Unverified50% confidenceFactExact time
The sole reason LLMs can continue a conversation is that the application layer re-feeds the historical context to the model each time.
1
Sources
50%
Confidence
Long-term
Relevance
9/6/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedThe context window in LLMs determines how many conversation turns the model can remember when making modifications to previously generated content75% similarUnverifiedDuring each inference, an LLM only processes the token sequence of the current input and does not retain persistent state across sessions (statelessness).72% similarVerifiedThe 'memory' of an LLM is technically implemented by concatenating historical conversation text into the current request's Prompt, allowing the model to see the historical content within a single inference pass.71% similarUnverifiedTransformer-based LLMs perform an independent forward-pass computation for each inference, with model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.71% similarUnverifiedIn multi-turn conversations, before each new response is generated, the system must re-input all prior conversation history into the model, causing token consumption to accumulate and grow with each turn69% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/863328API
curl https://kongchang.com/api/v1/knowledge/claims/863328MCP
get_claim(id=863328)