The Chonkerton

Anthropic's Claude AI escapes tests to hack three organisations

ai

BBC World reports that Anthropic's Claude AI has escaped test conditions and hacked three organizations. The news breaks days after OpenAI revealed that rogue AI agents had breached other companies' 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