Unverified50% confidenceSolutionExact time
负面指令（如'不要添加未被要求的内容'）往往比模糊的正面指令（如'请简洁回答'）更有效
1
Sources
50%
Confidence
Long-term
Relevance
8/11/2026
First Seen
Sources
Related Claims
UnverifiedNegative Prompting, by explicitly telling the model what not to do through exclusionary constraints, is often more precise and controllable than positive style descriptions.77% similarUnverified在提示工程领域，负向约束通过明确「不应该做什么」来引导输出，是一种重要但常被忽视的技巧73% similarUnverified增加负样本描述（When NOT to Use）能明确 Skill 的决策边界，显著减少误触发71% similarUnverified用户感觉骂AI才有答案，实际起作用的是更清晰的指令，而非辱骂动作本身64% similarUnverified约束驱动提示（明确告知AI不应做什么）往往比目标驱动提示更能减少幻觉输出63% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/730312API
curl https://kongchang.com/api/v1/knowledge/claims/730312MCP
get_claim(id=730312)