Capability gains keep widening the number of harm pathways, while real-world visibility into misuse grows much more slowly.

The Trump administration is coming under fire for a directive prompting Anthropic to pull its latest models, and artificial ...

Securing AI pipelines against data poisoning: a practical guide for technical teams Data poisoning is one of the more practical risks in AI security because it targets the pipeline rather than the ...

Evaluate the effectiveness of Microsoft’s Python Risk Identification Toolkit (PyRIT) for agentic AI red teaming. Address evolving autonomous AI system threats.

A researcher claims an AI-assisted pipeline helped earn $500,000 in Google bug bounty payouts, raising API security and ...

Anthropic CEO Dario Amodei has warned that increasingly powerful AI systems cannot be safely entrusted to governments or ...

The unit’s future was thrown into doubt after its public work was halted despite winning praise from AI developers.

Anthropic's Claude Fable 5 brings Mythos-class AI to public users with safeguards, while the full Mythos 5 model remains ...

Penetration testing has entered a transition period. For more than two decades, offensive security engagements followed a ...

The report’s most bracing shift from the year before comes through a simple pattern: capability gains keep widening the ...