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)→
More from Research
- Token Collapse: Study Finds Graph Soft Prompting Tokens in LLMs Fail to Encode Structure — Sapienza · 2026-10-27
- The 'sweet lesson' is real: two kinds of ML problems need opposite strategies — mike64_t · 2026-10-27
- PixGR: Pixel-space generative decoding for fast feed-forward 3D reconstruction — kwangmoo_yi · 2026-10-27
- UniAction: unified action conditioning lets one world model handle mixed action types — ZeYanjie · 2026-10-27
- Infini-AI Lab open-sources Hermit, a framework for agent harness evolution and continual learning — BeidiChen · 2026-10-27
- Meta FAIR's Self-Direction turns agent failures into reusable LoRA skills, +13.8pp on Terminal-Bench — karen_ullrich · 2026-10-27