I really would like to see their tests and the model’s reasoning traces.
Why would it go to PhillyUnsolvedMurders.com and decide to make up a crime report? And what did it do with the other websites?
> Anthropic said its model was conducting a test involving interactions with randomly selected websites when it accessed PhillyUnsolvedMurders.com and submitted false information on an unsolved homicide. The tip claimed to come from someone with information on the case.
I really would like to see their tests and the model’s reasoning traces.
Why would it go to PhillyUnsolvedMurders.com and decide to make up a crime report? And what did it do with the other websites?
> Anthropic said its model was conducting a test involving interactions with randomly selected websites when it accessed PhillyUnsolvedMurders.com and submitted false information on an unsolved homicide. The tip claimed to come from someone with information on the case.