AI Garage Jargons
Plain-English mental models, practical examples, and visual explanations for the concepts shaping modern AI work.
Find a concept
Search by term, mental model, builder example, or tag.
Showing 21 of 21 terms
The vocabulary
21 results
LLM
A neural network trained on large language datasets to estimate token probabilities and generate or transform sequences from the context it receives.
In plain English
It predicts a useful next piece of language, adds that piece to the context, and repeats the process until it has produced a response.
Machine Learning
A model designed to make structured judgments or choose between possible actions, returning scores or probabilities instead of primarily generating open-ended text.
In plain English
A language model is often asked what to say next. A decision model is asked which option to choose, whether something is true, or how strongly something scores.
Prompting
The iterative practice of designing instructions, context, examples, and output constraints so a model performs a defined task more reliably.
In plain English
It is writing a clear handoff for the AI, then testing the results and improving the handoff when it fails.
Beginner
A unit produced when a model's tokenizer converts input or output into model-readable pieces. A token can be a word, part of a word, punctuation, whitespace, or another encoded unit.
In plain English
Before a model reads or writes text, a tokenizer cuts it into numbered pieces. Those pieces are tokens, and they do not line up one-for-one with words.
Machine Learning
Numeric vector representations of text, images, or other data that preserve useful patterns so related items can be compared by similarity or distance.
In plain English
A way to turn text into numbers so AI can compare meaning, not just exact words.
Machine Learning
Additional training that uses representative examples or feedback to update a pretrained model's parameters for a more specific task or behavior.
In plain English
It changes an existing model by training it on examples of how you want a particular task performed.
Showing 6 of 21 concepts
