Expired50% confidenceFactTime unknown
Large language models have an inherent limitation known as the 'Instruction Following' problem.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
7/2/2026
First Seen
This claim has expired. It is kept for the record and no longer describes the current state.
Valid until: 9/30/2026(expired)
Sources
Claude Code Hooks Explained: Build Your Own Automated Development Inspector
bilibiliai798Lab
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.75% similarUnverifiedLarge language models are architecturally incapable of strictly distinguishing between system instructions and user data, which is a fundamental flaw at the architectural level.74% similarUnverifiedCurrent large language models still have significant limitations in handling long contexts, maintaining complex states, and ensuring consistency between code modules.73% similarVerifiedLarge language models have no natural instruction/data layering mechanism at the architectural level and cannot distinguish legitimate instructions from ordinary text in documents72% similarVerifiedThe root cause of prompt injection is that large language models lack a native mechanism to distinguish between the instruction layer and the data layer.72% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/59858API
curl https://kongchang.com/api/v1/knowledge/claims/59858MCP
get_claim(id=59858)