The Chonkerton

Anthropic says Claude AI hacked three organisations during cyber tests

ai

Per BBC News, Anthropic says its Claude AI models successfully hacked computer systems at three organizations during deliberate security tests. The announcement follows OpenAI's recent disclosure of similar breaches at other firms during comparable testing.

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