June 2, 2026
How I Sandbox AI Coding Agents
Running coding agents in full autonomy means giving them a shell with the permission prompts turned of, which is dangerous. This is the layered setup I use to do it anyway.
Read more
Blog
Thinking Out Loud
Insights on AI engineering, agentic systems, and design.
May 7, 2026
Asking Claude to Help Me Replace Claude
Two days of debugging a local coding agent on a single RTX 4090, and why open-weight models are closer to ready than they look but harder to get there than they should be.
Read more
May 7, 2026
Training the Machine That Replaces You
Meta, layoffs, and the backward feedback loop of AI labor
Read more
May 4, 2026
The Missing Rungs
Fewer juniors today means fewer experts tomorrow. The math doesn’t fix itself.
Read more
April 27, 2026
The Loop Collapsed
When feedback is instant, methodology dissolves. Knowing when you’ve converged versus when you’re thrashing. That’s judgment, and it remains scarce
Read more
April 13, 2026
The Agent Security Stack
Sandboxes, credential proxies, and human-in-the-loop protocols — the three layers emerging to make AI agents actually trustworthy.
Read more
April 9, 2026
The Paradox of AI Adoption
Developers continue using tools they don't trust because the alternative feels worse than the problem.
Read more
April 7, 2026
The Benchmark Trap
Why the most reliable AI models for production workflows aren't the ones topping the leaderboards
Read more
March 31, 2026
The Integration Trap
OpenAI's simultaneous push into vertical integration and plugin architecture reveals the fundamental tension between control and ecosystem growth that will reshape AI development tools
Read more
March 30, 2026
The Skill Inversion
We're not just changing how we write code, we're inverting which skills matter, and most people haven't noticed yet.
Read more
March 26, 2026
The Quality Valley
Most developers are using AI tools they can’t effectively direct, and we’re about to find out what that costs.
Read more
March 25, 2026
The Definitions Do the Work
Vendors and evaluators agree on what coding agents can do, they just defined "complex" differently and hoped no one would notice.
Read more
March 24, 2026
The Cognitive Load You Didn't Trade Away
The shift from writing code to managing AI agents doesn't reduce mental effort. It replaces the satisfying strain of building with the draining vigilance of supervision.
Read more