Abstracting The Hardness of Alignment: Unbounded Atomic Optimization — LessWrong

This post is part of the work done at Conjecture. …

x Abstracting The Hardness of Alignment: Unbounded Atomic Optimization — LessWrong Conjecture (org) Löb's theorem Optimization AI Frontpage 75 Abstracting The Hardness of Alignment: Unbounded Atomic Optimization by adamShimi 29th Jul 2022 AI Alignment Forum 19 min read 3 75 Ω 29 This post is part of the work done at Conjecture . Disagree to Agree ( Practically-A-Book Review: Yudkowsky Contra Ngo On Agents , Scott Alexander, 2022) This is a weird dialogue to start with. It grants so many assumptions about the risk of future AI that most of you probably think both participants are crazy. (Person

related reading

• Alignment remains a hard, unsolved problem — LessWronglesswrong.com
• AGI Ruin: A List of Lethalities — LessWronglesswrong.com
• LessWronglesswrong.com
• A positive case for how we might succeed at prosaic AI alignment — AI Alignment Forumalignmentforum.org
• Automated Alignment is Harder Than You Think — LessWronglesswrong.com
• The Field of AI Alignment: A Postmortem, and What To Do About It — LessWronglesswrong.com
• The Artificiality of Alignmentjoinreboot.org
• Shah and Yudkowsky on alignment failures — LessWronglesswrong.com
• The Best of LessWrong — LessWronglesswrong.com
• Optimality is the tiger, and agents are its teeth — LessWronglesswrong.com
• Shtetl-Optimized >> Blog Archive >> Theory and AI Alignmentscottaaronson.blog
• Sequent: Scale and Automation for Higher Confidence in Alignment — Sequentsequent.org