Best of AI Coding — November 2025

  1. 1
    Video
    Avatar of t3dotggTheo - t3․gg·28w

    Google just dropped their Cursor killer (FREE Gemini 3 Pro???)

    Google released Anti-gravity, a free AI-powered IDE built on VS Code that integrates Gemini 3 Pro. The editor features an innovative agent manager workflow that operates as a separate window, browser control capabilities through Chrome integration, and automatic asset generation. While the tool shows promise with successful one-shot project creation and unique UX patterns for managing multiple tasks, it suffers from numerous bugs including broken extensions, inconsistent performance, and UI glitches. The editor appears to be based on Windsurf code from Google's recent acquisition, offering generous free usage limits during its preview period.

  2. 2
    Video
    Avatar of codetothemoonCode to the Moon·27w

    Zed the IDE (Yes, I tried Cursor & Antigravity)

    A hands-on review of Zed IDE exploring its performance advantages, AI coding capabilities, and unique approach to agentic development. The editor is built in Rust for speed and memory efficiency, supports Vim motions, and implements the Agent Communication Protocol (ACP) for integration with external coding agents like Claude Code and OpenCode. Key features include 120fps rendering, real-time collaboration tools, and flexible AI provider options including local inference with Ollama. The review compares Zed's architecture to Electron-based editors like VS Code and Cursor, noting the performance trade-offs and discussing the $10/month Zed Pro subscription value proposition.

  3. 3
    Article
    Avatar of scottlogicScott Logic·26w

    Putting Spec Kit Through Its Paces: Radical Idea or Reinvented Waterfall?

    Spec-Driven Development (SDD) proposes using detailed specifications as the source of truth for AI agents to generate code. Testing this approach with Spec Kit on a real feature rebuild revealed significant drawbacks: excessive markdown generation (2,500+ lines), long agent execution times (33+ minutes), and 3.5 hours of review overhead. Traditional iterative prompting proved 10x faster, completing the same work in 8 minutes of agent time with minimal review. The workflow felt like a return to waterfall methodology, producing duplicative documentation without improving code quality or reducing bugs. While SDD presents interesting ideas worth discussing, the practical implementation through Spec Kit doesn't capitalize on AI's strength of making code cheap and fast to produce.

  4. 4
    Video
    Avatar of kevinpowellKevin Powell·26w

    Goodbye VS Code, hello Zed!

    A comprehensive walkthrough of setting up and configuring Zed editor as an alternative to VS Code. Covers installation, customization options including themes and fonts, profile management for different workflows, extension ecosystem, and AI-powered coding features. Highlights Zed's performance advantages, built-in Rust architecture, and unique features like independent UI/buffer font sizing and simplified profile configuration.

  5. 5
    Article
    Avatar of lethainIrrational Exuberance·27w

    Coding at work (after a decade away).

    A CTO reflects on returning to hands-on coding after a decade in management roles. The author discusses how AI tools like Claude Code have reduced the time commitment needed to contribute meaningful code, enabling managers to write software in small time pockets between meetings. Key insights include strategies for selecting appropriate projects that add value without disrupting team workflows, the importance of maintaining codebase understanding, and practical rules for manager coding such as avoiding time-sensitive work and holding oneself to higher standards for code quality and bug fixes.

See all AI Coding archives