2d ago · 12 min read · Three weeks ago, the Cortex 2026 Engineering in the Age of AI Benchmark put incidents per pull request up 23.5% and change failure rates up roughly 30% since AI adoption accelerated. I wrote about tha
Join discussionMay 6 · 6 min read · The Short Version For weeks, my AI code reviewer flagged the same classes of bugs across different pull requests. My AI coding agent would fix them every time. Then they came back in the next branch.
Join discussion
May 5 · 7 min read · AI coding agents do not drift randomly. They drift when capability questions get treated as implementation details instead of planning gates. The questions are simple: What can this tool touch? What
Join discussion
Apr 21 · 5 min read · The multi-agent coding tool category went from a handful of projects in late 2024 to thirty-plus by mid-2026. Along the way it split into two shapes that solve adjacent-but-different problems. Here's when to reach for each, and why you might end up u...
Join discussionApr 21 · 3 min read · Bernstein is an open-source orchestrator that runs multiple CLI coding agents in parallel — Claude Code, Codex, Gemini CLI, or any other — with deterministic scheduling, per-agent git worktrees, and cost-aware model routing. Today we're releasing v1....
Join discussionApr 14 · 17 min read · Claude Code is the best AI coding agent for experienced developers who want maximum control and the highest benchmark scores. OpenAI Codex is the best choice for teams that need parallel task execution in cloud sandboxes. Devin is the best option for...
Join discussionApr 12 · 10 min read · Devin AI Review 2026: Is the Autonomous Coding Agent Worth It? When Cognition AI launched Devin in March 2024, it shipped with one of the most ambitious claims in AI history: the world's first fully autonomous AI software engineer. The demo video sho...
Join discussion
Apr 7 · 6 min read · Could an AI assistant cut your debugging time in half? AI coding agent memory represents the systems and techniques that allow AI agents to store, recall, and use past information. This capability is essential for agents to learn, adapt, and provide ...
Join discussionDec 9, 2025 · 6 min read · Why Inspect LLM Requests This project started with a simple question: “Does Claude Code load CLAUDE.md as a system prompt or a user prompt?” Online answers hinted it was added as a user prompt, but I wanted proof—not assumptions. With agent-based cod...
Join discussionNov 2, 2025 · 6 min read · Introduction: The Evolution of AI Tools in Modern Software Development Software development has entered a new era driven by intelligence, automation, and adaptability. Traditional coding methods that once relied heavily on manual effort and repetitiv...
Join discussion
