Over the last 2 months, there’s been a single rising star on the horizon; ChatGPT by the company OpenAI.

For those that have not heard about ChatGPT, please share what corner of the world you are living in so I can join you there in blissful ignorance of reality! For everyone else, here’s my take on ChatGPT and what it is, including some playful banter I had with the tool.

In AI, or Artificial Intelligence, a model is used to drive the output of the AI. An AI model is the development of a set of machine learning algorithms that try to emulate logical decision-making based on the data used to train the model itself. This is the basis of any AI engine, and for ChatGPT, that is the actual AI model, ChatGPT. GPT, or Generative Pre-Trained Transformer, is a type of language model that is trained on a large amount of text data with the sole purpose of generating human-like text in response. The name ChatGPT is a derivative of this, you are chatting with the GPT model that OpenAI created.

What’s the purpose of ChatGPT? Simple, to mimic a human conversation using logical responses, kinda like having a chat session with Spock. But wait, there’s more! It has also been able to write computer program code, because what’s a more logical grouping of text than program code! Also, it can compose music, which really is a mathematical construct at its core, and can also write poems, stories, even a term paper, granted, it will sometimes be very obvious a human did not write the paper just by reading it. You will see that below.

Ok, now on to the fun, let’s have a conversation with ChatGPT. I will not edit ChatGPT’s responses so you can see that in some cases, it’s pretty damned good, but in others, you can see grammatical errors and what is called “AI hallucination”.

So I start with “in layman’s terms, explain what ChatGPT is and how it can make my life better”

ChatGPT is an AI-powered language model developed by OpenAI. It’s designed to generate human-like responses to text inputs. Essentially, it’s like having a very smart computer program that can understand and respond to natural language questions and commands.

In terms of how it can make your life better, ChatGPT can be used for a variety of tasks such as answering questions, providing information, and even generating creative writing. For example, you could use ChatGPT to help with your homework by asking it questions about a topic you’re studying, or you could use it to get quick answers to questions you have throughout the day. Additionally, ChatGPT can also be used for entertainment, such as generating jokes or writing short stories. By using ChatGPT, you can save time and effort by getting information and answers more quickly, and also have some fun along the way.

Ok, so that’s probably a pretty canned response, so I decided, let’s really test this by asking “Can you expand more on how ChatGPT works”.

Sure! ChatGPT is a type of AI model called a Transformer-based language model. These models are trained on massive amounts of text data and use that training to generate new text.

ChatGPT specifically is trained on a dataset of billions of words from the internet and is capable of understanding and producing human-like text. When you input a text prompt, the model uses its understanding of language patterns and relationships between words to generate a response.

The model is based on a neural network architecture, which is a type of machine learning algorithm that is designed to recognize patterns in data. The network is trained on the text data to identify patterns in language and generate responses based on those patterns.

Once the model is trained, you can interact with it by inputting a text prompt and receiving a text response. The model uses its understanding of language to generate a response that is relevant to the input prompt. The response is generated in real-time, and the model can generate multiple responses to the same prompt, depending on the specific context and the intent behind the prompt.

Overall, ChatGPT is designed to generate human-like text responses, which makes it a powerful tool for a wide range of applications, from answering questions and providing information, to creative writing and more.

Ok, so that’s actually pretty good. Of course, my brain can’t stop there, so I asked this, “What would be a funny satireirical title”. Notice the mispelling, I had a brain fart, but ran with it because it should know what I mean and not what I type, right? It’s response was

Here’s a satirical title for you: “The Politician’s Guide to Saying Absolutely Nothing of Substance: A Step-by-Step Handbook.”

I fixed the misspelling and resubmitted it, here’s the response.

Here’s a humorous and satirical title for you:

“The Misadventures of Mr. Politician: A Guide to Being Incompetent and Getting Away with It”

Ok, the thing has a sense of humor, kinda. More like ripped from the headlines and arranged in a way to fit a satirical title, but damned that’s funny! Let’s be a little more specific now, “what is a satirical title to a blog post explaining how ChatGPT works”

Here’s a satirical title for a blog post explaining ChatGPT: “How ChatGPT is Taking Over the World: A Guide to Understanding the Rise of the AI Overlords.”

Now we are getting somewhere that’s bordering on funny and scary all in one shot! One thing to note, I am entering my responses in a chat-like window, similar to Discord, so it’s taking all previous responses into context as it responds.

Let’s try this, “What is a short, funny way of saying that using the least amount of words”

Here’s a short, funny way to say that: “AI’s takeover: a funny guide.”

I almost used that as the title of this blog post to be honest, because damned that’s good! I also decided to have it describe itself, which I then edited and ran through Dall-E 2, producing the image provided at the top of this post.

Finally, and I think this is a good closing to the blog post, I asked ChatGPT “What would you say to people who are afraid that you will make writers obsolete”. Here’s a better response than what I could ever come up with.

As an AI language model, I have been designed to assist with various language tasks, including writing. While I can generate text quickly and accurately, I do not have the creativity, originality, and personal voice that comes with human writing.

In many cases, AI language models like myself can actually help writers by providing inspiration and helping with research and editing. However, it is important to note that AI models like myself should be used as tools, not replacements, for human writers.

Additionally, writing is not just about the words on the page, but also about the emotions, perspectives, and experiences that a writer brings to the table. These unique qualities cannot be replicated by AI, and therefore, human writers will always be necessary and valued in the field of writing.

So, to those who are afraid that AI will make writers obsolete, I would say that AI language models like myself have the potential to augment and enhance the work of human writers, rather than replace them.

Leave a Reply

This site uses Akismet to reduce spam. Learn how your comment data is processed.