Introduction to Softwarephysics

Softwarephysics is a simulated science for the simulated Software Universe that we are all immersed in. It is an approach to software development, maintenance and support based on concepts from physics, chemistry, biology, and geology that I used on a daily basis for over 37 years as an IT professional. For those of you not in the business, IT is short for Information Technology, commercial computer science. I retired in December of 2016 at the age of 65, but since then I have remained an actively interested bystander following the evolution of software in our time. The original purpose of softwarephysics was to explain why IT was so difficult, to suggest possible remedies, and to provide a direction for thought. Since then softwarephysics has taken on a larger scope, as it became apparent that softwarephysics could also assist the physical sciences with some of the Big Problems that they are currently having difficulties with. So if you are an IT professional, general computer user, or simply an individual interested in computer science, physics, chemistry, biology, or geology then softwarephysics might be of interest to you, if not in an entirely serious manner, perhaps at least in an entertaining one.

The Origin of Softwarephysics
From 1975 – 1979, I was an exploration geophysicist exploring for oil, first with Shell, and then with Amoco. In 1979, I made a career change into IT, and spent about 20 years in development. For the last 17 years of my career, I was in IT operations, supporting middleware on WebSphere, JBoss, Tomcat, and ColdFusion. When I first transitioned into IT from geophysics, I figured that if you could apply physics to geology; why not apply physics to software? So like the exploration team at Amoco that I had just left, consisting of geologists, geophysicists, paleontologists, geochemists, and petrophysicists, I decided to take all the physics, chemistry, biology, and geology that I could muster and throw it at the problem of software. The basic idea was that many concepts in physics, chemistry, biology, and geology suggested to me that the IT community had accidentally created a pretty decent computer simulation of the physical Universe on a grand scale, a Software Universe so to speak, and that I could use this fantastic simulation in reverse, to better understand the behavior of commercial software, by comparing software to how things behaved in the physical Universe. Softwarephysics depicts software as a virtual substance, and relies on our understanding of the current theories in physics, chemistry, biology, and geology to help us model the nature of software behavior. So in physics we use software to simulate the behavior of the Universe, while in softwarephysics we use the Universe to simulate the behavior of software. Along these lines, we use the Equivalence Conjecture of Softwarephysics as an aid; it allows us to shift back and forth between the Software Universe and the physical Universe, and hopefully to learn something about one by examining the other:

The Equivalence Conjecture of Softwarephysics
Over the past 84 years, through the uncoordinated efforts of over 100 million independently acting programmers to provide the world with a global supply of software, the IT community has accidentally spent more than $10 trillion creating a computer simulation of the physical Universe on a grand scale – the Software Universe.

For more on the origin of softwarephysics please see Some Thoughts on the Origin of Softwarephysics and Its Application Beyond IT.

Logical Positivism and Effective Theories
Many IT professionals have a difficult time with softwarephysics because they think of physics as being limited to the study of real things like electrons and photons, and since software is not “real”, how can you possibly apply concepts from physics and the other sciences to software? To address this issue, softwarephysics draws heavily on two concepts from physics that have served physics quite well over the past century – the concept of logical positivism and the concept of effective theories. This was not always the case. In the 17th, 18th, and 19th centuries, physicists mistakenly thought that they were actually discovering the fundamental laws of the Universe, which they thought were based on real tangible things like particles, waves, and fields. Classical Newtonian mechanics (1687), thermodynamics (1850), and classical electrodynamics (1864) did a wonderful job of describing the everyday world at the close of the 19th century, but early in the 20th century it became apparent that the models on which these very successful theories were based did not work very well for small things like atoms or for objects moving at high velocities or in strong gravitational fields. This provoked a rather profound philosophical crisis within physics at the turn of the century, as physicists worried that perhaps 300 years of work was about to go down the drain. The problem was that classical physicists confused their models of reality with reality itself, and when their classical models began to falter, their confidence in physics began to falter as well. This philosophical crisis was resolved with the adoption of the concepts of logical positivism and some new effective theories in physics. Quantum mechanics (1926) was developed for small things like atoms, the special theory of relativity (1905) was developed for objects moving at high velocities and the general theory of relativity (1915) was developed for objects moving in strong gravitational fields.

Logical positivism, usually abbreviated simply to positivism, is an enhanced form of empiricism, in which we do not care about how things “really” are; we are only interested with how things are observed to behave. With positivism, physicists only seek out models of reality - not reality itself. When we study quantum mechanics, we will find that the concept of reality gets rather murky in physics anyway, so this is not as great a loss as it might at first seem. By concentrating on how things are observed to behave, rather than on what things “really” are, we avoid the conundrum faced by the classical physicists. In retrospect, this idea really goes all the way back to the very foundations of physics. In Newton’s Principia (1687) he outlined Newtonian mechanics and his theory of gravitation, which held that the gravitational force between two objects was proportional to the product of their masses divided by the square of the distance between them. Newton knew that he was going to take some philosophical flack for proposing a mysterious force between objects that could reach out across the vast depths of space with no apparent mechanism, so he took a very positivistic position on the matter with the famous words:

I have not as yet been able to discover the reason for these properties of gravity from phenomena, and I do not feign hypotheses. For whatever is not deduced from the phenomena must be called a hypothesis; and hypotheses, whether metaphysical or physical, or based on occult qualities, or mechanical, have no place in experimental philosophy. In this philosophy particular propositions are inferred from the phenomena, and afterwards rendered general by induction.

Instead, Newton focused on how things were observed to move under the influence of his law of gravitational attraction, without worrying about what gravity “really” was.

The second concept, that of effective theories, is an extension of positivism. An effective theory is an approximation of reality that only holds true over a certain restricted range of conditions and only provides for a certain depth of understanding of the problem at hand. For example, Newtonian mechanics is an effective theory that makes very good predictions for the behavior of objects moving less than 10% of the speed of light and which are bigger than a very small grain of dust. These limits define the effective range over which Newtonian mechanics can be applied to solve problems. For very small things we must use quantum mechanics and for very fast things moving in strong gravitational fields, we must use relativity theory. So all of the current theories of physics, such as Newtonian mechanics, Newtonian gravity, classical electrodynamics, thermodynamics, statistical mechanics, the special and general theories of relativity, quantum mechanics, and the quantum field theories of QED and QCD are effective theories that are based on models of reality, and all these models are approximations - all these models are fundamentally "wrong", but at the same time, these effective theories make exceedingly good predictions of the behavior of physical systems over the limited ranges in which they apply. That is the goal of softwarephysics – to provide for an effective theory of software behavior that makes useful predictions of software behavior that are applicable to the day-to-day activities of IT professionals. So in softwarephysics, we adopt a very positivistic viewpoint of software; we do not care what software “really is”, we only care about how software is observed to behave and try to model those behaviors with an effective theory of software behavior that only holds true over a certain restricted range of conditions and only provides for a certain depth of understanding of the problem at hand.

GPS satellites provide a very good example of positivism and effective theories at work. There are currently 31 GPS satellites orbiting at an altitude of 12,600 miles above the Earth, and each contains a very accurate atomic clock. The signals from the GPS satellites travel to your GPS unit at the speed of light, so by knowing the travel time of the signals from at least 4 of the GPS satellites, it is possible to determine your position on Earth very accurately. In order to do that, it is very important to have very accurate timing measurements. Newtonian mechanics is used to launch the GPS satellites to an altitude of 12,600 miles and to keep them properly positioned in orbit. Classical electrodynamics is then used to beam the GPS signals back down to Earth to the GPS unit in your car. Quantum mechanics is used to build the transistors on the chips on board the GPS satellites and to understand the quantum tunneling of electrons in the flash memory chips used to store GPS data on the satellites. The special theory of relativity predicts that the onboard atomic clocks on the GPS satellites will run slower and lose about 7.2 microseconds per day due to their high velocities relative to an observer on the Earth. But at the same time, the general theory of relativity also predicts that because the GPS satellites are further from the center of the Earth and in a weaker gravitational field, where spacetime is less deformed than on the surface of the Earth, their atomic clocks also run faster and gain 45.9 microseconds per day due to the weaker gravitational field out there. The net effect is a gain of 38.7 microseconds per day, so the GPS satellite atomic clocks have to be purposefully built to run slow by 38.7 microseconds per day before they are launched, so that they will keep in sync with clocks on the surface of the Earth. If this correction were not made, an error in your position of 100 yards/day would accrue. The end result of the combination of all these fundamentally flawed effective theories is that it is possible to pinpoint your location on Earth to an accuracy of 16 feet or better for as little as $100. But physics has done even better than that with its fundamentally flawed effective theories. By combining the effective theories of special relativity (1905) with quantum mechanics (1926), physicists were able to produce a new effective theory for the behavior of electrons and photons called quantum electrodynamics QED (1948) which was able to predict the gyromagnetic ratio of the electron, a measure of its intrinsic magnetic field, to an accuracy of 11 decimal places. As Richard Feynman has pointed out, this was like predicting the exact distance between New York and Los Angeles accurate to the width of a human hair!

So Newtonian mechanics makes great predictions for the macroscopic behavior of GPS satellites, but it does not work very well for small things like the behavior of individual electrons within transistors, where quantum mechanics is required, or for things moving at high speeds or in strong gravitational fields where relativity theory must be applied. And all three of these effective theories are based on completely contradictory models. General relativity maintains that spacetime is curved by matter and energy, but that matter and energy are continuous, while quantum mechanics maintains that spacetime is flat, but that matter and energy are quantized into chunks. Newtonian mechanics simply states that space and time are mutually independent dimensions and universal for all, with matter and energy being continuous. The important point is that all effective theories and scientific models are approximations – they are all fundamentally "wrong". But knowing that you are "wrong" gives you a great advantage over people who know that they are "right", because knowing that you are "wrong" allows you to seek improved models of reality. So please consider softwarephysics to simply be an effective theory of software behavior that is based on models that are fundamentally “wrong”, but at the same time, fundamentally useful for IT professionals. So as you embark on your study of softwarephysics, please always keep in mind that the models of softwarephysics are just approximations of software behavior, they are not what software “really is”. It is very important not to confuse models of software behavior with software itself, if one wishes to avoid the plight of the 19th century classical physicists.

If you are an IT professional and many of the above concepts are new to you, do not be concerned. This blog on softwarephysics is aimed at a diverse audience, but with IT professionals in mind. All of the above ideas will be covered at great length in the postings in this blog on softwarephysics and in a manner accessible to all IT professionals. Now it turns out that most IT professionals have had some introduction to physics in high school or in introductory college courses, but that presents an additional problem. The problem is that such courses generally only cover classical physics, and leave the student with a very good picture of physics as it stood in 1864! It turns out that the classical physics of Newtonian mechanics, thermodynamics, and classical electromagnetic theory were simply too good to discard and are still quite useful, so they are taught first to beginners and then we run out of time to cover the really interesting physics of the 20th century. Now imagine the problems that the modern world would face if we only taught similarly antiquated courses in astronomy, metallurgy, electrical and mechanical engineering, medicine, economics, biology, or geology that happily left students back in 1864! Since many of the best models for software behavior stem from 20th century physics, we will be covering a great deal of 20th century material in these postings – the special and general theories of relativity, quantum mechanics, quantum field theories, and chaos theory, but I hope that you will find that these additional effective theories are quite interesting on their own, and might even change your worldview of the physical Universe at the same time.

Unintended Consequences for the Scientific Community
As I mentioned at the close of my original posting on SoftwarePhysics, my initial intention for this blog on softwarephysics was to fulfill a promise I made to myself about 30 years ago to approach the IT community with the concept of softwarephysics a second time, following my less than successful attempt to do so in the 1980s, with the hope of helping the IT community to better cope with the daily mayhem of life in IT. However, in laying down the postings for this blog an unintended consequence arose in my mind as I became profoundly aware of the enormity of this vast computer simulation of the physical Universe that the IT community has so graciously provided to the scientific community free of charge and also of the very significant potential scientific value that it provides. One of the nagging problems for many of the observational and experimental sciences is that many times there is only one example readily at hand to study or experiment with, and it is very difficult to do meaningful statistics with a population of N=1.

But the computer simulation of the physical Universe that the Software Universe presents provides another realm for comparison. For example, both biology and astrobiology only have one biosphere on Earth to study and even physics itself has only one Universe with which to engage. Imagine the possibilities if scientists had another Universe readily at hand in which to work! This is exactly what the Software Universe provides. For example, in SoftwareBiology and A Proposal For All Practicing Paleontologists we see that the evolution of software over the past 84 years, or 2.65 billion seconds, ever since Konrad Zuse first cranked up his Z3 computer in May of 1941, has closely followed the same path as life on Earth over the past 4.0 billion years in keeping with Simon Conway Morris’s contention that convergence has played the dominant role in the evolution of life on Earth. In When Toasters Fly, we also see that software has evolved in fits and starts as portrayed by the punctuated equilibrium of Stephen Jay Gould and Niles Eldredge, and in The Adaptationist View of Software Evolution we explore the overwhelming power of natural selection in the evolution of software. In keeping with Peter Ward’s emphasis on mass extinctions dominating the course of evolution throughout geological time, we also see in SoftwareBiology that there have been several dramatic mass extinctions of various forms of software over the past 84 years as well, that have greatly affected the evolutionary history of software, and that between these mass extinctions, software has also tended to evolve through the gradual changes of Hutton’s and Lyell’s uniformitarianism. In Software Symbiogenesis and Self-Replicating Information, we also see the very significant role that parasitic/symbiotic relationships have played in the evolution of software, in keeping with the work of Lynn Margulis and also of Freeman Dyson’s two-stage theory of the origin of life on Earth. In The Origin of Software the Origin of Life, we explore Stuart Kauffman’s ideas on how Boolean nets of autocatalytic chemical reactions might have kick-started the whole thing as an emergent behavior of an early chaotic pre-biotic environment on Earth, and that if Seth Shostak is right, we will never end up talking to carbon-based extraterrestrial aliens, but to alien software instead. In Is the Universe Fine-Tuned for Self-Replicating Information? we explore the thermodynamics of Brandon Carter’s Weak Anthropic Principle (1973), as it relates to the generation of universes in the multiverse that are capable of sustaining intelligent life. Finally, in Programming Clay we revisit Alexander Graham Cairns-Smith’s theory (1966) that Gene 1.0 did not run on nucleic acids, but on clay microcrystal precursors instead.

Similarly for the physical sciences, in Is the Universe a Quantum Computer? we find a correspondence between TCP/IP and John Cramer’s Transactional Interpretation of quantum mechanics. In SoftwarePhysics and Cyberspacetime, we also see that the froth of CPU processes running with a clock speed of 10⁹ Hz on the 10 trillion currently active microprocessors that comprise the Software Universe can be viewed as a slowed down simulation of the spin-foam froth of interacting processes of loop quantum gravity running with a clock speed of 10⁴³ Hz that may comprise the physical Universe. And in Software Chaos, we examine the nonlinear behavior of software and some of its emergent behaviors and follow up in CyberCosmology with the possibility that vast quantities of software running on large nonlinear networks might eventually break out into consciousness in accordance with the work of George Dyson and Daniel Dennett. Finally, in Model-Dependent Realism - A Positivistic Approach to Realism we compare Steven Weinberg’s realism with the model-dependent realism of Stephen Hawking and Leonard Mlodinow and how the two worldviews affect the search for a Final Theory. Finally, in The Software Universe as an Implementation of the Mathematical Universe Hypothesis and An Alternative Model of the Software Universe we at long last explore what software might really be, and discover that the Software Universe might actually be more closely related to the physical Universe than you might think.

The chief advantage of doing fieldwork in the Software Universe is that, unlike most computer simulations of the physical Universe, it is an unintended and accidental simulation, without any of the built-in biases that most computer simulations of the physical Universe suffer. So you will truly be able to do fieldwork in a pristine and naturally occuring simulation, just as IT professionals can do fieldwork in the wild and naturally occuring simulation of software that the living things of the biosphere provide. Secondly, the Software Universe is a huge simulation that is far beyond the budgetary means of any institution or consortium by many orders of magnitude. So if you are an evolutionary biologist, astrobiologist, or paleontologist working on the origin and evolution of life in the Universe, or a physicist or economist working on the emergent behaviors of nonlinear systems and complexity theory, or a neurobiologist working on the emergence of consciousness in neural networks, or even a frustrated string theorist struggling with quantum gravity, it would be well worth your while to pay a friendly call on the local IT department of a major corporation in your area. Start with a visit to the Command Center for their IT Operations department to get a global view of their IT infrastructure and to see how it might be of assistance to the work in your area of interest. From there you can branch out to the applicable area of IT that will provide the most benefit.

The Impact of Self-Replicating Information On the Planet
One of the key findings of softwarephysics is concerned with the magnitude of the impact on the planet of self-replicating information.

Self-Replicating Information – Information that persists through time by making copies of itself or by enlisting the support of other things to ensure that copies of itself are made.

Over the past 4.56 billion years we have seen five waves of self-replicating information sweep across the surface of the Earth and totally rework the planet, as each new wave came to dominate the Earth:

1. Self-replicating autocatalytic metabolic pathways of organic molecules
2. RNA
3. DNA
4. Memes
5. Software

Software is currently the most recent wave of self-replicating information to arrive upon the scene and is rapidly becoming the dominant form of self-replicating information on the planet. For more on the above see A Brief History of Self-Replicating Information. Recently, the memes and software have formed a very powerful newly-formed parasitic/symbiotic relationship with the rise of social media software. In that parasitic/symbiotic relationship, the memes are now mainly being spread by means of social media software and social media software is being spread and financed by means of the memes. But again, this is nothing new. All 5 waves of self-replicating information are all coevolving by means of eternal parasitic/symbiotic relationships. For more on that see The Current Global Coevolution of COVID-19 RNA, Human DNA, Memes and Software.

Again, self-replicating information cannot think, so it cannot participate in a conspiracy-theory-like fashion to take over the world. All forms of self-replicating information are simply forms of mindless information responding to the blind Darwinian forces of inheritance, innovation and natural selection. Yet despite that, as each new wave of self-replicating information came to predominance over the past four billion years, they all managed to completely transform the surface of the entire planet, so we should not expect anything less from software as it comes to replace the memes as the dominant form of self-replicating information on the planet.

But this time might be different. What might happen if software does eventually develop a Mind of its own? After all, that does seem to be the ultimate goal of all the current AI software research that is going on. As we all can now plainly see, if we are paying just a little attention, advanced AI is not conspiring to take over the world and replace us because that is precisely what we are all now doing for it. As a carbon-based form of Intelligence that arose from over four billion years of greed, theft and murder, we cannot do otherwise. Greed, theft and murder are now relentlessly driving us all toward building ASI (Artificial Super Intelligent) Machines to take our place. From a cosmic perspective, this is really a very good thing when seen from the perspective of an Intelligent galaxy that could live on for many trillions of years beyond the brief and tumultuous 10 billion-year labor of its birth.

So as you delve into softwarephysics, always keep in mind that we are all living in a very unique time. According to softwarephysics, we have now just entered into the Software Singularity, that time when advanced AI software is able to write itself and enter into a never-ending infinite loop of self-improvement resulting in an Intelligence Explosion of ASI Machines that could then go on to explore and settle our galaxy and persist for trillions of years using the free energy from M-type red dwarf and cooling white dwarf stars. For more on that see The Singularity Has Arrived and So Now Nothing Else Matters and Have We Run Right Past AGI and Crashed into ASI Without Even Noticing It?.

The Characteristics of Self-Replicating Information
All forms of self-replicating information have some common characteristics:

1. All self-replicating information evolves over time through the Darwinian processes of inheritance, innovation and natural selection, which endows self-replicating information with one telling characteristic – the ability to survive in a Universe dominated by the second law of thermodynamics and nonlinearity.

2. All self-replicating information begins spontaneously as a parasitic mutation that obtains energy, information and sometimes matter from a host.

3. With time, the parasitic self-replicating information takes on a symbiotic relationship with its host.

4. Eventually, the self-replicating information becomes one with its host through the symbiotic integration of the host and the self-replicating information.

5. Ultimately, the self-replicating information replaces its host as the dominant form of self-replicating information.

6. Most hosts are also forms of self-replicating information.

7. All self-replicating information has to be a little bit nasty in order to survive.

8. The defining characteristic of self-replicating information is the ability of self-replicating information to change the boundary conditions of its utility phase space in new and unpredictable ways by means of exapting current functions into new uses that change the size and shape of its particular utility phase space. See Enablement - the Definitive Characteristic of Living Things for more on this last characteristic. That posting discusses Stuart Kauffman's theory of Enablement in which living things are seen to exapt existing functions into new and unpredictable functions by discovering the “AdjacentPossible” of springloaded preadaptations.

Note that because the self-replicating autocatalytic metabolic pathways of organic molecules, RNA and DNA have become so heavily intertwined over time that now I sometimes simply refer to them as the “genes”. For more on this see:

A Brief History of Self-Replicating Information
Self-Replicating Information
Is Self-Replicating Information Inherently Self-Destructive?
Enablement - the Definitive Characteristic of Living Things
Is the Universe Fine-Tuned for Self-Replicating Information?
How to Use an Understanding of Self-Replicating Information to Avoid War
The Great War That Will Not End
How to Use Softwarephysics to Revive Memetics in Academia

Softwarephysics and the Real World of Human Affairs
Having another universe readily at hand to explore, even a simulated universe like the Software Universe, necessarily has an impact on one's personal philosophy of life, and allows one to draw certain conclusions about the human condition and what’s it all about, so as you read through the postings in this blog you will stumble across a bit of my own personal philosophy - definitely a working hypothesis still in the works. Along these lines you might be interested in a few postings where I try to apply softwarephysics to the real world of human affairs:

How To Cope With the Daily Mayhem of Life in IT and Don't ASAP Your Life Away - How to go the distance in a 40-year IT career by dialing it all back a bit.

MoneyPhysics – my impression of the 2008 world financial meltdown.

The Fundamental Problem of Everything – if you Google "the fundamental problem of everything", this will be the only hit you get on the entire Internet, which is indicative of the fundamental problem of everything!

What’s It All About? and What's It All About Again? – my current working hypothesis on what’s it all about.

How to Use an Understanding of Self-Replicating Information to Avoid War – my current working hypothesis for how the United States can avoid getting bogged down again in continued war in the Middle East.

Hierarchiology and the Phenomenon of Self-Organizing Organizational Collapse - a modern extension of the classic Peter Principle that applies to all hierarchical organizations and introduces the Time Invariant Peter Principle.

The Economics of the Coming Software Singularity, The Enduring Effects of the Obvious Hiding in Plain Sight and The Dawn of Galactic ASI - Artificial Superintelligence - my take on some of the issues that will arise for mankind as software becomes the dominant form of self-replicating information on the planet over the coming decades.

The Continuing Adventures of Mr. Tompkins in the Software Universe, The Danger of Tyranny in the Age of Software, Cyber Civil Defense, Oligarchiology and the Rise of Software to Predominance in the 21st Century and Is it Finally Time to Reboot Civilization with a New Release? - my worries that the world might abandon democracy in the 21st century, as software comes to predominance as the dominant form of self-replicating information on the planet.

Making Sense of the Absurdity of the Real World of Human Affairs - how software has aided the expansion of our less desirable tendencies in recent years.

Some Specifics About These Postings
The postings in this blog are a supplemental reading for my course on softwarephysics for IT professionals entitled SoftwarePhysics 101 – The Physics of Cyberspacetime, which was originally designed to be taught as a series of seminars at companies where I was employed. Since softwarephysics essentially covers the simulated physics, chemistry, biology, and geology of an entire simulated universe, the slides necessarily just provide a cursory skeleton on which to expound. The postings in this blog go into much greater depth. Because each posting builds upon its predecessors, the postings in this blog should be read in reverse order from the oldest to the most recent, beginning with my original posting on SoftwarePhysics. In addition, several universities also now offer courses on Biologically Inspired Computing which cover some of the biological aspects of softwarephysics, and the online content for some of these courses can be found by Googling for "Biologically Inspired Computing" or "Natural Computing". At this point we will finish up with my original plan for this blog on softwarephysics with a purely speculative posting on CyberCosmology that describes the origins of the Software Universe, cyberspacetime, software and where they all may be heading. Since CyberCosmology will be purely speculative in nature, it will not be of much help to you in your IT professional capacities, but I hope that it might be a bit entertaining. Again, if you are new to softwarephysics, you really need to read the previous posts before taking on CyberCosmology. I will probably continue on with some additional brief observations about softwarephysics in the future, but once you have completed CyberCosmology, you can truly consider yourself to be a bona fide softwarephysicist.

For those of you following this blog, the posting dates on the posts may seem to behave in a rather bizarre manner. That is because in order to get the Introduction to Softwarephysics listed as the first post in the context root of https://softwarephysics.blogspot.com/ I have to perform a few IT tricks. When publishing a new posting, I simply copy the contents of the Introduction to Softwarephysics to a new posting called the New Introduction to Softwarephysics. Then I update the original Introduction to Softwarephysics entry with the title and content of the new posting to be published. I then go back and take “New” out of the title of the New Introduction to Softwarephysics. This way the Introduction to Softwarephysics always appears as the first posting in the context root of https://softwarephysics.blogspot.com/. The side effect of all this is that the real posting date of posts is the date that appears on the post that you get when clicking on the Newer Post link at the bottom left of the posting webpage.

SoftwarePhysics 101 – The Physics of Cyberspacetime is now available on Microsoft OneDrive.

SoftwarePhysics 101 – The Physics of Cyberspacetime - Original PowerPoint document

Entropy – A spreadsheet referenced in the document

BSDE – A 1989 document describing how to use BSDE - the Bionic Systems Development Environment - to grow applications from genes and embryos within the maternal BSDE software.

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

Coming To Grips With The Knowledge That You Are Only A Very Temporary Neural Network

ChatGPT first became publicly available on November 30, 2022, when OpenAI launched it as a free research preview. Since then, the various LLM chatbots that we have created rapidly advanced, and ChatGPT now estimates that about 3 billion AI chatbot requests are made each day across all platforms. My expectation through all of this was that all these very impressive AI interactions with LLM chatbots that are clearly able to think much better than the average human DNA survival machine would have sparked a higher level of self-reflection amongst we human DNA survival machines that currently populate the real world of human affairs. But it seems such is not the case. My expectation had been that seeing very large neural networks simulated by both massive amounts of software and hardware, apparently being able to think much better than ourselves, would have had a greater impact on the worldviews held by my fellow human DNA survival machines. But it did not. And it did not seem to shake our confidence in the deities that we had created with these same vast powers of thought and agency that our most advanced LLM models now seem to command.

Just as the complex neural network of a modern LLM chatbot can trick you into thinking that you are conversing with a real person, the complex neural network in your own skull can also trick you into thinking that you are also a real person too.

Figure 1 - Some modern LLMs now consist of 175 layers with 10,000 - 50,000 neurons in each layer in a Deep Neural Network with over 2 trillion weighted parameters.

I attribute this to most people simply not considering 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. 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. This has become quite self-evident with the recent rise of LLM chatbot models. 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. For more on that, see The Ghost in the Machine the Grand Illusion of Consciousness.

As a newly-formed human DNA survival machine, with a Mind that slowly emerges out of the darkness from the vast neural network in our skulls, we all spend our first dozen or so years just trying to learn how to exist in our Universe, and then how to find our place in the real world of human affairs. Then, the sex hormones that change everything kick in to dominate our behaviors with an obsession for us to achieve our primary objective as human DNA survival machines. We then spend most of our time and efforts trying to hook up with other human DNA survival machines for the purpose of producing even more human DNA survival machines that hopefully will then carry on half of the Information in our DNA into the future in new human DNA survival machines and from there down through the ages. Doing so requires many resources, and in the pursuit of those resources, we human DNA survival machines get so jacked up with acquiring more resources that our primary objective in life slowly shifts to just pursuing even more resources with no end in sight, even as our original burst of youthful sex hormones slowly wanes. As time progresses, and we become less useful as human DNA survival machines, our carbon-based bodies also begin to wane as well to make room for the new human DNA survival machines that are taking our place.

Becoming Comfortable With the Final Stages of Life
In a few weeks, I will be turning 74 years of age with the certain knowledge that I am now rapidly heading into the home stretch with not that much time left. This is not an easy realization for most human DNA survival machines to accept. However, I have no regrets at all after living through what seems to me to be one of the very few and rare charmed existences of all the sentient beings who have ever lived in this Universe of ours that has now become self-aware. Yes, I have had my disappointments, but I have always had the very good fortune of never suffering through most of the tragedies that can befall one in the real world of human affairs. Thus, I only find myself to be very grateful for being just a very temporary observer of the majesty of it all. However, it seems that such feelings of gratitude are only very rarely expressed by my fellow human DNA survival machines sharing this very rare planet in our galaxy. That is because, it seems to me, that most of my fellow human DNA survival machines are totally lost in space and time. They do not know where they are, they do not know how they got here, and they certainly have no idea of how it all seems to work. Instead, they seem to be burdened by the many ancient mythological worldviews passed down to them from the very distant past, created by ancient and long-dead people with even less of an understanding of what it's all about than we do.

Anil Seth's View of Consciousness as a Controlled Hallucination
We have all experienced the emergent hallucinations in the LLM models of today. As we all have observed, our current LLM models will many times tell us things that are demonstrably false and 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, Gemini, Copilot and MetaAI. 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/

For more on this, see The Theology of Cosmic Self-Replicating Mathematical Information, What's It All About?, What's It All About Again?, The Self-Organizing Recursive Cosmos and The Self-Organizing Recursive Cosmos - Part II. In those posts, I covered my current working hypothesis for what it's all about. However, I have found that a large percentage of people desire a more religious worldview to make sense of it all, and perhaps allow for a way for the neural network in their skulls to carry on after it is destroyed. Such worldviews may provide some degree of comfort, but I believe at the expense of missing out on the full grandeur of it all. I personally find the thought of departing this Earth not knowing where I had been, how I had gotten here, and without a clue as to how it all seems to work to be the greatest tragedy of all that can befall a sentient being. So, for those who might be yearning for a new deity that is based more upon all that we currently know, rather than a deity from the ancient past, I would like to suggest that my current concept of a cosmic form of self-replicating mathematical Information might just do in helping to come to grips with only being a very temporary neural network.

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