Comment by chrisjj
3 hours ago
> There is also reasoning happening internally - e.g. look at the steps in the J-Space paper from earlier in the year
> That's the "reasoning process" that leads to the words,
That's not reasoning. Its just the words at intermediate LLM layers.
The paper's very title is clickbait. Its "global workspace" reasoning is delusional fantasy.
PS The paper: "Verbalizable Representations Form a Global Workspace in Language Models" https://transformer-circuits.pub/2026/workspace/index.html
Promotion here: "https://www.anthropic.com/research/global-workspace" https://www.anthropic.com/research/global-workspace
"these findings have changed our understanding of how Claude’s mind works"
The key phrase here is "our understanding". Pure self-delusion.