Unverified50% confidenceFactExact time
Language models often struggle to strictly distinguish between 'rules in the system prompt' and 'new instructions in the user message'.
1
Sources
50%
Confidence
Long-term
Relevance
10/14/2026
First Seen
Sources
Related Entities
Related Claims
VerifiedLarge language models are architecturally incapable of strictly distinguishing between system instructions and user data, which is a fundamental flaw at the architectural level.77% similarUnverified系统提示词的语言选择会影响输出风格，当系统提示词语言与用户输入语言不一致时会产生行为叠加效应77% similarUnverifiedLarge language models cannot reliably distinguish the boundary between system instructions and user/external content during inference—this is a fundamental limitation of prompt injection, similar in principle to SQL injection.76% similarUnverifiedWriting scoring rules into a prompt in natural language has drawbacks: wording variations across different calls may cause the model's understanding to drift, and the scoring logic cannot be directly parsed or reused by programs.75% similarUnverifiedThe natural language interface itself may also become a new layer of opacity: users do not know how the model interprets their descriptions, nor how much weight the interest list carries in ranking.74% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1029603API
curl https://kongchang.com/api/v1/knowledge/claims/1029603MCP
get_claim(id=1029603)