Expired50% confidenceFactExact time
Anthropic researchers discovered a global workspace structure similar to that of the human brain inside the Claude large model using mechanistic interpretability methods.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
7/9/2026
First Seen
This claim has expired. It is kept for the record and no longer describes the current state.
Valid until: 10/7/2026(expired)
Sources
AMD Ryzen AI Halo Dev Kit: A $4,000 Local LLM Powerhouse Taking on Apple and NVIDIA
bilibiliSynthMindX7/7/2026
Related Claims
UnverifiedAnthropic在Claude模型中发现了一个高度类似神经科学'全局工作空间理论'的结构，且该结构并非人为设计而是训练中自行涌现82% similarUnverified消融实验借鉴自神经科学中通过移除脑区研究功能定位的方法，通过系统性移除或替换模型单个组件来量化每个组件的边际贡献70% similarUnverified委派机制的设计思路类似于卡尼曼提出的人类大脑双进程理论（System 1和System 2）70% similarUnverified神经科学家Stanislas Dehaene与Jean-Pierre Changeux将全局工作空间理论发展为神经全局工作空间理论（NGWT）70% similarUnverified机制可解释性领域奠基人之一是Anthropic研究者Chris Olah，其早期在神经网络特征可视化方面的工作奠定了方法论基础69% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/366307API
curl https://kongchang.com/api/v1/knowledge/claims/366307MCP
get_claim(id=366307)