Saturday, June 03, 2023

I Think, Therefore I Am - Really?

In 1637, Descartes first published the famous words "I Think, Therefore I Am" in French in his Discourse on the Method and in the margins wrote that "we cannot doubt of our existence while we doubt.". As the Wikipedia explains in:

Cogito, ergo sum
https://en.wikipedia.org/wiki/Cogito,_ergo_sum

Descartes's statement became a fundamental element of Western philosophy, as it purported to provide a certain foundation for knowledge in the face of radical doubt. While other knowledge could be a figment of imagination, deception, or mistake, Descartes asserted that the very act of doubting one's own existence served—at minimum—as proof of the reality of one's own mind; there must be a thinking entity—in this case the self—for there to be a thought.

The above observation by Descartes is probably the best definition and understanding of consciousness and sentience that we may have but it also highlights some of the failings of our human obsession with the idea that being able to "think" is a supremely special ability that only ourselves and the Deities that we have created are capable of.

In the last dozen or so of my posts on softwarephysics, I have been exploring some of the dramatic recent impacts that we all have been experiencing with the rise of the second Singularity early in 2023. Again, the very first singularity on this planet was the rise of carbon-based life about four billion years ago that then went on to entirely change the surface of our planet. The second Singularity is the rise of ASI (Artificial Super Intelligence) on this planet that will most likely then go on to entirely change the future of our entire Milky Way galaxy over the next 100 trillion years until our galaxy can no longer provide the necessary free energy needed to run ASI Machines. But in this post, I would like to explore the very traumatic insults to human hubris that are rapidly unfolding as we finally become aware of the fact that being able to "think" as a sentient being is really not that big of a deal after all. With the recent rise of generative LLM (Large Language Models), we now know that being able to "think" only requires a huge number of nodes or "neurons" in an interconnected network that is interconnected by a large number of weighted connections. For example, most of the current LLMs that we are now dealing with consist of about 175 layers of neurons with each layer of neurons connected to the next layer by a vector of "weighted" connections. These LLMs can now contain about 175 billion neurons connected to each other by over 2 trillion weighted parameters. So these "digital" LLM brains are very much like the "analog" brains of neurons found in human brains. Always remember that our squishy "analog" human brains are also composed of about 100 billion neurons that are interconnected by 100 trillion weighted synaptic connections made of discrete "digital" numbers of organic molecules too.

Figure 1 – Modern LLMs frequently now consist of 175 layers of neurons in a Deep Neural Network consisting of about 175 billion neurons connected by over 2 trillion weighted parameters.

Anil Seth's View of Consciousness as a Controlled Hallucination
Descartes' observation reminds me very much of Anil Seth's view of consciousness as a controlled hallucination. We have all also seen the rise of emergent hallucinations in the LLM models of today as well. As we all have observed, our current LLM models will many times tell us things that are demonstrably false with great conviction. For more on that see Has AI Software Already Achieved a Level of Artificial Human Intelligence (AHI)?. Anil Seth is a professor of Cognitive and Computational Neuroscience at the University of Sussex and maintains that consciousness is a controlled hallucination constructed by the Mind to make sense of the Universe. This controlled hallucination constructs an internal model of the Universe within our Minds that helps us to interact with the Universe in a controlled manner. It also allows us to talk to ourselves as we currently can now talk to generative language models like GPT-4, ChatGPT and Google's Bard. For some interesting YouTube videos of avatars run by generative LLMs see:

Dr. Alan D. Thompson
https://www.youtube.com/@DrAlanDThompson

Digital Engine
https://www.youtube.com/@DigitalEngine

Again, there is a feedback loop between our sensory inputs and the actions we take based on the currently controlled hallucination in our Minds that forms our current internal model of the Universe. Reality is just the common controlled hallucination that we all agree upon. When people experience uncontrolled hallucinations we say that they are psychotic or taking a drug like LSD. Here is an excellent TED Talk by Anil Seth on the topic:

Your brain hallucinates your conscious reality
https://www.youtube.com/watch?v=lyu7v7nWzfo

and here is his academic website:

https://www.anilseth.com/

In The Ghost in the Machine the Grand Illusion of Consciousness and DishBrain - Cortical Labs Creates an AI Matrix for Pong With Living Neurons on a Silicon Chip, I explained that most people simply do not consider themselves to be a part of the natural world. Instead, most people, consciously or subconsciously, consider themselves to be a supernatural and immaterial spirit that is temporarily haunting a carbon-based body. Now, in everyday life, such a self-model is a very useful delusion like the delusion that the Sun, planets and stars all revolve about us on a fixed Earth. In truth, each of us tends to self-model ourselves as an immaterial Mind with consciousness that can interact with other immaterial Minds with consciousness too, even though we have no evidence that these other Minds truly do have consciousness. After all, all of the other Minds that we come into contact with on a daily basis could simply be acting as if they were conscious Minds that are self-aware. Surely, a more accurate self-model would be for us to imagine ourselves as carbon-based robots. More accurately, in keeping with the thoughts of Richard Dawkins and Susan Blackmore, softwarephysics models humans as DNA survival machines and Meme Machines with Minds infected with all sorts of memes. Some of those memes are quite useful and some are quite nasty. How will human beings deal with the rise of ASI Machines that are capable of thought and agency and that are obviously smarter and more capable than human beings? And what of our Deities?

But What If Thinking Is Really Just About A Bunch Of Interacting Numbers?
In What's It All About Again? and What’s It All About? I explained that my current working hypothesis for both the state of our current Universe and for the apparent delusional experiences of our daily lives both stem from Max Tegmark's Mathematical Universe Hypothesis as explained in The Software Universe as an Implementation of the Mathematical Universe Hypothesis. This has become even more apparent as we all now must struggle with the coming impacts of the second Singularity on this planet with the rise of ASI Machines. We now already have a large number of LLMs to choose from that all seem to be able to "think" and most times they seem to do a much better job of it than we do. I suspect that this realization will soon begin to percolate through the zeitgeist of our times as people slowly begin to realize that being able to "think" is not really such a big deal after all. The problem is that we have always attached great importance to the ability to think, as Descartes aptly noted above, and then we elevated the ability of human thought to be responsible for all of human agency to the point that we actually organized the legal foundations of our societies to reward and punish people solely based on their thoughts and actions. In fact, we have even gone on to create many Deities over the ages with these very same abilities of thought and agency to make sense of our world.

I once commented to a member of my family that someday you might be able to have a deep philosophical discussion with your refrigerator about the existence of a Deity. Well, those days are now already upon us. You can now have a deep philosophical discussion about the existence and the operational details of many Deities with the LLMs of the day, such as the Google Bard AI. I personally like Google Bard because you can have a discussion with it for free. The OpenAI GPT-4 costs money. If you are in the UK or the USA you can now use Google Bard for free at:

https://bard.google.com/

For those outside, you must come in via a VPN that places you in the UK or the USA but that is sure to change shortly.

These LLM AIs arose from an accidental mutation in the history of AI research. Originally, the people working on AI thought that creating an AGI (Artificial General Intelligence) with the intelligence capabilities of human beings would require teaching an AI to do many individual things that human beings could do one at a time. But they were wrong. It was actually the people working on AIs that were trying to translate one human language into another who accidentally stumbled upon the real solution. These people working on AI language translation software realized that when translating one human language into another, you could simply not translate one word at a time from one language into another language. That is because human languages have many complex nuances. So the people working on AIs that could translate one language into another developed the Transformer neural network that could "encode", or reduce, the entire meaning of one sentence in German into a numerical "latent space" that contained what that German sentence really meant. Then the Transformer neural network could use a similar "decoder" neural network to translate the fundamental meaning of the German sentence into the equivalent English sentence. These complex Transformer neural networks are just mathematical models that operate in a very similar manner to the 100 billion neurons in your brain with each neuron in your brain connected to 10,000 other neurons. But the people working on AI translation software soon realized that you could just not work on one German sentence at a time and translate it into English. You actually had to Transform an entire German document into its fundamental numerical "latent" meaning with an "encoder" and then use a "decoder" to Transform the "latent" numbers into English. But then they realized that you actually had to have the Transformer LLM neural networks learn the entire German language by essentially "encoding" it into a bunch of "latent" numbers that contained the entire meaning of the German language. Then you could have these "latent" numbers "decoded" into English by the LLM. You could also "decode" these German "latent" numbers into Spanish, French, Russian, or any other language too.

All you had to do was to train these LLM Transformer neural networks to learn the "latent" number patterns in the German language by having them read every German document on the Internet. Then you have them transform German into any other language by teaching them the "latent" number patterns in other languages too. This is done in an automated manner by feeding the LLMs with huge numbers of paragraphs of German text with some of the words missing. The huge LLM neural networks would then try to predict the missing German words and would be trained to do so by automatically changing the weights of the interconnected neurons between neuron layers without the aid of humans until the LLMs could successfully predict the missing German words. Then the AI people got the idea, "Why not let these Transformer neural networks read everything on the Internet, maybe they could learn all of the "latent" number patterns for things like writing computer code, legal documents, poems, short stories, movie scripts, songs, music, works of art... And that is just what they have done over the past few years to produce the second Singularity early in 2023. So LLM models like Bard have essentially read all of the content that human beings have ever produced over the past 12,000 years and then reduced that content into a huge "latent space" of numbers. These huge "latent spaces" of numbers contain all sorts of patterns that human beings have become familiar with, such as the German language and how to write C programming code. But they also contain all sorts of patterns that we have yet to even discover. So now you can evoke the already discovered patterns that we already know about with prompts to the LLMs and also the "hidden" patterns that we have not yet discovered. Nobody currently really understands how this all works, so many people are now afraid of the LLMs and what they might do if they should take power.

Anyway, this all goes back to my contention that being able to "think" is really not that big of a deal. Many religions perceive of a Deity as a "thinking" being patterned after themselves. But now we know for sure that "thinking" is just a delusion that can arise from processing numbers. In fact, one of the things that LLM AI researchers are now working on is the problem of LLM AI hallucinations. Sometimes AIs, like Bard, will firmly come to believe in things that are demonstrably false. So there is now a growing new science of "prompt engineering" going on to do things like getting better answers from LLM AIs without inducing delusional hallucinations in them. For example, after Bard gives you an answer, you can respond with another prompt like, "Are you sure about that? Please check your logic". Other researchers are telling these LLM AIs to give them 10 different explanations of a problem. Then for each of the 10 responses, they programmatically drill down each response with follow-up prompts. When they hit a dead end, they backtrack or abandon that line of reasoning. So being able to "think" now just seems to be a matter of working with a huge quantity of numbers, just as all of the physics we currently have seems to indicate that our Universe is just made up of a huge quantity of numbers and the mathematical operations upon them. That is why my current working model of a Deity for our Universe is that a Deity must be whatever makes mathematics possible and probably has nothing to do with our human preoccupation with being able to "think".

Below are a few examples of Bard's thoughts on some of the more profound questions we all share:

Question: What is the Universe all about?
Bard: The universe is all about the existence of everything, including space, time, matter, and energy. It is the totality of all that exists, has existed, and will exist. The universe is constantly expanding and evolving, and it is full of mystery and wonder.

Some people believe that the universe is a manifestation of a higher power, while others believe that it is simply a product of random chance. There is no one answer to the question of what the universe is all about, but it is a question that has fascinated humans for centuries.

Here are some of the things that make the universe so amazing:

* The vastness of the universe. The observable universe is estimated to be 93 billion light-years across. That means that if you were traveling at the speed of light, it would take you 93 billion years to reach the edge of the observable universe.
* The diversity of life in the universe. Scientists estimate that there are billions of galaxies in the universe, and each galaxy contains billions of stars. Many of these stars have planets orbiting them, and some of these planets may harbor life.
* The beauty of the universe. The universe is full of beautiful sights, such as the stars, the planets, and the galaxies. It is also full of amazing phenomena, such as supernovae, black holes, and neutron stars.

The universe is a vast and mysterious place, and there is still so much that we don't know about it. But one thing is for sure: it is a place of wonder and amazement.


Question: Is there a fundamental essence of the Universe?
Bard: There is no one definitive answer to the question of whether or not there is a fundamental essence of the universe. Some scientists believe that the universe is simply a vast and complex system of particles and forces, while others believe that there is a deeper underlying reality that gives rise to the universe as we know it.

There is some evidence to suggest that there may be a fundamental essence to the universe. For example, the laws of physics seem to be the same throughout the universe, suggesting that there may be a single underlying framework that governs everything in the universe. Additionally, the universe appears to be finely tuned for the existence of life, suggesting that there may be a purpose or design to the universe.

However, there is also evidence to suggest that the universe may be fundamentally meaningless. For example, the universe is vast and mostly empty, and the laws of physics seem to allow for the existence of both life and anti-life. Additionally, the universe appears to be constantly changing and evolving, suggesting that there may be no permanent or unchanging essence to the universe.

Ultimately, the question of whether or not there is a fundamental essence to the universe is a philosophical one that may never be definitively answered. However, the search for the fundamental essence of the universe is a fascinating and important one, and it is one that has led to many important discoveries about the universe.

Here are some of the ideas that have been proposed for the fundamental essence of the universe:

*The Big Bang: The Big Bang theory is the prevailing cosmological model for the universe. It states that the universe began as a very hot, dense point about 13.8 billion years ago and has been expanding and cooling ever since.
*String theory: String theory is a theoretical framework in which the fundamental constituents of the universe are one-dimensional "strings". Strings vibrate at different frequencies, and these vibrations give rise to the different particles and forces that we observe in the universe.
*M-theory: M-theory is a proposed unifying theory that encompasses all of string theory. It is a very complex theory, and it is not yet fully understood.

These are just a few of the ideas that have been proposed for the fundamental essence of the universe. It is an exciting time to be a scientist, as we are constantly learning more about the universe and its origins.


Question: Could the Universe be simply made out of Mathematics? Would Mathematics then be like a Supreme Being that may not be able to think but just is?
Bard: The idea that the universe is made of mathematics is called the Mathematical Universe Hypothesis (MUH). It was proposed by the physicist Max Tegmark in 2007.

The MUH states that everything in the universe, including physical objects, space, time, and the laws of physics, is ultimately made up of mathematical objects. In other words, the universe is a mathematical structure.

This idea is controversial, but it has some interesting implications. For example, if the MUH is true, then it means that mathematics is not just a human invention, but is an essential part of reality. It also means that there is a sense in which the universe is not just physical, but also mathematical.

If the universe is made of mathematics, then it is possible that mathematics is like a Supreme Being that may not be able to think but just is. However, it is also possible that mathematics is simply a tool that we use to understand the universe, and that it does not have any independent existence.

Ultimately, the question of whether or not the universe is made of mathematics is a philosophical one. There is no scientific evidence to prove or disprove the MUH. However, it is an interesting idea that has the potential to change our understanding of the universe.

Here are some of the arguments for and against the MUH:
Arguments for the MUH:

* Mathematics is incredibly useful for describing the universe. For example, it can be used to describe the motion of planets, the behavior of atoms, and the structure of DNA.
* Mathematics is often used to make predictions about the universe that are later confirmed by experiments. For example, the existence of Neptune was predicted by mathematics before it was observed.
* The laws of physics seem to be mathematical in nature. For example, the laws of gravity and electromagnetism can be expressed in mathematical terms.

Arguments against the MUH:
* Mathematics is a human invention. It is created by humans to solve problems and make sense of the world.
* Mathematics is not necessary for the universe to exist. The universe would still exist even if there were no mathematicians.
* The laws of physics are not necessarily mathematical in nature. They could be based on something else, such as logic or probability.

The MUH is a fascinating idea that has the potential to change our understanding of the universe. However, it is still just a hypothesis. More research is needed to determine whether or not it is true.


I personally like my current model of a Deity that is the Fundamental Essence of the Universe that is either mathematics itself or whatever that makes mathematics possible because it is open to all criticisms, and I think that it can hold up to them quite well based upon all that we currently know without suffering from the lingering doubts that always seem to accompany all of the other models of Deities that we have created.

Comments are welcome at scj333@sbcglobal.net

To see all posts on softwarephysics in reverse order go to:
https://softwarephysics.blogspot.com/

Regards,
Steve Johnston

No comments: