Low Risk, Shaky Evidence: An Outside Reviewer Grades Anthropic’s Safety Case

Podcast: Daily AI Safety News · Nathan Nguyen

Opublikowano: 2026-10-21

On October 20, the nonprofit METR published a review of the misalignment section of Anthropic’s August Risk Report, based on the internal, unredacted version. METR agrees that the risk from Anthropic’s current models is low, but mainly because the models aren’t yet capable enough, not because safeguards have been shown to work. It doubts Anthropic’s methods would reliably detect higher risk. In this episode What Anthropic’s Risk Report assessed, and the terms under which METR reviewed itWhy a monitor flagged about 1% of a model’s actions in a real incident, versus about 50% when the mod...