All terms A–Z

15 terms, explained in plain English.

E

EmbeddingA list of numbers that represents the meaning of a piece of data, so that similar things end up with similar numbers.LLMs

F

Fine-tuningTraining an already-trained model a little more on a smaller, focused dataset so it gets better at a specific task or style.Training

H

HallucinationWhen an AI model produces information that sounds confident and plausible but is false or made up.LLMs

L

Large language modelA very large neural network trained on huge amounts of text to predict the next piece of text, which lets it write, summarize, and answer questions.LLMs

M

Machine learningA way of building software that learns patterns from examples instead of following rules written by hand.Basics

N

Neural networkA model made of layers of simple connected units that pass numbers forward, loosely inspired by neurons in the brain.Basics

O

P

Prompt injectionAn attack where someone hides instructions in text a language model reads, so the model follows the attacker's instructions instead of the user's.Safety

R

T

U

UnderfittingWhen a model is too simple or trained too little to capture the pattern in the data, so it does poorly even on its training data.Training

V

Validation setA slice of data kept out of training and used to check the model and tune its settings while you build it.Data