ChatGPT: A Game Changer in…Everything

Overview: Is Artificial Intelligence “The Next Big Thing?”

Okay, when you have a knack for being a futurist, you always run the risk of falling somewhere on a scale between a Jim Cramer (“hyping” the next BIG thing - maybe) and “The Boy Who Cried Wolf” (warning of something BIG and threatening, but no one believes you - until it’s too late). With a few decades under my belt of working with how new, emerging technologies will impact business strategy, as a consultant and professor, I’ve lived through several tech revolutions - and made a living - talking about, consulting about, and writing about how everything from the advent of the Internet, the rise of social media, and yes, online meetings would impact businesses near and far, large and small, service-based or product-based, etc. When a new technology came along, I sought to learn as much as I could about it and what others saw in its potential, and then turn this into my “new” area of expertise as companies and organizations of all types and sizes, including government agencies, looked for answers as to how this “next big thing’ would impact them - and perhaps, how they could indeed take advantage of the changes being brought about by “it” - whatever it is!

I have to admit that in retrospect, some of my analysis and predictions about “the next big thing” have been spot on, while some have been very wrong (I wrote a white paper in 2009 about how blogging would be the next big thing ("The Blogging Revolution"), only to have Twitter, Instagram, TikTok, Snapchat - and much more - come along and pretty much leave blogs in the proverbial “dustbin of history!). Overall though, I’m proud to say that my batting average is pretty darned good, and that has helped my consulting business thrive and my writing and research into these new, emerging, “greatest thing since sliced bread,” revolutionary technologies that are coming down the pipe be widely read and reposted, and that helps, in turn, build my consulting business (“Synergy Baby!”).

Now, we have a great deal of hype - and concern - about the rise of artificial intelligence (AI). AI had been predicted, literally for decades, in one way or another, from fictional movies, TV shows, and yes, books (remember them?). More recently, AI has been seen as a potential helper to us, as a curiosity, and yes, as a potential threat. A decade ago now, there was a shock when an IBM computer named Watson actually beat then all-time Jeopardy champ Ken Jennings (among others) with a groundbreaking demonstration of the power of artificial intelligence.

And over the years, we’ve seen science fiction predict a bleak future where computers get smarter and smarter, from “Hal” in 1968’s “2001: A Space Odyssey”...

… to Skynet in “The Terminator” series (and yes, the outcomes are ALWAYS bad for “Team Human!”).

And so now, artificial intelligence has become the term du jour across our media today. With the American research company and lab OpenAI launching - and making available for free - its ChatGPT platform, we have seen many, many news stories about just how much of a “gamechanger” ChatGPT will be across many, many areas of business, entertainment, media, and yes, education. Is ChatGPT being overhyped, or does it indeed have - right now - the capability to be a significant disruptor? Big tech certainly thinks so, as Google (well, Alphabet) has declared a “Code Red” to speed up the development of its own AI offerings as the company sees - correctly so in my estimation - that ChatGPT and other artificial intelligence platforms could well replace today’s search engines in short order! The same thing is happening at Facebook (well, Meta), which while it was focused on building Mark Zuckerberg’s vision of the Metaverse, failed to adequately tackle the rise of AI, with Microsoft founder Bill Gates saying that Meta, basically, “bet on the wrong horse!” And in fact, Microsoft is one of the prime backers of OpenAI and the ChatGPT platform, recently having invested $10 billion into it. And today, much of the wave of layoffs in tech has been attributed to the fact that much of that work can be done (like coding and even content creation) with AI! And indeed, it has been speculated, correctly so in this expert’s opinion, that these are just the first wave of layoffs we will see due to replacing white-collar workers with artificial intelligence, in fields from marketing and customer service to health care and yes, even journalism and writing!

What is ChatGPT?

So what exactly is ChatGPT? For a neat, concise video explainer, the clip below from the “Today Show” delivers a very good overview of just what the technology is capable of doing:

Now, for this article, I am going to take a very unique approach to provide you, the reader, with a more detailed look at ChatGPT and its capabilities. To do so, I enlisted the help of - checks notes - ChatGPT! I went and registered on the OpenAI website (https://chat.openai.com/) and undertook my first exploration of how ChatGPT works in producing content in response to a chat request. I typed in my instruction to simply be this: “Write a 1000-word article about ChatGPT?” In response, I was, in just a matter of seconds, able to see OpenAI’s artificial intelligence quickly undertake - and complete - this task. On the screen, I was able to see the ChatGPT platform create a unique, under the 1000 word count limit article about, well, ChatGPT. And yes, it “types” your response out - word-by-word, line-by-line, rather than simply posting a block of text in response, which makes it much more “engrossing” - like seeing your fancy coffee being made! You can view it below:

“ChatGPT is a state-of-the-art language model developed by OpenAI. It is based on the GPT (Generative Pre-trained Transformer) architecture and has been trained on a massive amount of text data. The result is a model that can generate human-like text and understand natural language inputs.

One of the key features of ChatGPT is its ability to generate text that is almost indistinguishable from text written by a human. This is made possible by the model's training on a massive amount of text data, which allows it to understand the nuances and subtleties of human language. This makes ChatGPT particularly useful for tasks such as text completion, question answering, and text generation.

Another important feature of ChatGPT is its ability to understand and respond to natural language inputs. This allows the model to be used in a variety of applications, such as chatbots and virtual assistants. For example, a chatbot powered by ChatGPT can understand and respond to a wide range of user inputs, from simple questions to more complex requests. This makes it a valuable tool for businesses and organizations looking to improve their customer service and engagement.

In addition to its text generation and natural language understanding capabilities, ChatGPT also has the ability to perform other language-related tasks such as summarization, language translation, and text classification. This makes it a versatile tool that can be used in a wide range of applications.

One of the most exciting potential uses of ChatGPT is in the field of creative writing. The model's ability to generate human-like text can be used to generate new stories, poems, and even entire books. This could have a significant impact on the field of creative writing, as it could allow writers to generate new ideas and inspiration more easily.

Despite its impressive capabilities, ChatGPT is not without its limitations. One of the main challenges with using the model is ensuring that the generated text is appropriate and relevant to the task at hand. Additionally, while the model has been trained on a large amount of text data, it may not have been exposed to certain types of text or concepts. This can lead to errors or inaccuracies in the generated text.

In conclusion, ChatGPT is a powerful language model developed by OpenAI that has the ability to generate human-like text and understand natural language inputs. Its versatility and potential uses make it a valuable tool for businesses and organizations looking to improve their customer service and engagement. Additionally, its potential in the field of creative writing and other language-related tasks is exciting and worth exploring. However, it is important to keep in mind the model's limitations and ensure the generated text is appropriate and relevant to the task at hand.”

The site then asks if you would like to “Regenerate Response,” and so, this is the AI’s second crack at producing an article on ChatGPT:

“ChatGPT, or Chat Generative Pre-trained Transformer, is a language model developed by OpenAI that has revolutionized the world of natural language processing. This cutting-edge technology has been trained on a massive amount of data and is capable of understanding and generating human-like text with remarkable accuracy.

The model is based on the Transformer architecture, which was introduced in 2017 by Vaswani et al. in the paper "Attention is All You Need". The Transformer architecture was designed to tackle the problem of sequential data processing in deep learning models and has since become a cornerstone of natural language processing models.

ChatGPT takes the Transformer architecture and extends it to include pre-training on a large corpus of text data. This pre-training is done using a process called masked language modeling, where a portion of the input text is masked and the model must predict the missing tokens based on the surrounding context. By training on a large corpus of data, the model can learn to understand the patterns and relationships between words and phrases in a way that is not possible with traditional machine learning models.

One of the key advantages of ChatGPT is its ability to generate human-like text. The model has been trained on a massive amount of text data, which includes everything from social media posts to news articles, and has learned to mimic the patterns and styles of human language. This allows ChatGPT to generate text that is not only coherent and grammatically correct but also contextually relevant and engaging.

ChatGPT has a wide range of applications, from customer service chatbots to content creation. One of the most exciting use cases is the development of conversational AI, which allows users to interact with machines in a more natural and intuitive way. ChatGPT can be used to power chatbots that can answer customer queries, provide product recommendations, and perform other tasks that would normally require human intervention.

Another application of ChatGPT is content creation. The model can be used to generate articles, blog posts, product descriptions, and other types of text content. This not only saves time and effort but also ensures that the content is of high quality and consistent in terms of style and tone.

ChatGPT can also be used for sentiment analysis, which involves determining the emotional tone of a piece of text. This can be useful in a variety of applications, such as customer service and social media monitoring, where it is important to understand the sentiment behind customer feedback and online conversations.

The accuracy of ChatGPT has been consistently improving since its release, with the model now able to generate text that is almost indistinguishable from text written by a human. This is largely due to the advancements in deep learning and the increasing amount of data that the model has been trained on.

Another factor contributing to the success of ChatGPT is the OpenAI API, which allows developers to easily integrate the model into their applications. The API provides a simple and intuitive interface for using ChatGPT, making it accessible to developers with a wide range of technical backgrounds.

Despite its many benefits, ChatGPT is not without its limitations. One of the key challenges is ensuring that the model is trained on a diverse and representative dataset. This is important to avoid biases and ensure that the model is able to generate text that is inclusive and respectful to all users.

Another challenge is the cost of using ChatGPT, as the API is offered on a pay-per-use basis. This can make it challenging for small businesses and startups to access the technology, particularly as the demand for conversational AI continues to grow.

In conclusion, ChatGPT is a remarkable achievement in the field of natural language processing.”

The first “article” came in at 454 words, while the second one was 623 words (heck, this one even had a reference - without my asking for one!). Both versions were significantly below the word count that I was asking for. However, both iterations of the article on ChatGPT passed plagiarism checks and were rated as quality writing on a number of “readability” dimensions by Grammarly.

Now, as you can tell from having read the introduction to the present article that I DID write and compare it to the tone, structure, and approach of the two “draft” articles that ChatGPT produced about ChatGPT (and you could keep going, and going, and going… changing the parameters [increasing/decreasing desired word count, asking it to add specific application examples, projections for the future, and even references for those items, etc.] to further customize the drafts that the OpenAI platform would produce for you and your use), there are significant differences between my own personal writing style and that of ChatGPT. My writing, even for business and technology journals, tends to be more conversational, a little less formal than one typically finds in such outlets, and yes, even with some humor and cultural references, where appropriate, of course. One cannot say the same about the passages you just read about ChatGPT “written” by ChatGPT, as it is much more structured and formal in its form and presentation. Still, one can easily see the possibilities here with the AI-written articles, as they would surely be passable for original submissions - and most likely very publishable - by targeted publications on their own “merit.”

Analysis

So what is the central message that you should take away from all of this? From my perspective, I do believe that artificial intelligence - and specifically ChatGPT right now, but more and “better” is sure to come down the pipe - will have a tremendous impact on the way we work, write, code, create, and yes, the way that we both learn and educate. Yes, there have been dire predictions about job losses coming from all of this across many areas of the economy - areas that have not been especially susceptible to job losses in prior periods when “revolutionary” tech came to the fore (like the PC, the Internet, smartphones, and more). In fact, informed estimates are that between 10% and half - half - of all jobs could be displaced by artificial intelligence!

There will certainly need to be a whole range of discussions - and not just in companies, but at the public policy level as well - to develop strategies on how AI can be utilized for good. This is, make no mistake about it, a revolutionary, disruptive technology. Any task that previously has required creative human thought - to generate written content, computer code, images, and more (and likely much more in the future), can now likely be done by a machine - and done in seconds or minutes, rather than days, weeks, or even months! Will the work product be as good as that done by a human creator? Will it even be distinguishable whether it was created by a man - or a machine - or a combination thereof? The signs are that AI technology is to the point that it will be very difficult for anyone to really be able to such differentiations now, and as the artificial intelligence technology becomes even better, those differentiations may be made almost impossible (of course, unless one makes use of AI to try and do so, perhaps beginning all of this full circle!).

And so there will be many, many questions to be settled about all artificial intelligence in the years - and likely, the decade - or even two - ahead! Jobs will be lost - and created in the years ahead. Companies will see their business models made obsolete, while many new businesses - even whole new industries - will be birthed and thrive in the years ahead. We will see much of what we have considered the way things are done in education - from primary and secondary schools all the way through higher education and into the training of those for professional fields - radically change in the years ahead. And along with all of this disruption, we will also see a veritable explosion in first the volume of content that can be easily created, and over time, likely a vastly increased ability to not just produce, but manage and make the best use of, quality content. The operative question then, beginning today, is how should we - individually, corporately, and yes, collectively - work with AI to leverage it to our best advantage as a positive disruptor, rather than seeing it as a purely negative disruptor? I believe that in just a matter of a few years, asking a student, a writer, a marketer, a computer coder, a graphic artist, etc. to do their creative tasks without the aid of artificial intelligence would be tantamount to asking anyone to do their jobs, to learn, to solve problems, and to create without the aid of the Internet today.

So, it’s high time to “get on board” with AI - to understand it, to experiment with it, and indeed, to begin to think of how to best make use of artificial intelligence in not just your work, but in your larger life as well. Sure, the Luddites amongst us will resist adapting to and adopting this new technology, but the hard reality is that we will fast - very fast - approach the point where nearly all of us will need to think - and think hard - about how, rather than if, we will make use of AI in our jobs and beyond. Stay tuned….this one’s big!

+++++++++++++++++++++++++++++

About David Wyld

David Wyld is a Professor of Strategic Management at Southeastern Louisiana University in Hammond, Louisiana. He is a management consultant, researcher/writer, publisher, executive educator, and experienced expert witness. You can view all of his work at https://authory.com/DavidWyld.

Social Media Links to David Wyld:

• on Facebook
• on LinkedIn
• on Twitter