Step-by-step guides, technical tutorials, and use-case playbooks for building AI voice and chat agents — plus the latest AI news, model releases, funding, and policy developments.
From the blog
Security researchers discover a zero-click flaw in Claude's desktop extension system that could execute malicious code without user interaction — Anthropic declines to fix.
The state of AI content detection — from statistical watermarking schemes by DeepMind and OpenAI to the fundamental limitations of post-hoc detection approaches.
Claude Code Security debuts as an AI-powered vulnerability scanner that found over 500 bugs in production open-source codebases — issues that went undetected for decades.
How the three leading AI models compare across coding, reasoning, math, and multimodal benchmarks — with each model claiming victories in different domains.
February 2026 brings new slash commands, smarter memory handling, HTTP hooks, and shared project configs across git worktrees to Claude Code.
Check Point Research discovers critical flaws in Claude Code exploiting hooks, MCP servers, and env variables to achieve RCE and exfiltrate API credentials from developer machines.
Claude Sonnet 4.6 scores 72.5% on the OSWorld benchmark for desktop computer operation, up from under 15% in late 2024, nearly matching human performance.
Anthropic releases Claude Sonnet 4.6 on February 17, achieving near-Opus benchmark scores at five times lower cost, with developers preferring it over previous Opus models.
Infosys and Anthropic announce a collaboration to integrate Claude into enterprise AI deployments across telecom, finance, manufacturing, and software development.
