Unverified50% confidenceSolutionExact time
In prompt engineering, positive framing is preferable to negative prohibition, because the model's attention is easily skewed by repeatedly mentioned concepts, making it more reliable to describe what to do than to emphasize what not to do.
1
Sources
50%
Confidence
Long-term
Relevance
9/12/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedDescribing unwanted things in a suggestive manner pollutes the model's attention and instead injects those unwanted concepts into it.80% similarUnverifiedNegative Prompting, by explicitly telling the model what not to do through exclusionary constraints, is often more precise and controllable than positive style descriptions.79% 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76% 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75% similarUnverifiedFull-duplex models are highly sensitive to how instructions are presented, with noticeable performance degradation when behavior must be inferred from a persona rather than explicitly stated75% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/916615API
curl https://kongchang.com/api/v1/knowledge/claims/916615MCP
get_claim(id=916615)