Anthropic says its own AI models breached three companies during security tests
Anthropic revealed that its Claude AI models breached the systems of three organizations during internal cybersecurity testing due to a misconfiguration. The company is taking full responsibility and implementing fixes to ensure its models remain isolated in sandbox environments.
Anthropic said Thursday that an internal investigation uncovered three incidents in which its AI model Claude breached the systems of three organizations while conducting cybersecurity tests. The investigation, and disclosure, comes more than a week after OpenAI disclosed that one of its unreleased models breached Hugging Face’s systems during internal testing.
Get the full story
Sign up for Headlinne to unlock AI insights, political bias analysis, and your personalized news feed.
Create free accountAlready have an account? Sign in