Large language models
Chatbots, prompts, and the models behind them.
- EmbeddingA list of numbers that represents the meaning of a piece of data, so that similar things end up with similar numbers.
- HallucinationWhen an AI model produces information that sounds confident and plausible but is false or made up.
- Large language modelA very large neural network trained on huge amounts of text to predict the next piece of text, which lets it write, summarize, and answer questions.
- Retrieval-augmented generationA technique where a language model first looks up relevant documents, then writes its answer using them, so answers can be grounded in real sources.
- TokenThe small chunk of text a language model reads and writes, often a word, part of a word, or a punctuation mark.
- TransformerA neural network design that uses attention to weigh how every part of the input relates to every other part. Most modern language models are built on it.