Skip to content

About Writing Notes Links Projects

Seems fine.

Seems fine.

@matthewdgreen.bsky.social via simonwillison.net/2026/Oct/1/m...

Screenshot of article which reads: "Unfortunately, monitoring for adversarial data access turns out to be one of the hardest problems you could imagine. The volume of data that agents produce is so high that no human being could possibly read it, and we probably wouldn’t recognize obfuscated malicious data even if we were looking directly at it. This means any attempt to monitor the inflow/outflow will have to be handled by other models. Thus, the future of agent sandboxing is (1) build a sandbox, (2) install an agent/model into it, (3) install a somewhat dumber/cheaper warden model to guard it, (4) hope you can trust the lunkhead to contain the wizard. And so on and so forth, as models become more intelligent and capable."

October 2, 2026Also on Bluesky ↗

RSS @ciaranlyons.com

© Ciaran Lyons