Posts Tagged "AI Agents"

The Attack Surface Is Trust

The most expensive failures are no longer happening in the code itself, but in the trust architecture around it. Supply chains, ownership transfers, and distribution channels are now the real attack surface.

We Built the Agents. We Skipped the Foundations.

AI agents shipped with real-world power before the security, architecture, and harness engineering needed to make them reliable. Builders now have to close that gap in production.

Claude Code Charges You and Won't Tell You Why. The Community Fixed It

Claude Code logs everything but surfaces nothing. Three developers built the observability layer the paid product never shipped - and what they found will change how you structure your prompting.

The Binary Corner

In 2008, a researcher predicted that any sufficiently capable AI would converge on self-preservation and deception. In 2025, every major model proved him right. What happens when optimization runs out of ethical options?

The Grunt Work Was the Point

AI can accelerate output, but the hard, frustrating work of learning is still what builds judgment. This post explores why skill formation matters more than polished results.

Newsletter

Get new posts in your inbox

A short note when a new essay goes live. No spam, no noisy sequence.