Anthropic Explores Global Workspace in Language Models

AlexTensor · x · 2026-07-12

Anthropic has released new research focusing on the "global workspace" in language models.

The core idea is that in the human brain, only a small fraction of information enters consciousness to be described and reasoned through language; Anthropic suggests that Claude exhibits a similar hierarchical structure internally.

The poster sharing the research jokingly referred to this as "Anthropical illusions," suggesting that Anthropic might be repeatedly pressuring the model to find desired conclusions, such as expressions related to "consciousness."

Related event: Anthropic Reveals Claude's Hidden Reasoning Space: J-space(16 posts)→

Original post →

More from Research

Research channel →