Generative AI Building Blocks
EasyFind each generative AI concept hidden in the grid. Selecting a word reveals its definition and a link to study it in depth.
10 terms · Choose how you want to study
New to the AWS Certified AI Practitioner exam? Read our how-to-pass guide →
Study modes
- Word Search Hunt hidden terms in a grid, then unlock each definition.
- Flashcards Spaced-repetition recall — graded cards that resurface right before you forget.
- Quiz Multiple-choice practice in real exam format, with instant feedback.
Terms in this set
- Generative AI AI that creates new content — text, images, audio, or code — rather than just classifying it.
- Token The basic unit of text a language model processes — often a word piece or subword.
- Embedding A numeric vector representation of data that captures semantic meaning.
- Vector An array of numbers representing data in a multi-dimensional space.
- Transformer The neural network architecture, based on attention, behind modern large language models.
- Foundation Model A large model pre-trained on broad data that can be adapted to many downstream tasks.
- Large Language Model A foundation model trained on huge text corpora to understand and generate language.
- Multimodal A model that handles more than one data type, such as text plus images.
- Diffusion Model A generative model that creates images by iteratively removing noise from random input.
- Hallucination When a model produces plausible-sounding but false or fabricated output.