logoalt Hacker News

sachaa • today at 5:30 PM • 0 replies • view on HN

Also, they are thinking of one single LLM model at a time. What if we have a network of dynamically loaded micro-models loaded on demand based on the user intent? Think of a global DNS of micro-LLMs. We need to decentralize AI. I started building this here https://modelxare.com