Excellent investigation of the mechanics of language models. 🫢A notable blindspot, however: several teams have actually been **directly** c…

Excellent investigation of the mechanics of language models. 🫢A notable blindspot, however: several teams have actually been directly comparing the working of LLMs to those of the human brain 🧠 for a while. Here is a thread to highlight some of our (and our competitors'!) findings 👇 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.

Source: Yann LeCun (X) | 2026-07-07