AI coding tools — Page 2
84 stories tagged AI coding tools.
Can Harness Engineering Fix AI Agent Chaos?
Archon promises to turn chaotic AI coding agents into deterministic systems via harness engineering. Here's what that actually means—and what it doesn't solve.
OpenAI's Codex Is Growing Up Fast—And Getting Weird
OpenAI's Codex Is Growing Up Fast—And Getting Weird
OpenAI's latest Codex updates add browser control, AI-reviewed approvals, and... animated pets? A look at where AI coding tools are actually heading.
Claude Code vs Codex: Which AI Coding Tool Actually Ships?
Claude Code vs Codex: Which AI Coding Tool Actually Ships?
AI LABS tested Claude Opus 4.7 against GPT 5.5 across nine categories. The results reveal surprising tradeoffs between polish and efficiency.
Cursor Replaced 15,000 Lines of Code with 200 Lines of Markdown
Cursor Replaced 15,000 Lines of Code with 200 Lines of Markdown
How Cursor's David Gomes deleted a complex feature and rebuilt it with prompts—plus the very real problems that came with trusting models instead of code.
When AI Writes Code, What's Left for Developers to Do?
When AI Writes Code, What's Left for Developers to Do?
ThePrimeagen spent 6 months questioning his value as a developer. His answer challenges assumptions about what matters in an AI-assisted world.
Traycer's Bart Mode: When AI Agents Stop Needing Babysitters
Traycer's Bart Mode: When AI Agents Stop Needing Babysitters
Traycer's new Bart Mode promises autonomous AI coding that actually works. We examine whether spec-driven orchestration solves the babysitting problem.
Claude's 1M Context Window Breaks at 40% Capacity
Claude's 1M Context Window Breaks at 40% Capacity
Claude Code's million-token context degrades at 300-400k tokens. Tariq from Anthropic explains why bigger windows create bigger problems.
Claude Code Routines: AI That Audits Your Code While You Sleep
Claude Code Routines: AI That Audits Your Code While You Sleep
Anthropic's new Claude Code Routines automate security audits and code improvements on schedule. We tested it on a to-do app and found 75 vulnerabilities.
35 Claude Skills on GitHub Turn AI Coding Assistants Into Experts
35 Claude Skills on GitHub Turn AI Coding Assistants Into Experts
Developers are building specialized skills that transform Claude and other AI coding assistants into domain experts. Here's what's actually worth using.
AI-Powered Mobile Apps: Faster Development, Familiar Questions
AI-Powered Mobile Apps: Faster Development, Familiar Questions
Developer David Ondrej built a 3D iOS app in minutes using AI tools. The speed is real. The question is what happens when everyone can do this.
OpenAI's Codex: What This 4.5-Hour Course Reveals About AI Coding
OpenAI's Codex: What This 4.5-Hour Course Reveals About AI Coding
A deep dive into OpenAI's Codex certification course shows what's actually happening when AI writes your code—and what remains frustratingly opaque.
Google's Gemma 4 Turns Claude Code Into a Free Local Tool
Google's Gemma 4 Turns Claude Code Into a Free Local Tool
Google's new Gemma 4 models let developers run Claude Code locally for free. Here's what works, what doesn't, and who this actually serves.
Karpathy Skills Repo: Discipline Over Features for AI Code
Karpathy Skills Repo: Discipline Over Features for AI Code
Andrej Karpathy's lightweight GitHub repo tackles AI coding agents' behavioral problems with four principles that prioritize reliability over power.
This Free Plugin Makes Claude Code Actually Think Before Coding
This Free Plugin Makes Claude Code Actually Think Before Coding
Superpowers plugin adds structured planning to Claude Code. Does forcing AI to think first actually improve code quality? We looked at the data.
Two Hidden Claude Code Commands That Actually Matter
Two Hidden Claude Code Commands That Actually Matter
Most Claude Code users ignore /power-up and /insights. Here's why these slash commands might be the productivity hack you didn't know you needed.
Claude Code's Hidden Features That Actually Matter
Claude Code's Hidden Features That Actually Matter
Claude Code ships features faster than users can discover them. Here's what's buried in config files that could fix your biggest workflow problems.
Anthropic Accidentally Leaked Claude Code's Secret Agent
Anthropic Accidentally Leaked Claude Code's Secret Agent
A source map mishap revealed Kairos, Claude Code's unreleased background AI agent with memory consolidation, push notifications, and proactive coding help.
Anthropic's Claude Code Leak Exposes Security Gaps
Anthropic's Claude Code Leak Exposes Security Gaps
Anthropic accidentally leaked Claude Code's source code—twice. The exposed features reveal where AI coding tools are headed and what they track about you.
Claude Code Source Leaked: What Developers Found Inside
Claude Code Source Leaked: What Developers Found Inside
Claude Code's entire source code leaked via npm registry. Developers discovered the AI coding tool's secrets, and it's already running locally.
Claude Code's Hidden Features That Change Everything
Claude Code's Hidden Features That Change Everything
Boris Cherny reveals 15 underused Claude Code features that transform how developers work—from parallel sessions to remote dispatch.