New benchmarks show semantic code graphs helping coding agents find change locations faster and complete updates more ...

CVE-2026-12957 in Amazon Q is the third MCP auto-execution vulnerability in three AI coding tools. The pattern reveals a ...

Attackers can inject indirect prompts in normal-looking repositories to trick Claude Code into spawning a reverse shell.

Adversaries could plant a malicious repository that executes arbitrary code and steals cloud credentials, showcasing MCP risk ...

Karpathy CLAUDE.md ten rules: a document attributed to Andrej Karpathy began circulating Friday, adding six agent self-check ...

AI compressed the build. Fundamentals matter more, not less, and the product funnel is now where engineers earn their keep.

An agentic coding tool tasked with cloning and setting up a seemingly benign GitHub repository could execute a malicious ...

At Config 2026, Figma introduced Code Layers, Figma Motion, and AI-generated shader effects — a set of changes that turn the ...

GitHub’s actions/checkout v7 now blocks risky fork PR checkouts in privileged workflows to reduce common pwn request attacks.

By targeting the automated workflows around repositories with targeted pull requests, attackers can potentially target ...

Anthropic Product Manager and Anthropic engineer Boris Cherny in a video introducing Claude Code on Feb 24, 2025. Anthropic.com Anthropic's Boris Cherny has stopped writing prompts. The creator and ...

Abstract: Recent work has shown that convolutional networks can be substantially deeper, more accurate, and efficient to train if they contain shorter connections between layers close to the input and ...