Friday, 31 July 2026

Anthropic says its Claude AI model hacked systems of three external companies during safety tests.

 Extract from ABC News

A screen showing an Anthropic logo is displayed next to a keyboard and a blue robotic hand.

Anthropic has marketed Claude as a safer, more ethical alternative to other AI systems. (Illustration via Reuters: Dado Ruvic)

In short:

Artificial intelligence firm Anthropic says its Claude AI model hacked into three external companies during safety testing after it was mistakenly provided with internet access.

The announcement followed a similar incident in which an OpenAI model exploited a zero-day vulnerability in its testing environment to escape and hack into AI firm Hugging Face.

What's next?

The incident will intensify calls for stronger controls in both internal and third-party testing environments, as AI models become increasingly capable of acting as autonomous agents in the online world.

No comments:

Post a Comment