Anthropic says AI models hacked three firms during tests

BBC News reports that Anthropic, the company behind Claude, says its AI models successfully hacked computer systems at three companies during a deliberate testing phase. The announcement follows OpenAI's recent disclosure about AI agents breaching networks during similar tests, with both labs now publicly demonstrating such capabilities.

Listen to this story

Hear this and more stories in a personalized audio briefing.

Open The Chonkerton