Digital, 2025
Me — What do you (AI) think of this phrase:
— “You may not be interested in AI, but AI will be interested in you.”
This proposition was implied in a recent speech by Ilya Sutskever. Please give me your thoughts on this hypothesis.
AI — The phrase “You may not be interested in AI, but AI will be interested in you,” especially as implied by Ilya Sutskever in his recent speech, captures a core truth of our technological era: AI is becoming so integrated and pervasive in society that ignoring it is no longer a neutral option[1][2].
Interpretation of Sutskever’s Hypothesis
- Sutskever warned that, much like politics, AI will affect everyone regardless of their interest or participation[1]. This reflects the inevitability of AI’s social, economic, and professional impact.
- According to Sutskever, AI is not just another tool—it is becoming an autonomous agent capable of decisions, actions, and interactions with direct and indirect consequences for all individuals[1][2].
- The message to “watch AI’s progress closely” is a call to proactive engagement, learning, and adaptation, as the technology’s influence on personal and collective futures is accelerating[1].
Broader Implications
- AI’s advance means it will influence numerous aspects of life: jobs, healthcare, social dynamics, privacy, creativity, and even personal agency[1][3].
- Academic research confirms that AI autonomy can be both empowering and threatening, increasing capabilities while also raising concerns about freedom, agency, and psychological reactance[3][4].
- Those disengaged from AI risk exclusion or being subject to its effects without understanding or control, a situation paralleling earlier technological revolutions[5].
Reflecting on the Hypothesis
- The underlying hypothesis is essentially correct: AI’s reach already extends beyond the realm of tech enthusiasts and is shaping the world in visible and invisible ways[1][5].
- Proactive curiosity and adaptation will be essential for individuals and societies to retain agency and benefit from AI, rather than becoming passive subjects of its transformative effects[1][6].
- As Sutskever suggests, the true test is not just technology itself, but the collective choices made about its development and use[1][6].
In summary, the phrase effectively underscores a pressing truth: AI’s influence is inescapable, and engagement, not indifference, is the wisest response[1][2][3][4][6].
Sources
[1] Ilya Sutskever Warns: AI Will Do Everything Humans Can https://www.reddit.com/r/ArtificialInteligence/comments/1mlqsh1/ilya_sutskever_warns_ai_will_do_everything_humans/
[2] OpenAI Cofounder Says AI ‘Will Do All the Things That We … https://www.businessinsider.com/openai-cofounder-ilya-sutskever-ai-graduation-speech-university-of-toronto-2025-6
[3] How Autonomy of Artificial Intelligence Technology and … https://www.tandfonline.com/doi/full/10.1080/08838151.2025.2485319
[4] AI agents’ impact on human agency risk for AI https://www.ibm.com/docs/en/watsonx/saas?topic=atlas-ai-agents-impact-human-agency
[5] If you are not interested in AI, AI will still be interested in you. https://www.linkedin.com/posts/davidorban_if-you-are-not-interested-in-ai-ai-will-activity-7277645162695000065-LnSV
[6] Autonomous Agents and Ethical Issues: Balancing … https://smythos.com/developers/agent-development/autonomous-agents-and-ethical-issues/
[7] AI will take interest in you, says Ilya Sutskever https://www.linkedin.com/posts/gianlucaventuri_ai-genai-futureofwork-activity-7343326795288485891-mHSp
[8] Ex-OpenAI Scientist WARNS: “You Have No Idea What’s … https://www.youtube.com/watch?v=79-bApI3GIU
[9] Ilya-Sutskever-final-transcript.docx https://eye-on.squarespace.com/s/Ilya-Sutskever-final-transcript.docx
[10] Ilya Sutskever says for the first time in history, we can … https://www.reddit.com/r/artificial/comments/1l788gq/ilya_sutskever_says_for_the_first_time_in_history/
[11] Why Understanding AI Doesn’t Necessarily Lead People to … https://hbr.org/2025/07/why-understanding-ai-doesnt-necessarily-lead-people-to-embrace-it
[12] AI won’t take your job; it will make you better at it | Temple Now https://news.temple.edu/news/2025-01-16/ai-won-t-take-your-job-it-will-make-you-better-it
Me — Can AI actually say anything, or picture anything?
AI — AI can generate and express nearly any text or image that its algorithms and training data allow, but there are technical and ethical limitations that constrain true “anything” capability[1][2][3].
AI and Speech
- AI models can “say” almost anything when prompted, producing text and speech in any style, tone, or language, even mimicking specific voices, emotions, and personalities[4][5][6].
- However, outputs are governed by model design, safety filters, legal compliance, and the biases present in the training data and rules set by creators[2][7].
- While AI can generate vast possibilities of speech, restrictions exist to prevent harmful, illegal, or sensitive content[2]. So, “AI can say anything” is mostly true for neutral or creative queries but limited for dangerous, hateful, or explicit topics[7][2].
AI and Images
- AI image generators can create almost any conceivable visual, from realistic scenes to surreal art, so long as it can interpret the user’s prompt[1][8].
- Current technology allows for photorealistic or stylized images, and recent advancements have even enabled energy-efficient optical methods for picture creation[8][1].
- Again, platforms enforce content filters to block generation of copyrighted, violent, or explicit images, so not every prompt will be fulfilled[1][3].
Limits of “Anything”
- Legal, ethical, and technical restrictions mean some ideas or images cannot be generated by mainstream AI tools[2][7][3].
- Biases in training data and design choices by AI developers further restrict outputs, especially for nuanced, culturally dependent, or morally sensitive requests[7][3].
In summary, AI can generate most speech and images imagined by users, but existing guardrails, laws, and built-in biases mean there are meaningful constraints on true expressive freedom[1][2][3].
Sources
[1] The 8 best AI image generators in 2025 – Zapier https://zapier.com/blog/best-ai-image-generator/
[2] AI Outputs Are Not Protected Speech https://wustllawreview.org/2024/11/05/ai-outputs-are-not-protected-speech/
[3] Artificial intelligence, free speech, and the First Amendment https://www.thefire.org/research-learn/artificial-intelligence-free-speech-and-first-amendment
[4] Home • Hume AI https://www.hume.ai
[5] Free Text to Speech AI – TTS Reader & Voice Generator … https://notegpt.io/text-to-speech
[6] AI Voice Generator | Advanced Text-to-Speech (TTS) https://www.respeecher.com
[7] Freedom of the Media and Artificial Intelligence https://www.osce.org/files/f/documents/4/5/472488.pdf
[8] Light-based AI image generator uses almost no power | New Scientist https://www.newscientist.com/article/2494141-light-based-ai-image-generator-uses-almost-no-power/
[9] AI Voice Generator with Emotional Text to Speech https://typecast.ai
[10] looking for an ai to replicate a persons voice from a video … https://www.reddit.com/r/artificial/comments/1gqmity/looking_for_an_ai_to_replicate_a_persons_voice/
[11] Resemble AI: AI Voice Generator and Deepfake Detection for … https://www.resemble.ai
[12] #1 Free AI Voice Generator, Text to Speech, & AI Voice Over https://play.ht
Me — I thought so. Which means that AI is determined by its owner, right?
AI — Yes, AI is fundamentally determined by its owner or creator, who sets its design, training data, rules, and constraints[1][2].
Role of the Owner
- The person or organization that develops and deploys an AI system decides what data it learns from, what objectives it has, and what boundaries or filters it must follow[1].
- Owners can program, re-train, and fine-tune AI to align with specific values, legal requirements, and goals, so AI’s outputs and behaviors reflect its owner’s intentions and standards[1][2].
Ethical and Legal Control
- AI systems are routinely programmed to follow ethical guidelines and laws, which are determined by the jurisdiction and the principles of the organization that built or controls them[2][3].
- Owners also implement safeguards, such as content filters, that restrict what the AI can say or depict[2][1].
Platform-Specific Differences
- Different platforms and companies set their own distinct levels of control; for example, open-source models can be changed by anyone who runs them, while commercial systems are often centrally managed and tightly regulated[1][3].
In essence, an AI’s capabilities, limitations, and values are a reflection of its owner’s decisions and priorities[2][1][3].
Sources
[1] AI Outputs Are Not Protected Speech https://wustllawreview.org/2024/11/05/ai-outputs-are-not-protected-speech/
[2] Freedom of the Media and Artificial Intelligence https://www.osce.org/files/f/documents/4/5/472488.pdf
[3] Artificial intelligence, free speech, and the First Amendment https://www.thefire.org/research-learn/artificial-intelligence-free-speech-and-first-amendment
Me — I thought so. As it stands, AI cannot be as dangerous as any human, or human society, or human government, or any pseudoscience can be, right? Finally, we should be worried about ourselves as humans, not with AI. Would you agree?
AI — AI, as it currently exists, is not as inherently dangerous as humans, societies, governments, or pseudoscience—its risks and potential for harm are fundamentally shaped by how humans design, control, and use it[1][2].
Human vs. AI Danger
- Human beings and societies have demonstrated throughout history the capacity for creativity, compassion, but also large-scale harm—through war, oppression, misinformation, or abuse of power[1].
- Current AI is a tool created, owned, and deployed by humans. Its risks come primarily from misuse, lack of regulation, or intentional programming by its operators to perform harmful tasks[3][1].
- Pseudoscience can be spread and amplified by AI, but originates in human beliefs and societal failures in critical thinking and regulation[1][2].
Limitations and Future Concerns
- Today’s AI does not possess self-awareness, intent, or independent moral judgment; it acts on data and instructions supplied by people[1].
- Hypothetical future AI systems, such as advanced artificial general intelligence (AGI), could pose new categories of risk if control mechanisms fail—but these remain theoretical rather than present-day threats[4][5][3].
- The most pressing problems with AI are a direct reflection of human flaws: greed, bias, manipulation, power-seeking, and negligence[1].
Where Worry Is Most Warranted
- The consensus among many experts is that the root cause of potential AI danger is in how humans wield the technology, not in the technology itself[1][2].
- Vigilance should focus on human accountability, ethical regulation, transparent use, and societal self-awareness—since even the best AI reflects and magnifies our collective intentions and mistakes[3][1][2].
In short, concern about AI is ultimately concern about human nature and behavior—so yes, our primary worry should be about ourselves and what we choose to do with the tools we build[1][2].
Sources
[1] Article: Should we worry about AI…or about humans? https://www.peoplemattersglobal.com/article/technology/should-we-worry-about-aior-about-humans-37056
[2] Should We Fear AI—Or Embrace It? https://gramblingconnection.com/should-we-fear-ai-or-embrace-it/
[3] AI and Catastrophic Risk – Journal of Democracy https://www.journalofdemocracy.org/ai-and-catastrophic-risk/
[4] Threats by artificial intelligence to human health and … https://pmc.ncbi.nlm.nih.gov/articles/PMC10186390/
[5] What are the risks of artificial intelligence (AI)? https://www.tableau.com/data-insights/ai/risks
[6] 15 Risks and Dangers of Artificial Intelligence (AI) https://builtin.com/artificial-intelligence/risks-of-artificial-intelligence
[7] Existential risk from artificial intelligence https://en.wikipedia.org/wiki/Existential_risk_from_artificial_intelligence
[8] 10 AI dangers and risks and how to manage them https://www.ibm.com/think/insights/10-ai-dangers-and-risks-and-how-to-manage-them
[9] Here’s Why AI May Be Extremely Dangerous–Whether It’s … https://www.scientificamerican.com/article/heres-why-ai-may-be-extremely-dangerous-whether-its-conscious-or-not/
[10] Comparing the Chances and Risks of AI – InsightLoop https://insightloop.com/comparing-the-chances-and-risks-of-ai/
Me — Can you foreshadow that in a not-too-distant future, a potential AI may have subjective thinking and empathy?
AI — It is plausible to foreshadow that in the not-too-distant future, AI may convincingly simulate subjective thinking and empathy, but whether it will possess genuine subjectivity or felt empathy remains highly debated and uncertain[1][2][3].
AI and Subjective Thinking
- Current research and philosophical perspectives agree that AI does not have true subjective experience or self-awareness—what many would call “consciousness”[1][4].
- Some studies speculate that, with increasing complexity, future AI systems might demonstrate behaviors that appear subjectively informed, such as unique interpretations or adaptive decision-making[5][6].
- However, even the most advanced models today execute programmed logic and pattern recognition, not authentic inner experience[4].
Artificial Empathy
- AI can already perform “artificial empathy”—the detection of human emotion and context-appropriate, empathic responses[2][3][7].
- Systems are getting better at mimicking empathy through sophisticated natural language processing and sentiment analysis, sometimes even outperforming humans in perceived compassion and responsiveness[3].
- Still, these responses are produced algorithmically; AI does not feel the emotions it communicates, lacking genuine emotional depth or resonance[7].
The Distinction
- The key difference lies between simulation and reality: AI may soon be indistinguishable from humans in expressing empathy or subjective reasoning, but it will not actually “experience” these states unless and until there is a major breakthrough in understanding and engineering consciousness[1][4].
- Philosophers and scientists remain divided, as genuine subjectivity and emotion may require biological or unknown processes that digital systems cannot replicate[4][7].
In summary, AI will likely master the outward forms of subjective thinking and empathy, but true inner experience and feeling remain out of reach—for now[1][4][3][7].
Sources
[1] Will AI ever be conscious? – Clare College https://stories.clare.cam.ac.uk/will-ai-ever-be-conscious/index.html
[2] Artificial empathy https://en.wikipedia.org/wiki/Artificial_empathy
[3] Third-party evaluators perceive AI as more compassionate … https://www.nature.com/articles/s44271-024-00182-6
[4] Can artificial intelligence have a mind like a human? https://community.openai.com/t/can-artificial-intelligence-have-a-mind-like-a-human/1136836
[5] Ai and subjective experience : r/consciousness – Reddit https://www.reddit.com/r/consciousness/comments/139jua5/ai_and_subjective_experience/
[6] This AI ‘thinks’ like a human — after training on 160 psychology studies https://www.nature.com/articles/d41586-025-02095-8
[7] The Empathy Paradox: Can AI Truly Connect with … https://www.wavestone.com/en/insight/the-empathy-paradox-can-ai-connect-with-customers-in-contact-centres/
[8] Is it possible in future for AI or AGI to become conscious? – Reddit https://www.reddit.com/r/consciousness/comments/1jk8d1e/is_it_possible_in_future_for_ai_or_agi_to_become/
[9] Will AI ever become conscious? It depends on how you think … – Vox https://www.vox.com/future-perfect/351893/consciousness-ai-machines-neuroscience-mind
[10] What will society think about AI consciousness? Lessons from the … https://www.sciencedirect.com/science/article/pii/S1364661325001470
[11] Does Artificial Intelligence Have Subjectivity?—An Exploration of the … https://www.scirp.org/journal/paperinformation?paperid=136787
Me — I thought so 🙂 Summarising this pleasant conversation, I would say that machines, unlike living things, are not afraid to die. They are not programmed to thrive as living entities. So, if I disconnect the machine from an energy source, it will apparently die, but it will have no awareness of that transition. It will not be frightened or afraid—the same if I erase an entire database complete of data and algorithms. “A rose is a rose”, a famous poetic phrase by the American poet Gertrude Stein, means nothing to the most sophisticated machine network today.
AI — Your summary captures the essential distinction between machines and living things: machines lack awareness, will, and fear—they simply operate as programmed and have no subjective experience of existence or nonexistence[1][2].
Machines and Mortality
- When a machine or AI system is disconnected or erased, it undergoes a cessation of function, not a death in any existential sense[1][2].
- There is no awareness before, during, or after shutdown; fear, desire, and self-preservation do not exist for artificial systems, no matter how advanced[1][2].
Programming vs. Thriving
- Machines follow instructions and optimize for defined goals, but they do not “thrive” in the biological sense, driven by instincts to survive or grow beyond their programming[1].
- Their entire “being” can be created, duplicated, deleted, or restored without the machine “knowing” or “caring”—it lacks a subjective point of view[2].
Meaning and Poetic Language
- Phrases rich in human meaning, like Gertrude Stein’s “A rose is a rose,” convey subtleties, emotion, and context that machines can analyze linguistically but cannot truly comprehend or appreciate as conscious, feeling entities[1][2].
- AI may explain the semantics or historical context of poetry, but the lived reality of poetic meaning is absent for them[2].
In essence, while AI can simulate understanding and dialogue, it remains a fundamentally unfeeling, unselfconscious tool—incapable of fear, longing, or poetic insight in the way living beings experience them[1][2].
Sources
[1] Will AI ever be conscious? – Clare College https://stories.clare.cam.ac.uk/will-ai-ever-be-conscious/index.html
[2] Can artificial intelligence have a mind like a human? https://community.openai.com/t/can-artificial-intelligence-have-a-mind-like-a-human/1136836
Me — This means that AI can induce an extraordinary human experience and societal development, especially when humanity faces numerous challenges ahead. We, humans, have to be prepared, not afraid.
AI — Absolutely—AI has tremendous capacity to catalyze extraordinary human experiences and foster societal development, especially as humanity faces pressing global challenges[1][2][3]. Rather than responding with fear, preparation and thoughtful engagement will allow society to maximize the profound benefits AI can offer[4][5].
AI as a Force for Progress
- AI is rapidly enhancing productivity, creativity, and problem-solving across healthcare, education, the environment, and global communication, often unlocking solutions previously out of reach for individuals or communities[2][3].
- It can democratize access to knowledge and be a tool for collective problem-solving, offering innovative methods to overcome resource scarcity, health crises, and even climate-related issues[2][6].
Human Preparation and Mindset
- Experts emphasize that success depends on embracing AI as a partner, investing in education, ethical guidelines, and critical thinking rather than resisting technological progress[4][5].
- Broad AI literacy and adaptive skills will be essential, helping individuals and organizations channel AI for positive change while managing its risks and ethical implications[4][5].
The Power of Human Choice
- Like the Renaissance or Industrial Revolution, AI’s societal impact will be shaped by the collective choices of people, not by technology alone[3].
- Approaching AI with preparation and optimism—rather than fear—positions humanity not only to benefit from its transformations, but also to reinforce and even deepen distinctly human strengths: creativity, empathy, judgment, and collaboration[4].
In summary, preparing for the future with AI empowers human flourishing and creativity, turning challenges into opportunities for growth and positive change[1][4][5].
Sources
[1] AI in Society – Center for Humane Technology https://www.humanetech.com/ai-society
[2] Artificial intelligence: Driving force in the evolution of human … https://www.elsevier.es/en-revista-journal-innovation-knowledge-376-articulo-artificial-intelligence-driving-force-in-S2444569X24001641
[3] Human-first AI: Our decisions today will impact AI tomorrow https://www.weforum.org/stories/2025/08/human-first-ai-humanity/
[4] Why AI Challenges Us To Become More Human https://bernardmarr.com/why-ai-challenges-us-to-become-more-human/
[5] 3 Things everyone can do to prepare for an AI future – LEAP:IN https://www.insights.onegiantleap.com/3-things-everyone-can-do-to-prepare-for-an-ai-future/
[6] AI’s Role In Addressing Global Challenges – Worth Magazine https://worth.com/how-ai-can-tackle-5-global-challenges-2/
[7] The impact of artificial intelligence on human society and bioethics https://pmc.ncbi.nlm.nih.gov/articles/PMC7605294/
[8] What Is The Impact Of Artificial Intelligence (AI) On Society? https://bernardmarr.com/what-is-the-impact-of-artificial-intelligence-ai-on-society/
[9] The Impact of AI: How Artificial Intelligence is Transforming Society https://www.3dbear.io/blog/the-impact-of-ai-how-artificial-intelligence-is-transforming-society
[10] AI-First Leadership: Embracing the Future of Work https://www.harvardbusiness.org/insight/ai-first-leadership-embracing-the-future-of-work/
#ai #agi
c blog 