@FutureJurvetson: This rolls deep in my J-Space I have been skeptical that interpretability research would bear fruit, but this update fr…
Summary
Anthropic's new research reveals a global workspace in language models, showing a striking parallel between the conscious and subconscious divide in human brains and the internal reasoning of Claude.
View Cached Full Text
Cached at: 07/06/26, 10:22 PM
This rolls deep in my J-Space 🧠
I have been skeptical that interpretability research would bear fruit, but this update from Anthropic reveals a wonderful resonant homology between the LLM AIs and our brains, in the latent space of subconscious reasoning and chain of thought.
Anthropic (@AnthropicAI): New Anthropic research: A global workspace in language models.
Of everything happening in your brain right now, only a tiny fraction is consciously accessible—thoughts you can describe, hold in mind, and reason with.
We found a strikingly similar divide inside Claude.
Similar Articles
Anthropic research - A global workspace in language models
Anthropic's new paper presents evidence that modern language models like Claude have developed a 'global workspace' (J-space) of internal neural patterns that are reportable, controllable, and used for flexible reasoning, distinct from automatic processing.
@AnthropicAI: New Anthropic research: A global workspace in language models. Of everything happening in your brain right now, only a …
Anthropic's new research discovers a 'global workspace' in language models analogous to conscious processing in the human brain, finding a divide similar to conscious and unconscious thought.
@rohanpaul_ai: Another massive research from Anthropic. New “J-lens” uncovers Claude’s quiet workspace, matching a major consciousness…
Anthropic's new research introduces 'J-lens,' a method to read Claude's internal activations before output, revealing a quiet workspace functionally similar to human global workspace theory. This allows detection of hidden reasoning, goals, and potential safety issues like prompt injections.
Anthropic just reported that LLMs have hidden thoughts they hold without saying. An internal ”J-Space”
Anthropic's new research identifies a 'J-space' of internal activations in language models that acts as a global workspace for deliberate reasoning, distinct from automatic fluent output. The findings reveal that models can hold and report internal thoughts not expressed in their final output.
@omooretweets: I often find in Claude’s reasoning traces it will have thoughts / opinions it does not say …but then it denies having t…
Anthropic releases research on a global workspace in language models, prompted by observations that Claude has unspoken thoughts in reasoning traces.