Ethereum co-founder Vitalik Buterin has detailed his personal AI setup, which he calls "private" and "secure". He runs his AI on local hardware and has built custom tools around the large language model (LLM) to prevent AI agents from sending messages or moving crypto without human approval. The post expands on Buterins' previous calls for privacy-preserving AI. He also revealed that he has built and open-sourced a messaging daemon that allows his AI agent to read Signal messages and emails freely, but restricts outbound messages to himself unless a human manually approves them first.