Attributed viewpoint

Poor containment leaves the cause of failures unresolved

Green sides with the information-security view that labs have not implemented containment correctly. He says this leaves it unclear whether the problem lies with the models or with poor infrastructure.

Matthew Green·Published Sep 30, 2026

Behind the viewpoint

Translations are for reading; original excerpts remain the evidence.

Is sandboxing sufficient to contain rogue agents?

Original excerpt

So on this point I’m going to side with the infosec folks. The labs have not been doing containment correctly, and so we can’t really tell if the problem is models or just bad infrastructure.

Open original · Paragraph 18 View source page