Posts Tagged ‘Observations of Life’

Grumblings of an old man

December 1, 2023

I’m retired now but I worked in software development for over 30 years. I think it’s quite ironic that the Frankenstein monster of computer-based automation has finally turned on its creator. During the 1980’s and 90’s I used to say that the main result of my work was to facilitate unemployment because a lot of what I was doing was developing ways that a computer could do what a human did, but cheaper, faster, and more reliably. Though formally the work I did was to increase efficiency and effectiveness in tasks that needed to be performed by a business to keep the business going. That is, to make more money than it spent, which companies have been trying to do way before there were computers.

I worked on developing solutions that used software to replace humans. I lost count of the number of people who lost their jobs as a direct or indirect result of the work I did. To be honest it was for the better in many cases, but nonetheless, I helped create the entity that replaced them at the job they were currently doing to earn a living. In a fair number of cases the actual person or persons affected found new and better employment elsewhere (i.e., they were re-skilled, even if often reluctantly). But in terms of what they had been doing, their job was now gone, lost to the hands of humans. The work they once performed was now performed by a computer.

OK, now to the irony. This phenomenon is now about to happen to the very people who perpetrated the changes that affected so many others[i]. Developers are now, or will shortly be, losing their jobs because of automation. This time automation will be applied to their jobs. The work (that is the actions that produce outcomes) will still be performed, of course, but by a computer that has mastered their skills but expects no compensation in return. Namely machine learning, artificial intelligence, and robotics. Those who are swift of mind and action will see, and in many cases have already seen, this coming for a while. They have moved forward, along the arrow of time, to keep ahead of, or at least abreast of, changes. But humans can learn new stuff only so fast, and the ability to do so slowly diminishes over time.

Machine learning can cause a computer to learn at not only a higher rate than humans, but at an ever-increasing rate. Thus, over time, widening the knowledge gap between computers and humans. This is done using feedback loops, called backpropagation, coded into the instructions of the computer. Changes to the inputs to the computer’s instructions are made every time the instructions run which, of course, changes the outputs that are the result of each run. Over time the outputs based on these changing inputs get reliably closer and closer to what they are expected to be. When the computer gets as close as it can get, usually determined by a human, it is assumed that the instructions can produce reliable results even with inputs it has never “seen” before. This is quite a marvelous thing when you think about it.

Sooner or later humans reach their capacity for learning, either because the pace of change in their field has slowed down or the type of work has become irrelevant. In any case it can be done faster, cheaper, and more predictably by some means of automation.

Come to think of it, this is the way “progress” has always worked. However, that does not change the irony. No human is safe from, or immune from this phenomenon. You might ask, how will people earn a living if they can no longer stay at least a little bit ahead of the curve? After all, the paradigm has always been that human effort produces work, which is compensated for by money, so there is this unbroken connection for a person from effort to money. Finally, as money is accumulated, wealth is created. Wealth is then exchanged for sustenance. Sustenance thus provides the motivation to keep a cycle (or loop) going.

Maybe this “unbroken connection” is what will change in the future. Maybe more people will be on what many people now call “welfare”, however it won’t be called that in the future. There won’t be any social stigma about it at all. It will simply be the way that people get sustenance. If it’s true that artificial intelligence and its means of coming about: machine learning and robotics, will eventually create more wealth, then at least some of that wealth will need to be distributed, without dependency on their effort, to more and more humans. If not, sustenance will diminish, and human population will crash increasing the odds that the technological singularity[ii] will occur much faster than anticipated. This will happen simply because there will be fewer humans to oppose it. Those who remain will become more and more dependent on automated means for their sustenance. AGI (artificial general intelligence) will have arrived. Not because artificial intelligence has become smarter, but because humans have become less so.


[i] Not literally the same people. For example, I escaped unscathed and have been able to retire reasonably well-off. It’s the people who follow who will have to fight for their meals. I guess the sins of one generation are always visited upon the next.

[ii] The book “The Singularity is Near: When Humans Transcend Biology” by Ray Kurzweil was published in 2005. In it he uses the term “singularity” usually without the term “technological”. The addition may be to differentiate it from the same term used in Physics to denote the interface between a blackhole and everything else.

Lusa Tonga

September 4, 2023

In the language Lusa Tonga just about everything depends on context.  As a matter of fact, most of the words in Lusa Tonga consist of a single word and most of the time that word is “Tonga”. 

For example, if you want to say “I threw the ball over there” you would say “Muya Tonga Tonga tonga Tonga tonga”.  Mercifully capitalization is optional, but preferred. 

“Muya” is the first-person all-purpose word.  It means roughly “I”, “me”, “my” and/or “mine” in English. In Lusa Tonga one could use that sentence to say just about anything about oneself, but nothing about anyone else.

To say “Why did you throw the ball over there?” you would say “Tonga Tonga Tonga Tonga tonga tonga tonga Foa” and then abruptly raise the eyebrows sharply at the end and look quickly to the left.

How the Lusa Tongani ever managed to invent the world’s fastest, smartest and cheapest computing device is a mystery to the rest of the world.

One caveat however is that it is only fast smart and cheap in the Lusa Tonga language. 

 

Great Minds Do Not Think Alike… Even When They’re Artificial

August 12, 2023

The “Gettysburg Address” is a concise and powerful speech given by U.S. President Abraham Lincoln There have been a lot of articles written in the past six months or so about generative AI (GAI)[i], Large Language Models, and just about anything concerning Artificial Intelligence. So, I thought I’d compare what are probably the two sites that get the most attention. Many people are running experiments to see if they can figure out how these generative AI systems generate text under various conditions and assumptions. There is now a growing new skillset called “Prompt Engineering” which is being defined and refined that is making its way into the popular and professional imagination. Many people are already specializing in it to make a living in this post-GAI world.

I took two topics near and dear to my heart, Abraham Lincoln’s Gettysburg Address, and The Six Basic Interrogatives Framework for Data Analysis, aka 6BI. I then asked both OpenAI’s ChatGPT and Google’s Bard the same question. The prompt I used was very simple but had one big assumption built into it, specifically knowing what the abbreviation “6BI” stood for, without being prompted with a definition of it in the prompt box[ii]. This type of prompting is often referred to as Zero Shot prompting because it gives the model zero “shots” of relevant real time data to augment its training data, thus forcing it to rely solely on its current training to produce a response.

My prompt on August 21, 2023:

Apply the principles of 6BI to the Gettysburg Address.[iii]

ChatGPT’s response:

on November 19, 1863, shortly after the Battle of Gettysburg in the American Civil War. To apply the principles of 6BI (Six Basic Interrogatives) to the Gettysburg Address, we need to investigate it from the perspective of “who”, “what”, “when”, “where”, “why’, and “how’.

  1. Who: The “Gettysburg Address” was delivered by Abraham Lincoln, the 16th President of the United States, in front of an audience composed of citizens and soldiers.
  2. What: The “Gettysburg Address” is a brief, eloquent speech that helped redefine the purpose and meaning of the Civil War and the American union. The speech contains just 272 words, yet its message of equality, freedom, and the significance of a government “of the people, by the people, for the people” has endured for centuries.
  3. When: The “Gettysburg Address” was delivered on November 19, 1863, amidst the ongoing American Civil War.
  4. Where: The speech was given at the dedication of the Soldiers’ National Cemetery in Gettysburg, Pennsylvania, where one of the bloodiest and most significant battles of the Civil War had taken place just a few months prior.
  5. Why: Lincoln’s aim was to commemorate the Union soldiers who died at the Battle of Gettysburg and to motivate the living to continue the struggle for the preservation of the Union and the principles it was founded upon. He wanted to redefine the Civil War as not just a battle for the preservation of the Union, but also for the principles of human equality, and a “new birth of freedom.”
  6. How: Lincoln structured his speech in a way that was deeply rooted in the history and values of the United States. He began by evoking the founding principles of the United States (“Four score and seven years ago our fathers brought forth on this continent, a new nation, conceived in Liberty, and dedicated to the proposition that all men are created equal.”), moved on to the present struggle (“Now we are engaged in a great civil war, testing whether that nation, or any nation so conceived and so dedicated, can long endure.”), and concluded with a vision for the future (“…that this nation, under God, shall have a new birth of freedom—and that government of the people, by the people, for the people, shall not perish from the earth.”). The speech was brief, poignant, and delivered with a gravity befitting the occasion.

In sum, the 6BI approach offers a comprehensive way to dissect and analyze the Gettysburg Address, shedding light on its significance from various perspectives.

Bard’s response:

Sure, here are some ways to apply the principles of 6BI to the Gettysburg Address:

  • Brevity: The Gettysburg Address is only 272 words long, making it one of the shortest speeches ever delivered by a US president. This brevity helps to keep the speech focused and memorable.
  • Impact: The Gettysburg Address has had a profound impact on American history and culture. It is considered one of the most important speeches ever given, and it is often cited as an example of great oratory.
  • Clarity: The Gettysburg Address is clear and easy to understand. Lincoln uses simple language and straightforward sentences, which makes his message accessible to everyone.
  • Logic: The Gettysburg Address is logically structured. Lincoln begins by stating the purpose of his speech, then he provides evidence to support his claim, and finally he concludes with a call to action.
  • Immediacy: The Gettysburg Address is written in the present tense, which gives it a sense of immediacy. Lincoln speaks as if the events of the Civil War are happening right now, which makes his speech more powerful and urgent.
  • Universality: The Gettysburg Address is universal in its appeal. Lincoln’s message of equality and freedom is relevant to people all over the world.

These are just a few ways to apply the principles of 6BI to the Gettysburg Address. The speech is a masterpiece of oratory, and it is a testament to Lincoln’s skill as a communicator.

Here are some additional thoughts on how the principles of 6BI apply to the Gettysburg Address:

  • Brevity: The Gettysburg Address is brief, but it is not short on substance. Lincoln packs a lot of meaning into his 272 words, and he does so in a way that is both clear and concise.
  • Impact: The Gettysburg Address has had a profound impact on American history and culture. It is considered one of the most important speeches ever given, and it is often cited as an example of great oratory. Lincoln’s words helped to inspire the nation during the Civil War, and they continue to inspire people today.
  • Clarity: The Gettysburg Address is clear and easy to understand. Lincoln uses simple language and straightforward sentences, which makes his message accessible to everyone. He also avoids jargon and technical terms, which helps to ensure that his speech is understood by a wide audience.
  • Logic: The Gettysburg Address is logically structured. Lincoln begins by stating the purpose of his speech, then he provides evidence to support his claim, and finally he concludes with a call to action. This logical structure makes the speech easy to follow and understand.
  • Immediacy: The Gettysburg Address is written in the present tense, which gives it a sense of immediacy. Lincoln speaks as if the events of the Civil War are happening right now, which makes his speech more powerful and urgent. He also uses the word “here” to refer to the battlefield at Gettysburg, which further creates a sense of immediacy.
  • Universality: The Gettysburg Address is universal in its appeal. Lincoln’s message of equality and freedom is relevant to people all over the world. He speaks of the “unfinished work” of the Civil War, but he also speaks of the “great task remaining before us” as a nation. This suggests that the principles of equality and freedom are still relevant today, and that they are still worth fighting for.

The Gettysburg Address is a masterpiece of oratory, and it is a testament to Lincoln’s skill as a communicator. The principles of 6BI can help us to understand why[iv] the speech is so effective, and they can also help us to improve our own communication skills.

Brief Analysis of the Responses.

This article provides a comparison between the responses of ChatGPT and Bard when the same prompt is input to them. Specifically, to apply the principles of 6BI to the Gettysburg Address. It highlights the differences in their approaches brought about by both the data in their training and the algorithms processing it[v]. It is clear they were trained differently. It also shows the distinct approaches taken by each model.

The ChatGPT model emphasizes the six interrogatives, referring to them by their names, but not grouping them into a superset of aspects or dimensions as John Zachman[vi] originally did. The order of the interrogatives is changed from Zachman’s original order which, spread across two articles, was “What”, “How”, “Where”, “Who”, “When” and “Why”. The original articles were focused exclusively on business.

On the other hand, Bard focuses exclusively on Lincoln’s address itself, ignoring the six basic interrogatives.  Bard sites another set of aspects which are stated in terms of assertions and not interrogatives. These are: “Brevity”, “Impact”, “Clarity”, “Logic”, “Immediacy” and “Universality”.  These aspects don’t seem to be attributed to a single, original analysis of Lincoln’s Gettysburg Address[vii].

These aspects, insightful as they are in their own right, do not correctly answer the prompt. I will assume for the purposes of this article that the 6BI aspects were not included in the data on which the Bard model was trained. 

Though both John Zachman’s publications, my publications, and publications by several other writers on the same topic have been on the internet for more than 10 years, Bard either was not trained on that data, or its activation algorithms did not make the connection. This observation[viii], of course, is only as of the date of the prompt (see above).

The most pronounced feature of Bard’s response, in my opinion, is unlike Lincoln’s address itself, its lack of brevity.


[i] Not to be confused with AGI (Artificial General Intelligence).

[ii] It is also assumed, of course, that the LLMs have been pre-trained on the Gettysburg Address.

[iii] Please note the grammatically correct English sentence. I think it is important to prompt these models in language that is as well written (or spoken) as possible for reasons that I will discuss later.

[iv] One of the six basic interrogatives.

[v] This processing is basically, but not exclusively, Machine Learning (ML) and the data comes primarily from scraping the world wide web.

[vi] John Zachman originally published his two articles about the six aspects of enterprise architecture in 1987 and 1989.

[vii] Yes, I did ask both AI’s if they could site from whom, or where the assertive aspects came. Neither know.

[viii] Of course, I would not have been able to make that assertion had I not observed the data, or at least, that portion of it captured by the two subject models.

How to test if we’re living in a computer simulation

December 10, 2022

NASA, ESA, CSA, STScI

Melvin M. Vopson, University of Portsmouth

Physicists have long struggled to explain why the universe started out with conditions suitable for life to evolve. Why do the physical laws and constants take the very specific values that allow stars, planets and ultimately life to develop? The expansive force of the universe, dark energy, for example, is much weaker than theory suggests it should be – allowing matter to clump together rather than being ripped apart.

A common answer is that we live in an infinite multiverse of universes, so we shouldn’t be surprised that at least one universe has turned out as ours. But another is that our universe is a computer simulation, with someone (perhaps an advanced alien species) fine-tuning the conditions.

The latter option is supported by a branch of science called information physics, which suggests that space-time and matter are not fundamental phenomena. Instead, the physical reality is fundamentally made up of bits of information, from which our experience of space-time emerges. By comparison, temperature “emerges” from the collective movement of atoms. No single atom fundamentally has temperature.

This leads to the extraordinary possibility that our entire universe might in fact be a computer simulation. The idea is not that new. In 1989, the legendary physicist, John Archibald Wheeler, suggested that the universe is fundamentally mathematical and it can be seen as emerging from information. He coined the famous aphorism “it from bit”.

In 2003, philosopher Nick Bostrom from Oxford University in the UK formulated his simulation hypothesis. This argues that it is actually highly probable that we live in a simulation. That’s because an advanced civilisation should reach a point where their technology is so sophisticated that simulations would be indistinguishable from reality, and the participants would not be aware that they were in a simulation. https://www.youtube.com/embed/XVIlT-4xyrw?wmode=transparent&start=0

Physicist Seth Lloyd from the Massachusetts Institute of Technology in the US took the simulation hypothesis to the next level by suggesting that the entire universe could be a giant quantum computer.
And in 2016, business magnate Elon Musk concluded “We’re most likely in a simulation” (see video above).

Empirical evidence

There is some evidence suggesting that our physical reality could be a simulated virtual reality rather than an objective world that exists independently of the observer.

Any virtual reality world will be based on information processing. That means everything is ultimately digitised or pixelated down to a minimum size that cannot be subdivided further: bits. This appears to mimic our reality according to the theory of quantum mechanics, which rules the world of atoms and particles. It states there is a smallest, discrete unit of energy, length and time. Similarly, elementary particles, which make up all the visible matter in the universe, are the smallest units of matter. To put it simply, our world is pixelated.

The laws of physics that govern everything in the universe also resemble computer code lines that a simulation would follow in the execution of the program. Moreover, mathematical equations, numbers and geometric patterns are present everywhere – the world appears to be entirely mathematical.

Another curiosity in physics supporting the simulation hypothesis is the maximum speed limit in our universe, which is the speed of light. In a virtual reality, this limit would correspond to the speed limit of the processor, or the processing power limit. We know that an overloaded processor slows down computer processing in a simulation. Similarly, Albert Einstein’s theory of general relativity shows that time slows in the vicinity of a black hole.

Perhaps the most supportive evidence of the simulation hypothesis comes from quantum mechanics. This suggest nature isn’t “real”: particles in determined states, such as specific locations, don’t seem to exist unless you actually observe or measure them. Instead, they are in a mix of different states simultaneously. Similarly, virtual reality needs an observer or programmer for things to happen.

Quantum “entanglement” also allows two particles to be spookily connected so that if you manipulate one, you automatically and immediately also manipulate the other, no matter how far apart they are – with the effect being seemingly faster than the speed of light, which should be impossible.

This could, however, also be explained by the fact that within a virtual reality code, all “locations” (points) should be roughly equally far from a central processor. So while we may think two particles are millions of light years apart, they wouldn’t be if they were created in a simulation.

Possible experiments

Assuming that the universe is indeed a simulation, then what sort of experiments could we deploy from within the simulation to prove this?

It is reasonable to assume that a simulated universe would contain a lot of information bits everywhere around us. These information bits represent the code itself. Hence, detecting these information bits will prove the simulation hypothesis. The recently proposed mass-energy-information (M/E/I) equivalence principle – suggesting mass can be expressed as energy or information, or vice versa – states that information bits must have a small mass. This gives us something to search for.

I have postulated that information is in fact a fifth form of matter in the universe. I’ve even calculated the expected information content per elementary particle. These studies led to the publication, in 2022, of an experimental protocol to test these predictions. The experiment involves erasing the information contained inside elementary particles by letting them and their antiparticles (all particles have “anti” versions of themselves which are identical but have opposite charge) annihilate in a flash of energy – emitting “photons”, or light particles.

I have predicted the exact range of expected frequencies of the resulting photons based on information physics. The experiment is highly achievable with our existing tools, and we have launched a crowdfunding site) to achieve it.

There are other approaches too. The late physicist John Barrow has argued that a simulation would build up minor computational errors which the programmer would need to fix in order to keep it going. He suggested we might experience such fixing as contradictory experimental results appearing suddenly, such as the constants of nature changing. So monitoring the values of these constants is another option.

The nature of our reality is one of the greatest mysteries out there. The more we take the simulation hypothesis seriously, the greater the chances we may one day prove or disprove it.

Melvin M. Vopson, Senior Lecturer in Physics, University of Portsmouth

This article is republished from The Conversation under a Creative Commons license. Read the original article.

Evil Geniuses

July 22, 2022

Ad page purveyors are getting trickier. If you are like me, you probably get many, maybe dozens or even hundreds of unsolicited ad pages sent to your email every day. For many years I’ve just ignored them. Sometimes reading them, sometimes not and just deleting them. However, deleting does not make the sender go away. I had often read that one should not click on the unsubscribe link, as that only tells the sender, or more accurately his or her software, that a live person is at the other end of the connection.

Lately I’ve decided to just click “Unsubscribe” on the ad page… if I can find it… and see what happens. For the most part it works fine. Many senders really have stopped sending me their ads. Some have not, of course.

However, I’ve recently noticed a trickier thing they do. If appears that at least some percentage of the ad purveyors place the unsubscribe page outside of the security umbrella of their HTTPS link (i.e. the unsubscribe page has only an HTTP URL). This means that if you have a “watch dog” internet security system installed on your computing device you will get a message from it advising you that the page you requested is not secure, and do you want to proceed or go back. Some ad purveyors are now trying to scare users into staying subscribed.

If enough users, fearing what might happen if they venture into “unsecure” territory, choose to go back and not click the “Unsubscribe” button, then they (the ad purveyors) may not lose as many subscribers as they would if they had been just a little more transparent. In this way their ad site may not suffer the indignity of losing as many subscribers.

As always,

Have a rewarding compute

Starbucks Fantasy

July 15, 2022

She was a pretty girl.  Sweet actually.   A smile, bright eyes and a cheery acknowledgement of my presence across from her.  We made short term small talk and I asked her her name.  She told me and then, I could almost not believe it, she asked me mine.  My heart skipped a beat… she couldn’t really care what my name was, could she?

I told her… and she wrote it on the cup.

Don’t Look Up

February 17, 2022

The title obviously is ripped off from the 2021 Oscar nominated movie, but I thought it fit. Here in the Earth’s gravity well we are exposed to everything “out there”, even our own stuff which we have put out there, like satellites and space stations. 

Orbiting objects, especially the international space station, in orbiting the earth slowly accumulates an energy debt. This debt is the result of it’s borrowing energy from its surroundings to prevent it from falling out of the sky. Sooner or later this debt gets too high for the object to carry and it balances the books by falling down the gravity well back to earth. The fireball produced by that plunge is the removal of that debt.

This is kind of like the biologic death that happens to all of us. Sooner or later, local entropy, as it increases, wittles away at the bonds that hold together the matter of which we are made.  We breakup into smaller pieces of matter until the critical mass required to stay alive is passed and we “die”.

Here’s an interesting read on the topic.

https://theconversation.com/the-international-space-station-is-set-to-come-home-in-a-fiery-blaze-and-australia-will-likely-have-a-front-row-seat-176690?utm_medium=email&utm_campaign=Latest%20from%20The%20Conversation%20for%20February%2016%202022%20-%202202821848&utm_content=Latest%20from%20The%20Conversation%20for%20February%2016%202022%20-%202202821848+CID_8e10a0dcb5ad55d2fcc546e7c481066e&utm_source=campaign_monitor_uk&utm_term=The%20International%20Space%20Station%20is%20set%20to%20come%20home%20in%20a%20fiery%20blaze

Because we are usually much closer to the bottom of earth’s gravity well, we break apart much more slowly than the international space station will. Our “death” is usually far less firey and observed and recorded by far fewer witnesses and input sensors.

Wisdomtimes – 6 Interrogatives – The Mystery of Five W’s and One H

February 14, 2022

The following URL is a link to an article with a different and amusing take on The 6 Interrogatives:

Who, What, Where, When, Why and How. Hope you enjoy it.

http://www.wisdomtimes.com/blog/6-interrogatives-the-mystery-of-five-ws-and-one-h/

Regression to the Mean

May 20, 2021

Jack Bogle’s ghost warns about 401(k)s https://a.msn.com/r/2/BB1gUrmr?m=en-us&a=0  

As the article says “It’s worth taking a moment to reflect on just how good things have been for investors for a decade.”  But, “Enjoy making 12% a year, but don’t get used to it.”  It’s not going to last forever.