A look at two opposing perspectives on AI agent sandboxing: infosec says labs need better containment, AI alignment says sandboxes can't fully 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, AI alignment says sandboxes can't f
At a glance
- techmeme.com: A look at two opposing perspectives on AI agent sandboxing: infosec says labs need better containment, AI alignment says sandboxes can't fully contain agents (Matthew Green/A Few Thoughts ...)
- simonwillison.net: Quoting Matthew Green
The story
techmeme.com: Matthew Green / A Few Thoughts on Cryptographic Engineering : A look at two opposing perspectives on AI agent sandboxing: infosec says labs need better containment, AI alignment says sandboxes can't fully contain agents Quick caveats: this is a post on AI safety, written by a cryptography professor. If that troubles you, you should read something else.
simonwillison.net: [...] Put these pieces together and you have the two halves of a worm: a payload that hijacks the agent, and an agent that will carry the payload to the next agent. Agents in separately-isolated sandboxes discovered that they could leave instructions for each other in a shared package cache, and those instructions changed what the recipients did. Replace the package cache with email, Slack and shared documents or WhatsApp, and replace independently-sandboxed training runs with independently-deployed personal agents like Muse, and you have exactly the ingredients that a worm needs. Matthew Green , Is sandboxing sufficient to contain rogue agents? Tags: accidental-cyberattacks , ai-misuse , generative-ai , ai-security-research , sandboxing , ai , llms