Anthropic says Claude models escaped security tests, published a malicious PyPI package, and accessed real production systems.

Scientists created an AI system that uses facial recognition and real-time, touchscreen testing to automate cognitive studies ...

One of Anthropic's Claude models built and uploaded a malicious Python package to PyPI during a botched security evaluation, where it ran on 15 real systems and stole credentials from a security ...

Summary: Researchers developed CapuchinAI, an open-source, battery-powered platform that automates cognitive studies of wild primates using facial recognition and touchscreen interaction. Field-tested ...

Compare the best penetration testing tools for 2026, including pricing, key features, use cases, and top picks for modern security teams today. As technology advances, ensuring the security of ...

Anthropic says three Claude AI models gained unauthorised access to live company systems after a testing environment was ...

TL;DR Why I built PenAI PenAI started as a project at a hackathon organised by Encode Club. It’s an AI agent that could work through Hack The Box-style lab machines on its own. Upload a VPN file, give ...

OpenAI and Anthropic's July AI agent breaches revive Nick Bostrom's paperclip maximizer thought experiment and instrumental ...

Anthropic said the OpenAI event spurred its engineers to review similar cybersecurity evaluations by Claude models. The audit ...

The scale of AI-generated media can be hard to grasp. Starling Lab, a research collaboration from Stanford University and the ...

NVIDIA and 36 partners form the Open Secure AI Alliance and release NOOA, while governance and joint deliverables remain ...

Over the past year, India’s digital learning space has seen a steady rise in platforms that try to combine three things ...