The Pointers Problem: Clarifications/Variations — LessWrong

I've recently had several conversations about John Wentworth's post The Pointers Problem. I think there is some confusion about this post, because th…

x The Pointers Problem: Clarifications/Variations — LessWrong Pointing at Normativity The Pointers Problem AI Rationality Frontpage 61 The Pointers Problem: Clarifications/Variations by abramdemski 5th Jan 2021 AI Alignment Forum 22 min read 17 61 Ω 30 I've recently had several conversations about John Wentworth's post The Pointers Problem . I think there is some confusion about this post, because there are several related issues, which different people may take as primary. All of these issues are important to "the pointers problem", but John's post articulates a specific problem in a way that

related reading

• Alignment remains a hard, unsolved problem — LessWronglesswrong.com
• AGI Ruin: A List of Lethalities — LessWronglesswrong.com
• The formal goal is a pointer — LessWronglesswrong.com
• The Artificiality of Alignmentjoinreboot.org
• Stable Pointers to Value II: Environmental Goals — LessWronglesswrong.com
• Alignment Is Proven To Be Solvable - by SE Gygesverysane.ai
• A positive case for how we might succeed at prosaic AI alignment — AI Alignment Forumalignmentforum.org
• What Is The Alignment Problem? — LessWronglesswrong.com
• What Does It Mean to Align AI With Human Values? | Quanta Magazinequantamagazine.org
• Embedded Agency (full-text version) — LessWronglesswrong.com
• Alignment By Default — AI Alignment Forumalignmentforum.org
• The Best of LessWrong — LessWronglesswrong.com