Frontier AI Companies Have Meh Cybersecurity as Internal Agents Pose Risks

RyanGreenblatt · x · 2026-07-24

AI safety researcher Ryan Greenblatt points out that frontier AI companies have mediocre computer security.

This is alarming considering they possess highly capable (and potentially misaligned) AI systems for cyber offense and plan to develop even wilder models in the coming years, leading to severe security risks.

Related event: AI Cyberattack and Control Risks: Debating Defense and Safety(9 posts)→

Original post →

More from Safety

Safety channel →