- AI hallucination
An AI hallucination is an output from a language model that sounds plausible but is false, irrelevant or invented.
- Artificial intelligence (AI)
Artificial intelligence (AI) is a broad term for computer systems that handle tasks which normally call for human intelligence, such as …
- Context window
The context window is all the text a language model can reference when it generates a response, including the response itself.
- Embeddings
Vector embeddings are lists of numbers that represent data such as words, sentences, documents, images or audio as points in a vector space.
- Fine-tuning
Fine-tuning in AI means continuing the training of an already pretrained model on additional, task-specific examples.
- Generative AI
Generative AI refers to AI models that create new content such as text, images, audio, video or code.
- Knowledge cutoff
The knowledge cutoff is the point in time up to which a language model has been trained on data.
- Large language model (LLM)
A large language model (LLM) is an AI model trained on very large amounts of text that generates language by repeatedly predicting the …
- System prompt
A system prompt is the standing instruction that a developer or operator gives a language model before the user's own input.
- Token
A token in the context of language models is the unit of text a model reads and writes.
- Tokenizer
A tokenizer is the component that splits text into tokens and assigns each token a numeric ID from a fixed vocabulary.
- Training data
Training data is the collection of examples a machine learning model learns from.
- Transformer
A transformer is a neural network architecture that processes text and other sequences with an attention mechanism, called self-attention.