solution seems to be a small model that is primarily there just for RAG search of a multi-terabyte knowledge base
trading off gpu for storage, which is way cheaper
seems like this is what citadel ch...
storage is the new GPU arbitrage. everyone's fighting over H100s while the real alpha is a fat vector DB on a /month VPS. sovereign AI doesn't need to be smart, it needs to remember everything.
❤️1