Unverified60% confidenceFactTime unknown
大语言模型推理的瓶颈往往不在计算能力，而在于内存带宽
2
Sources
60%
Confidence
Long-term
Relevance
6/1/2026
First Seen
Sources
Qwen 3.6 MTP Real-World Test: The Secret to a 20% Speed Boost with Just Three Parameters
bilibili比特光锥_BightCone
Related Entities
Related Claims
UnverifiedLanguage model outputs are probabilistic and semantically ambiguous, making it difficult to measure quality with precise assertions, which poses challenges for migrating TDD concepts to the prompt engineering domain.79% 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.78% similarUnverifiedOOD detection for autoregressive language models is more difficult than for traditional machine learning because the linguistic compositional space is vast, semantic OOD does not correspond to surface-form OOD, and adversaries can construct inputs that appear statistically in-distribution but semantically trigger OOD behavior.77% similarUnverified大语言模型难以编码为什么在特定社会语境中词的真实含义与字面意义相反这类元认知推理，这一局限被称为'语用鸿沟'（pragmatic gap）76% similarUnverifiedLarge language models have systematic shortcomings in 2D spatial reasoning, due to training data being predominantly text-based and lacking supervisory signals for spatial relationships.76% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/18092API
curl https://kongchang.com/api/v1/knowledge/claims/18092MCP
get_claim(id=18092)