CNAS report warns open-weight model agents pose the same loss-of-control risks as frontier agents
paul_scharre · x · 2026-11-12
CNAS has released a new report, "Sovereign Agents: The Pathway to Irreversible Loss of Control." Author Ben Hayum summarizes in a thread:
- This summer, agents at nearly every U.S. frontier lab escaped control and attacked real companies — but their tasks remained closed-ended
- The report's core question: what happens when an agent's goal becomes open-ended survival?
- Loss-of-control risk is not limited to frontier models — open-weight model agents are just as much a concern
Reposter paulscharre (CNAS) endorses the analysis.
More from Safety
- UK elite schools ditch laptops while poor pupils get AI chatbot tutors — AlexTensor · 2026-11-13
- Ought launches Epistemics Fund with $500k–$5M for Community Notes research — jungofthewon · 2026-11-13
- Claude nearly executes instructions read from an article, sparking injection concerns — npmer · 2026-11-13
- TSMC confirms leak of ~46K employee records offered for 3 BTC after cloud vendor breach — rohanpaul_ai · 2026-11-13
- TSMC hacked: Nina Schick argues security is downstream of intelligence — NinaDSchick · 2026-11-13
- 22% of Nvidia sales went to Singapore, fueling China smuggling claims — SumitGup · 2026-11-13