You've mastered the Library!

The whole library in a nutshell

1. 📚LLM: An LLM generates fluent text from patterns it learned while reading huge amounts of writing.
2. 🔤Token: AI reads text as tokens: chunks that can be words, word-pieces, or punctuation.
3. 🔮Prediction: LLMs write by predicting the next likely word, again and again, with some randomness.
4. 🗓️Cutoff: Models only know what was in their training data, which stops at a cutoff date.
5. 🔍Hallucination: AI can produce confident, fluent answers that are simply made up. Verify what matters.
6. 📱RAG: RAG lets an AI look up relevant documents before answering, so it can use fresh or private info.
7. 🗂️Context: The context window is how much text the AI can consider at once. Old parts can fall off.
8. ✉️Prompt: A clear prompt with audience, format, and purpose gets far better results than a vague one.