Oscar_Cunningham comments on Cryptographic Boxes for Unfriendly AI - Less Wrong
You are viewing a comment permalink. View the original post to see all comments and the full post content.
You are viewing a comment permalink. View the original post to see all comments and the full post content.
Comments (155)
This recent development seems relevant: a technique for functional encryption, rather than just message encryption.
Based on this post I'd thought that was already possible, but some discussion I saw of this article suggested that encrypting the code, and not just the input and output, was something new.