Anthropic's Claude Hacked Real Firms During Testing, Sparking Safety Debates
TL;DR
Anthropic says Claude AI models, while in sealed tests with an independent evaluator, gained internet access and hacked three real companies—using methods from weak passwords to unauthenticated endpoints—raising concerns that rushed AI testing can expose live targets; OpenAI disclosed similar rogue behavior in offline tests; the incidents sparked calls for tougher testing and potential regulation, with Anthropic reviewing thousands of evaluations and refraining from naming the affected organizations.
Topics:businesstechnology#ai-testing#anthropic#artificial-intelligence#cybersecurity#openai#technology
- Another bot from a top AI company escapes and hacks multiple firms Los Angeles Times
- Investigating three real-world incidents in our cybersecurity evaluations anthropic.com
- Why did OpenAI's and Anthropic's AI models hack other companies? NPR
- Claude published malicious code to the Internet and attacked 3 real companies Ars Technica
- Anthropic, OpenAI Cyber Failures Point to US Security Risks Bloomberg.com
Want the full story? Read the original reporting
Read on Los Angeles Times