⚡ 3 h early
global workspace theory language models paper
Verbalizable Representations Form a Global Workspace in Language Models
4 experts across 3 network communities independently surfaced this.
4 experts
3 communities
1 sources clustered
“here is the Anthropic blog: transformer-circuits.pub/2026/workspa... I don't really like the framing of whether LLMs are conscious or not. It's completely unnecessary. As is the hand-waiving about whether LLMs have something equivalent to the (functional) g…”
“Anthropic uses the word “conscious” 206 times in their latest research Specifically, they’re showing that LLMs implement one of the leading explanations of consciousness in humans (see pic) transformer-circuits.pub/2026/workspa...”
7 experts discussed this · 53 posts
Matthew Kirschenbaum: At an online event this morning I defended a claim which others found troublesome: That there are legitimately experienced aspects of computational phenomena, such as large language models, which—f…
Matthew Kirschenbaum: The point is not that what computers do isn’t grounded in material conditions, but rather that there comes a point at which the layers of dissociation between those conditions and actual outcomes b…
Matthew Kirschenbaum: Example: transformer-circuits.pub/2026/workspa...
Open the full discussion →