Unverified50% confidenceFactExact time
大语言模型（LLM）不具备意图，因此严格意义上无法撒谎
1
Sources
50%
Confidence
Long-term
Relevance
8/18/2026
First Seen
Sources
Related Claims
UnverifiedLLMs lack grounding capability and cannot verify generated linguistic symbols against real-world states.77% similarUnverifiedLarge Language Models (LLMs) are fundamentally stateless—they cannot proactively fetch real-time information or directly execute external operations.72% similarUnverified单纯由LLM输出的未经形式化验证的自然语言证明，其可信度几乎为零70% similarVerifiedLarge language models have no natural instruction/data layering mechanism at the architectural level and cannot distinguish legitimate instructions from ordinary text in documents69% similarUnverifiedGoogle DeepMind的研究表明LLM可作为翻译器将非形式化数学语句转译为Lean或Isabelle表达，但准确率仍远未达到可部署水平69% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/771213API
curl https://kongchang.com/api/v1/knowledge/claims/771213MCP
get_claim(id=771213)