LLMs predict what text should come next, one token at a time. Scaled up, that simple idea lets them answer questions, write, translate and reason through problems.
Example
The model behind a chatbot you use to write video descriptions.
Why it matters to you
Most text-based AI tools you use run on an LLM.
Related terms
TokenA small piece of text, often part of a word, that language models read and write./knowledge-base/token/ChatbotA program you talk to in a conversation, by typing or speaking./knowledge-base/chatbot/Context WindowHow much text an AI model can “keep in mind” at once./knowledge-base/context-window/HallucinationWhen an AI confidently gives an answer that is wrong or made up./knowledge-base/hallucination/
