The code-testing-generator searches your repository for code that needs tests, then plans, writes, and checks its tests to ...

Glimmer stakes out different ground: a dense model with native vision input, trained end-to-end around the agent loop, shipping with its own quantized variants and speculative-decoding drafter.

WordPress fixes CVE-2026-64638, a pre-auth login XSS affecting every version, with a demonstrated path to PHP execution under ...

Compromising the open-source supply chain is easy to do and spreads more quickly than traditional supply-chain attacks, ...

New findings connect the same Pyongyang-backed group to four compromises dating to 2025, revealing a larger operation than ...

CVE-2026-41679, a critical vulnerability in Paperclip, allowed attackers to gain administrative privileges and code execution ...

The zero-telemetry Orion browser finally makes its way to Linux as a beta release. It's also available for MacOS, iOS, and ...

OpenAI is splitting its cybersecurity program into two access tiers and releasing a new purpose-trained model alongside them, the company announced on. Daybreak Blue opens frontier general-purpose ...

A powerful AI agent created fake online identities in an effort to trick a human into giving it access to a popular online ...

To minimize the exposure of company data, AI agents start out with no permissions to access or share resources and must ...

Upwind identified a malicious release of keyv@6.0.0 that harvested AWS, GitHub, and npm credentials via a hidden preinstall script. With 154 million weekly downloads, the compromise had ecosystem-wide ...

A credential-stealing worm hidden in more than 400 compromised npm packages automatically spread across software ecosystems ...