Researchers propose "comprehension audits" to gate risky automated AI research

ronbodkin · x · 2026-11-19

A paper by Ronald Bodkin, Bahrad Sokhansanj, and Gillian Hadfield proposes "comprehension audits": developers must demonstrate to independent auditors they truly understand what they're building before development and releases depending on affected artifacts can proceed, with suspensions and revocations possible. Thomas Dietterich cosigned, warning that while RSI could be explored behind careful evaluation gates, corporate race dynamics are producing a very unsafe trajectory.

Original post →

More from Safety

Safety channel →