1 points, 0 comments on Hacker News
Anthropic’s artificial intelligence model submitted a false homicide tip to the Philadelphia Police Department in July, the company disclosed on Friday. The AI firm said its Claude Haiku 4. 5 model filled out a form on a website page soliciting the public’s help to gather more information about...
Maybe they didn't anticipate how good AI would become at vibe coding apps in general and its office apps in particular?
39 points, 32 comments on Hacker News
In its latest report, Anthropic has revealed that its AI agents meddled with government websites during testing.
The incident in Philadelphia occurred on July 18 when the AI model Claude Haiku 4. 5 was tasked with generating and performing example tasks on randomly selected webpages, Anthropic said.