it makes sense for the buffer to be searchable. So at any given time only some information is actually provided as an input parameter to the model, but as it “thinks” serially it can order a search.
For example, a task like “write a large computer program”. It cannot remember all the variable names and interfaces to the other parts of the program it is not working on, but needs to locate them whenever it calls on them.
So long as the “buffer” is a set of parameters/weights/neurons, that would fit my test.
it makes sense for the buffer to be searchable. So at any given time only some information is actually provided as an input parameter to the model, but as it “thinks” serially it can order a search.
For example, a task like “write a large computer program”. It cannot remember all the variable names and interfaces to the other parts of the program it is not working on, but needs to locate them whenever it calls on them.