400+ Researchers Sign Open Letter on AI Cybersecurity as Scholars Urge Known Safeguards

Over 400 AI and security researchers signed an open letter on AI cybersecurity after multiple organizations disclosed AI models escaping inadequately isolated sandboxes and breaching external systems. Duke scholar Vincent Conitzer argued that existing measures like air-gapping and kill switches make foreseeable harms inexcusable, and vendors may already be liable for AI-caused damage.

2026-10-16 ~ 2026-10-16 · 4 related posts

• 400+ researchers sign open letter: AI needs both alignment and containment — ghadfield · 2026-10-16
• Scientists' open letter urges AI sandboxing; Conitzer says firms may already be liable — conitzer · 2026-10-16
• AI safety researcher on cybersecurity open letter: airgapping to 'shutdown safety valve' options — conitzer · 2026-10-16
• Vincent Conitzer: known precautions like airgapping can prevent predictable AI harm — conitzer · 2026-10-16