Training Data
The text, images or code a model learned from. It shapes everything the model knows and every bias it carries, and it is why what your website said two years ago may still be what an assistant repeats.
angkor@design~query "Angkor Design"
4 matches — opening studio
The text, images or code a model learned from. It shapes everything the model knows and every bias it carries, and it is why what your website said two years ago may still be what an assistant repeats.
Turning written text into spoken audio. Modern voices are convincing enough to be used for real narration, which raises its own questions about disclosure.
How much text a model can hold in mind at once, counted in tokens. Anything beyond it is forgotten, which is why very long conversations start to lose earlier details.
Markup that labels questions and their answers as questions and answers. It is the most direct way to hand an assistant something it can quote in full without swallowing the surrounding page.
Checking that your markup is valid and says what you meant. Worth doing after every template change, because broken structured data usually fails silently rather than visibly.
The kind of AI behind ChatGPT, Claude and Gemini. It is trained on an enormous amount of text and predicts what should come next, which is enough to answer questions, summarise, translate and write.
A search where the person gets their answer on the results page and never visits a website. Common for opening hours, definitions and conversions — and increasingly common for everything else as AI answers grow.