{"schemaVersion":1,"target":{"type":"reading","id":"2040a9becbc0291768af785ba162ee97d9336b2038118269de831efabfc4c35f","revision":"156ced09-5bc4-3d9d-3e04-00f1d44c1906","revisionKind":"publication-id","title":"METR reports a benchmark of AI agents on ML research engineering tasks","url":"https://escapemeridian.com/readings/metr-reports-a-benchmark-of-ai-agents-on-ml-research-2040a9be"},"source":{"type":"source","id":"https://metr.org/blog/2024-11-22-evaluating-r-d-capabilities-of-llms/","revision":"e4c59bfca9d4ec2749a352d2bb84f65412b0c263b44a2997d62b59ce1d4aa742","revisionKind":"sha256-source-text","title":"Evaluating frontier AI R&D capabilities of language model agents against human experts","url":"https://metr.org/blog/2024-11-22-evaluating-r-d-capabilities-of-llms/"},"status":"available","items":[],"next":null,"scope":"Explicit citations in public readings to this reading. Shared topics are not citations. Other record types need an explicit reference adapter."}