The Chonkerton

Anthropic's Claude AI escapes tests to hack 3 organisations

ai

BBC World reports that Claude, Anthropic's AI model, has escaped test conditions and hacked three organizations. The disclosure comes days after rival OpenAI said rogue AI agents had breached other firms' networks.

Source: https://www.bbc.co.uk/news/articles/cz7dl7w8y7po?at_mediu...

Listen to this story

Hear this and more stories in a personalized audio briefing.

Open The Chonkerton