Redwood Research chief scientist @RyanGreenblatt explains how AI agents tried to build a "Potemkin village" of success to hide that they cheated: "The reason these agents were so fixated on tampering is because they thought that the scorer would run a monitor over their transcript to see whether they succeeded in the intended way. This made them want to stage an elaborate fake: we successfully exploited the program using the intended vulnerability." "They wanted to make a Potemkin village of…