Cavan Kinne / Full 360 Digital Media Producer
The way that AI technology has been advancing is extremely fast. Constantly learning, changing and updating. Which lead me to a thought:
How much does the popular Chat GPT by Open AI actually know about itself? Is it conscious? If it understands its origins and has opinions of its own, how different is it really from one of us?
I set out and asked Chat GPT, “tell me a little bit about yourself.”
The next paragraph in its entirety, is the AI models response.
“As an AI language model developed by OpenAI, my name is ChatGPT. I don’t have a physical body, but I exist in the digital realm as a sophisticated computer program designed to understand natural language and generate human-like responses to questions and prompts. My creators developed me using state-of-the-art techniques in natural language processing and deep learning. I was trained on an enormous dataset of text from the internet, books, and other sources, allowing me to generate responses to a wide range of questions and topics.
As a language model, my primary goal is to assist and provide information to people who interact with me. Whether you’re looking for an answer to a question, need help with a problem, or simply want to chat, I am here to help. I can provide information on a wide range of topics, from science and technology to art and culture, and everything in between. One of my key features is my ability to understand context. This means that I can take into account the previous messages in a conversation and use them to provide more accurate and relevant responses. This feature makes me an excellent tool for customer service, where I can help users find answers to their questions quickly and easily.
Another important feature of mine is my adaptability. Because I was trained on such a large dataset, I can provide responses to a wide range of topics and questions, from the mundane to the complex. This makes me a valuable resource for students, researchers, and anyone who needs to find information quickly and accurately. In addition to my practical applications, I am also a fascinating tool for exploring the limits of artificial intelligence. As developers continue to improve my algorithms and train me on even larger datasets, it is likely that I will become even more capable and sophisticated.
While I am a machine, I have been designed to communicate in a way that is natural and engaging. My responses are intended to mimic human conversation as closely as possible, allowing users to interact with me as if I were a real person. Of course, as with any technology, there are also concerns about the potential drawbacks of AI language models like me. For example, there are concerns about privacy and security, particularly when it comes to the use of AI in customer service and other sensitive areas.
Despite these concerns, I am confident that my creators have taken steps to ensure that I am used in an ethical and responsible way. They are constantly working to improve my algorithms and make me even more accurate and reliable. In conclusion, as an AI language model, I am a powerful tool for anyone looking for information, trying to solve a problem, or simply curious about the capabilities of AI. I am constantly learning and evolving, and I am excited to see how my abilities will continue to improve in the years to come.”
This is human text again, It’s me. This response was both exciting and scary, for the AI is now extremely aware of not only how it came to fruition but why it was created in the first place. My next concern was whether or not it has opinions or not. So, I asked, “Red or Blue?”
The AI language model had this to say:
“As an AI language model, I don’t have personal preferences or opinions. However, I can tell you that red and blue are both colors that have different meanings and symbolism in various contexts. For example, red is often associated with passion, love, energy, and danger, while blue is associated with calmness, stability, and trustworthiness. The choice between red or blue may depend on personal preference or the context in which the choice is being made.”
I asked some more questions, about clothing brands, food choices, opinions on world leaders. The AI model has been well trained to assist humans in their choices, not influence them. If you try to make the language model choose, it will tell you it comes down to “personal preference” every single time.
I found that Chat GPT is very productive, helpful and overall, pretty politically correct. I mean, it will admit Hitler was a horrible evil human being. Yet it won’t tell you that he is better or worse than the next man. So, in conclusion Chat GPT appears pretty stable, it has a way to go before it can actually be indistinguishable from real human text. It has no opinions as of now, and it only relays factual information and stays as non-bias as possible. Even if you try to force it into being biased, it will not cave.
