Verbalizable Representations Form a Global Workspace in Language Models

Key differences warrant caution in drawing parallels

“We close by stressing that, although the machine approximates the functional architecture of conscious processing, there are still key differences – in its anatomy and its sense of self, and in its lack of a body and of an enduring episodic memory – which warrant caution in drawing parallels with the human mind.”

approximates conscious processing architecture but warrants caution

“We close by stressing that, although the machine approximates the functional architecture of conscious processing, there are still key differences – in its anatomy and its sense of self, and in its lack of a body and of an enduring episodic memory – which warrant caution in drawing parallels with the human mind.”

Evidence LLMs are developing potential inner lives

“We have seen that the new paper provides evidence that LLMs are developing cognitive landscapes in which an inner life may play out, that these have a depth and richness extending beyond what a naive picture might take to be required for next-token prediction, and that there is a meaningful functional similarity with consciousness-linked features in humans.”

Claude's processing does not produce consciousness

“Just as flight is possible with flapping wings or with jet engines, human brains and language models can figure out how to say plausible things either with consciousness (brains) or without it (language models). But the information processing unfolding inside Claude is no more likely to result in consciousness than a simulation of a weather system is likely to generate a real hurricane.”

doubts J-space is an access consciousness mechanism

“overall: the J-space is a powerful tool for interpretability, but its status as a key causal mechanism and as a mechanism of access consciousness remains to be demonstrated.”