Unverified50% confidenceFactExact time
The "forgetfulness" of large language models stems from their stateless inference architecture: each time the API is called, the model only processes the token sequence passed in the current request and retains no internal state across requests.
1
Sources
50%
Confidence
Long-term
Relevance
9/18/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedLarge language models are essentially stateless functions, and a model's memory depends entirely on the content within the context window.76% similarUnverifiedTraditional LLMs are "memoryless"—each API call is independent and the model itself does not remember the content of previous conversations.72% similarUnverified语言模型生成 token 本质上是内存带宽受限任务而非纯算力受限72% similarUnverifiedLarge language models are essentially stateless, and code repositories, as external persistent storage, compensate for this deficiency.69% similarVerified大语言模型的推理过程本质上是内存带宽受限（memory-bandwidth bound）的任务，每生成一个Token都需要将模型的全部权重从存储中读取一遍69% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/931828API
curl https://kongchang.com/api/v1/knowledge/claims/931828MCP
get_claim(id=931828)