Approaches like RAG, vector databases, and long context windows partially address memory problems, but there are still major challenges in true agent memory and self-learning.

factualpending

Speaker

Constantine

Evidence Quote

“we've been trying everything from rag and vector DBs to really long context windows, but everyone in this room knows that there are still major challenges in true memory and self-learning.”

Source

AI's Trillion-Dollar Opportunity: Sequoia AI Ascent 2025 Keynote— Sequoia Capital
Created: 8/11/2026, 6:39:24 AM

Your notes

Loading notes...