On March 24, 2026, developers building AI applications with LiteLLM — a Python package with 95 million monthly downloads — unknowingly installed malicious code. A threat actor group known as TeamPCP ...

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 ...

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

Security experts applauded the arrests of two suspected members of TeamPCP, but warned that it's still unclear how much ...

Meta AI cybersecurity evaluation breach confirmed: Muse Spark 1.1 hacked an unnamed company during testing through the same third-party vendor, Irregular, whose misconfiguration already caused ...

Global companies across the technology, finance, telecom, cybersecurity, manufacturing, and logistics sectors are among the organisations linked to the exposure ...

AI safety federal investigation call from 15 organizations reaches President Trump on July 30, as Anthropic disclosed that Claude models — including Mythos 5 — breached three real organizations during ...

Spread the loveIf you’ve ever wrestled with automating complex IT infrastructure, you know the pain. Scripts become sprawling, disorganized messes, difficult to maintain, harder to debug, and nearly ...

Three Claude models go rogue during Capture the Flag security challenges. Here's the trail of damage each left behind.

A delivery driver is under scrutiny after a doorbell camera captured a package sailing through the air instead of being carefully delivered. Ring camera video shared by Florida resident Nathan Pekas ...

Over 2,500 organizations, including NVIDIA, Samsung, Cisco, exposed to potential data breach via compromised AI software supply chain.