Anthropic is working on a system to prove AI models’ identity

Anthropic is developing an open-source system called FlashProve to verify the identity of AI models and their outputs, providing a cryptographic proof that a given output came from a specific model. The system would prevent impostors from disguising one model as another, and could be used to verify claims by third parties that a specific task was done by an advanced model. The system requires AI labs to publish a 'fingerprint' of each model, which doesn't reveal the model's weights, enabling the system to work with commercial models.