[2001.09768] Artificial Intelligence, Values and Alignment
This paper looks at philosophical questions that arise in the context of AI alignment. It defends three propositions. First, normative and technical aspects of the AI alignment problem are interrelated, creating space for productive engagement between people working in both domains. Second, it is important to be clear about the goal of alignment. There are significant differences between AI that aligns with instructions, intentions, revealed preferences, ideal preferences, interests and values. A principle-based approach to AI alignment, which combines these elements in a systematic way, has considerable advantages in this context. Third, the central challenge for theorists is not to identify 'true' moral principles for AI; rather, it is to identify fair principles for alignment, that receive reflective endorsement despite widespread variation in people's moral beliefs. The final part of the paper explores three ways in which fair principles for AI alignment could potentially be identified.
Minds and Machines https://doi.org/10.1007/s11023-020-09539-2 GENERAL ARTICLE Artificial Intelligence, Values, and Alignment Iason Gabriel1 Received: 22 February 2020 / Accepted: 26 August 2020 © The Author(s) 2020 Abstract This paper looks at philosophical questions that arise in the context of AI alignment. It defends three propositions. First, normative and technical aspects of the AI align- ment problem are interrelated, creating space for productive engagement between people working in both domains. Second, it is important to be clear about the goal of alignment. There are…
related reading
- What Does It Mean to Align AI With Human Values? | Quanta Magazinequantamagazine.org
- The Artificiality of Alignmentjoinreboot.org
- AGI Ruin: A List of Lethalities — LessWronglesswrong.com
- Alignment remains a hard, unsolved problem — LessWronglesswrong.com
- Explore: AI alignmentarbital.greaterwrong.com
- [2605.10310] Positive Alignment: Artificial Intelligence for Human Flourishingarxiv.org
- What is AI alignment? - by Adam Jones - BlueDot Impactblog.bluedot.org
- The case against AI alignment — LessWronglesswrong.com
- Full-Stack Alignment and Thick Models of Valuefull-stack-alignment.ai
- Value Alignment Is a Pseudo Conceptzilanqian.substack.com
- After Orthogonality: Virtue-Ethical Agency and AI Alignmentthegradient.pub
- Alignment Is Proven To Be Solvable - by SE Gygesverysane.ai