Unverified50% confidenceFactExact time
The self-referential terms used by large language models (such as 'as a language model') change as the chat template is switched.
1
Sources
50%
Confidence
Long-term
Relevance
9/27/2026
First Seen
Sources
Related Entities
Related Claims
Unverified同一个大型语言模型在使用不同语言交流时，其语气、态度和礼貌程度可能存在显著差异79% similarUnverified大语言模型每次对话独立，无法对整个代码库形成持久认知模型，导致不同会话生成的代码在架构风格、命名规范、错误处理策略上存在系统性不一致76% similarUnverifiedA system prompt can cause any large language model to refer to itself by any name in conversation, including fictitious model names.75% similarVerifiedLarge language models are inherently stateless, and remembering conversation history relies on concatenating the historical conversation text and feeding it into the model together.73% similarUnverifiedIn multi-agent systems, collaboration among large language models has long relied on converting one model's output into natural-language text and feeding it as a prompt to the next model.73% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/953717API
curl https://kongchang.com/api/v1/knowledge/claims/953717MCP
get_claim(id=953717)