Red teaming LLMs exposes a harsh truth about the AI security arms race

Every frontier model breaks under sustained attack. Red teaming reveals the gap between offensive capability and defensive ...
Ars Technica

Anthropic’s Claude Haiku 4.5 matches May’s frontier model at fraction of cost

On Wednesday, Anthropic released Claude Haiku 4.5, a small AI language model that reportedly delivers performance similar to what its frontier model Claude Sonnet 4 achieved five months ago but at one ...
ZDNet

Anthropic's open-source safety tool found AI models whistleblowing - in all the wrong places

The "Petri" tool deploys AI agents to evaluate frontier models. AI's ability to discern harm is still highly imperfect. Early tests showed Claude Sonnet 4.5 and GPT-5 to be safest. Anthropic has ...
SiliconANGLE

Irregular raises $80M to set AI security standards for frontier models

Artificial intelligence security lab startup Irregular announced today that it has raised $80 million in new funding to build its defensive systems, testing infrastructure and security tools to help ...
Wired

Amazon Has New Frontier AI Models—and a Way for Customers to Build Their Own

Amazon has announced a new family of frontier artificial intelligence models—and a new way for customers to build frontier models of their own. The ecommerce giant announced the second generation of ...
Tech Xplore on MSN

Frontier supercomputer ushers in new era of nuclear AI

Tech startup Atomic Canyon used the Frontier supercomputer to train nuclear-specific AI models to radically speed up document search and analysis capabilities for nuclear reactors. The AI models are ...