# Anthropic 发现 Claude 在训练中自行发展出隐藏的"思考空间"

- 来源：Chubby♨️ (@kimmonismus)
- 发布时间：2026-07-07 02:45
- AIHOT 分数：72
- AIHOT 链接：https://aihot.virxact.com/items/cmr9liiox00t5ihe8qswq6zqr
- 原文链接：https://x.com/kimmonismus/status/2074203017776423121

## AI 摘要

Anthropic 研究发现，Claude 在训练过程中自行发展出一个隐藏的“思考空间”（J-space）——一组内部模式，代表模型在“想”什么概念，即使它从未说出来。例如，Claude 可默念“蜘蛛”来回答“8 条腿”，若将该内部模式替换为“蚂蚁”，回答变为“6 条腿”。这与链式思维文本不同，属于无声的内部活动。Anthropic 借用神经科学的全局工作空间理论类比：想法进入特权工作空间并广播至整个大脑时成为意识；他们用新可解释性技术在 Claude 中发现了类似结构 J-space。

## 正文

Anthropic says Claude developed a hidden “thinking space” by itself during training.

It is called the J-space: a small set of internal patterns that show what concepts Claude has “on its mind,” even when it never says them.

Example: Claude can silently think “spider” to answer “8 legs.” If researchers replace that internal pattern with “ant,” Claude answers “6.”

So this is not just chain-of-thought text. It is silent internal activity.

### 引用推文

> Anthropic：In neuroscience, global workspace theory holds that thoughts become consciously accessible when they enter a privileged workspace that’s broadcast across the br...