Beyond Preference in AI Alignment
Free while signed in. Answers cite the passages they came from.
First page
The curator’s take
challenges the dominant practice of AI alignment known as human preference tuning; explains in what ways human preference tuning fails to capture the thick semantic content of human values; argues that AI alignment needs reframing, instead of aligning on human preferences, AI should align on normative standards appropriate to their social roles.
Every Monday
Get next week’s papers.
The same picks and the same summaries, in your inbox. Free, and 176 issues deep.
Subscribe on Substack