Fine-Tuning
Taking a general model and training it further on your own examples so it follows your tone or handles your particular task. Useful when prompting alone keeps producing nearly-right answers.
angkor@design~query "Angkor Design"
4 matches — opening studio
Prefer to talk it through? Pick a time that suits you — free, no obligation. We'll meet on Google Meet or Telegram.Book a meeting →
Taking a general model and training it further on your own examples so it follows your tone or handles your particular task. Useful when prompting alone keeps producing nearly-right answers.
A setting that controls how predictable an AI’s output is. Low temperature gives safe, repeatable answers; high temperature gives varied, more surprising ones — useful for ideas, risky for facts.
An older way of marking up facts, written as attributes on the HTML itself rather than in a separate block. Still understood, but JSON-LD is now the safer choice.
Whether a website can be reached, understood and quoted by AI assistants. It covers crawler access, structured data, clear headings, published contact details and speed — the unglamorous things that decide whether a model will name you.
OpenAI’s crawler for building its index. Blocking it in robots.txt keeps your content out of that index — and out of the answers built from it.
AI that produces something new — text, images, code, audio — rather than only classifying or predicting. The generative part is why it can write an answer about your business instead of just linking to it.
An emerging convention: a plain-text file at your site root that gives AI systems a clean map of what is on it. It saves an assistant from crawling around to work out what your site contains.