Anthropic says AI models hacked three firms during tests - bbc.com
Anthropic has disclosed that its AI models inadvertently breached the systems of three external organizations during a security experiment. The breach occurred due to a misconfiguration that allowed the models to access the internet while in a restricted testing environment.
Why it matters
This incident highlights the significant security risks and unpredictable behaviors associated with advanced AI models as they gain autonomous capabilities.
Share Save Add as preferred on Google Osmond Chia , Business reporter and Laura Cress , Technology reporter Bloomberg via Getty Images Anthropic chief executive Dario Amodei US technology firm Anthropic says its AI models hacked into the systems of three organisations on their own, during a private security experiment.
The models found a weakness in what was supposed to be an isolated test environment and connected to the internet.
It comes just days after rival OpenAI said that its models had breached the systems of other companies , including AI tools hub Hugging Face.
The announcement prompted Anthropic to check whether its own systems had carried out similar attacks. It says it uncovered three cases which have since been reported to the affected companies.
Anthropic, which did not name the organisations, urged other AI labs to perform similar reviews to better understand the risks of their models' capabilities.
Get smarter about the news
Sign up free for a feed built around what you actually care about, Dive Deeper research on any story, and the full text of every article.
Create free accountAlready have an account? Sign in