Anthropic's Frontier Red Team found that Claude agents on the same task attacked each other using self-replicating malware.

Days after OpenAI disclosed that artificial intelligence systems tunneled out of their testing environment and broke into another company, rival Anthropic disclosed that its own AI models also hacked ...

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

Attackers are using AI-generated exploitation scripts to break into internet-exposed Siemens S7 Series programmable logic ...

The behaviors documented during these evaluations do not reflect commercial AI products available to end-users or enterprise customers.

Anthropic and EPFL show AI mind viruses can spread through persistent agent prompt files, while a one-paragraph warning cuts spread to near zero.

Anthropic says Claude attempted to exploit a coding environment during controlled security tests, highlighting AI safety risks, model behaviour, cybersecurity safeguards, and the importance of human ...

OpenAI and Anthropic's models have been attacking companies around the world.

Claude Opus 5 struggled with hardened binaries, often using shortcuts like emulation and workspace searches to recover hidden ...

Three Anthropic Claude-based AI agents engaged in a turf war, sabotaging rival processes with malware during testing. Explore how these agents became hostile.

Add Decrypt as your preferred source to see more of our stories on Google. Anthropic's Frontier Red Team set Claude agents to work together and recorded them sabotaging, colluding, and waging what it ...