I call bullsh*t. There is no verbalisation of any reasoning process. Verbalisation, e.g. putting reasoning etc. into words requires some reasoning to exist. These LLMs have nothing but the words. That's why they are language models not e.g. reason models.
Yes, their reasoning is different from ours, and both considerably weaker in lots of ways, and stronger in other ways.
Playing with a coding agent now, they do think through problems and make sensible decisions. It's a mess to read, of correcting itself and second guessing, and verbiage. But... It works decently well these days.
There is also reasoning happening internally - e.g. look at the steps in the J-Space paper from earlier in the year (in quite a simple model relatively speaking). That's the "reasoning process" that leads to the words, and much like if I write out my thoughts, the words help the LLM reason better.
> 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.
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.