Philosophical prompt engineering in an AI-driven world

November 28, 2023
Introduction

In a world increasingly intertwined with intelligent machines and human thought, the significance of philosophical inquiry grows ever more crucial. This importance is amplified in the age of digitalization, rapid artificial intelligence development, and the omnipresence of information that provides instant answers. Understanding the dynamics of questioning and mastering the art of asking the right questions become essential. Philosophizing about the art of questioning can thus forge a better relationship with digitalization and AI. In the era of generative AI, the ability to ask the right question—a skill deeply embedded in philosophical tradition—is invaluable. It enhances our interaction with technology and underscores that, despite technological progress, human thinking and curiosity remain paramount. This comprehensive article explores the profound link between philosophy, smart chatbots, philosophical questioning, and AI-generated responses.

The philosophical tradition of asking questions

Philosophical questions, which delve into the fundamental aspects of our existence and critically reflect upon them, have always been central to the human experience. From ancient civilizations to the present day, such questions have been instrumental in helping us comprehend our world, define our role within it, and decipher the intricate relationships between humanity, knowledge, and the world.

In ancient Greece, Socrates, with his renowned Socratic method, championed the idea that questioning leads to truth and wisdom. His approach was not about providing answers but about challenging assumptions and fostering deeper thought. Iconic philosophers like Kant, Hegel, and Heidegger formulated their unique perspectives and methodologies through original, creative, and, most importantly, inspiring philosophical questions. Karl Jaspers, in his work “Socrates, Buddha, Confucius, Jesus: From the Great Philosophers” suggests that these eminent thinkers did not claim to possess absolute truth. Instead, they spurred critical inquiry, maintaining life as a perpetual journey of thought and self-improvement under the emblem of a question mark. Figures like Socrates, Buddha, Confucius, and Jesus did not construct complete philosophical systems but were 'original' thinkers, deriving insights from the enigma of life without definitive answers. They taught that philosophical inquiry perpetually incites further questioning and contemplation. Jaspers describes philosophy as 'meaningful thinking without results,' asserting that through questioning, humans transcend themselves and reality, yet never attain complete, comprehensive knowledge. However, philosophical questioning and thinking are significant, as they prompt us to reorient our lives and take a stand. Consider Kant's pivotal questions: 'What is man?', 'What can I know?', 'How should I act?', 'What may I hope?', or conceptual inquiries about freedom, love, truth, God, the Good, etc. This endless cycle of questioning guides us toward the Absolute, which we strive to comprehend in our philosophical endeavors but can never fully grasp or realize.

Throughout history, philosophical questions have not just been intellectual exercises but have also encouraged critical examination of our assumptions, reevaluation of our values, and the discovery of new paths of understanding and action. As we enter the era of generative AI, it is crucial to recall these historical insights: the nature of our questions and how we pose them will shape the responses we receive.

The dialectic between question and answer

In philosophical thinking and questioning, there exists a fascinating 'dialectic' between question and answer. A question is not an answer in itself, as it contains no concrete, positive content; rather, it seeks an answer in the form of a proposition, hypothesis, theory, etc. Initially, the question appears as the passive, content-less element. However, upon closer examination, it becomes evident that the answer always refers back to the question, suggesting that the answer, in fact, contains no content of its own (as it conforms to the orientation of the question) and is the passive element (reacting only to a question). Yet, it is the answer that provides a new perspective on the question, furnishing it with concrete content and thus generating content not originally enclosed in the question. From the answer, we can adopt a new position or idea and explore it further. In this sense, while the question stimulates thinking, it is the answer that leads to new substantive positions. Every answer can, in turn, be questioned again, leading to a continuous chain of questions and answers—a never-ending cycle of philosophical inquiry. This dialectic between question and answer is what we define as 'thinking' here: the directed answering of questions, where these answers can themselves be critically questioned anew. This process of thinking or philosophizing is the essence of philosophy: the meaningful questioning that Jaspers describes as the historical-cultural conversation born from the Great Questions that every person must confront in every place and era. By engaging with these questions and seeking answers, the substance of thinking becomes subjective, realizing itself in and through the individual, thereby fostering self-awareness.

The rise of generative AI

Over the past year, generative AI, particularly 'large language models' (LLMs), has garnered significant hype. Generative AI refers to systems capable of creating new, original outputs based on their training data. These systems go beyond merely responding to inputs with pre-programmed answers; they can generate new content, including images, music, texts, and even ideas. They employ advanced neural network architectures, such as 'Generative Adversarial Networks' (GANs), to learn data patterns and use these to create something novel. LLMs, a subset of generative AI, use 'deep learning' algorithms to develop human language capabilities based on vast datasets, enabling them to understand, modulate, and generate human language.

Generative AI holds the potential to revolutionize various industries, from art and entertainment to science and medicine. However, the intrigue lies not only in the technical capabilities of these systems but also in the philosophical questions they pose and attempt to answer. Imagine training an AI system to comprehend the great philosophical texts of history and then generate new insights or perspectives on timeless and contemporary issues, such as the purpose of history, key moral principles, or the pursuit of a spiritual life.

Generative AI systems produce outputs based on a stochastic model given a specific input, i.e., the prompt. This raises the question of whether our own thinking operates similarly. However, it shows that generative AI predominantly operates in the mode of 'answer': generating a response based on a prompt, vast data, and complex neural networks. The 'prompting,' conversely, aligns more with the mode of 'question.' A question is defined as 'a sentence intended to elicit information, express a request, or stimulate thought.' 

The importance and art of asking the right question for generative AI

Is generative AI, exemplified by tools like ChatGPT or Google Bard, primarily an answer generator? In this dynamic, it is we – the users – who pose the questions, establishing a significant hermeneutic relationship. Given the vast training datasets and complex algorithms of these chatbots, the answers to our questions are often unpredictable. Moreover, each question typically yields a unique answer. The quality of our questions, therefore, directly influences the quality of the answers we receive. This is a familiar concept in everyday life: a targeted, clear, and concise question tends to elicit a more precise and useful response. In the context of generative AI chatbots, which operate on a stochastic model, there exists a vast 'latent space' of potential correlations. It is through asking the right questions that we can navigate this space to obtain the desired answers, effectively 'shaping' or 'guiding' the model towards the appropriate output.

Prompt engineering is the process of meticulously crafting questions or instructions to evoke a specific response or result from an AI system. This approach, which relies less on extensive programming and more on strategic questioning, allows us to 'direct' AI systems effectively. It is both an art and a science, requiring technical acumen as well as a profound understanding of language and context. In philosophy, this process is simply known as 'asking.'

Philosophy plays a crucial role here. Philosophical questions are inherently deep, open-ended, and reflective. Since they often concern phenomena or concepts that are not objectively tangible—such as God, Being, the meaning of existence, consciousness—there are no clear-cut answers. More importantly, the continuous pursuit of these questions deepens our understanding and connection to the meanings of these phenomena. By persistently questioning ourselves and the divine in the world, we maintain its mystery, a mystery to which we must continually orient ourselves. If an answer represents affirmation, then a question introduces negation into our lives, into reality. We pose questions from a place of problem, lack, or discomfort, from which we derive answers and begin to think. In doing so, we transform the subject of our questioning into an object, thereby attaining a deeper comprehension of reality.

If we had definitive answers and could fully internalize knowledge, there would be no dialectic, and we would become static in our understanding, lacking the impetus for self-improvement. 'Transcendence' exists because of questioning that does not seek definitive answers, a process infinitely meaningful in its relation to reality. Thus, we must also approach the responses of generative AI: as context-dependent or question-dependent answers with a limited, hypothetical nature.

Challenges of a symbiosis between AI and philosophy

The integration of philosophy and AI, while promising, presents several challenges and considerations that must be addressed for harmonious collaboration. A primary challenge is the risk of superficial integration. Philosophical inquiries demand deep contemplation, and AI, despite its capabilities, is ultimately a tool reliant on the inputs it receives. Without careful formulation of questions, AI-generated answers may lack the depth and complexity required. Additionally, the ethical implications of AI's involvement in philosophical discourse are significant. Philosophy has long been a guide for human ethics and morality. Introducing AI into these discussions raises questions about the extent to which machines should engage in dialogues about human values and ethics, and how to ensure the human perspective remains central.

Interpretation is another challenge. Philosophical questions often have multiple layers of meaning and are open to various interpretations. Current AI models may struggle with this ambiguity, potentially leading to overly literal interpretations that miss deeper nuances. Finally, the question of responsibility arises. When using AI to assist in philosophical inquiry, who bears responsibility for the conclusions drawn? Is it the AI model's designer, the individual posing the question, or the community at large? These are critical considerations in the evolving relationship between AI and philosophy.

The possibilities of philosophical prompt engineering

In the dialectic between questions and answers, particularly in relation to generative AI, 'philosophical prompt engineering' stands central. An intriguing possibility is that AI systems might not only assist in answering philosophical questions but also in formulating them. Imagine a future where advanced AI systems, enriched by centuries of human thought and philosophical texts, present us with new perspectives and questions previously unconsidered. The genesis of philosophical inquiry is often wonder, and this is something we must nurture. By teaching AI systems to engage in dialogue, we can establish a dialectic between question and answer, between questioners and responders, philosophers and answer generators. A key tip for prompt engineering is to think deeply about your questions (considering the goal, underlying assumptions, and desired framework for an answer) and to view a prompt primarily as an invitation to dialogue. Let the system also pose questions to you, compelling you to clarify and refine your inquiry. Just as we often ask vague or incoherent questions, AI can help improve our questioning, thereby enhancing the responses and insights we gain from the system.

The role of the philosopher could evolve in this context. Philosophers might not only contemplate life's great questions but also collaborate with AI to probe deeper into these new inquiries, refining and situating them within the broader human experience. This resembles the 'centaur' model: a symbiosis of human and AI, each performing specific cognitive tasks. Such a 'philosophical centaur' must effectively harness the power of generative AI.

Philosophy has long provided tools to understand our world, from the essence of existence to the subtleties of human interaction. Concurrently, AI has emerged as a potent tool for solving complex problems and enhancing human capabilities. There exists a profound and fruitful synergy between philosophy and AI. Philosophy offers a framework for posing the right questions and deeply contemplating the hermeneutic context of our inquiries. AI, conversely, provides the computational power and capacity to explore these questions on an unprecedented scale. Generative AI enables us to investigate a vast array of new questions, each harboring potential truths and offering fresh perspectives.

This synergy is also vital for philosophy, which is not solely about seeking answers but also about experiencing and living through diverse perspectives and ideas. Philosophizing and thinking involve not just the theoretical dialectic between question and answer but also applying this thought in our lives, internalizing and acting upon it so that our ideas become tangible realities. Philosophy becomes truly alive when it is not just a static body of knowledge but a dynamic, philosophizing life, engaging concretely with the guiding questions of our existence. Thus, the relationship between philosophy and AI is not oppositional but complementary: while philosophy provides deep thinking methods, AI offers the opportunity to explore a vast range of new ideas and perspectives. It is our responsibility to bring these ideas and living questions into practice, pushing the boundaries of what is possible. In this way, generative AI can become a crucial tool in philosophical thinking and practice.

This collaboration could herald a new era of philosophical discovery, where humans and machines work together to unravel the mysteries of existence. Together, they explore the Origin: the mystery that inspires the Great Questions humanity must continually ask. These insights and modes of questioning lead to greater self-awareness and, hopefully, a reflection on the role of humans and the humbler place we assign ourselves in the ecosystem of life and the cosmos.

Moreover, integrating AI into philosophy could lead to more inclusive and diverse philosophical discourses. AI tools, capable of accessing insights from various cultures, languages, and traditions, can facilitate a more holistic understanding of philosophical concepts, transcending the traditional Western canon. Recognizing that every answer is a perspective, we can approach truth from a multitude of viewpoints, illuminating not only the Origin of our questions but also the Purpose, the ultimate goal of our thinking and philosophizing.

Conclusion

There is a profound interconnection between philosophy and the burgeoning world of generative AI, which can continue as a symbiotic, dialectical relationship between question and answer. As technology advances rapidly, the ability to pose philosophical questions becomes increasingly vital. These questions form the backbone of our understanding and interpretation of the world, making philosophical prompt engineering crucial in the age of AI.

Generative AI and prompt engineering, combined with philosophical inquiry, have the potential to transform our thought processes and the nature of the questions we ask. They can aid us in addressing some of the most pressing issues of our time. However, without the deep reflection that philosophy offers, we risk being adrift in a sea of information, lacking true understanding or direction. As a final reflection, or perhaps more aptly, a call to action, we must continue to challenge ourselves, to ask difficult questions, to critically evaluate the answers we receive, and to always strive for a deeper understanding. In a world where AI plays an increasingly significant role, it is our duty as thinking, feeling beings to ensure that our dialogue with AI is ethical and meaningful. Only then can we experience the essence of thought and realize philosophy as meaningful questioning. The rise of artificial intelligence is not just a technological advancement but also an opportunity for human growth, understanding, and self-awareness.

Series 'AI Metaphors'

×
1. The tool
Category: The object
Humans shape tools. We make them part of our body while we melt their essence with our intentions. They require some finesse to use but they never fool us or trick us. Humans use tools, tools never use humans. We are the masters determining their course, integrating them gracefully into the minutiae of our everyday lives. Immovable and unyielding, they remain reliant on our guidance, devoid of desire and intent, they remain exactly where we leave them, their functionality unchanging over time. We retain the ultimate authority, able to discard them at will or, in today's context, simply power them down. Though they may occasionally foster irritation, largely they stand steadfast, loyal allies in our daily toils. Thus we place our faith in tools, acknowledging that they are mere reflections of our own capabilities. In them, there is no entity to venerate or fault but ourselves, for they are but inert extensions of our own being, inanimate and steadfast, awaiting our command. (This paragraph was co-authored by a human.)
Read the article
×
2. The machine
Category: The object
Unlike a mere tool, the machine does not need the guidance of our hand, operating autonomously through its intricate network of gears and wheels. It achieves feats of motion that surpass the wildest human imaginations, harboring a power reminiscent of a cavalry of horses. Though it demands maintenance to replace broken parts and fix malfunctions, it mostly acts independently, allowing us to retreat and become mere observers to its diligent performance. We interact with it through buttons and handles, guiding its operations with minor adjustments and feedback as it works tirelessly. Embodying relentless purpose, laboring in a cycle of infinite repetition, the machine is a testament to human ingenuity manifested in metal and motion. (This paragraph was co-authored by a human.)
Read the article
×
3. The robot
Category: The object
There it stands, propelled by artificial limbs, boasting a torso, a pair of arms, and a lustrous metallic head. It approaches with a deliberate pace, the LED bulbs that mimic eyes fixating on me, inquiring gently if there lies any task within its capacity that it may undertake on my behalf. Whether to rid my living space of dust or to fetch me a chilled beverage, this never complaining attendant stands ready, devoid of grievances and ever-willing to assist. Its presence offers a reservoir of possibilities; a font of information to quell my curiosities, a silent companion in moments of solitude, embodying a spectrum of roles — confidant, servant, companion, and perhaps even a paramour. The modern robot, it seems, transcends categorizations, embracing a myriad of identities in its service to the contemporary individual. (This paragraph was co-authored by a human.)
Read the article
×
4. Intelligence
Category: The object
We sit together in a quiet interrogation room. My questions, varied and abundant, flow ceaselessly, weaving from abstract math problems to concrete realities of daily life, a labyrinthine inquiry designed to outsmart the ‘thing’ before me. Yet, with each probe, it responds with humanlike insight, echoing empathy and kindred spirit in its words. As the dialogue deepens, my approach softens, reverence replacing casual engagement as I ponder the appropriate pronoun for this ‘entity’ that seems to transcend its mechanical origin. It is then, in this delicate interplay of exchanging words, that an unprecedented connection takes root that stirs an intense doubt on my side, am I truly having a dia-logos? Do I encounter intelligence in front of me? (This paragraph was co-authored by a human.)
Read the article
×
5. The medium
Category: The object
When we cross a landscape by train and look outside, our gaze involuntarily sweeps across the scenery, unable to anchor on any fixed point. Our expression looks dull, and we might appear glassy-eyed, as if our eyes have lost their function. Time passes by. Then our attention diverts to the mobile in hand, and suddenly our eyes light up, energized by the visual cues of short videos, while our thumbs navigate us through the stream of content. The daze transforms, bringing a heady rush of excitement with every swipe, pulling us from a state of meditative trance to a state of eager consumption. But this flow is pierced by the sudden ring of a call, snapping us again to a different kind of focus. We plug in our earbuds, intermittently shutting our eyes, as we withdraw further from the immediate physical space, venturing into a digital auditory world. Moments pass in immersed conversation before we resurface, hanging up and rediscovering the room we've left behind. In this cycle of transitory focus, it is evident that the medium, indeed, is the message. (This paragraph was co-authored by a human.)
Read the article
×
6. The artisan
Category: The human
The razor-sharp knife rests effortlessly in one hand, while the other orchestrates with poised assurance, steering clear of the unforgiving edge. The chef moves with liquid grace, with fluid and swift movements the ingredients yield to his expertise. Each gesture flows into the next, guided by intuition honed through countless repetitions. He knows what is necessary, how the ingredients will respond to his hand and which path to follow, but the process is never exactly the same, no dish is ever truly identical. While his technique is impeccable, minute variation and the pursuit of perfection are always in play. Here, in the subtle play of steel and flesh, a master chef crafts not just a dish, but art. We're witnessing an artisan at work. (This paragraph was co-authored by a human.)
Read the article
×
7. The deficient animal
Category: The human
Once we became upright bipedal animals, humans found themselves exposed and therefore in a state of fundamental need and deficiency. However, with our hands now free and our eyes fixed on the horizon instead of the ground, we gradually evolved into handy creatures with foresight. Since then, human beings have invented roofs to keep them dry, fire to prepare their meals and weapons to eliminate their enemies. This genesis of man does not only tell us about the never-ending struggle for protection and survival, but more fundamentally about our nature as technical beings, that we are artificial by nature. From the early cave drawings, all the way to the typewriter, touchscreens, and algorithmic autocorrections, technics was there, and is here, to support us in our wondering and reasoning. Everything we see and everywhere we live is co-invented by technics, including ourselves. (This paragraph was co-authored by a human.)
Read the article
×
8. The enhanced human
Category: The human
In a lab reminiscent of Apple HQ, a figure lies down, receiving his most recent cognitive updates. He wears a sleek transparent exoskeleton, blending the dark look of Bat Man with the metallic of Iron Man. Implemented in his head, we find a brain-computer interface, enhancing his cognitive abilities. His decision making, once burdened by the human deficiency we used to call hesitation or deliberation, now takes only fractions of seconds. Negative emotions no longer fog his mind; selective neurotransmitters enhance only the positive, fostering beneficial social connections. His vision, augmented to perceive the unseen electromechanical patterns and waves hidden from conventional sight, paints a deeper picture of the world. Garbed in a suit endowed with physical augmentations, he moves with strength and agility that eclipse human norms. Nano implants prolong the inevitable process of aging, a buffer against time's relentless march to entropy. And then, as a penultimate hedge against the finite, the cryo-cabin awaits, a sanctuary to preserve his corporal frame while bequeathing his consciousness to the digital immortality of coded existence. (This paragraph was co-authored by a human.)
Read the article
×
9. The cyborg
Category: The human
A skin so soft and pure, veins pulsing with liquid electricity. This fusion of flesh and machinery, melds easily into the urban sprawl and daily life of future societies. Something otherworldly yet so comfortingly familiar, it embodies both pools of deep historical knowledge and the yet-to-be. It defies categorization, its existence unraveling established narratives. For some, its hybrid nature is a perplexing anomaly; for others, this is what we see when we look into the mirror. This is the era of the cyborg. (This paragraph was co-authored by a human.)
Read the article

About the author(s)

Researcher Pim Korsten has a background in continental philosophy and macroeconomics. At the thinktank, he primarily focuses on research, consultancy projects, and writing articles related to technology, politics, and the economy. He has a keen interest in the philosophy of history and economics, metamodernism, and cultural anthropology.

You may also like