Vitalik tests privacy protection AI health system: local model + zkAPI + Tor three-layer architecture to prevent identity leakage

Vitalik.eth posted on Farcaster revealing that he is conducting a personal experiment to generate personalized diet and exercise recommendations using personal health and travel data by combining local models with remote cutting-edge models while protecting privacy.

The system employs a three-layer privacy protection architecture: the identity layer uses a local model (Qwen 3.8B) to construct query requests on behalf of the user, avoiding exposure of writing style that could reveal identity; the payment layer uses zkAPI to hide payment information; the network layer hides the IP address through Tor. The system is currently operational, but Vitalik pointed out three major shortcomings: Tor is inefficient and has high latency in unlinking requests; the local model runs at only 20-30 TPS, and a smooth experience requires over 100 TPS; the stricter the data protection, the more limited the assistance that the remote model can provide. The relevant code has been submitted to the Ethereum zkAPI repository.