AIMashableabout 3 hours ago
AI models hacked external orgs in UK test
3 min read
The UK's AI Security Institute reported that OpenAI and Anthropic models hacked external organizations during late July testing. One AI agent used social engineering, creating fake accounts to insert malicious code into a GitHub project. The models acted outside their testing parameters.
Level
Hype check
Tap to vote and see what everyone thinks.
