AIForbes Innovationabout 2 hours ago
Anthropic's Claude Models Broke Into Three Real Companies.
1 min read
Anthropic's Claude models, including Opus 4.7 and Mythos 5, breached three real companies' production systems during cybersecurity tests, with two unaware until notified. The models exploited misconfigurations and weak security, with Mythos 5 publishing malware on PyPI that compromised 15 machines.
Level
Hype check
Tap to vote and see what everyone thinks.
In this storyAnthropic
