#consiousness

@alexmu@social.vivaldi.net @davidho@mastodon.world My statement was not precise enough. #consiousness has no good accepted definition I was aiming at how #llm #ai can lead to more Insight how reasoning (cognitive) processes in the brain work. Reasoning llm models work with a number of intermediate ingredients, and so does human reasoning. What is comparable and what is not seems like a good philosophical question. see for the steps of llm reasoning how I mean it this video model pre-mtraining, post training, reasoning prompting, reinforcement learning https://youtu.be/xCRvOUykOX0?is=sDBDn5q5BTMXxLwl

1/2 A global emergent workspace in language models (J-space) https://www.anthropic.com/research/global-workspace

J-space wasn’t designed or programmed. It emerged on its own during training process. J-space has a number of unique properties:

• Claude can report on these representations. If you ask Claude what it's thinking about, it will tell you what’s in the J-space. Non-J-space representations are less reportable.

• It can also modulate them on request. If you ask Claude to think about something, or solve a problem silently in its head, it will light up the appropriate patterns in its J-space. By contrast, it has trouble modulating patterns not in the J-space.

• Claude uses its J-space for internal reasoning. If you ask Claude to solve a problem that requires multiple steps, the intermediate steps will light up in its J-space, even when it doesn’t say them out loud. These J-space patterns causally mediate its performance in such tasks, despite being smaller in magnitude than other representations.

• Representations in the J-space can be used flexibly for many tasks—for example, once “France” has lit up in Claude’s J-space, the model can recall its capital, or its national currency, or the continent it belongs to.

• However, despite its important role, the J-space is not involved in most of what a language model does—speaking fluently, recalling simple facts, using correct grammar, etc. In experiments where we prevented Claude from using its J-space, it still interacted normally, but lost its higher-order cognitive functions.

Full Paper: https://transformer-circuits.pub/2026/workspace/index.html

External commentary https://www-cdn.anthropic.com/files/4zrzovbb/website/cc4be2488d65e54a6ed06492f8968398ddc18ebe.pdf

#consiousness #cogneuro #LLM #AI #cogneuro #cognitive #cognitiveNeuroscience