ive been finding that letting an LLM write its own memory bank tends to have it regurgiate your prompts more than keep something actually useful.
ive been finding that letting an LLM write its own memory bank tends to have it regurgiate your prompts more than keep something actually useful.
That is also true. Occasionally I would go in and clean up the docs and refocus them, but in the end I realized that I'm baby sitting the agent rather than relying on it to help me.