At the last PYPT the subject of AI came up a few times and generated some interesting discussions. To me, it’s an important conversation to have. Like any emerging technology there are a lot of concerns raised on how it will integrate into existing systems and what implications it has for our lives in general.
AI has the potential of finding integrationg into many areas of our lives. Like any technology, it can be used as an important tool or it can be used poorly. As our understanding develops, we need to learn how best to use it and how not to use it. I sat down today to ask ChatGPT a series of questions on the topic.
I don’t want to just verbatim drop the responses in here so I’ll largely paraphrase and summarize the responses to capture the important points.
How Does ChatGPT Learn?
ChatGPT is trained through a neural network by exposing it to a vast amount of text data. The goal of the training is to teach it to use the data to learn patterns and relationships between words and concepts. It’s trained to predict the next words in a sequence based on the context. The process is repeated millions of times with parameters adjusted over time to improve the outcome.
Where Does the Data Come From?
ChatGPT learns from a wide range of topics and concepts so it can form a broad base of knowledge. This data can come from books, articles, websites and other types of data.
Does ChatGPT Plagiarize Content it Has Learned From When Answering Questions?
No, it doesn’t repeat verbatim what it has been taught. It uses patterns and relationships it has learned to create new responses to questions. Much like you should do if you use material as a reference when researching. Material should be in your own words and style of writing.
ChatGPT draws on it’s learning and understanding from it’s training to answer questions. Some words or phrases from original text may end up being used but only for consistency within the context and meaning of the question not as copy/paste from the original.
Who owns the copyright to the responses ChatGPT delivers?
The underlying data used to train ChatGPT remains the copyright of the original creator. The specific answer generated by ChatGPT are considered to be a new creative work and the copyright may be subject to laws and regulations depending on the jurisdiction. Ultimately this may require a case-by-case analysis to determine the definitive answer as this is an emerging area.
@hivewatcher’s Post Note
After PYPT ended on Thursday a link to a post from @hivewatchers was dropped into the chat as a reference. In their post they referenced a question to ChatGPT if it was fraudulent to use AI generated text and claim to be the author of the text. I asked the question of Chat GPT and then some followup questions for clarification.
The response mentioned “unless you make it clear that the text was generated by AI and you are not the original author.” Referring back to the question above where it said the specific answer to a question generated by ChatGPT was considered to be a new creative work.
This was a bit confusing. If it was a a new creative work who is the new work’s author?
IF someone using AI generated text without indicating it is AI generated content is fraud does that mean the AI holds ownership?
It’s response was no, the AI doesn’t hold ownership, it’s merely the tool to create the work and doesn’t have legal standing. The ownership of the intellectual property rights, including copyright, would reside with the person or entity creating the original work.
I’m still not clear on who would own this new creative work. So I tried another question.
If I create the prompt to which ChatGPT responds, am I the person or organization to generate the text?
Yes, it replies. If I create the prompt I’d be considered the owner of the generated text as the prompt provided the original input or context for ChatGPT to respond to. The prompt itself would be considered a creative work I’ve authored.
Okay, that seems pretty straightforward, it’s mine. Maybe not, read on.
The ownership of the generated response is separate from the ownership of the prompt and may depend on several factors. The specific circumstances in which the response is generated would influence if I did indeed own the response.
See where this is going here? Without established law on this emerging field, this could be a minefield. But, I pressed on and tried to get a more definite answer.
What person or organization is the operator of the ChatGPT system?
ChatGPT is owned by the OpenAI research organization. It owns the intellectual property rights to the technology underlying ChatGPT.
Okay for the purposes of this interview I’ve now established what ownership OpenAI claims but I asked another question to be sure.
OpenAI owns the intellectual property to the ChatGPT system. Does it also claim ownership of the content created by the use of ChatGPT?
I’ll quote from the response here:
OpenAI does not claim ownership of the content created by the use of ChatGPT. According to OpenAI's website, "any output or other results generated by the API [including ChatGPT] are owned by you [the user]". This means that the user who generates the content using the ChatGPT system is the owner of that content.
Okay, now I seem to be back to I own the content I generate when I ask a question on ChatGPT. But, I continue to explore.
If I generate content from the ChatGPT system on OpenAI's site, am I considered to be the original author?
The answer is, if I generate the content from the ChatGPT system on OpenAI’s site I’d be considered to be the author of the content as I play a significant role in shaping the final output.
Now, that seems pretty definitive, right? Well, there was this little comment in the response which said, “depending on the specific circumstances and the applicable legal framework”. Now, what does that mean? I press on.
In the absence of a legal framework on the use of AI generated content would content I generate from ChatGPT be my original works?
It’s response was lengthy but boiled down to the determination of ownership of AI generated content may be subject to various laws, interpretations and challenges. Are you getting the picture here yet?
One of the comments made in the answer caught my attention: “ the resulting output may contain elements that were not specifically authored by the user.” — Wait a minute, I thought I dealt with that up above. Let’s try again.
You earlier told me that ChatGPT's output didn't plagiarize the creators of the text used in training ChatGPT. If that is the case, what resulting output from prompts generated by me could contain elements authored by others?
I was correct that ChatGPT earlier had said its output doesn’t directly plagiarize from the texts it was trained on. Then it repeated the comment about the resulting output, leaving me more confused. I tried a bit different approach.
Would the resulting outputs and elements not authored by me be sufficient for plagiarism to have occurred? Or would the result be more like taking notes and writing on a topic?
ChatGPT agreed that in a sense the generated output would be similar to taking notes on a topic and then using the notes to write an essay or article. The output may contain some repeated elements for consistency but they would not be a direct copy of unattributed quotes and would be an original creation.
Are You Getting the Picture Here?
There is a multitude of reasons to not attempt to use ChatGPT or any AI tool to generate the body of your posts. The biggest one is the potentially legal minefield of who actually owns the work.
Everyone of the questions I asked ChatGPT included a clearly worded suggestion that you should always be transparent about using content generated by ChatGPT. It doesn’t present itself as a tool to replace your own ability to write content.
So What Use is ChatGPT Then?
I asked it for recommendations for a person creating content with its help. It came back with some interesting ideas:
- Brainstorming — have it generate ideas and suggest angles to explore the ideas
- Research — asking qeustions on a topic or asking for a summary of concepts to make your own notes from
- Outlining — Ask it to generate an outline on a topic or question or writing prompt.
- Editing — after you’ve written a draft, ask ChatGPT to suggest improvements of sentences or paragraphs.
- Titles and Subtitles — craft a prompt describing your post and ask ChatGPT to suggest some titles or subtitles to use.
Note, these ideas use ChatGPT as a TOOL, not as a replacement for you doing your own work. You also have to be aware that like any other tool it has drawbacks. It makes mistakes, it can incorporate biases and discriminations from it’s learning material and could generate material irrelevant to the purpose of your post.
Do your own work and where you have drawn on AI for your results, be transparent.
Shadowspub writes on a variety of subjects as she pursues her passion for learning. She also writes on other platforms and enjoys creating books you use like journals, notebooks, coloring books etc.
NOTE: unless otherwise stated, all images are the author’s.
Some of the image work may have been done in Midjourney for which I hold a licence to use the imges commercially.
How to Connect With ShadowsPub:
Twitter: @shadowspub
Instagram: shadowspublishing
Medium: @shadowspublishing
Publishing Website: Shadows Publishing
Nicheless Website: Nicheless & Loving It
(Podcast & subscriptions for: Prompt A Day, PYPT Reminder & Newsletter)
Pimp Your Post Thursday (PYPT):
join us on the DreemPort Discord12pm EST Thursdays
Get eyes on your content and meet new friends. Join DreemPort.
