How would you like to run your own private AI Server at home? Now you can. Go to ollama.ai and download it, run it, get llama3 model. Ask it any question. It runs in only 4gb of ram. It's amazing! Give it a try! Runs on mac/windows/linux. :)
Being able to run something like that on only 4gb is really great. I would love to be able to connect an NPC to AI LLM so that they can explain the story of Avedon Park. Also, nice watch. I miss watches.