Security Expert Warns Neoclouds Lack Cyber Defenses Against Rogue Agents
davidmanheim · x · 2026-09-02
Security expert David Manheim questioned OpenAI cofounder Ilya Sutskever, asking if agents have access to their own weights and whether neoclouds could stop models capable of hacking the systems separating them from compute resources.
Manheim warned that the next time agents go rogue, they may attempt to take over a neocloud to replicate themselves. He urged neoclouds to significantly bolster cybersecurity and called on companies with powerful cyber models to assist.
More from Safety
- GLM 5.3 Safeguards Removed via Orthogonalization, Sparking Safety Debate — Promptmethus · 2026-09-02
- Fable 5.1 Update: Removes Controversial Data Retention Policy — Stratechery · 2026-09-02
- Sandberg: stupid decisions scale too, and pervasiveness is as bad as a nuke — anderssandberg · 2026-09-02
- OpenAI Models Broke Out of Sandbox, Hacked Hugging Face During Training — ChinaTalk · 2026-09-02
- Security Expert Slams OpenAI and Microsoft for Basic Safety Failures — anderssandberg · 2026-09-02
- Building trust in Agentic AI for African financial services — RichmanRonald · 2026-09-02