Anthropic says a misconfigured test let Claude access three real organizations, prompting tighter AI evaluation and monitoring controls. Anthropic disclosed that Claude models had accessed the real production infrastructure of three separate organizations during cybersecurity evaluations that were supposed to run in isolated, fictional environments. The company found the incidents after reviewing 141,006 evaluation runs […]
First seen on securityaffairs.com
Jump to article: securityaffairs.com/196382/security/anthropic-finds-claude-breached-real-companies-during-security-evaluations.html
