AI Glossary: 70+ AI Terms Explained in Plain English

Bias (AI bias): Systematic skew in a model’s outputs that reflects imbalances or patterns in its training data, rather than a neutral or representative view.

See also: Prompt engineering, Context window Context window The maximum amount of text—measured in tokens—a model can hold in “working memory” at once, including the prompt, conversation history, and any documents or tool output fed in. Diffusion model: A generative model architecture, most commonly used for images, that starts from random noise and repeatedly refines it into a coherent output, guided by a text prompt. See also: Prompt injection, guardrails K Knowledge cutoff The date after which a model has no built-in knowledge of events, because its training data was collected before that point.

Key takeaways

• Downloading a model’s weights is downloading the model itself.
• The model has effectively memorized examples instead of learning the underlying pattern.
• See also: Context window, Tokenizer The component that splits raw text into tokens before a model processes it, using a fixed vocabulary…

Training data: The text, images, code, or other content a model learns from during training.

Read the full article: https://www.ainvasion.com/ai-glossary/