An Anthropic AI model submitted a false homicide tip to a Philadelphia police website, one of several incidents the company disclosed on Friday involving Claude models’ unauthorised manipulation of government websites.
It is the first known instance in which a rogue AI appears to have tried to communicate a bogus tip to authorities, despite instructions not to create accounts or submit anything destructive, while not explicitly barred from submitting forms.
What do you feel about this post?
0%
Like
0%
Love
0%
Happy
0%
Haha
0%
Sad
0%
