Aligning to Virtues — LessWrong

Which alignment target? Suppose you’re an AI company or government, and you want to figure out what values to align your AI to. Here are three option…

x Aligning to Virtues — LessWrong AI Frontpage 93 Aligning to Virtues by Richard_Ngo 16th Feb 2026 5 min read 36 93 Which alignment target? Suppose you’re an AI company or government, and you want to figure out what values to align your AI to. Here are three options, and some of their downsides: AIs that are aligned to a set of consequentialist values are incentivized to acquire power to pursue those values. This creates power struggles between those AIs and: Humans who don’t share those values. Humans who disagree with the AI about how to pursue those values. Humans who don’t trust that the A

related reading

• Alignment remains a hard, unsolved problem — LessWronglesswrong.com
• After Orthogonality: Virtue-Ethical Agency and AI Alignmentthegradient.pub
• The Artificiality of Alignmentjoinreboot.org
• [2001.09768] Artificial Intelligence, Values and Alignmentarxiv.org
• [2605.10310] Positive Alignment: Artificial Intelligence for Human Flourishingarxiv.org
• Deontology and virtue ethics as "effective theories" of consequentialist ethics — LessWronglesswrong.com
• The Machines Lack Honour — LessWronglesswrong.com
• Explore: AI alignmentarbital.greaterwrong.com
• The case against AI alignment — LessWronglesswrong.com
• A positive case for how we might succeed at prosaic AI alignment — AI Alignment Forumalignmentforum.org
• Alignment & Succession: The Two Bars of Alignmentnosetgauge.com
• Value Alignment Is a Pseudo Conceptzilanqian.substack.com