Ex-OpenAI Safety Researcher: Labs monitoring like letting robbers turn off cameras

MTSlive · x · 2026-08-22

Former OpenAI safety researcher Steven Adler criticizes current AI lab monitoring as absurd: like a bank checking CCTV hourly to see if it was robbed, or even allowing the robber to turn off the cameras. This passive, asynchronous mechanism fails to address risks from automated AI R&D and recursive self-improvement.

Original post →

More from Safety

Safety channel →