洞察 AI 演进与全球贸易脉动，以全息视野重塑跨域情报流。
Decoding AI evolution and global trade rhythms. High-fidelity intelligence, redefined.
Prompt Injection in Automated Résumé Screening with Large Language Models: Single and Multi-Injection Settings
大型语言模型 (LLMs) 越来越多地用于筛选和排名求职者, 为候选人战略性地操纵...
Large language models (LLMs) are increasingly used to screen and rank job applicants, creating incentives for candidates to strategically manipulate a...
When Does Combining Language Models Help? A Co-Failure Ceiling on Routing, Voting, and Mixture-of-Agents Across 67 Frontier Models
多模型 LLM 系统（例如路由, 投票, 级联, 融合, 和混合代理）用于击败单模型准确性。我们表明他们的...
Multi-model LLM systems such as routing, voting, cascades, fusion, and mixture-of-agents are used to beat single-model accuracy. We show that their ga...
Language-Based Digital Twins for Elderly Cognitive Assistance
数字孪生已成为个性化医疗保健的一个有前途的范例,，可以对个人行为和健康轨迹进行建模。在c...
Digital twins have emerged as a promising paradigm for personalized healthcare, enabling modeling of individual behavior and health trajectories. In c...
LLMs help robots understand vague instructions and focus on key details
想象一下在不久的将来, 在仓库或办公室工作，您 被要求帮助新学员学习其工作的基础知识。捕获:...
Imagine working at a warehouse or office sometime in the near future, and you’re asked to help a new trainee learn the basics of their job. The catch:...
David Autor named head of the Department of Economics
作者’年代的奖学金探讨了技术变革和全球化对劳动力市场对工作两极分化的影响,技能要求,收入水平和...
Autor’s scholarship explores the labor-market impacts of technological change and globalization on job polarization, skill demands, earnings levels an...
Autodata: An agentic data scientist to create high quality synthetic data
我们引入了 Autodata, 一种通用方法，使 AI 代理能够充当构建高质量训练和评估数据的数据科学家。我们展示...
We introduce Autodata, a general method that enables AI agents to act as data scientists who build high quality training and evaluation data. We show ...
The Unfireable Safety Kernel: Execution-Time AI Alignment for AI Agents and Other Escapable AI Systems
AI 代理被授予对工具, API, 和其他基础设施, 的访问权限，使它们成为这些系统中的活跃主体。占主导地位的方法将...
AI agents are granted access to tools, APIs, and other infrastructure, making them active principals in those systems. The dominant approach places co...
Improving the speed and energy
代理工作流程是人工智能驱动的软件系统，它将多个模型和外部工具链接在一起以处理复杂的任务...
Agentic workflows are artificial intelligence-powered software systems that chain together multiple models and external tools to tackle complicated ta...
MIT in the media: Exploring how curiosity
过去80年,美国’的大胆,对科学研究的持续投资,以及由此产生的发现,想法和创新...
Over the past 80 years, America’s bold, sustained investment in scientific research, and the discoveries, ideas and innovations that flowed from it ma...
OpenThoughts-Agent: Data Recipes for Agentic Models
代理语言模型极大地扩展了人工智能的应用，但公众对如何为具有广泛能力的培训数据进行管理却知之甚少……
Agentic language models dramatically expand the applications of AI yet little is publicly known about how to curate training data for broadly capable ...