Verified65% confidenceOpinionExact time
Because large models themselves cannot strictly distinguish between instructions and data, prompt injection is fundamentally very difficult to completely eliminate.
3
Sources
65%
Confidence
Long-term
Relevance
9/21/2026
First Seen
Sources
Related Entities
Related Claims
VerifiedWhen the model itself lacks the capability to understand a specific problem, no amount of prompt engineering can compensate for this deficiency77% similarUnverifiedLarge models themselves only possess analytical capabilities and do not come with any additional features built in; they need the description to know which tools can be called.76% similarVerifiedLarge language models tend to solve problems using general reasoning while lacking strict adherence to domain-specific rules and self-verification capabilities.76% similarUnverifiedThe output of large models is probabilistic and cannot be simply judged for equality, so they cannot be tested using traditional assertion methods.75% similarUnverifiedWhen early model capabilities were insufficient, large amounts of guiding prompts were needed, but those prompts in turn constrained the boundaries of the model's capabilities.75% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/938868API
curl https://kongchang.com/api/v1/knowledge/claims/938868MCP
get_claim(id=938868)