Kimi-K3
Kimi K3 is an open-weight, 2.8T-parameter native multimodal agentic model with a 1M-token context window, designed for frontier coding, knowledge work, and reasoning tasks.
首次将Anthropic可解释性团队关于大模型内部工作空间的前沿研究完整译成中文,使中文研究者能够深入理解模型的可报告推理机制及其对齐意义。
Verbalizable Representations Form a Global Workspace in Language Models Anthropic · Transformer Circuits Thread · 2026-07-06 原文:https://transformer-circuits.pub/2026/workspace/index.html
Anthropic可解释性团队2026年7月发布的重磅论文完整中文翻译。论文在Claude内部找到了一个与人类「意识通达」高度对应的结构:模型能报告、能持有、能推理的「工作空间」(J空间),漂浮在90%以上不可言说的计算之上。团队用新工具J-lens(雅可比透镜)读取它、干预它,并展示了对齐审计与「反事实反思训练」两类应用。
| 文件 | 说明 |
|---|---|
| 语言模型中的全局工作空间-中文全译.pdf | 85页排版版,正文9章完整翻译,50张图 |
| 语言模型中的全局工作空间-中文全译.md | 同内容的Markdown源文件 |
figures/ | 论文全部94张图表的高清截图 |
覆盖论文正文全部9个部分(引言、方法、五大功能证据、结构性质、对齐审计、助手视角、反事实反思训练、相关工作、讨论)。附录未译,公式与文献引用处理方式见卷首译者按。
@article{gurnee2026verbalizable,
author={Gurnee, Wes and Sofroniew, Nicholas and Pearce, Adam and Piotrowski, Mateusz and Kauvar, Isaac and Chen, Runjin and Soligo, Anna and Bogdan, Paul and Ong, Euan and Wang, Rowan and Thompson, Ben and Abrahams, David and Kantamneni, Subhash and Ameisen, Emmanuel and Batson, Joshua and Lindsey, Jack},
title={Verbalizable Representations Form a Global Workspace in Language Models},
journal={Transformer Circuits Thread},
year={2026},
url={https://transformer-circuits.pub/2026/workspace/index.html}
}
Anthropic「语言模型中的全局工作空间」论文中文全译 | Chinese translation of Anthropic's Global Workspace paper (2026)
根据分类、Topic 和编程语言匹配的相似项目。
Kimi K3 is an open-weight, 2.8T-parameter native multimodal agentic model with a 1M-token context window, designed for frontier coding, knowledge work, and reasoning tasks.

A structured investing guide for Chinese beginners covering US stocks, options, and cryptocurrency, with focus on foundational concepts and risk awareness.

A curated collection of Computer Science fundamentals (PDFs, notes, cheatsheets, interview question banks) for placement preparation, covering seven core subjects plus general resources.