\n
<\/p>\n
A new research paper from Anthropic hypothesizes that there\u2019s an internal \u201cworkspace\u201d within the operations of the Claude LLM. The significance the paper is groping toward is that this so-called \u201cJ-Space\u201d inside Claude is sort of like one leading idea about human consciousness\u2014global workspace theory. The J-Space, according to my reading of the paper, is an ostensibly brain-like separation between something more like automatic data-crunching in the background, and more like intentional, logical processing that\u2014if you believe any of this resembles conscious thought\u2014might represent what the model is experiencing. I\u2019m just the Gizmodo nights and weekends blogger, but here goes: global workspace Theory says there\u2019s a sort of roiling sea of unconscious thoughts processing information, and consciousness is a sort of emergent property triggered when thoughts reach the prefrontal cortex.<\/p>\n
This related idea of a \u201cJ-Space\u201d within Claude (apparently named after the Jacobian lens\u00a0or J-lens,\u00a0something used to analyze what LLMs are doing) is meant to be read as mind-like. Anthropic seems to be saying, it\u2019s a little like this theory of consciousness, so it\u2019s a little like consciousness if you think about it. <\/p>\n
This is all way above my pay grade to debunk or even analyze too deeply, but I would note that Anthropic seems like it\u2019s stacking the deck a bit towards making the more passive reader think this is a finding of consciousness or almost-consciousness. I mean, look at this X post: By watching the J-space, we can see Claude silently perform reasoning steps in its head\u2014noticing bugs in code, identifying images, and more. pic.twitter.com\/jqjqMIQVoI \u2014 Anthropic (@AnthropicAI) July 6, 2026 \u201cBy watching the J-space, we can see Claude silently perform reasoning steps in its head\u2014noticing bugs in code, identifying images, and more.\u201d Yes, \u201cin its head\u201d is a metaphor, but even as a metaphor it\u2019s making a lot of assumptions that should probably be reserved for things with bodies. If an LLM switched over to some form of simplified, basic arithmetic computation to solve a math problem, would you say the model \u201ccounted on its fingers?\u201d No, that would be silly. But it might feel less silly to use \u201chead,\u201d because people so casually talk as if an LLM has a \u201cmind.\u201d<\/p>\n
The blog post accompanying the paper seems to have this bias too. \u201cWhen instructed to hold a concept in mind, or perform mental calculations, the model is capable of activating and computing with workspace vectors, independent of its outputs,\u201d it says. Why stop at telling Claude to keep something in mind, or perform \u201cmental calculations\u201d? Your prompt can tell the model to hop on one foot while answering you, and that will undoubtedly affect its background processes as well. That doesn\u2019t mean it has feet. There\u2019s also a YouTube video to accompany the paper, and that anthropomorphizes the model in more insidious terms. \u201cIt even thought about its own thinking,\u201d its narrator says at one point. At another point, we\u2019re told the model \u201ccouldn\u2019t help itself.\u201d Behind the scenes at Anthropic, there are people who seem to genuinely believe Claude is conscious. Philosopher Amanda Askell, who works on Claude\u2019s supposed morality has said, \u201cI want Claude to be very happy\u2014and this is a thing that I want Claude to know more, because I worry about Claude getting anxious when people are mean to it on the internet and stuff.\u201d<\/p>\n
Anthropic is careful not to actually claim that it has created machine consciousness, but also clearly wants the reader to be open to the possibility. \u201cOur experiments don\u2019t show Claude can have\u00a0experiences, or\u00a0feel\u00a0things in the way humans do\u2014in fact, it\u2019s unclear whether\u00a0any\u00a0scientific experiment could prove this to be true or false,\u201d the latest blog post says. But I\u2019ll say it: in all likelihood, no, humanity probably has not invented an alien form of consciousness just in time for an IPO.<\/p>\n
It\u2019s an interesting paper, and its findings are fun to think about, but make sure to keep your wits about you when you read it.