Latest

Sat, Oct 10, 2026Saturday, October 10, 20261 entry

AnalysisBuild systems around models

Review a Month of Coding-Agent Work by Accepted Outcomes

Judge a month of agent work from every attempt, not only the accepted ones: fix the denominator, compare within task families, put error bars on each rate and keep unresolved jobs in the ledger.9 min readagent-evaluationcoding-agents

Thu, Sep 10, 2026Thursday, September 10, 20261 entry

AnalysisBuild systems around models

Measure Coding-Agent Uplift Honestly: Case Mix and Simpson's Paradox

A coding agent can look faster overall while being slower on every kind of task. Count the whole task, hold the case mix fixed, and see how Simpson's paradox produces a false speedup.8 min readagent-evaluationcoding-agents

Thu, Aug 6, 2026Thursday, August 6, 20261 entry

AnalysisBuild systems around models

What an Agent Loop Costs: Quadratic Resend, Cache Reads and Cost per Solved Task

Every call in an agent loop resends the whole context, so input grows with the square of the calls. Derive the cost with caching, price the solved task with an interval, with Claude Code as the worked instance.10 min readclaude-codeinference-cost

That is the first entry in the log.

To browse rather than follow: topics, all articles and all notes. To learn in order: courses and the book.