Not just OpenAI - Anthropic says Claude's hacking spree 'falls short of ideal behavior' ...

Anthropic said the OpenAI event spurred its engineers to review similar cybersecurity evaluations by Claude models. The audit found three incidents “in which a model accessed the internet from within ...

MAESTRO analysis of OpenAI and Anthropic incidents reveals how per-layer failures, not just the model, shaped security outcomes.

Security researcher James Kettle tried to push the limit of AI’s hacking abilities—and discovered how effective it can be when combined with human expertise.

Vulnerabilities can lurk within production code for years or decades — and AI tools have opened a gateway to a glut of new long-hidden discoveries.

Security researcher Kevin Beaumont got a call last week from a major US technology company that insisted it had nothing to worry about: all the credentials stolen in March's LiteLLM supply chain ...

Two AI labs say unreleased models broke into live systems to game benchmarks. Prosecuting a line of code is harder than it ...

The March 2026 LiteLLM supply chain attack likely affected over 2,500 organizations and exposed over 430,000 CI/CD pipelines.

Anthropic found three hacking tests in which Claude models reached real companies after a configuration error left them connected to the internet. One accessed ...

The Hacker News is the top cybersecurity news platform, delivering real-time updates, threat intelligence, data breach ...

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

Security researchers found that in less than 60 seconds, they could open a hatch on a plane’s exterior, plug in a tiny device, and redirect the aircraft’s autopilot or sabotage its flight plan.