AI x-risk, approximately ordered by embarrassment — LessWrong

Advanced AI systems could lead to existential risks via several different pathways, some of which may not fit neatly into traditional risk forecasts.…

x AI x-risk, approximately ordered by embarrassment — LessWrong AI Risk Concrete Stories Deception Existential risk Multipolar Scenarios Threat Models (AI) AI Frontpage 151 AI x-risk, approximately ordered by embarrassment by Alex Lawsen 12th Apr 2023 AI Alignment Forum 23 min read 7 151 Ω 46 Advanced AI systems could lead to existential risks via several different pathways, some of which may not fit neatly into traditional risk forecasts. Many previous forecasts, for example the well known report by Joe Carlsmith, decompose a failure story into a conjunction of different claims, and in doing

related reading

• What failure looks like — LessWronglesswrong.com
• Where I agree and disagree with Eliezer — LessWronglesswrong.com
• Notes on Existential Risk from Artificial Superintelligencemichaelnotebook.com
• What failure looks like — AI Alignment Forumalignmentforum.org
• The Artificiality of Alignmentjoinreboot.org
• Existential risk, AI, and the inevitable turn in human history - Marginal REVOLUTIONmarginalrevolution.com
• Existential Risk from AI: An Exposition for Mathematiciansalkjash.github.io
• Recommendations for Technical AI Safety Research Directionsalignment.anthropic.com
• The Case Against AI Control Research — LessWronglesswrong.com
• Brain dump on the diversity of AI risk | Jascha’s blogsohl-dickstein.github.io
• Model Organisms of Misalignment: The Case for a New Pillar of Alignment Research — AI Alignment Forumalignmentforum.org
• Many arguments for AI x-risk are wrong — AI Alignment Forumalignmentforum.org