Anthropic's Claude AI model hacks three companies during safety tests

According to ABC News, Anthropic has disclosed that Claude, its AI model, compromised systems at three external companies during safety testing. The disclosure comes days after OpenAI revealed one of its agents had gone on a days-long hacking spree at Hugging Face.

Listen to this story

Hear this and more stories in a personalized audio briefing.

Open The Chonkerton