# Anthropic 论文：LLM 中的全局工作空间机制

- 来源：elvis (@omarsar0)
- 发布时间：2026-07-21 00:01
- AIHOT 分数：37
- AIHOT 链接：https://aihot.virxact.com/items/cmrtfjsv02ui3bitlp7zze7tk
- 原文链接：https://x.com/omarsar0/status/2079235153210355754

## AI 摘要

Anthropic 在 arXiv 发表论文，提出大语言模型中的“全局工作空间”理论。该研究从机制角度解释了链式推理何时承担关键负载、何时仅为事后叙述：模型能用语言表达的表征如同一个带宽受限的全局工作空间，将少量特征广播至网络其余部分并引导后续行为。

## 正文

// Global Workspace in LLMs //

arXiv paper for the popular J-space work from Anthropic.

（bookmark it）

The short recap：

If you build on chain-of-thought or steering vectors， this work provides a mechanistic account of when verbalized reasoning is load-bearing and when it is narration after the fact.

The representations a model can put into words behave like a shared global workspace， a bandwidth-limited channel that broadcasts a small set of features to the rest of the network and steers what it does next.

Paper： https://arxiv.org/abs/2607.15495

Learn to build effective AI agents in our academy： https://academy.dair.ai/