Jack Lindsey(@Jack_W_Lindsey):LLMs represent information using high-dimensional neural activity. A small bit of this activity appears to be privileged, available to the model to be described, modulated, and reasoned with. I expect that understanding this "workspace" is key to making sense of LLM cognition.

Jack Lindsey

@Jack_W_Lindsey

Neuroscience of AI brains @AnthropicAI. Previously neuroscience of real brains @cu_neurotheory.

参加 January 2019

165 フォロー中 19.8K ファン

Jack Lindsey@Jack_W_Lindsey

2026.07.06 19:36

LLMs represent information using high-dimensional neural activity. A small bit of this activity appears to be privileged, available to the model to be described, modulated, and reasoned with. I expect that understanding this "workspace" is key to making sense of LLM cognition.

Anthropic@AnthropicAI

2026.07.06 17:34

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.