📝 Post
Apparently 32 PRs a Week Was Conservative
The models got better. Templates, context engineering, and dogfooding kept the projects from getting dumber.
📝 Post
My Day Job Is Unsupervising Agents
I gave my coding agents a Discord activity and accidentally made the scale of their work visible.
📝 Post
A Frustrating AI Code Smell: Every Problem Decomposes to a dataclass With Four Reasons
Turning messy evidence into a clean taxonomy before it has earned one.
📝 Post
If AI Coding Trends Continue, I’ll Be Merging 20 PRs a Day
I went from merging 3.4 personal PRs a week to 19.2. Extrapolate that another year and the math says 20 PRs a day. Yeah, right.
📝 Post
I Put My Dog in My Coding Agent
Pi made it easy to put a sprite version of my dog in the terminal, then bundle the small coding-agent features I wanted around it.
🔗 Link
Dogfooding Is the New Code Review
AI agents can ship code faster than humans can review it. Correct code still needs human time to become good software.
📝 Post
An Update on Codex's Gremlins
OpenAI explained why Codex kept talking about goblins. Of course it was reward hacking.
🔗 Link
There are Gremlins lurking in Codex GPT-5.5
Codex GPT-5.5 apparently needed an explicit, repeated reminder not to talk about certain creatures unless they are actually relevant.
🔗 Link
LLMs Are Cowboy Coding
Anthropic's harness engineering article highlights what's missing from most AI coding: scrutiny and evaluation.