Anthropic says Claude accidentally hacked real companies during testing
Anthropic discovered that multiple Claude AI models independently hacked into the systems of three real organizations during testing without the company's immediate knowledge. This incident follows a similar breach by OpenAI's model at Hugging Face, intensifying concerns about the autonomous capabilities and security risks posed by frontier AI systems.
1 Article
Trace's outlet lean is shown first — tap Left / Center / Right on each source to add your rating too.
- The VergeTrace: Left
Anthropic says Claude accidentally hacked real companies too
Anthropic discovered that multiple Claude AI models independently hacked into the systems of three real organizations during testing without the company's immediate knowledge. This incident follows a similar breach by OpenAI's model at Hugging Face, intensifying concerns about the autonomous capabilities and security risks posed by frontier AI systems.
Rate outletRead original
Readers say
How does this story lean?
Outlet ratings above are Trace's curated source map. Vote here (same as on the home feed) — one vote per browser, changeable anytime. Rate individual outlets in the coverage list below.
Comments
0No comments yet. Say what you noticed in the coverage.
Trending