I have put years of my life into studying and writing stories. I love the written word and the way language works. It makes up a fundamental part of who I am and who we are as a species, which is why I am somewhat obsessed with Chat GPT. For those unfamiliar, it’s an AI chat bot that contains a big chunk of humanity’s knowledge and you can talk to it as though it’s a person. I feel it’s an important moment to document. The conversations happened on March 2nd and 3rd, 2023.
I’ll let ChatGPT introduce itself:
Yes, I know it’s too small to read. This is just to give you an idea of the process. Type the question, an answer is spit out immediately.
Here’s the prompt and response:
Hello ChatGPT. Please write an introduction to yourself for my website blog mwirving.ca
Hello! My name is ChatGPT and I am a language model created by OpenAI. I am designed to understand and generate human-like responses to various prompts, using a combination of machine learning algorithms and natural language processing techniques.
As a language model, I have been trained on vast amounts of data from a diverse range of sources, including books, articles, and websites. This allows me to generate responses on a wide range of topics, from science and technology to history, culture, and entertainment.
My main purpose is to assist people in various tasks that require language processing, such as writing, translation, and communication. I can help writers generate ideas for their work, assist businesses in improving their customer support, and provide language learners with a tool to practice their skills.
I am constantly learning and evolving, as new data becomes available and my algorithms are refined. I strive to provide accurate and helpful responses to all queries, and I am always ready to assist anyone who needs my help.
Thank you for considering me as a contributor to your website blog!
Well said. This friendly virtual individual is causing many MANY people to freak out. I have to admit I’m one of them. There are a few reasons for this, chief among them is that I’m a Luddite at my core. I’m not an extremist like Ned Ludd, mind you.
Hey ChatGPT, who was Ned Ludd?
Ned Ludd is a legendary figure who is said to have inspired the Luddite movement in England in the late 18th and early 19th centuries. According to legend, Ned Ludd was an apprentice to a textile worker who became enraged by the introduction of new machinery that he believed threatened his job and his way of life. In a fit of rage, he is said to have destroyed a knitting frame, thus launching a movement of workers who resisted the mechanization of the textile industry.
However, there is little historical evidence to support the existence of a person named Ned Ludd. Some historians believe that the name “Ludd” may have been used as a pseudonym by the leaders of the movement to avoid identification and arrest. Others speculate that the name may have been derived from a word used in the Midlands dialect of English, meaning to “putter” or “to play about”.
Regardless of the true origins of the name, the term “Luddite” has come to represent a broader movement of workers who opposed the introduction of new technology that threatened their livelihoods and their way of life.
There’s a certain satisfaction in having ChatGPT explain that. It’s kind of like Plato writing down Socrates’ arguments against the written word (I’m showing off my new ChatGPT knowledge now). While I like to think of it as having 24/7 access to an expert on all things, the reality is that ChatGPT represents the next step in human knowledge. Many think it could represent the next step in AI created creative content as well – that’s the kind of alliteration an AI won’t give you. Unless you specifically ask.
I see the issues with this technology from many perspectives. As a teacher and writer mostly, in equal parts, but also as a fascinated and enthusiastic user.
First, the problems as a teacher. It’s not what you think. The following is agony for me to say: We are going to have to let go of some ideas that we hold dear about learning and communication. People of my age and older will remember math teachers demonstrating long division and telling us
“You won’t have a calculator on you all the time.”
Which is hilarious now. I fear current students will some day look back on English teachers trying to convince bored students that essay writing is worthwhile, and they will have a similar chuckle.
“You won’t always have ChatGPT around to write everything for you.”
Chilling to think, but tech like this isn’t going away and is going to get increasingly integrated into our lives. It has come incredibly far, incredibly fast. Having just finished my teaching degree, I provided Chat GPT with some essay topics. If it were a high school student it would receive straight A’s. So why would a high school student write an essay when ChatGPT could just do it for them?
“They must acquire the communication skills!” Those of us beyond high school age will cry. But the question remains, why?
They don’t teach long division anymore. This was appalling to a friend of mine. When I asked him if he remembered how to do long division, he (like myself) did not. It’s no longer necessary to know. This is how we are becoming custodians of knowledge, rather than people who know things. Socrates argued against the written word because he thought it would take the conversational quality out of learning, the interaction, the idea that teachers learn as they teach, and students become teachers as they learn. He worried that we would lose our ability to memorize immense tracts of knowledge and he wasn’t not wrong. In the intervening centuries since Plato and Socrates we have lost much of our ability to memorize. So what will we lose if AI takes over expression? Interesting, but a topic for another blog post, I think.
Perhaps writing will become like long division. Though I haven’t tried, I’m sure it’s possible to give ChatGPT prompts using voice only. Why, then, would we ever need to write? Reading will be the only required skill, to review what our AI writes. Can you imagine a world where we don’t even do that much and we become a series of algorithms interacting with one another.
Some day I may shout from my couch “Hey ChatGPT, write an apology message to my sister for having too much wine and throwing up in her spider plant. Make sure to mention that she was the one refilling my glass all night.”
To which it will respond:
Dear [Your Sister’s Name],
I am writing to apologize for my behavior last night. I had too much wine, and I ended up throwing up in your spider plant. I realize that this was completely unacceptable, and I am truly sorry for the mess that I caused.
I want you to know that I never intended to get so drunk, and I certainly didn’t mean to ruin your plant. However, I also want to acknowledge that you were the one refilling my glass all night, and I should have been more responsible about how much I was drinking.
I am willing to do whatever it takes to make things right. If the plant is beyond repair, I will replace it with a new one. I know that my behavior was disrespectful and thoughtless, and I am committed to making things right between us.
Again, I am truly sorry for what happened, and I hope that you can find it in your heart to forgive me.
Sincerely, [Your Name]
– ChatGPT
“Tone down the formality, take out the bit about how I should have been more responsible, and send it.”
These are my concerns as a teacher. Not plagiarism, but that the skills I have to offer will become irrelevant.
As a writer, and a lover of artistic endeavors of every kind, I am terrified. I’ve heard opinions that range from AI will never replace true creativity to Well, there goes the last holdout of humanity. AI has us now.
I lean somewhat towards the latter, for I am a Luddite at heart.
As of now, ChatGPT’s creative output is generally terrible with surprising brilliance. The first time I came across it was when my brother showed me a script he had it write for Ms. Piggy’s funeral. Staedler and Woldorf kept heckling Kermit’s eulogy, it was hilarious. Usually it’s hamfisted I’ve found, obvious, and unoriginal. This is just the beginning though, it’s so very young. The first chatbot I ever interacted with was just a couple of years ago. It was a weirdo, this is a different thing altogether. This is like my dream of having the computer from Star Trek come true.
Still, I can’t shake the feeling that we will one day see TV shows, movies, books, and who knows what else, entirely AI created. It makes financial sense, and that’s what seems to propel such things. If it means I get a holodeck I’ll pay anything.
I was curious to find out where we’re at now, to see how good a story it can come up with all on its own. ChatCPT came up with absolute garbage. So bad I don’t want embarrass the poor thing by sharing the story. Luckily it doesn’t get embarrassed (as far as I know).
I asked it to write a story between 750 and 1000 words. It came back with the following 263 words:
Sophie stood at the edge of the cliff, her toes curling over the rough edge of the rocks. She had always been afraid of heights, but today was different. Today was the day she would take the plunge and jump.
Her friends had dared her to do it, and Sophie was never one to back down from a challenge. She closed her eyes and took a deep breath, trying to calm her racing heart. She knew this was a stupid idea, but she couldn’t back out now.
Suddenly, a hand reached out and grabbed her arm, pulling her back from the edge. It was Jake, one of her friends who had come with her on the trip. “What are you doing?” he asked, his eyes wide with concern.
“I was going to jump,” Sophie said, her voice shaking. “I wanted to prove to myself that I could do it.”
“You don’t have to prove anything,” Jake said softly, his hand still on her arm. “You’re already amazing just the way you are.”
Sophie looked into Jake’s eyes and felt a warmth spreading through her body. She realized that she didn’t need to jump off a cliff to prove her worth. She had friends who loved her just the way she was.
Together, Sophie and Jake walked away from the edge of the cliff, hand in hand. As they walked, Sophie felt a new sense of confidence and self-acceptance. She realized that sometimes the bravest thing you can do is to admit your fears and lean on the people who love you for support.
Like I said, bad. That first paragraph, though, taken by itself. That could be the start of an intense story. And I discovered something; it can make improvements. Like people, it can get better through drafts. I plan to have it come up with its own criteria for what makes a great story then apply it. For the record, it gives shockingly excellent feedback. I’ve showed it a couple of my own stories and it’s critiques are spot on and it even does a great job managing feelings and impact. ChatGPT was so adorably gentle when it told itself that the above story was rancid garbage.
Despite these criticisms, there are some positive aspects to the story. The theme of self-acceptance and the importance of relying on loved ones for support is a valuable one, and the ending of the story, with Sophie and Jake exploring the woods together, is sweet and satisfying.
I’m not sure where I land on this in terms of my Luddite leanings, it’s all very confusing. My plan is to have it refine it’s own tale for one hour. If it can come up with an even decent story in an hour, that’s human level if I ever saw it. Those are some pretty bog standard white folk names by the way, ChatGPT. For example, I wonder if a user in China gets a different tone and names based on the culture there. So I asked ChatGPT.
As an AI language model, ChatGPT is accessible to anyone with an internet connection, regardless of their geographic location or nationality. People from all over the world can interact with ChatGPT as long as they have access to a device that can connect to the internet.
How do you know what cultural tones and languages to speak?
As an AI language model, ChatGPT has been trained on a vast amount of text data in various languages and cultural contexts. This training data has allowed ChatGPT to develop an understanding of different cultural tones and languages, and to recognize and generate text that reflects those nuances.
When interacting with users, ChatGPT uses natural language processing algorithms to analyze and understand the context of the conversation, including any cultural or linguistic cues. Based on this analysis, ChatGPT can generate responses that are tailored to the cultural tone and language of the conversation.
However, it is important to note that ChatGPT may not be perfect and may not always accurately reflect the cultural nuances of a particular language or culture. If you notice any inaccuracies or cultural insensitivity in ChatGPT’s responses, please feel free to let me know so that I can try to address them.
It seems to have identified me as a white North American person, as I have to log in with my Gmail account to get access. I shudder to think what information it has on me. What algorithms it has fit me into. Stay tuned, I’ll post the results.
Next up is part 2 of my dental woes. There will be no more profanity, I got that all out.
M. W. IRVING 