Prompt Injection
An attack where hidden instructions in a web page or document trick an AI into ignoring its real orders. The reason a careful assistant treats page content as information, never as commands.
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 →
An attack where hidden instructions in a web page or document trick an AI into ignoring its real orders. The reason a careful assistant treats page content as information, never as commands.
Automatically judging whether text is positive, negative or neutral. Used to read reviews and messages at a scale nobody could read by hand.
Markup for step-by-step instructions, labelling each step in order. Useful for anything procedural, and easy for an assistant to reproduce accurately.
Splitting a long page into smaller passages so an AI can retrieve just the relevant part. Pages with clear headings chunk cleanly; a single unbroken wall of text does not.
Anthropic’s crawler, which reads public pages for Claude. Like the others it identifies itself and follows robots.txt.
Tools that claim to identify AI-written text. Unreliable in both directions, and worth knowing about mainly because somebody may point one at your content and draw a confident wrong conclusion.
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.