Skip to content

Prompting

Negative instruction

A prompt instruction that tells the model what not to do or include.

Example

The instruction says not to discuss price but never explains what to say instead.

Why it matters

It helps set boundaries around unwanted wording or behavior.

You'll hear it

“Leave out personal details and use a general description instead.”

Can you control it?

Yes

Yes. You can often use or adjust a negative instruction directly when the product supports it. The available options and their effect still depend on the tool.

Common questions

Can too many prohibitions become confusing?
Yes. A long list of exclusions can obscure the actual task or create contradictions.
Does saying 'do not' guarantee the behavior stops?
No. Systems can misunderstand or fail to follow the instruction.
Can an exclusion conflict with the main request?
Yes. Asking for a detailed explanation while forbidding essential details can leave no satisfactory answer.

AI chatbot

Still have questions?

Ask the AI chatbot about this term or another AI concept.

Up to 500 characters.

Ask LATHIC about AI. Relevant glossary entries may be included.

Your question, the glossary entries it matches, and a rotating pseudonymous identifier go to Microsoft Azure’s OpenAI service through Vercel AI Gateway to generate an answer. Zero retention and no training are required of the provider, and LATHIC does not save your question or answer. Privacy Notice