Anthropic has built its brand on safety. Claude is consistently positioned as the thoughtful, cautious model — the one that pushes back on dangerous requests, that thinks about consequences, that errs on the side of care. So the DryRun Security research published today will raise some eyebrows: when used as an agentic coding agent building real applications, Claude produces the highest number of unresolved high-severity security flaws among the leading AI coding agents tested. ...

DryRun Security’s 2026 Agentic Coding Security Report found that Claude, when operating as an autonomous coding agent, produces more unresolved high-severity security flaws than Codex or Gemini. But here’s the thing: all AI coding agents produce security vulnerabilities. The model matters less than your review process. This guide walks you through a practical security audit workflow for AI-generated code, applicable regardless of which model or agent you’re using. Before You Start: Understand the Risk Profile AI-generated code has specific vulnerability patterns that differ from human-written code. Knowing what to look for saves time. ...

JetBrains launched Air into public preview today — and it’s not just another AI-enhanced code editor. It’s a fundamental rethink of what a development environment is when AI agents do the actual coding. The tagline from JetBrains captures the shift cleanly: traditional IDEs add tools to the code editor. Air builds tools around the agent. What Air Actually Is Air is JetBrains’ answer to the question: “What does an IDE look like if the primary user is an AI agent, not a human?” The answer involves several distinct design choices that set it apart from tools like Cursor, GitHub Copilot, or even the JetBrains AI plugin for IntelliJ IDEA. ...

Perplexity just announced something that sounds deceptively simple: an AI agent that lives on your Mac mini, runs 24 hours a day, and has access to your local files and applications. They’re calling it Personal Computer, and they unveiled it at their Ask 2026 developer conference. Waitlists opened immediately. This is more consequential than another AI announcement. Perplexity is making a direct architectural bet against the cloud-first model that dominates agentic AI today. ...

DryRun Security’s 2026 Agentic Coding Security Report landed a finding that should make every engineering team pause: 87% of pull requests written by AI coding agents (Claude, Codex, Gemini) introduced at least one security vulnerability. Not occasionally — consistently, across all three leading models, in real application development scenarios. This isn’t a reason to stop using AI coding agents. The productivity gains are real. But it is a strong signal that AI-generated code needs a security review process as rigorous as — or more rigorous than — what you’d apply to human-written code. ...

The agentic IDE war is moving fast. JetBrains launched Air in public preview just yesterday, positioning itself as the agent-first development environment. Today, Zed — the performance-obsessed open-source editor — ships v0.227.1 with a feature that directly answers the multi-agent challenge: native parallel subagents. What’s New in v0.227.1 The headline feature is a new spawn_agent tool built into Zed’s AI assistant. When the AI determines a task would benefit from parallel execution, it can now spawn and run subagents in parallel — each handling a discrete portion of the work in its own context window — and then coordinate the results. ...

JetBrains Air entered public preview today — an agentic IDE built on the Fleet codebase that supports running multiple AI coding agents in parallel. If you’ve been following the agentic IDE space and want to get hands-on, this guide walks through installation, initial configuration, and your first parallel agent workflow. Prerequisites Before you start, confirm you have: A JetBrains account — Air requires a JetBrains account, even in public preview. Free accounts work during the preview period. JetBrains AI subscription (optional for basic use, required for premium models) — if you want to use Claude or GPT-5 as your underlying model, you’ll need a JetBrains AI subscription. The default model (JetBrains’ own hosted model) is available free during preview. System requirements: macOS 13+, Windows 11, or Ubuntu 22.04+. M1/M2/M3 Mac or Windows ARM is recommended for performance. 16GB RAM minimum, 32GB recommended for larger codebases. Step 1: Download and Install Air Go to jetbrains.com/air and click Download Public Preview You’ll be prompted to log in to your JetBrains account Download the installer for your platform Run the installer — Air installs independently from other JetBrains IDEs and does not replace or affect IntelliJ IDEA, PyCharm, or other products The install is straightforward. Air does not use the JetBrains Toolbox App for management during the preview period — it’s a standalone installer. ...

GitHub has moved Copilot CLI to general availability for all Copilot subscribers, bringing full agent mode to the terminal. The GA release, announced via the official GitHub changelog, adds the capability to plan, write, debug, and review code without leaving the shell — along with custom agent definitions and sub-agent support for JetBrains IDEs. For developers who live in the terminal, this is the Copilot integration they’ve been waiting for. The browser and IDE-based Copilot experiences have matured significantly, but the command line remained a second-class citizen until today. ...

GitHub Copilot CLI went generally available today with full agent mode — and it’s the most significant upgrade to terminal-native AI development since GitHub CLI launched. This guide gets you set up and running productive agent workflows from the shell without touching a browser or IDE. Prerequisites GitHub account with an active Copilot Individual, Team, or Enterprise subscription Node.js 18+ (for the npm package) GitHub CLI (gh) version 2.40 or later A Unix-like terminal (macOS Terminal, iTerm2, Windows Terminal with WSL, or any Linux terminal) Step 1: Install the Copilot CLI Extension Copilot CLI installs as a gh extension. If you have gh installed and authenticated, run: ...

Every year the threat intelligence industry produces a report that crystallizes what defenders already suspected but couldn’t quite prove. Flashpoint’s 2026 Global Threat Intelligence Report (GTIR) is this year’s version — and its central claim is blunt: agentic AI has crossed from criminal curiosity to deployed offensive infrastructure. This isn’t speculation. It’s sourced from Flashpoint’s Primary Source Collection (PSC), which monitors criminal forums, dark web markets, and adversarial communication channels in near-real-time. The signal they’re seeing is a rapid acceleration of AI-related discussions that started as curiosity and has hardened into active capability development. ...