Skip to content
BENIBIX Learn

Multi-Turn Conversation

Also known as Multi-Turn Chat, Conversation History (AI), Chat History

A chat with many messages back and forth. The model rereads the whole chat each turn.

Think of it like

It is like a game of catch. Each throw builds on the last one.

Example

Emma asks for a cake recipe. Then she types "make it for 12 people". The model knows which recipe she means, because the first message is sent again.

Why it matters

It is why a chat feels like it remembers. It is also why a very long chat gets slow, dear and muddled.

Definition

A multi-turn conversation is a chat with many back-and-forth messages. Each time you ask and the model replies, that is one turn. The model has no memory of its own between turns. So the app sends the whole chat so far with every new message. That is how the model knows what "it" or "that one" means. Long chats fill the context window and cost more.

Example code

json
[
  { "role": "user", "content": "Give me a cake recipe." },
  { "role": "assistant", "content": "Here is a lemon cake..." },
  { "role": "user", "content": "Make it for 12 people." }
]
Turn two only makes sense because turn one is sent along with it.
Each turn, the model reads the whole pile again. Then it writes back.

Common mistake

Thinking the model learns from the chat. It only rereads it, and it forgets it all once the chat ends.

Key takeaways

  1. 1
    Turns add up. Each new message joins the pile.
  2. 2
    Sent every time. The whole chat goes with each turn.
  3. 3
    Start fresh. A new chat clears a muddled one.

Learn it properly