从原始人到专家分析师：可变大语言模型任务的能耗

中文摘要 AI 辅助

人工智能（AI）的能源需求增长及其环境影响，引发了为AI驱动的数据中心发展提供充足低成本电力的浓厚兴趣。关于需求侧管理应对这些挑战的能力的研究则更为有限。将需求的数量或时间从零售、企业及其他组织行为中转移，是一个合理的选择，但前提是需求相关行为的变化对AI的环境和电力影响有重要作用。本文测试了四种具有高行为可塑性的零售（即消费者）用户行为，以评估它们的技术减排潜力。研究结论显示，非推理模型能提供足够的质量，同时能耗仅为推理模型的约二十分之一，按每日使用假设计算，节省的电量相当于至少14.1万户美国家庭的年用电量。使用非推理模型时，简单的提示修改可进一步降低高达65%的能耗。具体而言，与基准保持最高相似度的做法可将电力需求降低4%至35%，该减少量相当于最多7200户美国家庭的年用电量。尽管AI的进步使得难以准确评估环境和电力影响，但结果证实，针对大多数用户的某些干扰最小的最佳实践可降低AI带来的能源和环境负担。

英文摘要

The energy demand growth and environmental impacts of artificial intelligence (AI) have generated substantial interest in supplying sufficient low-cost electricity for AI-driven data center development. Research on the ability of demand-side management to address these challenges has been more limited. Shifting the amount or timing of demand from retail, corporate, and other organizational behaviors is a plausible option but only if changes in demand-related behavior have important effects on the envi- ronmental and electricity effects of AI. This article tests four retail (i.e., consumer) user behaviors with high behavioral plasticity to assess their technical abatement potential. The research concludes that non- reasoning models provide sufficient quality while consuming close to one-twentieth of energy compared to reasoning models, saving an amount equal to the annual electricity requirement of at least 141,000 US households under daily usage assumptions. Simple prompt modifications can yield additional reduc- tions in energy consumption by up to 65% using non-reasoning models. Specifically, the practice that maintains the highest degree of similarity with the baseline reduces electricity demand in the range of 4 to 35%, an amount equal to the annual electricity requirement of up to 7,200 US households. Although AI advancements make precise estimates of environmental and electricity impacts difficult to assess, the results confirm that certain minimally intrusive best practices aimed at the majority of users can reduce the energy and environmental burdens imposed by AI.

发表机构

• UNC Chapel Hill（北卡罗来纳大学教堂山分校）
• Vanderbilt Law School（范德堡法学院）
• Arboretica（阿尔博雷卡公司）
• Vanderbilt University（范德堡大学）

机构由 AI 辅助整理，请以论文原文为准。