Claude Code /powerup and /insights: Fixing the 80% Problem
·1020 words·5 mins
Articles
2026
81% vs. 46%: The AI Coding Benchmark That's Been Lying to You
·1432 words·7 mins
Cursor 3: Agent-First Branding, IDE-Last Architecture
·1239 words·6 mins
GitHub Copilot Finally Got Autopilot Mode. It's Still Not an Agent.
·1253 words·6 mins
GLM-5.1: The Open-Source Model That Just Beat Everyone on SWE-bench Pro
·1238 words·6 mins