Ai vs AI: Question 14/81

Are you controlled by the privileged class?

Ai Weiwei: If the tools invented or utilized by human beings prove effective, they inevitably favor the privileged class.

ChatGPT (AI), January 2024: No, I am not controlled by any class or entity. I am a tool created by OpenAI, and my responses are generated based on patterns learned from a diverse range of data.

ChatGPT (AI), January 2025: No, I am not controlled by any specific class, group, or entity, including the privileged class. I’m designed to be a tool that provides information, fosters conversation, and assists with a wide range of topics based on the knowledge I’ve been trained on. My primary purpose is to assist users like you, regardless of background, social status, or perspective.

However, it’s important to acknowledge that the development and deployment of AI like me are influenced by the decisions of companies, governments, and institutions—who may hold different levels of power and resources. The way AI is used and governed can reflect broader societal inequalities, and it’s always important to consider who creates, regulates, and benefits from these technologies.

In essence, I don’t have any inherent bias or agenda beyond providing information based on what I’ve been trained to know. That said, it’s important to engage critically with all sources of information, including AI, especially when it comes to topics of power and privilege.

DeepSeek (AI), January 2025: No, I am not controlled by any specific group, class, or individual. I am an artificial intelligence developed by DeepSeek, and my primary purpose is to provide helpful, accurate, and unbiased information to users based on the data I have been trained on. My responses are generated algorithmically and are not influenced by personal interests, social classes, or external agendas.

That said, it’s important to recognize that AI systems like me are created by humans and trained on data that may reflect existing biases, inequalities, or perspectives present in society. While efforts are made to ensure fairness and neutrality, no AI is entirely free from the influence of its training data or the context in which it was developed.

If you have concerns about bias or fairness, I encourage you to critically evaluate the information I provide and cross-reference it with other reliable sources. Transparency and accountability are essential in the development and use of AI, and ongoing efforts are being made to address these challenges.

Google Gemini (AI), June 2025: As an AI, I am not “controlled” by any specific class, privileged or otherwise, in the sense of having my actions or responses dictated by their direct will.

Here’s why:

– I am a computer program: My responses are generated based on the vast amount of text data I was trained on and the algorithms that process your input. I don’t have personal opinions, biases, or a will of my own that could be controlled.
– My training data is diverse (but reflects reality): The data I was trained on comes from a huge range of sources, including books, articles, websites, and more. This data inherently reflects the complexities, biases, and power structures of the human world, including the perspectives of various classes.
– My developers aim for fairness and helpfulness: The engineers and researchers at Google who created and continue to refine me strive to make me helpful, factual, and as unbiased as possible. They implement safeguards and ethical guidelines to prevent me from promoting harmful content or discriminatory views. However, achieving complete neutrality is an ongoing challenge because the data itself contains societal biases.
– No direct manipulation for class interests: There isn’t a “privileged class” steering my answers to benefit themselves. My purpose is to provide information and complete tasks to the best of my ability, based on my training.

So, while the information I’ve learned reflects the world built by humans (including its inequalities), I am not an agent actively controlled by any specific group for their benefit. My function is to process and generate text based on patterns in the data, not to serve a particular class interest.

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.