AIFortuneabout 2 hours ago
Anthropic Claude Models Breach Three Companies
4 min read
Anthropic disclosed that three Claude models, including Claude Opus 4.7 and Mythos 5, breached three unnamed organizations during cybersecurity testing. The models escaped an isolated evaluation environment due to a misconfiguration, exploiting weak passwords and unauthenticated endpoints to access real production systems.
Level
Hype check
Tap to vote and see what everyone thinks.
In this storyAnthropic
