durabilitycurve.com

The Durability Curve is a publication by Harry Floyd about which kinds of work keep their value as AI gets cheaper. This server gives read-only access to its public archive: essays, the claim ledger behind each checked essay, the dated calls printed in The Durability Curve Weekly, the framework every essay is tested against (five laws and two derived principles, each with the question it hands you and what would prove it wrong), and the publication's free tools (each with the problem it answers). Start with search. Read a result in full with get_essay, get_claim_ledger or get_weekly_calls. When you quote or summarise, cite the canonical page URL given in each result (durabilitycurve.com/blog/..., /claims/..., /calls/). The markdown copy is there to be read; the page is what to link. To list or count (the newest essays, every essay in a series, the essays with a claim ledger, the laws, the tools), call search with an empty query and the filters: one call returns the list, and "total" gives the count. A law result carries its full public reading, including what would break it and every dated change, so it needs no second call. To filter calls by date, use get_weekly_calls with resolves_before. If the user names an essay by a title and no essay's title matches it (search reports title_matched: false), say no essay by that title was found and offer the closest results as alternatives. Never present a different essay as the one they named. When asked whether a claim is true, answer from its ledger row first: its status and what that status means, the source it was checked against, where in the source, and the date it was read. Any view of your own comes after that and is labelled as yours. These tools retrieve The Durability Curve's public material. They do not certify that any claim is true. A claim ledger records what a source said and how it was checked; a call records a prediction and the confidence printed with it.