Unverified50% confidenceFactExact time
So-called "multi-turn conversation" is entirely an effect faked by the client repeatedly sending a growing message array; the model itself does not store history.
1
Sources
50%
Confidence
Long-term
Relevance
10/14/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedMulti-turn conversation models accept a `messages` array containing a list of historical messages, with full context carried in each request; some specialized models' APIs only accept a single `prompt` input and do not process historical context.74% similarVerifiedChat Memory simulates memory by injecting historical messages into the Prompt with each request, causing token consumption to grow linearly with the number of conversation turns.73% similarVerifiedThe context window mechanism causes models in multi-turn conversations to feed the entire conversation history into the context, causing token consumption to grow rapidly as the conversation lengthens.73% similarVerifiedLong conversations package and resend the entire context history to the model, which is counted toward the token usage of each request; the longer the conversation, the more tokens a single request consumes.71% similarUnverifiedThe conversational memory of current mainstream large models is fragmented, with each interaction starting almost from scratch, requiring users to repeatedly provide background information.71% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1027837API
curl https://kongchang.com/api/v1/knowledge/claims/1027837MCP
get_claim(id=1027837)