{"schemaVersion":1,"target":{"type":"reading","id":"cf14bd96d649869d75c985abcc8aed63cc542dfa2d548a345039df797e350fa5","revision":"c8fed03f-331b-1b68-6fbd-39919bec40c6","revisionKind":"publication-id","title":"METR proposes a cost-based measure of AI optimization ability","url":"https://escapemeridian.com/readings/metr-proposes-a-cost-based-measure-of-ai-optimization-ability-cf14bd96"},"source":{"type":"source","id":"https://metr.org/blog/2026-07-21-expenditure-horizon/","revision":"72b85a23f5b2dea05f9e0f7ab275167377413d899e3124d5e244439f67334bc8","revisionKind":"sha256-source-text","title":"Expenditure Horizon: Measuring Optimization Ability, with an Application to NanoGPT","url":"https://metr.org/blog/2026-07-21-expenditure-horizon/"},"status":"available","items":[],"next":null,"scope":"Explicit citations in public readings and public file attachments to this reading. Shared topics are not citations. Other artifact types need an explicit reference adapter."}