How AI answers
Follow one prompt from text to reply and see what limits it.
What is a token, and why is AI priced per token?
A token is a chunk of text, often a word or part of one, that AI services bill by, on what you send and what comes back. Counts differ by language and content.
Why can't AI count the letters in a word?
An AI model reads chunks of text as numbers, not letters, so a letter can hide inside a chunk. Spelling the word out, or running code, gets around it.
Why does a chatbot forget?
A chatbot keeps no memory between replies. Each reply re-reads the chat up to a fixed limit, so early instructions fall out and long chats cost more.
Why do answers appear word by word?
A chatbot makes one token per pass and adds it to the text, then runs again, so a reply arrives a piece at a time and the app shows each piece as it comes.
Why does the same question give different answers?
A model gives every possible next token a chance, and the app draws one at random by those chances, so two runs can differ. Temperature and top-p shape the draw.
What does attention do inside an AI model?
Attention lets each word of a text pick up what earlier words mean: it scores them, turns the scores into weights, and takes a weighted average.