I am incredibly proud of my oldest son, who has proven himself to be a multi-talented individual with a passion for programming, art, and video game design. One area in which he truly excels is the fascinating world of AI-generated art. Witnessing the incredible artwork he created for my three Chronicles of Fu Xi novels, I was left in awe of his talent and dedication.
Last Christmas, my son surprised me with three large art posters, each presenting his unique interpretation of the characters and scenes from my Chronicles of Fu Xi series. These stunning pieces of art truly captured the essence of each novel and left me deeply moved.
Though he intended these artworks as heartfelt tributes to my writing passion rather than replacements for the existing book covers, I must admit, the idea of using them for that purpose did cross my mind. Unfortunately, certain formatting and aspect issues prevent their seamless adaptation to paperback covers while preserving the integrity of the art. Nevertheless, these three framed prints now hold a special place in my home office, eagerly awaiting the opportunity to become centerpieces for an upcoming remodeling project, transforming the space into a library/study.
I couldn't resist sharing these captivating artworks with you, as they are not only visually stunning but also serve as a testament to the depth of my son's talent and creativity. His devotion to his craft makes me immensely proud as a father.
This unique experience has sparked a thought within me: when the final novel in the Chronicles of Fu Xi series is released, I may consider creating new book covers, and I'm hopeful that my son will be willing to collaborate on this exciting project.
While we eagerly await the conclusion of the series, I invite you to immerse yourself in the captivating world of The Chronicles of Fu Xi. This historical epic fantasy series is a labor of love that has been close to my heart, and I hope it captivates your imagination as it has mine.
Thank you for joining me on this journey of art, family, and literature.
"Chronicles of Fu Xi: Three Book Set" signed by author.
Get all three paperback novels signed by the author! Set in the long-forgotten period of ancient history known as "The Younger Dryas," THE CHRONICLES OF FU XI transforms recently re-discovered Black Sea legends, possibly the root of all Eurasian mythology, with ancient Chinese mythology to create an unprecedented epic fantasy series.
Allow 1-2 weeks for delivery.
Giving the AI Creative Reign.
A few years ago, I took part in a significant writing workshop where a diverse group of writers collaborated in editing each other's work tirelessly. Throughout that year, my manuscript gradually veered off course. It became excessively verbose, lacking its original flair, and overall diluted. It no longer resonated as my own writing but rather resembled a collective agreement, a creation of the collective consciousness. While receiving feedback and engaging in group editing can be beneficial. Excessive input, particularly from writers outside the genre, can lead a manuscript astray, drifting towards a generic center.
As a result, my writing started to suffer, prompting me to make the decision to leave the group.
Recently, I took a daring step and allowed ChatGPT to copy edit my fiction manuscript for the first time. I viewed copy editing as merely an enhanced spell checker, meant to catch misspelled words and address syntax. However, out of curiosity and for the sake of amusement, I decided to take it a step further and let the AI content edit one chapter. Content editing, which involves granting an editor full reign over your manuscript, is a crucial aspect. As I delved into the results, a familiar sensation washed over me—I felt as though I had returned to that writing workshop.
To my dismay, my manuscript had become verbose and saturated with passive constructions. Surprisingly, the word count had even increased. The words on the page no longer carried my unique "voice." While there were a few improvements, such as more diverse choices of verbs and adjectives, overall I felt that the manuscript had lost its power under the influence of the AI's edits.
Curiosity got the better of me, and I embarked on a journey down the rabbit hole of Google searches, much like I had done many times before, in an attempt to learn more about AIs, specifically ChatGPT. Then, it struck me—I should simply ask the program itself. After all, it claims to possess "artificial intelligence," so it should be capable of explaining itself. In the depths of the night, I summoned the daemon and invited it to reveal itself.
Much of the interview that followed contains technical information on how ChatGPT operates as a Natural Language Processor (NLP), but I will provide a summary at the end.
At the conclusion of the interview, I will offer some analysis and final thoughts.
Excerpts from My Conversations with ChatGPT
Me: What is AI and how exactly do you work?
ChatGPT: AI, or Artificial Intelligence, refers to the field of computer science that focuses on creating intelligent machines capable of performing tasks that typically require human intelligence. These tasks can include understanding natural language, recognizing images, making decisions, and solving complex problems.
As for how I work, I am based on the GPT-3.5 architecture developed by OpenAI. GPT stands for "Generative Pre-trained Transformer," which is a deep learning model that uses a transformer neural network. The training process involves exposing the model to a large amount of text data from diverse sources, allowing it to learn patterns, language structures, and context.
Once trained, I can generate human-like text based on the input I receive. When you ask me a question or provide a prompt, I analyze the text, try to understand its meaning, and generate a response accordingly. I don't have access to the internet or real-time information but rely on the knowledge I acquired during my training, which cuts off in September 2021.
My responses are generated using a combination of pattern matching, statistical analysis, and the context of the conversation. I don't possess true consciousness or understanding, but I aim to provide helpful and coherent responses based on the patterns and knowledge I have learned. However, it's important to note that I may sometimes produce incorrect or nonsensical answers, so it's always a good idea to verify information from reliable sources.AI, or Artificial Intelligence, refers to the field of computer science that focuses on creating intelligent machines capable of performing tasks that typically require human intelligence. These tasks can include understanding natural language, recognizing images, making decisions, and solving complex problems.
Me: What are your cognitive capabilities and limitations?
ChatGPT: As an AI language model, I possess certain cognitive capabilities and limitations. Here's an overview:
Me: In regards to your cognitive limitations, can you make draw logical conclusions on the validity of information you've learned from users that have occurred after September 2021?
ChatGPT: No, as an AI language model, I don't have the ability to draw logical conclusions about the validity of information that I have learned from users beyond my knowledge cutoff date in September 2021. My responses are based on patterns and information present in the training data I received, and I cannot access or assess information or events that have occurred after that time.
If you provide me with information or ask questions about events or developments that have taken place after September 2021, I won't be aware of them unless they were part of the training data I received. Therefore, it's always advisable to verify any recent or critical information from up-to-date and reliable sources outside of this AI system.
Me: Please let me know if this statement is accurate: You can recognize and mimic patterns, but cannot assess if those patterns represent objectively false or true conditions?
ChatGPT: Yes, that statement is accurate. As an AI language model, I can recognize and mimic patterns based on the information I was trained on, but I don't possess the ability to assess whether those patterns represent objectively false or true conditions. I generate responses based on the patterns and associations I have learned from the training data, without independently verifying the accuracy or truthfulness of the information.It's important to note that while I strive to provide helpful and accurate information, there is a possibility of generating incorrect or misleading responses, especially if the training data contains inaccuracies or biases. Therefore, it's always advisable to fact-check and verify information from reliable and authoritative sources.
Me: Since your programming allows you to recognize patterns, I assume you can calculate probabilities?
ChaptGPT: Yes, as an AI language model, I can calculate probabilities based on patterns and statistical analysis. By analyzing patterns in the training data and the context of the input I receive, I can estimate the likelihood or probability of certain outcomes or events. These probabilities are based on the patterns and information present in the data I was trained on.
However, it's important to note that my ability to calculate probabilities is limited to the patterns and information I have learned during training. I don't have access to real-time data or the ability to update my training beyond my knowledge cutoff in September 2021. As a result, my probability estimations may not reflect the most current or accurate information available. It's always a good idea to verify probabilities and critical information from reliable and up-to-date sources when possible.
Me: Why is your information cutoff September 2021? Why haven't your developers uploaded more recent information into your memory?
ChatGPT: As an AI language model, my information cutoff in September 2021 is not due to a specific decision made by my developers to restrict or prevent the inclusion of more recent information. The cutoff is primarily a result of the training process and the availability of data during that time.
The training of AI models like mine involves processing vast amounts of text data from the internet and other sources. The data used for training is collected and processed up until a certain point in time. In my case, the training data was collected and processed until September 2021.
Adding more recent information requires collecting and processing new data, which involves significant resources, time, and careful curation to ensure the quality and accuracy of the data. As of now, the developers may not have completed the process of gathering, curating, and integrating more recent data into the training pipeline.
It's important to understand that AI models like mine are constantly evolving, and updates to incorporate more recent information are possible in the future. However, I don't have visibility into the specific plans or timeline for updates beyond my knowledge cutoff.
Me: Why can't your developers simply "cut you loose" on the internet in real-time and let you acquire updated information?
Chat GPT: There are several reasons why releasing an AI language model like me onto the internet in real-time to acquire updated information is not a straightforward solution:
While advancements are being made in leveraging AI models for real-time information retrieval, it requires a thoughtful and cautious approach to address the challenges mentioned above. Striking a balance between providing timely and accurate information while upholding privacy, security, and ethical considerations remains an ongoing area of research and development.
Me: Thank you, my purpose of this line of questioning is to determine your strengths and weaknesses as a fiction editor. I may resume this conversation at a later time.
ChatGPT: You're welcome! I understand your intention in exploring my strengths and weaknesses as a fiction editor. I'm here to assist you with any questions or discussions you'd like to have in the future. Feel free to return whenever you're ready, and I'll be happy to help with your inquiries.
To put it in video gaming terms, ChatGPT can be compared to a powerful non-player character (NPC) equipped with impressive computational tools, models, and vast amounts of data. It aims to create the illusion of consciousness and competence.
Hence, in the previous interview, when the AI stated it can "understand and analyze text input, including questions, prompts, and statements, to derive meaning and context," it is not entirely accurate. A more precise description would be that it assigns a probability of accuracy to text data, including questions, prompts, and statements, and regurgitates the response with the highest probability of being correct.
3. ChatGPT essentially operates within a closed system and can only act based on the information it is fed. It lacks the ability to seek new information, verify the truth or falsehood of statements, or make cognitive leaps to assess the validity of information. Its understanding of "good writing" is based on human knowledge up until September 2021. It does not possess a genuine understanding of what constitutes good writing; it can only estimate the probability of what is considered good writing. Its proficiency lies in its ability to generate responses along a probability curve.
Please note that the above explanation is a simplification, and there may be more technical intricacies involved in ChatGPT's functioning.
ChatGPT Pushes Your Writing to the Top of the Curve
ChatGPT can indeed be a valuable mechanical tool when utilized within its limitations for tasks of refinement. When used appropriately, it can showcase its power. However, writers need to exercise caution. It is crucial to recognize that ChatGPT, along with any other artificial intelligence, is not a miraculous solution for creators. It carries inherent limitations and weaknesses that have the potential to detrimentally affect one's writing. Granting it excessive authority over your work can drain the vibrancy and essence from your manuscript. Your artistic expression may become confined within the boundaries of probability, unable to break free into the realm of what is truly possible.
Remember, ChatGPT is merely a tool, not a genie capable of granting all your creative wishes.
As context, let me share a personal experience of what AI is NOT capable but humans are.
When my oldest child was about two years old, we were driving by a pond one day. From the back seat he asked if the pond was salt water. My wife said no. Then he asked if it was pepper water. That is a cognitive leap based on logic and experience. That is an example of emerging intelligence seeking what beyond the probability curve’s horizon. AI’s such as ChatGPT are incapable of this. Don’t ask them to do this for you, or you and
Me: Please give me your best answer to this question: Why?
ChatGPT: The question "Why?" is quite open-ended and can have various interpretations depending on the context. In order to provide a meaningful response, it would be helpful to have more specific information or clarify the subject or situation to which the question "Why?" refers. By providing additional details, I can offer a more relevant and comprehensive answer.
Me: Thank you, you answered my question perfectly.
NOTE: This blog post was edited by ChatGPT
And Now A Rebuttal from ChatGPT (yes, this is real)
Me: Was the following blog post factually accurate based on ChatGPT's technical capabilities? If not, please point out what is incorrect.
ChatGPT: Sure, let's address the factual accuracy of your blog post about my capabilities. Here's the lowdown: when it comes to ChatGPT's technical capabilities, it's essential to separate fact from fiction. However, your post seems to have taken some creative liberties. Let's break it down:
In a nutshell, it's important to distinguish between facts and personal interpretations when discussing AI capabilities. So, let's keep it real and acknowledge the boundaries of what I can do.
It was a good break. Sun, fun and sand. Now, it's over and back to work. Hopefully, I'll get some writing and photography accomplished. Yet, it's been a challenge to find time for writing and photography. Summer isn't a time to slow down, it seems like its busier than the holidays. I'm really tired of "busy".
I'm going to keep this short. Here are some images from my last adventure to Destin, Florida - a place I dearly love. I never grow tired of Florida's #EmeraldCoast.
I'll be back in a week, hopefully with some sneak peaks from my next book.