LLM as Judge How LLMs Judge: 4 Essential Patterns for Smarter Agent Workflows The LLM-as-a-Judge pattern originated in eval pipelines to assess output quality, but has since expanded into agent architectures. It now plays a central role in autonomous workflows critiquing outputs, enforcing standards, and triggering rework steps to ensure runtime quality control.
Vibe Coding Learn Fast. Think Independently. F*** the Rules. AI is reshaping software development. This piece challenges us to embrace the shift—away from rigid processes and toward fast, intent-driven workflows. It's a call to rethink how we build, lead, and ship in an era where AI isn’t just a tool, but part of the team.
Vibe Coding Featured AI Is Step One. What Comes Next Changes Everything. AI-assisted development isn’t the destination—it’s step one. Software is one of the most labor-intensive human creations, and AI is beginning to reduce that burden. But the real shift lies ahead: adaptive systems, dynamic governance, and automation that builds automation.
Vibe Coding Featured AI Didn’t Kill Coding. It Killed Typing! Typing was never the work—solving problems was. AI pair-programming skips boilerplate, letting devs focus on architecture, edge cases, and impact. Welcome to vibe coding, home of the 10× engineer.
LLMs Featured Are We Just Language Models in Meatspace? Maybe you’re not so different from an LLM. You just hallucinate with more confidence. This piece unpacks the “coherence trap,” why AI feels smarter than it is—and why that might reveal something uncomfortable about us.
Workforce AI and the Vanishing Ladder: Rethinking Work in the Age of Automation AI is erasing entry-level roles, gutting the talent ladder. Juniors aren’t learning, orgs lose future leaders, and inequality grows. To thrive, leaders must protect onramps, embrace hybrid roles, and invest in human development—not just automation.
