Glossary
Plain definitions for the words everyone uses and nobody explains.
13 articles
W
- What is a context window?The model's working memory — and the reason a long chat starts forgetting things.
- What is a GGUF file?The file format behind every local model you have downloaded — and how to read its name.
- What is a token?The unit models read, count and bill in — and it is not a word.
- What is a transformer?The 2017 architecture underneath essentially every model you have heard of.
- What is an AI agent?A model that can take actions in a loop — and the word the industry has worn out.
- What is an AI hallucination?When a model states something false with total confidence — and why that is the normal case, not a glitch.
- What is an embedding?Turning meaning into coordinates — the trick that makes semantic search work.
- What is an NPU?The chip your laptop and phone now advertise — what it's for, and why its headline "TOPS" number tells you less than it looks.
- What is chain-of-thought prompting?Asking for the working, and getting a better answer as a side effect.
- What is fine-tuning?Teaching a model how to behave — not what is true.
- What is prompt caching?Paying once for the part of your prompt that never changes — and the write fee nobody mentions.
- What is quantization?Shrinking a model so it fits on hardware you own — and what you give up.
- What is RAG (retrieval-augmented generation)?Giving the model the documents instead of hoping it memorised them.