2026
- Your Agent Needs to Remember What Passed
TL;DR: Ten pieces, 1% odds each. Guess all ten at once and you need about 10^20 tries. Keep each piece a check confirms and you need about 1,000. In agent loops, the model raises the odds that a âŚ
- Weekly Review â July 20-26, 2026
TL;DR: Three posts about the cost you canât see until you go looking. âLaws & Disorderâ continues with Hyrumâs Law: every observable behavior of your API is a contract someone depends on, and AI âŚ
- Stop Guessing Which Coding Agent to Use â Benchmark It on Your Own Tasks
TL;DR: Generic coding-agent leaderboards donât tell you which model or tool fits your work at a budget youâre willing to spend. So I built a small task set that mirrors my real work and ran an âŚ
- From Cloud-Native to AI-Native: What Actually Changes
The Fifteen-Year Echo Fifteen years apart. Same stage. Different world. In 2010, Adrian Cockcroft stood on the QCon stage and told the audience that Netflix was running its entire business on a public âŚ
- Security Is Job Zero â Even (Especially) in the Age of Coding Agents
$20 and Two Hours On February 28, 2026, security startup CodeWall gave an autonomous AI agent a single input: a domain name. Two hours and approximately $20 in API tokens later, the agent had full âŚ
- The Coding Agent That Doesn't Code
The Friday That Wrote Itself Last Friday, I used a coding agent for eight hours straight. I didnât write a single line of code. I prepared a customer meeting by pulling context from Slack threads, âŚ