动态

Anthropic研究发现语言模型内部存在类似人类意识的全局工作空间

Anthropic研究发现语言模型内部存在类似人类意识的全局工作空间
Lance Martin
RT @AnthropicAI: New Anthropic research: A global workspace in language models.

Of everything happening in your brain right now, only a tiny fraction is consciously accessible—thoughts you can describe, hold in mind, and reason with.

We found a strikingly similar divide inside Claude. https://t.co/aLUPBifxth
动态Lance Martin2026-07-06原文

相关内容