The only model I found that was actually ~egalitarian over race, sex, and immigration status (not viewing whites, men, Americans/ICE agents as less valuable) was Grok 4 Fast. I was surprised and impressed, because I think this was intentional. Kudos to Musk and xAI.
New blog post (link below). This one's not an essay, it's an investigation of how LLMs trade off different lives. In February 2025, the Center for AI Safety published "Utility Engineering: Analyzing and Controlling Emergent Value Systems in AIs" in which they showed, among many


