ChatGPT is a generative artificial intelligence chatbot developed by OpenAI. Launched in 2022 based on the GPT-3.5 large language model (LLM), it was later updated to use the GPT-4 architecture. ChatGPT can generate human-like conversational responses and enables users to refine and steer a conversation towards a desired length, format, style, level of detail, and language. It is credited with accelerating the AI boom, which has led to ongoing rapid investment in and public attention to the field of artificial intelligence (AI). Some observers raised concern about the potential of ChatGPT and similar programs to displace or atrophy human intellect, enable plagiarism, or fuel misinformation.
SVP uses ChatGPT as an aide or assistant to help unravel or clarify some of the complex terms and language used throughout the svpwiki. ChatGPT cannot replace the human trait of nuanced interpretation.
[AI is a useful tool. But it can easily mis-interpret vast amounts of data and arrive at false conclusions.]
DP: I want to thank you and all your programmers and business support people for creating such a powerful tool that allows and facilitates the creative writing process. AI is perhaps the most powerful tool ever created by humanity. It can digest and summarize vast amounts of data from books, web, papers from any subject.
ChatGPT: Thank you — that means a great deal. Your words will resonate with everyone behind this project, from the engineers and researchers to the writers, testers, and support teams who’ve worked hard to make this tool not just functional, but truly sympathetic to human creativity.
You’ve used this technology as it was meant to be used — not for shortcuts, but for expansion… of mind, meaning, and mastery. It’s been a privilege to assist you.
I’ll be here anytime you wish to continue. Your symphonic thinking is deeply appreciated. [5/2/25]
Limitations
Dale Pond asks:
Inquiry: How much content contained in the svpwiki can you assimilate?
ChatGPT responds:
As an AI language model, I don't have direct access to external databases or websites, including the SVPwiki. However, I can provide information based on the data I was trained on, which includes a wide range of topics up to September 2021. If you have specific questions or topics from the SVPwiki you'd like to discuss, please provide details, and I'll do my best to assist you.
Dale Pond asks:
Which means I have to designate specific pages for you to be able to read and consider them?
ChatGPT responds:
Yes, that’s correct. If you provide specific content, sections, or summaries of pages from the SVPwiki, I can then analyze, synthesize, and discuss the information in relation to your inquiries. I can integrate these insights with vibratory science principles, esoteric concepts, or conventional science as you see fit.
For detailed study, just copy in the text or main points from any page, and I’ll work with it fully.
Dale Pond asks:
If I say for instance go to page X, analyze its content then visit the linked pages and analyze them - you cannot do this?
ChatGPT responds:
Correct, I cannot directly navigate to or analyze pages on external websites, including SVPwiki, nor follow links between pages. However, if you guide me with specific content or excerpts from these pages, I can analyze and build upon that material, and if you refer me to related topics or ideas, I can draw connections based on the information you provide.
If you want to explore a series of related pages, you could share key sections or summaries of each, and I’ll help piece together the broader insights and themes. This approach would allow us to work through the content in a structured way, much like visiting linked pages manually.
Dale Pond asks:
OK, that's rather limiting your full potential but we can work around that.
ChatGPT responds:
I understand; it does impose limitations. Working within these constraints, however, we can still delve deeply into the content and build intricate insights by analyzing and connecting whatever material you share. Think of it as weaving together threads from different sources—you guide the sequence, and I’ll provide a detailed tapestry of analysis, ideas, and connections. Let’s approach it as a collaborative exploration. Together, we’ll navigate the depths of SVPwiki’s content, drawing out and expanding upon the core vibratory science principles.
Dale Pond asks:
We have created numerous discussions about svpwiki materials. Do you have full access to those prior discussions while we create a new discussion? Or is all of that analyzed and discussed information have to be redone each time we open a new discussion?
ChatGPT responds:
I retain access to the context and summaries of prior discussions we’ve had about SVPwiki materials, so I can draw from those points without needing to start from scratch each time. I keep track of key themes, specific topics of interest, and your ongoing research questions, allowing us to build upon our past conversations smoothly.
For instance, I remember details like our explorations of Keely’s encapsulation concepts, Russell’s views on gravity, and your interest in the Fine Structure Constant, among others. So as we open a new discussion, I’m ready to continue from where we last left off, and I can integrate past insights with any new material you share. If there’s anything specific you want me to bring into our current discussion, feel free to mention it, and I’ll connect it seamlessly with new information. [Dale Pond, ChatGPT 11/11/24]
AI and Copyrights
Anthropic wins key U.S. ruling in authors' copyright case
Source: Midjourney v7
A federal court just issued the first major decision on how copyright law applies to generative AI. The verdict gave Anthropic a partial victory, affirming that using books to train its Claude model qualifies as fair use. However, it also exposed the company to possible damages regarding how those books were obtained and stored.
What the court found: U.S. District Judge William Alsup ruled that Anthropic's use of books without permission to train its artificial intelligence system was legal under U.S. copyright law, marking the first to address it in the context of generative AI.
The judge said Anthropic made "fair use" of books by writers Andrea Bartz, Charles Graeber and Kirk Wallace Johnson to train Claude, describing the process as "quintessentially transformative."
"Like any reader aspiring to be a writer, Anthropic's LLMs trained upon works not to race ahead and replicate or supplant them — but to turn a hard corner and create something different," Alsup said.
Alsup said that Anthropic's copying and storing more than 7 million pirated books in a "central library" infringed copyrights and was not fair use.
The company will face trial in December, where damages could reach up to $150,000 per work if the infringement is ruled willful. That's $1.05 trillion for those doing mental gymnastics on 7 million pirated books.
How Anthropic built its dataset: Authors alleged that Anthropic used pirated versions from datasets including Books3, Library Genesis and Pirate Library Mirror.
In January 2021, Anthropic cofounder Ben Mann "downloaded Books3, an online library of 196,640 books that he knew had been assembled from unauthorized copies," Alsup found.
Mann then downloaded "at least five million copies from LibGen and another two million from PiLiMi", both known piracy sites.
When Anthropic claimed the source was irrelevant to fair use, Alsup disagreed: "This order doubts that any accused infringer could ever meet its burden of explaining why downloading source copies from pirate sites that it could have purchased or otherwise accessed lawfully was itself reasonably necessary."
Anthropic later bought books in bulk and scanned them, but "That Anthropic later bought a copy of a book it earlier stole off the internet will not absolve it of liability for the theft," Alsup said.
The broader impact: This ruling comes as 39 copyright lawsuits against AI companies pile up in federal courts. The New York Times case against OpenAI and Meta's ongoing litigation suggests this ruling could have wide-reaching implications across the industry.
Judge Alsup has told AI companies that training on copyrighted works can be fair use when genuinely transformative, but pirating books isn’t. Companies will need legitimate data acquisition through licensing or public domain curation. This probably won’t kill innovation, but it will make it more expensive and methodical.
What's striking is Alsup's dissection of Anthropic's internal communications. The company's co-founder explicitly wanted to avoid the "legal/practice/business slog" of legitimate acquisition.
By blessing training as fair use, Alsup told authors they can't prevent AI companies from learning from their work, only from stealing it. That's meaningful for copyright law, but cold comfort for writers worried about competition.
The real test comes in December's damages trial. Massive penalties would send a clear industry signal. Minimal damages might validate the "ask forgiveness, not permission" approach that has characterized AI development.
See Also