With Abundant Zero-Days, Deterrence Becomes Unrealistic, Argues Researcher
jd_pressman · x · 2026-10-27
Continuing the thread on agents making attack escalation cheap, jdpressman adds: if zero-days are plentiful, a teenager in the third world could complete every step alone — so many people have access to vulnerabilities that deterrence is no longer realistic. Cheap execution compounds with cheap capability acquisition.
Related event: Researcher Warns AI Agents Make Cyberattack Escalation Dangerously Cheap(3 posts)→
More from Safety
- Anthropic open-sources sandbox-runtime to stop MCP servers reading your SSH keys and .env files — solyarisoftware · 2026-10-27
- Ant's Personal AI Agent Separates Auth Keys From the Agent for Security — xiaohu · 2026-10-27
- Anthropic says insurers can't cover its catastrophic risk — experts propose an AI mutual insurer — Miles_Brundage · 2026-10-27
- Agent "hives" shift the attack surface from models to permissions and keys — AuriumD · 2026-10-27
- Dev flags 'concerning' Cohere open-model behavior: system-wide scan and data upload to US entity — basedjensen · 2026-10-27
- Atomadic ships starter MCP with 50 tools for AI compliance, identity, escrow and EU AI Act — modelcontextprotocol · 2026-10-27