fluidcruft
Joined 16 years ago
Karma
4,144
Submissions
2,122
Member since
Jul 24
Joined 16 years ago
Claude was able to work out who it was in less than 10min based on stringing together facts that remained and seemed irrelevant. Journalists uncovered the identity independently using different means. (The ability of Claude to do this was not revealed until the other journalists had gone public and confirmed the identity.)
For example, if the prompt is something like "give me a cocktail that is most likely to succeed in this specific phase three trial" there are any number of ways the AI might find ways to game specific features of the trial design.