Concepts involved in generating text, images, audio, video and other content.
The maximum amount of information, measured in tokens, that a model can process within one interaction.
Artificial intelligence capable of creating new text, images, code, or other media based on learned patterns.
An AI output that appears plausible but is incorrect, unsupported, or entirely invented.
The phase where a trained AI model processes new data to generate an output or prediction.
The practice of designing, structuring, and refining inputs to get optimal outputs from AI models.
The foundational set of hidden instructions that define an AI model’s persona, boundaries, and behavior.
A numerical setting that influences the predictability of an AI model’s generated output.
The basic unit of data—often a part of a word—that an AI model processes.
Instructing an AI model to perform a task without providing any examples in the prompt.