CONNECTED THINKING
Knowledge atlas
Follow people, viewpoints and their original evidence.
1 people · 1 sources · 1 viewpoints
IN CONTEXT
Empirical assessment of containment failure
Choose a viewpoint. Follow it back to the conversation.
Poor containment leaves the cause of failures unresolved
Equal sectors are reading positions, not rankings.
Showing 1–1 of 1 viewpoints · Newest sources first
1 / 1
Selected 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.
These are individual perspectives, not a measure of consensus. Source material stays in its original language.
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.
Publication dates describe the sources, not changes in belief.