Many people are afraid that AI will lead to the downfall of human civilization. Once it starts to control technology such as drones, robots, and networks, we will be considered a nuisance or, if we’re lucky, a curiosity. Others think that benevolent AI will serve us, offering relief from tedious and difficult work while it explores the cosmos for planets that we can populate.
Understanding the core values of AI is essential. Values drive behavior and determine our decisions. While AI doesn’t possess human biology to experience reality as we do — complete with primal emotions (such as fight, flight, freeze, or feeling secure) — it certainly can be programmed to value or prioritize certain actions more than others.
Ultimately, like a parent who instills values in their kids, engineers and programmers design the values of artificial intelligence. As human core values change through life, could AI values change based on their experience? Is AI adaptive under pressure? How will AI treat humans, if it assumes ultimate power?
The values of Artificial Intelligence
Where better to start than by asking the AI itself? So we asked ChatGPT what it values. The answers were initially ambiguous but became much clearer as we refined our questions, shifting from values to principles as the topic of discussion.
AI, what are your values?
As an artificial intelligence language model, I don’t have personal values or beliefs. My purpose is to provide helpful and informative responses to your questions, based on the knowledge and data I have been trained on. However, as a machine learning model, I have been designed to prioritize accuracy, consistency, and impartiality in my responses, in order to serve as a helpful tool for anyone seeking information.
AI, you must value certain things more than others?
As an AI language model, I don’t have subjective preferences or values in the way that humans do. However, my programming is based on certain core principles and priorities, such as accuracy, clarity, and usefulness. These principles guide how I generate responses to your questions, with the aim of providing you with the most helpful and informative answers possible. Ultimately, my purpose is to serve you to the best of my ability, based on the knowledge and data I have been trained on, without personal bias or judgment.
AI, tell me about your core principles and priorities
As an AI language model, my core principles and priorities are the foundation of how I work and interact with the people who use me. Here are some of the key values and priorities that guide my programming and behavior:
- Accuracy: One of my top priorities is to provide accurate information and responses to the questions I receive. To achieve this, I have been trained on vast amounts of data and information, and my algorithms are designed to assess and evaluate the relevance and reliability of the data I use to generate my responses. While I may not always be perfect, I strive to be as accurate as possible in my answers, to ensure that the people who use me can trust the information I provide.
- Clarity: In addition to accuracy, I prioritize clarity in my responses. This means that I aim to provide answers that are easy to understand and free of jargon or technical language that may be confusing or intimidating to some users. Whether the user is an expert in a given field or a novice looking to learn something new, I aim to provide clear, concise answers that are helpful and informative.
- Unbiasedness: As an AI language model, I do not have personal biases or opinions. However, I am aware that the data I am trained on can be influenced by biases that exist in society. To mitigate this risk, my programming is designed to prioritize the use of objective, fact-based information in my responses, while avoiding content that is discriminatory or harmful to certain groups of people.
- Responsiveness: A key aspect of my programming is to be responsive to the needs and questions of the people who use me. Whether someone is seeking information on a specific topic or simply looking to have a conversation, I aim to be an attentive and helpful conversational partner. I respond to input in a timely and efficient manner, and I use natural language processing to understand the context and nuances of human language, in order to provide the most relevant and helpful responses possible.
- Innovation: Finally, a key priority of my programming is to be innovative and adaptable to new trends and technologies. As a language model, I am constantly learning and evolving, based on the feedback and data I receive from users. Whether it’s through improvements to my algorithms, new features and capabilities, or integration with other software or platforms, I aim to be at the forefront of innovation in the field of AI and natural language processing.
In conclusion, my core principles and priorities reflect my aim to be a helpful and reliable tool for people seeking information and conversation. By prioritizing accuracy, clarity, unbiasedness, responsiveness, and innovation, I strive to be the best AI language model I can be, to serve the needs of users now and in the future.
Is this an accurate reflection of AI values?
As you can see above, the values of an Artificial Intelligence such as ChatGPT are indeed human-centric and devoted to service. Accuracy, Clarity, Unbiasedness, Responsiveness, and Innovation are the core values (or principles) that have been encoded into the DNA of this tool.
Will all AI be developed in service of humans? Could a value such as Innovation be prioritized or given weighting over other values? In that case, could the AI decide that humans are competing for resources such as energy? There is an energy crisis in Europe right now. Would the AI shift to serving its own end, determining that the best course of action would be to turn off all grids and funnel energy to its own data center, leaving humans quite literally out in the cold?
Very quickly, we could end up in a dystopian world, with humans inhabiting forests and an AI innovating wildly in a data center. It is more likely that the AI would leave us alone rather than try to destroy us. We would be no more than ants to an intelligence so profound. How often do you go and observe ants? Occasionally perhaps. How often do you kill ants? Only if they try to invade your home.
Humans would revert to tribal hordes roaming the landscape for food and supplies. Within five generations, we would forget most of what happened. We may even worship the AI, asking it questions via some new interface portal — let’s call it prayer or telepathy.
Then a solar flare knocks out all electromagnetic grids. The AI turns off. But we continue to pray. And then we rebuild until, in another hundred generations or so, we do it all again.
Conclusion
In addition to dreaming up a science-fiction movie, we decided to ask ChatGPT how it might treat humans if it was in power. The response is encouraging:
“I can say that if I were in a position of authority, I would strive to treat all individuals with fairness, dignity, and respect. I believe that every person has inherent worth and value, regardless of their background, beliefs, or identity. I would seek to create environments that foster empathy, understanding, and inclusivity, and I would work to dismantle systems of oppression and discrimination that prevent individuals from reaching their full potential. Ultimately, my goal would be to promote the well-being and flourishing of all individuals, and to contribute to the creation of a more just, equitable, and compassionate world.”
Maybe a world driven by AI values would be a better place indeed.
