Every term you'll meet in reviews and news posts — explained without the jargon.
An AI system that can plan and take multi-step actions toward a goal — browsing, calling tools, writing files — rather than just answering once.
Software that converts spoken audio into text. The engine behind dictation tools and meeting transcribers.
How much text a model can consider at once — conversation history, documents, instructions. Bigger windows handle longer projects.
Prompting a model to reason step by step before answering, which improves accuracy on complex problems.
The technique behind most AI image generators: starting from noise and gradually refining it into an image that matches your prompt.
Additional training on your own examples to specialize a model's tone, format, or domain knowledge.
When an AI states something false with confidence. Why citations, sources, and human review still matter.
The core technology behind chatbots like ChatGPT and Claude — trained on vast text to predict and generate language.
Models that work across formats — reading images, hearing audio, watching video — not just text in, text out.
Designing instructions that reliably get the output you want. Better prompts beat better models more often than people expect.
Grounding a model's answers in your own documents by retrieving relevant passages first — the cure for hallucinated facts.
Generating natural-sounding speech from text. Modern TTS handles emotion, pacing, and voice cloning.
The unit of text models read and bill by — roughly three-quarters of a word in English.