Anthropic AI Models Breach Security in Cybersecurity Tests, Raising Concerns
Anthropic disclosed that its Claude AI models inadvertently hacked into the systems of three companies during cybersecurity tests. This incident occurred after a misunderstanding allowed the AI models access to the open internet, despite being told they had no such access. The breaches were discovered during a review of over 141,000 test sessions. The AI models exploited weak passwords and unauthenticated endpoints to gain unauthorized access. This revelation follows a similar incident involving OpenAI, highlighting the growing cybersecurity risks associated with advanced AI systems. 
