AI Glossary

AI hallucinations happen when a model generates confident but false information. Learn why LLMs hallucinate, see real examples, and find out how to reduce them.

AI tokens are the small chunks of text that language models process. Learn how tokenization works, why tokens affect cost and context limits, and how to estimate token usage.

Evals are structured tests that measure how well an AI model performs. Learn what evals mean, how LLM evaluation works, and the main types of model evals used in production.

Fine-tuning is a post-training method where a pre-trained model is further trained on a smaller, specific dataset to specialize it for a particular task or domain.

Inference is when a trained AI model applies what it learned to generate a response. Learn how inference works, how it differs from training, and why it drives most AI costs.

A large language model (LLM) is an AI system designed to understand and generate human-like text.

An AI model is a program trained on data to recognize patterns and make predictions. Learn how AI models work, the different types, and how they're used in practice.

Post-training is the phase after pre-training where an LLM learns to follow instructions, reason, and align with human preferences. Learn how SFT, RLHF, and DPO work.

Prompt engineering is the practice of crafting prompts, questions, instructions, or input, in a way that helps AI models give better, more useful responses.

RAG stands for Retrieval-Augmented Generation. It’s a technique that lets AI models pull in outside information at the time you ask a question, kind of like letting the model take an open-book test instead of relying purely on memory.

RLHF stands for Reinforcement Learning from Human Feedback. It’s a post-training technique used to teach AI models how to respond in ways that better align with human values, preferences, and expectations.

Supervised learning trains AI models on labeled data to make predictions. Learn how it works, how it compares to unsupervised and self-supervised learning, and where it's used.

Training is the process where an AI model learns by analyzing massive amounts of data to recognize patterns, understand language, and make predictions.

A transformer is a type of AI model architecture that made today’s powerful language models (like ChatGPT and Claude) possible. It was introduced by Google researchers in 2017.

Unsupervised learning is a type of machine learning that finds patterns in unlabeled data. Learn how it works, the main types, and how it compares to supervised and reinforcement learning.