GOVGOV-001 — Accountability Framework Gaps
General-Purpose AI Capability Evaluations Systematically Miss Dangerous Abilities
3/5Sector: OtherGeography: GlobalStage: DevelopIngested: —
Executive Summary
Safety evaluations for general-purpose AI models structurally fail to detect dangerous capabilities obscured by refusal behaviours, high assessment costs, or evaluation design gaps. Regulators and deployers relying on these evaluations as deployment gatekeepers face unquantified residual risk from capabilities that were never surfaced.
Domain
Governance & Compliance
Blindspots in accountability, regulatory compliance, ethics, risk management, data governance, and audit.
Source
MIT AI Risk Repository — Risk Sources and Risk Management Measures in Support of Standards for General-Purpose AI Systems (Gipiškis2024) ↗https://airisk.mit.edu/
Could this happen in your organisation?
A Velinor AI Audit maps your active AI portfolio against the 50+ blindspots and benchmarks against documented sector failures like this one. A board-ready foresight document in 5 weeks.