AI Dynamics

Global AI News Aggregator

Verifying AI Model Outputs and Public Signatures Without Revealing Weights

The use case is if you have a lot of people who all want to verify that the same known large expensive AI model said a thing. Another use case might be if there's some way to have a fixed model public signature without revealing its weights.

→ View original post on X — @esyudkowsky,

Commentaires

Leave a Reply

Your email address will not be published. Required fields are marked *