Skip to content

The Durability Curve · free by email

Every new piece as it ships, and the Weekly on Saturday, with the calls we grade.

107Pieces, dated
1245Claims verified at the primary source
7Instruments, no login

Your address goes to Substack, where you confirm it. Nothing is stored on this site.

The latest issue · Anthropic Says It Has Met Its Own AI Research Threshold. NVIDIA's New Chief Challenged Huang's Bets. Read it first

The Runbook

4 essays, August 2026 to October 2026. They test Instruments Over Theory (1). 108 claims across 2 of them are checked against a primary source in the public ledger.

01 · Every essay in this strand

  1. Did Your AI Actually Read the Doc?

    How to give ChatGPT and Claude the same project notes in one Google Doc, and test whether a new chat can use them.

    38 sourced claims
  2. Use AI to Learn Without Getting Worse at It

    Answer-giving AI left learners worse off once it was gone. Three setups built to keep the thinking with you, and a way to check what stuck.

    70 sourced claims
  3. The Skill That Never Fired

    A Claude skill can fail two ways: its instructions are wrong, or Claude never picks it. Anthropic's own tooling scores whether one skill fires. This tests it against the neighbour that can quietly win its requests, with a small routing eval you run yourself.

  4. Law IV
    Stop Re-Priming Claude Code by Hand

    The context you paste at the start of every session, put into one file you invoke with /prime.

All strands All the tools The claim ledger

The newsletter · Free

Subscribe to get each new piece in your inbox, with something to use in every one.

Several essays a week, plus Notes through the week.

Signup completes on Substack. Unsubscribe from any email.