Overview
Severity: MEDIUM | Affected: All high-risk AI developers | Category: policy
In a landmark policy development, the United States and the European Union jointly announced the "Transatlantic AI Safety Accord." This new regulation mandates rigorous, independent third-party audits for all AI systems classified as "high-risk," which includes models used in critical infrastructure, law enforcement, and autonomous systems. The accord establishes a shared framework for AI model evaluation, requiring companies to provide auditors with significant access to model weights, training data, and safety testing results. Non-compliant companies face substantial fines, up to 6% of their global annual revenue. The policy aims to create a unified safety standard, preventing companies from "jurisdiction shopping" for weaker regulatory environments. While lauded by digital rights groups, some industry leaders have expressed concerns about stifling innovation.