How can we build human values into AI? - Google DeepMind

As artificial intelligence (AI) becomes more powerful and more deeply integrated into our lives, the questions of how it is used and deployed are all the more important. What values guide AI?...

April 24, 2023 Responsibility & Safety Iason Gabriel and Kevin McKee Drawing from philosophy to identify fair principles for ethical AI As artificial intelligence (AI) becomes more powerful and more deeply integrated into our lives, the questions of how it is used and deployed are all the more important. What values guide AI? Whose values are they? And how are they selected? These questions shed light on the role played by principles – the foundational values that drive decisions big and small in AI. For humans, principles help shape the way we live our lives and our sense of right and…

related reading

• AI Principlesai.google
• The Artificiality of Alignmentjoinreboot.org
• [2001.09768] Artificial Intelligence, Values and Alignmentarxiv.org
• Suicidal Compassion: How Utilitarianism at AI Companies Endangers Humanityai-frontiers.org
• Full-Stack Alignment and Thick Models of Valuefull-stack-alignment.ai
• What Does It Mean to Align AI With Human Values? | Quanta Magazinequantamagazine.org
• AI for Decision Adviceforethought.org
• Explore: AI alignmentarbital.greaterwrong.com
• [2512.15584] A Decision-Theoretic Approach for Managing Misalignmentarxiv.org
• w26130.pdfnber.org
• Eigenism: Ethics for a Human-AI Futurearxiv.org
• After Orthogonality: Virtue-Ethical Agency and AI Alignmentthegradient.pub