Skip to main content
GGenerative AI
    • Start here
    • Learning paths5 paths
    • Modules11 modules
    • Projects5 projects
    • Quizzes
    • Flashcards
    • Homework
    • Interview prep8 question banks
    • Cheat sheets11 sheets
    • Glossary239 terms
    • Code snippets
    • Ask the mentor
    • My notes
    • My progress
SearchStart here
Menu
    • Start here
    • Learning paths5 paths
    • Modules11 modules
    • Projects5 projects
    • Quizzes
    • Flashcards
    • Homework
    • Interview prep8 question banks
    • Cheat sheets11 sheets
    • Glossary239 terms
    • Code snippets
    • Ask the mentor
    • My notes
    • My progress
  1. Reference
  2. Prompt injection

Glossary

Prompt injection

Text that changes what a model does in a way its operator did not intend. No guardrail fully prevents it; the aim is to limit what a hijacked model can do.

Where it is explained

  • Guardrails, safety and prompt injectionSafety and guardrails

See also

Terms explained in the same lessons.

  • Defence in depth
  • Direct prompt injection
  • False negative
  • False positive
  • Guardrail
  • Indirect prompt injection
Previous termPrompt cachingNext termQLoRA

All terms, A to Z

GGenerative AI

Learn generative AI from the first token to production systems.

  • Privacy
  • Search