결국 인간처럼 가려면 vector space 에 지식이 포진되어 있어야 하는데, weight training을 모든 순간 하는건 너무 비효율적이라 Vector Database 같이 따로 저장소를 둘 것 같다.AI Memory Tools Episodic memory Semantic memory Memory for agentsAt Sequoia’s AI Ascent conference in March, I talked about three limitations for agents: planning, UX, and memory. Check out that talk here. In this post I will dive more into memory. See the previous post on planning here, and the previous posts on UX here, here, and here.https://blog.langchain.dev/memory-for-agents/