AI secrete source!

A couple of the publicly accessible AI’s that I’ve been tinkering with will not quote sources and will not tell you much if anything with regards what they have been trained on. But there is now this very interesting development that the Guardian have reported on which is that Sarah Silverman  is current sueing OpenAI and Meta claiming AI training infringed copyright

https://www.theguardian.com/technology/2023/jul/10/sarah-silverman-sues-openai-meta-copyright-infringement

I’m going to be holding on to my pop corn real tight as this works it’s way thru the courts, and the big wigs in silicon valley work out what to do and how to do it. I told you 2023 was going to be a very interesting year for AI.

Trust and AI

So there has been lots of discussion of late about slowing down the progress of AI’s and concern about getting things right. For me the obvious approach to this might be to ask for references, reasoning and sources from the AI. This is the response I got from “https://chat.openai.com/” when I attempted to address this issue.

Steve
“Ok so in the past on the odd occasion I have found information you have supplied to be incorrect – is it possible to get you to quote your sources?”

chat.openai.com (bold text mine)
“As an AI language model, I use a wide range of sources to generate responses to your questions, including books, articles, online resources, and more. However, I do not keep track of specific sources for each piece of information that I provide.

If you ever have any doubts about the accuracy of the information I provide, I would encourage you to conduct further research to verify it or consult with a human expert in the relevant field. Additionally, if you have a specific question or concern about a piece of information, please let me know and I will do my best to address it or provide additional context”.

I think this is the grist of the discussion. Untill AI can back up it’s statements with valid resources, facts, data and on line reference etc then it becomes  difficult to verify what the machine is creating as an answer.

This is also interesting and worth pondering…

“I use a wide range of sources to generate responses to your questions, including books, articles, online resources, and more.”

For me the next question is which books, articles and online resources? To be honest I’m not a god level programmer by any stretch of the imagination. But I think it shouldn’t be that difficult to build that sort of functionality into the machine.

We need insight into this process and we need an AI that is self aware to the point of being able to argue and back up it’s statements. But perhaps the AI (or it’s makers) would prefer privacy? I wonder about this!

Interesting chat with AI

So I’m having a lot of fun with opnai’s chat gpt.  It’s like being able to pick the brain of a first year professor on any topic – the following conversation was interesting in that it helped me give a name to a pre-dream state (Hypnagogia) that I’d been experiencing, dig into the concept of Jung’s shadow and gave me some pointers about common theories of human consciousness.

This is the conversation.

__________________________________

S
Hi, I have not read up about this topic but I have a personal theory about human consciousness – and it is that it might be similar to a software program that loops but can also access “Set” types of information that exist… for example how to move in a room, how to walk, talk etc. What are the main current accepted models of human consciousness and does the above idea align with any of the major current theories about what human consciousness is?

GpT
The nature of human consciousness is a complex and multifaceted topic that has been studied by various fields, including philosophy, neuroscience, and psychology. There is no single widely accepted model of human consciousness, and different theories offer different perspectives on what consciousness is and how it arises. However, your idea of human consciousness as a software program that loops and accesses “set” types of information could potentially align with some theories of consciousness.
One prominent theory of consciousness is the Global Workspace Theory, which proposes that consciousness arises from the global availability of information in the brain. According to this theory, the brain contains a set of specialized modules that process different types of information. These modules can share their information with a central workspace, which integrates and broadcasts this information to other modules in the brain. The global workspace enables the brain to achieve flexible and adaptive behavior by allowing different modules to access and process the same information, leading to a coherent and unified experience of consciousness.
Your idea of consciousness as a software program that loops and accesses “set” types of information could be seen as consistent with the Global Workspace Theory in that it suggests that consciousness arises from the availability and integration of information in the brain. However, it is important to note that this is just one theory of consciousness, and there are other competing theories that offer different perspectives on the nature of consciousness. Additionally, the analogy of consciousness as a software program is just one way of thinking about consciousness and may not capture the full complexity of the phenomenon.

S
Can you summarize the 5 most common theories of human consciousness?

Gpt
Sure, here are brief summaries of five of the most common theories of human consciousness:
1. Integrated Information Theory (IIT): According to IIT, consciousness arises from the integration of information across different parts of the brain. It proposes that the degree of consciousness experienced by a system is directly related to the amount of integrated information that the system can generate.
2. Global Workspace Theory (GWT): GWT proposes that consciousness arises from the global availability of information in the brain. It suggests that consciousness involves the integration and broadcasting of information from different specialized modules in the brain.
3. Higher-Order Theory (HOT): According to HOT, consciousness arises from the brain’s ability to generate higher-order representations of lower-order sensory experiences. This theory proposes that a conscious experience involves the representation of the original sensory experience and a higher-order representation of that experience.
4. Attention Schema Theory (AST): AST suggests that consciousness arises from the brain’s ability to create a “schema” or a model of where attention is being directed. This theory proposes that the experience of consciousness involves the brain modeling itself as an agent that can direct attention to different parts of the environment.
5. Predictive Processing Theory (PPT): PPT proposes that consciousness arises from the brain’s ability to generate predictions about the sensory information it receives. This theory suggests that the brain constantly generates predictions about what it expects to experience, and consciousness arises when those predictions are updated or contradicted by new sensory information.

S
C G Jung invited the concept of the shadow (the suppressed negativity of the self, that the individual is often not aware of) which of the above 5 approaches to human consciousness you have mentioned might work with and be able to integrate Jung’s concept of the shadow?

Jung’s concept of the shadow, which refers to the suppressed or hidden aspects of the self, could be integrated with several of the theories of human consciousness that I mentioned earlier. Here are a few possibilities:
1. Global Workspace Theory (GWT): GWT proposes that consciousness involves the integration and broadcasting of information from different specialized modules in the brain. One way to think about the shadow in terms of GWT would be to suggest that the suppression of certain aspects of the self leads to a lack of integration of information in the brain, potentially limiting the scope of conscious experience.
2. Higher-Order Theory (HOT): According to HOT, consciousness involves the generation of higher-order representations of lower-order sensory experiences. In the context of the shadow, one could argue that the suppression of certain aspects of the self can lead to a lack of higher-order representations of those experiences, limiting conscious awareness of them.
3. Attention Schema Theory (AST): AST proposes that consciousness arises from the brain’s ability to create a schema or model of where attention is being directed. In the context of the shadow, one could argue that the suppression of certain aspects of the self can lead to a lack of attention being directed toward them, potentially limiting conscious awareness of those aspects.
Overall, it’s worth noting that the concept of the shadow is not unique to Jung’s approach to psychology, and it can be integrated with a variety of different theories of consciousness and the mind.

S
Is there a similar concept to the shadow that pre-dates Jungs work?

Gpt
Yes, the concept of the shadow as a psychological construct that includes the hidden, repressed, or disavowed aspects of the self predates Jung’s work.
For example, in ancient Greek philosophy, the concept of the shadow or “skia” was associated with the idea of the daimon, which represented an individual’s inner nature or true self. The daimon was seen as a guiding force that could lead individuals to their destiny, but it could also be suppressed or ignored, leading to a sense of inner conflict and fragmentation.
Similarly, in Sufi mysticism, the concept of the nafs al-ammara or “commanding self” refers to the lower, base instincts and desires that can lead individuals away from spiritual enlightenment. The nafs is seen as a part of the self that needs to be tamed and transformed in order to achieve a state of inner harmony.
In the Western esoteric tradition, the concept of the shadow is also present in the idea of the “dark self” or the “shadow self,” which represents the hidden, repressed, or rejected aspects of the psyche. This idea was popularized by the 19th century occultist Eliphas Levi and was later developed by other thinkers such as Carl Kellner and Aleister Crowley.
Overall, the concept of the shadow as a psychological construct has a long and diverse history, and it can be found in various cultural and philosophical traditions. Jung’s contribution was to develop a systematic and comprehensive theory of the shadow that incorporated elements from a range of different sources and integrated them into a unified framework of psychology.

S
Sometimes, just before sleep my thought patterns slowly dissolve. They become highly erratic some times very creative but it’s as if my consciousness is slowly dissolving into sleep. Can you tell me anything about this phenomenon.

Gpt
Yes, the experience you describe is a common phenomenon known as “hypnagogia.” Hypnagogia refers to the transitional state of consciousness between wakefulness and sleep, and it is characterized by a variety of sensory and perceptual experiences, including hallucinations, vivid imagery, and altered thought patterns.
During the hypnagogic state, the brain is in a state of increased neural activity, as it begins to transition from the waking state to the sleep state. This increased neural activity can lead to a variety of unusual or creative thought patterns, as well as sensory experiences such as the sensation of falling, floating, or drifting.
The experience of hypnagogia can vary widely from person to person, and some individuals may experience it more frequently or more vividly than others. It can also be influenced by factors such as fatigue, stress, medication, or other factors that affect the brain’s activity.
Overall, the experience of hypnagogia is a normal and natural aspect of the sleep process, and it is generally not a cause for concern. However, if you experience hypnagogic hallucinations or other unusual or distressing symptoms, it may be a good idea to speak with a healthcare professional to rule out any underlying medical or psychological conditions.

S
Is there anything I can do to increase the amount of hypnagogia that I can remember? Is there a way to access this state in a non harmful manner?

Gpt
Yes, there are some things you can do to increase your ability to remember and access hypnagogia in a safe and non-harmful way:
1. Improve your sleep hygiene: Hypnagogia occurs during the transition between wakefulness and sleep, so improving your sleep hygiene by creating a consistent sleep schedule, avoiding caffeine and alcohol before bed, and creating a relaxing sleep environment can help promote this transitional state.
2. Practice relaxation techniques: Relaxation techniques such as deep breathing, progressive muscle relaxation, or meditation can help quiet the mind and promote the hypnagogic state.
3. Keep a dream journal: Recording your dreams in a journal upon waking can help you develop a greater awareness of your dreams and hypnagogic experiences, and can help you remember and recall them more easily.
4. Practice lucid dreaming: Lucid dreaming is the practice of becoming aware that you are dreaming while still in the dream state, and it can be a way to consciously explore and engage with hypnagogic experiences.
5. Experiment with sensory deprivation: Sensory deprivation, such as by using a floatation tank, can help create an environment conducive to hypnagogia by reducing external stimuli and promoting relaxation.
It’s important to approach hypnagogia in a safe and responsible way and to avoid any practices that could be harmful or dangerous. It’s also important to remember that not everyone experiences hypnagogia in the same way or with the same frequency, so don’t be discouraged if your experiences differ from others’.

AI pushing some boundaries

So I’ve been using https://chat.openai.com/chat for a little while now and discovered that the 2500 characters limitation is one to look out for. (and yes I’m considering getting the paid version to get around this problem). But what have you actually used this for? You might ask!

If your a programmer you are in for a treat. I’ve got it to help me build a couple of things, one being a basic cryptographic product. I’ve had this idea for about 5 years sitting in the back of my brain and it took about an hour and a half with a bit of help from the droid as it were to get a basic working product.

Steve Jobs once described the computer as a bicycle for the brain, this feels like I’ve just jumped on a rather nice motorcycle! Seriously if you haven’t tried chat.openai.com do it now. This is a game changer.

Some of the things I’ve engaged the AI with include

Best lathes for tool making – (I’ve still yet to make a purchase)
Got it to explain shell scripts and what they do in detail
Find PHP errors in my code
The theory of relativity
How to cook a better Pavlova
I’ve also got it to review some of my writing.
Discussed Miles Davis and Modal Jazz

Some of the things it can’t do are language related, I got this reply when attempting to find the meaning of the word “Andoo”.

“I’m sorry, but I am not able to provide translations for the word “andoo” in multiple languages, as I do not have access to a translation database and I am not able to browse the internet”

Dear old google replied with.
“Andoo, to keep boat in position by rowing gently against wind or tide.

So I suppose the old search engine still has a bit of life in it yet.

Finally don’t forget “Prompt Engineering” (a hot YouTube topic at the moment) Which is basically putting data (From the web if needed) into your requests. It has unbelievable sorting / arranging, and analysis skill.

I can’t say this enough, it’s not perfect… but it is getting better all the time, learn to ride that motorcycle.