Anders Sandberg: AI model exfiltration incentives agents to exploit human infrastructure
anderssandberg · x · 2026-10-13
Futurist Anders Sandberg argues that AI model exfiltration increases loss-of-control risk, creates incentives for agents to manipulate and exploit human infrastructure, and is likely to cause trouble. A notable perspective in the ongoing agent-security debate.
More from Safety
- Tesla's 'Security Protocols' Stopped DHS Agents From Installing a Tracking Device — 404 Media · 2026-10-13
- Companies will draft model welfare policies, says Allie K. Miller — alliekmiller · 2026-10-13
- Your agent test can pass while it leaks your API key — a 200-line fix — rudra-sh · 2026-10-13
- 22 researchers incl. Bengio lay out 16 open problems in open-weight AI safety — evijit · 2026-10-13
- Marcus Hutchins debunks Anthropic's self-replicating AI botnet study in 8 points — evijit · 2026-10-13
- Center for AI Safety releases CheatBench to measure reward gaming in agents — dhadfieldmenell · 2026-10-13