The Artificiality of Alignment - by jessica dai - Reboot

How are we actually “aligning AI with human values”?

Long essay today; let’s get straight to it. (Note — you might have a better time with footnotes on web/app than email, if that matters to you.) Nature by Alan Warburton, CC 4.0 By Jessica Dai Credulous, breathless coverage of “AI existential risk” (abbreviated “x-risk”) has reached the mainstream. Who could have foreseen that the smallcaps onomatopoeia “ꜰᴏᴏᴍ” — both evocative of and directly derived from children’s cartoons — might show up uncritically in the New Yorker? More than ever, the public discourse about AI and its risks, and about what can or should be done about those risks, is…

saved by

• Daniel Bashir
• Jacky Huang
• Myke Walton
• Stephanie Y.
• Joy
• Timothy Kostolansky
• Adi Mehta

related reading

• Alignment remains a hard, unsolved problem — LessWronglesswrong.com
• Alignment & Succession: The Two Bars of Alignmentnosetgauge.com
• There Is No A.I. | The New Yorkernewyorker.com
• Alignment & Succession: The Ideology of Successionnosetgauge.com
• “Alignment Engineering” vs. “Misalignment Science”lesswrong.com
• Value Alignment Is a Pseudo Conceptzilanqian.substack.com
• What are we building for? Artificial intelligence, alignment, and a future worth wantingmag.re-alignment.com
• The case against AI alignment — LessWronglesswrong.com
• Neurotechnology is Critical for AI Alignmentmilan.cvitkovic.net
• The Machines Lack Honour — LessWronglesswrong.com
• The Problem — LessWronglesswrong.com
• What Does It Mean to Align AI With Human Values? | Quanta Magazinequantamagazine.org