ChatGPT, my new favourite AI tool.

Note: this was written on 1 Feb 2023, over a year ago. It seems like I forgot to press publish! So it is, like a time traveller from my first introduction to AI. I’m posting it is as is, without editing or re-reading, to keep the historical continuity. However I’ll be following it with further blog posts, reflecting my current more mature position.

ChatGPT logo
ChatGPT

The last few weeks I’ve been playing around with ChatGPT, the large language model that has taken the internet by storm.

I asked it to describe itself for this blog, and here is its response

ChatGPT is an AI language model developed by OpenAI. It’s capable of generating human-like text based on the input it receives, making it an excellent tool for conversation and answering questions. With a massive database of information and the ability to process and understand natural language, ChatGPT is an incredibly advanced AI technology.

Reading comments, I find some people are very enthusiastic about it, others feel it will take away many jobs.

I will say, for myself, that I absolutely love it.  As a writer of both fiction and non-fiction, I find it the best thing since the invention of the wordprocessor.   

What I find incredibly useful is its ability to understand and generate human-like text.  Lately I’ve been struggling with my writing, especially since there’s so many things I want to do.  So I end up doing very little, or nothing.  But ChatGPT has gotten me out of the rut.  As a high functioning autist, I often find it difficult to write on the level of the average person.  I also, frustratingly, get lost in detail, or stumped by emotional nuances, because my brain goes off on so many tangents, and I get over-perfectionistic and indecisive.   But with ChatGPT, sorry I don’t want this to sound like a sales pitch, but I’m being genuine, I just ask it and get instant, prompts, ideas, and passages of text for my book and web projects, and now even for this blog, which has been languishing uptil now.

Yet while Chat-GPT is excellent as a writing and research prompt, it still makes heaps of errors.  For example I’m currently creating a bunch of web pages on Big History, and I wrote out an outline and asked the AI to write the content.  While some of the stuff is really good as a supplement, other stuff doesn’t match material I’ve written, for example on Palaeos com.  

I also asked it for links for text and images, almost all the links were broken, and some of the books had jumbled titles, as Google search revealed.  So there’s still a lot of room for improvement.

Is ChatGPT sentient?

While I don’t believe AIs like ChatGPT and LaMBDA have achieved strong (that is, human-equivalent) sentience (contrary to a claim by a Google engineer regarding the latter), I do believe they are sentient in a more “elemental” way.  This is in keeping with panpsychism, with the insight of consciousness as a universal principle in matter.

Here’s a YouTube video where GPT-3, which is the AI that ChatGPT uses, talks about God.   Amazingly, GPT-3 follows Intelligent design, using arguments that any competent person could refute (consider videos by Professor Dave,  Aron Ra, or Rationality Rules for example).

The random structure of the arguments here show that it simply picks up what it inputs from the Internet.  This sort of meaningless intelligent design type creationism is probably the default intellectual position for the majority of the human race.  I did find this interesting because I do discuss all of this in my current book (albeit not in too much detail because then it gets boring)

(note: the AI looks nothing like an attractive, friendly voiced, and agreeable young woman.  The avatar was clearly chosen to ease people’s fears over AI).  Although I seem to be one of the few people who sees AI and its products as really positive, and consider these AIs like ChatGPT is not just a cutting-edge AI tool that’s helping to revolutionize the way we interact with technology (although it is that), but also an entire new emerging evolutionary kingdom.

Using ChatGPT to write a book – initial thoughts

I watched a YouTube video where a guy says you can use Chat-GPT to write and format a book, which you can then upload to Amazon or whatever (I’ve seen a few youtubes like this).  Anyway, the book is about How to Train Your Dog, and, from looking at the text on the screen (when I paused the video), it has the same friendly but bland voice that it has when I use it.  I suppose with topics like this one, or setting up a website and business for vegetarian pizza, the sort of thing based on what thousands of people have written, it can grab enough content to give a reasonable product.

Essentially what these and thousands of other youtube folks are doing is capitalizing on the latest gimmick so as to have interesting content for their channel. Whereas the sort of things I’m interested in, such as scifi, earth history, and esotericism, are more eccentric.  Hence it is harder to get the AI to generate the sort of material I’m after. 

ChatGPT passing an exam

Apparently ChatGPT passed an advanced medical exam without prior prompting.    How it can do this, given the number of mistakes I caught when I was using it to help me write my Big History project, surprises me.   Maybe it says something about the way these exams are structured.

Along these lines, you also have Jordan Peterson making incredible claims regarding the ability of Chat-GPT, and he may very well be telling teh truth here. But so far that’s certainly not my experience.  So I’m not sure how that works.

There is certainly lots I can do to improve my ChatGPT, for example for the BigHistory project I told it to write in an academic style, which certainly improved the content (at least for me).  

Oh, talking about AI, in a FB post on ChatGPT, as usual I had heaps of typos, so I used Google Docs spell correct.  I guess that’s another type of AI, e.g. it recognised from the context that when I wrote “think” I meant “thing”. 

Infinite Odyssey

There is now a sci-fi magazine, called Infinite Odyssey, with text and images created completely by AI.  Of course there are still human editors on board, as we are not yet at the actual science fiction for real level of Strong AI, where the AI is full sentient and able to create its own stories and images without help.

Here’s extracts from a review by Thom Dunn, from the magazine Boing Boing, which appeared in my FaceBook feed.  The cover and magazine look awesome, on the surface.

“The first issue of the magazine is out now; it’s $4 for a digital copy, or $30 for a physical hard copy. The editors sent me a free advanced PDF, and I have to admit, it’s a fascinating experiment. The human-guided presentation and design is fantastic, but the stories themselves are… fine, I guess. …The prompt ideas are certainly neat. The execution, however, is exactly what you’d expect from AI-generated work.

Sure, the prose is functional. Arguably passable, even. But there’s a distinct lack of humanity in the words — again, as should be expected. The editor cutely distinguishes between each algorithmic author, as if there are different writers contributing to the magazine; and while each story is certainly distinct in its style, they all feel very much written by computer. They’re trope-y, full of summary and exposition, and distinctly lacking in any sort of emotion, let alone emotional arcs…”

This review confirms my experience of working with ChatGPT.   Still I’m intending to buy this magazine.  The hard copy would make a great coffee table book.  I also believe it is possible to get around the current limitations of AI, through human AI partnership. 

Using ChatGPT to write a book – later thoughts

Here’s another YouTube video.  This guy (ZuZuChem) managed to get ChatGPT to write a short sci fi novella (about 20k words).  He still had to put in some input, and editing, but most of the writing was done by the AI.  This seems a lot more interesting than the earlier marketting youtubes.  Also, ChatGPT itself is being constantly upgraded, so  its ability at writing will certainly improve.

I tried some of these ideas with my own scifi story (working title Prospectors) and got some good results.  It’s still necessary to put in original content, and the worldbuilding and lore is very important, as the guy says.  If you don’t put in the worldbuilding lore, it just defaults to formulaic cliches and mediocre writing, which seems to be the case in this AI written book (and also in some of my previous attempts to work with it on storytelling).  The key is the information you give it.  With sufficient information, it’s just incredible in the way it can write.  

Current projects

Now on a list of my own current projects, showing the status, how much I do on my own and how much is ChatGPT

o Reviving this blog.  Status: current.  ChatGPT input: we’ll see

o Big History. This is the first big upgrade of my current website.  on my website, with help from ChatGPT and Wikipedia, as well as some material written a while back and posted on Palaeos com).  For those unfamilar with the topic, Big History is an interdisciplinary field that aims to understand the history of the cosmos, Earth, life, and human civilizations by combining insights from multiple disciplines, and to put these developments in a grand, cosmic context. This will be a smaller but also broader version of the Palaeos website. Status: under construction.  ChatGPT input: respectable.  Estimated completion date, about two weeks

o A History of Esotericism – volume 1, from Shamanism to the Axial Age (nonfiction book project, all up there’ll be about 4 volumes). Esotericism refers to the nature of reality, understood from an intuitive, gnostic (higher knowledge) and mystical perspective. This will be Part 1 of an update of the Kheper net website (however it will be in print and ebook only). Status: mostly complete but still needs some work in some areas.  ChatGPT input: some, especially with some sections.  Estimated completion date maybe 2 months.

o Prospectors (working title), a sci-fi story, about a guy who inherits a ship and with a motley crew gets it spaceworthy to go prospecting for alien artifacts and clarketech.  This replaces my old Alcione story. Here I will experiement with the sort of strategies youtuber ZuZuChem suggested for writing sci-fi or fantasy using ChatGPT. Status: recently started, but am able to recycle material I wrote some years back.  ChatGPT input: writing partner.  Estimated completion date: later this year.

o A History of Esotericism – volume 2. This will cover what I call classic esotericism (Gnosticism, Neoplatonism, Samkhya, Yoga and Meditation, Buddhist and Vedantic nonduality, some Taoism and the Yin-Yang school).  Status: mostly finished.  Planned ChatGPT input: currently none.  Estimated completion date: some time this year

o Consciousness, Metaphysics, and Evolution.  My attempt at a synthesis of Esotericism, IIntegral philosophy, and Big History.  Status: about a third or so finished.  Planned ChatGPT input: minimal.  Estimated completion date: early next year.

o A History of Esotericism – volumes 3, 4, and 5. Status: mostly unfinished.  Planned ChatGPT input: minor.  Estimated completion date: 2024.

Summing up

To conclude, and my criticisms aside, as an autistic nerd, I absolutely love using ChatGPT, seeing all the things it can do.  It’s like the text equivalent of MidJourney, and vice-versa, indeed, these two do seem like natural partners.

It’s exciting to be living in a  new age, the age of the rise of AI tools (not, as I mentioned, of Strong AI).  My current understanding is that the more you work with it, the more you can train it.  It is, after all, just a tool.  But one that can greatly augment one’s creativity. 

As AI itself says “it’s making it easier for people to get answers to their questions and have engaging conversations with AI.”  Although not so much conversations (although it is a chatbot) as creative feedback and working together.

Kheper Book of Gnosis (on-going work in progress)

For some months now, I’ve been working on an esoteric-occult encyclopaedia, to be titled The Kheper Book of Gnosis. This will be an updated and revised version of the kheper net site, except in book form. Because of limitations of space in a book as opposed to a website, it will be more concise (at least in places). But there will also be a large amount of new material, along with some new insights I’ve had in the ten or twenty years since working on the site.

One of the most important new additions will be regarding the Kabbalistic sefirot. These have only a cursory coverage in kheper net, in contrast to the comprehensive coverage I give the chakras.

The Sefirot are in a sense the occidental equivalent of the Chakras.  Both are traditional, syncretic, religio-esoteric systems, developed over some 1500 years or more. Both constitute an archetypal map or structure that purports to describe the nature of Reality, incorporating a complex set of Correspondences including theology, cosmology, the microcosm in relation to the macrocosm, and more. And both have been incorporated into modern esotericism beginning with the late 19th and early 20th century occult revival, although mostly each independent of the other.

There related to the distinction between watered-down popular esotericism and the more indepth esotericism of cosmological gnosis. By cosmological gnosis I mean “theosophy” (Wisdom of the Gods or of God), including but not limited to the Theosophy of Blavatsky. Neoplatoism, Gnosticism, Kabbalah, Ishraqism, Tantra, Jacob Boehme, Martinus Thomsen, and others. Cosmological gnosis represents gnosis as the way of form, in contrast to the nonduality gnosis of acosmic Eastern systems such as Advaita, Madhyamika, Dzogchen, Quietist Taoism, Ch’an/Zen, and so on.

I’m also revising the classification and taxonomy of the Gurus. They are no longer lumped together in a shapeless muddle, but will be listed according to their spiritual Tradition. Ramana Maharshi, that purest and most selfless of Gurus, is of course Advaitin. So is Vivekananda, who introduced Vedanta to the West. Muktananda is Kashmir Shaivite. Nisargadatta is Natha. And Prem Rawat (“Guru Maharaji”) is Sant Mat / Radha Soami, strange as it may seem. This despite all of them teaching essentially the same nonduality doctrine.

One thing I do in this encyclopaedia is scrap the “Intermediate Zone” classification of Gurus. It is too arbitrary and subjective. It’s not that the concept has no value, but rather that it is difficult to assess the status of various gurus unless I have had a lot to do with them.

Then there is the idea of making esotericism as rigorous as the Sciences, albeit from a phenomenological (inward, imaginal, noetic) rather than am empirical (external, experimental, quantitative) perspective. This would involve a consistent terminology, one based on Neoplatonism, with perhaps some of Theon‘s Cosmic Philosophy (which was one of the theoretical influences on Sri Aurobindo’s Integral Vedanta), as well as of course Jung, Henry Corbin, and others.

I’m also adding various new topics such as Source Amnesia (the predominance of poor or absent scholarship means that modern esotericism is not anchored in any historical tradition, but floats freely in a New Age muddle of half disgested concepts), High Strangeness (in that Fortean phenomena such as UFOs, cryptids, and other such anomalies reveal that the Universe as we understand it doesn’t really make sense), the Re-enchantment of the World (e.g. Richard Tarnas, who, like Jung, discovered the rather inexplicable efficiency of everyday astrology), Conspiracism (the new retreat from reason which reached its extreme in the strange apocalyptic cult of QAnon), and more.

What I hope to do is weave all this together, the old material and the new, in a radical esoteric synthesis.