Learn AI / Learning Paths /Understand ChatGPT and large language models

Understand ChatGPT and large language models

What is actually happening when a chat assistant answers you, and why fluent is not the same as correct.

9 terms · about 18 minutes · written with everyone in mind

Start with Large language model

Large language model
A very large text-processing model predicts likely next pieces of language from a prompt and uses that pattern-matching ability to generate or transform text.
Large Language Models · Starter
Token
A token is one unit from a model’s vocabulary used to represent input or output, often smaller than a word.
Large Language Models · Starter
Next-token prediction
A language model produces text by repeatedly estimating probabilities for small pieces of text that could come next in the current sequence.
Large Language Models · Starter
Prompt
The text, image or other input that guides a model on what kind of output to produce next.
Large Language Models · Starter
Context window
The maximum amount of input and prior output a language model can use at one time while producing the next part of a response.
Large Language Models · Starter
Completion
The text a language model produces after a prompt, built token by token from patterns learned during training.
Large Language Models · Starter
Temperature
A setting that controls how predictable or varied a language model’s next chosen words are during generation.
Large Language Models · Intermediate
Hallucination
A generated answer that sounds plausible but includes false, unsupported or invented details.
Large Language Models · Starter
"Understanding" (what models do and do not do)
In language models, apparent comprehension usually means producing text that fits patterns in data and context, not reliably building a grounded grasp of the world like a person does.
Large Language Models · Intermediate