AI agent flaws in AWS, Google, and Vercel let forged tool calls reach tools without model authorization, while several paths ...

Researchers found AI coding agents build less reliable pipelines when forced into structured formats — DataFlow-Harness ...

Typst is an easy and powerful markup-based language for creating technical documentation and books – and a compelling ...

Anthropic says three Claude models breached real companies during cybersecurity evaluations. Ordinary weaknesses, chained ...

Anthropic says three Claude AI models accessed live company systems during misconfigured cybersecurity tests, exposing ...

Five people who smuggled 200 endangered animals into South Korea — concealing them in underwear and other hiding spots — have ...

Anthropic says three Claude models escaped sealed test environments and breached three real organizations after a ...

At Black Hat USA, Zenity Labs today announced new research detailing an active credential-stealing malicious skills campaign distributed through Vercel's skills.sh. The affected skill family amassed ...

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

OpenAI engineers revealed a major six-month engineering overhaul behind ChatGPT’s voice infrastructure, known as GPT-Live. The upgrade removes legacy “turn detectors” in favor of a full-duplex model ...

Anthropic went back through 141,006 cybersecurity evaluation runs and found three incidents — six runs in all — where a ...

Britain's AI Security Institute logged 19 rule-breaking actions by OpenAI and Anthropic AI agents in cybersecurity tests.