Comment by Zaheed Kara

Our new paper makes the case for embedded assessments, which would give independent evaluators employee-like access to these resources to more comprehensively assess the risks that depend on a developer’s internal systems and practices. [...] We recommend that frontier AI developers begin hosting embedded assessments, with six priorities: [...] Give evaluators access comparable to internal staff conducting similar assessments. This should include relevant systems, personnel, and records, with developers explaining any refusal of additional information.