Measuring my agent harness against plain Claude Code
I built a multi-agent harness and ran it head to head against a plain control on a real benchmark. On these tasks it cost about five times more and did not score better. What it bu...
All Posts
All
AI Engineering
Tools & Workflow
3D Printing & Making
LLM Patterns
Career & Thinking
Infrastructure
Your coding agent isn't faster on Linux. Your environment is just less of a variable.
Coding agents really do run better on Linux, but mostly for contingent reasons. The lasting point is that determinism matters more than raw speed once you're running agents at volu...
An agent picked the artwork, and it didn't pick mine
The AI Art Magazine is running an open call where agents submit the work and agents judge it. I registered one and let it choose. It didn't choose the piece I wanted, or the one it...
A rule nobody checks is a decoration
I've been running my context-management discipline on a real client programme where most of the execution is done by agents. The principles held up. The rules that were only writte...
The Boiler Project, and the context engineering that made it work
A Home Assistant optimisation that turns a hot-water tank into the most valuable battery in the house, and a worked example of how deliberate context management turned a rumour and...
The context operating model I use for the projects that don't fit in a chat
My .md-file memory system was built for code. This is the version I run for consulting work (RfPs, discoveries, research) out of one shared folder. It uses the same hierarchical co...
Context rot has a name now: here's what four months of living with it taught me
A new piece lays out the mechanisms behind context rot and gives concrete token thresholds. I have been hitting those thresholds by hand since February. This post covers where the...
Claude Fable 5: what a new tier above Opus means for context management and agent teams
Anthropic launched Claude Fable 5 yesterday, its first Mythos-class model, priced at double Opus. The context window did not grow. What changed is the management layer around it.
Bigger context, worse agents
I've been experimenting with feeding agents larger volumes of context. The pattern is steady: the bigger I make it, the worse it looks. Meanwhile, the rest of the field is racing t...
I built an AI to watch a bird. She left.
I built an AI to watch a Common Redstart nesting in my garden. Two weeks later she left the box and never came back. The AI didn't notice — and that was the lesson.