Important terms of generative AI explained.
Few-Shot Learning refers to a method in artificial intelligence where an AI model can learn new tasks from just a few examples. Unlike traditional machine learning, which often requires thousands of training samples, Few-Shot Learning can work with just a handful of examples – sometimes as few as two or three. It can be compared … Read more
Transformers are a groundbreaking architecture for artificial neural networks, developed by Google in 2017, and now form the foundation for modern AI language models such as ChatGPT, Claude, or Google’s own Gemini. The name “Transformer” refers to these systems’ ability to transform input data (for example, texts) into another form. What makes Transformers special is … Read more
An LLM Router (Large Language Model Router) is a system that automatically directs incoming queries to the most appropriate language model. Similar to a traffic control system, the router determines which of the available AI models can solve a specific task most efficiently. This selection is based on various criteria such as the type of … Read more
Foundation Model refers to a large AI model trained on vast amounts of data that serves as a foundation for various specialized applications. It can be thought of as a base upon which other AI applications are built. These models are initially trained on a broad spectrum of data – from texts and images to … Read more
A Large Language Model, commonly abbreviated as LLM, is an advanced artificial neural network designed to understand, generate, and process human language. These models are termed “large” because they are trained on vast amounts of textual data and can contain billions of parameters. LLMs are capable of performing a wide range of tasks, including text … Read more
Mixture of Experts (MoE) is a concept in artificial intelligence that can best be understood as a team of specialists. In this approach, a complex task is divided among multiple smaller, specialized models – the so-called “experts” – instead of using a single large model for everything. A central “gatekeeper” or “router” decides which expert … Read more
Chain of Thought is a concept in artificial intelligence that describes the ability of AI systems to solve complex problems step-by-step, much like humans do. This method allows AI models to explain their thought processes in a way that humans can understand. Instead of just providing a final answer, the AI shows the individual steps … Read more
Today’s AI assistants provide answers to questions or perform simple, well-defined tasks. But they do not act independently. In addition, more complex tasks always require a human to act as a supervisor. AI agents, on the other hand, should find a solution on their own and pursue goals autonomously or semi-autonomously. AI agents use basic … Read more
A general world model is an ambitious concept in artificial intelligence. The goal is to create an AI system that can understand and simulate the world as comprehensively as a human. Imagine a virtual assistant that can not only generate text or images, but also understand, predict, and respond to complex real-world situations. For example, … Read more
Imagine you have a universal toolbox that contains many different tools, but is too large and cumbersome for certain tasks. To perform certain tasks efficiently, you can use small, specialized attachments called adapters. These adapters attach to the general-purpose tool and extend its function. For example, you can attach a screwdriver adapter to a drill … Read more