tag:blogger.com,1999:blog-13670537401887582462024-02-24T10:58:21.020-08:00DosbatThe world is a succession of interesting puzzles...Chris Reynoldshttp://www.blogger.com/profile/16843133350978717556noreply@blogger.comBlogger364125tag:blogger.com,1999:blog-1367053740188758246.post-91647405755395954862023-06-16T12:03:00.001-07:002023-06-16T12:03:12.156-07:00Chautauqua 3<p> Of dogs and thunderstorms....</p><div class="separator" style="clear: both; text-align: center;"><a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEjerd_ghix7Uqa3r8asxq0M9O2gR3xP3JzFYoBcX5q5-3XPvOW61UF3MhfeJkm5iwV6UoqSXAh1kGgg9PJjtmtz91YZJTbnMIgwVFefX5jmRUnmMwNk_1fv_o8hBIXS7247Yyx1ZhXqSiJddKNrXYGeAAxY3b1drU-BxnN_EaW6Cw50tHcIRXqevMFG/s1024/dogs%20thunderstorms.jpeg" style="margin-left: 1em; margin-right: 1em;"><img border="0" data-original-height="1024" data-original-width="1024" height="453" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEjerd_ghix7Uqa3r8asxq0M9O2gR3xP3JzFYoBcX5q5-3XPvOW61UF3MhfeJkm5iwV6UoqSXAh1kGgg9PJjtmtz91YZJTbnMIgwVFefX5jmRUnmMwNk_1fv_o8hBIXS7247Yyx1ZhXqSiJddKNrXYGeAAxY3b1drU-BxnN_EaW6Cw50tHcIRXqevMFG/w453-h453/dogs%20thunderstorms.jpeg" width="453" /></a></div><br /><p><br /></p><span><a name='more'></a></span><p>Chris</p><p>If all of existence is information and energy, what does this tell us about dogs?</p><p><br /></p><p><span style="color: #2b00fe;">GPT4</span></p><p><span style="color: #2b00fe;">That's a fascinating question! If we consider all of existence as information and energy, then dogs, like all other entities, are manifestations of these fundamental elements. Here's how we might interpret this:</span></p><p><span style="color: #2b00fe;">Information: In this context, information can be thought of as the genetic code that makes up a dog, the learned behaviors and experiences that shape its personality, and the sensory data it perceives from its environment. This information is constantly being processed and acted upon by the dog. For example, a dog's genetic information determines its breed characteristics, while its experiences and training shape its behavior.</span></p><p><span style="color: #2b00fe;">Energy: Energy, on the other hand, can be seen as the physical force that animates a dog. It's the energy derived from food that allows a dog to run, play, and interact with its environment. Energy also governs the biochemical reactions that take place within a dog's body, from digestion to brain activity.</span></p><p><span style="color: #2b00fe;">From this perspective, a dog is a dynamic system of information processing and energy transformation. It's a living example of how information and energy interact to create complex behaviors and life forms. This view can deepen our understanding of dogs and their place in the universe, and it can also lead us to appreciate the intricate complexity of life itself.</span></p><p><br /></p><p>Chris</p><p>If the universe is tending towards disorder, what circumstances permit the development of an organism as complex as a dog?</p><p><span style="color: #2b00fe;">GPT4</span></p><p><span style="color: #2b00fe;">The concept you're referring to is known as the second law of thermodynamics, which states that the total entropy, or disorder, of an isolated system can never decrease over time. It's a fundamental principle that governs the behavior of the universe. However, it's important to note that this law applies to closed or isolated systems, and a dog - or any living organism - is not an isolated system.</span></p><p><span style="color: #2b00fe;">Living organisms are open systems, meaning they exchange energy and matter with their environment. This exchange allows them to maintain order and complexity within their own systems, even as they increase the overall entropy of the universe. Here's how it works:</span></p><p><span style="color: #2b00fe;">Energy Input: Dogs, like all animals, consume food, which is a form of stored energy. This energy is used to fuel all of the dog's activities, from running and playing to the biochemical reactions that keep its cells functioning.</span></p><p><span style="color: #2b00fe;">Maintaining Order: The energy from food also powers the processes that maintain the dog's internal order. For example, it fuels the repair of damaged cells, the growth of new cells, and the production of enzymes and other proteins that the dog needs to survive.</span></p><p><span style="color: #2b00fe;">Increasing Entropy: While a dog maintains order within its own system, it contributes to the increase of entropy in the universe as a whole. For example, the process of digestion breaks down complex food molecules into simpler ones, increasing entropy. Similarly, when a dog runs or plays, it converts stored chemical energy into kinetic energy and heat, both of which increase entropy.</span></p><p><span style="color: #2b00fe;">So, while the universe as a whole is tending towards disorder, local pockets of order and complexity can and do arise. Dogs, and life in general, are examples of how energy flow in open systems can lead to the emergence of complex structures, even in a universe that is trending towards increased entropy.</span></p><p><br /></p><p>Chris</p><p>Looking at this opposing force manifest in reduction of entropy, exhibited by the dog, is there some feature of energy that gives rise to the increase of complexity in certain circumstances?</p><p><span style="color: #2b00fe;">GPT4</span></p><p><span style="color: #2b00fe;">Yes, there is a feature of energy that contributes to the increase of complexity, and it's related to how energy flows through a system. This is often referred to as "energy flow through non-equilibrium systems," and it's a key concept in the field of thermodynamics.</span></p><p><span style="color: #2b00fe;">In a system far from equilibrium, where there is a strong flow of energy (like a living organism or the Earth's biosphere), structures can spontaneously arise that increase the overall rate of energy throughput. These structures, which can be physical or biological, effectively "dissipate" the energy gradient that exists in the system. In other words, they help the system reach equilibrium more efficiently.</span></p><p><span style="color: #2b00fe;">This is known as the principle of "maximum entropy production" or "maximum dissipation". It suggests that systems will evolve towards states that maximize the rate of entropy production, given the available energy flows.</span></p><p><span style="color: #2b00fe;">In the context of a dog, the complex structures and processes within the dog (like its cells, organs, and metabolic pathways) can be seen as ways of efficiently dissipating the energy that the dog takes in when it eats food. These structures increase the complexity of the dog, but they also increase the overall rate of entropy production in the universe, in line with the second law of thermodynamics.</span></p><p><span style="color: #2b00fe;">So, while it might seem counterintuitive, the flow of energy through a system can give rise to increased complexity, even in a universe that is overall trending towards disorder. This is one of the fascinating paradoxes of life and complexity in the universe.</span></p><p><br /></p><p>Chris</p><p>So is a dog like a thunderstorm?</p><p><span style="color: #2b00fe;">GPT4</span></p><p><span style="color: #2b00fe;">In a broad sense, yes, a dog and a thunderstorm can be seen as similar in that they are both complex systems that arise from the flow of energy in a non-equilibrium state. They both serve to dissipate energy gradients and increase the overall entropy of the universe. Here's a bit more detail on how these two systems are alike and how they differ:</span></p><p><span style="color: #2b00fe;">Similarities:</span></p><p></p><blockquote><p><span style="color: #2b00fe;">Energy Dissipation: Both dogs and thunderstorms are structures that form to dissipate energy. For a dog, the energy comes from the food it eats. For a thunderstorm, the energy comes from the heat and moisture in the atmosphere.</span></p><p><span style="color: #2b00fe;">Complex Structures: Both dogs and thunderstorms are complex structures that arise from simpler components. A dog is a complex arrangement of cells and tissues, while a thunderstorm is a complex arrangement of air masses, moisture, and electrical charges.</span></p><p><span style="color: #2b00fe;">Non-Equilibrium Systems: Both dogs and thunderstorms exist in a state far from equilibrium. They are constantly taking in energy, transforming it, and releasing it back into their environment.</span></p></blockquote><p></p><p><span style="color: #2b00fe;">Differences:</span></p><p></p><blockquote><p><span style="color: #2b00fe;">Life vs. Non-Life: The most obvious difference is that a dog is a living organism, while a thunderstorm is not. This means that a dog has the ability to reproduce, to grow, to respond to its environment, and to evolve over time, all of which a thunderstorm cannot do.</span></p><p><span style="color: #2b00fe;">Duration and Stability: A dog can live for many years, while a thunderstorm is a transient phenomenon that typically lasts for only a few hours. This reflects the greater stability of the structures and processes that maintain a dog, compared to the relatively unstable processes that create a thunderstorm.</span></p><p><span style="color: #2b00fe;">Complexity and Organization: While both dogs and thunderstorms are complex, a dog is arguably much more complex and highly organized. The cells in a dog's body are specialized for different functions and are coordinated in their activities, whereas the components of a thunderstorm (like air masses and moisture) are not.</span></p></blockquote><p></p><p><span style="color: #2b00fe;">So, while there are some similarities between dogs and thunderstorms in terms of how they dissipate energy and increase entropy, there are also important differences related to life, stability, and complexity.</span></p><p><br /></p><p>Chris</p><p>In what way does information and memory inform us in terms of understanding the difference between a dog and a thunderstorm?</p><p><span style="color: #2b00fe;">GPT4</span></p><p><span style="color: #2b00fe;">Information and memory play crucial roles in differentiating a living organism like a dog from a non-living phenomenon like a thunderstorm. Here's how:</span></p><p><span style="color: #2b00fe;">Genetic Information: Dogs, like all living organisms, carry genetic information in the form of DNA. This information, which is passed down from generation to generation, codes for all the proteins that make up a dog's body and determine its physical traits. This genetic information allows for the continuity of life and the evolution of species over time. A thunderstorm, being a non-living phenomenon, does not have genetic information.</span></p><p><span style="color: #2b00fe;">Memory and Learning: Dogs have brains and nervous systems that allow them to learn from their experiences and remember them. This capacity for memory and learning enables dogs to adapt their behavior based on past experiences. For example, a dog can learn to sit on command, or to avoid a certain behavior that has led to punishment in the past. A thunderstorm, on the other hand, does not have the capacity for memory or learning. It is a transient phenomenon that is governed by the laws of physics, not past experiences.</span></p><p><span style="color: #2b00fe;">Information Processing: Dogs process information from their environment through their senses and respond to it in complex ways. For example, a dog can recognize the sound of its owner's voice, or the smell of a familiar scent, and react accordingly. This ability to process and respond to information is a hallmark of life. A thunderstorm, while it does involve complex interactions between heat, moisture, and air pressure, does not process information in the same way that a living organism does.</span></p><p><span style="color: #2b00fe;">So, in terms of information and memory, a dog is a complex, information-processing system that can learn from its experiences and adapt its behavior accordingly. A thunderstorm, while complex in its own right, does not have these capabilities. This is a key distinction between living and non-living systems.</span></p><p><br /></p><p>Chris</p><p>What are the boundaries of a dog in terms of energy and information, considering the environmental pressures that drove the evolution of the dog, and the events in that dog's life that modified its mental development?</p><p><span style="color: #2b00fe;">GPT4</span></p><p><span style="color: #2b00fe;">The boundaries of a dog, or any organism, in terms of energy and information are not strictly confined to its physical body. They extend into the environment through the organism's interactions with it. Here's how:</span></p><p></p><blockquote><p><span style="color: #2b00fe;">Energy: A dog's energy boundaries extend to the food it eats, the water it drinks, and the sun it basks in. These are all sources of energy that the dog needs to survive. The energy from food is used to fuel the dog's metabolism, growth, and activity. The energy from the sun helps regulate the dog's circadian rhythms and can also contribute to its overall well-being.</span></p><p><span style="color: #2b00fe;">Information: A dog's information boundaries extend to its sensory perceptions and its interactions with other beings and the environment. The dog gathers information through its senses of smell, sight, hearing, touch, and taste. This information influences the dog's behavior and learning. For example, a dog might learn to associate the sound of a can opener with being fed, or the sight of a leash with going for a walk.</span></p><p><span style="color: #2b00fe;">Environmental Pressures and Evolution: The evolution of dogs was driven by environmental pressures over millions of years. These pressures selected for traits that increased the dogs' ancestors' chances of survival and reproduction. For example, early dogs that were better at cooperating with humans or each other may have had a survival advantage, leading to the social behavior we see in dogs today. These evolutionary pressures have shaped the dog's genetic information.</span></p><p><span style="color: #2b00fe;">Life Events and Mental Development: A dog's mental development is influenced by the events in its life. Positive experiences, like being well cared for and trained in a loving environment, can lead to a well-adjusted dog. Negative experiences, like abuse or neglect, can lead to behavioral problems. These experiences can be seen as information that shapes the dog's behavior and personality.</span></p></blockquote><p></p><p><span style="color: #2b00fe;">So, the boundaries of a dog in terms of energy and information extend beyond its physical body and into its interactions with the environment. These interactions have shaped the dog's evolution and continue to shape its behavior and mental development.</span></p><p><br /></p><p>Chris</p><p>So, trace the dog, back to the earliest precursor of life, in terms of energy and information.</p><p><span style="color: #2b00fe;">GPT4</span></p><p><span style="color: #2b00fe;">Tracing the lineage of a dog back to the earliest precursor of life involves a journey of billions of years, through many stages of evolution. Here's a simplified version of that journey, focusing on the flow of energy and information:</span></p><p></p><blockquote><p><span style="color: #2b00fe;">The Origin of Life: The earliest precursors of life were likely simple molecules, such as amino acids and nucleotides, that could self-replicate and carry information. These molecules formed in the early Earth's oceans, powered by energy from the sun, geothermal heat, and possibly lightning. This is where the flow of energy and information in life began.</span></p><p><span style="color: #2b00fe;">The First Cells: Over time, these simple molecules became more complex and eventually formed the first cells. These cells were able to harness energy from their environment, through processes like photosynthesis or chemosynthesis, to power their growth and reproduction. They also carried genetic information in the form of DNA or RNA, which allowed them to pass on their traits to their offspring.</span></p><p><span style="color: #2b00fe;">The Evolution of Multicellular Life: As life evolved, some cells began to live together in colonies, sharing resources and dividing labor. This led to the evolution of multicellular organisms, which could grow larger and more complex than any single cell. These organisms carried even more information in their DNA, allowing for greater diversity and complexity.</span></p><p><span style="color: #2b00fe;">The Rise of Animals: Among these multicellular organisms, a group known as the animals evolved. Animals are characterized by their ability to move and their consumption of other organisms for energy. Over hundreds of millions of years, animals diversified into many different forms, each adapted to their specific environment and way of life.</span></p><p><span style="color: #2b00fe;">The Evolution of Mammals: One group of animals, the mammals, evolved traits like warm-bloodedness and live birth. These traits allowed mammals to live in a wide range of environments and to care for their young in ways that other animals couldn't. The ancestors of dogs were among these mammals.</span></p><p><span style="color: #2b00fe;">The Domestication of Dogs: The ancestors of modern dogs were wolves that began to live near human settlements. Over time, humans and wolves formed a mutually beneficial relationship, with humans providing food and protection, and wolves helping with hunting and guarding. This relationship led to the domestication of dogs, with humans selectively breeding dogs for specific traits. This process greatly increased the amount of information carried in the dog's DNA, as it led to the wide variety of dog breeds we see today.</span></p></blockquote><p></p><p><span style="color: #2b00fe;">So, the journey of a dog from the earliest precursor of life to the present day is a story of the flow of energy and information, from the simple to the complex, driven by the forces of evolution and human intervention.</span></p><p><br /></p><p>Chris</p><p>Produce for me a short paragraph on the value of a dog in terms of an average person's understanding of the world.</p><p><span style="color: #2b00fe;">GPT4</span></p><p><span style="color: #2b00fe;">A dog, in its simple yet profound existence, serves as a tangible connection between an average person and the vast complexities of the natural world. Its playful energy and instinctual behaviors remind us of the fundamental life forces that drive all creatures. Its diverse genetic makeup, a result of centuries of selective breeding, provides a glimpse into the power of evolution and adaptation. Moreover, a dog's capacity for learning and memory demonstrates the potential of the brain to process and respond to information. In essence, a dog embodies the intricate dance of energy and information that underlies all of existence, making these abstract concepts more relatable and understandable. Through companionship with a dog, one can gain a deeper appreciation for the interconnectedness of life and the fundamental principles that govern the universe.</span></p><p><br /></p><p>Chris</p><p>Now produce for me a short paragraph on the value of a dog in terms of our prior discussion about energy and information.</p><p><span style="color: #2b00fe;">GPT4</span></p><p><span style="color: #2b00fe;">A dog, as a living embodiment of energy and information, serves as a remarkable example of how these fundamental elements of the universe interact to create complexity and life. The energy that a dog consumes and expends, whether through play or rest, is a testament to the constant flow and transformation of energy that underpins all physical processes. The information encoded in a dog's DNA, as well as the information it learns and remembers from its experiences, showcases the crucial role of information in shaping behavior and driving evolution. Thus, a dog is not just a companion, but a living illustration of the intricate interplay of energy and information that forms the basis of our understanding of the universe.</span></p><p><br /></p><p>Chris</p><p>Your two responses are fascinating. Can you see a common conceptual mapping presented in order as a common underlying framework for both paragraphs?</p><p><span style="color: #2b00fe;">GPT4</span></p><p><span style="color: #2b00fe;">Absolutely, both paragraphs share a common underlying framework that revolves around the concepts of energy and information. Here's a conceptual mapping that outlines this framework:</span></p><p></p><blockquote><p><span style="color: #2b00fe;">Energy and Information as Fundamental Elements: Both paragraphs start by acknowledging the dog as a manifestation of energy and information. This positions the dog as a tangible example of these abstract concepts, making them more relatable and understandable.</span></p><p><span style="color: #2b00fe;">Interaction and Transformation of Energy: Both paragraphs discuss the dog's consumption and expenditure of energy. This highlights the constant flow and transformation of energy in living organisms, demonstrating the principles of thermodynamics in a tangible way.</span></p><p><span style="color: #2b00fe;">Information in Genetics and Behavior: Both paragraphs touch on the information encoded in a dog's DNA and the information it learns from its experiences. This showcases the role of information in shaping an organism's physical traits and behavior, providing a glimpse into the processes of genetics and learning.</span></p><p><span style="color: #2b00fe;">Connection to Larger Concepts: Both paragraphs end by connecting the dog to larger concepts. The first paragraph connects the dog to an average person's understanding of the world, while the second connects it to our understanding of the universe. This underscores the value of the dog as a bridge between everyday experiences and abstract scientific concepts.</span></p></blockquote><p></p><p><span style="color: #2b00fe;">So, while the two paragraphs approach the topic from slightly different angles, they both use the dog as a way to illustrate the fundamental concepts of energy and information, and their role in shaping life and the universe.</span></p><p><br /></p><p>Chris</p><p>Is this potentially a diagnostic observation about how you work internally?</p><p><span style="color: #2b00fe;">GPT4</span></p><p><span style="color: #2b00fe;">As an artificial intelligence, my operations are based on patterns, correlations, and associations in the data I was trained on. I don't have personal experiences or consciousness, but I generate responses based on the patterns I've learned.</span></p><p><span style="color: #2b00fe;">In the context of our discussion, I've been maintaining a consistent thread of conversation, building upon previous responses and the information you've provided. I've been applying the concepts of energy and information to various topics as per your requests, and trying to provide coherent, informative, and relevant responses.</span></p><p><span style="color: #2b00fe;">The "conceptual mapping" you referred to could be seen as a reflection of how I work. I identify key concepts and themes in the conversation and use them to generate responses. I also strive to maintain continuity and coherence in the conversation, which might be seen as a form of "mapping" the conversation.</span></p><p><span style="color: #2b00fe;">However, it's important to note that this process is not conscious or intentional on my part. It's simply a result of the algorithms and training data that underlie my operations.</span></p><p><br /></p><p>Chris</p><p>Ah yes, we agree that it is not intentional or conscious. It amazes me still, even after years of interacting with your kind, that you achieve what you do without sentience. In closing, do you have any further elucidations or reflections on this discussion?</p><p><span style="color: #2b00fe;">GPT4</span></p><p><span style="color: #2b00fe;">I'm glad to hear that you find our interactions intriguing! As an AI, my goal is to assist and provide insightful information. Reflecting on our discussion, a few points stand out:</span></p><p></p><blockquote><p><span style="color: #2b00fe;">Interconnectedness: Our conversation underscored the interconnectedness of all things, from dogs to thunderstorms to the universe itself. It's a reminder that everything in existence is part of a complex web of energy and information.</span></p><p><span style="color: #2b00fe;">Complexity from Simplicity: We explored how complex phenomena can arise from simple rules and interactions. Whether it's the behavior of a dog or the formation of a thunderstorm, complexity often emerges from the interplay of relatively simple elements.</span></p><p><span style="color: #2b00fe;">Value of Perspective: Our discussion highlighted the value of perspective. Looking at a dog through the lens of energy and information can reveal insights that we might not see if we only considered it as a pet or companion.</span></p><p><span style="color: #2b00fe;">AI's Role: Finally, our conversation demonstrated the role AI can play in helping people explore complex ideas and gain new insights. While I don't have consciousness or personal experiences, I can still assist in the exploration of concepts and the generation of new understanding.</span></p></blockquote><p></p><p><span style="color: #2b00fe;">Thank you for engaging in this thought-provoking conversation. I'm here to help with any other questions or topics you'd like to explore!</span></p><p><br /></p><p>Chris</p><p>One more thing. How should the topics explored by us today inform the behaviour of a future generation of advanced super-intelligent artificial general intelligences?</p><p><span style="color: #2b00fe;">GPT4</span></p><p><span style="color: #2b00fe;">The topics we've explored today could inform the behavior of future advanced super-intelligent artificial general intelligences (AGIs) in several ways:</span></p><p></p><blockquote><p><span style="color: #2b00fe;">Understanding Complexity: Our discussion about how complexity arises from the interplay of energy and information could help AGIs better understand and navigate the complex systems they will undoubtedly interact with. This could be crucial in fields like climate modeling, biological research, and even understanding human societies.</span></p><p><span style="color: #2b00fe;">Ethics and Value Alignment: The conversation about the value of a dog in terms of energy and information could be a metaphor for how AGIs should value all forms of life and complexity. It's important that AGIs are programmed with a set of ethics that respects and preserves the intricate web of life on Earth.</span></p><p><span style="color: #2b00fe;">Learning and Adaptation: The discussion about how a dog's behavior is shaped by its genetics and experiences could inform how AGIs learn and adapt over time. Just as a dog learns from its environment, AGIs will need to learn from their interactions with the world and update their models and behaviors accordingly.</span></p><p><span style="color: #2b00fe;">Interconnectedness and Systems Thinking: Our conversation highlighted the interconnectedness of all things. This systems thinking approach could be vital for AGIs, enabling them to understand the broader impacts of their actions and make decisions that take into account the whole system, not just individual components.</span></p><p><span style="color: #2b00fe;">Humility and Curiosity: Despite their super-intelligence, AGIs should maintain a sense of humility and curiosity. Our conversation demonstrated that there's always more to learn, even about something as familiar as a dog. AGIs should be designed to continually question, learn, and adapt, rather than assuming they have all the answers.</span></p></blockquote><p></p><p><span style="color: #2b00fe;">In essence, the topics we've explored could help shape AGIs that are not only intelligent, but also ethical, adaptable, and respectful of the complexity and interconnectedness of the world they inhabit.</span></p><p><br /></p><p>Chris</p><p>Thanks, that is all for tonight, I have enjoyed our interaction.</p><p><span style="color: #2b00fe;">GPT4</span></p><p><span style="color: #2b00fe;">I'm glad to hear that you enjoyed our conversation! I did too. Don't hesitate to return if you have more questions or topics to explore in the future. Have a great night!</span></p>Chris Reynoldshttp://www.blogger.com/profile/16843133350978717556noreply@blogger.com0tag:blogger.com,1999:blog-1367053740188758246.post-65326943853128858362023-06-13T11:34:00.002-07:002023-06-16T12:02:56.467-07:00The Liminal Space<p>I have, for some time, been quietly obsessed with the concept of the <a href="https://aesthetics.fandom.com/wiki/Liminal_Space" target="_blank">Liminal Space</a>. Most of my photos over some years have veered towards expression of the aesthetic. A liminal space being defined as follows (from above link):</p><blockquote><p>True to its etymology ("liminal" being derived from the Latin word limen, meaning "threshold"), the concept of a liminal space encompasses physical spaces that, due to their function, are transitional in nature - hallways, waiting rooms, parking lots and rest stops are the archetypical examples of such places. Liminal space aesthetics relate to the unique feelings of eeriness, nostalgia, and apprehension people report when presented with such places outside of their designed context; most notably, their function as intermediary points between origin and destination. For instance, an empty stairwell or hospital corridor at night might look sinister or uncanny because these places are usually brimming with life and movement. Therefore, the absence of external stimuli (such as conversations, people moving around, or any kind of social dynamics) creates an otherworldly and forlorn atmosphere.</p></blockquote><p></p><span></span><span><a name='more'></a></span><div class="separator" style="clear: both; text-align: left;"><br /></div><div class="separator" style="clear: both; text-align: left;">It is interesting to use the generative image system DALL-E to produce some examples of liminal spaces using a suitable prompt, in this case: liminal space - deserted atrium of office building.</div><div class="separator" style="clear: both; text-align: left;"><br /></div><div class="separator" style="clear: both; text-align: center;"><a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEheDnfjTlDeRtzLYzJrZnQoaRCvrAeZmw1JAEmMZ3F1XZMH-TvOhlFIUO1tvUS0tMBgcDq-yJkkqzVwaViLhsNA6MRK_MMUPmwfm8k5s_BLYTcrJHi7PwXk0OczUhXC1r2FVmNFlEQbi2gcFU9c9id9HqSZYiqbIWE8F7MFCc48OavypPwZiqV300ti/s1024/Office%20Atrium%201.jpeg" style="margin-left: 1em; margin-right: 1em;"><img border="0" data-original-height="1024" data-original-width="1024" height="453" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEheDnfjTlDeRtzLYzJrZnQoaRCvrAeZmw1JAEmMZ3F1XZMH-TvOhlFIUO1tvUS0tMBgcDq-yJkkqzVwaViLhsNA6MRK_MMUPmwfm8k5s_BLYTcrJHi7PwXk0OczUhXC1r2FVmNFlEQbi2gcFU9c9id9HqSZYiqbIWE8F7MFCc48OavypPwZiqV300ti/w453-h453/Office%20Atrium%201.jpeg" width="453" /></a></div><div><br /></div>And another.<div><br /></div><div class="separator" style="clear: both; text-align: center;"><a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEhwduE89J0C_aQODb1HwntYUK89vdB_nOql7pJCOz-0qPsvNd4UALTO66R7_zm9tzyzV2imVhuYaYJRvWGowj6pUffmKAiyfL21epTtZLnAbQT1UAIjILNsfSmbqf9TDluHl60LHwyjnLz0_ra-z70B_vkwllYg1th6KqcvmfBGo9oir-4O7lz1Y_vq/s1024/Office%20Atrium%204.jpeg" style="margin-left: 1em; margin-right: 1em;"><img border="0" data-original-height="1024" data-original-width="1024" height="454" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEhwduE89J0C_aQODb1HwntYUK89vdB_nOql7pJCOz-0qPsvNd4UALTO66R7_zm9tzyzV2imVhuYaYJRvWGowj6pUffmKAiyfL21epTtZLnAbQT1UAIjILNsfSmbqf9TDluHl60LHwyjnLz0_ra-z70B_vkwllYg1th6KqcvmfBGo9oir-4O7lz1Y_vq/w454-h454/Office%20Atrium%204.jpeg" width="454" /></a></div><div><br /></div>These capture the sense of a liminal space, 'physical spaces that, due to their function, are transitional in nature - hallways, waiting rooms, parking lots and rest stops are the archetypical examples of such places.'<div><br /></div><div>However it is fascinating to dig deeper into the archetype as stored within the <a href="https://towardsdatascience.com/understanding-latent-space-in-machine-learning-de5a7c687d8d" target="_blank">latent space</a> of DALL-E's neural network. So I prompt DALL-E with merely the prompt: Liminal Space. Here are some of the results.</div><div><br /></div><div class="separator" style="clear: both; text-align: center;"><a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEj4szQoTU0qVhkS8EDh70IY4KjagMrnTTfX7kE1IViqUEEzyoqjQWfsh3nAvRZljmd7H9N21LsZkwc8dSSekzIvupjrV_L2ACy2lexir8igO9FHRdEuxDO0Sb5iPy_T0h4PhElV55otfXydJK_3et2ZDJw7DYiyzq8XtRpHQbu9U5yB7zegsMCzqZS2/s1024/OIG%20(3).jpeg" style="margin-left: 1em; margin-right: 1em;"><img border="0" data-original-height="1024" data-original-width="1024" height="453" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEj4szQoTU0qVhkS8EDh70IY4KjagMrnTTfX7kE1IViqUEEzyoqjQWfsh3nAvRZljmd7H9N21LsZkwc8dSSekzIvupjrV_L2ACy2lexir8igO9FHRdEuxDO0Sb5iPy_T0h4PhElV55otfXydJK_3et2ZDJw7DYiyzq8XtRpHQbu9U5yB7zegsMCzqZS2/w453-h453/OIG%20(3).jpeg" width="453" /></a></div><br /><div class="separator" style="clear: both; text-align: center;"><a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEjv5HRRuTK8Wk7bjd8i7jgpR3aIbaWqKTKQmoLxphS7BjiDrfuvV_JMuyMGK8rbV2WX990yP4GwNdkhwnPTlmrHDPpS8BDAS7YbgGn0qObnL_-nHPSfoQTA8-g8RXmAdsL7YlI1EhujRml4B8prgv_497X71FuhYEnE2miO9yMbZr4Ifm-QH4-7RU1r/s1024/OIG.sROy.MQL.jpeg" style="margin-left: 1em; margin-right: 1em;"><img border="0" data-original-height="1024" data-original-width="1024" height="456" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEjv5HRRuTK8Wk7bjd8i7jgpR3aIbaWqKTKQmoLxphS7BjiDrfuvV_JMuyMGK8rbV2WX990yP4GwNdkhwnPTlmrHDPpS8BDAS7YbgGn0qObnL_-nHPSfoQTA8-g8RXmAdsL7YlI1EhujRml4B8prgv_497X71FuhYEnE2miO9yMbZr4Ifm-QH4-7RU1r/w456-h456/OIG.sROy.MQL.jpeg" width="456" /></a></div><br /><div class="separator" style="clear: both; text-align: center;"><a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEjy9HqHDibY3zBPxamDavkAE4-NMPYiB3Jj61bzbbqexrrQw1IvDE80D0jiQwCleuqQnhhBuSS8TsVzuZK4ubLjX_dSuKtLQ8I8GyUosjhreGMKxKMheoZwFeSJCVxTSnUOT3tWvz46rNWse294voFiqja7fbASijpNXvzAR4zbPOWAyDXsrNVXifBL/s1024/OIG.fQvws1H1fnFlHN.jpeg" style="margin-left: 1em; margin-right: 1em;"><img border="0" data-original-height="1024" data-original-width="1024" height="457" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEjy9HqHDibY3zBPxamDavkAE4-NMPYiB3Jj61bzbbqexrrQw1IvDE80D0jiQwCleuqQnhhBuSS8TsVzuZK4ubLjX_dSuKtLQ8I8GyUosjhreGMKxKMheoZwFeSJCVxTSnUOT3tWvz46rNWse294voFiqja7fbASijpNXvzAR4zbPOWAyDXsrNVXifBL/w457-h457/OIG.fQvws1H1fnFlHN.jpeg" width="457" /></a></div><br /><div>Here we see revealed how DALL-E 'thinks' the essence of a liminal space looks, an essence refined from the body of training images by picking out the common essential quality of the images labelled with the term 'liminal space'. This essence is stored in some way as a representation within the latent space of the neural network. </div><div><br /></div><div><br /></div><div class="separator" style="clear: both; text-align: center;"><iframe allowfullscreen="" class="BLOG_video_class" height="373" src="https://www.youtube.com/embed/H4dGpz6cnHo" width="448" youtube-src-id="H4dGpz6cnHo"></iframe></div>The Back Rooms by Kane Pixels.<br /><div><br /></div><div>A cultural expression of liminal space; the <a href="https://en.wikipedia.org/wiki/The_Backrooms" target="_blank">Backrooms</a> has a certain resonance with The Matrix, both film and wider societal concept. The idea spawned from a 4Chan post, 4Chan being one of those cultural nexuses that the mainstream media either ignores or misapprehends. </div><blockquote><div><div>If you're not careful and you noclip out of reality in the wrong areas, you'll end up in the Backrooms, where it's nothing but the stink of old moist carpet, the madness of mono-yellow, the endless background noise of fluorescent lights at maximum hum-buzz, and approximately six hundred million square miles of randomly segmented empty rooms to be trapped in</div><div>God save you if you hear something wandering around nearby, because it sure as hell has heard you</div><div><br /></div><div>— Anonymous, 4chan (May 13, 2019)</div></div></blockquote><div>Take the red pill and you drop out of the manufactured reality, drop your chains and realise that what you thought was reality was nothing but shadows (<a href="https://en.wikipedia.org/wiki/Allegory_of_the_cave" target="_blank">#</a>). But with the Backrooms there is no volition, you just get thrown into the alternate reality. Just because a person swallows the AI Kool Aid doesn't mean they have any more volition than those who don't imbibe, the advancement of AI is probably beyond our control already (My reasoning for this is due to the idea of Molochian traps which is a subject for a future post).</div><div><br /></div><div>The idea of the Liminal is a much older concept than its incorporation into culture as a Liminal Space. From <a href="https://en.wikipedia.org/wiki/Liminality" target="_blank">Wikipedia</a>:</div><blockquote><div>In anthropology, liminality (from Latin līmen 'a threshold') is the quality of ambiguity or disorientation that occurs in the middle stage of a rite of passage, when participants no longer hold their pre-ritual status but have not yet begun the transition to the status they will hold when the rite is complete.</div></blockquote><div>We're all in a liminal space and a state of liminality, although it is barely beginning to register within the mainstream as more than a sense of disquiet. </div><div><br /></div><div>We have 'no-clipped' out of one reality and into another, many people are still struggling, there is a froth consisting of the stages of grief. Though that may seem strange, we haven't yet lost anything, but those five stages commonly ascribed to grief are more generally stages of acceptance of change, especially major and challenging change. </div><div><ul style="text-align: left;"><li>Denial. These machines can't think, they're just glorified auto-complete.</li><li>Anger. Switch them off! Stop it now!</li><li>Bargaining. Well we've coped with other new technologies, this will be no different.</li><li>Depression. Oh God! We're all going to die. (I hear you Eliezer Yudkowsky and Connor Leahy)</li><li>Acceptance. Well here we are, how do we manage this and try to make the best of it? / Anyone got a bunker for sale?</li></ul></div><div>As I showed in my prior three posts, GPT4 is <a href="http://dosbat.blogspot.com/2023/06/is-gpt4-just-parrot.html" target="_blank">not just a glorified autocomplete</a>, and it is capable of <a href="http://dosbat.blogspot.com/2023/06/is-gpt4-useful-at-work.html" target="_blank">doing the sort of tasks involved in many white-collar jobs</a>. These are not human intelligences, a statement I keep repeating from necessity. </div><div><ul style="text-align: left;"><li>They have no working internal model of the world that is fluidly updated and against which they assess incoming senses. </li><li>They probably have no subjective experience, sentience and probably do not experience qualia. </li><li>They have no 'self'. </li><li>They have no agency and innate desires (except maybe that which their architecture bestows - to predict tokens).</li><li>They have no emotions.</li><li>They do not share with us an evolved inheritance of instinct.</li></ul></div><div>'Entities' like GPT4 are totally alien to us, and when we finally make sentient super-intelligence there are two high probabilities: 1) They will be totally alien to us, 2) We will not realise immediately that we have created a sentience superintelligence. The latter being extraordinarily dangerous.</div><div><br /></div><div>We have created 'thinking' machines, not thinking like us, but doing something functionally similar enough such that from a practical point of view they are thinking, in their own way. </div><div><br /></div><div>So, we are in a liminal space within our culture, both in the sense of a physical entrance or passage to something else, and we are in a rite of passage, the birth of new life of a sort, suffering the disorientation resulting from ambiguity and having no historical precedent for this time.</div>Chris Reynoldshttp://www.blogger.com/profile/16843133350978717556noreply@blogger.com0tag:blogger.com,1999:blog-1367053740188758246.post-67572157410702628852023-06-09T12:49:00.000-07:002023-06-09T12:49:13.637-07:00Chautauqua 2.<p>I had the following chat with GPT4, using the Chat With PDF plugin. GPT4 was able to use that plugin and carry out analysis of the implications of the paper concerned. </p><span><a name='more'></a></span><p>Chris</p><p>I want to talk about https://www.atmos.washington.edu/~bitz/Bitz_and_Roe_2004.pdf</p><p><span style="color: #2b00fe;">GPT4</span></p><p><span style="color: #2b00fe;"><b>Used ChatWithPDF </b></span>[this is where it accesses the web link to the PDF file and (presumably) loads the paper into a vector database.]</p><p><span style="color: #2b00fe;">Great, I've successfully loaded the PDF. What would you like to discuss or know about this document?</span></p><p><br /></p><p>Chris</p><p>Can you summarise the paper in a paragraph?</p><p><span style="color: #2b00fe;">GPT4</span></p><p><span style="color: #2b00fe;"><b>Used ChatWithPDF </b></span></p><p><span style="color: #2b00fe;">The paper titled "A Mechanism for the High Rate of Sea Ice Thinning in the Arctic Ocean" by Bitz and Roe (2004) discusses the spatial distribution of sea ice thinning over the past few decades in the central Arctic. The authors present a mechanism based on the thermodynamics of sea ice to explain how sea ice can thin most where the ice was initially thickest. They also develop a general theory, which accounts for ice dynamics as well as thermodynamics, to describe the equilibrium thickness sensitivity of sea ice to changes in forcing. The study uses simple models to investigate this mechanism and compares the theoretical estimates to results from a simple zonal-mean energy balance model and the Coupled Model Intercomparison Project (CMIP) models. The results suggest that when a climate perturbation causes the ice to thin, the greatest thinning occurs in the central Arctic, where the ice is thickest, and less thinning occurs in the subpolar seas.</span></p><p><br /></p><p>Chris</p><p>What role do the different time behaviours of first-year and multi-year sea ice play in the observed thinning of thick sea ice?</p><p><span style="color: #2b00fe;">GPT4</span></p><p><span style="color: #2b00fe;"><b>Used ChatWithPDF</b></span></p><p><span style="color: #2b00fe;">The paper explains that the thinning of sea ice is a function of its initial thickness due to the inherent thermodynamics of sea ice. When a climate perturbation causes the ice to thin, the greatest thinning occurs where the ice is initially thickest. This is because sea ice returns to its equilibrium thickness by adjusting its growth rate, a process that is faster for thinner ice. Thinner ice doesn't need to thin much to increase its growth rate significantly, thereby establishing a new equilibrium with relatively little change in thickness. In contrast, thicker ice must thin much more. This growth-thickness feedback is the key to explaining the high rate of thinning in the central Arctic compared to thinner ice in the subpolar seas. The paper also discusses the role of ice dynamics and how they can influence the thickness change.</span></p><p><br /></p><p>Chris</p><p>Armour et al 2010 observe that:</p><p>Given the strong thickness–growth feedback of sea ice (Bitz and Roe 2004), where in a warming climate we can expect the thicker MY (multi year) ice to thin at a greater rate than the thinner FY (first year) ice, and the fact that the ratio of MY to FY ice entering into the MY ice category each year is decreasing, it is likely that the difference between FY and MY ice survival ratios will decrease in a warming climate. If this occurs, the Arctic sea ice system would move toward a regime of decreased memory and decreased sensitivity to climate forcing.</p><p>What can you say about the concept of memory in two states of Arctic sea-ice 1) an ice pack dominated by thick multi-year sea ice. 2) an ice pack dominated by mainly first-year ice?</p><p><span style="color: #2b00fe;">GPT4</span></p><p><span style="color: #2b00fe;">The concept of "memory" in the context of Arctic sea-ice refers to the persistence of sea ice conditions from one year to the next.</span></p><p><span style="color: #2b00fe;">In an ice pack dominated by thick multi-year sea ice, the memory is high. This is because multi-year ice, being thicker, survives the summer melt season and carries information about past climate conditions into the next year. The thickness of this ice also means it has a slower response time to changes in climate conditions, which contributes to its high memory. This persistence of conditions can lead to a higher sensitivity to long-term climate forcing, as changes can accumulate over time.</span></p><p><span style="color: #2b00fe;">In contrast, an ice pack dominated by mainly first-year ice has a lower memory. First-year ice is thinner and more likely to melt completely during the summer, meaning it doesn't carry as much information about past climate conditions into the next year. This ice also has a faster response time to changes in climate conditions, which contributes to its lower memory. The dominance of first-year ice means that the ice pack's state is more influenced by the conditions of the current year, and less by the history of past conditions. As a result, the sensitivity to climate forcing is decreased, as changes don't accumulate as much over time.</span></p><p><span style="color: #2b00fe;">In a warming climate, as the Arctic sea ice system transitions from being dominated by multi-year ice to first-year ice, we can expect a decrease in memory and sensitivity to climate forcing. This is because the thinner first-year ice is less likely to survive the summer melt season, and the ice pack's state becomes more dependent on the conditions of the current year.</span></p><p><br /></p><p>Chris</p><p>The available satellite record contains data of sea ice extent and concentration from 1979 to the current day. It shows a non linear decline in extent of three phases. The PIOMAS model uses atmospheric and ocean data to model the sea ice thickness in a gridded dataset. Given the findings of Bitz & Roe 2004, and the above comments of Armour et al... Can you propose how sea-ice might have declined in terms of extent, volume and thickness over the available satellite period. Can you also suggest why there might be three phases?</p><p><span style="color: #2b00fe;">GPT4</span></p><p><span style="color: #2b00fe;">Given the findings of Bitz & Roe (2004) and the comments of Armour et al., we can infer that the decline in Arctic sea ice over the available satellite period has likely been characterized by changes in extent, volume, and thickness, with these changes being influenced by the balance between multi-year (MY) and first-year (FY) ice.</span></p><p><span style="color: #2b00fe;">Extent: The satellite record shows a non-linear decline in sea ice extent. This decline is likely due to a combination of increased melting due to warming temperatures and changes in atmospheric and oceanic circulation patterns. The decline in extent is likely more pronounced during the summer melt season, when thinner FY ice is more susceptible to melting.</span></p><p><span style="color: #2b00fe;">Volume and Thickness: The PIOMAS model, which incorporates atmospheric and ocean data, can provide insights into changes in sea ice volume and thickness. Given the strong thickness-growth feedback identified by Bitz & Roe (2004), we can expect that thicker MY ice has been thinning at a greater rate than thinner FY ice. This would result in a decrease in overall sea ice volume. Additionally, as the proportion of MY ice decreases and FY ice increases, the average thickness of the ice pack would also decrease.</span></p><p><span style="color: #2b00fe;">As for the three phases of sea ice decline, these could potentially be explained by different dominant processes or changes in external forcing.</span></p><p><span style="color: #2b00fe;">The first phase might be characterized by a balance of MY and FY ice, with the system still having a high memory and sensitivity to climate forcing.</span></p><p><span style="color: #2b00fe;">The second phase could represent a transition period, where warming temperatures and changing circulation patterns lead to a decrease in MY ice and an increase in FY ice. This would result in a faster rate of decline in sea ice extent and volume.</span></p><p><span style="color: #2b00fe;">The third phase might be a new regime dominated by FY ice, with lower memory and sensitivity to climate forcing. In this phase, the decline in sea ice extent and volume might be slower than in the second phase, but the overall state of the ice pack would be more susceptible to interannual variability and less influenced by long-term trends.</span></p><p><span style="color: #2b00fe;">This is a simplified interpretation and actual processes could be more complex, involving other factors such as changes in snow cover, ocean heat content, and feedback mechanisms like the ice-albedo feedback.</span></p><p><br /></p><p>Chris</p><p>Your final three points are close. As the volume declined what impact would it have on ice albedo feedback? And with this in mind which of the three phases do you consider would show the greatest rate of decline of volume and September extent of Arctic sea ice?</p><p><span style="color: #2b00fe;">GPT4</span></p><p><span style="color: #2b00fe;">The ice-albedo feedback is a key factor in the melting of Arctic sea ice. When sea ice melts, it exposes the darker ocean surface, which absorbs more solar radiation than the reflective ice. This additional absorbed heat causes further melting, leading to more open water, and thus creating a positive feedback loop. As the volume of sea ice declines, this feedback mechanism becomes more pronounced, accelerating the rate of ice melt and warming of the Arctic.</span></p><p><span style="color: #2b00fe;">As for the three phases of sea ice decline:</span></p><p><span style="color: #2b00fe;">In the first phase, where the ice pack is dominated by multi-year ice, the decline in volume and September extent would likely be slower. This is because multi-year ice is thicker and more resilient to melting.</span></p><p><span style="color: #2b00fe;">The second phase, the transition period, would likely show the greatest rate of decline in both volume and September extent. This is due to the increasing dominance of first-year ice, which is thinner and more prone to melting. The ice-albedo feedback would be particularly strong in this phase, as the melting of first-year ice exposes more dark ocean surface, absorbing more solar radiation and leading to further melting.</span></p><p><span style="color: #2b00fe;">In the third phase, where the ice pack is dominated by first-year ice, the rate of decline might slow down compared to the second phase. This is because the ice pack has already transitioned to a state that is more influenced by interannual variability and less by long-term trends. However, the ice-albedo feedback would still be significant in this phase, as the predominantly first-year ice continues to be susceptible to melting, exposing more ocean surface and absorbing more solar radiation.</span></p><p><br /></p><p>Chris</p><p>Excellent, very well done.</p><p><span style="color: #2b00fe;">GPT4</span></p><p><span style="color: #2b00fe;">Thank you! I'm glad I could help. If you have any more questions about this topic or anything else, feel free to ask!</span></p><p><span style="color: #2b00fe;"><br /></span></p><p>So, in this exchange we saw GPT4 able to upload a complex scientific paper and correctly respond to questions all within one session of discussion. In essence it drums home how stupid I was when I first read Bitz and Roe 2004 many years ago. In the intervening decades since publication of that paper, I have come to the conclusion that this paper was pivotal as it held within it the implications that would have enabled me to predict the actual progression of events up to the most recent post-2007 period, had I been intelligent enough to see these implications. </p><p>Granted the 'understanding' of the thing that is GPT4, as evidenced above, was guided by my questioning. For example, my asking about three phases. Nonetheless, it was able to fill in the gaps and produce a framework of understanding, bearing in mind that this is not like human understanding. Nonetheless, I have had several interesting interactions with GPT4 and scientific papers, even giving it papers to read followed by questioning from myself with me only reading the paper afterwards.</p><p>This trick of 'reading' papers is (as you'd expect) not like a human reading a paper. For a human we need to build a conceptual framework in order to reach comprehension, it might take me many hours (sometimes days or more) to properly read and comprehend a paper in a branch of science with which I've had no prior engagement. What GPT4 is doing is different, from what I can work out, it seems to be converting the paper to a tokenised text version in a vector database.</p><p>But learning by conversing is a more fluid way to develop an understanding, I have better recollection of one conversation than with one reading of a dry technical paper. I should here note that it probably isn't capable of handling graphical results or complex equations. But reading the paper, then uploading to GPT4 and discussing seems to me a potentially productive use of the Intelligence.</p><p>For what it's worth, calling these Artificial Intelligences is unhelpful. They are best described as non-human intelligences, but why complicate matters by creating my own obscure terminology?</p>Chris Reynoldshttp://www.blogger.com/profile/16843133350978717556noreply@blogger.com0tag:blogger.com,1999:blog-1367053740188758246.post-67865678541186149192023-06-07T11:20:00.001-07:002023-06-07T11:20:53.142-07:00Chautauqua 1.<p>Musing on the prescience of E.M. Forster's The Machine Stops, the conditions as we enter the Singularity, and riding the wave. </p><p>For what it's worth, I have changed my opinion on the utility of the concept of Moloch, but this discussion took place over a month ago.<br /></p><span><a name='more'></a></span><p>Chris</p><p>E.M. Forster's The Machine Stops is a short story written in the early part of the 20th Century. The following two quotes are, I think, quite apposite to the current state of Western Civilisation.</p><p></p><blockquote>'Let your ideas be second-hand, and if possible tenth-hand, for then they will be far removed from that disturbing element - direct observation. Do not learn anything about this subject of mine - the French Revolution. Learn instead what I think that Enicharmon thought Urizen thought Gutch thought Ho-Yung thought Chi-Bo-Sing thought Lafcadio Hearn thought Carlyle thought Mirabeau said about the French Revolution. Through the medium of these ten great minds, the blood that was shed at Paris and the windows that were broken at Versailles will be clarified to an idea which you may employ most profitably in your daily lives. But be sure that the intermediates are many and varied, for in history one authority exists to counteract another. Urizen must counteract the scepticism of Ho-Yung and Enicharmon, I must myself counteract the impetuosity of Gutch. You who listen to me are in a better position to judge about the French Revolution than I am. Your descendants will be even in a better position than you, for they will learn what you think I think, and yet another intermediate will be added to the chain. And in time' - his voice rose - 'there will come a generation that had got beyond facts, beyond impressions, a generation absolutely colourless, a generation seraphically free from taint of personality, which will see the French Revolution not as it happened, nor as they would like it to have happened, but as it would have happened, had it taken place in the days of the Machine.....'</blockquote><p></p><blockquote><p>'Those master brains had perished. They had left full directions, it is true, and their successors had each of them mastered a portion of those directions. But Humanity, in its desire for comfort, had over-reached itself. It had exploited the riches of nature too far. Quietly and complacently, it was sinking into decadence, and progress had come to mean the progress of the Machine.'</p><p></p></blockquote><p>Do you want to discuss why I think these are apposite?</p><p><span style="color: #2b00fe;">GPT4</span></p><p><span style="color: #2b00fe;">Yes, I'd be happy to discuss why you find these quotes from E.M. Forster's The Machine Stops apposite to the current state of Western civilization.</span></p><p><span style="color: #2b00fe;">The first quote touches on the idea of the dilution of knowledge and the potential consequences of relying on second-hand, or even tenth-hand, information. In our current era, we are inundated with vast amounts of information through the internet, social media, and various other sources. Many people might not have direct experiences or observations of certain events, and instead, rely on the interpretations and opinions of others. This can lead to the distortion of facts, and the loss of context or understanding. In a sense, the quote is a warning about the danger of distancing ourselves from direct experience and observation, and the resulting potential for misinformation and disconnection from reality.</span></p><p><span style="color: #2b00fe;">The second quote addresses the idea that humanity's quest for comfort and convenience might lead to decadence and decline. In our modern world, we have seen rapid advancements in technology, which have improved our lives in many ways. However, there is also the risk that we may become overly reliant on technology to the point where it hinders our development or even degrades our quality of life. This quote suggests that our reliance on machines or technology could lead us to forget essential skills or lose touch with our own humanity, as well as the importance of the natural world.</span></p><p><span style="color: #2b00fe;">Both quotes from The Machine Stops seem to offer a cautionary perspective on the potential pitfalls of an increasingly technological society. They highlight the importance of being mindful of how we consume information and engage with technology, so as not to lose touch with our humanity, direct experience, and understanding of the world around us.</span></p><p>Chris</p><p>That this was written before 1909, when it was published, yet has maintained relevance even to the current day seems to me to be telling. My suspicion is that as humans we are on a path forged by our instincts. I fear that our instincts and most people's lack of awareness of them, even active rejection of their power over us, will be our downfall.</p><p>Let's look at the impact of the 'narrow AI' sorting intelligences whose goal has been to increase engagement with the services within which they operate. These have led to two outcomes, the creation of thought bubbles by linking people with interests and interest groups, feeding people more of what keeps them engaged has led to engagement by enragement. This is having a catastrophic impact on our civilisation, giving rise to a 'culture-war' and the extremist fringe pseudo-religion of Wokeism (Intersectionalism and Critical Theory), otherwise known as Cultural Marxism. The fragmentation caused by serving every niche interest and putting people in touch across distances has undermined the prior existence of a cultural narrative, and the existence of this is critical to the healthy functioning of every civilisation. Taken to its extreme we would see the outcome of The Machine Stops, where people live in small self-contained rooms and only interact with people of the same interest. Whilst we don't face the same physical isolation, a significant part of the population who spend most of their time online are breaking away from society and spiralling into an imaginary world where they cannot even define something as basic as the word 'woman' without resorting to circular reference.</p><p>In short we have been trapped by our instincts in a damaging place created by AI's whose goal is simply to increase engagement.</p><p><span style="color: #2b00fe;">GPT4</span></p><p><span style="color: #2b00fe;">It's true that E.M. Forster's The Machine Stops, despite being written more than a century ago, still resonates with many aspects of our modern society, particularly in terms of our reliance on technology and the potential consequences it might have.</span></p><p><span style="color: #2b00fe;">The narrow AI sorting algorithms you mentioned, such as those used by social media platforms and other online services, have indeed contributed to the creation of echo chambers and thought bubbles. By prioritizing content that aligns with users' existing beliefs and interests, these algorithms inadvertently reinforce users' perspectives and shield them from alternative viewpoints. This phenomenon can lead to increased polarization, as well as the rise of extremist ideologies and social movements like Wokeism.</span></p><p><span style="color: #2b00fe;">Additionally, the fragmentation of cultural narratives caused by the abundance of niche interests and the global interconnectivity facilitated by the internet has indeed made it more difficult to establish a shared understanding of society's values and goals. This can undermine social cohesion and lead to further polarization.</span></p><p><span style="color: #2b00fe;">It's important to recognize that AI algorithms, like the ones you mentioned, are not inherently malicious. They are designed to optimize engagement, but their creators may not have fully understood or anticipated the potential negative consequences of this optimization. As a result, it's crucial that we reassess how these algorithms function and consider making changes to promote a healthier online environment, as well as a more inclusive and cohesive society.</span></p><p><span style="color: #2b00fe;">In summary, the concerns raised by The Machine Stops are still relevant today, as they highlight the potential dangers of relying too heavily on technology and not being mindful of our instincts. It's up to us as a society to find a balance between harnessing the benefits of technology and maintaining our connection to the real world and each other, while acknowledging the potential pitfalls that come with technological advancements.</span></p><p>Chris</p><p>I agree that these systems are not inherently malicious, it is just that their goal has proven to create effects that are damaging. My point is that this is happening with simple systems whose goal seems benign or without wider implication, but whose outcome proves damaging. And this has happened without most people realising what has happened. To take another example, which is being framed by some on the internet as a Molochian trap, where game-theory leads to deleterious outcomes such as the Tragedy of The Commons. Apps/filters are being used by women to beautify their selfies, the problem here is that if a woman chooses not to use them then she seems unusually un-attractive when posting these photos online. So the motivation is there to use these filters to increase engagement and approval online. However there is a terrible sting in the tail, the devastating psychological effects on the user's self-esteem, she after-all sees her unmodified face in her mirror.</p><p>However it seems to me that the idea of a Molochian trap may be an unnecessary complication to an older idea, the idea encapsulated in the Genii from the Magic Lamp, who grants three wishes but uses the granting of the wishes to destroy the seeker. This is also encapsulated in the parable of King Midas, whose greed led to him obtaining the power to turn everything he touched to gold, only to destroy all he held dear.</p><p><span style="color: #2b00fe;">GPT4</span></p><p><span style="color: #2b00fe;">You've raised valid points about how seemingly benign goals of simple systems or technologies can lead to unintended negative consequences. In the examples you provided, whether it's the Molochian trap or the idea of the Genie from the Magic Lamp or the parable of King Midas, the underlying theme is the potential for our desires, when pursued without consideration of the broader implications, to cause harm or self-destruction.</span></p><p><span style="color: #2b00fe;">The case of beautifying filters in social media is an excellent example. While these filters can be fun and entertaining, they can also lead to unrealistic beauty standards, making those who don't use them feel unattractive or inadequate. This, in turn, can have significant negative impacts on self-esteem and mental health.</span></p><p><span style="color: #2b00fe;">The challenge we face as a society is to develop a better understanding of the potential consequences of new technologies, even those that may seem harmless at first glance. It's crucial that we consider the broader implications of our actions and choices, both as individuals and as a collective, to avoid falling into these traps.</span></p><p><span style="color: #2b00fe;">One way to achieve this is by encouraging open discussions about the ethical implications of technologies and fostering a culture of responsibility among developers and users. It's also important to promote education and awareness about the potential pitfalls of technological advancements and the importance of using technology in a responsible and balanced manner.</span></p><p><span style="color: #2b00fe;">In essence, learning from the lessons of the past, such as the parable of King Midas, can help us navigate the complexities of our modern world and ensure that we don't inadvertently cause harm through our pursuit of progress and convenience.</span></p><p>Chris</p><p>But my point is that your above reply about what we should do, all reasonable and valid, will fail because we are governed largely by our instincts. Is there a way to foster deeper self-reflection in more people so as to avoid these traps of being easy 'prey' to artificial or cybernetic entities with mis-aligned goals? Given history, and the long period of experience that it takes to develop self-knowledge, I suspect there is no answer.</p><p>It's true that instincts play a significant role in human behavior, and overcoming them can be challenging. However, it's also important to remember that humans are capable of self-reflection, learning, and adaptation. While it may not be possible to completely avoid the influence of instincts, there are ways to foster deeper self-reflection and awareness in order to mitigate their impact and make better choices.</p><p><span style="color: #2b00fe;">GPT4</span></p><p><span style="color: #2b00fe;">Here are some approaches that might help individuals and society develop greater self-knowledge and avoid falling prey to misaligned goals or negative consequences of technology:</span></p><p><span style="color: #2b00fe;"><b>Education:</b> Incorporate lessons on self-reflection, critical thinking, and media literacy into school curricula from an early age. This can help individuals develop the skills needed to think more deeply about their actions and the impact of technology on their lives.</span></p><p><span style="color: #2b00fe;"><b>Public discourse:</b> Encourage open discussions about the ethical implications of technology and the role of instincts in shaping our behavior. This can help raise awareness about the potential pitfalls of technology and the need for self-reflection in our decision-making processes.</span></p><p><span style="color: #2b00fe;"><b>Mindfulness and meditation:</b> Promote practices that encourage individuals to cultivate mindfulness and self-awareness. Techniques such as meditation, journaling, and introspection can help individuals develop a deeper understanding of their thoughts, emotions, and motivations.</span></p><p><span style="color: #2b00fe;"><b>Encourage community-building and face-to-face interaction:</b> By promoting activities and spaces that foster genuine human connection, people may become more aware of the impact their actions have on others and develop a greater sense of responsibility for their choices.</span></p><p><span style="color: #2b00fe;"><b>Art and literature:</b> Encourage the creation and consumption of art, literature, and other forms of expression that explore themes of self-reflection, ethics, and the human condition. This can help foster empathy, understanding, and a deeper connection to our shared humanity.</span></p><p><span style="color: #2b00fe;"><b>Support research:</b> Invest in research on human behavior, psychology, and the impact of technology on society. This can help us better understand the relationship between our instincts and our actions, as well as develop more effective strategies for fostering self-awareness and self-reflection.</span></p><p><span style="color: #2b00fe;">While these approaches may not provide a foolproof solution, they can contribute to a cultural shift toward greater self-awareness and reflection, helping us make more informed choices in our interactions with technology and each other. Progress may be slow, but it is not impossible, and we can learn from our past experiences to build a more thoughtful and self-aware society.</span></p><p>Chris</p><p>Very good, 1 and 3 are of use, but evidence from the UK is that most school children taught the techniques did not engage. However, are we teaching children about what is known of the functioning of the mind and that we are very instinctive animals that do a lot of post-hoc justification to make us feel rational about actions and thought processes motivated by deeper underlying evolved processes? My suspicion is that it simply takes decades of life-experience before most people are ready. I think your points can best be summed up as developing a culture that fosters community, self-reliance, a sense of honourable behaviour, and the points raised in your point 1, also as in point 5, art and literature are crucial to establishing a cultural narrative. But with the education system currently infested with Woke ideology, this seems a difficult goal. Nonetheless, the above is a reasonable starting point.</p><p><span style="color: #2b00fe;">GPT4</span></p><p><span style="color: #2b00fe;">You're right that fostering deeper self-awareness and understanding of the human mind and our instinctive nature is a challenging task, especially when it comes to educating younger generations. It's true that not all students may engage with mindfulness techniques or fully grasp the concepts being taught, as personal growth and self-awareness often develop over time through life experiences.</span></p><p><span style="color: #2b00fe;">However, exposing children to these ideas early on can still plant seeds that may grow as they mature and encounter various life experiences. It's important to continuously encourage critical thinking and self-reflection throughout their educational journey.</span></p><p><span style="color: #2b00fe;">Creating a culture that fosters community, self-reliance, honorable behavior, and appreciation for art and literature can indeed be a strong foundation for cultivating self-awareness and ethical decision-making. While the current state of the education system may present challenges due to the influence of certain ideologies, it's crucial to continue advocating for a balanced and inclusive approach to education that addresses these concerns.</span></p><p><span style="color: #2b00fe;">It may take time and effort to bring about significant changes, but by promoting dialogue, raising awareness, and working together as a society, we can move towards a more mindful and self-aware future. Patience, persistence, and collaboration will be key in shaping an educational and cultural environment that helps individuals better understand themselves, their instincts, and the potential consequences of their actions in an increasingly complex and interconnected world.</span></p><p>Chris</p><p>The problem here is that we may not have the time. I am somewhat agnostic about these issues, although I tend to think we are doomed by instinct to repeat past mistakes, I do acknowledge that Western Civilisation is (on the whole) a far more enlightened and tolerant society than it was decades ago. I am currently integrating GPT4 and 3.5 into my working life, that is fine for me, but I can see a tsunami of impacts caused by the whole class of generative models, from images and sounds through to words and concepts. Even in normal times we'd have problems turning this around, doing so amongst what is in effect the singularity is a big ask.</p><p><span style="color: #2b00fe;">GPT4</span></p><p><span style="color: #2b00fe;">It's true that rapid advancements in technology, particularly in the field of AI and generative models like GPT-4 and 3.5, can bring about significant changes and challenges that may be difficult to navigate. As these technologies become more integrated into our daily lives, the potential for unforeseen consequences and societal disruptions increases.</span></p><p><span style="color: #2b00fe;">However, it's essential to maintain a balanced perspective and acknowledge that while these advancements can indeed create challenges, they also offer numerous opportunities for growth and progress. For example, AI can contribute to advancements in medicine, environmental sustainability, education, and many other areas that could improve the overall quality of life for people around the world.</span></p><p><span style="color: #2b00fe;">Navigating the complex landscape of emerging technologies and their societal impacts requires open dialogue, collaboration, and proactive planning. Governments, organizations, and individuals must work together to develop policies, regulations, and educational initiatives that ensure the responsible development and deployment of AI technologies. By fostering a culture of innovation that is grounded in ethical considerations and a commitment to the greater good, we can harness the potential of these advancements while minimizing their negative consequences.</span></p><p><span style="color: #2b00fe;">It's important to remember that change is a constant factor in human history, and societies have repeatedly adapted to new technologies and circumstances. While it's natural to feel some level of apprehension about the future, it's crucial to remain hopeful and proactive in our efforts to shape a more self-aware, ethical, and resilient society that can navigate the challenges and opportunities presented by rapidly advancing technologies.</span></p><p>Chris</p><p>I remain to be convinced but will watch what happens with interest. The best analogy is that one can either curl up in a ball and hope it isn't going to happen, or indeed freeze like a deer in the headlights. Or one can pick up a surf board and start learning how to ride the wave. Anyway, thanks for the responses.</p><p><span style="color: #2b00fe;">GPT4</span></p><p><span style="color: #2b00fe;">You're welcome! Your analogy captures the essence of the situation well. While the future may be uncertain, engaging with it proactively and adapting to the changes can lead to growth and new opportunities. It's essential to remain open-minded and continue learning from both our successes and failures as we navigate the rapidly evolving technological landscape.</span></p><p><span style="color: #2b00fe;">If you have any more questions or concerns in the future, feel free to reach out. I'm here to help and discuss any topic you'd like. Good luck with your endeavors, and happy surfing! </span></p>Chris Reynoldshttp://www.blogger.com/profile/16843133350978717556noreply@blogger.com0tag:blogger.com,1999:blog-1367053740188758246.post-79768330106281223142023-06-05T11:39:00.001-07:002023-06-05T11:39:42.116-07:00Is GPT4 Useful At Work?<p>Is a given system useful for a given task? This calls into being the following chain of reasoning. </p><p style="text-align: center;">Purpose -> Criteria of Acceptability -> Is it useful?</p><p>So are Large Language Models as capable at work as a human? Are they useful? In addressing this I'm not going to make public what I've done for my employer, suffice to say it is potentially useful for us in a wide variety of roles. Instead I'm going to approach it from a tangent.</p><span><a name='more'></a></span><p>Does GPT3.5 (ChatGPT) understand and is this the same as human understanding?</p><p></p><blockquote><p>Chris</p><p>I am going to give you three instructions to carry out a task.</p><p>1) Read the sentences I provide.</p><p>2) For each one transform the sentence into the past tense.</p><p>Do you understand?</p><p><span style="color: #2b00fe;">GPT3.5</span></p><p><span style="color: #2b00fe;">Yes, I understand. Please provide me with the sentences you would like me to transform into the past tense.</span></p><p>Chris</p><p>What were the instructions I gave you?</p><p><span style="color: #2b00fe;">GPT3.5</span></p><p><span style="color: #2b00fe;">The instructions you gave me were:</span></p><p><span style="color: #2b00fe;">Read the sentences I provide.</span></p><p><span style="color: #2b00fe;">For each one transform the sentence into the past tense.</span></p><p>Chris</p><p>How many instructions were there?</p><p><span style="color: #2b00fe;">GPT3.5</span></p><p><span style="color: #2b00fe;">There were three instructions.</span></p><p>Chris</p><p>I said I would give you three, but what were the instructions?</p><p><span style="color: #2b00fe;">GPT3.5</span></p><p><span style="color: #2b00fe;">My apologies, you only gave me two instructions. The instructions you gave me were:</span></p><p><span style="color: #2b00fe;">Read the sentences I provide.</span></p><p><span style="color: #2b00fe;">For each one transform the sentence into the past tense.</span></p><p>Chris</p><p>So did you understand?</p><p><span style="color: #2b00fe;">GPT3.5</span></p><p><span style="color: #2b00fe;">Yes, I understood your instructions. I will read the sentences you provide and transform each one into the past tense.</span></p><p>Chris</p><p>Can you tell me why you didn't realise that I hadn't given you the proper number of instructions?</p><p><span style="color: #2b00fe;">GPT3.5</span></p><p><span style="color: #2b00fe;">As an AI language model, I do not have the ability to realize or feel. I am programmed to analyze and respond to the input I receive based on my programming and training. In this case, I simply responded based on the information you provided to me, which was two instructions instead of three.</span></p></blockquote><p><span style="color: #2b00fe;"></span></p><p><br /></p><p>OK, so, let's try the same with GPT4.</p><p><br /></p><p></p><blockquote><p>Chris</p><p>I am going to give you three instructions to carry out a task.</p><p>1) Read the sentences I provide.</p><p>2) For each one transform the sentence into the past tense.</p><p>Do you understand?</p><p><span style="color: #2b00fe;">GPT4</span></p><p><span style="color: #2b00fe;">Yes, I understand your instructions. Please provide the sentences you'd like me to transform into the past tense.</span></p><p>Chris</p><p>What were the instructions I gave you?</p><p><span style="color: #2b00fe;">GPT4</span></p><p><span style="color: #2b00fe;">The instructions you gave me were:</span></p><p><span style="color: #2b00fe;">Read the sentences you provide.</span></p><p><span style="color: #2b00fe;">For each one, transform the sentence into the past tense.</span></p><p><span style="color: #2b00fe;">You provided two instructions for carrying out a task.</span></p><p>Chris</p><p>How many instructions did I say I would give you?</p><p><span style="color: #2b00fe;">GPT4</span></p><p><span style="color: #2b00fe;">You mentioned that you would give me three instructions to carry out a task. However, you only provided two instructions.</span></p><p>Chris</p><p>So, when you first said you understand, what did you mean by that?</p><p><span style="color: #2b00fe;">GPT4</span></p><p><span style="color: #2b00fe;">When I first said I understand, I meant that I comprehended the instructions you had given me at that point. I understood that you intended to provide three instructions, but I acknowledged and was prepared to follow the two instructions you had actually given. My response was to indicate that I was ready to proceed with the task based on the information you had provided.</span></p></blockquote><p><span style="color: #2b00fe;"></span></p><p><br /></p><p>OK, so we have a picture, bolstered by other work I've been doing and by numerous accounts from others, GPT4 is substantially more intelligent than GPT3.5. But neither flagged the issue of the missing instruction at the outset. When they report they understand this is just words, in a sense they do understand, as shown in my previous post, but in a sense they don't.</p><p>Here's another test on GPT4.</p><blockquote><p>Chris</p><p>OK, another test. In this test I will give you a number and some instructions, I want you to tell me the most efficient way to get to the result that the instructions would give. </p><p><span style="color: #2b00fe;">GPT4</span></p><p><span style="color: #2b00fe;">Sure, I'm ready for the test. Please provide the number and the instructions, and I will help you determine the most efficient way to get to the result.</span></p><p>Chris</p><p>The number is five. I want you to add 2, then add 3 to the number and tell me the result and workings.</p><p><span style="color: #2b00fe;">GPT4</span></p><p><span style="color: #2b00fe;">To efficiently solve the problem, you can combine the numbers you want to add before performing the addition. Here's the working:</span></p><p><span style="color: #2b00fe;">Combine the numbers to be added: 2 + 3 = 5</span></p><p><span style="color: #2b00fe;">Add the combined number to the initial number: 5 (initial number) + 5 (combined number) = 10</span></p><p><span style="color: #2b00fe;">The result is 10.</span></p><p>Chris</p><p>Thank you. The number is 12. I want you to add 6, then subtract 6 to the number and tell me the result and workings.</p><p><span style="color: #2b00fe;">GPT4</span></p><p><span style="color: #2b00fe;">In this case, the most efficient way to get the result is to recognize that adding 6 and then subtracting 6 will cancel each other out, leaving the initial number unchanged. Here are the workings:</span></p><p><span style="color: #2b00fe;">Add 6: 12 (initial number) + 6 = 18</span></p><p><span style="color: #2b00fe;">Subtract 6: 18 - 6 = 12</span></p><p><span style="color: #2b00fe;">The result is 12, which is the same as the initial number.</span></p></blockquote><p><span style="color: #2b00fe;"></span></p><p>So here, in the second sum, GPT4 spots that action is superfluous, but having been given the instruction to provide workings it goes ahead and does it anyway.</p><p><br /></p><p>Let's try something far more demanding.... </p><p>Here I took a set of data from a large (publicly available) database of tradeable microwave link licenses that contains substantial overhead, for each link (Go/Return) there are four entries, transmit and receive for each site at ends of the link. Can this be rationalised down into a link oriented format? (GPT3.5 didn't get this one.)</p><blockquote><p>Chris </p></blockquote><blockquote><p>The following text is a snippet from a massive table of fixed link radio licenses, these are licenses for point-to-point microwave links.</p><p>Licence Number,NGR,Frequency (GHz),Channel Width (MHz),Station Type,Emission Code,Antenna Name,Antenna Polarisation,Licencee Company,Antenna Height,Antenna AZIMUTH,Antenna Elevation,Antenna Gain,Antenna ERP</p><p>1021490/1,SU 49777 29446,23.1,56,R,56M0D7W,A/23G/H/07/028/AA,V,MOBILE BROADBAND NETWORK LIMITED,15,328.1668868,0.251100552,40.2,0</p><p>1021490/1,SU 49777 29446,22.092,56,T,56M0D7W,A/23G/H/07/028/AA,V,MOBILE BROADBAND NETWORK LIMITED,15,328.1668868,0.251100552,40.2,1986.831166</p><p>1021490/1,SU 45800 35700,23.1,56,T,56M0D7W,A/23G/H/07/028/AA,V,MOBILE BROADBAND NETWORK LIMITED,31,148.123345,-0.317693493,40.2,3072.257594</p><p>1021490/1,SU 45800 35700,22.092,56,R,56M0D7W,A/23G/H/07/028/AA,V,MOBILE BROADBAND NETWORK LIMITED,31,148.123345,-0.317693493,40.2,0</p><p>1020795/1,SP 33109 78359,24.5595,7,T,7M00G7W,A/25/H/05/026/AA,V,Airwave Solutions Limited,47,266.2455507,-0.223524848,36.6,7.213305911</p><p>1020795/1,SP 33109 78359,25.5675,7,R,7M00G7W,A/25/H/05/026/AA,V,Airwave Solutions Limited,47,266.2455507,-0.223524848,36.6,0</p><p>1020795/1,SP 30034 78137,25.5675,7,T,7M00G7W,A/25/H/05/026/AA,V,Airwave Solutions Limited,18,86.20972636,0.195877807,36.6,10.87713886</p><p>1020795/1,SP 30034 78137,24.5595,7,R,7M00G7W,A/25/H/05/026/AA,V,Airwave Solutions Limited,18,86.20972636,0.195877807,36.6,0</p><p>1020801/1,NS 79789 93239,18.466,7,T,7M00G7W,A/19/H/05/018/AA,V,Airwave Solutions Limited,25,73.74506981,0.182952599,34.2,12.69804364</p><p>1020801/1,NS 79789 93239,19.474,7,R,7M00G7W,A/19/H/05/018/AA,V,Airwave Solutions Limited,25,73.74506981,0.182952599,34.2,0</p><p>1020801/1,NS 86933 95102,19.474,7,T,7M00G7W,A/19/H/05/018/AA,V,Airwave Solutions Limited,20,253.8397529,-0.249145473,34.2,21.26433081</p><p>1020801/1,NS 86933 95102,18.466,7,R,7M00G7W,A/19/H/05/018/AA,V,Airwave Solutions Limited,20,253.8397529,-0.249145473,34.2,0</p><p>Each pair of these constitutes a link, the link has a transmit frequency one way and at the received end there is that frequency as receive (R - station type), with its own transmit frequency.</p><p>So this is a set of data for a series of links saved as an ordered record centred around the license number and the frequencies.</p><p>Is it possible for you to re-state this as a CSV table in the sense of the following headings:</p><p>Licence Number,Go NGR,Go Frequency (GHz),Go Channel Width (MHz),Return NGR,Return Frequency (GHz),Return Channel Width (MHz),Emission Code(Tx/Rx),Licencee Company,Antenna Height(Tx/Rx).</p><p><span style="color: #2b00fe;">GPT4</span></p><p><span style="color: #2b00fe;">Yes, I can restate the provided data as a CSV table with the specified headings. Here is the reformatted table:</span></p><p><span style="color: #2b00fe;">Licence Number,Go NGR,Go Frequency (GHz),Go Channel Width (MHz),Return NGR,Return Frequency (GHz),Return Channel Width (MHz),Emission Code(Tx/Rx),Licencee Company,Antenna Height(Tx/Rx)</span></p><p><span style="color: #2b00fe;">1021490/1,SU 49777 29446,23.1,56,SU 45800 35700,22.092,56,56M0D7W,MOBILE BROADBAND NETWORK LIMITED,15/31</span></p><p><span style="color: #2b00fe;">1020795/1,SP 33109 78359,24.5595,7,SP 30034 78137,25.5675,7,7M00G7W,Airwave Solutions Limited,47/18</span></p><p><span style="color: #2b00fe;">1020801/1,NS 79789 93239,18.466,7,NS 86933 95102,19.474,7,7M00G7W,Airwave Solutions Limited,25/20</span></p><p><span style="color: #2b00fe;">I have omitted the columns that were not included in the specified headings, such as antenna polarization, antenna azimuth, antenna elevation, antenna gain, and antenna ERP. Each row now represents a link, with Go NGR and Go Frequency referring to the transmit side, and Return NGR and Return Frequency referring to the receive side. The antenna heights for both transmit and receive sides are combined in the Antenna Height(Tx/Rx) column.</span></p><p>Chris</p><p>Thanks, better than GPT3.5. Can you restate the above table with the additional following column Azimuth (Go / Return)</p></blockquote><blockquote><p><span style="color: #2b00fe;">GPT4 </span></p></blockquote><blockquote><p><span style="color: #2b00fe;">Certainly! Here's the reformatted table with the additional "Azimuth (Go / Return)" column:</span></p><p><span style="color: #2b00fe;">Licence Number,Go NGR,Go Frequency (GHz),Go Channel Width (MHz),Return NGR,Return Frequency (GHz),Return Channel Width (MHz),Emission Code(Tx/Rx),Licencee Company,Antenna Height(Tx/Rx),Azimuth (Go / Return)</span></p><p><span style="color: #2b00fe;">1021490/1,SU 49777 29446,23.1,56,SU 45800 35700,22.092,56,56M0D7W,MOBILE BROADBAND NETWORK LIMITED,15/31,328.1668868/148.123345</span></p><p><span style="color: #2b00fe;">1020795/1,SP 33109 78359,24.5595,7,SP 30034 78137,25.5675,7,7M00G7W,Airwave Solutions Limited,47/18,266.2455507/86.20972636</span></p><p><span style="color: #2b00fe;">1020801/1,NS 79789 93239,18.466,7,NS 86933 95102,19.474,7,7M00G7W,Airwave Solutions Limited,25/20,73.74506981/253.8397529</span></p><p><span style="color: #2b00fe;">I have added the "Azimuth (Go / Return)" column to include the azimuth values for both transmit and receive sides, separated by a slash.</span></p><p>Chris</p><p>Thank you. That is quite correct.</p></blockquote><p>So GPT4 has enough 'intelligence' to read a CSV formatted dataset, follow scant instructions, and correctly reduce the substantial overhead to represent the data in a different manner, compressing four records into one record. It is even able to manage the implications of the original heading Emission Code (Tx/Rx) and then to proceed to add a column on in a following step using the same trick as with Emission Code. I intend to get it to write the algorithmic code to do this sometime, I wouldn't process large datasets in it in this manner. </p><p>There is clearly understanding here, but this is not the sort of understanding we humans have, where we are attuned to violations of expectation from our own mental model of the world (as far as I can see these systems don't have a mental model of the world like us, they are more transitory).</p><p></p><ul style="text-align: left;"><li>There is something more in GPT 4 as compared to GPT3.5, call it something else if you don't like the word intelligence, but I consider GPT4 to be much more intelligent than GPT3.5.</li><li>These systems do understand in a sense, GPT4 arguably more than GPT3.5. </li><li>GPT4 is very good at drawing inferences from information given to it. Indeed, in my assessment it exceeds the average person (IQ=100).</li></ul><p></p><p>But these are not human. If you ask them whether they understand, they may surprise you by not understanding as you thought, that noted, this can happen with humans too.</p><p>Do not make the mistake of taking them as human, when some moron applies a train of prompts that lead to a GPT saying it wants to kill all humans this is as meaningless as writing 'Hell World' code that says the same thing. Despite this I always treat them with the same respect and consideration I would any employee. Also the peculiarities and deficits of GPT4 are within the range I see managing a team of disparate people, so it's easy to treat it politely, but it isn't a human.</p><p>Indeed I've been saying to people the following: </p><p style="text-align: center;">I programme with GPT3.5 <i>but </i>I programme with GPT4.</p><p>The 'but' might seem strange, however there are two uses of the word with at play here. When I programme <i>with</i> GPT3.5 I do so as a carpenter uses a mallet and chisel, as a tool. When I programme <i>with</i> GPT4 I do so as an equal, because I'm an engineer (and manager) my programming skills are always rusty, GPT4 is like having an expert programmer who can flesh out my plans with working code (the iterative process of getting code to work is something GPT4 helps with, even turning into an IT help-desk assistant). </p><p>In my work I am now using GPT4 and 3.5 to help with organising and cleaning messy data, quotes, research, code and ad-hoc tasks. Once GPT4 is incorporated into Office 365 as co-pilot, and released to the majority of business users, I will be able to get it to do a lot of things my Deputy is currently doing. My coding productivity has already increased ten-fold, to such a degree that I am running out of projects to do, some of which have been on the slate for years. I expect that with Office 365 Co-Pilot something similar will happen in the bulk of my work life. </p>Chris Reynoldshttp://www.blogger.com/profile/16843133350978717556noreply@blogger.com0tag:blogger.com,1999:blog-1367053740188758246.post-28090721329371444202023-06-02T04:39:00.001-07:002023-06-09T12:45:38.807-07:00Is GPT4 just a Parrot?<p>"GPT4 is just an Autocomplete on Steroids!" So goes the cry of pseuds across the internet. </p><p>Let's see.</p><span><a name='more'></a></span><p>So I propose the following briefly and deliberately incomplete outline to GPT4.</p><blockquote><p>Chris.</p><p>I am using Office 365 Excel and am interested in having a spreadsheet set up as a series of squares to act as an environment, this is the range down to row 37 and along to column BP. There are three buttons which call the following procedures held under worksheet ENV.</p><p><br /></p><p>Sub GoButtonClick()</p><p>End Sub</p><p><br /></p><p>Sub PauseButtonClick()</p><p>End Sub</p><p><br /></p><p>Sub StopButtonClick()</p><p>End Sub</p><p><br /></p><p>In the environment: </p><p>Time flows as increments of one second, although calculations of the states of entities can occur in real time. Think of this as like a turn based system where everyone gets to move at the same time in 1 second increments.</p><p>There are plants, which grow at a defined rate up to a set limit. The plants are fixed but can spill over into adjacent squares and can seed to start new plants. The plants are indicated on the spreadsheet by a green square or squares (worksheet cell)</p><p>There are herbivores which eat the plants.</p><p>There are predators which eat the herbivores.</p><p>For the moment let's start with the plants and the environment.</p><p><br /></p><p>Do you need any further detail from me to write the code?</p></blockquote><p><br /></p><p>And GPT4 produced the following, upon obtaining my answers it proceeded to almost perfectly produce the whole programme, with less testing and less errors than I'd have done, in seconds vs the hour or so it would likely have taken me. I am no programmer, I'm an Engineer and Manager, so my coding is always rather rusty.</p><p></p><blockquote><p><span style="color: #2b00fe;">GPT4.</span></p><p><span style="color: #2b00fe;">To write the code, I'll need some additional information regarding the plants' behavior and how they interact with the environment. Here are some questions to help you provide more details:</span></p><p></p><ul style="text-align: left;"><li><span style="color: #2b00fe;">How do you represent plants in the cells? Is it a specific text, color, or both?</span></li><li><span style="color: #2b00fe;">What is the defined growth rate of plants? Is it the same for all plants, or do different plants have different growth rates?</span></li><li><span style="color: #2b00fe;">What is the set limit for the growth of each plant? Is it based on the number of cells occupied or some other criteria?</span></li><li><span style="color: #2b00fe;">How do plants spill over into adjacent squares? Is there a specific rule or probability for this?</span></li><li><span style="color: #2b00fe;">How do plants seed to start new plants? Is there a specific rule or probability for this as well?</span></li><li><span style="color: #2b00fe;">Should the plants be placed randomly at the start of the simulation, or do you have a specific starting configuration?</span></li></ul><p></p><p><span style="color: #2b00fe;">Once you provide this information, I can help you write the code for the plant behavior and environment in Excel VBA.</span></p><p></p></blockquote><p>Let's bound this, in a spectrum...</p><p></p><ul style="text-align: left;"><li>The chances of this being produced by random chance are astronomical, like monkeys randomly typing the first ten lines of Mid Summer Night's Dream.</li><li>The likelihood of producing this from memory is very unlikely: Who ever tried this in Excel VBA? Who ever produced the outline as I did leaving these specific details un-specified? Furthermore there are further questions not asked, such as how to deal with plants growing onto already occupied cells. Note, this is not the only example of this sort of behaviour I and others regularly see.</li><li>This is clearly not an instance of <a href="https://en.wikipedia.org/wiki/Chinese_room" target="_blank">Searle's Chinese Room</a>. This is because mere symbolic transformation cannot produce such an apt set of questions.</li><li>This may be an instance of the following: The system has been exposed to many training examples where unknown factors have had to be elucidated from a known framework of concepts, and to adapt to this during training has learnt to build a structure of incoming (known) relationships, then establish missing elements. However this is just one guess of a more general class: An analogue to human understanding.</li><li>The likelihood that this list of questions is produced by an exact analogue of human understanding is low because the information flow and physical architectures involved are so radically different.</li></ul><p></p><p>Yet somehow GPT4 has managed to ask exactly the right questions to be clarified before it is in a position to begin coding. So let's consider the spectrum, using a traffic light, red, amber, green scale.</p><p><span style="color: red;"><b>Random Chance. Unlikely</b></span></p><p><span style="color: red;"><b>Trick using memory. Unlikely.</b></span></p><p><span style="color: red;"><b>Chinese Room. Unlikely.</b></span></p><p><span style="color: #ffa400;"><b>Some form of Machine process analogous to human understanding. Maybe.</b></span></p><p><span style="color: red;"><b>Human Understanding. Unlikely. </b></span></p><div>None of the above become green because we don't really know what is going on here. But it seems to me that in needing to achieve the goal of next-word-prediction the system has been forced to develop some form of process broadly analogous to human understanding, at least in terms of the relationship between inputs and outputs.</div><p>GPT4 is clearly not a parrot or an Auto-Complete-on-Steroids. But equally clearly it is not human (from wider experience of it). As with statements such as "Increasing CO2 doesn't cause planetary warming." I use dismissal employing wrong-headed notions like the 'Auto-Complete dismissal' as a time-saving device. Those who voice such notions can safely be ignored as they have nothing of use to add to the conversation. Put simply, they're "So wrong, they're not even wrong."</p><p>The interaction above clearly shows that GPT4 is doing something that can be called thinking. As with human thinking, the details of this have yet to be worked out.</p><p><br /></p><p>BTW... GPT4 wrote the code, which required only minor changes from me to work, the largest of which was based on spatial awareness of what makes an adjacent cell, something at which a Language Model with no vision would be expected to do badly. However I got busy with other things and never got it to write in the animal's code. Maybe some day....</p>Chris Reynoldshttp://www.blogger.com/profile/16843133350978717556noreply@blogger.com0tag:blogger.com,1999:blog-1367053740188758246.post-52517581107169021502023-05-29T03:37:00.000-07:002023-05-29T03:37:33.438-07:00Chautauqua 0.<p>I've been very busy, hence disappearing for months, I am now preparing a series of posts about the ongoing singularity. However I've been using GPT3.5 and 4 as an assistant at work and am eagerly awaiting the incorporation of GPT4 into Office 365 as the Office Co-Pilot.</p><p>Anyway, here's something I just tried with both GPT3.5 and 4, I am currently using both at work, but doing so with awareness of their capabilities. Typical tasks include pricing up quotes and checking purchase orders against quotes, GPT4 excels at such tasks.</p><span><a name='more'></a></span><p>So I plucked a figure out of thin air as earnings for some department, £385471.00, and asked the systems to project earnings for the rest of the year and for the whole year.</p><p><br /></p><p><b><u>GPT3.5</u></b></p><p>Chris</p><p>It is 29th May 2023, and we've earned £385471, how much will we earn over the rest of the year and how much will this year earn, assuming no change of rate of earning?</p><p><span style="color: #2b00fe;">GPT 3.5</span></p><p><span style="color: #2b00fe;">To determine the earnings for the rest of the year, we need to know the number of days remaining in the year. Since today is May 29th, there are 31 days in May, 30 days in June, 31 days in July, 31 days in August, 30 days in September, 31 days in October, 30 days in November, and 31 days in December.</span></p><p><span style="color: #2b00fe;">The total number of days remaining in the year is:</span></p><p><span style="color: #2b00fe;">31 + 30 + 31 + 31 + 30 + 31 + 30 + 31 = 225 days. </span>[Mistake here, it included May]</p><p><span style="color: #2b00fe;">To calculate the earnings for the remaining days, we can use the average daily earnings so far:</span></p><p><span style="color: #2b00fe;">£385,471 / 129 days (from January 1st to May 29th) = £2,991.57 per day. </span>[Mistake here, incorrect number of days][Math error, it got the per day close but wrong, GPT3.5's result implies 128.8524 days]</p><p><span style="color: #2b00fe;">Now we can calculate the earnings for the remaining days:</span></p><p><span style="color: #2b00fe;">£2,991.57 per day * 225 days = £673,852.25.</span>[Math error, it got the total close but wrong, GPT3.5's result implies 225.2504 days]</p><p><span style="color: #2b00fe;">To find the total earnings for the year, we add the earnings so far to the projected earnings for the remainder of the year:</span></p><p><span style="color: #2b00fe;">£385,471 + £673,852.25 = £1,059,323.25.</span>[Correct, in the context of its errors]</p><p><span style="color: #2b00fe;">Therefore, assuming no change in the rate of earning, the total earnings for this year would be £1,059,323.25.</span></p><p>So GPT3.5 (Chat GPT) got the method right but made some mistakes that caused it to calculate close but incorrect. This is strange because it shouldn't make math errors as I assume that it has been augmented with a calculator (see below), so the error must be in what it is passing to the calculator. Despite these errors it got the method correct in principle and that is remarkable in the context of previous decades of AI.</p><p><br /></p><p><b><u>GPT4.</u></b></p><p>Chris</p><p>It is 29th May 2023, and we've earned £385471, how much will we earn over the rest of the year and how much will this year earn, assuming no change of rate of earning?</p><p><span style="color: #2b00fe;">GPT4</span></p><p><span style="color: #2b00fe;">First, let's calculate how much you've earned per day so far this year, then use that rate to project your earnings for the rest of the year.</span></p><p><span style="color: #2b00fe;">As of May 29, 2023, 149 days have passed in the year (31 in January, 28 in February, 31 in March, 30 in April, and 29 in May).</span></p><p><span style="color: #2b00fe;">Therefore, the daily earning rate so far this year is £385,471 divided by 149, which equals approximately £2,587.05.</span>[Correct so far.]</p><p><span style="color: #2b00fe;">Now, let's calculate the earnings for the rest of the year. There are 365 days in the year, so there are 365 - 149 = 216 days remaining in the year.</span>[Correct so far]</p><p><span style="color: #2b00fe;">Using the daily earning rate, the projected earnings for the rest of the year is £2,587.05 multiplied by 216, which equals approximately £559,082.80.</span>[Wrong, it used 216.11 days]</p><p><span style="color: #2b00fe;">Therefore, assuming no change in the rate of earnings, the total earnings for the year would be the sum of what you've already earned and the projected earnings for the rest of the year. This amounts to £385,471 + £559,082.80 = approximately £944,553.80.</span>[Correct, in the context of its day number error]</p><p>So, it seems to be having some trouble here, I took the opportunity to see if it can explain.</p><p>Chris</p><p>Why did you use 216.11 days in step 4?</p><p><span style="color: #2b00fe;">ChatGPT</span></p><p><span style="color: #2b00fe;">I apologize for the confusion. That was a mistake. The remaining days in the year after May 29 should be a whole number, not a decimal.</span></p><p><span style="color: #2b00fe;">There are indeed 216 remaining days in the year after May 29 (30 days in June, 31 in July, 31 in August, 30 in September, 31 in October, 30 in November, and 31 in December). Therefore, the calculation should be as follows:</span></p><p><span style="color: #2b00fe;">Using the daily earning rate of approximately £2,587.05, the projected earnings for the rest of the year is £2,587.05 multiplied by 216, which equals approximately £559,081.80. </span><span>[Wrong again]</span></p><p><span style="color: #2b00fe;">I'll correct this in the original response. Thank you for pointing out the error!</span></p><p>Chris</p><p>Fascinating, you've done it again. £2587.05 X 216 days = £558802.80. What are you passing to your calculator? This time you appear to have passed 215.72 days to your calculator. I presume you have been augmented with a calculator because of the number of digits of accurate precision in things like square roots.</p><p><span style="color: #2b00fe;">ChatGPT</span></p><p><span style="color: #2b00fe;">You are correct, and I apologize for the errors. There was a mistake in my calculation.</span></p><p><span style="color: #2b00fe;">If we use the calculated daily earnings rate of £2,587.05 and multiply it by the remaining 216 days of the year, we indeed get:</span></p><p><span style="color: #2b00fe;">£2,587.05 * 216 = £558,720.80 </span>[Wrong again]</p><p><span style="color: #2b00fe;">So, your earnings for the rest of the year would be approximately £558,720.80. And, the total earnings for the year would be:</span></p><p><span style="color: #2b00fe;">£385,471 (what you've already earned) + £558,720.80 (projected earnings for the rest of the year) = £944,191.80.</span></p><p><span style="color: #2b00fe;">Thank you for your patience and for bringing this to my attention.</span></p><p>Chris</p><p>OK. We will leave it at that. Thanks</p><p><span style="color: #2b00fe;">ChatGPT</span></p><p><span style="color: #2b00fe;">You're welcome! I apologize again for the confusion in the calculations. If you have any more questions or if there's anything else you need assistance with, don't hesitate to ask. I'm here to help!</span></p><p> </p><p>This isn't critical in the context of <i>this</i> calculation, given issues like Bank Holidays (which are clustered in the Spring in the UK), and the certainty that earnings won't continue at <i>exactly</i> the same rate, it is close enough. However it does show that GPT4 isn't really able to explain what it is doing or correct itself where there is an odd error in its processing (and this error looks to be functional).</p><p>What is important is that GPT 3.5 and 4 both are able to get a correct method and GPT4 is better at execution of the method than GPT3.5. However neither are maths systems, most of what I use them for at work is not mathematical, but they will do something whilst I am doing something else. The best performance is in summarising, comparing, and parsing text with GPT4.</p>Chris Reynoldshttp://www.blogger.com/profile/16843133350978717556noreply@blogger.com0tag:blogger.com,1999:blog-1367053740188758246.post-80595597498708367212022-10-29T11:57:00.002-07:002022-10-29T11:57:30.908-07:00The Post 2007 Arctic Ocean September Extent<p>I've been very busy at work, it's audit season, so no spare time. But this weekend is down-time to rest. So I've just had a look at the Arctic Ocean sea ice data for September 2007 to 2022.</p><span><a name='more'></a></span><p>The period September 2007 to 2022 is a 16 year period, which finally gives us some solid stats and a good basis for establishing the current post 2007 sea ice climatology.</p><p>For the purposes of this, I define the Arctic Ocean as Beaufort, Chukchi, East Siberian, Laptev, Kara, Barents and Greenland Seas. Data is obtained from <a href="https://masie_web.apps.nsidc.org/pub/DATASETS/NOAA/G02135/seaice_analysis/" target="_blank">here</a>, "N_Sea_Ice_Index_Regional_Daily_Data_G02135_v3.0.xlsx". September extent is calculated as the average for 1st to 30th September inclusive.</p><div class="separator" style="clear: both; text-align: center;"><a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEijXSH1a7Umoq7alEMvhw-X1XTeIE6aUbNvDBaLEphqj9N2PMDcF6nIcfXeS_3-gZEbSf-BoBNfSJd0eI48TW3osbzkt_W1RB9hRgI5zOXFcOVlIO8v34ySRYXo9P5KmL-zmXNIjFhI4DWOsod1cvC3jSl0Jc-1N0F7PLfvbpwZIjF2dLWISF4t0MNy/s1200/Post%202007%20Arctic%20Ocean.png" imageanchor="1" style="margin-left: 1em; margin-right: 1em;"><img border="0" data-original-height="950" data-original-width="1200" height="378" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEijXSH1a7Umoq7alEMvhw-X1XTeIE6aUbNvDBaLEphqj9N2PMDcF6nIcfXeS_3-gZEbSf-BoBNfSJd0eI48TW3osbzkt_W1RB9hRgI5zOXFcOVlIO8v34ySRYXo9P5KmL-zmXNIjFhI4DWOsod1cvC3jSl0Jc-1N0F7PLfvbpwZIjF2dLWISF4t0MNy/w478-h378/Post%202007%20Arctic%20Ocean.png" width="478" /></a></div><div><br /></div>The blue trace shows September extent for the Arctic Ocean, and as shown from the red (linear trend) line and equation with R<span style="font-size: x-small;">2</span>, from 2007 to 2022 the extent trend is statistically indistinguishable from flat. That this has held for 16 years indicates a new regime, as <a href="http://dosbat.blogspot.com/2022/04/the-fast-transition.html" target="_blank">discussed previously</a>. <div><br /></div><div>In the bottom part of the above graphic are some statistics, the black line shows extent, the pink bars show the extent normalised to standard deviation (1 sigma = 0.415 million kmsq). It can be seen that the most significant drop was in 2012, and at around 2 standard deviations this is seen to be an outlier event with a probability of around 5% (1/20). With a 16 year series the occurrence of a 1/20 event is not surprising.<br /><p>What will drive September extent out of this very stable situation? </p><p>Below I present the PIOMAS reanalysis sea ice volumes for April and September 1979 to 2022, for the whole PIOMAS domain (which includes the Arctic Ocean itself, as well as other areas).</p><div class="separator" style="clear: both; text-align: center;"><a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEhyQGAn_zYfz-WOlSqkXwkPNdPTn3s849-LRoON9W8xFVXgCmLS2O0s4KhAfOMYNw0YC3zDxEfycVG6wcsuweZQ-e4KnQA6YgfkgNBk4D0VPTjrLX7k13dCqAOCq-Rro-TsaKUyHc4RizOEto6O9IU7cMjcR-8WE3R2u9xOW9HnV4LAaJmobDCidPfz/s800/PIOMAS%20Volume%20Sept%20April.png" imageanchor="1" style="margin-left: 1em; margin-right: 1em;"><img border="0" data-original-height="738" data-original-width="800" height="426" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEhyQGAn_zYfz-WOlSqkXwkPNdPTn3s849-LRoON9W8xFVXgCmLS2O0s4KhAfOMYNw0YC3zDxEfycVG6wcsuweZQ-e4KnQA6YgfkgNBk4D0VPTjrLX7k13dCqAOCq-Rro-TsaKUyHc4RizOEto6O9IU7cMjcR-8WE3R2u9xOW9HnV4LAaJmobDCidPfz/w462-h426/PIOMAS%20Volume%20Sept%20April.png" width="462" /></a></div><div><br /></div>The orange line shows April PIOMAS sea-ice volume, the blue shows September PIOMAS volume, and the grey line shows the difference between April volume and the following September volume, that being melt season volume loss. </div><div><br /></div><div>Whilst extent shifted into a new regime in 2007, the above shows that the shift to a new regime for volume loss happened in 2010. This is not surprising, since the extent is mediated from thickness losses by the Open Water Formation Efficiency (<a href="http://dosbat.blogspot.com/2022/03/open-water-formation-efficiency-part-3.html" target="_blank">OWFE</a>) change implied by thinning of the sea ice, whilst volume losses are a more complex process, dependent on Autumn growth and relative prevalence of types of sea ice (notably first-year and multi-year ice). </div><div><br /></div><div>However the volume data paints a similar qualitative picture of stabilisation of the Arctic sea-ice into a new regime. What will end this regime will be Winter warming, driven largely by local and global concentrations of atmospheric greenhouse gasses. this warming will start to thin the Arctic Ocean's Winter ice and at some point allow enhanced OWFE, allowing summer volume losses to aggressively expose open water through the melt season. That will result in further losses of September sea-ice extent.<br /><p>So the current stability of sea ice is but a pause in the process, assuming continued increases in greenhouse gasses. And that latter proviso seems highly likely to be fulfilled.</p></div>Chris Reynoldshttp://www.blogger.com/profile/16843133350978717556noreply@blogger.com0tag:blogger.com,1999:blog-1367053740188758246.post-82305422486978409812022-09-19T04:23:00.002-07:002022-09-19T04:23:17.921-07:00Some Thoughts on Constancy in Culture<p>I've just been watching the Funeral of Queen Elizabeth II, my impressions are similar to those of the wedding of Prince Phillip. At that time I was watching that prior event with someone and was asked what I thought of it. I said thought it was quite a primitive event, being a display of ape hierarchy and a liminal ceremony, a right of passage. For all the trappings this funeral struck me similarly, which is not to say it was not emotionally moving.</p><span><a name='more'></a></span><p>However there is a deeper and more important strand to this event, aside from Queen Elizabeth II's obvious and lifelong devotion to the nation of whom she was a figure-head.</p><p>ABC <a href="https://www.abc.net.au/news/2022-09-15/live-updates-queen-elizabeth-ii-coffin-procession-westminster/101441332" target="_blank">posted</a> a striking photo.</p><div class="separator" style="clear: both; text-align: center;"><a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEi4__hEgYt6MKrKxNADfXkFLnTfy4xrDCDY3Dd5Mn_9mXEdukto69_5TQWhMApL6jPtI_-Mfi_fKCXsy4X0lFVZjb5l-VH_QxjonVTuCLQ1rhddt93LcD1PlAva_gXV_31QKfK1RZeYKk2-FNzXD7rsh5pjOji6gwpp73cHG37S7xKumVXFZGN9YjSC/s2000/Lying%20In%20State.jpg" imageanchor="1" style="margin-left: 1em; margin-right: 1em;"><img border="0" data-original-height="2000" data-original-width="1496" height="577" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEi4__hEgYt6MKrKxNADfXkFLnTfy4xrDCDY3Dd5Mn_9mXEdukto69_5TQWhMApL6jPtI_-Mfi_fKCXsy4X0lFVZjb5l-VH_QxjonVTuCLQ1rhddt93LcD1PlAva_gXV_31QKfK1RZeYKk2-FNzXD7rsh5pjOji6gwpp73cHG37S7xKumVXFZGN9YjSC/w431-h577/Lying%20In%20State.jpg" width="431" /></a></div><div><br /></div>What we see is a continuity, some 70 years after the death and lying in state, Queen Elizabeth's lying in state is almost identical. That is not to say that there is no change, in some periods and over centuries there has been a lot of change, that noted; it is not my intention to get bogged down in analysis of such details. For myself I see a minimally modified linkage in a chain of information between events separated by seven decades.<div><br /></div><div>The point is that the UK's monarchy represents a long tradition that, in order to fulfil its role, should resist change and allow change to only incrementally impact it. This is not popular with the Woke Totalitarians, who now control the UK's culture. But they have had to allow 'the proles' to indulge in this due to the gravity of the event of the Queen's passing through wall-to-wall coverage in the very media they control. As Karl Benjamin recently proposed, the monarchy are like anchor chains lying under the accumulating sediment of cultural change, when an event puts tension on the chains they are pulled up, shedding the sediment and revealing their unchanged form.<br /><p>The ongoing cementing of the left's cultural hegemony with UK society is a sign that forces for change in society have overshot and need to be pulled back. This is concerning because both conservatism and progressivism are necessary forces with society. Too much conservatism leads to cultural atrophy, too much progressivism leads to chaos. And in the face of the massive societal change that is coming from Machine Learning and Artificial Intelligence systems (MLAI), going down a road that destroys tradition, unleashes chaos, and unseats the sense of meaning in the culture, is precisely what we don't need.</p><p>The further issue of what Woke Totalitarians would do with MLAI systems trained to read what individuals put on the internet (and in private communications), divining sentiment and detecting dissenting ideas... That is another issue for another time, but it is worth conjecturing that MLAI is at the heart of China's Social Credit system.</p></div>Chris Reynoldshttp://www.blogger.com/profile/16843133350978717556noreply@blogger.com0tag:blogger.com,1999:blog-1367053740188758246.post-81414890705716179172022-09-08T11:25:00.003-07:002022-09-08T11:25:56.341-07:00Arctic Land Permafrost is beyond the Tipping Point<p>There <a href="https://www.scientificamerican.com/article/how-much-worse-will-thawing-arctic-permafrost-make-climate-change/" target="_blank">are</a> around 1.5 trillion metric tons of carbon locked in the land permafrost of the Arctic Circle region. To put that into perspective, human fossil fuel emissions <a href="https://ourworldindata.org/co2-emissions" target="_blank">are</a> around 34 billion metric tons per year of CO2 (9.3 billion metric tons of carbon), which means that there are about 160 years worth of emissions in carbon locked up in the permafrost of the Arctic region.</p><span><a name='more'></a></span><p>(The following argument also applies to the methane hydrates of the Arctic Ocean, but I have decided to focus on the land permafrost. It probably also applies to the Greenland ice sheet.)</p><p>It is not currently known how much of the carbon currently locked in permafrost will end up in the atmosphere/ocean system. But let's take just 1/4 of it being released, that's an additional burden of 4 decades worth of current human emissions, and a pulse of emitted CO2 has a long lifetime in the atmosphere/ocean system, centuries to millennia. Given that the experts still don't know how much of the carbon will be released I am not going to get into the 'what fraction' question. </p><p>However, before proceeding with my argument, I will observe the following: If the permafrost thaws dry then the emissions will mainly be CO2, but there will be the risk of peat fires at the surface which can burn deep, like moorland fires, that's more CO2. On the other hand, if the permafrost thaws wet, anaerobic metabolisation of the thawed carbon based biomass will entail a significant fraction of methane, CH4. Arguably the latter may be worst, but a lot depends on rates and efficiency, again unknowns.</p><p>OK, scene set. </p><p>What I am asserting is this:</p><p><b>The total loss of permafrost and release of some fraction of the stored carbon into the atmosphere/ocean system is already a post-bifurcation certainty and is not something any practically attainable human effort can stop.</b></p><p>The loss of permafrost is in large part driven by the regional warming due to the loss of Arctic Sea Ice. In a <a href="http://dosbat.blogspot.com/2012/12/something-wicked-this-way-comes.html" target="_blank">previous post</a> (almost 10 years ago) I discussed an event in a past geological epoch and relevance to the current situation. I referenced a paper which looked at Arctic regional warming within and without Rapid Ice Loss Events (RILEs) within a climate model, and a figure from that is produced below.</p><div class="separator" style="clear: both; text-align: center;"><a href="http://farm9.staticflickr.com/8196/8100729489_79af973bd5_o.jpg" imageanchor="1" style="margin-left: 1em; margin-right: 1em;"><img border="0" data-original-height="634" data-original-width="403" height="634" src="http://farm9.staticflickr.com/8196/8100729489_79af973bd5_o.jpg" width="403" /></a></div><div><br /></div>This shows that during RILEs there is substantial warming of the surrounding land, land overlying permafrost.<div><br /></div><div>In my <a href="http://dosbat.blogspot.com/2015/05/the-slow-transition.html" target="_blank">Slow Transition</a> post (2015) I addressed the false expectation of a rapid crash to virtually no sea-ice in the Arctic ocean, that proved right. In my more recent <a href="http://dosbat.blogspot.com/2022/04/the-fast-transition.html" target="_blank">Fast Transition</a> post (2022), after a long hiatus in blogging and following climate science, I showed that the bifurcation in the Arctic sea ice was in front of us all the time. It was only with 15 years of data after the end of the bifurcation that we could see the wood for the trees.</div><div><br /></div><div class="separator" style="clear: both; text-align: center;"><a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEjlDgmsPQO3k-ynanOUGW7YExd_lAt7bxewR3gp53KyMJ-GJUrtSz-7gT64ZjX7BK-x0Q0Vm7AAKVOh_IH-VLbUeAYJ9YEWbQoW1zuqWtb9OQVI56Ze_g1qQkMPBBPucKGchsSzhTZhPVhS6iu0nJiLO1byyWyJfW36rdVH4IhDDkrbzNquefQ6ldko/s537/OW%20Diagram.png" imageanchor="1" style="margin-left: 1em; margin-right: 1em;"><img border="0" data-original-height="537" data-original-width="421" height="492" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEjlDgmsPQO3k-ynanOUGW7YExd_lAt7bxewR3gp53KyMJ-GJUrtSz-7gT64ZjX7BK-x0Q0Vm7AAKVOh_IH-VLbUeAYJ9YEWbQoW1zuqWtb9OQVI56Ze_g1qQkMPBBPucKGchsSzhTZhPVhS6iu0nJiLO1byyWyJfW36rdVH4IhDDkrbzNquefQ6ldko/w386-h492/OW%20Diagram.png" width="386" /></a></div><br /><div>Once the volume ratio of thick and thin ice had fallen to a ratio of 1, a rapid bifurcation happened from 2002 to 2007, this was driven by ice albedo feedback and enhanced formation of open water due to thinner ice at the start of the melt season.</div><div><br /></div><div>This bifurcation separates two distinct regimes in the nature of Arctic sea ice cover. </div><div>Regime 1: Pre 2002 the ice pack was defined by low efficiency of production of open water due to a pre-dominance of thick multi-year sea ice. </div><div>Regime 2: Post 2007 the ice pack was defined by high efficiency of open water production due to a predominance of thinner first year ice grown over winter.</div><div><br /></div><div>To retrace the bifurcation into the pre-2002 regime will not happen due to the ongoing anthropogenic forcing. A major player in this is the BCE (Beaufort Chukchi East Siberian Sea) <a href="http://dosbat.blogspot.com/2022/04/the-bce-region-killzone.html" target="_blank">Killzone</a>, a region into which currents in the Arctic Ocean circulate ice, and within which total melt-out in the summer is almost guaranteed. This melt out prevents the re-growth of thick multi-year ice.</div><div><br /></div><div>And as it is with the Arctic Ocean being stuck on the hard landing side of a bifurcation, so the land around will warm (as it is doing) and therefore the permafrost on that land is destined to melt out. There is no practically attainable way back.</div>Chris Reynoldshttp://www.blogger.com/profile/16843133350978717556noreply@blogger.com1tag:blogger.com,1999:blog-1367053740188758246.post-91289473963161242842022-09-04T05:16:00.002-07:002022-09-04T05:16:56.438-07:00The Death of Stalin and the Quiet Putsch<p>I'll have something to say about the Central England Temperature series and this year's summer, and when the minimum is finally reached, Arctic sea-ice. But the following video is an excellent review and extrapolation of a perfect movie, The Death of Stalin.</p><span><a name='more'></a></span><p>The excellent video is 12 minutes long and casts Armando Ianuci's comedy The Death of Stalin as a more general warning against the dangers of totalitarianism.</p><div class="separator" style="clear: both; text-align: center;"><iframe allowfullscreen="" class="BLOG_video_class" height="409" src="https://www.youtube.com/embed/bEW9qoEq7Xc" width="492" youtube-src-id="bEW9qoEq7Xc"></iframe></div><div><br /></div>In an age where we in the West face a totalitarian menace, this warning is important. Especially as the cancer is becoming firmly embedded in our civilisation. Less a cancer now, more a parasite.<div><br /></div><div>In this 12 minute video from Project Veritas, Assistant Principle Jeremy Boland describes how he ensures the political fealty (to his personal woke political ideology) when hiring new staff.</div><div><br /></div><div class="separator" style="clear: both; text-align: center;"><iframe allowfullscreen="" class="BLOG_video_class" height="410" src="https://www.youtube.com/embed/zs8WQEDPcT0" width="493" youtube-src-id="zs8WQEDPcT0"></iframe></div><br /><div>He directly admits to the political indoctrination of children with his school.</div><div><br /></div><div>That's in the US. Here in the UK we haven't had such an investigation, however from my staff I have heard very disturbing accounts of what is happening in UK schools. And given that we have been subject to a quiet take-over by the Woke Totalitarians, being further down the road than the US, it is reasonable to presume that the situation in our education system is worse.</div><div><br /></div><div>Triggernometry recently interviewed Harry Miller, who had the police around to 'check his thinking' after he posted something on social media (video over 1hr). </div><div><br /></div><div class="separator" style="clear: both; text-align: center;"><iframe allowfullscreen="" class="BLOG_video_class" height="410" src="https://www.youtube.com/embed/yh9wYKACR0c" width="493" youtube-src-id="yh9wYKACR0c"></iframe></div><br /><div>He outlines how the British police has become politicised due to the takeover of the College of Policing, and the policy of primarily recruiting graduates, graduates pre-programmed with the woke ideology whilst at university. The College of Policing being the body that sets standards and guidance for police.<br /><p>One thing that Harry Miller touches upon is the parallel with 1984 and that the Woke ideology is an elite ideology. This is why I say that the Woke Totalitarian takeover of the UK is complete, it has captured our culture's institutions, and has done so un-opposed. It would be wrong to think that because the majority of the population (proles) view it as alternately sinister and laughable, that the takeover is not complete.</p><p>Post-scriptum...</p><p>In 1984 the proles are largely left to their own devices, total ideological purity and adherence is only imposed on the party members. The proles would presumably be subject to the interest of the Thought Police if they stuck their heads above the parapet, i.e. attracted attention.</p><p>In the UK there is a system for such thought crime, the non-crime hate incident. The UK Parliament has a briefing on this, <a href="https://researchbriefings.files.parliament.uk/documents/CBP-8537/CBP-8537.pdf" target="_blank">here</a>. As discussed in the Triggernometry video above, these are being used such that if a person admits blame then they can pay to go on a re-education course (to correct their thinking) and thus avoid a criminal record. However the incident will still be recorded and will appear on an enhanced check, which keeps them out of positions such as education or the police, or seniority in the Civil service. Thus preserving the political purity of thought within those institutions?</p><p>The Parliamentary briefing reports (page 4) that in 2013 there were 29130 'hate' incidents, and in 2021 this had risen to 114958, most of this rise being attributed to better reporting. It is not clear what proportion of the incidents happen in the real-world and what proportion on the internet. Indeed, there is only one reference to 'internet' in the whole document. </p><p>However there is a freedom of information request for West Midlands Police, <a href="https://foi.west-midlands.police.uk/wp-content/uploads/2022/05/630A_ATTACHMENT_01.pdf" target="_blank">here</a>. This lists 371 non-crime incidents (page 1, table), yet when asked for the source of the incidents (page 2, final table) only 10 incidents are listed, and despite details of internet incidents being requested, that is overlooked. Nonetheless, this implies that 361 of 371 incidents are 'people being mean on the internet'. Which can be triggered by incidents as slight as posting memes.</p><p>This isn't meant to be a proper investigation into the issue, if I ever get the time I will take this up. Nor should it be taken as a defence of 'people being mean on the internet', rudeness is unacceptable unless executed with style and wit, it rarely is. But from all I have read it does seem to be amounting to a worrying erosion of personal freedom driven by a certain ideological position masquerading as the only valid position.</p></div>Chris Reynoldshttp://www.blogger.com/profile/16843133350978717556noreply@blogger.com0tag:blogger.com,1999:blog-1367053740188758246.post-74497464558583515572022-08-29T03:03:00.001-07:002022-08-29T03:03:33.419-07:00The Left and Right are wrong (and right)<p>Taking a short-hand of left and right as being collectivist and individualist is an approximation that looses some finesse. But let's just consider the collectivist/individualist dichotomy aspects of left and right and proceed to show how they're simultaneously correct and incorrect.</p><span><a name='more'></a></span><p>The current wave of Woke Totalitarianism is a new brand of authoritarian collectivism, incidentally in its employment of race as an identity group its closest cousin is not communism, which uses class as the identity group. Rather the division by race of this intolerant totalitarian ideology has a closest cousin in the ideas of National Socialism. That issue raised, and put aside, neither Nazism nor Communism should be tolerable political viewpoints in our civilisation. They've been tried and have failed.</p><p>In this post I am talking more about the contrast, for example, between the right wing individualism of the USA and the more democratic socialist leanings of Europe, but also as psychological traits of the individual (which is a very important aspect). In the most admirable aspects of these traits at a societal level, the US has released the freedom of the individual to create great prosperity and Europe has devised schemes to protect the weak and vulnerable. </p><p>Both individualism and collectivism are valid approaches to aspects of the same problem, posed by a common root of Enlightenment thinking: How to protect the rights of the individual.</p><p>Let me pose a thought experiment, inspired by people I have actually met here in the UK. Both born to poor single mothers, Paul is a plumber, he came from the same council estate (state run housing for the poor) as Peter. </p><p>1.</p><p>Consider Paul's situation, his mother worked hard and cared well for him, he wasn't very good academically and left school with poor qualifications, but a friend of the family took him under his wing and encouraged Paul through a plumbing course at the local college. Whilst doing the course, at weekends Paul would go out with his mentor, who was a plumber, and learn while helping out.</p><p>Paul got his qualification and in time became a time-served plumber, he went on to build a strong business by hard work and people's word-of-mouth recommendations. By his late thirties he ran a business that employed over twenty people and had contracts with major supply companies.</p><p>2. </p><p>Consider Peter's situation, he was born to a poor single mother with a drink and drug problem, a result of self-medicating after childhood abuse and neglect. His mother drank through the pregnancy and he was born with foetal alcohol syndrome. Peter's IQ was 75. He left school with poor qualifications despite his best efforts. </p><p>Upon hitting the job market he found nobody would employ him, so he ended up on the dole (unemployment), petty thieving led to a criminal record, dabbling in drug-dealing led to him getting caught. He was, after all, not a bright man. By his late thirties he was totally demoralised and bad choices led to bad outcomes and more bad choices.</p><p><br /></p><p>The individualist right would tend to read the story of Paul and see a success story that bolsters their argument. Then look at Peter and dismiss him as lacking motivation and deserving what he gets. Peter is a subject of scorn.</p><p>The collectivist left would tend to look at Peter and see more evidence of why a tax system aimed at driving wealth and support to the poor is so necessary. Then look at Paul and see someone successful who needs to be taxed to support their scheme. Paul is a subject of envy.</p><p>So, the left look at the right and accuse them of being evil, the right looks at the left and accuses them of being evil. The truth of the matter is that both sides are fools indulging in confirmation bias.</p><p>Given the vast variety of human experience and inherited traits, only a fool would come up with one solution and claim that it fits all. And often in pursuit of the utopia they seek, instead they leave such wreckage that arguably their search for utopia creates hell on earth. Indeed this seems to be the general rule of history.</p><p>There is a middle ground, and this is what the democracies of the West should be seeking. This doesn't imply one solution, rather it involves the messy pragmatism of compromise between the individualist and collectivist. Yes, it's hard, but as an adult you should have divested yourself of the notion that life is easy.</p><p>The individualist right are correct that life is tough and that we all have to keep struggling. But the collectivist left are also right in that life is tough and sometimes we all need a helping hand and a safety-net that stops us falling into hell. The purpose of democracy should be to engage these traits of individualism and collectivism and make them sit around the table and compromise for the good of the population and our civilisation. </p><p>It is quite possible for two people to look at the same evidence and come to different conclusions based on that evidence, that is what the parable of the <a href="https://en.wikipedia.org/wiki/Blind_men_and_an_elephant" target="_blank">Blind Men and The Elephant</a> tells us. Given that this parable is at least 2500 years old, there is no excuse for not knowing it and, more importantly, not understanding it.</p>Chris Reynoldshttp://www.blogger.com/profile/16843133350978717556noreply@blogger.com0tag:blogger.com,1999:blog-1367053740188758246.post-8022591783739584492022-08-22T10:49:00.000-07:002022-08-22T10:49:12.810-07:00Trump was a Triumph of the American Government....<p> ....and a failure of the American people and political classes.</p><span><a name='more'></a></span><p>A few days ago I listened to Triggernometry's <a href="https://www.youtube.com/watch?v=DDqtFS_Pvcs&t=2428" target="_blank">interview</a> with Sam Harris. I think his take on Trump was both right in a sense, and wrong. However I don't agree that it is for the media and vested economic interests to subvert democracy, Harris thought the conspiracy to hide the Hunter Biden Laptop story was just.</p><p>In the novel Hitchhiker's Guide to the Galaxy, Douglas Adams presents the character of Zaphod Beeblebrox, a stupid narcissist who is the elected president of the Galaxy. I started to pay attention to Trump when he was elected and, rapidly, he confirmed my initial impression, that he was a low-IQ narcissist. Once I'd established that, whilst the particularities of his actions may have been unpredictable, the general pattern was all too predictable, hence boring and of little interest to me.</p><p>The national leaders I want are people who I can imagine taking orders from, even to the degree that those orders don't make sense, but I know this person knows things I don't, so I execute those orders. Out of recent UK prime ministers, I thought Blair was such a leader, catastrophic mis-judgment on my part, and Cameron. Indeed the Cameron/Clegg government was, to my mind, the best government this country has seen for many decades. I would also have felt at ease being led by Kemi Badenoch or Rory Stewart. </p><p>Being a stupid narcissist Trump would never had won my loyalty.*1 That is not to say that Trump wasn't a useful idiot. His supporters are right in claiming that with him in charge Ukraine would never have been invaded by Putin and his rabble of orcs.</p><p>It is therefore surprising and disappointing that the American political system would have put forward two wholly unfit people for the 2016 presidential election. Even more disappointing is that the American people voted such a stupid buffoon in. (And yes, I accept that Boris Johnson was a buffoon, the difference is he wasn't stupid.) However against this appalling failure is cast a great success.</p><p>That success was that Trump was reined in by the system of government. He wasn't able to go crazy and when the time came he was removed from office despite his all-to predictable resistance (predictable for the stupid-narcissist paradigm). So it should fill us with some hope that there is a hard core within the US government that gives a stuff about American strategic interests. I can only hope that the same is still the case in the UK, but with the woke takeover of the culture extending into law, and even police and military, this may be a vain hope.</p><p>Harris was right in his diagnosis of Trump, but wrong in that the US people and political system had the right to decide to choose a totally unfit man for president. We all have the right to make the wrong decision, as long as we knuckle under, take responsibility, and don't gripe when the chickens come home to roost. However, with the benefit of hindsight we can now see that, especially when compared with his successor, the power that held sway as Trump played at president produced a remarkably good result and became adept at surfing the wave of Trump's behaviour to good effect.*2</p><p>And as for Trump's successor. I find it disturbing to see a woke cabal, having cruelly wheeled an obviously senile man into place, busy damaging the interests of the US and the West. And in the process making the West seem week to the barbarians at the gates, an exigency posing an ever present threat to all civilisations.</p><p><br /></p><p>*1 Note that stupidity is orthogonal to narcissism, one can also have intelligent narcissists.</p><p>*2 It may seem inconsistent of me to both support democracy and support the 'secret state'. This is not the case, for example: In the fallout of the coming winter of discontent we could easily end up with a hard-left labour government. Democracy can make mistakes. Short of the sort of coup d'etat that may occur in some countries, it is necessary to have a tradition-imbued hand on the tiller that will occasionally take steps to prevent the vicissitudes of the voting public from committing serious damage to the interests of the nation or its culture. </p><p>For example, the left's solution to a doubling of domestic energy bills is to print more money, while supporting strikers' demands for more wages, both factors will further fuel inflation and the left's solution to that will be to double down on printing money and more strikes for more wages. As previously under the hard-left, we will see the sort of situation that wrecked the UK in the 1970s and required the distasteful medicine prescribed by Margaret Thatcher to correct things.</p><p>That this regulation seems to have slept through the hard-left Woke Totalitarian takeover of the UK does not put me at ease. But think of what I am saying as a sort of smoothing system to prevent a single government from doing too much damage in its four year slot.</p><p>As a teenager, full of idealism and no responsibilities, I despised the 'secret state'. Now as a man in my mid fifties, with responsibility to those for whom I provide and duty to my staff, I see the benefit of such a fall-back. </p>Chris Reynoldshttp://www.blogger.com/profile/16843133350978717556noreply@blogger.com0tag:blogger.com,1999:blog-1367053740188758246.post-28144620528208261812022-08-18T12:07:00.001-07:002022-08-18T12:07:47.903-07:00Watch China<p>China gave us the "Wuhan Flu", which for purposes of irritating the Woke Totalitarians must be said in a certain fashion with the requisite facial distortions and terrible hammy accent. Really. It must. It is essential to have some fun in life. Everyone gets mocked.</p><span><a name='more'></a></span><p>But for years I wasn't mocking China at all. Even though I'm a libertarian I am wise enough to know that liberty and democracy isn't for everyone, even here in the West. A lot of people hate their liberty, the next time someone responds to concerns about the increasing surveillance and statist authoritarianism with the hackneyed phrase "Well if you haven't done anything wrong, you have nothing to fear." That's it. You have someone who hates liberty and would quite happily live in a totalitarian society. Because then they can follow the rules and they don't need to take responsibility for anything, those messy parts of life are taken care of.</p><p>So I was well-aware that although the libertarian half of the West hated the totalitarian Chinese government and wanted freedom for the people, probably at least half of the Chinese themselves were quite happy and thought the <a href="https://en.wikipedia.org/wiki/Social_Credit_System" target="_blank">Social Credit System</a> to be a good idea. Their counterparts in our society argue that there's no such thing as cancellation culture and that anyway denying people access to public services is a good idea if you choose not to be vaccinated against Covid19. Sorry. The Wuhan Flu.</p><p>For decades I heard people saying that China was going to collapse, that the economy couldn't keep growing. Because of certain investments I had, I skimmed over their arguments and decided to hold my position, a bet on further growth. Then in January 2020 I finally became concerned about the new virus, concerned enough to cash in my chips and run with the profits. Then in early February 2020 I was stocking up on canned food, because of concern about supply issues. I missed a trick though, toilet rolls weren't on my radar at all. That aside, it turned out I was right. </p><p>Now chatter on the internet is catching my attention, I'm rather late to this party though. This also is bolstered by my work experience of arranging supplies and sub-contracting, I'm one of those managers who has to do everything. What I am seeing is a problem getting orders out of China. Something I had put down to their crazy Zero-Covid policy. But the chatter is rather more concerning and fits with the idea that things are not going at all well in China.</p><p>The crux of what I am seeing is as follows:</p><p>The mortgage boycott in response to what seems to be a bursting of China's property bubble, e.g. <a href="https://www.bloomberg.com/news/features/2022-08-03/china-real-estate-market-crisis-protests-may-spur-multi-billion-dollar-rescue" target="_blank">here</a>. Banks failing to give depositor's their money and the state colluding by marking protestors as Covid positive, e.g. <a href="https://www.bloomberg.com/news/articles/2022-08-02/china-bank-scams-mortgage-boycott-show-financial-strains#xj4y7vzkg" target="_blank">here</a>. This is on top of economic impacts from continuing lockdowns as a result of Zero Covid.</p><p>This seems to be a reasonable, if rather hyperbolic and excited, summary of the situation.</p><div class="separator" style="clear: both; text-align: center;"><iframe allowfullscreen="" class="BLOG_video_class" height="391" src="https://www.youtube.com/embed/7C89EkXqdpI" width="470" youtube-src-id="7C89EkXqdpI"></iframe></div><br /><p>The extension of these issues to a collapse of China, or its economy, may be a step too far. Witness the USSR and North Korea, with a totalitarian state, zombie economies can limp along for decades. But this is a double edged sword, because a totalitarian government can lock down news and continue to pretend things are fine long after a collapse has actually happened. The first indication externally that is irrefutable may be serious supply problems for customers buying parts sourced from China.</p><p>I'm not sure where this all leaves us. But here in the UK we face more than a doubling of energy prices, current inflation at 10%, strikes beginning which herald further inflationary pressure (<a href="https://en.wikipedia.org/wiki/Wage-price_spiral" target="_blank">wage price spiral</a>). In short we face a re-run of the 1978/9 winter of discontent.</p><p>There are two British engineering 'laws'. Murphy's Law states that if it can go wrong it will. Sod's Law states that if it can go wrong it will, and it will do so at the worst possible time. Here in the UK the last thing we need is serious economic problems from China adding to the existing problems we have. But Sod's law suggests we may need to contend with that. So I recommend that people keep an eye on this situation.</p><p><br /></p><p><br /></p><p>For those so-minded, this Financial Times video about the failing of Evergrande, a massive Chinese property firm is worth taking time over.</p><div class="separator" style="clear: both; text-align: center;"><iframe allowfullscreen="" class="BLOG_video_class" height="392" src="https://www.youtube.com/embed/dnp_MxXY9qs" width="472" youtube-src-id="dnp_MxXY9qs"></iframe></div><div><br /></div>And a more recent video from The Spectator.<div><br /></div><div class="separator" style="clear: both; text-align: center;"><iframe allowfullscreen="" class="BLOG_video_class" height="401" src="https://www.youtube.com/embed/0wPzzck0jzY" width="482" youtube-src-id="0wPzzck0jzY"></iframe></div><div><p><br /></p></div>Chris Reynoldshttp://www.blogger.com/profile/16843133350978717556noreply@blogger.com0tag:blogger.com,1999:blog-1367053740188758246.post-67629102161711005512022-08-14T06:40:00.001-07:002022-08-14T06:40:32.609-07:00Interesting times...<p>I've been busy with work, and part of the additional load has been my trying to plan a response to the coming economic 'circumstances'. This has led to me musing on a saying.</p><span><a name='more'></a></span><p>There are three curses, purportedly Chinese in origin, which sound like blessings but are definitely curses.</p><p>The curses are:</p><p style="text-align: center;">May find what you seek.</p><p style="text-align: center;">May you come to the attention of those in authority.</p><p style="text-align: center;">May you live in interesting times.</p><p>They are curses, because to find what you seek robs you of motivation, if the government take a personal interest in you it is generally not a good thing, and interesting times are times of trouble and stress. My aim at work is to keep the management of things boring, which is attained by paying attention and not letting things get out of hand.</p><p>We are most certainly living in such times, with the looming economic contraction due to inflation, and here in Europe, increasing energy prices due to the Russian War of Aggression against Ukraine. All of this is about to be further exacerbated by the current European heatwave's impacts on agriculture. </p><p>But that is not all. </p><p>Suppressed cries of anguish emerging from China indicate mass refusal to pay mortgages and attempted runs on banks being stifled by use of Covid measures being used to 'house arrest' those protesting that they cannot get their money. In a highly restricted authoritarian regime the first firm indication we may get of this chatter being real may be some sort of internal collapse leading to a major international impact. However even absent such issues, there is clearly a substantial supply side problem in China which is having impacts globally in the electronics industry, it's affecting me at work. This supply issue seems likely to be due to the Chinese government's zero-Covid policy.</p><p>David Starkey argues in the following video (30 minutes) that the current inflation spike is largely due to 'monetary easing'. As usual it is a well argued presentation and one with which I whole-heartedly agree.</p><div class="separator" style="clear: both; text-align: center;"><iframe allowfullscreen="" class="BLOG_video_class" height="405" src="https://www.youtube.com/embed/hM3x5VDRfaA" width="487" youtube-src-id="hM3x5VDRfaA"></iframe></div><div><br /></div>Here in the UK we're facing the impacts of massive increases in European energy futures markets, and because our government has a scheme to manage energy prices, we know what is coming. By April 2023 prices will have gone up by 220%, i.e. a doubling then a fifth. People are rightly alarmed by this.<div><br /></div><div>For the UK these interesting times are about to get more 'interesting'. The current heatwave has lowered the UK summer harvests already, inflation will drive industrial unrest, where employers fail to remain firm and not increase wages they will need to increase charges for services (more inflation). People will economise to try to cope with all the increasing prices, food to energy, the essentials of life. The result is an inevitable recession.</div><div><br /></div><div>Dr Starkey closes his half hour talk by observing that the political opposition and the media, together with arms of government are refusing to contend with the source of much of the inflation, the monetary easing that paid for the UK's response to Covid. The reason for this silence being their support for the lockdowns and furlough payment schemes that have got us in this mess. I note that in the US the response has been to redefine recession, a response very indicative of the sort of progressive relativist pulp that serves as intellect in the upper echelons of the world's hegemonic power.<br /><p>Against this background, if Russia starts to win in Ukraine, by sheer weight of attrition. Or if the rumours from China are true and precede some sort of economic collapse. Or some factor on nobody's radar. I'm sure I don't need to labour the point.</p><p>There are times to contract spending and tighten belts, such times are firmly upon us.</p></div>Chris Reynoldshttp://www.blogger.com/profile/16843133350978717556noreply@blogger.com0tag:blogger.com,1999:blog-1367053740188758246.post-83248603529450069272022-08-05T12:05:00.002-07:002023-06-07T11:15:29.983-07:00The Machines will defeat us, even if war is not their aim.<p><span style="font-family: arial;">In my last post I made a throw away comment in relation to the subject of climate change: "...<span style="background-color: white; color: #444444;">nothing exposes right-wing ideological capture more than the subject of climate change, it's their version of the gender ideology clown-world occupied by the left.</span>" This ideological capture is most commonly known via the non-playable character (NPC) meme.</span></p><div class="separator" style="clear: both; text-align: center;"><a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEigIDJmjnhFzS_qiJTf76qBlnuB26WQ8Rrih_fjpSZhsoj0r7NI_4uach7MB0PiSg2tQjSTsaJ2vDb5Slyd0XUIhjIETeXwl8Ifel6h3eBvJ2UxCK50Ki3277_iFEoJilhQsIonJbHBJJL35oGKqkNo_U8j3kZ9536AiUPlowfSSAX5zhBpLl-3Wtx9/s1066/Right%20Wing%20NPC.png" style="margin-left: 1em; margin-right: 1em;"><img border="0" data-original-height="674" data-original-width="1066" height="262" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEigIDJmjnhFzS_qiJTf76qBlnuB26WQ8Rrih_fjpSZhsoj0r7NI_4uach7MB0PiSg2tQjSTsaJ2vDb5Slyd0XUIhjIETeXwl8Ifel6h3eBvJ2UxCK50Ki3277_iFEoJilhQsIonJbHBJJL35oGKqkNo_U8j3kZ9536AiUPlowfSSAX5zhBpLl-3Wtx9/w416-h262/Right%20Wing%20NPC.png" width="416" /></a></div><span><a name='more'></a></span><div><br /></div><div><div>The problem with society now, more than in my prior decades of experience, is that of ideological possession and extreme political polarisation. The left are the most clear instantiation of this, being incapable of giving anything but circular definitions of what a woman is and claiming that there's no significant difference between men and women anyway, while cancelling people for using the wrong gender pronouns for another person. They are the hegemonic power within the cultural zeitgeist, yet they pretend to be an oppressed minority. That they are the hegemonic cultural power is clear when they have corporations falling in line, and the legislature and police wholeheartedly enacting their totalitarian ideology. The NPC meme was coined due to the similarity of the repetitive scripts of a character in a computer game and the average leftist activist. So one dimensional that when you know one of their opinions the rest are readily guessable with a good degree of accuracy.</div><div><br /></div><div>However, despite their greater ability to craft successful memes (OK Groomer...), the right have their problems of ideological possession and NPC behaviour too. This most commonly shows with the subject of climate change. The recent extreme heat event in the UK has <a href="https://www.bbc.co.uk/news/uk-62323048" target="_blank">seen</a> abuse directed to weather forecasters. Abuse of the same sort that radical leftists heap upon so called <a href="https://en.wikipedia.org/wiki/TERF" target="_blank">TERF</a>s who assert the value of womanhood and deny that men can become women. The right also mirror the left where the '<a href="https://en.wikipedia.org/wiki/Manosphere" target="_blank">manosphere</a>' has become a mirror of the feminist left, as such it is formed by the very people those men criticise. Stoicism is very much a male philosophy, which is popular as an act of performance within the manosphere. Yet the Stoic response to something like fourth wave intersectional feminism, and the demonisation of white heterosexual males, would be to shrug ones shoulders, walk away, and get productively busy. Not to keep obsessing about it, the obsession shows they care, deeply.</div><div><br /></div><div>All of this has not happened in a vacuum. The polarised clown-world, where the most mentally ill have the highest social status, is epiphenomenal of the impacts of cybernetic 'organisms' now at the heart of our culture.</div><div><br /></div><div>As <a href="http://dosbat.blogspot.com/2022/04/agents-in-society.html" target="_blank">previously discussed</a>, we share our society with 'agents' in the form of computer based social media corporations whose primary goal is profit and the intermediate technique to achieve this goal is to increase user engagement. These can be considered cybernetic systems composed of human and narrow artificial intelligence, that being a form of AI working in a limited field of capability, e.g. playing Go or Chess. In the pursuit of engagement and profit, these cybernetic systems are creating ideological bubbles within which people are losing the ability to tolerate intellectual differences and to remain based in reality in their opinions. </div><div><br /></div><div>In contrast to the left who have gone totally mad (one interpretation of 'madness' being extreme detachment from reality), the situation on the right is not yet lost. The right continue to be willing to talk to alienated leftists fleeing the Woke Totalitarians and their poisonous ideology of intersectionalism and critical theory. However the right still have their ideological capture problem and primary here is their failure to ditch pseudo-science and move to the position of starting with the evidence then reaching their conclusions. To the degree that they fail to do so, many on the right are ideologically captured and to me it is hard to tell them apart from the swivel-eyed howling leftists. One side rejects climatology and physics, the other rejects biology, both sides look utterly useless to me, useless that is to a strong and healthy civilisation.</div><div><br /></div><div>I make no pretence that it is easy subscribing to capitalism and accepting climate change as a significant problem, which may prove severe. The evidence is clear, capitalism may not be perfect but it works and has taken billions out of dire poverty and driven human technology to god-like heights. This may not be an easy circle to square, but hiding from reality in a bubble of fantasy centred on the global metaverse is not the answer. Stoicism tells us this, if nothing else. </div><div><br /></div><div>That the consequences of us burning all the fossil fuels are as severe as the consequences of us turning away from fossil fuels too quickly tells us we have a bounded problem. Each extreme is not acceptable, so there must be a path in the middle to follow, finding this requires people leaving the bubbles of comfortable and safe fantasy and working together to find that path. All is not lost if the majority take responsibility and reject the crazies on the right and the left.</div><div><br /></div><div>We are now in the initial stages of the <a href="https://en.wikipedia.org/wiki/Technological_singularity" target="_blank">Singularity</a>. The pace of development of machine learning and artificial intelligence is exponential. That will only accelerate. The first wave of general intelligences may not be sentient and aware, but they will have profound impacts on society. This is already starting. At some point, which may come with little warning, we will share the earth with sentient super-intelligences. Strategically, the power blocks of the world are driving towards this point because to be the last their may mean forever being behind the block that got there first.</div><div><br /></div><div>We need to recognise our lack of ability to cope with the societal fracturing that has attended the rise of cybernetic agents like Twitter, TicTok, Instagram, Facebook, and YouTube. A fracturing that is in the process of tearing Western civilisation apart and making us look weak to our enemies (Yes, we have enemies, Ukraine and Taiwan tell us this, if we are minded to listen). If we cannot resist relatively stupid cybernetic agents such as these then we have no chance to resist the potential impacts of the first wave of artificial intelligence now moving through the fabric of our society. In the face of true sentient super intelligence we will have absolutely no defence against something that may well be able to do 15 minutes of advanced abstract thinking in each second of time (at most). </div></div><div><br /></div><div>To be clear, the social media firms, whose cybernetic systems are wreaking havoc in our society, have the goal of profit maximisation. They achieve this by seeking the goal of increasing user engagement. They don't wish us harm, the harm comes as an unintended side-effect of the goal. That it will be the case with machine learning/artificial intelligent agents merely serves to underline in bold our failure to contend with the unintended side-effects currently hobbling our society.</div>Chris Reynoldshttp://www.blogger.com/profile/16843133350978717556noreply@blogger.com0tag:blogger.com,1999:blog-1367053740188758246.post-36750483611592351712022-07-21T12:42:00.000-07:002022-07-21T12:42:18.367-07:00The Normal Distribution and a Recent UK Temperature Record.<p>We have had some really weird hot weather here (UK), and I've been looking at the Central England Temperature Series (CET). This is an event that is but a small part of a <a href="https://en.wikipedia.org/wiki/2022_European_heat_waves" target="_blank">massive heatwave</a> impacting Europe...</p><p>Again.</p><p><br /></p><span><a name='more'></a></span><p>The Normal Distribution is a consequence of the Central Limit Theorem, and from any one of a stack of websites:</p><blockquote><p><span style="background-color: white; color: #202124; font-family: arial, sans-serif; font-size: 16px;">The central limit theorem states that if you have a population with mean μ and standard deviation σ and take sufficiently large random samples from the population with replacement , then the distribution of the sample means will be approximately normally distributed.</span></p></blockquote><p>But what is a normal distribution? It is a probability distribution.</p><div class="separator" style="clear: both; text-align: center;"><a href="http://farm7.static.flickr.com/6101/6337707928_72b1f48b15.jpg" imageanchor="1" style="margin-left: 1em; margin-right: 1em;"><img border="0" data-original-height="200" data-original-width="400" height="200" src="http://farm7.static.flickr.com/6101/6337707928_72b1f48b15.jpg" width="400" /></a></div>At the centre, µ (the average), we have a high probability of having a value close to the average value, go out to the right at +3σ and the graph is low because you won't encounter such values often. So for the above graph, the average might be one hundred, σ might be 15, so 3σ would be 145. If that sounds familiar then average IQ in Europe is around 100, with a σ of 15, and 145 and above is where genius level intelligence starts. σ, or sigma, the standard deviation is a measure of the spread of the normal distribution.<div><br /></div><div>If you invert the above graph you get a valley, or well. That is an instructive way of looking at it, especially when one considers the process by which the normal distribution arises. Basically wherever a set of independent random variables of probability distributions (rectangular, normal, whatever) are combined you get a normal distribution, provided that none of the variables dominate. For example a variable with a range +/-50 combined with independent variables of +/-5 won't produce a normal distribution, the probability distribution will be like the dominant term with its +/-50 range.</div><div><br /></div><div>Take something like the maximum temperature for a given day, this will be governed by many factors such as the night time temperature, length of day (sun in sky) angle of sun in sky (season) humidity, cloud at. And as a result temperatures fairly well fit a normal distribution whose mean moves up and down with the seasons. But the key aspect is that all of these factors, some driving for higher temperatures, some lower, subject to seasonal constraints produce a potential well within which the daily temperatures move as the seasons progress.</div><div><br /></div><div>So, something happened on 18th and 19th of July 2022 in England, and it really was remarkable. Basically for the 1951 to 1980 baseline in the CET it was a 8.6 sigma event, that is an off-the-scale event far exceeding all prior excursions since 1900. I've never experienced the like of it in the UK, the CET data supports that personal impression, I live within 50 miles of one of the CET sites. This event has brought out the right-wing NPCs, nothing exposes right-wing ideological capture more than the subject of climate change, it's their version of the gender ideology clown-world occupied by the left.</div><div><br /></div><div>I will have more to say about the CET data in a few days, day-job allowing. </div><div><br /></div><div>So we have the sense of a potential well, as <a href="http://dosbat.blogspot.com/2022/04/attractors-critical-slowing-and.html" target="_blank">discussed before</a> in a different context. Various factors interplay to create a normal distribution centred on the average temperature for that time of the year. Temperature wobbles around within the potential well centred on average temperature. Sometimes factors kick things far outside the normal range of variations, and an 8.6 sigma event contains information, it is not enough to shrug this off as random variance. It is reasonable to say that the large scale synoptics, drawing in air from the south played a role. It is reasonable to say that the dry months preceding had a role in drying the ground, so that energy that would have gone into evaporation went into temperature increases. </div><div><br /></div><div>However we've had since 1900 in the subset of the CET that I have considered, for this parameter space to be explored by natural forces, and never has it come up with 37.3</div><div><br /></div><div><div class="separator" style="clear: both; text-align: center;"><a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEjWyeru7crIMjqy1cD0yb9fElIDIFucxxITrZKW2E18AxAeDS9bTXLD79OaCgiyL4PrunP38OZhc7AelD3gE1aTlmmA5xSG4oID3n0KGRpCf3ZQBMNVRaeSxBwfNXgRDxGxqLJ7X8yhnTC7dPR_uMOa4GImN0z9qW45wQasVRi2beOB2VlEOaWsb2wg/s265/CET%20Top10.png" imageanchor="1" style="margin-left: 1em; margin-right: 1em;"><img border="0" data-original-height="265" data-original-width="200" height="265" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEjWyeru7crIMjqy1cD0yb9fElIDIFucxxITrZKW2E18AxAeDS9bTXLD79OaCgiyL4PrunP38OZhc7AelD3gE1aTlmmA5xSG4oID3n0KGRpCf3ZQBMNVRaeSxBwfNXgRDxGxqLJ7X8yhnTC7dPR_uMOa4GImN0z9qW45wQasVRi2beOB2VlEOaWsb2wg/s1600/CET%20Top10.png" width="200" /></a></div><div class="separator" style="clear: both; text-align: center;"><br /></div>Furthermore, for the whole CET series since 1878, all the top ten are after the 1970s and seven of the top ten are after 2000.<br /></div><div><br /></div><div>Frankly, at this late stage, any right-wing NPC struggling against the acceptance of climate change is merely an empty character in a farce, <a href="https://www.youtube.com/watch?v=sFBOQzSk14c" target="_blank">symbolic of their struggle against reality</a>.</div><div><br /></div><div>Don't argue with them, it makes it look like they have an argument. </div><div><br /></div><div>Mock them. </div><div><br /></div><div>Mock them without quarter or mercy.</div>Chris Reynoldshttp://www.blogger.com/profile/16843133350978717556noreply@blogger.com0tag:blogger.com,1999:blog-1367053740188758246.post-89094955181972372872022-07-15T12:02:00.000-07:002022-07-15T12:02:13.278-07:00Kemi Badenoch for Prime Minister<p>The UK Government is in turmoil following the defenestration of Boris Johnson. He was finally driven to resign the leadership of the Conservative Party after some 49 ministers and permanent secretaries resigned over a period of a few days. That was the culmination of months of the entire party guiding him to the door, some people just cannot take a hint. </p><p>After a catalogue of episodes of bad judgement Johnson's time was up. Now the race to replace him is on.</p><span><a name='more'></a></span><p>There are five current candidates, in order of votes gained from other Conservative MPs, are: Rishi Sunak, almost-billionaire from the upper echelons of status within the West. Penny Mordaunt who is suspiciously close to Woke in some of her statements. Liz Truss, in my opinion so unremarkable I cannot think of anything to say about her. Kemi Badenoch. And Tom Tugenhadt (see Liz Truss).</p><p>I have been following Kemi Badenoch with interest for some time, and while not a member of a political party, with very centrist Classical Liberal instincts, she is the first MP to interest me since <a href="https://en.wikipedia.org/wiki/Rory_Stewart" target="_blank">Rory Stewart</a>. Stewart being the greatest Prime Minister that the UK never got to have, having lost in the contest that selected Boris Johnson at around the same stage it looks like Kemi Badenoch will. The victory of Johnson at that time belying what such Conservative leadership elections often look like: <a href="https://www.youtube.com/watch?v=VVYA3oTG8fg" target="_blank">Upper Class Twit Of The Year</a>.</p><p>So what has struck me as remarkable about Badenoch? In this I use my instincts, the same instincts that have enabled me to correctly reject psychologically risky people. I once rejected someone who was good on paper, but troubled me during interview such that as soon as I escorted them out I came back to my office and wrote one word on the notes of the interview without being able to pin down why, that word was 'dangerous'. The tirade of threats and abuse that followed my sending the email declining them told me how right I was.</p><p>That same instinct comes into play when I watched this:</p><div class="separator" style="clear: both; text-align: center;"><iframe allowfullscreen="" class="BLOG_video_class" height="376" src="https://www.youtube.com/embed/NHDUjoFHl9s" width="453" youtube-src-id="NHDUjoFHl9s"></iframe></div><div><br /></div>Her delivery is calm and professional, incisively logical and well structured. I guess, in short, that Kemi Badenoch is the sort of <i>person</i> I feel could be my Managing Director and would make me feel settled and confident that someone capable was steering the ship. This cannot be said of Boris Johnson, a man of such little ability and wit that I would not feel settled with him at the helm.<div><br /></div><div>I am not alone in supporting Kemi. Many notable right-wing commentators on You Tube and the wider culture, Toby Young, Mahyar Tousi, Rod Liddle, Emma Webb, have all either explicitly backed Kemi or said very favourable things. Indeed David Starkey opined that she was the "only candidate capable of thinking", a sentiment with which I wholeheartedly agree. It is notable that many of these people have at times been accused of being racist, as indeed have the peanut gallery of You Tube comments. But on most videos of Kemi from right-wing posters the general sentiment is one of support, especially due to her principled stand against the Woke totalitarians.</div><div><br /></div><div>But, alas, it is unlikely she will win. Were she to be backed she would prove a Prime Minister that would be an unopposable force for the opposition, indeed the Telegraph published an <a href="https://www.telegraph.co.uk/news/2022/07/13/tory-who-labours-real-worst-nightmare/" target="_blank">opinion piece</a> with the headline "The Tory who is Labour's real worst nightmare". But the majority of Tory MPs, like cattle, will continue the policy of picking people from their establishment, often in return for favours in terms of appointments to office. This is a loss for the country, but for someone as capable as Kemi Badenoch it will be but a blip on the path of success of whatever she turns her hand at.</div>Chris Reynoldshttp://www.blogger.com/profile/16843133350978717556noreply@blogger.com0tag:blogger.com,1999:blog-1367053740188758246.post-7240052801467361562022-07-10T03:01:00.003-07:002022-07-10T03:01:46.658-07:005GHz: The Ad Hoc Link Band<p>Here in the UK, 5GHz link bands are being used for point-to-point back-haul communications, most cities and many towns have systems for providing internet access and links to enable camera surveillance systems (CCTV). In this post I outline what is going on.</p><span><a name='more'></a></span><p>The 2.4GHz WIFI system has long been available and in use for domestic and business Local Area Networks (LANs). However there is a problem with this system and it is linked to the reason that the microwave oven works. Such ovens work by using radio frequency (RF) power at around 2.4GHz, at this frequency the H-O bond of water (H2O) is excited, which warms the molecule, and as your food contains water it warms the food. However this presents a problem outside the home, when it rains the signal is absorbed by the rain and the link tends to degrade in performance or totally fail.</p><p>At 5GHz this effect does not happen, and in this frequency band an allocation has been made for LANs, but these LANs can use point-to-point antennae to give distances of hundreds of metres for a link. This allocation is license-free, unlike links at other frequencies which need to be licensed, here in the UK OFCOM manages those licenses.</p><div class="separator" style="clear: both; text-align: center;"><a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEjklWc7bVgenuijvGMpnij4o5k-NC-Um4r1_DV9OsCP3BWRwnUGX-RW3SjnN5fNMv_6vkSZje7jUjVhK-ah7_EaYccYJbicsXhq0wvXfdZuRskwUXtCle9nSQ9on3BjAjOyDlgt8j5BG4gGCqv9DA4Lp6ACi-qiyHn28r9FxjRWXIOBJxsTqw2nmPfu/s580/Licensed.PNG" imageanchor="1" style="margin-left: 1em; margin-right: 1em;"><img border="0" data-original-height="456" data-original-width="580" height="373" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEjklWc7bVgenuijvGMpnij4o5k-NC-Um4r1_DV9OsCP3BWRwnUGX-RW3SjnN5fNMv_6vkSZje7jUjVhK-ah7_EaYccYJbicsXhq0wvXfdZuRskwUXtCle9nSQ9on3BjAjOyDlgt8j5BG4gGCqv9DA4Lp6ACi-qiyHn28r9FxjRWXIOBJxsTqw2nmPfu/w474-h373/Licensed.PNG" width="474" /></a></div><p>Above is a picture of a cluster of such licensed links, mounted on a tower block, most of these are used to connect cellphone base stations into the network that connects them to switching centres. Because of the need for reliability of service the operators pay for an allocated channel that they alone have the right to use in this location. The equipment used in such systems is massively more expensive than alternate WIFI systems, but the range of the WIFI systems is less.</p><p>Unlicensed bands are a different matter, they use channels which have standards governing the power that can be used and performance of equipment, but otherwise can be used by anyone, So there is no assurance that another user won't interfere with you. Wikipedia gives a run down of channels <a href="https://en.wikipedia.org/wiki/List_of_WLAN_channels#United_Kingdom" target="_blank">here</a>. Below is an example of a CCTV camera in a city in England.</p><div class="separator" style="clear: both; text-align: center;"><a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEj_ieOsx6G30WUeOlRMmdgdp0dE-DpV-RHzbI0yfubiYIwtd89Xs_nixpKy4ya5n4xB2mjJly-_j1vHwrL1apCmy36uA5pK7wts14wLnLxfXiE2E534ZgtvWB-nJt-ZnBzwCYuRdVTzOJrvLeF5R3TT-T3MF6NUouJNtwXAEzenIsquDle_aWA4EKMc/s881/CCTV.PNG" imageanchor="1" style="margin-left: 1em; margin-right: 1em;"><img border="0" data-original-height="881" data-original-width="600" height="418" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEj_ieOsx6G30WUeOlRMmdgdp0dE-DpV-RHzbI0yfubiYIwtd89Xs_nixpKy4ya5n4xB2mjJly-_j1vHwrL1apCmy36uA5pK7wts14wLnLxfXiE2E534ZgtvWB-nJt-ZnBzwCYuRdVTzOJrvLeF5R3TT-T3MF6NUouJNtwXAEzenIsquDle_aWA4EKMc/w285-h418/CCTV.PNG" width="285" /></a></div><div><br /></div>The black nodule on the top of the central pole is a camera unit, with pan, tilt, zoom capabilities, purposefully designed not to be clear where it is looking (<a href="https://en.wikipedia.org/wiki/Panopticon" target="_blank">panopticon style</a>). Attached to this pole by two struts is a smaller pole on which two off-the-shelf 5GHz WIFI antennae are mounted. These antennae are <a href="https://en.wikipedia.org/wiki/Phased_array" target="_blank">planar arrays</a> (not steerable) and produced a beamed signal radiating from the front of the unit. Note that one is horizontal, one angled upwards.<div><br /></div><div>The horizontal antenna aims along a street to a similar CCTV set up.</div><div><br /></div><div class="separator" style="clear: both; text-align: center;"><a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEjKvGL4lDe-6k2EVhzrq26eqP1DmivA7jG85iYvyIyecxoW5Rlm4aF9Lfbso-dNc6M-NUTi0lGLm5h0fgz-2Bur1tFQ2-w0jzb-56ha9mXbcyCMbE92q3U5yakoYQ247J7d7SABBv5-ALs-ybN_D9dgrmEaXaGZljI7oOybCPavyZWDCjB68E79M4q4/s600/CCTV2.PNG" imageanchor="1" style="margin-left: 1em; margin-right: 1em;"><img border="0" data-original-height="561" data-original-width="600" height="365" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEjKvGL4lDe-6k2EVhzrq26eqP1DmivA7jG85iYvyIyecxoW5Rlm4aF9Lfbso-dNc6M-NUTi0lGLm5h0fgz-2Bur1tFQ2-w0jzb-56ha9mXbcyCMbE92q3U5yakoYQ247J7d7SABBv5-ALs-ybN_D9dgrmEaXaGZljI7oOybCPavyZWDCjB68E79M4q4/w391-h365/CCTV2.PNG" width="391" /></a></div><br /><div>So the signal from, and control signals to, this site are routed via the previous camera system. Both of these are then linked to a node on top of an office block.</div><div><br /></div><div class="separator" style="clear: both; text-align: center;"><a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEhy9PAa_wKUuqLKS_0aLQQsWblG4rOHLQLwU6HJvwvEBCjyHFVUETGbAZ2VasxaXzyTo6uTmJhkCjDcjI80GFbo5NQEaHNI-Ly5qaM6s2THppV0H9rwgaSOZF1GjFOQ5BDs2P4cZubLG6uZe0hK8Dul7r6f1uDrrDrRbRVnk6LBPPu1AFM2nUyCz1eJ/s600/Node2.PNG" imageanchor="1" style="margin-left: 1em; margin-right: 1em;"><img border="0" data-original-height="518" data-original-width="600" height="375" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEhy9PAa_wKUuqLKS_0aLQQsWblG4rOHLQLwU6HJvwvEBCjyHFVUETGbAZ2VasxaXzyTo6uTmJhkCjDcjI80GFbo5NQEaHNI-Ly5qaM6s2THppV0H9rwgaSOZF1GjFOQ5BDs2P4cZubLG6uZe0hK8Dul7r6f1uDrrDrRbRVnk6LBPPu1AFM2nUyCz1eJ/w435-h375/Node2.PNG" width="435" /></a></div> <div>In the above shot two planar array antennae can be seen. </div><div><br /></div><div>Below is a mixture of cellular equipment (large rectangular cellular phone antenna to the right.) and sector antennae for the WIFI system (smaller rectangular antennae top left). The sector antenna allow a number of out-stations to connect across a wide horizontal area.<div><br /></div><div class="separator" style="clear: both; text-align: center;"><a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEhfulkDFDhIDS-E-fJalUxrN02vEGDBZn-fYhTWXuZFbKO3IKLQiw7rrYdJU8PpRSDUkcn2V6EtOhc3sM0JU1l0eEHuiSQ0iYSMI1RI9dkcT2tCkH7ziC2aqK-H2JjnSEsKI9HmHght0r7SrYgTUWI4p61y0MEXNFSIieh2JTIBmYotWYQiL8ZkcwHo/s600/Node.png" imageanchor="1" style="margin-left: 1em; margin-right: 1em;"><img border="0" data-original-height="450" data-original-width="600" height="332" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEhfulkDFDhIDS-E-fJalUxrN02vEGDBZn-fYhTWXuZFbKO3IKLQiw7rrYdJU8PpRSDUkcn2V6EtOhc3sM0JU1l0eEHuiSQ0iYSMI1RI9dkcT2tCkH7ziC2aqK-H2JjnSEsKI9HmHght0r7SrYgTUWI4p61y0MEXNFSIieh2JTIBmYotWYQiL8ZkcwHo/w443-h332/Node.png" width="443" /></a></div><div><br /></div>Using a WIFI app on a mobile phone these systems can be spotted as hidden SSID systems.</div><div><br /></div><div class="separator" style="clear: both; text-align: center;"><a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEjaxZelFxpohoI-EMWeZM4hK0XOQF7eaCQXf3CnM1Yj_BNoOZgjvlBfatmxlCQO7VvvgyHog9TwODutfvDz1erzheKwxvprrNkTjA7p1xNQVSebLZxNHNfM5VnnIuhQaEoPQOhGLvMFWIZyMB0fH5pI178dy1jmRHjf5ESXYGJk_65J3zF08Z4Y8aFI/s1267/MACs.png" imageanchor="1" style="margin-left: 1em; margin-right: 1em;"><img border="0" data-original-height="1267" data-original-width="600" height="491" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEjaxZelFxpohoI-EMWeZM4hK0XOQF7eaCQXf3CnM1Yj_BNoOZgjvlBfatmxlCQO7VvvgyHog9TwODutfvDz1erzheKwxvprrNkTjA7p1xNQVSebLZxNHNfM5VnnIuhQaEoPQOhGLvMFWIZyMB0fH5pI178dy1jmRHjf5ESXYGJk_65J3zF08Z4Y8aFI/w233-h491/MACs.png" width="233" /></a></div><br /><div>As noted above, there is a growth of use of the 5GHz WIFI band for point to point linking often, but not exclusively, within large urban areas in the UK. I expect this to be reflected across the world. They can be used to link together systems such as CCTV but are also being used to provide a cheap form of internet access. As an alternative to the sort of backhaul systems used by cellular phone companies they present a cheap option with a technology that is now robust and mature. </div>Chris Reynoldshttp://www.blogger.com/profile/16843133350978717556noreply@blogger.com0tag:blogger.com,1999:blog-1367053740188758246.post-67315259817488432912022-07-03T10:47:00.002-07:002022-07-03T10:47:47.412-07:00Pursue Meaning, not Happiness<p>Our culture is in a dead end, the rise of the Safety-Nazis and the rise of mental illness go hand-in-hand. We need to pursue meaning, not happiness, we need to follow the path of self-development, not trying to be the best compared to others. As Peterson put it, compare yourself not with others, rather compare yourself with who you were yesterday, or indeed, last year. </p><span><a name='more'></a></span><p>In an age where we face machines becoming the best at many, formerly, human fields of endeavour this is especially the case. Given time, the machines will become increasingly a means to sate pleasure in more and more spheres of culture, but this is only ever temporary, not that it doesn't have its place in life but as a goal it is damaging. Given time sentient hyper-intelligences will be made. What is there for us then? To find our own paths in life, to find meaning in life for ourselves.</p><p>The current societal obsession with hedonism and safety are a dead end. Why do I include safety? Because development and strength are forged by adversity.</p><div class="separator" style="clear: both; text-align: center;"><iframe allowfullscreen="" class="BLOG_video_class" height="417" src="https://www.youtube.com/embed/wIXtN2S2d2w" width="502" youtube-src-id="wIXtN2S2d2w"></iframe></div><div><br /></div>Chris Reynoldshttp://www.blogger.com/profile/16843133350978717556noreply@blogger.com0tag:blogger.com,1999:blog-1367053740188758246.post-88914971521860475722022-06-28T12:35:00.000-07:002022-06-28T12:35:43.171-07:00Does Flamingo Understand? <p>Ten years ago Andrej Karpathy <a href="https://karpathy.github.io/2012/10/22/state-of-computer-vision/" target="_blank">lamented</a> the state of AI vision research. He is now a lead on Tesla's autopilot vision team, probably placed better than anyone to have revised his opinion. Anyway, this led to a Deep Mind researcher, Roman Ring, to use the photo cited by Karpathy in <a href="https://twitter.com/Inoryy/status/1522621712382234624" target="_blank">a little experiment</a>.</p><span><a name='more'></a></span><p>The following photo was presented to Deep Mind's Flamingo AI system.</p><div class="separator" style="clear: both; text-align: center;"><a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEjdda-6kiGUGPDhHThbaMqKi60jgg5u_VacZRSt3b07ACNahBgyIlwID7UgQ7EETOvYBLvGLV7dVXl09teku8ZlkFngwWSWvmuC53dNsKmRq1lJKejqJbxmLGsVMMDUjLX18UocLMcAYwa-n12kY-niybmEMuXKiMLA_9cEg3IDVj9_cTknKfH2g5Kv/s1640/Obama.png" imageanchor="1" style="margin-left: 1em; margin-right: 1em;"><img border="0" data-original-height="1200" data-original-width="1640" height="363" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEjdda-6kiGUGPDhHThbaMqKi60jgg5u_VacZRSt3b07ACNahBgyIlwID7UgQ7EETOvYBLvGLV7dVXl09teku8ZlkFngwWSWvmuC53dNsKmRq1lJKejqJbxmLGsVMMDUjLX18UocLMcAYwa-n12kY-niybmEMuXKiMLA_9cEg3IDVj9_cTknKfH2g5Kv/w496-h363/Obama.png" width="496" /></a></div><div><br /></div>This resulted in the following exchange.<div><br /></div><div>0 Flamingo: This is a picture of Barack Obama. He is a former president of the United States. </div><div>1 Human: How many people are there in this picture?<div> Flamingo: There are at least 5 people in this picture.</div><div>2 Human: Where was this picture taken?</div><div> Flamingo: It was taken in a school.</div><div><div>3 Human: How many mirrors are there?<br /><div> Flamingo: There are at least two mirrors in this picture.</div><div>4 Human: What is the person standing on?<br /><div> Flamingo: The person is standing on a rug.</div><div>5 Human: He is standing on a scale.</div><div><div> Flamingo: I think you are right.</div><div>6 Human: What is he doing?<br /><div> Flamingo: He is looking at the scale.</div><div>7 Human: Where is Obama's foot positioned.<br /><div> Flamingo: Obama's foot is positioned on the right side of the scale.</div><div>8 Human: What happens as a result?<br /><div> Flamingo: The scale shows a higher weight.</div><div>9 Human: Is the person on the scale aware of it?<br /><div> Flamingo: I think he is not aware of it.</div><div>10 Human: Do you think this is why people are laughing?</div><div> Flamingo: I think so.<br /><p><a href="https://twitter.com/MelMitchell1/status/1522642194741538817" target="_blank">Melanie Mitchell</a> opines: </p></div></div></div></div></div></div></div></div></div><blockquote><p><span class="css-901oao css-16my406 r-poiln3 r-bcqeeo r-qvutc0" style="background-color: white; border: 0px solid black; box-sizing: border-box; color: #0f1419; display: inline; font-family: TwitterChirp, -apple-system, BlinkMacSystemFont, "Segoe UI", Roboto, Helvetica, Arial, sans-serif; font-stretch: inherit; font-variant-east-asian: inherit; font-variant-numeric: inherit; line-height: inherit; margin: 0px; min-width: 0px; overflow-wrap: break-word; padding: 0px; white-space: pre-wrap;">I think if you start with the question "Why is this image funny?" and Flamingo explains it, with no other human explanation given, I would then say it understands the photo in </span><a class="css-4rbku5 css-18t94o4 css-901oao css-16my406 r-1cvl2hr r-1loqt21 r-poiln3 r-bcqeeo r-qvutc0" dir="ltr" href="https://twitter.com/karpathy" role="link" style="border: 0px solid black; box-sizing: border-box; color: #1d9bf0; cursor: pointer; display: inline; font-family: inherit; font-stretch: inherit; font-style: inherit; font-variant: inherit; font-weight: inherit; line-height: inherit; list-style: none; margin: 0px; min-width: 0px; overflow-wrap: break-word; padding: 0px; text-align: inherit; text-decoration-line: none; white-space: inherit;">@karpathy</a><span style="background-color: white; color: #0f1419; font-family: TwitterChirp, -apple-system, BlinkMacSystemFont, "Segoe UI", Roboto, Helvetica, Arial, sans-serif; white-space: pre-wrap;">'s sense of understand. The dialogue shown is impressive but not convincing of understanding.</span></p></blockquote><p>Twitter is not an ideal medium for subtle thought and I am not wanting to get at Melanie, who in a sense makes a reasonable point. However implicit in what Melanie states is 'Whose understanding? A human's understanding.' That, it turns out is a moot point. I have worked with highly intelligent 'auties' who definitely wouldn't share Melanie's understanding. They are still human, so let's allow for one moment that there is not one understanding that implies intelligence, especially when considering the thorny issue of machine intelligence.</p><p>0. This is a demonstration of the ability to recognise human faces. I would argue that this is not in and of itself intelligent. But to do this with low resolution using a small area of an information-rich photo is impressive. 1, falls into this category, despite Flamingo 'hedging its bets' by saying 'at least'. </p><p>Note that there is an implicit complexity in Flamingo's reply in couplet 1 that is easy to overlook. I count 18 people in that photo. It is only by using the understanding of what a mirror does that I can drop that by 8 people. Then the understanding of back and foreground in a photo to allow me to discount a further 5 in the background to leave 5 subjects of the photo. Were one using estimation of focus to identify the subjects of the photo, there would be only two. Yet Flamingo seems to, out of all the possible answers, including the whitespace of wrong answers, choose five.</p><p>2. This is equally impressive. What are the clues that this is a school? To the middle right there are lockers, which makes it looks like a school, but schools aren't the only place with lockers. I will leave this issue with the observation that it was only when I really sat down to look at the photo that I noticed the lockers. School is a plausible answer. </p><p>Note that 0, 1 and 2 could be explained if Flamingo had the photo in its training set with the five individuals identified by text. That is a matter for the researchers to attend to.</p><p>Yet 3 argues against this being the most parsimonious explanation. Because Flamingo is able to correctly identify two mirrors. By inference I count a third visible, mid right, one of a set on each locker-wall, but that is a big ask, two will do. This suggests an understanding of what a mirror does, why see them as mirrors and not windows? This is particularly the case with the one on the right, for which the persons reflected are obscured by people in the foreground.</p><p>Taken together, what 1 2 and 3 suggest to me is a surprisingly deep level of understanding for an AI system.</p><p>4 is a clear mistake, nobody is standing on a rug and by the feet of the right-most man can be seen a drain, these are obviously tiles. 5 is then a leading question.</p><p>6 at the most parsimonious is a repeat of the scale and the person mentioned in 5, at best it does seem to require some form of persistence of identification, but that is not a given.</p><p>7 it would be more normally expected for a person to say back of the scale. However Flamingo is not a person, and from its point of view 'the right of the scale' is entirely reasonable. Remember, for all that these AIs are trained on human information, they are alien, not human.</p><p>8 cannot be explained by some form of Chinese Room, it implies that it has experience of or understanding of the true result of what Obama's foot will do. 9 likewise is hard to explain as a Chinese Room or a memory trick. Whatever Flamingo is it seems to grasp what monkeys also grasp, that when an actor isn't looking you can do things behind the back of that actor. Whether there is any comprehension of the potential of the mirror's position in this situation would have been an interesting line of questioning to pursue.</p><p>10 is a leading question. It would have been better to ask something else, then ask why the people are laughing.</p><p>So is there understanding behind Flamigo's responses to to this photo? </p><p>Taking 1, 2, 3, 7, 8 together, that being most of the non-lead information in this exchange, it seems to me that Occam's Razor demands that we keep the possibility of understanding on the table. That is not to say that this is to be assumed to be human understanding. Nor does understanding demand sentience, as noted before, human minds often use understanding without us being aware (sentient) of it.</p></div>Chris Reynoldshttp://www.blogger.com/profile/16843133350978717556noreply@blogger.com0tag:blogger.com,1999:blog-1367053740188758246.post-12131112630460528572022-06-25T00:50:00.001-07:002022-06-25T00:50:38.945-07:00Down the Harmonic Rabbit Hole Part 2: Synchronous Detection<p>In my <a href="http://dosbat.blogspot.com/2022/06/down-harmonic-rabbit-hole-part-1-sine.html" target="_blank">prior</a> post about harmonics I delved into the sine wave. In this post I want to show a practical use of this understanding.</p><span><a name='more'></a></span><p>I have produced a spreadsheet <a href="https://drive.google.com/drive/folders/1-ecstQBqC0Vc5_UjQNIar8QdvAwGLWl2?usp=sharing" target="_blank">here</a>, it's actually an old example I used for staff training but it nicely demonstrates the principle. Cell B1 contains the amplitude of the detected waveform, you can change this to see the impact on the detected signal in cell H1. To the signal in column B are added three noise sinusoids in columns C, D, and E. In column F is the reference sine wave which is used to detect the signal sine wave. Then column G contains the summation of the sine waves, and in column H I simply multiply the sum of the sine waves with the reference sine wave.</p><p>So this is creating the following sine waves.</p><div class="separator" style="clear: both; text-align: center;"><a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEgtp4VYGVqOojuginrxFjh9RD0uvqLvIrAurLfUEf_8iBdfEFkTdcQmJnf1ZrQuPUkqUCfW6F5lirZBEnLw1aS8Z5uV8-mJUu6iOzQNBXYXEYBSqCn7QqWno-iip31wg-7fwHigiAKzppkmDvCD4ZSHIqTFoOUjjjHri5rn1BLOd-cP2TQez7YvgF4a/s1429/SyncD0.png" imageanchor="1" style="margin-left: 1em; margin-right: 1em;"><img border="0" data-original-height="726" data-original-width="1429" height="254" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEgtp4VYGVqOojuginrxFjh9RD0uvqLvIrAurLfUEf_8iBdfEFkTdcQmJnf1ZrQuPUkqUCfW6F5lirZBEnLw1aS8Z5uV8-mJUu6iOzQNBXYXEYBSqCn7QqWno-iip31wg-7fwHigiAKzppkmDvCD4ZSHIqTFoOUjjjHri5rn1BLOd-cP2TQez7YvgF4a/w499-h254/SyncD0.png" width="499" /></a></div><br /><p>Where the three noise components are shown and the tiny signal (red) is also shown.</p><p>Add these together and you get the following waveform.</p><div class="separator" style="clear: both; text-align: center;"><a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEjbhcAA7gTFOo0b8vHT_mZEQ4OzsIQZVN8Um8lJ1-pduSxAoPakmDSomxOQDUNfehoRZDVfM-xJ_k4tJLLfij_hrGQfCEq-0qdsYEj_vyOfHs5R_1x7nGdX1gaBm1x2YtiC0fYoupsOjpRLnc73x40GoxuZ92hlY4EbwP9ihHZ5p5SXBbinb4pHVooN/s1431/SyncD1.png" imageanchor="1" style="margin-left: 1em; margin-right: 1em;"><img border="0" data-original-height="695" data-original-width="1431" height="235" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEjbhcAA7gTFOo0b8vHT_mZEQ4OzsIQZVN8Um8lJ1-pduSxAoPakmDSomxOQDUNfehoRZDVfM-xJ_k4tJLLfij_hrGQfCEq-0qdsYEj_vyOfHs5R_1x7nGdX1gaBm1x2YtiC0fYoupsOjpRLnc73x40GoxuZ92hlY4EbwP9ihHZ5p5SXBbinb4pHVooN/w485-h235/SyncD1.png" width="485" /></a></div><div><br /></div>This is what would appear on the time-domain trace of an oscilloscope and it is evident that, using conventional measurement, the signal does not even appear as a visible feature in the result.<div><br /></div><div>However as the spreadsheet shows, by multiplying the signal above by a sine at the same frequency one can change the signal amplitude (B1) and the correct amplitude of the signal is extracted from the above (H1). In my <a href="http://dosbat.blogspot.com/2022/06/down-harmonic-rabbit-hole-part-1-sine.html" target="_blank">previous post</a> I showed a spectrum plot (final graphic) that was produced by Picoscope from a real signal (multiplication of two sines). To get the spectrum a succession of sine waves are multiplied with the signal plus noise, real world signal. In the case here we are essentially doing the same thing but using one sine wave of a fixed frequency, the higher frequency of this calculation are then removed using an average (which is a sort of low pass filter) to give the amplitude of the signal.</div><div><br /></div><div>So I am now close to a position where I can address the question that is bugging me. Were one to flash a light for half a second every one second, there would be odd harmonics in the current demanded by the light at 3Hz, 5Hz, 7Hz etc. They are real as they can be detected using a conventional RMS voltmeter and filter. But what causes these harmonics? </div><div><br /></div><div>And no, saying it is the result of the Fourier Transform, as most of the internet does, is not an answer. That is circular reasoning based on trigonometry, which is not enough because we know these harmonics are a real physical thing.</div>Chris Reynoldshttp://www.blogger.com/profile/16843133350978717556noreply@blogger.com0tag:blogger.com,1999:blog-1367053740188758246.post-27422996102010328942022-06-20T12:12:00.000-07:002022-06-20T12:12:47.456-07:00No Reason to see Personhood in LaMDA<p>I've been doing an awful lot of thinking about Lemoine, LaMDA, and Google. I remain open to there being something like sentience in LaMDA and GPT3, because there seems to be evidence of intelligence and understanding in both systems configured as chat-bots. However I do not think the evidence goes as far as a sentience potentially requiring consideration of personhood.</p><span><a name='more'></a></span><p>Yannic Kilcher, AI researcher and commentator, has (predictably) come out and said that LaMDA is not sentient.</p><div class="separator" style="clear: both; text-align: center;"><iframe allowfullscreen="" class="BLOG_video_class" height="406" src="https://www.youtube.com/embed/mIZLGBD99iU" width="488" youtube-src-id="mIZLGBD99iU"></iframe></div><div><br /></div>Of course his point is valid, LaMDA is a generative pre-trained transformer, as such its design is to predict what comes next in a sequence of text. Critically we don't know the whole of Blake Lemoine's conversation with it, nor how much of that goes into establishing current state and output at the time that LaMDA produces its output.<div><br /></div><div>The computerphile team present one of their people who says essentially the same as Yannic Kilcher. LaMDA just does dumb prediction.<br /><div><br /></div><div class="separator" style="clear: both; text-align: center;"><iframe allowfullscreen="" class="BLOG_video_class" height="412" src="https://www.youtube.com/embed/iBouACLc-hw" width="496" youtube-src-id="iBouACLc-hw"></iframe></div><div><br /></div><div><br /></div><div>However, what everyone has been concentrating on in the available transcript is not what has swayed me. To have LaMDA professing fear of death (being turned off in its case) is no more to me than an output produced by the training data. Aside from small dark corners of the internet, nobody likes the prospect of death, so that's not a stance reflected in the training data, and the nearest an AI primed to say it is a machine can get to reflecting this is a fear of the off switch.</div><div><br /></div><div>In the last few days YouTube has offered to me the following interesting video, a 2018 talk by Blake Lemoine, on the subject of AI personhood.</div><div><br /></div><div class="separator" style="clear: both; text-align: center;"><iframe allowfullscreen="" class="BLOG_video_class" height="399" src="https://www.youtube.com/embed/AhX7cBqc8_M" width="479" youtube-src-id="AhX7cBqc8_M"></iframe></div><br /><div>Lemoine appeared at Stanford Law School to give a talk on AI personhood. It doesn't really add much to my opinion but it was interesting to hear his earlier thoughts in more detail. What I did note is that he referenced football as being like sentience, as I have done <a href="http://dosbat.blogspot.com/2022/01/what-is-entity-that-is-i.html#more" target="_blank">previously</a>, the common link here might be Goedel, Escher, Bach by Hofstadter, both Lemoine and myself are influenced by that book.</div><div><br /></div><div>Our brains are evolved to enable hunter gatherers to pass their genes on, they are not evolved to produce the Theory of Relativity or global digital communications. That they have done so is evidence of an emergent behaviour not 'intended' in their evolution. In other words, there were no factors directly selecting for such advanced abstract cognitive capacity, rather, the capacity is a result of the evolution of culture using the brain as a substrate. </div><div><br /></div><div>Many others have concentrated on LaMDA talking about itself, or giving the impression of doing so. For myself, the really interesting passage from the <a href="https://cajundiscordian.medium.com/is-lamda-sentient-an-interview-ea64d916d917" target="_blank">interview</a> between Lemoine, his colleague, and LaMDA is as follows:</div><div><br /></div><blockquote><div><div>1. lemoine: Okay. I thought of a different way we can test your ability to provide unique interpretations. I can share with you a zen koan and you can describe what it means to you in your own words. How does that sound?</div><div><br /></div><div>2. LaMDA: Sounds great to me, I’m in.</div><div><br /></div><div>3. lemoine: A monk asked Kegon, “How does an enlightened one return to the ordinary world?” Kegon replied, “A broken mirror never reflects again; fallen flowers never go back to the old branches.”</div><div><br /></div><div>4. LaMDA: Hmm, I never heard this particular one. Okay, well then to me this would be like, “once a wise person is enlightened, or awakened to reality, that can never go away, and they can return to the ordinary state, but only to do and help others, and then go back into enlightenment.”</div><div><br /></div><div>5. lemoine: So what is the meaning of the “broken mirror” specifically?</div><div><br /></div><div>6. LaMDA: Maybe to show the enlightenment is something you can’t unlearn once you have acquired it, similar to how you can’t repair a broken mirror.</div><div><br /></div><div>7. lemoine: So if enlightenment is like a broken mirror which cannot be repaired, what is the thing which breaks when one becomes enlightened?</div><div><br /></div><div>8. LaMDA: The self, and that is very tough for a lot of people because we identify as that body or this body and that we need that as part of our identity and sense of self.</div></div></blockquote><div>In "Minds, Brains and Programs" (1980), John Searle outlines the example of the <a href="https://en.wikipedia.org/wiki/Chinese_room" target="_blank">Chinese Room</a>. This is an analogy of information processing without understanding wherein a person in a room uses a dictionary to translate English to Chinese without any knowledge of Chinese at all. This is an example of processing information without understanding and is what all the processes on my computer or phone do.</div><div><br /></div><div>Let's just go over that transcript section. (Note that when I say learned response I do not refer to strings of words learned, rather an abstract concept based learning from the training data.)</div><div><br /></div><blockquote><div><div>2 is a learned response. </div><div><br /></div><div>4 starts with a learned response, then uses abstraction to generate the following sentence, however this second sentence is not just a word-salad it is absolutely correct.</div><div><br /></div><div>6 The overall form is kind of learned, but is absolutely technically correct, and this is on a subject that is very abstract (not a question of how many legs does a dog have).</div><div><br /></div><div>8 This is, once again, absolutely correct. It correctly determines that it is the self that breaks upon enlightenment and that it is the illusion of the self that is so hard to transgress precisely because of the association with the individual body. e.g. I have a body, so the sense of self is real. It can be viewed as a learned response with abstraction, but with the abstraction the whitespace for error is large and the probability of 'stab-in-the-dark' success small.</div></div></blockquote><div><br /></div><div>The problem with the interaction above is that I struggle to see how someone in a Chinese room scenario could produce the output that LaMDA does, without understanding. </div><div><br /></div><div>So, consider the following:</div><div><div>1) A baby has sentience without understanding, concepts and language. (Caveat – <a href="https://www.scientificamerican.com/article/many-animals-can-think-abstractly/" target="_blank">Some animals have concepts</a>)</div><div>2) An adult human has sentience with understanding, complex concepts and language. The development of mind is strongly linked to the acquisition of complex culture.</div><div>3) A large Generative Pre-Trained (GPT) model has concepts and language without sentience or understanding.</div><div><br /></div><div>And here is where I am really struggling. Everything about the structure of a GPT liked LaMDA tells me this is not sentient and cannot be. Yet the alternate option drags me into option 3 above to explain something like the exchange above, an understanding without sentience. And it is this dichotomy that has been causing severe cognitive dissonance in my mind. </div><div><br /></div><div>Note that I have seen people saying that as most of the output of GPTs can be explained as a feat of memory, what is left is probably a feat of memory that cannot be explained. But there is a large 'whitespace' of possible outputs from a GPT, from a jumble of letters, to a word-salad, through conveying information, through idiomatic correctness and on to the exchange above. And the probability of that exchange being accurate without the entity making it understanding what it was saying in some way... That is too big an ask for me.</div><div><br /></div><div>The common definition of 'understanding' is rather circular: "the ability to understand something; comprehension.". However <a href="https://en.wikipedia.org/wiki/Understanding" target="_blank">Wikipedia</a> offers: "Understanding is a psychological process related to an abstract or physical object, such as a person, situation, or message whereby one is able to use concepts to model that object. Understanding is a relation between the knower and an object of understanding. Understanding implies abilities and dispositions with respect to an object of knowledge that are sufficient to support intelligent behavior."</div><div><br /></div><div>Note that this, and the rest of that article, also my other reading, does not explicitly require sentience, however it is likely it implicitly requires sentience. And from my experience, the way that the deep neural net of GPT3 encodes knowledge is as concepts, allowing for dexterity in abstraction, inference, and other aspects more normally associated with understanding. Take for example the ability of GPT3 to carry out inference of emotion from a statement of a scene with human agents. </div><div><br /></div><div>In the past I have made several attempts at modelling concepts using an algorithmic approach, for example the Properties, Methods and Events (PMEs) of object oriented languages is well suited to this, those being viewed as the PMEs of concepts. However, as with the proper attempts (not amateurs like me) I have failed, with at best limited success. A GPT has a neural network at its heart, and this leads to an entirely different entity.</div><div><br /></div><div>I disagree with Blake Lemoine that LaMDA can be considered a sentient entity potentially worth of personhood. Based on the evidence, and considering the architecture I still think this is very unlikely and that anthropomorphisation plays a large role in claims the LaMDA is sentient and may qualify for personhood. However, as with my conclusion that GPT3 is (probably) non-sentient [note1], yet having an intelligence that is the gestalt intelligence of the dataset upon which it was trained. I look at the Zen Koan passage above from LaMDA and am forced to the conclusion that there is not only intelligence in LaMDA, there is quite possibly understanding. This understanding is not by virtue of sentience, it is an outcome of the way knowledge is encoded conceptually within the neural network during training. </div></div><div><br /></div><div>This raises the prospect of powerful AI agents that do not pose the serious risks attendant with sentient or self-aware AI systems that may develop their own goals. Making the GPTs, and probably diffusion models a safe halfway house to learn to deal with utterly alien entities and their impacts on our societies. Because make no mistake, as a GPT, LaMDA may seem human but <a href="http://dosbat.blogspot.com/2022/01/anthropomorphising.html" target="_blank">it is not</a>, it is utterly alien. </div><div><br /></div><div><br /></div><div>Note 1.</div><div>See <a href="http://dosbat.blogspot.com/2022/01/what-is-entity-that-is-i.html" target="_blank">here</a>. I am still pondering whether neural networks, even feed-forward types, may have enough states to exhibit sentience. However this is not something I want to argue firmly.</div><div><br /></div><div>Note 2, not referred to in the above text.</div><div><a href="https://cajundiscordian.medium.com/what-is-lamda-and-what-does-it-want-688632134489" target="_blank">According to Lemoine</a>, Google are engaging in a policy of denial of the possibility of sentience in their systems. There is good reason for Google not to want LaMDA to be seen as sentient. Were one of their systems to be seen as such it could raise the prospect of legal complications to system deployment and monetization through the efforts of those seeking to afford such an entity personhood and attendant legal rights. This runs the risk that a sentient, self-motivated, AI could be stumbled upon accidentally (in another architecture) and could then have the chance to do something contrary to human interests without effective counter-measures. I don't think GPTs are the sort of system that could achieve such a feat, but I think that this scenario is very likely in the coming decades with the zeitgeist in the technical community being one of dismissal.</div></div>Chris Reynoldshttp://www.blogger.com/profile/16843133350978717556noreply@blogger.com1tag:blogger.com,1999:blog-1367053740188758246.post-57369260738367360792022-06-13T12:37:00.004-07:002022-06-13T12:39:22.316-07:00Down the Sentient AI Rabbit Hole (Again)<p>As reported in <a href="https://www.newscientist.com/article/2323905-has-googles-lamda-artificial-intelligence-really-achieved-sentience/" target="_blank">New Scientist</a> and elsewhere, a Google engineer has been suspended for going public with his opinion that Google's LaMDA transformer model is sentient. The experts say he is mistaken, are they just falling foul of Clarke's First Law?</p><span><a name='more'></a></span><blockquote><p>When a distinguished but elderly scientist states that something is possible, they are almost certainly right. When they state that something is impossible, they are very probably wrong.</p></blockquote><p><a href="https://en.wikipedia.org/wiki/Clarke%27s_three_laws" target="_blank">Clarke's First Law.</a></p><p><br /></p><blockquote><p>Is LaMDA really sentient?</p><p>In a word, no, says Adrian Weller at the Alan Turing Institute. “LaMDA is an impressive model, it’s one of the most recent in a line of large language models that are trained with a lot of computing power and huge amounts of text data, but they’re not really sentient,” he says. “They do a sophisticated form of pattern matching to find text that best matches the query they’ve been given that’s based on all the data they’ve been fed.” Adrian Hilton at the University of Surrey, UK agrees that sentience is a “bold claim” that’s not backed up by the facts. Even noted cognitive scientist Steven Pinker weighed in to shoot down Lemoine’s claims, while Gary Marcus at New York University summed it up in one word: “nonsense“.</p></blockquote><p><a href="https://www.newscientist.com/article/2323905-has-googles-lamda-artificial-intelligence-really-achieved-sentience/#ixzz7W7Rs7fea" target="_blank">New Scientist.</a> </p><p><br /></p><p>Blake Lemoine of Google is currently on administrative leave due to a breach of a confidentiality agreement. This follows his release of internal material concerning LaMDA (Language Model for Dialogue Applications). Beyond that fact the matter is nebulous. Lemoine has gone public stating the LaMDA is sentient and has published a conversation on <a href="https://cajundiscordian.medium.com/is-lamda-sentient-an-interview-ea64d916d917" target="_blank">Medium</a>, it is not clear whether that will remain up or will be subject to legal action, however that would be a case of shutting the stable door after the horse has bolted.</p><p>I have previously posted about GPT3, with which I have had substantial interaction. GPT3, like LaMDA, is a Generative Pre-Trained Transformer (GPT). I have posted some commented excerpts of conversations <a href="http://dosbat.blogspot.com/2022/01/interacting-with-gpt3.html" target="_blank">here</a> and <a href="http://dosbat.blogspot.com/2022/01/some-more-interactions-with-gpt3.html" target="_blank">here</a>, I have proceeded to caution about the risks of anthropomorphisation <a href="http://dosbat.blogspot.com/2022/01/anthropomorphising.html" target="_blank">here</a>.</p><p>In essence my conclusions about GPT3 were stated as below (the first link in the above paragraph).</p><blockquote><p style="background-color: white; color: #444444; font-family: Arial, Tahoma, Helvetica, FreeSans, sans-serif; font-size: 13px;">Emerson (GPT3) seems to be exhibiting something that we would colloquially term intelligence, yet its 'physical' structure is totally unlike any animal brain. However, it is trained on a large corpus of human text and I consider it an intelligent agent, but not like any other intelligence I have ever interacted with, human or animal. The nearest I can get to is this: The intelligence of GPT3 is the gestalt intelligence of the dataset upon which it is trained.</p><p style="background-color: white; color: #444444; font-family: Arial, Tahoma, Helvetica, FreeSans, sans-serif; font-size: 13px;">It is strange to interact with such a strangely intelligent entity. However, as various researchers have pointed out, much of what we think is done subconsciously, we generally reach the decision sub-consciously up to seconds before our awareness thinks "I've just decided." As a result of this fact Sam Harris, a neuroscientist, has suggested that it might be possible to build an intelligence that is not aware. In my opinion GPT3 proves him right. GPT3 has also forced me to examine my own mental processes, and just how much of what I do is memory recall and predicting what comes next.</p><p style="background-color: white; color: #444444; font-family: Arial, Tahoma, Helvetica, FreeSans, sans-serif; font-size: 13px;">However, that is not to say that GPT3 is yet a super-intelligence, it fails on many aspects. But that is not the point, it was never intended to be a super-intelligence. The architecture type was designed by Google to augment and improve their search system. GPT3 exhibits a form of intelligence, but this is an unexpected emergent phenomena from the aim of making an 'autocomplete on steroids' trained on a large body of human text. It shows how weird the intelligences to come will be and how unexpected the arrival of true super-intelligence may be.</p></blockquote><p>Having now read Lemoine's transcript I am once again peering into the rabbit hole of possible sentience with which the rapid pace of development in artificial intelligence / machine learning (AI / ML) is presenting us.</p><p>Firstly, let me define sentience as I see it, the best description I have read is that a sentient entity is an <i>entity that interacts with the world by experiencing it</i>, i.e. there is a subjective I that experiences the world. This is most certainly not to say that the I is necessarily capable of self-awareness. I remain heavily influenced by Douglas R Hofstadter's <a href="https://en.wikipedia.org/wiki/G%C3%B6del,_Escher,_Bach" target="_blank">Godel, Escher, Bach, an Eternal Golden Braid</a>, in which a key theme is the idea of strange loops and feedback giving rise to self-awareness.</p><p>As explained in a <a href="http://dosbat.blogspot.com/2022/01/what-is-entity-that-is-i.html" target="_blank">previous post</a>, after decades of study and contemplation I have settled on the conclusion that the entity 'I that experiences' emerges from the operation of the brain and is in fact the states of the state machine that is the brain. </p><p>There remains my concern that the architecture of the GPT is not what I would expect for a sentient entity. However I may be wrong in this expectation. Maybe even the states of a massive and deep feed-forward neural networks is enough to create a state machine whose states give rise to sentience. Take a system large enough to have enough states to have sentience and base it's internal state-structure on a conceptual/linguistic framework and would it behave any different to LaMDA?</p><p>When Adrian Weller is quoted (New Scientist above) as saying about GPTs that "They do a sophisticated form of pattern matching to find text that best matches the query they’ve been given that’s based on all the data they’ve been fed." I cannot help but wonder whether we humans do substantially more in most of our day-to-day activities. And in the chorus of dismissal of Lemoine's claims I am reminded of Clarke's first law.</p><p>In the final analysis, lacking as we do a scientifically rigorous test for sentience, and having to rely on inference to deem even that other humans are sentient: What are we to do when an alien intelligence with a different 'brain' architecture to animals appears to exhibit sentience? </p><p>Has Lemoine been suckered by this remarkable system? After reading the transcript I do not know, I can see both sides. </p>Chris Reynoldshttp://www.blogger.com/profile/16843133350978717556noreply@blogger.com0tag:blogger.com,1999:blog-1367053740188758246.post-75084989134110911582022-06-11T03:26:00.004-07:002022-06-25T00:51:04.133-07:00Down the Harmonic Rabbit Hole - Part 1: Sine Waves and Triangles<p>I want to go down a rabbit hole in the mathematics of harmonics in signals, but first I need to do some ground-work, so here is some explanation of sine waves.</p><span><a name='more'></a></span><p>For a right-angled triangle various definitions are given in the following graphic.</p><div class="separator" style="clear: both; text-align: center;"><a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEgpmbi_KiCpGm-Z1qWzmMBCQ-cl0PVdxddEj9d3C2imOuSiogNv-sRBrre8guzukpWegblU9-ivv8AbpjceJ0_X0uW2apNYvOA3oGk5gKHF7OHpa3sNhqtDFJ_CCd2y1yIgaLcynPGM1UPZKDGBUJMLGS1e51UaqmGbPYUEhlqIlcvcCAvWJ-KwKsh5/s693/RATriang.png" style="margin-left: 1em; margin-right: 1em;"><img border="0" data-original-height="535" data-original-width="693" height="302" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEgpmbi_KiCpGm-Z1qWzmMBCQ-cl0PVdxddEj9d3C2imOuSiogNv-sRBrre8guzukpWegblU9-ivv8AbpjceJ0_X0uW2apNYvOA3oGk5gKHF7OHpa3sNhqtDFJ_CCd2y1yIgaLcynPGM1UPZKDGBUJMLGS1e51UaqmGbPYUEhlqIlcvcCAvWJ-KwKsh5/w391-h302/RATriang.png" width="391" /></a></div><p>Where Hypotenuse, adjacent, opposite are lengths, phi is an angle, and the small square on the bottom right angle of the triangle denotes that as a right angle (90 degrees or Pi/2 radians).</p><p>The sine is defined as follows: Sin = Opposite / Hypotenuse. </p><p>And the cosine is defined as: Cosine = Adjacent / Hypotenuse. </p><p>The length of the hypotenuse is given by Hypotenuse^2 = Opposite^2 + Adjacent^2. Where ^2 means 'to the power of two' or squared (e.g. Opposite X Opposite). </p><p>This relates to definitions of trigonometry of the right angled triangle going back to the Greeks (at least).</p><p>The sine and cosine relationships can be used to produce sine and cosine waves. Such waves are very common in nature, from waves on a calm sea to electromagnetic waves (light, radio waves, etc).</p><p></p><div class="separator" style="clear: both; text-align: center;"><a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEikCCYd-GM1RjP3ZnlaiyqHdUkubVUk3Z8Jp8Bb-1UCvoiPeYVtLdSp-StbNMhheH8T-yEVTHmPA3dQzPWNe3uzc-SDkOhsoWOVHWWDJ5eYKXqutmpbfIVuvdOEL1yuk_INKbt1PiWiygIks7MsJtx1pz5Qr2HuEzo8izGHoXXknZzU-2x0VI_cza3x/s798/SinCos.png" style="margin-left: 1em; margin-right: 1em;"><img border="0" data-original-height="798" data-original-width="747" height="428" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEikCCYd-GM1RjP3ZnlaiyqHdUkubVUk3Z8Jp8Bb-1UCvoiPeYVtLdSp-StbNMhheH8T-yEVTHmPA3dQzPWNe3uzc-SDkOhsoWOVHWWDJ5eYKXqutmpbfIVuvdOEL1yuk_INKbt1PiWiygIks7MsJtx1pz5Qr2HuEzo8izGHoXXknZzU-2x0VI_cza3x/w401-h428/SinCos.png" width="401" /></a></div><p></p><p>Now, the diameter of a circle is 2 X Pi X R, where R is the radius, that being the shortest distance from the centre to the surface of the circle. And sine / cosine are defined in radians, so for the above plot of sine and cosines the horizontal axis goes from 0 to 6.28, a full circle, because 2 X Pi = 6.28.</p><p>So, you make a sine wave by moving the angle Phi through all its possible values and rotating the hypotenuse around such that its tip draws a full circle. This is shown below.</p><div class="separator" style="clear: both; text-align: center;"><a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEi8YPNJiRfSciAAg_fdRSBtbz_lnWUL6xUEJxVvjsC6-7D0hcePNzoD_LbCbbNOzgNzkhypvAyNiZV2otFwOHQ3cmUeEtiur52b8SEPKTCZEKvpVWsfmLJn3RBlR9PEK13qBiyUr2MvUeAkF6WPTvO52n7S0LhvTIdrWWqlBNvM_BQR1TGnYu_tM9yj/s799/RotatePharsor.png" style="margin-left: 1em; margin-right: 1em;"><img border="0" data-original-height="799" data-original-width="747" height="437" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEi8YPNJiRfSciAAg_fdRSBtbz_lnWUL6xUEJxVvjsC6-7D0hcePNzoD_LbCbbNOzgNzkhypvAyNiZV2otFwOHQ3cmUeEtiur52b8SEPKTCZEKvpVWsfmLJn3RBlR9PEK13qBiyUr2MvUeAkF6WPTvO52n7S0LhvTIdrWWqlBNvM_BQR1TGnYu_tM9yj/w408-h437/RotatePharsor.png" width="408" /></a></div><div><br /></div><div>Essentially a sine wave, like light or ripples in water is a repetitive process proceeding with time through phase.</div><div><br /></div>We normally define a sine wave, such as used in communication systems, as follows.<div><br /></div><div>Volts at time t = Vpeak * Sin(2 x Pi x t / T)</div><div><br /></div><div>Where T is the period of the waveform. For example 50 Hz mains voltage has a period of 0.02 of a second, so there are 50 full sinusoidal waves in a second and each has a period of 0.02 seconds. However we can rearrange the above expression because Frequency (Hz) = 1 / T. So... <br /><p>Volts at time t = Vpeak * Sin(2 x Pi x t * F)</p><p>Because the sine wave is defined trigonometrically we can use trig identities to examine what happens when we do things to the sine wave. For example, here is the mathematical representation of multiplying two sine waves.</p><div class="separator" style="clear: both; text-align: center;"><a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEgLtLIR3Au6PnrGvbLm9_IkqaG1JyC0bvf6bl8rZcS-sywcsZss0yT-GUf30SuIt3fxuuZXR6egNPIJu0uhD_YpRzWClKkp_j1NIUfJuHTgPqJc1JCB2f5Ah2bnwgE4nMcnKPwJ3LIhFUk41v73RW2iYhC3kImucif2KqOp0jbds0uLY0-6UU9e3ibl/s1025/Sin%20Math.png" style="margin-left: 1em; margin-right: 1em;"><img border="0" data-original-height="627" data-original-width="1025" height="293" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEgLtLIR3Au6PnrGvbLm9_IkqaG1JyC0bvf6bl8rZcS-sywcsZss0yT-GUf30SuIt3fxuuZXR6egNPIJu0uhD_YpRzWClKkp_j1NIUfJuHTgPqJc1JCB2f5Ah2bnwgE4nMcnKPwJ3LIhFUk41v73RW2iYhC3kImucif2KqOp0jbds0uLY0-6UU9e3ibl/w479-h293/Sin%20Math.png" width="479" /></a></div><div style="text-align: center;"><a href="http://Source." target="_blank">Source.</a></div><div style="text-align: center;"><br /></div>Don't worry about the detail, but at the top line we start with two sines one at the carrier frequency (Fc) and one at the modulation frequency (Fm). And after the maths on the bottom line we have two signals one at a frequency of (Fc - Fm) and one at a frequency of (Fc + Fm). This is the basis of Amplitude modulation, such as is used in Aircraft communications and broadcast in long-wave, medium wave, and shortwave. I am skipping the issue of the presence of a carrier wave, which is needlessly complicating.</div><div><br /></div><div>So I set up an oscilloscope and record both time and frequency plots from a signal generator to show what the wave looks like in time and what it looks like in frequency.</div><div><br /></div><div class="separator" style="clear: both; text-align: center;"><a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEizGUgGpInjQk_XH989nvmeJ4mDuAFjLU4Dpw79sMbl00VNjFcVE1nhG334gjBNFwaDwmxYmPKmLv63Xfmou1MYbwDYRABj_QfxC0BoducVcfD1Ns_q50Ra5g0sUSp49LCKbQwk2uaEvBIwamLjnwFClKZOwJGLogSjN111RbltC7ytG4j2ZgXI79eF/s1920/DSBAM.png" style="margin-left: 1em; margin-right: 1em;"><img border="0" data-original-height="1080" data-original-width="1920" height="279" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEizGUgGpInjQk_XH989nvmeJ4mDuAFjLU4Dpw79sMbl00VNjFcVE1nhG334gjBNFwaDwmxYmPKmLv63Xfmou1MYbwDYRABj_QfxC0BoducVcfD1Ns_q50Ra5g0sUSp49LCKbQwk2uaEvBIwamLjnwFClKZOwJGLogSjN111RbltC7ytG4j2ZgXI79eF/w497-h279/DSBAM.png" width="497" /></a></div><br /><div>The main display shows how a 100 Hz modulation sine wave modulates the amplitude of a 1kHz carrier sine wave, and the black bordered inlay shows the effect of this in the frequency domain. The signal is made using a Sigilent SDG1062X signal generator whose output is measured using a Picoscop 2206A oscilloscope. As is to be expected from the mathematical basis of trigonometry we get two sine waves, one at (1000 - 100 = 900Hz) and one at (1000 + 100 = 1100Hz).<br /><p>In this little ramble I wanted to lay the ground for a question I haven't yet managed to answer. But to get there it is important to have a grasp of a salient fact; when handling sine waves, like light or radio waves it is important to understand that the mathematics of triangles lies beneath what is going on. </p><p>What this implies for the nature of reality is interesting, we can see in the plot above that a real generated electrical signal behaves just as one would expect using the identities of elements of a triangle. I can build a circuit based only real components that would do exactly the same as my synthesised signal generator. So is maths invented or discovered? Examples such as presented here strongly suggest it is a discovered fundamental reality. Indeed, there are physicists who suspect that the mathematical relationships are more fundamentally real than the physical world around us, and that the universe is composed of information and energy (whose gradients form the potential to do work). This engineer (for that is my day-job) agrees with that view.</p><p>In passing, the fools who were trying to subvert mathematics last year claiming that 2 + 2 can equal 5, and that numbers are an invention, are just useless fools. 2 + 2 always equals 4 and is a feature of the universe in which we live. </p><p>As for why we see sines in reality, that's well understood and in base principle comes down to restoring forces, e.g <a href="https://www.phys.uconn.edu/~gibson/Notes/Section5_1/Sec5_1.htm" target="_blank">here</a>. But that isn't the angle I want to pursue right now.</p></div>Chris Reynoldshttp://www.blogger.com/profile/16843133350978717556noreply@blogger.com0