A look at two opposing perspectives on AI agent sandboxing: infosec says labs need better containment while AI alignment says sandboxes cannot contain agents (Matthew Green/A Few Thoughts ...)
Matthew Green / A Few Thoughts on Cryptographic Engineering : A look at two opposing perspectives on AI agent sandboxing: infosec says labs need better containment while AI alignment says sandboxes cannot contain agents Quick caveats: this is a post on AI safety, written by a cryptography professor…
Read the full story at Techmeme ↗