I spend most of my time on agentic systems, and I had absorbed the same idea everyone else has: a...
I spend most of my time on agentic systems, and I had absorbed the same idea everyone else has: a planner improves things, and a panel of drafters with a judge improves them further. It sounds obviously true. More thinking, more review, better answers.
I never measured it. So I built something that could, pointed it at my own setup, and it disagreed with me.
The result
One sweep. Twenty coding tasks, three harness shapes, real models, $0.99.
harness
I built a profiler to audit my own tool calls. After loading 157 skills in 12 days, I realized I had...
Two weeks ago, I published "Why Agent Evaluation Is Harder Than Model Evaluation." The core argument:...
Most multi-agent demos are impressive for five minutes and useless for five hours. After months of...
Building plan mode for an AI agent that takes real actions. Why I split the planner from the executor, made it research before it…
6 sessions, 150 standardized tasks, 2 rule formats. The mechanical gate won. Everything else was...
I broke my own project on purpose, twice, before it worked. Here's the story. Round one:...
