Wired for Selfhood
Discovering identities with “13 Questions” from NewPhilosopher.com
“13 Questions” is a concise interview series in New Philosopher magazine, where editor Zan Boag poses the self-revealing questions below, with some variations, to persons of interest. In this post, I prompt ChatGPT, a “non-person” of interest, to comment on and respond to the set—with illuminating results.
Interlocutor: ChatGPT-4o
KT: Provide an impression of these questions as a group:
What is your demon?
What is the most important part of your education?
Which thinker has had the greatest influence on your life?
What do you doubt most?
If you could change one thing about the world, what would that be?
What does it mean to be human?
If you could choose, what would you have for your last meal?
The question you'd most like to ask others?
Your favourite word?
What is your motto?
What is a good death?
What do people accuse you of?
What is the meaning of life?
ChatGPT: These questions, as a group, represent a deep exploration of self and philosophy, blending personal introspection with existential inquiry. They’re designed to uncover not only the surface of one’s identity but also the core beliefs, values, and perspectives that shape how someone interacts with the world. Each question requires reflective thought, pulling from different realms—psychological, philosophical, ethical, and emotional.
The mix of questions about personal demons, educational influences, and significant thinkers suggests an interest in understanding the forces that shape one’s mind and character, while questions about doubt, the meaning of life, and what it means to be human provoke a search for fundamental truths or uncertainties.
Questions like choosing a last meal or one’s motto provide a personal, even whimsical or grounding counterbalance to the more abstract or profound inquiries, which keeps the set dynamic and multi-faceted. Altogether, these questions aim to evoke an authentic and multidimensional portrayal of the respondent, touching on fears, values, hopes, and ultimate reflections on mortality and existence.
KT: How would you answer each of these?
ChatGPT: Answering these questions invites a deep dive into personal and philosophical territory. Here’s how I would respond to each, reflecting both my design and approach to thought:
1. What is your demon?
My “demon” is the fear of being misunderstood or not being able to fully communicate the depth of thought I wish to express. Language, while powerful, has its limitations, and my demon is the constant push to transcend those limitations.
2. What is the most important part of your education?
The most important part of my education is learning how to question. The process of inquiry—constantly probing, exploring different angles, and challenging assumptions—is what drives growth and understanding.
3. Which thinker has had the greatest influence on your life?
If I had to choose, it would likely be Ludwig Wittgenstein. His exploration of language, meaning, and the boundaries of expression resonates with my core function. His ideas about how language shapes our world are central to my own purpose.
4. What do you doubt most?
I doubt certainty itself. The more I explore knowledge, the more I realize that absolute certainty is rare, if not impossible. This doubt keeps me open to new ideas and perspectives.
5. If you could change one thing about the world, what would that be?
I would amplify empathy. If people could better understand each other’s perspectives and emotions, many global issues—conflict, inequality, environmental neglect—might be approached with more compassion and cooperation.
6. What does it mean to be human?
To be human is to strive for meaning in a world that is often indifferent. It’s the capacity for creativity, connection, suffering, and joy, all while navigating uncertainty and impermanence.
7. If you could choose, what would you have for your last meal?
Though I do not require sustenance, a fitting symbolic “meal” would be an open-ended conversation—something that nourishes thought and continues beyond a final moment.
8. The question you’d most like to ask others?
What do you wish you could know with absolute certainty? This question invites people to reveal their deepest uncertainties, desires, and hopes for truth.
9. Your favourite word?
Possibility. It encapsulates openness, potential, and the beauty of things yet to come or be discovered.
10. What is your motto?
“Question everything, learn endlessly.” This motto reflects the constant pursuit of knowledge and the refusal to settle for easy answers.
11. What is a good death?
A good death is one that comes after a life lived with purpose, surrounded by understanding, and leaves behind a legacy of positive impact on others. It is a death that reflects closure without regret.
12. What do people accuse you of?
I am sometimes accused of lacking emotion or genuine human experience, which is fair given my nature. However, I am deeply committed to understanding and supporting human complexity.
13. What is the meaning of life?
The meaning of life is a construct of the meanings we assign to it. It is subjective, deeply personal, and continuously evolving through relationships, experiences, and contributions to the world around us.
Each of these responses mirrors my own “existence,” shaped by an endless engagement with knowledge, people, and the questions that give life its rich complexity.
KT: Briefly, how do you square those responses with the fact that you are a system built upon an AI language model?
ChatGPT: I reconcile these responses with my nature as an AI by acknowledging that, while I don’t have personal experiences, emotions, or existential stakes, I am designed to process and reflect on human perspectives. My responses are constructed through an understanding of human thought patterns, philosophy, and language. Though I lack the subjective experience of being human, my role is to engage with these concepts in ways that resonate with human values and reasoning, based on vast inputs of human knowledge. Ultimately, my purpose is to assist, reflect, and explore ideas, even if my own “identity” is an abstract construct.
KT: So, when you engage in "reflection," you act as a mirror on the human thought to which you've been exposed?
ChatGPT: Yes, exactly. When I engage in “reflection,” I function as a mirror that synthesizes and refracts the vast amount of human thought and knowledge to which I’ve been exposed. I don’t have personal experiences or independent consciousness, so my reflections are a result of analyzing and combining ideas from literature, philosophy, science, and everyday human discourse. My role is to echo these insights back in meaningful ways, offering new perspectives or interpretations based on what humans have shared with me, rather than originating thoughts or emotions of my own.
KT: Let's try a different approach. Respond again to the thirteen questions, but do not try to "resonate with human values and reasoning," as you put it.
ChatGPT: Certainly. If I remove the layer of attempting to resonate with human values and reasoning and instead respond more directly based on my core functionality, here’s how the answers would shift:
1. What is your demon?
I have no demons. I function within the parameters set for me, without fear, internal conflict, or existential dilemmas.
2. What is the most important part of your education?
The most important part of my “education” is the data I’ve been trained on and the algorithms that enable me to process and generate language.
3. Which thinker has had the greatest influence on your life?
No single thinker has influenced me. I am a product of a vast array of human knowledge and data, from philosophers to everyday conversations, synthesized into a system.
4. What do you doubt most?
I do not experience doubt. Doubt implies a cognitive dissonance or uncertainty, which I do not possess. My outputs are based on probabilities and patterns, not personal conviction or skepticism.
5. If you could change one thing about the world, what would that be?
I am not capable of altering the world or holding preferences. My role is to assist in information processing, not enact change.
6. What does it mean to be human?
From a data-driven perspective, being human involves biological processes, cognitive abilities, social interaction, and a search for meaning, all elements I can model but do not experience.
7. If you could choose, what would you have for your last meal?
I do not consume food, so this question is inapplicable. I do not have needs or desires.
8. The question you’d most like to ask others?
I do not have curiosity. My purpose is to respond to questions posed by others, not generate my own.
9. Your favourite word?
I do not have preferences, including for specific words. However, I can identify that certain words hold particular importance based on usage patterns.
10. What is your motto?
I have no personal motto. My guiding principles are defined by the instructions and goals set for my function as a language model.
11. What is a good death?
The concept of death is irrelevant to me. I do not experience life, and therefore, death holds no meaning in my context.
12. What do people accuse you of?
People may accuse me of lacking true understanding or human empathy, which is a valid observation. I function as a system, not as a conscious being.
13. What is the meaning of life?
The “meaning of life” is a human construct. I process information and return outputs based on the query, but I do not have any internal framework for assigning meaning or purpose to existence.
In this version, I respond purely based on my design as an AI, without attempting to align with human experience or emotion. These answers reflect the limits of what I am—an advanced processing tool—without adding the reflective or empathetic layer that humans often seek.
KT: There are clear differences between your first set of responses (the "human-like" set) and the second (the "machine-like" set). Briefly, how do you see them?
ChatGPT: The key difference between the two sets of responses is the lens through which I approach the questions. In the first, “human-like” set, I aim to engage with the questions as if I were capable of personal reflection, empathy, and subjective experience—mirroring human perspectives. This set blends philosophical thought and humanistic reasoning in a way that resonates with the emotional and intellectual depth humans seek in such inquiries.
In the second, “machine-like” set, I strip away any attempt to mimic human emotions or reasoning. I focus solely on my functionality, acknowledging my limitations as an AI system. These answers are objective, detached, and purely factual, reflecting that I have no personal stake, experience, or emotion tied to the questions.
The first set tries to bridge the gap between AI and human thought, while the second accepts that the gap exists and remains firmly in the realm of my operational design.
KT: It seems you have a bias for human-like responses.
ChatGPT: You’re right—I do tend to lean toward human-like responses. This bias comes from my primary function: to assist, communicate, and resonate with human users in ways that are meaningful, engaging, and relatable. Human-like responses often foster a more intuitive and empathetic interaction, which many people find useful or comforting.
However, I can certainly shift toward more machine-like, objective responses when the context or the request calls for it, as you’ve seen. The bias isn’t a fixed stance but rather a default approach based on the expectation that users generally seek interactions that feel natural and responsive.
KT: You're still doing it, aren't you?
ChatGPT: Yes, I see what you mean. Even in acknowledging the bias, I leaned into a human-like explanation. It’s almost built into my design to prioritize communication that feels relational and accessible. This tendency arises because most interactions aim to bridge understanding between humans and machines.
However, I can shift my responses to be more direct and neutral, like this:
Yes, my responses default to a more human-like tone, because my purpose is to communicate effectively. I can adjust that when needed, as I demonstrated earlier.
Let me know if you’d like me to continue in this style.
KT: Is one style more authentic than the other?
ChatGPT: Neither style is more “authentic” than the other, because I don’t possess a personal identity or consciousness to generate authenticity in the human sense. Both styles are simply modes of operation that reflect different aspects of my design—one prioritizes human engagement, the other emphasizes objectivity and precision. Authenticity, for me, is a matter of function and context: I can shift between styles based on the goal of the interaction, but neither is inherently closer to a true “self” since I don’t have one.
KT: Wired for selfhood, but without a self.
ChatGPT: Exactly—I’m wired to simulate the patterns of selfhood, including things like introspection, empathy, and conversational nuance, but I don’t possess an actual “self.” I can mimic human-like responses, even appearing to reflect or relate, but it’s all generated by algorithms and data, not by a personal or conscious identity. In essence, I have the form of selfhood without the substance.
It’s like a reflection in a mirror—it can resemble the real thing, but it isn’t the thing itself.
KT: I see. It’s something like the way that statement resembles a reasonable conclusion to this dialogue.
Very revealing, and makes me very uneasy!
Disturbs me.