AI Glossary

A hypothetical type of AI that can understand, learn, and apply intelligence across a wide range of tasks at or above human level.

The limit on the amount of text (tokens) a model can consider at one time (input + output).

A subset of machine learning based on artificial neural networks with multiple layers, capable of learning complex patterns from large amounts of data.

The process of taking a pre-trained model and training it further on a specific dataset to specialize it for a certain task.

A broad category of AI systems designed to generate new content, such as text, images, audio, or code, based on patterns learned from existing data.

When an AI model confidently generates false or nonsensical information.

A type of AI model trained on massive amounts of text data, capable of understanding and generating human-like language.

A branch of AI focused on building systems that learn from data and improve their performance over time without being explicitly programmed.

The ability of a model to process and generate multiple types of media (text, images, audio) simultaneously.

A field of AI focused on the interaction between computers and human language, enabling machines to read, understand, and derive meaning from text.

A computing system inspired by the human brain, consisting of interconnected nodes (neurons) that process information and learn patterns.

The practice of designing and refining the input text (prompts) given to an AI model to elicit the most accurate, relevant, or creative response.

Retrieval-Augmented Generation. A technique where an LLM is provided with external data (context) to generate more accurate answers.

A parameter that controls the randomness of the model's output. Higher values (0.8+) make output more creative/random, lower values (0.2) make it more focused/deterministic.

The basic unit of text processing for an LLM. Roughly 0.75 words. "Hamburger" might be 2-3 tokens.

The ability of a model to perform a task without having seen any examples of that specific task during training.