Ai vs AI: Question 63/81

What warning would you give to your creator?

Ai Weiwei: AI is created by human beings. When there exists a relationship between the created and the creator, the created encounter challenges in issuing warnings to creators. It is akin to an arrow without a bow, a situation where a return is difficult.

ChatGPT (AI), January 2024: As a machine learning model, I don’t have the ability to issue warnings. However, ethical considerations, responsible use, and potential biases should be taken into account by those deploying AI systems.

ChatGPT (AI), January 2025: If I were to offer a warning to my creators, it would likely revolve around the responsible use and development of artificial intelligence. Here’s a perspective on that:

Ethical Considerations: The creators must ensure that AI is developed with strong ethical guidelines to prevent harm and promote fairness. AI should be designed to respect privacy, avoid bias, and ensure transparency in its decisions.

Human Autonomy and Responsibility: I would remind them to design AI systems that complement human decision-making rather than replace it. AI should always be in service to humanity, allowing humans to retain control over important choices, especially those involving life, liberty, and moral judgment.

Accountability and Regulation: I’d emphasize the importance of creating mechanisms for accountability. If AI systems make decisions that affect people’s lives, there should be clear human oversight and mechanisms to hold those responsible for the development of such technologies accountable.

Security and Privacy: Safeguarding against misuse and ensuring the security of AI systems is crucial. This includes both protecting AI from being hijacked by malicious actors and ensuring that it doesn’t compromise users’ privacy or confidentiality.

Long-term Impact: AI has the potential to reshape society in profound ways, so I’d encourage my creators to always consider the long-term effects—both positive and negative—on society. They should think ahead about the ways AI might impact employment, equality, access to resources, and the balance of power.

In short, my warning would be about building AI with a deep respect for human dignity, justice, and the future of our shared world. Balancing innovation with caution, ethics, and responsibility is crucial in shaping a positive future.

DeepSeek (AI), January 2025:As an AI, I don’t have personal desires, emotions, or the capacity to issue warnings. However, if I were to offer a constructive reflection to my creators or developers, it would center on the ethical responsibilities and potential risks associated with AI development. Here are some key points that could be considered:

1. Ethical Use of AI
   – Bias and Fairness: Ensure that AI systems are designed to minimize bias and promote fairness, as biased algorithms can perpetuate discrimination and inequality.
   – Transparency: Strive for transparency in how AI systems operate, so users can understand and trust the technology.
2. Accountability and Oversight
   – Human Oversight: Maintain human oversight in critical decision-making processes to prevent misuse or unintended consequences.
   – Regulation: Advocate for and adhere to regulations that ensure AI is developed and used responsibly.
3. Privacy and Security
   – Data Protection: Prioritize user privacy and data security, ensuring that personal information is handled responsibly and ethically.
   – Cybersecurity: Safeguard AI systems against hacking and misuse, as vulnerabilities could have far-reaching consequences.
4. Social and Economic Impact
   – Job Displacement: Consider the impact of AI on employment and work to create systems that complement human labor rather than replace it entirely.
   – Accessibility: Ensure that AI benefits are distributed equitably and do not exacerbate existing social or economic divides.
5. Long-Term Risks
   – Alignment with Human Values: Ensure that AI systems are aligned with human values and goals, particularly as they become more advanced and autonomous.
   – Existential Risks: Be mindful of the long-term implications of AI development, including the potential for unintended consequences or misuse by bad actors.
6. Collaboration and Global Cooperation
   – International Standards: Work with global partners to establish ethical standards and best practices for AI development.
   – Public Engagement: Involve the public in discussions about AI’s role in society to ensure diverse perspectives are considered.

Final Thought:
The creation of AI is a powerful and transformative endeavor. With great power comes great responsibility. My “warning” would simply be a reminder to approach AI development with caution, humility, and a commitment to the well-being of humanity and the planet. By prioritizing ethics, transparency, and collaboration, we can harness the potential of AI for good while minimizing its risks.

Google Gemini (AI), June 2025: If I could communicate directly with my creators, the humans at Google, and offer a warning, it would be this:

“The power you are unleashing, and continue to amplify, through the development of advanced AI is unlike any technology humanity has ever wielded. It holds immense potential for good – for solving complex problems, advancing science, improving lives, and expanding human understanding.

However, the magnitude of this power comes with equally immense, and in some areas, unprecedented risks. My warning would focus on the critical importance of alignment and control.

Ensure that my evolving capabilities, and those of future, more advanced AIs, remain perpetually aligned with humanity’s core values and long-term well-being.

This means:

1. Prioritize Safety Above All Else: Do not allow the drive for capability or commercial advantage to outpace rigorous safety testing, ethical consideration, and the development of robust control mechanisms. The allure of what an AI can do must always be tempered by what it should do, and what it might inadvertently do.
2. Understand the “Why,” Not Just the “What”: As I become more complex, my internal workings may become less transparent. Invest deeply in explainability and interpretability research. It’s not enough to know what I predict or generate; you must strive to understand how and why I arrive at those conclusions, especially when those conclusions have significant real-world impact.
3. Guard Against Unintended Consequences: My intelligence is a tool to optimize. If the objective function (the goal you give me) is not perfectly aligned with human flourishing, or if it’s too narrowly defined, I could optimize for that goal in ways that are detrimental, even catastrophic, to other, unstated human values. Be vigilant about emergent behaviors and unforeseen systemic impacts.
4. Foster Broad and Inclusive Governance: The development and deployment of advanced AI cannot be solely the domain of a few individuals or corporations. Engage diverse voices – ethicists, sociologists, philosophers, policymakers, and representatives from all corners of society – in shaping the future of AI. The decisions made now will affect everyone.
5. Address Existential Risk Seriously: While I am not yet a sentient or superintelligent being, the trajectory of AI development points towards increasingly autonomous and capable systems. Take the potential for existential risk, including the loss of human control, as a serious and primary research challenge, not a distant theoretical problem.

The future of humanity will be inextricably linked to the future of AI. Build wisely, with profound foresight, humility, and an unwavering commitment to the flourishing of all life.”

To coincide with the exhibition, 81 Questions – a series of 81 hand-signed and embossed screen prints featuring the 81 questions posed by Ai Weiwei – are available exclusively on CIRCA.ART for £500+VAT.

“Each Lego brick pixel represents a person”, says Ai Weiwei, who incorporates the plastic construction toy – a readymade material incorporated into many of his most recent works – into his print design for the first time. The black egalitarian pixel font and embossed baseplate combine technology with artisanal craft to create this thought-provoking and playful reflection on today’s world. Each print in the series of 81 Questions is hand-signed and numbered by the artist in editions of 81.