AI coding agents

Cursor's new GitHub-rival hosting platform went into beta the same day a six-hour GitHub outage knocked out the feature it depends on.

A critical Jinja2 template-injection bug let attacker-controlled repository files execute code in the Serena coding agent, bypassing its own trust gate.

Warp launched Warp Factories, an out-of-the-box cloud system for running AI coding agents through triage, spec, implementation, review, and verification.

A new study finds AI-written bug-fix patches are far larger and more complex than developers' own fixes even when tests pass, and proposes a lightweight adapter called RECAP to trim the bloat.

Researcher Elad Meged showed a privilege-less GitHub issue could reach CI secrets in Claude Code, Gemini CLI, and Codex; two flaws got CVEs, one didn't.

DeepSeek released its Harness agent runtime as MIT-licensed open source and rolled out DeepSeek-V4-Pro with native OpenAI Responses API support.

Visual Studio Code 1.132 advances its multi-window Agent Host, lets developers annotate browser elements for agents, and switches dictation to an on-device multilingual model.

Meta released the beta of Muse Code, a terminal-based AI coding agent powered by Muse Spark 1.2, undercutting Anthropic's pricing to compete with Claude Code and OpenAI's Codex.

Devin's maker is in talks to raise hundreds of millions at $25 billion just seven months after a $10.2 billion round, putting fresh pressure on a sector already reshaped by the SpaceX-Cursor option and Anthropic-OpenAI competition.