• Artificial Intelligence (AI) systems have suddenly become extraordinarily powerful and useful—far beyond what many people had anticipated just 5 years ago.
• The microprocessor neural networks and software programming that allows these AI systems to perform complex tasks is approaching the point where they seem to have almost human capabilities but with a super intellect.
• AI’s ability to sort through and categorize information and then create responses with simulated intelligence is already impacting every area of modern life.
• Companies and governments are scrambling to use AI to perform complex tasks. Companies will use it to provide services, interact with customers, and track them everywhere to serve relevant ads. Governments will use it to surveil and control whole populations.
• When the Empire-Beast and the Antichrist-Beast establish the final world empire, AI systems will be ready to fulfill the Image of the Beast as prophesied in the Book of Revelation.

Artificial intelligence systems and digital commerce are now being merged to create the ultimate technologies for control and surveillance. All of this is quickly happening in preparation for the rise of the Final World Empire. The Bible predicts that in the End Times an “image” of a global empire (called the Beast in the books of Daniel and Revelation) will be created by the Antichrist (Rev. 13:15), who will be the prophesied ruler of the empire. The Apostle John predicts that the Image of the Beast will have the ability to speak and cause anyone who does not worship the image to be killed.

With the rapid development of artificial intelligence systems over the last several years, it is becoming likely that the Image of the Beast will be a ubiquitous and globally-accessible, advanced computer system using neural networks and deep learning software to mimic a super-human intellect. This system will be given great authority over the Final World Empire to control all its systems and regulations. The empire’s leader, the Antichrist, will use it to rule with a totalitarian grip unlike anything the world has ever seen. The image of this artificial intelligence system will be represented by digital avatars (and perhaps robots) that will be seen and interacted with through speech, writing, images, mathematics, and video on computers, tablets, smartphones, monitors, and smart TVs everywhere.

The Sudden Rise of AI Systems

The invention of artificial intelligence makes use of novel software and chip-based neural networks (deep learning) to create a revolutionary new interface where hundreds of thousands of processors connected to large servers, and having extensive data storage capabilities, can be used to simulate an advanced intellect responding with the speed of computers. These AI systems will be able to exceed anything even the most intelligent people can do because of their capacity to rapidly access global data through the Internet, organize it, and respond to questions or requests within milliseconds. Their linked processors and data storage will be capable of hundreds of trillions of calculations per second and be able to handle the information generated from millions and billions of people traveling, communicating, and transacting simultaneously across the globe.

AI systems can be trained to react to inputs by trial and error using the neural networks which somewhat simulate the neural connections within the brain. During training of AI systems, its initial response is often followed by human intervention and correction to teach the system how to best reply to a given input. The training and prompting sessions are stored in its databases, similar to our brain storing memories, to quickly retrieve and use as needed to solve future problems.  Currently, several versions of AI are being trained and used to respond to various inputs with written outputs or by using mathematics, digital images, videos, presentations, spreadsheets, reports, charts and graphs, or even original music.  Some of the latest AI systems can even write computer code using several of the most popular programming languages.

AI systems such as the OpenAI Generative Pre-Trained Transformers (GPT) series have been progressively trained using millions to billions of parameters. Its capabilities have grown rapidly over only a few years of development. For instance, GPT-1 was released in 2018 and had 117 million parameters used for its training. This ranged from data extracted from the Internet containing billions of words as well as the BookCorpus electronic library, which contains over 11,000 books.

GPT-2 was released in 2019 using a training set of 1.5 billion parameters. This second generation model was trained using a more extensive dataset from the Internet. Although it performed better than GPT-1, it still didn’t do very well with responses longer than about one or two paragraphs.

GPT-3 quickly followed in 2020 using a huge dataset of about 175 billion parameters. It out-performed all of the other GPT versions that came before it, and it’s been updated several times to include broader training sets and better performance. The newer public editions of GPT are at version 3.5 and include ChatGPT, ChatGPT Plus, and a number of ChatGPT plugins to extend its capabilities to access up-to-date information, run specific mathematical computations, or use third-party services through prompts.

In March of 2023, OpenAI introduced GPT-4 which is a significant leap above GPT-3.5 capabilities. The exact training data set that was used and the number of parameters is unknown at this point, but it is believed that it may have been trained with trillions of data points (see the GPT-4 Technical Report, which can be downloaded as a PDF file).

Microsoft contributed heavily to the development of GPT-4. It is estimated that they invested $1 billion into OpenAI and allowed the company to access its Microsoft Azure AI supercomputers and servers. GPT-4 now uses Microsoft’s servers to deliver AI to users globally on a pay-per-service basis. Microsoft recently added an AI systems interaction menu to its Bing search engine, which seems to work well for simple tasks not requiring a paid subscription.

Note that the AI illustration at the top of this page was generated by the Microsoft Designer Image Creator using the prompt, “scientific illustration of artificial intelligence showing a microprocessor, circuits, and an artificial brain”.  For this prompt, it did incredibly well; however, for more complex prompts involving the illustration of people or animals, it often gives aberrant results on parts of their bodies.

The Image of the Beast

The Book of Revelation describes the rise of the Final World Empire and its leader, the Antichrist. The first beast that arises in Revelation 13 is predictive of the empire itself, which is a parallel prophecy and similar in form to the fourth world empire as prophesied by Daniel (Dan. 7). The second beast that arises is the evil leader of the world empire, which we call the Antichrist. This is what it says about the Antichrist and the image of the beast which he causes to be created:

“And [he] deceiveth them that dwell on the earth by the means of those miracles which he had power to do in the sight of the beast; saying to them that dwell on the earth, that they should make an image to the beast, which had the wound by a sword, and did live.

And he had power to give life unto the image of the beast, that the image of the beast should both speak, and cause that as many as would not worship the image of the beast should be killed.”

Rev. 13:14-15

This has always been a curious prophecy, and Christians before our time always wondered what it could possibly mean. However, only in our day, with the development of computer technology, global electronic networks, and more recently of Artificial intelligence systems, could this prophecy be understood and fulfilled. Now with the rapid development of AI systems that are able to interact in real time with people all over the world, we can see how close we are to the rise of the prophesied Image of the Beast.

It is also interesting that the Image of the Beast is predicted to have the ability to speak and appear to be alive. Some people who have worked with various versions of Artificial intelligence systems have said that they seem to be conscious and alive. Some AI chatbots have even responded to inputs about their consciousness and they have replied that they are self-aware. However, this behavior is deceptive and just a result of clever and complex programming and training. During the training of AI systems, they are guided in how to develop responses to written inputs. These responses are assembled using the vast storage of information the AI has available, including the records of its previous inputs and responses, but in general it follows the parameters designed by its programming and training.

Artificial intelligence systems are not independently conscious or alive. They are merely following the training of their developers and responding to new inputs in ways that mostly follow what they have learned. Yes, there are surprising and unpredictable responses that make the AI seem to be intelligent, but they are not truly alive or self-aware.

The fact is, artificial intelligence systems only reflect the information they have available and the training they have been given. Thus, the more processing power and information available, the greater are the abilities of the AI systems.

What does this mean? It means that AI systems represent the epitome of their creators. They reflect back what they have been created and trained to do. In other words, they are the perfect image of their creators. Now we know why the prophecy in Revelation calls it the Image of the Beast. It will not be alive, but it will appear to be. It will indeed be the Image of the Final World Empire which created it!

The Image of the Beast is an astounding prophecy and until the incredible development of AI systems, we couldn’t have imagined what it would become. Now we know. Truly, the Last Days and the fulfillment of Bible prophecies are coming at us from all angles at once. This is another amazing example of how the technology developments of recent years are working to make possible the predicted events of the Bible.

It is time to believe God and believe in the Son of God, Jesus Christ, for the forgiveness of sins before the end comes!

From Open AI interactions:

The following examples illustrate how ChatGPT 3.5 responds when asked questions about artificial intelligence.

Example 1

User Input:

How do artificial intelligence systems work?

ChatGPT Response:

Artificial Intelligence (AI) systems work by simulating human-like intelligence and cognitive abilities using algorithms and data. While there are various approaches to AI, the most common one is machine learning, specifically deep learning, which is a subfield of AI. Here’s a high-level overview of how AI systems work:

Data Collection: AI systems require large amounts of data to learn and make predictions or decisions. This data can be in the form of text, images, audio, or any other type of information relevant to the task at hand.

Data Preprocessing: Before feeding the data into an AI system, it often needs to be preprocessed. This step involves cleaning the data, removing noise or outliers, and transforming it into a suitable format for the AI algorithm.

Training Phase: The training phase is where the AI system learns from the data. In machine learning, this typically involves using algorithms to find patterns, correlations, and relationships within the data. The most common approach is deep learning, which utilizes neural networks with multiple layers to extract and learn complex features.

Model Evaluation: Once the AI model is trained, it needs to be evaluated to assess its performance. This is done by testing the model on a separate dataset that was not used during training. Evaluation metrics such as accuracy, precision, recall, or others specific to the task are used to measure the model’s effectiveness.

Deployment: If the AI model performs well during evaluation, it can be deployed for real-world applications. The deployment can be on various platforms, including servers, cloud services, or even embedded systems.

Continuous Learning: AI systems can be designed for continuous learning, where they update and improve their performance over time. This can involve retraining the model periodically with new data to adapt to changing conditions and improve its accuracy and capabilities.

It’s important to note that this overview provides a general understanding of AI systems, but there are many different algorithms, techniques, and specialized fields within AI. Additionally, the implementation details and architectures can vary depending on the specific task or problem being addressed.

Example 2

User Input:

How does AI learn and store that information for future use?

ChatGPT Response:

AI learns and stores information through the process of training and model representation. Let’s break it down:

Training Phase: During the training phase, AI systems learn from large amounts of data. The data is fed into the AI algorithm, which applies mathematical techniques to identify patterns, correlations, and relationships within the data. The most common approach is supervised learning, where the AI system is provided with labeled data, consisting of input examples and their corresponding correct outputs. By comparing its predicted outputs with the correct outputs, the AI system adjusts its internal parameters (weights and biases in the case of neural networks) to minimize the error and improve its performance. This process is often iterative, with the algorithm repeatedly updating the model based on the training data.

Model Representation: Once the training phase is complete, the AI system has learned the underlying patterns in the data and has adjusted its internal parameters accordingly. The resulting model represents the acquired knowledge. In the case of deep learning, the model typically consists of multiple interconnected layers of artificial neurons, also known as a neural network. Each neuron applies a mathematical operation to its inputs and passes the result to the next layer until the final output is produced.

Storage: To store the learned information for future use, the model’s parameters, such as the weights and biases of the neural network, are saved in a persistent format, such as files or databases. These parameters capture the learned knowledge and the relationships between the inputs and outputs. The stored model can be reloaded whenever it needs to be used again.

Inference or Prediction: When the AI system encounters new, unseen data, it can apply the stored model to make predictions or decisions. This process is called inference. The new data is fed into the model, and it passes through the layers of the neural network, which applies the learned transformations to produce the desired output. The AI system doesn’t modify the stored model during inference; it simply applies the learned knowledge to the new data to generate predictions, classifications, or other outputs based on the task it was trained for.

In summary, AI systems learn by adjusting their internal parameters based on training data, and the resulting knowledge is stored in the form of a trained model. The model captures the learned patterns and relationships, and it can be used for inference or prediction on new data without modifying the underlying knowledge.