Unverified50% confidenceFactExact time
LLM在架构层面采用Transformer的注意力机制，每次推理在当前上下文窗口内独立完成，不存在跨会话的持久化状态
1
Sources
50%
Confidence
Long-term
Relevance
7/10/2026
First Seen
Sources
OpenWiki: A CLI Tool That Automatically Generates AI Agent Documentation for Codebases
hackernewshackernews7/1/2026
Related Claims
UnverifiedTransformer-based LLMs perform an independent forward-pass computation for each inference, with model weights fixed during the inference phase; what is referred to as context memory is essentially the re-injection of historical conversation text into the prompt.78% similarUnverifiedThe statelessness of LLMs is a fundamental characteristic of the Transformer architecture; the model stores no state after a session ends or the context is cleared.77% similarUnverifiedLLM无法从机制层面区分哪些token是指令、哪些是数据，因为所有输入在进入注意力层前都被统一转换为嵌入表示77% similarUnverifiedTransformer模型的注意力机制使模型能够在长达数千Token的上下文窗口内追踪对话语义，而早期LSTM模型受限于固定窗口的短期记忆76% similarUnverifiedThe inference mechanism of the Transformer architecture determines that the model itself has no persistent memory capability, and all 'memory' relies entirely on the context provided in the current session.75% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/464677API
curl https://kongchang.com/api/v1/knowledge/claims/464677MCP
get_claim(id=464677)