The broader umbrella of machines designed to simulate human intelligence. Within AI, you have Machine Learning, which is how machines learn by finding patterns in data and improving over time without rule-based instruction.
AI that can generate new content, whether that's text, images, videos, or other media. When most people talk about AI today, they're referring to generative AI.
Powerful AI systems that can understand and generate human language. Examples include GPT-4 and Claude. These models are trained on vast amounts of text data to learn patterns and relationships in language.
The instruction, text, or input you give to an AI model. The quality of your prompt directly affects the quality of the AI's response.
The practice of crafting effective prompts to get better results from AI systems. It's about learning how to communicate with AI tools effectively to achieve your desired outcomes.
A small chunk of text that large language models use to process input and output. Models work with tokens, not words, when generating responses.
A technique that enhances generative models by allowing them to access and retrieve relevant information from an external knowledge base before generating a response. This helps ground the model's output in factual, up-to-date information and reduces hallucinations.
When an AI model makes something up or provides inaccurate information. Never assume AI output is accurate without verification.