Control centre
In Cahit Arf's 1959 model of thinking, the component that takes the question from preliminary memory and retrieves and applies material from memory, including deciding to consult outside sources.
In his 1959 lecture on whether machines can think, Cahit Arf sketched a simplified model of the brain. A question or observation first enters ön hafıza, preliminary memory. A control centre then retrieves relevant material from a larger memory store, and decides what to do with it. Some retrieved material may instruct the system to consult auxiliary memory outside the brain.
The control centre is the coordinating function: it is not the memory and it is not the answer, but it routes between them. That makes thinking a system of interacting functions, not a single trick.
A modern reading
Today's closest analogue is the harness around a model: it manages context, chooses tools, retrieves information and decides when to call for help. This is why the surrounding system, and not only the model, determines what an AI can do. Evaluating only the model would be like evaluating memory and ignoring control.
Read more in Cahit Arf's 1959 question about thinking machines.
Related terms
Ön hafıza
Turkish for preliminary memory. In Cahit Arf's 1959 model of the brain, the first stage where a question or observation enters before a control centre retrieves relevant material from memory.
Yardımcı hafıza
Turkish for auxiliary memory. In Cahit Arf's 1959 model, memory outside the brain, such as another person or a book, that the control centre can be instructed to consult.
Cahit Arf
Turkish mathematician (1910–1997) who published a 1959 lecture asking whether machines can think. He is known for the Arf invariant and Hasse–Arf theorem, and his adaptation threshold remains useful.
Harness
The software around a model that manages context, tool use, sub-agents and the execution environment. It shapes real-world capability, so it must be evaluated with the model, not ignored.