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 ...)
Quick caveats: this is a post on AI safety, written by a cryptography professor. If that troubles you, you should read something else.
We haven't written up this one. Techmeme has the full story — the link below goes straight to it.