✳flâneur — a map of the web's best reading

What could an AI-caused existential catastrophe actually look like? - 80,000 Hours

80000hours.org · 3,095 words · saved by 1 readers

Arguments for AI being risky are often very abstract. Here we explain several concrete ways an AI system might be able to actually gain power.

On this page: Introduction 1 How could a power-seeking AI actually take power? 2 How could the full story play out? 2.1 Existential catastrophe through getting what you measure 2.2 Existential catastrophe through a single extremely advanced artificial intelligence 3 Return to the full article 4 Or, if you’re new, start from the beginning Image generated by DALL-E 2 . Table of Contents 1 How could a power-seeking AI actually take power? 2 How could the full story play out? 2.1 Existential catastrophe through getting what you measure 2.2 Existential catastrophe through a single extremely a

Explore this link on the map →

related reading