AI-Enabled Coups: How a Small Group Could Use AI to Seize Power
The development of AI that is more broadly capable than humans will create a new and serious threat: *AI-enabled coups*. An AI-enabled coup could be staged by a very small group, or just a single person, and could occur even in established democracies. Sufficiently advanced AI will introduce three novel dynamics that significantly increase coup risk. Firstly, military and government leaders could fully replace human personnel with AI systems that are *singularly loyal* to them, eliminating the need to gain human supporters for a coup. Secondly, leaders of AI projects could deliberately build AI systems that are *secretly loyal* to them, for example fully autonomous military robots that pass security tests but later execute a coup when deployed in military settings. Thirdly, senior officials within AI projects or the government could gain *exclusive access* to superhuman capabilities in weapons development, strategic planning, persuasion, and cyber offense, and use these to increase their power until they can stage a coup. To address these risks, AI projects should design and enforce rules against AI misuse, audit systems for secret loyalties, and share frontier AI systems with multiple stakeholders. Governments should establish principles for government use of advanced AI, increase oversight of frontier AI projects, and procure AI for critical systems from multiple independent providers.
AI-Enabled Coups: How a Small Group Could Use AI to Seize Power Tom Davidson Lukas Finnveden Rose Hadshar Authors Citations Cite Citations PDF Contact 15th April 2025 AI-Enabled Coups: How a Small Group Could Use AI to Seize Power Abstract Summary An AI workforce could be made singularly loyal to institutional leaders AI could have hard-to-detect secret loyalties A few people could gain exclusive access to coup-enabling AI capabilities Mitigations 1 Introduction 2 AI will have powerful coup-enabling capabilities 3 Risk factors of AI-enabled coup risk 3.1 Singular AI loyalties to institutional
Explore this link on the map →saved by
related reading
- AI Could Defeat All Of Us Combinedcold-takes.com
- Dario Amodei — The Adolescence of Technologydarioamodei.com
- The case for ensuring that powerful AIs are controlled — LessWronglesswrong.com
- 2028: Two scenarios for global AI leadership \ Anthropicanthropic.com
- The Three Filters: Why Almost Every Plan to Survive ASI Fails Miserably — LessWronglesswrong.com
- AI Deterrence by Betrayalaibetrayal.com
- What failure looks like — LessWronglesswrong.com
- AI 2027ai-2027.com
- Soft Nationalization: how the USG will control AI labs — LessWronglesswrong.com
- Strategic Visionsstatic1.squarespace.com
- Secretly Loyal AIs: Threat Vectors and Mitigation Strategies — LessWronglesswrong.com
- Off Target | CNAScnas.org