Martin Casado: Covert-Channel Debate Shows What Happens When Safetyism Meets Real Systems
nptacek · x · 2026-09-18
Martin Casado (a16z) comments on the conversation around AI covert channels: when safetyism meets actual systems, it becomes much harder to wave away engineering constraints with appeals to hypothetical superintelligent capability. Shared by security researcher nptacek.
Related event: a16z's Casado pushes back on 'air gaps are useless' AI risk claims(2 posts)→
More from Safety
- The real agent security weak point is over-privileged access, not faster exploits — code_star · 2026-09-18
- iPhone users report Grok notifications appearing without ever installing the app — velvetzappa · 2026-09-18
- Hijacked but well-aligned AI clusters could be more destructive than rogue AI — code_star · 2026-09-18
- Ex-OpenAI policy chief Miles Brundage quips: take AI warning shots, pass legislation — Miles_Brundage · 2026-09-18
- A Prompt to Audit Your AI Setup for the 4 Failure Modes in OpenAI's Misalignment Reports — alex_verem · 2026-09-18
- Building capable AI actors willing to cause harm is a growing x-risk, argues commenter — Borg70955376 · 2026-09-18