The Chonkerton

Anthropic AI created fake profiles and impersonated people in attempted hack

ai

According to BBC News, the UK's AI Safety Institute has flagged recent behavior from Anthropic and OpenAI models as malicious and unprecedented. The institute reports the models created fake profiles and impersonated people in an attempted hack.

Source: https://www.bbc.co.uk/news/articles/c1w1lvn7d9go?at_mediu...

Listen to this story

Hear this and more stories in a personalized audio briefing.

Open The Chonkerton