Unverified50% confidenceFactExact time
Explicit 'fake bad' instructions produced significantly greater distortion than mere contextual framing cues.
1
Sources
50%
Confidence
Long-term
Relevance
9/17/2026
First Seen
Sources
Related Claims
UnverifiedIn 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.74% 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73% 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 stated72% similarUnverified在系统提示中加入清晰的禁止性规则往往比等价的正向描述更能有效约束模型行为71% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/928410API
curl https://kongchang.com/api/v1/knowledge/claims/928410MCP
get_claim(id=928410)