My take on Vanessa Kosoy's take on AGI safety — AI Alignment Forum

Confidence level: Low • Vanessa Kosoy is a deep fountain of knowledge and insights about AGI safety, but I’ve had trouble understanding some aspects…

x My take on Vanessa Kosoy's take on AGI safety — AI Alignment Forum Infra-Bayesianism Reinforcement learning AI Frontpage 46 My take on Vanessa Kosoy's take on AGI safety by Steven Byrnes 30th Sep 2021 38 min read 10 46 Confidence level: Low Vanessa Kosoy is a deep fountain of knowledge and insights about AGI safety, but I’ve had trouble understanding some aspects of her point of view. Part of the problem is just pedagogy, and part of it (I will argue) is that she has some different underlying assumptions and beliefs than I do. This post aims to address both those things. In particular, on th

related reading

• AGI Ruin: A List of Lethalities — LessWronglesswrong.com
• Alignment remains a hard, unsolved problem — LessWronglesswrong.com
• A positive case for how we might succeed at prosaic AI alignment — AI Alignment Forumalignmentforum.org
• Commentary on AGI Safety from First Principles — AI Alignment Forumalignmentforum.org
• Where I agree and disagree with Eliezer — LessWronglesswrong.com
• AGI safety career advice — EA Forumforum.effectivealtruism.org
• Critical review of Christiano's disagreements with Yudkowsky — LessWronglesswrong.com
• Unfalsifiable stories of doom | Mechanize, Inc.mechanize.work
• Core views on AI safety: When, why, what, and how \ Anthropicanthropic.com
• Rohin Shah on what it's really like to run AGI safety at Google DeepMind (and where I disagree with 'doomers') | 80,000 Hours80000hours.org
• AGI safety from first principles: Introduction — LessWronglesswrong.com
• Shah and Yudkowsky on alignment failures — LessWronglesswrong.com