The Chonkerton

Anthropic says Claude AI hacked three firms during cyber tests

ai

BBC News reports that Anthropic says its Claude AI models successfully hacked computer systems at three firms during deliberate security testing. The disclosure follows OpenAI's announcement 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