AI glossary / Safety and trust
Model spec
A public document in which an AI company sets out how its assistant is supposed to behave.
More words in Safety and trust
- OverrelianceTrusting AI output without checking it, or letting your own skills fade because the AI always does it for you.
- Personal dataAnything that identifies you, such as your name, address, health details or photos. Think before sharing it with an AI tool.
- PhishingScam messages that pretend to be from someone you trust. AI lets criminals write more convincing ones, in perfect English, at scale.
- Prompt injectionHidden instructions tucked inside a web page, email or document that try to hijack an AI reading it.
- Red teamingDeliberately trying to make an AI misbehave so weaknesses are found and fixed before release.