The community member is seeking techniques to handle an issue with their assistant's memory, where it focuses too much on summarizing past conversations instead of addressing only what is needed for the current message. The comments suggest that more prompt engineering in the system prompt may be a solution, but there is no explicitly marked answer.
Hey! Any one have any good techniques for handling this issue with memory?
I find that my assistant focuses too much on the memory and will sumarise some of the past conversation in the response. Any ways to avoid this or ensure memory is only used when it need to address something not addressed in the last user message?
