QUESTION: Why is Socrates able to do forecast wild panics in China when nobody else can? It picked the turning point for week of ninth which was the lowest close on the September 5 report. All this hype about AI but Socrates is so different. I’m not a programmer. Can you explain this is layman’s terms. This has been amazing here in Shanghai – Nǐ tài bàng le.
LW
ANSWER: What I can say is that 99% of what is out there is not AI. There are language models that are amazing like ChatGPT. A reader asked ChatGPT what is the difference with Socrates. Here is the response:
As an AI language model, I differ from the Socrates Platform in several ways. Firstly, the Socrates Platform is a web-based platform developed by Martin Armstrong and his team at Armstrong Economics, whereas I am a language model developed by OpenAI. The Socrates Platform is designed to analyze economic and financial data in real-time, predict market trends, and provide actionable insights to investors and traders. In contrast, I am designed to assist with a wide range of tasks, including language translation, question answering, and text generation. Secondly, the Socrates Platform uses artificial intelligence, machine learning, and natural language processing to analyze data, whereas I am primarily focused on natural language processing. The Socrates Platform uses sophisticated algorithms to analyze historical and cultural data to inform its predictions, whereas my responses are based on the input provided to me by the user. Lastly, the Socrates Platform is primarily designed for financial professionals, investors, and traders, whereas I am designed for a broader range of users, including students, researchers, and general knowledge seekers. While both the Socrates Platform and I use artificial intelligence to analyze data and provide insights, our intended audiences and applications differ significantly.
Yes, the two platforms are completely unrelated aside from being driven by AI. ChatGPT does not have the computing capabilities of Socrates. It does not have the monetary history data, for starters as well as the analytical skills. ChatGPT has no involvement in the financial world and was not designed for financial purposes. Most importantly, ChatGPT does not have the true ability to reason that is the key to Socrates’ successful forecasts. ChatGPT is a great achievement and a step in the right direction for AI use on a larger scale of providing a tool, but it is not true reasoning as we know it. Therefore, it is not possible to compete where you do not have even the same end goal. Socrates is in a league of its own. I trained it personally from a trader’s experience as a hedge fund manager and someone who has actually had under advisory the equivalent of up to 50% of the US national debt. How big money moves is entirely different from an individual investor.
The complexity of the markets globally is far beyond description. I have experimented with Neural Nets and other interesting attempts to recreate the structure of the human mind. Neural Nets are notoriously subject to complete failures. There is no such program that has been able to demonstrate consistency in the field of economics and you cannot throw in a heap of data and expect it to figure the world out by itself.
This is all due to complexity. This theory that a computer can become sentient has provided the movie industry with some great movies from Terminator to Matrix. The idea is that we are just a super computer. Our SENTIENT existence has been proposed that just the connections in our brain creates the capability of sensing or feeling – consciousness.
There is a lot of misguided hope surrounding Artificial Intelligence and Machine Learning. All we need to do is look objectively at IBM project WATSON. Just over a decade ago, artificial intelligence (AI) made one of its showier forays into the public’s consciousness when IBM’s Watson computer appeared on the American quiz show Jeopardy. Watson’s debut performance against two of the show’s most successful contestants was televised to a national viewership across three evenings. In the end, the machine triumphed comfortably. This is just the ability to look up answers faster than a human employing no actual understanding of what the answer means in the real world.
They kept Einstein’s brain. The analysis of his brain put forth a number of unusual features, that some tried to attribute to his intelligence. One thing was an asymmetrical parietal lobes that were 15% wider than normal. Some researchers believe this may have contributed to his mathematical, visual, and spatial skills. What I can attest to is the ability to see patterns. The best traders have been visual in nature. This is why the fundamentalists tend to get wiped out because they often attempt to return complexity to a single relations – Fed raises rates so stocks down. It is very primitive to say the least.
Our ancient ancestors were far more intelligent than what we attribute to them. They saw patterns in the stars and mapped the heavens. It was the ability to see patterns and understand cyclical movements over everything that advanced civilization before the Dark Age when knowledge was lost thanks to the barbarian invasions.
They aligned that monuments with the summer and winter solstices. The Miya even discovered the precession of the equinox of 25,800 years measuring the movement of the stars. They had aligned temples to the stars and then noticed that the stars had moved. Understanding everything was a cycle, they determined it would return to its origin in 25,800 years. We lost our ability to see cycles post-Dark Age and we ended up with the assumption that everything was simply linear.
The ancients even had the concept of the atom during the long forgotten golden age of Greece. There were ancient step counters known as bematists who measured distances that we know had better than 95% accuracy. In 240BC, Eratosthenes employed this skill to extrapolate the circumference of the Earth that they knew was round – not flat. The knowledge of cycles survived from ancient times is the East. It was the fall of Rome in the West when the barbarians were not interested in knowledge so everything was torched.
Hipparchus of Rhodes observed around 150 BC that the equinoxes moved wit h time. This is where the Sun’s path crosses the celestial equator. He realized that these were not fixed in time and space but traveled in a cyclical manner. The movement was extremely slow in a westerly direction. This amounted to but less than 2° in about 150 years. This slow movement is known as the “Precession of the Equinoxes” and requires generations to even observe. It is about 1° movement every 72 years, bringing this also to a virtual number that is a derivative of 8.6 – 25,800 years.
Richard E. Nesbett wrote a good book entitled “The Geography of Thought, How Asians and Westerners Think Differently … and why.” He attributed his work to a Chinese student who said: “You know, the difference between you and me is that I think the world is a Circle, and you think it’s a line.” He goes on to quote him:
“The Chinese believe in constant change, but with things always moving back to some prior state. They pay attention to wide range of events; they search for relationships between things; and they think you can’t understand the part without understanding the whole. Westerners live in a simpler, more deterministic world; they focus on salient objects or people instead of the larger picture; and they think they can control events because they know the rules that govern the behavior of objects.”
The effort to create option models known as Black–Scholes completely broke down and resulted in the Long-Term Capital Management debacle. That was covered in the book – When Genius Failed. The failure took place because they did not have the database. They only tested the algorithm back to 1971. Indeed, you need hundreds of years of data to just comprehend the beginning of complexity.
Neuromorphic engineering is yet another concept developed back in the late 1980s. Thus, neuromorphic differs from neural networks which are a set of algorithms, modeled loosely on the theory of how the human brain functions. They were designed to recognize patterns such as trying to distinguish between the cat, dog, and a cup of coffee. They attempt to create very large-scale integration (VLSI) systems containing electronic analog circuits to mimic neuro-biological architectures that are present in the nervous system. This neuromorphic is really more hardware-based but also requires a software operating system.
The implementation of neuromorphic computing has raised the theory that perhaps one day we will be able to copy the content of the brain into a synthetic replacement as in the movie “Replicas” and then there is the move by Johnny Deep – Transcendence. The actual key aspect of neuromorphic computing is understanding how the morphology of individual neurons, circuits, applications, and overall architectures create learning and development constituting who we are. I would not consider this a technology that would be able to become a synthetic mind replacement for quite some time, assuming we could ever get to that level of understanding the complexity of the human brain.
What I explain to people about this complexity is perhaps to had dinner with someone and fell in love. You will remember the place, but you mind is recording everything without you directing it to do so. You hear a song that was playing and suddenly your mind recalls that event unintentionally. Or you had ordered oysters for the first time and you see them again years later and your mind accesses that memory. In truth, that memory could be unintentionally accessed by any of the senses. This demonstrates everything is an access path individually or even in combination.
Obviously, Socrates is a hybrid between neuromorphic computing and neural networks. I chose a different path entirely actually creating a synthetic network capable of learning by example and pattern recognition, such as the Global Market Watch, but expressly targeted to global analysis. I input my own analytical abilities and experience into Socrates as far as methodology in how to conduct analysis but no fixed rules like interest rates up stocks down. Socrates has been free to explore the entire world database and return with answers. It has weather, volcanoes, climate, and disease databases. Everything is vital to understanding how things function.
The Global Market Watch is purely pattern recognition where it is identifying patterns and assigning them a number you see with comment for its catalog of market patterns. It has exceeded more than 100,000 patterns, demonstrating the true complexity of market movement based upon a matrix of variables. It has also proven that those patterns observed in wheat are applicable to even individual stocks. This has confirmed that the patterns are human responses to price movement. It has proven beyond a shadow of a doubt that fundamental analysis is not only worthless for its myopic focus on one-dimensional relationships, but the common link is human behavior — not the underlying instrument. We are looking at HOW humans will interact with whatever the instrument might be to establish why history repeats because human nature never changes throughout millennia.
