Verified70% confidenceFactExact time
Large language models are architecturally incapable of strictly distinguishing between system instructions and user data, which is a fundamental flaw at the architectural level.
4
Sources
70%
Confidence
Long-term
Relevance
7/17/2026
First Seen
Sources
Related Claims
UnverifiedLarge 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.79% similarVerifiedLarge language models have no natural instruction/data layering mechanism at the architectural level and cannot distinguish legitimate instructions from ordinary text in documents78% similarUnverifiedLanguage models often struggle to strictly distinguish between 'rules in the system prompt' and 'new instructions in the user message'.77% similarVerified提示注入的根本原因在于大语言模型缺乏区分指令层与数据层的原生机制77% similarUnverified大语言模型每次对话独立，无法对整个代码库形成持久认知模型，导致不同会话生成的代码在架构风格、命名规范、错误处理策略上存在系统性不一致77% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/547475API
curl https://kongchang.com/api/v1/knowledge/claims/547475MCP
get_claim(id=547475)