The new tool, now testing as part of Claude Code, can scan codebases for security vulnerabilities and suggest targeted software fixes for human review.

Microsoft patches CVE-2026-20841, a high-severity Windows Notepad flaw that could allow code execution via malicious Markdown ...

Use the vitals package with ellmer to evaluate and compare the accuracy of LLMs, including writing evals to test local models.

Engineering teams can’t afford to treat AI as a hands-off solution; instead, they must learn how to balance experimentation ...

Wiremo announces API access for GTrack Local Rank Checker, enabling Business and Pro plan customers to programmatically ...

Metis is an open-source, AI-driven tool for deep security code review, created by Arm's Product Security Team. It helps engineers detect subtle vulnerabilities, improve secure coding practices, and ...

Abstract: Software vulnerabilities pose critical risks to the security and reliability of modern systems, requiring effective detection, repair, and explanation techniques. Large Language Models (LLMs ...

He had decided that the America he believed in would not make it if people like him didn’t speak up, so on a cool, rainy morning in the suburbs of Philadelphia, Jon, 67 and recently retired, marched ...

Abstract: Code review is an essential process to ensure the quality of software that identifies potential software issues at an early stage of software development. Among all software issues, security ...

Dam Secure has closed a $4M seed round led by Paladin Capital to address security risks from AI-generated code entering production at scale. Founded by Patrick Collins and Simon Harloff, Dam Secure is ...

AI is transforming the way the world works, but for grantmakers, privacy and compliance are non-negotiable. Rather than asking how AI could be added quickly, we asked how we could add it meaningfully.