GeistHaus
log in · sign up

AI-Enabled Coups: How a Small Group Could Use AI to Seize Power

forethought.org

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.

16 pages link to this URL
The Intelligence Curse
The Intelligence Curse Luke Drago; Rudolf Laine

This series examines the incoming crisis of human irrelevance and provides a map towards a future where people remain the masters of their destiny.

0 inbound links article en
AI Safety Landscape and Strategic Gaps
Philosophical Multicore Michael Dickens

I wrote a report giving a high-level review of what work people are doing in AI safety. The report specifically focused on two areas: AI policy/advocacy and non-human welfare (including animals and digital minds).

3 inbound links article en
Pausing AI Is the Best Answer to Post-Alignment Problems
Philosophical Multicore Michael Dickens

Even if we solve the AI alignment problem, we still face post-alignment problems, which are all the other existential problems1 that AI may bring. Existential in the classic sense of “a permanent loss of most of the potential flourishing of the future”. ↩

1 inbound link article en