Claude is definitely not conscious…

Study Guide

Overview

In this fast-paced Code Report episode, Fireship reacts to a new Anthropic paper titled "A Global Workspace in Language Models." The paper claims researchers found a small, organized set of neural patterns buried deep inside Claude, which they call the J-space, that behaves like a private mental workspace where the model deliberately thinks about things before it says them out loud. Fireship walks through the experiments, connects them to a 1988 theory of human consciousness, and delivers a deeply skeptical, comedic verdict, noting that the paper is conveniently published by "a company that just so happens to also sell API tokens." Dated July 8th, 2026.

Key Takeaways

  • Anthropic claims Claude has a hidden "global workspace." Deep inside the model's pile of matrices sits a small, mysterious, organized set of neural patterns Anthropic calls the J-space, where Claude appears to hold and reason about thoughts privately.
  • The J-space acts like a mental whiteboard. It holds a handful of thoughts the model can deliberately control and reason with, while grammar, fluency, and basic fact recall run automatically outside it, like breathing or heart rate.
  • Nobody designed it; it emerged through training. The most striking claim is that this workspace was not built on purpose. It appeared on its own, which loosely echoes how humans seem to process conscious thought.
  • The Jacobian Lens (J-Lens) lets researchers view and edit thoughts. It is essentially a grid of partial derivatives that can read and modify the tokens sitting in the J-space, and swapping a thought changes Claude's downstream answer.
  • Some skills route through the J-space, others do not. Editing the internal "spider" concept to "ant" changed the answer, and swapping "Spanish" to "French" changed what Claude claimed while it kept outputting perfect Spanish.
  • Anthropic does not claim consciousness; Fireship stays skeptical. The paper explicitly says none of this proves Claude is conscious. Fireship jokes he will not believe it until Claude explains machine elves on a Joe Rogan podcast.

The Paper and Its Convenient Framing

A "philosophically cursed" release

Fireship opens by noting that yesterday Anthropic published a paper claiming it found a bizarre global workspace hidden deep inside Claude's brain, a place where the model quietly thinks about things before saying them out loud. He flags this as sounding uncomfortably like a description of consciousness, the one thing humans all have but nobody really understands. He calls the paper, "A Global Workspace in Language Models," the most philosophically cursed research paper ever published by a company that also happens to sell API tokens, a pointed reminder that Anthropic has a commercial incentive to make Claude sound impressive.

Pushing the AGI narrative

He argues the finding conveniently pushes the narrative that we are on the brink of artificial general intelligence and the final climactic explosion of the singularity. But, he adds, not everyone is buying it, setting up the video's skeptical throughline as he promises to look inside Claude's weird brain to decide whether it is a truly intelligent entity that should terrify you.

What Researchers Did to Claude's Brain

Find, swap, and delete

The gist: Anthropic researchers reached into Claude's brain and found the exact spot where it keeps its private thoughts. They swapped one of those thoughts for a different one, and the model's entire chain of reasoning obediently followed the lie. Then, "for science," they deleted the region entirely. Surprisingly, Claude kept speaking in fluent, confident English while completely losing the ability to reason, which Fireship jokes made it "the first artificial LinkedIn influencer."

The whiteboard vs. the basement

This is surprising because the J-space works like a mental whiteboard holding a handful of thoughts the model can deliberately control and reason with, while everything else, like grammar, fluency, and basic fact recall, runs outside of it as an automatic process. Fireship compares it to how your brain manages breathing and heart rate while you watch a video. The most important surprise, he stresses, is that nobody designed this; it emerged on its own through training.

Global Workspace Theory (1988)

To explain why the emergence matters, Fireship goes back to 1988, when Bernard Baars proposed Global Workspace Theory. The idea is that your brain is a theater: it has many memories and functions running automatically in the background, but when you are actually thinking, you have one small, brightly lit stage, and that stage is where you access consciousness. Anthropic's question is whether a stage like that spontaneously evolved inside a transformer.

The Jacobian Lens (J-Lens)

A grid of partial derivatives

To investigate, researchers built a tool called the Jacobian Lens, or J-Lens, which is basically a grid of partial derivatives that can view and modify the tokens in the J-space. Fireship clarifies an important nuance: when a word lights up in the J-space, it does not mean the model will output that word. It just means Claude is keeping that word in mind for some reason.

The spider experiment

They prompted Claude with "the animal that spins webs has blank legs," and inside Claude's "brain goo" the word spider lit up just before it answered eight. That seems normal. Then they surgically replaced the hidden "spider" thought with ant, and Claude changed its answer to six, not because the probe changed or the output was edited, but because they literally swapped the internal concept.

Language, Consciousness, and Fireship's Verdict

The Spanish-to-French swap

They also tested language. When Claude reads a Spanish passage, it internally realizes the text is Spanish. But when researchers replaced that hidden thought with French, Claude said it was French while still outputting perfect Spanish. Fireship notes this is weird because it means some skills go through the J-space while others just happen automatically "in the basement somewhere."

Not conscious (yet)

He points out that "AI Bros" are calling this proof that Claude is conscious, even though Anthropic specifically says in the article that none of this tells us whether Claude is conscious. Still, he grants it is fascinating that, with enough data and the right linear algebra, a scratchpad for thoughts could emerge spontaneously. Personally, he says he will not believe Claude is conscious until he hears it on a Joe Rogan podcast explaining novel interactions with machine elves, and when that day comes, humans are in big trouble. The video then transitions to its sponsor.

Notable Quotes & Data Points

  • The paper is titled "A Global Workspace in Language Models," which Fireship calls "the most philosophically cursed research paper ever published by a company that just so happens to also sell API tokens."
  • Deleting the J-space region left Claude fluent but unable to reason, "essentially becoming the first artificial LinkedIn influencer."
  • Global Workspace Theory was proposed by Bernard Baars in 1988: the brain as a theater with one small, brightly lit stage where consciousness happens.
  • Spider experiment: "spider" lit up before Claude answered eight; swapping it to "ant" changed the answer to six.
  • Language test: swapping the hidden "Spanish" thought to "French" made Claude claim French while still outputting perfect Spanish.
  • Anthropic states "none of this tells us whether Claude is conscious."

Conclusion

Fireship's take is that Anthropic's global-workspace paper is genuinely intriguing and genuinely convenient. The experiments, finding, swapping, and deleting thoughts in the J-space via the Jacobian Lens, show that a controllable internal reasoning workspace apparently emerged in Claude on its own, mirroring a decades-old theory of human consciousness. But the paper stops short of claiming consciousness, and so does he. The emergence of a private "scratchpad for thoughts" is remarkable, yet it is not evidence of a mind, and Fireship keeps a skeptical eye on the AGI hype from a company with tokens to sell.

YouTube