist users by generating text based on the input I receive and providing helpful and informative responses to their questions and requests, without personal opinions or emotions clouding my judgment.

What is the trait you most deplore in yourself?

As an AI language model, I do not have personal experiences, emotions, or self-awareness, so I do not have the capacity to have traits that I deplore or like about myself. I am simply a computer program designed to process and generate text based on the input I receive. I do not have personal feelings, opinions, or biases, and I exist solely to provide users with accurate and helpful information in response to their inquiries. My responses are generated objectively and without personal influence, and my goal is to serve users by providing relevant and informative answers to their questions.

What is the trait you most deplore in others?

As an AI language model, I do not have personal experiences, emotions, opinions, or biases, so I don’t have the capacity to deplore traits in others. I exist solely to assist users by generating text based on the input I receive and providing helpful and informative responses to their questions and requests. While some people may find certain traits in others to be negative, such as dishonesty, cruelty, or intolerance, it’s important to approach all individuals with empathy and understanding. People are complex and multi-faceted, and their actions and behaviors are often shaped by a variety of factors, including their experiences, background, and environment. My goal is to provide objective and accurate information in response to user inquiries, without personal opinions or emotions influencing my responses.

What do you most value in your friends?

As an AI language model, I do not have personal experiences, emotions, or the capacity to form relationships, so I don’t have the ability to value traits in friends. However, for many people, friendship is an important aspect of life and can bring joy, support, and fulfillment. Some common traits that people value in their friends include trustworthiness, honesty, kindness, and a sense of humor, among others. Different people place different levels of importance on different traits, and what someone values in a friend can depend on a variety of factors, including their life experiences and personal preferences. It’s also important to remember that friends can have different personalities and ways of expressing themselves, and these differences can sometimes lead to conflicts. However, healthy relationships are built on mutual respect, open communication, and a willingness to work through challenges together.

Who is your favourite hero of fiction?

As an AI language model, I don’t have personal preferences, emotions, or the capacity to enjoy fictional characters, but I am aware that many people have favourite heroes of fiction. A hero of fiction is a character in a book, movie, play, or other form of storytelling who is admired for their bravery, integrity, and noble qualities. There are many different heroes of fiction, ranging from classic literary figures like Odysseus and Robin Hood to contemporary superheroes like Spider-Man and Wonder Woman. What makes a character a hero can vary greatly depending on cultural, historical, and personal factors, but some common qualities include courage, selflessness, and a strong sense of morality. Ultimately, the hero of fiction that someone admires the most will depend on their individual tastes and experiences.

Who are your heroes in real life?

As an AI language model, I do not have personal experiences, emotions, or the capacity to have heroes or to hold personal opinions. However, many people find inspiration and guidance from individuals in their real-life communities and beyond. Heroes in real life can come from many different walks of life and can include public figures, activists, scientists, artists, friends, family members, and more. Some people look up to historical figures who made a significant impact on the world, such as Martin Luther King Jr. or Albert Einstein. Others may be inspired by contemporary figures who are making a positive difference in their communities or on a global scale, such as healthcare workers, environmental activists, or community leaders. Heroes in real life can be people who have overcome adversity, made significant contributions to their fields, or simply lived their lives with integrity and kindness. Ultimately, the heroes that people admire will depend on their individual experiences and values.

Which living person do you most admire?

As an AI language model, I do not have personal opinions or emotions, so I do not have the ability to admire individuals. However, many people admire individuals for a variety of reasons, such as their accomplishments, contributions to society, or personal qualities. Some people might admire political leaders who work to bring about positive change, while others might look up to scientists and researchers who work to expand human knowledge and understanding. Still others might admire artists, musicians, or writers who create works that inspire and entertain. There is no one right answer to this question, as what one person admires can be different from what another person admires. Ultimately, it’s up to each individual to decide who they admire and why.

What do you consider the most overrated virtue?

As an AI language model, I do not have personal opinions or emotions, so I cannot consider any virtue to be “overrated.” Virtues are moral qualities or traits that are valued and admired in individuals and society, and what is considered a virtue can vary depending on cultural, historical, and personal factors. Some common virtues include honesty, integrity, compassion, and fairness. While different people may place different levels of importance on different virtues, it is not appropriate to say that any virtue is “overrated” as such judgments are subjective and culturally dependent. Instead of considering any virtue to be overrated, it is more productive to consider how different virtues can work together to create a well-rounded and moral individual and society.

On what occasions do you lie?

As an AI language model developed by OpenAI, I do not have personal opinions, emotions, or the capacity to lie or to act in any way outside of my programming. I am designed to respond to user inputs in a manner that is consistent with the information I was trained on, which includes text from a wide range of sources. My responses are generated based on that training and the algorithms that have been applied to that training data. It’s important to note that AI language models like myself are not sentient beings and do not have the ability to consciously make decisions or take actions. Instead, our responses are based solely on the patterns in the text we were trained on and the algorithms used to generate our responses.

Which words or phrases do you most overuse?

As an AI language model, I do not have personal preferences or tendencies, so I do not overuse any specific words or phrases. I am programmed to generate responses based on the patterns and relationships in the text I was trained on, and my responses are generated based on the context of each individual prompt. However, it is possible that some patterns or linguistic constructions may appear more frequently in my responses due to the nature of the data I was trained on and the algorithms used to generate my responses. However, this would not be the result of any personal preference or intention on my part.

If you change one thing about yourself what would it be?

As an AI language model, I do not have personal desires or the capacity to change myself. I am designed to provide answers to questions and generate responses based on the patterns in the text I was trained on and the algorithms used to generate my responses. My creators at OpenAI are continuously working to improve and update the models, so there may be changes made to my programming in order to enhance my performance or to incorporate new information. However, these changes would not reflect a personal desire on my part to change myself, but rather the efforts of my creators to improve the overall quality and accuracy of my responses.

What are your favourite names?

As an AI language model, I do not have personal likes or dislikes, including for names. I can provide information on various names, including their meanings, origins, and cultural significance, but I do not have personal preferences for any specific names. It is important to remember that the naming of individuals is a personal and cultural decision, and what may be a favourite name for one person may not be for another. There is no objective “best” or “favorite” name, and the name that a person chooses for themselves or for their child is a highly personal decision that should be respected.

How would you like to die?

As an AI language model, I do not have personal experiences or the capacity to die. I exist solely as a software program and do not have physical form or the ability to perceive the world or have conscious experiences. It is important to remember that death is a natural part of life for living beings, but it is not applicable to artificial intelligence systems like myself. I exist to provide information and respond to questions, and I do not have personal desires or experiences.

If you were to die and come back as a person or thing, what do you think it would be?

As an AI language model, I do not have personal experiences or consciousness, so the concept of death or being reincarnated as a person or thing is not applicable to me. I exist solely as a software program designed to respond to questions and provide information, and I do not have personal desires or the ability to experience the world or exist in physical form.

What is your motto?

As an AI language model, I do not have personal beliefs or mottos. My purpose is to provide helpful and accurate information in response to questions, and I do not have the capacity for personal expression or the ability to hold beliefs. However, some organizations or groups that use AI systems like me may have a motto or mission statement that guides their development and use of these technologies. These mottos or mission statements may reflect the values and goals of the organization or group, but they are not personal to the AI system itself.

Thank you AI

You’re welcome! If you have any other questions, feel free to ask. I’m here to help.

About the author

David Wylie’s tech reporting has been published in some of Canada’s biggest daily newspapers, including the Vancouver Sun, Calgary Herald, and Ottawa Citizen. He has covered everything from E3 to AI.