Verified75% confidenceFactExact time
Large language models have no natural instruction/data layering mechanism at the architectural level and cannot distinguish legitimate instructions from ordinary text in documents
5
Sources
75%
Confidence
Long-term
Relevance
7/11/2026
First Seen
Sources
GPT-5.6 Sol Limited Preview: The Safety Boundaries Behind AI's Capability Expansion
bilibili江枫渔火AI7/9/2026
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.78% similarUnverified大型语言模型本身只能生成文本，无法直接操作文件系统或网络，实际执行能力依赖开发框架预先注册的工具函数76% 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76% 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.73% similarUnverifiedThe semantic structure of code differs fundamentally from natural language, making it difficult for embedding models to accurately preserve information such as identifier naming, call relationships, and scope.73% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/487544API
curl https://kongchang.com/api/v1/knowledge/claims/487544MCP
get_claim(id=487544)