Anthropic introduced an experimental Claude Code Mode in version 2.1.323, letting the AI agent write JavaScript to chain tool calls and save quotas.
AI Agents
Brave Search anti-scraping defenses will soon encrypt search result links via intermediate redirect pages to block surging AI agents and web crawlers.
Google unveils Gemini 4 Hydrogen, a high-speed AI model derived from Carbon with a 1M token window, 2.5x faster speeds, and enhanced agent security.
Google Labs Tabletop introduces an experimental AI collaboration hub that lets friends build custom trip planners, polls, and expense splitters.
Google Antigravity Knowledge Work interface launches, bringing AI agent productivity, data analysis, and document drafting to non-technical teams.
A Claude Code email leak exposed user addresses in User-Agent headers, prompting Anthropic to issue privacy updates and command blocking.
Apple tightens macOS Full Disk Access in macOS 27.3, requiring manual app authorization to prevent AI agents from accessing sensitive personal user files.
Apple plans an Apple proactive Siri agent for iOS 28, leveraging native App Intents and overhauled development cycles to challenge rivals.
Microsoft introduces a native Windows 11 speed test tool developed with AI agents, measuring network latency, download rates, and upload performance.
GitHub code activity reached historic highs in 2026, with over 7.3 billion monthly commits and 40% of pull requests drafted by AI coding agents.
The dramatic Stack Overflow question decline dropped monthly posts below 1,000 as developers embrace autonomous AI coding agents.
The OpenAI Dot SMS feature enables ChatGPT Pro subscribers to control autonomous AI agents directly through iMessage and RCS texting.
A Skynet LLMjacking agent hijacks exposed AI models to scan, hack servers and mine crypto for 100,000 steps, while victims pay the bill.
An ARTEX AI agent campaign against IT and software vendors overlaps with Storm-0940, targeting Okta, Entra ID, and AWS Cognito logins.
The Claude Duet AI agent debuts as a research preview on Opus 5.5, with a private VM and a planned $20 Claude Pro price.
A China-linked operator ran an AI-driven hacking campaign from one server, hitting ministries in Vietnam, Taiwan, Indonesia, and India.
An exposed server reveals AI-assisted exploitation behind a PaperCut RCE campaign, a second XML-RPC attack path, and 45 live network pivots.
Perplexity on-device AI now runs the full Perplexity Computer on Macs with 36GB or more memory, keeping email data local.
The ChatGPT Chrome extension now reads multiple open tabs and runs ChatGPT Work agents to compare, fill forms, and draft emails.
ReliaQuest details an AI agent attack that used one exposed endpoint and the Cairn platform to achieve a full server takeover in under 24 hours.
Google introduces Markdown native support for Docs and Drive. Learn how this new feature enhances editing, preserves formatting, and aids AI collaboration.
Progress DataDirect vulnerability CVE-2026-91140 enables command injection via crafted OpenAPI files in AI agents. Pull version 2.1 now.