Artificial Intelligence, which until recently was only available to the public through fictional stories or news articles about pieces of technology developed in labs with restricted access, has been taking the consumer world by storm with several public AI systems being released. The most notable of them is ChatGPT, a recently released chatbot produced by the company OpenAI. Let the bot tell you itself!

ChatGPT, the language model developed by OpenAI, is revolutionizing the field of conversational AI. With its advanced understanding of human language, ChatGPT can respond to a wide variety of questions in a manner that is both coherent and natural. Having been trained on a massive amount of text data, this AI model can engage in conversation, impart information, and even narrate stories with a fluency that astounds.

ChatGPT has many capabilities, not only can it respond to basic questions but it can also respond to complex questions and writing prompts producing results that are almost indistinguishable from the work of a person. For example, is the previous paragraph notably different from what might be produced by a writer?

It can even explain exactly how it was trained and how it produces responses; when asked to explain its training ChatGPT provided this result, 

“When I say I was “trained,” I mean that I was exposed to a large dataset of text and learned to generate responses based on that data. The process of training a language model like me involves using machine learning algorithms to analyze vast amounts of text and identify patterns in the relationships between words, phrases, and sentences. These patterns are then encoded into a mathematical model that I use to generate new text. In other words, my training allowed me to develop an understanding of the patterns and structures of language, which enables me to generate responses that are grammatically correct and semantically meaningful. However, because my training data comes from a specific time period and reflects the biases and limitations of the text it was based on, my responses may not always be accurate or up-to-date.”

ChatGPT’s ability to understand, interpret, and respond to complex prompts is practically identical to the processes that take place in the mind when one is tasked with understanding, interpreting, and responding to the complex prompts present in our social environments.

Its vast potential and diverse uses have already grasped the interest of mainstream media, even causing Google to announce its own AI chatbot Bard. While this AI is still being tested before the public has access to it, the success and further development of ChatGPT, and now Bard, has even prompted The New York Times to publish an article detailing how ChatGPT has “kicked off an AI arms race.”

Regardless of whether or not this claim is valid the impact that ChatGPT has had in the few months since its release to the public is undeniable. And continuing to express its exciting capabilities ChatGPT can recognize its potential benefits and drawbacks to society.

Arguably some of the most interesting conversations sparked by ChatGPT have been the ones discussing potential ethical concerns, whether or not the use of what ChatGPT produces is plagiarism or if the use of it is justifiable regardless, concerns about producing biased or malicious misinformation, and especially if it can or will influence job displacement.

ChatGPT can acknowledge and provide potential solutions for these possible adverse consequences. Whether it be its potential lack of creativity, producing biased, inaccurate information, or potential job displacement, ChatGPT is able to produce varied solutions for these problems.

To address the potential for job displacement associated with AI, policymakers, and organizations are exploring programs and initiatives to help people reskill and transition to new jobs. This includes initiatives to promote education and training in new and emerging technologies, as well as support for entrepreneurship and small business development.

When asked about possible responses to ChatGPT Mr. John Carino an NHS English teacher expressed concerns about its purpose and its design saying that when attempts are made to outdo language or the work of humanity, like a writing AI, regardless of their technological capabilities they will always fall short and be unable to properly emulate what humans produce. 

Even students remain cautious about the possible misuse of this technology. Comments were made about how we as a society use these technologies in ways that limit and nullify creativity instead of providing benefits. 

Jaylen Kinnie, an NHS junior and School news co-editor, elaborated on this point expressing how ChatGPT can be a useful tool for research and acquiring information however when it is used for one to avoid writing for themselves it damages their creativity and their own ability to write which was expressed as an essential skill.

As a result of this concern about properly using ChatGPT apps designed to detect ChatGPT’s writing has been developed. A Princeton Computer Science Major Edward Tian developed his app GPTZero and said on Twitter that its algorithms can “quickly and efficiently detect whether an essay ChatGPT or human written.” Tian understands that AI will continue to exist but that efforts should be made “so that these new technologies are adopted properly.”

When discussing technology as useful and potentially dangerous as AI, these intentions must be emphasized. It is important that ChatGPT, and other AIs like it, be developed, and used with the intent, not to damage intellectualism, but to aid learning processes and potentially revolutionize learning altogether.