# Anthropic研究：Claude自发形成可观测的内部推理空间"J-Space"

- 来源：elvis (@omarsar0)
- 发布时间：2026-07-07 06:47
- AIHOT 分数：67
- AIHOT 链接：https://aihot.virxact.com/items/cmr9u05ps001qihdbtv3w8jlf
- 原文链接：https://x.com/omarsar0/status/2074264122330612223

## AI 摘要

Anthropic新研究发现，Claude在训练中自行涌现出名为“J-Space”的内部工作空间，区别于链式推理或暂存区。该空间承载、整合并在模型不同部分传递信息，研究者可直接读取并操控其内容以引导模型行为。这是首次能精确定位模型内部推理发生的具体区域，使可解释性从“推断输出文本”转向“直接观察内部机制”。该发现可能推动更强推理能力，并强化模型对齐、审计与安全管控。Anthropic将其类比为人类意识中的“全局工作空间”。

## 正文

Must-read research by Anthropic.

Here is the simple explanation and why this is a big deal.

We suspect LLMs perform "internal reasoning". But little is known or do good methods exist to understand it.

Anthropic claims that J-Space （which differs from chain-of-thought or scratchpad）， emerged on its own through training and provides a window into how Claude "reasons" internally.

In other words， this shows that Claude has a sort of internal workspace where information gets held， combined， and passed between different parts of the model. They can read from it， and they can steer the model by changing it.

As it is the case with these reports， the consciousness angle will get all the attention. However， the bigger story is that for the first time you can point to a specific place inside the model where reasoning is staged， rather than guessing at it from the text that comes out.

This， of course， changes what interpretability can be. We spent years inferring what a model was doing from what it said. Now there's a mechanism to observe directly， and a direct lever to move. This could enable even more advanced levels of "reasoning" in LLMs and bridges gaps in frontier intelligence and world models.

If you can see where a model holds an idea， you can also verify it， audit it， and catch it working toward a goal you never gave it. You can implement better guardrails and predict dangerous/unwanted scenarios better.

### 引用推文

> Anthropic：New Anthropic research: A global workspace in language models. Of everything happening in your brain right now, only a tiny fraction is consciously accessible-t...