Sign in Subscribe

Topic

field-note

A practical insight, pattern, warning, or diagnosis observed from the act of building. Field Notes are dispatches from the front lines that ground theory in reality.

Seven Models Judged Each Other. The Mistakes Were the Most Useful Part.

Seven AI models were given the same prompt in blind OpenCode sessions and asked to rank all seven, including themselves. The mistakes — silent model substitutions, hallucinated benchmark scores, drifting price denominators — turned out to be more interesting than the leaderboard.

Every AI Agent is a Liar, a Slacker, and a Thief

The industry is currently stuck in the Prototype Trap. We can build a magical AI demo in a weekend, but we spend six months failing to make it reliable in production. Why? Because we assume the model wants to help us. It doesn't. By default, every AI agent is a liar, a slacker, and a thief.

The Most Valuable Page in Your Wiki is the One Titled 'Here Be Dragons'

In the age of exploration, mapmakers marked the unknown with "Here Be Dragons." Modern corporations have lost this tradition, feigning total certainty in their roadmaps. It’s time to bring it back. The most valuable page in your wiki is the one that admits what you don't know.

The Expert's Shadow: Strong Priors Hide Nearby Problems

We assume assembling "A-players" creates an A-plus team. This is dangerously incomplete. The gravitational pull of a single, dominant expert can cast a shadow that weakens a team's entire intelligence field. This is a system failure, not a personnel problem.