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.
Supporting 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.
Share insightCheck this claim