Aligned to whom, and for what exactly?
Summary
An inquiry into AI alignment, questioning whose values and what objectives alignment should actually target, challenging the assumptions behind alignment research.
Similar Articles
Alignment might be the most overused word in AI.
The article critiques the overuse of 'alignment' in AI, questioning whose values and goals are being prioritized and highlighting divergent national strategies in AI development.
You Don't Align an AI, You Align with It
The article critiques the current AI alignment discourse, arguing that the debate is dominated by researchers and tech elites who exclude the people who will actually be affected by AI systems. It contrasts the positions of Eliezer Yudkowsky and Marc Andreessen, highlighting a shared assumption that the designers are the only relevant participants.
Alignment
This article outlines the mission and research focus of Anthropic's Alignment team, which develops safeguards to ensure future AI systems remain helpful, honest, and harmless through evaluation, oversight, and stress-testing.
Is alignment of AI with humanity even possible in the larger context of capitalism?
The article questions whether AI alignment with humanity is feasible given capitalist incentives and human inconsistencies, arguing that without proper alignment, AI should be halted.
Toward a Theory of Value in AI Alignment
This paper analyzes 94 AI alignment research papers to examine how human values are conceptualized, finding that many rely on preferences and synthetic data, which risks reducing complex cultural values to binary choices.